[PATCH v5 05/16] md/raid1: implement pers->should_error()

[Kenta Akagi]

The failfast feature in RAID1 and RAID10 assumes that when md_error() is
called, the array remains functional because the last rdev neither fails
nor sets MD_BROKEN.

However, the current implementation can cause the array to lose
its last in-sync device or be marked as MD_BROKEN, which breaks the
assumption and can lead to array failure.

To address this issue, introduce a new handler, md_cond_error(), to
ensure that failfast I/O does not mark the array as broken.

md_cond_error() checks whether a device should be faulted based on
pers->should_error().  This commit implements should_error() callback
for raid1 personality, which returns true if faulting the specified rdev
would cause the mddev to become non-functional.

Signed-off-by: Kenta Akagi <k@xxxxxxx>
---
 drivers/md/raid1.c | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 202e510f73a4..69b7730f3875 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1732,6 +1732,40 @@ static void raid1_status(struct seq_file *seq, struct mddev *mddev)
 	seq_printf(seq, "]");
 }
 
+/**
+ * raid1_should_error() - Determine if this rdev should be failed
+ * @mddev: affected md device
+ * @rdev: member device to check
+ * @bio: the bio that caused the failure
+ *
+ * When failfast bios failure, rdev can fail, but the mddev must not fail.
+ * This function tells md_cond_error() not to fail rdev if bio is failfast
+ * and last rdev.
+ *
+ * Returns: %false if bio is failfast and rdev is the last in-sync device.
+ *	     Otherwise %true - should fail this rdev.
+ */
+static bool raid1_should_error(struct mddev *mddev, struct md_rdev *rdev, struct bio *bio)
+{
+	int i;
+	struct r1conf *conf = mddev->private;
+
+	if (!(bio->bi_opf & MD_FAILFAST) ||
+	    !test_bit(FailFast, &rdev->flags) ||
+	    test_bit(Faulty, &rdev->flags))
+		return true;
+
+	for (i = 0; i < conf->raid_disks; i++) {
+		struct md_rdev *rdev2 = conf->mirrors[i].rdev;
+
+		if (rdev2 && rdev2 != rdev &&
+		    test_bit(In_sync, &rdev2->flags) &&
+		    !test_bit(Faulty, &rdev2->flags))
+			return true;
+	}
+	return false;
+}
+
 /**
  * raid1_error() - RAID1 error handler.
  * @mddev: affected md device.
@@ -3486,6 +3520,7 @@ static struct md_personality raid1_personality =
 	.free		= raid1_free,
 	.status		= raid1_status,
 	.error_handler	= raid1_error,
+	.should_error	= raid1_should_error,
 	.hot_add_disk	= raid1_add_disk,
 	.hot_remove_disk= raid1_remove_disk,
 	.spare_active	= raid1_spare_active,
-- 
2.50.1