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 md_cond_error() that handles failfast
bio errors without stopped the array. This function checks whether the
array will become inoperable if a rdev fails, and if so, it skips
error handling to ensure the array remains in an operational state.

Callers of md_error() will be updated to use this new function in
subsequent commits to properly handle failfast scenarios.

Signed-off-by: Kenta Akagi <k@mgml.me>
---
 drivers/md/md.c | 33 +++++++++++++++++++++++++++++++++
 drivers/md/md.h |  1 +
 2 files changed, 34 insertions(+)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4ad9cb0ac98c..e33ab564f26b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8479,6 +8479,39 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev)
 }
 EXPORT_SYMBOL(md_error);
 
+/** md_cond_error() - conditionally md_error()
+ * @mddev: affected md device
+ * @rdev: member device to fail
+ * @bio: bio whose triggered device failure
+ *
+ * Check if the personality wants to fail this rdev for this bio,
+ * and if so, call _md_error().
+ * This function has no different behavior from md_error except
+ * for the raid1/10 with failfast enabled rdevs.
+ *
+ * Returns: %true if rdev already or become Faulty, %false if not.
+ */
+bool md_cond_error(struct mddev *mddev, struct md_rdev *rdev, struct bio *bio)
+{
+	if (WARN_ON_ONCE(!mddev->pers))
+		/* return true because we don't want caller to retry */
+		return true;
+
+	spin_lock(&mddev->device_lock);
+
+	if (mddev->pers->should_error &&
+	    !mddev->pers->should_error(mddev, rdev, bio)) {
+		spin_unlock(&mddev->device_lock);
+		return test_bit(Faulty, &rdev->flags);
+	}
+
+	_md_error(mddev, rdev);
+	spin_unlock(&mddev->device_lock);
+
+	return !WARN_ON_ONCE(!test_bit(Faulty, &rdev->flags));
+}
+EXPORT_SYMBOL(md_cond_error);
+
 /* seq_file implementation /proc/mdstat */
 
 static void status_unused(struct seq_file *seq)
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 01c8182431d1..38f9874538a6 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -916,6 +916,7 @@ extern void md_write_end(struct mddev *mddev);
 extern void md_done_sync(struct mddev *mddev, int blocks, int ok);
 void _md_error(struct mddev *mddev, struct md_rdev *rdev);
 extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
+extern bool md_cond_error(struct mddev *mddev, struct md_rdev *rdev, struct bio *bio);
 extern void md_finish_reshape(struct mddev *mddev);
 void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 			struct bio *bio, sector_t start, sector_t size);
-- 
2.50.1