Merge branch 'md-next' of git://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-5.4/block

Pull MD fixes from Song.

* 'md-next' of git://git.kernel.org/pub/scm/linux/kernel/git/song/md:
  md/raid5: use bio_end_sector to calculate last_sector
  md/raid1: fail run raid1 array when active disk less than one
  md raid0/linear: Mark array as 'broken' and fail BIOs if a member is gone

6 files changed, 58 insertions, 6 deletions

diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 7354466ddc90..c766c559d36d 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -258,6 +258,11 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 		     bio_sector < start_sector))
 		goto out_of_bounds;
 
+	if (unlikely(is_mddev_broken(tmp_dev->rdev, "linear"))) {
+		bio_io_error(bio);
+		return true;
+	}
+
 	if (unlikely(bio_end_sector(bio) > end_sector)) {
 		/* This bio crosses a device boundary, so we have to split it */
 		struct bio *split = bio_split(bio, end_sector - bio_sector,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index b46bb143e3c5..73d5a1b04022 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -376,6 +376,11 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 	struct mddev *mddev = q->queuedata;
 	unsigned int sectors;
 
+	if (unlikely(test_bit(MD_BROKEN, &mddev->flags)) && (rw == WRITE)) {
+		bio_io_error(bio);
+		return BLK_QC_T_NONE;
+	}
+
 	blk_queue_split(q, &bio);
 
 	if (mddev == NULL || mddev->pers == NULL) {
@@ -4158,12 +4163,17 @@ __ATTR_PREALLOC(resync_start, S_IRUGO|S_IWUSR,
  * active-idle
  *     like active, but no writes have been seen for a while (100msec).
  *
+ * broken
+ *     RAID0/LINEAR-only: same as clean, but array is missing a member.
+ *     It's useful because RAID0/LINEAR mounted-arrays aren't stopped
+ *     when a member is gone, so this state will at least alert the
+ *     user that something is wrong.
  */
 enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active,
-		   write_pending, active_idle, bad_word};
+		   write_pending, active_idle, broken, bad_word};
 static char *array_states[] = {
 	"clear", "inactive", "suspended", "readonly", "read-auto", "clean", "active",
-	"write-pending", "active-idle", NULL };
+	"write-pending", "active-idle", "broken", NULL };
 
 static int match_word(const char *word, char **list)
 {
@@ -4179,7 +4189,7 @@ array_state_show(struct mddev *mddev, char *page)
 {
 	enum array_state st = inactive;
 
-	if (mddev->pers && !test_bit(MD_NOT_READY, &mddev->flags))
+	if (mddev->pers && !test_bit(MD_NOT_READY, &mddev->flags)) {
 		switch(mddev->ro) {
 		case 1:
 			st = readonly;
@@ -4199,7 +4209,10 @@ array_state_show(struct mddev *mddev, char *page)
 				st = active;
 			spin_unlock(&mddev->lock);
 		}
-	else {
+
+		if (test_bit(MD_BROKEN, &mddev->flags) && st == clean)
+			st = broken;
+	} else {
 		if (list_empty(&mddev->disks) &&
 		    mddev->raid_disks == 0 &&
 		    mddev->dev_sectors == 0)
@@ -4313,6 +4326,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 		break;
 	case write_pending:
 	case active_idle:
+	case broken:
 		/* these cannot be set */
 		break;
 	}
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 1edcd967eb8e..c5e3ff398b59 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -251,6 +251,9 @@ enum mddev_flags {
 	MD_NOT_READY,		/* do_md_run() is active, so 'array_state'
 				 * must not report that array is ready yet
 				 */
+	MD_BROKEN,              /* This is used in RAID-0/LINEAR only, to stop
+				 * I/O in case an array member is gone/failed.
+				 */
 };
 
 enum mddev_sb_flags {
@@ -739,6 +742,19 @@ extern void mddev_create_wb_pool(struct mddev *mddev, struct md_rdev *rdev,
 struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr);
 struct md_rdev *md_find_rdev_rcu(struct mddev *mddev, dev_t dev);
 
+static inline bool is_mddev_broken(struct md_rdev *rdev, const char *md_type)
+{
+	int flags = rdev->bdev->bd_disk->flags;
+
+	if (!(flags & GENHD_FL_UP)) {
+		if (!test_and_set_bit(MD_BROKEN, &rdev->mddev->flags))
+			pr_warn("md: %s: %s array has a missing/failed member\n",
+				mdname(rdev->mddev), md_type);
+		return true;
+	}
+	return false;
+}
+
 static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
 {
 	int faulty = test_bit(Faulty, &rdev->flags);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index bf5cf184a260..bc422eae2c95 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -586,6 +586,12 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 
 	zone = find_zone(mddev->private, &sector);
 	tmp_dev = map_sector(mddev, zone, sector, &sector);
+
+	if (unlikely(is_mddev_broken(tmp_dev, "raid0"))) {
+		bio_io_error(bio);
+		return true;
+	}
+
 	bio_set_dev(bio, tmp_dev->bdev);
 	bio->bi_iter.bi_sector = sector + zone->dev_start +
 		tmp_dev->data_offset;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 6ea4f2679b78..0466ee2453b4 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -3129,6 +3129,13 @@ static int raid1_run(struct mddev *mddev)
 		    !test_bit(In_sync, &conf->mirrors[i].rdev->flags) ||
 		    test_bit(Faulty, &conf->mirrors[i].rdev->flags))
 			mddev->degraded++;
+	/*
+	 * RAID1 needs at least one disk in active
+	 */
+	if (conf->raid_disks - mddev->degraded < 1) {
+		ret = -EINVAL;
+		goto abort;
+	}
 
 	if (conf->raid_disks - mddev->degraded == 1)
 		mddev->recovery_cp = MaxSector;
@@ -3162,8 +3169,12 @@ static int raid1_run(struct mddev *mddev)
 	ret = md_integrity_register(mddev);
 	if (ret) {
 		md_unregister_thread(&mddev->thread);
-		raid1_free(mddev, conf);
+		goto abort;
 	}
+	return 0;
+
+abort:
+	raid1_free(mddev, conf);
 	return ret;
 }
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 88e56ee98976..da6a86e28318 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5499,7 +5499,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 		return;
 
 	logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1);
-	last_sector = bi->bi_iter.bi_sector + (bi->bi_iter.bi_size>>9);
+	last_sector = bio_end_sector(bi);
 
 	bi->bi_next = NULL;