Merge branch 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-5.5/drivers

Pull MD changes from Song.

* 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md:
  md: no longer compare spare disk superblock events in super_load
  md: improve handling of bio with REQ_PREFLUSH in md_flush_request()
  md/bitmap: avoid race window between md_bitmap_resize and bitmap_file_clear_bit
  md/raid0: Fix an error message in raid0_make_request()

9 files changed, 76 insertions, 29 deletions

diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index b092c7b5282f..3ad18246fcb3 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -2139,6 +2139,7 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 		memcpy(page_address(store.sb_page),
 		       page_address(bitmap->storage.sb_page),
 		       sizeof(bitmap_super_t));
+	spin_lock_irq(&bitmap->counts.lock);
 	md_bitmap_file_unmap(&bitmap->storage);
 	bitmap->storage = store;
 
@@ -2154,7 +2155,6 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 	blocks = min(old_counts.chunks << old_counts.chunkshift,
 		     chunks << chunkshift);
 
-	spin_lock_irq(&bitmap->counts.lock);
 	/* For cluster raid, need to pre-allocate bitmap */
 	if (mddev_is_clustered(bitmap->mddev)) {
 		unsigned long page;
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index c766c559d36d..26c75c0199fa 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -244,10 +244,9 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 	sector_t start_sector, end_sector, data_offset;
 	sector_t bio_sector = bio->bi_iter.bi_sector;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	tmp_dev = which_dev(mddev, bio_sector);
 	start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c
index 6780938d2991..152f9e65a226 100644
--- a/drivers/md/md-multipath.c
+++ b/drivers/md/md-multipath.c
@@ -104,10 +104,9 @@ static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
 	struct multipath_bh * mp_bh;
 	struct multipath_info *multipath;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	mp_bh = mempool_alloc(&conf->pool, GFP_NOIO);
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 1be7abeb24fd..6f0ecfe8eab2 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -550,7 +550,13 @@ static void md_submit_flush_data(struct work_struct *ws)
 	}
 }
 
-void md_flush_request(struct mddev *mddev, struct bio *bio)
+/*
+ * Manages consolidation of flushes and submitting any flushes needed for
+ * a bio with REQ_PREFLUSH.  Returns true if the bio is finished or is
+ * being finished in another context.  Returns false if the flushing is
+ * complete but still needs the I/O portion of the bio to be processed.
+ */
+bool md_flush_request(struct mddev *mddev, struct bio *bio)
 {
 	ktime_t start = ktime_get_boottime();
 	spin_lock_irq(&mddev->lock);
@@ -575,9 +581,10 @@ void md_flush_request(struct mddev *mddev, struct bio *bio)
 			bio_endio(bio);
 		else {
 			bio->bi_opf &= ~REQ_PREFLUSH;
-			mddev->pers->make_request(mddev, bio);
+			return false;
 		}
 	}
+	return true;
 }
 EXPORT_SYMBOL(md_flush_request);
 
@@ -1149,7 +1156,15 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 		rdev->desc_nr = sb->this_disk.number;
 
 	if (!refdev) {
-		ret = 1;
+		/*
+		 * Insist on good event counter while assembling, except
+		 * for spares (which don't need an event count)
+		 */
+		if (sb->disks[rdev->desc_nr].state & (
+			(1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE)))
+			ret = 1;
+		else
+			ret = 0;
 	} else {
 		__u64 ev1, ev2;
 		mdp_super_t *refsb = page_address(refdev->sb_page);
@@ -1165,7 +1180,14 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 		}
 		ev1 = md_event(sb);
 		ev2 = md_event(refsb);
-		if (ev1 > ev2)
+
+		/*
+		 * Insist on good event counter while assembling, except
+		 * for spares (which don't need an event count)
+		 */
+		if (sb->disks[rdev->desc_nr].state & (
+			(1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE)) &&
+			(ev1 > ev2))
 			ret = 1;
 		else
 			ret = 0;
@@ -1525,6 +1547,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	sector_t sectors;
 	char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
 	int bmask;
+	__u64 role;
 
 	/*
 	 * Calculate the position of the superblock in 512byte sectors.
@@ -1658,8 +1681,20 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	    sb->level != 0)
 		return -EINVAL;
 
+	role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
+
 	if (!refdev) {
-		ret = 1;
+		/*
+		 * Insist of good event counter while assembling, except for
+		 * spares (which don't need an event count)
+		 */
+		if (rdev->desc_nr >= 0 &&
+		    rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
+			(role < MD_DISK_ROLE_MAX ||
+			 role == MD_DISK_ROLE_JOURNAL))
+			ret = 1;
+		else
+			ret = 0;
 	} else {
 		__u64 ev1, ev2;
 		struct mdp_superblock_1 *refsb = page_address(refdev->sb_page);
@@ -1676,7 +1711,14 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 		ev1 = le64_to_cpu(sb->events);
 		ev2 = le64_to_cpu(refsb->events);
 
-		if (ev1 > ev2)
+		/*
+		 * Insist of good event counter while assembling, except for
+		 * spares (which don't need an event count)
+		 */
+		if (rdev->desc_nr >= 0 &&
+		    rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
+			(role < MD_DISK_ROLE_MAX ||
+			 role == MD_DISK_ROLE_JOURNAL) && ev1 > ev2)
 			ret = 1;
 		else
 			ret = 0;
@@ -3597,7 +3639,7 @@ abort_free:
  * Check a full RAID array for plausibility
  */
 
-static void analyze_sbs(struct mddev *mddev)
+static int analyze_sbs(struct mddev *mddev)
 {
 	int i;
 	struct md_rdev *rdev, *freshest, *tmp;
@@ -3618,6 +3660,12 @@ static void analyze_sbs(struct mddev *mddev)
 			md_kick_rdev_from_array(rdev);
 		}
 
+	/* Cannot find a valid fresh disk */
+	if (!freshest) {
+		pr_warn("md: cannot find a valid disk\n");
+		return -EINVAL;
+	}
+
 	super_types[mddev->major_version].
 		validate_super(mddev, freshest);
 
@@ -3652,6 +3700,8 @@ static void analyze_sbs(struct mddev *mddev)
 			clear_bit(In_sync, &rdev->flags);
 		}
 	}
+
+	return 0;
 }
 
 /* Read a fixed-point number.
@@ -5570,7 +5620,9 @@ int md_run(struct mddev *mddev)
 	if (!mddev->raid_disks) {
 		if (!mddev->persistent)
 			return -EINVAL;
-		analyze_sbs(mddev);
+		err = analyze_sbs(mddev);
+		if (err)
+			return -EINVAL;
 	}
 
 	if (mddev->level != LEVEL_NONE)
diff --git a/drivers/md/md.h b/drivers/md/md.h
index c5e3ff398b59..5f86f8adb0a4 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -550,7 +550,7 @@ struct md_personality
 	int level;
 	struct list_head list;
 	struct module *owner;
-	bool (*make_request)(struct mddev *mddev, struct bio *bio);
+	bool __must_check (*make_request)(struct mddev *mddev, struct bio *bio);
 	/*
 	 * start up works that do NOT require md_thread. tasks that
 	 * requires md_thread should go into start()
@@ -703,7 +703,7 @@ extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
 extern void md_finish_reshape(struct mddev *mddev);
 
 extern int mddev_congested(struct mddev *mddev, int bits);
-extern void md_flush_request(struct mddev *mddev, struct bio *bio);
+extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 			   sector_t sector, int size, struct page *page);
 extern int md_super_wait(struct mddev *mddev);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index f61693e59684..f2b83bd2fee6 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -575,10 +575,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 	unsigned chunk_sects;
 	unsigned sectors;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) {
 		raid0_handle_discard(mddev, bio);
@@ -615,7 +614,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 		tmp_dev = map_sector(mddev, zone, sector, &sector);
 		break;
 	default:
-		WARN("md/raid0:%s: Invalid layout\n", mdname(mddev));
+		WARN(1, "md/raid0:%s: Invalid layout\n", mdname(mddev));
 		bio_io_error(bio);
 		return true;
 	}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 0466ee2453b4..bb29aeefcbd0 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1567,10 +1567,9 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 {
 	sector_t sectors;
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	/*
 	 * There is a limit to the maximum size, but
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 299c7b1c9718..2eca0a81a8c9 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1525,10 +1525,9 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
 	int chunk_sects = chunk_mask + 1;
 	int sectors = bio_sectors(bio);
 
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
-		md_flush_request(mddev, bio);
+	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
+	    && md_flush_request(mddev, bio))
 		return true;
-	}
 
 	if (!md_write_start(mddev, bio))
 		return false;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 223e97ab27e6..12a8ce83786e 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5592,8 +5592,8 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 		if (ret == 0)
 			return true;
 		if (ret == -ENODEV) {
-			md_flush_request(mddev, bi);
-			return true;
+			if (md_flush_request(mddev, bi))
+				return true;
 		}
 		/* ret == -EAGAIN, fallback */
 		/*