Merge branch 'md-next' of git://git.kernel.org/pub/scm/linux/kernel/g…

…it/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:
  raid5: use bio_end_sector in r5_next_bio
  raid5: remove STRIPE_OPS_REQ_PENDING
  md: add feature flag MD_FEATURE_RAID0_LAYOUT
  md/raid0: avoid RAID0 data corruption due to layout confusion.
  raid5: don't set STRIPE_HANDLE to stripe which is in batch list
  raid5: don't increment read_errors on EILSEQ return

drivers/md/md.c

@@ -1237,6 +1237,8 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
 			mddev->new_layout = mddev->layout;
 			mddev->new_chunk_sectors = mddev->chunk_sectors;
 		}
+		if (mddev->level == 0)
+			mddev->layout = -1;
 
 		if (sb->state & (1<<MD_SB_CLEAN))
 			mddev->recovery_cp = MaxSector;
@@ -1652,6 +1654,10 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 		rdev->ppl.sector = rdev->sb_start + rdev->ppl.offset;
 	}
 
+	if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT) &&
+	    sb->level != 0)
+		return -EINVAL;
+
 	if (!refdev) {
 		ret = 1;
 	} else {
@@ -1762,6 +1768,10 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 			mddev->new_chunk_sectors = mddev->chunk_sectors;
 		}
 
+		if (mddev->level == 0 &&
+		    !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RAID0_LAYOUT))
+			mddev->layout = -1;
+
 		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)
 			set_bit(MD_HAS_JOURNAL, &mddev->flags);
 
@@ -6898,6 +6908,9 @@ static int set_array_info(struct mddev *mddev, mdu_array_info_t *info)
 	mddev->external	     = 0;
 
 	mddev->layout        = info->layout;
+	if (mddev->level == 0)
+		/* Cannot trust RAID0 layout info here */
+		mddev->layout = -1;
 	mddev->chunk_sectors = info->chunk_size >> 9;
 
 	if (mddev->persistent) {

drivers/md/raid0.c

@@ -19,6 +19,9 @@
 #include "raid0.h"
 #include "raid5.h"
 
+static int default_layout = 0;
+module_param(default_layout, int, 0644);
+
 #define UNSUPPORTED_MDDEV_FLAGS		\
 	((1L << MD_HAS_JOURNAL) |	\
 	 (1L << MD_JOURNAL_CLEAN) |	\
@@ -139,6 +142,22 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	}
 	pr_debug("md/raid0:%s: FINAL %d zones\n",
 		 mdname(mddev), conf->nr_strip_zones);
+
+	if (conf->nr_strip_zones == 1) {
+		conf->layout = RAID0_ORIG_LAYOUT;
+	} else if (mddev->layout == RAID0_ORIG_LAYOUT ||
+		   mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+		conf->layout = mddev->layout;
+	} else if (default_layout == RAID0_ORIG_LAYOUT ||
+		   default_layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+		conf->layout = default_layout;
+	} else {
+		pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n",
+		       mdname(mddev));
+		pr_err("md/raid0: please set raid.default_layout to 1 or 2\n");
+		err = -ENOTSUPP;
+		goto abort;
+	}
 	/*
 	 * now since we have the hard sector sizes, we can make sure
 	 * chunk size is a multiple of that sector size
@@ -547,10 +566,12 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 
 static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 {
+	struct r0conf *conf = mddev->private;
 	struct strip_zone *zone;
 	struct md_rdev *tmp_dev;
 	sector_t bio_sector;
 	sector_t sector;
+	sector_t orig_sector;
 	unsigned chunk_sects;
 	unsigned sectors;
 
@@ -584,8 +605,20 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 		bio = split;
 	}
 
+	orig_sector = sector;
 	zone = find_zone(mddev->private, &sector);
-	tmp_dev = map_sector(mddev, zone, sector, &sector);
+	switch (conf->layout) {
+	case RAID0_ORIG_LAYOUT:
+		tmp_dev = map_sector(mddev, zone, orig_sector, &sector);
+		break;
+	case RAID0_ALT_MULTIZONE_LAYOUT:
+		tmp_dev = map_sector(mddev, zone, sector, &sector);
+		break;
+	default:
+		WARN("md/raid0:%s: Invalid layout\n", mdname(mddev));
+		bio_io_error(bio);
+		return true;
+	}
 
 	if (unlikely(is_mddev_broken(tmp_dev, "raid0"))) {
 		bio_io_error(bio);

drivers/md/raid0.h

@@ -8,11 +8,25 @@ struct strip_zone {
 	int	 nb_dev;	/* # of devices attached to the zone */
 };
 
+/* Linux 3.14 (20d0189b101) made an unintended change to
+ * the RAID0 layout for multi-zone arrays (where devices aren't all
+ * the same size.
+ * RAID0_ORIG_LAYOUT restores the original layout
+ * RAID0_ALT_MULTIZONE_LAYOUT uses the altered layout
+ * The layouts are identical when there is only one zone (all
+ * devices the same size).
+ */
+
+enum r0layout {
+	RAID0_ORIG_LAYOUT = 1,
+	RAID0_ALT_MULTIZONE_LAYOUT = 2,
+};
 struct r0conf {
 	struct strip_zone	*strip_zone;
 	struct md_rdev		**devlist; /* lists of rdevs, pointed to
 					    * by strip_zone->dev */
 	int			nr_strip_zones;
+	enum r0layout		layout;
 };
 
 #endif

drivers/md/raid5.c

@@ -2526,7 +2526,8 @@ static void raid5_end_read_request(struct bio * bi)
 		int set_bad = 0;
 
 		clear_bit(R5_UPTODATE, &sh->dev[i].flags);
-		atomic_inc(&rdev->read_errors);
+		if (!(bi->bi_status == BLK_STS_PROTECTION))
+			atomic_inc(&rdev->read_errors);
 		if (test_bit(R5_ReadRepl, &sh->dev[i].flags))
 			pr_warn_ratelimited(
 				"md/raid:%s: read error on replacement device (sector %llu on %s).\n",
@@ -4620,7 +4621,6 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
 					  (1 << STRIPE_FULL_WRITE) |
 					  (1 << STRIPE_BIOFILL_RUN) |
 					  (1 << STRIPE_COMPUTE_RUN)  |
-					  (1 << STRIPE_OPS_REQ_PENDING) |
 					  (1 << STRIPE_DISCARD) |
 					  (1 << STRIPE_BATCH_READY) |
 					  (1 << STRIPE_BATCH_ERR) |
@@ -5726,7 +5726,8 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 				do_flush = false;
 			}
 
-			set_bit(STRIPE_HANDLE, &sh->state);
+			if (!sh->batch_head)
+				set_bit(STRIPE_HANDLE, &sh->state);
 			clear_bit(STRIPE_DELAYED, &sh->state);
 			if ((!sh->batch_head || sh == sh->batch_head) &&
 			    (bi->bi_opf & REQ_SYNC) &&

drivers/md/raid5.h

@@ -357,7 +357,6 @@ enum {
 	STRIPE_FULL_WRITE,	/* all blocks are set to be overwritten */
 	STRIPE_BIOFILL_RUN,
 	STRIPE_COMPUTE_RUN,
-	STRIPE_OPS_REQ_PENDING,
 	STRIPE_ON_UNPLUG_LIST,
 	STRIPE_DISCARD,
 	STRIPE_ON_RELEASE_LIST,
@@ -493,9 +492,7 @@ struct disk_info {
  */
 static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
 {
-	int sectors = bio_sectors(bio);
-
-	if (bio->bi_iter.bi_sector + sectors < sector + STRIPE_SECTORS)
+	if (bio_end_sector(bio) < sector + STRIPE_SECTORS)
 		return bio->bi_next;
 	else
 		return NULL;

include/uapi/linux/raid/md_p.h

@@ -329,6 +329,7 @@ struct mdp_superblock_1 {
 #define	MD_FEATURE_JOURNAL		512 /* support write cache */
 #define	MD_FEATURE_PPL			1024 /* support PPL */
 #define	MD_FEATURE_MULTIPLE_PPLS	2048 /* support for multiple PPLs */
+#define	MD_FEATURE_RAID0_LAYOUT		4096 /* layout is meaningful for RAID0 */
 #define	MD_FEATURE_ALL			(MD_FEATURE_BITMAP_OFFSET	\
 					|MD_FEATURE_RECOVERY_OFFSET	\
 					|MD_FEATURE_RESHAPE_ACTIVE	\
@@ -341,6 +342,7 @@ struct mdp_superblock_1 {
 					|MD_FEATURE_JOURNAL		\
 					|MD_FEATURE_PPL			\
 					|MD_FEATURE_MULTIPLE_PPLS	\
+					|MD_FEATURE_RAID0_LAYOUT	\
 					)
 
 struct r5l_payload_header {