Merge branch 'md-next' of...

Merge branch 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-5.9/drivers

Pull MD for 5.9 from Song.

* 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md:
  md/raid10: avoid deadlock on recovery.
  raid: md_p.h: drop duplicated word in a comment
  md-cluster: fix rmmod issue when md_cluster convert bitmap to none
  md-cluster: fix safemode_delay value when converting to clustered bitmap
  md/raid5: support config stripe_size by sysfs entry
  md/raid5: set default stripe_size as 4096
  md/raid456: convert macro STRIPE_* to RAID5_STRIPE_*
  raid5: remove the meaningless check in raid5_make_request
  raid5: put the comment of clear_batch_ready to the right place
  raid5: call clear_batch_ready before set STRIPE_ACTIVE
  md: raid10: Fix compilation warning
  md: raid5: Fix compilation warning
  md: raid5-cache: Remove set but unused variable
  md: Fix compilation warning

drivers/md/md.c

@@ -101,6 +101,8 @@ static void mddev_detach(struct mddev *mddev);
  * count by 2 for every hour elapsed between read errors.
  */
 #define MD_DEFAULT_MAX_CORRECTED_READ_ERRORS 20
+/* Default safemode delay: 200 msec */
+#define DEFAULT_SAFEMODE_DELAY ((200 * HZ)/1000 +1)
 /*
  * Current RAID-1,4,5 parallel reconstruction 'guaranteed speed limit'
  * is 1000 KB/sec, so the extra system load does not show up that much.
@@ -2469,8 +2471,8 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 		goto fail;
 
 	ko = &part_to_dev(rdev->bdev->bd_part)->kobj;
-	if (sysfs_create_link(&rdev->kobj, ko, "block"))
-		/* failure here is OK */;
+	/* failure here is OK */
+	err = sysfs_create_link(&rdev->kobj, ko, "block");
 	rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state");
 	rdev->sysfs_unack_badblocks =
 		sysfs_get_dirent_safe(rdev->kobj.sd, "unacknowledged_bad_blocks");
@@ -3238,8 +3240,8 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len)
 			return err;
 		} else
 			sysfs_notify_dirent_safe(rdev->sysfs_state);
-		if (sysfs_link_rdev(rdev->mddev, rdev))
 		/* failure here is OK */;
+		sysfs_link_rdev(rdev->mddev, rdev);
 		/* don't wakeup anyone, leave that to userspace. */
 	} else {
 		if (slot >= rdev->mddev->raid_disks &&
@@ -6034,7 +6036,7 @@ int md_run(struct mddev *mddev)
 	if (mddev_is_clustered(mddev))
 		mddev->safemode_delay = 0;
 	else
-		mddev->safemode_delay = (200 * HZ)/1000 +1; /* 200 msec delay */
+		mddev->safemode_delay = DEFAULT_SAFEMODE_DELAY;
 	mddev->in_sync = 1;
 	smp_wmb();
 	spin_lock(&mddev->lock);
@@ -7413,6 +7415,8 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 
 				mddev->bitmap_info.nodes = 0;
 				md_cluster_ops->leave(mddev);
+				module_put(md_cluster_mod);
+				mddev->safemode_delay = DEFAULT_SAFEMODE_DELAY;
 			}
 			mddev_suspend(mddev);
 			md_bitmap_destroy(mddev);
@@ -8408,6 +8412,7 @@ EXPORT_SYMBOL(unregister_md_cluster_operations);
 
 int md_setup_cluster(struct mddev *mddev, int nodes)
 {
+	int ret;
 	if (!md_cluster_ops)
 		request_module("md-cluster");
 	spin_lock(&pers_lock);
@@ -8419,7 +8424,10 @@ int md_setup_cluster(struct mddev *mddev, int nodes)
 	}
 	spin_unlock(&pers_lock);
 
-	return md_cluster_ops->join(mddev, nodes);
+	ret = md_cluster_ops->join(mddev, nodes);
+	if (!ret)
+		mddev->safemode_delay = 0;
+	return ret;
 }
 
 void md_cluster_stop(struct mddev *mddev)
@@ -9113,8 +9121,8 @@ static int remove_and_add_spares(struct mddev *mddev,
 			rdev->recovery_offset = 0;
 		}
 		if (mddev->pers->hot_add_disk(mddev, rdev) == 0) {
-			if (sysfs_link_rdev(mddev, rdev))
-				/* failure here is OK */;
+			/* failure here is OK */
+			sysfs_link_rdev(mddev, rdev);
 			if (!test_bit(Journal, &rdev->flags))
 				spares++;
 			md_new_event(mddev);

drivers/md/raid10.c

@@ -980,6 +980,7 @@ static void wait_barrier(struct r10conf *conf)
 {
 	spin_lock_irq(&conf->resync_lock);
 	if (conf->barrier) {
+		struct bio_list *bio_list = current->bio_list;
 		conf->nr_waiting++;
 		/* Wait for the barrier to drop.
 		 * However if there are already pending
@@ -994,9 +995,16 @@ static void wait_barrier(struct r10conf *conf)
 		wait_event_lock_irq(conf->wait_barrier,
 				    !conf->barrier ||
 				    (atomic_read(&conf->nr_pending) &&
-				     current->bio_list &&
-				     (!bio_list_empty(&current->bio_list[0]) ||
-				      !bio_list_empty(&current->bio_list[1]))),
+				     bio_list &&
+				     (!bio_list_empty(&bio_list[0]) ||
+				      !bio_list_empty(&bio_list[1]))) ||
+				     /* move on if recovery thread is
+				      * blocked by us
+				      */
+				     (conf->mddev->thread->tsk == current &&
+				      test_bit(MD_RECOVERY_RUNNING,
+					       &conf->mddev->recovery) &&
+				      conf->nr_queued > 0),
 				    conf->resync_lock);
 		conf->nr_waiting--;
 		if (!conf->nr_waiting)
@@ -4307,8 +4315,8 @@ static int raid10_start_reshape(struct mddev *mddev)
 					else
 						rdev->recovery_offset = 0;
 
-					if (sysfs_link_rdev(mddev, rdev))
-						/* Failure here  is OK */;
+					/* Failure here is OK */
+					sysfs_link_rdev(mddev, rdev);
 				}
 			} else if (rdev->raid_disk >= conf->prev.raid_disks
 				   && !test_bit(Faulty, &rdev->flags)) {

drivers/md/raid5-cache.c

@@ -195,9 +195,7 @@ struct r5l_log {
 static inline sector_t r5c_tree_index(struct r5conf *conf,
 				      sector_t sect)
 {
-	sector_t offset;
-
-	offset = sector_div(sect, conf->chunk_sectors);
+	sector_div(sect, conf->chunk_sectors);
 	return sect;
 }
 
@@ -298,8 +296,8 @@ r5c_return_dev_pending_writes(struct r5conf *conf, struct r5dev *dev)
 	wbi = dev->written;
 	dev->written = NULL;
 	while (wbi && wbi->bi_iter.bi_sector <
-	       dev->sector + STRIPE_SECTORS) {
-		wbi2 = r5_next_bio(wbi, dev->sector);
+	       dev->sector + RAID5_STRIPE_SECTORS(conf)) {
+		wbi2 = r5_next_bio(conf, wbi, dev->sector);
 		md_write_end(conf->mddev);
 		bio_endio(wbi);
 		wbi = wbi2;
@@ -316,7 +314,7 @@ void r5c_handle_cached_data_endio(struct r5conf *conf,
 			set_bit(R5_UPTODATE, &sh->dev[i].flags);
 			r5c_return_dev_pending_writes(conf, &sh->dev[i]);
 			md_bitmap_endwrite(conf->mddev->bitmap, sh->sector,
-					   STRIPE_SECTORS,
+					   RAID5_STRIPE_SECTORS(conf),
 					   !test_bit(STRIPE_DEGRADED, &sh->state),
 					   0);
 		}
@@ -364,7 +362,7 @@ void r5c_check_cached_full_stripe(struct r5conf *conf)
 	 */
 	if (atomic_read(&conf->r5c_cached_full_stripes) >=
 	    min(R5C_FULL_STRIPE_FLUSH_BATCH(conf),
-		conf->chunk_sectors >> STRIPE_SHIFT))
+		conf->chunk_sectors >> RAID5_STRIPE_SHIFT(conf)))
 		r5l_wake_reclaim(conf->log, 0);
 }
 

drivers/md/raid5-ppl.c

@@ -324,7 +324,7 @@ static int ppl_log_stripe(struct ppl_log *log, struct stripe_head *sh)
 		 * be just after the last logged stripe and write to the same
 		 * disks. Use bit shift and logarithm to avoid 64-bit division.
 		 */
-		if ((sh->sector == sh_last->sector + STRIPE_SECTORS) &&
+		if ((sh->sector == sh_last->sector + RAID5_STRIPE_SECTORS(conf)) &&
 		    (data_sector >> ilog2(conf->chunk_sectors) ==
 		     data_sector_last >> ilog2(conf->chunk_sectors)) &&
 		    ((data_sector - data_sector_last) * data_disks ==
@@ -844,9 +844,9 @@ static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e,
 
 	/* if start and end is 4k aligned, use a 4k block */
 	if (block_size == 512 &&
-	    (r_sector_first & (STRIPE_SECTORS - 1)) == 0 &&
-	    (r_sector_last & (STRIPE_SECTORS - 1)) == 0)
-		block_size = STRIPE_SIZE;
+	    (r_sector_first & (RAID5_STRIPE_SECTORS(conf) - 1)) == 0 &&
+	    (r_sector_last & (RAID5_STRIPE_SECTORS(conf) - 1)) == 0)
+		block_size = RAID5_STRIPE_SIZE(conf);
 
 	/* iterate through blocks in strip */
 	for (i = 0; i < strip_sectors; i += (block_size >> 9)) {
@@ -1274,7 +1274,8 @@ static int ppl_validate_rdev(struct md_rdev *rdev)
 	ppl_data_sectors = rdev->ppl.size - (PPL_HEADER_SIZE >> 9);
 
 	if (ppl_data_sectors > 0)
-		ppl_data_sectors = rounddown(ppl_data_sectors, STRIPE_SECTORS);
+		ppl_data_sectors = rounddown(ppl_data_sectors,
+				RAID5_STRIPE_SECTORS((struct r5conf *)rdev->mddev->private));
 
 	if (ppl_data_sectors <= 0) {
 		pr_warn("md/raid:%s: PPL space too small on %s\n",

drivers/md/raid5.h

@@ -472,32 +472,20 @@ struct disk_info {
  */
 
 #define NR_STRIPES		256
+#define DEFAULT_STRIPE_SIZE	4096
+
+#if PAGE_SIZE == DEFAULT_STRIPE_SIZE
 #define STRIPE_SIZE		PAGE_SIZE
 #define STRIPE_SHIFT		(PAGE_SHIFT - 9)
 #define STRIPE_SECTORS		(STRIPE_SIZE>>9)
+#endif
+
 #define	IO_THRESHOLD		1
 #define BYPASS_THRESHOLD	1
 #define NR_HASH			(PAGE_SIZE / sizeof(struct hlist_head))
 #define HASH_MASK		(NR_HASH - 1)
 #define MAX_STRIPE_BATCH	8
 
-/* bio's attached to a stripe+device for I/O are linked together in bi_sector
- * order without overlap.  There may be several bio's per stripe+device, and
- * a bio could span several devices.
- * When walking this list for a particular stripe+device, we must never proceed
- * beyond a bio that extends past this device, as the next bio might no longer
- * be valid.
- * This function is used to determine the 'next' bio in the list, given the
- * sector of the current stripe+device
- */
-static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
-{
-	if (bio_end_sector(bio) < sector + STRIPE_SECTORS)
-		return bio->bi_next;
-	else
-		return NULL;
-}
-
 /* NOTE NR_STRIPE_HASH_LOCKS must remain below 64.
  * This is because we sometimes take all the spinlocks
  * and creating that much locking depth can cause
@@ -574,6 +562,11 @@ struct r5conf {
 	int			raid_disks;
 	int			max_nr_stripes;
 	int			min_nr_stripes;
+#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
+	unsigned long	stripe_size;
+	unsigned int	stripe_shift;
+	unsigned long	stripe_sectors;
+#endif
 
 	/* reshape_progress is the leading edge of a 'reshape'
 	 * It has value MaxSector when no reshape is happening
@@ -690,6 +683,32 @@ struct r5conf {
 	struct r5pending_data	*next_pending_data;
 };
 
+#if PAGE_SIZE == DEFAULT_STRIPE_SIZE
+#define RAID5_STRIPE_SIZE(conf)	STRIPE_SIZE
+#define RAID5_STRIPE_SHIFT(conf)	STRIPE_SHIFT
+#define RAID5_STRIPE_SECTORS(conf)	STRIPE_SECTORS
+#else
+#define RAID5_STRIPE_SIZE(conf)	((conf)->stripe_size)
+#define RAID5_STRIPE_SHIFT(conf)	((conf)->stripe_shift)
+#define RAID5_STRIPE_SECTORS(conf)	((conf)->stripe_sectors)
+#endif
+
+/* bio's attached to a stripe+device for I/O are linked together in bi_sector
+ * order without overlap.  There may be several bio's per stripe+device, and
+ * a bio could span several devices.
+ * When walking this list for a particular stripe+device, we must never proceed
+ * beyond a bio that extends past this device, as the next bio might no longer
+ * be valid.
+ * This function is used to determine the 'next' bio in the list, given the
+ * sector of the current stripe+device
+ */
+static inline struct bio *r5_next_bio(struct r5conf *conf, struct bio *bio, sector_t sector)
+{
+	if (bio_end_sector(bio) < sector + RAID5_STRIPE_SECTORS(conf))
+		return bio->bi_next;
+	else
+		return NULL;
+}
 
 /*
  * Our supported algorithms

include/uapi/linux/raid/md_p.h

@@ -123,7 +123,7 @@ typedef struct mdp_device_descriptor_s {
 
 /*
  * Notes:
- * - if an array is being reshaped (restriped) in order to change the
+ * - if an array is being reshaped (restriped) in order to change
  *   the number of active devices in the array, 'raid_disks' will be
  *   the larger of the old and new numbers.  'delta_disks' will
  *   be the "new - old".  So if +ve, raid_disks is the new value, and