Merge tag 'md/4.8-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md

Pull MD fixes from Shaohua Li:
 "This includes several bug fixes:

   - Alexey Obitotskiy fixed a hang for faulty raid5 array with external
     management

   - Song Liu fixed two raid5 journal related bugs

   - Tomasz Majchrzak fixed a bad block recording issue and an
     accounting issue for raid10

   - ZhengYuan Liu fixed an accounting issue for raid5

   - I fixed a potential race condition and memory leak with DIF/DIX
     enabled

   - other trival fixes"

* tag 'md/4.8-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md:
  raid5: avoid unnecessary bio data set
  raid5: fix memory leak of bio integrity data
  raid10: record correct address of bad block
  md-cluster: fix error return code in join()
  r5cache: set MD_JOURNAL_CLEAN correctly
  md: don't print the same repeated messages about delayed sync operation
  md: remove obsolete ret in md_start_sync
  md: do not count journal as spare in GET_ARRAY_INFO
  md: Prevent IO hold during accessing to faulty raid5 array
  MD: hold mddev lock to change bitmap location
  raid5: fix incorrectly counter of conf->empty_inactive_list_nr
  raid10: increment write counter after bio is split

drivers/md/bitmap.c

@@ -2183,19 +2183,29 @@ location_show(struct mddev *mddev, char *page)
 static ssize_t
 location_store(struct mddev *mddev, const char *buf, size_t len)
 {
+	int rv;
 
+	rv = mddev_lock(mddev);
+	if (rv)
+		return rv;
 	if (mddev->pers) {
-		if (!mddev->pers->quiesce)
-			return -EBUSY;
-		if (mddev->recovery || mddev->sync_thread)
-			return -EBUSY;
+		if (!mddev->pers->quiesce) {
+			rv = -EBUSY;
+			goto out;
+		}
+		if (mddev->recovery || mddev->sync_thread) {
+			rv = -EBUSY;
+			goto out;
+		}
 	}
 
 	if (mddev->bitmap || mddev->bitmap_info.file ||
 	    mddev->bitmap_info.offset) {
 		/* bitmap already configured.  Only option is to clear it */
-		if (strncmp(buf, "none", 4) != 0)
-			return -EBUSY;
+		if (strncmp(buf, "none", 4) != 0) {
+			rv = -EBUSY;
+			goto out;
+		}
 		if (mddev->pers) {
 			mddev->pers->quiesce(mddev, 1);
 			bitmap_destroy(mddev);
@@ -2214,21 +2224,25 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 			/* nothing to be done */;
 		else if (strncmp(buf, "file:", 5) == 0) {
 			/* Not supported yet */
-			return -EINVAL;
+			rv = -EINVAL;
+			goto out;
 		} else {
-			int rv;
 			if (buf[0] == '+')
 				rv = kstrtoll(buf+1, 10, &offset);
 			else
 				rv = kstrtoll(buf, 10, &offset);
 			if (rv)
-				return rv;
-			if (offset == 0)
-				return -EINVAL;
+				goto out;
+			if (offset == 0) {
+				rv = -EINVAL;
+				goto out;
+			}
 			if (mddev->bitmap_info.external == 0 &&
 			    mddev->major_version == 0 &&
-			    offset != mddev->bitmap_info.default_offset)
-				return -EINVAL;
+			    offset != mddev->bitmap_info.default_offset) {
+				rv = -EINVAL;
+				goto out;
+			}
 			mddev->bitmap_info.offset = offset;
 			if (mddev->pers) {
 				struct bitmap *bitmap;
@@ -2245,7 +2259,7 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 				mddev->pers->quiesce(mddev, 0);
 				if (rv) {
 					bitmap_destroy(mddev);
-					return rv;
+					goto out;
 				}
 			}
 		}
@@ -2257,6 +2271,11 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 		set_bit(MD_CHANGE_DEVS, &mddev->flags);
 		md_wakeup_thread(mddev->thread);
 	}
+	rv = 0;
+out:
+	mddev_unlock(mddev);
+	if (rv)
+		return rv;
 	return len;
 }
 

drivers/md/md-cluster.c

@@ -834,8 +834,10 @@ static int join(struct mddev *mddev, int nodes)
 		goto err;
 	}
 	cinfo->ack_lockres = lockres_init(mddev, "ack", ack_bast, 0);
-	if (!cinfo->ack_lockres)
+	if (!cinfo->ack_lockres) {
+		ret = -ENOMEM;
 		goto err;
+	}
 	/* get sync CR lock on ACK. */
 	if (dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_CR))
 		pr_err("md-cluster: failed to get a sync CR lock on ACK!(%d)\n",
@@ -849,8 +851,10 @@ static int join(struct mddev *mddev, int nodes)
 	pr_info("md-cluster: Joined cluster %s slot %d\n", str, cinfo->slot_number);
 	snprintf(str, 64, "bitmap%04d", cinfo->slot_number - 1);
 	cinfo->bitmap_lockres = lockres_init(mddev, str, NULL, 1);
-	if (!cinfo->bitmap_lockres)
+	if (!cinfo->bitmap_lockres) {
+		ret = -ENOMEM;
 		goto err;
+	}
 	if (dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW)) {
 		pr_err("Failed to get bitmap lock\n");
 		ret = -EINVAL;
@@ -858,8 +862,10 @@ static int join(struct mddev *mddev, int nodes)
 	}
 
 	cinfo->resync_lockres = lockres_init(mddev, "resync", NULL, 0);
-	if (!cinfo->resync_lockres)
+	if (!cinfo->resync_lockres) {
+		ret = -ENOMEM;
 		goto err;
+	}
 
 	return 0;
 err:

drivers/md/md.c

@@ -1604,11 +1604,8 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 			mddev->new_chunk_sectors = mddev->chunk_sectors;
 		}
 
-		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL) {
+		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)
 			set_bit(MD_HAS_JOURNAL, &mddev->flags);
-			if (mddev->recovery_cp == MaxSector)
-				set_bit(MD_JOURNAL_CLEAN, &mddev->flags);
-		}
 	} else if (mddev->pers == NULL) {
 		/* Insist of good event counter while assembling, except for
 		 * spares (which don't need an event count) */
@@ -5851,6 +5848,9 @@ static int get_array_info(struct mddev *mddev, void __user *arg)
 			working++;
 			if (test_bit(In_sync, &rdev->flags))
 				insync++;
+			else if (test_bit(Journal, &rdev->flags))
+				/* TODO: add journal count to md_u.h */
+				;
 			else
 				spare++;
 		}
@@ -7862,6 +7862,7 @@ void md_do_sync(struct md_thread *thread)
 	 */
 
 	do {
+		int mddev2_minor = -1;
 		mddev->curr_resync = 2;
 
 	try_again:
@@ -7891,10 +7892,14 @@ void md_do_sync(struct md_thread *thread)
 				prepare_to_wait(&resync_wait, &wq, TASK_INTERRUPTIBLE);
 				if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
 				    mddev2->curr_resync >= mddev->curr_resync) {
-					printk(KERN_INFO "md: delaying %s of %s"
-					       " until %s has finished (they"
-					       " share one or more physical units)\n",
-					       desc, mdname(mddev), mdname(mddev2));
+					if (mddev2_minor != mddev2->md_minor) {
+						mddev2_minor = mddev2->md_minor;
+						printk(KERN_INFO "md: delaying %s of %s"
+						       " until %s has finished (they"
+						       " share one or more physical units)\n",
+						       desc, mdname(mddev),
+						       mdname(mddev2));
+					}
 					mddev_put(mddev2);
 					if (signal_pending(current))
 						flush_signals(current);
@@ -8275,16 +8280,13 @@ static int remove_and_add_spares(struct mddev *mddev,
 static void md_start_sync(struct work_struct *ws)
 {
 	struct mddev *mddev = container_of(ws, struct mddev, del_work);
-	int ret = 0;
 
 	mddev->sync_thread = md_register_thread(md_do_sync,
 						mddev,
 						"resync");
 	if (!mddev->sync_thread) {
-		if (!(mddev_is_clustered(mddev) && ret == -EAGAIN))
-			printk(KERN_ERR "%s: could not start resync"
-			       " thread...\n",
-			       mdname(mddev));
+		printk(KERN_ERR "%s: could not start resync thread...\n",
+		       mdname(mddev));
 		/* leave the spares where they are, it shouldn't hurt */
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);

drivers/md/raid10.c

@@ -1064,6 +1064,8 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
 	int max_sectors;
 	int sectors;
 
+	md_write_start(mddev, bio);
+
 	/*
 	 * Register the new request and wait if the reconstruction
 	 * thread has put up a bar for new requests.
@@ -1445,8 +1447,6 @@ static void raid10_make_request(struct mddev *mddev, struct bio *bio)
 		return;
 	}
 
-	md_write_start(mddev, bio);
-
 	do {
 
 		/*
@@ -2465,20 +2465,21 @@ static int narrow_write_error(struct r10bio *r10_bio, int i)
 
 	while (sect_to_write) {
 		struct bio *wbio;
+		sector_t wsector;
 		if (sectors > sect_to_write)
 			sectors = sect_to_write;
 		/* Write at 'sector' for 'sectors' */
 		wbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
 		bio_trim(wbio, sector - bio->bi_iter.bi_sector, sectors);
-		wbio->bi_iter.bi_sector = (r10_bio->devs[i].addr+
-				   choose_data_offset(r10_bio, rdev) +
-				   (sector - r10_bio->sector));
+		wsector = r10_bio->devs[i].addr + (sector - r10_bio->sector);
+		wbio->bi_iter.bi_sector = wsector +
+				   choose_data_offset(r10_bio, rdev);
 		wbio->bi_bdev = rdev->bdev;
 		bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
 
 		if (submit_bio_wait(wbio) < 0)
 			/* Failure! */
-			ok = rdev_set_badblocks(rdev, sector,
+			ok = rdev_set_badblocks(rdev, wsector,
 						sectors, 0)
 				&& ok;
 

drivers/md/raid5.c

@@ -659,6 +659,7 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
 {
 	struct stripe_head *sh;
 	int hash = stripe_hash_locks_hash(sector);
+	int inc_empty_inactive_list_flag;
 
 	pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
 
@@ -703,7 +704,12 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
 					atomic_inc(&conf->active_stripes);
 				BUG_ON(list_empty(&sh->lru) &&
 				       !test_bit(STRIPE_EXPANDING, &sh->state));
+				inc_empty_inactive_list_flag = 0;
+				if (!list_empty(conf->inactive_list + hash))
+					inc_empty_inactive_list_flag = 1;
 				list_del_init(&sh->lru);
+				if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
+					atomic_inc(&conf->empty_inactive_list_nr);
 				if (sh->group) {
 					sh->group->stripes_cnt--;
 					sh->group = NULL;
@@ -762,6 +768,7 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
 	sector_t head_sector, tmp_sec;
 	int hash;
 	int dd_idx;
+	int inc_empty_inactive_list_flag;
 
 	/* Don't cross chunks, so stripe pd_idx/qd_idx is the same */
 	tmp_sec = sh->sector;
@@ -779,7 +786,12 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
 				atomic_inc(&conf->active_stripes);
 			BUG_ON(list_empty(&head->lru) &&
 			       !test_bit(STRIPE_EXPANDING, &head->state));
+			inc_empty_inactive_list_flag = 0;
+			if (!list_empty(conf->inactive_list + hash))
+				inc_empty_inactive_list_flag = 1;
 			list_del_init(&head->lru);
+			if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
+				atomic_inc(&conf->empty_inactive_list_nr);
 			if (head->group) {
 				head->group->stripes_cnt--;
 				head->group = NULL;
@@ -993,7 +1005,6 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 
 			set_bit(STRIPE_IO_STARTED, &sh->state);
 
-			bio_reset(bi);
 			bi->bi_bdev = rdev->bdev;
 			bio_set_op_attrs(bi, op, op_flags);
 			bi->bi_end_io = op_is_write(op)
@@ -1045,7 +1056,6 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 
 			set_bit(STRIPE_IO_STARTED, &sh->state);
 
-			bio_reset(rbi);
 			rbi->bi_bdev = rrdev->bdev;
 			bio_set_op_attrs(rbi, op, op_flags);
 			BUG_ON(!op_is_write(op));
@@ -1978,9 +1988,11 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 	put_cpu();
 }
 
-static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp)
+static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
+	int disks)
 {
 	struct stripe_head *sh;
+	int i;
 
 	sh = kmem_cache_zalloc(sc, gfp);
 	if (sh) {
@@ -1989,6 +2001,17 @@ static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp)
 		INIT_LIST_HEAD(&sh->batch_list);
 		INIT_LIST_HEAD(&sh->lru);
 		atomic_set(&sh->count, 1);
+		for (i = 0; i < disks; i++) {
+			struct r5dev *dev = &sh->dev[i];
+
+			bio_init(&dev->req);
+			dev->req.bi_io_vec = &dev->vec;
+			dev->req.bi_max_vecs = 1;
+
+			bio_init(&dev->rreq);
+			dev->rreq.bi_io_vec = &dev->rvec;
+			dev->rreq.bi_max_vecs = 1;
+		}
 	}
 	return sh;
 }
@@ -1996,7 +2019,7 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
 {
 	struct stripe_head *sh;
 
-	sh = alloc_stripe(conf->slab_cache, gfp);
+	sh = alloc_stripe(conf->slab_cache, gfp, conf->pool_size);
 	if (!sh)
 		return 0;
 
@@ -2167,7 +2190,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	mutex_lock(&conf->cache_size_mutex);
 
 	for (i = conf->max_nr_stripes; i; i--) {
-		nsh = alloc_stripe(sc, GFP_KERNEL);
+		nsh = alloc_stripe(sc, GFP_KERNEL, newsize);
 		if (!nsh)
 			break;
 
@@ -2299,6 +2322,7 @@ static void raid5_end_read_request(struct bio * bi)
 		(unsigned long long)sh->sector, i, atomic_read(&sh->count),
 		bi->bi_error);
 	if (i == disks) {
+		bio_reset(bi);
 		BUG();
 		return;
 	}
@@ -2402,6 +2426,7 @@ static void raid5_end_read_request(struct bio * bi)
 	clear_bit(R5_LOCKED, &sh->dev[i].flags);
 	set_bit(STRIPE_HANDLE, &sh->state);
 	raid5_release_stripe(sh);
+	bio_reset(bi);
 }
 
 static void raid5_end_write_request(struct bio *bi)
@@ -2436,6 +2461,7 @@ static void raid5_end_write_request(struct bio *bi)
 		(unsigned long long)sh->sector, i, atomic_read(&sh->count),
 		bi->bi_error);
 	if (i == disks) {
+		bio_reset(bi);
 		BUG();
 		return;
 	}
@@ -2479,22 +2505,13 @@ static void raid5_end_write_request(struct bio *bi)
 
 	if (sh->batch_head && sh != sh->batch_head)
 		raid5_release_stripe(sh->batch_head);
+	bio_reset(bi);
 }
 
 static void raid5_build_block(struct stripe_head *sh, int i, int previous)
 {
 	struct r5dev *dev = &sh->dev[i];
 
-	bio_init(&dev->req);
-	dev->req.bi_io_vec = &dev->vec;
-	dev->req.bi_max_vecs = 1;
-	dev->req.bi_private = sh;
-
-	bio_init(&dev->rreq);
-	dev->rreq.bi_io_vec = &dev->rvec;
-	dev->rreq.bi_max_vecs = 1;
-	dev->rreq.bi_private = sh;
-
 	dev->flags = 0;
 	dev->sector = raid5_compute_blocknr(sh, i, previous);
 }
@@ -4628,7 +4645,9 @@ static void handle_stripe(struct stripe_head *sh)
 	}
 
 	if (!bio_list_empty(&s.return_bi)) {
-		if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags)) {
+		if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags) &&
+				(s.failed <= conf->max_degraded ||
+					conf->mddev->external == 0)) {
 			spin_lock_irq(&conf->device_lock);
 			bio_list_merge(&conf->return_bi, &s.return_bi);
 			spin_unlock_irq(&conf->device_lock);
@@ -6826,11 +6845,14 @@ static int raid5_run(struct mddev *mddev)
 	if (IS_ERR(conf))
 		return PTR_ERR(conf);
 
-	if (test_bit(MD_HAS_JOURNAL, &mddev->flags) && !journal_dev) {
-		printk(KERN_ERR "md/raid:%s: journal disk is missing, force array readonly\n",
-		       mdname(mddev));
-		mddev->ro = 1;
-		set_disk_ro(mddev->gendisk, 1);
+	if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
+		if (!journal_dev) {
+			pr_err("md/raid:%s: journal disk is missing, force array readonly\n",
+			       mdname(mddev));
+			mddev->ro = 1;
+			set_disk_ro(mddev->gendisk, 1);
+		} else if (mddev->recovery_cp == MaxSector)
+			set_bit(MD_JOURNAL_CLEAN, &mddev->flags);
 	}
 
 	conf->min_offset_diff = min_offset_diff;