Merge branch 'linus' into x86/asm, to pick up recent fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

12 files changed, 182 insertions, 123 deletions

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 95a4ca6ce6ff..849ad441cd76 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -760,7 +760,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 	if (!d->nr_stripes ||
 	    d->nr_stripes > INT_MAX ||
 	    d->nr_stripes > SIZE_MAX / sizeof(atomic_t)) {
-		pr_err("nr_stripes too large");
+		pr_err("nr_stripes too large or invalid: %u (start sector beyond end of disk?)",
+			(unsigned)d->nr_stripes);
 		return -ENOMEM;
 	}
 
@@ -1820,7 +1821,7 @@ static int cache_alloc(struct cache *ca)
 	free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
 
 	if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) ||
-	    !init_fifo(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
+	    !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
 	    !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) ||
 	    !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) ||
 	    !init_fifo(&ca->free_inc,	free << 2, GFP_KERNEL) ||
@@ -1844,7 +1845,7 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
 				struct block_device *bdev, struct cache *ca)
 {
 	char name[BDEVNAME_SIZE];
-	const char *err = NULL;
+	const char *err = NULL; /* must be set for any error case */
 	int ret = 0;
 
 	memcpy(&ca->sb, sb, sizeof(struct cache_sb));
@@ -1861,8 +1862,13 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
 		ca->discard = CACHE_DISCARD(&ca->sb);
 
 	ret = cache_alloc(ca);
-	if (ret != 0)
+	if (ret != 0) {
+		if (ret == -ENOMEM)
+			err = "cache_alloc(): -ENOMEM";
+		else
+			err = "cache_alloc(): unknown error";
 		goto err;
+	}
 
 	if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) {
 		err = "error calling kobject_add";
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 6fff794e0c72..13041ee37ad6 100644
--- a/drivers/md/bitmap.c
+++ b/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;
 }
 
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 6571c81465e1..8625040bae92 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1879,7 +1879,7 @@ static int __init dm_bufio_init(void)
 	__cache_size_refresh();
 	mutex_unlock(&dm_bufio_clients_lock);
 
-	dm_bufio_wq = create_singlethread_workqueue("dm_bufio_cache");
+	dm_bufio_wq = alloc_workqueue("dm_bufio_cache", WQ_MEM_RECLAIM, 0);
 	if (!dm_bufio_wq)
 		return -ENOMEM;
 
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index eedba67b0e3e..874295757caa 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1453,7 +1453,7 @@ static int crypt_alloc_tfms(struct crypt_config *cc, char *ciphermode)
 	unsigned i;
 	int err;
 
-	cc->tfms = kmalloc(cc->tfms_count * sizeof(struct crypto_skcipher *),
+	cc->tfms = kzalloc(cc->tfms_count * sizeof(struct crypto_skcipher *),
 			   GFP_KERNEL);
 	if (!cc->tfms)
 		return -ENOMEM;
@@ -1924,6 +1924,13 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 		return DM_MAPIO_REMAPPED;
 	}
 
+	/*
+	 * Check if bio is too large, split as needed.
+	 */
+	if (unlikely(bio->bi_iter.bi_size > (BIO_MAX_PAGES << PAGE_SHIFT)) &&
+	    bio_data_dir(bio) == WRITE)
+		dm_accept_partial_bio(bio, ((BIO_MAX_PAGES << PAGE_SHIFT) >> SECTOR_SHIFT));
+
 	io = dm_per_bio_data(bio, cc->per_bio_data_size);
 	crypt_io_init(io, cc, bio, dm_target_offset(ti, bio->bi_iter.bi_sector));
 	io->ctx.req = (struct skcipher_request *)(io + 1);
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 97e446d54a15..6a2e8dd44a1b 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -289,15 +289,13 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 		pb->bio_submitted = true;
 
 		/*
-		 * Map reads as normal only if corrupt_bio_byte set.
+		 * Error reads if neither corrupt_bio_byte or drop_writes are set.
+		 * Otherwise, flakey_end_io() will decide if the reads should be modified.
 		 */
 		if (bio_data_dir(bio) == READ) {
-			/* If flags were specified, only corrupt those that match. */
-			if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) &&
-			    all_corrupt_bio_flags_match(bio, fc))
-				goto map_bio;
-			else
+			if (!fc->corrupt_bio_byte && !test_bit(DROP_WRITES, &fc->flags))
 				return -EIO;
+			goto map_bio;
 		}
 
 		/*
@@ -334,14 +332,21 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error)
 	struct flakey_c *fc = ti->private;
 	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
 
-	/*
-	 * Corrupt successful READs while in down state.
-	 */
 	if (!error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
-		if (fc->corrupt_bio_byte)
+		if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) &&
+		    all_corrupt_bio_flags_match(bio, fc)) {
+			/*
+			 * Corrupt successful matching READs while in down state.
+			 */
 			corrupt_bio_data(bio, fc);
-		else
+
+		} else if (!test_bit(DROP_WRITES, &fc->flags)) {
+			/*
+			 * Error read during the down_interval if drop_writes
+			 * wasn't configured.
+			 */
 			return -EIO;
+		}
 	}
 
 	return error;
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index 4ab68033f9d1..49e4d8d4558f 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -259,12 +259,12 @@ static int log_one_block(struct log_writes_c *lc,
 		goto out;
 	sector++;
 
-	bio = bio_alloc(GFP_KERNEL, block->vec_cnt);
+	atomic_inc(&lc->io_blocks);
+	bio = bio_alloc(GFP_KERNEL, min(block->vec_cnt, BIO_MAX_PAGES));
 	if (!bio) {
 		DMERR("Couldn't alloc log bio");
 		goto error;
 	}
-	atomic_inc(&lc->io_blocks);
 	bio->bi_iter.bi_size = 0;
 	bio->bi_iter.bi_sector = sector;
 	bio->bi_bdev = lc->logdev->bdev;
@@ -282,7 +282,7 @@ static int log_one_block(struct log_writes_c *lc,
 		if (ret != block->vecs[i].bv_len) {
 			atomic_inc(&lc->io_blocks);
 			submit_bio(bio);
-			bio = bio_alloc(GFP_KERNEL, block->vec_cnt - i);
+			bio = bio_alloc(GFP_KERNEL, min(block->vec_cnt - i, BIO_MAX_PAGES));
 			if (!bio) {
 				DMERR("Couldn't alloc log bio");
 				goto error;
@@ -459,9 +459,9 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad;
 	}
 
-	ret = -EINVAL;
 	lc->log_kthread = kthread_run(log_writes_kthread, lc, "log-write");
-	if (!lc->log_kthread) {
+	if (IS_ERR(lc->log_kthread)) {
+		ret = PTR_ERR(lc->log_kthread);
 		ti->error = "Couldn't alloc kthread";
 		dm_put_device(ti, lc->dev);
 		dm_put_device(ti, lc->logdev);
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index 4ca2d1df5b44..07fc1ad42ec5 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -291,9 +291,10 @@ static void header_from_disk(struct log_header_core *core, struct log_header_dis
 	core->nr_regions = le64_to_cpu(disk->nr_regions);
 }
 
-static int rw_header(struct log_c *lc, int rw)
+static int rw_header(struct log_c *lc, int op)
 {
-	lc->io_req.bi_op = rw;
+	lc->io_req.bi_op = op;
+	lc->io_req.bi_op_flags = 0;
 
 	return dm_io(&lc->io_req, 1, &lc->header_location, NULL);
 }
@@ -316,7 +317,7 @@ static int read_header(struct log_c *log)
 {
 	int r;
 
-	r = rw_header(log, READ);
+	r = rw_header(log, REQ_OP_READ);
 	if (r)
 		return r;
 
@@ -630,7 +631,7 @@ static int disk_resume(struct dm_dirty_log *log)
 	header_to_disk(&lc->header, lc->disk_header);
 
 	/* write the new header */
-	r = rw_header(lc, WRITE);
+	r = rw_header(lc, REQ_OP_WRITE);
 	if (!r) {
 		r = flush_header(lc);
 		if (r)
@@ -698,7 +699,7 @@ static int disk_flush(struct dm_dirty_log *log)
 			log_clear_bit(lc, lc->clean_bits, i);
 	}
 
-	r = rw_header(lc, WRITE);
+	r = rw_header(lc, REQ_OP_WRITE);
 	if (r)
 		fail_log_device(lc);
 	else {
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 41573f1f626f..34a840d9df76 100644
--- a/drivers/md/md-cluster.c
+++ b/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:
diff --git a/drivers/md/md.c b/drivers/md/md.c
index d646f6e444f0..915e84d631a2 100644
--- a/drivers/md/md.c
+++ b/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++;
 		}
@@ -7610,16 +7610,12 @@ EXPORT_SYMBOL(unregister_md_cluster_operations);
 
 int md_setup_cluster(struct mddev *mddev, int nodes)
 {
-	int err;
-
-	err = request_module("md-cluster");
-	if (err) {
-		pr_err("md-cluster module not found.\n");
-		return -ENOENT;
-	}
-
+	if (!md_cluster_ops)
+		request_module("md-cluster");
 	spin_lock(&pers_lock);
+	/* ensure module won't be unloaded */
 	if (!md_cluster_ops || !try_module_get(md_cluster_mod)) {
+		pr_err("can't find md-cluster module or get it's reference.\n");
 		spin_unlock(&pers_lock);
 		return -ENOENT;
 	}
@@ -7862,6 +7858,7 @@ void md_do_sync(struct md_thread *thread)
 	 */
 
 	do {
+		int mddev2_minor = -1;
 		mddev->curr_resync = 2;
 
 	try_again:
@@ -7891,10 +7888,14 @@ 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 +8276,13 @@ no_add:
 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);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 0e4efcd10795..be1a9fca3b2d 100644
--- a/drivers/md/raid10.c
+++ b/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;
 
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 51f76ddbe265..1b1ab4a1d132 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -96,7 +96,6 @@ struct r5l_log {
 	spinlock_t no_space_stripes_lock;
 
 	bool need_cache_flush;
-	bool in_teardown;
 };
 
 /*
@@ -704,31 +703,22 @@ static void r5l_write_super_and_discard_space(struct r5l_log *log,
 
 	mddev = log->rdev->mddev;
 	/*
-	 * This is to avoid a deadlock. r5l_quiesce holds reconfig_mutex and
-	 * wait for this thread to finish. This thread waits for
-	 * MD_CHANGE_PENDING clear, which is supposed to be done in
-	 * md_check_recovery(). md_check_recovery() tries to get
-	 * reconfig_mutex. Since r5l_quiesce already holds the mutex,
-	 * md_check_recovery() fails, so the PENDING never get cleared. The
-	 * in_teardown check workaround this issue.
+	 * Discard could zero data, so before discard we must make sure
+	 * superblock is updated to new log tail. Updating superblock (either
+	 * directly call md_update_sb() or depend on md thread) must hold
+	 * reconfig mutex. On the other hand, raid5_quiesce is called with
+	 * reconfig_mutex hold. The first step of raid5_quiesce() is waitting
+	 * for all IO finish, hence waitting for reclaim thread, while reclaim
+	 * thread is calling this function and waitting for reconfig mutex. So
+	 * there is a deadlock. We workaround this issue with a trylock.
+	 * FIXME: we could miss discard if we can't take reconfig mutex
 	 */
-	if (!log->in_teardown) {
-		set_mask_bits(&mddev->flags, 0,
-			      BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
-		md_wakeup_thread(mddev->thread);
-		wait_event(mddev->sb_wait,
-			!test_bit(MD_CHANGE_PENDING, &mddev->flags) ||
-			log->in_teardown);
-		/*
-		 * r5l_quiesce could run after in_teardown check and hold
-		 * mutex first. Superblock might get updated twice.
-		 */
-		if (log->in_teardown)
-			md_update_sb(mddev, 1);
-	} else {
-		WARN_ON(!mddev_is_locked(mddev));
-		md_update_sb(mddev, 1);
-	}
+	set_mask_bits(&mddev->flags, 0,
+		BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
+	if (!mddev_trylock(mddev))
+		return;
+	md_update_sb(mddev, 1);
+	mddev_unlock(mddev);
 
 	/* discard IO error really doesn't matter, ignore it */
 	if (log->last_checkpoint < end) {
@@ -827,7 +817,6 @@ void r5l_quiesce(struct r5l_log *log, int state)
 	if (!log || state == 2)
 		return;
 	if (state == 0) {
-		log->in_teardown = 0;
 		/*
 		 * This is a special case for hotadd. In suspend, the array has
 		 * no journal. In resume, journal is initialized as well as the
@@ -838,11 +827,6 @@ void r5l_quiesce(struct r5l_log *log, int state)
 		log->reclaim_thread = md_register_thread(r5l_reclaim_thread,
 					log->rdev->mddev, "reclaim");
 	} else if (state == 1) {
-		/*
-		 * at this point all stripes are finished, so io_unit is at
-		 * least in STRIPE_END state
-		 */
-		log->in_teardown = 1;
 		/* make sure r5l_write_super_and_discard_space exits */
 		mddev = log->rdev->mddev;
 		wake_up(&mddev->sb_wait);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 8912407a4dd0..ee7fc3701700 100644
--- a/drivers/md/raid5.c
+++ b/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 @@ again:
 
 			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 @@ again:
 
 			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;
 	}
@@ -2399,6 +2423,7 @@ static void raid5_end_read_request(struct bio * bi)
 		}
 	}
 	rdev_dec_pending(rdev, conf->mddev);
+	bio_reset(bi);
 	clear_bit(R5_LOCKED, &sh->dev[i].flags);
 	set_bit(STRIPE_HANDLE, &sh->state);
 	raid5_release_stripe(sh);
@@ -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;
 	}
@@ -2472,6 +2498,7 @@ static void raid5_end_write_request(struct bio *bi)
 	if (sh->batch_head && bi->bi_error && !replacement)
 		set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
 
+	bio_reset(bi);
 	if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
 		clear_bit(R5_LOCKED, &sh->dev[i].flags);
 	set_bit(STRIPE_HANDLE, &sh->state);
@@ -2485,16 +2512,6 @@ 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 @@ finish:
 	}
 
 	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);
@@ -6620,6 +6639,16 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	}
 
 	conf->min_nr_stripes = NR_STRIPES;
+	if (mddev->reshape_position != MaxSector) {
+		int stripes = max_t(int,
+			((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4,
+			((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4);
+		conf->min_nr_stripes = max(NR_STRIPES, stripes);
+		if (conf->min_nr_stripes != NR_STRIPES)
+			printk(KERN_INFO
+				"md/raid:%s: force stripe size %d for reshape\n",
+				mdname(mddev), conf->min_nr_stripes);
+	}
 	memory = conf->min_nr_stripes * (sizeof(struct stripe_head) +
 		 max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
 	atomic_set(&conf->empty_inactive_list_nr, NR_STRIPE_HASH_LOCKS);
@@ -6826,11 +6855,14 @@ 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;