for-linus-20180608

-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAlsa4sQQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpqPNEADbZby01Q6i+dTZYIosz5+/gq8gSkCcpQ/T
 krK/f2MlwD7Rdog1BnGNNP5XOqK8pKIGdARL1FQKpViii6xGIoOc2F4VK+vO44yR
 LI+BeeOM6rWNOAoBO4CqeZz/Fv5IYi7KURWogYhZMqrxBqT2OeD9MMowm5NulBix
 YZ2ttFWiTJScJttJCDPE6cu9EjHDeK63Nr7+UU80k3atU4eUpUp1mRFGmtaYWulq
 l3KaENCwm00WCVqM4i/gVWr2AkgTZqAAyeCx7IrPsrQrCMEhxEpMnU52e2kXSxhM
 Qx6FLNEOjzARuBDurtfJE74usQcW2xDLzT8fh2UStnPpt6S/JX6f9GMBVk0G7I8B
 8COF4DF+bzdbhhz2SiZaTFOmDML5H1iQ8t6lTTms0Bnq29mE3E4QFom8lO+2BxN3
 g6PFhvYaOkhTVtV5BPXpXs9xZBLHrv5G/JopXsZh0RF1kpiova+nfA1K2uJPFpJ0
 NcHuMZKmIG3uBqY3fj5Ul+zuVhZ/1v8B69zWoSWafLrk+VRdcEAniuY2E6SsQFP5
 gV4GNja85S53DnlIVwEUXPYMiY6opiwP53yMNMvkB/FdzaQB5Ehdif2fhZu64QmE
 TtqbHtAuV0VZ3z4GrJ3XNbV6Np4wMOhYls4lTkZsnqNNO2sw/eoTYcmwxLDEYOQw
 uQ9rhZh4IQ==
 =N3BP
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-20180608' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A few fixes for this merge window, where some of them should go in
  sooner rather than later, hence a new pull this week. This pull
  request contains:

   - Set of NVMe fixes, mostly follow up cleanups/fixes to the queue
     changes, but also teardown/removal and misc changes (Christop/Dan/
     Johannes/Sagi/Steve).

   - Two lightnvm fixes for issues that showed up in this window
     (Colin/Wei).

   - Failfast/driver flags inheritance for flush requests (Hannes).

   - The md device put sanitization and fix (Kent).

   - dm bio_set inheritance fix (me).

   - nbd discard granularity fix (Josef).

   - nbd consistency in command printing (Kevin).

   - Loop recursion validation fix (Ted).

   - Partition overlap check (Wang)"

[ .. and now my build is warning-free again thanks to the md fix  - Linus ]

* tag 'for-linus-20180608' of git://git.kernel.dk/linux-block: (22 commits)
  nvme: cleanup double shift issue
  nvme-pci: make CMB SQ mod-param read-only
  nvme-pci: unquiesce dead controller queues
  nvme-pci: remove HMB teardown on reset
  nvme-pci: queue creation fixes
  nvme-pci: remove unnecessary completion doorbell check
  nvme-pci: remove unnecessary nested locking
  nvmet: filter newlines from user input
  nvme-rdma: correctly check for target keyed sgl support
  nvme: don't hold nvmf_transports_rwsem for more than transport lookups
  nvmet: return all zeroed buffer when we can't find an active namespace
  md: Unify mddev destruction paths
  dm: use bioset_init_from_src() to copy bio_set
  block: add bioset_init_from_src() helper
  block: always set partition number to '0' in blk_partition_remap()
  block: pass failfast and driver-specific flags to flush requests
  nbd: set discard_alignment to the granularity
  nbd: Consistently use request pointer in debug messages.
  block: add verifier for cmdline partition
  lightnvm: pblk: fix resource leak of invalid_bitmap
  ...

block/bio.c

@@ -1997,6 +1997,24 @@ bad:
 }
 EXPORT_SYMBOL(bioset_init);
 
+/*
+ * Initialize and setup a new bio_set, based on the settings from
+ * another bio_set.
+ */
+int bioset_init_from_src(struct bio_set *bs, struct bio_set *src)
+{
+	int flags;
+
+	flags = 0;
+	if (src->bvec_pool.min_nr)
+		flags |= BIOSET_NEED_BVECS;
+	if (src->rescue_workqueue)
+		flags |= BIOSET_NEED_RESCUER;
+
+	return bioset_init(bs, src->bio_pool.min_nr, src->front_pad, flags);
+}
+EXPORT_SYMBOL(bioset_init_from_src);
+
 #ifdef CONFIG_BLK_CGROUP
 
 /**

block/blk-core.c

@@ -2220,10 +2220,10 @@ static inline int blk_partition_remap(struct bio *bio)
 		if (bio_check_eod(bio, part_nr_sects_read(p)))
 			goto out;
 		bio->bi_iter.bi_sector += p->start_sect;
-		bio->bi_partno = 0;
 		trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p),
 				      bio->bi_iter.bi_sector - p->start_sect);
 	}
+	bio->bi_partno = 0;
 	ret = 0;
 out:
 	rcu_read_unlock();

block/blk-flush.c

@@ -94,7 +94,7 @@ enum {
 };
 
 static bool blk_kick_flush(struct request_queue *q,
-			   struct blk_flush_queue *fq);
+			   struct blk_flush_queue *fq, unsigned int flags);
 
 static unsigned int blk_flush_policy(unsigned long fflags, struct request *rq)
 {
@@ -212,7 +212,7 @@ static bool blk_flush_complete_seq(struct request *rq,
 		BUG();
 	}
 
-	kicked = blk_kick_flush(q, fq);
+	kicked = blk_kick_flush(q, fq, rq->cmd_flags);
 	return kicked | queued;
 }
 
@@ -281,6 +281,7 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
  * blk_kick_flush - consider issuing flush request
  * @q: request_queue being kicked
  * @fq: flush queue
+ * @flags: cmd_flags of the original request
  *
  * Flush related states of @q have changed, consider issuing flush request.
  * Please read the comment at the top of this file for more info.
@@ -291,7 +292,8 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
  * RETURNS:
  * %true if flush was issued, %false otherwise.
  */
-static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
+static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
+			   unsigned int flags)
 {
 	struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx];
 	struct request *first_rq =
@@ -346,6 +348,7 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 	}
 
 	flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH;
+	flush_rq->cmd_flags |= (flags & REQ_DRV) | (flags & REQ_FAILFAST_MASK);
 	flush_rq->rq_flags |= RQF_FLUSH_SEQ;
 	flush_rq->rq_disk = first_rq->rq_disk;
 	flush_rq->end_io = flush_end_io;

block/partitions/cmdline.c

@@ -58,6 +58,62 @@ static int __init cmdline_parts_setup(char *s)
 }
 __setup("blkdevparts=", cmdline_parts_setup);
 
+static bool has_overlaps(sector_t from, sector_t size,
+			 sector_t from2, sector_t size2)
+{
+	sector_t end = from + size;
+	sector_t end2 = from2 + size2;
+
+	if (from >= from2 && from < end2)
+		return true;
+
+	if (end > from2 && end <= end2)
+		return true;
+
+	if (from2 >= from && from2 < end)
+		return true;
+
+	if (end2 > from && end2 <= end)
+		return true;
+
+	return false;
+}
+
+static inline void overlaps_warns_header(void)
+{
+	pr_warn("Overlapping partitions are used in command line partitions.");
+	pr_warn("Don't use filesystems on overlapping partitions:");
+}
+
+static void cmdline_parts_verifier(int slot, struct parsed_partitions *state)
+{
+	int i;
+	bool header = true;
+
+	for (; slot < state->limit && state->parts[slot].has_info; slot++) {
+		for (i = slot+1; i < state->limit && state->parts[i].has_info;
+		     i++) {
+			if (has_overlaps(state->parts[slot].from,
+					 state->parts[slot].size,
+					 state->parts[i].from,
+					 state->parts[i].size)) {
+				if (header) {
+					header = false;
+					overlaps_warns_header();
+				}
+				pr_warn("%s[%llu,%llu] overlaps with "
+					"%s[%llu,%llu].",
+					state->parts[slot].info.volname,
+					(u64)state->parts[slot].from << 9,
+					(u64)state->parts[slot].size << 9,
+					state->parts[i].info.volname,
+					(u64)state->parts[i].from << 9,
+					(u64)state->parts[i].size << 9);
+			}
+		}
+	}
+}
+
 /*
  * Purpose: allocate cmdline partitions.
  * Returns:
@@ -93,6 +149,7 @@ int cmdline_partition(struct parsed_partitions *state)
 	disk_size = get_capacity(state->bdev->bd_disk) << 9;
 
 	cmdline_parts_set(parts, disk_size, 1, add_part, (void *)state);
+	cmdline_parts_verifier(1, state);
 
 	strlcat(state->pp_buf, "\n", PAGE_SIZE);
 

drivers/block/loop.c

@@ -647,6 +647,36 @@ static void loop_reread_partitions(struct loop_device *lo,
 			__func__, lo->lo_number, lo->lo_file_name, rc);
 }
 
+static inline int is_loop_device(struct file *file)
+{
+	struct inode *i = file->f_mapping->host;
+
+	return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR;
+}
+
+static int loop_validate_file(struct file *file, struct block_device *bdev)
+{
+	struct inode	*inode = file->f_mapping->host;
+	struct file	*f = file;
+
+	/* Avoid recursion */
+	while (is_loop_device(f)) {
+		struct loop_device *l;
+
+		if (f->f_mapping->host->i_bdev == bdev)
+			return -EBADF;
+
+		l = f->f_mapping->host->i_bdev->bd_disk->private_data;
+		if (l->lo_state == Lo_unbound) {
+			return -EINVAL;
+		}
+		f = l->lo_backing_file;
+	}
+	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
+		return -EINVAL;
+	return 0;
+}
+
 /*
  * loop_change_fd switched the backing store of a loopback device to
  * a new file. This is useful for operating system installers to free up
@@ -676,14 +706,15 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	if (!file)
 		goto out;
 
+	error = loop_validate_file(file, bdev);
+	if (error)
+		goto out_putf;
+
 	inode = file->f_mapping->host;
 	old_file = lo->lo_backing_file;
 
 	error = -EINVAL;
 
-	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
-		goto out_putf;
-
 	/* size of the new backing store needs to be the same */
 	if (get_loop_size(lo, file) != get_loop_size(lo, old_file))
 		goto out_putf;
@@ -709,13 +740,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	return error;
 }
 
-static inline int is_loop_device(struct file *file)
-{
-	struct inode *i = file->f_mapping->host;
-
-	return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR;
-}
-
 /* loop sysfs attributes */
 
 static ssize_t loop_attr_show(struct device *dev, char *page,
@@ -881,7 +905,7 @@ static int loop_prepare_queue(struct loop_device *lo)
 static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 		       struct block_device *bdev, unsigned int arg)
 {
-	struct file	*file, *f;
+	struct file	*file;
 	struct inode	*inode;
 	struct address_space *mapping;
 	int		lo_flags = 0;
@@ -900,29 +924,13 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	if (lo->lo_state != Lo_unbound)
 		goto out_putf;
 
-	/* Avoid recursion */
+	error = loop_validate_file(file, bdev);
-	f = file;
+	if (error)
-	while (is_loop_device(f)) {
+		goto out_putf;
-		struct loop_device *l;
-
-		if (f->f_mapping->host->i_bdev == bdev)
-			goto out_putf;
-
-		l = f->f_mapping->host->i_bdev->bd_disk->private_data;
-		if (l->lo_state == Lo_unbound) {
-			error = -EINVAL;
-			goto out_putf;
-		}
-		f = l->lo_backing_file;
-	}
 
 	mapping = file->f_mapping;
 	inode = mapping->host;
 
-	error = -EINVAL;
-	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
-		goto out_putf;
-
 	if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) ||
 	    !file->f_op->write_iter)
 		lo_flags |= LO_FLAGS_READ_ONLY;

drivers/block/nbd.c

@@ -246,6 +246,7 @@ static void nbd_size_update(struct nbd_device *nbd)
 
 	if (config->flags & NBD_FLAG_SEND_TRIM) {
 		nbd->disk->queue->limits.discard_granularity = config->blksize;
+		nbd->disk->queue->limits.discard_alignment = config->blksize;
 		blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX);
 	}
 	blk_queue_logical_block_size(nbd->disk->queue, config->blksize);
@@ -275,7 +276,7 @@ static void nbd_complete_rq(struct request *req)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
 
-	dev_dbg(nbd_to_dev(cmd->nbd), "request %p: %s\n", cmd,
+	dev_dbg(nbd_to_dev(cmd->nbd), "request %p: %s\n", req,
 		cmd->status ? "failed" : "done");
 
 	blk_mq_end_request(req, cmd->status);
@@ -482,7 +483,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	memcpy(request.handle, &tag, sizeof(tag));
 
 	dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n",
-		cmd, nbdcmd_to_ascii(type),
+		req, nbdcmd_to_ascii(type),
 		(unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req));
 	result = sock_xmit(nbd, index, 1, &from,
 			(type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent);
@@ -518,7 +519,7 @@ send_pages:
 			int flags = is_last ? 0 : MSG_MORE;
 
 			dev_dbg(nbd_to_dev(nbd), "request %p: sending %d bytes data\n",
-				cmd, bvec.bv_len);
+				req, bvec.bv_len);
 			iov_iter_bvec(&from, ITER_BVEC | WRITE,
 				      &bvec, 1, bvec.bv_len);
 			if (skip) {
@@ -610,7 +611,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		return cmd;
 	}
 
-	dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", cmd);
+	dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", req);
 	if (rq_data_dir(req) != WRITE) {
 		struct req_iterator iter;
 		struct bio_vec bvec;
@@ -637,7 +638,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 				return ERR_PTR(-EIO);
 			}
 			dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n",
-				cmd, bvec.bv_len);
+				req, bvec.bv_len);
 		}
 	} else {
 		/* See the comment in nbd_queue_rq. */
@@ -1062,6 +1063,7 @@ static void nbd_config_put(struct nbd_device *nbd)
 
 		nbd->tag_set.timeout = 0;
 		nbd->disk->queue->limits.discard_granularity = 0;
+		nbd->disk->queue->limits.discard_alignment = 0;
 		blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX);
 		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, nbd->disk->queue);
 
@@ -1516,6 +1518,7 @@ static int nbd_dev_add(int index)
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue);
 	disk->queue->limits.discard_granularity = 0;
+	disk->queue->limits.discard_alignment = 0;
 	blk_queue_max_discard_sectors(disk->queue, 0);
 	blk_queue_max_segment_size(disk->queue, UINT_MAX);
 	blk_queue_max_segments(disk->queue, USHRT_MAX);

drivers/lightnvm/pblk-gc.c

@@ -203,7 +203,7 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
 		if (!lba_list) {
 			pr_err("pblk: could not interpret emeta (line %d)\n",
 					line->id);
-			goto fail_free_ws;
+			goto fail_free_invalid_bitmap;
 		}
 	}
 
@@ -280,6 +280,7 @@ fail_free_gc_rq:
 	kfree(gc_rq);
 fail_free_lba_list:
 	pblk_mfree(lba_list, l_mg->emeta_alloc_type);
+fail_free_invalid_bitmap:
 	kfree(invalid_bitmap);
 fail_free_ws:
 	kfree(line_ws);

drivers/lightnvm/pblk-init.c

@@ -20,7 +20,7 @@
 
 #include "pblk.h"
 
-unsigned int write_buffer_size;
+static unsigned int write_buffer_size;
 
 module_param(write_buffer_size, uint, 0644);
 MODULE_PARM_DESC(write_buffer_size, "number of entries in a write buffer");

drivers/md/dm.c

@@ -1953,9 +1953,10 @@ static void free_dev(struct mapped_device *md)
 	kvfree(md);
 }
 
-static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
+static int __bind_mempools(struct mapped_device *md, struct dm_table *t)
 {
 	struct dm_md_mempools *p = dm_table_get_md_mempools(t);
+	int ret = 0;
 
 	if (dm_table_bio_based(t)) {
 		/*
@@ -1982,13 +1983,16 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
 	       bioset_initialized(&md->bs) ||
 	       bioset_initialized(&md->io_bs));
 
-	md->bs = p->bs;
+	ret = bioset_init_from_src(&md->bs, &p->bs);
-	memset(&p->bs, 0, sizeof(p->bs));
+	if (ret)
-	md->io_bs = p->io_bs;
+		goto out;
-	memset(&p->io_bs, 0, sizeof(p->io_bs));
+	ret = bioset_init_from_src(&md->io_bs, &p->io_bs);
+	if (ret)
+		bioset_exit(&md->bs);
 out:
 	/* mempool bind completed, no longer need any mempools in the table */
 	dm_table_free_md_mempools(t);
+	return ret;
 }
 
 /*
@@ -2033,6 +2037,7 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 	struct request_queue *q = md->queue;
 	bool request_based = dm_table_request_based(t);
 	sector_t size;
+	int ret;
 
 	lockdep_assert_held(&md->suspend_lock);
 
@@ -2068,7 +2073,11 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 		md->immutable_target = dm_table_get_immutable_target(t);
 	}
 
-	__bind_mempools(md, t);
+	ret = __bind_mempools(md, t);
+	if (ret) {
+		old_map = ERR_PTR(ret);
+		goto out;
+	}
 
 	old_map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));
 	rcu_assign_pointer(md->map, (void *)t);
@@ -2078,6 +2087,7 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 	if (old_map)
 		dm_sync_table(md);
 
+out:
 	return old_map;
 }
 

drivers/md/md.c

@@ -84,6 +84,8 @@ static void autostart_arrays(int part);
 static LIST_HEAD(pers_list);
 static DEFINE_SPINLOCK(pers_lock);
 
+static struct kobj_type md_ktype;
+
 struct md_cluster_operations *md_cluster_ops;
 EXPORT_SYMBOL(md_cluster_ops);
 struct module *md_cluster_mod;
@@ -510,11 +512,6 @@ static void mddev_delayed_delete(struct work_struct *ws);
 
 static void mddev_put(struct mddev *mddev)
 {
-	struct bio_set bs, sync_bs;
-
-	memset(&bs, 0, sizeof(bs));
-	memset(&sync_bs, 0, sizeof(sync_bs));
-
 	if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))
 		return;
 	if (!mddev->raid_disks && list_empty(&mddev->disks) &&
@@ -522,30 +519,23 @@ static void mddev_put(struct mddev *mddev)
 		/* Array is not configured at all, and not held active,
 		 * so destroy it */
 		list_del_init(&mddev->all_mddevs);
-		bs = mddev->bio_set;
+
-		sync_bs = mddev->sync_set;
+		/*
-		memset(&mddev->bio_set, 0, sizeof(mddev->bio_set));
+		 * Call queue_work inside the spinlock so that
-		memset(&mddev->sync_set, 0, sizeof(mddev->sync_set));
+		 * flush_workqueue() after mddev_find will succeed in waiting
-		if (mddev->gendisk) {
+		 * for the work to be done.
-			/* We did a probe so need to clean up.  Call
+		 */
-			 * queue_work inside the spinlock so that
+		INIT_WORK(&mddev->del_work, mddev_delayed_delete);
-			 * flush_workqueue() after mddev_find will
+		queue_work(md_misc_wq, &mddev->del_work);
-			 * succeed in waiting for the work to be done.
-			 */
-			INIT_WORK(&mddev->del_work, mddev_delayed_delete);
-			queue_work(md_misc_wq, &mddev->del_work);
-		} else
-			kfree(mddev);
 	}
 	spin_unlock(&all_mddevs_lock);
-	bioset_exit(&bs);
-	bioset_exit(&sync_bs);
 }
 
 static void md_safemode_timeout(struct timer_list *t);
 
 void mddev_init(struct mddev *mddev)
 {
+	kobject_init(&mddev->kobj, &md_ktype);
 	mutex_init(&mddev->open_mutex);
 	mutex_init(&mddev->reconfig_mutex);
 	mutex_init(&mddev->bitmap_info.mutex);
@@ -5215,6 +5205,8 @@ static void md_free(struct kobject *ko)
 		put_disk(mddev->gendisk);
 	percpu_ref_exit(&mddev->writes_pending);
 
+	bioset_exit(&mddev->bio_set);
+	bioset_exit(&mddev->sync_set);
 	kfree(mddev);
 }
 
@@ -5348,8 +5340,7 @@ static int md_alloc(dev_t dev, char *name)
 	mutex_lock(&mddev->open_mutex);
 	add_disk(disk);
 
-	error = kobject_init_and_add(&mddev->kobj, &md_ktype,
+	error = kobject_add(&mddev->kobj, &disk_to_dev(disk)->kobj, "%s", "md");
-				     &disk_to_dev(disk)->kobj, "%s", "md");
 	if (error) {
 		/* This isn't possible, but as kobject_init_and_add is marked
 		 * __must_check, we must do something with the result
@@ -5506,7 +5497,7 @@ int md_run(struct mddev *mddev)
 	if (!bioset_initialized(&mddev->sync_set)) {
 		err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
 		if (err)
-			goto abort;
+			return err;
 	}
 
 	spin_lock(&pers_lock);
@@ -5519,8 +5510,7 @@ int md_run(struct mddev *mddev)
 		else
 			pr_warn("md: personality for level %s is not loaded!\n",
 				mddev->clevel);
-		err = -EINVAL;
+		return -EINVAL;
-		goto abort;
 	}
 	spin_unlock(&pers_lock);
 	if (mddev->level != pers->level) {
@@ -5533,8 +5523,7 @@ int md_run(struct mddev *mddev)
 	    pers->start_reshape == NULL) {
 		/* This personality cannot handle reshaping... */
 		module_put(pers->owner);
-		err = -EINVAL;
+		return -EINVAL;
-		goto abort;
 	}
 
 	if (pers->sync_request) {
@@ -5603,7 +5592,7 @@ int md_run(struct mddev *mddev)
 		mddev->private = NULL;
 		module_put(pers->owner);
 		bitmap_destroy(mddev);
-		goto abort;
+		return err;
 	}
 	if (mddev->queue) {
 		bool nonrot = true;
@@ -5665,12 +5654,6 @@ int md_run(struct mddev *mddev)
 	sysfs_notify_dirent_safe(mddev->sysfs_action);
 	sysfs_notify(&mddev->kobj, NULL, "degraded");
 	return 0;
-
-abort:
-	bioset_exit(&mddev->bio_set);
-	bioset_exit(&mddev->sync_set);
-
-	return err;
 }
 EXPORT_SYMBOL_GPL(md_run);
 

drivers/nvme/host/core.c

@@ -3245,7 +3245,7 @@ static void nvme_scan_work(struct work_struct *work)
 
 	WARN_ON_ONCE(!ctrl->tagset);
 
-	if (test_and_clear_bit(EVENT_NS_CHANGED, &ctrl->events)) {
+	if (test_and_clear_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) {
 		if (nvme_scan_changed_ns_log(ctrl))
 			goto out_sort_namespaces;
 		dev_info(ctrl->device, "rescanning namespaces.\n");
@@ -3386,7 +3386,7 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 {
 	switch ((result & 0xff00) >> 8) {
 	case NVME_AER_NOTICE_NS_CHANGED:
-		set_bit(EVENT_NS_CHANGED, &ctrl->events);
+		set_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events);
 		nvme_queue_scan(ctrl);
 		break;
 	case NVME_AER_NOTICE_FW_ACT_STARTING:

drivers/nvme/host/fabrics.c

@@ -952,6 +952,7 @@ nvmf_create_ctrl(struct device *dev, const char *buf, size_t count)
 		ret = -EBUSY;
 		goto out_unlock;
 	}
+	up_read(&nvmf_transports_rwsem);
 
 	ret = nvmf_check_required_opts(opts, ops->required_opts);
 	if (ret)
@@ -968,11 +969,11 @@ nvmf_create_ctrl(struct device *dev, const char *buf, size_t count)
 	}
 
 	module_put(ops->module);
-	up_read(&nvmf_transports_rwsem);
 	return ctrl;
 
 out_module_put:
 	module_put(ops->module);
+	goto out_free_opts;
 out_unlock:
 	up_read(&nvmf_transports_rwsem);
 out_free_opts:

drivers/nvme/host/fabrics.h

@@ -124,6 +124,9 @@ struct nvmf_ctrl_options {
  *	1. At minimum, 'required_opts' and 'allowed_opts' should
  *	   be set to the same enum parsing options defined earlier.
  *	2. create_ctrl() must be defined (even if it does nothing)
+ *	3. struct nvmf_transport_ops must be statically allocated in the
+ *	   modules .bss section so that a pure module_get on @module
+ *	   prevents the memory from beeing freed.
  */
 struct nvmf_transport_ops {
 	struct list_head	entry;

drivers/nvme/host/nvme.h

@@ -194,7 +194,6 @@ struct nvme_ctrl {
 	struct delayed_work ka_work;
 	struct nvme_command ka_cmd;
 	struct work_struct fw_act_work;
-#define EVENT_NS_CHANGED		(1 << 0)
 	unsigned long events;
 
 	/* Power saving configuration */

drivers/nvme/host/pci.c

@@ -42,7 +42,7 @@ static int use_threaded_interrupts;
 module_param(use_threaded_interrupts, int, 0);
 
 static bool use_cmb_sqes = true;
-module_param(use_cmb_sqes, bool, 0644);
+module_param(use_cmb_sqes, bool, 0444);
 MODULE_PARM_DESC(use_cmb_sqes, "use controller's memory buffer for I/O SQes");
 
 static unsigned int max_host_mem_size_mb = 128;
@@ -920,11 +920,9 @@ static inline void nvme_ring_cq_doorbell(struct nvme_queue *nvmeq)
 {
 	u16 head = nvmeq->cq_head;
 
-	if (likely(nvmeq->cq_vector >= 0)) {
+	if (nvme_dbbuf_update_and_check_event(head, nvmeq->dbbuf_cq_db,
-		if (nvme_dbbuf_update_and_check_event(head, nvmeq->dbbuf_cq_db,
+					      nvmeq->dbbuf_cq_ei))
-						      nvmeq->dbbuf_cq_ei))
+		writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
-			writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
-	}
 }
 
 static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
@@ -1477,11 +1475,13 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
 	 */
 	vector = dev->num_vecs == 1 ? 0 : qid;
 	result = adapter_alloc_cq(dev, qid, nvmeq, vector);
-	if (result < 0)
+	if (result)
-		goto out;
+		return result;
 
 	result = adapter_alloc_sq(dev, qid, nvmeq);
 	if (result < 0)
+		return result;
+	else if (result)
 		goto release_cq;
 
 	/*
@@ -1503,7 +1503,6 @@ release_sq:
 	adapter_delete_sq(dev, qid);
 release_cq:
 	adapter_delete_cq(dev, qid);
-out:
 	return result;
 }
 
@@ -2012,13 +2011,7 @@ static void nvme_del_cq_end(struct request *req, blk_status_t error)
 	if (!error) {
 		unsigned long flags;
 
-		/*
+		spin_lock_irqsave(&nvmeq->cq_lock, flags);
-		 * We might be called with the AQ cq_lock held
-		 * and the I/O queue cq_lock should always
-		 * nest inside the AQ one.
-		 */
-		spin_lock_irqsave_nested(&nvmeq->cq_lock, flags,
-					SINGLE_DEPTH_NESTING);
 		nvme_process_cq(nvmeq, &start, &end, -1);
 		spin_unlock_irqrestore(&nvmeq->cq_lock, flags);
 
@@ -2231,14 +2224,6 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	nvme_stop_queues(&dev->ctrl);
 
 	if (!dead && dev->ctrl.queue_count > 0) {
-		/*
-		 * If the controller is still alive tell it to stop using the
-		 * host memory buffer.  In theory the shutdown / reset should
-		 * make sure that it doesn't access the host memoery anymore,
-		 * but I'd rather be safe than sorry..
-		 */
-		if (dev->host_mem_descs)
-			nvme_set_host_mem(dev, 0);
 		nvme_disable_io_queues(dev);
 		nvme_disable_admin_queue(dev, shutdown);
 	}
@@ -2614,7 +2599,7 @@ static void nvme_remove(struct pci_dev *pdev)
 
 	if (!pci_device_is_present(pdev)) {
 		nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DEAD);
-		nvme_dev_disable(dev, false);
+		nvme_dev_disable(dev, true);
 	}
 
 	flush_work(&dev->ctrl.reset_work);

drivers/nvme/host/rdma.c

@@ -1951,8 +1951,9 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	}
 
 	/* sanity check keyed sgls */
-	if (!(ctrl->ctrl.sgls & (1 << 20))) {
+	if (!(ctrl->ctrl.sgls & (1 << 2))) {
-		dev_err(ctrl->ctrl.device, "Mandatory keyed sgls are not support\n");
+		dev_err(ctrl->ctrl.device,
+			"Mandatory keyed sgls are not supported!\n");
 		ret = -EINVAL;
 		goto out_remove_admin_queue;
 	}

drivers/nvme/target/admin-cmd.c

@@ -270,8 +270,7 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	struct nvme_id_ns *id;
 	u16 status = 0;
 
-	ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->identify.nsid);
+	if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) {
-	if (!ns) {
 		status = NVME_SC_INVALID_NS | NVME_SC_DNR;
 		goto out;
 	}
@@ -279,9 +278,14 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	id = kzalloc(sizeof(*id), GFP_KERNEL);
 	if (!id) {
 		status = NVME_SC_INTERNAL;
-		goto out_put_ns;
+		goto out;
 	}
 
+	/* return an all zeroed buffer if we can't find an active namespace */
+	ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->identify.nsid);
+	if (!ns)
+		goto done;
+
 	/*
 	 * nuse = ncap = nsze isn't always true, but we have no way to find
 	 * that out from the underlying device.
@@ -306,11 +310,10 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 
 	id->lbaf[0].ds = ns->blksize_shift;
 
-	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
-
-	kfree(id);
-out_put_ns:
 	nvmet_put_namespace(ns);
+done:
+	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
+	kfree(id);
 out:
 	nvmet_req_complete(req, status);
 }

drivers/nvme/target/configfs.c

@@ -137,8 +137,10 @@ static ssize_t nvmet_addr_traddr_store(struct config_item *item,
 		pr_err("Disable the address before modifying\n");
 		return -EACCES;
 	}
-	return snprintf(port->disc_addr.traddr,
+
-			sizeof(port->disc_addr.traddr), "%s", page);
+	if (sscanf(page, "%s\n", port->disc_addr.traddr) != 1)
+		return -EINVAL;
+	return count;
 }
 
 CONFIGFS_ATTR(nvmet_, addr_traddr);
@@ -208,8 +210,10 @@ static ssize_t nvmet_addr_trsvcid_store(struct config_item *item,
 		pr_err("Disable the address before modifying\n");
 		return -EACCES;
 	}
-	return snprintf(port->disc_addr.trsvcid,
+
-			sizeof(port->disc_addr.trsvcid), "%s", page);
+	if (sscanf(page, "%s\n", port->disc_addr.trsvcid) != 1)
+		return -EINVAL;
+	return count;
 }
 
 CONFIGFS_ATTR(nvmet_, addr_trsvcid);
@@ -288,7 +292,7 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item,
 	kfree(ns->device_path);
 
 	ret = -ENOMEM;
-	ns->device_path = kstrdup(page, GFP_KERNEL);
+	ns->device_path = kstrndup(page, strcspn(page, "\n"), GFP_KERNEL);
 	if (!ns->device_path)
 		goto out_unlock;
 

include/linux/bio.h

@@ -422,6 +422,7 @@ enum {
 extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags);
 extern void bioset_exit(struct bio_set *);
 extern int biovec_init_pool(mempool_t *pool, int pool_entries);
+extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src);
 
 extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *);
 extern void bio_put(struct bio *);