Merge tag 'for-4.16/dm-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:

 - Fix an uninitialized variable false warning in dm bufio

 - Fix DM's passthrough ioctl support to be race free against an
   underlying device being removed.

 - Fix corner-case of DM raid resync reporting if/when the raid becomes
   degraded during resync; otherwise automated raid repair will fail.

 - A few DM multipath fixes to make non-SCSI optimizations, that were
   introduced during the 4.16 merge, useful for all non-SCSI devices,
   rather than narrowly define this non-SCSI mode in terms of "nvme".

   This allows the removal of "queue_mode nvme" that really didn't need
   to be introduced. Instead DM core will internalize whether
   nvme-specific IO submission optimizations are doable and DM multipath
   will only do SCSI-specific device handler operations if SCSI is in
   use.

* tag 'for-4.16/dm-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm table: allow upgrade from bio-based to specialized bio-based variant
  dm mpath: remove unnecessary NVMe branching in favor of scsi_dh checks
  dm table: fix "nvme" test
  dm raid: fix incorrect sync_ratio when degraded
  dm: use blkdev_get rather than bdgrab when issuing pass-through ioctl
  dm bufio: avoid false-positive Wmaybe-uninitialized warning

5 files changed, 65 insertions, 75 deletions

diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 414c9af54ded..aa2032fa80d4 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -386,9 +386,6 @@ static void __cache_size_refresh(void)
 static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask,
 			       enum data_mode *data_mode)
 {
-	unsigned noio_flag;
-	void *ptr;
-
 	if (c->block_size <= DM_BUFIO_BLOCK_SIZE_SLAB_LIMIT) {
 		*data_mode = DATA_MODE_SLAB;
 		return kmem_cache_alloc(DM_BUFIO_CACHE(c), gfp_mask);
@@ -412,16 +409,15 @@ static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask,
 	 * all allocations done by this process (including pagetables) are done
 	 * as if GFP_NOIO was specified.
 	 */
+	if (gfp_mask & __GFP_NORETRY) {
+		unsigned noio_flag = memalloc_noio_save();
+		void *ptr = __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL);
 
-	if (gfp_mask & __GFP_NORETRY)
-		noio_flag = memalloc_noio_save();
-
-	ptr = __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL);
-
-	if (gfp_mask & __GFP_NORETRY)
 		memalloc_noio_restore(noio_flag);
+		return ptr;
+	}
 
-	return ptr;
+	return __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL);
 }
 
 /*
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 7d3e572072f5..3fde9e9faddd 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -22,6 +22,7 @@
 #include <linux/time.h>
 #include <linux/workqueue.h>
 #include <linux/delay.h>
+#include <scsi/scsi_device.h>
 #include <scsi/scsi_dh.h>
 #include <linux/atomic.h>
 #include <linux/blk-mq.h>
@@ -211,25 +212,13 @@ static int alloc_multipath_stage2(struct dm_target *ti, struct multipath *m)
 		else
 			m->queue_mode = DM_TYPE_REQUEST_BASED;
 
-	} else if (m->queue_mode == DM_TYPE_BIO_BASED ||
-		   m->queue_mode == DM_TYPE_NVME_BIO_BASED) {
+	} else if (m->queue_mode == DM_TYPE_BIO_BASED) {
 		INIT_WORK(&m->process_queued_bios, process_queued_bios);
-
-		if (m->queue_mode == DM_TYPE_BIO_BASED) {
-			/*
-			 * bio-based doesn't support any direct scsi_dh management;
-			 * it just discovers if a scsi_dh is attached.
-			 */
-			set_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags);
-		}
-	}
-
-	if (m->queue_mode != DM_TYPE_NVME_BIO_BASED) {
-		set_bit(MPATHF_QUEUE_IO, &m->flags);
-		atomic_set(&m->pg_init_in_progress, 0);
-		atomic_set(&m->pg_init_count, 0);
-		m->pg_init_delay_msecs = DM_PG_INIT_DELAY_DEFAULT;
-		init_waitqueue_head(&m->pg_init_wait);
+		/*
+		 * bio-based doesn't support any direct scsi_dh management;
+		 * it just discovers if a scsi_dh is attached.
+		 */
+		set_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags);
 	}
 
 	dm_table_set_type(ti->table, m->queue_mode);
@@ -337,14 +326,12 @@ static void __switch_pg(struct multipath *m, struct priority_group *pg)
 {
 	m->current_pg = pg;
 
-	if (m->queue_mode == DM_TYPE_NVME_BIO_BASED)
-		return;
-
 	/* Must we initialise the PG first, and queue I/O till it's ready? */
 	if (m->hw_handler_name) {
 		set_bit(MPATHF_PG_INIT_REQUIRED, &m->flags);
 		set_bit(MPATHF_QUEUE_IO, &m->flags);
 	} else {
+		/* FIXME: not needed if no scsi_dh is attached */
 		clear_bit(MPATHF_PG_INIT_REQUIRED, &m->flags);
 		clear_bit(MPATHF_QUEUE_IO, &m->flags);
 	}
@@ -385,8 +372,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes)
 	unsigned bypassed = 1;
 
 	if (!atomic_read(&m->nr_valid_paths)) {
-		if (m->queue_mode != DM_TYPE_NVME_BIO_BASED)
-			clear_bit(MPATHF_QUEUE_IO, &m->flags);
+		clear_bit(MPATHF_QUEUE_IO, &m->flags);
 		goto failed;
 	}
 
@@ -599,7 +585,7 @@ static struct pgpath *__map_bio(struct multipath *m, struct bio *bio)
 	return pgpath;
 }
 
-static struct pgpath *__map_bio_nvme(struct multipath *m, struct bio *bio)
+static struct pgpath *__map_bio_fast(struct multipath *m, struct bio *bio)
 {
 	struct pgpath *pgpath;
 	unsigned long flags;
@@ -634,8 +620,8 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio,
 {
 	struct pgpath *pgpath;
 
-	if (m->queue_mode == DM_TYPE_NVME_BIO_BASED)
-		pgpath = __map_bio_nvme(m, bio);
+	if (!m->hw_handler_name)
+		pgpath = __map_bio_fast(m, bio);
 	else
 		pgpath = __map_bio(m, bio);
 
@@ -675,8 +661,7 @@ static void process_queued_io_list(struct multipath *m)
 {
 	if (m->queue_mode == DM_TYPE_MQ_REQUEST_BASED)
 		dm_mq_kick_requeue_list(dm_table_get_md(m->ti->table));
-	else if (m->queue_mode == DM_TYPE_BIO_BASED ||
-		 m->queue_mode == DM_TYPE_NVME_BIO_BASED)
+	else if (m->queue_mode == DM_TYPE_BIO_BASED)
 		queue_work(kmultipathd, &m->process_queued_bios);
 }
 
@@ -838,6 +823,16 @@ retain:
 			 */
 			kfree(m->hw_handler_name);
 			m->hw_handler_name = attached_handler_name;
+
+			/*
+			 * Init fields that are only used when a scsi_dh is attached
+			 */
+			if (!test_and_set_bit(MPATHF_QUEUE_IO, &m->flags)) {
+				atomic_set(&m->pg_init_in_progress, 0);
+				atomic_set(&m->pg_init_count, 0);
+				m->pg_init_delay_msecs = DM_PG_INIT_DELAY_DEFAULT;
+				init_waitqueue_head(&m->pg_init_wait);
+			}
 		}
 	}
 
@@ -873,6 +868,7 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps
 	int r;
 	struct pgpath *p;
 	struct multipath *m = ti->private;
+	struct scsi_device *sdev;
 
 	/* we need at least a path arg */
 	if (as->argc < 1) {
@@ -891,7 +887,9 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps
 		goto bad;
 	}
 
-	if (m->queue_mode != DM_TYPE_NVME_BIO_BASED) {
+	sdev = scsi_device_from_queue(bdev_get_queue(p->path.dev->bdev));
+	if (sdev) {
+		put_device(&sdev->sdev_gendev);
 		INIT_DELAYED_WORK(&p->activate_path, activate_path_work);
 		r = setup_scsi_dh(p->path.dev->bdev, m, &ti->error);
 		if (r) {
@@ -1001,8 +999,7 @@ static int parse_hw_handler(struct dm_arg_set *as, struct multipath *m)
 	if (!hw_argc)
 		return 0;
 
-	if (m->queue_mode == DM_TYPE_BIO_BASED ||
-	    m->queue_mode == DM_TYPE_NVME_BIO_BASED) {
+	if (m->queue_mode == DM_TYPE_BIO_BASED) {
 		dm_consume_args(as, hw_argc);
 		DMERR("bio-based multipath doesn't allow hardware handler args");
 		return 0;
@@ -1091,8 +1088,6 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m)
 
 			if (!strcasecmp(queue_mode_name, "bio"))
 				m->queue_mode = DM_TYPE_BIO_BASED;
-			else if (!strcasecmp(queue_mode_name, "nvme"))
-				m->queue_mode = DM_TYPE_NVME_BIO_BASED;
 			else if (!strcasecmp(queue_mode_name, "rq"))
 				m->queue_mode = DM_TYPE_REQUEST_BASED;
 			else if (!strcasecmp(queue_mode_name, "mq"))
@@ -1193,7 +1188,7 @@ static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	ti->num_discard_bios = 1;
 	ti->num_write_same_bios = 1;
 	ti->num_write_zeroes_bios = 1;
-	if (m->queue_mode == DM_TYPE_BIO_BASED || m->queue_mode == DM_TYPE_NVME_BIO_BASED)
+	if (m->queue_mode == DM_TYPE_BIO_BASED)
 		ti->per_io_data_size = multipath_per_bio_data_size();
 	else
 		ti->per_io_data_size = sizeof(struct dm_mpath_io);
@@ -1730,9 +1725,6 @@ static void multipath_status(struct dm_target *ti, status_type_t type,
 			case DM_TYPE_BIO_BASED:
 				DMEMIT("queue_mode bio ");
 				break;
-			case DM_TYPE_NVME_BIO_BASED:
-				DMEMIT("queue_mode nvme ");
-				break;
 			case DM_TYPE_MQ_REQUEST_BASED:
 				DMEMIT("queue_mode mq ");
 				break;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 7ef469e902c6..c1d1034ff7b7 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3408,9 +3408,10 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
 		set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
 
 	} else {
-		if (test_bit(MD_RECOVERY_NEEDED, &recovery) ||
-		    test_bit(MD_RECOVERY_RESHAPE, &recovery) ||
-		    test_bit(MD_RECOVERY_RUNNING, &recovery))
+		if (!test_bit(MD_RECOVERY_INTR, &recovery) &&
+		    (test_bit(MD_RECOVERY_NEEDED, &recovery) ||
+		     test_bit(MD_RECOVERY_RESHAPE, &recovery) ||
+		     test_bit(MD_RECOVERY_RUNNING, &recovery)))
 			r = mddev->curr_resync_completed;
 		else
 			r = mddev->recovery_cp;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 5fe7ec356c33..7eb3e2a3c07d 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -942,17 +942,12 @@ static int dm_table_determine_type(struct dm_table *t)
 
 	if (t->type != DM_TYPE_NONE) {
 		/* target already set the table's type */
-		if (t->type == DM_TYPE_BIO_BASED)
-			return 0;
-		else if (t->type == DM_TYPE_NVME_BIO_BASED) {
-			if (!dm_table_does_not_support_partial_completion(t)) {
-				DMERR("nvme bio-based is only possible with devices"
-				      " that don't support partial completion");
-				return -EINVAL;
-			}
-			/* Fallthru, also verify all devices are blk-mq */
+		if (t->type == DM_TYPE_BIO_BASED) {
+			/* possibly upgrade to a variant of bio-based */
+			goto verify_bio_based;
 		}
 		BUG_ON(t->type == DM_TYPE_DAX_BIO_BASED);
+		BUG_ON(t->type == DM_TYPE_NVME_BIO_BASED);
 		goto verify_rq_based;
 	}
 
@@ -985,6 +980,7 @@ static int dm_table_determine_type(struct dm_table *t)
 	}
 
 	if (bio_based) {
+verify_bio_based:
 		/* We must use this table as bio-based */
 		t->type = DM_TYPE_BIO_BASED;
 		if (dm_table_supports_dax(t) ||
@@ -1755,7 +1751,7 @@ static int device_no_partial_completion(struct dm_target *ti, struct dm_dev *dev
 	char b[BDEVNAME_SIZE];
 
 	/* For now, NVMe devices are the only devices of this class */
-	return (strncmp(bdevname(dev->bdev, b), "nvme", 3) == 0);
+	return (strncmp(bdevname(dev->bdev, b), "nvme", 4) == 0);
 }
 
 static bool dm_table_does_not_support_partial_completion(struct dm_table *t)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 68136806d365..45328d8b2859 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -458,9 +458,11 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return dm_get_geometry(md, geo);
 }
 
-static int dm_grab_bdev_for_ioctl(struct mapped_device *md,
-				  struct block_device **bdev,
-				  fmode_t *mode)
+static char *_dm_claim_ptr = "I belong to device-mapper";
+
+static int dm_get_bdev_for_ioctl(struct mapped_device *md,
+				 struct block_device **bdev,
+				 fmode_t *mode)
 {
 	struct dm_target *tgt;
 	struct dm_table *map;
@@ -490,6 +492,10 @@ retry:
 		goto out;
 
 	bdgrab(*bdev);
+	r = blkdev_get(*bdev, *mode, _dm_claim_ptr);
+	if (r < 0)
+		goto out;
+
 	dm_put_live_table(md, srcu_idx);
 	return r;
 
@@ -508,7 +514,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 	struct mapped_device *md = bdev->bd_disk->private_data;
 	int r;
 
-	r = dm_grab_bdev_for_ioctl(md, &bdev, &mode);
+	r = dm_get_bdev_for_ioctl(md, &bdev, &mode);
 	if (r < 0)
 		return r;
 
@@ -528,7 +534,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 
 	r =  __blkdev_driver_ioctl(bdev, mode, cmd, arg);
 out:
-	bdput(bdev);
+	blkdev_put(bdev, mode);
 	return r;
 }
 
@@ -708,14 +714,13 @@ static void dm_put_live_table_fast(struct mapped_device *md) __releases(RCU)
 static int open_table_device(struct table_device *td, dev_t dev,
 			     struct mapped_device *md)
 {
-	static char *_claim_ptr = "I belong to device-mapper";
 	struct block_device *bdev;
 
 	int r;
 
 	BUG_ON(td->dm_dev.bdev);
 
-	bdev = blkdev_get_by_dev(dev, td->dm_dev.mode | FMODE_EXCL, _claim_ptr);
+	bdev = blkdev_get_by_dev(dev, td->dm_dev.mode | FMODE_EXCL, _dm_claim_ptr);
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
 
@@ -3011,7 +3016,7 @@ static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
 	fmode_t mode;
 	int r;
 
-	r = dm_grab_bdev_for_ioctl(md, &bdev, &mode);
+	r = dm_get_bdev_for_ioctl(md, &bdev, &mode);
 	if (r < 0)
 		return r;
 
@@ -3021,7 +3026,7 @@ static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
 	else
 		r = -EOPNOTSUPP;
 
-	bdput(bdev);
+	blkdev_put(bdev, mode);
 	return r;
 }
 
@@ -3032,7 +3037,7 @@ static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
 	fmode_t mode;
 	int r;
 
-	r = dm_grab_bdev_for_ioctl(md, &bdev, &mode);
+	r = dm_get_bdev_for_ioctl(md, &bdev, &mode);
 	if (r < 0)
 		return r;
 
@@ -3042,7 +3047,7 @@ static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
 	else
 		r = -EOPNOTSUPP;
 
-	bdput(bdev);
+	blkdev_put(bdev, mode);
 	return r;
 }
 
@@ -3054,7 +3059,7 @@ static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key,
 	fmode_t mode;
 	int r;
 
-	r = dm_grab_bdev_for_ioctl(md, &bdev, &mode);
+	r = dm_get_bdev_for_ioctl(md, &bdev, &mode);
 	if (r < 0)
 		return r;
 
@@ -3064,7 +3069,7 @@ static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key,
 	else
 		r = -EOPNOTSUPP;
 
-	bdput(bdev);
+	blkdev_put(bdev, mode);
 	return r;
 }
 
@@ -3075,7 +3080,7 @@ static int dm_pr_clear(struct block_device *bdev, u64 key)
 	fmode_t mode;
 	int r;
 
-	r = dm_grab_bdev_for_ioctl(md, &bdev, &mode);
+	r = dm_get_bdev_for_ioctl(md, &bdev, &mode);
 	if (r < 0)
 		return r;
 
@@ -3085,7 +3090,7 @@ static int dm_pr_clear(struct block_device *bdev, u64 key)
 	else
 		r = -EOPNOTSUPP;
 
-	bdput(bdev);
+	blkdev_put(bdev, mode);
 	return r;
 }