Merge tag 'v4.0-rc2' into irq/core, to refresh the tree before applying new changes

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

18 files changed, 1157 insertions, 866 deletions

diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 014a1cfc41c5..1b8094d4d7af 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -393,14 +393,15 @@ config BLK_DEV_RAM_SIZE
 	  The default value is 4096 kilobytes. Only change this if you know
 	  what you are doing.
 
-config BLK_DEV_XIP
-	bool "Support XIP filesystems on RAM block device"
-	depends on BLK_DEV_RAM
+config BLK_DEV_RAM_DAX
+	bool "Support Direct Access (DAX) to RAM block devices"
+	depends on BLK_DEV_RAM && FS_DAX
 	default n
 	help
-	  Support XIP filesystems (such as ext2 with XIP support on) on
-	  top of block ram device. This will slightly enlarge the kernel, and
-	  will prevent RAM block device backing store memory from being
+	  Support filesystems using DAX to access RAM block devices.  This
+	  avoids double-buffering data in the page cache before copying it
+	  to the block device.  Answering Y will slightly enlarge the kernel,
+	  and will prevent RAM block device backing store memory from being
 	  allocated from highmem (only a problem for highmem systems).
 
 config CDROM_PKTCDVD
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 3598110d2cef..64ab4951e9d6 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -97,13 +97,13 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector)
 	 * Must use NOIO because we don't want to recurse back into the
 	 * block or filesystem layers from page reclaim.
 	 *
-	 * Cannot support XIP and highmem, because our ->direct_access
-	 * routine for XIP must return memory that is always addressable.
-	 * If XIP was reworked to use pfns and kmap throughout, this
+	 * Cannot support DAX and highmem, because our ->direct_access
+	 * routine for DAX must return memory that is always addressable.
+	 * If DAX was reworked to use pfns and kmap throughout, this
 	 * restriction might be able to be lifted.
 	 */
 	gfp_flags = GFP_NOIO | __GFP_ZERO;
-#ifndef CONFIG_BLK_DEV_XIP
+#ifndef CONFIG_BLK_DEV_RAM_DAX
 	gfp_flags |= __GFP_HIGHMEM;
 #endif
 	page = alloc_page(gfp_flags);
@@ -369,27 +369,29 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
 	return err;
 }
 
-#ifdef CONFIG_BLK_DEV_XIP
-static int brd_direct_access(struct block_device *bdev, sector_t sector,
-			void **kaddr, unsigned long *pfn)
+#ifdef CONFIG_BLK_DEV_RAM_DAX
+static long brd_direct_access(struct block_device *bdev, sector_t sector,
+			void **kaddr, unsigned long *pfn, long size)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	struct page *page;
 
 	if (!brd)
 		return -ENODEV;
-	if (sector & (PAGE_SECTORS-1))
-		return -EINVAL;
-	if (sector + PAGE_SECTORS > get_capacity(bdev->bd_disk))
-		return -ERANGE;
 	page = brd_insert_page(brd, sector);
 	if (!page)
 		return -ENOSPC;
 	*kaddr = page_address(page);
 	*pfn = page_to_pfn(page);
 
-	return 0;
+	/*
+	 * TODO: If size > PAGE_SIZE, we could look to see if the next page in
+	 * the file happens to be mapped to the next page of physical RAM.
+	 */
+	return PAGE_SIZE;
 }
+#else
+#define brd_direct_access NULL
 #endif
 
 static int brd_ioctl(struct block_device *bdev, fmode_t mode,
@@ -430,27 +432,24 @@ static const struct block_device_operations brd_fops = {
 	.owner =		THIS_MODULE,
 	.rw_page =		brd_rw_page,
 	.ioctl =		brd_ioctl,
-#ifdef CONFIG_BLK_DEV_XIP
 	.direct_access =	brd_direct_access,
-#endif
 };
 
 /*
  * And now the modules code and kernel interface.
  */
-static int rd_nr;
-int rd_size = CONFIG_BLK_DEV_RAM_SIZE;
-static int max_part;
-static int part_shift;
-static int part_show = 0;
+static int rd_nr = CONFIG_BLK_DEV_RAM_COUNT;
 module_param(rd_nr, int, S_IRUGO);
 MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices");
+
+int rd_size = CONFIG_BLK_DEV_RAM_SIZE;
 module_param(rd_size, int, S_IRUGO);
 MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes.");
+
+static int max_part = 1;
 module_param(max_part, int, S_IRUGO);
-MODULE_PARM_DESC(max_part, "Maximum number of partitions per RAM disk");
-module_param(part_show, int, S_IRUGO);
-MODULE_PARM_DESC(part_show, "Control RAM disk visibility in /proc/partitions");
+MODULE_PARM_DESC(max_part, "Num Minors to reserve between devices");
+
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(RAMDISK_MAJOR);
 MODULE_ALIAS("rd");
@@ -487,25 +486,33 @@ static struct brd_device *brd_alloc(int i)
 	brd->brd_queue = blk_alloc_queue(GFP_KERNEL);
 	if (!brd->brd_queue)
 		goto out_free_dev;
+
 	blk_queue_make_request(brd->brd_queue, brd_make_request);
 	blk_queue_max_hw_sectors(brd->brd_queue, 1024);
 	blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);
 
+	/* This is so fdisk will align partitions on 4k, because of
+	 * direct_access API needing 4k alignment, returning a PFN
+	 * (This is only a problem on very small devices <= 4M,
+	 *  otherwise fdisk will align on 1M. Regardless this call
+	 *  is harmless)
+	 */
+	blk_queue_physical_block_size(brd->brd_queue, PAGE_SIZE);
+
 	brd->brd_queue->limits.discard_granularity = PAGE_SIZE;
 	brd->brd_queue->limits.max_discard_sectors = UINT_MAX;
 	brd->brd_queue->limits.discard_zeroes_data = 1;
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, brd->brd_queue);
 
-	disk = brd->brd_disk = alloc_disk(1 << part_shift);
+	disk = brd->brd_disk = alloc_disk(max_part);
 	if (!disk)
 		goto out_free_queue;
 	disk->major		= RAMDISK_MAJOR;
-	disk->first_minor	= i << part_shift;
+	disk->first_minor	= i * max_part;
 	disk->fops		= &brd_fops;
 	disk->private_data	= brd;
 	disk->queue		= brd->brd_queue;
-	if (!part_show)
-		disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
+	disk->flags		= GENHD_FL_EXT_DEVT;
 	sprintf(disk->disk_name, "ram%d", i);
 	set_capacity(disk, rd_size * 2);
 
@@ -527,10 +534,11 @@ static void brd_free(struct brd_device *brd)
 	kfree(brd);
 }
 
-static struct brd_device *brd_init_one(int i)
+static struct brd_device *brd_init_one(int i, bool *new)
 {
 	struct brd_device *brd;
 
+	*new = false;
 	list_for_each_entry(brd, &brd_devices, brd_list) {
 		if (brd->brd_number == i)
 			goto out;
@@ -541,6 +549,7 @@ static struct brd_device *brd_init_one(int i)
 		add_disk(brd->brd_disk);
 		list_add_tail(&brd->brd_list, &brd_devices);
 	}
+	*new = true;
 out:
 	return brd;
 }
@@ -556,70 +565,46 @@ static struct kobject *brd_probe(dev_t dev, int *part, void *data)
 {
 	struct brd_device *brd;
 	struct kobject *kobj;
+	bool new;
 
 	mutex_lock(&brd_devices_mutex);
-	brd = brd_init_one(MINOR(dev) >> part_shift);
+	brd = brd_init_one(MINOR(dev) / max_part, &new);
 	kobj = brd ? get_disk(brd->brd_disk) : NULL;
 	mutex_unlock(&brd_devices_mutex);
 
-	*part = 0;
+	if (new)
+		*part = 0;
+
 	return kobj;
 }
 
 static int __init brd_init(void)
 {
-	int i, nr;
-	unsigned long range;
 	struct brd_device *brd, *next;
+	int i;
 
 	/*
 	 * brd module now has a feature to instantiate underlying device
 	 * structure on-demand, provided that there is an access dev node.
-	 * However, this will not work well with user space tool that doesn't
-	 * know about such "feature".  In order to not break any existing
-	 * tool, we do the following:
 	 *
-	 * (1) if rd_nr is specified, create that many upfront, and this
-	 *     also becomes a hard limit.
-	 * (2) if rd_nr is not specified, create CONFIG_BLK_DEV_RAM_COUNT
-	 *     (default 16) rd device on module load, user can further
-	 *     extend brd device by create dev node themselves and have
-	 *     kernel automatically instantiate actual device on-demand.
+	 * (1) if rd_nr is specified, create that many upfront. else
+	 *     it defaults to CONFIG_BLK_DEV_RAM_COUNT
+	 * (2) User can further extend brd devices by create dev node themselves
+	 *     and have kernel automatically instantiate actual device
+	 *     on-demand. Example:
+	 *		mknod /path/devnod_name b 1 X	# 1 is the rd major
+	 *		fdisk -l /path/devnod_name
+	 *	If (X / max_part) was not already created it will be created
+	 *	dynamically.
 	 */
 
-	part_shift = 0;
-	if (max_part > 0) {
-		part_shift = fls(max_part);
-
-		/*
-		 * Adjust max_part according to part_shift as it is exported
-		 * to user space so that user can decide correct minor number
-		 * if [s]he want to create more devices.
-		 *
-		 * Note that -1 is required because partition 0 is reserved
-		 * for the whole disk.
-		 */
-		max_part = (1UL << part_shift) - 1;
-	}
-
-	if ((1UL << part_shift) > DISK_MAX_PARTS)
-		return -EINVAL;
-
-	if (rd_nr > 1UL << (MINORBITS - part_shift))
-		return -EINVAL;
-
-	if (rd_nr) {
-		nr = rd_nr;
-		range = rd_nr << part_shift;
-	} else {
-		nr = CONFIG_BLK_DEV_RAM_COUNT;
-		range = 1UL << MINORBITS;
-	}
-
 	if (register_blkdev(RAMDISK_MAJOR, "ramdisk"))
 		return -EIO;
 
-	for (i = 0; i < nr; i++) {
+	if (unlikely(!max_part))
+		max_part = 1;
+
+	for (i = 0; i < rd_nr; i++) {
 		brd = brd_alloc(i);
 		if (!brd)
 			goto out_free;
@@ -631,10 +616,10 @@ static int __init brd_init(void)
 	list_for_each_entry(brd, &brd_devices, brd_list)
 		add_disk(brd->brd_disk);
 
-	blk_register_region(MKDEV(RAMDISK_MAJOR, 0), range,
+	blk_register_region(MKDEV(RAMDISK_MAJOR, 0), 1UL << MINORBITS,
 				  THIS_MODULE, brd_probe, NULL, NULL);
 
-	printk(KERN_INFO "brd: module loaded\n");
+	pr_info("brd: module loaded\n");
 	return 0;
 
 out_free:
@@ -644,21 +629,21 @@ out_free:
 	}
 	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
 
+	pr_info("brd: module NOT loaded !!!\n");
 	return -ENOMEM;
 }
 
 static void __exit brd_exit(void)
 {
-	unsigned long range;
 	struct brd_device *brd, *next;
 
-	range = rd_nr ? rd_nr << part_shift : 1UL << MINORBITS;
-
 	list_for_each_entry_safe(brd, next, &brd_devices, brd_list)
 		brd_del_one(brd);
 
-	blk_unregister_region(MKDEV(RAMDISK_MAJOR, 0), range);
+	blk_unregister_region(MKDEV(RAMDISK_MAJOR, 0), 1UL << MINORBITS);
 	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
+
+	pr_info("brd: module unloaded\n");
 }
 
 module_init(brd_init);
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index d169b4a79267..cee20354ac37 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1388,7 +1388,7 @@ int drbd_submit_peer_request(struct drbd_device *device,
 		list_add_tail(&peer_req->w.list, &device->active_ee);
 		spin_unlock_irq(&device->resource->req_lock);
 		if (blkdev_issue_zeroout(device->ldev->backing_bdev,
-			sector, data_size >> 9, GFP_NOIO))
+			sector, data_size >> 9, GFP_NOIO, false))
 			peer_req->flags |= EE_WAS_ERROR;
 		drbd_endio_write_sec_final(peer_req);
 		return 0;
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 56d46ffb08e1..a08cda955285 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -4112,6 +4112,13 @@ static ssize_t floppy_cmos_show(struct device *dev,
 
 static DEVICE_ATTR(cmos, S_IRUGO, floppy_cmos_show, NULL);
 
+static struct attribute *floppy_dev_attrs[] = {
+	&dev_attr_cmos.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(floppy_dev);
+
 static void floppy_device_release(struct device *dev)
 {
 }
@@ -4324,16 +4331,12 @@ static int __init do_floppy_init(void)
 		floppy_device[drive].name = floppy_device_name;
 		floppy_device[drive].id = drive;
 		floppy_device[drive].dev.release = floppy_device_release;
+		floppy_device[drive].dev.groups = floppy_dev_groups;
 
 		err = platform_device_register(&floppy_device[drive]);
 		if (err)
 			goto out_remove_drives;
 
-		err = device_create_file(&floppy_device[drive].dev,
-					 &dev_attr_cmos);
-		if (err)
-			goto out_unreg_platform_dev;
-
 		/* to be cleaned up... */
 		disks[drive]->private_data = (void *)(long)drive;
 		disks[drive]->flags |= GENHD_FL_REMOVABLE;
@@ -4343,13 +4346,10 @@ static int __init do_floppy_init(void)
 
 	return 0;
 
-out_unreg_platform_dev:
-	platform_device_unregister(&floppy_device[drive]);
 out_remove_drives:
 	while (drive--) {
 		if (floppy_available(drive)) {
 			del_gendisk(disks[drive]);
-			device_remove_file(&floppy_device[drive].dev, &dev_attr_cmos);
 			platform_device_unregister(&floppy_device[drive]);
 		}
 	}
@@ -4594,7 +4594,6 @@ static void __exit floppy_module_exit(void)
 
 		if (floppy_available(drive)) {
 			del_gendisk(disks[drive]);
-			device_remove_file(&floppy_device[drive].dev, &dev_attr_cmos);
 			platform_device_unregister(&floppy_device[drive]);
 		}
 		blk_cleanup_queue(disks[drive]->queue);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 6cb1beb47c25..d1f168b73634 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -85,6 +85,8 @@ static DEFINE_MUTEX(loop_index_mutex);
 static int max_part;
 static int part_shift;
 
+static struct workqueue_struct *loop_wq;
+
 /*
  * Transfer functions
  */
@@ -284,12 +286,12 @@ static int do_lo_send_write(struct loop_device *lo, struct bio_vec *bvec,
 	return ret;
 }
 
-static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
+static int lo_send(struct loop_device *lo, struct request *rq, loff_t pos)
 {
 	int (*do_lo_send)(struct loop_device *, struct bio_vec *, loff_t,
 			struct page *page);
 	struct bio_vec bvec;
-	struct bvec_iter iter;
+	struct req_iterator iter;
 	struct page *page = NULL;
 	int ret = 0;
 
@@ -303,7 +305,7 @@ static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
 		do_lo_send = do_lo_send_direct_write;
 	}
 
-	bio_for_each_segment(bvec, bio, iter) {
+	rq_for_each_segment(bvec, rq, iter) {
 		ret = do_lo_send(lo, &bvec, pos, page);
 		if (ret < 0)
 			break;
@@ -391,19 +393,22 @@ do_lo_receive(struct loop_device *lo,
 }
 
 static int
-lo_receive(struct loop_device *lo, struct bio *bio, int bsize, loff_t pos)
+lo_receive(struct loop_device *lo, struct request *rq, int bsize, loff_t pos)
 {
 	struct bio_vec bvec;
-	struct bvec_iter iter;
+	struct req_iterator iter;
 	ssize_t s;
 
-	bio_for_each_segment(bvec, bio, iter) {
+	rq_for_each_segment(bvec, rq, iter) {
 		s = do_lo_receive(lo, &bvec, bsize, pos);
 		if (s < 0)
 			return s;
 
 		if (s != bvec.bv_len) {
-			zero_fill_bio(bio);
+			struct bio *bio;
+
+			__rq_for_each_bio(bio, rq)
+				zero_fill_bio(bio);
 			break;
 		}
 		pos += bvec.bv_len;
@@ -411,106 +416,58 @@ lo_receive(struct loop_device *lo, struct bio *bio, int bsize, loff_t pos)
 	return 0;
 }
 
-static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
+static int lo_discard(struct loop_device *lo, struct request *rq, loff_t pos)
 {
-	loff_t pos;
+	/*
+	 * We use punch hole to reclaim the free space used by the
+	 * image a.k.a. discard. However we do not support discard if
+	 * encryption is enabled, because it may give an attacker
+	 * useful information.
+	 */
+	struct file *file = lo->lo_backing_file;
+	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
 	int ret;
 
-	pos = ((loff_t) bio->bi_iter.bi_sector << 9) + lo->lo_offset;
-
-	if (bio_rw(bio) == WRITE) {
-		struct file *file = lo->lo_backing_file;
-
-		if (bio->bi_rw & REQ_FLUSH) {
-			ret = vfs_fsync(file, 0);
-			if (unlikely(ret && ret != -EINVAL)) {
-				ret = -EIO;
-				goto out;
-			}
-		}
-
-		/*
-		 * We use punch hole to reclaim the free space used by the
-		 * image a.k.a. discard. However we do not support discard if
-		 * encryption is enabled, because it may give an attacker
-		 * useful information.
-		 */
-		if (bio->bi_rw & REQ_DISCARD) {
-			struct file *file = lo->lo_backing_file;
-			int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
-
-			if ((!file->f_op->fallocate) ||
-			    lo->lo_encrypt_key_size) {
-				ret = -EOPNOTSUPP;
-				goto out;
-			}
-			ret = file->f_op->fallocate(file, mode, pos,
-						    bio->bi_iter.bi_size);
-			if (unlikely(ret && ret != -EINVAL &&
-				     ret != -EOPNOTSUPP))
-				ret = -EIO;
-			goto out;
-		}
-
-		ret = lo_send(lo, bio, pos);
-
-		if ((bio->bi_rw & REQ_FUA) && !ret) {
-			ret = vfs_fsync(file, 0);
-			if (unlikely(ret && ret != -EINVAL))
-				ret = -EIO;
-		}
-	} else
-		ret = lo_receive(lo, bio, lo->lo_blocksize, pos);
+	if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
 
-out:
+	ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq));
+	if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP))
+		ret = -EIO;
+ out:
 	return ret;
 }
 
-/*
- * Add bio to back of pending list
- */
-static void loop_add_bio(struct loop_device *lo, struct bio *bio)
+static int lo_req_flush(struct loop_device *lo, struct request *rq)
 {
-	lo->lo_bio_count++;
-	bio_list_add(&lo->lo_bio_list, bio);
-}
+	struct file *file = lo->lo_backing_file;
+	int ret = vfs_fsync(file, 0);
+	if (unlikely(ret && ret != -EINVAL))
+		ret = -EIO;
 
-/*
- * Grab first pending buffer
- */
-static struct bio *loop_get_bio(struct loop_device *lo)
-{
-	lo->lo_bio_count--;
-	return bio_list_pop(&lo->lo_bio_list);
+	return ret;
 }
 
-static void loop_make_request(struct request_queue *q, struct bio *old_bio)
+static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 {
-	struct loop_device *lo = q->queuedata;
-	int rw = bio_rw(old_bio);
-
-	if (rw == READA)
-		rw = READ;
+	loff_t pos;
+	int ret;
 
-	BUG_ON(!lo || (rw != READ && rw != WRITE));
+	pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset;
 
-	spin_lock_irq(&lo->lo_lock);
-	if (lo->lo_state != Lo_bound)
-		goto out;
-	if (unlikely(rw == WRITE && (lo->lo_flags & LO_FLAGS_READ_ONLY)))
-		goto out;
-	if (lo->lo_bio_count >= q->nr_congestion_on)
-		wait_event_lock_irq(lo->lo_req_wait,
-				    lo->lo_bio_count < q->nr_congestion_off,
-				    lo->lo_lock);
-	loop_add_bio(lo, old_bio);
-	wake_up(&lo->lo_event);
-	spin_unlock_irq(&lo->lo_lock);
-	return;
+	if (rq->cmd_flags & REQ_WRITE) {
+		if (rq->cmd_flags & REQ_FLUSH)
+			ret = lo_req_flush(lo, rq);
+		else if (rq->cmd_flags & REQ_DISCARD)
+			ret = lo_discard(lo, rq, pos);
+		else
+			ret = lo_send(lo, rq, pos);
+	} else
+		ret = lo_receive(lo, rq, lo->lo_blocksize, pos);
 
-out:
-	spin_unlock_irq(&lo->lo_lock);
-	bio_io_error(old_bio);
+	return ret;
 }
 
 struct switch_request {
@@ -518,57 +475,26 @@ struct switch_request {
 	struct completion wait;
 };
 
-static void do_loop_switch(struct loop_device *, struct switch_request *);
-
-static inline void loop_handle_bio(struct loop_device *lo, struct bio *bio)
-{
-	if (unlikely(!bio->bi_bdev)) {
-		do_loop_switch(lo, bio->bi_private);
-		bio_put(bio);
-	} else {
-		int ret = do_bio_filebacked(lo, bio);
-		bio_endio(bio, ret);
-	}
-}
-
 /*
- * worker thread that handles reads/writes to file backed loop devices,
- * to avoid blocking in our make_request_fn. it also does loop decrypting
- * on reads for block backed loop, as that is too heavy to do from
- * b_end_io context where irqs may be disabled.
- *
- * Loop explanation:  loop_clr_fd() sets lo_state to Lo_rundown before
- * calling kthread_stop().  Therefore once kthread_should_stop() is
- * true, make_request will not place any more requests.  Therefore
- * once kthread_should_stop() is true and lo_bio is NULL, we are
- * done with the loop.
+ * Do the actual switch; called from the BIO completion routine
  */
-static int loop_thread(void *data)
+static void do_loop_switch(struct loop_device *lo, struct switch_request *p)
 {
-	struct loop_device *lo = data;
-	struct bio *bio;
-
-	set_user_nice(current, MIN_NICE);
-
-	while (!kthread_should_stop() || !bio_list_empty(&lo->lo_bio_list)) {
-
-		wait_event_interruptible(lo->lo_event,
-				!bio_list_empty(&lo->lo_bio_list) ||
-				kthread_should_stop());
-
-		if (bio_list_empty(&lo->lo_bio_list))
-			continue;
-		spin_lock_irq(&lo->lo_lock);
-		bio = loop_get_bio(lo);
-		if (lo->lo_bio_count < lo->lo_queue->nr_congestion_off)
-			wake_up(&lo->lo_req_wait);
-		spin_unlock_irq(&lo->lo_lock);
+	struct file *file = p->file;
+	struct file *old_file = lo->lo_backing_file;
+	struct address_space *mapping;
 
-		BUG_ON(!bio);
-		loop_handle_bio(lo, bio);
-	}
+	/* if no new file, only flush of queued bios requested */
+	if (!file)
+		return;
 
-	return 0;
+	mapping = file->f_mapping;
+	mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
+	lo->lo_backing_file = file;
+	lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ?
+		mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
+	lo->old_gfp_mask = mapping_gfp_mask(mapping);
+	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 }
 
 /*
@@ -579,15 +505,18 @@ static int loop_thread(void *data)
 static int loop_switch(struct loop_device *lo, struct file *file)
 {
 	struct switch_request w;
-	struct bio *bio = bio_alloc(GFP_KERNEL, 0);
-	if (!bio)
-		return -ENOMEM;
-	init_completion(&w.wait);
+
 	w.file = file;
-	bio->bi_private = &w;
-	bio->bi_bdev = NULL;
-	loop_make_request(lo->lo_queue, bio);
-	wait_for_completion(&w.wait);
+
+	/* freeze queue and wait for completion of scheduled requests */
+	blk_mq_freeze_queue(lo->lo_queue);
+
+	/* do the switch action */
+	do_loop_switch(lo, &w);
+
+	/* unfreeze */
+	blk_mq_unfreeze_queue(lo->lo_queue);
+
 	return 0;
 }
 
@@ -596,39 +525,10 @@ static int loop_switch(struct loop_device *lo, struct file *file)
  */
 static int loop_flush(struct loop_device *lo)
 {
-	/* loop not yet configured, no running thread, nothing to flush */
-	if (!lo->lo_thread)
-		return 0;
-
 	return loop_switch(lo, NULL);
 }
 
 /*
- * Do the actual switch; called from the BIO completion routine
- */
-static void do_loop_switch(struct loop_device *lo, struct switch_request *p)
-{
-	struct file *file = p->file;
-	struct file *old_file = lo->lo_backing_file;
-	struct address_space *mapping;
-
-	/* if no new file, only flush of queued bios requested */
-	if (!file)
-		goto out;
-
-	mapping = file->f_mapping;
-	mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
-	lo->lo_backing_file = file;
-	lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ?
-		mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
-	lo->old_gfp_mask = mapping_gfp_mask(mapping);
-	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
-out:
-	complete(&p->wait);
-}
-
-
-/*
  * 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
  * the original file and in High Availability environments to switch to
@@ -889,12 +789,9 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	lo->transfer = transfer_none;
 	lo->ioctl = NULL;
 	lo->lo_sizelimit = 0;
-	lo->lo_bio_count = 0;
 	lo->old_gfp_mask = mapping_gfp_mask(mapping);
 	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 
-	bio_list_init(&lo->lo_bio_list);
-
 	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
 		blk_queue_flush(lo->lo_queue, REQ_FLUSH);
 
@@ -906,14 +803,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 
 	set_blocksize(bdev, lo_blocksize);
 
-	lo->lo_thread = kthread_create(loop_thread, lo, "loop%d",
-						lo->lo_number);
-	if (IS_ERR(lo->lo_thread)) {
-		error = PTR_ERR(lo->lo_thread);
-		goto out_clr;
-	}
 	lo->lo_state = Lo_bound;
-	wake_up_process(lo->lo_thread);
 	if (part_shift)
 		lo->lo_flags |= LO_FLAGS_PARTSCAN;
 	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
@@ -925,18 +815,6 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	bdgrab(bdev);
 	return 0;
 
-out_clr:
-	loop_sysfs_exit(lo);
-	lo->lo_thread = NULL;
-	lo->lo_device = NULL;
-	lo->lo_backing_file = NULL;
-	lo->lo_flags = 0;
-	set_capacity(lo->lo_disk, 0);
-	invalidate_bdev(bdev);
-	bd_set_size(bdev, 0);
-	kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
-	mapping_set_gfp_mask(mapping, lo->old_gfp_mask);
-	lo->lo_state = Lo_unbound;
  out_putf:
 	fput(file);
  out:
@@ -1012,11 +890,6 @@ static int loop_clr_fd(struct loop_device *lo)
 
 	spin_lock_irq(&lo->lo_lock);
 	lo->lo_state = Lo_rundown;
-	spin_unlock_irq(&lo->lo_lock);
-
-	kthread_stop(lo->lo_thread);
-
-	spin_lock_irq(&lo->lo_lock);
 	lo->lo_backing_file = NULL;
 	spin_unlock_irq(&lo->lo_lock);
 
@@ -1028,7 +901,6 @@ static int loop_clr_fd(struct loop_device *lo)
 	lo->lo_offset = 0;
 	lo->lo_sizelimit = 0;
 	lo->lo_encrypt_key_size = 0;
-	lo->lo_thread = NULL;
 	memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
 	memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
 	memset(lo->lo_file_name, 0, LO_NAME_SIZE);
@@ -1601,6 +1473,105 @@ int loop_unregister_transfer(int number)
 EXPORT_SYMBOL(loop_register_transfer);
 EXPORT_SYMBOL(loop_unregister_transfer);
 
+static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
+		const struct blk_mq_queue_data *bd)
+{
+	struct loop_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
+
+	blk_mq_start_request(bd->rq);
+
+	if (cmd->rq->cmd_flags & REQ_WRITE) {
+		struct loop_device *lo = cmd->rq->q->queuedata;
+		bool need_sched = true;
+
+		spin_lock_irq(&lo->lo_lock);
+		if (lo->write_started)
+			need_sched = false;
+		else
+			lo->write_started = true;
+		list_add_tail(&cmd->list, &lo->write_cmd_head);
+		spin_unlock_irq(&lo->lo_lock);
+
+		if (need_sched)
+			queue_work(loop_wq, &lo->write_work);
+	} else {
+		queue_work(loop_wq, &cmd->read_work);
+	}
+
+	return BLK_MQ_RQ_QUEUE_OK;
+}
+
+static void loop_handle_cmd(struct loop_cmd *cmd)
+{
+	const bool write = cmd->rq->cmd_flags & REQ_WRITE;
+	struct loop_device *lo = cmd->rq->q->queuedata;
+	int ret = -EIO;
+
+	if (lo->lo_state != Lo_bound)
+		goto failed;
+
+	if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY))
+		goto failed;
+
+	ret = do_req_filebacked(lo, cmd->rq);
+
+ failed:
+	if (ret)
+		cmd->rq->errors = -EIO;
+	blk_mq_complete_request(cmd->rq);
+}
+
+static void loop_queue_write_work(struct work_struct *work)
+{
+	struct loop_device *lo =
+		container_of(work, struct loop_device, write_work);
+	LIST_HEAD(cmd_list);
+
+	spin_lock_irq(&lo->lo_lock);
+ repeat:
+	list_splice_init(&lo->write_cmd_head, &cmd_list);
+	spin_unlock_irq(&lo->lo_lock);
+
+	while (!list_empty(&cmd_list)) {
+		struct loop_cmd *cmd = list_first_entry(&cmd_list,
+				struct loop_cmd, list);
+		list_del_init(&cmd->list);
+		loop_handle_cmd(cmd);
+	}
+
+	spin_lock_irq(&lo->lo_lock);
+	if (!list_empty(&lo->write_cmd_head))
+		goto repeat;
+	lo->write_started = false;
+	spin_unlock_irq(&lo->lo_lock);
+}
+
+static void loop_queue_read_work(struct work_struct *work)
+{
+	struct loop_cmd *cmd =
+		container_of(work, struct loop_cmd, read_work);
+
+	loop_handle_cmd(cmd);
+}
+
+static int loop_init_request(void *data, struct request *rq,
+		unsigned int hctx_idx, unsigned int request_idx,
+		unsigned int numa_node)
+{
+	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
+
+	cmd->rq = rq;
+	INIT_WORK(&cmd->read_work, loop_queue_read_work);
+
+	return 0;
+}
+
+static struct blk_mq_ops loop_mq_ops = {
+	.queue_rq       = loop_queue_rq,
+	.map_queue      = blk_mq_map_queue,
+	.init_request	= loop_init_request,
+};
+
 static int loop_add(struct loop_device **l, int i)
 {
 	struct loop_device *lo;
@@ -1627,16 +1598,28 @@ static int loop_add(struct loop_device **l, int i)
 	i = err;
 
 	err = -ENOMEM;
-	lo->lo_queue = blk_alloc_queue(GFP_KERNEL);
-	if (!lo->lo_queue)
+	lo->tag_set.ops = &loop_mq_ops;
+	lo->tag_set.nr_hw_queues = 1;
+	lo->tag_set.queue_depth = 128;
+	lo->tag_set.numa_node = NUMA_NO_NODE;
+	lo->tag_set.cmd_size = sizeof(struct loop_cmd);
+	lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+	lo->tag_set.driver_data = lo;
+
+	err = blk_mq_alloc_tag_set(&lo->tag_set);
+	if (err)
 		goto out_free_idr;
 
-	/*
-	 * set queue make_request_fn
-	 */
-	blk_queue_make_request(lo->lo_queue, loop_make_request);
+	lo->lo_queue = blk_mq_init_queue(&lo->tag_set);
+	if (IS_ERR_OR_NULL(lo->lo_queue)) {
+		err = PTR_ERR(lo->lo_queue);
+		goto out_cleanup_tags;
+	}
 	lo->lo_queue->queuedata = lo;
 
+	INIT_LIST_HEAD(&lo->write_cmd_head);
+	INIT_WORK(&lo->write_work, loop_queue_write_work);
+
 	disk = lo->lo_disk = alloc_disk(1 << part_shift);
 	if (!disk)
 		goto out_free_queue;
@@ -1664,9 +1647,6 @@ static int loop_add(struct loop_device **l, int i)
 	disk->flags |= GENHD_FL_EXT_DEVT;
 	mutex_init(&lo->lo_ctl_mutex);
 	lo->lo_number		= i;
-	lo->lo_thread		= NULL;
-	init_waitqueue_head(&lo->lo_event);
-	init_waitqueue_head(&lo->lo_req_wait);
 	spin_lock_init(&lo->lo_lock);
 	disk->major		= LOOP_MAJOR;
 	disk->first_minor	= i << part_shift;
@@ -1680,6 +1660,8 @@ static int loop_add(struct loop_device **l, int i)
 
 out_free_queue:
 	blk_cleanup_queue(lo->lo_queue);
+out_cleanup_tags:
+	blk_mq_free_tag_set(&lo->tag_set);
 out_free_idr:
 	idr_remove(&loop_index_idr, i);
 out_free_dev:
@@ -1692,6 +1674,7 @@ static void loop_remove(struct loop_device *lo)
 {
 	del_gendisk(lo->lo_disk);
 	blk_cleanup_queue(lo->lo_queue);
+	blk_mq_free_tag_set(&lo->tag_set);
 	put_disk(lo->lo_disk);
 	kfree(lo);
 }
@@ -1875,6 +1858,13 @@ static int __init loop_init(void)
 		goto misc_out;
 	}
 
+	loop_wq = alloc_workqueue("kloopd",
+			WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_UNBOUND, 0);
+	if (!loop_wq) {
+		err = -ENOMEM;
+		goto misc_out;
+	}
+
 	blk_register_region(MKDEV(LOOP_MAJOR, 0), range,
 				  THIS_MODULE, loop_probe, NULL, NULL);
 
@@ -1912,6 +1902,8 @@ static void __exit loop_exit(void)
 	blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range);
 	unregister_blkdev(LOOP_MAJOR, "loop");
 
+	destroy_workqueue(loop_wq);
+
 	misc_deregister(&loop_misc);
 }
 
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index 90df5d6485b6..301c27f8323f 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -11,8 +11,10 @@
 
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
+#include <linux/workqueue.h>
 #include <uapi/linux/loop.h>
 
 /* Possible states of device */
@@ -52,19 +54,23 @@ struct loop_device {
 	gfp_t		old_gfp_mask;
 
 	spinlock_t		lo_lock;
-	struct bio_list		lo_bio_list;
-	unsigned int		lo_bio_count;
+	struct list_head	write_cmd_head;
+	struct work_struct	write_work;
+	bool			write_started;
 	int			lo_state;
 	struct mutex		lo_ctl_mutex;
-	struct task_struct	*lo_thread;
-	wait_queue_head_t	lo_event;
-	/* wait queue for incoming requests */
-	wait_queue_head_t	lo_req_wait;
 
 	struct request_queue	*lo_queue;
+	struct blk_mq_tag_set	tag_set;
 	struct gendisk		*lo_disk;
 };
 
+struct loop_cmd {
+	struct work_struct read_work;
+	struct request *rq;
+	struct list_head list;
+};
+
 /* Support for loadable transfer modules */
 struct loop_func_table {
 	int number;	/* filter type */ 
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index aa2224aa7caa..65cd61a4145e 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -579,7 +579,7 @@ static int null_add_dev(void)
 	sector_div(size, bs);
 	set_capacity(disk, size);
 
-	disk->flags |= GENHD_FL_EXT_DEVT;
+	disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO;
 	disk->major		= null_major;
 	disk->first_minor	= nullb->index;
 	disk->fops		= &null_fops;
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index d826bf3e62c8..ceb32dd52a6c 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -37,17 +37,18 @@
 #include <linux/ptrace.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/t10-pi.h>
 #include <linux/types.h>
 #include <scsi/sg.h>
 #include <asm-generic/io-64-nonatomic-lo-hi.h>
 
+#define NVME_MINORS		(1U << MINORBITS)
 #define NVME_Q_DEPTH		1024
 #define NVME_AQ_DEPTH		64
 #define SQ_SIZE(depth)		(depth * sizeof(struct nvme_command))
 #define CQ_SIZE(depth)		(depth * sizeof(struct nvme_completion))
 #define ADMIN_TIMEOUT		(admin_timeout * HZ)
 #define SHUTDOWN_TIMEOUT	(shutdown_timeout * HZ)
-#define IOD_TIMEOUT		(retry_time * HZ)
 
 static unsigned char admin_timeout = 60;
 module_param(admin_timeout, byte, 0644);
@@ -57,10 +58,6 @@ unsigned char nvme_io_timeout = 30;
 module_param_named(io_timeout, nvme_io_timeout, byte, 0644);
 MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O");
 
-static unsigned char retry_time = 30;
-module_param(retry_time, byte, 0644);
-MODULE_PARM_DESC(retry_time, "time in seconds to retry failed I/O");
-
 static unsigned char shutdown_timeout = 5;
 module_param(shutdown_timeout, byte, 0644);
 MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown");
@@ -68,6 +65,9 @@ MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown")
 static int nvme_major;
 module_param(nvme_major, int, 0);
 
+static int nvme_char_major;
+module_param(nvme_char_major, int, 0);
+
 static int use_threaded_interrupts;
 module_param(use_threaded_interrupts, int, 0);
 
@@ -76,7 +76,8 @@ static LIST_HEAD(dev_list);
 static struct task_struct *nvme_thread;
 static struct workqueue_struct *nvme_workq;
 static wait_queue_head_t nvme_kthread_wait;
-static struct notifier_block nvme_nb;
+
+static struct class *nvme_class;
 
 static void nvme_reset_failed_dev(struct work_struct *ws);
 static int nvme_process_cq(struct nvme_queue *nvmeq);
@@ -95,7 +96,6 @@ struct async_cmd_info {
  * commands and one for I/O commands).
  */
 struct nvme_queue {
-	struct llist_node node;
 	struct device *q_dmadev;
 	struct nvme_dev *dev;
 	char irqname[24];	/* nvme4294967295-65535\0 */
@@ -144,8 +144,37 @@ struct nvme_cmd_info {
 	void *ctx;
 	int aborted;
 	struct nvme_queue *nvmeq;
+	struct nvme_iod iod[0];
 };
 
+/*
+ * Max size of iod being embedded in the request payload
+ */
+#define NVME_INT_PAGES		2
+#define NVME_INT_BYTES(dev)	(NVME_INT_PAGES * (dev)->page_size)
+
+/*
+ * Will slightly overestimate the number of pages needed.  This is OK
+ * as it only leads to a small amount of wasted memory for the lifetime of
+ * the I/O.
+ */
+static int nvme_npages(unsigned size, struct nvme_dev *dev)
+{
+	unsigned nprps = DIV_ROUND_UP(size + dev->page_size, dev->page_size);
+	return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8);
+}
+
+static unsigned int nvme_cmd_size(struct nvme_dev *dev)
+{
+	unsigned int ret = sizeof(struct nvme_cmd_info);
+
+	ret += sizeof(struct nvme_iod);
+	ret += sizeof(__le64 *) * nvme_npages(NVME_INT_BYTES(dev), dev);
+	ret += sizeof(struct scatterlist) * NVME_INT_PAGES;
+
+	return ret;
+}
+
 static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 				unsigned int hctx_idx)
 {
@@ -218,6 +247,19 @@ static void nvme_set_info(struct nvme_cmd_info *cmd, void *ctx,
 	blk_mq_start_request(blk_mq_rq_from_pdu(cmd));
 }
 
+static void *iod_get_private(struct nvme_iod *iod)
+{
+	return (void *) (iod->private & ~0x1UL);
+}
+
+/*
+ * If bit 0 is set, the iod is embedded in the request payload.
+ */
+static bool iod_should_kfree(struct nvme_iod *iod)
+{
+	return (iod->private & 0x01) == 0;
+}
+
 /* Special values must be less than 0x1000 */
 #define CMD_CTX_BASE		((void *)POISON_POINTER_DELTA)
 #define CMD_CTX_CANCELLED	(0x30C + CMD_CTX_BASE)
@@ -361,35 +403,53 @@ static __le64 **iod_list(struct nvme_iod *iod)
 	return ((void *)iod) + iod->offset;
 }
 
-/*
- * Will slightly overestimate the number of pages needed.  This is OK
- * as it only leads to a small amount of wasted memory for the lifetime of
- * the I/O.
- */
-static int nvme_npages(unsigned size, struct nvme_dev *dev)
+static inline void iod_init(struct nvme_iod *iod, unsigned nbytes,
+			    unsigned nseg, unsigned long private)
 {
-	unsigned nprps = DIV_ROUND_UP(size + dev->page_size, dev->page_size);
-	return DIV_ROUND_UP(8 * nprps, dev->page_size - 8);
+	iod->private = private;
+	iod->offset = offsetof(struct nvme_iod, sg[nseg]);
+	iod->npages = -1;
+	iod->length = nbytes;
+	iod->nents = 0;
 }
 
 static struct nvme_iod *
-nvme_alloc_iod(unsigned nseg, unsigned nbytes, struct nvme_dev *dev, gfp_t gfp)
+__nvme_alloc_iod(unsigned nseg, unsigned bytes, struct nvme_dev *dev,
+		 unsigned long priv, gfp_t gfp)
 {
 	struct nvme_iod *iod = kmalloc(sizeof(struct nvme_iod) +
-				sizeof(__le64 *) * nvme_npages(nbytes, dev) +
+				sizeof(__le64 *) * nvme_npages(bytes, dev) +
 				sizeof(struct scatterlist) * nseg, gfp);
 
-	if (iod) {
-		iod->offset = offsetof(struct nvme_iod, sg[nseg]);
-		iod->npages = -1;
-		iod->length = nbytes;
-		iod->nents = 0;
-		iod->first_dma = 0ULL;
-	}
+	if (iod)
+		iod_init(iod, bytes, nseg, priv);
 
 	return iod;
 }
 
+static struct nvme_iod *nvme_alloc_iod(struct request *rq, struct nvme_dev *dev,
+			               gfp_t gfp)
+{
+	unsigned size = !(rq->cmd_flags & REQ_DISCARD) ? blk_rq_bytes(rq) :
+                                                sizeof(struct nvme_dsm_range);
+	unsigned long mask = 0;
+	struct nvme_iod *iod;
+
+	if (rq->nr_phys_segments <= NVME_INT_PAGES &&
+	    size <= NVME_INT_BYTES(dev)) {
+		struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(rq);
+
+		iod = cmd->iod;
+		mask = 0x01;
+		iod_init(iod, size, rq->nr_phys_segments,
+				(unsigned long) rq | 0x01);
+		return iod;
+	}
+
+	return __nvme_alloc_iod(rq->nr_phys_segments, size, dev,
+				(unsigned long) rq, gfp);
+}
+
 void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
 {
 	const int last_prp = dev->page_size / 8 - 1;
@@ -405,7 +465,9 @@ void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
 		dma_pool_free(dev->prp_page_pool, prp_list, prp_dma);
 		prp_dma = next_prp_dma;
 	}
-	kfree(iod);
+
+	if (iod_should_kfree(iod))
+		kfree(iod);
 }
 
 static int nvme_error_status(u16 status)
@@ -420,11 +482,120 @@ static int nvme_error_status(u16 status)
 	}
 }
 
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
+{
+	if (be32_to_cpu(pi->ref_tag) == v)
+		pi->ref_tag = cpu_to_be32(p);
+}
+
+static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
+{
+	if (be32_to_cpu(pi->ref_tag) == p)
+		pi->ref_tag = cpu_to_be32(v);
+}
+
+/**
+ * nvme_dif_remap - remaps ref tags to bip seed and physical lba
+ *
+ * The virtual start sector is the one that was originally submitted by the
+ * block layer.	Due to partitioning, MD/DM cloning, etc. the actual physical
+ * start sector may be different. Remap protection information to match the
+ * physical LBA on writes, and back to the original seed on reads.
+ *
+ * Type 0 and 3 do not have a ref tag, so no remapping required.
+ */
+static void nvme_dif_remap(struct request *req,
+			void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))
+{
+	struct nvme_ns *ns = req->rq_disk->private_data;
+	struct bio_integrity_payload *bip;
+	struct t10_pi_tuple *pi;
+	void *p, *pmap;
+	u32 i, nlb, ts, phys, virt;
+
+	if (!ns->pi_type || ns->pi_type == NVME_NS_DPS_PI_TYPE3)
+		return;
+
+	bip = bio_integrity(req->bio);
+	if (!bip)
+		return;
+
+	pmap = kmap_atomic(bip->bip_vec->bv_page) + bip->bip_vec->bv_offset;
+	if (!pmap)
+		return;
+
+	p = pmap;
+	virt = bip_get_seed(bip);
+	phys = nvme_block_nr(ns, blk_rq_pos(req));
+	nlb = (blk_rq_bytes(req) >> ns->lba_shift);
+	ts = ns->disk->integrity->tuple_size;
+
+	for (i = 0; i < nlb; i++, virt++, phys++) {
+		pi = (struct t10_pi_tuple *)p;
+		dif_swap(phys, virt, pi);
+		p += ts;
+	}
+	kunmap_atomic(pmap);
+}
+
+static int nvme_noop_verify(struct blk_integrity_iter *iter)
+{
+	return 0;
+}
+
+static int nvme_noop_generate(struct blk_integrity_iter *iter)
+{
+	return 0;
+}
+
+struct blk_integrity nvme_meta_noop = {
+	.name			= "NVME_META_NOOP",
+	.generate_fn		= nvme_noop_generate,
+	.verify_fn		= nvme_noop_verify,
+};
+
+static void nvme_init_integrity(struct nvme_ns *ns)
+{
+	struct blk_integrity integrity;
+
+	switch (ns->pi_type) {
+	case NVME_NS_DPS_PI_TYPE3:
+		integrity = t10_pi_type3_crc;
+		break;
+	case NVME_NS_DPS_PI_TYPE1:
+	case NVME_NS_DPS_PI_TYPE2:
+		integrity = t10_pi_type1_crc;
+		break;
+	default:
+		integrity = nvme_meta_noop;
+		break;
+	}
+	integrity.tuple_size = ns->ms;
+	blk_integrity_register(ns->disk, &integrity);
+	blk_queue_max_integrity_segments(ns->queue, 1);
+}
+#else /* CONFIG_BLK_DEV_INTEGRITY */
+static void nvme_dif_remap(struct request *req,
+			void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))
+{
+}
+static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
+{
+}
+static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
+{
+}
+static void nvme_init_integrity(struct nvme_ns *ns)
+{
+}
+#endif
+
 static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 						struct nvme_completion *cqe)
 {
 	struct nvme_iod *iod = ctx;
-	struct request *req = iod->private;
+	struct request *req = iod_get_private(iod);
 	struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
 
 	u16 status = le16_to_cpup(&cqe->status) >> 1;
@@ -450,9 +621,16 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 			"completing aborted command with status:%04x\n",
 			status);
 
-	if (iod->nents)
+	if (iod->nents) {
 		dma_unmap_sg(&nvmeq->dev->pci_dev->dev, iod->sg, iod->nents,
 			rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+		if (blk_integrity_rq(req)) {
+			if (!rq_data_dir(req))
+				nvme_dif_remap(req, nvme_dif_complete);
+			dma_unmap_sg(&nvmeq->dev->pci_dev->dev, iod->meta_sg, 1,
+				rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+		}
+	}
 	nvme_free_iod(nvmeq->dev, iod);
 
 	blk_mq_complete_request(req);
@@ -585,7 +763,7 @@ static void nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod,
 							struct nvme_ns *ns)
 {
-	struct request *req = iod->private;
+	struct request *req = iod_get_private(iod);
 	struct nvme_command *cmnd;
 	u16 control = 0;
 	u32 dsmgmt = 0;
@@ -608,6 +786,24 @@ static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod,
 	cmnd->rw.prp2 = cpu_to_le64(iod->first_dma);
 	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
 	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
+
+	if (blk_integrity_rq(req)) {
+		cmnd->rw.metadata = cpu_to_le64(sg_dma_address(iod->meta_sg));
+		switch (ns->pi_type) {
+		case NVME_NS_DPS_PI_TYPE3:
+			control |= NVME_RW_PRINFO_PRCHK_GUARD;
+			break;
+		case NVME_NS_DPS_PI_TYPE1:
+		case NVME_NS_DPS_PI_TYPE2:
+			control |= NVME_RW_PRINFO_PRCHK_GUARD |
+					NVME_RW_PRINFO_PRCHK_REF;
+			cmnd->rw.reftag = cpu_to_le32(
+					nvme_block_nr(ns, blk_rq_pos(req)));
+			break;
+		}
+	} else if (ns->ms)
+		control |= NVME_RW_PRINFO_PRACT;
+
 	cmnd->rw.control = cpu_to_le16(control);
 	cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
 
@@ -626,17 +822,25 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct request *req = bd->rq;
 	struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
 	struct nvme_iod *iod;
-	int psegs = req->nr_phys_segments;
 	enum dma_data_direction dma_dir;
-	unsigned size = !(req->cmd_flags & REQ_DISCARD) ? blk_rq_bytes(req) :
-						sizeof(struct nvme_dsm_range);
 
-	iod = nvme_alloc_iod(psegs, size, ns->dev, GFP_ATOMIC);
+	/*
+	 * If formated with metadata, require the block layer provide a buffer
+	 * unless this namespace is formated such that the metadata can be
+	 * stripped/generated by the controller with PRACT=1.
+	 */
+	if (ns->ms && !blk_integrity_rq(req)) {
+		if (!(ns->pi_type && ns->ms == 8)) {
+			req->errors = -EFAULT;
+			blk_mq_complete_request(req);
+			return BLK_MQ_RQ_QUEUE_OK;
+		}
+	}
+
+	iod = nvme_alloc_iod(req, ns->dev, GFP_ATOMIC);
 	if (!iod)
 		return BLK_MQ_RQ_QUEUE_BUSY;
 
-	iod->private = req;
-
 	if (req->cmd_flags & REQ_DISCARD) {
 		void *range;
 		/*
@@ -651,10 +855,10 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 			goto retry_cmd;
 		iod_list(iod)[0] = (__le64 *)range;
 		iod->npages = 0;
-	} else if (psegs) {
+	} else if (req->nr_phys_segments) {
 		dma_dir = rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
 
-		sg_init_table(iod->sg, psegs);
+		sg_init_table(iod->sg, req->nr_phys_segments);
 		iod->nents = blk_rq_map_sg(req->q, req, iod->sg);
 		if (!iod->nents)
 			goto error_cmd;
@@ -668,6 +872,21 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 					iod->nents, dma_dir);
 			goto retry_cmd;
 		}
+		if (blk_integrity_rq(req)) {
+			if (blk_rq_count_integrity_sg(req->q, req->bio) != 1)
+				goto error_cmd;
+
+			sg_init_table(iod->meta_sg, 1);
+			if (blk_rq_map_integrity_sg(
+					req->q, req->bio, iod->meta_sg) != 1)
+				goto error_cmd;
+
+			if (rq_data_dir(req))
+				nvme_dif_remap(req, nvme_dif_prep);
+
+			if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir))
+				goto error_cmd;
+		}
 	}
 
 	nvme_set_info(cmd, iod, req_completion);
@@ -760,14 +979,6 @@ static irqreturn_t nvme_irq_check(int irq, void *data)
 	return IRQ_WAKE_THREAD;
 }
 
-static void nvme_abort_cmd_info(struct nvme_queue *nvmeq, struct nvme_cmd_info *
-								cmd_info)
-{
-	spin_lock_irq(&nvmeq->q_lock);
-	cancel_cmd_info(cmd_info, NULL);
-	spin_unlock_irq(&nvmeq->q_lock);
-}
-
 struct sync_cmd_info {
 	struct task_struct *task;
 	u32 result;
@@ -790,7 +1001,6 @@ static void sync_completion(struct nvme_queue *nvmeq, void *ctx,
 static int nvme_submit_sync_cmd(struct request *req, struct nvme_command *cmd,
 						u32 *result, unsigned timeout)
 {
-	int ret;
 	struct sync_cmd_info cmdinfo;
 	struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
 	struct nvme_queue *nvmeq = cmd_rq->nvmeq;
@@ -802,29 +1012,12 @@ static int nvme_submit_sync_cmd(struct request *req, struct nvme_command *cmd,
 
 	nvme_set_info(cmd_rq, &cmdinfo, sync_completion);
 
-	set_current_state(TASK_KILLABLE);
-	ret = nvme_submit_cmd(nvmeq, cmd);
-	if (ret) {
-		nvme_finish_cmd(nvmeq, req->tag, NULL);
-		set_current_state(TASK_RUNNING);
-	}
-	ret = schedule_timeout(timeout);
-
-	/*
-	 * Ensure that sync_completion has either run, or that it will
-	 * never run.
-	 */
-	nvme_abort_cmd_info(nvmeq, blk_mq_rq_to_pdu(req));
-
-	/*
-	 * We never got the completion
-	 */
-	if (cmdinfo.status == -EINTR)
-		return -EINTR;
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	nvme_submit_cmd(nvmeq, cmd);
+	schedule();
 
 	if (result)
 		*result = cmdinfo.result;
-
 	return cmdinfo.status;
 }
 
@@ -1101,29 +1294,18 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
 	struct nvme_queue *nvmeq = cmd->nvmeq;
 
-	/*
-	 * The aborted req will be completed on receiving the abort req.
-	 * We enable the timer again. If hit twice, it'll cause a device reset,
-	 * as the device then is in a faulty state.
-	 */
-	int ret = BLK_EH_RESET_TIMER;
-
 	dev_warn(nvmeq->q_dmadev, "Timeout I/O %d QID %d\n", req->tag,
 							nvmeq->qid);
-
 	spin_lock_irq(&nvmeq->q_lock);
-	if (!nvmeq->dev->initialized) {
-		/*
-		 * Force cancelled command frees the request, which requires we
-		 * return BLK_EH_NOT_HANDLED.
-		 */
-		nvme_cancel_queue_ios(nvmeq->hctx, req, nvmeq, reserved);
-		ret = BLK_EH_NOT_HANDLED;
-	} else
-		nvme_abort_req(req);
+	nvme_abort_req(req);
 	spin_unlock_irq(&nvmeq->q_lock);
 
-	return ret;
+	/*
+	 * The aborted req will be completed on receiving the abort req.
+	 * We enable the timer again. If hit twice, it'll cause a device reset,
+	 * as the device then is in a faulty state.
+	 */
+	return BLK_EH_RESET_TIMER;
 }
 
 static void nvme_free_queue(struct nvme_queue *nvmeq)
@@ -1137,21 +1319,14 @@ static void nvme_free_queue(struct nvme_queue *nvmeq)
 
 static void nvme_free_queues(struct nvme_dev *dev, int lowest)
 {
-	LLIST_HEAD(q_list);
-	struct nvme_queue *nvmeq, *next;
-	struct llist_node *entry;
 	int i;
 
 	for (i = dev->queue_count - 1; i >= lowest; i--) {
 		struct nvme_queue *nvmeq = dev->queues[i];
-		llist_add(&nvmeq->node, &q_list);
 		dev->queue_count--;
 		dev->queues[i] = NULL;
-	}
-	synchronize_rcu();
-	entry = llist_del_all(&q_list);
-	llist_for_each_entry_safe(nvmeq, next, entry, node)
 		nvme_free_queue(nvmeq);
+	}
 }
 
 /**
@@ -1183,7 +1358,6 @@ static void nvme_clear_queue(struct nvme_queue *nvmeq)
 	struct blk_mq_hw_ctx *hctx = nvmeq->hctx;
 
 	spin_lock_irq(&nvmeq->q_lock);
-	nvme_process_cq(nvmeq);
 	if (hctx && hctx->tags)
 		blk_mq_tag_busy_iter(hctx, nvme_cancel_queue_ios, nvmeq);
 	spin_unlock_irq(&nvmeq->q_lock);
@@ -1206,7 +1380,10 @@ static void nvme_disable_queue(struct nvme_dev *dev, int qid)
 	}
 	if (!qid && dev->admin_q)
 		blk_mq_freeze_queue_start(dev->admin_q);
-	nvme_clear_queue(nvmeq);
+
+	spin_lock_irq(&nvmeq->q_lock);
+	nvme_process_cq(nvmeq);
+	spin_unlock_irq(&nvmeq->q_lock);
 }
 
 static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
@@ -1408,7 +1585,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 		dev->admin_tagset.queue_depth = NVME_AQ_DEPTH - 1;
 		dev->admin_tagset.timeout = ADMIN_TIMEOUT;
 		dev->admin_tagset.numa_node = dev_to_node(&dev->pci_dev->dev);
-		dev->admin_tagset.cmd_size = sizeof(struct nvme_cmd_info);
+		dev->admin_tagset.cmd_size = nvme_cmd_size(dev);
 		dev->admin_tagset.driver_data = dev;
 
 		if (blk_mq_alloc_tag_set(&dev->admin_tagset))
@@ -1522,7 +1699,7 @@ struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
 	}
 
 	err = -ENOMEM;
-	iod = nvme_alloc_iod(count, length, dev, GFP_KERNEL);
+	iod = __nvme_alloc_iod(count, length, dev, 0, GFP_KERNEL);
 	if (!iod)
 		goto put_pages;
 
@@ -1825,13 +2002,24 @@ static int nvme_getgeo(struct block_device *bd, struct hd_geometry *geo)
 	return 0;
 }
 
+static void nvme_config_discard(struct nvme_ns *ns)
+{
+	u32 logical_block_size = queue_logical_block_size(ns->queue);
+	ns->queue->limits.discard_zeroes_data = 0;
+	ns->queue->limits.discard_alignment = logical_block_size;
+	ns->queue->limits.discard_granularity = logical_block_size;
+	ns->queue->limits.max_discard_sectors = 0xffffffff;
+	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
+}
+
 static int nvme_revalidate_disk(struct gendisk *disk)
 {
 	struct nvme_ns *ns = disk->private_data;
 	struct nvme_dev *dev = ns->dev;
 	struct nvme_id_ns *id;
 	dma_addr_t dma_addr;
-	int lbaf;
+	int lbaf, pi_type, old_ms;
+	unsigned short bs;
 
 	id = dma_alloc_coherent(&dev->pci_dev->dev, 4096, &dma_addr,
 								GFP_KERNEL);
@@ -1840,16 +2028,51 @@ static int nvme_revalidate_disk(struct gendisk *disk)
 								__func__);
 		return 0;
 	}
+	if (nvme_identify(dev, ns->ns_id, 0, dma_addr)) {
+		dev_warn(&dev->pci_dev->dev,
+			"identify failed ns:%d, setting capacity to 0\n",
+			ns->ns_id);
+		memset(id, 0, sizeof(*id));
+	}
 
-	if (nvme_identify(dev, ns->ns_id, 0, dma_addr))
-		goto free;
-
-	lbaf = id->flbas & 0xf;
+	old_ms = ns->ms;
+	lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
 	ns->lba_shift = id->lbaf[lbaf].ds;
+	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
+
+	/*
+	 * If identify namespace failed, use default 512 byte block size so
+	 * block layer can use before failing read/write for 0 capacity.
+	 */
+	if (ns->lba_shift == 0)
+		ns->lba_shift = 9;
+	bs = 1 << ns->lba_shift;
+
+	/* XXX: PI implementation requires metadata equal t10 pi tuple size */
+	pi_type = ns->ms == sizeof(struct t10_pi_tuple) ?
+					id->dps & NVME_NS_DPS_PI_MASK : 0;
+
+	if (blk_get_integrity(disk) && (ns->pi_type != pi_type ||
+				ns->ms != old_ms ||
+				bs != queue_logical_block_size(disk->queue) ||
+				(ns->ms && id->flbas & NVME_NS_FLBAS_META_EXT)))
+		blk_integrity_unregister(disk);
+
+	ns->pi_type = pi_type;
+	blk_queue_logical_block_size(ns->queue, bs);
+
+	if (ns->ms && !blk_get_integrity(disk) && (disk->flags & GENHD_FL_UP) &&
+				!(id->flbas & NVME_NS_FLBAS_META_EXT))
+		nvme_init_integrity(ns);
+
+	if (id->ncap == 0 || (ns->ms && !blk_get_integrity(disk)))
+		set_capacity(disk, 0);
+	else
+		set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
+
+	if (dev->oncs & NVME_CTRL_ONCS_DSM)
+		nvme_config_discard(ns);
 
-	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
-	set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
- free:
 	dma_free_coherent(&dev->pci_dev->dev, 4096, id, dma_addr);
 	return 0;
 }
@@ -1873,8 +2096,7 @@ static int nvme_kthread(void *data)
 		spin_lock(&dev_list_lock);
 		list_for_each_entry_safe(dev, next, &dev_list, node) {
 			int i;
-			if (readl(&dev->bar->csts) & NVME_CSTS_CFS &&
-							dev->initialized) {
+			if (readl(&dev->bar->csts) & NVME_CSTS_CFS) {
 				if (work_busy(&dev->reset_work))
 					continue;
 				list_del_init(&dev->node);
@@ -1906,30 +2128,16 @@ static int nvme_kthread(void *data)
 	return 0;
 }
 
-static void nvme_config_discard(struct nvme_ns *ns)
-{
-	u32 logical_block_size = queue_logical_block_size(ns->queue);
-	ns->queue->limits.discard_zeroes_data = 0;
-	ns->queue->limits.discard_alignment = logical_block_size;
-	ns->queue->limits.discard_granularity = logical_block_size;
-	ns->queue->limits.max_discard_sectors = 0xffffffff;
-	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
-}
-
-static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
-			struct nvme_id_ns *id, struct nvme_lba_range_type *rt)
+static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 {
 	struct nvme_ns *ns;
 	struct gendisk *disk;
 	int node = dev_to_node(&dev->pci_dev->dev);
-	int lbaf;
-
-	if (rt->attributes & NVME_LBART_ATTRIB_HIDE)
-		return NULL;
 
 	ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
 	if (!ns)
-		return NULL;
+		return;
+
 	ns->queue = blk_mq_init_queue(&dev->tagset);
 	if (IS_ERR(ns->queue))
 		goto out_free_ns;
@@ -1945,9 +2153,9 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
 
 	ns->ns_id = nsid;
 	ns->disk = disk;
-	lbaf = id->flbas & 0xf;
-	ns->lba_shift = id->lbaf[lbaf].ds;
-	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
+	ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */
+	list_add_tail(&ns->list, &dev->namespaces);
+
 	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
 	if (dev->max_hw_sectors)
 		blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);
@@ -1961,21 +2169,26 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
 	disk->fops = &nvme_fops;
 	disk->private_data = ns;
 	disk->queue = ns->queue;
-	disk->driverfs_dev = &dev->pci_dev->dev;
+	disk->driverfs_dev = dev->device;
 	disk->flags = GENHD_FL_EXT_DEVT;
 	sprintf(disk->disk_name, "nvme%dn%d", dev->instance, nsid);
-	set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
-
-	if (dev->oncs & NVME_CTRL_ONCS_DSM)
-		nvme_config_discard(ns);
-
-	return ns;
 
+	/*
+	 * Initialize capacity to 0 until we establish the namespace format and
+	 * setup integrity extentions if necessary. The revalidate_disk after
+	 * add_disk allows the driver to register with integrity if the format
+	 * requires it.
+	 */
+	set_capacity(disk, 0);
+	nvme_revalidate_disk(ns->disk);
+	add_disk(ns->disk);
+	if (ns->ms)
+		revalidate_disk(ns->disk);
+	return;
  out_free_queue:
 	blk_cleanup_queue(ns->queue);
  out_free_ns:
 	kfree(ns);
-	return NULL;
 }
 
 static void nvme_create_io_queues(struct nvme_dev *dev)
@@ -2100,22 +2313,20 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	struct pci_dev *pdev = dev->pci_dev;
 	int res;
 	unsigned nn, i;
-	struct nvme_ns *ns;
 	struct nvme_id_ctrl *ctrl;
-	struct nvme_id_ns *id_ns;
 	void *mem;
 	dma_addr_t dma_addr;
 	int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12;
 
-	mem = dma_alloc_coherent(&pdev->dev, 8192, &dma_addr, GFP_KERNEL);
+	mem = dma_alloc_coherent(&pdev->dev, 4096, &dma_addr, GFP_KERNEL);
 	if (!mem)
 		return -ENOMEM;
 
 	res = nvme_identify(dev, 0, 1, dma_addr);
 	if (res) {
 		dev_err(&pdev->dev, "Identify Controller failed (%d)\n", res);
-		res = -EIO;
-		goto out;
+		dma_free_coherent(&dev->pci_dev->dev, 4096, mem, dma_addr);
+		return -EIO;
 	}
 
 	ctrl = mem;
@@ -2141,6 +2352,7 @@ static int nvme_dev_add(struct nvme_dev *dev)
 		} else
 			dev->max_hw_sectors = max_hw_sectors;
 	}
+	dma_free_coherent(&dev->pci_dev->dev, 4096, mem, dma_addr);
 
 	dev->tagset.ops = &nvme_mq_ops;
 	dev->tagset.nr_hw_queues = dev->online_queues - 1;
@@ -2148,38 +2360,17 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	dev->tagset.numa_node = dev_to_node(&dev->pci_dev->dev);
 	dev->tagset.queue_depth =
 				min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1;
-	dev->tagset.cmd_size = sizeof(struct nvme_cmd_info);
+	dev->tagset.cmd_size = nvme_cmd_size(dev);
 	dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
 	dev->tagset.driver_data = dev;
 
 	if (blk_mq_alloc_tag_set(&dev->tagset))
-		goto out;
-
-	id_ns = mem;
-	for (i = 1; i <= nn; i++) {
-		res = nvme_identify(dev, i, 0, dma_addr);
-		if (res)
-			continue;
-
-		if (id_ns->ncap == 0)
-			continue;
-
-		res = nvme_get_features(dev, NVME_FEAT_LBA_RANGE, i,
-							dma_addr + 4096, NULL);
-		if (res)
-			memset(mem + 4096, 0, 4096);
+		return 0;
 
-		ns = nvme_alloc_ns(dev, i, mem, mem + 4096);
-		if (ns)
-			list_add_tail(&ns->list, &dev->namespaces);
-	}
-	list_for_each_entry(ns, &dev->namespaces, list)
-		add_disk(ns->disk);
-	res = 0;
+	for (i = 1; i <= nn; i++)
+		nvme_alloc_ns(dev, i);
 
- out:
-	dma_free_coherent(&dev->pci_dev->dev, 8192, mem, dma_addr);
-	return res;
+	return 0;
 }
 
 static int nvme_dev_map(struct nvme_dev *dev)
@@ -2308,8 +2499,6 @@ static struct nvme_delq_ctx *nvme_get_dq(struct nvme_delq_ctx *dq)
 static void nvme_del_queue_end(struct nvme_queue *nvmeq)
 {
 	struct nvme_delq_ctx *dq = nvmeq->cmdinfo.ctx;
-
-	nvme_clear_queue(nvmeq);
 	nvme_put_dq(dq);
 }
 
@@ -2452,7 +2641,6 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 	int i;
 	u32 csts = -1;
 
-	dev->initialized = 0;
 	nvme_dev_list_remove(dev);
 
 	if (dev->bar) {
@@ -2463,7 +2651,6 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 		for (i = dev->queue_count - 1; i >= 0; i--) {
 			struct nvme_queue *nvmeq = dev->queues[i];
 			nvme_suspend_queue(nvmeq);
-			nvme_clear_queue(nvmeq);
 		}
 	} else {
 		nvme_disable_io_queues(dev);
@@ -2471,6 +2658,9 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 		nvme_disable_queue(dev, 0);
 	}
 	nvme_dev_unmap(dev);
+
+	for (i = dev->queue_count - 1; i >= 0; i--)
+		nvme_clear_queue(dev->queues[i]);
 }
 
 static void nvme_dev_remove(struct nvme_dev *dev)
@@ -2478,8 +2668,11 @@ static void nvme_dev_remove(struct nvme_dev *dev)
 	struct nvme_ns *ns;
 
 	list_for_each_entry(ns, &dev->namespaces, list) {
-		if (ns->disk->flags & GENHD_FL_UP)
+		if (ns->disk->flags & GENHD_FL_UP) {
+			if (blk_get_integrity(ns->disk))
+				blk_integrity_unregister(ns->disk);
 			del_gendisk(ns->disk);
+		}
 		if (!blk_queue_dying(ns->queue)) {
 			blk_mq_abort_requeue_list(ns->queue);
 			blk_cleanup_queue(ns->queue);
@@ -2561,6 +2754,7 @@ static void nvme_free_dev(struct kref *kref)
 	struct nvme_dev *dev = container_of(kref, struct nvme_dev, kref);
 
 	pci_dev_put(dev->pci_dev);
+	put_device(dev->device);
 	nvme_free_namespaces(dev);
 	nvme_release_instance(dev);
 	blk_mq_free_tag_set(&dev->tagset);
@@ -2572,11 +2766,27 @@ static void nvme_free_dev(struct kref *kref)
 
 static int nvme_dev_open(struct inode *inode, struct file *f)
 {
-	struct nvme_dev *dev = container_of(f->private_data, struct nvme_dev,
-								miscdev);
-	kref_get(&dev->kref);
-	f->private_data = dev;
-	return 0;
+	struct nvme_dev *dev;
+	int instance = iminor(inode);
+	int ret = -ENODEV;
+
+	spin_lock(&dev_list_lock);
+	list_for_each_entry(dev, &dev_list, node) {
+		if (dev->instance == instance) {
+			if (!dev->admin_q) {
+				ret = -EWOULDBLOCK;
+				break;
+			}
+			if (!kref_get_unless_zero(&dev->kref))
+				break;
+			f->private_data = dev;
+			ret = 0;
+			break;
+		}
+	}
+	spin_unlock(&dev_list_lock);
+
+	return ret;
 }
 
 static int nvme_dev_release(struct inode *inode, struct file *f)
@@ -2718,7 +2928,6 @@ static int nvme_dev_resume(struct nvme_dev *dev)
 		nvme_unfreeze_queues(dev);
 		nvme_set_irq_hints(dev);
 	}
-	dev->initialized = 1;
 	return 0;
 }
 
@@ -2749,6 +2958,7 @@ static void nvme_reset_workfn(struct work_struct *work)
 	dev->reset_workfn(work);
 }
 
+static void nvme_async_probe(struct work_struct *work);
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	int node, result = -ENOMEM;
@@ -2784,37 +2994,20 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto release;
 
 	kref_init(&dev->kref);
-	result = nvme_dev_start(dev);
-	if (result)
+	dev->device = device_create(nvme_class, &pdev->dev,
+				MKDEV(nvme_char_major, dev->instance),
+				dev, "nvme%d", dev->instance);
+	if (IS_ERR(dev->device)) {
+		result = PTR_ERR(dev->device);
 		goto release_pools;
+	}
+	get_device(dev->device);
 
-	if (dev->online_queues > 1)
-		result = nvme_dev_add(dev);
-	if (result)
-		goto shutdown;
-
-	scnprintf(dev->name, sizeof(dev->name), "nvme%d", dev->instance);
-	dev->miscdev.minor = MISC_DYNAMIC_MINOR;
-	dev->miscdev.parent = &pdev->dev;
-	dev->miscdev.name = dev->name;
-	dev->miscdev.fops = &nvme_dev_fops;
-	result = misc_register(&dev->miscdev);
-	if (result)
-		goto remove;
-
-	nvme_set_irq_hints(dev);
-
-	dev->initialized = 1;
+	INIT_WORK(&dev->probe_work, nvme_async_probe);
+	schedule_work(&dev->probe_work);
 	return 0;
 
- remove:
-	nvme_dev_remove(dev);
-	nvme_dev_remove_admin(dev);
-	nvme_free_namespaces(dev);
- shutdown:
-	nvme_dev_shutdown(dev);
  release_pools:
-	nvme_free_queues(dev, 0);
 	nvme_release_prp_pools(dev);
  release:
 	nvme_release_instance(dev);
@@ -2827,6 +3020,29 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	return result;
 }
 
+static void nvme_async_probe(struct work_struct *work)
+{
+	struct nvme_dev *dev = container_of(work, struct nvme_dev, probe_work);
+	int result;
+
+	result = nvme_dev_start(dev);
+	if (result)
+		goto reset;
+
+	if (dev->online_queues > 1)
+		result = nvme_dev_add(dev);
+	if (result)
+		goto reset;
+
+	nvme_set_irq_hints(dev);
+	return;
+ reset:
+	if (!work_busy(&dev->reset_work)) {
+		dev->reset_workfn = nvme_reset_failed_dev;
+		queue_work(nvme_workq, &dev->reset_work);
+	}
+}
+
 static void nvme_reset_notify(struct pci_dev *pdev, bool prepare)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
@@ -2852,11 +3068,12 @@ static void nvme_remove(struct pci_dev *pdev)
 	spin_unlock(&dev_list_lock);
 
 	pci_set_drvdata(pdev, NULL);
+	flush_work(&dev->probe_work);
 	flush_work(&dev->reset_work);
-	misc_deregister(&dev->miscdev);
 	nvme_dev_shutdown(dev);
 	nvme_dev_remove(dev);
 	nvme_dev_remove_admin(dev);
+	device_destroy(nvme_class, MKDEV(nvme_char_major, dev->instance));
 	nvme_free_queues(dev, 0);
 	nvme_release_prp_pools(dev);
 	kref_put(&dev->kref, nvme_free_dev);
@@ -2940,11 +3157,26 @@ static int __init nvme_init(void)
 	else if (result > 0)
 		nvme_major = result;
 
+	result = __register_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme",
+							&nvme_dev_fops);
+	if (result < 0)
+		goto unregister_blkdev;
+	else if (result > 0)
+		nvme_char_major = result;
+
+	nvme_class = class_create(THIS_MODULE, "nvme");
+	if (!nvme_class)
+		goto unregister_chrdev;
+
 	result = pci_register_driver(&nvme_driver);
 	if (result)
-		goto unregister_blkdev;
+		goto destroy_class;
 	return 0;
 
+ destroy_class:
+	class_destroy(nvme_class);
+ unregister_chrdev:
+	__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
  unregister_blkdev:
 	unregister_blkdev(nvme_major, "nvme");
  kill_workq:
@@ -2955,9 +3187,10 @@ static int __init nvme_init(void)
 static void __exit nvme_exit(void)
 {
 	pci_unregister_driver(&nvme_driver);
-	unregister_hotcpu_notifier(&nvme_nb);
 	unregister_blkdev(nvme_major, "nvme");
 	destroy_workqueue(nvme_workq);
+	class_destroy(nvme_class);
+	__unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
 	BUG_ON(nvme_thread && !IS_ERR(nvme_thread));
 	_nvme_check_size();
 }
diff --git a/drivers/block/nvme-scsi.c b/drivers/block/nvme-scsi.c
index 5e78568026c3..e10196e0182d 100644
--- a/drivers/block/nvme-scsi.c
+++ b/drivers/block/nvme-scsi.c
@@ -779,10 +779,8 @@ static int nvme_trans_device_id_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	struct nvme_dev *dev = ns->dev;
 	dma_addr_t dma_addr;
 	void *mem;
-	struct nvme_id_ctrl *id_ctrl;
 	int res = SNTI_TRANSLATION_SUCCESS;
 	int nvme_sc;
-	u8 ieee[4];
 	int xfer_len;
 	__be32 tmp_id = cpu_to_be32(ns->ns_id);
 
@@ -793,46 +791,60 @@ static int nvme_trans_device_id_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 		goto out_dma;
 	}
 
-	/* nvme controller identify */
-	nvme_sc = nvme_identify(dev, 0, 1, dma_addr);
-	res = nvme_trans_status_code(hdr, nvme_sc);
-	if (res)
-		goto out_free;
-	if (nvme_sc) {
-		res = nvme_sc;
-		goto out_free;
-	}
-	id_ctrl = mem;
-
-	/* Since SCSI tried to save 4 bits... [SPC-4(r34) Table 591] */
-	ieee[0] = id_ctrl->ieee[0] << 4;
-	ieee[1] = id_ctrl->ieee[0] >> 4 | id_ctrl->ieee[1] << 4;
-	ieee[2] = id_ctrl->ieee[1] >> 4 | id_ctrl->ieee[2] << 4;
-	ieee[3] = id_ctrl->ieee[2] >> 4;
-
-	memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
+	memset(inq_response, 0, alloc_len);
 	inq_response[1] = INQ_DEVICE_IDENTIFICATION_PAGE;    /* Page Code */
-	inq_response[3] = 20;      /* Page Length */
-	/* Designation Descriptor start */
-	inq_response[4] = 0x01;    /* Proto ID=0h | Code set=1h */
-	inq_response[5] = 0x03;    /* PIV=0b | Asso=00b | Designator Type=3h */
-	inq_response[6] = 0x00;    /* Rsvd */
-	inq_response[7] = 16;      /* Designator Length */
-	/* Designator start */
-	inq_response[8] = 0x60 | ieee[3]; /* NAA=6h | IEEE ID MSB, High nibble*/
-	inq_response[9] = ieee[2];        /* IEEE ID */
-	inq_response[10] = ieee[1];       /* IEEE ID */
-	inq_response[11] = ieee[0];       /* IEEE ID| Vendor Specific ID... */
-	inq_response[12] = (dev->pci_dev->vendor & 0xFF00) >> 8;
-	inq_response[13] = (dev->pci_dev->vendor & 0x00FF);
-	inq_response[14] = dev->serial[0];
-	inq_response[15] = dev->serial[1];
-	inq_response[16] = dev->model[0];
-	inq_response[17] = dev->model[1];
-	memcpy(&inq_response[18], &tmp_id, sizeof(u32));
-	/* Last 2 bytes are zero */
+	if (readl(&dev->bar->vs) >= NVME_VS(1, 1)) {
+		struct nvme_id_ns *id_ns = mem;
+		void *eui = id_ns->eui64;
+		int len = sizeof(id_ns->eui64);
 
-	xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH);
+		nvme_sc = nvme_identify(dev, ns->ns_id, 0, dma_addr);
+		res = nvme_trans_status_code(hdr, nvme_sc);
+		if (res)
+			goto out_free;
+		if (nvme_sc) {
+			res = nvme_sc;
+			goto out_free;
+		}
+
+		if (readl(&dev->bar->vs) >= NVME_VS(1, 2)) {
+			if (bitmap_empty(eui, len * 8)) {
+				eui = id_ns->nguid;
+				len = sizeof(id_ns->nguid);
+			}
+		}
+		if (bitmap_empty(eui, len * 8))
+			goto scsi_string;
+
+		inq_response[3] = 4 + len; /* Page Length */
+		/* Designation Descriptor start */
+		inq_response[4] = 0x01;    /* Proto ID=0h | Code set=1h */
+		inq_response[5] = 0x02;    /* PIV=0b | Asso=00b | Designator Type=2h */
+		inq_response[6] = 0x00;    /* Rsvd */
+		inq_response[7] = len;     /* Designator Length */
+		memcpy(&inq_response[8], eui, len);
+	} else {
+ scsi_string:
+		if (alloc_len < 72) {
+			res = nvme_trans_completion(hdr,
+					SAM_STAT_CHECK_CONDITION,
+					ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
+					SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
+			goto out_free;
+		}
+		inq_response[3] = 0x48;    /* Page Length */
+		/* Designation Descriptor start */
+		inq_response[4] = 0x03;    /* Proto ID=0h | Code set=3h */
+		inq_response[5] = 0x08;    /* PIV=0b | Asso=00b | Designator Type=8h */
+		inq_response[6] = 0x00;    /* Rsvd */
+		inq_response[7] = 0x44;    /* Designator Length */
+
+		sprintf(&inq_response[8], "%04x", dev->pci_dev->vendor);
+		memcpy(&inq_response[12], dev->model, sizeof(dev->model));
+		sprintf(&inq_response[52], "%04x", tmp_id);
+		memcpy(&inq_response[56], dev->serial, sizeof(dev->serial));
+	}
+	xfer_len = alloc_len;
 	res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
 
  out_free:
@@ -1600,7 +1612,7 @@ static inline void nvme_trans_modesel_get_bd_len(u8 *parm_list, u8 cdb10,
 		/* 10 Byte CDB */
 		*bd_len = (parm_list[MODE_SELECT_10_BD_OFFSET] << 8) +
 			parm_list[MODE_SELECT_10_BD_OFFSET + 1];
-		*llbaa = parm_list[MODE_SELECT_10_LLBAA_OFFSET] &&
+		*llbaa = parm_list[MODE_SELECT_10_LLBAA_OFFSET] &
 				MODE_SELECT_10_LLBAA_MASK;
 	} else {
 		/* 6 Byte CDB */
@@ -2222,7 +2234,7 @@ static int nvme_trans_inquiry(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	page_code = GET_INQ_PAGE_CODE(cmd);
 	alloc_len = GET_INQ_ALLOC_LENGTH(cmd);
 
-	inq_response = kmalloc(STANDARD_INQUIRY_LENGTH, GFP_KERNEL);
+	inq_response = kmalloc(alloc_len, GFP_KERNEL);
 	if (inq_response == NULL) {
 		res = -ENOMEM;
 		goto out_mem;
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
index 79aa179305b5..e22942596207 100644
--- a/drivers/block/osdblk.c
+++ b/drivers/block/osdblk.c
@@ -423,7 +423,7 @@ static int osdblk_init_disk(struct osdblk_device *osdev)
 	}
 
 	/* switch queue to TCQ mode; allocate tag map */
-	rc = blk_queue_init_tags(q, OSDBLK_MAX_REQ, NULL);
+	rc = blk_queue_init_tags(q, OSDBLK_MAX_REQ, NULL, BLK_TAG_ALLOC_FIFO);
 	if (rc) {
 		blk_cleanup_queue(q);
 		put_disk(disk);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 3ec85dfce124..b40af3203089 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -38,6 +38,7 @@
 #include <linux/kernel.h>
 #include <linux/device.h>
 #include <linux/module.h>
+#include <linux/blk-mq.h>
 #include <linux/fs.h>
 #include <linux/blkdev.h>
 #include <linux/slab.h>
@@ -340,9 +341,7 @@ struct rbd_device {
 
 	char			name[DEV_NAME_LEN]; /* blkdev name, e.g. rbd3 */
 
-	struct list_head	rq_queue;	/* incoming rq queue */
 	spinlock_t		lock;		/* queue, flags, open_count */
-	struct work_struct	rq_work;
 
 	struct rbd_image_header	header;
 	unsigned long		flags;		/* possibly lock protected */
@@ -360,6 +359,9 @@ struct rbd_device {
 	atomic_t		parent_ref;
 	struct rbd_device	*parent;
 
+	/* Block layer tags. */
+	struct blk_mq_tag_set	tag_set;
+
 	/* protects updating the header */
 	struct rw_semaphore     header_rwsem;
 
@@ -1817,7 +1819,8 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
 
 	/*
 	 * We support a 64-bit length, but ultimately it has to be
-	 * passed to blk_end_request(), which takes an unsigned int.
+	 * passed to the block layer, which just supports a 32-bit
+	 * length field.
 	 */
 	obj_request->xferred = osd_req->r_reply_op_len[0];
 	rbd_assert(obj_request->xferred < (u64)UINT_MAX);
@@ -2098,32 +2101,26 @@ static void rbd_dev_parent_put(struct rbd_device *rbd_dev)
  * If an image has a non-zero parent overlap, get a reference to its
  * parent.
  *
- * We must get the reference before checking for the overlap to
- * coordinate properly with zeroing the parent overlap in
- * rbd_dev_v2_parent_info() when an image gets flattened.  We
- * drop it again if there is no overlap.
- *
  * Returns true if the rbd device has a parent with a non-zero
  * overlap and a reference for it was successfully taken, or
  * false otherwise.
  */
 static bool rbd_dev_parent_get(struct rbd_device *rbd_dev)
 {
-	int counter;
+	int counter = 0;
 
 	if (!rbd_dev->parent_spec)
 		return false;
 
-	counter = atomic_inc_return_safe(&rbd_dev->parent_ref);
-	if (counter > 0 && rbd_dev->parent_overlap)
-		return true;
-
-	/* Image was flattened, but parent is not yet torn down */
+	down_read(&rbd_dev->header_rwsem);
+	if (rbd_dev->parent_overlap)
+		counter = atomic_inc_return_safe(&rbd_dev->parent_ref);
+	up_read(&rbd_dev->header_rwsem);
 
 	if (counter < 0)
 		rbd_warn(rbd_dev, "parent reference overflow");
 
-	return false;
+	return counter > 0;
 }
 
 /*
@@ -2281,7 +2278,10 @@ static bool rbd_img_obj_end_request(struct rbd_obj_request *obj_request)
 		more = obj_request->which < img_request->obj_request_count - 1;
 	} else {
 		rbd_assert(img_request->rq != NULL);
-		more = blk_end_request(img_request->rq, result, xferred);
+
+		more = blk_update_request(img_request->rq, result, xferred);
+		if (!more)
+			__blk_mq_end_request(img_request->rq, result);
 	}
 
 	return more;
@@ -3310,8 +3310,10 @@ out:
 	return ret;
 }
 
-static void rbd_handle_request(struct rbd_device *rbd_dev, struct request *rq)
+static void rbd_queue_workfn(struct work_struct *work)
 {
+	struct request *rq = blk_mq_rq_from_pdu(work);
+	struct rbd_device *rbd_dev = rq->q->queuedata;
 	struct rbd_img_request *img_request;
 	struct ceph_snap_context *snapc = NULL;
 	u64 offset = (u64)blk_rq_pos(rq) << SECTOR_SHIFT;
@@ -3320,6 +3322,13 @@ static void rbd_handle_request(struct rbd_device *rbd_dev, struct request *rq)
 	u64 mapping_size;
 	int result;
 
+	if (rq->cmd_type != REQ_TYPE_FS) {
+		dout("%s: non-fs request type %d\n", __func__,
+			(int) rq->cmd_type);
+		result = -EIO;
+		goto err;
+	}
+
 	if (rq->cmd_flags & REQ_DISCARD)
 		op_type = OBJ_OP_DISCARD;
 	else if (rq->cmd_flags & REQ_WRITE)
@@ -3365,6 +3374,8 @@ static void rbd_handle_request(struct rbd_device *rbd_dev, struct request *rq)
 		goto err_rq;	/* Shouldn't happen */
 	}
 
+	blk_mq_start_request(rq);
+
 	down_read(&rbd_dev->header_rwsem);
 	mapping_size = rbd_dev->mapping.size;
 	if (op_type != OBJ_OP_READ) {
@@ -3410,53 +3421,18 @@ err_rq:
 		rbd_warn(rbd_dev, "%s %llx at %llx result %d",
 			 obj_op_name(op_type), length, offset, result);
 	ceph_put_snap_context(snapc);
-	blk_end_request_all(rq, result);
+err:
+	blk_mq_end_request(rq, result);
 }
 
-static void rbd_request_workfn(struct work_struct *work)
+static int rbd_queue_rq(struct blk_mq_hw_ctx *hctx,
+		const struct blk_mq_queue_data *bd)
 {
-	struct rbd_device *rbd_dev =
-	    container_of(work, struct rbd_device, rq_work);
-	struct request *rq, *next;
-	LIST_HEAD(requests);
+	struct request *rq = bd->rq;
+	struct work_struct *work = blk_mq_rq_to_pdu(rq);
 
-	spin_lock_irq(&rbd_dev->lock); /* rq->q->queue_lock */
-	list_splice_init(&rbd_dev->rq_queue, &requests);
-	spin_unlock_irq(&rbd_dev->lock);
-
-	list_for_each_entry_safe(rq, next, &requests, queuelist) {
-		list_del_init(&rq->queuelist);
-		rbd_handle_request(rbd_dev, rq);
-	}
-}
-
-/*
- * Called with q->queue_lock held and interrupts disabled, possibly on
- * the way to schedule().  Do not sleep here!
- */
-static void rbd_request_fn(struct request_queue *q)
-{
-	struct rbd_device *rbd_dev = q->queuedata;
-	struct request *rq;
-	int queued = 0;
-
-	rbd_assert(rbd_dev);
-
-	while ((rq = blk_fetch_request(q))) {
-		/* Ignore any non-FS requests that filter through. */
-		if (rq->cmd_type != REQ_TYPE_FS) {
-			dout("%s: non-fs request type %d\n", __func__,
-				(int) rq->cmd_type);
-			__blk_end_request_all(rq, 0);
-			continue;
-		}
-
-		list_add_tail(&rq->queuelist, &rbd_dev->rq_queue);
-		queued++;
-	}
-
-	if (queued)
-		queue_work(rbd_wq, &rbd_dev->rq_work);
+	queue_work(rbd_wq, work);
+	return BLK_MQ_RQ_QUEUE_OK;
 }
 
 /*
@@ -3517,6 +3493,7 @@ static void rbd_free_disk(struct rbd_device *rbd_dev)
 		del_gendisk(disk);
 		if (disk->queue)
 			blk_cleanup_queue(disk->queue);
+		blk_mq_free_tag_set(&rbd_dev->tag_set);
 	}
 	put_disk(disk);
 }
@@ -3700,7 +3677,7 @@ static int rbd_dev_refresh(struct rbd_device *rbd_dev)
 
 	ret = rbd_dev_header_info(rbd_dev);
 	if (ret)
-		return ret;
+		goto out;
 
 	/*
 	 * If there is a parent, see if it has disappeared due to the
@@ -3709,30 +3686,46 @@ static int rbd_dev_refresh(struct rbd_device *rbd_dev)
 	if (rbd_dev->parent) {
 		ret = rbd_dev_v2_parent_info(rbd_dev);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	if (rbd_dev->spec->snap_id == CEPH_NOSNAP) {
-		if (rbd_dev->mapping.size != rbd_dev->header.image_size)
-			rbd_dev->mapping.size = rbd_dev->header.image_size;
+		rbd_dev->mapping.size = rbd_dev->header.image_size;
 	} else {
 		/* validate mapped snapshot's EXISTS flag */
 		rbd_exists_validate(rbd_dev);
 	}
 
+out:
 	up_write(&rbd_dev->header_rwsem);
-
-	if (mapping_size != rbd_dev->mapping.size)
+	if (!ret && mapping_size != rbd_dev->mapping.size)
 		rbd_dev_update_size(rbd_dev);
 
+	return ret;
+}
+
+static int rbd_init_request(void *data, struct request *rq,
+		unsigned int hctx_idx, unsigned int request_idx,
+		unsigned int numa_node)
+{
+	struct work_struct *work = blk_mq_rq_to_pdu(rq);
+
+	INIT_WORK(work, rbd_queue_workfn);
 	return 0;
 }
 
+static struct blk_mq_ops rbd_mq_ops = {
+	.queue_rq	= rbd_queue_rq,
+	.map_queue	= blk_mq_map_queue,
+	.init_request	= rbd_init_request,
+};
+
 static int rbd_init_disk(struct rbd_device *rbd_dev)
 {
 	struct gendisk *disk;
 	struct request_queue *q;
 	u64 segment_size;
+	int err;
 
 	/* create gendisk info */
 	disk = alloc_disk(single_major ?
@@ -3750,10 +3743,25 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	disk->fops = &rbd_bd_ops;
 	disk->private_data = rbd_dev;
 
-	q = blk_init_queue(rbd_request_fn, &rbd_dev->lock);
-	if (!q)
+	memset(&rbd_dev->tag_set, 0, sizeof(rbd_dev->tag_set));
+	rbd_dev->tag_set.ops = &rbd_mq_ops;
+	rbd_dev->tag_set.queue_depth = BLKDEV_MAX_RQ;
+	rbd_dev->tag_set.numa_node = NUMA_NO_NODE;
+	rbd_dev->tag_set.flags =
+		BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+	rbd_dev->tag_set.nr_hw_queues = 1;
+	rbd_dev->tag_set.cmd_size = sizeof(struct work_struct);
+
+	err = blk_mq_alloc_tag_set(&rbd_dev->tag_set);
+	if (err)
 		goto out_disk;
 
+	q = blk_mq_init_queue(&rbd_dev->tag_set);
+	if (IS_ERR(q)) {
+		err = PTR_ERR(q);
+		goto out_tag_set;
+	}
+
 	/* We use the default size, but let's be explicit about it. */
 	blk_queue_physical_block_size(q, SECTOR_SIZE);
 
@@ -3779,10 +3787,11 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	rbd_dev->disk = disk;
 
 	return 0;
+out_tag_set:
+	blk_mq_free_tag_set(&rbd_dev->tag_set);
 out_disk:
 	put_disk(disk);
-
-	return -ENOMEM;
+	return err;
 }
 
 /*
@@ -4039,8 +4048,6 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
 		return NULL;
 
 	spin_lock_init(&rbd_dev->lock);
-	INIT_LIST_HEAD(&rbd_dev->rq_queue);
-	INIT_WORK(&rbd_dev->rq_work, rbd_request_workfn);
 	rbd_dev->flags = 0;
 	atomic_set(&rbd_dev->parent_ref, 0);
 	INIT_LIST_HEAD(&rbd_dev->node);
@@ -4239,7 +4246,6 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
 		 */
 		if (rbd_dev->parent_overlap) {
 			rbd_dev->parent_overlap = 0;
-			smp_mb();
 			rbd_dev_parent_put(rbd_dev);
 			pr_info("%s: clone image has been flattened\n",
 				rbd_dev->disk->disk_name);
@@ -4281,33 +4287,22 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
 	}
 
 	/*
-	 * We always update the parent overlap.  If it's zero we
-	 * treat it specially.
+	 * We always update the parent overlap.  If it's zero we issue
+	 * a warning, as we will proceed as if there was no parent.
 	 */
-	rbd_dev->parent_overlap = overlap;
-	smp_mb();
 	if (!overlap) {
-
-		/* A null parent_spec indicates it's the initial probe */
-
 		if (parent_spec) {
-			/*
-			 * The overlap has become zero, so the clone
-			 * must have been resized down to 0 at some
-			 * point.  Treat this the same as a flatten.
-			 */
-			rbd_dev_parent_put(rbd_dev);
-			pr_info("%s: clone image now standalone\n",
-				rbd_dev->disk->disk_name);
+			/* refresh, careful to warn just once */
+			if (rbd_dev->parent_overlap)
+				rbd_warn(rbd_dev,
+				    "clone now standalone (overlap became 0)");
 		} else {
-			/*
-			 * For the initial probe, if we find the
-			 * overlap is zero we just pretend there was
-			 * no parent image.
-			 */
-			rbd_warn(rbd_dev, "ignoring parent with overlap 0");
+			/* initial probe */
+			rbd_warn(rbd_dev, "clone is standalone (overlap 0)");
 		}
 	}
+	rbd_dev->parent_overlap = overlap;
+
 out:
 	ret = 0;
 out_err:
@@ -4779,36 +4774,6 @@ static inline size_t next_token(const char **buf)
 }
 
 /*
- * Finds the next token in *buf, and if the provided token buffer is
- * big enough, copies the found token into it.  The result, if
- * copied, is guaranteed to be terminated with '\0'.  Note that *buf
- * must be terminated with '\0' on entry.
- *
- * Returns the length of the token found (not including the '\0').
- * Return value will be 0 if no token is found, and it will be >=
- * token_size if the token would not fit.
- *
- * The *buf pointer will be updated to point beyond the end of the
- * found token.  Note that this occurs even if the token buffer is
- * too small to hold it.
- */
-static inline size_t copy_token(const char **buf,
-				char *token,
-				size_t token_size)
-{
-        size_t len;
-
-	len = next_token(buf);
-	if (len < token_size) {
-		memcpy(token, *buf, len);
-		*(token + len) = '\0';
-	}
-	*buf += len;
-
-        return len;
-}
-
-/*
  * Finds the next token in *buf, dynamically allocates a buffer big
  * enough to hold a copy of it, and copies the token into the new
  * buffer.  The copy is guaranteed to be terminated with '\0'.  Note
@@ -5114,10 +5079,7 @@ static void rbd_dev_unprobe(struct rbd_device *rbd_dev)
 {
 	struct rbd_image_header	*header;
 
-	/* Drop parent reference unless it's already been done (or none) */
-
-	if (rbd_dev->parent_overlap)
-		rbd_dev_parent_put(rbd_dev);
+	rbd_dev_parent_put(rbd_dev);
 
 	/* Free dynamic fields from the header, then zero it out */
 
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index cdfbd21e3597..655e570b9b31 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -28,8 +28,7 @@ struct virtio_blk_vq {
 	char name[VQ_NAME_LEN];
 } ____cacheline_aligned_in_smp;
 
-struct virtio_blk
-{
+struct virtio_blk {
 	struct virtio_device *vdev;
 
 	/* The disk structure for the kernel. */
@@ -52,8 +51,7 @@ struct virtio_blk
 	struct virtio_blk_vq *vqs;
 };
 
-struct virtblk_req
-{
+struct virtblk_req {
 	struct request *req;
 	struct virtio_blk_outhdr out_hdr;
 	struct virtio_scsi_inhdr in_hdr;
@@ -575,6 +573,12 @@ static int virtblk_probe(struct virtio_device *vdev)
 	u16 min_io_size;
 	u8 physical_block_exp, alignment_offset;
 
+	if (!vdev->config->get) {
+		dev_err(&vdev->dev, "%s failure: config access disabled\n",
+			__func__);
+		return -EINVAL;
+	}
+
 	err = ida_simple_get(&vd_index_ida, 0, minor_to_index(1 << MINORBITS),
 			     GFP_KERNEL);
 	if (err < 0)
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 63fc7f06a014..2a04d341e598 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -47,6 +47,7 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 #include <xen/balloon.h>
+#include <xen/grant_table.h>
 #include "common.h"
 
 /*
@@ -100,7 +101,7 @@ module_param(log_stats, int, 0644);
 
 #define BLKBACK_INVALID_HANDLE (~0)
 
-/* Number of free pages to remove on each call to free_xenballooned_pages */
+/* Number of free pages to remove on each call to gnttab_free_pages */
 #define NUM_BATCH_FREE_PAGES 10
 
 static inline int get_free_page(struct xen_blkif *blkif, struct page **page)
@@ -111,7 +112,7 @@ static inline int get_free_page(struct xen_blkif *blkif, struct page **page)
 	if (list_empty(&blkif->free_pages)) {
 		BUG_ON(blkif->free_pages_num != 0);
 		spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
-		return alloc_xenballooned_pages(1, page, false);
+		return gnttab_alloc_pages(1, page);
 	}
 	BUG_ON(blkif->free_pages_num == 0);
 	page[0] = list_first_entry(&blkif->free_pages, struct page, lru);
@@ -151,14 +152,14 @@ static inline void shrink_free_pagepool(struct xen_blkif *blkif, int num)
 		blkif->free_pages_num--;
 		if (++num_pages == NUM_BATCH_FREE_PAGES) {
 			spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
-			free_xenballooned_pages(num_pages, page);
+			gnttab_free_pages(num_pages, page);
 			spin_lock_irqsave(&blkif->free_pages_lock, flags);
 			num_pages = 0;
 		}
 	}
 	spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
 	if (num_pages != 0)
-		free_xenballooned_pages(num_pages, page);
+		gnttab_free_pages(num_pages, page);
 }
 
 #define vaddr(page) ((unsigned long)pfn_to_kaddr(page_to_pfn(page)))
@@ -262,6 +263,17 @@ static void put_persistent_gnt(struct xen_blkif *blkif,
 	atomic_dec(&blkif->persistent_gnt_in_use);
 }
 
+static void free_persistent_gnts_unmap_callback(int result,
+						struct gntab_unmap_queue_data *data)
+{
+	struct completion *c = data->data;
+
+	/* BUG_ON used to reproduce existing behaviour,
+	   but is this the best way to deal with this? */
+	BUG_ON(result);
+	complete(c);
+}
+
 static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root,
                                  unsigned int num)
 {
@@ -269,8 +281,17 @@ static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root,
 	struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	struct persistent_gnt *persistent_gnt;
 	struct rb_node *n;
-	int ret = 0;
 	int segs_to_unmap = 0;
+	struct gntab_unmap_queue_data unmap_data;
+	struct completion unmap_completion;
+
+	init_completion(&unmap_completion);
+
+	unmap_data.data = &unmap_completion;
+	unmap_data.done = &free_persistent_gnts_unmap_callback;
+	unmap_data.pages = pages;
+	unmap_data.unmap_ops = unmap;
+	unmap_data.kunmap_ops = NULL;
 
 	foreach_grant_safe(persistent_gnt, n, root, node) {
 		BUG_ON(persistent_gnt->handle ==
@@ -285,9 +306,11 @@ static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root,
 
 		if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST ||
 			!rb_next(&persistent_gnt->node)) {
-			ret = gnttab_unmap_refs(unmap, NULL, pages,
-				segs_to_unmap);
-			BUG_ON(ret);
+
+			unmap_data.count = segs_to_unmap;
+			gnttab_unmap_refs_async(&unmap_data);
+			wait_for_completion(&unmap_completion);
+
 			put_free_pages(blkif, pages, segs_to_unmap);
 			segs_to_unmap = 0;
 		}
@@ -653,18 +676,14 @@ void xen_blkbk_free_caches(struct xen_blkif *blkif)
 	shrink_free_pagepool(blkif, 0 /* All */);
 }
 
-/*
- * Unmap the grant references, and also remove the M2P over-rides
- * used in the 'pending_req'.
- */
-static void xen_blkbk_unmap(struct xen_blkif *blkif,
-                            struct grant_page *pages[],
-                            int num)
+static unsigned int xen_blkbk_unmap_prepare(
+	struct xen_blkif *blkif,
+	struct grant_page **pages,
+	unsigned int num,
+	struct gnttab_unmap_grant_ref *unmap_ops,
+	struct page **unmap_pages)
 {
-	struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
-	struct page *unmap_pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	unsigned int i, invcount = 0;
-	int ret;
 
 	for (i = 0; i < num; i++) {
 		if (pages[i]->persistent_gnt != NULL) {
@@ -674,21 +693,95 @@ static void xen_blkbk_unmap(struct xen_blkif *blkif,
 		if (pages[i]->handle == BLKBACK_INVALID_HANDLE)
 			continue;
 		unmap_pages[invcount] = pages[i]->page;
-		gnttab_set_unmap_op(&unmap[invcount], vaddr(pages[i]->page),
+		gnttab_set_unmap_op(&unmap_ops[invcount], vaddr(pages[i]->page),
 				    GNTMAP_host_map, pages[i]->handle);
 		pages[i]->handle = BLKBACK_INVALID_HANDLE;
-		if (++invcount == BLKIF_MAX_SEGMENTS_PER_REQUEST) {
-			ret = gnttab_unmap_refs(unmap, NULL, unmap_pages,
-			                        invcount);
+		invcount++;
+       }
+
+       return invcount;
+}
+
+static void xen_blkbk_unmap_and_respond_callback(int result, struct gntab_unmap_queue_data *data)
+{
+	struct pending_req* pending_req = (struct pending_req*) (data->data);
+	struct xen_blkif *blkif = pending_req->blkif;
+
+	/* BUG_ON used to reproduce existing behaviour,
+	   but is this the best way to deal with this? */
+	BUG_ON(result);
+
+	put_free_pages(blkif, data->pages, data->count);
+	make_response(blkif, pending_req->id,
+		      pending_req->operation, pending_req->status);
+	free_req(blkif, pending_req);
+	/*
+	 * Make sure the request is freed before releasing blkif,
+	 * or there could be a race between free_req and the
+	 * cleanup done in xen_blkif_free during shutdown.
+	 *
+	 * NB: The fact that we might try to wake up pending_free_wq
+	 * before drain_complete (in case there's a drain going on)
+	 * it's not a problem with our current implementation
+	 * because we can assure there's no thread waiting on
+	 * pending_free_wq if there's a drain going on, but it has
+	 * to be taken into account if the current model is changed.
+	 */
+	if (atomic_dec_and_test(&blkif->inflight) && atomic_read(&blkif->drain)) {
+		complete(&blkif->drain_complete);
+	}
+	xen_blkif_put(blkif);
+}
+
+static void xen_blkbk_unmap_and_respond(struct pending_req *req)
+{
+	struct gntab_unmap_queue_data* work = &req->gnttab_unmap_data;
+	struct xen_blkif *blkif = req->blkif;
+	struct grant_page **pages = req->segments;
+	unsigned int invcount;
+
+	invcount = xen_blkbk_unmap_prepare(blkif, pages, req->nr_pages,
+					   req->unmap, req->unmap_pages);
+
+	work->data = req;
+	work->done = xen_blkbk_unmap_and_respond_callback;
+	work->unmap_ops = req->unmap;
+	work->kunmap_ops = NULL;
+	work->pages = req->unmap_pages;
+	work->count = invcount;
+
+	gnttab_unmap_refs_async(&req->gnttab_unmap_data);
+}
+
+
+/*
+ * Unmap the grant references.
+ *
+ * This could accumulate ops up to the batch size to reduce the number
+ * of hypercalls, but since this is only used in error paths there's
+ * no real need.
+ */
+static void xen_blkbk_unmap(struct xen_blkif *blkif,
+                            struct grant_page *pages[],
+                            int num)
+{
+	struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+	struct page *unmap_pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+	unsigned int invcount = 0;
+	int ret;
+
+	while (num) {
+		unsigned int batch = min(num, BLKIF_MAX_SEGMENTS_PER_REQUEST);
+		
+		invcount = xen_blkbk_unmap_prepare(blkif, pages, batch,
+						   unmap, unmap_pages);
+		if (invcount) {
+			ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, invcount);
 			BUG_ON(ret);
 			put_free_pages(blkif, unmap_pages, invcount);
-			invcount = 0;
 		}
-	}
-	if (invcount) {
-		ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, invcount);
-		BUG_ON(ret);
-		put_free_pages(blkif, unmap_pages, invcount);
+		pages += batch;
+		num -= batch;
 	}
 }
 
@@ -982,32 +1075,8 @@ static void __end_block_io_op(struct pending_req *pending_req, int error)
 	 * the grant references associated with 'request' and provide
 	 * the proper response on the ring.
 	 */
-	if (atomic_dec_and_test(&pending_req->pendcnt)) {
-		struct xen_blkif *blkif = pending_req->blkif;
-
-		xen_blkbk_unmap(blkif,
-		                pending_req->segments,
-		                pending_req->nr_pages);
-		make_response(blkif, pending_req->id,
-			      pending_req->operation, pending_req->status);
-		free_req(blkif, pending_req);
-		/*
-		 * Make sure the request is freed before releasing blkif,
-		 * or there could be a race between free_req and the
-		 * cleanup done in xen_blkif_free during shutdown.
-		 *
-		 * NB: The fact that we might try to wake up pending_free_wq
-		 * before drain_complete (in case there's a drain going on)
-		 * it's not a problem with our current implementation
-		 * because we can assure there's no thread waiting on
-		 * pending_free_wq if there's a drain going on, but it has
-		 * to be taken into account if the current model is changed.
-		 */
-		if (atomic_dec_and_test(&blkif->inflight) && atomic_read(&blkif->drain)) {
-			complete(&blkif->drain_complete);
-		}
-		xen_blkif_put(blkif);
-	}
+	if (atomic_dec_and_test(&pending_req->pendcnt))
+		xen_blkbk_unmap_and_respond(pending_req);
 }
 
 /*
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index f65b807e3236..375d28851860 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -214,6 +214,15 @@ enum blkif_protocol {
 	BLKIF_PROTOCOL_X86_64 = 3,
 };
 
+/*
+ * Default protocol if the frontend doesn't specify one.
+ */
+#ifdef CONFIG_X86
+#  define BLKIF_PROTOCOL_DEFAULT BLKIF_PROTOCOL_X86_32
+#else
+#  define BLKIF_PROTOCOL_DEFAULT BLKIF_PROTOCOL_NATIVE
+#endif
+
 struct xen_vbd {
 	/* What the domain refers to this vbd as. */
 	blkif_vdev_t		handle;
@@ -350,6 +359,9 @@ struct pending_req {
 	struct grant_page	*indirect_pages[MAX_INDIRECT_PAGES];
 	struct seg_buf		seg[MAX_INDIRECT_SEGMENTS];
 	struct bio		*biolist[MAX_INDIRECT_SEGMENTS];
+	struct gnttab_unmap_grant_ref unmap[MAX_INDIRECT_SEGMENTS];
+	struct page                   *unmap_pages[MAX_INDIRECT_SEGMENTS];
+	struct gntab_unmap_queue_data gnttab_unmap_data;
 };
 
 
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 630a489e757d..e3afe97280b1 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -868,11 +868,11 @@ static int connect_ring(struct backend_info *be)
 		return err;
 	}
 
-	be->blkif->blk_protocol = BLKIF_PROTOCOL_NATIVE;
+	be->blkif->blk_protocol = BLKIF_PROTOCOL_DEFAULT;
 	err = xenbus_gather(XBT_NIL, dev->otherend, "protocol",
 			    "%63s", protocol, NULL);
 	if (err)
-		strcpy(protocol, "unspecified, assuming native");
+		strcpy(protocol, "unspecified, assuming default");
 	else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_NATIVE))
 		be->blkif->blk_protocol = BLKIF_PROTOCOL_NATIVE;
 	else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_X86_32))
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 2236c6f31608..37779e4c4585 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1391,7 +1391,7 @@ static int blkfront_probe(struct xenbus_device *dev,
 			if (major != XENVBD_MAJOR) {
 				printk(KERN_INFO
 						"%s: HVM does not support vbd %d as xen block device\n",
-						__FUNCTION__, vdevice);
+						__func__, vdevice);
 				return -ENODEV;
 			}
 		}
@@ -1511,7 +1511,7 @@ static int blkif_recover(struct blkfront_info *info)
 		merge_bio.tail = copy[i].request->biotail;
 		bio_list_merge(&bio_list, &merge_bio);
 		copy[i].request->bio = NULL;
-		blk_put_request(copy[i].request);
+		blk_end_request_all(copy[i].request, 0);
 	}
 
 	kfree(copy);
@@ -1534,7 +1534,7 @@ static int blkif_recover(struct blkfront_info *info)
 		req->bio = NULL;
 		if (req->cmd_flags & (REQ_FLUSH | REQ_FUA))
 			pr_alert("diskcache flush request found!\n");
-		__blk_put_request(info->rq, req);
+		__blk_end_request_all(req, 0);
 	}
 	spin_unlock_irq(&info->io_lock);
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index bd8bda386e02..871bd3550cb0 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -53,9 +53,9 @@ static ssize_t name##_show(struct device *d,		\
 }									\
 static DEVICE_ATTR_RO(name);
 
-static inline int init_done(struct zram *zram)
+static inline bool init_done(struct zram *zram)
 {
-	return zram->meta != NULL;
+	return zram->disksize;
 }
 
 static inline struct zram *dev_to_zram(struct device *dev)
@@ -307,42 +307,67 @@ static inline int valid_io_request(struct zram *zram,
 	return 1;
 }
 
-static void zram_meta_free(struct zram_meta *meta)
+static void zram_meta_free(struct zram_meta *meta, u64 disksize)
 {
+	size_t num_pages = disksize >> PAGE_SHIFT;
+	size_t index;
+
+	/* Free all pages that are still in this zram device */
+	for (index = 0; index < num_pages; index++) {
+		unsigned long handle = meta->table[index].handle;
+
+		if (!handle)
+			continue;
+
+		zs_free(meta->mem_pool, handle);
+	}
+
 	zs_destroy_pool(meta->mem_pool);
 	vfree(meta->table);
 	kfree(meta);
 }
 
-static struct zram_meta *zram_meta_alloc(u64 disksize)
+static struct zram_meta *zram_meta_alloc(int device_id, u64 disksize)
 {
 	size_t num_pages;
+	char pool_name[8];
 	struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL);
+
 	if (!meta)
-		goto out;
+		return NULL;
 
 	num_pages = disksize >> PAGE_SHIFT;
 	meta->table = vzalloc(num_pages * sizeof(*meta->table));
 	if (!meta->table) {
 		pr_err("Error allocating zram address table\n");
-		goto free_meta;
+		goto out_error;
 	}
 
-	meta->mem_pool = zs_create_pool(GFP_NOIO | __GFP_HIGHMEM);
+	snprintf(pool_name, sizeof(pool_name), "zram%d", device_id);
+	meta->mem_pool = zs_create_pool(pool_name, GFP_NOIO | __GFP_HIGHMEM);
 	if (!meta->mem_pool) {
 		pr_err("Error creating memory pool\n");
-		goto free_table;
+		goto out_error;
 	}
 
 	return meta;
 
-free_table:
+out_error:
 	vfree(meta->table);
-free_meta:
 	kfree(meta);
-	meta = NULL;
-out:
-	return meta;
+	return NULL;
+}
+
+static inline bool zram_meta_get(struct zram *zram)
+{
+	if (atomic_inc_not_zero(&zram->refcount))
+		return true;
+	return false;
+}
+
+static inline void zram_meta_put(struct zram *zram)
+{
+	atomic_dec(&zram->refcount);
 }
 
 static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
@@ -503,7 +528,7 @@ out_cleanup:
 static inline void update_used_max(struct zram *zram,
 					const unsigned long pages)
 {
-	int old_max, cur_max;
+	unsigned long old_max, cur_max;
 
 	old_max = atomic_long_read(&zram->stats.max_used_pages);
 
@@ -704,10 +729,11 @@ static void zram_bio_discard(struct zram *zram, u32 index,
 	}
 }
 
-static void zram_reset_device(struct zram *zram, bool reset_capacity)
+static void zram_reset_device(struct zram *zram)
 {
-	size_t index;
 	struct zram_meta *meta;
+	struct zcomp *comp;
+	u64 disksize;
 
 	down_write(&zram->init_lock);
 
@@ -719,36 +745,30 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity)
 	}
 
 	meta = zram->meta;
-	/* Free all pages that are still in this zram device */
-	for (index = 0; index < zram->disksize >> PAGE_SHIFT; index++) {
-		unsigned long handle = meta->table[index].handle;
-		if (!handle)
-			continue;
-
-		zs_free(meta->mem_pool, handle);
-	}
-
-	zcomp_destroy(zram->comp);
-	zram->max_comp_streams = 1;
+	comp = zram->comp;
+	disksize = zram->disksize;
+	/*
+	 * Refcount will go down to 0 eventually and r/w handler
+	 * cannot handle further I/O so it will bail out by
+	 * check zram_meta_get.
+	 */
+	zram_meta_put(zram);
+	/*
+	 * We want to free zram_meta in process context to avoid
+	 * deadlock between reclaim path and any other locks.
+	 */
+	wait_event(zram->io_done, atomic_read(&zram->refcount) == 0);
 
-	zram_meta_free(zram->meta);
-	zram->meta = NULL;
 	/* Reset stats */
 	memset(&zram->stats, 0, sizeof(zram->stats));
-
 	zram->disksize = 0;
-	if (reset_capacity)
-		set_capacity(zram->disk, 0);
+	zram->max_comp_streams = 1;
+	set_capacity(zram->disk, 0);
 
 	up_write(&zram->init_lock);
-
-	/*
-	 * Revalidate disk out of the init_lock to avoid lockdep splat.
-	 * It's okay because disk's capacity is protected by init_lock
-	 * so that revalidate_disk always sees up-to-date capacity.
-	 */
-	if (reset_capacity)
-		revalidate_disk(zram->disk);
+	/* I/O operation under all of CPU are done so let's free */
+	zram_meta_free(meta, disksize);
+	zcomp_destroy(comp);
 }
 
 static ssize_t disksize_store(struct device *dev,
@@ -765,7 +785,7 @@ static ssize_t disksize_store(struct device *dev,
 		return -EINVAL;
 
 	disksize = PAGE_ALIGN(disksize);
-	meta = zram_meta_alloc(disksize);
+	meta = zram_meta_alloc(zram->disk->first_minor, disksize);
 	if (!meta)
 		return -ENOMEM;
 
@@ -784,6 +804,8 @@ static ssize_t disksize_store(struct device *dev,
 		goto out_destroy_comp;
 	}
 
+	init_waitqueue_head(&zram->io_done);
+	atomic_set(&zram->refcount, 1);
 	zram->meta = meta;
 	zram->comp = comp;
 	zram->disksize = disksize;
@@ -803,7 +825,7 @@ out_destroy_comp:
 	up_write(&zram->init_lock);
 	zcomp_destroy(comp);
 out_free_meta:
-	zram_meta_free(meta);
+	zram_meta_free(meta, disksize);
 	return err;
 }
 
@@ -821,8 +843,9 @@ static ssize_t reset_store(struct device *dev,
 	if (!bdev)
 		return -ENOMEM;
 
+	mutex_lock(&bdev->bd_mutex);
 	/* Do not reset an active device! */
-	if (bdev->bd_holders) {
+	if (bdev->bd_openers) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -838,12 +861,16 @@ static ssize_t reset_store(struct device *dev,
 
 	/* Make sure all pending I/O is finished */
 	fsync_bdev(bdev);
+	zram_reset_device(zram);
+
+	mutex_unlock(&bdev->bd_mutex);
+	revalidate_disk(zram->disk);
 	bdput(bdev);
 
-	zram_reset_device(zram, true);
 	return len;
 
 out:
+	mutex_unlock(&bdev->bd_mutex);
 	bdput(bdev);
 	return ret;
 }
@@ -909,23 +936,21 @@ static void zram_make_request(struct request_queue *queue, struct bio *bio)
 {
 	struct zram *zram = queue->queuedata;
 
-	down_read(&zram->init_lock);
-	if (unlikely(!init_done(zram)))
+	if (unlikely(!zram_meta_get(zram)))
 		goto error;
 
 	if (!valid_io_request(zram, bio->bi_iter.bi_sector,
 					bio->bi_iter.bi_size)) {
 		atomic64_inc(&zram->stats.invalid_io);
-		goto error;
+		goto put_zram;
 	}
 
 	__zram_make_request(zram, bio);
-	up_read(&zram->init_lock);
-
+	zram_meta_put(zram);
 	return;
-
+put_zram:
+	zram_meta_put(zram);
 error:
-	up_read(&zram->init_lock);
 	bio_io_error(bio);
 }
 
@@ -947,21 +972,19 @@ static void zram_slot_free_notify(struct block_device *bdev,
 static int zram_rw_page(struct block_device *bdev, sector_t sector,
 		       struct page *page, int rw)
 {
-	int offset, err;
+	int offset, err = -EIO;
 	u32 index;
 	struct zram *zram;
 	struct bio_vec bv;
 
 	zram = bdev->bd_disk->private_data;
+	if (unlikely(!zram_meta_get(zram)))
+		goto out;
+
 	if (!valid_io_request(zram, sector, PAGE_SIZE)) {
 		atomic64_inc(&zram->stats.invalid_io);
-		return -EINVAL;
-	}
-
-	down_read(&zram->init_lock);
-	if (unlikely(!init_done(zram))) {
-		err = -EIO;
-		goto out_unlock;
+		err = -EINVAL;
+		goto put_zram;
 	}
 
 	index = sector >> SECTORS_PER_PAGE_SHIFT;
@@ -972,8 +995,9 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
 	bv.bv_offset = 0;
 
 	err = zram_bvec_rw(zram, &bv, index, offset, rw);
-out_unlock:
-	up_read(&zram->init_lock);
+put_zram:
+	zram_meta_put(zram);
+out:
 	/*
 	 * If I/O fails, just return error(ie, non-zero) without
 	 * calling page_endio.
@@ -1039,19 +1063,19 @@ static struct attribute_group zram_disk_attr_group = {
 
 static int create_device(struct zram *zram, int device_id)
 {
+	struct request_queue *queue;
 	int ret = -ENOMEM;
 
 	init_rwsem(&zram->init_lock);
 
-	zram->queue = blk_alloc_queue(GFP_KERNEL);
-	if (!zram->queue) {
+	queue = blk_alloc_queue(GFP_KERNEL);
+	if (!queue) {
 		pr_err("Error allocating disk queue for device %d\n",
 			device_id);
 		goto out;
 	}
 
-	blk_queue_make_request(zram->queue, zram_make_request);
-	zram->queue->queuedata = zram;
+	blk_queue_make_request(queue, zram_make_request);
 
 	 /* gendisk structure */
 	zram->disk = alloc_disk(1);
@@ -1064,7 +1088,8 @@ static int create_device(struct zram *zram, int device_id)
 	zram->disk->major = zram_major;
 	zram->disk->first_minor = device_id;
 	zram->disk->fops = &zram_devops;
-	zram->disk->queue = zram->queue;
+	zram->disk->queue = queue;
+	zram->disk->queue->queuedata = zram;
 	zram->disk->private_data = zram;
 	snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
 
@@ -1115,20 +1140,35 @@ out_free_disk:
 	del_gendisk(zram->disk);
 	put_disk(zram->disk);
 out_free_queue:
-	blk_cleanup_queue(zram->queue);
+	blk_cleanup_queue(queue);
 out:
 	return ret;
 }
 
-static void destroy_device(struct zram *zram)
+static void destroy_devices(unsigned int nr)
 {
-	sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
-			&zram_disk_attr_group);
+	struct zram *zram;
+	unsigned int i;
 
-	del_gendisk(zram->disk);
-	put_disk(zram->disk);
+	for (i = 0; i < nr; i++) {
+		zram = &zram_devices[i];
+		/*
+		 * Remove sysfs first, so no one will perform a disksize
+		 * store while we destroy the devices
+		 */
+		sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
+				&zram_disk_attr_group);
+
+		zram_reset_device(zram);
 
-	blk_cleanup_queue(zram->queue);
+		blk_cleanup_queue(zram->disk->queue);
+		del_gendisk(zram->disk);
+		put_disk(zram->disk);
+	}
+
+	kfree(zram_devices);
+	unregister_blkdev(zram_major, "zram");
+	pr_info("Destroyed %u device(s)\n", nr);
 }
 
 static int __init zram_init(void)
@@ -1138,64 +1178,39 @@ static int __init zram_init(void)
 	if (num_devices > max_num_devices) {
 		pr_warn("Invalid value for num_devices: %u\n",
 				num_devices);
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	zram_major = register_blkdev(0, "zram");
 	if (zram_major <= 0) {
 		pr_warn("Unable to get major number\n");
-		ret = -EBUSY;
-		goto out;
+		return -EBUSY;
 	}
 
 	/* Allocate the device array and initialize each one */
 	zram_devices = kzalloc(num_devices * sizeof(struct zram), GFP_KERNEL);
 	if (!zram_devices) {
-		ret = -ENOMEM;
-		goto unregister;
+		unregister_blkdev(zram_major, "zram");
+		return -ENOMEM;
 	}
 
 	for (dev_id = 0; dev_id < num_devices; dev_id++) {
 		ret = create_device(&zram_devices[dev_id], dev_id);
 		if (ret)
-			goto free_devices;
+			goto out_error;
 	}
 
-	pr_info("Created %u device(s) ...\n", num_devices);
-
+	pr_info("Created %u device(s)\n", num_devices);
 	return 0;
 
-free_devices:
-	while (dev_id)
-		destroy_device(&zram_devices[--dev_id]);
-	kfree(zram_devices);
-unregister:
-	unregister_blkdev(zram_major, "zram");
-out:
+out_error:
+	destroy_devices(dev_id);
 	return ret;
 }
 
 static void __exit zram_exit(void)
 {
-	int i;
-	struct zram *zram;
-
-	for (i = 0; i < num_devices; i++) {
-		zram = &zram_devices[i];
-
-		destroy_device(zram);
-		/*
-		 * Shouldn't access zram->disk after destroy_device
-		 * because destroy_device already released zram->disk.
-		 */
-		zram_reset_device(zram, false);
-	}
-
-	unregister_blkdev(zram_major, "zram");
-
-	kfree(zram_devices);
-	pr_debug("Cleanup done!\n");
+	destroy_devices(num_devices);
 }
 
 module_init(zram_init);
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index b05a816b09ac..17056e589146 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -100,24 +100,25 @@ struct zram_meta {
 
 struct zram {
 	struct zram_meta *meta;
-	struct request_queue *queue;
-	struct gendisk *disk;
 	struct zcomp *comp;
-
-	/* Prevent concurrent execution of device init, reset and R/W request */
+	struct gendisk *disk;
+	/* Prevent concurrent execution of device init */
 	struct rw_semaphore init_lock;
 	/*
-	 * This is the limit on amount of *uncompressed* worth of data
-	 * we can store in a disk.
+	 * the number of pages zram can consume for storing compressed data
 	 */
-	u64 disksize;	/* bytes */
+	unsigned long limit_pages;
 	int max_comp_streams;
+
 	struct zram_stats stats;
+	atomic_t refcount; /* refcount for zram_meta */
+	/* wait all IO under all of cpu are done */
+	wait_queue_head_t io_done;
 	/*
-	 * the number of pages zram can consume for storing compressed data
+	 * This is the limit on amount of *uncompressed* worth of data
+	 * we can store in a disk.
 	 */
-	unsigned long limit_pages;
-
+	u64 disksize;	/* bytes */
 	char compressor[10];
 };
 #endif