for-6.5/block-2023-06-23

-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAmSV8dwQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpilGD/9Yys1oxIXJpRf00fzrylAlBthRxMjFQVWw
 zAut106hAQiBHvU8IkmGA3MvEFVHxtzwYhHI7IR8K3aZBIqscweCqmVI9JyogJw9
 U9Twnzel47VmuKdM94FeoN+hbj1fP8EWTjzmy67/zEEfFCdmHvNlMi3lSrGYIpFy
 39LxTB99Y4UarM5PtWbes37GYYljzMSWKuo4AfBkvq1eQa+sZ0Vq2xAABKq3UM7f
 apqhgHtkJooRePDP0eQp+kAyyVMgW2jIK+oIdJDxNF3CKTu2w40RzaYz6fp+jVSU
 H4R/xS59GW4/xql+VBJDh/qJg9K62DPPYjlW8BmSR8+IjvfFpsyH3/MacE50CD3P
 20fs/Mnj49H79fDrQEHJI53cOOb2EmUitbwLbvOcColNTPpt8loBtdQxjF2RMU8R
 Nyort9DJPFclYCxky1LYg1CNEC2Ln4Zy/jD47wPvqRmOQphOoVlV/hPnOEqvjaZC
 49Vn70W2DeE9cXvYI7ha+XIg6/oj+Gs3iusEbV08Ci7EAtXgI+ZUUsQ97K8UNiUh
 h2lqSJtuI7lBpYP9sf+BeCch5UCC+xGYyTdoM5f58lehWBBPtbs0g7S9RyRyOYxe
 n+yxEUo3dAGzJ/xsKAjinbZfeWIpr0b1TkAh4w3Cq/BKzRr9Bp8lBAxYuancbQ+Y
 1ADPteUOTA==
 =zP4Y
 -----END PGP SIGNATURE-----

Merge tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull request via Keith:
      - Various cleanups all around (Irvin, Chaitanya, Christophe)
      - Better struct packing (Christophe JAILLET)
      - Reduce controller error logs for optional commands (Keith)
      - Support for >=64KiB block sizes (Daniel Gomez)
      - Fabrics fixes and code organization (Max, Chaitanya, Daniel
        Wagner)

 - bcache updates via Coly:
      - Fix a race at init time (Mingzhe Zou)
      - Misc fixes and cleanups (Andrea, Thomas, Zheng, Ye)

 - use page pinning in the block layer for dio (David)

 - convert old block dio code to page pinning (David, Christoph)

 - cleanups for pktcdvd (Andy)

 - cleanups for rnbd (Guoqing)

 - use the unchecked __bio_add_page() for the initial single page
   additions (Johannes)

 - fix overflows in the Amiga partition handling code (Michael)

 - improve mq-deadline zoned device support (Bart)

 - keep passthrough requests out of the IO schedulers (Christoph, Ming)

 - improve support for flush requests, making them less special to deal
   with (Christoph)

 - add bdev holder ops and shutdown methods (Christoph)

 - fix the name_to_dev_t() situation and use cases (Christoph)

 - decouple the block open flags from fmode_t (Christoph)

 - ublk updates and cleanups, including adding user copy support (Ming)

 - BFQ sanity checking (Bart)

 - convert brd from radix to xarray (Pankaj)

 - constify various structures (Thomas, Ivan)

 - more fine grained persistent reservation ioctl capability checks
   (Jingbo)

 - misc fixes and cleanups (Arnd, Azeem, Demi, Ed, Hengqi, Hou, Jan,
   Jordy, Li, Min, Yu, Zhong, Waiman)

* tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux: (266 commits)
  scsi/sg: don't grab scsi host module reference
  ext4: Fix warning in blkdev_put()
  block: don't return -EINVAL for not found names in devt_from_devname
  cdrom: Fix spectre-v1 gadget
  block: Improve kernel-doc headers
  blk-mq: don't insert passthrough request into sw queue
  bsg: make bsg_class a static const structure
  ublk: make ublk_chr_class a static const structure
  aoe: make aoe_class a static const structure
  block/rnbd: make all 'class' structures const
  block: fix the exclusive open mask in disk_scan_partitions
  block: add overflow checks for Amiga partition support
  block: change all __u32 annotations to __be32 in affs_hardblocks.h
  block: fix signed int overflow in Amiga partition support
  block: add capacity validation in bdev_add_partition()
  block: fine-granular CAP_SYS_ADMIN for Persistent Reservation
  block: disallow Persistent Reservation on partitions
  reiserfs: fix blkdev_put() warning from release_journal_dev()
  block: fix wrong mode for blkdev_get_by_dev() from disk_scan_partitions()
  block: document the holder argument to blkdev_get_by_path
  ...

Documentation/admin-guide/bcache.rst

@@ -508,9 +508,6 @@ cache_miss_collisions
   cache miss, but raced with a write and data was already present (usually 0
   since the synchronization for cache misses was rewritten)
 
-cache_readaheads
-  Count of times readahead occurred.
-
 Sysfs - cache set
 ~~~~~~~~~~~~~~~~~
 

Documentation/admin-guide/cgroup-v2.rst

@@ -2022,31 +2022,33 @@ that attribute:
   no-change
 	Do not modify the I/O priority class.
 
-  none-to-rt
+  promote-to-rt
-	For requests that do not have an I/O priority class (NONE),
+	For requests that have a non-RT I/O priority class, change it into RT.
-	change the I/O priority class into RT. Do not modify
+	Also change the priority level of these requests to 4. Do not modify
-	the I/O priority class of other requests.
+	the I/O priority of requests that have priority class RT.
 
   restrict-to-be
 	For requests that do not have an I/O priority class or that have I/O
-	priority class RT, change it into BE. Do not modify the I/O priority
+	priority class RT, change it into BE. Also change the priority level
-	class of requests that have priority class IDLE.
+	of these requests to 0. Do not modify the I/O priority class of
+	requests that have priority class IDLE.
 
   idle
 	Change the I/O priority class of all requests into IDLE, the lowest
 	I/O priority class.
 
+  none-to-rt
+	Deprecated. Just an alias for promote-to-rt.
+
 The following numerical values are associated with the I/O priority policies:
 
-+-------------+---+
++----------------+---+
-| no-change   | 0 |
+| no-change      | 0 |
-+-------------+---+
++----------------+---+
-| none-to-rt  | 1 |
+| rt-to-be       | 2 |
-+-------------+---+
++----------------+---+
-| rt-to-be    | 2 |
+| all-to-idle    | 3 |
-+-------------+---+
++----------------+---+
-| all-to-idle | 3 |
-+-------------+---+
 
 The numerical value that corresponds to each I/O priority class is as follows:
 
@@ -2062,9 +2064,13 @@ The numerical value that corresponds to each I/O priority class is as follows:
 
 The algorithm to set the I/O priority class for a request is as follows:
 
-- Translate the I/O priority class policy into a number.
+- If I/O priority class policy is promote-to-rt, change the request I/O
-- Change the request I/O priority class into the maximum of the I/O priority
+  priority class to IOPRIO_CLASS_RT and change the request I/O priority
-  class policy number and the numerical I/O priority class.
+  level to 4.
+- If I/O priorityt class is not promote-to-rt, translate the I/O priority
+  class policy into a number, then change the request I/O priority class
+  into the maximum of the I/O priority class policy number and the numerical
+  I/O priority class.
 
 PID
 ---

Documentation/admin-guide/kernel-parameters.txt

@@ -5452,7 +5452,12 @@
 			port and the regular usb controller gets disabled.
 
 	root=		[KNL] Root filesystem
-			See name_to_dev_t comment in init/do_mounts.c.
+			Usually this a a block device specifier of some kind,
+			see the early_lookup_bdev comment in
+			block/early-lookup.c for details.
+			Alternatively this can be "ram" for the legacy initial
+			ramdisk, "nfs" and "cifs" for root on a network file
+			system, or "mtd" and "ubi" for mounting from raw flash.
 
 	rootdelay=	[KNL] Delay (in seconds) to pause before attempting to
 			mount the root filesystem

Documentation/core-api/pin_user_pages.rst

@@ -112,6 +112,12 @@ pages:
 This also leads to limitations: there are only 31-10==21 bits available for a
 counter that increments 10 bits at a time.
 
+* Because of that limitation, special handling is applied to the zero pages
+  when using FOLL_PIN.  We only pretend to pin a zero page - we don't alter its
+  refcount or pincount at all (it is permanent, so there's no need).  The
+  unpinning functions also don't do anything to a zero page.  This is
+  transparent to the caller.
+
 * Callers must specifically request "dma-pinned tracking of pages". In other
   words, just calling get_user_pages() will not suffice; a new set of functions,
   pin_user_page() and related, must be used.

arch/alpha/kernel/setup.c

@@ -658,7 +658,7 @@ setup_arch(char **cmdline_p)
 #endif
 
 	/* Default root filesystem to sda2.  */
-	ROOT_DEV = Root_SDA2;
+	ROOT_DEV = MKDEV(SCSI_DISK0_MAJOR, 2);
 
 #ifdef CONFIG_EISA
 	/* FIXME:  only set this when we actually have EISA in this box? */

arch/ia64/kernel/setup.c

@@ -627,7 +627,7 @@ setup_arch (char **cmdline_p)
 	 * is physical disk 1 partition 1 and the Linux root disk is
 	 * physical disk 1 partition 2.
 	 */
-	ROOT_DEV = Root_SDA2;		/* default to second partition on first drive */
+	ROOT_DEV = MKDEV(SCSI_DISK0_MAJOR, 2);
 
 	if (is_uv_system())
 		uv_setup(cmdline_p);

arch/powerpc/platforms/powermac/setup.c

@@ -76,7 +76,8 @@ int pmac_newworld;
 
 static int current_root_goodness = -1;
 
-#define DEFAULT_ROOT_DEVICE Root_SDA1	/* sda1 - slightly silly choice */
+/* sda1 - slightly silly choice */
+#define DEFAULT_ROOT_DEVICE	MKDEV(SCSI_DISK0_MAJOR, 1)
 
 sys_ctrler_t sys_ctrler = SYS_CTRLER_UNKNOWN;
 EXPORT_SYMBOL(sys_ctrler);

arch/um/drivers/ubd_kern.c

@@ -108,9 +108,9 @@ static inline void ubd_set_bit(__u64 bit, unsigned char *data)
 static DEFINE_MUTEX(ubd_lock);
 static DEFINE_MUTEX(ubd_mutex); /* replaces BKL, might not be needed */
 
-static int ubd_open(struct block_device *bdev, fmode_t mode);
+static int ubd_open(struct gendisk *disk, blk_mode_t mode);
-static void ubd_release(struct gendisk *disk, fmode_t mode);
+static void ubd_release(struct gendisk *disk);
-static int ubd_ioctl(struct block_device *bdev, fmode_t mode,
+static int ubd_ioctl(struct block_device *bdev, blk_mode_t mode,
 		     unsigned int cmd, unsigned long arg);
 static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo);
 
@@ -1154,9 +1154,8 @@ static int __init ubd_driver_init(void){
 
 device_initcall(ubd_driver_init);
 
-static int ubd_open(struct block_device *bdev, fmode_t mode)
+static int ubd_open(struct gendisk *disk, blk_mode_t mode)
 {
-	struct gendisk *disk = bdev->bd_disk;
 	struct ubd *ubd_dev = disk->private_data;
 	int err = 0;
 
@@ -1171,19 +1170,12 @@ static int ubd_open(struct block_device *bdev, fmode_t mode)
 	}
 	ubd_dev->count++;
 	set_disk_ro(disk, !ubd_dev->openflags.w);
-
-	/* This should no more be needed. And it didn't work anyway to exclude
-	 * read-write remounting of filesystems.*/
-	/*if((mode & FMODE_WRITE) && !ubd_dev->openflags.w){
-	        if(--ubd_dev->count == 0) ubd_close_dev(ubd_dev);
-	        err = -EROFS;
-	}*/
 out:
 	mutex_unlock(&ubd_mutex);
 	return err;
 }
 
-static void ubd_release(struct gendisk *disk, fmode_t mode)
+static void ubd_release(struct gendisk *disk)
 {
 	struct ubd *ubd_dev = disk->private_data;
 
@@ -1397,7 +1389,7 @@ static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return 0;
 }
 
-static int ubd_ioctl(struct block_device *bdev, fmode_t mode,
+static int ubd_ioctl(struct block_device *bdev, blk_mode_t mode,
 		     unsigned int cmd, unsigned long arg)
 {
 	struct ubd *ubd_dev = bdev->bd_disk->private_data;

arch/xtensa/platforms/iss/simdisk.c

@@ -120,9 +120,9 @@ static void simdisk_submit_bio(struct bio *bio)
 	bio_endio(bio);
 }
 
-static int simdisk_open(struct block_device *bdev, fmode_t mode)
+static int simdisk_open(struct gendisk *disk, blk_mode_t mode)
 {
-	struct simdisk *dev = bdev->bd_disk->private_data;
+	struct simdisk *dev = disk->private_data;
 
 	spin_lock(&dev->lock);
 	++dev->users;
@@ -130,7 +130,7 @@ static int simdisk_open(struct block_device *bdev, fmode_t mode)
 	return 0;
 }
 
-static void simdisk_release(struct gendisk *disk, fmode_t mode)
+static void simdisk_release(struct gendisk *disk)
 {
 	struct simdisk *dev = disk->private_data;
 	spin_lock(&dev->lock);

block/Makefile

@@ -9,7 +9,7 @@ obj-y		:= bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
 			genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \
-			disk-events.o blk-ia-ranges.o
+			disk-events.o blk-ia-ranges.o early-lookup.o
 
 obj-$(CONFIG_BOUNCE)		+= bounce.o
 obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o

block/bdev.c

@@ -93,7 +93,7 @@ EXPORT_SYMBOL(invalidate_bdev);
  * Drop all buffers & page cache for given bdev range. This function bails
  * with error if bdev has other exclusive owner (such as filesystem).
  */
-int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
+int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode,
 			loff_t lstart, loff_t lend)
 {
 	/*
@@ -101,14 +101,14 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
 	 * while we discard the buffer cache to avoid discarding buffers
 	 * under live filesystem.
 	 */
-	if (!(mode & FMODE_EXCL)) {
+	if (!(mode & BLK_OPEN_EXCL)) {
-		int err = bd_prepare_to_claim(bdev, truncate_bdev_range);
+		int err = bd_prepare_to_claim(bdev, truncate_bdev_range, NULL);
 		if (err)
 			goto invalidate;
 	}
 
 	truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend);
-	if (!(mode & FMODE_EXCL))
+	if (!(mode & BLK_OPEN_EXCL))
 		bd_abort_claiming(bdev, truncate_bdev_range);
 	return 0;
 
@@ -308,7 +308,7 @@ EXPORT_SYMBOL(thaw_bdev);
  * pseudo-fs
  */
 
-static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock);
+static  __cacheline_aligned_in_smp DEFINE_MUTEX(bdev_lock);
 static struct kmem_cache * bdev_cachep __read_mostly;
 
 static struct inode *bdev_alloc_inode(struct super_block *sb)
@@ -415,6 +415,7 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	bdev = I_BDEV(inode);
 	mutex_init(&bdev->bd_fsfreeze_mutex);
 	spin_lock_init(&bdev->bd_size_lock);
+	mutex_init(&bdev->bd_holder_lock);
 	bdev->bd_partno = partno;
 	bdev->bd_inode = inode;
 	bdev->bd_queue = disk->queue;
@@ -463,39 +464,48 @@ long nr_blockdev_pages(void)
 /**
  * bd_may_claim - test whether a block device can be claimed
  * @bdev: block device of interest
- * @whole: whole block device containing @bdev, may equal @bdev
  * @holder: holder trying to claim @bdev
+ * @hops: holder ops
  *
  * Test whether @bdev can be claimed by @holder.
  *
- * CONTEXT:
- * spin_lock(&bdev_lock).
- *
  * RETURNS:
  * %true if @bdev can be claimed, %false otherwise.
  */
-static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
+static bool bd_may_claim(struct block_device *bdev, void *holder,
-			 void *holder)
+		const struct blk_holder_ops *hops)
 {
-	if (bdev->bd_holder == holder)
+	struct block_device *whole = bdev_whole(bdev);
-		return true;	 /* already a holder */
-	else if (bdev->bd_holder != NULL)
-		return false; 	 /* held by someone else */
-	else if (whole == bdev)
-		return true;  	 /* is a whole device which isn't held */
 
-	else if (whole->bd_holder == bd_may_claim)
+	lockdep_assert_held(&bdev_lock);
-		return true; 	 /* is a partition of a device that is being partitioned */
+
-	else if (whole->bd_holder != NULL)
+	if (bdev->bd_holder) {
-		return false;	 /* is a partition of a held device */
+		/*
-	else
+		 * The same holder can always re-claim.
-		return true;	 /* is a partition of an un-held device */
+		 */
+		if (bdev->bd_holder == holder) {
+			if (WARN_ON_ONCE(bdev->bd_holder_ops != hops))
+				return false;
+			return true;
+		}
+		return false;
+	}
+
+	/*
+	 * If the whole devices holder is set to bd_may_claim, a partition on
+	 * the device is claimed, but not the whole device.
+	 */
+	if (whole != bdev &&
+	    whole->bd_holder && whole->bd_holder != bd_may_claim)
+		return false;
+	return true;
 }
 
 /**
  * bd_prepare_to_claim - claim a block device
  * @bdev: block device of interest
  * @holder: holder trying to claim @bdev
+ * @hops: holder ops.
  *
  * Claim @bdev.  This function fails if @bdev is already claimed by another
  * holder and waits if another claiming is in progress. return, the caller
@@ -504,17 +514,18 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
  * RETURNS:
  * 0 if @bdev can be claimed, -EBUSY otherwise.
  */
-int bd_prepare_to_claim(struct block_device *bdev, void *holder)
+int bd_prepare_to_claim(struct block_device *bdev, void *holder,
+		const struct blk_holder_ops *hops)
 {
 	struct block_device *whole = bdev_whole(bdev);
 
 	if (WARN_ON_ONCE(!holder))
 		return -EINVAL;
 retry:
-	spin_lock(&bdev_lock);
+	mutex_lock(&bdev_lock);
 	/* if someone else claimed, fail */
-	if (!bd_may_claim(bdev, whole, holder)) {
+	if (!bd_may_claim(bdev, holder, hops)) {
-		spin_unlock(&bdev_lock);
+		mutex_unlock(&bdev_lock);
 		return -EBUSY;
 	}
 
@@ -524,7 +535,7 @@ retry:
 		DEFINE_WAIT(wait);
 
 		prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
-		spin_unlock(&bdev_lock);
+		mutex_unlock(&bdev_lock);
 		schedule();
 		finish_wait(wq, &wait);
 		goto retry;
@@ -532,7 +543,7 @@ retry:
 
 	/* yay, all mine */
 	whole->bd_claiming = holder;
-	spin_unlock(&bdev_lock);
+	mutex_unlock(&bdev_lock);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */
@@ -550,16 +561,18 @@ static void bd_clear_claiming(struct block_device *whole, void *holder)
  * bd_finish_claiming - finish claiming of a block device
  * @bdev: block device of interest
  * @holder: holder that has claimed @bdev
+ * @hops: block device holder operations
  *
  * Finish exclusive open of a block device. Mark the device as exlusively
  * open by the holder and wake up all waiters for exclusive open to finish.
  */
-static void bd_finish_claiming(struct block_device *bdev, void *holder)
+static void bd_finish_claiming(struct block_device *bdev, void *holder,
+		const struct blk_holder_ops *hops)
 {
 	struct block_device *whole = bdev_whole(bdev);
 
-	spin_lock(&bdev_lock);
+	mutex_lock(&bdev_lock);
-	BUG_ON(!bd_may_claim(bdev, whole, holder));
+	BUG_ON(!bd_may_claim(bdev, holder, hops));
 	/*
 	 * Note that for a whole device bd_holders will be incremented twice,
 	 * and bd_holder will be set to bd_may_claim before being set to holder
@@ -567,9 +580,12 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder)
 	whole->bd_holders++;
 	whole->bd_holder = bd_may_claim;
 	bdev->bd_holders++;
+	mutex_lock(&bdev->bd_holder_lock);
 	bdev->bd_holder = holder;
+	bdev->bd_holder_ops = hops;
+	mutex_unlock(&bdev->bd_holder_lock);
 	bd_clear_claiming(whole, holder);
-	spin_unlock(&bdev_lock);
+	mutex_unlock(&bdev_lock);
 }
 
 /**
@@ -583,12 +599,47 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder)
  */
 void bd_abort_claiming(struct block_device *bdev, void *holder)
 {
-	spin_lock(&bdev_lock);
+	mutex_lock(&bdev_lock);
 	bd_clear_claiming(bdev_whole(bdev), holder);
-	spin_unlock(&bdev_lock);
+	mutex_unlock(&bdev_lock);
 }
 EXPORT_SYMBOL(bd_abort_claiming);
 
+static void bd_end_claim(struct block_device *bdev, void *holder)
+{
+	struct block_device *whole = bdev_whole(bdev);
+	bool unblock = false;
+
+	/*
+	 * Release a claim on the device.  The holder fields are protected with
+	 * bdev_lock.  open_mutex is used to synchronize disk_holder unlinking.
+	 */
+	mutex_lock(&bdev_lock);
+	WARN_ON_ONCE(bdev->bd_holder != holder);
+	WARN_ON_ONCE(--bdev->bd_holders < 0);
+	WARN_ON_ONCE(--whole->bd_holders < 0);
+	if (!bdev->bd_holders) {
+		mutex_lock(&bdev->bd_holder_lock);
+		bdev->bd_holder = NULL;
+		bdev->bd_holder_ops = NULL;
+		mutex_unlock(&bdev->bd_holder_lock);
+		if (bdev->bd_write_holder)
+			unblock = true;
+	}
+	if (!whole->bd_holders)
+		whole->bd_holder = NULL;
+	mutex_unlock(&bdev_lock);
+
+	/*
+	 * If this was the last claim, remove holder link and unblock evpoll if
+	 * it was a write holder.
+	 */
+	if (unblock) {
+		disk_unblock_events(bdev->bd_disk);
+		bdev->bd_write_holder = false;
+	}
+}
+
 static void blkdev_flush_mapping(struct block_device *bdev)
 {
 	WARN_ON_ONCE(bdev->bd_holders);
@@ -597,13 +648,13 @@ static void blkdev_flush_mapping(struct block_device *bdev)
 	bdev_write_inode(bdev);
 }
 
-static int blkdev_get_whole(struct block_device *bdev, fmode_t mode)
+static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode)
 {
 	struct gendisk *disk = bdev->bd_disk;
 	int ret;
 
 	if (disk->fops->open) {
-		ret = disk->fops->open(bdev, mode);
+		ret = disk->fops->open(disk, mode);
 		if (ret) {
 			/* avoid ghost partitions on a removed medium */
 			if (ret == -ENOMEDIUM &&
@@ -621,22 +672,19 @@ static int blkdev_get_whole(struct block_device *bdev, fmode_t mode)
 	return 0;
 }
 
-static void blkdev_put_whole(struct block_device *bdev, fmode_t mode)
+static void blkdev_put_whole(struct block_device *bdev)
 {
 	if (atomic_dec_and_test(&bdev->bd_openers))
 		blkdev_flush_mapping(bdev);
 	if (bdev->bd_disk->fops->release)
-		bdev->bd_disk->fops->release(bdev->bd_disk, mode);
+		bdev->bd_disk->fops->release(bdev->bd_disk);
 }
 
-static int blkdev_get_part(struct block_device *part, fmode_t mode)
+static int blkdev_get_part(struct block_device *part, blk_mode_t mode)
 {
 	struct gendisk *disk = part->bd_disk;
 	int ret;
 
-	if (atomic_read(&part->bd_openers))
-		goto done;
-
 	ret = blkdev_get_whole(bdev_whole(part), mode);
 	if (ret)
 		return ret;
@@ -645,26 +693,27 @@ static int blkdev_get_part(struct block_device *part, fmode_t mode)
 	if (!bdev_nr_sectors(part))
 		goto out_blkdev_put;
 
-	disk->open_partitions++;
+	if (!atomic_read(&part->bd_openers)) {
-	set_init_blocksize(part);
+		disk->open_partitions++;
-done:
+		set_init_blocksize(part);
+	}
 	atomic_inc(&part->bd_openers);
 	return 0;
 
 out_blkdev_put:
-	blkdev_put_whole(bdev_whole(part), mode);
+	blkdev_put_whole(bdev_whole(part));
 	return ret;
 }
 
-static void blkdev_put_part(struct block_device *part, fmode_t mode)
+static void blkdev_put_part(struct block_device *part)
 {
 	struct block_device *whole = bdev_whole(part);
 
-	if (!atomic_dec_and_test(&part->bd_openers))
+	if (atomic_dec_and_test(&part->bd_openers)) {
-		return;
+		blkdev_flush_mapping(part);
-	blkdev_flush_mapping(part);
+		whole->bd_disk->open_partitions--;
-	whole->bd_disk->open_partitions--;
+	}
-	blkdev_put_whole(whole, mode);
+	blkdev_put_whole(whole);
 }
 
 struct block_device *blkdev_get_no_open(dev_t dev)
@@ -699,13 +748,13 @@ void blkdev_put_no_open(struct block_device *bdev)
 /**
  * blkdev_get_by_dev - open a block device by device number
  * @dev: device number of block device to open
- * @mode: FMODE_* mask
+ * @mode: open mode (BLK_OPEN_*)
  * @holder: exclusive holder identifier
+ * @hops: holder operations
  *
- * Open the block device described by device number @dev. If @mode includes
+ * Open the block device described by device number @dev. If @holder is not
- * %FMODE_EXCL, the block device is opened with exclusive access.  Specifying
+ * %NULL, the block device is opened with exclusive access.  Exclusive opens may
- * %FMODE_EXCL with a %NULL @holder is invalid.  Exclusive opens may nest for
+ * nest for the same @holder.
- * the same @holder.
  *
  * Use this interface ONLY if you really do not have anything better - i.e. when
  * you are behind a truly sucky interface and all you are given is a device
@@ -717,7 +766,8 @@ void blkdev_put_no_open(struct block_device *bdev)
  * RETURNS:
  * Reference to the block_device on success, ERR_PTR(-errno) on failure.
  */
-struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
+struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder,
+		const struct blk_holder_ops *hops)
 {
 	bool unblock_events = true;
 	struct block_device *bdev;
@@ -726,8 +776,8 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 
 	ret = devcgroup_check_permission(DEVCG_DEV_BLOCK,
 			MAJOR(dev), MINOR(dev),
-			((mode & FMODE_READ) ? DEVCG_ACC_READ : 0) |
+			((mode & BLK_OPEN_READ) ? DEVCG_ACC_READ : 0) |
-			((mode & FMODE_WRITE) ? DEVCG_ACC_WRITE : 0));
+			((mode & BLK_OPEN_WRITE) ? DEVCG_ACC_WRITE : 0));
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -736,10 +786,16 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 		return ERR_PTR(-ENXIO);
 	disk = bdev->bd_disk;
 
-	if (mode & FMODE_EXCL) {
+	if (holder) {
-		ret = bd_prepare_to_claim(bdev, holder);
+		mode |= BLK_OPEN_EXCL;
+		ret = bd_prepare_to_claim(bdev, holder, hops);
 		if (ret)
 			goto put_blkdev;
+	} else {
+		if (WARN_ON_ONCE(mode & BLK_OPEN_EXCL)) {
+			ret = -EIO;
+			goto put_blkdev;
+		}
 	}
 
 	disk_block_events(disk);
@@ -756,8 +812,8 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 		ret = blkdev_get_whole(bdev, mode);
 	if (ret)
 		goto put_module;
-	if (mode & FMODE_EXCL) {
+	if (holder) {
-		bd_finish_claiming(bdev, holder);
+		bd_finish_claiming(bdev, holder, hops);
 
 		/*
 		 * Block event polling for write claims if requested.  Any write
@@ -766,7 +822,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 		 * writeable reference is too fragile given the way @mode is
 		 * used in blkdev_get/put().
 		 */
-		if ((mode & FMODE_WRITE) && !bdev->bd_write_holder &&
+		if ((mode & BLK_OPEN_WRITE) && !bdev->bd_write_holder &&
 		    (disk->event_flags & DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE)) {
 			bdev->bd_write_holder = true;
 			unblock_events = false;
@@ -780,7 +836,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 put_module:
 	module_put(disk->fops->owner);
 abort_claiming:
-	if (mode & FMODE_EXCL)
+	if (holder)
 		bd_abort_claiming(bdev, holder);
 	mutex_unlock(&disk->open_mutex);
 	disk_unblock_events(disk);
@@ -793,13 +849,13 @@ EXPORT_SYMBOL(blkdev_get_by_dev);
 /**
  * blkdev_get_by_path - open a block device by name
  * @path: path to the block device to open
- * @mode: FMODE_* mask
+ * @mode: open mode (BLK_OPEN_*)
  * @holder: exclusive holder identifier
+ * @hops: holder operations
  *
- * Open the block device described by the device file at @path.  If @mode
+ * Open the block device described by the device file at @path.  If @holder is
- * includes %FMODE_EXCL, the block device is opened with exclusive access.
+ * not %NULL, the block device is opened with exclusive access.  Exclusive opens
- * Specifying %FMODE_EXCL with a %NULL @holder is invalid.  Exclusive opens may
+ * may nest for the same @holder.
- * nest for the same @holder.
  *
  * CONTEXT:
  * Might sleep.
@@ -807,8 +863,8 @@ EXPORT_SYMBOL(blkdev_get_by_dev);
  * RETURNS:
  * Reference to the block_device on success, ERR_PTR(-errno) on failure.
  */
-struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
+struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode,
-					void *holder)
+		void *holder, const struct blk_holder_ops *hops)
 {
 	struct block_device *bdev;
 	dev_t dev;
@@ -818,9 +874,9 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 	if (error)
 		return ERR_PTR(error);
 
-	bdev = blkdev_get_by_dev(dev, mode, holder);
+	bdev = blkdev_get_by_dev(dev, mode, holder, hops);
-	if (!IS_ERR(bdev) && (mode & FMODE_WRITE) && bdev_read_only(bdev)) {
+	if (!IS_ERR(bdev) && (mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) {
-		blkdev_put(bdev, mode);
+		blkdev_put(bdev, holder);
 		return ERR_PTR(-EACCES);
 	}
 
@@ -828,7 +884,7 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 }
 EXPORT_SYMBOL(blkdev_get_by_path);
 
-void blkdev_put(struct block_device *bdev, fmode_t mode)
+void blkdev_put(struct block_device *bdev, void *holder)
 {
 	struct gendisk *disk = bdev->bd_disk;
 
@@ -843,36 +899,8 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
 		sync_blockdev(bdev);
 
 	mutex_lock(&disk->open_mutex);
-	if (mode & FMODE_EXCL) {
+	if (holder)
-		struct block_device *whole = bdev_whole(bdev);
+		bd_end_claim(bdev, holder);
-		bool bdev_free;
-
-		/*
-		 * Release a claim on the device.  The holder fields
-		 * are protected with bdev_lock.  open_mutex is to
-		 * synchronize disk_holder unlinking.
-		 */
-		spin_lock(&bdev_lock);
-
-		WARN_ON_ONCE(--bdev->bd_holders < 0);
-		WARN_ON_ONCE(--whole->bd_holders < 0);
-
-		if ((bdev_free = !bdev->bd_holders))
-			bdev->bd_holder = NULL;
-		if (!whole->bd_holders)
-			whole->bd_holder = NULL;
-
-		spin_unlock(&bdev_lock);
-
-		/*
-		 * If this was the last claim, remove holder link and
-		 * unblock evpoll if it was a write holder.
-		 */
-		if (bdev_free && bdev->bd_write_holder) {
-			disk_unblock_events(disk);
-			bdev->bd_write_holder = false;
-		}
-	}
 
 	/*
 	 * Trigger event checking and tell drivers to flush MEDIA_CHANGE
@@ -882,9 +910,9 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
 	disk_flush_events(disk, DISK_EVENT_MEDIA_CHANGE);
 
 	if (bdev_is_partition(bdev))
-		blkdev_put_part(bdev, mode);
+		blkdev_put_part(bdev);
 	else
-		blkdev_put_whole(bdev, mode);
+		blkdev_put_whole(bdev);
 	mutex_unlock(&disk->open_mutex);
 
 	module_put(disk->fops->owner);

block/bfq-iosched.c

@@ -5403,6 +5403,10 @@ void bfq_put_queue(struct bfq_queue *bfqq)
 	if (bfqq->bfqd->last_completed_rq_bfqq == bfqq)
 		bfqq->bfqd->last_completed_rq_bfqq = NULL;
 
+	WARN_ON_ONCE(!list_empty(&bfqq->fifo));
+	WARN_ON_ONCE(!RB_EMPTY_ROOT(&bfqq->sort_list));
+	WARN_ON_ONCE(bfqq->dispatched);
+
 	kmem_cache_free(bfq_pool, bfqq);
 	bfqg_and_blkg_put(bfqg);
 }
@@ -7135,6 +7139,7 @@ static void bfq_exit_queue(struct elevator_queue *e)
 {
 	struct bfq_data *bfqd = e->elevator_data;
 	struct bfq_queue *bfqq, *n;
+	unsigned int actuator;
 
 	hrtimer_cancel(&bfqd->idle_slice_timer);
 
@@ -7143,6 +7148,10 @@ static void bfq_exit_queue(struct elevator_queue *e)
 		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
 	spin_unlock_irq(&bfqd->lock);
 
+	for (actuator = 0; actuator < bfqd->num_actuators; actuator++)
+		WARN_ON_ONCE(bfqd->rq_in_driver[actuator]);
+	WARN_ON_ONCE(bfqd->tot_rq_in_driver);
+
 	hrtimer_cancel(&bfqd->idle_slice_timer);
 
 	/* release oom-queue reference to root group */

block/bio.c

@@ -1138,6 +1138,14 @@ int bio_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_add_page);
 
+void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len,
+			  size_t off)
+{
+	WARN_ON_ONCE(len > UINT_MAX);
+	WARN_ON_ONCE(off > UINT_MAX);
+	__bio_add_page(bio, &folio->page, len, off);
+}
+
 /**
  * bio_add_folio - Attempt to add part of a folio to a bio.
  * @bio: BIO to add to.
@@ -1169,7 +1177,7 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty)
 	bio_for_each_segment_all(bvec, bio, iter_all) {
 		if (mark_dirty && !PageCompound(bvec->bv_page))
 			set_page_dirty_lock(bvec->bv_page);
-		put_page(bvec->bv_page);
+		bio_release_page(bio, bvec->bv_page);
 	}
 }
 EXPORT_SYMBOL_GPL(__bio_release_pages);
@@ -1191,7 +1199,6 @@ void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
 	bio->bi_io_vec = (struct bio_vec *)iter->bvec;
 	bio->bi_iter.bi_bvec_done = iter->iov_offset;
 	bio->bi_iter.bi_size = size;
-	bio_set_flag(bio, BIO_NO_PAGE_REF);
 	bio_set_flag(bio, BIO_CLONED);
 }
 
@@ -1206,7 +1213,7 @@ static int bio_iov_add_page(struct bio *bio, struct page *page,
 	}
 
 	if (same_page)
-		put_page(page);
+		bio_release_page(bio, page);
 	return 0;
 }
 
@@ -1220,7 +1227,7 @@ static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
 			queue_max_zone_append_sectors(q), &same_page) != len)
 		return -EINVAL;
 	if (same_page)
-		put_page(page);
+		bio_release_page(bio, page);
 	return 0;
 }
 
@@ -1231,10 +1238,10 @@ static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
  * @bio: bio to add pages to
  * @iter: iov iterator describing the region to be mapped
  *
- * Pins pages from *iter and appends them to @bio's bvec array. The
+ * Extracts pages from *iter and appends them to @bio's bvec array.  The pages
- * pages will have to be released using put_page() when done.
+ * will have to be cleaned up in the way indicated by the BIO_PAGE_PINNED flag.
- * For multi-segment *iter, this function only adds pages from the
+ * For a multi-segment *iter, this function only adds pages from the next
- * next non-empty segment of the iov iterator.
+ * non-empty segment of the iov iterator.
  */
 static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 {
@@ -1266,9 +1273,9 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	 * result to ensure the bio's total size is correct. The remainder of
 	 * the iov data will be picked up in the next bio iteration.
 	 */
-	size = iov_iter_get_pages(iter, pages,
+	size = iov_iter_extract_pages(iter, &pages,
-				  UINT_MAX - bio->bi_iter.bi_size,
+				      UINT_MAX - bio->bi_iter.bi_size,
-				  nr_pages, &offset, extraction_flags);
+				      nr_pages, extraction_flags, &offset);
 	if (unlikely(size <= 0))
 		return size ? size : -EFAULT;
 
@@ -1301,7 +1308,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	iov_iter_revert(iter, left);
 out:
 	while (i < nr_pages)
-		put_page(pages[i++]);
+		bio_release_page(bio, pages[i++]);
 
 	return ret;
 }
@@ -1336,6 +1343,8 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 		return 0;
 	}
 
+	if (iov_iter_extract_will_pin(iter))
+		bio_set_flag(bio, BIO_PAGE_PINNED);
 	do {
 		ret = __bio_iov_iter_get_pages(bio, iter);
 	} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
@@ -1489,8 +1498,8 @@ void bio_set_pages_dirty(struct bio *bio)
  * the BIO and re-dirty the pages in process context.
  *
  * It is expected that bio_check_pages_dirty() will wholly own the BIO from
- * here on.  It will run one put_page() against each page and will run one
+ * here on.  It will unpin each page and will run one bio_put() against the
- * bio_put() against the BIO.
+ * BIO.
  */
 
 static void bio_dirty_fn(struct work_struct *work);

block/blk-cgroup-fc-appid.c

@@ -34,7 +34,7 @@ int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len)
 	 * the vmid from the fabric.
 	 * Adding the overhead of a lock is not necessary.
 	 */
-	strlcpy(blkcg->fc_app_id, app_id, app_id_len);
+	strscpy(blkcg->fc_app_id, app_id, app_id_len);
 	css_put(css);
 out_cgrp_put:
 	cgroup_put(cgrp);

block/blk-cgroup.c

@@ -624,8 +624,13 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 			struct blkg_iostat_set *bis =
 				per_cpu_ptr(blkg->iostat_cpu, cpu);
 			memset(bis, 0, sizeof(*bis));
+
+			/* Re-initialize the cleared blkg_iostat_set */
+			u64_stats_init(&bis->sync);
+			bis->blkg = blkg;
 		}
 		memset(&blkg->iostat, 0, sizeof(blkg->iostat));
+		u64_stats_init(&blkg->iostat.sync);
 
 		for (i = 0; i < BLKCG_MAX_POLS; i++) {
 			struct blkcg_policy *pol = blkcg_policy[i];
@@ -762,6 +767,13 @@ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx)
 		return -ENODEV;
 	}
 
+	mutex_lock(&bdev->bd_queue->rq_qos_mutex);
+	if (!disk_live(bdev->bd_disk)) {
+		blkdev_put_no_open(bdev);
+		mutex_unlock(&bdev->bd_queue->rq_qos_mutex);
+		return -ENODEV;
+	}
+
 	ctx->body = input;
 	ctx->bdev = bdev;
 	return 0;
@@ -906,6 +918,7 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);
  */
 void blkg_conf_exit(struct blkg_conf_ctx *ctx)
 	__releases(&ctx->bdev->bd_queue->queue_lock)
+	__releases(&ctx->bdev->bd_queue->rq_qos_mutex)
 {
 	if (ctx->blkg) {
 		spin_unlock_irq(&bdev_get_queue(ctx->bdev)->queue_lock);
@@ -913,6 +926,7 @@ void blkg_conf_exit(struct blkg_conf_ctx *ctx)
 	}
 
 	if (ctx->bdev) {
+		mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex);
 		blkdev_put_no_open(ctx->bdev);
 		ctx->body = NULL;
 		ctx->bdev = NULL;

block/blk-core.c

@@ -420,6 +420,7 @@ struct request_queue *blk_alloc_queue(int node_id)
 	mutex_init(&q->debugfs_mutex);
 	mutex_init(&q->sysfs_lock);
 	mutex_init(&q->sysfs_dir_lock);
+	mutex_init(&q->rq_qos_mutex);
 	spin_lock_init(&q->queue_lock);
 
 	init_waitqueue_head(&q->mq_freeze_wq);

block/blk-flush.c

@@ -188,7 +188,9 @@ static void blk_flush_complete_seq(struct request *rq,
 
 	case REQ_FSEQ_DATA:
 		list_move_tail(&rq->flush.list, &fq->flush_data_in_flight);
-		blk_mq_add_to_requeue_list(rq, BLK_MQ_INSERT_AT_HEAD);
+		spin_lock(&q->requeue_lock);
+		list_add_tail(&rq->queuelist, &q->flush_list);
+		spin_unlock(&q->requeue_lock);
 		blk_mq_kick_requeue_list(q);
 		break;
 
@@ -346,7 +348,10 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
 	smp_wmb();
 	req_ref_set(flush_rq, 1);
 
-	blk_mq_add_to_requeue_list(flush_rq, 0);
+	spin_lock(&q->requeue_lock);
+	list_add_tail(&flush_rq->queuelist, &q->flush_list);
+	spin_unlock(&q->requeue_lock);
+
 	blk_mq_kick_requeue_list(q);
 }
 
@@ -376,22 +381,29 @@ static enum rq_end_io_ret mq_flush_data_end_io(struct request *rq,
 	return RQ_END_IO_NONE;
 }
 
-/**
+static void blk_rq_init_flush(struct request *rq)
- * blk_insert_flush - insert a new PREFLUSH/FUA request
+{
- * @rq: request to insert
+	rq->flush.seq = 0;
- *
+	INIT_LIST_HEAD(&rq->flush.list);
- * To be called from __elv_add_request() for %ELEVATOR_INSERT_FLUSH insertions.
+	rq->rq_flags |= RQF_FLUSH_SEQ;
- * or __blk_mq_run_hw_queue() to dispatch request.
+	rq->flush.saved_end_io = rq->end_io; /* Usually NULL */
- * @rq is being submitted.  Analyze what needs to be done and put it on the
+	rq->end_io = mq_flush_data_end_io;
- * right queue.
+}
+
+/*
+ * Insert a PREFLUSH/FUA request into the flush state machine.
+ * Returns true if the request has been consumed by the flush state machine,
+ * or false if the caller should continue to process it.
  */
-void blk_insert_flush(struct request *rq)
+bool blk_insert_flush(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 	unsigned long fflags = q->queue_flags;	/* may change, cache */
 	unsigned int policy = blk_flush_policy(fflags, rq);
 	struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx);
-	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
+	/* FLUSH/FUA request must never be merged */
+	WARN_ON_ONCE(rq->bio != rq->biotail);
 
 	/*
 	 * @policy now records what operations need to be done.  Adjust
@@ -408,45 +420,45 @@ void blk_insert_flush(struct request *rq)
 	 */
 	rq->cmd_flags |= REQ_SYNC;
 
-	/*
+	switch (policy) {
-	 * An empty flush handed down from a stacking driver may
+	case 0:
-	 * translate into nothing if the underlying device does not
+		/*
-	 * advertise a write-back cache.  In this case, simply
+		 * An empty flush handed down from a stacking driver may
-	 * complete the request.
+		 * translate into nothing if the underlying device does not
-	 */
+		 * advertise a write-back cache.  In this case, simply
-	if (!policy) {
+		 * complete the request.
+		 */
 		blk_mq_end_request(rq, 0);
-		return;
+		return true;
+	case REQ_FSEQ_DATA:
+		/*
+		 * If there's data, but no flush is necessary, the request can
+		 * be processed directly without going through flush machinery.
+		 * Queue for normal execution.
+		 */
+		return false;
+	case REQ_FSEQ_DATA | REQ_FSEQ_POSTFLUSH:
+		/*
+		 * Initialize the flush fields and completion handler to trigger
+		 * the post flush, and then just pass the command on.
+		 */
+		blk_rq_init_flush(rq);
+		rq->flush.seq |= REQ_FSEQ_POSTFLUSH;
+		spin_lock_irq(&fq->mq_flush_lock);
+		list_move_tail(&rq->flush.list, &fq->flush_data_in_flight);
+		spin_unlock_irq(&fq->mq_flush_lock);
+		return false;
+	default:
+		/*
+		 * Mark the request as part of a flush sequence and submit it
+		 * for further processing to the flush state machine.
+		 */
+		blk_rq_init_flush(rq);
+		spin_lock_irq(&fq->mq_flush_lock);
+		blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0);
+		spin_unlock_irq(&fq->mq_flush_lock);
+		return true;
 	}
-
-	BUG_ON(rq->bio != rq->biotail); /*assumes zero or single bio rq */
-
-	/*
-	 * If there's data but flush is not necessary, the request can be
-	 * processed directly without going through flush machinery.  Queue
-	 * for normal execution.
-	 */
-	if ((policy & REQ_FSEQ_DATA) &&
-	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
-		blk_mq_request_bypass_insert(rq, 0);
-		blk_mq_run_hw_queue(hctx, false);
-		return;
-	}
-
-	/*
-	 * @rq should go through flush machinery.  Mark it part of flush
-	 * sequence and submit for further processing.
-	 */
-	memset(&rq->flush, 0, sizeof(rq->flush));
-	INIT_LIST_HEAD(&rq->flush.list);
-	rq->rq_flags |= RQF_FLUSH_SEQ;
-	rq->flush.saved_end_io = rq->end_io; /* Usually NULL */
-
-	rq->end_io = mq_flush_data_end_io;
-
-	spin_lock_irq(&fq->mq_flush_lock);
-	blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0);
-	spin_unlock_irq(&fq->mq_flush_lock);
 }
 
 /**

block/blk-ioc.c

@@ -77,6 +77,10 @@ static void ioc_destroy_icq(struct io_cq *icq)
 	struct elevator_type *et = q->elevator->type;
 
 	lockdep_assert_held(&ioc->lock);
+	lockdep_assert_held(&q->queue_lock);
+
+	if (icq->flags & ICQ_DESTROYED)
+		return;
 
 	radix_tree_delete(&ioc->icq_tree, icq->q->id);
 	hlist_del_init(&icq->ioc_node);
@@ -128,12 +132,7 @@ static void ioc_release_fn(struct work_struct *work)
 			spin_lock(&q->queue_lock);
 			spin_lock(&ioc->lock);
 
-			/*
+			ioc_destroy_icq(icq);
-			 * The icq may have been destroyed when the ioc lock
-			 * was released.
-			 */
-			if (!(icq->flags & ICQ_DESTROYED))
-				ioc_destroy_icq(icq);
 
 			spin_unlock(&q->queue_lock);
 			rcu_read_unlock();
@@ -171,23 +170,20 @@ static bool ioc_delay_free(struct io_context *ioc)
  */
 void ioc_clear_queue(struct request_queue *q)
 {
-	LIST_HEAD(icq_list);
-
 	spin_lock_irq(&q->queue_lock);
-	list_splice_init(&q->icq_list, &icq_list);
+	while (!list_empty(&q->icq_list)) {
-	spin_unlock_irq(&q->queue_lock);
-
-	rcu_read_lock();
-	while (!list_empty(&icq_list)) {
 		struct io_cq *icq =
-			list_entry(icq_list.next, struct io_cq, q_node);
+			list_first_entry(&q->icq_list, struct io_cq, q_node);
 
-		spin_lock_irq(&icq->ioc->lock);
+		/*
-		if (!(icq->flags & ICQ_DESTROYED))
+		 * Other context won't hold ioc lock to wait for queue_lock, see
-			ioc_destroy_icq(icq);
+		 * details in ioc_release_fn().
-		spin_unlock_irq(&icq->ioc->lock);
+		 */
+		spin_lock(&icq->ioc->lock);
+		ioc_destroy_icq(icq);
+		spin_unlock(&icq->ioc->lock);
 	}
-	rcu_read_unlock();
+	spin_unlock_irq(&q->queue_lock);
 }
 #else /* CONFIG_BLK_ICQ */
 static inline void ioc_exit_icqs(struct io_context *ioc)

block/blk-iocost.c

@@ -2455,6 +2455,7 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime,
 	u32 hwi, adj_step;
 	s64 margin;
 	u64 cost, new_inuse;
+	unsigned long flags;
 
 	current_hweight(iocg, NULL, &hwi);
 	old_hwi = hwi;
@@ -2473,11 +2474,11 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime,
 	    iocg->inuse == iocg->active)
 		return cost;
 
-	spin_lock_irq(&ioc->lock);
+	spin_lock_irqsave(&ioc->lock, flags);
 
 	/* we own inuse only when @iocg is in the normal active state */
 	if (iocg->abs_vdebt || list_empty(&iocg->active_list)) {
-		spin_unlock_irq(&ioc->lock);
+		spin_unlock_irqrestore(&ioc->lock, flags);
 		return cost;
 	}
 
@@ -2498,7 +2499,7 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime,
 	} while (time_after64(vtime + cost, now->vnow) &&
 		 iocg->inuse != iocg->active);
 
-	spin_unlock_irq(&ioc->lock);
+	spin_unlock_irqrestore(&ioc->lock, flags);
 
 	TRACE_IOCG_PATH(inuse_adjust, iocg, now,
 			old_inuse, iocg->inuse, old_hwi, hwi);

block/blk-ioprio.c

@@ -23,25 +23,28 @@
 /**
  * enum prio_policy - I/O priority class policy.
  * @POLICY_NO_CHANGE: (default) do not modify the I/O priority class.
- * @POLICY_NONE_TO_RT: modify IOPRIO_CLASS_NONE into IOPRIO_CLASS_RT.
+ * @POLICY_PROMOTE_TO_RT: modify no-IOPRIO_CLASS_RT to IOPRIO_CLASS_RT.
  * @POLICY_RESTRICT_TO_BE: modify IOPRIO_CLASS_NONE and IOPRIO_CLASS_RT into
  *		IOPRIO_CLASS_BE.
  * @POLICY_ALL_TO_IDLE: change the I/O priority class into IOPRIO_CLASS_IDLE.
+ * @POLICY_NONE_TO_RT: an alias for POLICY_PROMOTE_TO_RT.
  *
  * See also <linux/ioprio.h>.
  */
 enum prio_policy {
 	POLICY_NO_CHANGE	= 0,
-	POLICY_NONE_TO_RT	= 1,
+	POLICY_PROMOTE_TO_RT	= 1,
 	POLICY_RESTRICT_TO_BE	= 2,
 	POLICY_ALL_TO_IDLE	= 3,
+	POLICY_NONE_TO_RT	= 4,
 };
 
 static const char *policy_name[] = {
 	[POLICY_NO_CHANGE]	= "no-change",
-	[POLICY_NONE_TO_RT]	= "none-to-rt",
+	[POLICY_PROMOTE_TO_RT]	= "promote-to-rt",
 	[POLICY_RESTRICT_TO_BE]	= "restrict-to-be",
 	[POLICY_ALL_TO_IDLE]	= "idle",
+	[POLICY_NONE_TO_RT]	= "none-to-rt",
 };
 
 static struct blkcg_policy ioprio_policy;
@@ -189,6 +192,20 @@ void blkcg_set_ioprio(struct bio *bio)
 	if (!blkcg || blkcg->prio_policy == POLICY_NO_CHANGE)
 		return;
 
+	if (blkcg->prio_policy == POLICY_PROMOTE_TO_RT ||
+	    blkcg->prio_policy == POLICY_NONE_TO_RT) {
+		/*
+		 * For RT threads, the default priority level is 4 because
+		 * task_nice is 0. By promoting non-RT io-priority to RT-class
+		 * and default level 4, those requests that are already
+		 * RT-class but need a higher io-priority can use ioprio_set()
+		 * to achieve this.
+		 */
+		if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) != IOPRIO_CLASS_RT)
+			bio->bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_RT, 4);
+		return;
+	}
+
 	/*
 	 * Except for IOPRIO_CLASS_NONE, higher I/O priority numbers
 	 * correspond to a lower priority. Hence, the max_t() below selects

block/blk-map.c

@@ -281,21 +281,21 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 
 	if (blk_queue_pci_p2pdma(rq->q))
 		extraction_flags |= ITER_ALLOW_P2PDMA;
+	if (iov_iter_extract_will_pin(iter))
+		bio_set_flag(bio, BIO_PAGE_PINNED);
 
 	while (iov_iter_count(iter)) {
-		struct page **pages, *stack_pages[UIO_FASTIOV];
+		struct page *stack_pages[UIO_FASTIOV];
+		struct page **pages = stack_pages;
 		ssize_t bytes;
 		size_t offs;
 		int npages;
 
-		if (nr_vecs <= ARRAY_SIZE(stack_pages)) {
+		if (nr_vecs > ARRAY_SIZE(stack_pages))
-			pages = stack_pages;
+			pages = NULL;
-			bytes = iov_iter_get_pages(iter, pages, LONG_MAX,
+
-						   nr_vecs, &offs, extraction_flags);
+		bytes = iov_iter_extract_pages(iter, &pages, LONG_MAX,
-		} else {
+					       nr_vecs, extraction_flags, &offs);
-			bytes = iov_iter_get_pages_alloc(iter, &pages,
-						LONG_MAX, &offs, extraction_flags);
-		}
 		if (unlikely(bytes <= 0)) {
 			ret = bytes ? bytes : -EFAULT;
 			goto out_unmap;
@@ -317,7 +317,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 				if (!bio_add_hw_page(rq->q, bio, page, n, offs,
 						     max_sectors, &same_page)) {
 					if (same_page)
-						put_page(page);
+						bio_release_page(bio, page);
 					break;
 				}
 
@@ -329,7 +329,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 		 * release the pages we didn't map into the bio, if any
 		 */
 		while (j < npages)
-			put_page(pages[j++]);
+			bio_release_page(bio, pages[j++]);
 		if (pages != stack_pages)
 			kvfree(pages);
 		/* couldn't stuff something into bio? */

block/blk-mq-debugfs.c

@@ -88,6 +88,7 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(IO_STAT),
 	QUEUE_FLAG_NAME(NOXMERGES),
 	QUEUE_FLAG_NAME(ADD_RANDOM),
+	QUEUE_FLAG_NAME(SYNCHRONOUS),
 	QUEUE_FLAG_NAME(SAME_FORCE),
 	QUEUE_FLAG_NAME(INIT_DONE),
 	QUEUE_FLAG_NAME(STABLE_WRITES),
@@ -103,6 +104,8 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(RQ_ALLOC_TIME),
 	QUEUE_FLAG_NAME(HCTX_ACTIVE),
 	QUEUE_FLAG_NAME(NOWAIT),
+	QUEUE_FLAG_NAME(SQ_SCHED),
+	QUEUE_FLAG_NAME(SKIP_TAGSET_QUIESCE),
 };
 #undef QUEUE_FLAG_NAME
 
@@ -241,14 +244,14 @@ static const char *const cmd_flag_name[] = {
 #define RQF_NAME(name) [ilog2((__force u32)RQF_##name)] = #name
 static const char *const rqf_name[] = {
 	RQF_NAME(STARTED),
-	RQF_NAME(SOFTBARRIER),
 	RQF_NAME(FLUSH_SEQ),
 	RQF_NAME(MIXED_MERGE),
 	RQF_NAME(MQ_INFLIGHT),
 	RQF_NAME(DONTPREP),
+	RQF_NAME(SCHED_TAGS),
+	RQF_NAME(USE_SCHED),
 	RQF_NAME(FAILED),
 	RQF_NAME(QUIET),
-	RQF_NAME(ELVPRIV),
 	RQF_NAME(IO_STAT),
 	RQF_NAME(PM),
 	RQF_NAME(HASHED),
@@ -256,7 +259,6 @@ static const char *const rqf_name[] = {
 	RQF_NAME(SPECIAL_PAYLOAD),
 	RQF_NAME(ZONE_WRITE_LOCKED),
 	RQF_NAME(TIMED_OUT),
-	RQF_NAME(ELV),
 	RQF_NAME(RESV),
 };
 #undef RQF_NAME
@@ -399,7 +401,7 @@ static void blk_mq_debugfs_tags_show(struct seq_file *m,
 	seq_printf(m, "nr_tags=%u\n", tags->nr_tags);
 	seq_printf(m, "nr_reserved_tags=%u\n", tags->nr_reserved_tags);
 	seq_printf(m, "active_queues=%d\n",
-		   atomic_read(&tags->active_queues));
+		   READ_ONCE(tags->active_queues));
 
 	seq_puts(m, "\nbitmap_tags:\n");
 	sbitmap_queue_show(&tags->bitmap_tags, m);

block/blk-mq-sched.h

@@ -37,7 +37,7 @@ static inline bool
 blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
 			 struct bio *bio)
 {
-	if (rq->rq_flags & RQF_ELV) {
+	if (rq->rq_flags & RQF_USE_SCHED) {
 		struct elevator_queue *e = q->elevator;
 
 		if (e->type->ops.allow_merge)
@@ -48,7 +48,7 @@ blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
 
 static inline void blk_mq_sched_completed_request(struct request *rq, u64 now)
 {
-	if (rq->rq_flags & RQF_ELV) {
+	if (rq->rq_flags & RQF_USE_SCHED) {
 		struct elevator_queue *e = rq->q->elevator;
 
 		if (e->type->ops.completed_request)
@@ -58,11 +58,11 @@ static inline void blk_mq_sched_completed_request(struct request *rq, u64 now)
 
 static inline void blk_mq_sched_requeue_request(struct request *rq)
 {
-	if (rq->rq_flags & RQF_ELV) {
+	if (rq->rq_flags & RQF_USE_SCHED) {
 		struct request_queue *q = rq->q;
 		struct elevator_queue *e = q->elevator;
 
-		if ((rq->rq_flags & RQF_ELVPRIV) && e->type->ops.requeue_request)
+		if (e->type->ops.requeue_request)
 			e->type->ops.requeue_request(rq);
 	}
 }

block/blk-mq-tag.c

@@ -38,6 +38,7 @@ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags,
 void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
 	unsigned int users;
+	struct blk_mq_tags *tags = hctx->tags;
 
 	/*
 	 * calling test_bit() prior to test_and_set_bit() is intentional,
@@ -55,9 +56,11 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 			return;
 	}
 
-	users = atomic_inc_return(&hctx->tags->active_queues);
+	spin_lock_irq(&tags->lock);
-
+	users = tags->active_queues + 1;
-	blk_mq_update_wake_batch(hctx->tags, users);
+	WRITE_ONCE(tags->active_queues, users);
+	blk_mq_update_wake_batch(tags, users);
+	spin_unlock_irq(&tags->lock);
 }
 
 /*
@@ -90,9 +93,11 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
 			return;
 	}
 
-	users = atomic_dec_return(&tags->active_queues);
+	spin_lock_irq(&tags->lock);
-
+	users = tags->active_queues - 1;
+	WRITE_ONCE(tags->active_queues, users);
 	blk_mq_update_wake_batch(tags, users);
+	spin_unlock_irq(&tags->lock);
 
 	blk_mq_tag_wakeup_all(tags, false);
 }

block/blk-mq.c

@@ -45,6 +45,8 @@
 static DEFINE_PER_CPU(struct llist_head, blk_cpu_done);
 
 static void blk_mq_insert_request(struct request *rq, blk_insert_t flags);
+static void blk_mq_request_bypass_insert(struct request *rq,
+		blk_insert_t flags);
 static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		struct list_head *list);
 
@@ -354,12 +356,12 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 		data->rq_flags |= RQF_IO_STAT;
 	rq->rq_flags = data->rq_flags;
 
-	if (!(data->rq_flags & RQF_ELV)) {
+	if (data->rq_flags & RQF_SCHED_TAGS) {
-		rq->tag = tag;
-		rq->internal_tag = BLK_MQ_NO_TAG;
-	} else {
 		rq->tag = BLK_MQ_NO_TAG;
 		rq->internal_tag = tag;
+	} else {
+		rq->tag = tag;
+		rq->internal_tag = BLK_MQ_NO_TAG;
 	}
 	rq->timeout = 0;
 
@@ -386,17 +388,14 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	WRITE_ONCE(rq->deadline, 0);
 	req_ref_set(rq, 1);
 
-	if (rq->rq_flags & RQF_ELV) {
+	if (rq->rq_flags & RQF_USE_SCHED) {
 		struct elevator_queue *e = data->q->elevator;
 
 		INIT_HLIST_NODE(&rq->hash);
 		RB_CLEAR_NODE(&rq->rb_node);
 
-		if (!op_is_flush(data->cmd_flags) &&
+		if (e->type->ops.prepare_request)
-		    e->type->ops.prepare_request) {
 			e->type->ops.prepare_request(rq);
-			rq->rq_flags |= RQF_ELVPRIV;
-		}
 	}
 
 	return rq;
@@ -449,26 +448,32 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 		data->flags |= BLK_MQ_REQ_NOWAIT;
 
 	if (q->elevator) {
-		struct elevator_queue *e = q->elevator;
+		/*
-
+		 * All requests use scheduler tags when an I/O scheduler is
-		data->rq_flags |= RQF_ELV;
+		 * enabled for the queue.
+		 */
+		data->rq_flags |= RQF_SCHED_TAGS;
 
 		/*
 		 * Flush/passthrough requests are special and go directly to the
-		 * dispatch list. Don't include reserved tags in the
+		 * dispatch list.
-		 * limiting, as it isn't useful.
 		 */
-		if (!op_is_flush(data->cmd_flags) &&
+		if ((data->cmd_flags & REQ_OP_MASK) != REQ_OP_FLUSH &&
-		    !blk_op_is_passthrough(data->cmd_flags) &&
+		    !blk_op_is_passthrough(data->cmd_flags)) {
-		    e->type->ops.limit_depth &&
+			struct elevator_mq_ops *ops = &q->elevator->type->ops;
-		    !(data->flags & BLK_MQ_REQ_RESERVED))
+
-			e->type->ops.limit_depth(data->cmd_flags, data);
+			WARN_ON_ONCE(data->flags & BLK_MQ_REQ_RESERVED);
+
+			data->rq_flags |= RQF_USE_SCHED;
+			if (ops->limit_depth)
+				ops->limit_depth(data->cmd_flags, data);
+		}
 	}
 
 retry:
 	data->ctx = blk_mq_get_ctx(q);
 	data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx);
-	if (!(data->rq_flags & RQF_ELV))
+	if (!(data->rq_flags & RQF_SCHED_TAGS))
 		blk_mq_tag_busy(data->hctx);
 
 	if (data->flags & BLK_MQ_REQ_RESERVED)
@@ -648,10 +653,10 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 		goto out_queue_exit;
 	data.ctx = __blk_mq_get_ctx(q, cpu);
 
-	if (!q->elevator)
+	if (q->elevator)
-		blk_mq_tag_busy(data.hctx);
+		data.rq_flags |= RQF_SCHED_TAGS;
 	else
-		data.rq_flags |= RQF_ELV;
+		blk_mq_tag_busy(data.hctx);
 
 	if (flags & BLK_MQ_REQ_RESERVED)
 		data.rq_flags |= RQF_RESV;
@@ -699,7 +704,7 @@ void blk_mq_free_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
-	if ((rq->rq_flags & RQF_ELVPRIV) &&
+	if ((rq->rq_flags & RQF_USE_SCHED) &&
 	    q->elevator->type->ops.finish_request)
 		q->elevator->type->ops.finish_request(rq);
 
@@ -957,6 +962,8 @@ EXPORT_SYMBOL_GPL(blk_update_request);
 
 static inline void blk_account_io_done(struct request *req, u64 now)
 {
+	trace_block_io_done(req);
+
 	/*
 	 * Account IO completion.  flush_rq isn't accounted as a
 	 * normal IO on queueing nor completion.  Accounting the
@@ -976,6 +983,8 @@ static inline void blk_account_io_done(struct request *req, u64 now)
 
 static inline void blk_account_io_start(struct request *req)
 {
+	trace_block_io_start(req);
+
 	if (blk_do_io_stat(req)) {
 		/*
 		 * All non-passthrough requests are created from a bio with one
@@ -1176,8 +1185,9 @@ bool blk_mq_complete_request_remote(struct request *rq)
 	 * or a polled request, always complete locally,
 	 * it's pointless to redirect the completion.
 	 */
-	if (rq->mq_hctx->nr_ctx == 1 ||
+	if ((rq->mq_hctx->nr_ctx == 1 &&
-		rq->cmd_flags & REQ_POLLED)
+	     rq->mq_ctx->cpu == raw_smp_processor_id()) ||
+	     rq->cmd_flags & REQ_POLLED)
 		return false;
 
 	if (blk_mq_complete_need_ipi(rq)) {
@@ -1270,7 +1280,7 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
 
 	if (!plug->multiple_queues && last && last->q != rq->q)
 		plug->multiple_queues = true;
-	if (!plug->has_elevator && (rq->rq_flags & RQF_ELV))
+	if (!plug->has_elevator && (rq->rq_flags & RQF_USE_SCHED))
 		plug->has_elevator = true;
 	rq->rq_next = NULL;
 	rq_list_add(&plug->mq_list, rq);
@@ -1411,13 +1421,16 @@ static void __blk_mq_requeue_request(struct request *rq)
 void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list)
 {
 	struct request_queue *q = rq->q;
+	unsigned long flags;
 
 	__blk_mq_requeue_request(rq);
 
 	/* this request will be re-inserted to io scheduler queue */
 	blk_mq_sched_requeue_request(rq);
 
-	blk_mq_add_to_requeue_list(rq, BLK_MQ_INSERT_AT_HEAD);
+	spin_lock_irqsave(&q->requeue_lock, flags);
+	list_add_tail(&rq->queuelist, &q->requeue_list);
+	spin_unlock_irqrestore(&q->requeue_lock, flags);
 
 	if (kick_requeue_list)
 		blk_mq_kick_requeue_list(q);
@@ -1429,13 +1442,16 @@ static void blk_mq_requeue_work(struct work_struct *work)
 	struct request_queue *q =
 		container_of(work, struct request_queue, requeue_work.work);
 	LIST_HEAD(rq_list);
-	struct request *rq, *next;
+	LIST_HEAD(flush_list);
+	struct request *rq;
 
 	spin_lock_irq(&q->requeue_lock);
 	list_splice_init(&q->requeue_list, &rq_list);
+	list_splice_init(&q->flush_list, &flush_list);
 	spin_unlock_irq(&q->requeue_lock);
 
-	list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
+	while (!list_empty(&rq_list)) {
+		rq = list_entry(rq_list.next, struct request, queuelist);
 		/*
 		 * If RQF_DONTPREP ist set, the request has been started by the
 		 * driver already and might have driver-specific data allocated
@@ -1443,18 +1459,16 @@ static void blk_mq_requeue_work(struct work_struct *work)
 		 * block layer merges for the request.
 		 */
 		if (rq->rq_flags & RQF_DONTPREP) {
-			rq->rq_flags &= ~RQF_SOFTBARRIER;
 			list_del_init(&rq->queuelist);
 			blk_mq_request_bypass_insert(rq, 0);
-		} else if (rq->rq_flags & RQF_SOFTBARRIER) {
+		} else {
-			rq->rq_flags &= ~RQF_SOFTBARRIER;
 			list_del_init(&rq->queuelist);
 			blk_mq_insert_request(rq, BLK_MQ_INSERT_AT_HEAD);
 		}
 	}
 
-	while (!list_empty(&rq_list)) {
+	while (!list_empty(&flush_list)) {
-		rq = list_entry(rq_list.next, struct request, queuelist);
+		rq = list_entry(flush_list.next, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 		blk_mq_insert_request(rq, 0);
 	}
@@ -1462,27 +1476,6 @@ static void blk_mq_requeue_work(struct work_struct *work)
 	blk_mq_run_hw_queues(q, false);
 }
 
-void blk_mq_add_to_requeue_list(struct request *rq, blk_insert_t insert_flags)
-{
-	struct request_queue *q = rq->q;
-	unsigned long flags;
-
-	/*
-	 * We abuse this flag that is otherwise used by the I/O scheduler to
-	 * request head insertion from the workqueue.
-	 */
-	BUG_ON(rq->rq_flags & RQF_SOFTBARRIER);
-
-	spin_lock_irqsave(&q->requeue_lock, flags);
-	if (insert_flags & BLK_MQ_INSERT_AT_HEAD) {
-		rq->rq_flags |= RQF_SOFTBARRIER;
-		list_add(&rq->queuelist, &q->requeue_list);
-	} else {
-		list_add_tail(&rq->queuelist, &q->requeue_list);
-	}
-	spin_unlock_irqrestore(&q->requeue_lock, flags);
-}
-
 void blk_mq_kick_requeue_list(struct request_queue *q)
 {
 	kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, 0);
@@ -2427,7 +2420,7 @@ static void blk_mq_run_work_fn(struct work_struct *work)
  * Should only be used carefully, when the caller knows we want to
  * bypass a potential IO scheduler on the target device.
  */
-void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags)
+static void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags)
 {
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
@@ -2492,7 +2485,7 @@ static void blk_mq_insert_request(struct request *rq, blk_insert_t flags)
 		 * dispatch it given we prioritize requests in hctx->dispatch.
 		 */
 		blk_mq_request_bypass_insert(rq, flags);
-	} else if (rq->rq_flags & RQF_FLUSH_SEQ) {
+	} else if (req_op(rq) == REQ_OP_FLUSH) {
 		/*
 		 * Firstly normal IO request is inserted to scheduler queue or
 		 * sw queue, meantime we add flush request to dispatch queue(
@@ -2622,7 +2615,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 		return;
 	}
 
-	if ((rq->rq_flags & RQF_ELV) || !blk_mq_get_budget_and_tag(rq)) {
+	if ((rq->rq_flags & RQF_USE_SCHED) || !blk_mq_get_budget_and_tag(rq)) {
 		blk_mq_insert_request(rq, 0);
 		blk_mq_run_hw_queue(hctx, false);
 		return;
@@ -2711,6 +2704,7 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)
 	struct request *requeue_list = NULL;
 	struct request **requeue_lastp = &requeue_list;
 	unsigned int depth = 0;
+	bool is_passthrough = false;
 	LIST_HEAD(list);
 
 	do {
@@ -2719,7 +2713,9 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)
 		if (!this_hctx) {
 			this_hctx = rq->mq_hctx;
 			this_ctx = rq->mq_ctx;
-		} else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) {
+			is_passthrough = blk_rq_is_passthrough(rq);
+		} else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx ||
+			   is_passthrough != blk_rq_is_passthrough(rq)) {
 			rq_list_add_tail(&requeue_lastp, rq);
 			continue;
 		}
@@ -2731,7 +2727,13 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)
 	trace_block_unplug(this_hctx->queue, depth, !from_sched);
 
 	percpu_ref_get(&this_hctx->queue->q_usage_counter);
-	if (this_hctx->queue->elevator) {
+	/* passthrough requests should never be issued to the I/O scheduler */
+	if (is_passthrough) {
+		spin_lock(&this_hctx->lock);
+		list_splice_tail_init(&list, &this_hctx->dispatch);
+		spin_unlock(&this_hctx->lock);
+		blk_mq_run_hw_queue(this_hctx, from_sched);
+	} else if (this_hctx->queue->elevator) {
 		this_hctx->queue->elevator->type->ops.insert_requests(this_hctx,
 				&list, 0);
 		blk_mq_run_hw_queue(this_hctx, from_sched);
@@ -2970,10 +2972,8 @@ void blk_mq_submit_bio(struct bio *bio)
 		return;
 	}
 
-	if (op_is_flush(bio->bi_opf)) {
+	if (op_is_flush(bio->bi_opf) && blk_insert_flush(rq))
-		blk_insert_flush(rq);
 		return;
-	}
 
 	if (plug) {
 		blk_add_rq_to_plug(plug, rq);
@@ -2981,7 +2981,7 @@ void blk_mq_submit_bio(struct bio *bio)
 	}
 
 	hctx = rq->mq_hctx;
-	if ((rq->rq_flags & RQF_ELV) ||
+	if ((rq->rq_flags & RQF_USE_SCHED) ||
 	    (hctx->dispatch_busy && (q->nr_hw_queues == 1 || !is_sync))) {
 		blk_mq_insert_request(rq, 0);
 		blk_mq_run_hw_queue(hctx, true);
@@ -4232,6 +4232,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	blk_mq_update_poll_flag(q);
 
 	INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work);
+	INIT_LIST_HEAD(&q->flush_list);
 	INIT_LIST_HEAD(&q->requeue_list);
 	spin_lock_init(&q->requeue_lock);
 
@@ -4608,9 +4609,6 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
 {
 	struct blk_mq_qe_pair *qe;
 
-	if (!q->elevator)
-		return true;
-
 	qe = kmalloc(sizeof(*qe), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY);
 	if (!qe)
 		return false;
@@ -4618,6 +4616,12 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
 	/* q->elevator needs protection from ->sysfs_lock */
 	mutex_lock(&q->sysfs_lock);
 
+	/* the check has to be done with holding sysfs_lock */
+	if (!q->elevator) {
+		kfree(qe);
+		goto unlock;
+	}
+
 	INIT_LIST_HEAD(&qe->node);
 	qe->q = q;
 	qe->type = q->elevator->type;
@@ -4625,6 +4629,7 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
 	__elevator_get(qe->type);
 	list_add(&qe->node, head);
 	elevator_disable(q);
+unlock:
 	mutex_unlock(&q->sysfs_lock);
 
 	return true;

block/blk-mq.h

@@ -47,7 +47,6 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
 bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *,
 			     unsigned int);
-void blk_mq_add_to_requeue_list(struct request *rq, blk_insert_t insert_flags);
 void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
 struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_ctx *start);
@@ -64,10 +63,6 @@ struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set,
 void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set,
 			     struct blk_mq_tags *tags,
 			     unsigned int hctx_idx);
-/*
- * Internal helpers for request insertion into sw queues
- */
-void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags);
 
 /*
  * CPU -> queue mappings
@@ -226,9 +221,9 @@ static inline bool blk_mq_is_shared_tags(unsigned int flags)
 
 static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
 {
-	if (!(data->rq_flags & RQF_ELV))
+	if (data->rq_flags & RQF_SCHED_TAGS)
-		return data->hctx->tags;
+		return data->hctx->sched_tags;
-	return data->hctx->sched_tags;
+	return data->hctx->tags;
 }
 
 static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
@@ -417,8 +412,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 			return true;
 	}
 
-	users = atomic_read(&hctx->tags->active_queues);
+	users = READ_ONCE(hctx->tags->active_queues);
-
 	if (!users)
 		return true;
 

block/blk-rq-qos.c

@@ -288,11 +288,13 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data,
 
 void rq_qos_exit(struct request_queue *q)
 {
+	mutex_lock(&q->rq_qos_mutex);
 	while (q->rq_qos) {
 		struct rq_qos *rqos = q->rq_qos;
 		q->rq_qos = rqos->next;
 		rqos->ops->exit(rqos);
 	}
+	mutex_unlock(&q->rq_qos_mutex);
 }
 
 int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id,
@@ -300,6 +302,8 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id,
 {
 	struct request_queue *q = disk->queue;
 
+	lockdep_assert_held(&q->rq_qos_mutex);
+
 	rqos->disk = disk;
 	rqos->id = id;
 	rqos->ops = ops;
@@ -307,18 +311,13 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id,
 	/*
 	 * No IO can be in-flight when adding rqos, so freeze queue, which
 	 * is fine since we only support rq_qos for blk-mq queue.
-	 *
-	 * Reuse ->queue_lock for protecting against other concurrent
-	 * rq_qos adding/deleting
 	 */
 	blk_mq_freeze_queue(q);
 
-	spin_lock_irq(&q->queue_lock);
 	if (rq_qos_id(q, rqos->id))
 		goto ebusy;
 	rqos->next = q->rq_qos;
 	q->rq_qos = rqos;
-	spin_unlock_irq(&q->queue_lock);
 
 	blk_mq_unfreeze_queue(q);
 
@@ -330,7 +329,6 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id,
 
 	return 0;
 ebusy:
-	spin_unlock_irq(&q->queue_lock);
 	blk_mq_unfreeze_queue(q);
 	return -EBUSY;
 }
@@ -340,21 +338,15 @@ void rq_qos_del(struct rq_qos *rqos)
 	struct request_queue *q = rqos->disk->queue;
 	struct rq_qos **cur;
 
-	/*
+	lockdep_assert_held(&q->rq_qos_mutex);
-	 * See comment in rq_qos_add() about freezing queue & using
-	 * ->queue_lock.
-	 */
-	blk_mq_freeze_queue(q);
 
-	spin_lock_irq(&q->queue_lock);
+	blk_mq_freeze_queue(q);
 	for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) {
 		if (*cur == rqos) {
 			*cur = rqos->next;
 			break;
 		}
 	}
-	spin_unlock_irq(&q->queue_lock);
-
 	blk_mq_unfreeze_queue(q);
 
 	mutex_lock(&q->debugfs_mutex);

block/blk-wbt.c

@@ -944,7 +944,9 @@ int wbt_init(struct gendisk *disk)
 	/*
 	 * Assign rwb and add the stats callback.
 	 */
+	mutex_lock(&q->rq_qos_mutex);
 	ret = rq_qos_add(&rwb->rqos, disk, RQ_QOS_WBT, &wbt_rqos_ops);
+	mutex_unlock(&q->rq_qos_mutex);
 	if (ret)
 		goto err_free;
 

block/blk-zoned.c

@@ -57,16 +57,10 @@ EXPORT_SYMBOL_GPL(blk_zone_cond_str);
  */
 bool blk_req_needs_zone_write_lock(struct request *rq)
 {
-	if (blk_rq_is_passthrough(rq))
-		return false;
-
 	if (!rq->q->disk->seq_zones_wlock)
 		return false;
 
-	if (bdev_op_is_zoned_write(rq->q->disk->part0, req_op(rq)))
+	return blk_rq_is_seq_zoned_write(rq);
-		return blk_rq_zone_is_seq(rq);
-
-	return false;
 }
 EXPORT_SYMBOL_GPL(blk_req_needs_zone_write_lock);
 
@@ -329,8 +323,8 @@ static int blkdev_copy_zone_to_user(struct blk_zone *zone, unsigned int idx,
  * BLKREPORTZONE ioctl processing.
  * Called from blkdev_ioctl.
  */
-int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
+int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd,
-			      unsigned int cmd, unsigned long arg)
+		unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
 	struct zone_report_args args;
@@ -362,8 +356,8 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	return 0;
 }
 
-static int blkdev_truncate_zone_range(struct block_device *bdev, fmode_t mode,
+static int blkdev_truncate_zone_range(struct block_device *bdev,
-				      const struct blk_zone_range *zrange)
+		blk_mode_t mode, const struct blk_zone_range *zrange)
 {
 	loff_t start, end;
 
@@ -382,7 +376,7 @@ static int blkdev_truncate_zone_range(struct block_device *bdev, fmode_t mode,
  * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing.
  * Called from blkdev_ioctl.
  */
-int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
+int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 			   unsigned int cmd, unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
@@ -396,7 +390,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
 	if (!bdev_is_zoned(bdev))
 		return -ENOTTY;
 
-	if (!(mode & FMODE_WRITE))
+	if (!(mode & BLK_OPEN_WRITE))
 		return -EBADF;
 
 	if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range)))

block/blk.h

@@ -269,7 +269,7 @@ bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
  */
 #define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED)
 
-void blk_insert_flush(struct request *rq);
+bool blk_insert_flush(struct request *rq);
 
 int elevator_switch(struct request_queue *q, struct elevator_type *new_e);
 void elevator_disable(struct request_queue *q);
@@ -394,10 +394,27 @@ static inline struct bio *blk_queue_bounce(struct bio *bio,
 #ifdef CONFIG_BLK_DEV_ZONED
 void disk_free_zone_bitmaps(struct gendisk *disk);
 void disk_clear_zone_settings(struct gendisk *disk);
-#else
+int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd,
+		unsigned long arg);
+int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
+		unsigned int cmd, unsigned long arg);
+#else /* CONFIG_BLK_DEV_ZONED */
 static inline void disk_free_zone_bitmaps(struct gendisk *disk) {}
 static inline void disk_clear_zone_settings(struct gendisk *disk) {}
-#endif
+static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
+		unsigned int cmd, unsigned long arg)
+{
+	return -ENOTTY;
+}
+static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev,
+		blk_mode_t mode, unsigned int cmd, unsigned long arg)
+{
+	return -ENOTTY;
+}
+#endif /* CONFIG_BLK_DEV_ZONED */
+
+struct block_device *bdev_alloc(struct gendisk *disk, u8 partno);
+void bdev_add(struct block_device *bdev, dev_t dev);
 
 int blk_alloc_ext_minor(void);
 void blk_free_ext_minor(unsigned int minor);
@@ -409,7 +426,7 @@ int bdev_add_partition(struct gendisk *disk, int partno, sector_t start,
 int bdev_del_partition(struct gendisk *disk, int partno);
 int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start,
 		sector_t length);
-void blk_drop_partitions(struct gendisk *disk);
+void drop_partition(struct block_device *part);
 
 void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors);
 
@@ -420,9 +437,19 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset,
 		unsigned int max_sectors, bool *same_page);
 
+/*
+ * Clean up a page appropriately, where the page may be pinned, may have a
+ * ref taken on it or neither.
+ */
+static inline void bio_release_page(struct bio *bio, struct page *page)
+{
+	if (bio_flagged(bio, BIO_PAGE_PINNED))
+		unpin_user_page(page);
+}
+
 struct request_queue *blk_alloc_queue(int node_id);
 
-int disk_scan_partitions(struct gendisk *disk, fmode_t mode);
+int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode);
 
 int disk_alloc_events(struct gendisk *disk);
 void disk_add_events(struct gendisk *disk);
@@ -437,6 +464,9 @@ extern struct device_attribute dev_attr_events_poll_msecs;
 
 extern struct attribute_group blk_trace_attr_group;
 
+blk_mode_t file_to_blk_mode(struct file *file);
+int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode,
+		loff_t lstart, loff_t lend);
 long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg);
 long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg);
 

block/bsg-lib.c

@@ -26,7 +26,7 @@ struct bsg_set {
 };
 
 static int bsg_transport_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr,
-		fmode_t mode, unsigned int timeout)
+		bool open_for_write, unsigned int timeout)
 {
 	struct bsg_job *job;
 	struct request *rq;

block/bsg.c

@@ -39,7 +39,7 @@ static inline struct bsg_device *to_bsg_device(struct inode *inode)
 #define BSG_MAX_DEVS		32768
 
 static DEFINE_IDA(bsg_minor_ida);
-static struct class *bsg_class;
+static const struct class bsg_class;
 static int bsg_major;
 
 static unsigned int bsg_timeout(struct bsg_device *bd, struct sg_io_v4 *hdr)
@@ -54,7 +54,8 @@ static unsigned int bsg_timeout(struct bsg_device *bd, struct sg_io_v4 *hdr)
 	return max_t(unsigned int, timeout, BLK_MIN_SG_TIMEOUT);
 }
 
-static int bsg_sg_io(struct bsg_device *bd, fmode_t mode, void __user *uarg)
+static int bsg_sg_io(struct bsg_device *bd, bool open_for_write,
+		     void __user *uarg)
 {
 	struct sg_io_v4 hdr;
 	int ret;
@@ -63,7 +64,8 @@ static int bsg_sg_io(struct bsg_device *bd, fmode_t mode, void __user *uarg)
 		return -EFAULT;
 	if (hdr.guard != 'Q')
 		return -EINVAL;
-	ret = bd->sg_io_fn(bd->queue, &hdr, mode, bsg_timeout(bd, &hdr));
+	ret = bd->sg_io_fn(bd->queue, &hdr, open_for_write,
+			   bsg_timeout(bd, &hdr));
 	if (!ret && copy_to_user(uarg, &hdr, sizeof(hdr)))
 		return -EFAULT;
 	return ret;
@@ -146,7 +148,7 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case SG_EMULATED_HOST:
 		return put_user(1, intp);
 	case SG_IO:
-		return bsg_sg_io(bd, file->f_mode, uarg);
+		return bsg_sg_io(bd, file->f_mode & FMODE_WRITE, uarg);
 	case SCSI_IOCTL_SEND_COMMAND:
 		pr_warn_ratelimited("%s: calling unsupported SCSI_IOCTL_SEND_COMMAND\n",
 				current->comm);
@@ -206,7 +208,7 @@ struct bsg_device *bsg_register_queue(struct request_queue *q,
 		return ERR_PTR(ret);
 	}
 	bd->device.devt = MKDEV(bsg_major, ret);
-	bd->device.class = bsg_class;
+	bd->device.class = &bsg_class;
 	bd->device.parent = parent;
 	bd->device.release = bsg_device_release;
 	dev_set_name(&bd->device, "%s", name);
@@ -240,15 +242,19 @@ static char *bsg_devnode(const struct device *dev, umode_t *mode)
 	return kasprintf(GFP_KERNEL, "bsg/%s", dev_name(dev));
 }
 
+static const struct class bsg_class = {
+	.name		= "bsg",
+	.devnode	= bsg_devnode,
+};
+
 static int __init bsg_init(void)
 {
 	dev_t devid;
 	int ret;
 
-	bsg_class = class_create("bsg");
+	ret = class_register(&bsg_class);
-	if (IS_ERR(bsg_class))
+	if (ret)
-		return PTR_ERR(bsg_class);
+		return ret;
-	bsg_class->devnode = bsg_devnode;
 
 	ret = alloc_chrdev_region(&devid, 0, BSG_MAX_DEVS, "bsg");
 	if (ret)
@@ -260,7 +266,7 @@ static int __init bsg_init(void)
 	return 0;
 
 destroy_bsg_class:
-	class_destroy(bsg_class);
+	class_unregister(&bsg_class);
 	return ret;
 }
 

block/disk-events.c

@@ -263,31 +263,31 @@ static unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask)
 }
 
 /**
- * bdev_check_media_change - check if a removable media has been changed
+ * disk_check_media_change - check if a removable media has been changed
- * @bdev: block device to check
+ * @disk: gendisk to check
  *
  * Check whether a removable media has been changed, and attempt to free all
  * dentries and inodes and invalidates all block device page cache entries in
  * that case.
  *
- * Returns %true if the block device changed, or %false if not.
+ * Returns %true if the media has changed, or %false if not.
  */
-bool bdev_check_media_change(struct block_device *bdev)
+bool disk_check_media_change(struct gendisk *disk)
 {
 	unsigned int events;
 
-	events = disk_clear_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE |
+	events = disk_clear_events(disk, DISK_EVENT_MEDIA_CHANGE |
 				   DISK_EVENT_EJECT_REQUEST);
 	if (!(events & DISK_EVENT_MEDIA_CHANGE))
 		return false;
 
-	if (__invalidate_device(bdev, true))
+	if (__invalidate_device(disk->part0, true))
 		pr_warn("VFS: busy inodes on changed media %s\n",
-			bdev->bd_disk->disk_name);
+			disk->disk_name);
-	set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
+	set_bit(GD_NEED_PART_SCAN, &disk->state);
 	return true;
 }
-EXPORT_SYMBOL(bdev_check_media_change);
+EXPORT_SYMBOL(disk_check_media_change);
 
 /**
  * disk_force_media_change - force a media change event
@@ -307,6 +307,7 @@ bool disk_force_media_change(struct gendisk *disk, unsigned int events)
 	if (!(events & DISK_EVENT_MEDIA_CHANGE))
 		return false;
 
+	inc_diskseq(disk);
 	if (__invalidate_device(disk->part0, true))
 		pr_warn("VFS: busy inodes on changed media %s\n",
 			disk->disk_name);

block/early-lookup.c

@@ -0,0 +1,316 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Code for looking up block devices in the early boot code before mounting the
+ * root file system.
+ */
+#include <linux/blkdev.h>
+#include <linux/ctype.h>
+
+struct uuidcmp {
+	const char *uuid;
+	int len;
+};
+
+/**
+ * match_dev_by_uuid - callback for finding a partition using its uuid
+ * @dev:	device passed in by the caller
+ * @data:	opaque pointer to the desired struct uuidcmp to match
+ *
+ * Returns 1 if the device matches, and 0 otherwise.
+ */
+static int __init match_dev_by_uuid(struct device *dev, const void *data)
+{
+	struct block_device *bdev = dev_to_bdev(dev);
+	const struct uuidcmp *cmp = data;
+
+	if (!bdev->bd_meta_info ||
+	    strncasecmp(cmp->uuid, bdev->bd_meta_info->uuid, cmp->len))
+		return 0;
+	return 1;
+}
+
+/**
+ * devt_from_partuuid - looks up the dev_t of a partition by its UUID
+ * @uuid_str:	char array containing ascii UUID
+ * @devt:	dev_t result
+ *
+ * The function will return the first partition which contains a matching
+ * UUID value in its partition_meta_info struct.  This does not search
+ * by filesystem UUIDs.
+ *
+ * If @uuid_str is followed by a "/PARTNROFF=%d", then the number will be
+ * extracted and used as an offset from the partition identified by the UUID.
+ *
+ * Returns 0 on success or a negative error code on failure.
+ */
+static int __init devt_from_partuuid(const char *uuid_str, dev_t *devt)
+{
+	struct uuidcmp cmp;
+	struct device *dev = NULL;
+	int offset = 0;
+	char *slash;
+
+	cmp.uuid = uuid_str;
+
+	slash = strchr(uuid_str, '/');
+	/* Check for optional partition number offset attributes. */
+	if (slash) {
+		char c = 0;
+
+		/* Explicitly fail on poor PARTUUID syntax. */
+		if (sscanf(slash + 1, "PARTNROFF=%d%c", &offset, &c) != 1)
+			goto out_invalid;
+		cmp.len = slash - uuid_str;
+	} else {
+		cmp.len = strlen(uuid_str);
+	}
+
+	if (!cmp.len)
+		goto out_invalid;
+
+	dev = class_find_device(&block_class, NULL, &cmp, &match_dev_by_uuid);
+	if (!dev)
+		return -ENODEV;
+
+	if (offset) {
+		/*
+		 * Attempt to find the requested partition by adding an offset
+		 * to the partition number found by UUID.
+		 */
+		*devt = part_devt(dev_to_disk(dev),
+				  dev_to_bdev(dev)->bd_partno + offset);
+	} else {
+		*devt = dev->devt;
+	}
+
+	put_device(dev);
+	return 0;
+
+out_invalid:
+	pr_err("VFS: PARTUUID= is invalid.\n"
+	       "Expected PARTUUID=<valid-uuid-id>[/PARTNROFF=%%d]\n");
+	return -EINVAL;
+}
+
+/**
+ * match_dev_by_label - callback for finding a partition using its label
+ * @dev:	device passed in by the caller
+ * @data:	opaque pointer to the label to match
+ *
+ * Returns 1 if the device matches, and 0 otherwise.
+ */
+static int __init match_dev_by_label(struct device *dev, const void *data)
+{
+	struct block_device *bdev = dev_to_bdev(dev);
+	const char *label = data;
+
+	if (!bdev->bd_meta_info || strcmp(label, bdev->bd_meta_info->volname))
+		return 0;
+	return 1;
+}
+
+static int __init devt_from_partlabel(const char *label, dev_t *devt)
+{
+	struct device *dev;
+
+	dev = class_find_device(&block_class, NULL, label, &match_dev_by_label);
+	if (!dev)
+		return -ENODEV;
+	*devt = dev->devt;
+	put_device(dev);
+	return 0;
+}
+
+static dev_t __init blk_lookup_devt(const char *name, int partno)
+{
+	dev_t devt = MKDEV(0, 0);
+	struct class_dev_iter iter;
+	struct device *dev;
+
+	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
+	while ((dev = class_dev_iter_next(&iter))) {
+		struct gendisk *disk = dev_to_disk(dev);
+
+		if (strcmp(dev_name(dev), name))
+			continue;
+
+		if (partno < disk->minors) {
+			/* We need to return the right devno, even
+			 * if the partition doesn't exist yet.
+			 */
+			devt = MKDEV(MAJOR(dev->devt),
+				     MINOR(dev->devt) + partno);
+		} else {
+			devt = part_devt(disk, partno);
+			if (devt)
+				break;
+		}
+	}
+	class_dev_iter_exit(&iter);
+	return devt;
+}
+
+static int __init devt_from_devname(const char *name, dev_t *devt)
+{
+	int part;
+	char s[32];
+	char *p;
+
+	if (strlen(name) > 31)
+		return -EINVAL;
+	strcpy(s, name);
+	for (p = s; *p; p++) {
+		if (*p == '/')
+			*p = '!';
+	}
+
+	*devt = blk_lookup_devt(s, 0);
+	if (*devt)
+		return 0;
+
+	/*
+	 * Try non-existent, but valid partition, which may only exist after
+	 * opening the device, like partitioned md devices.
+	 */
+	while (p > s && isdigit(p[-1]))
+		p--;
+	if (p == s || !*p || *p == '0')
+		return -ENODEV;
+
+	/* try disk name without <part number> */
+	part = simple_strtoul(p, NULL, 10);
+	*p = '\0';
+	*devt = blk_lookup_devt(s, part);
+	if (*devt)
+		return 0;
+
+	/* try disk name without p<part number> */
+	if (p < s + 2 || !isdigit(p[-2]) || p[-1] != 'p')
+		return -ENODEV;
+	p[-1] = '\0';
+	*devt = blk_lookup_devt(s, part);
+	if (*devt)
+		return 0;
+	return -ENODEV;
+}
+
+static int __init devt_from_devnum(const char *name, dev_t *devt)
+{
+	unsigned maj, min, offset;
+	char *p, dummy;
+
+	if (sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2 ||
+	    sscanf(name, "%u:%u:%u:%c", &maj, &min, &offset, &dummy) == 3) {
+		*devt = MKDEV(maj, min);
+		if (maj != MAJOR(*devt) || min != MINOR(*devt))
+			return -EINVAL;
+	} else {
+		*devt = new_decode_dev(simple_strtoul(name, &p, 16));
+		if (*p)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ *	Convert a name into device number.  We accept the following variants:
+ *
+ *	1) <hex_major><hex_minor> device number in hexadecimal represents itself
+ *         no leading 0x, for example b302.
+ *	3) /dev/<disk_name> represents the device number of disk
+ *	4) /dev/<disk_name><decimal> represents the device number
+ *         of partition - device number of disk plus the partition number
+ *	5) /dev/<disk_name>p<decimal> - same as the above, that form is
+ *	   used when disk name of partitioned disk ends on a digit.
+ *	6) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the
+ *	   unique id of a partition if the partition table provides it.
+ *	   The UUID may be either an EFI/GPT UUID, or refer to an MSDOS
+ *	   partition using the format SSSSSSSS-PP, where SSSSSSSS is a zero-
+ *	   filled hex representation of the 32-bit "NT disk signature", and PP
+ *	   is a zero-filled hex representation of the 1-based partition number.
+ *	7) PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation to
+ *	   a partition with a known unique id.
+ *	8) <major>:<minor> major and minor number of the device separated by
+ *	   a colon.
+ *	9) PARTLABEL=<name> with name being the GPT partition label.
+ *	   MSDOS partitions do not support labels!
+ *
+ *	If name doesn't have fall into the categories above, we return (0,0).
+ *	block_class is used to check if something is a disk name. If the disk
+ *	name contains slashes, the device name has them replaced with
+ *	bangs.
+ */
+int __init early_lookup_bdev(const char *name, dev_t *devt)
+{
+	if (strncmp(name, "PARTUUID=", 9) == 0)
+		return devt_from_partuuid(name + 9, devt);
+	if (strncmp(name, "PARTLABEL=", 10) == 0)
+		return devt_from_partlabel(name + 10, devt);
+	if (strncmp(name, "/dev/", 5) == 0)
+		return devt_from_devname(name + 5, devt);
+	return devt_from_devnum(name, devt);
+}
+
+static char __init *bdevt_str(dev_t devt, char *buf)
+{
+	if (MAJOR(devt) <= 0xff && MINOR(devt) <= 0xff) {
+		char tbuf[BDEVT_SIZE];
+		snprintf(tbuf, BDEVT_SIZE, "%02x%02x", MAJOR(devt), MINOR(devt));
+		snprintf(buf, BDEVT_SIZE, "%-9s", tbuf);
+	} else
+		snprintf(buf, BDEVT_SIZE, "%03x:%05x", MAJOR(devt), MINOR(devt));
+
+	return buf;
+}
+
+/*
+ * print a full list of all partitions - intended for places where the root
+ * filesystem can't be mounted and thus to give the victim some idea of what
+ * went wrong
+ */
+void __init printk_all_partitions(void)
+{
+	struct class_dev_iter iter;
+	struct device *dev;
+
+	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
+	while ((dev = class_dev_iter_next(&iter))) {
+		struct gendisk *disk = dev_to_disk(dev);
+		struct block_device *part;
+		char devt_buf[BDEVT_SIZE];
+		unsigned long idx;
+
+		/*
+		 * Don't show empty devices or things that have been
+		 * suppressed
+		 */
+		if (get_capacity(disk) == 0 || (disk->flags & GENHD_FL_HIDDEN))
+			continue;
+
+		/*
+		 * Note, unlike /proc/partitions, I am showing the numbers in
+		 * hex - the same format as the root= option takes.
+		 */
+		rcu_read_lock();
+		xa_for_each(&disk->part_tbl, idx, part) {
+			if (!bdev_nr_sectors(part))
+				continue;
+			printk("%s%s %10llu %pg %s",
+			       bdev_is_partition(part) ? "  " : "",
+			       bdevt_str(part->bd_dev, devt_buf),
+			       bdev_nr_sectors(part) >> 1, part,
+			       part->bd_meta_info ?
+					part->bd_meta_info->uuid : "");
+			if (bdev_is_partition(part))
+				printk("\n");
+			else if (dev->parent && dev->parent->driver)
+				printk(" driver: %s\n",
+					dev->parent->driver->name);
+			else
+				printk(" (driver?)\n");
+		}
+		rcu_read_unlock();
+	}
+	class_dev_iter_exit(&iter);
+}

block/elevator.c

@@ -751,7 +751,7 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *buf,
 	if (!elv_support_iosched(q))
 		return count;
 
-	strlcpy(elevator_name, buf, sizeof(elevator_name));
+	strscpy(elevator_name, buf, sizeof(elevator_name));
 	ret = elevator_change(q, strstrip(elevator_name));
 	if (!ret)
 		return count;

block/fops.c

@@ -54,7 +54,7 @@ static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos,
 static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 		struct iov_iter *iter, unsigned int nr_pages)
 {
-	struct block_device *bdev = iocb->ki_filp->private_data;
+	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
 	struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs;
 	loff_t pos = iocb->ki_pos;
 	bool should_dirty = false;
@@ -170,7 +170,7 @@ static void blkdev_bio_end_io(struct bio *bio)
 static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		unsigned int nr_pages)
 {
-	struct block_device *bdev = iocb->ki_filp->private_data;
+	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
 	struct blk_plug plug;
 	struct blkdev_dio *dio;
 	struct bio *bio;
@@ -310,7 +310,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 					struct iov_iter *iter,
 					unsigned int nr_pages)
 {
-	struct block_device *bdev = iocb->ki_filp->private_data;
+	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
 	bool is_read = iov_iter_rw(iter) == READ;
 	blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
 	struct blkdev_dio *dio;
@@ -451,7 +451,7 @@ static loff_t blkdev_llseek(struct file *file, loff_t offset, int whence)
 static int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
 		int datasync)
 {
-	struct block_device *bdev = filp->private_data;
+	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
 	int error;
 
 	error = file_write_and_wait_range(filp, start, end);
@@ -470,6 +470,30 @@ static int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
 	return error;
 }
 
+blk_mode_t file_to_blk_mode(struct file *file)
+{
+	blk_mode_t mode = 0;
+
+	if (file->f_mode & FMODE_READ)
+		mode |= BLK_OPEN_READ;
+	if (file->f_mode & FMODE_WRITE)
+		mode |= BLK_OPEN_WRITE;
+	if (file->private_data)
+		mode |= BLK_OPEN_EXCL;
+	if (file->f_flags & O_NDELAY)
+		mode |= BLK_OPEN_NDELAY;
+
+	/*
+	 * If all bits in O_ACCMODE set (aka O_RDWR | O_WRONLY), the floppy
+	 * driver has historically allowed ioctls as if the file was opened for
+	 * writing, but does not allow and actual reads or writes.
+	 */
+	if ((file->f_flags & O_ACCMODE) == (O_RDWR | O_WRONLY))
+		mode |= BLK_OPEN_WRITE_IOCTL;
+
+	return mode;
+}
+
 static int blkdev_open(struct inode *inode, struct file *filp)
 {
 	struct block_device *bdev;
@@ -483,31 +507,29 @@ static int blkdev_open(struct inode *inode, struct file *filp)
 	filp->f_flags |= O_LARGEFILE;
 	filp->f_mode |= FMODE_BUF_RASYNC;
 
-	if (filp->f_flags & O_NDELAY)
+	/*
-		filp->f_mode |= FMODE_NDELAY;
+	 * Use the file private data to store the holder for exclusive openes.
+	 * file_to_blk_mode relies on it being present to set BLK_OPEN_EXCL.
+	 */
 	if (filp->f_flags & O_EXCL)
-		filp->f_mode |= FMODE_EXCL;
+		filp->private_data = filp;
-	if ((filp->f_flags & O_ACCMODE) == 3)
-		filp->f_mode |= FMODE_WRITE_IOCTL;
 
-	bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp);
+	bdev = blkdev_get_by_dev(inode->i_rdev, file_to_blk_mode(filp),
+				 filp->private_data, NULL);
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
 
 	if (bdev_nowait(bdev))
 		filp->f_mode |= FMODE_NOWAIT;
 
-	filp->private_data = bdev;
 	filp->f_mapping = bdev->bd_inode->i_mapping;
 	filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
 	return 0;
 }
 
-static int blkdev_close(struct inode *inode, struct file *filp)
+static int blkdev_release(struct inode *inode, struct file *filp)
 {
-	struct block_device *bdev = filp->private_data;
+	blkdev_put(I_BDEV(filp->f_mapping->host), filp->private_data);
-
-	blkdev_put(bdev, filp->f_mode);
 	return 0;
 }
 
@@ -520,10 +542,9 @@ static int blkdev_close(struct inode *inode, struct file *filp)
  */
 static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
-	struct block_device *bdev = iocb->ki_filp->private_data;
+	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
 	struct inode *bd_inode = bdev->bd_inode;
 	loff_t size = bdev_nr_bytes(bdev);
-	struct blk_plug plug;
 	size_t shorted = 0;
 	ssize_t ret;
 
@@ -548,18 +569,16 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		iov_iter_truncate(from, size);
 	}
 
-	blk_start_plug(&plug);
 	ret = __generic_file_write_iter(iocb, from);
 	if (ret > 0)
 		ret = generic_write_sync(iocb, ret);
 	iov_iter_reexpand(from, iov_iter_count(from) + shorted);
-	blk_finish_plug(&plug);
 	return ret;
 }
 
 static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
-	struct block_device *bdev = iocb->ki_filp->private_data;
+	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
 	loff_t size = bdev_nr_bytes(bdev);
 	loff_t pos = iocb->ki_pos;
 	size_t shorted = 0;
@@ -652,7 +671,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 	filemap_invalidate_lock(inode->i_mapping);
 
 	/* Invalidate the page cache, including dirty pages. */
-	error = truncate_bdev_range(bdev, file->f_mode, start, end);
+	error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end);
 	if (error)
 		goto fail;
 
@@ -693,7 +712,7 @@ static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
 
 const struct file_operations def_blk_fops = {
 	.open		= blkdev_open,
-	.release	= blkdev_close,
+	.release	= blkdev_release,
 	.llseek		= blkdev_llseek,
 	.read_iter	= blkdev_read_iter,
 	.write_iter	= blkdev_write_iter,

block/genhd.c

@@ -25,8 +25,9 @@
 #include <linux/pm_runtime.h>
 #include <linux/badblocks.h>
 #include <linux/part_stat.h>
-#include "blk-throttle.h"
+#include <linux/blktrace_api.h>
 
+#include "blk-throttle.h"
 #include "blk.h"
 #include "blk-mq-sched.h"
 #include "blk-rq-qos.h"
@@ -253,7 +254,7 @@ int __register_blkdev(unsigned int major, const char *name,
 #ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
 	p->probe = probe;
 #endif
-	strlcpy(p->name, name, sizeof(p->name));
+	strscpy(p->name, name, sizeof(p->name));
 	p->next = NULL;
 	index = major_to_index(major);
 
@@ -318,18 +319,6 @@ void blk_free_ext_minor(unsigned int minor)
 	ida_free(&ext_devt_ida, minor);
 }
 
-static char *bdevt_str(dev_t devt, char *buf)
-{
-	if (MAJOR(devt) <= 0xff && MINOR(devt) <= 0xff) {
-		char tbuf[BDEVT_SIZE];
-		snprintf(tbuf, BDEVT_SIZE, "%02x%02x", MAJOR(devt), MINOR(devt));
-		snprintf(buf, BDEVT_SIZE, "%-9s", tbuf);
-	} else
-		snprintf(buf, BDEVT_SIZE, "%03x:%05x", MAJOR(devt), MINOR(devt));
-
-	return buf;
-}
-
 void disk_uevent(struct gendisk *disk, enum kobject_action action)
 {
 	struct block_device *part;
@@ -351,7 +340,7 @@ void disk_uevent(struct gendisk *disk, enum kobject_action action)
 }
 EXPORT_SYMBOL_GPL(disk_uevent);
 
-int disk_scan_partitions(struct gendisk *disk, fmode_t mode)
+int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode)
 {
 	struct block_device *bdev;
 	int ret = 0;
@@ -369,18 +358,20 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode)
 	 * synchronize with other exclusive openers and other partition
 	 * scanners.
 	 */
-	if (!(mode & FMODE_EXCL)) {
+	if (!(mode & BLK_OPEN_EXCL)) {
-		ret = bd_prepare_to_claim(disk->part0, disk_scan_partitions);
+		ret = bd_prepare_to_claim(disk->part0, disk_scan_partitions,
+					  NULL);
 		if (ret)
 			return ret;
 	}
 
 	set_bit(GD_NEED_PART_SCAN, &disk->state);
-	bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~FMODE_EXCL, NULL);
+	bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~BLK_OPEN_EXCL, NULL,
+				 NULL);
 	if (IS_ERR(bdev))
 		ret =  PTR_ERR(bdev);
 	else
-		blkdev_put(bdev, mode & ~FMODE_EXCL);
+		blkdev_put(bdev, NULL);
 
 	/*
 	 * If blkdev_get_by_dev() failed early, GD_NEED_PART_SCAN is still set,
@@ -388,7 +379,7 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode)
 	 * creat partition for underlying disk.
 	 */
 	clear_bit(GD_NEED_PART_SCAN, &disk->state);
-	if (!(mode & FMODE_EXCL))
+	if (!(mode & BLK_OPEN_EXCL))
 		bd_abort_claiming(disk->part0, disk_scan_partitions);
 	return ret;
 }
@@ -516,7 +507,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 
 		bdev_add(disk->part0, ddev->devt);
 		if (get_capacity(disk))
-			disk_scan_partitions(disk, FMODE_READ);
+			disk_scan_partitions(disk, BLK_OPEN_READ);
 
 		/*
 		 * Announce the disk and partitions after all partitions are
@@ -563,6 +554,28 @@ out_exit_elevator:
 }
 EXPORT_SYMBOL(device_add_disk);
 
+static void blk_report_disk_dead(struct gendisk *disk)
+{
+	struct block_device *bdev;
+	unsigned long idx;
+
+	rcu_read_lock();
+	xa_for_each(&disk->part_tbl, idx, bdev) {
+		if (!kobject_get_unless_zero(&bdev->bd_device.kobj))
+			continue;
+		rcu_read_unlock();
+
+		mutex_lock(&bdev->bd_holder_lock);
+		if (bdev->bd_holder_ops && bdev->bd_holder_ops->mark_dead)
+			bdev->bd_holder_ops->mark_dead(bdev);
+		mutex_unlock(&bdev->bd_holder_lock);
+
+		put_device(&bdev->bd_device);
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
+}
+
 /**
  * blk_mark_disk_dead - mark a disk as dead
  * @disk: disk to mark as dead
@@ -572,13 +585,26 @@ EXPORT_SYMBOL(device_add_disk);
  */
 void blk_mark_disk_dead(struct gendisk *disk)
 {
-	set_bit(GD_DEAD, &disk->state);
+	/*
-	blk_queue_start_drain(disk->queue);
+	 * Fail any new I/O.
+	 */
+	if (test_and_set_bit(GD_DEAD, &disk->state))
+		return;
+
+	if (test_bit(GD_OWNS_QUEUE, &disk->state))
+		blk_queue_flag_set(QUEUE_FLAG_DYING, disk->queue);
 
 	/*
 	 * Stop buffered writers from dirtying pages that can't be written out.
 	 */
-	set_capacity_and_notify(disk, 0);
+	set_capacity(disk, 0);
+
+	/*
+	 * Prevent new I/O from crossing bio_queue_enter().
+	 */
+	blk_queue_start_drain(disk->queue);
+
+	blk_report_disk_dead(disk);
 }
 EXPORT_SYMBOL_GPL(blk_mark_disk_dead);
 
@@ -604,6 +630,8 @@ EXPORT_SYMBOL_GPL(blk_mark_disk_dead);
 void del_gendisk(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
+	struct block_device *part;
+	unsigned long idx;
 
 	might_sleep();
 
@@ -612,26 +640,27 @@ void del_gendisk(struct gendisk *disk)
 
 	disk_del_events(disk);
 
+	/*
+	 * Prevent new openers by unlinked the bdev inode, and write out
+	 * dirty data before marking the disk dead and stopping all I/O.
+	 */
 	mutex_lock(&disk->open_mutex);
-	remove_inode_hash(disk->part0->bd_inode);
+	xa_for_each(&disk->part_tbl, idx, part) {
-	blk_drop_partitions(disk);
+		remove_inode_hash(part->bd_inode);
+		fsync_bdev(part);
+		__invalidate_device(part, true);
+	}
 	mutex_unlock(&disk->open_mutex);
 
-	fsync_bdev(disk->part0);
+	blk_mark_disk_dead(disk);
-	__invalidate_device(disk->part0, true);
 
 	/*
-	 * Fail any new I/O.
+	 * Drop all partitions now that the disk is marked dead.
 	 */
-	set_bit(GD_DEAD, &disk->state);
+	mutex_lock(&disk->open_mutex);
-	if (test_bit(GD_OWNS_QUEUE, &disk->state))
+	xa_for_each_start(&disk->part_tbl, idx, part, 1)
-		blk_queue_flag_set(QUEUE_FLAG_DYING, q);
+		drop_partition(part);
-	set_capacity(disk, 0);
+	mutex_unlock(&disk->open_mutex);
-
-	/*
-	 * Prevent new I/O from crossing bio_queue_enter().
-	 */
-	blk_queue_start_drain(q);
 
 	if (!(disk->flags & GENHD_FL_HIDDEN)) {
 		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
@@ -755,57 +784,6 @@ void blk_request_module(dev_t devt)
 }
 #endif /* CONFIG_BLOCK_LEGACY_AUTOLOAD */
 
-/*
- * print a full list of all partitions - intended for places where the root
- * filesystem can't be mounted and thus to give the victim some idea of what
- * went wrong
- */
-void __init printk_all_partitions(void)
-{
-	struct class_dev_iter iter;
-	struct device *dev;
-
-	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
-	while ((dev = class_dev_iter_next(&iter))) {
-		struct gendisk *disk = dev_to_disk(dev);
-		struct block_device *part;
-		char devt_buf[BDEVT_SIZE];
-		unsigned long idx;
-
-		/*
-		 * Don't show empty devices or things that have been
-		 * suppressed
-		 */
-		if (get_capacity(disk) == 0 || (disk->flags & GENHD_FL_HIDDEN))
-			continue;
-
-		/*
-		 * Note, unlike /proc/partitions, I am showing the numbers in
-		 * hex - the same format as the root= option takes.
-		 */
-		rcu_read_lock();
-		xa_for_each(&disk->part_tbl, idx, part) {
-			if (!bdev_nr_sectors(part))
-				continue;
-			printk("%s%s %10llu %pg %s",
-			       bdev_is_partition(part) ? "  " : "",
-			       bdevt_str(part->bd_dev, devt_buf),
-			       bdev_nr_sectors(part) >> 1, part,
-			       part->bd_meta_info ?
-					part->bd_meta_info->uuid : "");
-			if (bdev_is_partition(part))
-				printk("\n");
-			else if (dev->parent && dev->parent->driver)
-				printk(" driver: %s\n",
-					dev->parent->driver->name);
-			else
-				printk(" (driver?)\n");
-		}
-		rcu_read_unlock();
-	}
-	class_dev_iter_exit(&iter);
-}
-
 #ifdef CONFIG_PROC_FS
 /* iterator */
 static void *disk_seqf_start(struct seq_file *seqf, loff_t *pos)
@@ -1171,6 +1149,8 @@ static void disk_release(struct device *dev)
 	might_sleep();
 	WARN_ON_ONCE(disk_live(disk));
 
+	blk_trace_remove(disk->queue);
+
 	/*
 	 * To undo the all initialization from blk_mq_init_allocated_queue in
 	 * case of a probe failure where add_disk is never called we have to
@@ -1339,35 +1319,6 @@ dev_t part_devt(struct gendisk *disk, u8 partno)
 	return devt;
 }
 
-dev_t blk_lookup_devt(const char *name, int partno)
-{
-	dev_t devt = MKDEV(0, 0);
-	struct class_dev_iter iter;
-	struct device *dev;
-
-	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
-	while ((dev = class_dev_iter_next(&iter))) {
-		struct gendisk *disk = dev_to_disk(dev);
-
-		if (strcmp(dev_name(dev), name))
-			continue;
-
-		if (partno < disk->minors) {
-			/* We need to return the right devno, even
-			 * if the partition doesn't exist yet.
-			 */
-			devt = MKDEV(MAJOR(dev->devt),
-				     MINOR(dev->devt) + partno);
-		} else {
-			devt = part_devt(disk, partno);
-			if (devt)
-				break;
-		}
-	}
-	class_dev_iter_exit(&iter);
-	return devt;
-}
-
 struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 		struct lock_class_key *lkclass)
 {

block/ioctl.c

@@ -82,7 +82,7 @@ static int compat_blkpg_ioctl(struct block_device *bdev,
 }
 #endif
 
-static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
+static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
 		unsigned long arg)
 {
 	uint64_t range[2];
@@ -90,7 +90,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 	struct inode *inode = bdev->bd_inode;
 	int err;
 
-	if (!(mode & FMODE_WRITE))
+	if (!(mode & BLK_OPEN_WRITE))
 		return -EBADF;
 
 	if (!bdev_max_discard_sectors(bdev))
@@ -120,14 +120,14 @@ fail:
 	return err;
 }
 
-static int blk_ioctl_secure_erase(struct block_device *bdev, fmode_t mode,
+static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode,
 		void __user *argp)
 {
 	uint64_t start, len;
 	uint64_t range[2];
 	int err;
 
-	if (!(mode & FMODE_WRITE))
+	if (!(mode & BLK_OPEN_WRITE))
 		return -EBADF;
 	if (!bdev_max_secure_erase_sectors(bdev))
 		return -EOPNOTSUPP;
@@ -151,7 +151,7 @@ static int blk_ioctl_secure_erase(struct block_device *bdev, fmode_t mode,
 }
 
 
-static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
+static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
 		unsigned long arg)
 {
 	uint64_t range[2];
@@ -159,7 +159,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 	struct inode *inode = bdev->bd_inode;
 	int err;
 
-	if (!(mode & FMODE_WRITE))
+	if (!(mode & BLK_OPEN_WRITE))
 		return -EBADF;
 
 	if (copy_from_user(range, (void __user *)arg, sizeof(range)))
@@ -240,7 +240,7 @@ static int compat_put_ulong(compat_ulong_t __user *argp, compat_ulong_t val)
  * drivers that implement only commands that are completely compatible
  * between 32-bit and 64-bit user space
  */
-int blkdev_compat_ptr_ioctl(struct block_device *bdev, fmode_t mode,
+int blkdev_compat_ptr_ioctl(struct block_device *bdev, blk_mode_t mode,
 			unsigned cmd, unsigned long arg)
 {
 	struct gendisk *disk = bdev->bd_disk;
@@ -254,13 +254,28 @@ int blkdev_compat_ptr_ioctl(struct block_device *bdev, fmode_t mode,
 EXPORT_SYMBOL(blkdev_compat_ptr_ioctl);
 #endif
 
-static int blkdev_pr_register(struct block_device *bdev,
+static bool blkdev_pr_allowed(struct block_device *bdev, blk_mode_t mode)
+{
+	/* no sense to make reservations for partitions */
+	if (bdev_is_partition(bdev))
+		return false;
+
+	if (capable(CAP_SYS_ADMIN))
+		return true;
+	/*
+	 * Only allow unprivileged reservations if the file descriptor is open
+	 * for writing.
+	 */
+	return mode & BLK_OPEN_WRITE;
+}
+
+static int blkdev_pr_register(struct block_device *bdev, blk_mode_t mode,
 		struct pr_registration __user *arg)
 {
 	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
 	struct pr_registration reg;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!blkdev_pr_allowed(bdev, mode))
 		return -EPERM;
 	if (!ops || !ops->pr_register)
 		return -EOPNOTSUPP;
@@ -272,13 +287,13 @@ static int blkdev_pr_register(struct block_device *bdev,
 	return ops->pr_register(bdev, reg.old_key, reg.new_key, reg.flags);
 }
 
-static int blkdev_pr_reserve(struct block_device *bdev,
+static int blkdev_pr_reserve(struct block_device *bdev, blk_mode_t mode,
 		struct pr_reservation __user *arg)
 {
 	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
 	struct pr_reservation rsv;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!blkdev_pr_allowed(bdev, mode))
 		return -EPERM;
 	if (!ops || !ops->pr_reserve)
 		return -EOPNOTSUPP;
@@ -290,13 +305,13 @@ static int blkdev_pr_reserve(struct block_device *bdev,
 	return ops->pr_reserve(bdev, rsv.key, rsv.type, rsv.flags);
 }
 
-static int blkdev_pr_release(struct block_device *bdev,
+static int blkdev_pr_release(struct block_device *bdev, blk_mode_t mode,
 		struct pr_reservation __user *arg)
 {
 	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
 	struct pr_reservation rsv;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!blkdev_pr_allowed(bdev, mode))
 		return -EPERM;
 	if (!ops || !ops->pr_release)
 		return -EOPNOTSUPP;
@@ -308,13 +323,13 @@ static int blkdev_pr_release(struct block_device *bdev,
 	return ops->pr_release(bdev, rsv.key, rsv.type);
 }
 
-static int blkdev_pr_preempt(struct block_device *bdev,
+static int blkdev_pr_preempt(struct block_device *bdev, blk_mode_t mode,
 		struct pr_preempt __user *arg, bool abort)
 {
 	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
 	struct pr_preempt p;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!blkdev_pr_allowed(bdev, mode))
 		return -EPERM;
 	if (!ops || !ops->pr_preempt)
 		return -EOPNOTSUPP;
@@ -326,13 +341,13 @@ static int blkdev_pr_preempt(struct block_device *bdev,
 	return ops->pr_preempt(bdev, p.old_key, p.new_key, p.type, abort);
 }
 
-static int blkdev_pr_clear(struct block_device *bdev,
+static int blkdev_pr_clear(struct block_device *bdev, blk_mode_t mode,
 		struct pr_clear __user *arg)
 {
 	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
 	struct pr_clear c;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!blkdev_pr_allowed(bdev, mode))
 		return -EPERM;
 	if (!ops || !ops->pr_clear)
 		return -EOPNOTSUPP;
@@ -344,8 +359,8 @@ static int blkdev_pr_clear(struct block_device *bdev,
 	return ops->pr_clear(bdev, c.key);
 }
 
-static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
+static int blkdev_flushbuf(struct block_device *bdev, unsigned cmd,
-		unsigned cmd, unsigned long arg)
+		unsigned long arg)
 {
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
@@ -354,8 +369,8 @@ static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
 	return 0;
 }
 
-static int blkdev_roset(struct block_device *bdev, fmode_t mode,
+static int blkdev_roset(struct block_device *bdev, unsigned cmd,
-		unsigned cmd, unsigned long arg)
+		unsigned long arg)
 {
 	int ret, n;
 
@@ -439,7 +454,7 @@ static int compat_hdio_getgeo(struct block_device *bdev,
 #endif
 
 /* set the logical block size */
-static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
+static int blkdev_bszset(struct block_device *bdev, blk_mode_t mode,
 		int __user *argp)
 {
 	int ret, n;
@@ -451,13 +466,13 @@ static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
 	if (get_user(n, argp))
 		return -EFAULT;
 
-	if (mode & FMODE_EXCL)
+	if (mode & BLK_OPEN_EXCL)
 		return set_blocksize(bdev, n);
 
-	if (IS_ERR(blkdev_get_by_dev(bdev->bd_dev, mode | FMODE_EXCL, &bdev)))
+	if (IS_ERR(blkdev_get_by_dev(bdev->bd_dev, mode, &bdev, NULL)))
 		return -EBUSY;
 	ret = set_blocksize(bdev, n);
-	blkdev_put(bdev, mode | FMODE_EXCL);
+	blkdev_put(bdev, &bdev);
 
 	return ret;
 }
@@ -467,7 +482,7 @@ static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
  * user space. Note the separate arg/argp parameters that are needed
  * to deal with the compat_ptr() conversion.
  */
-static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode,
+static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode,
 			       unsigned int cmd, unsigned long arg,
 			       void __user *argp)
 {
@@ -475,9 +490,9 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode,
 
 	switch (cmd) {
 	case BLKFLSBUF:
-		return blkdev_flushbuf(bdev, mode, cmd, arg);
+		return blkdev_flushbuf(bdev, cmd, arg);
 	case BLKROSET:
-		return blkdev_roset(bdev, mode, cmd, arg);
+		return blkdev_roset(bdev, cmd, arg);
 	case BLKDISCARD:
 		return blk_ioctl_discard(bdev, mode, arg);
 	case BLKSECDISCARD:
@@ -487,7 +502,7 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode,
 	case BLKGETDISKSEQ:
 		return put_u64(argp, bdev->bd_disk->diskseq);
 	case BLKREPORTZONE:
-		return blkdev_report_zones_ioctl(bdev, mode, cmd, arg);
+		return blkdev_report_zones_ioctl(bdev, cmd, arg);
 	case BLKRESETZONE:
 	case BLKOPENZONE:
 	case BLKCLOSEZONE:
@@ -534,17 +549,17 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode,
 	case BLKTRACETEARDOWN:
 		return blk_trace_ioctl(bdev, cmd, argp);
 	case IOC_PR_REGISTER:
-		return blkdev_pr_register(bdev, argp);
+		return blkdev_pr_register(bdev, mode, argp);
 	case IOC_PR_RESERVE:
-		return blkdev_pr_reserve(bdev, argp);
+		return blkdev_pr_reserve(bdev, mode, argp);
 	case IOC_PR_RELEASE:
-		return blkdev_pr_release(bdev, argp);
+		return blkdev_pr_release(bdev, mode, argp);
 	case IOC_PR_PREEMPT:
-		return blkdev_pr_preempt(bdev, argp, false);
+		return blkdev_pr_preempt(bdev, mode, argp, false);
 	case IOC_PR_PREEMPT_ABORT:
-		return blkdev_pr_preempt(bdev, argp, true);
+		return blkdev_pr_preempt(bdev, mode, argp, true);
 	case IOC_PR_CLEAR:
-		return blkdev_pr_clear(bdev, argp);
+		return blkdev_pr_clear(bdev, mode, argp);
 	default:
 		return -ENOIOCTLCMD;
 	}
@@ -560,18 +575,9 @@ long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 {
 	struct block_device *bdev = I_BDEV(file->f_mapping->host);
 	void __user *argp = (void __user *)arg;
-	fmode_t mode = file->f_mode;
+	blk_mode_t mode = file_to_blk_mode(file);
 	int ret;
 
-	/*
-	 * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
-	 * to updated it before every ioctl.
-	 */
-	if (file->f_flags & O_NDELAY)
-		mode |= FMODE_NDELAY;
-	else
-		mode &= ~FMODE_NDELAY;
-
 	switch (cmd) {
 	/* These need separate implementations for the data structure */
 	case HDIO_GETGEO:
@@ -630,16 +636,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	void __user *argp = compat_ptr(arg);
 	struct block_device *bdev = I_BDEV(file->f_mapping->host);
 	struct gendisk *disk = bdev->bd_disk;
-	fmode_t mode = file->f_mode;
+	blk_mode_t mode = file_to_blk_mode(file);
-
-	/*
-	 * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
-	 * to updated it before every ioctl.
-	 */
-	if (file->f_flags & O_NDELAY)
-		mode |= FMODE_NDELAY;
-	else
-		mode &= ~FMODE_NDELAY;
 
 	switch (cmd) {
 	/* These need separate implementations for the data structure */

block/mq-deadline.c

@@ -74,8 +74,8 @@ struct dd_per_prio {
 	struct list_head dispatch;
 	struct rb_root sort_list[DD_DIR_COUNT];
 	struct list_head fifo_list[DD_DIR_COUNT];
-	/* Next request in FIFO order. Read, write or both are NULL. */
+	/* Position of the most recently dispatched request. */
-	struct request *next_rq[DD_DIR_COUNT];
+	sector_t latest_pos[DD_DIR_COUNT];
 	struct io_stats_per_prio stats;
 };
 
@@ -156,6 +156,40 @@ deadline_latter_request(struct request *rq)
 	return NULL;
 }
 
+/*
+ * Return the first request for which blk_rq_pos() >= @pos. For zoned devices,
+ * return the first request after the start of the zone containing @pos.
+ */
+static inline struct request *deadline_from_pos(struct dd_per_prio *per_prio,
+				enum dd_data_dir data_dir, sector_t pos)
+{
+	struct rb_node *node = per_prio->sort_list[data_dir].rb_node;
+	struct request *rq, *res = NULL;
+
+	if (!node)
+		return NULL;
+
+	rq = rb_entry_rq(node);
+	/*
+	 * A zoned write may have been requeued with a starting position that
+	 * is below that of the most recently dispatched request. Hence, for
+	 * zoned writes, start searching from the start of a zone.
+	 */
+	if (blk_rq_is_seq_zoned_write(rq))
+		pos -= round_down(pos, rq->q->limits.chunk_sectors);
+
+	while (node) {
+		rq = rb_entry_rq(node);
+		if (blk_rq_pos(rq) >= pos) {
+			res = rq;
+			node = node->rb_left;
+		} else {
+			node = node->rb_right;
+		}
+	}
+	return res;
+}
+
 static void
 deadline_add_rq_rb(struct dd_per_prio *per_prio, struct request *rq)
 {
@@ -167,11 +201,6 @@ deadline_add_rq_rb(struct dd_per_prio *per_prio, struct request *rq)
 static inline void
 deadline_del_rq_rb(struct dd_per_prio *per_prio, struct request *rq)
 {
-	const enum dd_data_dir data_dir = rq_data_dir(rq);
-
-	if (per_prio->next_rq[data_dir] == rq)
-		per_prio->next_rq[data_dir] = deadline_latter_request(rq);
-
 	elv_rb_del(deadline_rb_root(per_prio, rq), rq);
 }
 
@@ -251,10 +280,6 @@ static void
 deadline_move_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
 		      struct request *rq)
 {
-	const enum dd_data_dir data_dir = rq_data_dir(rq);
-
-	per_prio->next_rq[data_dir] = deadline_latter_request(rq);
-
 	/*
 	 * take it off the sort and fifo list
 	 */
@@ -272,21 +297,15 @@ static u32 dd_queued(struct deadline_data *dd, enum dd_prio prio)
 }
 
 /*
- * deadline_check_fifo returns 0 if there are no expired requests on the fifo,
+ * deadline_check_fifo returns true if and only if there are expired requests
- * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir])
+ * in the FIFO list. Requires !list_empty(&dd->fifo_list[data_dir]).
  */
-static inline int deadline_check_fifo(struct dd_per_prio *per_prio,
+static inline bool deadline_check_fifo(struct dd_per_prio *per_prio,
-				      enum dd_data_dir data_dir)
+				       enum dd_data_dir data_dir)
 {
 	struct request *rq = rq_entry_fifo(per_prio->fifo_list[data_dir].next);
 
-	/*
+	return time_is_before_eq_jiffies((unsigned long)rq->fifo_time);
-	 * rq is expired!
-	 */
-	if (time_after_eq(jiffies, (unsigned long)rq->fifo_time))
-		return 1;
-
-	return 0;
 }
 
 /*
@@ -310,14 +329,11 @@ static struct request *deadline_skip_seq_writes(struct deadline_data *dd,
 						struct request *rq)
 {
 	sector_t pos = blk_rq_pos(rq);
-	sector_t skipped_sectors = 0;
 
-	while (rq) {
+	do {
-		if (blk_rq_pos(rq) != pos + skipped_sectors)
+		pos += blk_rq_sectors(rq);
-			break;
-		skipped_sectors += blk_rq_sectors(rq);
 		rq = deadline_latter_request(rq);
-	}
+	} while (rq && blk_rq_pos(rq) == pos);
 
 	return rq;
 }
@@ -330,7 +346,7 @@ static struct request *
 deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
 		      enum dd_data_dir data_dir)
 {
-	struct request *rq;
+	struct request *rq, *rb_rq, *next;
 	unsigned long flags;
 
 	if (list_empty(&per_prio->fifo_list[data_dir]))
@@ -348,7 +364,12 @@ deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
 	 * zones and these zones are unlocked.
 	 */
 	spin_lock_irqsave(&dd->zone_lock, flags);
-	list_for_each_entry(rq, &per_prio->fifo_list[DD_WRITE], queuelist) {
+	list_for_each_entry_safe(rq, next, &per_prio->fifo_list[DD_WRITE],
+				 queuelist) {
+		/* Check whether a prior request exists for the same zone. */
+		rb_rq = deadline_from_pos(per_prio, data_dir, blk_rq_pos(rq));
+		if (rb_rq && blk_rq_pos(rb_rq) < blk_rq_pos(rq))
+			rq = rb_rq;
 		if (blk_req_can_dispatch_to_zone(rq) &&
 		    (blk_queue_nonrot(rq->q) ||
 		     !deadline_is_seq_write(dd, rq)))
@@ -372,7 +393,8 @@ deadline_next_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
 	struct request *rq;
 	unsigned long flags;
 
-	rq = per_prio->next_rq[data_dir];
+	rq = deadline_from_pos(per_prio, data_dir,
+			       per_prio->latest_pos[data_dir]);
 	if (!rq)
 		return NULL;
 
@@ -435,6 +457,7 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd,
 		if (started_after(dd, rq, latest_start))
 			return NULL;
 		list_del_init(&rq->queuelist);
+		data_dir = rq_data_dir(rq);
 		goto done;
 	}
 
@@ -442,9 +465,11 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd,
 	 * batches are currently reads XOR writes
 	 */
 	rq = deadline_next_request(dd, per_prio, dd->last_dir);
-	if (rq && dd->batching < dd->fifo_batch)
+	if (rq && dd->batching < dd->fifo_batch) {
-		/* we have a next request are still entitled to batch */
+		/* we have a next request and are still entitled to batch */
+		data_dir = rq_data_dir(rq);
 		goto dispatch_request;
+	}
 
 	/*
 	 * at this point we are not running a batch. select the appropriate
@@ -522,6 +547,7 @@ dispatch_request:
 done:
 	ioprio_class = dd_rq_ioclass(rq);
 	prio = ioprio_class_to_prio[ioprio_class];
+	dd->per_prio[prio].latest_pos[data_dir] = blk_rq_pos(rq);
 	dd->per_prio[prio].stats.dispatched++;
 	/*
 	 * If the request needs its target zone locked, do it.
@@ -766,7 +792,7 @@ static bool dd_bio_merge(struct request_queue *q, struct bio *bio,
  * add rq to rbtree and fifo
  */
 static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
-			      blk_insert_t flags)
+			      blk_insert_t flags, struct list_head *free)
 {
 	struct request_queue *q = hctx->queue;
 	struct deadline_data *dd = q->elevator->elevator_data;
@@ -775,7 +801,6 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	u8 ioprio_class = IOPRIO_PRIO_CLASS(ioprio);
 	struct dd_per_prio *per_prio;
 	enum dd_prio prio;
-	LIST_HEAD(free);
 
 	lockdep_assert_held(&dd->lock);
 
@@ -792,10 +817,8 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		rq->elv.priv[0] = (void *)(uintptr_t)1;
 	}
 
-	if (blk_mq_sched_try_insert_merge(q, rq, &free)) {
+	if (blk_mq_sched_try_insert_merge(q, rq, free))
-		blk_mq_free_requests(&free);
 		return;
-	}
 
 	trace_block_rq_insert(rq);
 
@@ -803,6 +826,8 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		list_add(&rq->queuelist, &per_prio->dispatch);
 		rq->fifo_time = jiffies;
 	} else {
+		struct list_head *insert_before;
+
 		deadline_add_rq_rb(per_prio, rq);
 
 		if (rq_mergeable(rq)) {
@@ -815,7 +840,20 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		 * set expire time and add to fifo list
 		 */
 		rq->fifo_time = jiffies + dd->fifo_expire[data_dir];
-		list_add_tail(&rq->queuelist, &per_prio->fifo_list[data_dir]);
+		insert_before = &per_prio->fifo_list[data_dir];
+#ifdef CONFIG_BLK_DEV_ZONED
+		/*
+		 * Insert zoned writes such that requests are sorted by
+		 * position per zone.
+		 */
+		if (blk_rq_is_seq_zoned_write(rq)) {
+			struct request *rq2 = deadline_latter_request(rq);
+
+			if (rq2 && blk_rq_zone_no(rq2) == blk_rq_zone_no(rq))
+				insert_before = &rq2->queuelist;
+		}
+#endif
+		list_add_tail(&rq->queuelist, insert_before);
 	}
 }
 
@@ -828,6 +866,7 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
 {
 	struct request_queue *q = hctx->queue;
 	struct deadline_data *dd = q->elevator->elevator_data;
+	LIST_HEAD(free);
 
 	spin_lock(&dd->lock);
 	while (!list_empty(list)) {
@@ -835,9 +874,11 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
 
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		dd_insert_request(hctx, rq, flags);
+		dd_insert_request(hctx, rq, flags, &free);
 	}
 	spin_unlock(&dd->lock);
+
+	blk_mq_free_requests(&free);
 }
 
 /* Callback from inside blk_mq_rq_ctx_init(). */
@@ -1035,8 +1076,10 @@ static int deadline_##name##_next_rq_show(void *data,			\
 	struct request_queue *q = data;					\
 	struct deadline_data *dd = q->elevator->elevator_data;		\
 	struct dd_per_prio *per_prio = &dd->per_prio[prio];		\
-	struct request *rq = per_prio->next_rq[data_dir];		\
+	struct request *rq;						\
 									\
+	rq = deadline_from_pos(per_prio, data_dir,			\
+			       per_prio->latest_pos[data_dir]);		\
 	if (rq)								\
 		__blk_mq_debugfs_rq_show(m, rq);			\
 	return 0;							\

block/partitions/amiga.c

@@ -11,10 +11,18 @@
 #define pr_fmt(fmt) fmt
 
 #include <linux/types.h>
+#include <linux/mm_types.h>
+#include <linux/overflow.h>
 #include <linux/affs_hardblocks.h>
 
 #include "check.h"
 
+/* magic offsets in partition DosEnvVec */
+#define NR_HD	3
+#define NR_SECT	5
+#define LO_CYL	9
+#define HI_CYL	10
+
 static __inline__ u32
 checksum_block(__be32 *m, int size)
 {
@@ -31,8 +39,12 @@ int amiga_partition(struct parsed_partitions *state)
 	unsigned char *data;
 	struct RigidDiskBlock *rdb;
 	struct PartitionBlock *pb;
-	int start_sect, nr_sects, blk, part, res = 0;
+	u64 start_sect, nr_sects;
-	int blksize = 1;	/* Multiplier for disk block size */
+	sector_t blk, end_sect;
+	u32 cylblk;		/* rdb_CylBlocks = nr_heads*sect_per_track */
+	u32 nr_hd, nr_sect, lo_cyl, hi_cyl;
+	int part, res = 0;
+	unsigned int blksize = 1;	/* Multiplier for disk block size */
 	int slot = 1;
 
 	for (blk = 0; ; blk++, put_dev_sector(sect)) {
@@ -40,7 +52,7 @@ int amiga_partition(struct parsed_partitions *state)
 			goto rdb_done;
 		data = read_part_sector(state, blk, &sect);
 		if (!data) {
-			pr_err("Dev %s: unable to read RDB block %d\n",
+			pr_err("Dev %s: unable to read RDB block %llu\n",
 			       state->disk->disk_name, blk);
 			res = -1;
 			goto rdb_done;
@@ -57,12 +69,12 @@ int amiga_partition(struct parsed_partitions *state)
 		*(__be32 *)(data+0xdc) = 0;
 		if (checksum_block((__be32 *)data,
 				be32_to_cpu(rdb->rdb_SummedLongs) & 0x7F)==0) {
-			pr_err("Trashed word at 0xd0 in block %d ignored in checksum calculation\n",
+			pr_err("Trashed word at 0xd0 in block %llu ignored in checksum calculation\n",
 			       blk);
 			break;
 		}
 
-		pr_err("Dev %s: RDB in block %d has bad checksum\n",
+		pr_err("Dev %s: RDB in block %llu has bad checksum\n",
 		       state->disk->disk_name, blk);
 	}
 
@@ -79,10 +91,15 @@ int amiga_partition(struct parsed_partitions *state)
 	blk = be32_to_cpu(rdb->rdb_PartitionList);
 	put_dev_sector(sect);
 	for (part = 1; blk>0 && part<=16; part++, put_dev_sector(sect)) {
-		blk *= blksize;	/* Read in terms partition table understands */
+		/* Read in terms partition table understands */
+		if (check_mul_overflow(blk, (sector_t) blksize, &blk)) {
+			pr_err("Dev %s: overflow calculating partition block %llu! Skipping partitions %u and beyond\n",
+				state->disk->disk_name, blk, part);
+			break;
+		}
 		data = read_part_sector(state, blk, &sect);
 		if (!data) {
-			pr_err("Dev %s: unable to read partition block %d\n",
+			pr_err("Dev %s: unable to read partition block %llu\n",
 			       state->disk->disk_name, blk);
 			res = -1;
 			goto rdb_done;
@@ -94,19 +111,70 @@ int amiga_partition(struct parsed_partitions *state)
 		if (checksum_block((__be32 *)pb, be32_to_cpu(pb->pb_SummedLongs) & 0x7F) != 0 )
 			continue;
 
-		/* Tell Kernel about it */
+		/* RDB gives us more than enough rope to hang ourselves with,
+		 * many times over (2^128 bytes if all fields max out).
+		 * Some careful checks are in order, so check for potential
+		 * overflows.
+		 * We are multiplying four 32 bit numbers to one sector_t!
+		 */
+
+		nr_hd   = be32_to_cpu(pb->pb_Environment[NR_HD]);
+		nr_sect = be32_to_cpu(pb->pb_Environment[NR_SECT]);
+
+		/* CylBlocks is total number of blocks per cylinder */
+		if (check_mul_overflow(nr_hd, nr_sect, &cylblk)) {
+			pr_err("Dev %s: heads*sects %u overflows u32, skipping partition!\n",
+				state->disk->disk_name, cylblk);
+			continue;
+		}
+
+		/* check for consistency with RDB defined CylBlocks */
+		if (cylblk > be32_to_cpu(rdb->rdb_CylBlocks)) {
+			pr_warn("Dev %s: cylblk %u > rdb_CylBlocks %u!\n",
+				state->disk->disk_name, cylblk,
+				be32_to_cpu(rdb->rdb_CylBlocks));
+		}
+
+		/* RDB allows for variable logical block size -
+		 * normalize to 512 byte blocks and check result.
+		 */
+
+		if (check_mul_overflow(cylblk, blksize, &cylblk)) {
+			pr_err("Dev %s: partition %u bytes per cyl. overflows u32, skipping partition!\n",
+				state->disk->disk_name, part);
+			continue;
+		}
+
+		/* Calculate partition start and end. Limit of 32 bit on cylblk
+		 * guarantees no overflow occurs if LBD support is enabled.
+		 */
+
+		lo_cyl = be32_to_cpu(pb->pb_Environment[LO_CYL]);
+		start_sect = ((u64) lo_cyl * cylblk);
+
+		hi_cyl = be32_to_cpu(pb->pb_Environment[HI_CYL]);
+		nr_sects = (((u64) hi_cyl - lo_cyl + 1) * cylblk);
 
-		nr_sects = (be32_to_cpu(pb->pb_Environment[10]) + 1 -
-			    be32_to_cpu(pb->pb_Environment[9])) *
-			   be32_to_cpu(pb->pb_Environment[3]) *
-			   be32_to_cpu(pb->pb_Environment[5]) *
-			   blksize;
 		if (!nr_sects)
 			continue;
-		start_sect = be32_to_cpu(pb->pb_Environment[9]) *
+
-			     be32_to_cpu(pb->pb_Environment[3]) *
+		/* Warn user if partition end overflows u32 (AmigaDOS limit) */
-			     be32_to_cpu(pb->pb_Environment[5]) *
+
-			     blksize;
+		if ((start_sect + nr_sects) > UINT_MAX) {
+			pr_warn("Dev %s: partition %u (%llu-%llu) needs 64 bit device support!\n",
+				state->disk->disk_name, part,
+				start_sect, start_sect + nr_sects);
+		}
+
+		if (check_add_overflow(start_sect, nr_sects, &end_sect)) {
+			pr_err("Dev %s: partition %u (%llu-%llu) needs LBD device support, skipping partition!\n",
+				state->disk->disk_name, part,
+				start_sect, end_sect);
+			continue;
+		}
+
+		/* Tell Kernel about it */
+
 		put_partition(state,slot++,start_sect,nr_sects);
 		{
 			/* Be even more informative to aid mounting */

block/partitions/core.c

@@ -12,7 +12,7 @@
 #include <linux/raid/detect.h>
 #include "check.h"
 
-static int (*check_part[])(struct parsed_partitions *) = {
+static int (*const check_part[])(struct parsed_partitions *) = {
 	/*
 	 * Probe partition formats with tables at disk address 0
 	 * that also have an ADFS boot block at 0xdc0.
@@ -228,7 +228,7 @@ static struct attribute *part_attrs[] = {
 	NULL
 };
 
-static struct attribute_group part_attr_group = {
+static const struct attribute_group part_attr_group = {
 	.attrs = part_attrs,
 };
 
@@ -256,31 +256,36 @@ static int part_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	return 0;
 }
 
-struct device_type part_type = {
+const struct device_type part_type = {
 	.name		= "partition",
 	.groups		= part_attr_groups,
 	.release	= part_release,
 	.uevent		= part_uevent,
 };
 
-static void delete_partition(struct block_device *part)
+void drop_partition(struct block_device *part)
 {
 	lockdep_assert_held(&part->bd_disk->open_mutex);
 
-	fsync_bdev(part);
-	__invalidate_device(part, true);
-
 	xa_erase(&part->bd_disk->part_tbl, part->bd_partno);
 	kobject_put(part->bd_holder_dir);
-	device_del(&part->bd_device);
 
+	device_del(&part->bd_device);
+	put_device(&part->bd_device);
+}
+
+static void delete_partition(struct block_device *part)
+{
 	/*
 	 * Remove the block device from the inode hash, so that it cannot be
 	 * looked up any more even when openers still hold references.
 	 */
 	remove_inode_hash(part->bd_inode);
 
-	put_device(&part->bd_device);
+	fsync_bdev(part);
+	__invalidate_device(part, true);
+
+	drop_partition(part);
 }
 
 static ssize_t whole_disk_show(struct device *dev,
@@ -288,7 +293,7 @@ static ssize_t whole_disk_show(struct device *dev,
 {
 	return 0;
 }
-static DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL);
+static const DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL);
 
 /*
  * Must be called either with open_mutex held, before a disk can be opened or
@@ -436,10 +441,21 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start,
 int bdev_add_partition(struct gendisk *disk, int partno, sector_t start,
 		sector_t length)
 {
+	sector_t capacity = get_capacity(disk), end;
 	struct block_device *part;
 	int ret;
 
 	mutex_lock(&disk->open_mutex);
+	if (check_add_overflow(start, length, &end)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (start >= capacity || end > capacity) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	if (!disk_live(disk)) {
 		ret = -ENXIO;
 		goto out;
@@ -519,17 +535,6 @@ static bool disk_unlock_native_capacity(struct gendisk *disk)
 	return true;
 }
 
-void blk_drop_partitions(struct gendisk *disk)
-{
-	struct block_device *part;
-	unsigned long idx;
-
-	lockdep_assert_held(&disk->open_mutex);
-
-	xa_for_each_start(&disk->part_tbl, idx, part, 1)
-		delete_partition(part);
-}
-
 static bool blk_add_partition(struct gendisk *disk,
 		struct parsed_partitions *state, int p)
 {
@@ -646,6 +651,8 @@ out_free_state:
 
 int bdev_disk_changed(struct gendisk *disk, bool invalidate)
 {
+	struct block_device *part;
+	unsigned long idx;
 	int ret = 0;
 
 	lockdep_assert_held(&disk->open_mutex);
@@ -658,8 +665,9 @@ rescan:
 		return -EBUSY;
 	sync_blockdev(disk->part0);
 	invalidate_bdev(disk->part0);
-	blk_drop_partitions(disk);
 
+	xa_for_each_start(&disk->part_tbl, idx, part, 1)
+		delete_partition(part);
 	clear_bit(GD_NEED_PART_SCAN, &disk->state);
 
 	/*

drivers/base/dd.c

@@ -751,14 +751,12 @@ static int really_probe_debug(struct device *dev, struct device_driver *drv)
  *
  * Should somehow figure out how to use a semaphore, not an atomic variable...
  */
-int driver_probe_done(void)
+bool __init driver_probe_done(void)
 {
 	int local_probe_count = atomic_read(&probe_count);
 
 	pr_debug("%s: probe_count = %d\n", __func__, local_probe_count);
-	if (local_probe_count)
+	return !local_probe_count;
-		return -EBUSY;
-	return 0;
 }
 
 /**

drivers/block/amiflop.c

@@ -1532,7 +1532,7 @@ static int fd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return 0;
 }
 
-static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode,
+static int fd_locked_ioctl(struct block_device *bdev, blk_mode_t mode,
 		    unsigned int cmd, unsigned long param)
 {
 	struct amiga_floppy_struct *p = bdev->bd_disk->private_data;
@@ -1607,7 +1607,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode,
 	return 0;
 }
 
-static int fd_ioctl(struct block_device *bdev, fmode_t mode,
+static int fd_ioctl(struct block_device *bdev, blk_mode_t mode,
 			     unsigned int cmd, unsigned long param)
 {
 	int ret;
@@ -1654,10 +1654,10 @@ static void fd_probe(int dev)
  * /dev/PS0 etc), and disallows simultaneous access to the same
  * drive with different device numbers.
  */
-static int floppy_open(struct block_device *bdev, fmode_t mode)
+static int floppy_open(struct gendisk *disk, blk_mode_t mode)
 {
-	int drive = MINOR(bdev->bd_dev) & 3;
+	int drive = disk->first_minor & 3;
-	int system =  (MINOR(bdev->bd_dev) & 4) >> 2;
+	int system = (disk->first_minor & 4) >> 2;
 	int old_dev;
 	unsigned long flags;
 
@@ -1673,10 +1673,9 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 		mutex_unlock(&amiflop_mutex);
 		return -ENXIO;
 	}
-
+	if (mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) {
-	if (mode & (FMODE_READ|FMODE_WRITE)) {
+		disk_check_media_change(disk);
-		bdev_check_media_change(bdev);
+		if (mode & BLK_OPEN_WRITE) {
-		if (mode & FMODE_WRITE) {
 			int wrprot;
 
 			get_fdc(drive);
@@ -1691,7 +1690,6 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 			}
 		}
 	}
-
 	local_irq_save(flags);
 	fd_ref[drive]++;
 	fd_device[drive] = system;
@@ -1709,7 +1707,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 	return 0;
 }
 
-static void floppy_release(struct gendisk *disk, fmode_t mode)
+static void floppy_release(struct gendisk *disk)
 {
 	struct amiga_floppy_struct *p = disk->private_data;
 	int drive = p - unit;

drivers/block/aoe/aoeblk.c

@@ -204,9 +204,9 @@ aoedisk_rm_debugfs(struct aoedev *d)
 }
 
 static int
-aoeblk_open(struct block_device *bdev, fmode_t mode)
+aoeblk_open(struct gendisk *disk, blk_mode_t mode)
 {
-	struct aoedev *d = bdev->bd_disk->private_data;
+	struct aoedev *d = disk->private_data;
 	ulong flags;
 
 	if (!virt_addr_valid(d)) {
@@ -232,7 +232,7 @@ aoeblk_open(struct block_device *bdev, fmode_t mode)
 }
 
 static void
-aoeblk_release(struct gendisk *disk, fmode_t mode)
+aoeblk_release(struct gendisk *disk)
 {
 	struct aoedev *d = disk->private_data;
 	ulong flags;
@@ -285,7 +285,7 @@ aoeblk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 }
 
 static int
-aoeblk_ioctl(struct block_device *bdev, fmode_t mode, uint cmd, ulong arg)
+aoeblk_ioctl(struct block_device *bdev, blk_mode_t mode, uint cmd, ulong arg)
 {
 	struct aoedev *d;
 

drivers/block/aoe/aoechr.c

@@ -49,7 +49,7 @@ static int emsgs_head_idx, emsgs_tail_idx;
 static struct completion emsgs_comp;
 static spinlock_t emsgs_lock;
 static int nblocked_emsgs_readers;
-static struct class *aoe_class;
+
 static struct aoe_chardev chardevs[] = {
 	{ MINOR_ERR, "err" },
 	{ MINOR_DISCOVER, "discover" },
@@ -58,6 +58,16 @@ static struct aoe_chardev chardevs[] = {
 	{ MINOR_FLUSH, "flush" },
 };
 
+static char *aoe_devnode(const struct device *dev, umode_t *mode)
+{
+	return kasprintf(GFP_KERNEL, "etherd/%s", dev_name(dev));
+}
+
+static const struct class aoe_class = {
+	.name = "aoe",
+	.devnode = aoe_devnode,
+};
+
 static int
 discover(void)
 {
@@ -273,11 +283,6 @@ static const struct file_operations aoe_fops = {
 	.llseek = noop_llseek,
 };
 
-static char *aoe_devnode(const struct device *dev, umode_t *mode)
-{
-	return kasprintf(GFP_KERNEL, "etherd/%s", dev_name(dev));
-}
-
 int __init
 aoechr_init(void)
 {
@@ -290,15 +295,14 @@ aoechr_init(void)
 	}
 	init_completion(&emsgs_comp);
 	spin_lock_init(&emsgs_lock);
-	aoe_class = class_create("aoe");
+	n = class_register(&aoe_class);
-	if (IS_ERR(aoe_class)) {
+	if (n) {
 		unregister_chrdev(AOE_MAJOR, "aoechr");
-		return PTR_ERR(aoe_class);
+		return n;
 	}
-	aoe_class->devnode = aoe_devnode;
 
 	for (i = 0; i < ARRAY_SIZE(chardevs); ++i)
-		device_create(aoe_class, NULL,
+		device_create(&aoe_class, NULL,
 			      MKDEV(AOE_MAJOR, chardevs[i].minor), NULL,
 			      chardevs[i].name);
 
@@ -311,8 +315,8 @@ aoechr_exit(void)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(chardevs); ++i)
-		device_destroy(aoe_class, MKDEV(AOE_MAJOR, chardevs[i].minor));
+		device_destroy(&aoe_class, MKDEV(AOE_MAJOR, chardevs[i].minor));
-	class_destroy(aoe_class);
+	class_unregister(&aoe_class);
 	unregister_chrdev(AOE_MAJOR, "aoechr");
 }
 

drivers/block/ataflop.c

@@ -442,13 +442,13 @@ static void fd_times_out(struct timer_list *unused);
 static void finish_fdc( void );
 static void finish_fdc_done( int dummy );
 static void setup_req_params( int drive );
-static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
+static int fd_locked_ioctl(struct block_device *bdev, blk_mode_t mode,
-                     cmd, unsigned long param);
+		unsigned int cmd, unsigned long param);
 static void fd_probe( int drive );
 static int fd_test_drive_present( int drive );
 static void config_types( void );
-static int floppy_open(struct block_device *bdev, fmode_t mode);
+static int floppy_open(struct gendisk *disk, blk_mode_t mode);
-static void floppy_release(struct gendisk *disk, fmode_t mode);
+static void floppy_release(struct gendisk *disk);
 
 /************************* End of Prototypes **************************/
 
@@ -1581,7 +1581,7 @@ out:
 	return BLK_STS_OK;
 }
 
-static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode,
+static int fd_locked_ioctl(struct block_device *bdev, blk_mode_t mode,
 		    unsigned int cmd, unsigned long param)
 {
 	struct gendisk *disk = bdev->bd_disk;
@@ -1760,15 +1760,15 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode,
 		/* invalidate the buffer track to force a reread */
 		BufferDrive = -1;
 		set_bit(drive, &fake_change);
-		if (bdev_check_media_change(bdev))
+		if (disk_check_media_change(disk))
-			floppy_revalidate(bdev->bd_disk);
+			floppy_revalidate(disk);
 		return 0;
 	default:
 		return -EINVAL;
 	}
 }
 
-static int fd_ioctl(struct block_device *bdev, fmode_t mode,
+static int fd_ioctl(struct block_device *bdev, blk_mode_t mode,
 			     unsigned int cmd, unsigned long arg)
 {
 	int ret;
@@ -1915,32 +1915,31 @@ static void __init config_types( void )
  * drive with different device numbers.
  */
 
-static int floppy_open(struct block_device *bdev, fmode_t mode)
+static int floppy_open(struct gendisk *disk, blk_mode_t mode)
 {
-	struct atari_floppy_struct *p = bdev->bd_disk->private_data;
+	struct atari_floppy_struct *p = disk->private_data;
-	int type  = MINOR(bdev->bd_dev) >> 2;
+	int type = disk->first_minor >> 2;
 
 	DPRINT(("fd_open: type=%d\n",type));
 	if (p->ref && p->type != type)
 		return -EBUSY;
 
-	if (p->ref == -1 || (p->ref && mode & FMODE_EXCL))
+	if (p->ref == -1 || (p->ref && mode & BLK_OPEN_EXCL))
 		return -EBUSY;
-
+	if (mode & BLK_OPEN_EXCL)
-	if (mode & FMODE_EXCL)
 		p->ref = -1;
 	else
 		p->ref++;
 
 	p->type = type;
 
-	if (mode & FMODE_NDELAY)
+	if (mode & BLK_OPEN_NDELAY)
 		return 0;
 
-	if (mode & (FMODE_READ|FMODE_WRITE)) {
+	if (mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) {
-		if (bdev_check_media_change(bdev))
+		if (disk_check_media_change(disk))
-			floppy_revalidate(bdev->bd_disk);
+			floppy_revalidate(disk);
-		if (mode & FMODE_WRITE) {
+		if (mode & BLK_OPEN_WRITE) {
 			if (p->wpstat) {
 				if (p->ref < 0)
 					p->ref = 0;
@@ -1953,18 +1952,18 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 	return 0;
 }
 
-static int floppy_unlocked_open(struct block_device *bdev, fmode_t mode)
+static int floppy_unlocked_open(struct gendisk *disk, blk_mode_t mode)
 {
 	int ret;
 
 	mutex_lock(&ataflop_mutex);
-	ret = floppy_open(bdev, mode);
+	ret = floppy_open(disk, mode);
 	mutex_unlock(&ataflop_mutex);
 
 	return ret;
 }
 
-static void floppy_release(struct gendisk *disk, fmode_t mode)
+static void floppy_release(struct gendisk *disk)
 {
 	struct atari_floppy_struct *p = disk->private_data;
 	mutex_lock(&ataflop_mutex);

drivers/block/brd.c

@@ -19,7 +19,7 @@
 #include <linux/highmem.h>
 #include <linux/mutex.h>
 #include <linux/pagemap.h>
-#include <linux/radix-tree.h>
+#include <linux/xarray.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/backing-dev.h>
@@ -28,7 +28,7 @@
 #include <linux/uaccess.h>
 
 /*
- * Each block ramdisk device has a radix_tree brd_pages of pages that stores
+ * Each block ramdisk device has a xarray brd_pages of pages that stores
  * the pages containing the block device's contents. A brd page's ->index is
  * its offset in PAGE_SIZE units. This is similar to, but in no way connected
  * with, the kernel's pagecache or buffer cache (which sit above our block
@@ -40,11 +40,9 @@ struct brd_device {
 	struct list_head	brd_list;
 
 	/*
-	 * Backing store of pages and lock to protect it. This is the contents
+	 * Backing store of pages. This is the contents of the block device.
-	 * of the block device.
 	 */
-	spinlock_t		brd_lock;
+	struct xarray	        brd_pages;
-	struct radix_tree_root	brd_pages;
 	u64			brd_nr_pages;
 };
 
@@ -56,21 +54,8 @@ static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector)
 	pgoff_t idx;
 	struct page *page;
 
-	/*
-	 * The page lifetime is protected by the fact that we have opened the
-	 * device node -- brd pages will never be deleted under us, so we
-	 * don't need any further locking or refcounting.
-	 *
-	 * This is strictly true for the radix-tree nodes as well (ie. we
-	 * don't actually need the rcu_read_lock()), however that is not a
-	 * documented feature of the radix-tree API so it is better to be
-	 * safe here (we don't have total exclusion from radix tree updates
-	 * here, only deletes).
-	 */
-	rcu_read_lock();
 	idx = sector >> PAGE_SECTORS_SHIFT; /* sector to page index */
-	page = radix_tree_lookup(&brd->brd_pages, idx);
+	page = xa_load(&brd->brd_pages, idx);
-	rcu_read_unlock();
 
 	BUG_ON(page && page->index != idx);
 
@@ -83,7 +68,7 @@ static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector)
 static int brd_insert_page(struct brd_device *brd, sector_t sector, gfp_t gfp)
 {
 	pgoff_t idx;
-	struct page *page;
+	struct page *page, *cur;
 	int ret = 0;
 
 	page = brd_lookup_page(brd, sector);
@@ -94,71 +79,42 @@ static int brd_insert_page(struct brd_device *brd, sector_t sector, gfp_t gfp)
 	if (!page)
 		return -ENOMEM;
 
-	if (radix_tree_maybe_preload(gfp)) {
+	xa_lock(&brd->brd_pages);
-		__free_page(page);
-		return -ENOMEM;
-	}
 
-	spin_lock(&brd->brd_lock);
 	idx = sector >> PAGE_SECTORS_SHIFT;
 	page->index = idx;
-	if (radix_tree_insert(&brd->brd_pages, idx, page)) {
+
+	cur = __xa_cmpxchg(&brd->brd_pages, idx, NULL, page, gfp);
+
+	if (unlikely(cur)) {
 		__free_page(page);
-		page = radix_tree_lookup(&brd->brd_pages, idx);
+		ret = xa_err(cur);
-		if (!page)
+		if (!ret && (cur->index != idx))
-			ret = -ENOMEM;
-		else if (page->index != idx)
 			ret = -EIO;
 	} else {
 		brd->brd_nr_pages++;
 	}
-	spin_unlock(&brd->brd_lock);
 
-	radix_tree_preload_end();
+	xa_unlock(&brd->brd_pages);
+
 	return ret;
 }
 
 /*
- * Free all backing store pages and radix tree. This must only be called when
+ * Free all backing store pages and xarray. This must only be called when
  * there are no other users of the device.
  */
-#define FREE_BATCH 16
 static void brd_free_pages(struct brd_device *brd)
 {
-	unsigned long pos = 0;
+	struct page *page;
-	struct page *pages[FREE_BATCH];
+	pgoff_t idx;
-	int nr_pages;
 
-	do {
+	xa_for_each(&brd->brd_pages, idx, page) {
-		int i;
+		__free_page(page);
-
-		nr_pages = radix_tree_gang_lookup(&brd->brd_pages,
-				(void **)pages, pos, FREE_BATCH);
-
-		for (i = 0; i < nr_pages; i++) {
-			void *ret;
-
-			BUG_ON(pages[i]->index < pos);
-			pos = pages[i]->index;
-			ret = radix_tree_delete(&brd->brd_pages, pos);
-			BUG_ON(!ret || ret != pages[i]);
-			__free_page(pages[i]);
-		}
-
-		pos++;
-
-		/*
-		 * It takes 3.4 seconds to remove 80GiB ramdisk.
-		 * So, we need cond_resched to avoid stalling the CPU.
-		 */
 		cond_resched();
+	}
 
-		/*
+	xa_destroy(&brd->brd_pages);
-		 * This assumes radix_tree_gang_lookup always returns as
-		 * many pages as possible. If the radix-tree code changes,
-		 * so will this have to.
-		 */
-	} while (nr_pages == FREE_BATCH);
 }
 
 /*
@@ -372,8 +328,7 @@ static int brd_alloc(int i)
 	brd->brd_number		= i;
 	list_add_tail(&brd->brd_list, &brd_devices);
 
-	spin_lock_init(&brd->brd_lock);
+	xa_init(&brd->brd_pages);
-	INIT_RADIX_TREE(&brd->brd_pages, GFP_ATOMIC);
 
 	snprintf(buf, DISK_NAME_LEN, "ram%d", i);
 	if (!IS_ERR_OR_NULL(brd_debugfs_dir))

drivers/block/drbd/drbd_bitmap.c

@@ -1043,9 +1043,7 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho
 	bio = bio_alloc_bioset(device->ldev->md_bdev, 1, op, GFP_NOIO,
 			&drbd_md_io_bio_set);
 	bio->bi_iter.bi_sector = on_disk_sector;
-	/* bio_add_page of a single page to an empty bio will always succeed,
+	__bio_add_page(bio, page, len, 0);
-	 * according to api.  Do we want to assert that? */
-	bio_add_page(bio, page, len, 0);
 	bio->bi_private = ctx;
 	bio->bi_end_io = drbd_bm_endio;
 

drivers/block/drbd/drbd_main.c

@@ -37,7 +37,6 @@
 #include <linux/notifier.h>
 #include <linux/kthread.h>
 #include <linux/workqueue.h>
-#define __KERNEL_SYSCALLS__
 #include <linux/unistd.h>
 #include <linux/vmalloc.h>
 #include <linux/sched/signal.h>
@@ -50,8 +49,8 @@
 #include "drbd_debugfs.h"
 
 static DEFINE_MUTEX(drbd_main_mutex);
-static int drbd_open(struct block_device *bdev, fmode_t mode);
+static int drbd_open(struct gendisk *disk, blk_mode_t mode);
-static void drbd_release(struct gendisk *gd, fmode_t mode);
+static void drbd_release(struct gendisk *gd);
 static void md_sync_timer_fn(struct timer_list *t);
 static int w_bitmap_io(struct drbd_work *w, int unused);
 
@@ -1883,9 +1882,9 @@ int drbd_send_all(struct drbd_connection *connection, struct socket *sock, void
 	return 0;
 }
 
-static int drbd_open(struct block_device *bdev, fmode_t mode)
+static int drbd_open(struct gendisk *disk, blk_mode_t mode)
 {
-	struct drbd_device *device = bdev->bd_disk->private_data;
+	struct drbd_device *device = disk->private_data;
 	unsigned long flags;
 	int rv = 0;
 
@@ -1895,7 +1894,7 @@ static int drbd_open(struct block_device *bdev, fmode_t mode)
 	 * and no race with updating open_cnt */
 
 	if (device->state.role != R_PRIMARY) {
-		if (mode & FMODE_WRITE)
+		if (mode & BLK_OPEN_WRITE)
 			rv = -EROFS;
 		else if (!drbd_allow_oos)
 			rv = -EMEDIUMTYPE;
@@ -1909,9 +1908,10 @@ static int drbd_open(struct block_device *bdev, fmode_t mode)
 	return rv;
 }
 
-static void drbd_release(struct gendisk *gd, fmode_t mode)
+static void drbd_release(struct gendisk *gd)
 {
 	struct drbd_device *device = gd->private_data;
+
 	mutex_lock(&drbd_main_mutex);
 	device->open_cnt--;
 	mutex_unlock(&drbd_main_mutex);

drivers/block/drbd/drbd_nl.c

@@ -1640,8 +1640,8 @@ static struct block_device *open_backing_dev(struct drbd_device *device,
 	struct block_device *bdev;
 	int err = 0;
 
-	bdev = blkdev_get_by_path(bdev_path,
+	bdev = blkdev_get_by_path(bdev_path, BLK_OPEN_READ | BLK_OPEN_WRITE,
-				  FMODE_READ | FMODE_WRITE | FMODE_EXCL, claim_ptr);
+				  claim_ptr, NULL);
 	if (IS_ERR(bdev)) {
 		drbd_err(device, "open(\"%s\") failed with %ld\n",
 				bdev_path, PTR_ERR(bdev));
@@ -1653,7 +1653,7 @@ static struct block_device *open_backing_dev(struct drbd_device *device,
 
 	err = bd_link_disk_holder(bdev, device->vdisk);
 	if (err) {
-		blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
+		blkdev_put(bdev, claim_ptr);
 		drbd_err(device, "bd_link_disk_holder(\"%s\", ...) failed with %d\n",
 				bdev_path, err);
 		bdev = ERR_PTR(err);
@@ -1695,13 +1695,13 @@ static int open_backing_devices(struct drbd_device *device,
 }
 
 static void close_backing_dev(struct drbd_device *device, struct block_device *bdev,
-	bool do_bd_unlink)
+		void *claim_ptr, bool do_bd_unlink)
 {
 	if (!bdev)
 		return;
 	if (do_bd_unlink)
 		bd_unlink_disk_holder(bdev, device->vdisk);
-	blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
+	blkdev_put(bdev, claim_ptr);
 }
 
 void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev *ldev)
@@ -1709,8 +1709,11 @@ void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev *
 	if (ldev == NULL)
 		return;
 
-	close_backing_dev(device, ldev->md_bdev, ldev->md_bdev != ldev->backing_bdev);
+	close_backing_dev(device, ldev->md_bdev,
-	close_backing_dev(device, ldev->backing_bdev, true);
+			  ldev->md.meta_dev_idx < 0 ?
+				(void *)device : (void *)drbd_m_holder,
+			  ldev->md_bdev != ldev->backing_bdev);
+	close_backing_dev(device, ldev->backing_bdev, device, true);
 
 	kfree(ldev->disk_conf);
 	kfree(ldev);
@@ -2126,8 +2129,11 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
  fail:
 	conn_reconfig_done(connection);
 	if (nbc) {
-		close_backing_dev(device, nbc->md_bdev, nbc->md_bdev != nbc->backing_bdev);
+		close_backing_dev(device, nbc->md_bdev,
-		close_backing_dev(device, nbc->backing_bdev, true);
+			  nbc->disk_conf->meta_dev_idx < 0 ?
+				(void *)device : (void *)drbd_m_holder,
+			  nbc->md_bdev != nbc->backing_bdev);
+		close_backing_dev(device, nbc->backing_bdev, device, true);
 		kfree(nbc);
 	}
 	kfree(new_disk_conf);

drivers/block/drbd/drbd_receiver.c

@@ -27,7 +27,6 @@
 #include <uapi/linux/sched/types.h>
 #include <linux/sched/signal.h>
 #include <linux/pkt_sched.h>
-#define __KERNEL_SYSCALLS__
 #include <linux/unistd.h>
 #include <linux/vmalloc.h>
 #include <linux/random.h>

drivers/block/floppy.c

@@ -402,7 +402,7 @@ static struct floppy_drive_struct drive_state[N_DRIVE];
 static struct floppy_write_errors write_errors[N_DRIVE];
 static struct timer_list motor_off_timer[N_DRIVE];
 static struct blk_mq_tag_set tag_sets[N_DRIVE];
-static struct block_device *opened_bdev[N_DRIVE];
+static struct gendisk *opened_disk[N_DRIVE];
 static DEFINE_MUTEX(open_lock);
 static struct floppy_raw_cmd *raw_cmd, default_raw_cmd;
 
@@ -3210,13 +3210,13 @@ static int floppy_raw_cmd_ioctl(int type, int drive, int cmd,
 
 #endif
 
-static int invalidate_drive(struct block_device *bdev)
+static int invalidate_drive(struct gendisk *disk)
 {
 	/* invalidate the buffer track to force a reread */
-	set_bit((long)bdev->bd_disk->private_data, &fake_change);
+	set_bit((long)disk->private_data, &fake_change);
 	process_fd_request();
-	if (bdev_check_media_change(bdev))
+	if (disk_check_media_change(disk))
-		floppy_revalidate(bdev->bd_disk);
+		floppy_revalidate(disk);
 	return 0;
 }
 
@@ -3251,10 +3251,11 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g,
 			    floppy_type[type].size + 1;
 		process_fd_request();
 		for (cnt = 0; cnt < N_DRIVE; cnt++) {
-			struct block_device *bdev = opened_bdev[cnt];
+			struct gendisk *disk = opened_disk[cnt];
-			if (!bdev || ITYPE(drive_state[cnt].fd_device) != type)
+
+			if (!disk || ITYPE(drive_state[cnt].fd_device) != type)
 				continue;
-			__invalidate_device(bdev, true);
+			__invalidate_device(disk->part0, true);
 		}
 		mutex_unlock(&open_lock);
 	} else {
@@ -3287,7 +3288,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g,
 		    drive_state[current_drive].maxtrack ||
 		    ((user_params[drive].sect ^ oldStretch) &
 		     (FD_SWAPSIDES | FD_SECTBASEMASK)))
-			invalidate_drive(bdev);
+			invalidate_drive(bdev->bd_disk);
 		else
 			process_fd_request();
 	}
@@ -3393,8 +3394,8 @@ static bool valid_floppy_drive_params(const short autodetect[FD_AUTODETECT_SIZE]
 	return true;
 }
 
-static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
+static int fd_locked_ioctl(struct block_device *bdev, blk_mode_t mode,
-		    unsigned long param)
+		unsigned int cmd, unsigned long param)
 {
 	int drive = (long)bdev->bd_disk->private_data;
 	int type = ITYPE(drive_state[drive].fd_device);
@@ -3427,7 +3428,8 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		return ret;
 
 	/* permission checks */
-	if (((cmd & 0x40) && !(mode & (FMODE_WRITE | FMODE_WRITE_IOCTL))) ||
+	if (((cmd & 0x40) &&
+	     !(mode & (BLK_OPEN_WRITE | BLK_OPEN_WRITE_IOCTL))) ||
 	    ((cmd & 0x80) && !capable(CAP_SYS_ADMIN)))
 		return -EPERM;
 
@@ -3464,7 +3466,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		current_type[drive] = NULL;
 		floppy_sizes[drive] = MAX_DISK_SIZE << 1;
 		drive_state[drive].keep_data = 0;
-		return invalidate_drive(bdev);
+		return invalidate_drive(bdev->bd_disk);
 	case FDSETPRM:
 	case FDDEFPRM:
 		return set_geometry(cmd, &inparam.g, drive, type, bdev);
@@ -3503,7 +3505,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 	case FDFLUSH:
 		if (lock_fdc(drive))
 			return -EINTR;
-		return invalidate_drive(bdev);
+		return invalidate_drive(bdev->bd_disk);
 	case FDSETEMSGTRESH:
 		drive_params[drive].max_errors.reporting = (unsigned short)(param & 0x0f);
 		return 0;
@@ -3565,7 +3567,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 	return 0;
 }
 
-static int fd_ioctl(struct block_device *bdev, fmode_t mode,
+static int fd_ioctl(struct block_device *bdev, blk_mode_t mode,
 			     unsigned int cmd, unsigned long param)
 {
 	int ret;
@@ -3653,8 +3655,8 @@ struct compat_floppy_write_errors {
 #define FDGETFDCSTAT32 _IOR(2, 0x15, struct compat_floppy_fdc_state)
 #define FDWERRORGET32  _IOR(2, 0x17, struct compat_floppy_write_errors)
 
-static int compat_set_geometry(struct block_device *bdev, fmode_t mode, unsigned int cmd,
+static int compat_set_geometry(struct block_device *bdev, blk_mode_t mode,
-		    struct compat_floppy_struct __user *arg)
+		unsigned int cmd, struct compat_floppy_struct __user *arg)
 {
 	struct floppy_struct v;
 	int drive, type;
@@ -3663,7 +3665,7 @@ static int compat_set_geometry(struct block_device *bdev, fmode_t mode, unsigned
 	BUILD_BUG_ON(offsetof(struct floppy_struct, name) !=
 		     offsetof(struct compat_floppy_struct, name));
 
-	if (!(mode & (FMODE_WRITE | FMODE_WRITE_IOCTL)))
+	if (!(mode & (BLK_OPEN_WRITE | BLK_OPEN_WRITE_IOCTL)))
 		return -EPERM;
 
 	memset(&v, 0, sizeof(struct floppy_struct));
@@ -3860,8 +3862,8 @@ static int compat_werrorget(int drive,
 	return 0;
 }
 
-static int fd_compat_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
+static int fd_compat_ioctl(struct block_device *bdev, blk_mode_t mode,
-		    unsigned long param)
+		unsigned int cmd, unsigned long param)
 {
 	int drive = (long)bdev->bd_disk->private_data;
 	switch (cmd) {
@@ -3962,7 +3964,7 @@ static void __init config_types(void)
 		pr_cont("\n");
 }
 
-static void floppy_release(struct gendisk *disk, fmode_t mode)
+static void floppy_release(struct gendisk *disk)
 {
 	int drive = (long)disk->private_data;
 
@@ -3973,7 +3975,7 @@ static void floppy_release(struct gendisk *disk, fmode_t mode)
 		drive_state[drive].fd_ref = 0;
 	}
 	if (!drive_state[drive].fd_ref)
-		opened_bdev[drive] = NULL;
+		opened_disk[drive] = NULL;
 	mutex_unlock(&open_lock);
 	mutex_unlock(&floppy_mutex);
 }
@@ -3983,9 +3985,9 @@ static void floppy_release(struct gendisk *disk, fmode_t mode)
  * /dev/PS0 etc), and disallows simultaneous access to the same
  * drive with different device numbers.
  */
-static int floppy_open(struct block_device *bdev, fmode_t mode)
+static int floppy_open(struct gendisk *disk, blk_mode_t mode)
 {
-	int drive = (long)bdev->bd_disk->private_data;
+	int drive = (long)disk->private_data;
 	int old_dev, new_dev;
 	int try;
 	int res = -EBUSY;
@@ -3994,7 +3996,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 	mutex_lock(&floppy_mutex);
 	mutex_lock(&open_lock);
 	old_dev = drive_state[drive].fd_device;
-	if (opened_bdev[drive] && opened_bdev[drive] != bdev)
+	if (opened_disk[drive] && opened_disk[drive] != disk)
 		goto out2;
 
 	if (!drive_state[drive].fd_ref && (drive_params[drive].flags & FD_BROKEN_DCL)) {
@@ -4004,7 +4006,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 
 	drive_state[drive].fd_ref++;
 
-	opened_bdev[drive] = bdev;
+	opened_disk[drive] = disk;
 
 	res = -ENXIO;
 
@@ -4038,7 +4040,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 		}
 	}
 
-	new_dev = MINOR(bdev->bd_dev);
+	new_dev = disk->first_minor;
 	drive_state[drive].fd_device = new_dev;
 	set_capacity(disks[drive][ITYPE(new_dev)], floppy_sizes[new_dev]);
 	if (old_dev != -1 && old_dev != new_dev) {
@@ -4048,21 +4050,20 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 
 	if (fdc_state[FDC(drive)].rawcmd == 1)
 		fdc_state[FDC(drive)].rawcmd = 2;
-
+	if (!(mode & BLK_OPEN_NDELAY)) {
-	if (!(mode & FMODE_NDELAY)) {
+		if (mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) {
-		if (mode & (FMODE_READ|FMODE_WRITE)) {
 			drive_state[drive].last_checked = 0;
 			clear_bit(FD_OPEN_SHOULD_FAIL_BIT,
 				  &drive_state[drive].flags);
-			if (bdev_check_media_change(bdev))
+			if (disk_check_media_change(disk))
-				floppy_revalidate(bdev->bd_disk);
+				floppy_revalidate(disk);
 			if (test_bit(FD_DISK_CHANGED_BIT, &drive_state[drive].flags))
 				goto out;
 			if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &drive_state[drive].flags))
 				goto out;
 		}
 		res = -EROFS;
-		if ((mode & FMODE_WRITE) &&
+		if ((mode & BLK_OPEN_WRITE) &&
 		    !test_bit(FD_DISK_WRITABLE_BIT, &drive_state[drive].flags))
 			goto out;
 	}
@@ -4073,7 +4074,7 @@ out:
 	drive_state[drive].fd_ref--;
 
 	if (!drive_state[drive].fd_ref)
-		opened_bdev[drive] = NULL;
+		opened_disk[drive] = NULL;
 out2:
 	mutex_unlock(&open_lock);
 	mutex_unlock(&floppy_mutex);
@@ -4147,7 +4148,7 @@ static int __floppy_read_block_0(struct block_device *bdev, int drive)
 	cbdata.drive = drive;
 
 	bio_init(&bio, bdev, &bio_vec, 1, REQ_OP_READ);
-	bio_add_page(&bio, page, block_size(bdev), 0);
+	__bio_add_page(&bio, page, block_size(bdev), 0);
 
 	bio.bi_iter.bi_sector = 0;
 	bio.bi_flags |= (1 << BIO_QUIET);
@@ -4203,7 +4204,8 @@ static int floppy_revalidate(struct gendisk *disk)
 			drive_state[drive].generation++;
 		if (drive_no_geom(drive)) {
 			/* auto-sensing */
-			res = __floppy_read_block_0(opened_bdev[drive], drive);
+			res = __floppy_read_block_0(opened_disk[drive]->part0,
+						    drive);
 		} else {
 			if (cf)
 				poll_drive(false, FD_RAW_NEED_DISK);

drivers/block/loop.c

@@ -990,7 +990,7 @@ loop_set_status_from_info(struct loop_device *lo,
 	return 0;
 }
 
-static int loop_configure(struct loop_device *lo, fmode_t mode,
+static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 			  struct block_device *bdev,
 			  const struct loop_config *config)
 {
@@ -1014,8 +1014,8 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 	 * If we don't hold exclusive handle for the device, upgrade to it
 	 * here to avoid changing device under exclusive owner.
 	 */
-	if (!(mode & FMODE_EXCL)) {
+	if (!(mode & BLK_OPEN_EXCL)) {
-		error = bd_prepare_to_claim(bdev, loop_configure);
+		error = bd_prepare_to_claim(bdev, loop_configure, NULL);
 		if (error)
 			goto out_putf;
 	}
@@ -1050,7 +1050,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 	if (error)
 		goto out_unlock;
 
-	if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) ||
+	if (!(file->f_mode & FMODE_WRITE) || !(mode & BLK_OPEN_WRITE) ||
 	    !file->f_op->write_iter)
 		lo->lo_flags |= LO_FLAGS_READ_ONLY;
 
@@ -1116,7 +1116,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 	if (partscan)
 		loop_reread_partitions(lo);
 
-	if (!(mode & FMODE_EXCL))
+	if (!(mode & BLK_OPEN_EXCL))
 		bd_abort_claiming(bdev, loop_configure);
 
 	return 0;
@@ -1124,7 +1124,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 out_unlock:
 	loop_global_unlock(lo, is_loop);
 out_bdev:
-	if (!(mode & FMODE_EXCL))
+	if (!(mode & BLK_OPEN_EXCL))
 		bd_abort_claiming(bdev, loop_configure);
 out_putf:
 	fput(file);
@@ -1528,7 +1528,7 @@ static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd,
 	return err;
 }
 
-static int lo_ioctl(struct block_device *bdev, fmode_t mode,
+static int lo_ioctl(struct block_device *bdev, blk_mode_t mode,
 	unsigned int cmd, unsigned long arg)
 {
 	struct loop_device *lo = bdev->bd_disk->private_data;
@@ -1563,24 +1563,22 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 		return loop_clr_fd(lo);
 	case LOOP_SET_STATUS:
 		err = -EPERM;
-		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) {
+		if ((mode & BLK_OPEN_WRITE) || capable(CAP_SYS_ADMIN))
 			err = loop_set_status_old(lo, argp);
-		}
 		break;
 	case LOOP_GET_STATUS:
 		return loop_get_status_old(lo, argp);
 	case LOOP_SET_STATUS64:
 		err = -EPERM;
-		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) {
+		if ((mode & BLK_OPEN_WRITE) || capable(CAP_SYS_ADMIN))
 			err = loop_set_status64(lo, argp);
-		}
 		break;
 	case LOOP_GET_STATUS64:
 		return loop_get_status64(lo, argp);
 	case LOOP_SET_CAPACITY:
 	case LOOP_SET_DIRECT_IO:
 	case LOOP_SET_BLOCK_SIZE:
-		if (!(mode & FMODE_WRITE) && !capable(CAP_SYS_ADMIN))
+		if (!(mode & BLK_OPEN_WRITE) && !capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		fallthrough;
 	default:
@@ -1691,7 +1689,7 @@ loop_get_status_compat(struct loop_device *lo,
 	return err;
 }
 
-static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
+static int lo_compat_ioctl(struct block_device *bdev, blk_mode_t mode,
 			   unsigned int cmd, unsigned long arg)
 {
 	struct loop_device *lo = bdev->bd_disk->private_data;
@@ -1727,7 +1725,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 }
 #endif
 
-static void lo_release(struct gendisk *disk, fmode_t mode)
+static void lo_release(struct gendisk *disk)
 {
 	struct loop_device *lo = disk->private_data;
 

drivers/block/mtip32xx/mtip32xx.c

@@ -3041,7 +3041,7 @@ static int rssd_disk_name_format(char *prefix,
  *                 structure pointer.
  */
 static int mtip_block_ioctl(struct block_device *dev,
-			    fmode_t mode,
+			    blk_mode_t mode,
 			    unsigned cmd,
 			    unsigned long arg)
 {
@@ -3079,7 +3079,7 @@ static int mtip_block_ioctl(struct block_device *dev,
  *                 structure pointer.
  */
 static int mtip_block_compat_ioctl(struct block_device *dev,
-			    fmode_t mode,
+			    blk_mode_t mode,
 			    unsigned cmd,
 			    unsigned long arg)
 {

drivers/block/nbd.c

@@ -1502,7 +1502,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 	return -ENOTTY;
 }
 
-static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
+static int nbd_ioctl(struct block_device *bdev, blk_mode_t mode,
 		     unsigned int cmd, unsigned long arg)
 {
 	struct nbd_device *nbd = bdev->bd_disk->private_data;
@@ -1553,13 +1553,13 @@ static struct nbd_config *nbd_alloc_config(void)
 	return config;
 }
 
-static int nbd_open(struct block_device *bdev, fmode_t mode)
+static int nbd_open(struct gendisk *disk, blk_mode_t mode)
 {
 	struct nbd_device *nbd;
 	int ret = 0;
 
 	mutex_lock(&nbd_index_mutex);
-	nbd = bdev->bd_disk->private_data;
+	nbd = disk->private_data;
 	if (!nbd) {
 		ret = -ENXIO;
 		goto out;
@@ -1587,17 +1587,17 @@ static int nbd_open(struct block_device *bdev, fmode_t mode)
 		refcount_inc(&nbd->refs);
 		mutex_unlock(&nbd->config_lock);
 		if (max_part)
-			set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
+			set_bit(GD_NEED_PART_SCAN, &disk->state);
 	} else if (nbd_disconnected(nbd->config)) {
 		if (max_part)
-			set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
+			set_bit(GD_NEED_PART_SCAN, &disk->state);
 	}
 out:
 	mutex_unlock(&nbd_index_mutex);
 	return ret;
 }
 
-static void nbd_release(struct gendisk *disk, fmode_t mode)
+static void nbd_release(struct gendisk *disk)
 {
 	struct nbd_device *nbd = disk->private_data;
 
@@ -1776,7 +1776,8 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 		if (err == -ENOSPC)
 			err = -EEXIST;
 	} else {
-		err = idr_alloc(&nbd_index_idr, nbd, 0, 0, GFP_KERNEL);
+		err = idr_alloc(&nbd_index_idr, nbd, 0,
+				(MINORMASK >> part_shift) + 1, GFP_KERNEL);
 		if (err >= 0)
 			index = err;
 	}

drivers/block/rbd.c

@@ -660,9 +660,9 @@ static bool pending_result_dec(struct pending_result *pending, int *result)
 	return true;
 }
 
-static int rbd_open(struct block_device *bdev, fmode_t mode)
+static int rbd_open(struct gendisk *disk, blk_mode_t mode)
 {
-	struct rbd_device *rbd_dev = bdev->bd_disk->private_data;
+	struct rbd_device *rbd_dev = disk->private_data;
 	bool removing = false;
 
 	spin_lock_irq(&rbd_dev->lock);
@@ -679,7 +679,7 @@ static int rbd_open(struct block_device *bdev, fmode_t mode)
 	return 0;
 }
 
-static void rbd_release(struct gendisk *disk, fmode_t mode)
+static void rbd_release(struct gendisk *disk)
 {
 	struct rbd_device *rbd_dev = disk->private_data;
 	unsigned long open_count_before;

drivers/block/rnbd/Makefile

@@ -3,13 +3,11 @@
 ccflags-y := -I$(srctree)/drivers/infiniband/ulp/rtrs
 
 rnbd-client-y := rnbd-clt.o \
-		  rnbd-clt-sysfs.o \
+		  rnbd-clt-sysfs.o
-		  rnbd-common.o
 
 CFLAGS_rnbd-srv-trace.o = -I$(src)
 
-rnbd-server-y := rnbd-common.o \
+rnbd-server-y := rnbd-srv.o \
-		  rnbd-srv.o \
 		  rnbd-srv-sysfs.o \
 		  rnbd-srv-trace.o
 

drivers/block/rnbd/rnbd-clt-sysfs.c

@@ -24,7 +24,9 @@
 #include "rnbd-clt.h"
 
 static struct device *rnbd_dev;
-static struct class *rnbd_dev_class;
+static const struct class rnbd_dev_class = {
+	.name = "rnbd_client",
+};
 static struct kobject *rnbd_devs_kobj;
 
 enum {
@@ -278,7 +280,7 @@ static ssize_t access_mode_show(struct kobject *kobj,
 
 	dev = container_of(kobj, struct rnbd_clt_dev, kobj);
 
-	return sysfs_emit(page, "%s\n", rnbd_access_mode_str(dev->access_mode));
+	return sysfs_emit(page, "%s\n", rnbd_access_modes[dev->access_mode].str);
 }
 
 static struct kobj_attribute rnbd_clt_access_mode =
@@ -596,7 +598,7 @@ static ssize_t rnbd_clt_map_device_store(struct kobject *kobj,
 
 	pr_info("Mapping device %s on session %s, (access_mode: %s, nr_poll_queues: %d)\n",
 		pathname, sessname,
-		rnbd_access_mode_str(access_mode),
+		rnbd_access_modes[access_mode].str,
 		nr_poll_queues);
 
 	dev = rnbd_clt_map_device(sessname, paths, path_cnt, port_nr, pathname,
@@ -646,11 +648,11 @@ int rnbd_clt_create_sysfs_files(void)
 {
 	int err;
 
-	rnbd_dev_class = class_create("rnbd-client");
+	err = class_register(&rnbd_dev_class);
-	if (IS_ERR(rnbd_dev_class))
+	if (err)
-		return PTR_ERR(rnbd_dev_class);
+		return err;
 
-	rnbd_dev = device_create_with_groups(rnbd_dev_class, NULL,
+	rnbd_dev = device_create_with_groups(&rnbd_dev_class, NULL,
 					      MKDEV(0, 0), NULL,
 					      default_attr_groups, "ctl");
 	if (IS_ERR(rnbd_dev)) {
@@ -666,9 +668,9 @@ int rnbd_clt_create_sysfs_files(void)
 	return 0;
 
 dev_destroy:
-	device_destroy(rnbd_dev_class, MKDEV(0, 0));
+	device_destroy(&rnbd_dev_class, MKDEV(0, 0));
 cls_destroy:
-	class_destroy(rnbd_dev_class);
+	class_unregister(&rnbd_dev_class);
 
 	return err;
 }
@@ -678,6 +680,6 @@ void rnbd_clt_destroy_sysfs_files(void)
 	sysfs_remove_group(&rnbd_dev->kobj, &default_attr_group);
 	kobject_del(rnbd_devs_kobj);
 	kobject_put(rnbd_devs_kobj);
-	device_destroy(rnbd_dev_class, MKDEV(0, 0));
+	device_destroy(&rnbd_dev_class, MKDEV(0, 0));
-	class_destroy(rnbd_dev_class);
+	class_unregister(&rnbd_dev_class);
 }

drivers/block/rnbd/rnbd-clt.c

@@ -921,11 +921,11 @@ rnbd_clt_session *find_or_create_sess(const char *sessname, bool *first)
 	return sess;
 }
 
-static int rnbd_client_open(struct block_device *block_device, fmode_t mode)
+static int rnbd_client_open(struct gendisk *disk, blk_mode_t mode)
 {
-	struct rnbd_clt_dev *dev = block_device->bd_disk->private_data;
+	struct rnbd_clt_dev *dev = disk->private_data;
 
-	if (get_disk_ro(dev->gd) && (mode & FMODE_WRITE))
+	if (get_disk_ro(dev->gd) && (mode & BLK_OPEN_WRITE))
 		return -EPERM;
 
 	if (dev->dev_state == DEV_STATE_UNMAPPED ||
@@ -935,7 +935,7 @@ static int rnbd_client_open(struct block_device *block_device, fmode_t mode)
 	return 0;
 }
 
-static void rnbd_client_release(struct gendisk *gen, fmode_t mode)
+static void rnbd_client_release(struct gendisk *gen)
 {
 	struct rnbd_clt_dev *dev = gen->private_data;
 

drivers/block/rnbd/rnbd-common.c

@@ -1,23 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * RDMA Network Block Driver
- *
- * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved.
- * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved.
- * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved.
- */
-#include "rnbd-proto.h"
-
-const char *rnbd_access_mode_str(enum rnbd_access_mode mode)
-{
-	switch (mode) {
-	case RNBD_ACCESS_RO:
-		return "ro";
-	case RNBD_ACCESS_RW:
-		return "rw";
-	case RNBD_ACCESS_MIGRATION:
-		return "migration";
-	default:
-		return "unknown";
-	}
-}

drivers/block/rnbd/rnbd-proto.h

@@ -61,6 +61,15 @@ enum rnbd_access_mode {
 	RNBD_ACCESS_MIGRATION,
 };
 
+static const __maybe_unused struct {
+	enum rnbd_access_mode mode;
+	const char *str;
+} rnbd_access_modes[] = {
+	[RNBD_ACCESS_RO] = {RNBD_ACCESS_RO, "ro"},
+	[RNBD_ACCESS_RW] = {RNBD_ACCESS_RW, "rw"},
+	[RNBD_ACCESS_MIGRATION] = {RNBD_ACCESS_MIGRATION, "migration"},
+};
+
 /**
  * struct rnbd_msg_sess_info - initial session info from client to server
  * @hdr:		message header
@@ -185,7 +194,6 @@ struct rnbd_msg_io {
 enum rnbd_io_flags {
 
 	/* Operations */
-
 	RNBD_OP_READ		= 0,
 	RNBD_OP_WRITE		= 1,
 	RNBD_OP_FLUSH		= 2,
@@ -193,15 +201,9 @@ enum rnbd_io_flags {
 	RNBD_OP_SECURE_ERASE	= 4,
 	RNBD_OP_WRITE_SAME	= 5,
 
-	RNBD_OP_LAST,
-
 	/* Flags */
-
 	RNBD_F_SYNC  = 1<<(RNBD_OP_BITS + 0),
 	RNBD_F_FUA   = 1<<(RNBD_OP_BITS + 1),
-
-	RNBD_F_ALL   = (RNBD_F_SYNC | RNBD_F_FUA)
-
 };
 
 static inline u32 rnbd_op(u32 flags)
@@ -214,21 +216,6 @@ static inline u32 rnbd_flags(u32 flags)
 	return flags & ~RNBD_OP_MASK;
 }
 
-static inline bool rnbd_flags_supported(u32 flags)
-{
-	u32 op;
-
-	op = rnbd_op(flags);
-	flags = rnbd_flags(flags);
-
-	if (op >= RNBD_OP_LAST)
-		return false;
-	if (flags & ~RNBD_F_ALL)
-		return false;
-
-	return true;
-}
-
 static inline blk_opf_t rnbd_to_bio_flags(u32 rnbd_opf)
 {
 	blk_opf_t bio_opf;

drivers/block/rnbd/rnbd-srv-sysfs.c

@@ -9,7 +9,6 @@
 #undef pr_fmt
 #define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt
 
-#include <uapi/linux/limits.h>
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
 #include <linux/stat.h>
@@ -20,7 +19,9 @@
 #include "rnbd-srv.h"
 
 static struct device *rnbd_dev;
-static struct class *rnbd_dev_class;
+static const struct class rnbd_dev_class = {
+	.name = "rnbd-server",
+};
 static struct kobject *rnbd_devs_kobj;
 
 static void rnbd_srv_dev_release(struct kobject *kobj)
@@ -88,8 +89,7 @@ static ssize_t read_only_show(struct kobject *kobj, struct kobj_attribute *attr,
 
 	sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj);
 
-	return sysfs_emit(page, "%d\n",
+	return sysfs_emit(page, "%d\n", sess_dev->readonly);
-			  !(sess_dev->open_flags & FMODE_WRITE));
 }
 
 static struct kobj_attribute rnbd_srv_dev_session_ro_attr =
@@ -104,7 +104,7 @@ static ssize_t access_mode_show(struct kobject *kobj,
 	sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj);
 
 	return sysfs_emit(page, "%s\n",
-			  rnbd_access_mode_str(sess_dev->access_mode));
+			  rnbd_access_modes[sess_dev->access_mode].str);
 }
 
 static struct kobj_attribute rnbd_srv_dev_session_access_mode_attr =
@@ -215,12 +215,12 @@ int rnbd_srv_create_sysfs_files(void)
 {
 	int err;
 
-	rnbd_dev_class = class_create("rnbd-server");
+	err = class_register(&rnbd_dev_class);
-	if (IS_ERR(rnbd_dev_class))
+	if (err)
-		return PTR_ERR(rnbd_dev_class);
+		return err;
 
-	rnbd_dev = device_create(rnbd_dev_class, NULL,
+	rnbd_dev = device_create(&rnbd_dev_class, NULL,
-				  MKDEV(0, 0), NULL, "ctl");
+				 MKDEV(0, 0), NULL, "ctl");
 	if (IS_ERR(rnbd_dev)) {
 		err = PTR_ERR(rnbd_dev);
 		goto cls_destroy;
@@ -234,9 +234,9 @@ int rnbd_srv_create_sysfs_files(void)
 	return 0;
 
 dev_destroy:
-	device_destroy(rnbd_dev_class, MKDEV(0, 0));
+	device_destroy(&rnbd_dev_class, MKDEV(0, 0));
 cls_destroy:
-	class_destroy(rnbd_dev_class);
+	class_unregister(&rnbd_dev_class);
 
 	return err;
 }
@@ -245,6 +245,6 @@ void rnbd_srv_destroy_sysfs_files(void)
 {
 	kobject_del(rnbd_devs_kobj);
 	kobject_put(rnbd_devs_kobj);
-	device_destroy(rnbd_dev_class, MKDEV(0, 0));
+	device_destroy(&rnbd_dev_class, MKDEV(0, 0));
-	class_destroy(rnbd_dev_class);
+	class_unregister(&rnbd_dev_class);
 }

drivers/block/rnbd/rnbd-srv.c

@@ -96,7 +96,7 @@ rnbd_get_sess_dev(int dev_id, struct rnbd_srv_session *srv_sess)
 		ret = kref_get_unless_zero(&sess_dev->kref);
 	rcu_read_unlock();
 
-	if (!sess_dev || !ret)
+	if (!ret)
 		return ERR_PTR(-ENXIO);
 
 	return sess_dev;
@@ -180,7 +180,7 @@ static void destroy_device(struct kref *kref)
 
 	WARN_ONCE(!list_empty(&dev->sess_dev_list),
 		  "Device %s is being destroyed but still in use!\n",
-		  dev->id);
+		  dev->name);
 
 	spin_lock(&dev_lock);
 	list_del(&dev->list);
@@ -219,10 +219,10 @@ void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev, bool keep_id)
 	rnbd_put_sess_dev(sess_dev);
 	wait_for_completion(&dc); /* wait for inflights to drop to zero */
 
-	blkdev_put(sess_dev->bdev, sess_dev->open_flags);
+	blkdev_put(sess_dev->bdev, NULL);
 	mutex_lock(&sess_dev->dev->lock);
 	list_del(&sess_dev->dev_list);
-	if (sess_dev->open_flags & FMODE_WRITE)
+	if (!sess_dev->readonly)
 		sess_dev->dev->open_write_cnt--;
 	mutex_unlock(&sess_dev->dev->lock);
 
@@ -356,7 +356,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 			    const void *msg, size_t len,
 			    void *data, size_t datalen);
 
-static int process_msg_sess_info(struct rnbd_srv_session *srv_sess,
+static void process_msg_sess_info(struct rnbd_srv_session *srv_sess,
 				 const void *msg, size_t len,
 				 void *data, size_t datalen);
 
@@ -384,8 +384,7 @@ static int rnbd_srv_rdma_ev(void *priv, struct rtrs_srv_op *id,
 		ret = process_msg_open(srv_sess, usr, usrlen, data, datalen);
 		break;
 	case RNBD_MSG_SESS_INFO:
-		ret = process_msg_sess_info(srv_sess, usr, usrlen, data,
+		process_msg_sess_info(srv_sess, usr, usrlen, data, datalen);
-					    datalen);
 		break;
 	default:
 		pr_warn("Received unexpected message type %d from session %s\n",
@@ -431,7 +430,7 @@ static struct rnbd_srv_dev *rnbd_srv_init_srv_dev(struct block_device *bdev)
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	snprintf(dev->id, sizeof(dev->id), "%pg", bdev);
+	snprintf(dev->name, sizeof(dev->name), "%pg", bdev);
 	kref_init(&dev->kref);
 	INIT_LIST_HEAD(&dev->sess_dev_list);
 	mutex_init(&dev->lock);
@@ -446,7 +445,7 @@ rnbd_srv_find_or_add_srv_dev(struct rnbd_srv_dev *new_dev)
 
 	spin_lock(&dev_lock);
 	list_for_each_entry(dev, &dev_list, list) {
-		if (!strncmp(dev->id, new_dev->id, sizeof(dev->id))) {
+		if (!strncmp(dev->name, new_dev->name, sizeof(dev->name))) {
 			if (!kref_get_unless_zero(&dev->kref))
 				/*
 				 * We lost the race, device is almost dead.
@@ -467,39 +466,38 @@ static int rnbd_srv_check_update_open_perm(struct rnbd_srv_dev *srv_dev,
 					    struct rnbd_srv_session *srv_sess,
 					    enum rnbd_access_mode access_mode)
 {
-	int ret = -EPERM;
+	int ret = 0;
 
 	mutex_lock(&srv_dev->lock);
 
 	switch (access_mode) {
 	case RNBD_ACCESS_RO:
-		ret = 0;
 		break;
 	case RNBD_ACCESS_RW:
 		if (srv_dev->open_write_cnt == 0)  {
 			srv_dev->open_write_cnt++;
-			ret = 0;
 		} else {
 			pr_err("Mapping device '%s' for session %s with RW permissions failed. Device already opened as 'RW' by %d client(s), access mode %s.\n",
-			       srv_dev->id, srv_sess->sessname,
+			       srv_dev->name, srv_sess->sessname,
 			       srv_dev->open_write_cnt,
-			       rnbd_access_mode_str(access_mode));
+			       rnbd_access_modes[access_mode].str);
+			ret = -EPERM;
 		}
 		break;
 	case RNBD_ACCESS_MIGRATION:
 		if (srv_dev->open_write_cnt < 2) {
 			srv_dev->open_write_cnt++;
-			ret = 0;
 		} else {
 			pr_err("Mapping device '%s' for session %s with migration permissions failed. Device already opened as 'RW' by %d client(s), access mode %s.\n",
-			       srv_dev->id, srv_sess->sessname,
+			       srv_dev->name, srv_sess->sessname,
 			       srv_dev->open_write_cnt,
-			       rnbd_access_mode_str(access_mode));
+			       rnbd_access_modes[access_mode].str);
+			ret = -EPERM;
 		}
 		break;
 	default:
 		pr_err("Received mapping request for device '%s' on session %s with invalid access mode: %d\n",
-		       srv_dev->id, srv_sess->sessname, access_mode);
+		       srv_dev->name, srv_sess->sessname, access_mode);
 		ret = -EINVAL;
 	}
 
@@ -561,7 +559,7 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp,
 static struct rnbd_srv_sess_dev *
 rnbd_srv_create_set_sess_dev(struct rnbd_srv_session *srv_sess,
 			      const struct rnbd_msg_open *open_msg,
-			      struct block_device *bdev, fmode_t open_flags,
+			      struct block_device *bdev, bool readonly,
 			      struct rnbd_srv_dev *srv_dev)
 {
 	struct rnbd_srv_sess_dev *sdev = rnbd_sess_dev_alloc(srv_sess);
@@ -576,7 +574,7 @@ rnbd_srv_create_set_sess_dev(struct rnbd_srv_session *srv_sess,
 	sdev->bdev		= bdev;
 	sdev->sess		= srv_sess;
 	sdev->dev		= srv_dev;
-	sdev->open_flags	= open_flags;
+	sdev->readonly		= readonly;
 	sdev->access_mode	= open_msg->access_mode;
 
 	return sdev;
@@ -631,7 +629,7 @@ static char *rnbd_srv_get_full_path(struct rnbd_srv_session *srv_sess,
 	return full_path;
 }
 
-static int process_msg_sess_info(struct rnbd_srv_session *srv_sess,
+static void process_msg_sess_info(struct rnbd_srv_session *srv_sess,
 				 const void *msg, size_t len,
 				 void *data, size_t datalen)
 {
@@ -644,8 +642,6 @@ static int process_msg_sess_info(struct rnbd_srv_session *srv_sess,
 
 	rsp->hdr.type = cpu_to_le16(RNBD_MSG_SESS_INFO_RSP);
 	rsp->ver = srv_sess->ver;
-
-	return 0;
 }
 
 /**
@@ -681,15 +677,14 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 	struct rnbd_srv_sess_dev *srv_sess_dev;
 	const struct rnbd_msg_open *open_msg = msg;
 	struct block_device *bdev;
-	fmode_t open_flags;
+	blk_mode_t open_flags = BLK_OPEN_READ;
 	char *full_path;
 	struct rnbd_msg_open_rsp *rsp = data;
 
 	trace_process_msg_open(srv_sess, open_msg);
 
-	open_flags = FMODE_READ;
 	if (open_msg->access_mode != RNBD_ACCESS_RO)
-		open_flags |= FMODE_WRITE;
+		open_flags |= BLK_OPEN_WRITE;
 
 	mutex_lock(&srv_sess->lock);
 
@@ -719,7 +714,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 		goto reject;
 	}
 
-	bdev = blkdev_get_by_path(full_path, open_flags, THIS_MODULE);
+	bdev = blkdev_get_by_path(full_path, open_flags, NULL, NULL);
 	if (IS_ERR(bdev)) {
 		ret = PTR_ERR(bdev);
 		pr_err("Opening device '%s' on session %s failed, failed to open the block device, err: %d\n",
@@ -736,9 +731,9 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 		goto blkdev_put;
 	}
 
-	srv_sess_dev = rnbd_srv_create_set_sess_dev(srv_sess, open_msg,
+	srv_sess_dev = rnbd_srv_create_set_sess_dev(srv_sess, open_msg, bdev,
-						     bdev, open_flags,
+				open_msg->access_mode == RNBD_ACCESS_RO,
-						     srv_dev);
+				srv_dev);
 	if (IS_ERR(srv_sess_dev)) {
 		pr_err("Opening device '%s' on session %s failed, creating sess_dev failed, err: %ld\n",
 		       full_path, srv_sess->sessname, PTR_ERR(srv_sess_dev));
@@ -774,7 +769,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 	list_add(&srv_sess_dev->dev_list, &srv_dev->sess_dev_list);
 	mutex_unlock(&srv_dev->lock);
 
-	rnbd_srv_info(srv_sess_dev, "Opened device '%s'\n", srv_dev->id);
+	rnbd_srv_info(srv_sess_dev, "Opened device '%s'\n", srv_dev->name);
 
 	kfree(full_path);
 
@@ -795,7 +790,7 @@ srv_dev_put:
 	}
 	rnbd_put_srv_dev(srv_dev);
 blkdev_put:
-	blkdev_put(bdev, open_flags);
+	blkdev_put(bdev, NULL);
 free_path:
 	kfree(full_path);
 reject:
@@ -808,7 +803,7 @@ static struct rtrs_srv_ctx *rtrs_ctx;
 static struct rtrs_srv_ops rtrs_ops;
 static int __init rnbd_srv_init_module(void)
 {
-	int err;
+	int err = 0;
 
 	BUILD_BUG_ON(sizeof(struct rnbd_msg_hdr) != 4);
 	BUILD_BUG_ON(sizeof(struct rnbd_msg_sess_info) != 36);
@@ -822,19 +817,17 @@ static int __init rnbd_srv_init_module(void)
 	};
 	rtrs_ctx = rtrs_srv_open(&rtrs_ops, port_nr);
 	if (IS_ERR(rtrs_ctx)) {
-		err = PTR_ERR(rtrs_ctx);
 		pr_err("rtrs_srv_open(), err: %d\n", err);
-		return err;
+		return PTR_ERR(rtrs_ctx);
 	}
 
 	err = rnbd_srv_create_sysfs_files();
 	if (err) {
 		pr_err("rnbd_srv_create_sysfs_files(), err: %d\n", err);
 		rtrs_srv_close(rtrs_ctx);
-		return err;
 	}
 
-	return 0;
+	return err;
 }
 
 static void __exit rnbd_srv_cleanup_module(void)

drivers/block/rnbd/rnbd-srv.h

@@ -35,7 +35,7 @@ struct rnbd_srv_dev {
 	struct kobject                  dev_kobj;
 	struct kobject                  *dev_sessions_kobj;
 	struct kref                     kref;
-	char				id[NAME_MAX];
+	char				name[NAME_MAX];
 	/* List of rnbd_srv_sess_dev structs */
 	struct list_head		sess_dev_list;
 	struct mutex			lock;
@@ -52,7 +52,7 @@ struct rnbd_srv_sess_dev {
 	struct kobject                  kobj;
 	u32                             device_id;
 	bool				keep_id;
-	fmode_t                         open_flags;
+	bool				readonly;
 	struct kref			kref;
 	struct completion               *destroy_comp;
 	char				pathname[NAME_MAX];

drivers/block/sunvdc.c

@@ -139,7 +139,7 @@ static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo)
  * when vdisk_mtype is VD_MEDIA_TYPE_CD or VD_MEDIA_TYPE_DVD.
  * Needed to be able to install inside an ldom from an iso image.
  */
-static int vdc_ioctl(struct block_device *bdev, fmode_t mode,
+static int vdc_ioctl(struct block_device *bdev, blk_mode_t mode,
 		     unsigned command, unsigned long argument)
 {
 	struct vdc_port *port = bdev->bd_disk->private_data;

drivers/block/swim.c

@@ -608,20 +608,18 @@ static void setup_medium(struct floppy_state *fs)
 	}
 }
 
-static int floppy_open(struct block_device *bdev, fmode_t mode)
+static int floppy_open(struct gendisk *disk, blk_mode_t mode)
 {
-	struct floppy_state *fs = bdev->bd_disk->private_data;
+	struct floppy_state *fs = disk->private_data;
 	struct swim __iomem *base = fs->swd->base;
 	int err;
 
-	if (fs->ref_count == -1 || (fs->ref_count && mode & FMODE_EXCL))
+	if (fs->ref_count == -1 || (fs->ref_count && mode & BLK_OPEN_EXCL))
 		return -EBUSY;
-
+	if (mode & BLK_OPEN_EXCL)
-	if (mode & FMODE_EXCL)
 		fs->ref_count = -1;
 	else
 		fs->ref_count++;
-
 	swim_write(base, setup, S_IBM_DRIVE  | S_FCLK_DIV2);
 	udelay(10);
 	swim_drive(base, fs->location);
@@ -636,13 +634,13 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 
 	set_capacity(fs->disk, fs->total_secs);
 
-	if (mode & FMODE_NDELAY)
+	if (mode & BLK_OPEN_NDELAY)
 		return 0;
 
-	if (mode & (FMODE_READ|FMODE_WRITE)) {
+	if (mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) {
-		if (bdev_check_media_change(bdev) && fs->disk_in)
+		if (disk_check_media_change(disk) && fs->disk_in)
 			fs->ejected = 0;
-		if ((mode & FMODE_WRITE) && fs->write_protected) {
+		if ((mode & BLK_OPEN_WRITE) && fs->write_protected) {
 			err = -EROFS;
 			goto out;
 		}
@@ -659,18 +657,18 @@ out:
 	return err;
 }
 
-static int floppy_unlocked_open(struct block_device *bdev, fmode_t mode)
+static int floppy_unlocked_open(struct gendisk *disk, blk_mode_t mode)
 {
 	int ret;
 
 	mutex_lock(&swim_mutex);
-	ret = floppy_open(bdev, mode);
+	ret = floppy_open(disk, mode);
 	mutex_unlock(&swim_mutex);
 
 	return ret;
 }
 
-static void floppy_release(struct gendisk *disk, fmode_t mode)
+static void floppy_release(struct gendisk *disk)
 {
 	struct floppy_state *fs = disk->private_data;
 	struct swim __iomem *base = fs->swd->base;
@@ -686,7 +684,7 @@ static void floppy_release(struct gendisk *disk, fmode_t mode)
 	mutex_unlock(&swim_mutex);
 }
 
-static int floppy_ioctl(struct block_device *bdev, fmode_t mode,
+static int floppy_ioctl(struct block_device *bdev, blk_mode_t mode,
 			unsigned int cmd, unsigned long param)
 {
 	struct floppy_state *fs = bdev->bd_disk->private_data;

drivers/block/swim3.c

@@ -246,10 +246,9 @@ static int grab_drive(struct floppy_state *fs, enum swim_state state,
 		      int interruptible);
 static void release_drive(struct floppy_state *fs);
 static int fd_eject(struct floppy_state *fs);
-static int floppy_ioctl(struct block_device *bdev, fmode_t mode,
+static int floppy_ioctl(struct block_device *bdev, blk_mode_t mode,
 			unsigned int cmd, unsigned long param);
-static int floppy_open(struct block_device *bdev, fmode_t mode);
+static int floppy_open(struct gendisk *disk, blk_mode_t mode);
-static void floppy_release(struct gendisk *disk, fmode_t mode);
 static unsigned int floppy_check_events(struct gendisk *disk,
 					unsigned int clearing);
 static int floppy_revalidate(struct gendisk *disk);
@@ -883,7 +882,7 @@ static int fd_eject(struct floppy_state *fs)
 static struct floppy_struct floppy_type =
 	{ 2880,18,2,80,0,0x1B,0x00,0xCF,0x6C,NULL };	/*  7 1.44MB 3.5"   */
 
-static int floppy_locked_ioctl(struct block_device *bdev, fmode_t mode,
+static int floppy_locked_ioctl(struct block_device *bdev, blk_mode_t mode,
 			unsigned int cmd, unsigned long param)
 {
 	struct floppy_state *fs = bdev->bd_disk->private_data;
@@ -911,7 +910,7 @@ static int floppy_locked_ioctl(struct block_device *bdev, fmode_t mode,
 	return -ENOTTY;
 }
 
-static int floppy_ioctl(struct block_device *bdev, fmode_t mode,
+static int floppy_ioctl(struct block_device *bdev, blk_mode_t mode,
 				 unsigned int cmd, unsigned long param)
 {
 	int ret;
@@ -923,9 +922,9 @@ static int floppy_ioctl(struct block_device *bdev, fmode_t mode,
 	return ret;
 }
 
-static int floppy_open(struct block_device *bdev, fmode_t mode)
+static int floppy_open(struct gendisk *disk, blk_mode_t mode)
 {
-	struct floppy_state *fs = bdev->bd_disk->private_data;
+	struct floppy_state *fs = disk->private_data;
 	struct swim3 __iomem *sw = fs->swim3;
 	int n, err = 0;
 
@@ -958,18 +957,18 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 		swim3_action(fs, SETMFM);
 		swim3_select(fs, RELAX);
 
-	} else if (fs->ref_count == -1 || mode & FMODE_EXCL)
+	} else if (fs->ref_count == -1 || mode & BLK_OPEN_EXCL)
 		return -EBUSY;
 
-	if (err == 0 && (mode & FMODE_NDELAY) == 0
+	if (err == 0 && !(mode & BLK_OPEN_NDELAY) &&
-	    && (mode & (FMODE_READ|FMODE_WRITE))) {
+	    (mode & (BLK_OPEN_READ | BLK_OPEN_WRITE))) {
-		if (bdev_check_media_change(bdev))
+		if (disk_check_media_change(disk))
-			floppy_revalidate(bdev->bd_disk);
+			floppy_revalidate(disk);
 		if (fs->ejected)
 			err = -ENXIO;
 	}
 
-	if (err == 0 && (mode & FMODE_WRITE)) {
+	if (err == 0 && (mode & BLK_OPEN_WRITE)) {
 		if (fs->write_prot < 0)
 			fs->write_prot = swim3_readbit(fs, WRITE_PROT);
 		if (fs->write_prot)
@@ -985,7 +984,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 		return err;
 	}
 
-	if (mode & FMODE_EXCL)
+	if (mode & BLK_OPEN_EXCL)
 		fs->ref_count = -1;
 	else
 		++fs->ref_count;
@@ -993,18 +992,18 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 	return 0;
 }
 
-static int floppy_unlocked_open(struct block_device *bdev, fmode_t mode)
+static int floppy_unlocked_open(struct gendisk *disk, blk_mode_t mode)
 {
 	int ret;
 
 	mutex_lock(&swim3_mutex);
-	ret = floppy_open(bdev, mode);
+	ret = floppy_open(disk, mode);
 	mutex_unlock(&swim3_mutex);
 
 	return ret;
 }
 
-static void floppy_release(struct gendisk *disk, fmode_t mode)
+static void floppy_release(struct gendisk *disk)
 {
 	struct floppy_state *fs = disk->private_data;
 	struct swim3 __iomem *sw = fs->swim3;

drivers/block/ublk_drv.c

@@ -43,6 +43,7 @@
 #include <asm/page.h>
 #include <linux/task_work.h>
 #include <linux/namei.h>
+#include <linux/kref.h>
 #include <uapi/linux/ublk_cmd.h>
 
 #define UBLK_MINORS		(1U << MINORBITS)
@@ -54,7 +55,8 @@
 		| UBLK_F_USER_RECOVERY \
 		| UBLK_F_USER_RECOVERY_REISSUE \
 		| UBLK_F_UNPRIVILEGED_DEV \
-		| UBLK_F_CMD_IOCTL_ENCODE)
+		| UBLK_F_CMD_IOCTL_ENCODE \
+		| UBLK_F_USER_COPY)
 
 /* All UBLK_PARAM_TYPE_* should be included here */
 #define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | \
@@ -62,7 +64,8 @@
 
 struct ublk_rq_data {
 	struct llist_node node;
-	struct callback_head work;
+
+	struct kref ref;
 };
 
 struct ublk_uring_cmd_pdu {
@@ -182,8 +185,13 @@ struct ublk_params_header {
 	__u32	types;
 };
 
+static inline void __ublk_complete_rq(struct request *req);
+static void ublk_complete_rq(struct kref *ref);
+
 static dev_t ublk_chr_devt;
-static struct class *ublk_chr_class;
+static const struct class ublk_chr_class = {
+	.name = "ublk-char",
+};
 
 static DEFINE_IDR(ublk_index_idr);
 static DEFINE_SPINLOCK(ublk_idr_lock);
@@ -202,6 +210,23 @@ static unsigned int ublks_added;	/* protected by ublk_ctl_mutex */
 
 static struct miscdevice ublk_misc;
 
+static inline unsigned ublk_pos_to_hwq(loff_t pos)
+{
+	return ((pos - UBLKSRV_IO_BUF_OFFSET) >> UBLK_QID_OFF) &
+		UBLK_QID_BITS_MASK;
+}
+
+static inline unsigned ublk_pos_to_buf_off(loff_t pos)
+{
+	return (pos - UBLKSRV_IO_BUF_OFFSET) & UBLK_IO_BUF_BITS_MASK;
+}
+
+static inline unsigned ublk_pos_to_tag(loff_t pos)
+{
+	return ((pos - UBLKSRV_IO_BUF_OFFSET) >> UBLK_TAG_OFF) &
+		UBLK_TAG_BITS_MASK;
+}
+
 static void ublk_dev_param_basic_apply(struct ublk_device *ub)
 {
 	struct request_queue *q = ub->ub_disk->queue;
@@ -290,12 +315,52 @@ static int ublk_apply_params(struct ublk_device *ub)
 	return 0;
 }
 
-static inline bool ublk_can_use_task_work(const struct ublk_queue *ubq)
+static inline bool ublk_support_user_copy(const struct ublk_queue *ubq)
 {
-	if (IS_BUILTIN(CONFIG_BLK_DEV_UBLK) &&
+	return ubq->flags & UBLK_F_USER_COPY;
-			!(ubq->flags & UBLK_F_URING_CMD_COMP_IN_TASK))
+}
-		return true;
+
-	return false;
+static inline bool ublk_need_req_ref(const struct ublk_queue *ubq)
+{
+	/*
+	 * read()/write() is involved in user copy, so request reference
+	 * has to be grabbed
+	 */
+	return ublk_support_user_copy(ubq);
+}
+
+static inline void ublk_init_req_ref(const struct ublk_queue *ubq,
+		struct request *req)
+{
+	if (ublk_need_req_ref(ubq)) {
+		struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
+
+		kref_init(&data->ref);
+	}
+}
+
+static inline bool ublk_get_req_ref(const struct ublk_queue *ubq,
+		struct request *req)
+{
+	if (ublk_need_req_ref(ubq)) {
+		struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
+
+		return kref_get_unless_zero(&data->ref);
+	}
+
+	return true;
+}
+
+static inline void ublk_put_req_ref(const struct ublk_queue *ubq,
+		struct request *req)
+{
+	if (ublk_need_req_ref(ubq)) {
+		struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
+
+		kref_put(&data->ref, ublk_complete_rq);
+	} else {
+		__ublk_complete_rq(req);
+	}
 }
 
 static inline bool ublk_need_get_data(const struct ublk_queue *ubq)
@@ -384,9 +449,9 @@ static void ublk_store_owner_uid_gid(unsigned int *owner_uid,
 	*owner_gid = from_kgid(&init_user_ns, gid);
 }
 
-static int ublk_open(struct block_device *bdev, fmode_t mode)
+static int ublk_open(struct gendisk *disk, blk_mode_t mode)
 {
-	struct ublk_device *ub = bdev->bd_disk->private_data;
+	struct ublk_device *ub = disk->private_data;
 
 	if (capable(CAP_SYS_ADMIN))
 		return 0;
@@ -421,49 +486,39 @@ static const struct block_device_operations ub_fops = {
 
 #define UBLK_MAX_PIN_PAGES	32
 
-struct ublk_map_data {
-	const struct request *rq;
-	unsigned long	ubuf;
-	unsigned int	len;
-};
-
 struct ublk_io_iter {
 	struct page *pages[UBLK_MAX_PIN_PAGES];
-	unsigned pg_off;	/* offset in the 1st page in pages */
-	int nr_pages;		/* how many page pointers in pages */
 	struct bio *bio;
 	struct bvec_iter iter;
 };
 
-static inline unsigned ublk_copy_io_pages(struct ublk_io_iter *data,
+/* return how many pages are copied */
-		unsigned max_bytes, bool to_vm)
+static void ublk_copy_io_pages(struct ublk_io_iter *data,
+		size_t total, size_t pg_off, int dir)
 {
-	const unsigned total = min_t(unsigned, max_bytes,
-			PAGE_SIZE - data->pg_off +
-			((data->nr_pages - 1) << PAGE_SHIFT));
 	unsigned done = 0;
 	unsigned pg_idx = 0;
 
 	while (done < total) {
 		struct bio_vec bv = bio_iter_iovec(data->bio, data->iter);
-		const unsigned int bytes = min3(bv.bv_len, total - done,
+		unsigned int bytes = min3(bv.bv_len, (unsigned)total - done,
-				(unsigned)(PAGE_SIZE - data->pg_off));
+				(unsigned)(PAGE_SIZE - pg_off));
 		void *bv_buf = bvec_kmap_local(&bv);
 		void *pg_buf = kmap_local_page(data->pages[pg_idx]);
 
-		if (to_vm)
+		if (dir == ITER_DEST)
-			memcpy(pg_buf + data->pg_off, bv_buf, bytes);
+			memcpy(pg_buf + pg_off, bv_buf, bytes);
 		else
-			memcpy(bv_buf, pg_buf + data->pg_off, bytes);
+			memcpy(bv_buf, pg_buf + pg_off, bytes);
 
 		kunmap_local(pg_buf);
 		kunmap_local(bv_buf);
 
 		/* advance page array */
-		data->pg_off += bytes;
+		pg_off += bytes;
-		if (data->pg_off == PAGE_SIZE) {
+		if (pg_off == PAGE_SIZE) {
 			pg_idx += 1;
-			data->pg_off = 0;
+			pg_off = 0;
 		}
 
 		done += bytes;
@@ -477,41 +532,58 @@ static inline unsigned ublk_copy_io_pages(struct ublk_io_iter *data,
 			data->iter = data->bio->bi_iter;
 		}
 	}
-
-	return done;
 }
 
-static int ublk_copy_user_pages(struct ublk_map_data *data, bool to_vm)
+static bool ublk_advance_io_iter(const struct request *req,
+		struct ublk_io_iter *iter, unsigned int offset)
 {
-	const unsigned int gup_flags = to_vm ? FOLL_WRITE : 0;
+	struct bio *bio = req->bio;
-	const unsigned long start_vm = data->ubuf;
-	unsigned int done = 0;
-	struct ublk_io_iter iter = {
-		.pg_off	= start_vm & (PAGE_SIZE - 1),
-		.bio	= data->rq->bio,
-		.iter	= data->rq->bio->bi_iter,
-	};
-	const unsigned int nr_pages = round_up(data->len +
-			(start_vm & (PAGE_SIZE - 1)), PAGE_SIZE) >> PAGE_SHIFT;
 
-	while (done < nr_pages) {
+	for_each_bio(bio) {
-		const unsigned to_pin = min_t(unsigned, UBLK_MAX_PIN_PAGES,
+		if (bio->bi_iter.bi_size > offset) {
-				nr_pages - done);
+			iter->bio = bio;
-		unsigned i, len;
+			iter->iter = bio->bi_iter;
+			bio_advance_iter(iter->bio, &iter->iter, offset);
+			return true;
+		}
+		offset -= bio->bi_iter.bi_size;
+	}
+	return false;
+}
 
-		iter.nr_pages = get_user_pages_fast(start_vm +
+/*
-				(done << PAGE_SHIFT), to_pin, gup_flags,
+ * Copy data between request pages and io_iter, and 'offset'
-				iter.pages);
+ * is the start point of linear offset of request.
-		if (iter.nr_pages <= 0)
+ */
-			return done == 0 ? iter.nr_pages : done;
+static size_t ublk_copy_user_pages(const struct request *req,
-		len = ublk_copy_io_pages(&iter, data->len, to_vm);
+		unsigned offset, struct iov_iter *uiter, int dir)
-		for (i = 0; i < iter.nr_pages; i++) {
+{
-			if (to_vm)
+	struct ublk_io_iter iter;
+	size_t done = 0;
+
+	if (!ublk_advance_io_iter(req, &iter, offset))
+		return 0;
+
+	while (iov_iter_count(uiter) && iter.bio) {
+		unsigned nr_pages;
+		ssize_t len;
+		size_t off;
+		int i;
+
+		len = iov_iter_get_pages2(uiter, iter.pages,
+				iov_iter_count(uiter),
+				UBLK_MAX_PIN_PAGES, &off);
+		if (len <= 0)
+			return done;
+
+		ublk_copy_io_pages(&iter, len, off, dir);
+		nr_pages = DIV_ROUND_UP(len + off, PAGE_SIZE);
+		for (i = 0; i < nr_pages; i++) {
+			if (dir == ITER_DEST)
 				set_page_dirty(iter.pages[i]);
 			put_page(iter.pages[i]);
 		}
-		data->len -= len;
+		done += len;
-		done += iter.nr_pages;
 	}
 
 	return done;
@@ -532,21 +604,23 @@ static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req,
 {
 	const unsigned int rq_bytes = blk_rq_bytes(req);
 
+	if (ublk_support_user_copy(ubq))
+		return rq_bytes;
+
 	/*
 	 * no zero copy, we delay copy WRITE request data into ublksrv
 	 * context and the big benefit is that pinning pages in current
 	 * context is pretty fast, see ublk_pin_user_pages
 	 */
 	if (ublk_need_map_req(req)) {
-		struct ublk_map_data data = {
+		struct iov_iter iter;
-			.rq	=	req,
+		struct iovec iov;
-			.ubuf	=	io->addr,
+		const int dir = ITER_DEST;
-			.len	=	rq_bytes,
-		};
 
-		ublk_copy_user_pages(&data, true);
+		import_single_range(dir, u64_to_user_ptr(io->addr), rq_bytes,
+				&iov, &iter);
 
-		return rq_bytes - data.len;
+		return ublk_copy_user_pages(req, 0, &iter, dir);
 	}
 	return rq_bytes;
 }
@@ -557,18 +631,19 @@ static int ublk_unmap_io(const struct ublk_queue *ubq,
 {
 	const unsigned int rq_bytes = blk_rq_bytes(req);
 
+	if (ublk_support_user_copy(ubq))
+		return rq_bytes;
+
 	if (ublk_need_unmap_req(req)) {
-		struct ublk_map_data data = {
+		struct iov_iter iter;
-			.rq	=	req,
+		struct iovec iov;
-			.ubuf	=	io->addr,
+		const int dir = ITER_SOURCE;
-			.len	=	io->res,
-		};
 
 		WARN_ON_ONCE(io->res > rq_bytes);
 
-		ublk_copy_user_pages(&data, false);
+		import_single_range(dir, u64_to_user_ptr(io->addr), io->res,
-
+				&iov, &iter);
-		return io->res - data.len;
+		return ublk_copy_user_pages(req, 0, &iter, dir);
 	}
 	return rq_bytes;
 }
@@ -648,13 +723,19 @@ static inline bool ubq_daemon_is_dying(struct ublk_queue *ubq)
 }
 
 /* todo: handle partial completion */
-static void ublk_complete_rq(struct request *req)
+static inline void __ublk_complete_rq(struct request *req)
 {
 	struct ublk_queue *ubq = req->mq_hctx->driver_data;
 	struct ublk_io *io = &ubq->ios[req->tag];
 	unsigned int unmapped_bytes;
 	blk_status_t res = BLK_STS_OK;
 
+	/* called from ublk_abort_queue() code path */
+	if (io->flags & UBLK_IO_FLAG_ABORTED) {
+		res = BLK_STS_IOERR;
+		goto exit;
+	}
+
 	/* failed read IO if nothing is read */
 	if (!io->res && req_op(req) == REQ_OP_READ)
 		io->res = -EIO;
@@ -694,6 +775,15 @@ exit:
 	blk_mq_end_request(req, res);
 }
 
+static void ublk_complete_rq(struct kref *ref)
+{
+	struct ublk_rq_data *data = container_of(ref, struct ublk_rq_data,
+			ref);
+	struct request *req = blk_mq_rq_from_pdu(data);
+
+	__ublk_complete_rq(req);
+}
+
 /*
  * Since __ublk_rq_task_work always fails requests immediately during
  * exiting, __ublk_fail_req() is only called from abort context during
@@ -712,7 +802,7 @@ static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
 		if (ublk_queue_can_use_recovery_reissue(ubq))
 			blk_mq_requeue_request(req, false);
 		else
-			blk_mq_end_request(req, BLK_STS_IOERR);
+			ublk_put_req_ref(ubq, req);
 	}
 }
 
@@ -821,6 +911,7 @@ static inline void __ublk_rq_task_work(struct request *req,
 			mapped_bytes >> 9;
 	}
 
+	ublk_init_req_ref(ubq, req);
 	ubq_complete_io_cmd(io, UBLK_IO_RES_OK, issue_flags);
 }
 
@@ -852,17 +943,6 @@ static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd, unsigned issue_flags)
 	ublk_forward_io_cmds(ubq, issue_flags);
 }
 
-static void ublk_rq_task_work_fn(struct callback_head *work)
-{
-	struct ublk_rq_data *data = container_of(work,
-			struct ublk_rq_data, work);
-	struct request *req = blk_mq_rq_from_pdu(data);
-	struct ublk_queue *ubq = req->mq_hctx->driver_data;
-	unsigned issue_flags = IO_URING_F_UNLOCKED;
-
-	ublk_forward_io_cmds(ubq, issue_flags);
-}
-
 static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq)
 {
 	struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq);
@@ -886,10 +966,6 @@ static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq)
 	 */
 	if (unlikely(io->flags & UBLK_IO_FLAG_ABORTED)) {
 		ublk_abort_io_cmds(ubq);
-	} else if (ublk_can_use_task_work(ubq)) {
-		if (task_work_add(ubq->ubq_daemon, &data->work,
-					TWA_SIGNAL_NO_IPI))
-			ublk_abort_io_cmds(ubq);
 	} else {
 		struct io_uring_cmd *cmd = io->cmd;
 		struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
@@ -961,19 +1037,9 @@ static int ublk_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data,
 	return 0;
 }
 
-static int ublk_init_rq(struct blk_mq_tag_set *set, struct request *req,
-		unsigned int hctx_idx, unsigned int numa_node)
-{
-	struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
-
-	init_task_work(&data->work, ublk_rq_task_work_fn);
-	return 0;
-}
-
 static const struct blk_mq_ops ublk_mq_ops = {
 	.queue_rq       = ublk_queue_rq,
 	.init_hctx	= ublk_init_hctx,
-	.init_request   = ublk_init_rq,
 	.timeout	= ublk_timeout,
 };
 
@@ -1050,7 +1116,7 @@ static void ublk_commit_completion(struct ublk_device *ub,
 	req = blk_mq_tag_to_rq(ub->tag_set.tags[qid], tag);
 
 	if (req && likely(!blk_should_fake_timeout(req->q)))
-		ublk_complete_rq(req);
+		ublk_put_req_ref(ubq, req);
 }
 
 /*
@@ -1295,6 +1361,14 @@ static inline int ublk_check_cmd_op(u32 cmd_op)
 	return 0;
 }
 
+static inline void ublk_fill_io_cmd(struct ublk_io *io,
+		struct io_uring_cmd *cmd, unsigned long buf_addr)
+{
+	io->cmd = cmd;
+	io->flags |= UBLK_IO_FLAG_ACTIVE;
+	io->addr = buf_addr;
+}
+
 static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 			       unsigned int issue_flags,
 			       const struct ublksrv_io_cmd *ub_cmd)
@@ -1340,6 +1414,11 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 			^ (_IOC_NR(cmd_op) == UBLK_IO_NEED_GET_DATA))
 		goto out;
 
+	if (ublk_support_user_copy(ubq) && ub_cmd->addr) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	ret = ublk_check_cmd_op(cmd_op);
 	if (ret)
 		goto out;
@@ -1358,36 +1437,41 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 		 */
 		if (io->flags & UBLK_IO_FLAG_OWNED_BY_SRV)
 			goto out;
-		/* FETCH_RQ has to provide IO buffer if NEED GET DATA is not enabled */
-		if (!ub_cmd->addr && !ublk_need_get_data(ubq))
-			goto out;
-		io->cmd = cmd;
-		io->flags |= UBLK_IO_FLAG_ACTIVE;
-		io->addr = ub_cmd->addr;
 
+		if (!ublk_support_user_copy(ubq)) {
+			/*
+			 * FETCH_RQ has to provide IO buffer if NEED GET
+			 * DATA is not enabled
+			 */
+			if (!ub_cmd->addr && !ublk_need_get_data(ubq))
+				goto out;
+		}
+
+		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
 		ublk_mark_io_ready(ub, ubq);
 		break;
 	case UBLK_IO_COMMIT_AND_FETCH_REQ:
 		req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag);
-		/*
+
-		 * COMMIT_AND_FETCH_REQ has to provide IO buffer if NEED GET DATA is
-		 * not enabled or it is Read IO.
-		 */
-		if (!ub_cmd->addr && (!ublk_need_get_data(ubq) || req_op(req) == REQ_OP_READ))
-			goto out;
 		if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
 			goto out;
-		io->addr = ub_cmd->addr;
+
-		io->flags |= UBLK_IO_FLAG_ACTIVE;
+		if (!ublk_support_user_copy(ubq)) {
-		io->cmd = cmd;
+			/*
+			 * COMMIT_AND_FETCH_REQ has to provide IO buffer if
+			 * NEED GET DATA is not enabled or it is Read IO.
+			 */
+			if (!ub_cmd->addr && (!ublk_need_get_data(ubq) ||
+						req_op(req) == REQ_OP_READ))
+				goto out;
+		}
+		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
 		ublk_commit_completion(ub, ub_cmd);
 		break;
 	case UBLK_IO_NEED_GET_DATA:
 		if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
 			goto out;
-		io->addr = ub_cmd->addr;
+		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
-		io->cmd = cmd;
-		io->flags |= UBLK_IO_FLAG_ACTIVE;
 		ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag);
 		break;
 	default:
@@ -1402,6 +1486,36 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 	return -EIOCBQUEUED;
 }
 
+static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub,
+		struct ublk_queue *ubq, int tag, size_t offset)
+{
+	struct request *req;
+
+	if (!ublk_need_req_ref(ubq))
+		return NULL;
+
+	req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag);
+	if (!req)
+		return NULL;
+
+	if (!ublk_get_req_ref(ubq, req))
+		return NULL;
+
+	if (unlikely(!blk_mq_request_started(req) || req->tag != tag))
+		goto fail_put;
+
+	if (!ublk_rq_has_data(req))
+		goto fail_put;
+
+	if (offset > blk_rq_bytes(req))
+		goto fail_put;
+
+	return req;
+fail_put:
+	ublk_put_req_ref(ubq, req);
+	return NULL;
+}
+
 static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
 {
 	/*
@@ -1419,11 +1533,112 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
 	return __ublk_ch_uring_cmd(cmd, issue_flags, &ub_cmd);
 }
 
+static inline bool ublk_check_ubuf_dir(const struct request *req,
+		int ubuf_dir)
+{
+	/* copy ubuf to request pages */
+	if (req_op(req) == REQ_OP_READ && ubuf_dir == ITER_SOURCE)
+		return true;
+
+	/* copy request pages to ubuf */
+	if (req_op(req) == REQ_OP_WRITE && ubuf_dir == ITER_DEST)
+		return true;
+
+	return false;
+}
+
+static struct request *ublk_check_and_get_req(struct kiocb *iocb,
+		struct iov_iter *iter, size_t *off, int dir)
+{
+	struct ublk_device *ub = iocb->ki_filp->private_data;
+	struct ublk_queue *ubq;
+	struct request *req;
+	size_t buf_off;
+	u16 tag, q_id;
+
+	if (!ub)
+		return ERR_PTR(-EACCES);
+
+	if (!user_backed_iter(iter))
+		return ERR_PTR(-EACCES);
+
+	if (ub->dev_info.state == UBLK_S_DEV_DEAD)
+		return ERR_PTR(-EACCES);
+
+	tag = ublk_pos_to_tag(iocb->ki_pos);
+	q_id = ublk_pos_to_hwq(iocb->ki_pos);
+	buf_off = ublk_pos_to_buf_off(iocb->ki_pos);
+
+	if (q_id >= ub->dev_info.nr_hw_queues)
+		return ERR_PTR(-EINVAL);
+
+	ubq = ublk_get_queue(ub, q_id);
+	if (!ubq)
+		return ERR_PTR(-EINVAL);
+
+	if (tag >= ubq->q_depth)
+		return ERR_PTR(-EINVAL);
+
+	req = __ublk_check_and_get_req(ub, ubq, tag, buf_off);
+	if (!req)
+		return ERR_PTR(-EINVAL);
+
+	if (!req->mq_hctx || !req->mq_hctx->driver_data)
+		goto fail;
+
+	if (!ublk_check_ubuf_dir(req, dir))
+		goto fail;
+
+	*off = buf_off;
+	return req;
+fail:
+	ublk_put_req_ref(ubq, req);
+	return ERR_PTR(-EACCES);
+}
+
+static ssize_t ublk_ch_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct ublk_queue *ubq;
+	struct request *req;
+	size_t buf_off;
+	size_t ret;
+
+	req = ublk_check_and_get_req(iocb, to, &buf_off, ITER_DEST);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	ret = ublk_copy_user_pages(req, buf_off, to, ITER_DEST);
+	ubq = req->mq_hctx->driver_data;
+	ublk_put_req_ref(ubq, req);
+
+	return ret;
+}
+
+static ssize_t ublk_ch_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct ublk_queue *ubq;
+	struct request *req;
+	size_t buf_off;
+	size_t ret;
+
+	req = ublk_check_and_get_req(iocb, from, &buf_off, ITER_SOURCE);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	ret = ublk_copy_user_pages(req, buf_off, from, ITER_SOURCE);
+	ubq = req->mq_hctx->driver_data;
+	ublk_put_req_ref(ubq, req);
+
+	return ret;
+}
+
 static const struct file_operations ublk_ch_fops = {
 	.owner = THIS_MODULE,
 	.open = ublk_ch_open,
 	.release = ublk_ch_release,
 	.llseek = no_llseek,
+	.read_iter = ublk_ch_read_iter,
+	.write_iter = ublk_ch_write_iter,
 	.uring_cmd = ublk_ch_uring_cmd,
 	.mmap = ublk_ch_mmap,
 };
@@ -1547,7 +1762,7 @@ static int ublk_add_chdev(struct ublk_device *ub)
 
 	dev->parent = ublk_misc.this_device;
 	dev->devt = MKDEV(MAJOR(ublk_chr_devt), minor);
-	dev->class = ublk_chr_class;
+	dev->class = &ublk_chr_class;
 	dev->release = ublk_cdev_rel;
 	device_initialize(dev);
 
@@ -1818,10 +2033,12 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
 	 */
 	ub->dev_info.flags &= UBLK_F_ALL;
 
-	if (!IS_BUILTIN(CONFIG_BLK_DEV_UBLK))
+	ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE |
-		ub->dev_info.flags |= UBLK_F_URING_CMD_COMP_IN_TASK;
+		UBLK_F_URING_CMD_COMP_IN_TASK;
 
-	ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE;
+	/* GET_DATA isn't needed any more with USER_COPY */
+	if (ub->dev_info.flags & UBLK_F_USER_COPY)
+		ub->dev_info.flags &= ~UBLK_F_NEED_GET_DATA;
 
 	/* We are not ready to support zero copy */
 	ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY;
@@ -2133,6 +2350,21 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub,
 	return ret;
 }
 
+static int ublk_ctrl_get_features(struct io_uring_cmd *cmd)
+{
+	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
+	void __user *argp = (void __user *)(unsigned long)header->addr;
+	u64 features = UBLK_F_ALL & ~UBLK_F_SUPPORT_ZERO_COPY;
+
+	if (header->len != UBLK_FEATURES_LEN || !header->addr)
+		return -EINVAL;
+
+	if (copy_to_user(argp, &features, UBLK_FEATURES_LEN))
+		return -EFAULT;
+
+	return 0;
+}
+
 /*
  * All control commands are sent via /dev/ublk-control, so we have to check
  * the destination device's permission
@@ -2213,6 +2445,7 @@ static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub,
 	case UBLK_CMD_GET_DEV_INFO2:
 	case UBLK_CMD_GET_QUEUE_AFFINITY:
 	case UBLK_CMD_GET_PARAMS:
+	case (_IOC_NR(UBLK_U_CMD_GET_FEATURES)):
 		mask = MAY_READ;
 		break;
 	case UBLK_CMD_START_DEV:
@@ -2262,6 +2495,11 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 	if (ret)
 		goto out;
 
+	if (cmd_op == UBLK_U_CMD_GET_FEATURES) {
+		ret = ublk_ctrl_get_features(cmd);
+		goto out;
+	}
+
 	if (_IOC_NR(cmd_op) != UBLK_CMD_ADD_DEV) {
 		ret = -ENODEV;
 		ub = ublk_get_device_from_id(header->dev_id);
@@ -2337,6 +2575,9 @@ static int __init ublk_init(void)
 {
 	int ret;
 
+	BUILD_BUG_ON((u64)UBLKSRV_IO_BUF_OFFSET +
+			UBLKSRV_IO_BUF_TOTAL_SIZE < UBLKSRV_IO_BUF_OFFSET);
+
 	init_waitqueue_head(&ublk_idr_wq);
 
 	ret = misc_register(&ublk_misc);
@@ -2347,11 +2588,10 @@ static int __init ublk_init(void)
 	if (ret)
 		goto unregister_mis;
 
-	ublk_chr_class = class_create("ublk-char");
+	ret = class_register(&ublk_chr_class);
-	if (IS_ERR(ublk_chr_class)) {
+	if (ret)
-		ret = PTR_ERR(ublk_chr_class);
 		goto free_chrdev_region;
-	}
+
 	return 0;
 
 free_chrdev_region:
@@ -2369,7 +2609,7 @@ static void __exit ublk_exit(void)
 	idr_for_each_entry(&ublk_index_idr, ub, id)
 		ublk_remove(ub);
 
-	class_destroy(ublk_chr_class);
+	class_unregister(&ublk_chr_class);
 	misc_deregister(&ublk_misc);
 
 	idr_destroy(&ublk_index_idr);

drivers/block/xen-blkback/xenbus.c

@@ -473,7 +473,7 @@ static void xenvbd_sysfs_delif(struct xenbus_device *dev)
 static void xen_vbd_free(struct xen_vbd *vbd)
 {
 	if (vbd->bdev)
-		blkdev_put(vbd->bdev, vbd->readonly ? FMODE_READ : FMODE_WRITE);
+		blkdev_put(vbd->bdev, NULL);
 	vbd->bdev = NULL;
 }
 
@@ -492,7 +492,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 	vbd->pdevice  = MKDEV(major, minor);
 
 	bdev = blkdev_get_by_dev(vbd->pdevice, vbd->readonly ?
-				 FMODE_READ : FMODE_WRITE, NULL);
+				 BLK_OPEN_READ : BLK_OPEN_WRITE, NULL, NULL);
 
 	if (IS_ERR(bdev)) {
 		pr_warn("xen_vbd_create: device %08x could not be opened\n",

drivers/block/xen-blkfront.c

@@ -509,7 +509,7 @@ static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg)
 	return 0;
 }
 
-static int blkif_ioctl(struct block_device *bdev, fmode_t mode,
+static int blkif_ioctl(struct block_device *bdev, blk_mode_t mode,
 		       unsigned command, unsigned long argument)
 {
 	struct blkfront_info *info = bdev->bd_disk->private_data;

drivers/block/z2ram.c

@@ -140,16 +140,14 @@ static void get_chipram(void)
 	return;
 }
 
-static int z2_open(struct block_device *bdev, fmode_t mode)
+static int z2_open(struct gendisk *disk, blk_mode_t mode)
 {
-	int device;
+	int device = disk->first_minor;
 	int max_z2_map = (Z2RAM_SIZE / Z2RAM_CHUNKSIZE) * sizeof(z2ram_map[0]);
 	int max_chip_map = (amiga_chip_size / Z2RAM_CHUNKSIZE) *
 	    sizeof(z2ram_map[0]);
 	int rc = -ENOMEM;
 
-	device = MINOR(bdev->bd_dev);
-
 	mutex_lock(&z2ram_mutex);
 	if (current_device != -1 && current_device != device) {
 		rc = -EBUSY;
@@ -290,7 +288,7 @@ err_out:
 	return rc;
 }
 
-static void z2_release(struct gendisk *disk, fmode_t mode)
+static void z2_release(struct gendisk *disk)
 {
 	mutex_lock(&z2ram_mutex);
 	if (current_device == -1) {

drivers/block/zram/zram_drv.c

@@ -420,7 +420,7 @@ static void reset_bdev(struct zram *zram)
 		return;
 
 	bdev = zram->bdev;
-	blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+	blkdev_put(bdev, zram);
 	/* hope filp_close flush all of IO */
 	filp_close(zram->backing_dev, NULL);
 	zram->backing_dev = NULL;
@@ -507,8 +507,8 @@ static ssize_t backing_dev_store(struct device *dev,
 		goto out;
 	}
 
-	bdev = blkdev_get_by_dev(inode->i_rdev,
+	bdev = blkdev_get_by_dev(inode->i_rdev, BLK_OPEN_READ | BLK_OPEN_WRITE,
-			FMODE_READ | FMODE_WRITE | FMODE_EXCL, zram);
+				 zram, NULL);
 	if (IS_ERR(bdev)) {
 		err = PTR_ERR(bdev);
 		bdev = NULL;
@@ -539,7 +539,7 @@ out:
 	kvfree(bitmap);
 
 	if (bdev)
-		blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
+		blkdev_put(bdev, zram);
 
 	if (backing_dev)
 		filp_close(backing_dev, NULL);
@@ -700,7 +700,7 @@ static ssize_t writeback_store(struct device *dev,
 		bio_init(&bio, zram->bdev, &bio_vec, 1,
 			 REQ_OP_WRITE | REQ_SYNC);
 		bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9);
-		bio_add_page(&bio, page, PAGE_SIZE, 0);
+		__bio_add_page(&bio, page, PAGE_SIZE, 0);
 
 		/*
 		 * XXX: A single page IO would be inefficient for write
@@ -2097,19 +2097,16 @@ static ssize_t reset_store(struct device *dev,
 	return len;
 }
 
-static int zram_open(struct block_device *bdev, fmode_t mode)
+static int zram_open(struct gendisk *disk, blk_mode_t mode)
 {
-	int ret = 0;
+	struct zram *zram = disk->private_data;
-	struct zram *zram;
 
-	WARN_ON(!mutex_is_locked(&bdev->bd_disk->open_mutex));
+	WARN_ON(!mutex_is_locked(&disk->open_mutex));
 
-	zram = bdev->bd_disk->private_data;
 	/* zram was claimed to reset so open request fails */
 	if (zram->claim)
-		ret = -EBUSY;
+		return -EBUSY;
-
+	return 0;
-	return ret;
 }
 
 static const struct block_device_operations zram_devops = {

drivers/cdrom/cdrom.c

@@ -264,6 +264,7 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/nospec.h>
 #include <linux/slab.h> 
 #include <linux/cdrom.h>
 #include <linux/sysctl.h>
@@ -978,15 +979,6 @@ static void cdrom_dvd_rw_close_write(struct cdrom_device_info *cdi)
 	cdi->media_written = 0;
 }
 
-static int cdrom_close_write(struct cdrom_device_info *cdi)
-{
-#if 0
-	return cdrom_flush_cache(cdi);
-#else
-	return 0;
-#endif
-}
-
 /* badly broken, I know. Is due for a fixup anytime. */
 static void cdrom_count_tracks(struct cdrom_device_info *cdi, tracktype *tracks)
 {
@@ -1155,8 +1147,7 @@ clean_up_and_return:
  * is in their own interest: device control becomes a lot easier
  * this way.
  */
-int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev,
+int cdrom_open(struct cdrom_device_info *cdi, blk_mode_t mode)
-	       fmode_t mode)
 {
 	int ret;
 
@@ -1165,7 +1156,7 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev,
 	/* if this was a O_NONBLOCK open and we should honor the flags,
 	 * do a quick open without drive/disc integrity checks. */
 	cdi->use_count++;
-	if ((mode & FMODE_NDELAY) && (cdi->options & CDO_USE_FFLAGS)) {
+	if ((mode & BLK_OPEN_NDELAY) && (cdi->options & CDO_USE_FFLAGS)) {
 		ret = cdi->ops->open(cdi, 1);
 	} else {
 		ret = open_for_data(cdi);
@@ -1173,7 +1164,7 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev,
 			goto err;
 		if (CDROM_CAN(CDC_GENERIC_PACKET))
 			cdrom_mmc3_profile(cdi);
-		if (mode & FMODE_WRITE) {
+		if (mode & BLK_OPEN_WRITE) {
 			ret = -EROFS;
 			if (cdrom_open_write(cdi))
 				goto err_release;
@@ -1182,6 +1173,7 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev,
 			ret = 0;
 			cdi->media_written = 0;
 		}
+		cdi->opened_for_data = true;
 	}
 
 	if (ret)
@@ -1259,10 +1251,9 @@ static int check_for_audio_disc(struct cdrom_device_info *cdi,
 	return 0;
 }
 
-void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode)
+void cdrom_release(struct cdrom_device_info *cdi)
 {
 	const struct cdrom_device_ops *cdo = cdi->ops;
-	int opened_for_data;
 
 	cd_dbg(CD_CLOSE, "entering cdrom_release\n");
 
@@ -1280,20 +1271,12 @@ void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode)
 		}
 	}
 
-	opened_for_data = !(cdi->options & CDO_USE_FFLAGS) ||
-		!(mode & FMODE_NDELAY);
-
-	/*
-	 * flush cache on last write release
-	 */
-	if (CDROM_CAN(CDC_RAM) && !cdi->use_count && cdi->for_data)
-		cdrom_close_write(cdi);
-
 	cdo->release(cdi);
-	if (cdi->use_count == 0) {      /* last process that closes dev*/
+
-		if (opened_for_data &&
+	if (cdi->use_count == 0 && cdi->opened_for_data) {
-		    cdi->options & CDO_AUTO_EJECT && CDROM_CAN(CDC_OPEN_TRAY))
+		if (cdi->options & CDO_AUTO_EJECT && CDROM_CAN(CDC_OPEN_TRAY))
 			cdo->tray_move(cdi, 1);
+		cdi->opened_for_data = false;
 	}
 }
 EXPORT_SYMBOL(cdrom_release);
@@ -2329,6 +2312,9 @@ static int cdrom_ioctl_media_changed(struct cdrom_device_info *cdi,
 	if (arg >= cdi->capacity)
 		return -EINVAL;
 
+	/* Prevent arg from speculatively bypassing the length check */
+	barrier_nospec();
+
 	info = kmalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
@@ -3337,7 +3323,7 @@ static int mmc_ioctl(struct cdrom_device_info *cdi, unsigned int cmd,
  * ATAPI / SCSI specific code now mainly resides in mmc_ioctl().
  */
 int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev,
-		fmode_t mode, unsigned int cmd, unsigned long arg)
+		unsigned int cmd, unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
 	int ret;

drivers/cdrom/gdrom.c

@@ -474,19 +474,19 @@ static const struct cdrom_device_ops gdrom_ops = {
 				  CDC_RESET | CDC_DRIVE_STATUS | CDC_CD_R,
 };
 
-static int gdrom_bdops_open(struct block_device *bdev, fmode_t mode)
+static int gdrom_bdops_open(struct gendisk *disk, blk_mode_t mode)
 {
 	int ret;
 
-	bdev_check_media_change(bdev);
+	disk_check_media_change(disk);
 
 	mutex_lock(&gdrom_mutex);
-	ret = cdrom_open(gd.cd_info, bdev, mode);
+	ret = cdrom_open(gd.cd_info);
 	mutex_unlock(&gdrom_mutex);
 	return ret;
 }
 
-static void gdrom_bdops_release(struct gendisk *disk, fmode_t mode)
+static void gdrom_bdops_release(struct gendisk *disk)
 {
 	mutex_lock(&gdrom_mutex);
 	cdrom_release(gd.cd_info, mode);
@@ -499,13 +499,13 @@ static unsigned int gdrom_bdops_check_events(struct gendisk *disk,
 	return cdrom_check_events(gd.cd_info, clearing);
 }
 
-static int gdrom_bdops_ioctl(struct block_device *bdev, fmode_t mode,
+static int gdrom_bdops_ioctl(struct block_device *bdev, blk_mode_t mode,
 	unsigned cmd, unsigned long arg)
 {
 	int ret;
 
 	mutex_lock(&gdrom_mutex);
-	ret = cdrom_ioctl(gd.cd_info, bdev, mode, cmd, arg);
+	ret = cdrom_ioctl(gd.cd_info, bdev, cmd, arg);
 	mutex_unlock(&gdrom_mutex);
 
 	return ret;

drivers/md/bcache/bcache.h

@@ -275,7 +275,7 @@ struct bcache_device {
 
 	int (*cache_miss)(struct btree *b, struct search *s,
 			  struct bio *bio, unsigned int sectors);
-	int (*ioctl)(struct bcache_device *d, fmode_t mode,
+	int (*ioctl)(struct bcache_device *d, blk_mode_t mode,
 		     unsigned int cmd, unsigned long arg);
 };
 
@@ -1004,11 +1004,11 @@ extern struct workqueue_struct *bch_flush_wq;
 extern struct mutex bch_register_lock;
 extern struct list_head bch_cache_sets;
 
-extern struct kobj_type bch_cached_dev_ktype;
+extern const struct kobj_type bch_cached_dev_ktype;
-extern struct kobj_type bch_flash_dev_ktype;
+extern const struct kobj_type bch_flash_dev_ktype;
-extern struct kobj_type bch_cache_set_ktype;
+extern const struct kobj_type bch_cache_set_ktype;
-extern struct kobj_type bch_cache_set_internal_ktype;
+extern const struct kobj_type bch_cache_set_internal_ktype;
-extern struct kobj_type bch_cache_ktype;
+extern const struct kobj_type bch_cache_ktype;
 
 void bch_cached_dev_release(struct kobject *kobj);
 void bch_flash_dev_release(struct kobject *kobj);

drivers/md/bcache/btree.c

@@ -885,7 +885,7 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op,
  * cannibalize_bucket() will take. This means every time we unlock the root of
  * the btree, we need to release this lock if we have it held.
  */
-static void bch_cannibalize_unlock(struct cache_set *c)
+void bch_cannibalize_unlock(struct cache_set *c)
 {
 	spin_lock(&c->btree_cannibalize_lock);
 	if (c->btree_cache_alloc_lock == current) {
@@ -1090,10 +1090,12 @@ struct btree *__bch_btree_node_alloc(struct cache_set *c, struct btree_op *op,
 				     struct btree *parent)
 {
 	BKEY_PADDED(key) k;
-	struct btree *b = ERR_PTR(-EAGAIN);
+	struct btree *b;
 
 	mutex_lock(&c->bucket_lock);
 retry:
+	/* return ERR_PTR(-EAGAIN) when it fails */
+	b = ERR_PTR(-EAGAIN);
 	if (__bch_bucket_alloc_set(c, RESERVE_BTREE, &k.key, wait))
 		goto err;
 
@@ -1138,7 +1140,7 @@ static struct btree *btree_node_alloc_replacement(struct btree *b,
 {
 	struct btree *n = bch_btree_node_alloc(b->c, op, b->level, b->parent);
 
-	if (!IS_ERR_OR_NULL(n)) {
+	if (!IS_ERR(n)) {
 		mutex_lock(&n->write_lock);
 		bch_btree_sort_into(&b->keys, &n->keys, &b->c->sort);
 		bkey_copy_key(&n->key, &b->key);
@@ -1340,7 +1342,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
 	memset(new_nodes, 0, sizeof(new_nodes));
 	closure_init_stack(&cl);
 
-	while (nodes < GC_MERGE_NODES && !IS_ERR_OR_NULL(r[nodes].b))
+	while (nodes < GC_MERGE_NODES && !IS_ERR(r[nodes].b))
 		keys += r[nodes++].keys;
 
 	blocks = btree_default_blocks(b->c) * 2 / 3;
@@ -1352,7 +1354,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
 
 	for (i = 0; i < nodes; i++) {
 		new_nodes[i] = btree_node_alloc_replacement(r[i].b, NULL);
-		if (IS_ERR_OR_NULL(new_nodes[i]))
+		if (IS_ERR(new_nodes[i]))
 			goto out_nocoalesce;
 	}
 
@@ -1487,7 +1489,7 @@ out_nocoalesce:
 	bch_keylist_free(&keylist);
 
 	for (i = 0; i < nodes; i++)
-		if (!IS_ERR_OR_NULL(new_nodes[i])) {
+		if (!IS_ERR(new_nodes[i])) {
 			btree_node_free(new_nodes[i]);
 			rw_unlock(true, new_nodes[i]);
 		}
@@ -1669,7 +1671,7 @@ static int bch_btree_gc_root(struct btree *b, struct btree_op *op,
 	if (should_rewrite) {
 		n = btree_node_alloc_replacement(b, NULL);
 
-		if (!IS_ERR_OR_NULL(n)) {
+		if (!IS_ERR(n)) {
 			bch_btree_node_write_sync(n);
 
 			bch_btree_set_root(n);
@@ -1968,6 +1970,15 @@ static int bch_btree_check_thread(void *arg)
 			c->gc_stats.nodes++;
 			bch_btree_op_init(&op, 0);
 			ret = bcache_btree(check_recurse, p, c->root, &op);
+			/*
+			 * The op may be added to cache_set's btree_cache_wait
+			 * in mca_cannibalize(), must ensure it is removed from
+			 * the list and release btree_cache_alloc_lock before
+			 * free op memory.
+			 * Otherwise, the btree_cache_wait will be damaged.
+			 */
+			bch_cannibalize_unlock(c);
+			finish_wait(&c->btree_cache_wait, &(&op)->wait);
 			if (ret)
 				goto out;
 		}

drivers/md/bcache/btree.h

@@ -282,6 +282,7 @@ void bch_initial_gc_finish(struct cache_set *c);
 void bch_moving_gc(struct cache_set *c);
 int bch_btree_check(struct cache_set *c);
 void bch_initial_mark_key(struct cache_set *c, int level, struct bkey *k);
+void bch_cannibalize_unlock(struct cache_set *c);
 
 static inline void wake_up_gc(struct cache_set *c)
 {

drivers/md/bcache/request.c

@@ -1228,7 +1228,7 @@ void cached_dev_submit_bio(struct bio *bio)
 		detached_dev_do_request(d, bio, orig_bdev, start_time);
 }
 
-static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode,
+static int cached_dev_ioctl(struct bcache_device *d, blk_mode_t mode,
 			    unsigned int cmd, unsigned long arg)
 {
 	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
@@ -1318,7 +1318,7 @@ void flash_dev_submit_bio(struct bio *bio)
 	continue_at(cl, search_free, NULL);
 }
 
-static int flash_dev_ioctl(struct bcache_device *d, fmode_t mode,
+static int flash_dev_ioctl(struct bcache_device *d, blk_mode_t mode,
 			   unsigned int cmd, unsigned long arg)
 {
 	return -ENOTTY;

drivers/md/bcache/stats.h

@@ -18,7 +18,6 @@ struct cache_stats {
 	unsigned long cache_misses;
 	unsigned long cache_bypass_hits;
 	unsigned long cache_bypass_misses;
-	unsigned long cache_readaheads;
 	unsigned long cache_miss_collisions;
 	unsigned long sectors_bypassed;
 

drivers/md/bcache/super.c

@@ -732,9 +732,9 @@ out:
 
 /* Bcache device */
 
-static int open_dev(struct block_device *b, fmode_t mode)
+static int open_dev(struct gendisk *disk, blk_mode_t mode)
 {
-	struct bcache_device *d = b->bd_disk->private_data;
+	struct bcache_device *d = disk->private_data;
 
 	if (test_bit(BCACHE_DEV_CLOSING, &d->flags))
 		return -ENXIO;
@@ -743,14 +743,14 @@ static int open_dev(struct block_device *b, fmode_t mode)
 	return 0;
 }
 
-static void release_dev(struct gendisk *b, fmode_t mode)
+static void release_dev(struct gendisk *b)
 {
 	struct bcache_device *d = b->private_data;
 
 	closure_put(&d->cl);
 }
 
-static int ioctl_dev(struct block_device *b, fmode_t mode,
+static int ioctl_dev(struct block_device *b, blk_mode_t mode,
 		     unsigned int cmd, unsigned long arg)
 {
 	struct bcache_device *d = b->bd_disk->private_data;
@@ -1369,7 +1369,7 @@ static void cached_dev_free(struct closure *cl)
 		put_page(virt_to_page(dc->sb_disk));
 
 	if (!IS_ERR_OR_NULL(dc->bdev))
-		blkdev_put(dc->bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+		blkdev_put(dc->bdev, bcache_kobj);
 
 	wake_up(&unregister_wait);
 
@@ -1723,7 +1723,7 @@ static void cache_set_flush(struct closure *cl)
 	if (!IS_ERR_OR_NULL(c->gc_thread))
 		kthread_stop(c->gc_thread);
 
-	if (!IS_ERR_OR_NULL(c->root))
+	if (!IS_ERR(c->root))
 		list_add(&c->root->list, &c->btree_cache);
 
 	/*
@@ -2087,7 +2087,7 @@ static int run_cache_set(struct cache_set *c)
 
 		err = "cannot allocate new btree root";
 		c->root = __bch_btree_node_alloc(c, NULL, 0, true, NULL);
-		if (IS_ERR_OR_NULL(c->root))
+		if (IS_ERR(c->root))
 			goto err;
 
 		mutex_lock(&c->root->write_lock);
@@ -2218,7 +2218,7 @@ void bch_cache_release(struct kobject *kobj)
 		put_page(virt_to_page(ca->sb_disk));
 
 	if (!IS_ERR_OR_NULL(ca->bdev))
-		blkdev_put(ca->bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+		blkdev_put(ca->bdev, bcache_kobj);
 
 	kfree(ca);
 	module_put(THIS_MODULE);
@@ -2359,7 +2359,7 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 		 * call blkdev_put() to bdev in bch_cache_release(). So we
 		 * explicitly call blkdev_put() here.
 		 */
-		blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+		blkdev_put(bdev, bcache_kobj);
 		if (ret == -ENOMEM)
 			err = "cache_alloc(): -ENOMEM";
 		else if (ret == -EPERM)
@@ -2461,7 +2461,7 @@ static void register_bdev_worker(struct work_struct *work)
 	if (!dc) {
 		fail = true;
 		put_page(virt_to_page(args->sb_disk));
-		blkdev_put(args->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
+		blkdev_put(args->bdev, bcache_kobj);
 		goto out;
 	}
 
@@ -2491,7 +2491,7 @@ static void register_cache_worker(struct work_struct *work)
 	if (!ca) {
 		fail = true;
 		put_page(virt_to_page(args->sb_disk));
-		blkdev_put(args->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
+		blkdev_put(args->bdev, bcache_kobj);
 		goto out;
 	}
 
@@ -2558,9 +2558,8 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 
 	ret = -EINVAL;
 	err = "failed to open device";
-	bdev = blkdev_get_by_path(strim(path),
+	bdev = blkdev_get_by_path(strim(path), BLK_OPEN_READ | BLK_OPEN_WRITE,
-				  FMODE_READ|FMODE_WRITE|FMODE_EXCL,
+				  bcache_kobj, NULL);
-				  sb);
 	if (IS_ERR(bdev)) {
 		if (bdev == ERR_PTR(-EBUSY)) {
 			dev_t dev;
@@ -2648,7 +2647,7 @@ async_done:
 out_put_sb_page:
 	put_page(virt_to_page(sb_disk));
 out_blkdev_put:
-	blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
+	blkdev_put(bdev, register_bcache);
 out_free_sb:
 	kfree(sb);
 out_free_path:

drivers/md/bcache/sysfs.c

@@ -1111,26 +1111,25 @@ SHOW(__bch_cache)
 
 		vfree(p);
 
-		ret = scnprintf(buf, PAGE_SIZE,
+		ret = sysfs_emit(buf,
-				"Unused:		%zu%%\n"
+				 "Unused:		%zu%%\n"
-				"Clean:		%zu%%\n"
+				 "Clean:		%zu%%\n"
-				"Dirty:		%zu%%\n"
+				 "Dirty:		%zu%%\n"
-				"Metadata:	%zu%%\n"
+				 "Metadata:	%zu%%\n"
-				"Average:	%llu\n"
+				 "Average:	%llu\n"
-				"Sectors per Q:	%zu\n"
+				 "Sectors per Q:	%zu\n"
-				"Quantiles:	[",
+				 "Quantiles:	[",
-				unused * 100 / (size_t) ca->sb.nbuckets,
+				 unused * 100 / (size_t) ca->sb.nbuckets,
-				available * 100 / (size_t) ca->sb.nbuckets,
+				 available * 100 / (size_t) ca->sb.nbuckets,
-				dirty * 100 / (size_t) ca->sb.nbuckets,
+				 dirty * 100 / (size_t) ca->sb.nbuckets,
-				meta * 100 / (size_t) ca->sb.nbuckets, sum,
+				 meta * 100 / (size_t) ca->sb.nbuckets, sum,
-				n * ca->sb.bucket_size / (ARRAY_SIZE(q) + 1));
+				 n * ca->sb.bucket_size / (ARRAY_SIZE(q) + 1));
 
 		for (i = 0; i < ARRAY_SIZE(q); i++)
-			ret += scnprintf(buf + ret, PAGE_SIZE - ret,
+			ret += sysfs_emit_at(buf, ret, "%u ", q[i]);
-					 "%u ", q[i]);
 		ret--;
 
-		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "]\n");
+		ret += sysfs_emit_at(buf, ret, "]\n");
 
 		return ret;
 	}

drivers/md/bcache/sysfs.h

@@ -3,7 +3,7 @@
 #define _BCACHE_SYSFS_H_
 
 #define KTYPE(type)							\
-struct kobj_type type ## _ktype = {					\
+const struct kobj_type type ## _ktype = {					\
 	.release	= type ## _release,				\
 	.sysfs_ops	= &((const struct sysfs_ops) {			\
 		.show	= type ## _show,				\

drivers/md/bcache/writeback.c

@@ -890,6 +890,16 @@ static int bch_root_node_dirty_init(struct cache_set *c,
 	if (ret < 0)
 		pr_warn("sectors dirty init failed, ret=%d!\n", ret);
 
+	/*
+	 * The op may be added to cache_set's btree_cache_wait
+	 * in mca_cannibalize(), must ensure it is removed from
+	 * the list and release btree_cache_alloc_lock before
+	 * free op memory.
+	 * Otherwise, the btree_cache_wait will be damaged.
+	 */
+	bch_cannibalize_unlock(c);
+	finish_wait(&c->btree_cache_wait, &(&op.op)->wait);
+
 	return ret;
 }
 

drivers/md/dm-cache-target.c

@@ -2051,8 +2051,8 @@ static int parse_metadata_dev(struct cache_args *ca, struct dm_arg_set *as,
 	if (!at_least_one_arg(as, error))
 		return -EINVAL;
 
-	r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE,
+	r = dm_get_device(ca->ti, dm_shift_arg(as),
-			  &ca->metadata_dev);
+			  BLK_OPEN_READ | BLK_OPEN_WRITE, &ca->metadata_dev);
 	if (r) {
 		*error = "Error opening metadata device";
 		return r;
@@ -2074,8 +2074,8 @@ static int parse_cache_dev(struct cache_args *ca, struct dm_arg_set *as,
 	if (!at_least_one_arg(as, error))
 		return -EINVAL;
 
-	r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE,
+	r = dm_get_device(ca->ti, dm_shift_arg(as),
-			  &ca->cache_dev);
+			  BLK_OPEN_READ | BLK_OPEN_WRITE, &ca->cache_dev);
 	if (r) {
 		*error = "Error opening cache device";
 		return r;
@@ -2093,8 +2093,8 @@ static int parse_origin_dev(struct cache_args *ca, struct dm_arg_set *as,
 	if (!at_least_one_arg(as, error))
 		return -EINVAL;
 
-	r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE,
+	r = dm_get_device(ca->ti, dm_shift_arg(as),
-			  &ca->origin_dev);
+			  BLK_OPEN_READ | BLK_OPEN_WRITE, &ca->origin_dev);
 	if (r) {
 		*error = "Error opening origin device";
 		return r;

drivers/md/dm-clone-target.c

@@ -1683,8 +1683,8 @@ static int parse_metadata_dev(struct clone *clone, struct dm_arg_set *as, char *
 	int r;
 	sector_t metadata_dev_size;
 
-	r = dm_get_device(clone->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE,
+	r = dm_get_device(clone->ti, dm_shift_arg(as),
-			  &clone->metadata_dev);
+			  BLK_OPEN_READ | BLK_OPEN_WRITE, &clone->metadata_dev);
 	if (r) {
 		*error = "Error opening metadata device";
 		return r;
@@ -1703,8 +1703,8 @@ static int parse_dest_dev(struct clone *clone, struct dm_arg_set *as, char **err
 	int r;
 	sector_t dest_dev_size;
 
-	r = dm_get_device(clone->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE,
+	r = dm_get_device(clone->ti, dm_shift_arg(as),
-			  &clone->dest_dev);
+			  BLK_OPEN_READ | BLK_OPEN_WRITE, &clone->dest_dev);
 	if (r) {
 		*error = "Error opening destination device";
 		return r;
@@ -1725,7 +1725,7 @@ static int parse_source_dev(struct clone *clone, struct dm_arg_set *as, char **e
 	int r;
 	sector_t source_dev_size;
 
-	r = dm_get_device(clone->ti, dm_shift_arg(as), FMODE_READ,
+	r = dm_get_device(clone->ti, dm_shift_arg(as), BLK_OPEN_READ,
 			  &clone->source_dev);
 	if (r) {
 		*error = "Error opening source device";

drivers/md/dm-core.h

@@ -207,11 +207,10 @@ struct dm_table {
 	unsigned integrity_added:1;
 
 	/*
-	 * Indicates the rw permissions for the new logical
+	 * Indicates the rw permissions for the new logical device.  This
-	 * device.  This should be a combination of FMODE_READ
+	 * should be a combination of BLK_OPEN_READ and BLK_OPEN_WRITE.
-	 * and FMODE_WRITE.
 	 */
-	fmode_t mode;
+	blk_mode_t mode;
 
 	/* a list of devices used by this table */
 	struct list_head devices;

drivers/md/dm-crypt.c

@@ -1693,8 +1693,7 @@ retry:
 
 		len = (remaining_size > PAGE_SIZE) ? PAGE_SIZE : remaining_size;
 
-		bio_add_page(clone, page, len, 0);
+		__bio_add_page(clone, page, len, 0);
-
 		remaining_size -= len;
 	}
 

drivers/md/dm-era-target.c

@@ -1482,14 +1482,16 @@ static int era_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	era->ti = ti;
 
-	r = dm_get_device(ti, argv[0], FMODE_READ | FMODE_WRITE, &era->metadata_dev);
+	r = dm_get_device(ti, argv[0], BLK_OPEN_READ | BLK_OPEN_WRITE,
+			  &era->metadata_dev);
 	if (r) {
 		ti->error = "Error opening metadata device";
 		era_destroy(era);
 		return -EINVAL;
 	}
 
-	r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &era->origin_dev);
+	r = dm_get_device(ti, argv[1], BLK_OPEN_READ | BLK_OPEN_WRITE,
+			  &era->origin_dev);
 	if (r) {
 		ti->error = "Error opening data device";
 		era_destroy(era);

drivers/md/dm-init.c

@@ -293,8 +293,10 @@ static int __init dm_init_init(void)
 
 	for (i = 0; i < ARRAY_SIZE(waitfor); i++) {
 		if (waitfor[i]) {
+			dev_t dev;
+
 			DMINFO("waiting for device %s ...", waitfor[i]);
-			while (!dm_get_dev_t(waitfor[i]))
+			while (early_lookup_bdev(waitfor[i], &dev))
 				fsleep(5000);
 		}
 	}

drivers/md/dm-ioctl.c

@@ -861,7 +861,7 @@ static void __dev_status(struct mapped_device *md, struct dm_ioctl *param)
 
 		table = dm_get_inactive_table(md, &srcu_idx);
 		if (table) {
-			if (!(dm_table_get_mode(table) & FMODE_WRITE))
+			if (!(dm_table_get_mode(table) & BLK_OPEN_WRITE))
 				param->flags |= DM_READONLY_FLAG;
 			param->target_count = table->num_targets;
 		}
@@ -1189,7 +1189,7 @@ static int do_resume(struct dm_ioctl *param)
 		if (old_size && new_size && old_size != new_size)
 			need_resize_uevent = true;
 
-		if (dm_table_get_mode(new_map) & FMODE_WRITE)
+		if (dm_table_get_mode(new_map) & BLK_OPEN_WRITE)
 			set_disk_ro(dm_disk(md), 0);
 		else
 			set_disk_ro(dm_disk(md), 1);
@@ -1378,12 +1378,12 @@ static int dev_arm_poll(struct file *filp, struct dm_ioctl *param, size_t param_
 	return 0;
 }
 
-static inline fmode_t get_mode(struct dm_ioctl *param)
+static inline blk_mode_t get_mode(struct dm_ioctl *param)
 {
-	fmode_t mode = FMODE_READ | FMODE_WRITE;
+	blk_mode_t mode = BLK_OPEN_READ | BLK_OPEN_WRITE;
 
 	if (param->flags & DM_READONLY_FLAG)
-		mode = FMODE_READ;
+		mode = BLK_OPEN_READ;
 
 	return mode;
 }

drivers/md/dm-raid.c

@@ -3750,11 +3750,11 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
 		 * canceling read-auto mode
 		 */
 		mddev->ro = 0;
-		if (!mddev->suspended && mddev->sync_thread)
+		if (!mddev->suspended)
 			md_wakeup_thread(mddev->sync_thread);
 	}
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	if (!mddev->suspended && mddev->thread)
+	if (!mddev->suspended)
 		md_wakeup_thread(mddev->thread);
 
 	return 0;

drivers/md/dm-snap.c

@@ -1241,9 +1241,8 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	int i;
 	int r = -EINVAL;
 	char *origin_path, *cow_path;
-	dev_t origin_dev, cow_dev;
 	unsigned int args_used, num_flush_bios = 1;
-	fmode_t origin_mode = FMODE_READ;
+	blk_mode_t origin_mode = BLK_OPEN_READ;
 
 	if (argc < 4) {
 		ti->error = "requires 4 or more arguments";
@@ -1253,7 +1252,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	if (dm_target_is_snapshot_merge(ti)) {
 		num_flush_bios = 2;
-		origin_mode = FMODE_WRITE;
+		origin_mode = BLK_OPEN_WRITE;
 	}
 
 	s = kzalloc(sizeof(*s), GFP_KERNEL);
@@ -1279,24 +1278,21 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		ti->error = "Cannot get origin device";
 		goto bad_origin;
 	}
-	origin_dev = s->origin->bdev->bd_dev;
 
 	cow_path = argv[0];
 	argv++;
 	argc--;
 
-	cow_dev = dm_get_dev_t(cow_path);
-	if (cow_dev && cow_dev == origin_dev) {
-		ti->error = "COW device cannot be the same as origin device";
-		r = -EINVAL;
-		goto bad_cow;
-	}
-
 	r = dm_get_device(ti, cow_path, dm_table_get_mode(ti->table), &s->cow);
 	if (r) {
 		ti->error = "Cannot get COW device";
 		goto bad_cow;
 	}
+	if (s->cow->bdev && s->cow->bdev == s->origin->bdev) {
+		ti->error = "COW device cannot be the same as origin device";
+		r = -EINVAL;
+		goto bad_store;
+	}
 
 	r = dm_exception_store_create(ti, argc, argv, s, &args_used, &s->store);
 	if (r) {

drivers/md/dm-table.c

@@ -126,7 +126,7 @@ static int alloc_targets(struct dm_table *t, unsigned int num)
 	return 0;
 }
 
-int dm_table_create(struct dm_table **result, fmode_t mode,
+int dm_table_create(struct dm_table **result, blk_mode_t mode,
 		    unsigned int num_targets, struct mapped_device *md)
 {
 	struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL);
@@ -304,7 +304,7 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
  * device and not to touch the existing bdev field in case
  * it is accessed concurrently.
  */
-static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
+static int upgrade_mode(struct dm_dev_internal *dd, blk_mode_t new_mode,
 			struct mapped_device *md)
 {
 	int r;
@@ -323,24 +323,14 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
 	return 0;
 }
 
-/*
- * Convert the path to a device
- */
-dev_t dm_get_dev_t(const char *path)
-{
-	dev_t dev;
-
-	if (lookup_bdev(path, &dev))
-		dev = name_to_dev_t(path);
-	return dev;
-}
-EXPORT_SYMBOL_GPL(dm_get_dev_t);
-
 /*
  * Add a device to the list, or just increment the usage count if
  * it's already present.
+ *
+ * Note: the __ref annotation is because this function can call the __init
+ * marked early_lookup_bdev when called during early boot code from dm-init.c.
  */
-int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
+int __ref dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode,
 		  struct dm_dev **result)
 {
 	int r;
@@ -358,9 +348,13 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
 		if (MAJOR(dev) != major || MINOR(dev) != minor)
 			return -EOVERFLOW;
 	} else {
-		dev = dm_get_dev_t(path);
+		r = lookup_bdev(path, &dev);
-		if (!dev)
+#ifndef MODULE
-			return -ENODEV;
+		if (r && system_state < SYSTEM_RUNNING)
+			r = early_lookup_bdev(path, &dev);
+#endif
+		if (r)
+			return r;
 	}
 	if (dev == disk_devt(t->md->disk))
 		return -EINVAL;
@@ -668,7 +662,8 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 		t->singleton = true;
 	}
 
-	if (dm_target_always_writeable(ti->type) && !(t->mode & FMODE_WRITE)) {
+	if (dm_target_always_writeable(ti->type) &&
+	    !(t->mode & BLK_OPEN_WRITE)) {
 		ti->error = "target type may not be included in a read-only table";
 		goto bad;
 	}
@@ -2039,7 +2034,7 @@ struct list_head *dm_table_get_devices(struct dm_table *t)
 	return &t->devices;
 }
 
-fmode_t dm_table_get_mode(struct dm_table *t)
+blk_mode_t dm_table_get_mode(struct dm_table *t)
 {
 	return t->mode;
 }

drivers/md/dm-thin.c

@@ -3300,7 +3300,7 @@ static int pool_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	unsigned long block_size;
 	dm_block_t low_water_blocks;
 	struct dm_dev *metadata_dev;
-	fmode_t metadata_mode;
+	blk_mode_t metadata_mode;
 
 	/*
 	 * FIXME Remove validation from scope of lock.
@@ -3333,7 +3333,8 @@ static int pool_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	if (r)
 		goto out_unlock;
 
-	metadata_mode = FMODE_READ | ((pf.mode == PM_READ_ONLY) ? 0 : FMODE_WRITE);
+	metadata_mode = BLK_OPEN_READ |
+		((pf.mode == PM_READ_ONLY) ? 0 : BLK_OPEN_WRITE);
 	r = dm_get_device(ti, argv[0], metadata_mode, &metadata_dev);
 	if (r) {
 		ti->error = "Error opening metadata block device";
@@ -3341,7 +3342,7 @@ static int pool_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 	warn_if_metadata_device_too_big(metadata_dev->bdev);
 
-	r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &data_dev);
+	r = dm_get_device(ti, argv[1], BLK_OPEN_READ | BLK_OPEN_WRITE, &data_dev);
 	if (r) {
 		ti->error = "Error getting data device";
 		goto out_metadata;
@@ -4222,7 +4223,7 @@ static int thin_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 			goto bad_origin_dev;
 		}
 
-		r = dm_get_device(ti, argv[2], FMODE_READ, &origin_dev);
+		r = dm_get_device(ti, argv[2], BLK_OPEN_READ, &origin_dev);
 		if (r) {
 			ti->error = "Error opening origin device";
 			goto bad_origin_dev;

drivers/md/dm-verity-fec.c

@@ -607,7 +607,7 @@ int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v,
 	(*argc)--;
 
 	if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV)) {
-		r = dm_get_device(ti, arg_value, FMODE_READ, &v->fec->dev);
+		r = dm_get_device(ti, arg_value, BLK_OPEN_READ, &v->fec->dev);
 		if (r) {
 			ti->error = "FEC device lookup failed";
 			return r;

drivers/md/dm-verity-target.c

@@ -1196,7 +1196,7 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	if (r)
 		goto bad;
 
-	if ((dm_table_get_mode(ti->table) & ~FMODE_READ)) {
+	if ((dm_table_get_mode(ti->table) & ~BLK_OPEN_READ)) {
 		ti->error = "Device must be readonly";
 		r = -EINVAL;
 		goto bad;
@@ -1225,13 +1225,13 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 	v->version = num;
 
-	r = dm_get_device(ti, argv[1], FMODE_READ, &v->data_dev);
+	r = dm_get_device(ti, argv[1], BLK_OPEN_READ, &v->data_dev);
 	if (r) {
 		ti->error = "Data device lookup failed";
 		goto bad;
 	}
 
-	r = dm_get_device(ti, argv[2], FMODE_READ, &v->hash_dev);
+	r = dm_get_device(ti, argv[2], BLK_OPEN_READ, &v->hash_dev);
 	if (r) {
 		ti->error = "Hash device lookup failed";
 		goto bad;

drivers/md/dm-zoned-metadata.c

@@ -577,7 +577,7 @@ static struct dmz_mblock *dmz_get_mblock_slow(struct dmz_metadata *zmd,
 	bio->bi_iter.bi_sector = dmz_blk2sect(block);
 	bio->bi_private = mblk;
 	bio->bi_end_io = dmz_mblock_bio_end_io;
-	bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0);
+	__bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0);
 	submit_bio(bio);
 
 	return mblk;
@@ -728,7 +728,7 @@ static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk,
 	bio->bi_iter.bi_sector = dmz_blk2sect(block);
 	bio->bi_private = mblk;
 	bio->bi_end_io = dmz_mblock_bio_end_io;
-	bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0);
+	__bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0);
 	submit_bio(bio);
 
 	return 0;
@@ -752,7 +752,7 @@ static int dmz_rdwr_block(struct dmz_dev *dev, enum req_op op,
 	bio = bio_alloc(dev->bdev, 1, op | REQ_SYNC | REQ_META | REQ_PRIO,
 			GFP_NOIO);
 	bio->bi_iter.bi_sector = dmz_blk2sect(block);
-	bio_add_page(bio, page, DMZ_BLOCK_SIZE, 0);
+	__bio_add_page(bio, page, DMZ_BLOCK_SIZE, 0);
 	ret = submit_bio_wait(bio);
 	bio_put(bio);
 

drivers/md/dm.c

@@ -310,13 +310,13 @@ int dm_deleting_md(struct mapped_device *md)
 	return test_bit(DMF_DELETING, &md->flags);
 }
 
-static int dm_blk_open(struct block_device *bdev, fmode_t mode)
+static int dm_blk_open(struct gendisk *disk, blk_mode_t mode)
 {
 	struct mapped_device *md;
 
 	spin_lock(&_minor_lock);
 
-	md = bdev->bd_disk->private_data;
+	md = disk->private_data;
 	if (!md)
 		goto out;
 
@@ -334,7 +334,7 @@ out:
 	return md ? 0 : -ENXIO;
 }
 
-static void dm_blk_close(struct gendisk *disk, fmode_t mode)
+static void dm_blk_close(struct gendisk *disk)
 {
 	struct mapped_device *md;
 
@@ -448,7 +448,7 @@ static void dm_unprepare_ioctl(struct mapped_device *md, int srcu_idx)
 	dm_put_live_table(md, srcu_idx);
 }
 
-static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
+static int dm_blk_ioctl(struct block_device *bdev, blk_mode_t mode,
 			unsigned int cmd, unsigned long arg)
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
@@ -734,7 +734,7 @@ static char *_dm_claim_ptr = "I belong to device-mapper";
  * Open a table device so we can use it as a map destination.
  */
 static struct table_device *open_table_device(struct mapped_device *md,
-		dev_t dev, fmode_t mode)
+		dev_t dev, blk_mode_t mode)
 {
 	struct table_device *td;
 	struct block_device *bdev;
@@ -746,7 +746,7 @@ static struct table_device *open_table_device(struct mapped_device *md,
 		return ERR_PTR(-ENOMEM);
 	refcount_set(&td->count, 1);
 
-	bdev = blkdev_get_by_dev(dev, mode | FMODE_EXCL, _dm_claim_ptr);
+	bdev = blkdev_get_by_dev(dev, mode, _dm_claim_ptr, NULL);
 	if (IS_ERR(bdev)) {
 		r = PTR_ERR(bdev);
 		goto out_free_td;
@@ -771,7 +771,7 @@ static struct table_device *open_table_device(struct mapped_device *md,
 	return td;
 
 out_blkdev_put:
-	blkdev_put(bdev, mode | FMODE_EXCL);
+	blkdev_put(bdev, _dm_claim_ptr);
 out_free_td:
 	kfree(td);
 	return ERR_PTR(r);
@@ -784,14 +784,14 @@ static void close_table_device(struct table_device *td, struct mapped_device *md
 {
 	if (md->disk->slave_dir)
 		bd_unlink_disk_holder(td->dm_dev.bdev, md->disk);
-	blkdev_put(td->dm_dev.bdev, td->dm_dev.mode | FMODE_EXCL);
+	blkdev_put(td->dm_dev.bdev, _dm_claim_ptr);
 	put_dax(td->dm_dev.dax_dev);
 	list_del(&td->list);
 	kfree(td);
 }
 
 static struct table_device *find_table_device(struct list_head *l, dev_t dev,
-					      fmode_t mode)
+					      blk_mode_t mode)
 {
 	struct table_device *td;
 
@@ -802,7 +802,7 @@ static struct table_device *find_table_device(struct list_head *l, dev_t dev,
 	return NULL;
 }
 
-int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode,
+int dm_get_table_device(struct mapped_device *md, dev_t dev, blk_mode_t mode,
 			struct dm_dev **result)
 {
 	struct table_device *td;

drivers/md/dm.h

@@ -203,7 +203,7 @@ int dm_open_count(struct mapped_device *md);
 int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only_deferred);
 int dm_cancel_deferred_remove(struct mapped_device *md);
 int dm_request_based(struct mapped_device *md);
-int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode,
+int dm_get_table_device(struct mapped_device *md, dev_t dev, blk_mode_t mode,
 			struct dm_dev **result);
 void dm_put_table_device(struct mapped_device *md, struct dm_dev *d);