for-6.11/block-20240710

-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAmaOTd8QHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgppqIEACUr8Vv2FtezvT3OfVSlYWHHLXzkRhwEG5s
 vdk0o7Ow6U54sMjfymbHTgLD0ZOJf3uJ6BI95FQuW41jPzDFVbx4Hy8QzqonMkw9
 1D/YQ4zrVL2mOKBzATbKpoGJzMOzGeoXEueFZ1AYPAX7RrDtP4xPQNfrcfkdE2zF
 LycJN70Vp6lrZZMuI9yb9ts1tf7TFzK0HJANxOAKTgSiPmBmxesjkJlhrdUrgkAU
 qDVyjj7u/ssndBJAb9i6Bl95Do8s9t4DeJq5/6wgKqtf5hClMXzPVB8Wy084gr6E
 rTRsCEhOug3qEZSqfAgAxnd3XFRNc/p2KMUe5YZ4mAqux4hpSmIQQDM/5X5K9vEv
 f4MNqUGlqyqntZx+KPyFpf7kLHFYS1qK4ub0FojWJEY4GrbBPNjjncLJ9+ozR0c8
 kNDaFjMNAjalBee1FxNNH8LdVcd28rrCkPxRLEfO/gvBMUmvJf4ZyKmSED0v5DhY
 vZqKlBqG+wg0EXvdiWEHMDh9Y+q/2XBIkS6NN/Bhh61HNu+XzC838ts1X7lR+4o2
 AM5Vapw+v0q6kFBMRP3IcJI/c0UcIU8EQU7axMyzWtvhog8kx8x01hIj1L4UyYYr
 rUdWrkugBVXJbywFuH/QIJxWxS/z4JdSw5VjASJLIrXy+aANmmG9Wonv95eyhpUv
 5iv+EdRSNA==
 =wVi8
 -----END PGP SIGNATURE-----

Merge tag 'for-6.11/block-20240710' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe updates via Keith:
     - Device initialization memory leak fixes (Keith)
     - More constants defined (Weiwen)
     - Target debugfs support (Hannes)
     - PCIe subsystem reset enhancements (Keith)
     - Queue-depth multipath policy (Redhat and PureStorage)
     - Implement get_unique_id (Christoph)
     - Authentication error fixes (Gaosheng)

 - MD updates via Song
     - sync_action fix and refactoring (Yu Kuai)
     - Various small fixes (Christoph Hellwig, Li Nan, and Ofir Gal, Yu
       Kuai, Benjamin Marzinski, Christophe JAILLET, Yang Li)

 - Fix loop detach/open race (Gulam)

 - Fix lower control limit for blk-throttle (Yu)

 - Add module descriptions to various drivers (Jeff)

 - Add support for atomic writes for block devices, and statx reporting
   for same. Includes SCSI and NVMe (John, Prasad, Alan)

 - Add IO priority information to block trace points (Dongliang)

 - Various zone improvements and tweaks (Damien)

 - mq-deadline tag reservation improvements (Bart)

 - Ignore direct reclaim swap writes in writeback throttling (Baokun)

 - Block integrity improvements and fixes (Anuj)

 - Add basic support for rust based block drivers. Has a dummy null_blk
   variant for now (Andreas)

 - Series converting driver settings to queue limits, and cleanups and
   fixes related to that (Christoph)

 - Cleanup for poking too deeply into the bvec internals, in preparation
   for DMA mapping API changes (Christoph)

 - Various minor tweaks and fixes (Jiapeng, John, Kanchan, Mikulas,
   Ming, Zhu, Damien, Christophe, Chaitanya)

* tag 'for-6.11/block-20240710' of git://git.kernel.dk/linux: (206 commits)
  floppy: add missing MODULE_DESCRIPTION() macro
  loop: add missing MODULE_DESCRIPTION() macro
  ublk_drv: add missing MODULE_DESCRIPTION() macro
  xen/blkback: add missing MODULE_DESCRIPTION() macro
  block/rnbd: Constify struct kobj_type
  block: take offset into account in blk_bvec_map_sg again
  block: fix get_max_segment_size() warning
  loop: Don't bother validating blocksize
  virtio_blk: Don't bother validating blocksize
  null_blk: Don't bother validating blocksize
  block: Validate logical block size in blk_validate_limits()
  virtio_blk: Fix default logical block size fallback
  nvmet-auth: fix nvmet_auth hash error handling
  nvme: implement ->get_unique_id
  block: pass a phys_addr_t to get_max_segment_size
  block: add a bvec_phys helper
  blk-lib: check for kill signal in ioctl BLKZEROOUT
  block: limit the Write Zeroes to manually writing zeroes fallback
  block: refacto blkdev_issue_zeroout
  block: move read-only and supported checks into (__)blkdev_issue_zeroout
  ...

.mailmap

@@ -690,6 +690,7 @@ Vivien Didelot <vivien.didelot@gmail.com> <vivien.didelot@savoirfairelinux.com>
 Vlad Dogaru <ddvlad@gmail.com> <vlad.dogaru@intel.com>
 Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com>
 Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com>
+Weiwen Hu <huweiwen@linux.alibaba.com> <sehuww@mail.scut.edu.cn>
 WeiXiong Liao <gmpy.liaowx@gmail.com> <liaoweixiong@allwinnertech.com>
 Wen Gong <quic_wgong@quicinc.com> <wgong@codeaurora.org>
 Wesley Cheng <quic_wcheng@quicinc.com> <wcheng@codeaurora.org>

Documentation/ABI/stable/sysfs-block

@@ -21,6 +21,59 @@ Description:
 		device is offset from the internal allocation unit's
 		natural alignment.
 
+What:		/sys/block/<disk>/atomic_write_max_bytes
+Date:		February 2024
+Contact:	Himanshu Madhani <himanshu.madhani@oracle.com>
+Description:
+		[RO] This parameter specifies the maximum atomic write
+		size reported by the device. This parameter is relevant
+		for merging of writes, where a merged atomic write
+		operation must not exceed this number of bytes.
+		This parameter may be greater than the value in
+		atomic_write_unit_max_bytes as
+		atomic_write_unit_max_bytes will be rounded down to a
+		power-of-two and atomic_write_unit_max_bytes may also be
+		limited by some other queue limits, such as max_segments.
+		This parameter - along with atomic_write_unit_min_bytes
+		and atomic_write_unit_max_bytes - will not be larger than
+		max_hw_sectors_kb, but may be larger than max_sectors_kb.
+
+
+What:		/sys/block/<disk>/atomic_write_unit_min_bytes
+Date:		February 2024
+Contact:	Himanshu Madhani <himanshu.madhani@oracle.com>
+Description:
+		[RO] This parameter specifies the smallest block which can
+		be written atomically with an atomic write operation. All
+		atomic write operations must begin at a
+		atomic_write_unit_min boundary and must be multiples of
+		atomic_write_unit_min. This value must be a power-of-two.
+
+
+What:		/sys/block/<disk>/atomic_write_unit_max_bytes
+Date:		February 2024
+Contact:	Himanshu Madhani <himanshu.madhani@oracle.com>
+Description:
+		[RO] This parameter defines the largest block which can be
+		written atomically with an atomic write operation. This
+		value must be a multiple of atomic_write_unit_min and must
+		be a power-of-two. This value will not be larger than
+		atomic_write_max_bytes.
+
+
+What:		/sys/block/<disk>/atomic_write_boundary_bytes
+Date:		February 2024
+Contact:	Himanshu Madhani <himanshu.madhani@oracle.com>
+Description:
+		[RO] A device may need to internally split an atomic write I/O
+		which straddles a given logical block address boundary. This
+		parameter specifies the size in bytes of the atomic boundary if
+		one is reported by the device. This value must be a
+		power-of-two and at least the size as in
+		atomic_write_unit_max_bytes.
+		Any attempt to merge atomic write I/Os must not result in a
+		merged I/O which crosses this boundary (if any).
+
 
 What:		/sys/block/<disk>/diskseq
 Date:		February 2021

Documentation/block/data-integrity.rst

@@ -153,18 +153,11 @@ bio_free() will automatically free the bip.
 4.2 Block Device
 ----------------
 
-Because the format of the protection data is tied to the physical
+Block devices can set up the integrity information in the integrity
-disk, each block device has been extended with a block integrity
+sub-struture of the queue_limits structure.
-profile (struct blk_integrity).  This optional profile is registered
-with the block layer using blk_integrity_register().
-
-The profile contains callback functions for generating and verifying
-the protection data, as well as getting and setting application tags.
-The profile also contains a few constants to aid in completing,
-merging and splitting the integrity metadata.
 
 Layered block devices will need to pick a profile that's appropriate
-for all subdevices.  blk_integrity_compare() can help with that.  DM
+for all subdevices.  queue_limits_stack_integrity() can help with that.  DM
 and MD linear, RAID0 and RAID1 are currently supported.  RAID4/5/6
 will require extra work due to the application tag.
 
@@ -250,42 +243,6 @@ will require extra work due to the application tag.
       integrity upon completion.
 
 
-5.4 Registering A Block Device As Capable Of Exchanging Integrity Metadata
---------------------------------------------------------------------------
-
-    To enable integrity exchange on a block device the gendisk must be
-    registered as capable:
-
-    `int blk_integrity_register(gendisk, blk_integrity);`
-
-      The blk_integrity struct is a template and should contain the
-      following::
-
-        static struct blk_integrity my_profile = {
-            .name                   = "STANDARDSBODY-TYPE-VARIANT-CSUM",
-            .generate_fn            = my_generate_fn,
-	    .verify_fn              = my_verify_fn,
-	    .tuple_size             = sizeof(struct my_tuple_size),
-	    .tag_size               = <tag bytes per hw sector>,
-        };
-
-      'name' is a text string which will be visible in sysfs.  This is
-      part of the userland API so chose it carefully and never change
-      it.  The format is standards body-type-variant.
-      E.g. T10-DIF-TYPE1-IP or T13-EPP-0-CRC.
-
-      'generate_fn' generates appropriate integrity metadata (for WRITE).
-
-      'verify_fn' verifies that the data buffer matches the integrity
-      metadata.
-
-      'tuple_size' must be set to match the size of the integrity
-      metadata per sector.  I.e. 8 for DIF and EPP.
-
-      'tag_size' must be set to identify how many bytes of tag space
-      are available per hardware sector.  For DIF this is either 2 or
-      0 depending on the value of the Control Mode Page ATO bit.
-
 ----------------------------------------------------------------------
 
 2007-12-24 Martin K. Petersen <martin.petersen@oracle.com>

Documentation/block/writeback_cache_control.rst

@@ -46,41 +46,50 @@ worry if the underlying devices need any explicit cache flushing and how
 the Forced Unit Access is implemented.  The REQ_PREFLUSH and REQ_FUA flags
 may both be set on a single bio.
 
-
+Feature settings for block drivers
-Implementation details for bio based block drivers
+----------------------------------
---------------------------------------------------------------
-
-These drivers will always see the REQ_PREFLUSH and REQ_FUA bits as they sit
-directly below the submit_bio interface.  For remapping drivers the REQ_FUA
-bits need to be propagated to underlying devices, and a global flush needs
-to be implemented for bios with the REQ_PREFLUSH bit set.  For real device
-drivers that do not have a volatile cache the REQ_PREFLUSH and REQ_FUA bits
-on non-empty bios can simply be ignored, and REQ_PREFLUSH requests without
-data can be completed successfully without doing any work.  Drivers for
-devices with volatile caches need to implement the support for these
-flags themselves without any help from the block layer.
-
-
-Implementation details for request_fn based block drivers
----------------------------------------------------------
 
 For devices that do not support volatile write caches there is no driver
 support required, the block layer completes empty REQ_PREFLUSH requests before
 entering the driver and strips off the REQ_PREFLUSH and REQ_FUA bits from
-requests that have a payload.  For devices with volatile write caches the
+requests that have a payload.
-driver needs to tell the block layer that it supports flushing caches by
-doing::
 
-	blk_queue_write_cache(sdkp->disk->queue, true, false);
+For devices with volatile write caches the driver needs to tell the block layer
+that it supports flushing caches by setting the
 
-and handle empty REQ_OP_FLUSH requests in its prep_fn/request_fn.  Note that
+   BLK_FEAT_WRITE_CACHE
-REQ_PREFLUSH requests with a payload are automatically turned into a sequence
-of an empty REQ_OP_FLUSH request followed by the actual write by the block
-layer.  For devices that also support the FUA bit the block layer needs
-to be told to pass through the REQ_FUA bit using::
 
-	blk_queue_write_cache(sdkp->disk->queue, true, true);
+flag in the queue_limits feature field.  For devices that also support the FUA
+bit the block layer needs to be told to pass on the REQ_FUA bit by also setting
+the
 
-and the driver must handle write requests that have the REQ_FUA bit set
+   BLK_FEAT_FUA
-in prep_fn/request_fn.  If the FUA bit is not natively supported the block
+
-layer turns it into an empty REQ_OP_FLUSH request after the actual write.
+flag in the features field of the queue_limits structure.
+
+Implementation details for bio based block drivers
+--------------------------------------------------
+
+For bio based drivers the REQ_PREFLUSH and REQ_FUA bit are simply passed on to
+the driver if the driver sets the BLK_FEAT_WRITE_CACHE flag and the driver
+needs to handle them.
+
+*NOTE*: The REQ_FUA bit also gets passed on when the BLK_FEAT_FUA flags is
+_not_ set.  Any bio based driver that sets BLK_FEAT_WRITE_CACHE also needs to
+handle REQ_FUA.
+
+For remapping drivers the REQ_FUA bits need to be propagated to underlying
+devices, and a global flush needs to be implemented for bios with the
+REQ_PREFLUSH bit set.
+
+Implementation details for blk-mq drivers
+-----------------------------------------
+
+When the BLK_FEAT_WRITE_CACHE flag is set, REQ_OP_WRITE | REQ_PREFLUSH requests
+with a payload are automatically turned into a sequence of a REQ_OP_FLUSH
+request followed by the actual write by the block layer.
+
+When the BLK_FEAT_FUA flags is set, the REQ_FUA bit is simply passed on for the
+REQ_OP_WRITE request, else a REQ_OP_FLUSH request is sent by the block layer
+after the completion of the write request for bio submissions with the REQ_FUA
+bit set.

MAINTAINERS

@@ -3759,6 +3759,20 @@ F:	include/linux/blk*
 F:	kernel/trace/blktrace.c
 F:	lib/sbitmap.c
 
+BLOCK LAYER DEVICE DRIVER API [RUST]
+M:	Andreas Hindborg <a.hindborg@samsung.com>
+R:	Boqun Feng <boqun.feng@gmail.com>
+L:	linux-block@vger.kernel.org
+L:	rust-for-linux@vger.kernel.org
+S:	Supported
+W:	https://rust-for-linux.com
+B:	https://github.com/Rust-for-Linux/linux/issues
+C:	https://rust-for-linux.zulipchat.com/#narrow/stream/Block
+T:	git https://github.com/Rust-for-Linux/linux.git rust-block-next
+F:	drivers/block/rnull.rs
+F:	rust/kernel/block.rs
+F:	rust/kernel/block/
+
 BLOCK2MTD DRIVER
 M:	Joern Engel <joern@lazybastard.org>
 L:	linux-mtd@lists.infradead.org

arch/m68k/emu/nfblock.c

@@ -71,7 +71,7 @@ static void nfhd_submit_bio(struct bio *bio)
 		len = bvec.bv_len;
 		len >>= 9;
 		nfhd_read_write(dev->id, 0, dir, sec >> shift, len >> shift,
-				page_to_phys(bvec.bv_page) + bvec.bv_offset);
+				bvec_phys(&bvec));
 		sec += len;
 	}
 	bio_endio(bio);
@@ -98,6 +98,7 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
 {
 	struct queue_limits lim = {
 		.logical_block_size	= bsize,
+		.features		= BLK_FEAT_ROTATIONAL,
 	};
 	struct nfhd_device *dev;
 	int dev_id = id - NFHD_DEV_OFFSET;

arch/um/drivers/ubd_kern.c

@@ -447,43 +447,31 @@ static int bulk_req_safe_read(
 	return n;
 }
 
-/* Called without dev->lock held, and only in interrupt context. */
+static void ubd_end_request(struct io_thread_req *io_req)
-static void ubd_handler(void)
 {
-	int n;
+	if (io_req->error == BLK_STS_NOTSUPP) {
-	int count;
+		if (req_op(io_req->req) == REQ_OP_DISCARD)
-
+			blk_queue_disable_discard(io_req->req->q);
-	while(1){
+		else if (req_op(io_req->req) == REQ_OP_WRITE_ZEROES)
-		n = bulk_req_safe_read(
+			blk_queue_disable_write_zeroes(io_req->req->q);
-			thread_fd,
-			irq_req_buffer,
-			&irq_remainder,
-			&irq_remainder_size,
-			UBD_REQ_BUFFER_SIZE
-		);
-		if (n < 0) {
-			if(n == -EAGAIN)
-				break;
-			printk(KERN_ERR "spurious interrupt in ubd_handler, "
-			       "err = %d\n", -n);
-			return;
-		}
-		for (count = 0; count < n/sizeof(struct io_thread_req *); count++) {
-			struct io_thread_req *io_req = (*irq_req_buffer)[count];
-
-			if ((io_req->error == BLK_STS_NOTSUPP) && (req_op(io_req->req) == REQ_OP_DISCARD)) {
-				blk_queue_max_discard_sectors(io_req->req->q, 0);
-				blk_queue_max_write_zeroes_sectors(io_req->req->q, 0);
-			}
-			blk_mq_end_request(io_req->req, io_req->error);
-			kfree(io_req);
-		}
 	}
+	blk_mq_end_request(io_req->req, io_req->error);
+	kfree(io_req);
 }
 
 static irqreturn_t ubd_intr(int irq, void *dev)
 {
-	ubd_handler();
+	int len, i;
+
+	while ((len = bulk_req_safe_read(thread_fd, irq_req_buffer,
+			&irq_remainder, &irq_remainder_size,
+			UBD_REQ_BUFFER_SIZE)) >= 0) {
+		for (i = 0; i < len / sizeof(struct io_thread_req *); i++)
+			ubd_end_request((*irq_req_buffer)[i]);
+	}
+
+	if (len < 0 && len != -EAGAIN)
+		pr_err("spurious interrupt in %s, err = %d\n", __func__, len);
 	return IRQ_HANDLED;
 }
 
@@ -847,6 +835,7 @@ static int ubd_add(int n, char **error_out)
 	struct queue_limits lim = {
 		.max_segments		= MAX_SG,
 		.seg_boundary_mask	= PAGE_SIZE - 1,
+		.features		= BLK_FEAT_WRITE_CACHE,
 	};
 	struct gendisk *disk;
 	int err = 0;
@@ -893,8 +882,6 @@ static int ubd_add(int n, char **error_out)
 		goto out_cleanup_tags;
 	}
 
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
-	blk_queue_write_cache(disk->queue, true, false);
 	disk->major = UBD_MAJOR;
 	disk->first_minor = n << UBD_SHIFT;
 	disk->minors = 1 << UBD_SHIFT;

arch/xtensa/platforms/iss/simdisk.c

@@ -263,6 +263,9 @@ static const struct proc_ops simdisk_proc_ops = {
 static int __init simdisk_setup(struct simdisk *dev, int which,
 		struct proc_dir_entry *procdir)
 {
+	struct queue_limits lim = {
+		.features		= BLK_FEAT_ROTATIONAL,
+	};
 	char tmp[2] = { '0' + which, 0 };
 	int err;
 
@@ -271,7 +274,7 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
 	spin_lock_init(&dev->lock);
 	dev->users = 0;
 
-	dev->gd = blk_alloc_disk(NULL, NUMA_NO_NODE);
+	dev->gd = blk_alloc_disk(&lim, NUMA_NO_NODE);
 	if (IS_ERR(dev->gd)) {
 		err = PTR_ERR(dev->gd);
 		goto out;

block/Kconfig

@@ -62,6 +62,8 @@ config BLK_DEV_BSGLIB
 
 config BLK_DEV_INTEGRITY
 	bool "Block layer data integrity support"
+	select CRC_T10DIF
+	select CRC64_ROCKSOFT
 	help
 	Some storage devices allow extra information to be
 	stored/retrieved to help protect the data.  The block layer
@@ -72,12 +74,6 @@ config BLK_DEV_INTEGRITY
 	T10/SCSI Data Integrity Field or the T13/ATA External Path
 	Protection.  If in doubt, say N.
 
-config BLK_DEV_INTEGRITY_T10
-	tristate
-	depends on BLK_DEV_INTEGRITY
-	select CRC_T10DIF
-	select CRC64_ROCKSOFT
-
 config BLK_DEV_WRITE_MOUNTED
 	bool "Allow writing to mounted block devices"
 	default y

block/Makefile

@@ -26,8 +26,7 @@ obj-$(CONFIG_MQ_IOSCHED_KYBER)	+= kyber-iosched.o
 bfq-y				:= bfq-iosched.o bfq-wf2q.o bfq-cgroup.o
 obj-$(CONFIG_IOSCHED_BFQ)	+= bfq.o
 
-obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o
+obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
-obj-$(CONFIG_BLK_DEV_INTEGRITY_T10)	+= t10-pi.o
 obj-$(CONFIG_BLK_MQ_PCI)	+= blk-mq-pci.o
 obj-$(CONFIG_BLK_MQ_VIRTIO)	+= blk-mq-virtio.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o

block/bdev.c

@@ -385,7 +385,7 @@ static struct file_system_type bd_type = {
 };
 
 struct super_block *blockdev_superblock __ro_after_init;
-struct vfsmount *blockdev_mnt __ro_after_init;
+static struct vfsmount *blockdev_mnt __ro_after_init;
 EXPORT_SYMBOL_GPL(blockdev_superblock);
 
 void __init bdev_cache_init(void)
@@ -1260,23 +1260,42 @@ void sync_bdevs(bool wait)
 }
 
 /*
- * Handle STATX_DIOALIGN for block devices.
+ * Handle STATX_{DIOALIGN, WRITE_ATOMIC} for block devices.
- *
- * Note that the inode passed to this is the inode of a block device node file,
- * not the block device's internal inode.  Therefore it is *not* valid to use
- * I_BDEV() here; the block device has to be looked up by i_rdev instead.
  */
-void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
+void bdev_statx(struct path *path, struct kstat *stat,
+		u32 request_mask)
 {
+	struct inode *backing_inode;
 	struct block_device *bdev;
 
-	bdev = blkdev_get_no_open(inode->i_rdev);
+	if (!(request_mask & (STATX_DIOALIGN | STATX_WRITE_ATOMIC)))
+		return;
+
+	backing_inode = d_backing_inode(path->dentry);
+
+	/*
+	 * Note that backing_inode is the inode of a block device node file,
+	 * not the block device's internal inode.  Therefore it is *not* valid
+	 * to use I_BDEV() here; the block device has to be looked up by i_rdev
+	 * instead.
+	 */
+	bdev = blkdev_get_no_open(backing_inode->i_rdev);
 	if (!bdev)
 		return;
 
-	stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
+	if (request_mask & STATX_DIOALIGN) {
-	stat->dio_offset_align = bdev_logical_block_size(bdev);
+		stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
-	stat->result_mask |= STATX_DIOALIGN;
+		stat->dio_offset_align = bdev_logical_block_size(bdev);
+		stat->result_mask |= STATX_DIOALIGN;
+	}
+
+	if (request_mask & STATX_WRITE_ATOMIC && bdev_can_atomic_write(bdev)) {
+		struct request_queue *bd_queue = bdev->bd_queue;
+
+		generic_fill_statx_atomic_writes(stat,
+			queue_atomic_write_unit_min_bytes(bd_queue),
+			queue_atomic_write_unit_max_bytes(bd_queue));
+	}
 
 	blkdev_put_no_open(bdev);
 }

block/bfq-cgroup.c

@@ -797,57 +797,6 @@ void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
 	 */
 	bfq_link_bfqg(bfqd, bfqg);
 	__bfq_bic_change_cgroup(bfqd, bic, bfqg);
-	/*
-	 * Update blkg_path for bfq_log_* functions. We cache this
-	 * path, and update it here, for the following
-	 * reasons. Operations on blkg objects in blk-cgroup are
-	 * protected with the request_queue lock, and not with the
-	 * lock that protects the instances of this scheduler
-	 * (bfqd->lock). This exposes BFQ to the following sort of
-	 * race.
-	 *
-	 * The blkg_lookup performed in bfq_get_queue, protected
-	 * through rcu, may happen to return the address of a copy of
-	 * the original blkg. If this is the case, then the
-	 * bfqg_and_blkg_get performed in bfq_get_queue, to pin down
-	 * the blkg, is useless: it does not prevent blk-cgroup code
-	 * from destroying both the original blkg and all objects
-	 * directly or indirectly referred by the copy of the
-	 * blkg.
-	 *
-	 * On the bright side, destroy operations on a blkg invoke, as
-	 * a first step, hooks of the scheduler associated with the
-	 * blkg. And these hooks are executed with bfqd->lock held for
-	 * BFQ. As a consequence, for any blkg associated with the
-	 * request queue this instance of the scheduler is attached
-	 * to, we are guaranteed that such a blkg is not destroyed, and
-	 * that all the pointers it contains are consistent, while we
-	 * are holding bfqd->lock. A blkg_lookup performed with
-	 * bfqd->lock held then returns a fully consistent blkg, which
-	 * remains consistent until this lock is held.
-	 *
-	 * Thanks to the last fact, and to the fact that: (1) bfqg has
-	 * been obtained through a blkg_lookup in the above
-	 * assignment, and (2) bfqd->lock is being held, here we can
-	 * safely use the policy data for the involved blkg (i.e., the
-	 * field bfqg->pd) to get to the blkg associated with bfqg,
-	 * and then we can safely use any field of blkg. After we
-	 * release bfqd->lock, even just getting blkg through this
-	 * bfqg may cause dangling references to be traversed, as
-	 * bfqg->pd may not exist any more.
-	 *
-	 * In view of the above facts, here we cache, in the bfqg, any
-	 * blkg data we may need for this bic, and for its associated
-	 * bfq_queue. As of now, we need to cache only the path of the
-	 * blkg, which is used in the bfq_log_* functions.
-	 *
-	 * Finally, note that bfqg itself needs to be protected from
-	 * destruction on the blkg_free of the original blkg (which
-	 * invokes bfq_pd_free). We use an additional private
-	 * refcounter for bfqg, to let it disappear only after no
-	 * bfq_queue refers to it any longer.
-	 */
-	blkg_path(bfqg_to_blkg(bfqg), bfqg->blkg_path, sizeof(bfqg->blkg_path));
 	bic->blkcg_serial_nr = serial_nr;
 }
 

block/bfq-iosched.c

@@ -5463,29 +5463,10 @@ static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync,
 	}
 }
 
-static void bfq_exit_icq(struct io_cq *icq)
+static void _bfq_exit_icq(struct bfq_io_cq *bic, unsigned int num_actuators)
 {
-	struct bfq_io_cq *bic = icq_to_bic(icq);
-	struct bfq_data *bfqd = bic_to_bfqd(bic);
-	unsigned long flags;
-	unsigned int act_idx;
-	/*
-	 * If bfqd and thus bfqd->num_actuators is not available any
-	 * longer, then cycle over all possible per-actuator bfqqs in
-	 * next loop. We rely on bic being zeroed on creation, and
-	 * therefore on its unused per-actuator fields being NULL.
-	 */
-	unsigned int num_actuators = BFQ_MAX_ACTUATORS;
 	struct bfq_iocq_bfqq_data *bfqq_data = bic->bfqq_data;
-
+	unsigned int act_idx;
-	/*
-	 * bfqd is NULL if scheduler already exited, and in that case
-	 * this is the last time these queues are accessed.
-	 */
-	if (bfqd) {
-		spin_lock_irqsave(&bfqd->lock, flags);
-		num_actuators = bfqd->num_actuators;
-	}
 
 	for (act_idx = 0; act_idx < num_actuators; act_idx++) {
 		if (bfqq_data[act_idx].stable_merge_bfqq)
@@ -5494,9 +5475,30 @@ static void bfq_exit_icq(struct io_cq *icq)
 		bfq_exit_icq_bfqq(bic, true, act_idx);
 		bfq_exit_icq_bfqq(bic, false, act_idx);
 	}
+}
 
-	if (bfqd)
+static void bfq_exit_icq(struct io_cq *icq)
+{
+	struct bfq_io_cq *bic = icq_to_bic(icq);
+	struct bfq_data *bfqd = bic_to_bfqd(bic);
+	unsigned long flags;
+
+	/*
+	 * If bfqd and thus bfqd->num_actuators is not available any
+	 * longer, then cycle over all possible per-actuator bfqqs in
+	 * next loop. We rely on bic being zeroed on creation, and
+	 * therefore on its unused per-actuator fields being NULL.
+	 *
+	 * bfqd is NULL if scheduler already exited, and in that case
+	 * this is the last time these queues are accessed.
+	 */
+	if (bfqd) {
+		spin_lock_irqsave(&bfqd->lock, flags);
+		_bfq_exit_icq(bic, bfqd->num_actuators);
 		spin_unlock_irqrestore(&bfqd->lock, flags);
+	} else {
+		_bfq_exit_icq(bic, BFQ_MAX_ACTUATORS);
+	}
 }
 
 /*

block/bfq-iosched.h

@@ -1003,9 +1003,6 @@ struct bfq_group {
 	/* must be the first member */
 	struct blkg_policy_data pd;
 
-	/* cached path for this blkg (see comments in bfq_bic_update_cgroup) */
-	char blkg_path[128];
-
 	/* reference counter (see comments in bfq_bic_update_cgroup) */
 	refcount_t ref;
 

block/bio-integrity.c

@@ -76,7 +76,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 					  &bip->bip_max_vcnt, gfp_mask);
 		if (!bip->bip_vec)
 			goto err;
-	} else {
+	} else if (nr_vecs) {
 		bip->bip_vec = bip->bip_inline_vecs;
 	}
 
@@ -276,6 +276,7 @@ static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec,
 
 	bip->bip_flags |= BIP_INTEGRITY_USER | BIP_COPY_USER;
 	bip->bip_iter.bi_sector = seed;
+	bip->bip_vcnt = nr_vecs;
 	return 0;
 free_bip:
 	bio_integrity_free(bio);
@@ -297,6 +298,7 @@ static int bio_integrity_init_user(struct bio *bio, struct bio_vec *bvec,
 	bip->bip_flags |= BIP_INTEGRITY_USER;
 	bip->bip_iter.bi_sector = seed;
 	bip->bip_iter.bi_size = len;
+	bip->bip_vcnt = nr_vecs;
 	return 0;
 }
 
@@ -334,7 +336,7 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes,
 			   u32 seed)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	unsigned int align = q->dma_pad_mask | queue_dma_alignment(q);
+	unsigned int align = blk_lim_dma_alignment_and_pad(&q->limits);
 	struct page *stack_pages[UIO_FASTIOV], **pages = stack_pages;
 	struct bio_vec stack_vec[UIO_FASTIOV], *bvec = stack_vec;
 	unsigned int direction, nr_bvecs;
@@ -396,44 +398,6 @@ free_bvec:
 }
 EXPORT_SYMBOL_GPL(bio_integrity_map_user);
 
-/**
- * bio_integrity_process - Process integrity metadata for a bio
- * @bio:	bio to generate/verify integrity metadata for
- * @proc_iter:  iterator to process
- * @proc_fn:	Pointer to the relevant processing function
- */
-static blk_status_t bio_integrity_process(struct bio *bio,
-		struct bvec_iter *proc_iter, integrity_processing_fn *proc_fn)
-{
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
-	struct blk_integrity_iter iter;
-	struct bvec_iter bviter;
-	struct bio_vec bv;
-	struct bio_integrity_payload *bip = bio_integrity(bio);
-	blk_status_t ret = BLK_STS_OK;
-
-	iter.disk_name = bio->bi_bdev->bd_disk->disk_name;
-	iter.interval = 1 << bi->interval_exp;
-	iter.tuple_size = bi->tuple_size;
-	iter.seed = proc_iter->bi_sector;
-	iter.prot_buf = bvec_virt(bip->bip_vec);
-	iter.pi_offset = bi->pi_offset;
-
-	__bio_for_each_segment(bv, bio, bviter, *proc_iter) {
-		void *kaddr = bvec_kmap_local(&bv);
-
-		iter.data_buf = kaddr;
-		iter.data_size = bv.bv_len;
-		ret = proc_fn(&iter);
-		kunmap_local(kaddr);
-
-		if (ret)
-			break;
-
-	}
-	return ret;
-}
-
 /**
  * bio_integrity_prep - Prepare bio for integrity I/O
  * @bio:	bio to prepare
@@ -450,17 +414,13 @@ bool bio_integrity_prep(struct bio *bio)
 {
 	struct bio_integrity_payload *bip;
 	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
+	unsigned int len;
 	void *buf;
-	unsigned long start, end;
+	gfp_t gfp = GFP_NOIO;
-	unsigned int len, nr_pages;
-	unsigned int bytes, offset, i;
 
 	if (!bi)
 		return true;
 
-	if (bio_op(bio) != REQ_OP_READ && bio_op(bio) != REQ_OP_WRITE)
-		return true;
-
 	if (!bio_sectors(bio))
 		return true;
 
@@ -468,32 +428,36 @@ bool bio_integrity_prep(struct bio *bio)
 	if (bio_integrity(bio))
 		return true;
 
-	if (bio_data_dir(bio) == READ) {
+	switch (bio_op(bio)) {
-		if (!bi->profile->verify_fn ||
+	case REQ_OP_READ:
-		    !(bi->flags & BLK_INTEGRITY_VERIFY))
+		if (bi->flags & BLK_INTEGRITY_NOVERIFY)
 			return true;
-	} else {
+		break;
-		if (!bi->profile->generate_fn ||
+	case REQ_OP_WRITE:
-		    !(bi->flags & BLK_INTEGRITY_GENERATE))
+		if (bi->flags & BLK_INTEGRITY_NOGENERATE)
 			return true;
+
+		/*
+		 * Zero the memory allocated to not leak uninitialized kernel
+		 * memory to disk for non-integrity metadata where nothing else
+		 * initializes the memory.
+		 */
+		if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE)
+			gfp |= __GFP_ZERO;
+		break;
+	default:
+		return true;
 	}
 
 	/* Allocate kernel buffer for protection data */
 	len = bio_integrity_bytes(bi, bio_sectors(bio));
-	buf = kmalloc(len, GFP_NOIO);
+	buf = kmalloc(len, gfp);
 	if (unlikely(buf == NULL)) {
-		printk(KERN_ERR "could not allocate integrity buffer\n");
 		goto err_end_io;
 	}
 
-	end = (((unsigned long) buf) + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	bip = bio_integrity_alloc(bio, GFP_NOIO, 1);
-	start = ((unsigned long) buf) >> PAGE_SHIFT;
-	nr_pages = end - start;
-
-	/* Allocate bio integrity payload and integrity vectors */
-	bip = bio_integrity_alloc(bio, GFP_NOIO, nr_pages);
 	if (IS_ERR(bip)) {
-		printk(KERN_ERR "could not allocate data integrity bioset\n");
 		kfree(buf);
 		goto err_end_io;
 	}
@@ -501,35 +465,20 @@ bool bio_integrity_prep(struct bio *bio)
 	bip->bip_flags |= BIP_BLOCK_INTEGRITY;
 	bip_set_seed(bip, bio->bi_iter.bi_sector);
 
-	if (bi->flags & BLK_INTEGRITY_IP_CHECKSUM)
+	if (bi->csum_type == BLK_INTEGRITY_CSUM_IP)
 		bip->bip_flags |= BIP_IP_CHECKSUM;
 
-	/* Map it */
+	if (bio_integrity_add_page(bio, virt_to_page(buf), len,
-	offset = offset_in_page(buf);
+			offset_in_page(buf)) < len) {
-	for (i = 0; i < nr_pages && len > 0; i++) {
+		printk(KERN_ERR "could not attach integrity payload\n");
-		bytes = PAGE_SIZE - offset;
+		goto err_end_io;
-
-		if (bytes > len)
-			bytes = len;
-
-		if (bio_integrity_add_page(bio, virt_to_page(buf),
-					   bytes, offset) < bytes) {
-			printk(KERN_ERR "could not attach integrity payload\n");
-			goto err_end_io;
-		}
-
-		buf += bytes;
-		len -= bytes;
-		offset = 0;
 	}
 
 	/* Auto-generate integrity metadata if this is a write */
-	if (bio_data_dir(bio) == WRITE) {
+	if (bio_data_dir(bio) == WRITE)
-		bio_integrity_process(bio, &bio->bi_iter,
+		blk_integrity_generate(bio);
-				      bi->profile->generate_fn);
+	else
-	} else {
 		bip->bio_iter = bio->bi_iter;
-	}
 	return true;
 
 err_end_io:
@@ -552,15 +501,8 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 	struct bio_integrity_payload *bip =
 		container_of(work, struct bio_integrity_payload, bip_work);
 	struct bio *bio = bip->bip_bio;
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 
-	/*
+	blk_integrity_verify(bio);
-	 * At the moment verify is called bio's iterator was advanced
-	 * during split and completion, we need to rewind iterator to
-	 * it's original position.
-	 */
-	bio->bi_status = bio_integrity_process(bio, &bip->bio_iter,
-						bi->profile->verify_fn);
 	bio_integrity_free(bio);
 	bio_endio(bio);
 }
@@ -582,7 +524,7 @@ bool __bio_integrity_endio(struct bio *bio)
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 
 	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status &&
-	    (bip->bip_flags & BIP_BLOCK_INTEGRITY) && bi->profile->verify_fn) {
+	    (bip->bip_flags & BIP_BLOCK_INTEGRITY) && bi->csum_type) {
 		INIT_WORK(&bip->bip_work, bio_integrity_verify_fn);
 		queue_work(kintegrityd_wq, &bip->bip_work);
 		return false;
@@ -642,14 +584,11 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 
 	BUG_ON(bip_src == NULL);
 
-	bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt);
+	bip = bio_integrity_alloc(bio, gfp_mask, 0);
 	if (IS_ERR(bip))
 		return PTR_ERR(bip);
 
-	memcpy(bip->bip_vec, bip_src->bip_vec,
+	bip->bip_vec = bip_src->bip_vec;
-	       bip_src->bip_vcnt * sizeof(struct bio_vec));
-
-	bip->bip_vcnt = bip_src->bip_vcnt;
 	bip->bip_iter = bip_src->bip_iter;
 	bip->bip_flags = bip_src->bip_flags & ~BIP_BLOCK_INTEGRITY;
 

block/bio.c

@@ -953,7 +953,7 @@ bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv,
 		bool *same_page)
 {
 	unsigned long mask = queue_segment_boundary(q);
-	phys_addr_t addr1 = page_to_phys(bv->bv_page) + bv->bv_offset;
+	phys_addr_t addr1 = bvec_phys(bv);
 	phys_addr_t addr2 = page_to_phys(page) + offset + len - 1;
 
 	if ((addr1 | mask) != (addr2 | mask))

block/blk-cgroup.h

@@ -300,19 +300,6 @@ static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd)
 	return cpd ? cpd->blkcg : NULL;
 }
 
-/**
- * blkg_path - format cgroup path of blkg
- * @blkg: blkg of interest
- * @buf: target buffer
- * @buflen: target buffer length
- *
- * Format the path of the cgroup of @blkg into @buf.
- */
-static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
-{
-	return cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
-}
-
 /**
  * blkg_get - get a blkg reference
  * @blkg: blkg to get

block/blk-core.c

@@ -94,20 +94,6 @@ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_queue_flag_clear);
 
-/**
- * blk_queue_flag_test_and_set - atomically test and set a queue flag
- * @flag: flag to be set
- * @q: request queue
- *
- * Returns the previous value of @flag - 0 if the flag was not set and 1 if
- * the flag was already set.
- */
-bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q)
-{
-	return test_and_set_bit(flag, &q->queue_flags);
-}
-EXPORT_SYMBOL_GPL(blk_queue_flag_test_and_set);
-
 #define REQ_OP_NAME(name) [REQ_OP_##name] = #name
 static const char *const blk_op_name[] = {
 	REQ_OP_NAME(READ),
@@ -174,6 +160,8 @@ static const struct {
 	/* Command duration limit device-side timeout */
 	[BLK_STS_DURATION_LIMIT]	= { -ETIME, "duration limit exceeded" },
 
+	[BLK_STS_INVAL]		= { -EINVAL,	"invalid" },
+
 	/* everything else not covered above: */
 	[BLK_STS_IOERR]		= { -EIO,	"I/O" },
 };
@@ -739,6 +727,18 @@ void submit_bio_noacct_nocheck(struct bio *bio)
 		__submit_bio_noacct(bio);
 }
 
+static blk_status_t blk_validate_atomic_write_op_size(struct request_queue *q,
+						 struct bio *bio)
+{
+	if (bio->bi_iter.bi_size > queue_atomic_write_unit_max_bytes(q))
+		return BLK_STS_INVAL;
+
+	if (bio->bi_iter.bi_size % queue_atomic_write_unit_min_bytes(q))
+		return BLK_STS_INVAL;
+
+	return BLK_STS_OK;
+}
+
 /**
  * submit_bio_noacct - re-submit a bio to the block device layer for I/O
  * @bio:  The bio describing the location in memory and on the device.
@@ -782,7 +782,7 @@ void submit_bio_noacct(struct bio *bio)
 		if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_WRITE &&
 				 bio_op(bio) != REQ_OP_ZONE_APPEND))
 			goto end_io;
-		if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
+		if (!bdev_write_cache(bdev)) {
 			bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
 			if (!bio_sectors(bio)) {
 				status = BLK_STS_OK;
@@ -791,12 +791,17 @@ void submit_bio_noacct(struct bio *bio)
 		}
 	}
 
-	if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+	if (!(q->limits.features & BLK_FEAT_POLL))
 		bio_clear_polled(bio);
 
 	switch (bio_op(bio)) {
 	case REQ_OP_READ:
 	case REQ_OP_WRITE:
+		if (bio->bi_opf & REQ_ATOMIC) {
+			status = blk_validate_atomic_write_op_size(q, bio);
+			if (status != BLK_STS_OK)
+				goto end_io;
+		}
 		break;
 	case REQ_OP_FLUSH:
 		/*
@@ -825,11 +830,8 @@ void submit_bio_noacct(struct bio *bio)
 	case REQ_OP_ZONE_OPEN:
 	case REQ_OP_ZONE_CLOSE:
 	case REQ_OP_ZONE_FINISH:
-		if (!bdev_is_zoned(bio->bi_bdev))
-			goto not_supported;
-		break;
 	case REQ_OP_ZONE_RESET_ALL:
-		if (!bdev_is_zoned(bio->bi_bdev) || !blk_queue_zone_resetall(q))
+		if (!bdev_is_zoned(bio->bi_bdev))
 			goto not_supported;
 		break;
 	case REQ_OP_DRV_IN:
@@ -915,8 +917,7 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
 		return 0;
 
 	q = bdev_get_queue(bdev);
-	if (cookie == BLK_QC_T_NONE ||
+	if (cookie == BLK_QC_T_NONE || !(q->limits.features & BLK_FEAT_POLL))
-	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
 		return 0;
 
 	blk_flush_plug(current->plug, false);

block/blk-flush.c

@@ -100,23 +100,6 @@ blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx)
 	return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx)->fq;
 }
 
-static unsigned int blk_flush_policy(unsigned long fflags, struct request *rq)
-{
-	unsigned int policy = 0;
-
-	if (blk_rq_sectors(rq))
-		policy |= REQ_FSEQ_DATA;
-
-	if (fflags & (1UL << QUEUE_FLAG_WC)) {
-		if (rq->cmd_flags & REQ_PREFLUSH)
-			policy |= REQ_FSEQ_PREFLUSH;
-		if (!(fflags & (1UL << QUEUE_FLAG_FUA)) &&
-		    (rq->cmd_flags & REQ_FUA))
-			policy |= REQ_FSEQ_POSTFLUSH;
-	}
-	return policy;
-}
-
 static unsigned int blk_flush_cur_seq(struct request *rq)
 {
 	return 1 << ffz(rq->flush.seq);
@@ -399,19 +382,32 @@ static void blk_rq_init_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);
+	bool supports_fua = q->limits.features & BLK_FEAT_FUA;
+	unsigned int policy = 0;
 
 	/* FLUSH/FUA request must never be merged */
 	WARN_ON_ONCE(rq->bio != rq->biotail);
 
+	if (blk_rq_sectors(rq))
+		policy |= REQ_FSEQ_DATA;
+
+	/*
+	 * Check which flushes we need to sequence for this operation.
+	 */
+	if (blk_queue_write_cache(q)) {
+		if (rq->cmd_flags & REQ_PREFLUSH)
+			policy |= REQ_FSEQ_PREFLUSH;
+		if ((rq->cmd_flags & REQ_FUA) && !supports_fua)
+			policy |= REQ_FSEQ_POSTFLUSH;
+	}
+
 	/*
 	 * @policy now records what operations need to be done.  Adjust
 	 * REQ_PREFLUSH and FUA for the driver.
 	 */
 	rq->cmd_flags &= ~REQ_PREFLUSH;
-	if (!(fflags & (1UL << QUEUE_FLAG_FUA)))
+	if (!supports_fua)
 		rq->cmd_flags &= ~REQ_FUA;
 
 	/*

block/blk-integrity.c

@@ -107,60 +107,6 @@ new_segment:
 }
 EXPORT_SYMBOL(blk_rq_map_integrity_sg);
 
-/**
- * blk_integrity_compare - Compare integrity profile of two disks
- * @gd1:	Disk to compare
- * @gd2:	Disk to compare
- *
- * Description: Meta-devices like DM and MD need to verify that all
- * sub-devices use the same integrity format before advertising to
- * upper layers that they can send/receive integrity metadata.  This
- * function can be used to check whether two gendisk devices have
- * compatible integrity formats.
- */
-int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2)
-{
-	struct blk_integrity *b1 = &gd1->queue->integrity;
-	struct blk_integrity *b2 = &gd2->queue->integrity;
-
-	if (!b1->profile && !b2->profile)
-		return 0;
-
-	if (!b1->profile || !b2->profile)
-		return -1;
-
-	if (b1->interval_exp != b2->interval_exp) {
-		pr_err("%s: %s/%s protection interval %u != %u\n",
-		       __func__, gd1->disk_name, gd2->disk_name,
-		       1 << b1->interval_exp, 1 << b2->interval_exp);
-		return -1;
-	}
-
-	if (b1->tuple_size != b2->tuple_size) {
-		pr_err("%s: %s/%s tuple sz %u != %u\n", __func__,
-		       gd1->disk_name, gd2->disk_name,
-		       b1->tuple_size, b2->tuple_size);
-		return -1;
-	}
-
-	if (b1->tag_size && b2->tag_size && (b1->tag_size != b2->tag_size)) {
-		pr_err("%s: %s/%s tag sz %u != %u\n", __func__,
-		       gd1->disk_name, gd2->disk_name,
-		       b1->tag_size, b2->tag_size);
-		return -1;
-	}
-
-	if (b1->profile != b2->profile) {
-		pr_err("%s: %s/%s type %s != %s\n", __func__,
-		       gd1->disk_name, gd2->disk_name,
-		       b1->profile->name, b2->profile->name);
-		return -1;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(blk_integrity_compare);
-
 bool blk_integrity_merge_rq(struct request_queue *q, struct request *req,
 			    struct request *next)
 {
@@ -214,7 +160,64 @@ bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
 
 static inline struct blk_integrity *dev_to_bi(struct device *dev)
 {
-	return &dev_to_disk(dev)->queue->integrity;
+	return &dev_to_disk(dev)->queue->limits.integrity;
+}
+
+const char *blk_integrity_profile_name(struct blk_integrity *bi)
+{
+	switch (bi->csum_type) {
+	case BLK_INTEGRITY_CSUM_IP:
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
+			return "T10-DIF-TYPE1-IP";
+		return "T10-DIF-TYPE3-IP";
+	case BLK_INTEGRITY_CSUM_CRC:
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
+			return "T10-DIF-TYPE1-CRC";
+		return "T10-DIF-TYPE3-CRC";
+	case BLK_INTEGRITY_CSUM_CRC64:
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
+			return "EXT-DIF-TYPE1-CRC64";
+		return "EXT-DIF-TYPE3-CRC64";
+	case BLK_INTEGRITY_CSUM_NONE:
+		break;
+	}
+
+	return "nop";
+}
+EXPORT_SYMBOL_GPL(blk_integrity_profile_name);
+
+static ssize_t flag_store(struct device *dev, const char *page, size_t count,
+		unsigned char flag)
+{
+	struct request_queue *q = dev_to_disk(dev)->queue;
+	struct queue_limits lim;
+	unsigned long val;
+	int err;
+
+	err = kstrtoul(page, 10, &val);
+	if (err)
+		return err;
+
+	/* note that the flags are inverted vs the values in the sysfs files */
+	lim = queue_limits_start_update(q);
+	if (val)
+		lim.integrity.flags &= ~flag;
+	else
+		lim.integrity.flags |= flag;
+
+	blk_mq_freeze_queue(q);
+	err = queue_limits_commit_update(q, &lim);
+	blk_mq_unfreeze_queue(q);
+	if (err)
+		return err;
+	return count;
+}
+
+static ssize_t flag_show(struct device *dev, char *page, unsigned char flag)
+{
+	struct blk_integrity *bi = dev_to_bi(dev);
+
+	return sysfs_emit(page, "%d\n", !(bi->flags & flag));
 }
 
 static ssize_t format_show(struct device *dev, struct device_attribute *attr,
@@ -222,9 +225,9 @@ static ssize_t format_show(struct device *dev, struct device_attribute *attr,
 {
 	struct blk_integrity *bi = dev_to_bi(dev);
 
-	if (bi->profile && bi->profile->name)
+	if (!bi->tuple_size)
-		return sysfs_emit(page, "%s\n", bi->profile->name);
+		return sysfs_emit(page, "none\n");
-	return sysfs_emit(page, "none\n");
+	return sysfs_emit(page, "%s\n", blk_integrity_profile_name(bi));
 }
 
 static ssize_t tag_size_show(struct device *dev, struct device_attribute *attr,
@@ -249,49 +252,26 @@ static ssize_t read_verify_store(struct device *dev,
 				 struct device_attribute *attr,
 				 const char *page, size_t count)
 {
-	struct blk_integrity *bi = dev_to_bi(dev);
+	return flag_store(dev, page, count, BLK_INTEGRITY_NOVERIFY);
-	char *p = (char *) page;
-	unsigned long val = simple_strtoul(p, &p, 10);
-
-	if (val)
-		bi->flags |= BLK_INTEGRITY_VERIFY;
-	else
-		bi->flags &= ~BLK_INTEGRITY_VERIFY;
-
-	return count;
 }
 
 static ssize_t read_verify_show(struct device *dev,
 				struct device_attribute *attr, char *page)
 {
-	struct blk_integrity *bi = dev_to_bi(dev);
+	return flag_show(dev, page, BLK_INTEGRITY_NOVERIFY);
-
-	return sysfs_emit(page, "%d\n", !!(bi->flags & BLK_INTEGRITY_VERIFY));
 }
 
 static ssize_t write_generate_store(struct device *dev,
 				    struct device_attribute *attr,
 				    const char *page, size_t count)
 {
-	struct blk_integrity *bi = dev_to_bi(dev);
+	return flag_store(dev, page, count, BLK_INTEGRITY_NOGENERATE);
-
-	char *p = (char *) page;
-	unsigned long val = simple_strtoul(p, &p, 10);
-
-	if (val)
-		bi->flags |= BLK_INTEGRITY_GENERATE;
-	else
-		bi->flags &= ~BLK_INTEGRITY_GENERATE;
-
-	return count;
 }
 
 static ssize_t write_generate_show(struct device *dev,
 				   struct device_attribute *attr, char *page)
 {
-	struct blk_integrity *bi = dev_to_bi(dev);
+	return flag_show(dev, page, BLK_INTEGRITY_NOGENERATE);
-
-	return sysfs_emit(page, "%d\n", !!(bi->flags & BLK_INTEGRITY_GENERATE));
 }
 
 static ssize_t device_is_integrity_capable_show(struct device *dev,
@@ -325,81 +305,3 @@ const struct attribute_group blk_integrity_attr_group = {
 	.name = "integrity",
 	.attrs = integrity_attrs,
 };
-
-static blk_status_t blk_integrity_nop_fn(struct blk_integrity_iter *iter)
-{
-	return BLK_STS_OK;
-}
-
-static void blk_integrity_nop_prepare(struct request *rq)
-{
-}
-
-static void blk_integrity_nop_complete(struct request *rq,
-		unsigned int nr_bytes)
-{
-}
-
-static const struct blk_integrity_profile nop_profile = {
-	.name = "nop",
-	.generate_fn = blk_integrity_nop_fn,
-	.verify_fn = blk_integrity_nop_fn,
-	.prepare_fn = blk_integrity_nop_prepare,
-	.complete_fn = blk_integrity_nop_complete,
-};
-
-/**
- * blk_integrity_register - Register a gendisk as being integrity-capable
- * @disk:	struct gendisk pointer to make integrity-aware
- * @template:	block integrity profile to register
- *
- * Description: When a device needs to advertise itself as being able to
- * send/receive integrity metadata it must use this function to register
- * the capability with the block layer. The template is a blk_integrity
- * struct with values appropriate for the underlying hardware. See
- * Documentation/block/data-integrity.rst.
- */
-void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
-{
-	struct blk_integrity *bi = &disk->queue->integrity;
-
-	bi->flags = BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE |
-		template->flags;
-	bi->interval_exp = template->interval_exp ? :
-		ilog2(queue_logical_block_size(disk->queue));
-	bi->profile = template->profile ? template->profile : &nop_profile;
-	bi->tuple_size = template->tuple_size;
-	bi->tag_size = template->tag_size;
-	bi->pi_offset = template->pi_offset;
-
-	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);
-
-#ifdef CONFIG_BLK_INLINE_ENCRYPTION
-	if (disk->queue->crypto_profile) {
-		pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n");
-		disk->queue->crypto_profile = NULL;
-	}
-#endif
-}
-EXPORT_SYMBOL(blk_integrity_register);
-
-/**
- * blk_integrity_unregister - Unregister block integrity profile
- * @disk:	disk whose integrity profile to unregister
- *
- * Description: This function unregisters the integrity capability from
- * a block device.
- */
-void blk_integrity_unregister(struct gendisk *disk)
-{
-	struct blk_integrity *bi = &disk->queue->integrity;
-
-	if (!bi->profile)
-		return;
-
-	/* ensure all bios are off the integrity workqueue */
-	blk_flush_integrity();
-	blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue);
-	memset(bi, 0, sizeof(*bi));
-}
-EXPORT_SYMBOL(blk_integrity_unregister);

block/blk-lib.c

@@ -103,38 +103,71 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL(blkdev_issue_discard);
 
-static int __blkdev_issue_write_zeroes(struct block_device *bdev,
+static sector_t bio_write_zeroes_limit(struct block_device *bdev)
+{
+	sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
+
+	return min(bdev_write_zeroes_sectors(bdev),
+		(UINT_MAX >> SECTOR_SHIFT) & ~bs_mask);
+}
+
+static void __blkdev_issue_write_zeroes(struct block_device *bdev,
 		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
 		struct bio **biop, unsigned flags)
 {
-	struct bio *bio = *biop;
-	unsigned int max_sectors;
-
-	if (bdev_read_only(bdev))
-		return -EPERM;
-
-	/* Ensure that max_sectors doesn't overflow bi_size */
-	max_sectors = bdev_write_zeroes_sectors(bdev);
-
-	if (max_sectors == 0)
-		return -EOPNOTSUPP;
-
 	while (nr_sects) {
-		unsigned int len = min_t(sector_t, nr_sects, max_sectors);
+		unsigned int len = min_t(sector_t, nr_sects,
+				bio_write_zeroes_limit(bdev));
+		struct bio *bio;
 
-		bio = blk_next_bio(bio, bdev, 0, REQ_OP_WRITE_ZEROES, gfp_mask);
+		if ((flags & BLKDEV_ZERO_KILLABLE) &&
+		    fatal_signal_pending(current))
+			break;
+
+		bio = bio_alloc(bdev, 0, REQ_OP_WRITE_ZEROES, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		if (flags & BLKDEV_ZERO_NOUNMAP)
 			bio->bi_opf |= REQ_NOUNMAP;
 
 		bio->bi_iter.bi_size = len << SECTOR_SHIFT;
+		*biop = bio_chain_and_submit(*biop, bio);
+
 		nr_sects -= len;
 		sector += len;
 		cond_resched();
 	}
+}
 
-	*biop = bio;
+static int blkdev_issue_write_zeroes(struct block_device *bdev, sector_t sector,
-	return 0;
+		sector_t nr_sects, gfp_t gfp, unsigned flags)
+{
+	struct bio *bio = NULL;
+	struct blk_plug plug;
+	int ret = 0;
+
+	blk_start_plug(&plug);
+	__blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp, &bio, flags);
+	if (bio) {
+		if ((flags & BLKDEV_ZERO_KILLABLE) &&
+		    fatal_signal_pending(current)) {
+			bio_await_chain(bio);
+			blk_finish_plug(&plug);
+			return -EINTR;
+		}
+		ret = submit_bio_wait(bio);
+		bio_put(bio);
+	}
+	blk_finish_plug(&plug);
+
+	/*
+	 * For some devices there is no non-destructive way to verify whether
+	 * WRITE ZEROES is actually supported.  These will clear the capability
+	 * on an I/O error, in which case we'll turn any error into
+	 * "not supported" here.
+	 */
+	if (ret && !bdev_write_zeroes_sectors(bdev))
+		return -EOPNOTSUPP;
+	return ret;
 }
 
 /*
@@ -150,35 +183,63 @@ static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects)
 	return min(pages, (sector_t)BIO_MAX_VECS);
 }
 
-static int __blkdev_issue_zero_pages(struct block_device *bdev,
+static void __blkdev_issue_zero_pages(struct block_device *bdev,
 		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
-		struct bio **biop)
+		struct bio **biop, unsigned int flags)
 {
-	struct bio *bio = *biop;
+	while (nr_sects) {
-	int bi_size = 0;
+		unsigned int nr_vecs = __blkdev_sectors_to_bio_pages(nr_sects);
-	unsigned int sz;
+		struct bio *bio;
 
-	if (bdev_read_only(bdev))
+		bio = bio_alloc(bdev, nr_vecs, REQ_OP_WRITE, gfp_mask);
-		return -EPERM;
-
-	while (nr_sects != 0) {
-		bio = blk_next_bio(bio, bdev, __blkdev_sectors_to_bio_pages(nr_sects),
-				   REQ_OP_WRITE, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 
-		while (nr_sects != 0) {
+		if ((flags & BLKDEV_ZERO_KILLABLE) &&
-			sz = min((sector_t) PAGE_SIZE, nr_sects << 9);
+		    fatal_signal_pending(current))
-			bi_size = bio_add_page(bio, ZERO_PAGE(0), sz, 0);
+			break;
-			nr_sects -= bi_size >> 9;
+
-			sector += bi_size >> 9;
+		do {
-			if (bi_size < sz)
+			unsigned int len, added;
+
+			len = min_t(sector_t,
+				PAGE_SIZE, nr_sects << SECTOR_SHIFT);
+			added = bio_add_page(bio, ZERO_PAGE(0), len, 0);
+			if (added < len)
 				break;
-		}
+			nr_sects -= added >> SECTOR_SHIFT;
+			sector += added >> SECTOR_SHIFT;
+		} while (nr_sects);
+
+		*biop = bio_chain_and_submit(*biop, bio);
 		cond_resched();
 	}
+}
 
-	*biop = bio;
+static int blkdev_issue_zero_pages(struct block_device *bdev, sector_t sector,
-	return 0;
+		sector_t nr_sects, gfp_t gfp, unsigned flags)
+{
+	struct bio *bio = NULL;
+	struct blk_plug plug;
+	int ret = 0;
+
+	if (flags & BLKDEV_ZERO_NOFALLBACK)
+		return -EOPNOTSUPP;
+
+	blk_start_plug(&plug);
+	__blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp, &bio, flags);
+	if (bio) {
+		if ((flags & BLKDEV_ZERO_KILLABLE) &&
+		    fatal_signal_pending(current)) {
+			bio_await_chain(bio);
+			blk_finish_plug(&plug);
+			return -EINTR;
+		}
+		ret = submit_bio_wait(bio);
+		bio_put(bio);
+	}
+	blk_finish_plug(&plug);
+
+	return ret;
 }
 
 /**
@@ -204,20 +265,19 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
 		unsigned flags)
 {
-	int ret;
+	if (bdev_read_only(bdev))
-	sector_t bs_mask;
+		return -EPERM;
 
-	bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
+	if (bdev_write_zeroes_sectors(bdev)) {
-	if ((sector | nr_sects) & bs_mask)
+		__blkdev_issue_write_zeroes(bdev, sector, nr_sects,
-		return -EINVAL;
+				gfp_mask, biop, flags);
-
+	} else {
-	ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask,
+		if (flags & BLKDEV_ZERO_NOFALLBACK)
-			biop, flags);
+			return -EOPNOTSUPP;
-	if (ret != -EOPNOTSUPP || (flags & BLKDEV_ZERO_NOFALLBACK))
+		__blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask,
-		return ret;
+				biop, flags);
-
+	}
-	return __blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask,
+	return 0;
-					 biop);
 }
 EXPORT_SYMBOL(__blkdev_issue_zeroout);
 
@@ -237,51 +297,21 @@ EXPORT_SYMBOL(__blkdev_issue_zeroout);
 int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, unsigned flags)
 {
-	int ret = 0;
+	int ret;
-	sector_t bs_mask;
-	struct bio *bio;
-	struct blk_plug plug;
-	bool try_write_zeroes = !!bdev_write_zeroes_sectors(bdev);
 
-	bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
+	if ((sector | nr_sects) & ((bdev_logical_block_size(bdev) >> 9) - 1))
-	if ((sector | nr_sects) & bs_mask)
 		return -EINVAL;
+	if (bdev_read_only(bdev))
+		return -EPERM;
 
-retry:
+	if (bdev_write_zeroes_sectors(bdev)) {
-	bio = NULL;
+		ret = blkdev_issue_write_zeroes(bdev, sector, nr_sects,
-	blk_start_plug(&plug);
+				gfp_mask, flags);
-	if (try_write_zeroes) {
+		if (ret != -EOPNOTSUPP)
-		ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects,
+			return ret;
-						  gfp_mask, &bio, flags);
-	} else if (!(flags & BLKDEV_ZERO_NOFALLBACK)) {
-		ret = __blkdev_issue_zero_pages(bdev, sector, nr_sects,
-						gfp_mask, &bio);
-	} else {
-		/* No zeroing offload support */
-		ret = -EOPNOTSUPP;
-	}
-	if (ret == 0 && bio) {
-		ret = submit_bio_wait(bio);
-		bio_put(bio);
-	}
-	blk_finish_plug(&plug);
-	if (ret && try_write_zeroes) {
-		if (!(flags & BLKDEV_ZERO_NOFALLBACK)) {
-			try_write_zeroes = false;
-			goto retry;
-		}
-		if (!bdev_write_zeroes_sectors(bdev)) {
-			/*
-			 * Zeroing offload support was indicated, but the
-			 * device reported ILLEGAL REQUEST (for some devices
-			 * there is no non-destructive way to verify whether
-			 * WRITE ZEROES is actually supported).
-			 */
-			ret = -EOPNOTSUPP;
-		}
 	}
 
-	return ret;
+	return blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask, flags);
 }
 EXPORT_SYMBOL(blkdev_issue_zeroout);
 

block/blk-map.c

@@ -634,7 +634,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 			const struct iov_iter *iter, gfp_t gfp_mask)
 {
 	bool copy = false, map_bvec = false;
-	unsigned long align = q->dma_pad_mask | queue_dma_alignment(q);
+	unsigned long align = blk_lim_dma_alignment_and_pad(&q->limits);
 	struct bio *bio = NULL;
 	struct iov_iter i;
 	int ret = -EINVAL;

block/blk-merge.c

@@ -154,6 +154,19 @@ static struct bio *bio_split_write_zeroes(struct bio *bio,
 	return bio_split(bio, lim->max_write_zeroes_sectors, GFP_NOIO, bs);
 }
 
+static inline unsigned int blk_boundary_sectors(const struct queue_limits *lim,
+						bool is_atomic)
+{
+	/*
+	 * chunk_sectors must be a multiple of atomic_write_boundary_sectors if
+	 * both non-zero.
+	 */
+	if (is_atomic && lim->atomic_write_boundary_sectors)
+		return lim->atomic_write_boundary_sectors;
+
+	return lim->chunk_sectors;
+}
+
 /*
  * Return the maximum number of sectors from the start of a bio that may be
  * submitted as a single request to a block device. If enough sectors remain,
@@ -167,12 +180,23 @@ static inline unsigned get_max_io_size(struct bio *bio,
 {
 	unsigned pbs = lim->physical_block_size >> SECTOR_SHIFT;
 	unsigned lbs = lim->logical_block_size >> SECTOR_SHIFT;
-	unsigned max_sectors = lim->max_sectors, start, end;
+	bool is_atomic = bio->bi_opf & REQ_ATOMIC;
+	unsigned boundary_sectors = blk_boundary_sectors(lim, is_atomic);
+	unsigned max_sectors, start, end;
 
-	if (lim->chunk_sectors) {
+	/*
+	 * We ignore lim->max_sectors for atomic writes because it may less
+	 * than the actual bio size, which we cannot tolerate.
+	 */
+	if (is_atomic)
+		max_sectors = lim->atomic_write_max_sectors;
+	else
+		max_sectors = lim->max_sectors;
+
+	if (boundary_sectors) {
 		max_sectors = min(max_sectors,
-			blk_chunk_sectors_left(bio->bi_iter.bi_sector,
+			blk_boundary_sectors_left(bio->bi_iter.bi_sector,
-					       lim->chunk_sectors));
+					      boundary_sectors));
 	}
 
 	start = bio->bi_iter.bi_sector & (pbs - 1);
@@ -185,23 +209,22 @@ static inline unsigned get_max_io_size(struct bio *bio,
 /**
  * get_max_segment_size() - maximum number of bytes to add as a single segment
  * @lim: Request queue limits.
- * @start_page: See below.
+ * @paddr: address of the range to add
- * @offset: Offset from @start_page where to add a segment.
+ * @len: maximum length available to add at @paddr
  *
- * Returns the maximum number of bytes that can be added as a single segment.
+ * Returns the maximum number of bytes of the range starting at @paddr that can
+ * be added to a single segment.
  */
 static inline unsigned get_max_segment_size(const struct queue_limits *lim,
-		struct page *start_page, unsigned long offset)
+		phys_addr_t paddr, unsigned int len)
 {
-	unsigned long mask = lim->seg_boundary_mask;
-
-	offset = mask & (page_to_phys(start_page) + offset);
-
 	/*
 	 * Prevent an overflow if mask = ULONG_MAX and offset = 0 by adding 1
 	 * after having calculated the minimum.
 	 */
-	return min(mask - offset, (unsigned long)lim->max_segment_size - 1) + 1;
+	return min_t(unsigned long, len,
+		min(lim->seg_boundary_mask - (lim->seg_boundary_mask & paddr),
+		    (unsigned long)lim->max_segment_size - 1) + 1);
 }
 
 /**
@@ -234,9 +257,7 @@ static bool bvec_split_segs(const struct queue_limits *lim,
 	unsigned seg_size = 0;
 
 	while (len && *nsegs < max_segs) {
-		seg_size = get_max_segment_size(lim, bv->bv_page,
+		seg_size = get_max_segment_size(lim, bvec_phys(bv) + total_len, len);
-						bv->bv_offset + total_len);
-		seg_size = min(seg_size, len);
 
 		(*nsegs)++;
 		total_len += seg_size;
@@ -305,6 +326,11 @@ struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim,
 	*segs = nsegs;
 	return NULL;
 split:
+	if (bio->bi_opf & REQ_ATOMIC) {
+		bio->bi_status = BLK_STS_INVAL;
+		bio_endio(bio);
+		return ERR_PTR(-EINVAL);
+	}
 	/*
 	 * We can't sanely support splitting for a REQ_NOWAIT bio. End it
 	 * with EAGAIN if splitting is required and return an error pointer.
@@ -465,8 +491,8 @@ static unsigned blk_bvec_map_sg(struct request_queue *q,
 
 	while (nbytes > 0) {
 		unsigned offset = bvec->bv_offset + total;
-		unsigned len = min(get_max_segment_size(&q->limits,
+		unsigned len = get_max_segment_size(&q->limits,
-				   bvec->bv_page, offset), nbytes);
+				bvec_phys(bvec) + total, nbytes);
 		struct page *page = bvec->bv_page;
 
 		/*
@@ -588,18 +614,22 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
 						  sector_t offset)
 {
 	struct request_queue *q = rq->q;
-	unsigned int max_sectors;
+	struct queue_limits *lim = &q->limits;
+	unsigned int max_sectors, boundary_sectors;
+	bool is_atomic = rq->cmd_flags & REQ_ATOMIC;
 
 	if (blk_rq_is_passthrough(rq))
 		return q->limits.max_hw_sectors;
 
-	max_sectors = blk_queue_get_max_sectors(q, req_op(rq));
+	boundary_sectors = blk_boundary_sectors(lim, is_atomic);
-	if (!q->limits.chunk_sectors ||
+	max_sectors = blk_queue_get_max_sectors(rq);
+
+	if (!boundary_sectors ||
 	    req_op(rq) == REQ_OP_DISCARD ||
 	    req_op(rq) == REQ_OP_SECURE_ERASE)
 		return max_sectors;
 	return min(max_sectors,
-		   blk_chunk_sectors_left(offset, q->limits.chunk_sectors));
+		   blk_boundary_sectors_left(offset, boundary_sectors));
 }
 
 static inline int ll_new_hw_segment(struct request *req, struct bio *bio,
@@ -797,6 +827,18 @@ static enum elv_merge blk_try_req_merge(struct request *req,
 	return ELEVATOR_NO_MERGE;
 }
 
+static bool blk_atomic_write_mergeable_rq_bio(struct request *rq,
+					      struct bio *bio)
+{
+	return (rq->cmd_flags & REQ_ATOMIC) == (bio->bi_opf & REQ_ATOMIC);
+}
+
+static bool blk_atomic_write_mergeable_rqs(struct request *rq,
+					   struct request *next)
+{
+	return (rq->cmd_flags & REQ_ATOMIC) == (next->cmd_flags & REQ_ATOMIC);
+}
+
 /*
  * For non-mq, this has to be called with the request spinlock acquired.
  * For mq with scheduling, the appropriate queue wide lock should be held.
@@ -820,6 +862,9 @@ static struct request *attempt_merge(struct request_queue *q,
 	if (req->ioprio != next->ioprio)
 		return NULL;
 
+	if (!blk_atomic_write_mergeable_rqs(req, next))
+		return NULL;
+
 	/*
 	 * If we are allowed to merge, then append bio list
 	 * from next to rq and release next. merge_requests_fn
@@ -951,6 +996,9 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (rq->ioprio != bio_prio(bio))
 		return false;
 
+	if (blk_atomic_write_mergeable_rq_bio(rq, bio) == false)
+		return false;
+
 	return true;
 }
 

block/blk-mq-debugfs.c

@@ -84,28 +84,15 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(NOMERGES),
 	QUEUE_FLAG_NAME(SAME_COMP),
 	QUEUE_FLAG_NAME(FAIL_IO),
-	QUEUE_FLAG_NAME(NONROT),
-	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),
-	QUEUE_FLAG_NAME(POLL),
-	QUEUE_FLAG_NAME(WC),
-	QUEUE_FLAG_NAME(FUA),
-	QUEUE_FLAG_NAME(DAX),
 	QUEUE_FLAG_NAME(STATS),
 	QUEUE_FLAG_NAME(REGISTERED),
 	QUEUE_FLAG_NAME(QUIESCED),
-	QUEUE_FLAG_NAME(PCI_P2PDMA),
-	QUEUE_FLAG_NAME(ZONE_RESETALL),
 	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
 

block/blk-mq.c

@@ -448,6 +448,10 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 	if (data->cmd_flags & REQ_NOWAIT)
 		data->flags |= BLK_MQ_REQ_NOWAIT;
 
+retry:
+	data->ctx = blk_mq_get_ctx(q);
+	data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx);
+
 	if (q->elevator) {
 		/*
 		 * All requests use scheduler tags when an I/O scheduler is
@@ -469,13 +473,9 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 			if (ops->limit_depth)
 				ops->limit_depth(data->cmd_flags, data);
 		}
-	}
+	} else {
-
-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_SCHED_TAGS))
 		blk_mq_tag_busy(data->hctx);
+	}
 
 	if (data->flags & BLK_MQ_REQ_RESERVED)
 		data->rq_flags |= RQF_RESV;
@@ -804,10 +804,8 @@ static void blk_complete_request(struct request *req)
 	if (!bio)
 		return;
 
-#ifdef CONFIG_BLK_DEV_INTEGRITY
 	if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ)
-		req->q->integrity.profile->complete_fn(req, total_bytes);
+		blk_integrity_complete(req, total_bytes);
-#endif
 
 	/*
 	 * Upper layers may call blk_crypto_evict_key() anytime after the last
@@ -875,11 +873,9 @@ bool blk_update_request(struct request *req, blk_status_t error,
 	if (!req->bio)
 		return false;
 
-#ifdef CONFIG_BLK_DEV_INTEGRITY
 	if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ &&
 	    error == BLK_STS_OK)
-		req->q->integrity.profile->complete_fn(req, nr_bytes);
+		blk_integrity_complete(req, nr_bytes);
-#endif
 
 	/*
 	 * Upper layers may call blk_crypto_evict_key() anytime after the last
@@ -1264,10 +1260,9 @@ void blk_mq_start_request(struct request *rq)
 	WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT);
 	rq->mq_hctx->tags->rqs[rq->tag] = rq;
 
-#ifdef CONFIG_BLK_DEV_INTEGRITY
 	if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE)
-		q->integrity.profile->prepare_fn(rq);
+		blk_integrity_prepare(rq);
-#endif
+
 	if (rq->bio && rq->bio->bi_opf & REQ_POLLED)
 	        WRITE_ONCE(rq->bio->bi_cookie, rq->mq_hctx->queue_num);
 }
@@ -2914,6 +2909,17 @@ static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
 	INIT_LIST_HEAD(&rq->queuelist);
 }
 
+static bool bio_unaligned(const struct bio *bio, struct request_queue *q)
+{
+	unsigned int bs_mask = queue_logical_block_size(q) - 1;
+
+	/* .bi_sector of any zero sized bio need to be initialized */
+	if ((bio->bi_iter.bi_size & bs_mask) ||
+	    ((bio->bi_iter.bi_sector << SECTOR_SHIFT) & bs_mask))
+		return true;
+	return false;
+}
+
 /**
  * blk_mq_submit_bio - Create and send a request to block device.
  * @bio: Bio pointer.
@@ -2966,6 +2972,15 @@ void blk_mq_submit_bio(struct bio *bio)
 			return;
 	}
 
+	/*
+	 * Device reconfiguration may change logical block size, so alignment
+	 * check has to be done with queue usage counter held
+	 */
+	if (unlikely(bio_unaligned(bio, q))) {
+		bio_io_error(bio);
+		goto queue_exit;
+	}
+
 	if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
 		bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
 		if (!bio)
@@ -3041,7 +3056,7 @@ queue_exit:
 blk_status_t blk_insert_cloned_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
-	unsigned int max_sectors = blk_queue_get_max_sectors(q, req_op(rq));
+	unsigned int max_sectors = blk_queue_get_max_sectors(rq);
 	unsigned int max_segments = blk_rq_get_max_segments(rq);
 	blk_status_t ret;
 
@@ -4114,6 +4129,12 @@ void blk_mq_release(struct request_queue *q)
 	blk_mq_sysfs_deinit(q);
 }
 
+static bool blk_mq_can_poll(struct blk_mq_tag_set *set)
+{
+	return set->nr_maps > HCTX_TYPE_POLL &&
+		set->map[HCTX_TYPE_POLL].nr_queues;
+}
+
 struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
 		struct queue_limits *lim, void *queuedata)
 {
@@ -4121,7 +4142,13 @@ struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
 	struct request_queue *q;
 	int ret;
 
-	q = blk_alloc_queue(lim ? lim : &default_lim, set->numa_node);
+	if (!lim)
+		lim = &default_lim;
+	lim->features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT;
+	if (blk_mq_can_poll(set))
+		lim->features |= BLK_FEAT_POLL;
+
+	q = blk_alloc_queue(lim, set->numa_node);
 	if (IS_ERR(q))
 		return q;
 	q->queuedata = queuedata;
@@ -4274,17 +4301,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	mutex_unlock(&q->sysfs_lock);
 }
 
-static void blk_mq_update_poll_flag(struct request_queue *q)
-{
-	struct blk_mq_tag_set *set = q->tag_set;
-
-	if (set->nr_maps > HCTX_TYPE_POLL &&
-	    set->map[HCTX_TYPE_POLL].nr_queues)
-		blk_queue_flag_set(QUEUE_FLAG_POLL, q);
-	else
-		blk_queue_flag_clear(QUEUE_FLAG_POLL, q);
-}
-
 int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		struct request_queue *q)
 {
@@ -4312,7 +4328,6 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	q->tag_set = set;
 
 	q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
-	blk_mq_update_poll_flag(q);
 
 	INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work);
 	INIT_LIST_HEAD(&q->flush_list);
@@ -4636,13 +4651,15 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 	int ret;
 	unsigned long i;
 
+	if (WARN_ON_ONCE(!q->mq_freeze_depth))
+		return -EINVAL;
+
 	if (!set)
 		return -EINVAL;
 
 	if (q->nr_requests == nr)
 		return 0;
 
-	blk_mq_freeze_queue(q);
 	blk_mq_quiesce_queue(q);
 
 	ret = 0;
@@ -4676,7 +4693,6 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 	}
 
 	blk_mq_unquiesce_queue(q);
-	blk_mq_unfreeze_queue(q);
 
 	return ret;
 }
@@ -4798,8 +4814,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 fallback:
 	blk_mq_update_queue_map(set);
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+		struct queue_limits lim;
+
 		blk_mq_realloc_hw_ctxs(set, q);
-		blk_mq_update_poll_flag(q);
+
 		if (q->nr_hw_queues != set->nr_hw_queues) {
 			int i = prev_nr_hw_queues;
 
@@ -4811,6 +4829,13 @@ fallback:
 			set->nr_hw_queues = prev_nr_hw_queues;
 			goto fallback;
 		}
+		lim = queue_limits_start_update(q);
+		if (blk_mq_can_poll(set))
+			lim.features |= BLK_FEAT_POLL;
+		else
+			lim.features &= ~BLK_FEAT_POLL;
+		if (queue_limits_commit_update(q, &lim) < 0)
+			pr_warn("updating the poll flag failed\n");
 		blk_mq_map_swqueue(q);
 	}
 

block/blk-settings.c

@@ -6,7 +6,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/bio.h>
-#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
 #include <linux/pagemap.h>
 #include <linux/backing-dev-defs.h>
 #include <linux/gcd.h>
@@ -55,7 +55,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 }
 EXPORT_SYMBOL(blk_set_stacking_limits);
 
-static void blk_apply_bdi_limits(struct backing_dev_info *bdi,
+void blk_apply_bdi_limits(struct backing_dev_info *bdi,
 		struct queue_limits *lim)
 {
 	/*
@@ -68,7 +68,7 @@ static void blk_apply_bdi_limits(struct backing_dev_info *bdi,
 
 static int blk_validate_zoned_limits(struct queue_limits *lim)
 {
-	if (!lim->zoned) {
+	if (!(lim->features & BLK_FEAT_ZONED)) {
 		if (WARN_ON_ONCE(lim->max_open_zones) ||
 		    WARN_ON_ONCE(lim->max_active_zones) ||
 		    WARN_ON_ONCE(lim->zone_write_granularity) ||
@@ -80,6 +80,14 @@ static int blk_validate_zoned_limits(struct queue_limits *lim)
 	if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED)))
 		return -EINVAL;
 
+	/*
+	 * Given that active zones include open zones, the maximum number of
+	 * open zones cannot be larger than the maximum number of active zones.
+	 */
+	if (lim->max_active_zones &&
+	    lim->max_open_zones > lim->max_active_zones)
+		return -EINVAL;
+
 	if (lim->zone_write_granularity < lim->logical_block_size)
 		lim->zone_write_granularity = lim->logical_block_size;
 
@@ -97,6 +105,120 @@ static int blk_validate_zoned_limits(struct queue_limits *lim)
 	return 0;
 }
 
+static int blk_validate_integrity_limits(struct queue_limits *lim)
+{
+	struct blk_integrity *bi = &lim->integrity;
+
+	if (!bi->tuple_size) {
+		if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE ||
+		    bi->tag_size || ((bi->flags & BLK_INTEGRITY_REF_TAG))) {
+			pr_warn("invalid PI settings.\n");
+			return -EINVAL;
+		}
+		return 0;
+	}
+
+	if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) {
+		pr_warn("integrity support disabled.\n");
+		return -EINVAL;
+	}
+
+	if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE &&
+	    (bi->flags & BLK_INTEGRITY_REF_TAG)) {
+		pr_warn("ref tag not support without checksum.\n");
+		return -EINVAL;
+	}
+
+	if (!bi->interval_exp)
+		bi->interval_exp = ilog2(lim->logical_block_size);
+
+	return 0;
+}
+
+/*
+ * Returns max guaranteed bytes which we can fit in a bio.
+ *
+ * We request that an atomic_write is ITER_UBUF iov_iter (so a single vector),
+ * so we assume that we can fit in at least PAGE_SIZE in a segment, apart from
+ * the first and last segments.
+ */
+static unsigned int blk_queue_max_guaranteed_bio(struct queue_limits *lim)
+{
+	unsigned int max_segments = min(BIO_MAX_VECS, lim->max_segments);
+	unsigned int length;
+
+	length = min(max_segments, 2) * lim->logical_block_size;
+	if (max_segments > 2)
+		length += (max_segments - 2) * PAGE_SIZE;
+
+	return length;
+}
+
+static void blk_atomic_writes_update_limits(struct queue_limits *lim)
+{
+	unsigned int unit_limit = min(lim->max_hw_sectors << SECTOR_SHIFT,
+					blk_queue_max_guaranteed_bio(lim));
+
+	unit_limit = rounddown_pow_of_two(unit_limit);
+
+	lim->atomic_write_max_sectors =
+		min(lim->atomic_write_hw_max >> SECTOR_SHIFT,
+			lim->max_hw_sectors);
+	lim->atomic_write_unit_min =
+		min(lim->atomic_write_hw_unit_min, unit_limit);
+	lim->atomic_write_unit_max =
+		min(lim->atomic_write_hw_unit_max, unit_limit);
+	lim->atomic_write_boundary_sectors =
+		lim->atomic_write_hw_boundary >> SECTOR_SHIFT;
+}
+
+static void blk_validate_atomic_write_limits(struct queue_limits *lim)
+{
+	unsigned int boundary_sectors;
+
+	if (!lim->atomic_write_hw_max)
+		goto unsupported;
+
+	boundary_sectors = lim->atomic_write_hw_boundary >> SECTOR_SHIFT;
+
+	if (boundary_sectors) {
+		/*
+		 * A feature of boundary support is that it disallows bios to
+		 * be merged which would result in a merged request which
+		 * crosses either a chunk sector or atomic write HW boundary,
+		 * even though chunk sectors may be just set for performance.
+		 * For simplicity, disallow atomic writes for a chunk sector
+		 * which is non-zero and smaller than atomic write HW boundary.
+		 * Furthermore, chunk sectors must be a multiple of atomic
+		 * write HW boundary. Otherwise boundary support becomes
+		 * complicated.
+		 * Devices which do not conform to these rules can be dealt
+		 * with if and when they show up.
+		 */
+		if (WARN_ON_ONCE(lim->chunk_sectors % boundary_sectors))
+			goto unsupported;
+
+		/*
+		 * The boundary size just needs to be a multiple of unit_max
+		 * (and not necessarily a power-of-2), so this following check
+		 * could be relaxed in future.
+		 * Furthermore, if needed, unit_max could even be reduced so
+		 * that it is compliant with a !power-of-2 boundary.
+		 */
+		if (!is_power_of_2(boundary_sectors))
+			goto unsupported;
+	}
+
+	blk_atomic_writes_update_limits(lim);
+	return;
+
+unsupported:
+	lim->atomic_write_max_sectors = 0;
+	lim->atomic_write_boundary_sectors = 0;
+	lim->atomic_write_unit_min = 0;
+	lim->atomic_write_unit_max = 0;
+}
+
 /*
  * Check that the limits in lim are valid, initialize defaults for unset
  * values, and cap values based on others where needed.
@@ -105,6 +227,7 @@ static int blk_validate_limits(struct queue_limits *lim)
 {
 	unsigned int max_hw_sectors;
 	unsigned int logical_block_sectors;
+	int err;
 
 	/*
 	 * Unless otherwise specified, default to 512 byte logical blocks and a
@@ -112,6 +235,10 @@ static int blk_validate_limits(struct queue_limits *lim)
 	 */
 	if (!lim->logical_block_size)
 		lim->logical_block_size = SECTOR_SIZE;
+	else if (blk_validate_block_size(lim->logical_block_size)) {
+		pr_warn("Invalid logical block size (%d)\n", lim->logical_block_size);
+		return -EINVAL;
+	}
 	if (lim->physical_block_size < lim->logical_block_size)
 		lim->physical_block_size = lim->logical_block_size;
 
@@ -153,6 +280,12 @@ static int blk_validate_limits(struct queue_limits *lim)
 		if (lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE)
 			return -EINVAL;
 		lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors);
+	} else if (lim->io_opt > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) {
+		lim->max_sectors =
+			min(max_hw_sectors, lim->io_opt >> SECTOR_SHIFT);
+	} else if (lim->io_min > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) {
+		lim->max_sectors =
+			min(max_hw_sectors, lim->io_min >> SECTOR_SHIFT);
 	} else {
 		lim->max_sectors = min(max_hw_sectors, BLK_DEF_MAX_SECTORS_CAP);
 	}
@@ -220,9 +353,17 @@ static int blk_validate_limits(struct queue_limits *lim)
 
 	if (lim->alignment_offset) {
 		lim->alignment_offset &= (lim->physical_block_size - 1);
-		lim->misaligned = 0;
+		lim->flags &= ~BLK_FLAG_MISALIGNED;
 	}
 
+	if (!(lim->features & BLK_FEAT_WRITE_CACHE))
+		lim->features &= ~BLK_FEAT_FUA;
+
+	blk_validate_atomic_write_limits(lim);
+
+	err = blk_validate_integrity_limits(lim);
+	if (err)
+		return err;
 	return blk_validate_zoned_limits(lim);
 }
 
@@ -254,15 +395,25 @@ int blk_set_default_limits(struct queue_limits *lim)
  */
 int queue_limits_commit_update(struct request_queue *q,
 		struct queue_limits *lim)
-	__releases(q->limits_lock)
 {
-	int error = blk_validate_limits(lim);
+	int error;
 
-	if (!error) {
+	error = blk_validate_limits(lim);
-		q->limits = *lim;
+	if (error)
-		if (q->disk)
+		goto out_unlock;
-			blk_apply_bdi_limits(q->disk->bdi, lim);
+
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+	if (q->crypto_profile && lim->integrity.tag_size) {
+		pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together.\n");
+		error = -EINVAL;
+		goto out_unlock;
 	}
+#endif
+
+	q->limits = *lim;
+	if (q->disk)
+		blk_apply_bdi_limits(q->disk->bdi, lim);
+out_unlock:
 	mutex_unlock(&q->limits_lock);
 	return error;
 }
@@ -286,204 +437,6 @@ int queue_limits_set(struct request_queue *q, struct queue_limits *lim)
 }
 EXPORT_SYMBOL_GPL(queue_limits_set);
 
-/**
- * blk_queue_chunk_sectors - set size of the chunk for this queue
- * @q:  the request queue for the device
- * @chunk_sectors:  chunk sectors in the usual 512b unit
- *
- * Description:
- *    If a driver doesn't want IOs to cross a given chunk size, it can set
- *    this limit and prevent merging across chunks. Note that the block layer
- *    must accept a page worth of data at any offset. So if the crossing of
- *    chunks is a hard limitation in the driver, it must still be prepared
- *    to split single page bios.
- **/
-void blk_queue_chunk_sectors(struct request_queue *q, unsigned int chunk_sectors)
-{
-	q->limits.chunk_sectors = chunk_sectors;
-}
-EXPORT_SYMBOL(blk_queue_chunk_sectors);
-
-/**
- * blk_queue_max_discard_sectors - set max sectors for a single discard
- * @q:  the request queue for the device
- * @max_discard_sectors: maximum number of sectors to discard
- **/
-void blk_queue_max_discard_sectors(struct request_queue *q,
-		unsigned int max_discard_sectors)
-{
-	struct queue_limits *lim = &q->limits;
-
-	lim->max_hw_discard_sectors = max_discard_sectors;
-	lim->max_discard_sectors =
-		min(max_discard_sectors, lim->max_user_discard_sectors);
-}
-EXPORT_SYMBOL(blk_queue_max_discard_sectors);
-
-/**
- * blk_queue_max_secure_erase_sectors - set max sectors for a secure erase
- * @q:  the request queue for the device
- * @max_sectors: maximum number of sectors to secure_erase
- **/
-void blk_queue_max_secure_erase_sectors(struct request_queue *q,
-		unsigned int max_sectors)
-{
-	q->limits.max_secure_erase_sectors = max_sectors;
-}
-EXPORT_SYMBOL(blk_queue_max_secure_erase_sectors);
-
-/**
- * blk_queue_max_write_zeroes_sectors - set max sectors for a single
- *                                      write zeroes
- * @q:  the request queue for the device
- * @max_write_zeroes_sectors: maximum number of sectors to write per command
- **/
-void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
-		unsigned int max_write_zeroes_sectors)
-{
-	q->limits.max_write_zeroes_sectors = max_write_zeroes_sectors;
-}
-EXPORT_SYMBOL(blk_queue_max_write_zeroes_sectors);
-
-/**
- * blk_queue_max_zone_append_sectors - set max sectors for a single zone append
- * @q:  the request queue for the device
- * @max_zone_append_sectors: maximum number of sectors to write per command
- *
- * Sets the maximum number of sectors allowed for zone append commands. If
- * Specifying 0 for @max_zone_append_sectors indicates that the queue does
- * not natively support zone append operations and that the block layer must
- * emulate these operations using regular writes.
- **/
-void blk_queue_max_zone_append_sectors(struct request_queue *q,
-		unsigned int max_zone_append_sectors)
-{
-	unsigned int max_sectors = 0;
-
-	if (WARN_ON(!blk_queue_is_zoned(q)))
-		return;
-
-	if (max_zone_append_sectors) {
-		max_sectors = min(q->limits.max_hw_sectors,
-				  max_zone_append_sectors);
-		max_sectors = min(q->limits.chunk_sectors, max_sectors);
-
-		/*
-		 * Signal eventual driver bugs resulting in the max_zone_append
-		 * sectors limit being 0 due to the chunk_sectors limit (zone
-		 * size) not set or the max_hw_sectors limit not set.
-		 */
-		WARN_ON_ONCE(!max_sectors);
-	}
-
-	q->limits.max_zone_append_sectors = max_sectors;
-}
-EXPORT_SYMBOL_GPL(blk_queue_max_zone_append_sectors);
-
-/**
- * blk_queue_logical_block_size - set logical block size for the queue
- * @q:  the request queue for the device
- * @size:  the logical block size, in bytes
- *
- * Description:
- *   This should be set to the lowest possible block size that the
- *   storage device can address.  The default of 512 covers most
- *   hardware.
- **/
-void blk_queue_logical_block_size(struct request_queue *q, unsigned int size)
-{
-	struct queue_limits *limits = &q->limits;
-
-	limits->logical_block_size = size;
-
-	if (limits->discard_granularity < limits->logical_block_size)
-		limits->discard_granularity = limits->logical_block_size;
-
-	if (limits->physical_block_size < size)
-		limits->physical_block_size = size;
-
-	if (limits->io_min < limits->physical_block_size)
-		limits->io_min = limits->physical_block_size;
-
-	limits->max_hw_sectors =
-		round_down(limits->max_hw_sectors, size >> SECTOR_SHIFT);
-	limits->max_sectors =
-		round_down(limits->max_sectors, size >> SECTOR_SHIFT);
-}
-EXPORT_SYMBOL(blk_queue_logical_block_size);
-
-/**
- * blk_queue_physical_block_size - set physical block size for the queue
- * @q:  the request queue for the device
- * @size:  the physical block size, in bytes
- *
- * Description:
- *   This should be set to the lowest possible sector size that the
- *   hardware can operate on without reverting to read-modify-write
- *   operations.
- */
-void blk_queue_physical_block_size(struct request_queue *q, unsigned int size)
-{
-	q->limits.physical_block_size = size;
-
-	if (q->limits.physical_block_size < q->limits.logical_block_size)
-		q->limits.physical_block_size = q->limits.logical_block_size;
-
-	if (q->limits.discard_granularity < q->limits.physical_block_size)
-		q->limits.discard_granularity = q->limits.physical_block_size;
-
-	if (q->limits.io_min < q->limits.physical_block_size)
-		q->limits.io_min = q->limits.physical_block_size;
-}
-EXPORT_SYMBOL(blk_queue_physical_block_size);
-
-/**
- * blk_queue_zone_write_granularity - set zone write granularity for the queue
- * @q:  the request queue for the zoned device
- * @size:  the zone write granularity size, in bytes
- *
- * Description:
- *   This should be set to the lowest possible size allowing to write in
- *   sequential zones of a zoned block device.
- */
-void blk_queue_zone_write_granularity(struct request_queue *q,
-				      unsigned int size)
-{
-	if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
-		return;
-
-	q->limits.zone_write_granularity = size;
-
-	if (q->limits.zone_write_granularity < q->limits.logical_block_size)
-		q->limits.zone_write_granularity = q->limits.logical_block_size;
-}
-EXPORT_SYMBOL_GPL(blk_queue_zone_write_granularity);
-
-/**
- * blk_queue_alignment_offset - set physical block alignment offset
- * @q:	the request queue for the device
- * @offset: alignment offset in bytes
- *
- * Description:
- *   Some devices are naturally misaligned to compensate for things like
- *   the legacy DOS partition table 63-sector offset.  Low-level drivers
- *   should call this function for devices whose first sector is not
- *   naturally aligned.
- */
-void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
-{
-	q->limits.alignment_offset =
-		offset & (q->limits.physical_block_size - 1);
-	q->limits.misaligned = 0;
-}
-EXPORT_SYMBOL(blk_queue_alignment_offset);
-
-void disk_update_readahead(struct gendisk *disk)
-{
-	blk_apply_bdi_limits(disk->bdi, &disk->queue->limits);
-}
-EXPORT_SYMBOL_GPL(disk_update_readahead);
-
 /**
  * blk_limits_io_min - set minimum request size for a device
  * @limits: the queue limits
@@ -507,26 +460,6 @@ void blk_limits_io_min(struct queue_limits *limits, unsigned int min)
 }
 EXPORT_SYMBOL(blk_limits_io_min);
 
-/**
- * blk_queue_io_min - set minimum request size for the queue
- * @q:	the request queue for the device
- * @min:  smallest I/O size in bytes
- *
- * Description:
- *   Storage devices may report a granularity or preferred minimum I/O
- *   size which is the smallest request the device can perform without
- *   incurring a performance penalty.  For disk drives this is often the
- *   physical block size.  For RAID arrays it is often the stripe chunk
- *   size.  A properly aligned multiple of minimum_io_size is the
- *   preferred request size for workloads where a high number of I/O
- *   operations is desired.
- */
-void blk_queue_io_min(struct request_queue *q, unsigned int min)
-{
-	blk_limits_io_min(&q->limits, min);
-}
-EXPORT_SYMBOL(blk_queue_io_min);
-
 /**
  * blk_limits_io_opt - set optimal request size for a device
  * @limits: the queue limits
@@ -614,6 +547,21 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 {
 	unsigned int top, bottom, alignment, ret = 0;
 
+	t->features |= (b->features & BLK_FEAT_INHERIT_MASK);
+
+	/*
+	 * BLK_FEAT_NOWAIT and BLK_FEAT_POLL need to be supported both by the
+	 * stacking driver and all underlying devices.  The stacking driver sets
+	 * the flags before stacking the limits, and this will clear the flags
+	 * if any of the underlying devices does not support it.
+	 */
+	if (!(b->features & BLK_FEAT_NOWAIT))
+		t->features &= ~BLK_FEAT_NOWAIT;
+	if (!(b->features & BLK_FEAT_POLL))
+		t->features &= ~BLK_FEAT_POLL;
+
+	t->flags |= (b->flags & BLK_FLAG_MISALIGNED);
+
 	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
 	t->max_user_sectors = min_not_zero(t->max_user_sectors,
 			b->max_user_sectors);
@@ -623,7 +571,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 					b->max_write_zeroes_sectors);
 	t->max_zone_append_sectors = min(queue_limits_max_zone_append_sectors(t),
 					 queue_limits_max_zone_append_sectors(b));
-	t->bounce = max(t->bounce, b->bounce);
 
 	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
 					    b->seg_boundary_mask);
@@ -639,8 +586,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->max_segment_size = min_not_zero(t->max_segment_size,
 					   b->max_segment_size);
 
-	t->misaligned |= b->misaligned;
-
 	alignment = queue_limit_alignment_offset(b, start);
 
 	/* Bottom device has different alignment.  Check that it is
@@ -654,7 +599,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 		/* Verify that top and bottom intervals line up */
 		if (max(top, bottom) % min(top, bottom)) {
-			t->misaligned = 1;
+			t->flags |= BLK_FLAG_MISALIGNED;
 			ret = -1;
 		}
 	}
@@ -676,42 +621,38 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	/* Physical block size a multiple of the logical block size? */
 	if (t->physical_block_size & (t->logical_block_size - 1)) {
 		t->physical_block_size = t->logical_block_size;
-		t->misaligned = 1;
+		t->flags |= BLK_FLAG_MISALIGNED;
 		ret = -1;
 	}
 
 	/* Minimum I/O a multiple of the physical block size? */
 	if (t->io_min & (t->physical_block_size - 1)) {
 		t->io_min = t->physical_block_size;
-		t->misaligned = 1;
+		t->flags |= BLK_FLAG_MISALIGNED;
 		ret = -1;
 	}
 
 	/* Optimal I/O a multiple of the physical block size? */
 	if (t->io_opt & (t->physical_block_size - 1)) {
 		t->io_opt = 0;
-		t->misaligned = 1;
+		t->flags |= BLK_FLAG_MISALIGNED;
 		ret = -1;
 	}
 
 	/* chunk_sectors a multiple of the physical block size? */
 	if ((t->chunk_sectors << 9) & (t->physical_block_size - 1)) {
 		t->chunk_sectors = 0;
-		t->misaligned = 1;
+		t->flags |= BLK_FLAG_MISALIGNED;
 		ret = -1;
 	}
 
-	t->raid_partial_stripes_expensive =
-		max(t->raid_partial_stripes_expensive,
-		    b->raid_partial_stripes_expensive);
-
 	/* Find lowest common alignment_offset */
 	t->alignment_offset = lcm_not_zero(t->alignment_offset, alignment)
 		% max(t->physical_block_size, t->io_min);
 
 	/* Verify that new alignment_offset is on a logical block boundary */
 	if (t->alignment_offset & (t->logical_block_size - 1)) {
-		t->misaligned = 1;
+		t->flags |= BLK_FLAG_MISALIGNED;
 		ret = -1;
 	}
 
@@ -723,16 +664,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	if (b->discard_granularity) {
 		alignment = queue_limit_discard_alignment(b, start);
 
-		if (t->discard_granularity != 0 &&
-		    t->discard_alignment != alignment) {
-			top = t->discard_granularity + t->discard_alignment;
-			bottom = b->discard_granularity + alignment;
-
-			/* Verify that top and bottom intervals line up */
-			if ((max(top, bottom) % min(top, bottom)) != 0)
-				t->discard_misaligned = 1;
-		}
-
 		t->max_discard_sectors = min_not_zero(t->max_discard_sectors,
 						      b->max_discard_sectors);
 		t->max_hw_discard_sectors = min_not_zero(t->max_hw_discard_sectors,
@@ -746,8 +677,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 						   b->max_secure_erase_sectors);
 	t->zone_write_granularity = max(t->zone_write_granularity,
 					b->zone_write_granularity);
-	t->zoned = max(t->zoned, b->zoned);
+	if (!(t->features & BLK_FEAT_ZONED)) {
-	if (!t->zoned) {
 		t->zone_write_granularity = 0;
 		t->max_zone_append_sectors = 0;
 	}
@@ -781,21 +711,65 @@ void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
 EXPORT_SYMBOL_GPL(queue_limits_stack_bdev);
 
 /**
- * blk_queue_update_dma_pad - update pad mask
+ * queue_limits_stack_integrity - stack integrity profile
- * @q:     the request queue for the device
+ * @t: target queue limits
- * @mask:  pad mask
+ * @b: base queue limits
  *
- * Update dma pad mask.
+ * Check if the integrity profile in the @b can be stacked into the
+ * target @t.  Stacking is possible if either:
  *
- * Appending pad buffer to a request modifies the last entry of a
+ *   a) does not have any integrity information stacked into it yet
- * scatter list such that it includes the pad buffer.
+ *   b) the integrity profile in @b is identical to the one in @t
- **/
+ *
-void blk_queue_update_dma_pad(struct request_queue *q, unsigned int mask)
+ * If @b can be stacked into @t, return %true.  Else return %false and clear the
+ * integrity information in @t.
+ */
+bool queue_limits_stack_integrity(struct queue_limits *t,
+		struct queue_limits *b)
 {
-	if (mask > q->dma_pad_mask)
+	struct blk_integrity *ti = &t->integrity;
-		q->dma_pad_mask = mask;
+	struct blk_integrity *bi = &b->integrity;
+
+	if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY))
+		return true;
+
+	if (!ti->tuple_size) {
+		/* inherit the settings from the first underlying device */
+		if (!(ti->flags & BLK_INTEGRITY_STACKED)) {
+			ti->flags = BLK_INTEGRITY_DEVICE_CAPABLE |
+				(bi->flags & BLK_INTEGRITY_REF_TAG);
+			ti->csum_type = bi->csum_type;
+			ti->tuple_size = bi->tuple_size;
+			ti->pi_offset = bi->pi_offset;
+			ti->interval_exp = bi->interval_exp;
+			ti->tag_size = bi->tag_size;
+			goto done;
+		}
+		if (!bi->tuple_size)
+			goto done;
+	}
+
+	if (ti->tuple_size != bi->tuple_size)
+		goto incompatible;
+	if (ti->interval_exp != bi->interval_exp)
+		goto incompatible;
+	if (ti->tag_size != bi->tag_size)
+		goto incompatible;
+	if (ti->csum_type != bi->csum_type)
+		goto incompatible;
+	if ((ti->flags & BLK_INTEGRITY_REF_TAG) !=
+	    (bi->flags & BLK_INTEGRITY_REF_TAG))
+		goto incompatible;
+
+done:
+	ti->flags |= BLK_INTEGRITY_STACKED;
+	return true;
+
+incompatible:
+	memset(ti, 0, sizeof(*ti));
+	return false;
 }
-EXPORT_SYMBOL(blk_queue_update_dma_pad);
+EXPORT_SYMBOL_GPL(queue_limits_stack_integrity);
 
 /**
  * blk_set_queue_depth - tell the block layer about the device queue depth
@@ -810,54 +784,11 @@ void blk_set_queue_depth(struct request_queue *q, unsigned int depth)
 }
 EXPORT_SYMBOL(blk_set_queue_depth);
 
-/**
- * blk_queue_write_cache - configure queue's write cache
- * @q:		the request queue for the device
- * @wc:		write back cache on or off
- * @fua:	device supports FUA writes, if true
- *
- * Tell the block layer about the write cache of @q.
- */
-void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
-{
-	if (wc) {
-		blk_queue_flag_set(QUEUE_FLAG_HW_WC, q);
-		blk_queue_flag_set(QUEUE_FLAG_WC, q);
-	} else {
-		blk_queue_flag_clear(QUEUE_FLAG_HW_WC, q);
-		blk_queue_flag_clear(QUEUE_FLAG_WC, q);
-	}
-	if (fua)
-		blk_queue_flag_set(QUEUE_FLAG_FUA, q);
-	else
-		blk_queue_flag_clear(QUEUE_FLAG_FUA, q);
-}
-EXPORT_SYMBOL_GPL(blk_queue_write_cache);
-
-/**
- * disk_set_zoned - inidicate a zoned device
- * @disk:	gendisk to configure
- */
-void disk_set_zoned(struct gendisk *disk)
-{
-	struct request_queue *q = disk->queue;
-
-	WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED));
-
-	/*
-	 * Set the zone write granularity to the device logical block
-	 * size by default. The driver can change this value if needed.
-	 */
-	q->limits.zoned = true;
-	blk_queue_zone_write_granularity(q, queue_logical_block_size(q));
-}
-EXPORT_SYMBOL_GPL(disk_set_zoned);
-
 int bdev_alignment_offset(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 
-	if (q->limits.misaligned)
+	if (q->limits.flags & BLK_FLAG_MISALIGNED)
 		return -1;
 	if (bdev_is_partition(bdev))
 		return queue_limit_alignment_offset(&q->limits,

block/blk-sysfs.c

@@ -22,8 +22,8 @@
 
 struct queue_sysfs_entry {
 	struct attribute attr;
-	ssize_t (*show)(struct request_queue *, char *);
+	ssize_t (*show)(struct gendisk *disk, char *page);
-	ssize_t (*store)(struct request_queue *, const char *, size_t);
+	ssize_t (*store)(struct gendisk *disk, const char *page, size_t count);
 };
 
 static ssize_t
@@ -47,18 +47,18 @@ queue_var_store(unsigned long *var, const char *page, size_t count)
 	return count;
 }
 
-static ssize_t queue_requests_show(struct request_queue *q, char *page)
+static ssize_t queue_requests_show(struct gendisk *disk, char *page)
 {
-	return queue_var_show(q->nr_requests, page);
+	return queue_var_show(disk->queue->nr_requests, page);
 }
 
 static ssize_t
-queue_requests_store(struct request_queue *q, const char *page, size_t count)
+queue_requests_store(struct gendisk *disk, const char *page, size_t count)
 {
 	unsigned long nr;
 	int ret, err;
 
-	if (!queue_is_mq(q))
+	if (!queue_is_mq(disk->queue))
 		return -EINVAL;
 
 	ret = queue_var_store(&nr, page, count);
@@ -68,111 +68,91 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
 	if (nr < BLKDEV_MIN_RQ)
 		nr = BLKDEV_MIN_RQ;
 
-	err = blk_mq_update_nr_requests(q, nr);
+	err = blk_mq_update_nr_requests(disk->queue, nr);
 	if (err)
 		return err;
 
 	return ret;
 }
 
-static ssize_t queue_ra_show(struct request_queue *q, char *page)
+static ssize_t queue_ra_show(struct gendisk *disk, char *page)
 {
-	unsigned long ra_kb;
+	return queue_var_show(disk->bdi->ra_pages << (PAGE_SHIFT - 10), page);
-
-	if (!q->disk)
-		return -EINVAL;
-	ra_kb = q->disk->bdi->ra_pages << (PAGE_SHIFT - 10);
-	return queue_var_show(ra_kb, page);
 }
 
 static ssize_t
-queue_ra_store(struct request_queue *q, const char *page, size_t count)
+queue_ra_store(struct gendisk *disk, const char *page, size_t count)
 {
 	unsigned long ra_kb;
 	ssize_t ret;
 
-	if (!q->disk)
-		return -EINVAL;
 	ret = queue_var_store(&ra_kb, page, count);
 	if (ret < 0)
 		return ret;
-	q->disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10);
+	disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10);
 	return ret;
 }
 
-static ssize_t queue_max_sectors_show(struct request_queue *q, char *page)
+#define QUEUE_SYSFS_LIMIT_SHOW(_field)					\
-{
+static ssize_t queue_##_field##_show(struct gendisk *disk, char *page)	\
-	int max_sectors_kb = queue_max_sectors(q) >> 1;
+{									\
-
+	return queue_var_show(disk->queue->limits._field, page);	\
-	return queue_var_show(max_sectors_kb, page);
 }
 
-static ssize_t queue_max_segments_show(struct request_queue *q, char *page)
+QUEUE_SYSFS_LIMIT_SHOW(max_segments)
-{
+QUEUE_SYSFS_LIMIT_SHOW(max_discard_segments)
-	return queue_var_show(queue_max_segments(q), page);
+QUEUE_SYSFS_LIMIT_SHOW(max_integrity_segments)
+QUEUE_SYSFS_LIMIT_SHOW(max_segment_size)
+QUEUE_SYSFS_LIMIT_SHOW(logical_block_size)
+QUEUE_SYSFS_LIMIT_SHOW(physical_block_size)
+QUEUE_SYSFS_LIMIT_SHOW(chunk_sectors)
+QUEUE_SYSFS_LIMIT_SHOW(io_min)
+QUEUE_SYSFS_LIMIT_SHOW(io_opt)
+QUEUE_SYSFS_LIMIT_SHOW(discard_granularity)
+QUEUE_SYSFS_LIMIT_SHOW(zone_write_granularity)
+QUEUE_SYSFS_LIMIT_SHOW(virt_boundary_mask)
+QUEUE_SYSFS_LIMIT_SHOW(dma_alignment)
+QUEUE_SYSFS_LIMIT_SHOW(max_open_zones)
+QUEUE_SYSFS_LIMIT_SHOW(max_active_zones)
+QUEUE_SYSFS_LIMIT_SHOW(atomic_write_unit_min)
+QUEUE_SYSFS_LIMIT_SHOW(atomic_write_unit_max)
+
+#define QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(_field)			\
+static ssize_t queue_##_field##_show(struct gendisk *disk, char *page)	\
+{									\
+	return sprintf(page, "%llu\n",					\
+		(unsigned long long)disk->queue->limits._field <<	\
+			SECTOR_SHIFT);					\
 }
 
-static ssize_t queue_max_discard_segments_show(struct request_queue *q,
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_discard_sectors)
-		char *page)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_hw_discard_sectors)
-{
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_write_zeroes_sectors)
-	return queue_var_show(queue_max_discard_segments(q), page);
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(atomic_write_max_sectors)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(atomic_write_boundary_sectors)
+
+#define QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(_field)			\
+static ssize_t queue_##_field##_show(struct gendisk *disk, char *page)	\
+{									\
+	return queue_var_show(disk->queue->limits._field >> 1, page);	\
 }
 
-static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(max_sectors)
-{
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(max_hw_sectors)
-	return queue_var_show(q->limits.max_integrity_segments, page);
+
+#define QUEUE_SYSFS_SHOW_CONST(_name, _val)				\
+static ssize_t queue_##_name##_show(struct gendisk *disk, char *page)	\
+{									\
+	return sprintf(page, "%d\n", _val);				\
 }
 
-static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page)
+/* deprecated fields */
-{
+QUEUE_SYSFS_SHOW_CONST(discard_zeroes_data, 0)
-	return queue_var_show(queue_max_segment_size(q), page);
+QUEUE_SYSFS_SHOW_CONST(write_same_max, 0)
-}
+QUEUE_SYSFS_SHOW_CONST(poll_delay, -1)
 
-static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page)
+static ssize_t queue_max_discard_sectors_store(struct gendisk *disk,
-{
+		const char *page, size_t count)
-	return queue_var_show(queue_logical_block_size(q), page);
-}
-
-static ssize_t queue_physical_block_size_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_physical_block_size(q), page);
-}
-
-static ssize_t queue_chunk_sectors_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(q->limits.chunk_sectors, page);
-}
-
-static ssize_t queue_io_min_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_io_min(q), page);
-}
-
-static ssize_t queue_io_opt_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_io_opt(q), page);
-}
-
-static ssize_t queue_discard_granularity_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(q->limits.discard_granularity, page);
-}
-
-static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page)
-{
-
-	return sprintf(page, "%llu\n",
-		(unsigned long long)q->limits.max_hw_discard_sectors << 9);
-}
-
-static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
-{
-	return sprintf(page, "%llu\n",
-		       (unsigned long long)q->limits.max_discard_sectors << 9);
-}
-
-static ssize_t queue_discard_max_store(struct request_queue *q,
-				       const char *page, size_t count)
 {
 	unsigned long max_discard_bytes;
 	struct queue_limits lim;
@@ -183,54 +163,34 @@ static ssize_t queue_discard_max_store(struct request_queue *q,
 	if (ret < 0)
 		return ret;
 
-	if (max_discard_bytes & (q->limits.discard_granularity - 1))
+	if (max_discard_bytes & (disk->queue->limits.discard_granularity - 1))
 		return -EINVAL;
 
 	if ((max_discard_bytes >> SECTOR_SHIFT) > UINT_MAX)
 		return -EINVAL;
 
-	blk_mq_freeze_queue(q);
+	lim = queue_limits_start_update(disk->queue);
-	lim = queue_limits_start_update(q);
 	lim.max_user_discard_sectors = max_discard_bytes >> SECTOR_SHIFT;
-	err = queue_limits_commit_update(q, &lim);
+	err = queue_limits_commit_update(disk->queue, &lim);
-	blk_mq_unfreeze_queue(q);
-
 	if (err)
 		return err;
 	return ret;
 }
 
-static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page)
+/*
-{
+ * For zone append queue_max_zone_append_sectors does not just return the
-	return queue_var_show(0, page);
+ * underlying queue limits, but actually contains a calculation.  Because of
-}
+ * that we can't simply use QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES here.
-
+ */
-static ssize_t queue_write_same_max_show(struct request_queue *q, char *page)
+static ssize_t queue_zone_append_max_show(struct gendisk *disk, char *page)
-{
-	return queue_var_show(0, page);
-}
-
-static ssize_t queue_write_zeroes_max_show(struct request_queue *q, char *page)
 {
 	return sprintf(page, "%llu\n",
-		(unsigned long long)q->limits.max_write_zeroes_sectors << 9);
+		(u64)queue_max_zone_append_sectors(disk->queue) <<
-}
+			SECTOR_SHIFT);
-
-static ssize_t queue_zone_write_granularity_show(struct request_queue *q,
-						 char *page)
-{
-	return queue_var_show(queue_zone_write_granularity(q), page);
-}
-
-static ssize_t queue_zone_append_max_show(struct request_queue *q, char *page)
-{
-	unsigned long long max_sectors = queue_max_zone_append_sectors(q);
-
-	return sprintf(page, "%llu\n", max_sectors << SECTOR_SHIFT);
 }
 
 static ssize_t
-queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
+queue_max_sectors_store(struct gendisk *disk, const char *page, size_t count)
 {
 	unsigned long max_sectors_kb;
 	struct queue_limits lim;
@@ -241,94 +201,83 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 	if (ret < 0)
 		return ret;
 
-	blk_mq_freeze_queue(q);
+	lim = queue_limits_start_update(disk->queue);
-	lim = queue_limits_start_update(q);
 	lim.max_user_sectors = max_sectors_kb << 1;
-	err = queue_limits_commit_update(q, &lim);
+	err = queue_limits_commit_update(disk->queue, &lim);
-	blk_mq_unfreeze_queue(q);
 	if (err)
 		return err;
 	return ret;
 }
 
-static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
+static ssize_t queue_feature_store(struct gendisk *disk, const char *page,
+		size_t count, blk_features_t feature)
 {
-	int max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1;
+	struct queue_limits lim;
+	unsigned long val;
+	ssize_t ret;
 
-	return queue_var_show(max_hw_sectors_kb, page);
+	ret = queue_var_store(&val, page, count);
+	if (ret < 0)
+		return ret;
+
+	lim = queue_limits_start_update(disk->queue);
+	if (val)
+		lim.features |= feature;
+	else
+		lim.features &= ~feature;
+	ret = queue_limits_commit_update(disk->queue, &lim);
+	if (ret)
+		return ret;
+	return count;
 }
 
-static ssize_t queue_virt_boundary_mask_show(struct request_queue *q, char *page)
+#define QUEUE_SYSFS_FEATURE(_name, _feature)				\
-{
+static ssize_t queue_##_name##_show(struct gendisk *disk, char *page)	\
-	return queue_var_show(q->limits.virt_boundary_mask, page);
-}
-
-static ssize_t queue_dma_alignment_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_dma_alignment(q), page);
-}
-
-#define QUEUE_SYSFS_BIT_FNS(name, flag, neg)				\
-static ssize_t								\
-queue_##name##_show(struct request_queue *q, char *page)		\
 {									\
-	int bit;							\
+	return sprintf(page, "%u\n",					\
-	bit = test_bit(QUEUE_FLAG_##flag, &q->queue_flags);		\
+		!!(disk->queue->limits.features & _feature));		\
-	return queue_var_show(neg ? !bit : bit, page);			\
 }									\
-static ssize_t								\
+static ssize_t queue_##_name##_store(struct gendisk *disk,		\
-queue_##name##_store(struct request_queue *q, const char *page, size_t count) \
+		const char *page, size_t count)				\
 {									\
-	unsigned long val;						\
+	return queue_feature_store(disk, page, count, _feature);	\
-	ssize_t ret;							\
-	ret = queue_var_store(&val, page, count);			\
-	if (ret < 0)							\
-		 return ret;						\
-	if (neg)							\
-		val = !val;						\
-									\
-	if (val)							\
-		blk_queue_flag_set(QUEUE_FLAG_##flag, q);		\
-	else								\
-		blk_queue_flag_clear(QUEUE_FLAG_##flag, q);		\
-	return ret;							\
 }
 
-QUEUE_SYSFS_BIT_FNS(nonrot, NONROT, 1);
+QUEUE_SYSFS_FEATURE(rotational, BLK_FEAT_ROTATIONAL)
-QUEUE_SYSFS_BIT_FNS(random, ADD_RANDOM, 0);
+QUEUE_SYSFS_FEATURE(add_random, BLK_FEAT_ADD_RANDOM)
-QUEUE_SYSFS_BIT_FNS(iostats, IO_STAT, 0);
+QUEUE_SYSFS_FEATURE(iostats, BLK_FEAT_IO_STAT)
-QUEUE_SYSFS_BIT_FNS(stable_writes, STABLE_WRITES, 0);
+QUEUE_SYSFS_FEATURE(stable_writes, BLK_FEAT_STABLE_WRITES);
-#undef QUEUE_SYSFS_BIT_FNS
 
-static ssize_t queue_zoned_show(struct request_queue *q, char *page)
+#define QUEUE_SYSFS_FEATURE_SHOW(_name, _feature)			\
+static ssize_t queue_##_name##_show(struct gendisk *disk, char *page)	\
+{									\
+	return sprintf(page, "%u\n",					\
+		!!(disk->queue->limits.features & _feature));		\
+}
+
+QUEUE_SYSFS_FEATURE_SHOW(poll, BLK_FEAT_POLL);
+QUEUE_SYSFS_FEATURE_SHOW(fua, BLK_FEAT_FUA);
+QUEUE_SYSFS_FEATURE_SHOW(dax, BLK_FEAT_DAX);
+
+static ssize_t queue_zoned_show(struct gendisk *disk, char *page)
 {
-	if (blk_queue_is_zoned(q))
+	if (blk_queue_is_zoned(disk->queue))
 		return sprintf(page, "host-managed\n");
 	return sprintf(page, "none\n");
 }
 
-static ssize_t queue_nr_zones_show(struct request_queue *q, char *page)
+static ssize_t queue_nr_zones_show(struct gendisk *disk, char *page)
 {
-	return queue_var_show(disk_nr_zones(q->disk), page);
+	return queue_var_show(disk_nr_zones(disk), page);
 }
 
-static ssize_t queue_max_open_zones_show(struct request_queue *q, char *page)
+static ssize_t queue_nomerges_show(struct gendisk *disk, char *page)
 {
-	return queue_var_show(bdev_max_open_zones(q->disk->part0), page);
+	return queue_var_show((blk_queue_nomerges(disk->queue) << 1) |
+			       blk_queue_noxmerges(disk->queue), page);
 }
 
-static ssize_t queue_max_active_zones_show(struct request_queue *q, char *page)
+static ssize_t queue_nomerges_store(struct gendisk *disk, const char *page,
-{
-	return queue_var_show(bdev_max_active_zones(q->disk->part0), page);
-}
-
-static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
-{
-	return queue_var_show((blk_queue_nomerges(q) << 1) |
-			       blk_queue_noxmerges(q), page);
-}
-
-static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
 				    size_t count)
 {
 	unsigned long nm;
@@ -337,29 +286,30 @@ static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
 	if (ret < 0)
 		return ret;
 
-	blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, q);
+	blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, disk->queue);
-	blk_queue_flag_clear(QUEUE_FLAG_NOXMERGES, q);
+	blk_queue_flag_clear(QUEUE_FLAG_NOXMERGES, disk->queue);
 	if (nm == 2)
-		blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q);
+		blk_queue_flag_set(QUEUE_FLAG_NOMERGES, disk->queue);
 	else if (nm)
-		blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
+		blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, disk->queue);
 
 	return ret;
 }
 
-static ssize_t queue_rq_affinity_show(struct request_queue *q, char *page)
+static ssize_t queue_rq_affinity_show(struct gendisk *disk, char *page)
 {
-	bool set = test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags);
+	bool set = test_bit(QUEUE_FLAG_SAME_COMP, &disk->queue->queue_flags);
-	bool force = test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags);
+	bool force = test_bit(QUEUE_FLAG_SAME_FORCE, &disk->queue->queue_flags);
 
 	return queue_var_show(set << force, page);
 }
 
 static ssize_t
-queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
+queue_rq_affinity_store(struct gendisk *disk, const char *page, size_t count)
 {
 	ssize_t ret = -EINVAL;
 #ifdef CONFIG_SMP
+	struct request_queue *q = disk->queue;
 	unsigned long val;
 
 	ret = queue_var_store(&val, page, count);
@@ -380,38 +330,28 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
 	return ret;
 }
 
-static ssize_t queue_poll_delay_show(struct request_queue *q, char *page)
+static ssize_t queue_poll_delay_store(struct gendisk *disk, const char *page,
-{
-	return sprintf(page, "%d\n", -1);
-}
-
-static ssize_t queue_poll_delay_store(struct request_queue *q, const char *page,
 				size_t count)
 {
 	return count;
 }
 
-static ssize_t queue_poll_show(struct request_queue *q, char *page)
+static ssize_t queue_poll_store(struct gendisk *disk, const char *page,
-{
-	return queue_var_show(test_bit(QUEUE_FLAG_POLL, &q->queue_flags), page);
-}
-
-static ssize_t queue_poll_store(struct request_queue *q, const char *page,
 				size_t count)
 {
-	if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+	if (!(disk->queue->limits.features & BLK_FEAT_POLL))
 		return -EINVAL;
 	pr_info_ratelimited("writes to the poll attribute are ignored.\n");
 	pr_info_ratelimited("please use driver specific parameters instead.\n");
 	return count;
 }
 
-static ssize_t queue_io_timeout_show(struct request_queue *q, char *page)
+static ssize_t queue_io_timeout_show(struct gendisk *disk, char *page)
 {
-	return sprintf(page, "%u\n", jiffies_to_msecs(q->rq_timeout));
+	return sprintf(page, "%u\n", jiffies_to_msecs(disk->queue->rq_timeout));
 }
 
-static ssize_t queue_io_timeout_store(struct request_queue *q, const char *page,
+static ssize_t queue_io_timeout_store(struct gendisk *disk, const char *page,
 				  size_t count)
 {
 	unsigned int val;
@@ -421,46 +361,45 @@ static ssize_t queue_io_timeout_store(struct request_queue *q, const char *page,
 	if (err || val == 0)
 		return -EINVAL;
 
-	blk_queue_rq_timeout(q, msecs_to_jiffies(val));
+	blk_queue_rq_timeout(disk->queue, msecs_to_jiffies(val));
 
 	return count;
 }
 
-static ssize_t queue_wc_show(struct request_queue *q, char *page)
+static ssize_t queue_wc_show(struct gendisk *disk, char *page)
 {
-	if (test_bit(QUEUE_FLAG_WC, &q->queue_flags))
+	if (blk_queue_write_cache(disk->queue))
 		return sprintf(page, "write back\n");
-
 	return sprintf(page, "write through\n");
 }
 
-static ssize_t queue_wc_store(struct request_queue *q, const char *page,
+static ssize_t queue_wc_store(struct gendisk *disk, const char *page,
 			      size_t count)
 {
+	struct queue_limits lim;
+	bool disable;
+	int err;
+
 	if (!strncmp(page, "write back", 10)) {
-		if (!test_bit(QUEUE_FLAG_HW_WC, &q->queue_flags))
+		disable = false;
-			return -EINVAL;
-		blk_queue_flag_set(QUEUE_FLAG_WC, q);
 	} else if (!strncmp(page, "write through", 13) ||
-		 !strncmp(page, "none", 4)) {
+		   !strncmp(page, "none", 4)) {
-		blk_queue_flag_clear(QUEUE_FLAG_WC, q);
+		disable = true;
 	} else {
 		return -EINVAL;
 	}
 
+	lim = queue_limits_start_update(disk->queue);
+	if (disable)
+		lim.flags |= BLK_FLAG_WRITE_CACHE_DISABLED;
+	else
+		lim.flags &= ~BLK_FLAG_WRITE_CACHE_DISABLED;
+	err = queue_limits_commit_update(disk->queue, &lim);
+	if (err)
+		return err;
 	return count;
 }
 
-static ssize_t queue_fua_show(struct request_queue *q, char *page)
-{
-	return sprintf(page, "%u\n", test_bit(QUEUE_FLAG_FUA, &q->queue_flags));
-}
-
-static ssize_t queue_dax_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(blk_queue_dax(q), page);
-}
-
 #define QUEUE_RO_ENTRY(_prefix, _name)			\
 static struct queue_sysfs_entry _prefix##_entry = {	\
 	.attr	= { .name = _name, .mode = 0444 },	\
@@ -491,12 +430,18 @@ QUEUE_RO_ENTRY(queue_io_opt, "optimal_io_size");
 
 QUEUE_RO_ENTRY(queue_max_discard_segments, "max_discard_segments");
 QUEUE_RO_ENTRY(queue_discard_granularity, "discard_granularity");
-QUEUE_RO_ENTRY(queue_discard_max_hw, "discard_max_hw_bytes");
+QUEUE_RO_ENTRY(queue_max_hw_discard_sectors, "discard_max_hw_bytes");
-QUEUE_RW_ENTRY(queue_discard_max, "discard_max_bytes");
+QUEUE_RW_ENTRY(queue_max_discard_sectors, "discard_max_bytes");
 QUEUE_RO_ENTRY(queue_discard_zeroes_data, "discard_zeroes_data");
 
+QUEUE_RO_ENTRY(queue_atomic_write_max_sectors, "atomic_write_max_bytes");
+QUEUE_RO_ENTRY(queue_atomic_write_boundary_sectors,
+		"atomic_write_boundary_bytes");
+QUEUE_RO_ENTRY(queue_atomic_write_unit_max, "atomic_write_unit_max_bytes");
+QUEUE_RO_ENTRY(queue_atomic_write_unit_min, "atomic_write_unit_min_bytes");
+
 QUEUE_RO_ENTRY(queue_write_same_max, "write_same_max_bytes");
-QUEUE_RO_ENTRY(queue_write_zeroes_max, "write_zeroes_max_bytes");
+QUEUE_RO_ENTRY(queue_max_write_zeroes_sectors, "write_zeroes_max_bytes");
 QUEUE_RO_ENTRY(queue_zone_append_max, "zone_append_max_bytes");
 QUEUE_RO_ENTRY(queue_zone_write_granularity, "zone_write_granularity");
 
@@ -522,9 +467,9 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = {
 	.show = queue_logical_block_size_show,
 };
 
-QUEUE_RW_ENTRY(queue_nonrot, "rotational");
+QUEUE_RW_ENTRY(queue_rotational, "rotational");
 QUEUE_RW_ENTRY(queue_iostats, "iostats");
-QUEUE_RW_ENTRY(queue_random, "add_random");
+QUEUE_RW_ENTRY(queue_add_random, "add_random");
 QUEUE_RW_ENTRY(queue_stable_writes, "stable_writes");
 
 #ifdef CONFIG_BLK_WBT
@@ -541,20 +486,22 @@ static ssize_t queue_var_store64(s64 *var, const char *page)
 	return 0;
 }
 
-static ssize_t queue_wb_lat_show(struct request_queue *q, char *page)
+static ssize_t queue_wb_lat_show(struct gendisk *disk, char *page)
 {
-	if (!wbt_rq_qos(q))
+	if (!wbt_rq_qos(disk->queue))
 		return -EINVAL;
 
-	if (wbt_disabled(q))
+	if (wbt_disabled(disk->queue))
 		return sprintf(page, "0\n");
 
-	return sprintf(page, "%llu\n", div_u64(wbt_get_min_lat(q), 1000));
+	return sprintf(page, "%llu\n",
+		div_u64(wbt_get_min_lat(disk->queue), 1000));
 }
 
-static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
+static ssize_t queue_wb_lat_store(struct gendisk *disk, const char *page,
 				  size_t count)
 {
+	struct request_queue *q = disk->queue;
 	struct rq_qos *rqos;
 	ssize_t ret;
 	s64 val;
@@ -567,7 +514,7 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 
 	rqos = wbt_rq_qos(q);
 	if (!rqos) {
-		ret = wbt_init(q->disk);
+		ret = wbt_init(disk);
 		if (ret)
 			return ret;
 	}
@@ -585,13 +532,11 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 	 * ends up either enabling or disabling wbt completely. We can't
 	 * have IO inflight if that happens.
 	 */
-	blk_mq_freeze_queue(q);
 	blk_mq_quiesce_queue(q);
 
 	wbt_set_min_lat(q, val);
 
 	blk_mq_unquiesce_queue(q);
-	blk_mq_unfreeze_queue(q);
 
 	return count;
 }
@@ -615,14 +560,18 @@ static struct attribute *queue_attrs[] = {
 	&queue_io_min_entry.attr,
 	&queue_io_opt_entry.attr,
 	&queue_discard_granularity_entry.attr,
-	&queue_discard_max_entry.attr,
+	&queue_max_discard_sectors_entry.attr,
-	&queue_discard_max_hw_entry.attr,
+	&queue_max_hw_discard_sectors_entry.attr,
 	&queue_discard_zeroes_data_entry.attr,
+	&queue_atomic_write_max_sectors_entry.attr,
+	&queue_atomic_write_boundary_sectors_entry.attr,
+	&queue_atomic_write_unit_min_entry.attr,
+	&queue_atomic_write_unit_max_entry.attr,
 	&queue_write_same_max_entry.attr,
-	&queue_write_zeroes_max_entry.attr,
+	&queue_max_write_zeroes_sectors_entry.attr,
 	&queue_zone_append_max_entry.attr,
 	&queue_zone_write_granularity_entry.attr,
-	&queue_nonrot_entry.attr,
+	&queue_rotational_entry.attr,
 	&queue_zoned_entry.attr,
 	&queue_nr_zones_entry.attr,
 	&queue_max_open_zones_entry.attr,
@@ -630,7 +579,7 @@ static struct attribute *queue_attrs[] = {
 	&queue_nomerges_entry.attr,
 	&queue_iostats_entry.attr,
 	&queue_stable_writes_entry.attr,
-	&queue_random_entry.attr,
+	&queue_add_random_entry.attr,
 	&queue_poll_entry.attr,
 	&queue_wc_entry.attr,
 	&queue_fua_entry.attr,
@@ -699,14 +648,13 @@ queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 {
 	struct queue_sysfs_entry *entry = to_queue(attr);
 	struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj);
-	struct request_queue *q = disk->queue;
 	ssize_t res;
 
 	if (!entry->show)
 		return -EIO;
-	mutex_lock(&q->sysfs_lock);
+	mutex_lock(&disk->queue->sysfs_lock);
-	res = entry->show(q, page);
+	res = entry->show(disk, page);
-	mutex_unlock(&q->sysfs_lock);
+	mutex_unlock(&disk->queue->sysfs_lock);
 	return res;
 }
 
@@ -722,9 +670,11 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
 	if (!entry->store)
 		return -EIO;
 
+	blk_mq_freeze_queue(q);
 	mutex_lock(&q->sysfs_lock);
-	res = entry->store(q, page, length);
+	res = entry->store(disk, page, length);
 	mutex_unlock(&q->sysfs_lock);
+	blk_mq_unfreeze_queue(q);
 	return res;
 }
 

block/blk-throttle.c

@@ -704,6 +704,9 @@ static unsigned long tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio
 
 	/* Calc approx time to dispatch */
 	jiffy_wait = jiffy_elapsed_rnd - jiffy_elapsed;
+
+	/* make sure at least one io can be dispatched after waiting */
+	jiffy_wait = max(jiffy_wait, HZ / iops_limit + 1);
 	return jiffy_wait;
 }
 

block/blk-wbt.c

@@ -37,7 +37,7 @@
 enum wbt_flags {
 	WBT_TRACKED		= 1,	/* write, tracked for throttling */
 	WBT_READ		= 2,	/* read */
-	WBT_KSWAPD		= 4,	/* write, from kswapd */
+	WBT_SWAP		= 4,	/* write, from swap_writepage() */
 	WBT_DISCARD		= 8,	/* discard */
 
 	WBT_NR_BITS		= 4,	/* number of bits */
@@ -45,7 +45,7 @@ enum wbt_flags {
 
 enum {
 	WBT_RWQ_BG		= 0,
-	WBT_RWQ_KSWAPD,
+	WBT_RWQ_SWAP,
 	WBT_RWQ_DISCARD,
 	WBT_NUM_RWQ,
 };
@@ -172,8 +172,8 @@ static bool wb_recent_wait(struct rq_wb *rwb)
 static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb,
 					  enum wbt_flags wb_acct)
 {
-	if (wb_acct & WBT_KSWAPD)
+	if (wb_acct & WBT_SWAP)
-		return &rwb->rq_wait[WBT_RWQ_KSWAPD];
+		return &rwb->rq_wait[WBT_RWQ_SWAP];
 	else if (wb_acct & WBT_DISCARD)
 		return &rwb->rq_wait[WBT_RWQ_DISCARD];
 
@@ -206,8 +206,8 @@ static void wbt_rqw_done(struct rq_wb *rwb, struct rq_wait *rqw,
 	 */
 	if (wb_acct & WBT_DISCARD)
 		limit = rwb->wb_background;
-	else if (test_bit(QUEUE_FLAG_WC, &rwb->rqos.disk->queue->queue_flags) &&
+	else if (blk_queue_write_cache(rwb->rqos.disk->queue) &&
-	         !wb_recent_wait(rwb))
+		 !wb_recent_wait(rwb))
 		limit = 0;
 	else
 		limit = rwb->wb_normal;
@@ -528,7 +528,7 @@ static bool close_io(struct rq_wb *rwb)
 		time_before(now, rwb->last_comp + HZ / 10);
 }
 
-#define REQ_HIPRIO	(REQ_SYNC | REQ_META | REQ_PRIO)
+#define REQ_HIPRIO	(REQ_SYNC | REQ_META | REQ_PRIO | REQ_SWAP)
 
 static inline unsigned int get_limit(struct rq_wb *rwb, blk_opf_t opf)
 {
@@ -539,13 +539,13 @@ static inline unsigned int get_limit(struct rq_wb *rwb, blk_opf_t opf)
 
 	/*
 	 * At this point we know it's a buffered write. If this is
-	 * kswapd trying to free memory, or REQ_SYNC is set, then
+	 * swap trying to free memory, or REQ_SYNC is set, then
 	 * it's WB_SYNC_ALL writeback, and we'll use the max limit for
 	 * that. If the write is marked as a background write, then use
 	 * the idle limit, or go to normal if we haven't had competing
 	 * IO for a bit.
 	 */
-	if ((opf & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd())
+	if ((opf & REQ_HIPRIO) || wb_recent_wait(rwb))
 		limit = rwb->rq_depth.max_depth;
 	else if ((opf & REQ_BACKGROUND) || close_io(rwb)) {
 		/*
@@ -622,8 +622,8 @@ static enum wbt_flags bio_to_wbt_flags(struct rq_wb *rwb, struct bio *bio)
 	if (bio_op(bio) == REQ_OP_READ) {
 		flags = WBT_READ;
 	} else if (wbt_should_throttle(bio)) {
-		if (current_is_kswapd())
+		if (bio->bi_opf & REQ_SWAP)
-			flags |= WBT_KSWAPD;
+			flags |= WBT_SWAP;
 		if (bio_op(bio) == REQ_OP_DISCARD)
 			flags |= WBT_DISCARD;
 		flags |= WBT_TRACKED;

block/blk-zoned.c

@@ -115,24 +115,6 @@ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond)
 }
 EXPORT_SYMBOL_GPL(blk_zone_cond_str);
 
-/**
- * bdev_nr_zones - Get number of zones
- * @bdev:	Target device
- *
- * Return the total number of zones of a zoned block device.  For a block
- * device without zone capabilities, the number of zones is always 0.
- */
-unsigned int bdev_nr_zones(struct block_device *bdev)
-{
-	sector_t zone_sectors = bdev_zone_sectors(bdev);
-
-	if (!bdev_is_zoned(bdev))
-		return 0;
-	return (bdev_nr_sectors(bdev) + zone_sectors - 1) >>
-		ilog2(zone_sectors);
-}
-EXPORT_SYMBOL_GPL(bdev_nr_zones);
-
 /**
  * blkdev_report_zones - Get zones information
  * @bdev:	Target block device
@@ -168,77 +150,6 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(blkdev_report_zones);
 
-static inline unsigned long *blk_alloc_zone_bitmap(int node,
-						   unsigned int nr_zones)
-{
-	return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long),
-			    GFP_NOIO, node);
-}
-
-static int blk_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx,
-				  void *data)
-{
-	/*
-	 * For an all-zones reset, ignore conventional, empty, read-only
-	 * and offline zones.
-	 */
-	switch (zone->cond) {
-	case BLK_ZONE_COND_NOT_WP:
-	case BLK_ZONE_COND_EMPTY:
-	case BLK_ZONE_COND_READONLY:
-	case BLK_ZONE_COND_OFFLINE:
-		return 0;
-	default:
-		set_bit(idx, (unsigned long *)data);
-		return 0;
-	}
-}
-
-static int blkdev_zone_reset_all_emulated(struct block_device *bdev)
-{
-	struct gendisk *disk = bdev->bd_disk;
-	sector_t capacity = bdev_nr_sectors(bdev);
-	sector_t zone_sectors = bdev_zone_sectors(bdev);
-	unsigned long *need_reset;
-	struct bio *bio = NULL;
-	sector_t sector = 0;
-	int ret;
-
-	need_reset = blk_alloc_zone_bitmap(disk->queue->node, disk->nr_zones);
-	if (!need_reset)
-		return -ENOMEM;
-
-	ret = disk->fops->report_zones(disk, 0, disk->nr_zones,
-				       blk_zone_need_reset_cb, need_reset);
-	if (ret < 0)
-		goto out_free_need_reset;
-
-	ret = 0;
-	while (sector < capacity) {
-		if (!test_bit(disk_zone_no(disk, sector), need_reset)) {
-			sector += zone_sectors;
-			continue;
-		}
-
-		bio = blk_next_bio(bio, bdev, 0, REQ_OP_ZONE_RESET | REQ_SYNC,
-				   GFP_KERNEL);
-		bio->bi_iter.bi_sector = sector;
-		sector += zone_sectors;
-
-		/* This may take a while, so be nice to others */
-		cond_resched();
-	}
-
-	if (bio) {
-		ret = submit_bio_wait(bio);
-		bio_put(bio);
-	}
-
-out_free_need_reset:
-	kfree(need_reset);
-	return ret;
-}
-
 static int blkdev_zone_reset_all(struct block_device *bdev)
 {
 	struct bio bio;
@@ -265,7 +176,6 @@ static int blkdev_zone_reset_all(struct block_device *bdev)
 int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
 		     sector_t sector, sector_t nr_sectors)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
 	sector_t zone_sectors = bdev_zone_sectors(bdev);
 	sector_t capacity = bdev_nr_sectors(bdev);
 	sector_t end_sector = sector + nr_sectors;
@@ -293,16 +203,11 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
 		return -EINVAL;
 
 	/*
-	 * In the case of a zone reset operation over all zones,
+	 * In the case of a zone reset operation over all zones, use
-	 * REQ_OP_ZONE_RESET_ALL can be used with devices supporting this
+	 * REQ_OP_ZONE_RESET_ALL.
-	 * command. For other devices, we emulate this command behavior by
-	 * identifying the zones needing a reset.
 	 */
-	if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity) {
+	if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity)
-		if (!blk_queue_zone_resetall(q))
-			return blkdev_zone_reset_all_emulated(bdev);
 		return blkdev_zone_reset_all(bdev);
-	}
 
 	while (sector < end_sector) {
 		bio = blk_next_bio(bio, bdev, 0, op | REQ_SYNC, GFP_KERNEL);
@@ -1573,7 +1478,7 @@ void disk_free_zone_resources(struct gendisk *disk)
 	mempool_destroy(disk->zone_wplugs_pool);
 	disk->zone_wplugs_pool = NULL;
 
-	kfree(disk->conv_zones_bitmap);
+	bitmap_free(disk->conv_zones_bitmap);
 	disk->conv_zones_bitmap = NULL;
 	disk->zone_capacity = 0;
 	disk->last_zone_capacity = 0;
@@ -1650,8 +1555,22 @@ static int disk_update_zone_resources(struct gendisk *disk,
 		return -ENODEV;
 	}
 
+	lim = queue_limits_start_update(q);
+
+	/*
+	 * Some devices can advertize zone resource limits that are larger than
+	 * the number of sequential zones of the zoned block device, e.g. a
+	 * small ZNS namespace. For such case, assume that the zoned device has
+	 * no zone resource limits.
+	 */
+	nr_seq_zones = disk->nr_zones - nr_conv_zones;
+	if (lim.max_open_zones >= nr_seq_zones)
+		lim.max_open_zones = 0;
+	if (lim.max_active_zones >= nr_seq_zones)
+		lim.max_active_zones = 0;
+
 	if (!disk->zone_wplugs_pool)
-		return 0;
+		goto commit;
 
 	/*
 	 * If the device has no limit on the maximum number of open and active
@@ -1660,9 +1579,6 @@ static int disk_update_zone_resources(struct gendisk *disk,
 	 * dynamic zone write plug allocation when simultaneously writing to
 	 * more zones than the size of the mempool.
 	 */
-	lim = queue_limits_start_update(q);
-
-	nr_seq_zones = disk->nr_zones - nr_conv_zones;
 	pool_size = max(lim.max_open_zones, lim.max_active_zones);
 	if (!pool_size)
 		pool_size = min(BLK_ZONE_WPLUG_DEFAULT_POOL_SIZE, nr_seq_zones);
@@ -1676,6 +1592,7 @@ static int disk_update_zone_resources(struct gendisk *disk,
 			lim.max_open_zones = 0;
 	}
 
+commit:
 	return queue_limits_commit_update(q, &lim);
 }
 
@@ -1683,7 +1600,6 @@ static int blk_revalidate_conv_zone(struct blk_zone *zone, unsigned int idx,
 				    struct blk_revalidate_zone_args *args)
 {
 	struct gendisk *disk = args->disk;
-	struct request_queue *q = disk->queue;
 
 	if (zone->capacity != zone->len) {
 		pr_warn("%s: Invalid conventional zone capacity\n",
@@ -1699,7 +1615,7 @@ static int blk_revalidate_conv_zone(struct blk_zone *zone, unsigned int idx,
 
 	if (!args->conv_zones_bitmap) {
 		args->conv_zones_bitmap =
-			blk_alloc_zone_bitmap(q->node, args->nr_zones);
+			bitmap_zalloc(args->nr_zones, GFP_NOIO);
 		if (!args->conv_zones_bitmap)
 			return -ENOMEM;
 	}

block/blk.h

@@ -98,8 +98,8 @@ static inline bool biovec_phys_mergeable(struct request_queue *q,
 		struct bio_vec *vec1, struct bio_vec *vec2)
 {
 	unsigned long mask = queue_segment_boundary(q);
-	phys_addr_t addr1 = page_to_phys(vec1->bv_page) + vec1->bv_offset;
+	phys_addr_t addr1 = bvec_phys(vec1);
-	phys_addr_t addr2 = page_to_phys(vec2->bv_page) + vec2->bv_offset;
+	phys_addr_t addr2 = bvec_phys(vec2);
 
 	/*
 	 * Merging adjacent physical pages may not work correctly under KMSAN
@@ -181,9 +181,11 @@ static inline unsigned int blk_rq_get_max_segments(struct request *rq)
 	return queue_max_segments(rq->q);
 }
 
-static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
+static inline unsigned int blk_queue_get_max_sectors(struct request *rq)
-						     enum req_op op)
 {
+	struct request_queue *q = rq->q;
+	enum req_op op = req_op(rq);
+
 	if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE))
 		return min(q->limits.max_discard_sectors,
 			   UINT_MAX >> SECTOR_SHIFT);
@@ -191,6 +193,9 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 	if (unlikely(op == REQ_OP_WRITE_ZEROES))
 		return q->limits.max_write_zeroes_sectors;
 
+	if (rq->cmd_flags & REQ_ATOMIC)
+		return q->limits.atomic_write_max_sectors;
+
 	return q->limits.max_sectors;
 }
 
@@ -352,6 +357,8 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio);
 enum elv_merge blk_try_merge(struct request *rq, struct bio *bio);
 
 int blk_set_default_limits(struct queue_limits *lim);
+void blk_apply_bdi_limits(struct backing_dev_info *bdi,
+		struct queue_limits *lim);
 int blk_dev_init(void);
 
 /*
@@ -393,7 +400,7 @@ struct bio *__blk_queue_bounce(struct bio *bio, struct request_queue *q);
 static inline bool blk_queue_may_bounce(struct request_queue *q)
 {
 	return IS_ENABLED(CONFIG_BOUNCE) &&
-		q->limits.bounce == BLK_BOUNCE_HIGH &&
+		(q->limits.features & BLK_FEAT_BOUNCE_HIGH) &&
 		max_low_pfn >= max_pfn;
 }
 
@@ -673,4 +680,9 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder,
 	      const struct blk_holder_ops *hops, struct file *bdev_file);
 int bdev_permission(dev_t dev, blk_mode_t mode, void *holder);
 
+void blk_integrity_generate(struct bio *bio);
+void blk_integrity_verify(struct bio *bio);
+void blk_integrity_prepare(struct request *rq);
+void blk_integrity_complete(struct request *rq, unsigned int nr_bytes);
+
 #endif /* BLK_INTERNAL_H */

block/elevator.c

@@ -709,24 +709,25 @@ static int elevator_change(struct request_queue *q, const char *elevator_name)
 	return ret;
 }
 
-ssize_t elv_iosched_store(struct request_queue *q, const char *buf,
+ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,
 			  size_t count)
 {
 	char elevator_name[ELV_NAME_MAX];
 	int ret;
 
-	if (!elv_support_iosched(q))
+	if (!elv_support_iosched(disk->queue))
 		return count;
 
 	strscpy(elevator_name, buf, sizeof(elevator_name));
-	ret = elevator_change(q, strstrip(elevator_name));
+	ret = elevator_change(disk->queue, strstrip(elevator_name));
 	if (!ret)
 		return count;
 	return ret;
 }
 
-ssize_t elv_iosched_show(struct request_queue *q, char *name)
+ssize_t elv_iosched_show(struct gendisk *disk, char *name)
 {
+	struct request_queue *q = disk->queue;
 	struct elevator_queue *eq = q->elevator;
 	struct elevator_type *cur = NULL, *e;
 	int len = 0;

block/elevator.h

@@ -147,8 +147,8 @@ extern void elv_unregister(struct elevator_type *);
 /*
  * io scheduler sysfs switching
  */
-extern ssize_t elv_iosched_show(struct request_queue *, char *);
+ssize_t elv_iosched_show(struct gendisk *disk, char *page);
-extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
+ssize_t elv_iosched_store(struct gendisk *disk, const char *page, size_t count);
 
 extern bool elv_bio_merge_ok(struct request *, struct bio *);
 extern struct elevator_queue *elevator_alloc(struct request_queue *,

block/fops.c

@@ -34,9 +34,12 @@ static blk_opf_t dio_bio_write_op(struct kiocb *iocb)
 	return opf;
 }
 
-static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos,
+static bool blkdev_dio_invalid(struct block_device *bdev, loff_t pos,
-			      struct iov_iter *iter)
+				struct iov_iter *iter, bool is_atomic)
 {
+	if (is_atomic && !generic_atomic_write_valid(iter, pos))
+		return true;
+
 	return pos & (bdev_logical_block_size(bdev) - 1) ||
 		!bdev_iter_is_aligned(bdev, iter);
 }
@@ -72,6 +75,8 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 	bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT;
 	bio.bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
 	bio.bi_ioprio = iocb->ki_ioprio;
+	if (iocb->ki_flags & IOCB_ATOMIC)
+		bio.bi_opf |= REQ_ATOMIC;
 
 	ret = bio_iov_iter_get_pages(&bio, iter);
 	if (unlikely(ret))
@@ -343,6 +348,9 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 		task_io_account_write(bio->bi_iter.bi_size);
 	}
 
+	if (iocb->ki_flags & IOCB_ATOMIC)
+		bio->bi_opf |= REQ_ATOMIC;
+
 	if (iocb->ki_flags & IOCB_NOWAIT)
 		bio->bi_opf |= REQ_NOWAIT;
 
@@ -359,12 +367,13 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
+	bool is_atomic = iocb->ki_flags & IOCB_ATOMIC;
 	unsigned int nr_pages;
 
 	if (!iov_iter_count(iter))
 		return 0;
 
-	if (blkdev_dio_unaligned(bdev, iocb->ki_pos, iter))
+	if (blkdev_dio_invalid(bdev, iocb->ki_pos, iter, is_atomic))
 		return -EINVAL;
 
 	nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
@@ -373,6 +382,8 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 			return __blkdev_direct_IO_simple(iocb, iter, bdev,
 							nr_pages);
 		return __blkdev_direct_IO_async(iocb, iter, bdev, nr_pages);
+	} else if (is_atomic) {
+		return -EINVAL;
 	}
 	return __blkdev_direct_IO(iocb, iter, bdev, bio_max_segs(nr_pages));
 }
@@ -383,10 +394,11 @@ static int blkdev_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	struct block_device *bdev = I_BDEV(inode);
 	loff_t isize = i_size_read(inode);
 
-	iomap->bdev = bdev;
-	iomap->offset = ALIGN_DOWN(offset, bdev_logical_block_size(bdev));
 	if (offset >= isize)
 		return -EIO;
+
+	iomap->bdev = bdev;
+	iomap->offset = ALIGN_DOWN(offset, bdev_logical_block_size(bdev));
 	iomap->type = IOMAP_MAPPED;
 	iomap->addr = iomap->offset;
 	iomap->length = isize - iomap->offset;
@@ -612,6 +624,9 @@ static int blkdev_open(struct inode *inode, struct file *filp)
 	if (!bdev)
 		return -ENXIO;
 
+	if (bdev_can_atomic_write(bdev) && filp->f_flags & O_DIRECT)
+		filp->f_mode |= FMODE_CAN_ATOMIC_WRITE;
+
 	ret = bdev_open(bdev, mode, filp->private_data, NULL, filp);
 	if (ret)
 		blkdev_put_no_open(bdev);

block/genhd.c

@@ -524,7 +524,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 		disk->part0->bd_dev = MKDEV(disk->major, disk->first_minor);
 	}
 
-	disk_update_readahead(disk);
+	blk_apply_bdi_limits(disk->bdi, &disk->queue->limits);
 	disk_add_events(disk);
 	set_bit(GD_ADDED, &disk->state);
 	return 0;

block/ioctl.c

@@ -224,7 +224,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
 		goto fail;
 
 	err = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL,
-				   BLKDEV_ZERO_NOUNMAP);
+				   BLKDEV_ZERO_NOUNMAP | BLKDEV_ZERO_KILLABLE);
 
 fail:
 	filemap_invalidate_unlock(bdev->bd_mapping);

block/mq-deadline.c

@@ -487,6 +487,20 @@ unlock:
 	return rq;
 }
 
+/*
+ * 'depth' is a number in the range 1..INT_MAX representing a number of
+ * requests. Scale it with a factor (1 << bt->sb.shift) / q->nr_requests since
+ * 1..(1 << bt->sb.shift) is the range expected by sbitmap_get_shallow().
+ * Values larger than q->nr_requests have the same effect as q->nr_requests.
+ */
+static int dd_to_word_depth(struct blk_mq_hw_ctx *hctx, unsigned int qdepth)
+{
+	struct sbitmap_queue *bt = &hctx->sched_tags->bitmap_tags;
+	const unsigned int nrr = hctx->queue->nr_requests;
+
+	return ((qdepth << bt->sb.shift) + nrr - 1) / nrr;
+}
+
 /*
  * Called by __blk_mq_alloc_request(). The shallow_depth value set by this
  * function is used by __blk_mq_get_tag().
@@ -503,7 +517,7 @@ static void dd_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
 	 * Throttle asynchronous requests and writes such that these requests
 	 * do not block the allocation of synchronous requests.
 	 */
-	data->shallow_depth = dd->async_depth;
+	data->shallow_depth = dd_to_word_depth(data->hctx, dd->async_depth);
 }
 
 /* Called by blk_mq_update_nr_requests(). */
@@ -513,9 +527,9 @@ static void dd_depth_updated(struct blk_mq_hw_ctx *hctx)
 	struct deadline_data *dd = q->elevator->elevator_data;
 	struct blk_mq_tags *tags = hctx->sched_tags;
 
-	dd->async_depth = max(1UL, 3 * q->nr_requests / 4);
+	dd->async_depth = q->nr_requests;
 
-	sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, dd->async_depth);
+	sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, 1);
 }
 
 /* Called by blk_mq_init_hctx() and blk_mq_init_sched(). */

block/t10-pi.c

@@ -11,17 +11,23 @@
 #include <linux/module.h>
 #include <net/checksum.h>
 #include <asm/unaligned.h>
+#include "blk.h"
 
-typedef __be16 (csum_fn) (__be16, void *, unsigned int);
+struct blk_integrity_iter {
+	void			*prot_buf;
+	void			*data_buf;
+	sector_t		seed;
+	unsigned int		data_size;
+	unsigned short		interval;
+	const char		*disk_name;
+};
 
-static __be16 t10_pi_crc_fn(__be16 crc, void *data, unsigned int len)
+static __be16 t10_pi_csum(__be16 csum, void *data, unsigned int len,
+		unsigned char csum_type)
 {
-	return cpu_to_be16(crc_t10dif_update(be16_to_cpu(crc), data, len));
+	if (csum_type == BLK_INTEGRITY_CSUM_IP)
-}
+		return (__force __be16)ip_compute_csum(data, len);
-
+	return cpu_to_be16(crc_t10dif_update(be16_to_cpu(csum), data, len));
-static __be16 t10_pi_ip_fn(__be16 csum, void *data, unsigned int len)
-{
-	return (__force __be16)ip_compute_csum(data, len);
 }
 
 /*
@@ -29,48 +35,44 @@ static __be16 t10_pi_ip_fn(__be16 csum, void *data, unsigned int len)
  * 16 bit app tag, 32 bit reference tag. Type 3 does not define the ref
  * tag.
  */
-static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter,
+static void t10_pi_generate(struct blk_integrity_iter *iter,
-		csum_fn *fn, enum t10_dif_type type)
+		struct blk_integrity *bi)
 {
-	u8 offset = iter->pi_offset;
+	u8 offset = bi->pi_offset;
 	unsigned int i;
 
 	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
 		struct t10_pi_tuple *pi = iter->prot_buf + offset;
 
-		pi->guard_tag = fn(0, iter->data_buf, iter->interval);
+		pi->guard_tag = t10_pi_csum(0, iter->data_buf, iter->interval,
+				bi->csum_type);
 		if (offset)
-			pi->guard_tag = fn(pi->guard_tag, iter->prot_buf,
+			pi->guard_tag = t10_pi_csum(pi->guard_tag,
-					   offset);
+					iter->prot_buf, offset, bi->csum_type);
 		pi->app_tag = 0;
 
-		if (type == T10_PI_TYPE1_PROTECTION)
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
 			pi->ref_tag = cpu_to_be32(lower_32_bits(iter->seed));
 		else
 			pi->ref_tag = 0;
 
 		iter->data_buf += iter->interval;
-		iter->prot_buf += iter->tuple_size;
+		iter->prot_buf += bi->tuple_size;
 		iter->seed++;
 	}
-
-	return BLK_STS_OK;
 }
 
 static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
-		csum_fn *fn, enum t10_dif_type type)
+		struct blk_integrity *bi)
 {
-	u8 offset = iter->pi_offset;
+	u8 offset = bi->pi_offset;
 	unsigned int i;
 
-	BUG_ON(type == T10_PI_TYPE0_PROTECTION);
-
 	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
 		struct t10_pi_tuple *pi = iter->prot_buf + offset;
 		__be16 csum;
 
-		if (type == T10_PI_TYPE1_PROTECTION ||
+		if (bi->flags & BLK_INTEGRITY_REF_TAG) {
-		    type == T10_PI_TYPE2_PROTECTION) {
 			if (pi->app_tag == T10_PI_APP_ESCAPE)
 				goto next;
 
@@ -82,15 +84,17 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 				       iter->seed, be32_to_cpu(pi->ref_tag));
 				return BLK_STS_PROTECTION;
 			}
-		} else if (type == T10_PI_TYPE3_PROTECTION) {
+		} else {
 			if (pi->app_tag == T10_PI_APP_ESCAPE &&
 			    pi->ref_tag == T10_PI_REF_ESCAPE)
 				goto next;
 		}
 
-		csum = fn(0, iter->data_buf, iter->interval);
+		csum = t10_pi_csum(0, iter->data_buf, iter->interval,
+				bi->csum_type);
 		if (offset)
-			csum = fn(csum, iter->prot_buf, offset);
+			csum = t10_pi_csum(csum, iter->prot_buf, offset,
+					bi->csum_type);
 
 		if (pi->guard_tag != csum) {
 			pr_err("%s: guard tag error at sector %llu " \
@@ -102,33 +106,13 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 
 next:
 		iter->data_buf += iter->interval;
-		iter->prot_buf += iter->tuple_size;
+		iter->prot_buf += bi->tuple_size;
 		iter->seed++;
 	}
 
 	return BLK_STS_OK;
 }
 
-static blk_status_t t10_pi_type1_generate_crc(struct blk_integrity_iter *iter)
-{
-	return t10_pi_generate(iter, t10_pi_crc_fn, T10_PI_TYPE1_PROTECTION);
-}
-
-static blk_status_t t10_pi_type1_generate_ip(struct blk_integrity_iter *iter)
-{
-	return t10_pi_generate(iter, t10_pi_ip_fn, T10_PI_TYPE1_PROTECTION);
-}
-
-static blk_status_t t10_pi_type1_verify_crc(struct blk_integrity_iter *iter)
-{
-	return t10_pi_verify(iter, t10_pi_crc_fn, T10_PI_TYPE1_PROTECTION);
-}
-
-static blk_status_t t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
-{
-	return t10_pi_verify(iter, t10_pi_ip_fn, T10_PI_TYPE1_PROTECTION);
-}
-
 /**
  * t10_pi_type1_prepare - prepare PI prior submitting request to device
  * @rq:              request with PI that should be prepared
@@ -141,7 +125,7 @@ static blk_status_t t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
  */
 static void t10_pi_type1_prepare(struct request *rq)
 {
-	struct blk_integrity *bi = &rq->q->integrity;
+	struct blk_integrity *bi = &rq->q->limits.integrity;
 	const int tuple_sz = bi->tuple_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
@@ -192,7 +176,7 @@ static void t10_pi_type1_prepare(struct request *rq)
  */
 static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
-	struct blk_integrity *bi = &rq->q->integrity;
+	struct blk_integrity *bi = &rq->q->limits.integrity;
 	unsigned intervals = nr_bytes >> bi->interval_exp;
 	const int tuple_sz = bi->tuple_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
@@ -225,81 +209,15 @@ static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 	}
 }
 
-static blk_status_t t10_pi_type3_generate_crc(struct blk_integrity_iter *iter)
-{
-	return t10_pi_generate(iter, t10_pi_crc_fn, T10_PI_TYPE3_PROTECTION);
-}
-
-static blk_status_t t10_pi_type3_generate_ip(struct blk_integrity_iter *iter)
-{
-	return t10_pi_generate(iter, t10_pi_ip_fn, T10_PI_TYPE3_PROTECTION);
-}
-
-static blk_status_t t10_pi_type3_verify_crc(struct blk_integrity_iter *iter)
-{
-	return t10_pi_verify(iter, t10_pi_crc_fn, T10_PI_TYPE3_PROTECTION);
-}
-
-static blk_status_t t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
-{
-	return t10_pi_verify(iter, t10_pi_ip_fn, T10_PI_TYPE3_PROTECTION);
-}
-
-/* Type 3 does not have a reference tag so no remapping is required. */
-static void t10_pi_type3_prepare(struct request *rq)
-{
-}
-
-/* Type 3 does not have a reference tag so no remapping is required. */
-static void t10_pi_type3_complete(struct request *rq, unsigned int nr_bytes)
-{
-}
-
-const struct blk_integrity_profile t10_pi_type1_crc = {
-	.name			= "T10-DIF-TYPE1-CRC",
-	.generate_fn		= t10_pi_type1_generate_crc,
-	.verify_fn		= t10_pi_type1_verify_crc,
-	.prepare_fn		= t10_pi_type1_prepare,
-	.complete_fn		= t10_pi_type1_complete,
-};
-EXPORT_SYMBOL(t10_pi_type1_crc);
-
-const struct blk_integrity_profile t10_pi_type1_ip = {
-	.name			= "T10-DIF-TYPE1-IP",
-	.generate_fn		= t10_pi_type1_generate_ip,
-	.verify_fn		= t10_pi_type1_verify_ip,
-	.prepare_fn		= t10_pi_type1_prepare,
-	.complete_fn		= t10_pi_type1_complete,
-};
-EXPORT_SYMBOL(t10_pi_type1_ip);
-
-const struct blk_integrity_profile t10_pi_type3_crc = {
-	.name			= "T10-DIF-TYPE3-CRC",
-	.generate_fn		= t10_pi_type3_generate_crc,
-	.verify_fn		= t10_pi_type3_verify_crc,
-	.prepare_fn		= t10_pi_type3_prepare,
-	.complete_fn		= t10_pi_type3_complete,
-};
-EXPORT_SYMBOL(t10_pi_type3_crc);
-
-const struct blk_integrity_profile t10_pi_type3_ip = {
-	.name			= "T10-DIF-TYPE3-IP",
-	.generate_fn		= t10_pi_type3_generate_ip,
-	.verify_fn		= t10_pi_type3_verify_ip,
-	.prepare_fn		= t10_pi_type3_prepare,
-	.complete_fn		= t10_pi_type3_complete,
-};
-EXPORT_SYMBOL(t10_pi_type3_ip);
-
 static __be64 ext_pi_crc64(u64 crc, void *data, unsigned int len)
 {
 	return cpu_to_be64(crc64_rocksoft_update(crc, data, len));
 }
 
-static blk_status_t ext_pi_crc64_generate(struct blk_integrity_iter *iter,
+static void ext_pi_crc64_generate(struct blk_integrity_iter *iter,
-					enum t10_dif_type type)
+		struct blk_integrity *bi)
 {
-	u8 offset = iter->pi_offset;
+	u8 offset = bi->pi_offset;
 	unsigned int i;
 
 	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
@@ -311,17 +229,15 @@ static blk_status_t ext_pi_crc64_generate(struct blk_integrity_iter *iter,
 					iter->prot_buf, offset);
 		pi->app_tag = 0;
 
-		if (type == T10_PI_TYPE1_PROTECTION)
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
 			put_unaligned_be48(iter->seed, pi->ref_tag);
 		else
 			put_unaligned_be48(0ULL, pi->ref_tag);
 
 		iter->data_buf += iter->interval;
-		iter->prot_buf += iter->tuple_size;
+		iter->prot_buf += bi->tuple_size;
 		iter->seed++;
 	}
-
-	return BLK_STS_OK;
 }
 
 static bool ext_pi_ref_escape(u8 *ref_tag)
@@ -332,9 +248,9 @@ static bool ext_pi_ref_escape(u8 *ref_tag)
 }
 
 static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
-				      enum t10_dif_type type)
+		struct blk_integrity *bi)
 {
-	u8 offset = iter->pi_offset;
+	u8 offset = bi->pi_offset;
 	unsigned int i;
 
 	for (i = 0; i < iter->data_size; i += iter->interval) {
@@ -342,7 +258,7 @@ static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
 		u64 ref, seed;
 		__be64 csum;
 
-		if (type == T10_PI_TYPE1_PROTECTION) {
+		if (bi->flags & BLK_INTEGRITY_REF_TAG) {
 			if (pi->app_tag == T10_PI_APP_ESCAPE)
 				goto next;
 
@@ -353,7 +269,7 @@ static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
 					iter->disk_name, seed, ref);
 				return BLK_STS_PROTECTION;
 			}
-		} else if (type == T10_PI_TYPE3_PROTECTION) {
+		} else {
 			if (pi->app_tag == T10_PI_APP_ESCAPE &&
 			    ext_pi_ref_escape(pi->ref_tag))
 				goto next;
@@ -374,26 +290,16 @@ static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
 
 next:
 		iter->data_buf += iter->interval;
-		iter->prot_buf += iter->tuple_size;
+		iter->prot_buf += bi->tuple_size;
 		iter->seed++;
 	}
 
 	return BLK_STS_OK;
 }
 
-static blk_status_t ext_pi_type1_verify_crc64(struct blk_integrity_iter *iter)
-{
-	return ext_pi_crc64_verify(iter, T10_PI_TYPE1_PROTECTION);
-}
-
-static blk_status_t ext_pi_type1_generate_crc64(struct blk_integrity_iter *iter)
-{
-	return ext_pi_crc64_generate(iter, T10_PI_TYPE1_PROTECTION);
-}
-
 static void ext_pi_type1_prepare(struct request *rq)
 {
-	struct blk_integrity *bi = &rq->q->integrity;
+	struct blk_integrity *bi = &rq->q->limits.integrity;
 	const int tuple_sz = bi->tuple_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
@@ -433,7 +339,7 @@ static void ext_pi_type1_prepare(struct request *rq)
 
 static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
-	struct blk_integrity *bi = &rq->q->integrity;
+	struct blk_integrity *bi = &rq->q->limits.integrity;
 	unsigned intervals = nr_bytes >> bi->interval_exp;
 	const int tuple_sz = bi->tuple_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
@@ -467,33 +373,105 @@ static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 	}
 }
 
-static blk_status_t ext_pi_type3_verify_crc64(struct blk_integrity_iter *iter)
+void blk_integrity_generate(struct bio *bio)
 {
-	return ext_pi_crc64_verify(iter, T10_PI_TYPE3_PROTECTION);
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+	struct blk_integrity_iter iter;
+	struct bvec_iter bviter;
+	struct bio_vec bv;
+
+	iter.disk_name = bio->bi_bdev->bd_disk->disk_name;
+	iter.interval = 1 << bi->interval_exp;
+	iter.seed = bio->bi_iter.bi_sector;
+	iter.prot_buf = bvec_virt(bip->bip_vec);
+	bio_for_each_segment(bv, bio, bviter) {
+		void *kaddr = bvec_kmap_local(&bv);
+
+		iter.data_buf = kaddr;
+		iter.data_size = bv.bv_len;
+		switch (bi->csum_type) {
+		case BLK_INTEGRITY_CSUM_CRC64:
+			ext_pi_crc64_generate(&iter, bi);
+			break;
+		case BLK_INTEGRITY_CSUM_CRC:
+		case BLK_INTEGRITY_CSUM_IP:
+			t10_pi_generate(&iter, bi);
+			break;
+		default:
+			break;
+		}
+		kunmap_local(kaddr);
+	}
 }
 
-static blk_status_t ext_pi_type3_generate_crc64(struct blk_integrity_iter *iter)
+void blk_integrity_verify(struct bio *bio)
 {
-	return ext_pi_crc64_generate(iter, T10_PI_TYPE3_PROTECTION);
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+	struct blk_integrity_iter iter;
+	struct bvec_iter bviter;
+	struct bio_vec bv;
+
+	/*
+	 * At the moment verify is called bi_iter has been advanced during split
+	 * and completion, so use the copy created during submission here.
+	 */
+	iter.disk_name = bio->bi_bdev->bd_disk->disk_name;
+	iter.interval = 1 << bi->interval_exp;
+	iter.seed = bip->bio_iter.bi_sector;
+	iter.prot_buf = bvec_virt(bip->bip_vec);
+	__bio_for_each_segment(bv, bio, bviter, bip->bio_iter) {
+		void *kaddr = bvec_kmap_local(&bv);
+		blk_status_t ret = BLK_STS_OK;
+
+		iter.data_buf = kaddr;
+		iter.data_size = bv.bv_len;
+		switch (bi->csum_type) {
+		case BLK_INTEGRITY_CSUM_CRC64:
+			ret = ext_pi_crc64_verify(&iter, bi);
+			break;
+		case BLK_INTEGRITY_CSUM_CRC:
+		case BLK_INTEGRITY_CSUM_IP:
+			ret = t10_pi_verify(&iter, bi);
+			break;
+		default:
+			break;
+		}
+		kunmap_local(kaddr);
+
+		if (ret) {
+			bio->bi_status = ret;
+			return;
+		}
+	}
 }
 
-const struct blk_integrity_profile ext_pi_type1_crc64 = {
+void blk_integrity_prepare(struct request *rq)
-	.name			= "EXT-DIF-TYPE1-CRC64",
+{
-	.generate_fn		= ext_pi_type1_generate_crc64,
+	struct blk_integrity *bi = &rq->q->limits.integrity;
-	.verify_fn		= ext_pi_type1_verify_crc64,
-	.prepare_fn		= ext_pi_type1_prepare,
-	.complete_fn		= ext_pi_type1_complete,
-};
-EXPORT_SYMBOL_GPL(ext_pi_type1_crc64);
 
-const struct blk_integrity_profile ext_pi_type3_crc64 = {
+	if (!(bi->flags & BLK_INTEGRITY_REF_TAG))
-	.name			= "EXT-DIF-TYPE3-CRC64",
+		return;
-	.generate_fn		= ext_pi_type3_generate_crc64,
+
-	.verify_fn		= ext_pi_type3_verify_crc64,
+	if (bi->csum_type == BLK_INTEGRITY_CSUM_CRC64)
-	.prepare_fn		= t10_pi_type3_prepare,
+		ext_pi_type1_prepare(rq);
-	.complete_fn		= t10_pi_type3_complete,
+	else
-};
+		t10_pi_type1_prepare(rq);
-EXPORT_SYMBOL_GPL(ext_pi_type3_crc64);
+}
+
+void blk_integrity_complete(struct request *rq, unsigned int nr_bytes)
+{
+	struct blk_integrity *bi = &rq->q->limits.integrity;
+
+	if (!(bi->flags & BLK_INTEGRITY_REF_TAG))
+		return;
+
+	if (bi->csum_type == BLK_INTEGRITY_CSUM_CRC64)
+		ext_pi_type1_complete(rq, nr_bytes);
+	else
+		t10_pi_type1_complete(rq, nr_bytes);
+}
 
 MODULE_DESCRIPTION("T10 Protection Information module");
 MODULE_LICENSE("GPL");

drivers/ata/libata-scsi.c

@@ -1024,7 +1024,6 @@ EXPORT_SYMBOL_GPL(ata_scsi_dma_need_drain);
 int ata_scsi_dev_config(struct scsi_device *sdev, struct queue_limits *lim,
 		struct ata_device *dev)
 {
-	struct request_queue *q = sdev->request_queue;
 	int depth = 1;
 
 	if (!ata_id_has_unload(dev->id))
@@ -1038,7 +1037,7 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct queue_limits *lim,
 		sdev->sector_size = ATA_SECT_SIZE;
 
 		/* set DMA padding */
-		blk_queue_update_dma_pad(q, ATA_DMA_PAD_SZ - 1);
+		lim->dma_pad_mask = ATA_DMA_PAD_SZ - 1;
 
 		/* make room for appending the drain */
 		lim->max_segments--;

drivers/ata/pata_macio.c

@@ -816,7 +816,7 @@ static int pata_macio_device_configure(struct scsi_device *sdev,
 	/* OHare has issues with non cache aligned DMA on some chipsets */
 	if (priv->kind == controller_ohare) {
 		lim->dma_alignment = 31;
-		blk_queue_update_dma_pad(sdev->request_queue, 31);
+		lim->dma_pad_mask = 31;
 
 		/* Tell the world about it */
 		ata_dev_info(dev, "OHare alignment limits applied\n");
@@ -831,7 +831,7 @@ static int pata_macio_device_configure(struct scsi_device *sdev,
 	if (priv->kind == controller_sh_ata6 || priv->kind == controller_k2_ata6) {
 		/* Allright these are bad, apply restrictions */
 		lim->dma_alignment = 15;
-		blk_queue_update_dma_pad(sdev->request_queue, 15);
+		lim->dma_pad_mask = 15;
 
 		/* We enable MWI and hack cache line size directly here, this
 		 * is specific to this chipset and not normal values, we happen

drivers/block/Kconfig

@@ -354,6 +354,15 @@ config VIRTIO_BLK
 	  This is the virtual block driver for virtio.  It can be used with
           QEMU based VMMs (like KVM or Xen).  Say Y or M.
 
+config BLK_DEV_RUST_NULL
+	tristate "Rust null block driver (Experimental)"
+	depends on RUST
+	help
+	  This is the Rust implementation of the null block driver. For now it
+	  is only a minimal stub.
+
+	  If unsure, say N.
+
 config BLK_DEV_RBD
 	tristate "Rados block device (RBD)"
 	depends on INET && BLOCK

drivers/block/Makefile

@@ -9,6 +9,9 @@
 # needed for trace events
 ccflags-y				+= -I$(src)
 
+obj-$(CONFIG_BLK_DEV_RUST_NULL) += rnull_mod.o
+rnull_mod-y := rnull.o
+
 obj-$(CONFIG_MAC_FLOPPY)	+= swim3.o
 obj-$(CONFIG_BLK_DEV_SWIM)	+= swim_mod.o
 obj-$(CONFIG_BLK_DEV_FD)	+= floppy.o

drivers/block/amiflop.c

@@ -232,6 +232,7 @@ static DEFINE_MUTEX(amiflop_mutex);
 static unsigned long int fd_def_df0 = FD_DD_3;     /* default for df0 if it doesn't identify */
 
 module_param(fd_def_df0, ulong, 0);
+MODULE_DESCRIPTION("Amiga floppy driver");
 MODULE_LICENSE("GPL");
 
 /*
@@ -1776,10 +1777,13 @@ static const struct blk_mq_ops amiflop_mq_ops = {
 
 static int fd_alloc_disk(int drive, int system)
 {
+	struct queue_limits lim = {
+		.features		= BLK_FEAT_ROTATIONAL,
+	};
 	struct gendisk *disk;
 	int err;
 
-	disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL, NULL);
+	disk = blk_mq_alloc_disk(&unit[drive].tag_set, &lim, NULL);
 	if (IS_ERR(disk))
 		return PTR_ERR(disk);
 

drivers/block/aoe/aoeblk.c

@@ -337,6 +337,7 @@ aoeblk_gdalloc(void *vp)
 	struct queue_limits lim = {
 		.max_hw_sectors		= aoe_maxsectors,
 		.io_opt			= SZ_2M,
+		.features		= BLK_FEAT_ROTATIONAL,
 	};
 	ulong flags;
 	int late = 0;

drivers/block/ataflop.c

@@ -1992,9 +1992,12 @@ static const struct blk_mq_ops ataflop_mq_ops = {
 
 static int ataflop_alloc_disk(unsigned int drive, unsigned int type)
 {
+	struct queue_limits lim = {
+		.features		= BLK_FEAT_ROTATIONAL,
+	};
 	struct gendisk *disk;
 
-	disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL, NULL);
+	disk = blk_mq_alloc_disk(&unit[drive].tag_set, &lim, NULL);
 	if (IS_ERR(disk))
 		return PTR_ERR(disk);
 
@@ -2197,4 +2200,5 @@ static void __exit atari_floppy_exit(void)
 module_init(atari_floppy_init)
 module_exit(atari_floppy_exit)
 
+MODULE_DESCRIPTION("Atari floppy driver");
 MODULE_LICENSE("GPL");

drivers/block/brd.c

@@ -296,6 +296,7 @@ static int max_part = 1;
 module_param(max_part, int, 0444);
 MODULE_PARM_DESC(max_part, "Num Minors to reserve between devices");
 
+MODULE_DESCRIPTION("Ram backed block device driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(RAMDISK_MAJOR);
 MODULE_ALIAS("rd");
@@ -335,6 +336,8 @@ static int brd_alloc(int i)
 		.max_hw_discard_sectors	= UINT_MAX,
 		.max_discard_segments	= 1,
 		.discard_granularity	= PAGE_SIZE,
+		.features		= BLK_FEAT_SYNCHRONOUS |
+					  BLK_FEAT_NOWAIT,
 	};
 
 	list_for_each_entry(brd, &brd_devices, brd_list)
@@ -366,10 +369,6 @@ static int brd_alloc(int i)
 	strscpy(disk->disk_name, buf, DISK_NAME_LEN);
 	set_capacity(disk, rd_size * 2);
 	
-	/* Tell the block layer that this is not a rotational device */
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
-	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, disk->queue);
-	blk_queue_flag_set(QUEUE_FLAG_NOWAIT, disk->queue);
 	err = add_disk(disk);
 	if (err)
 		goto out_cleanup_disk;

drivers/block/drbd/drbd_main.c

@@ -2697,6 +2697,9 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 		 * connect.
 		 */
 		.max_hw_sectors		= DRBD_MAX_BIO_SIZE_SAFE >> 8,
+		.features		= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA |
+					  BLK_FEAT_ROTATIONAL |
+					  BLK_FEAT_STABLE_WRITES,
 	};
 
 	device = minor_to_device(minor);
@@ -2735,9 +2738,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	sprintf(disk->disk_name, "drbd%d", minor);
 	disk->private_data = device;
 
-	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);
-	blk_queue_write_cache(disk->queue, true, true);
-
 	device->md_io.page = alloc_page(GFP_KERNEL);
 	if (!device->md_io.page)
 		goto out_no_io_page;

drivers/block/floppy.c

@@ -4516,7 +4516,8 @@ static bool floppy_available(int drive)
 static int floppy_alloc_disk(unsigned int drive, unsigned int type)
 {
 	struct queue_limits lim = {
-		.max_hw_sectors = 64,
+		.max_hw_sectors		= 64,
+		.features		= BLK_FEAT_ROTATIONAL,
 	};
 	struct gendisk *disk;
 
@@ -5016,6 +5017,7 @@ module_param(floppy, charp, 0);
 module_param(FLOPPY_IRQ, int, 0);
 module_param(FLOPPY_DMA, int, 0);
 MODULE_AUTHOR("Alain L. Knaff");
+MODULE_DESCRIPTION("Normal floppy disk support");
 MODULE_LICENSE("GPL");
 
 /* This doesn't actually get used other than for module information */

drivers/block/loop.c

@@ -211,13 +211,10 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
 	if (lo->lo_state == Lo_bound)
 		blk_mq_freeze_queue(lo->lo_queue);
 	lo->use_dio = use_dio;
-	if (use_dio) {
+	if (use_dio)
-		blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, lo->lo_queue);
 		lo->lo_flags |= LO_FLAGS_DIRECT_IO;
-	} else {
+	else
-		blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue);
 		lo->lo_flags &= ~LO_FLAGS_DIRECT_IO;
-	}
 	if (lo->lo_state == Lo_bound)
 		blk_mq_unfreeze_queue(lo->lo_queue);
 }
@@ -939,24 +936,6 @@ static void loop_free_idle_workers_timer(struct timer_list *timer)
 	return loop_free_idle_workers(lo, false);
 }
 
-static void loop_update_rotational(struct loop_device *lo)
-{
-	struct file *file = lo->lo_backing_file;
-	struct inode *file_inode = file->f_mapping->host;
-	struct block_device *file_bdev = file_inode->i_sb->s_bdev;
-	struct request_queue *q = lo->lo_queue;
-	bool nonrot = true;
-
-	/* not all filesystems (e.g. tmpfs) have a sb->s_bdev */
-	if (file_bdev)
-		nonrot = bdev_nonrot(file_bdev);
-
-	if (nonrot)
-		blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-	else
-		blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
-}
-
 /**
  * loop_set_status_from_info - configure device from loop_info
  * @lo: struct loop_device to configure
@@ -998,17 +977,40 @@ loop_set_status_from_info(struct loop_device *lo,
 	return 0;
 }
 
-static int loop_reconfigure_limits(struct loop_device *lo, unsigned short bsize,
+static unsigned short loop_default_blocksize(struct loop_device *lo,
-		bool update_discard_settings)
+		struct block_device *backing_bdev)
 {
+	/* In case of direct I/O, match underlying block size */
+	if ((lo->lo_backing_file->f_flags & O_DIRECT) && backing_bdev)
+		return bdev_logical_block_size(backing_bdev);
+	return SECTOR_SIZE;
+}
+
+static int loop_reconfigure_limits(struct loop_device *lo, unsigned short bsize)
+{
+	struct file *file = lo->lo_backing_file;
+	struct inode *inode = file->f_mapping->host;
+	struct block_device *backing_bdev = NULL;
 	struct queue_limits lim;
 
+	if (S_ISBLK(inode->i_mode))
+		backing_bdev = I_BDEV(inode);
+	else if (inode->i_sb->s_bdev)
+		backing_bdev = inode->i_sb->s_bdev;
+
+	if (!bsize)
+		bsize = loop_default_blocksize(lo, backing_bdev);
+
 	lim = queue_limits_start_update(lo->lo_queue);
 	lim.logical_block_size = bsize;
 	lim.physical_block_size = bsize;
 	lim.io_min = bsize;
-	if (update_discard_settings)
+	lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_ROTATIONAL);
-		loop_config_discard(lo, &lim);
+	if (file->f_op->fsync && !(lo->lo_flags & LO_FLAGS_READ_ONLY))
+		lim.features |= BLK_FEAT_WRITE_CACHE;
+	if (backing_bdev && !bdev_nonrot(backing_bdev))
+		lim.features |= BLK_FEAT_ROTATIONAL;
+	loop_config_discard(lo, &lim);
 	return queue_limits_commit_update(lo->lo_queue, &lim);
 }
 
@@ -1017,12 +1019,10 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 			  const struct loop_config *config)
 {
 	struct file *file = fget(config->fd);
-	struct inode *inode;
 	struct address_space *mapping;
 	int error;
 	loff_t size;
 	bool partscan;
-	unsigned short bsize;
 	bool is_loop;
 
 	if (!file)
@@ -1055,19 +1055,12 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 		goto out_unlock;
 
 	mapping = file->f_mapping;
-	inode = mapping->host;
 
 	if ((config->info.lo_flags & ~LOOP_CONFIGURE_SETTABLE_FLAGS) != 0) {
 		error = -EINVAL;
 		goto out_unlock;
 	}
 
-	if (config->block_size) {
-		error = blk_validate_block_size(config->block_size);
-		if (error)
-			goto out_unlock;
-	}
-
 	error = loop_set_status_from_info(lo, &config->info);
 	if (error)
 		goto out_unlock;
@@ -1098,22 +1091,10 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 	lo->old_gfp_mask = mapping_gfp_mask(mapping);
 	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 
-	if (!(lo->lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
+	error = loop_reconfigure_limits(lo, config->block_size);
-		blk_queue_write_cache(lo->lo_queue, true, false);
+	if (error)
-
-	if (config->block_size)
-		bsize = config->block_size;
-	else if ((lo->lo_backing_file->f_flags & O_DIRECT) && inode->i_sb->s_bdev)
-		/* In case of direct I/O, match underlying block size */
-		bsize = bdev_logical_block_size(inode->i_sb->s_bdev);
-	else
-		bsize = 512;
-
-	error = loop_reconfigure_limits(lo, bsize, true);
-	if (WARN_ON_ONCE(error))
 		goto out_unlock;
 
-	loop_update_rotational(lo);
 	loop_update_dio(lo);
 	loop_sysfs_init(lo);
 
@@ -1154,22 +1135,12 @@ out_putf:
 	return error;
 }
 
-static void __loop_clr_fd(struct loop_device *lo, bool release)
+static void __loop_clr_fd(struct loop_device *lo)
 {
+	struct queue_limits lim;
 	struct file *filp;
 	gfp_t gfp = lo->old_gfp_mask;
 
-	if (test_bit(QUEUE_FLAG_WC, &lo->lo_queue->queue_flags))
-		blk_queue_write_cache(lo->lo_queue, false, false);
-
-	/*
-	 * Freeze the request queue when unbinding on a live file descriptor and
-	 * thus an open device.  When called from ->release we are guaranteed
-	 * that there is no I/O in progress already.
-	 */
-	if (!release)
-		blk_mq_freeze_queue(lo->lo_queue);
-
 	spin_lock_irq(&lo->lo_lock);
 	filp = lo->lo_backing_file;
 	lo->lo_backing_file = NULL;
@@ -1179,7 +1150,14 @@ static void __loop_clr_fd(struct loop_device *lo, bool release)
 	lo->lo_offset = 0;
 	lo->lo_sizelimit = 0;
 	memset(lo->lo_file_name, 0, LO_NAME_SIZE);
-	loop_reconfigure_limits(lo, 512, false);
+
+	/* reset the block size to the default */
+	lim = queue_limits_start_update(lo->lo_queue);
+	lim.logical_block_size = SECTOR_SIZE;
+	lim.physical_block_size = SECTOR_SIZE;
+	lim.io_min = SECTOR_SIZE;
+	queue_limits_commit_update(lo->lo_queue, &lim);
+
 	invalidate_disk(lo->lo_disk);
 	loop_sysfs_exit(lo);
 	/* let user-space know about this change */
@@ -1187,8 +1165,6 @@ static void __loop_clr_fd(struct loop_device *lo, bool release)
 	mapping_set_gfp_mask(filp->f_mapping, gfp);
 	/* This is safe: open() is still holding a reference. */
 	module_put(THIS_MODULE);
-	if (!release)
-		blk_mq_unfreeze_queue(lo->lo_queue);
 
 	disk_force_media_change(lo->lo_disk);
 
@@ -1203,11 +1179,7 @@ static void __loop_clr_fd(struct loop_device *lo, bool release)
 		 * must be at least one and it can only become zero when the
 		 * current holder is released.
 		 */
-		if (!release)
-			mutex_lock(&lo->lo_disk->open_mutex);
 		err = bdev_disk_changed(lo->lo_disk, false);
-		if (!release)
-			mutex_unlock(&lo->lo_disk->open_mutex);
 		if (err)
 			pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
 				__func__, lo->lo_number, err);
@@ -1256,24 +1228,16 @@ static int loop_clr_fd(struct loop_device *lo)
 		return -ENXIO;
 	}
 	/*
-	 * If we've explicitly asked to tear down the loop device,
+	 * Mark the device for removing the backing device on last close.
-	 * and it has an elevated reference count, set it for auto-teardown when
+	 * If we are the only opener, also switch the state to roundown here to
-	 * the last reference goes away. This stops $!~#$@ udev from
+	 * prevent new openers from coming in.
-	 * preventing teardown because it decided that it needs to run blkid on
-	 * the loopback device whenever they appear. xfstests is notorious for
-	 * failing tests because blkid via udev races with a losetup
-	 * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d
-	 * command to fail with EBUSY.
 	 */
-	if (disk_openers(lo->lo_disk) > 1) {
+
-		lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
+	lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
-		loop_global_unlock(lo, true);
+	if (disk_openers(lo->lo_disk) == 1)
-		return 0;
+		lo->lo_state = Lo_rundown;
-	}
-	lo->lo_state = Lo_rundown;
 	loop_global_unlock(lo, true);
 
-	__loop_clr_fd(lo, false);
 	return 0;
 }
 
@@ -1500,10 +1464,6 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 	if (lo->lo_state != Lo_bound)
 		return -ENXIO;
 
-	err = blk_validate_block_size(arg);
-	if (err)
-		return err;
-
 	if (lo->lo_queue->limits.logical_block_size == arg)
 		return 0;
 
@@ -1511,7 +1471,7 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 	invalidate_bdev(lo->lo_device);
 
 	blk_mq_freeze_queue(lo->lo_queue);
-	err = loop_reconfigure_limits(lo, arg, false);
+	err = loop_reconfigure_limits(lo, arg);
 	loop_update_dio(lo);
 	blk_mq_unfreeze_queue(lo->lo_queue);
 
@@ -1740,25 +1700,43 @@ static int lo_compat_ioctl(struct block_device *bdev, blk_mode_t mode,
 }
 #endif
 
+static int lo_open(struct gendisk *disk, blk_mode_t mode)
+{
+	struct loop_device *lo = disk->private_data;
+	int err;
+
+	err = mutex_lock_killable(&lo->lo_mutex);
+	if (err)
+		return err;
+
+	if (lo->lo_state == Lo_deleting || lo->lo_state == Lo_rundown)
+		err = -ENXIO;
+	mutex_unlock(&lo->lo_mutex);
+	return err;
+}
+
 static void lo_release(struct gendisk *disk)
 {
 	struct loop_device *lo = disk->private_data;
+	bool need_clear = false;
 
 	if (disk_openers(disk) > 0)
 		return;
+	/*
+	 * Clear the backing device information if this is the last close of
+	 * a device that's been marked for auto clear, or on which LOOP_CLR_FD
+	 * has been called.
+	 */
 
 	mutex_lock(&lo->lo_mutex);
-	if (lo->lo_state == Lo_bound && (lo->lo_flags & LO_FLAGS_AUTOCLEAR)) {
+	if (lo->lo_state == Lo_bound && (lo->lo_flags & LO_FLAGS_AUTOCLEAR))
 		lo->lo_state = Lo_rundown;
-		mutex_unlock(&lo->lo_mutex);
+
-		/*
+	need_clear = (lo->lo_state == Lo_rundown);
-		 * In autoclear mode, stop the loop thread
-		 * and remove configuration after last close.
-		 */
-		__loop_clr_fd(lo, true);
-		return;
-	}
 	mutex_unlock(&lo->lo_mutex);
+
+	if (need_clear)
+		__loop_clr_fd(lo);
 }
 
 static void lo_free_disk(struct gendisk *disk)
@@ -1775,6 +1753,7 @@ static void lo_free_disk(struct gendisk *disk)
 
 static const struct block_device_operations lo_fops = {
 	.owner =	THIS_MODULE,
+	.open =         lo_open,
 	.release =	lo_release,
 	.ioctl =	lo_ioctl,
 #ifdef CONFIG_COMPAT
@@ -1853,6 +1832,7 @@ static const struct kernel_param_ops loop_hw_qdepth_param_ops = {
 device_param_cb(hw_queue_depth, &loop_hw_qdepth_param_ops, &hw_queue_depth, 0444);
 MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: " __stringify(LOOP_DEFAULT_HW_Q_DEPTH));
 
+MODULE_DESCRIPTION("Loopback device support");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR);
 
@@ -2059,14 +2039,6 @@ static int loop_add(int i)
 	}
 	lo->lo_queue = lo->lo_disk->queue;
 
-	/*
-	 * By default, we do buffer IO, so it doesn't make sense to enable
-	 * merge because the I/O submitted to backing file is handled page by
-	 * page. For directio mode, merge does help to dispatch bigger request
-	 * to underlayer disk. We will enable merge once directio is enabled.
-	 */
-	blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue);
-
 	/*
 	 * Disable partition scanning by default. The in-kernel partition
 	 * scanning can be requested individually per-device during its

drivers/block/mtip32xx/mtip32xx.c

@@ -3485,8 +3485,6 @@ skip_create_disk:
 		goto start_service_thread;
 
 	/* Set device limits. */
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, dd->queue);
-	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, dd->queue);
 	dma_set_max_seg_size(&dd->pdev->dev, 0x400000);
 
 	/* Set the capacity of the device in 512 byte sectors. */

drivers/block/n64cart.c

@@ -150,8 +150,6 @@ static int __init n64cart_probe(struct platform_device *pdev)
 	set_capacity(disk, size >> SECTOR_SHIFT);
 	set_disk_ro(disk, 1);
 
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
-
 	err = add_disk(disk);
 	if (err)
 		goto out_cleanup_disk;

drivers/block/nbd.c

@@ -342,6 +342,14 @@ static int __nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
 		lim.max_hw_discard_sectors = UINT_MAX;
 	else
 		lim.max_hw_discard_sectors = 0;
+	if (!(nbd->config->flags & NBD_FLAG_SEND_FLUSH)) {
+		lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA);
+	} else if (nbd->config->flags & NBD_FLAG_SEND_FUA) {
+		lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA;
+	} else {
+		lim.features |= BLK_FEAT_WRITE_CACHE;
+		lim.features &= ~BLK_FEAT_FUA;
+	}
 	lim.logical_block_size = blksize;
 	lim.physical_block_size = blksize;
 	error = queue_limits_commit_update(nbd->disk->queue, &lim);
@@ -1279,19 +1287,10 @@ static void nbd_bdev_reset(struct nbd_device *nbd)
 
 static void nbd_parse_flags(struct nbd_device *nbd)
 {
-	struct nbd_config *config = nbd->config;
+	if (nbd->config->flags & NBD_FLAG_READ_ONLY)
-	if (config->flags & NBD_FLAG_READ_ONLY)
 		set_disk_ro(nbd->disk, true);
 	else
 		set_disk_ro(nbd->disk, false);
-	if (config->flags & NBD_FLAG_SEND_FLUSH) {
-		if (config->flags & NBD_FLAG_SEND_FUA)
-			blk_queue_write_cache(nbd->disk->queue, true, true);
-		else
-			blk_queue_write_cache(nbd->disk->queue, true, false);
-	}
-	else
-		blk_queue_write_cache(nbd->disk->queue, false, false);
 }
 
 static void send_disconnects(struct nbd_device *nbd)
@@ -1801,7 +1800,7 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 {
 	struct queue_limits lim = {
 		.max_hw_sectors		= 65536,
-		.max_user_sectors	= 256,
+		.io_opt			= 256 << SECTOR_SHIFT,
 		.max_segments		= USHRT_MAX,
 		.max_segment_size	= UINT_MAX,
 	};
@@ -1861,11 +1860,6 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 		goto out_err_disk;
 	}
 
-	/*
-	 * Tell the block layer that we are not a rotational device
-	 */
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
-
 	mutex_init(&nbd->config_lock);
 	refcount_set(&nbd->config_refs, 0);
 	/*

drivers/block/null_blk/main.c

@@ -77,7 +77,7 @@ enum {
 	NULL_IRQ_TIMER		= 2,
 };
 
-static bool g_virt_boundary = false;
+static bool g_virt_boundary;
 module_param_named(virt_boundary, g_virt_boundary, bool, 0444);
 MODULE_PARM_DESC(virt_boundary, "Require a virtual boundary for the device. Default: False");
 
@@ -227,7 +227,7 @@ MODULE_PARM_DESC(mbps, "Cache size in MiB for memory-backed device. Default: 0 (
 
 static bool g_fua = true;
 module_param_named(fua, g_fua, bool, 0444);
-MODULE_PARM_DESC(zoned, "Enable/disable FUA support when cache_size is used. Default: true");
+MODULE_PARM_DESC(fua, "Enable/disable FUA support when cache_size is used. Default: true");
 
 static unsigned int g_mbps;
 module_param_named(mbps, g_mbps, uint, 0444);
@@ -262,6 +262,10 @@ module_param_named(zone_append_max_sectors, g_zone_append_max_sectors, int, 0444
 MODULE_PARM_DESC(zone_append_max_sectors,
 		 "Maximum size of a zone append command (in 512B sectors). Specify 0 for zone append emulation");
 
+static bool g_zone_full;
+module_param_named(zone_full, g_zone_full, bool, S_IRUGO);
+MODULE_PARM_DESC(zone_full, "Initialize the sequential write required zones of a zoned device to be full. Default: false");
+
 static struct nullb_device *null_alloc_dev(void);
 static void null_free_dev(struct nullb_device *dev);
 static void null_del_dev(struct nullb *nullb);
@@ -458,6 +462,7 @@ NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
 NULLB_DEVICE_ATTR(zone_max_open, uint, NULL);
 NULLB_DEVICE_ATTR(zone_max_active, uint, NULL);
 NULLB_DEVICE_ATTR(zone_append_max_sectors, uint, NULL);
+NULLB_DEVICE_ATTR(zone_full, bool, NULL);
 NULLB_DEVICE_ATTR(virt_boundary, bool, NULL);
 NULLB_DEVICE_ATTR(no_sched, bool, NULL);
 NULLB_DEVICE_ATTR(shared_tags, bool, NULL);
@@ -610,6 +615,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_zone_append_max_sectors,
 	&nullb_device_attr_zone_readonly,
 	&nullb_device_attr_zone_offline,
+	&nullb_device_attr_zone_full,
 	&nullb_device_attr_virt_boundary,
 	&nullb_device_attr_no_sched,
 	&nullb_device_attr_shared_tags,
@@ -700,7 +706,7 @@ static ssize_t memb_group_features_show(struct config_item *item, char *page)
 			"shared_tags,size,submit_queues,use_per_node_hctx,"
 			"virt_boundary,zoned,zone_capacity,zone_max_active,"
 			"zone_max_open,zone_nr_conv,zone_offline,zone_readonly,"
-			"zone_size,zone_append_max_sectors\n");
+			"zone_size,zone_append_max_sectors,zone_full\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -781,6 +787,7 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->zone_max_open = g_zone_max_open;
 	dev->zone_max_active = g_zone_max_active;
 	dev->zone_append_max_sectors = g_zone_append_max_sectors;
+	dev->zone_full = g_zone_full;
 	dev->virt_boundary = g_virt_boundary;
 	dev->no_sched = g_no_sched;
 	dev->shared_tags = g_shared_tags;
@@ -1824,9 +1831,6 @@ static int null_validate_conf(struct nullb_device *dev)
 		dev->queue_mode = NULL_Q_MQ;
 	}
 
-	if (blk_validate_block_size(dev->blocksize))
-		return -EINVAL;
-
 	if (dev->use_per_node_hctx) {
 		if (dev->submit_queues != nr_online_nodes)
 			dev->submit_queues = nr_online_nodes;
@@ -1928,6 +1932,13 @@ static int null_add_dev(struct nullb_device *dev)
 			goto out_cleanup_tags;
 	}
 
+	if (dev->cache_size > 0) {
+		set_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags);
+		lim.features |= BLK_FEAT_WRITE_CACHE;
+		if (dev->fua)
+			lim.features |= BLK_FEAT_FUA;
+	}
+
 	nullb->disk = blk_mq_alloc_disk(nullb->tag_set, &lim, nullb);
 	if (IS_ERR(nullb->disk)) {
 		rv = PTR_ERR(nullb->disk);
@@ -1940,13 +1951,7 @@ static int null_add_dev(struct nullb_device *dev)
 		nullb_setup_bwtimer(nullb);
 	}
 
-	if (dev->cache_size > 0) {
-		set_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags);
-		blk_queue_write_cache(nullb->q, true, dev->fua);
-	}
-
 	nullb->q->queuedata = nullb;
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
 
 	rv = ida_alloc(&nullb_indexes, GFP_KERNEL);
 	if (rv < 0)

drivers/block/null_blk/null_blk.h

@@ -101,6 +101,7 @@ struct nullb_device {
 	bool memory_backed; /* if data is stored in memory */
 	bool discard; /* if support discard */
 	bool zoned; /* if device is zoned */
+	bool zone_full; /* Initialize zones to be full */
 	bool virt_boundary; /* virtual boundary on/off for the device */
 	bool no_sched; /* no IO scheduler for the device */
 	bool shared_tags; /* share tag set between devices for blk-mq */

drivers/block/null_blk/zoned.c

@@ -145,7 +145,7 @@ int null_init_zoned_dev(struct nullb_device *dev,
 		zone = &dev->zones[i];
 
 		null_init_zone_lock(dev, zone);
-		zone->start = zone->wp = sector;
+		zone->start = sector;
 		if (zone->start + dev->zone_size_sects > dev_capacity_sects)
 			zone->len = dev_capacity_sects - zone->start;
 		else
@@ -153,12 +153,18 @@ int null_init_zoned_dev(struct nullb_device *dev,
 		zone->capacity =
 			min_t(sector_t, zone->len, zone_capacity_sects);
 		zone->type = BLK_ZONE_TYPE_SEQWRITE_REQ;
-		zone->cond = BLK_ZONE_COND_EMPTY;
+		if (dev->zone_full) {
+			zone->cond = BLK_ZONE_COND_FULL;
+			zone->wp = zone->start + zone->capacity;
+		} else{
+			zone->cond = BLK_ZONE_COND_EMPTY;
+			zone->wp = zone->start;
+		}
 
 		sector += dev->zone_size_sects;
 	}
 
-	lim->zoned = true;
+	lim->features |= BLK_FEAT_ZONED;
 	lim->chunk_sectors = dev->zone_size_sects;
 	lim->max_zone_append_sectors = dev->zone_append_max_sectors;
 	lim->max_open_zones = dev->zone_max_open;
@@ -171,9 +177,6 @@ int null_register_zoned_dev(struct nullb *nullb)
 	struct request_queue *q = nullb->q;
 	struct gendisk *disk = nullb->disk;
 
-	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
-	disk->nr_zones = bdev_nr_zones(disk->part0);
-
 	pr_info("%s: using %s zone append\n",
 		disk->disk_name,
 		queue_emulates_zone_append(q) ? "emulated" : "native");

drivers/block/pktcdvd.c

@@ -2622,6 +2622,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 	struct queue_limits lim = {
 		.max_hw_sectors		= PACKET_MAX_SECTORS,
 		.logical_block_size	= CD_FRAMESIZE,
+		.features		= BLK_FEAT_ROTATIONAL,
 	};
 	int idx;
 	int ret = -ENOMEM;

drivers/block/ps3disk.c

@@ -388,9 +388,9 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 		.max_segments		= -1,
 		.max_segment_size	= dev->bounce_size,
 		.dma_alignment		= dev->blk_size - 1,
+		.features		= BLK_FEAT_WRITE_CACHE |
+					  BLK_FEAT_ROTATIONAL,
 	};
-
-	struct request_queue *queue;
 	struct gendisk *gendisk;
 
 	if (dev->blk_size < 512) {
@@ -447,10 +447,6 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 		goto fail_free_tag_set;
 	}
 
-	queue = gendisk->queue;
-
-	blk_queue_write_cache(queue, true, false);
-
 	priv->gendisk = gendisk;
 	gendisk->major = ps3disk_major;
 	gendisk->first_minor = devidx * PS3DISK_MINORS;

drivers/block/rbd.c

@@ -4949,14 +4949,12 @@ static const struct blk_mq_ops rbd_mq_ops = {
 static int rbd_init_disk(struct rbd_device *rbd_dev)
 {
 	struct gendisk *disk;
-	struct request_queue *q;
 	unsigned int objset_bytes =
 	    rbd_dev->layout.object_size * rbd_dev->layout.stripe_count;
 	struct queue_limits lim = {
 		.max_hw_sectors		= objset_bytes >> SECTOR_SHIFT,
-		.max_user_sectors	= objset_bytes >> SECTOR_SHIFT,
+		.io_opt			= objset_bytes,
 		.io_min			= rbd_dev->opts->alloc_size,
-		.io_opt			= rbd_dev->opts->alloc_size,
 		.max_segments		= USHRT_MAX,
 		.max_segment_size	= UINT_MAX,
 	};
@@ -4980,12 +4978,14 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 		lim.max_write_zeroes_sectors = objset_bytes >> SECTOR_SHIFT;
 	}
 
+	if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
+		lim.features |= BLK_FEAT_STABLE_WRITES;
+
 	disk = blk_mq_alloc_disk(&rbd_dev->tag_set, &lim, rbd_dev);
 	if (IS_ERR(disk)) {
 		err = PTR_ERR(disk);
 		goto out_tag_set;
 	}
-	q = disk->queue;
 
 	snprintf(disk->disk_name, sizeof(disk->disk_name), RBD_DRV_NAME "%d",
 		 rbd_dev->dev_id);
@@ -4997,13 +4997,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 		disk->minors = RBD_MINORS_PER_MAJOR;
 	disk->fops = &rbd_bd_ops;
 	disk->private_data = rbd_dev;
-
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-	/* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */
-
-	if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
-		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
-
 	rbd_dev->disk = disk;
 
 	return 0;

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

@@ -475,7 +475,7 @@ void rnbd_clt_remove_dev_symlink(struct rnbd_clt_dev *dev)
 	}
 }
 
-static struct kobj_type rnbd_dev_ktype = {
+static const struct kobj_type rnbd_dev_ktype = {
 	.sysfs_ops      = &kobj_sysfs_ops,
 	.default_groups = rnbd_dev_groups,
 };

drivers/block/rnbd/rnbd-clt.c

@@ -1352,10 +1352,6 @@ static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev,
 	if (dev->access_mode == RNBD_ACCESS_RO)
 		set_disk_ro(dev->gd, true);
 
-	/*
-	 * Network device does not need rotational
-	 */
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, dev->queue);
 	err = add_disk(dev->gd);
 	if (err)
 		put_disk(dev->gd);
@@ -1389,18 +1385,18 @@ static int rnbd_client_setup_device(struct rnbd_clt_dev *dev,
 			le32_to_cpu(rsp->max_discard_sectors);
 	}
 
+	if (rsp->cache_policy & RNBD_WRITEBACK) {
+		lim.features |= BLK_FEAT_WRITE_CACHE;
+		if (rsp->cache_policy & RNBD_FUA)
+			lim.features |= BLK_FEAT_FUA;
+	}
+
 	dev->gd = blk_mq_alloc_disk(&dev->sess->tag_set, &lim, dev);
 	if (IS_ERR(dev->gd))
 		return PTR_ERR(dev->gd);
 	dev->queue = dev->gd->queue;
 	rnbd_init_mq_hw_queues(dev);
 
-	blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue);
-	blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue);
-	blk_queue_write_cache(dev->queue,
-			      !!(rsp->cache_policy & RNBD_WRITEBACK),
-			      !!(rsp->cache_policy & RNBD_FUA));
-
 	return rnbd_clt_setup_gen_disk(dev, rsp, idx);
 }
 

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

@@ -33,7 +33,7 @@ static void rnbd_srv_dev_release(struct kobject *kobj)
 	kfree(dev);
 }
 
-static struct kobj_type dev_ktype = {
+static const struct kobj_type dev_ktype = {
 	.sysfs_ops = &kobj_sysfs_ops,
 	.release = rnbd_srv_dev_release
 };
@@ -184,7 +184,7 @@ static void rnbd_srv_sess_dev_release(struct kobject *kobj)
 	rnbd_destroy_sess_dev(sess_dev, sess_dev->keep_id);
 }
 
-static struct kobj_type rnbd_srv_sess_dev_ktype = {
+static const struct kobj_type rnbd_srv_sess_dev_ktype = {
 	.sysfs_ops	= &kobj_sysfs_ops,
 	.release	= rnbd_srv_sess_dev_release,
 };

drivers/block/rnull.rs

@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! This is a Rust implementation of the C null block driver.
+//!
+//! Supported features:
+//!
+//! - blk-mq interface
+//! - direct completion
+//! - block size 4k
+//!
+//! The driver is not configurable.
+
+use kernel::{
+    alloc::flags,
+    block::mq::{
+        self,
+        gen_disk::{self, GenDisk},
+        Operations, TagSet,
+    },
+    error::Result,
+    new_mutex, pr_info,
+    prelude::*,
+    sync::{Arc, Mutex},
+    types::ARef,
+};
+
+module! {
+    type: NullBlkModule,
+    name: "rnull_mod",
+    author: "Andreas Hindborg",
+    license: "GPL v2",
+}
+
+struct NullBlkModule {
+    _disk: Pin<Box<Mutex<GenDisk<NullBlkDevice>>>>,
+}
+
+impl kernel::Module for NullBlkModule {
+    fn init(_module: &'static ThisModule) -> Result<Self> {
+        pr_info!("Rust null_blk loaded\n");
+        let tagset = Arc::pin_init(TagSet::new(1, 256, 1), flags::GFP_KERNEL)?;
+
+        let disk = gen_disk::GenDiskBuilder::new()
+            .capacity_sectors(4096 << 11)
+            .logical_block_size(4096)?
+            .physical_block_size(4096)?
+            .rotational(false)
+            .build(format_args!("rnullb{}", 0), tagset)?;
+
+        let disk = Box::pin_init(new_mutex!(disk, "nullb:disk"), flags::GFP_KERNEL)?;
+
+        Ok(Self { _disk: disk })
+    }
+}
+
+struct NullBlkDevice;
+
+#[vtable]
+impl Operations for NullBlkDevice {
+    #[inline(always)]
+    fn queue_rq(rq: ARef<mq::Request<Self>>, _is_last: bool) -> Result {
+        mq::Request::end_ok(rq)
+            .map_err(|_e| kernel::error::code::EIO)
+            // We take no refcounts on the request, so we expect to be able to
+            // end the request. The request reference must be unique at this
+            // point, and so `end_ok` cannot fail.
+            .expect("Fatal error - expected to be able to end request");
+
+        Ok(())
+    }
+
+    fn commit_rqs() {}
+}

drivers/block/sunvdc.c

@@ -791,6 +791,7 @@ static int probe_disk(struct vdc_port *port)
 		.seg_boundary_mask		= PAGE_SIZE - 1,
 		.max_segment_size		= PAGE_SIZE,
 		.max_segments			= port->ring_cookies,
+		.features			= BLK_FEAT_ROTATIONAL,
 	};
 	struct request_queue *q;
 	struct gendisk *g;

drivers/block/swim.c

@@ -787,6 +787,9 @@ static void swim_cleanup_floppy_disk(struct floppy_state *fs)
 
 static int swim_floppy_init(struct swim_priv *swd)
 {
+	struct queue_limits lim = {
+		.features		= BLK_FEAT_ROTATIONAL,
+	};
 	int err;
 	int drive;
 	struct swim __iomem *base = swd->base;
@@ -820,7 +823,7 @@ static int swim_floppy_init(struct swim_priv *swd)
 			goto exit_put_disks;
 
 		swd->unit[drive].disk =
-			blk_mq_alloc_disk(&swd->unit[drive].tag_set, NULL,
+			blk_mq_alloc_disk(&swd->unit[drive].tag_set, &lim,
 					  &swd->unit[drive]);
 		if (IS_ERR(swd->unit[drive].disk)) {
 			blk_mq_free_tag_set(&swd->unit[drive].tag_set);

drivers/block/swim3.c

@@ -1189,6 +1189,9 @@ static int swim3_add_device(struct macio_dev *mdev, int index)
 static int swim3_attach(struct macio_dev *mdev,
 			const struct of_device_id *match)
 {
+	struct queue_limits lim = {
+		.features		= BLK_FEAT_ROTATIONAL,
+	};
 	struct floppy_state *fs;
 	struct gendisk *disk;
 	int rc;
@@ -1210,7 +1213,7 @@ static int swim3_attach(struct macio_dev *mdev,
 	if (rc)
 		goto out_unregister;
 
-	disk = blk_mq_alloc_disk(&fs->tag_set, NULL, fs);
+	disk = blk_mq_alloc_disk(&fs->tag_set, &lim, fs);
 	if (IS_ERR(disk)) {
 		rc = PTR_ERR(disk);
 		goto out_free_tag_set;

drivers/block/ublk_drv.c

@@ -248,8 +248,6 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
 
 static void ublk_dev_param_zoned_apply(struct ublk_device *ub)
 {
-	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue);
-
 	ub->ub_disk->nr_zones = ublk_get_nr_zones(ub);
 }
 
@@ -484,16 +482,8 @@ static inline unsigned ublk_pos_to_tag(loff_t pos)
 
 static void ublk_dev_param_basic_apply(struct ublk_device *ub)
 {
-	struct request_queue *q = ub->ub_disk->queue;
 	const struct ublk_param_basic *p = &ub->params.basic;
 
-	blk_queue_write_cache(q, p->attrs & UBLK_ATTR_VOLATILE_CACHE,
-			p->attrs & UBLK_ATTR_FUA);
-	if (p->attrs & UBLK_ATTR_ROTATIONAL)
-		blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
-	else
-		blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-
 	if (p->attrs & UBLK_ATTR_READ_ONLY)
 		set_disk_ro(ub->ub_disk, true);
 
@@ -2204,12 +2194,21 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED))
 			return -EOPNOTSUPP;
 
-		lim.zoned = true;
+		lim.features |= BLK_FEAT_ZONED;
 		lim.max_active_zones = p->max_active_zones;
 		lim.max_open_zones =  p->max_open_zones;
 		lim.max_zone_append_sectors = p->max_zone_append_sectors;
 	}
 
+	if (ub->params.basic.attrs & UBLK_ATTR_VOLATILE_CACHE) {
+		lim.features |= BLK_FEAT_WRITE_CACHE;
+		if (ub->params.basic.attrs & UBLK_ATTR_FUA)
+			lim.features |= BLK_FEAT_FUA;
+	}
+
+	if (ub->params.basic.attrs & UBLK_ATTR_ROTATIONAL)
+		lim.features |= BLK_FEAT_ROTATIONAL;
+
 	if (wait_for_completion_interruptible(&ub->completion) != 0)
 		return -EINTR;
 
@@ -3017,4 +3016,5 @@ module_param_cb(ublks_max, &ublk_max_ublks_ops, &ublks_max, 0644);
 MODULE_PARM_DESC(ublks_max, "max number of ublk devices allowed to add(default: 64)");
 
 MODULE_AUTHOR("Ming Lei <ming.lei@redhat.com>");
+MODULE_DESCRIPTION("Userspace block device");
 MODULE_LICENSE("GPL");

drivers/block/virtio_blk.c

@@ -728,7 +728,7 @@ static int virtblk_read_zoned_limits(struct virtio_blk *vblk,
 
 	dev_dbg(&vdev->dev, "probing host-managed zoned device\n");
 
-	lim->zoned = true;
+	lim->features |= BLK_FEAT_ZONED;
 
 	virtio_cread(vdev, struct virtio_blk_config,
 		     zoned.max_open_zones, &v);
@@ -1089,14 +1089,6 @@ static int virtblk_get_cache_mode(struct virtio_device *vdev)
 	return writeback;
 }
 
-static void virtblk_update_cache_mode(struct virtio_device *vdev)
-{
-	u8 writeback = virtblk_get_cache_mode(vdev);
-	struct virtio_blk *vblk = vdev->priv;
-
-	blk_queue_write_cache(vblk->disk->queue, writeback, false);
-}
-
 static const char *const virtblk_cache_types[] = {
 	"write through", "write back"
 };
@@ -1108,6 +1100,7 @@ cache_type_store(struct device *dev, struct device_attribute *attr,
 	struct gendisk *disk = dev_to_disk(dev);
 	struct virtio_blk *vblk = disk->private_data;
 	struct virtio_device *vdev = vblk->vdev;
+	struct queue_limits lim;
 	int i;
 
 	BUG_ON(!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_CONFIG_WCE));
@@ -1116,7 +1109,17 @@ cache_type_store(struct device *dev, struct device_attribute *attr,
 		return i;
 
 	virtio_cwrite8(vdev, offsetof(struct virtio_blk_config, wce), i);
-	virtblk_update_cache_mode(vdev);
+
+	lim = queue_limits_start_update(disk->queue);
+	if (virtblk_get_cache_mode(vdev))
+		lim.features |= BLK_FEAT_WRITE_CACHE;
+	else
+		lim.features &= ~BLK_FEAT_WRITE_CACHE;
+	blk_mq_freeze_queue(disk->queue);
+	i = queue_limits_commit_update(disk->queue, &lim);
+	blk_mq_unfreeze_queue(disk->queue);
+	if (i)
+		return i;
 	return count;
 }
 
@@ -1247,7 +1250,7 @@ static int virtblk_read_limits(struct virtio_blk *vblk,
 		struct queue_limits *lim)
 {
 	struct virtio_device *vdev = vblk->vdev;
-	u32 v, blk_size, max_size, sg_elems, opt_io_size;
+	u32 v, max_size, sg_elems, opt_io_size;
 	u32 max_discard_segs = 0;
 	u32 discard_granularity = 0;
 	u16 min_io_size;
@@ -1286,46 +1289,36 @@ static int virtblk_read_limits(struct virtio_blk *vblk,
 	lim->max_segment_size = max_size;
 
 	/* Host can optionally specify the block size of the device */
-	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_BLK_SIZE,
+	virtio_cread_feature(vdev, VIRTIO_BLK_F_BLK_SIZE,
 				   struct virtio_blk_config, blk_size,
-				   &blk_size);
+				   &lim->logical_block_size);
-	if (!err) {
-		err = blk_validate_block_size(blk_size);
-		if (err) {
-			dev_err(&vdev->dev,
-				"virtio_blk: invalid block size: 0x%x\n",
-				blk_size);
-			return err;
-		}
-
-		lim->logical_block_size = blk_size;
-	} else
-		blk_size = lim->logical_block_size;
 
 	/* Use topology information if available */
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
 				   struct virtio_blk_config, physical_block_exp,
 				   &physical_block_exp);
 	if (!err && physical_block_exp)
-		lim->physical_block_size = blk_size * (1 << physical_block_exp);
+		lim->physical_block_size =
+			lim->logical_block_size * (1 << physical_block_exp);
 
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
 				   struct virtio_blk_config, alignment_offset,
 				   &alignment_offset);
 	if (!err && alignment_offset)
-		lim->alignment_offset = blk_size * alignment_offset;
+		lim->alignment_offset =
+			lim->logical_block_size * alignment_offset;
 
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
 				   struct virtio_blk_config, min_io_size,
 				   &min_io_size);
 	if (!err && min_io_size)
-		lim->io_min = blk_size * min_io_size;
+		lim->io_min = lim->logical_block_size * min_io_size;
 
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
 				   struct virtio_blk_config, opt_io_size,
 				   &opt_io_size);
 	if (!err && opt_io_size)
-		lim->io_opt = blk_size * opt_io_size;
+		lim->io_opt = lim->logical_block_size * opt_io_size;
 
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) {
 		virtio_cread(vdev, struct virtio_blk_config,
@@ -1419,7 +1412,7 @@ static int virtblk_read_limits(struct virtio_blk *vblk,
 			lim->discard_granularity =
 				discard_granularity << SECTOR_SHIFT;
 		else
-			lim->discard_granularity = blk_size;
+			lim->discard_granularity = lim->logical_block_size;
 	}
 
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_ZONED)) {
@@ -1448,7 +1441,10 @@ static int virtblk_read_limits(struct virtio_blk *vblk,
 static int virtblk_probe(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk;
-	struct queue_limits lim = { };
+	struct queue_limits lim = {
+		.features		= BLK_FEAT_ROTATIONAL,
+		.logical_block_size	= SECTOR_SIZE,
+	};
 	int err, index;
 	unsigned int queue_depth;
 
@@ -1512,6 +1508,9 @@ static int virtblk_probe(struct virtio_device *vdev)
 	if (err)
 		goto out_free_tags;
 
+	if (virtblk_get_cache_mode(vdev))
+		lim.features |= BLK_FEAT_WRITE_CACHE;
+
 	vblk->disk = blk_mq_alloc_disk(&vblk->tag_set, &lim, vblk);
 	if (IS_ERR(vblk->disk)) {
 		err = PTR_ERR(vblk->disk);
@@ -1527,9 +1526,6 @@ static int virtblk_probe(struct virtio_device *vdev)
 	vblk->disk->fops = &virtblk_fops;
 	vblk->index = index;
 
-	/* configure queue flush support */
-	virtblk_update_cache_mode(vdev);
-
 	/* If disk is read-only in the host, the guest should obey */
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
 		set_disk_ro(vblk->disk, 1);
@@ -1541,8 +1537,8 @@ static int virtblk_probe(struct virtio_device *vdev)
 	 * All steps that follow use the VQs therefore they need to be
 	 * placed after the virtio_device_ready() call above.
 	 */
-	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && lim.zoned) {
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
-		blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, vblk->disk->queue);
+	    (lim.features & BLK_FEAT_ZONED)) {
 		err = blk_revalidate_disk_zones(vblk->disk);
 		if (err)
 			goto out_cleanup_disk;

drivers/block/xen-blkback/blkback.c

@@ -1563,5 +1563,6 @@ static void __exit xen_blkif_fini(void)
 
 module_exit(xen_blkif_fini);
 
+MODULE_DESCRIPTION("Virtual block device back-end driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_ALIAS("xen-backend:vbd");

drivers/block/xen-blkfront.c

@@ -788,6 +788,11 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 			 * A barrier request a superset of FUA, so we can
 			 * implement it the same way.  (It's also a FLUSH+FUA,
 			 * since it is guaranteed ordered WRT previous writes.)
+			 *
+			 * Note that can end up here with a FUA write and the
+			 * flags cleared.  This happens when the flag was
+			 * run-time disabled after a failing I/O, and we'll
+			 * simplify submit it as a normal write.
 			 */
 			if (info->feature_flush && info->feature_fua)
 				ring_req->operation =
@@ -795,8 +800,6 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 			else if (info->feature_flush)
 				ring_req->operation =
 					BLKIF_OP_FLUSH_DISKCACHE;
-			else
-				ring_req->operation = 0;
 		}
 		ring_req->u.rw.nr_segments = num_grant;
 		if (unlikely(require_extra_req)) {
@@ -887,16 +890,6 @@ static inline void flush_requests(struct blkfront_ring_info *rinfo)
 		notify_remote_via_irq(rinfo->irq);
 }
 
-static inline bool blkif_request_flush_invalid(struct request *req,
-					       struct blkfront_info *info)
-{
-	return (blk_rq_is_passthrough(req) ||
-		((req_op(req) == REQ_OP_FLUSH) &&
-		 !info->feature_flush) ||
-		((req->cmd_flags & REQ_FUA) &&
-		 !info->feature_fua));
-}
-
 static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
 			  const struct blk_mq_queue_data *qd)
 {
@@ -908,12 +901,22 @@ static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
 	rinfo = get_rinfo(info, qid);
 	blk_mq_start_request(qd->rq);
 	spin_lock_irqsave(&rinfo->ring_lock, flags);
+
+	/*
+	 * Check if the backend actually supports flushes.
+	 *
+	 * While the block layer won't send us flushes if we don't claim to
+	 * support them, the Xen protocol allows the backend to revoke support
+	 * at any time.  That is of course a really bad idea and dangerous, but
+	 * has been allowed for 10+ years.  In that case we simply clear the
+	 * flags, and directly return here for an empty flush and ignore the
+	 * FUA flag later on.
+	 */
+	if (unlikely(req_op(qd->rq) == REQ_OP_FLUSH && !info->feature_flush))
+		goto complete;
+
 	if (RING_FULL(&rinfo->ring))
 		goto out_busy;
-
-	if (blkif_request_flush_invalid(qd->rq, rinfo->dev_info))
-		goto out_err;
-
 	if (blkif_queue_request(qd->rq, rinfo))
 		goto out_busy;
 
@@ -921,14 +924,14 @@ static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
 	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
 	return BLK_STS_OK;
 
-out_err:
-	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
-	return BLK_STS_IOERR;
-
 out_busy:
 	blk_mq_stop_hw_queue(hctx);
 	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
 	return BLK_STS_DEV_RESOURCE;
+complete:
+	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
+	blk_mq_end_request(qd->rq, BLK_STS_OK);
+	return BLK_STS_OK;
 }
 
 static void blkif_complete_rq(struct request *rq)
@@ -956,6 +959,12 @@ static void blkif_set_queue_limits(const struct blkfront_info *info,
 			lim->max_secure_erase_sectors = UINT_MAX;
 	}
 
+	if (info->feature_flush) {
+		lim->features |= BLK_FEAT_WRITE_CACHE;
+		if (info->feature_fua)
+			lim->features |= BLK_FEAT_FUA;
+	}
+
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
 	lim->logical_block_size = info->sector_size;
 	lim->physical_block_size = info->physical_sector_size;
@@ -984,8 +993,6 @@ static const char *flush_info(struct blkfront_info *info)
 
 static void xlvbd_flush(struct blkfront_info *info)
 {
-	blk_queue_write_cache(info->rq, info->feature_flush ? true : false,
-			      info->feature_fua ? true : false);
 	pr_info("blkfront: %s: %s %s %s %s %s %s %s\n",
 		info->gd->disk_name, flush_info(info),
 		"persistent grants:", info->feature_persistent ?
@@ -1063,8 +1070,7 @@ static char *encode_disk_name(char *ptr, unsigned int n)
 }
 
 static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
-		struct blkfront_info *info, u16 sector_size,
+		struct blkfront_info *info)
-		unsigned int physical_sector_size)
 {
 	struct queue_limits lim = {};
 	struct gendisk *gd;
@@ -1139,7 +1145,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 		err = PTR_ERR(gd);
 		goto out_free_tag_set;
 	}
-	blk_queue_flag_set(QUEUE_FLAG_VIRT, gd->queue);
 
 	strcpy(gd->disk_name, DEV_NAME);
 	ptr = encode_disk_name(gd->disk_name + sizeof(DEV_NAME) - 1, offset);
@@ -1159,8 +1164,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 
 	info->rq = gd->queue;
 	info->gd = gd;
-	info->sector_size = sector_size;
-	info->physical_sector_size = physical_sector_size;
 
 	xlvbd_flush(info);
 
@@ -1605,8 +1608,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 				blkif_req(req)->error = BLK_STS_NOTSUPP;
 				info->feature_discard = 0;
 				info->feature_secdiscard = 0;
-				blk_queue_max_discard_sectors(rq, 0);
+				blk_queue_disable_discard(rq);
-				blk_queue_max_secure_erase_sectors(rq, 0);
+				blk_queue_disable_secure_erase(rq);
 			}
 			break;
 		case BLKIF_OP_FLUSH_DISKCACHE:
@@ -1627,7 +1630,6 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 					blkif_req(req)->error = BLK_STS_OK;
 				info->feature_fua = 0;
 				info->feature_flush = 0;
-				xlvbd_flush(info);
 			}
 			fallthrough;
 		case BLKIF_OP_READ:
@@ -2315,8 +2317,6 @@ static void blkfront_gather_backend_features(struct blkfront_info *info)
 static void blkfront_connect(struct blkfront_info *info)
 {
 	unsigned long long sectors;
-	unsigned long sector_size;
-	unsigned int physical_sector_size;
 	int err, i;
 	struct blkfront_ring_info *rinfo;
 
@@ -2355,7 +2355,7 @@ static void blkfront_connect(struct blkfront_info *info)
 	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
 			    "sectors", "%llu", &sectors,
 			    "info", "%u", &info->vdisk_info,
-			    "sector-size", "%lu", &sector_size,
+			    "sector-size", "%lu", &info->sector_size,
 			    NULL);
 	if (err) {
 		xenbus_dev_fatal(info->xbdev, err,
@@ -2369,9 +2369,9 @@ static void blkfront_connect(struct blkfront_info *info)
 	 * provide this. Assume physical sector size to be the same as
 	 * sector_size in that case.
 	 */
-	physical_sector_size = xenbus_read_unsigned(info->xbdev->otherend,
+	info->physical_sector_size = xenbus_read_unsigned(info->xbdev->otherend,
 						    "physical-sector-size",
-						    sector_size);
+						    info->sector_size);
 	blkfront_gather_backend_features(info);
 	for_each_rinfo(info, rinfo, i) {
 		err = blkfront_setup_indirect(rinfo);
@@ -2383,8 +2383,7 @@ static void blkfront_connect(struct blkfront_info *info)
 		}
 	}
 
-	err = xlvbd_alloc_gendisk(sectors, info, sector_size,
+	err = xlvbd_alloc_gendisk(sectors, info);
-				  physical_sector_size);
 	if (err) {
 		xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
 				 info->xbdev->otherend);

drivers/block/z2ram.c

@@ -409,4 +409,5 @@ static void __exit z2_exit(void)
 
 module_init(z2_init);
 module_exit(z2_exit);
+MODULE_DESCRIPTION("Amiga Zorro II ramdisk driver");
 MODULE_LICENSE("GPL");

drivers/block/zram/zram_drv.c

@@ -2208,6 +2208,8 @@ static int zram_add(void)
 #if ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE
 		.max_write_zeroes_sectors	= UINT_MAX,
 #endif
+		.features			= BLK_FEAT_STABLE_WRITES |
+						  BLK_FEAT_SYNCHRONOUS,
 	};
 	struct zram *zram;
 	int ret, device_id;
@@ -2245,10 +2247,6 @@ static int zram_add(void)
 
 	/* Actual capacity set using sysfs (/sys/block/zram<id>/disksize */
 	set_capacity(zram->disk, 0);
-	/* zram devices sort of resembles non-rotational disks */
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, zram->disk->queue);
-	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, zram->disk->queue);
-	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue);
 	ret = device_add_disk(NULL, zram->disk, zram_disk_groups);
 	if (ret)
 		goto out_cleanup_disk;

drivers/cdrom/cdrom.c

@@ -3708,4 +3708,5 @@ static void __exit cdrom_exit(void)
 
 module_init(cdrom_init);
 module_exit(cdrom_exit);
+MODULE_DESCRIPTION("Uniform CD-ROM driver");
 MODULE_LICENSE("GPL");

drivers/cdrom/gdrom.c

@@ -744,6 +744,7 @@ static int probe_gdrom(struct platform_device *devptr)
 		.max_segments			= 1,
 		/* set a large max size to get most from DMA */
 		.max_segment_size		= 0x40000,
+		.features			= BLK_FEAT_ROTATIONAL,
 	};
 	int err;
 

drivers/md/bcache/super.c

@@ -897,7 +897,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 		sector_t sectors, struct block_device *cached_bdev,
 		const struct block_device_operations *ops)
 {
-	struct request_queue *q;
 	const size_t max_stripes = min_t(size_t, INT_MAX,
 					 SIZE_MAX / sizeof(atomic_t));
 	struct queue_limits lim = {
@@ -909,6 +908,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 		.io_min			= block_size,
 		.logical_block_size	= block_size,
 		.physical_block_size	= block_size,
+		.features		= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA,
 	};
 	uint64_t n;
 	int idx;
@@ -974,13 +974,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	d->disk->minors		= BCACHE_MINORS;
 	d->disk->fops		= ops;
 	d->disk->private_data	= d;
-
-	q = d->disk->queue;
-
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, d->disk->queue);
-
-	blk_queue_write_cache(q, true, true);
-
 	return 0;
 
 out_bioset_exit:
@@ -1423,8 +1416,8 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 	}
 
 	if (bdev_io_opt(dc->bdev))
-		dc->partial_stripes_expensive =
+		dc->partial_stripes_expensive = !!(q->limits.features &
-			q->limits.raid_partial_stripes_expensive;
+			BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE);
 
 	ret = bcache_device_init(&dc->disk, block_size,
 			 bdev_nr_sectors(dc->bdev) - dc->sb.data_offset,

drivers/md/dm-cache-target.c

@@ -3403,7 +3403,6 @@ static void set_discard_limits(struct cache *cache, struct queue_limits *limits)
 	limits->max_hw_discard_sectors = origin_limits->max_hw_discard_sectors;
 	limits->discard_granularity = origin_limits->discard_granularity;
 	limits->discard_alignment = origin_limits->discard_alignment;
-	limits->discard_misaligned = origin_limits->discard_misaligned;
 }
 
 static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits)

drivers/md/dm-clone-target.c

@@ -2059,7 +2059,6 @@ static void set_discard_limits(struct clone *clone, struct queue_limits *limits)
 	limits->max_hw_discard_sectors = dest_limits->max_hw_discard_sectors;
 	limits->discard_granularity = dest_limits->discard_granularity;
 	limits->discard_alignment = dest_limits->discard_alignment;
-	limits->discard_misaligned = dest_limits->discard_misaligned;
 	limits->max_discard_segments = dest_limits->max_discard_segments;
 }
 

drivers/md/dm-core.h

@@ -206,7 +206,6 @@ struct dm_table {
 
 	bool integrity_supported:1;
 	bool singleton:1;
-	unsigned integrity_added:1;
 
 	/*
 	 * Indicates the rw permissions for the new logical device.  This

drivers/md/dm-crypt.c

@@ -1176,8 +1176,8 @@ static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti)
 	struct blk_integrity *bi = blk_get_integrity(cc->dev->bdev->bd_disk);
 	struct mapped_device *md = dm_table_get_md(ti->table);
 
-	/* From now we require underlying device with our integrity profile */
+	/* We require an underlying device with non-PI metadata */
-	if (!bi || strcasecmp(bi->profile->name, "DM-DIF-EXT-TAG")) {
+	if (!bi || bi->csum_type != BLK_INTEGRITY_CSUM_NONE) {
 		ti->error = "Integrity profile not supported.";
 		return -EINVAL;
 	}

drivers/md/dm-integrity.c

@@ -350,25 +350,6 @@ static struct kmem_cache *journal_io_cache;
 #define DEBUG_bytes(bytes, len, msg, ...)	do { } while (0)
 #endif
 
-static void dm_integrity_prepare(struct request *rq)
-{
-}
-
-static void dm_integrity_complete(struct request *rq, unsigned int nr_bytes)
-{
-}
-
-/*
- * DM Integrity profile, protection is performed layer above (dm-crypt)
- */
-static const struct blk_integrity_profile dm_integrity_profile = {
-	.name			= "DM-DIF-EXT-TAG",
-	.generate_fn		= NULL,
-	.verify_fn		= NULL,
-	.prepare_fn		= dm_integrity_prepare,
-	.complete_fn		= dm_integrity_complete,
-};
-
 static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map);
 static void integrity_bio_wait(struct work_struct *w);
 static void dm_integrity_dtr(struct dm_target *ti);
@@ -3494,6 +3475,17 @@ static void dm_integrity_io_hints(struct dm_target *ti, struct queue_limits *lim
 		limits->dma_alignment = limits->logical_block_size - 1;
 		limits->discard_granularity = ic->sectors_per_block << SECTOR_SHIFT;
 	}
+
+	if (!ic->internal_hash) {
+		struct blk_integrity *bi = &limits->integrity;
+
+		memset(bi, 0, sizeof(*bi));
+		bi->tuple_size = ic->tag_size;
+		bi->tag_size = bi->tuple_size;
+		bi->interval_exp =
+			ic->sb->log2_sectors_per_block + SECTOR_SHIFT;
+	}
+
 	limits->max_integrity_segments = USHRT_MAX;
 }
 
@@ -3650,20 +3642,6 @@ try_smaller_buffer:
 	return 0;
 }
 
-static void dm_integrity_set(struct dm_target *ti, struct dm_integrity_c *ic)
-{
-	struct gendisk *disk = dm_disk(dm_table_get_md(ti->table));
-	struct blk_integrity bi;
-
-	memset(&bi, 0, sizeof(bi));
-	bi.profile = &dm_integrity_profile;
-	bi.tuple_size = ic->tag_size;
-	bi.tag_size = bi.tuple_size;
-	bi.interval_exp = ic->sb->log2_sectors_per_block + SECTOR_SHIFT;
-
-	blk_integrity_register(disk, &bi);
-}
-
 static void dm_integrity_free_page_list(struct page_list *pl)
 {
 	unsigned int i;
@@ -4649,9 +4627,6 @@ try_smaller_buffer:
 		}
 	}
 
-	if (!ic->internal_hash)
-		dm_integrity_set(ti, ic);
-
 	ti->num_flush_bios = 1;
 	ti->flush_supported = true;
 	if (ic->discard)

drivers/md/dm-raid.c

@@ -3542,7 +3542,7 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 		recovery = rs->md.recovery;
 		state = decipher_sync_action(mddev, recovery);
 		progress = rs_get_progress(rs, recovery, state, resync_max_sectors);
-		resync_mismatches = (mddev->last_sync_action && !strcasecmp(mddev->last_sync_action, "check")) ?
+		resync_mismatches = mddev->last_sync_action == ACTION_CHECK ?
 				    atomic64_read(&mddev->resync_mismatches) : 0;
 
 		/* HM FIXME: do we want another state char for raid0? It shows 'D'/'A'/'-' now */

drivers/md/dm-table.c

@@ -425,6 +425,13 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 		       q->limits.logical_block_size,
 		       q->limits.alignment_offset,
 		       (unsigned long long) start << SECTOR_SHIFT);
+
+	/*
+	 * Only stack the integrity profile if the target doesn't have native
+	 * integrity support.
+	 */
+	if (!dm_target_has_integrity(ti->type))
+		queue_limits_stack_integrity_bdev(limits, bdev);
 	return 0;
 }
 
@@ -572,6 +579,12 @@ int dm_split_args(int *argc, char ***argvp, char *input)
 	return 0;
 }
 
+static void dm_set_stacking_limits(struct queue_limits *limits)
+{
+	blk_set_stacking_limits(limits);
+	limits->features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL;
+}
+
 /*
  * Impose necessary and sufficient conditions on a devices's table such
  * that any incoming bio which respects its logical_block_size can be
@@ -610,7 +623,7 @@ static int validate_hardware_logical_block_alignment(struct dm_table *t,
 	for (i = 0; i < t->num_targets; i++) {
 		ti = dm_table_get_target(t, i);
 
-		blk_set_stacking_limits(&ti_limits);
+		dm_set_stacking_limits(&ti_limits);
 
 		/* combine all target devices' limits */
 		if (ti->type->iterate_devices)
@@ -702,9 +715,6 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 		t->immutable_target_type = ti->type;
 	}
 
-	if (dm_target_has_integrity(ti->type))
-		t->integrity_added = 1;
-
 	ti->table = t;
 	ti->begin = start;
 	ti->len = len;
@@ -1014,14 +1024,13 @@ bool dm_table_request_based(struct dm_table *t)
 	return __table_type_request_based(dm_table_get_type(t));
 }
 
-static bool dm_table_supports_poll(struct dm_table *t);
-
 static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *md)
 {
 	enum dm_queue_mode type = dm_table_get_type(t);
 	unsigned int per_io_data_size = 0, front_pad, io_front_pad;
 	unsigned int min_pool_size = 0, pool_size;
 	struct dm_md_mempools *pools;
+	unsigned int bioset_flags = 0;
 
 	if (unlikely(type == DM_TYPE_NONE)) {
 		DMERR("no table type is set, can't allocate mempools");
@@ -1038,6 +1047,9 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
 		goto init_bs;
 	}
 
+	if (md->queue->limits.features & BLK_FEAT_POLL)
+		bioset_flags |= BIOSET_PERCPU_CACHE;
+
 	for (unsigned int i = 0; i < t->num_targets; i++) {
 		struct dm_target *ti = dm_table_get_target(t, i);
 
@@ -1050,8 +1062,7 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
 
 	io_front_pad = roundup(per_io_data_size,
 		__alignof__(struct dm_io)) + DM_IO_BIO_OFFSET;
-	if (bioset_init(&pools->io_bs, pool_size, io_front_pad,
+	if (bioset_init(&pools->io_bs, pool_size, io_front_pad, bioset_flags))
-			dm_table_supports_poll(t) ? BIOSET_PERCPU_CACHE : 0))
 		goto out_free_pools;
 	if (t->integrity_supported &&
 	    bioset_integrity_create(&pools->io_bs, pool_size))
@@ -1119,99 +1130,6 @@ static int dm_table_build_index(struct dm_table *t)
 	return r;
 }
 
-static bool integrity_profile_exists(struct gendisk *disk)
-{
-	return !!blk_get_integrity(disk);
-}
-
-/*
- * Get a disk whose integrity profile reflects the table's profile.
- * Returns NULL if integrity support was inconsistent or unavailable.
- */
-static struct gendisk *dm_table_get_integrity_disk(struct dm_table *t)
-{
-	struct list_head *devices = dm_table_get_devices(t);
-	struct dm_dev_internal *dd = NULL;
-	struct gendisk *prev_disk = NULL, *template_disk = NULL;
-
-	for (unsigned int i = 0; i < t->num_targets; i++) {
-		struct dm_target *ti = dm_table_get_target(t, i);
-
-		if (!dm_target_passes_integrity(ti->type))
-			goto no_integrity;
-	}
-
-	list_for_each_entry(dd, devices, list) {
-		template_disk = dd->dm_dev->bdev->bd_disk;
-		if (!integrity_profile_exists(template_disk))
-			goto no_integrity;
-		else if (prev_disk &&
-			 blk_integrity_compare(prev_disk, template_disk) < 0)
-			goto no_integrity;
-		prev_disk = template_disk;
-	}
-
-	return template_disk;
-
-no_integrity:
-	if (prev_disk)
-		DMWARN("%s: integrity not set: %s and %s profile mismatch",
-		       dm_device_name(t->md),
-		       prev_disk->disk_name,
-		       template_disk->disk_name);
-	return NULL;
-}
-
-/*
- * Register the mapped device for blk_integrity support if the
- * underlying devices have an integrity profile.  But all devices may
- * not have matching profiles (checking all devices isn't reliable
- * during table load because this table may use other DM device(s) which
- * must be resumed before they will have an initialized integity
- * profile).  Consequently, stacked DM devices force a 2 stage integrity
- * profile validation: First pass during table load, final pass during
- * resume.
- */
-static int dm_table_register_integrity(struct dm_table *t)
-{
-	struct mapped_device *md = t->md;
-	struct gendisk *template_disk = NULL;
-
-	/* If target handles integrity itself do not register it here. */
-	if (t->integrity_added)
-		return 0;
-
-	template_disk = dm_table_get_integrity_disk(t);
-	if (!template_disk)
-		return 0;
-
-	if (!integrity_profile_exists(dm_disk(md))) {
-		t->integrity_supported = true;
-		/*
-		 * Register integrity profile during table load; we can do
-		 * this because the final profile must match during resume.
-		 */
-		blk_integrity_register(dm_disk(md),
-				       blk_get_integrity(template_disk));
-		return 0;
-	}
-
-	/*
-	 * If DM device already has an initialized integrity
-	 * profile the new profile should not conflict.
-	 */
-	if (blk_integrity_compare(dm_disk(md), template_disk) < 0) {
-		DMERR("%s: conflict with existing integrity profile: %s profile mismatch",
-		      dm_device_name(t->md),
-		      template_disk->disk_name);
-		return 1;
-	}
-
-	/* Preserve existing integrity profile */
-	t->integrity_supported = true;
-	return 0;
-}
-
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 
 struct dm_crypto_profile {
@@ -1423,12 +1341,6 @@ int dm_table_complete(struct dm_table *t)
 		return r;
 	}
 
-	r = dm_table_register_integrity(t);
-	if (r) {
-		DMERR("could not register integrity profile.");
-		return r;
-	}
-
 	r = dm_table_construct_crypto_profile(t);
 	if (r) {
 		DMERR("could not construct crypto profile.");
@@ -1493,14 +1405,6 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector)
 	return &t->targets[(KEYS_PER_NODE * n) + k];
 }
 
-static int device_not_poll_capable(struct dm_target *ti, struct dm_dev *dev,
-				   sector_t start, sector_t len, void *data)
-{
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-
-	return !test_bit(QUEUE_FLAG_POLL, &q->queue_flags);
-}
-
 /*
  * type->iterate_devices() should be called when the sanity check needs to
  * iterate and check all underlying data devices. iterate_devices() will
@@ -1548,19 +1452,6 @@ static int count_device(struct dm_target *ti, struct dm_dev *dev,
 	return 0;
 }
 
-static bool dm_table_supports_poll(struct dm_table *t)
-{
-	for (unsigned int i = 0; i < t->num_targets; i++) {
-		struct dm_target *ti = dm_table_get_target(t, i);
-
-		if (!ti->type->iterate_devices ||
-		    ti->type->iterate_devices(ti, device_not_poll_capable, NULL))
-			return false;
-	}
-
-	return true;
-}
-
 /*
  * Check whether a table has no data devices attached using each
  * target's iterate_devices method.
@@ -1686,12 +1577,20 @@ int dm_calculate_queue_limits(struct dm_table *t,
 	unsigned int zone_sectors = 0;
 	bool zoned = false;
 
-	blk_set_stacking_limits(limits);
+	dm_set_stacking_limits(limits);
+
+	t->integrity_supported = true;
+	for (unsigned int i = 0; i < t->num_targets; i++) {
+		struct dm_target *ti = dm_table_get_target(t, i);
+
+		if (!dm_target_passes_integrity(ti->type))
+			t->integrity_supported = false;
+	}
 
 	for (unsigned int i = 0; i < t->num_targets; i++) {
 		struct dm_target *ti = dm_table_get_target(t, i);
 
-		blk_set_stacking_limits(&ti_limits);
+		dm_set_stacking_limits(&ti_limits);
 
 		if (!ti->type->iterate_devices) {
 			/* Set I/O hints portion of queue limits */
@@ -1706,12 +1605,12 @@ int dm_calculate_queue_limits(struct dm_table *t,
 		ti->type->iterate_devices(ti, dm_set_device_limits,
 					  &ti_limits);
 
-		if (!zoned && ti_limits.zoned) {
+		if (!zoned && (ti_limits.features & BLK_FEAT_ZONED)) {
 			/*
 			 * After stacking all limits, validate all devices
 			 * in table support this zoned model and zone sectors.
 			 */
-			zoned = ti_limits.zoned;
+			zoned = (ti_limits.features & BLK_FEAT_ZONED);
 			zone_sectors = ti_limits.chunk_sectors;
 		}
 
@@ -1738,6 +1637,18 @@ combine_limits:
 			       dm_device_name(t->md),
 			       (unsigned long long) ti->begin,
 			       (unsigned long long) ti->len);
+
+		if (t->integrity_supported ||
+		    dm_target_has_integrity(ti->type)) {
+			if (!queue_limits_stack_integrity(limits, &ti_limits)) {
+				DMWARN("%s: adding target device (start sect %llu len %llu) "
+				       "disabled integrity support due to incompatibility",
+				       dm_device_name(t->md),
+				       (unsigned long long) ti->begin,
+				       (unsigned long long) ti->len);
+				t->integrity_supported = false;
+			}
+		}
 	}
 
 	/*
@@ -1747,12 +1658,12 @@ combine_limits:
 	 *   zoned model on host-managed zoned block devices.
 	 * BUT...
 	 */
-	if (limits->zoned) {
+	if (limits->features & BLK_FEAT_ZONED) {
 		/*
 		 * ...IF the above limits stacking determined a zoned model
 		 * validate that all of the table's devices conform to it.
 		 */
-		zoned = limits->zoned;
+		zoned = limits->features & BLK_FEAT_ZONED;
 		zone_sectors = limits->chunk_sectors;
 	}
 	if (validate_hardware_zoned(t, zoned, zone_sectors))
@@ -1762,63 +1673,15 @@ combine_limits:
 }
 
 /*
- * Verify that all devices have an integrity profile that matches the
+ * Check if a target requires flush support even if none of the underlying
- * DM device's registered integrity profile.  If the profiles don't
+ * devices need it (e.g. to persist target-specific metadata).
- * match then unregister the DM device's integrity profile.
  */
-static void dm_table_verify_integrity(struct dm_table *t)
+static bool dm_table_supports_flush(struct dm_table *t)
 {
-	struct gendisk *template_disk = NULL;
-
-	if (t->integrity_added)
-		return;
-
-	if (t->integrity_supported) {
-		/*
-		 * Verify that the original integrity profile
-		 * matches all the devices in this table.
-		 */
-		template_disk = dm_table_get_integrity_disk(t);
-		if (template_disk &&
-		    blk_integrity_compare(dm_disk(t->md), template_disk) >= 0)
-			return;
-	}
-
-	if (integrity_profile_exists(dm_disk(t->md))) {
-		DMWARN("%s: unable to establish an integrity profile",
-		       dm_device_name(t->md));
-		blk_integrity_unregister(dm_disk(t->md));
-	}
-}
-
-static int device_flush_capable(struct dm_target *ti, struct dm_dev *dev,
-				sector_t start, sector_t len, void *data)
-{
-	unsigned long flush = (unsigned long) data;
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-
-	return (q->queue_flags & flush);
-}
-
-static bool dm_table_supports_flush(struct dm_table *t, unsigned long flush)
-{
-	/*
-	 * Require at least one underlying device to support flushes.
-	 * t->devices includes internal dm devices such as mirror logs
-	 * so we need to use iterate_devices here, which targets
-	 * supporting flushes must provide.
-	 */
 	for (unsigned int i = 0; i < t->num_targets; i++) {
 		struct dm_target *ti = dm_table_get_target(t, i);
 
-		if (!ti->num_flush_bios)
+		if (ti->num_flush_bios && ti->flush_supported)
-			continue;
-
-		if (ti->flush_supported)
-			return true;
-
-		if (ti->type->iterate_devices &&
-		    ti->type->iterate_devices(ti, device_flush_capable, (void *) flush))
 			return true;
 	}
 
@@ -1839,20 +1702,6 @@ static int device_dax_write_cache_enabled(struct dm_target *ti,
 	return false;
 }
 
-static int device_is_rotational(struct dm_target *ti, struct dm_dev *dev,
-				sector_t start, sector_t len, void *data)
-{
-	return !bdev_nonrot(dev->bdev);
-}
-
-static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev,
-			     sector_t start, sector_t len, void *data)
-{
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-
-	return !blk_queue_add_random(q);
-}
-
 static int device_not_write_zeroes_capable(struct dm_target *ti, struct dm_dev *dev,
 					   sector_t start, sector_t len, void *data)
 {
@@ -1877,12 +1726,6 @@ static bool dm_table_supports_write_zeroes(struct dm_table *t)
 	return true;
 }
 
-static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev,
-				     sector_t start, sector_t len, void *data)
-{
-	return !bdev_nowait(dev->bdev);
-}
-
 static bool dm_table_supports_nowait(struct dm_table *t)
 {
 	for (unsigned int i = 0; i < t->num_targets; i++) {
@@ -1890,10 +1733,6 @@ static bool dm_table_supports_nowait(struct dm_table *t)
 
 		if (!dm_target_supports_nowait(ti->type))
 			return false;
-
-		if (!ti->type->iterate_devices ||
-		    ti->type->iterate_devices(ti, device_not_nowait_capable, NULL))
-			return false;
 	}
 
 	return true;
@@ -1950,29 +1789,25 @@ static bool dm_table_supports_secure_erase(struct dm_table *t)
 	return true;
 }
 
-static int device_requires_stable_pages(struct dm_target *ti,
-					struct dm_dev *dev, sector_t start,
-					sector_t len, void *data)
-{
-	return bdev_stable_writes(dev->bdev);
-}
-
 int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			      struct queue_limits *limits)
 {
-	bool wc = false, fua = false;
 	int r;
 
-	if (dm_table_supports_nowait(t))
+	if (!dm_table_supports_nowait(t))
-		blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
+		limits->features &= ~BLK_FEAT_NOWAIT;
-	else
+
-		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q);
+	/*
+	 * The current polling impementation does not support request based
+	 * stacking.
+	 */
+	if (!__table_type_bio_based(t->type))
+		limits->features &= ~BLK_FEAT_POLL;
 
 	if (!dm_table_supports_discards(t)) {
 		limits->max_hw_discard_sectors = 0;
 		limits->discard_granularity = 0;
 		limits->discard_alignment = 0;
-		limits->discard_misaligned = 0;
 	}
 
 	if (!dm_table_supports_write_zeroes(t))
@@ -1981,58 +1816,22 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	if (!dm_table_supports_secure_erase(t))
 		limits->max_secure_erase_sectors = 0;
 
-	if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) {
+	if (dm_table_supports_flush(t))
-		wc = true;
+		limits->features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA;
-		if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_FUA)))
-			fua = true;
-	}
-	blk_queue_write_cache(q, wc, fua);
 
 	if (dm_table_supports_dax(t, device_not_dax_capable)) {
-		blk_queue_flag_set(QUEUE_FLAG_DAX, q);
+		limits->features |= BLK_FEAT_DAX;
 		if (dm_table_supports_dax(t, device_not_dax_synchronous_capable))
 			set_dax_synchronous(t->md->dax_dev);
 	} else
-		blk_queue_flag_clear(QUEUE_FLAG_DAX, q);
+		limits->features &= ~BLK_FEAT_DAX;
 
 	if (dm_table_any_dev_attr(t, device_dax_write_cache_enabled, NULL))
 		dax_write_cache(t->md->dax_dev, true);
 
-	/* Ensure that all underlying devices are non-rotational. */
+	/* For a zoned table, setup the zone related queue attributes. */
-	if (dm_table_any_dev_attr(t, device_is_rotational, NULL))
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
-		blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
+	    (limits->features & BLK_FEAT_ZONED)) {
-	else
-		blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-
-	dm_table_verify_integrity(t);
-
-	/*
-	 * Some devices don't use blk_integrity but still want stable pages
-	 * because they do their own checksumming.
-	 * If any underlying device requires stable pages, a table must require
-	 * them as well.  Only targets that support iterate_devices are considered:
-	 * don't want error, zero, etc to require stable pages.
-	 */
-	if (dm_table_any_dev_attr(t, device_requires_stable_pages, NULL))
-		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
-	else
-		blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);
-
-	/*
-	 * Determine whether or not this queue's I/O timings contribute
-	 * to the entropy pool, Only request-based targets use this.
-	 * Clear QUEUE_FLAG_ADD_RANDOM if any underlying device does not
-	 * have it set.
-	 */
-	if (blk_queue_add_random(q) &&
-	    dm_table_any_dev_attr(t, device_is_not_random, NULL))
-		blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q);
-
-	/*
-	 * For a zoned target, setup the zones related queue attributes
-	 * and resources necessary for zone append emulation if necessary.
-	 */
-	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && limits->zoned) {
 		r = dm_set_zones_restrictions(t, q, limits);
 		if (r)
 			return r;
@@ -2042,22 +1841,18 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	if (r)
 		return r;
 
-	dm_update_crypto_profile(q, t);
-
 	/*
-	 * Check for request-based device is left to
+	 * Now that the limits are set, check the zones mapped by the table
-	 * dm_mq_init_request_queue()->blk_mq_init_allocated_queue().
+	 * and setup the resources for zone append emulation if necessary.
-	 *
-	 * For bio-based device, only set QUEUE_FLAG_POLL when all
-	 * underlying devices supporting polling.
 	 */
-	if (__table_type_bio_based(t->type)) {
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
-		if (dm_table_supports_poll(t))
+	    (limits->features & BLK_FEAT_ZONED)) {
-			blk_queue_flag_set(QUEUE_FLAG_POLL, q);
+		r = dm_revalidate_zones(t, q);
-		else
+		if (r)
-			blk_queue_flag_clear(QUEUE_FLAG_POLL, q);
+			return r;
 	}
 
+	dm_update_crypto_profile(q, t);
 	return 0;
 }
 

drivers/md/dm-zone.c

@@ -13,8 +13,6 @@
 
 #define DM_MSG_PREFIX "zone"
 
-#define DM_ZONE_INVALID_WP_OFST		UINT_MAX
-
 /*
  * For internal zone reports bypassing the top BIO submission path.
  */
@@ -145,35 +143,28 @@ bool dm_is_zone_write(struct mapped_device *md, struct bio *bio)
 	}
 }
 
-/*
- * Count conventional zones of a mapped zoned device. If the device
- * only has conventional zones, do not expose it as zoned.
- */
-static int dm_check_zoned_cb(struct blk_zone *zone, unsigned int idx,
-			     void *data)
-{
-	unsigned int *nr_conv_zones = data;
-
-	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
-		(*nr_conv_zones)++;
-
-	return 0;
-}
-
 /*
  * Revalidate the zones of a mapped device to initialize resource necessary
  * for zone append emulation. Note that we cannot simply use the block layer
  * blk_revalidate_disk_zones() function here as the mapped device is suspended
  * (this is called from __bind() context).
  */
-static int dm_revalidate_zones(struct mapped_device *md, struct dm_table *t)
+int dm_revalidate_zones(struct dm_table *t, struct request_queue *q)
 {
+	struct mapped_device *md = t->md;
 	struct gendisk *disk = md->disk;
 	int ret;
 
+	if (!get_capacity(disk))
+		return 0;
+
 	/* Revalidate only if something changed. */
-	if (!disk->nr_zones || disk->nr_zones != md->nr_zones)
+	if (!disk->nr_zones || disk->nr_zones != md->nr_zones) {
+		DMINFO("%s using %s zone append",
+		       disk->disk_name,
+		       queue_emulates_zone_append(q) ? "emulated" : "native");
 		md->nr_zones = 0;
+	}
 
 	if (md->nr_zones)
 		return 0;
@@ -220,13 +211,129 @@ static bool dm_table_supports_zone_append(struct dm_table *t)
 	return true;
 }
 
+struct dm_device_zone_count {
+	sector_t start;
+	sector_t len;
+	unsigned int total_nr_seq_zones;
+	unsigned int target_nr_seq_zones;
+};
+
+/*
+ * Count the total number of and the number of mapped sequential zones of a
+ * target zoned device.
+ */
+static int dm_device_count_zones_cb(struct blk_zone *zone,
+				    unsigned int idx, void *data)
+{
+	struct dm_device_zone_count *zc = data;
+
+	if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) {
+		zc->total_nr_seq_zones++;
+		if (zone->start >= zc->start &&
+		    zone->start < zc->start + zc->len)
+			zc->target_nr_seq_zones++;
+	}
+
+	return 0;
+}
+
+static int dm_device_count_zones(struct dm_dev *dev,
+				 struct dm_device_zone_count *zc)
+{
+	int ret;
+
+	ret = blkdev_report_zones(dev->bdev, 0, BLK_ALL_ZONES,
+				  dm_device_count_zones_cb, zc);
+	if (ret < 0)
+		return ret;
+	if (!ret)
+		return -EIO;
+	return 0;
+}
+
+struct dm_zone_resource_limits {
+	unsigned int mapped_nr_seq_zones;
+	struct queue_limits *lim;
+	bool reliable_limits;
+};
+
+static int device_get_zone_resource_limits(struct dm_target *ti,
+					   struct dm_dev *dev, sector_t start,
+					   sector_t len, void *data)
+{
+	struct dm_zone_resource_limits *zlim = data;
+	struct gendisk *disk = dev->bdev->bd_disk;
+	unsigned int max_open_zones, max_active_zones;
+	int ret;
+	struct dm_device_zone_count zc = {
+		.start = start,
+		.len = len,
+	};
+
+	/*
+	 * If the target is not the whole device, the device zone resources may
+	 * be shared between different targets. Check this by counting the
+	 * number of mapped sequential zones: if this number is smaller than the
+	 * total number of sequential zones of the target device, then resource
+	 * sharing may happen and the zone limits will not be reliable.
+	 */
+	ret = dm_device_count_zones(dev, &zc);
+	if (ret) {
+		DMERR("Count %s zones failed %d", disk->disk_name, ret);
+		return ret;
+	}
+
+	/*
+	 * If the target does not map any sequential zones, then we do not need
+	 * any zone resource limits.
+	 */
+	if (!zc.target_nr_seq_zones)
+		return 0;
+
+	/*
+	 * If the target does not map all sequential zones, the limits
+	 * will not be reliable and we cannot use REQ_OP_ZONE_RESET_ALL.
+	 */
+	if (zc.target_nr_seq_zones < zc.total_nr_seq_zones) {
+		zlim->reliable_limits = false;
+		ti->zone_reset_all_supported = false;
+	}
+
+	/*
+	 * If the target maps less sequential zones than the limit values, then
+	 * we do not have limits for this target.
+	 */
+	max_active_zones = disk->queue->limits.max_active_zones;
+	if (max_active_zones >= zc.target_nr_seq_zones)
+		max_active_zones = 0;
+	zlim->lim->max_active_zones =
+		min_not_zero(max_active_zones, zlim->lim->max_active_zones);
+
+	max_open_zones = disk->queue->limits.max_open_zones;
+	if (max_open_zones >= zc.target_nr_seq_zones)
+		max_open_zones = 0;
+	zlim->lim->max_open_zones =
+		min_not_zero(max_open_zones, zlim->lim->max_open_zones);
+
+	/*
+	 * Also count the total number of sequential zones for the mapped
+	 * device so that when we are done inspecting all its targets, we are
+	 * able to check if the mapped device actually has any sequential zones.
+	 */
+	zlim->mapped_nr_seq_zones += zc.target_nr_seq_zones;
+
+	return 0;
+}
+
 int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
 		struct queue_limits *lim)
 {
 	struct mapped_device *md = t->md;
 	struct gendisk *disk = md->disk;
-	unsigned int nr_conv_zones = 0;
+	struct dm_zone_resource_limits zlim = {
-	int ret;
+		.reliable_limits = true,
+		.lim = lim,
+	};
 
 	/*
 	 * Check if zone append is natively supported, and if not, set the
@@ -240,46 +347,63 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
 		lim->max_zone_append_sectors = 0;
 	}
 
-	if (!get_capacity(md->disk))
-		return 0;
-
 	/*
-	 * Count conventional zones to check that the mapped device will indeed 
+	 * Determine the max open and max active zone limits for the mapped
-	 * have sequential write required zones.
+	 * device by inspecting the zone resource limits and the zones mapped
+	 * by each target.
 	 */
-	md->zone_revalidate_map = t;
+	for (unsigned int i = 0; i < t->num_targets; i++) {
-	ret = dm_blk_report_zones(disk, 0, UINT_MAX,
+		struct dm_target *ti = dm_table_get_target(t, i);
-				  dm_check_zoned_cb, &nr_conv_zones);
+
-	md->zone_revalidate_map = NULL;
+		/*
-	if (ret < 0) {
+		 * Assume that the target can accept REQ_OP_ZONE_RESET_ALL.
-		DMERR("Check zoned failed %d", ret);
+		 * device_get_zone_resource_limits() may adjust this if one of
-		return ret;
+		 * the device used by the target does not have all its
+		 * sequential write required zones mapped.
+		 */
+		ti->zone_reset_all_supported = true;
+
+		if (!ti->type->iterate_devices ||
+		    ti->type->iterate_devices(ti,
+				device_get_zone_resource_limits, &zlim)) {
+			DMERR("Could not determine %s zone resource limits",
+			      disk->disk_name);
+			return -ENODEV;
+		}
 	}
 
 	/*
-	 * If we only have conventional zones, expose the mapped device as
+	 * If we only have conventional zones mapped, expose the mapped device
-	 * a regular device.
+	 + as a regular device.
 	 */
-	if (nr_conv_zones >= ret) {
+	if (!zlim.mapped_nr_seq_zones) {
 		lim->max_open_zones = 0;
 		lim->max_active_zones = 0;
-		lim->zoned = false;
+		lim->max_zone_append_sectors = 0;
+		lim->zone_write_granularity = 0;
+		lim->chunk_sectors = 0;
+		lim->features &= ~BLK_FEAT_ZONED;
 		clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
+		md->nr_zones = 0;
 		disk->nr_zones = 0;
 		return 0;
 	}
 
-	if (!md->disk->nr_zones) {
+	/*
-		DMINFO("%s using %s zone append",
+	 * Warn once (when the capacity is not yet set) if the mapped device is
-		       md->disk->disk_name,
+	 * partially using zone resources of the target devices as that leads to
-		       queue_emulates_zone_append(q) ? "emulated" : "native");
+	 * unreliable limits, i.e. if another mapped device uses the same
-	}
+	 * underlying devices, we cannot enforce zone limits to guarantee that
+	 * writing will not lead to errors. Note that we really should return
+	 * an error for such case but there is no easy way to find out if
+	 * another mapped device uses the same underlying zoned devices.
+	 */
+	if (!get_capacity(disk) && !zlim.reliable_limits)
+		DMWARN("%s zone resource limits may be unreliable",
+		       disk->disk_name);
 
-	ret = dm_revalidate_zones(md, t);
+	if (lim->features & BLK_FEAT_ZONED &&
-	if (ret < 0)
+	    !static_key_enabled(&zoned_enabled.key))
-		return ret;
-
-	if (!static_key_enabled(&zoned_enabled.key))
 		static_branch_enable(&zoned_enabled);
 	return 0;
 }
@@ -306,3 +430,39 @@ void dm_zone_endio(struct dm_io *io, struct bio *clone)
 
 	return;
 }
+
+static int dm_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx,
+				 void *data)
+{
+	/*
+	 * For an all-zones reset, ignore conventional, empty, read-only
+	 * and offline zones.
+	 */
+	switch (zone->cond) {
+	case BLK_ZONE_COND_NOT_WP:
+	case BLK_ZONE_COND_EMPTY:
+	case BLK_ZONE_COND_READONLY:
+	case BLK_ZONE_COND_OFFLINE:
+		return 0;
+	default:
+		set_bit(idx, (unsigned long *)data);
+		return 0;
+	}
+}
+
+int dm_zone_get_reset_bitmap(struct mapped_device *md, struct dm_table *t,
+			     sector_t sector, unsigned int nr_zones,
+			     unsigned long *need_reset)
+{
+	int ret;
+
+	ret = dm_blk_do_report_zones(md, t, sector, nr_zones,
+				     dm_zone_need_reset_cb, need_reset);
+	if (ret != nr_zones) {
+		DMERR("Get %s zone reset bitmap failed\n",
+		      md->disk->disk_name);
+		return -EIO;
+	}
+
+	return 0;
+}

drivers/md/dm-zoned-target.c

@@ -1009,7 +1009,7 @@ static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	limits->max_sectors = chunk_sectors;
 
 	/* We are exposing a drive-managed zoned block device */
-	limits->zoned = false;
+	limits->features &= ~BLK_FEAT_ZONED;
 }
 
 /*

drivers/md/dm.c

@@ -1188,7 +1188,7 @@ static sector_t __max_io_len(struct dm_target *ti, sector_t sector,
 		return len;
 	return min_t(sector_t, len,
 		min(max_sectors ? : queue_max_sectors(ti->table->md->queue),
-		    blk_chunk_sectors_left(target_offset, max_granularity)));
+		    blk_boundary_sectors_left(target_offset, max_granularity)));
 }
 
 static inline sector_t max_io_len(struct dm_target *ti, sector_t sector)
@@ -1598,20 +1598,19 @@ static void __send_abnormal_io(struct clone_info *ci, struct dm_target *ti,
 
 static bool is_abnormal_io(struct bio *bio)
 {
-	enum req_op op = bio_op(bio);
+	switch (bio_op(bio)) {
-
+	case REQ_OP_READ:
-	if (op != REQ_OP_READ && op != REQ_OP_WRITE && op != REQ_OP_FLUSH) {
+	case REQ_OP_WRITE:
-		switch (op) {
+	case REQ_OP_FLUSH:
-		case REQ_OP_DISCARD:
+		return false;
-		case REQ_OP_SECURE_ERASE:
+	case REQ_OP_DISCARD:
-		case REQ_OP_WRITE_ZEROES:
+	case REQ_OP_SECURE_ERASE:
-			return true;
+	case REQ_OP_WRITE_ZEROES:
-		default:
+	case REQ_OP_ZONE_RESET_ALL:
-			break;
+		return true;
-		}
+	default:
+		return false;
 	}
-
-	return false;
 }
 
 static blk_status_t __process_abnormal_io(struct clone_info *ci,
@@ -1776,6 +1775,119 @@ static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio)
 {
 	return dm_emulate_zone_append(md) && blk_zone_plug_bio(bio, 0);
 }
+
+static blk_status_t __send_zone_reset_all_emulated(struct clone_info *ci,
+						   struct dm_target *ti)
+{
+	struct bio_list blist = BIO_EMPTY_LIST;
+	struct mapped_device *md = ci->io->md;
+	unsigned int zone_sectors = md->disk->queue->limits.chunk_sectors;
+	unsigned long *need_reset;
+	unsigned int i, nr_zones, nr_reset;
+	unsigned int num_bios = 0;
+	blk_status_t sts = BLK_STS_OK;
+	sector_t sector = ti->begin;
+	struct bio *clone;
+	int ret;
+
+	nr_zones = ti->len >> ilog2(zone_sectors);
+	need_reset = bitmap_zalloc(nr_zones, GFP_NOIO);
+	if (!need_reset)
+		return BLK_STS_RESOURCE;
+
+	ret = dm_zone_get_reset_bitmap(md, ci->map, ti->begin,
+				       nr_zones, need_reset);
+	if (ret) {
+		sts = BLK_STS_IOERR;
+		goto free_bitmap;
+	}
+
+	/* If we have no zone to reset, we are done. */
+	nr_reset = bitmap_weight(need_reset, nr_zones);
+	if (!nr_reset)
+		goto free_bitmap;
+
+	atomic_add(nr_zones, &ci->io->io_count);
+
+	for (i = 0; i < nr_zones; i++) {
+
+		if (!test_bit(i, need_reset)) {
+			sector += zone_sectors;
+			continue;
+		}
+
+		if (bio_list_empty(&blist)) {
+			/* This may take a while, so be nice to others */
+			if (num_bios)
+				cond_resched();
+
+			/*
+			 * We may need to reset thousands of zones, so let's
+			 * not go crazy with the clone allocation.
+			 */
+			alloc_multiple_bios(&blist, ci, ti, min(nr_reset, 32),
+					    NULL, GFP_NOIO);
+		}
+
+		/* Get a clone and change it to a regular reset operation. */
+		clone = bio_list_pop(&blist);
+		clone->bi_opf &= ~REQ_OP_MASK;
+		clone->bi_opf |= REQ_OP_ZONE_RESET | REQ_SYNC;
+		clone->bi_iter.bi_sector = sector;
+		clone->bi_iter.bi_size = 0;
+		__map_bio(clone);
+
+		sector += zone_sectors;
+		num_bios++;
+		nr_reset--;
+	}
+
+	WARN_ON_ONCE(!bio_list_empty(&blist));
+	atomic_sub(nr_zones - num_bios, &ci->io->io_count);
+	ci->sector_count = 0;
+
+free_bitmap:
+	bitmap_free(need_reset);
+
+	return sts;
+}
+
+static void __send_zone_reset_all_native(struct clone_info *ci,
+					 struct dm_target *ti)
+{
+	unsigned int bios;
+
+	atomic_add(1, &ci->io->io_count);
+	bios = __send_duplicate_bios(ci, ti, 1, NULL, GFP_NOIO);
+	atomic_sub(1 - bios, &ci->io->io_count);
+
+	ci->sector_count = 0;
+}
+
+static blk_status_t __send_zone_reset_all(struct clone_info *ci)
+{
+	struct dm_table *t = ci->map;
+	blk_status_t sts = BLK_STS_OK;
+
+	for (unsigned int i = 0; i < t->num_targets; i++) {
+		struct dm_target *ti = dm_table_get_target(t, i);
+
+		if (ti->zone_reset_all_supported) {
+			__send_zone_reset_all_native(ci, ti);
+			continue;
+		}
+
+		sts = __send_zone_reset_all_emulated(ci, ti);
+		if (sts != BLK_STS_OK)
+			break;
+	}
+
+	/* Release the reference that alloc_io() took for submission. */
+	atomic_sub(1, &ci->io->io_count);
+
+	return sts;
+}
+
 #else
 static inline bool dm_zone_bio_needs_split(struct mapped_device *md,
 					   struct bio *bio)
@@ -1786,6 +1898,10 @@ static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio)
 {
 	return false;
 }
+static blk_status_t __send_zone_reset_all(struct clone_info *ci)
+{
+	return BLK_STS_NOTSUPP;
+}
 #endif
 
 /*
@@ -1799,9 +1915,14 @@ static void dm_split_and_process_bio(struct mapped_device *md,
 	blk_status_t error = BLK_STS_OK;
 	bool is_abnormal, need_split;
 
-	need_split = is_abnormal = is_abnormal_io(bio);
+	is_abnormal = is_abnormal_io(bio);
-	if (static_branch_unlikely(&zoned_enabled))
+	if (static_branch_unlikely(&zoned_enabled)) {
-		need_split = is_abnormal || dm_zone_bio_needs_split(md, bio);
+		/* Special case REQ_OP_ZONE_RESET_ALL as it cannot be split. */
+		need_split = (bio_op(bio) != REQ_OP_ZONE_RESET_ALL) &&
+			(is_abnormal || dm_zone_bio_needs_split(md, bio));
+	} else {
+		need_split = is_abnormal;
+	}
 
 	if (unlikely(need_split)) {
 		/*
@@ -1842,6 +1963,12 @@ static void dm_split_and_process_bio(struct mapped_device *md,
 		goto out;
 	}
 
+	if (static_branch_unlikely(&zoned_enabled) &&
+	    (bio_op(bio) == REQ_OP_ZONE_RESET_ALL)) {
+		error = __send_zone_reset_all(&ci);
+		goto out;
+	}
+
 	error = __split_and_process_bio(&ci);
 	if (error || !ci.sector_count)
 		goto out;
@@ -2386,22 +2513,15 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 	struct table_device *td;
 	int r;
 
-	switch (type) {
+	WARN_ON_ONCE(type == DM_TYPE_NONE);
-	case DM_TYPE_REQUEST_BASED:
+
+	if (type == DM_TYPE_REQUEST_BASED) {
 		md->disk->fops = &dm_rq_blk_dops;
 		r = dm_mq_init_request_queue(md, t);
 		if (r) {
 			DMERR("Cannot initialize queue for request-based dm mapped device");
 			return r;
 		}
-		break;
-	case DM_TYPE_BIO_BASED:
-	case DM_TYPE_DAX_BIO_BASED:
-		blk_queue_flag_set(QUEUE_FLAG_IO_STAT, md->queue);
-		break;
-	case DM_TYPE_NONE:
-		WARN_ON_ONCE(true);
-		break;
 	}
 
 	r = dm_calculate_queue_limits(t, &limits);

drivers/md/dm.h

@@ -103,12 +103,16 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t);
  */
 int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
 		struct queue_limits *lim);
+int dm_revalidate_zones(struct dm_table *t, struct request_queue *q);
 void dm_zone_endio(struct dm_io *io, struct bio *clone);
 #ifdef CONFIG_BLK_DEV_ZONED
 int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
 			unsigned int nr_zones, report_zones_cb cb, void *data);
 bool dm_is_zone_write(struct mapped_device *md, struct bio *bio);
 int dm_zone_map_bio(struct dm_target_io *io);
+int dm_zone_get_reset_bitmap(struct mapped_device *md, struct dm_table *t,
+			     sector_t sector, unsigned int nr_zones,
+			     unsigned long *need_reset);
 #else
 #define dm_blk_report_zones	NULL
 static inline bool dm_is_zone_write(struct mapped_device *md, struct bio *bio)

drivers/md/md-bitmap.c

@@ -227,6 +227,8 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap,
 	struct block_device *bdev;
 	struct mddev *mddev = bitmap->mddev;
 	struct bitmap_storage *store = &bitmap->storage;
+	unsigned int bitmap_limit = (bitmap->storage.file_pages - pg_index) <<
+		PAGE_SHIFT;
 	loff_t sboff, offset = mddev->bitmap_info.offset;
 	sector_t ps = pg_index * PAGE_SIZE / SECTOR_SIZE;
 	unsigned int size = PAGE_SIZE;
@@ -269,11 +271,9 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap,
 		if (size == 0)
 			/* bitmap runs in to data */
 			return -EINVAL;
-	} else {
-		/* DATA METADATA BITMAP - no problems */
 	}
 
-	md_super_write(mddev, rdev, sboff + ps, (int) size, page);
+	md_super_write(mddev, rdev, sboff + ps, (int)min(size, bitmap_limit), page);
 	return 0;
 }
 

drivers/md/md-cluster.c

@@ -1570,7 +1570,7 @@ out:
 	return err;
 }
 
-static struct md_cluster_operations cluster_ops = {
+static const struct md_cluster_operations cluster_ops = {
 	.join   = join,
 	.leave  = leave,
 	.slot_number = slot_number,

drivers/md/md.c

@@ -69,13 +69,23 @@
 #include "md-bitmap.h"
 #include "md-cluster.h"
 
+static const char *action_name[NR_SYNC_ACTIONS] = {
+	[ACTION_RESYNC]		= "resync",
+	[ACTION_RECOVER]	= "recover",
+	[ACTION_CHECK]		= "check",
+	[ACTION_REPAIR]		= "repair",
+	[ACTION_RESHAPE]	= "reshape",
+	[ACTION_FROZEN]		= "frozen",
+	[ACTION_IDLE]		= "idle",
+};
+
 /* pers_list is a list of registered personalities protected by pers_lock. */
 static LIST_HEAD(pers_list);
 static DEFINE_SPINLOCK(pers_lock);
 
 static const struct kobj_type md_ktype;
 
-struct md_cluster_operations *md_cluster_ops;
+const struct md_cluster_operations *md_cluster_ops;
 EXPORT_SYMBOL(md_cluster_ops);
 static struct module *md_cluster_mod;
 
@@ -479,7 +489,6 @@ int mddev_suspend(struct mddev *mddev, bool interruptible)
 	 */
 	WRITE_ONCE(mddev->suspended, mddev->suspended + 1);
 
-	del_timer_sync(&mddev->safemode_timer);
 	/* restrict memory reclaim I/O during raid array is suspend */
 	mddev->noio_flag = memalloc_noio_save();
 
@@ -550,13 +559,9 @@ static void md_end_flush(struct bio *bio)
 
 	rdev_dec_pending(rdev, mddev);
 
-	if (atomic_dec_and_test(&mddev->flush_pending)) {
+	if (atomic_dec_and_test(&mddev->flush_pending))
-		/* The pair is percpu_ref_get() from md_flush_request() */
-		percpu_ref_put(&mddev->active_io);
-
 		/* The pre-request flush has finished */
 		queue_work(md_wq, &mddev->flush_work);
-	}
 }
 
 static void md_submit_flush_data(struct work_struct *ws);
@@ -587,12 +592,8 @@ static void submit_flushes(struct work_struct *ws)
 			rcu_read_lock();
 		}
 	rcu_read_unlock();
-	if (atomic_dec_and_test(&mddev->flush_pending)) {
+	if (atomic_dec_and_test(&mddev->flush_pending))
-		/* The pair is percpu_ref_get() from md_flush_request() */
-		percpu_ref_put(&mddev->active_io);
-
 		queue_work(md_wq, &mddev->flush_work);
-	}
 }
 
 static void md_submit_flush_data(struct work_struct *ws)
@@ -617,8 +618,20 @@ static void md_submit_flush_data(struct work_struct *ws)
 		bio_endio(bio);
 	} else {
 		bio->bi_opf &= ~REQ_PREFLUSH;
-		md_handle_request(mddev, bio);
+
+		/*
+		 * make_requst() will never return error here, it only
+		 * returns error in raid5_make_request() by dm-raid.
+		 * Since dm always splits data and flush operation into
+		 * two separate io, io size of flush submitted by dm
+		 * always is 0, make_request() will not be called here.
+		 */
+		if (WARN_ON_ONCE(!mddev->pers->make_request(mddev, bio)))
+			bio_io_error(bio);
 	}
+
+	/* The pair is percpu_ref_get() from md_flush_request() */
+	percpu_ref_put(&mddev->active_io);
 }
 
 /*
@@ -654,24 +667,22 @@ bool md_flush_request(struct mddev *mddev, struct bio *bio)
 		WARN_ON(percpu_ref_is_zero(&mddev->active_io));
 		percpu_ref_get(&mddev->active_io);
 		mddev->flush_bio = bio;
-		bio = NULL;
+		spin_unlock_irq(&mddev->lock);
-	}
-	spin_unlock_irq(&mddev->lock);
-
-	if (!bio) {
 		INIT_WORK(&mddev->flush_work, submit_flushes);
 		queue_work(md_wq, &mddev->flush_work);
-	} else {
+		return true;
-		/* flush was performed for some other bio while we waited. */
-		if (bio->bi_iter.bi_size == 0)
-			/* an empty barrier - all done */
-			bio_endio(bio);
-		else {
-			bio->bi_opf &= ~REQ_PREFLUSH;
-			return false;
-		}
 	}
-	return true;
+
+	/* flush was performed for some other bio while we waited. */
+	spin_unlock_irq(&mddev->lock);
+	if (bio->bi_iter.bi_size == 0) {
+		/* pure flush without data - all done */
+		bio_endio(bio);
+		return true;
+	}
+
+	bio->bi_opf &= ~REQ_PREFLUSH;
+	return false;
 }
 EXPORT_SYMBOL(md_flush_request);
 
@@ -742,7 +753,6 @@ int mddev_init(struct mddev *mddev)
 
 	mutex_init(&mddev->open_mutex);
 	mutex_init(&mddev->reconfig_mutex);
-	mutex_init(&mddev->sync_mutex);
 	mutex_init(&mddev->suspend_mutex);
 	mutex_init(&mddev->bitmap_info.mutex);
 	INIT_LIST_HEAD(&mddev->disks);
@@ -758,7 +768,7 @@ int mddev_init(struct mddev *mddev)
 	init_waitqueue_head(&mddev->recovery_wait);
 	mddev->reshape_position = MaxSector;
 	mddev->reshape_backwards = 0;
-	mddev->last_sync_action = "none";
+	mddev->last_sync_action = ACTION_IDLE;
 	mddev->resync_min = 0;
 	mddev->resync_max = MaxSector;
 	mddev->level = LEVEL_NONE;
@@ -2410,36 +2420,10 @@ static LIST_HEAD(pending_raid_disks);
  */
 int md_integrity_register(struct mddev *mddev)
 {
-	struct md_rdev *rdev, *reference = NULL;
-
 	if (list_empty(&mddev->disks))
 		return 0; /* nothing to do */
-	if (mddev_is_dm(mddev) || blk_get_integrity(mddev->gendisk))
+	if (mddev_is_dm(mddev) || !blk_get_integrity(mddev->gendisk))
-		return 0; /* shouldn't register, or already is */
+		return 0; /* shouldn't register */
-	rdev_for_each(rdev, mddev) {
-		/* skip spares and non-functional disks */
-		if (test_bit(Faulty, &rdev->flags))
-			continue;
-		if (rdev->raid_disk < 0)
-			continue;
-		if (!reference) {
-			/* Use the first rdev as the reference */
-			reference = rdev;
-			continue;
-		}
-		/* does this rdev's profile match the reference profile? */
-		if (blk_integrity_compare(reference->bdev->bd_disk,
-				rdev->bdev->bd_disk) < 0)
-			return -EINVAL;
-	}
-	if (!reference || !bdev_get_integrity(reference->bdev))
-		return 0;
-	/*
-	 * All component devices are integrity capable and have matching
-	 * profiles, register the common profile for the md device.
-	 */
-	blk_integrity_register(mddev->gendisk,
-			       bdev_get_integrity(reference->bdev));
 
 	pr_debug("md: data integrity enabled on %s\n", mdname(mddev));
 	if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE) ||
@@ -2459,32 +2443,6 @@ int md_integrity_register(struct mddev *mddev)
 }
 EXPORT_SYMBOL(md_integrity_register);
 
-/*
- * Attempt to add an rdev, but only if it is consistent with the current
- * integrity profile
- */
-int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev)
-{
-	struct blk_integrity *bi_mddev;
-
-	if (mddev_is_dm(mddev))
-		return 0;
-
-	bi_mddev = blk_get_integrity(mddev->gendisk);
-
-	if (!bi_mddev) /* nothing to do */
-		return 0;
-
-	if (blk_integrity_compare(mddev->gendisk, rdev->bdev->bd_disk) != 0) {
-		pr_err("%s: incompatible integrity profile for %pg\n",
-		       mdname(mddev), rdev->bdev);
-		return -ENXIO;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(md_integrity_add_rdev);
-
 static bool rdev_read_only(struct md_rdev *rdev)
 {
 	return bdev_read_only(rdev->bdev) ||
@@ -4867,30 +4825,81 @@ out_unlock:
 static struct md_sysfs_entry md_metadata =
 __ATTR_PREALLOC(metadata_version, S_IRUGO|S_IWUSR, metadata_show, metadata_store);
 
+enum sync_action md_sync_action(struct mddev *mddev)
+{
+	unsigned long recovery = mddev->recovery;
+
+	/*
+	 * frozen has the highest priority, means running sync_thread will be
+	 * stopped immediately, and no new sync_thread can start.
+	 */
+	if (test_bit(MD_RECOVERY_FROZEN, &recovery))
+		return ACTION_FROZEN;
+
+	/*
+	 * read-only array can't register sync_thread, and it can only
+	 * add/remove spares.
+	 */
+	if (!md_is_rdwr(mddev))
+		return ACTION_IDLE;
+
+	/*
+	 * idle means no sync_thread is running, and no new sync_thread is
+	 * requested.
+	 */
+	if (!test_bit(MD_RECOVERY_RUNNING, &recovery) &&
+	    !test_bit(MD_RECOVERY_NEEDED, &recovery))
+		return ACTION_IDLE;
+
+	if (test_bit(MD_RECOVERY_RESHAPE, &recovery) ||
+	    mddev->reshape_position != MaxSector)
+		return ACTION_RESHAPE;
+
+	if (test_bit(MD_RECOVERY_RECOVER, &recovery))
+		return ACTION_RECOVER;
+
+	if (test_bit(MD_RECOVERY_SYNC, &recovery)) {
+		/*
+		 * MD_RECOVERY_CHECK must be paired with
+		 * MD_RECOVERY_REQUESTED.
+		 */
+		if (test_bit(MD_RECOVERY_CHECK, &recovery))
+			return ACTION_CHECK;
+		if (test_bit(MD_RECOVERY_REQUESTED, &recovery))
+			return ACTION_REPAIR;
+		return ACTION_RESYNC;
+	}
+
+	/*
+	 * MD_RECOVERY_NEEDED or MD_RECOVERY_RUNNING is set, however, no
+	 * sync_action is specified.
+	 */
+	return ACTION_IDLE;
+}
+
+enum sync_action md_sync_action_by_name(const char *page)
+{
+	enum sync_action action;
+
+	for (action = 0; action < NR_SYNC_ACTIONS; ++action) {
+		if (cmd_match(page, action_name[action]))
+			return action;
+	}
+
+	return NR_SYNC_ACTIONS;
+}
+
+const char *md_sync_action_name(enum sync_action action)
+{
+	return action_name[action];
+}
+
 static ssize_t
 action_show(struct mddev *mddev, char *page)
 {
-	char *type = "idle";
+	enum sync_action action = md_sync_action(mddev);
-	unsigned long recovery = mddev->recovery;
+
-	if (test_bit(MD_RECOVERY_FROZEN, &recovery))
+	return sprintf(page, "%s\n", md_sync_action_name(action));
-		type = "frozen";
-	else if (test_bit(MD_RECOVERY_RUNNING, &recovery) ||
-	    (md_is_rdwr(mddev) && test_bit(MD_RECOVERY_NEEDED, &recovery))) {
-		if (test_bit(MD_RECOVERY_RESHAPE, &recovery))
-			type = "reshape";
-		else if (test_bit(MD_RECOVERY_SYNC, &recovery)) {
-			if (!test_bit(MD_RECOVERY_REQUESTED, &recovery))
-				type = "resync";
-			else if (test_bit(MD_RECOVERY_CHECK, &recovery))
-				type = "check";
-			else
-				type = "repair";
-		} else if (test_bit(MD_RECOVERY_RECOVER, &recovery))
-			type = "recover";
-		else if (mddev->reshape_position != MaxSector)
-			type = "reshape";
-	}
-	return sprintf(page, "%s\n", type);
 }
 
 /**
@@ -4899,15 +4908,10 @@ action_show(struct mddev *mddev, char *page)
  * @locked:	if set, reconfig_mutex will still be held after this function
  *		return; if not set, reconfig_mutex will be released after this
  *		function return.
- * @check_seq:	if set, only wait for curent running sync_thread to stop, noted
- *		that new sync_thread can still start.
  */
-static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq)
+static void stop_sync_thread(struct mddev *mddev, bool locked)
 {
-	int sync_seq;
+	int sync_seq = atomic_read(&mddev->sync_seq);
-
-	if (check_seq)
-		sync_seq = atomic_read(&mddev->sync_seq);
 
 	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		if (!locked)
@@ -4928,7 +4932,8 @@ static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq)
 
 	wait_event(resync_wait,
 		   !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
-		   (check_seq && sync_seq != atomic_read(&mddev->sync_seq)));
+		   (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery) &&
+		    sync_seq != atomic_read(&mddev->sync_seq)));
 
 	if (locked)
 		mddev_lock_nointr(mddev);
@@ -4939,7 +4944,7 @@ void md_idle_sync_thread(struct mddev *mddev)
 	lockdep_assert_held(&mddev->reconfig_mutex);
 
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	stop_sync_thread(mddev, true, true);
+	stop_sync_thread(mddev, true);
 }
 EXPORT_SYMBOL_GPL(md_idle_sync_thread);
 
@@ -4948,7 +4953,7 @@ void md_frozen_sync_thread(struct mddev *mddev)
 	lockdep_assert_held(&mddev->reconfig_mutex);
 
 	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	stop_sync_thread(mddev, true, false);
+	stop_sync_thread(mddev, true);
 }
 EXPORT_SYMBOL_GPL(md_frozen_sync_thread);
 
@@ -4963,100 +4968,127 @@ void md_unfrozen_sync_thread(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(md_unfrozen_sync_thread);
 
-static void idle_sync_thread(struct mddev *mddev)
+static int mddev_start_reshape(struct mddev *mddev)
 {
-	mutex_lock(&mddev->sync_mutex);
+	int ret;
-	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 
-	if (mddev_lock(mddev)) {
+	if (mddev->pers->start_reshape == NULL)
-		mutex_unlock(&mddev->sync_mutex);
+		return -EINVAL;
-		return;
+
+	if (mddev->reshape_position == MaxSector ||
+	    mddev->pers->check_reshape == NULL ||
+	    mddev->pers->check_reshape(mddev)) {
+		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+		ret = mddev->pers->start_reshape(mddev);
+		if (ret)
+			return ret;
+	} else {
+		/*
+		 * If reshape is still in progress, and md_check_recovery() can
+		 * continue to reshape, don't restart reshape because data can
+		 * be corrupted for raid456.
+		 */
+		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	}
 
-	stop_sync_thread(mddev, false, true);
+	sysfs_notify_dirent_safe(mddev->sysfs_degraded);
-	mutex_unlock(&mddev->sync_mutex);
+	return 0;
-}
-
-static void frozen_sync_thread(struct mddev *mddev)
-{
-	mutex_lock(&mddev->sync_mutex);
-	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-
-	if (mddev_lock(mddev)) {
-		mutex_unlock(&mddev->sync_mutex);
-		return;
-	}
-
-	stop_sync_thread(mddev, false, false);
-	mutex_unlock(&mddev->sync_mutex);
 }
 
 static ssize_t
 action_store(struct mddev *mddev, const char *page, size_t len)
 {
+	int ret;
+	enum sync_action action;
+
 	if (!mddev->pers || !mddev->pers->sync_request)
 		return -EINVAL;
 
+retry:
+	if (work_busy(&mddev->sync_work))
+		flush_work(&mddev->sync_work);
 
-	if (cmd_match(page, "idle"))
+	ret = mddev_lock(mddev);
-		idle_sync_thread(mddev);
+	if (ret)
-	else if (cmd_match(page, "frozen"))
+		return ret;
-		frozen_sync_thread(mddev);
+
-	else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+	if (work_busy(&mddev->sync_work)) {
-		return -EBUSY;
+		mddev_unlock(mddev);
-	else if (cmd_match(page, "resync"))
+		goto retry;
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	else if (cmd_match(page, "recover")) {
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-	} else if (cmd_match(page, "reshape")) {
-		int err;
-		if (mddev->pers->start_reshape == NULL)
-			return -EINVAL;
-		err = mddev_lock(mddev);
-		if (!err) {
-			if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
-				err =  -EBUSY;
-			} else if (mddev->reshape_position == MaxSector ||
-				   mddev->pers->check_reshape == NULL ||
-				   mddev->pers->check_reshape(mddev)) {
-				clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-				err = mddev->pers->start_reshape(mddev);
-			} else {
-				/*
-				 * If reshape is still in progress, and
-				 * md_check_recovery() can continue to reshape,
-				 * don't restart reshape because data can be
-				 * corrupted for raid456.
-				 */
-				clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-			}
-			mddev_unlock(mddev);
-		}
-		if (err)
-			return err;
-		sysfs_notify_dirent_safe(mddev->sysfs_degraded);
-	} else {
-		if (cmd_match(page, "check"))
-			set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
-		else if (!cmd_match(page, "repair"))
-			return -EINVAL;
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-		set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
-		set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 	}
+
+	action = md_sync_action_by_name(page);
+
+	/* TODO: mdadm rely on "idle" to start sync_thread. */
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
+		switch (action) {
+		case ACTION_FROZEN:
+			md_frozen_sync_thread(mddev);
+			ret = len;
+			goto out;
+		case ACTION_IDLE:
+			md_idle_sync_thread(mddev);
+			break;
+		case ACTION_RESHAPE:
+		case ACTION_RECOVER:
+		case ACTION_CHECK:
+		case ACTION_REPAIR:
+		case ACTION_RESYNC:
+			ret = -EBUSY;
+			goto out;
+		default:
+			ret = -EINVAL;
+			goto out;
+		}
+	} else {
+		switch (action) {
+		case ACTION_FROZEN:
+			set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+			ret = len;
+			goto out;
+		case ACTION_RESHAPE:
+			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+			ret = mddev_start_reshape(mddev);
+			if (ret)
+				goto out;
+			break;
+		case ACTION_RECOVER:
+			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+			set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+			break;
+		case ACTION_CHECK:
+			set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+			fallthrough;
+		case ACTION_REPAIR:
+			set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+			set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+			fallthrough;
+		case ACTION_RESYNC:
+		case ACTION_IDLE:
+			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+			break;
+		default:
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
 	if (mddev->ro == MD_AUTO_READ) {
 		/* A write to sync_action is enough to justify
 		 * canceling read-auto mode
 		 */
-		flush_work(&mddev->sync_work);
 		mddev->ro = MD_RDWR;
 		md_wakeup_thread(mddev->sync_thread);
 	}
+
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 	sysfs_notify_dirent_safe(mddev->sysfs_action);
-	return len;
+	ret = len;
+
+out:
+	mddev_unlock(mddev);
+	return ret;
 }
 
 static struct md_sysfs_entry md_scan_mode =
@@ -5065,7 +5097,8 @@ __ATTR_PREALLOC(sync_action, S_IRUGO|S_IWUSR, action_show, action_store);
 static ssize_t
 last_sync_action_show(struct mddev *mddev, char *page)
 {
-	return sprintf(page, "%s\n", mddev->last_sync_action);
+	return sprintf(page, "%s\n",
+		       md_sync_action_name(mddev->last_sync_action));
 }
 
 static struct md_sysfs_entry md_last_scan_mode = __ATTR_RO(last_sync_action);
@@ -5755,14 +5788,20 @@ static const struct kobj_type md_ktype = {
 int mdp_major = 0;
 
 /* stack the limit for all rdevs into lim */
-void mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim)
+int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim,
+		unsigned int flags)
 {
 	struct md_rdev *rdev;
 
 	rdev_for_each(rdev, mddev) {
 		queue_limits_stack_bdev(lim, rdev->bdev, rdev->data_offset,
 					mddev->gendisk->disk_name);
+		if ((flags & MDDEV_STACK_INTEGRITY) &&
+		    !queue_limits_stack_integrity_bdev(lim, rdev->bdev))
+			return -EINVAL;
 	}
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(mddev_stack_rdev_limits);
 
@@ -5777,6 +5816,14 @@ int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev)
 	lim = queue_limits_start_update(mddev->gendisk->queue);
 	queue_limits_stack_bdev(&lim, rdev->bdev, rdev->data_offset,
 				mddev->gendisk->disk_name);
+
+	if (!queue_limits_stack_integrity_bdev(&lim, rdev->bdev)) {
+		pr_err("%s: incompatible integrity profile for %pg\n",
+		       mdname(mddev), rdev->bdev);
+		queue_limits_cancel_update(mddev->gendisk->queue);
+		return -ENXIO;
+	}
+
 	return queue_limits_commit_update(mddev->gendisk->queue, &lim);
 }
 EXPORT_SYMBOL_GPL(mddev_stack_new_rdev);
@@ -5806,6 +5853,14 @@ static void mddev_delayed_delete(struct work_struct *ws)
 	kobject_put(&mddev->kobj);
 }
 
+void md_init_stacking_limits(struct queue_limits *lim)
+{
+	blk_set_stacking_limits(lim);
+	lim->features = BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA |
+			BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT;
+}
+EXPORT_SYMBOL_GPL(md_init_stacking_limits);
+
 struct mddev *md_alloc(dev_t dev, char *name)
 {
 	/*
@@ -5823,7 +5878,7 @@ struct mddev *md_alloc(dev_t dev, char *name)
 	int partitioned;
 	int shift;
 	int unit;
-	int error ;
+	int error;
 
 	/*
 	 * Wait for any previous instance of this device to be completely
@@ -5881,7 +5936,6 @@ struct mddev *md_alloc(dev_t dev, char *name)
 	disk->fops = &md_fops;
 	disk->private_data = mddev;
 
-	blk_queue_write_cache(disk->queue, true, true);
 	disk->events |= DISK_EVENT_MEDIA_CHANGE;
 	mddev->gendisk = disk;
 	error = add_disk(disk);
@@ -6185,28 +6239,6 @@ int md_run(struct mddev *mddev)
 		}
 	}
 
-	if (!mddev_is_dm(mddev)) {
-		struct request_queue *q = mddev->gendisk->queue;
-		bool nonrot = true;
-
-		rdev_for_each(rdev, mddev) {
-			if (rdev->raid_disk >= 0 && !bdev_nonrot(rdev->bdev)) {
-				nonrot = false;
-				break;
-			}
-		}
-		if (mddev->degraded)
-			nonrot = false;
-		if (nonrot)
-			blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-		else
-			blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
-		blk_queue_flag_set(QUEUE_FLAG_IO_STAT, q);
-
-		/* Set the NOWAIT flags if all underlying devices support it */
-		if (nowait)
-			blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
-	}
 	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
 		    sysfs_create_group(&mddev->kobj, &md_redundancy_group))
@@ -6437,7 +6469,7 @@ void md_stop_writes(struct mddev *mddev)
 {
 	mddev_lock_nointr(mddev);
 	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	stop_sync_thread(mddev, true, false);
+	stop_sync_thread(mddev, true);
 	__md_stop_writes(mddev);
 	mddev_unlock(mddev);
 }
@@ -6505,7 +6537,7 @@ static int md_set_readonly(struct mddev *mddev)
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	}
 
-	stop_sync_thread(mddev, false, false);
+	stop_sync_thread(mddev, false);
 	wait_event(mddev->sb_wait,
 		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 	mddev_lock_nointr(mddev);
@@ -6551,7 +6583,7 @@ static int do_md_stop(struct mddev *mddev, int mode)
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	}
 
-	stop_sync_thread(mddev, true, false);
+	stop_sync_thread(mddev, true);
 
 	if (mddev->sysfs_active ||
 	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
@@ -7165,15 +7197,6 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
 	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 	if (!mddev->thread)
 		md_update_sb(mddev, 1);
-	/*
-	 * If the new disk does not support REQ_NOWAIT,
-	 * disable on the whole MD.
-	 */
-	if (!bdev_nowait(rdev->bdev)) {
-		pr_info("%s: Disabling nowait because %pg does not support nowait\n",
-			mdname(mddev), rdev->bdev);
-		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->gendisk->queue);
-	}
 	/*
 	 * Kick recovery, maybe this spare has to be added to the
 	 * array immediately.
@@ -7742,12 +7765,6 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 		return get_bitmap_file(mddev, argp);
 	}
 
-	if (cmd == HOT_REMOVE_DISK)
-		/* need to ensure recovery thread has run */
-		wait_event_interruptible_timeout(mddev->sb_wait,
-						 !test_bit(MD_RECOVERY_NEEDED,
-							   &mddev->recovery),
-						 msecs_to_jiffies(5000));
 	if (cmd == STOP_ARRAY || cmd == STOP_ARRAY_RO) {
 		/* Need to flush page cache, and ensure no-one else opens
 		 * and writes
@@ -8520,7 +8537,7 @@ int unregister_md_personality(struct md_personality *p)
 }
 EXPORT_SYMBOL(unregister_md_personality);
 
-int register_md_cluster_operations(struct md_cluster_operations *ops,
+int register_md_cluster_operations(const struct md_cluster_operations *ops,
 				   struct module *module)
 {
 	int ret = 0;
@@ -8641,12 +8658,12 @@ EXPORT_SYMBOL(md_done_sync);
  * A return value of 'false' means that the write wasn't recorded
  * and cannot proceed as the array is being suspend.
  */
-bool md_write_start(struct mddev *mddev, struct bio *bi)
+void md_write_start(struct mddev *mddev, struct bio *bi)
 {
 	int did_change = 0;
 
 	if (bio_data_dir(bi) != WRITE)
-		return true;
+		return;
 
 	BUG_ON(mddev->ro == MD_RDONLY);
 	if (mddev->ro == MD_AUTO_READ) {
@@ -8679,15 +8696,9 @@ bool md_write_start(struct mddev *mddev, struct bio *bi)
 	if (did_change)
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	if (!mddev->has_superblocks)
-		return true;
+		return;
 	wait_event(mddev->sb_wait,
-		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) ||
+		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
-		   is_md_suspended(mddev));
-	if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
-		percpu_ref_put(&mddev->writes_pending);
-		return false;
-	}
-	return true;
 }
 EXPORT_SYMBOL(md_write_start);
 
@@ -8835,6 +8846,77 @@ void md_allow_write(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(md_allow_write);
 
+static sector_t md_sync_max_sectors(struct mddev *mddev,
+				    enum sync_action action)
+{
+	switch (action) {
+	case ACTION_RESYNC:
+	case ACTION_CHECK:
+	case ACTION_REPAIR:
+		atomic64_set(&mddev->resync_mismatches, 0);
+		fallthrough;
+	case ACTION_RESHAPE:
+		return mddev->resync_max_sectors;
+	case ACTION_RECOVER:
+		return mddev->dev_sectors;
+	default:
+		return 0;
+	}
+}
+
+static sector_t md_sync_position(struct mddev *mddev, enum sync_action action)
+{
+	sector_t start = 0;
+	struct md_rdev *rdev;
+
+	switch (action) {
+	case ACTION_CHECK:
+	case ACTION_REPAIR:
+		return mddev->resync_min;
+	case ACTION_RESYNC:
+		if (!mddev->bitmap)
+			return mddev->recovery_cp;
+		return 0;
+	case ACTION_RESHAPE:
+		/*
+		 * If the original node aborts reshaping then we continue the
+		 * reshaping, so set again to avoid restart reshape from the
+		 * first beginning
+		 */
+		if (mddev_is_clustered(mddev) &&
+		    mddev->reshape_position != MaxSector)
+			return mddev->reshape_position;
+		return 0;
+	case ACTION_RECOVER:
+		start = MaxSector;
+		rcu_read_lock();
+		rdev_for_each_rcu(rdev, mddev)
+			if (rdev->raid_disk >= 0 &&
+			    !test_bit(Journal, &rdev->flags) &&
+			    !test_bit(Faulty, &rdev->flags) &&
+			    !test_bit(In_sync, &rdev->flags) &&
+			    rdev->recovery_offset < start)
+				start = rdev->recovery_offset;
+		rcu_read_unlock();
+
+		/* If there is a bitmap, we need to make sure all
+		 * writes that started before we added a spare
+		 * complete before we start doing a recovery.
+		 * Otherwise the write might complete and (via
+		 * bitmap_endwrite) set a bit in the bitmap after the
+		 * recovery has checked that bit and skipped that
+		 * region.
+		 */
+		if (mddev->bitmap) {
+			mddev->pers->quiesce(mddev, 1);
+			mddev->pers->quiesce(mddev, 0);
+		}
+		return start;
+	default:
+		return MaxSector;
+	}
+}
+
 #define SYNC_MARKS	10
 #define	SYNC_MARK_STEP	(3*HZ)
 #define UPDATE_FREQUENCY (5*60*HZ)
@@ -8851,7 +8933,8 @@ void md_do_sync(struct md_thread *thread)
 	sector_t last_check;
 	int skipped = 0;
 	struct md_rdev *rdev;
-	char *desc, *action = NULL;
+	enum sync_action action;
+	const char *desc;
 	struct blk_plug plug;
 	int ret;
 
@@ -8882,21 +8965,9 @@ void md_do_sync(struct md_thread *thread)
 			goto skip;
 	}
 
-	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+	action = md_sync_action(mddev);
-		if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)) {
+	desc = md_sync_action_name(action);
-			desc = "data-check";
+	mddev->last_sync_action = action;
-			action = "check";
-		} else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
-			desc = "requested-resync";
-			action = "repair";
-		} else
-			desc = "resync";
-	} else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
-		desc = "reshape";
-	else
-		desc = "recovery";
-
-	mddev->last_sync_action = action ?: desc;
 
 	/*
 	 * Before starting a resync we must have set curr_resync to
@@ -8964,56 +9035,8 @@ void md_do_sync(struct md_thread *thread)
 		spin_unlock(&all_mddevs_lock);
 	} while (mddev->curr_resync < MD_RESYNC_DELAYED);
 
-	j = 0;
+	max_sectors = md_sync_max_sectors(mddev, action);
-	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+	j = md_sync_position(mddev, action);
-		/* resync follows the size requested by the personality,
-		 * which defaults to physical size, but can be virtual size
-		 */
-		max_sectors = mddev->resync_max_sectors;
-		atomic64_set(&mddev->resync_mismatches, 0);
-		/* we don't use the checkpoint if there's a bitmap */
-		if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
-			j = mddev->resync_min;
-		else if (!mddev->bitmap)
-			j = mddev->recovery_cp;
-
-	} else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) {
-		max_sectors = mddev->resync_max_sectors;
-		/*
-		 * If the original node aborts reshaping then we continue the
-		 * reshaping, so set j again to avoid restart reshape from the
-		 * first beginning
-		 */
-		if (mddev_is_clustered(mddev) &&
-		    mddev->reshape_position != MaxSector)
-			j = mddev->reshape_position;
-	} else {
-		/* recovery follows the physical size of devices */
-		max_sectors = mddev->dev_sectors;
-		j = MaxSector;
-		rcu_read_lock();
-		rdev_for_each_rcu(rdev, mddev)
-			if (rdev->raid_disk >= 0 &&
-			    !test_bit(Journal, &rdev->flags) &&
-			    !test_bit(Faulty, &rdev->flags) &&
-			    !test_bit(In_sync, &rdev->flags) &&
-			    rdev->recovery_offset < j)
-				j = rdev->recovery_offset;
-		rcu_read_unlock();
-
-		/* If there is a bitmap, we need to make sure all
-		 * writes that started before we added a spare
-		 * complete before we start doing a recovery.
-		 * Otherwise the write might complete and (via
-		 * bitmap_endwrite) set a bit in the bitmap after the
-		 * recovery has checked that bit and skipped that
-		 * region.
-		 */
-		if (mddev->bitmap) {
-			mddev->pers->quiesce(mddev, 1);
-			mddev->pers->quiesce(mddev, 0);
-		}
-	}
 
 	pr_info("md: %s of RAID array %s\n", desc, mdname(mddev));
 	pr_debug("md: minimum _guaranteed_  speed: %d KB/sec/disk.\n", speed_min(mddev));
@@ -9095,7 +9118,8 @@ void md_do_sync(struct md_thread *thread)
 		if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
 			break;
 
-		sectors = mddev->pers->sync_request(mddev, j, &skipped);
+		sectors = mddev->pers->sync_request(mddev, j, max_sectors,
+						    &skipped);
 		if (sectors == 0) {
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 			break;
@@ -9185,7 +9209,7 @@ void md_do_sync(struct md_thread *thread)
 		mddev->curr_resync_completed = mddev->curr_resync;
 		sysfs_notify_dirent_safe(mddev->sysfs_completed);
 	}
-	mddev->pers->sync_request(mddev, max_sectors, &skipped);
+	mddev->pers->sync_request(mddev, max_sectors, max_sectors, &skipped);
 
 	if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
 	    mddev->curr_resync > MD_RESYNC_ACTIVE) {

drivers/md/md.h

@@ -34,6 +34,61 @@
  */
 #define	MD_FAILFAST	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT)
 
+/* Status of sync thread. */
+enum sync_action {
+	/*
+	 * Represent by MD_RECOVERY_SYNC, start when:
+	 * 1) after assemble, sync data from first rdev to other copies, this
+	 * must be done first before other sync actions and will only execute
+	 * once;
+	 * 2) resize the array(notice that this is not reshape), sync data for
+	 * the new range;
+	 */
+	ACTION_RESYNC,
+	/*
+	 * Represent by MD_RECOVERY_RECOVER, start when:
+	 * 1) for new replacement, sync data based on the replace rdev or
+	 * available copies from other rdev;
+	 * 2) for new member disk while the array is degraded, sync data from
+	 * other rdev;
+	 * 3) reassemble after power failure or re-add a hot removed rdev, sync
+	 * data from first rdev to other copies based on bitmap;
+	 */
+	ACTION_RECOVER,
+	/*
+	 * Represent by MD_RECOVERY_SYNC | MD_RECOVERY_REQUESTED |
+	 * MD_RECOVERY_CHECK, start when user echo "check" to sysfs api
+	 * sync_action, used to check if data copies from differenct rdev are
+	 * the same. The number of mismatch sectors will be exported to user
+	 * by sysfs api mismatch_cnt;
+	 */
+	ACTION_CHECK,
+	/*
+	 * Represent by MD_RECOVERY_SYNC | MD_RECOVERY_REQUESTED, start when
+	 * user echo "repair" to sysfs api sync_action, usually paired with
+	 * ACTION_CHECK, used to force syncing data once user found that there
+	 * are inconsistent data,
+	 */
+	ACTION_REPAIR,
+	/*
+	 * Represent by MD_RECOVERY_RESHAPE, start when new member disk is added
+	 * to the conf, notice that this is different from spares or
+	 * replacement;
+	 */
+	ACTION_RESHAPE,
+	/*
+	 * Represent by MD_RECOVERY_FROZEN, can be set by sysfs api sync_action
+	 * or internal usage like setting the array read-only, will forbid above
+	 * actions.
+	 */
+	ACTION_FROZEN,
+	/*
+	 * All above actions don't match.
+	 */
+	ACTION_IDLE,
+	NR_SYNC_ACTIONS,
+};
+
 /*
  * The struct embedded in rdev is used to serialize IO.
  */
@@ -371,13 +426,12 @@ struct mddev {
 	struct md_thread __rcu		*thread;	/* management thread */
 	struct md_thread __rcu		*sync_thread;	/* doing resync or reconstruct */
 
-	/* 'last_sync_action' is initialized to "none".  It is set when a
+	/*
-	 * sync operation (i.e "data-check", "requested-resync", "resync",
+	 * Set when a sync operation is started. It holds this value even
-	 * "recovery", or "reshape") is started.  It holds this value even
 	 * when the sync thread is "frozen" (interrupted) or "idle" (stopped
-	 * or finished).  It is overwritten when a new sync operation is begun.
+	 * or finished). It is overwritten when a new sync operation is begun.
 	 */
-	char				*last_sync_action;
+	enum sync_action		last_sync_action;
 	sector_t			curr_resync;	/* last block scheduled */
 	/* As resync requests can complete out of order, we cannot easily track
 	 * how much resync has been completed.  So we occasionally pause until
@@ -540,8 +594,6 @@ struct mddev {
 	 */
 	struct list_head		deleting;
 
-	/* Used to synchronize idle and frozen for action_store() */
-	struct mutex			sync_mutex;
 	/* The sequence number for sync thread */
 	atomic_t sync_seq;
 
@@ -551,22 +603,46 @@ struct mddev {
 };
 
 enum recovery_flags {
+	/* flags for sync thread running status */
+
 	/*
-	 * If neither SYNC or RESHAPE are set, then it is a recovery.
+	 * set when one of sync action is set and new sync thread need to be
+	 * registered, or just add/remove spares from conf.
 	 */
-	MD_RECOVERY_RUNNING,	/* a thread is running, or about to be started */
+	MD_RECOVERY_NEEDED,
-	MD_RECOVERY_SYNC,	/* actually doing a resync, not a recovery */
+	/* sync thread is running, or about to be started */
-	MD_RECOVERY_RECOVER,	/* doing recovery, or need to try it. */
+	MD_RECOVERY_RUNNING,
-	MD_RECOVERY_INTR,	/* resync needs to be aborted for some reason */
+	/* sync thread needs to be aborted for some reason */
-	MD_RECOVERY_DONE,	/* thread is done and is waiting to be reaped */
+	MD_RECOVERY_INTR,
-	MD_RECOVERY_NEEDED,	/* we might need to start a resync/recover */
+	/* sync thread is done and is waiting to be unregistered */
-	MD_RECOVERY_REQUESTED,	/* user-space has requested a sync (used with SYNC) */
+	MD_RECOVERY_DONE,
-	MD_RECOVERY_CHECK,	/* user-space request for check-only, no repair */
+	/* running sync thread must abort immediately, and not restart */
-	MD_RECOVERY_RESHAPE,	/* A reshape is happening */
+	MD_RECOVERY_FROZEN,
-	MD_RECOVERY_FROZEN,	/* User request to abort, and not restart, any action */
+	/* waiting for pers->start() to finish */
-	MD_RECOVERY_ERROR,	/* sync-action interrupted because io-error */
+	MD_RECOVERY_WAIT,
-	MD_RECOVERY_WAIT,	/* waiting for pers->start() to finish */
+	/* interrupted because io-error */
-	MD_RESYNCING_REMOTE,	/* remote node is running resync thread */
+	MD_RECOVERY_ERROR,
+
+	/* flags determines sync action, see details in enum sync_action */
+
+	/* if just this flag is set, action is resync. */
+	MD_RECOVERY_SYNC,
+	/*
+	 * paired with MD_RECOVERY_SYNC, if MD_RECOVERY_CHECK is not set,
+	 * action is repair, means user requested resync.
+	 */
+	MD_RECOVERY_REQUESTED,
+	/*
+	 * paired with MD_RECOVERY_SYNC and MD_RECOVERY_REQUESTED, action is
+	 * check.
+	 */
+	MD_RECOVERY_CHECK,
+	/* recovery, or need to try it */
+	MD_RECOVERY_RECOVER,
+	/* reshape */
+	MD_RECOVERY_RESHAPE,
+	/* remote node is running resync thread */
+	MD_RESYNCING_REMOTE,
 };
 
 enum md_ro_state {
@@ -653,7 +729,8 @@ struct md_personality
 	int (*hot_add_disk) (struct mddev *mddev, struct md_rdev *rdev);
 	int (*hot_remove_disk) (struct mddev *mddev, struct md_rdev *rdev);
 	int (*spare_active) (struct mddev *mddev);
-	sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr, int *skipped);
+	sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr,
+				 sector_t max_sector, int *skipped);
 	int (*resize) (struct mddev *mddev, sector_t sectors);
 	sector_t (*size) (struct mddev *mddev, sector_t sectors, int raid_disks);
 	int (*check_reshape) (struct mddev *mddev);
@@ -772,7 +849,7 @@ static inline void safe_put_page(struct page *p)
 
 extern int register_md_personality(struct md_personality *p);
 extern int unregister_md_personality(struct md_personality *p);
-extern int register_md_cluster_operations(struct md_cluster_operations *ops,
+extern int register_md_cluster_operations(const struct md_cluster_operations *ops,
 		struct module *module);
 extern int unregister_md_cluster_operations(void);
 extern int md_setup_cluster(struct mddev *mddev, int nodes);
@@ -785,7 +862,10 @@ extern void md_unregister_thread(struct mddev *mddev, struct md_thread __rcu **t
 extern void md_wakeup_thread(struct md_thread __rcu *thread);
 extern void md_check_recovery(struct mddev *mddev);
 extern void md_reap_sync_thread(struct mddev *mddev);
-extern bool md_write_start(struct mddev *mddev, struct bio *bi);
+extern enum sync_action md_sync_action(struct mddev *mddev);
+extern enum sync_action md_sync_action_by_name(const char *page);
+extern const char *md_sync_action_name(enum sync_action action);
+extern void md_write_start(struct mddev *mddev, struct bio *bi);
 extern void md_write_inc(struct mddev *mddev, struct bio *bi);
 extern void md_write_end(struct mddev *mddev);
 extern void md_done_sync(struct mddev *mddev, int blocks, int ok);
@@ -809,11 +889,11 @@ extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev);
 extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors);
 extern int md_check_no_bitmap(struct mddev *mddev);
 extern int md_integrity_register(struct mddev *mddev);
-extern int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev);
 extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);
 
 extern int mddev_init(struct mddev *mddev);
 extern void mddev_destroy(struct mddev *mddev);
+void md_init_stacking_limits(struct queue_limits *lim);
 struct mddev *md_alloc(dev_t dev, char *name);
 void mddev_put(struct mddev *mddev);
 extern int md_run(struct mddev *mddev);
@@ -852,7 +932,7 @@ static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
 	}
 }
 
-extern struct md_cluster_operations *md_cluster_ops;
+extern const struct md_cluster_operations *md_cluster_ops;
 static inline int mddev_is_clustered(struct mddev *mddev)
 {
 	return mddev->cluster_info && mddev->bitmap_info.nodes > 1;
@@ -908,7 +988,9 @@ void md_autostart_arrays(int part);
 int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info);
 int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info);
 int do_md_run(struct mddev *mddev);
-void mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim);
+#define MDDEV_STACK_INTEGRITY	(1u << 0)
+int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim,
+		unsigned int flags);
 int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev);
 void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes);
 

drivers/md/raid0.c

@@ -365,30 +365,30 @@ static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks
 	return array_sectors;
 }
 
-static void free_conf(struct mddev *mddev, struct r0conf *conf)
+static void raid0_free(struct mddev *mddev, void *priv)
 {
+	struct r0conf *conf = priv;
+
 	kfree(conf->strip_zone);
 	kfree(conf->devlist);
 	kfree(conf);
 }
 
-static void raid0_free(struct mddev *mddev, void *priv)
-{
-	struct r0conf *conf = priv;
-
-	free_conf(mddev, conf);
-}
-
 static int raid0_set_limits(struct mddev *mddev)
 {
 	struct queue_limits lim;
+	int err;
 
-	blk_set_stacking_limits(&lim);
+	md_init_stacking_limits(&lim);
 	lim.max_hw_sectors = mddev->chunk_sectors;
 	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * mddev->raid_disks;
-	mddev_stack_rdev_limits(mddev, &lim);
+	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
+	if (err) {
+		queue_limits_cancel_update(mddev->gendisk->queue);
+		return err;
+	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
@@ -415,7 +415,7 @@ static int raid0_run(struct mddev *mddev)
 	if (!mddev_is_dm(mddev)) {
 		ret = raid0_set_limits(mddev);
 		if (ret)
-			goto out_free_conf;
+			return ret;
 	}
 
 	/* calculate array device size */
@@ -427,13 +427,7 @@ static int raid0_run(struct mddev *mddev)
 
 	dump_zones(mddev);
 
-	ret = md_integrity_register(mddev);
+	return md_integrity_register(mddev);
-	if (ret)
-		goto out_free_conf;
-	return 0;
-out_free_conf:
-	free_conf(mddev, conf);
-	return ret;
 }
 
 /*

drivers/md/raid1.c

@@ -1687,8 +1687,7 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 	if (bio_data_dir(bio) == READ)
 		raid1_read_request(mddev, bio, sectors, NULL);
 	else {
-		if (!md_write_start(mddev,bio))
+		md_write_start(mddev,bio);
-			return false;
 		raid1_write_request(mddev, bio, sectors);
 	}
 	return true;
@@ -1907,9 +1906,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (mddev->recovery_disabled == conf->recovery_disabled)
 		return -EBUSY;
 
-	if (md_integrity_add_rdev(rdev, mddev))
-		return -ENXIO;
-
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
@@ -2757,12 +2753,12 @@ static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf)
  */
 
 static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
-				   int *skipped)
+				   sector_t max_sector, int *skipped)
 {
 	struct r1conf *conf = mddev->private;
 	struct r1bio *r1_bio;
 	struct bio *bio;
-	sector_t max_sector, nr_sectors;
+	sector_t nr_sectors;
 	int disk = -1;
 	int i;
 	int wonly = -1;
@@ -2778,7 +2774,6 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		if (init_resync(conf))
 			return 0;
 
-	max_sector = mddev->dev_sectors;
 	if (sector_nr >= max_sector) {
 		/* If we aborted, we need to abort the
 		 * sync on the 'current' bitmap chunk (there will
@@ -3197,14 +3192,18 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 static int raid1_set_limits(struct mddev *mddev)
 {
 	struct queue_limits lim;
+	int err;
 
-	blk_set_stacking_limits(&lim);
+	md_init_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
-	mddev_stack_rdev_limits(mddev, &lim);
+	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
+	if (err) {
+		queue_limits_cancel_update(mddev->gendisk->queue);
+		return err;
+	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
-static void raid1_free(struct mddev *mddev, void *priv);
 static int raid1_run(struct mddev *mddev)
 {
 	struct r1conf *conf;
@@ -3238,7 +3237,7 @@ static int raid1_run(struct mddev *mddev)
 	if (!mddev_is_dm(mddev)) {
 		ret = raid1_set_limits(mddev);
 		if (ret)
-			goto abort;
+			return ret;
 	}
 
 	mddev->degraded = 0;
@@ -3252,8 +3251,7 @@ static int raid1_run(struct mddev *mddev)
 	 */
 	if (conf->raid_disks - mddev->degraded < 1) {
 		md_unregister_thread(mddev, &conf->thread);
-		ret = -EINVAL;
+		return -EINVAL;
-		goto abort;
 	}
 
 	if (conf->raid_disks - mddev->degraded == 1)
@@ -3277,14 +3275,8 @@ static int raid1_run(struct mddev *mddev)
 	md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
 
 	ret = md_integrity_register(mddev);
-	if (ret) {
+	if (ret)
 		md_unregister_thread(mddev, &mddev->thread);
-		goto abort;
-	}
-	return 0;
-
-abort:
-	raid1_free(mddev, conf);
 	return ret;
 }
 

drivers/md/raid10.c

@@ -1836,8 +1836,7 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
 	    && md_flush_request(mddev, bio))
 		return true;
 
-	if (!md_write_start(mddev, bio))
+	md_write_start(mddev, bio);
-		return false;
 
 	if (unlikely(bio_op(bio) == REQ_OP_DISCARD))
 		if (!raid10_handle_discard(mddev, bio))
@@ -2083,9 +2082,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (rdev->saved_raid_disk < 0 && !_enough(conf, 1, -1))
 		return -EINVAL;
 
-	if (md_integrity_add_rdev(rdev, mddev))
-		return -ENXIO;
-
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
@@ -3140,12 +3136,12 @@ static void raid10_set_cluster_sync_high(struct r10conf *conf)
  */
 
 static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
-			     int *skipped)
+				    sector_t max_sector, int *skipped)
 {
 	struct r10conf *conf = mddev->private;
 	struct r10bio *r10_bio;
 	struct bio *biolist = NULL, *bio;
-	sector_t max_sector, nr_sectors;
+	sector_t nr_sectors;
 	int i;
 	int max_sync;
 	sector_t sync_blocks;
@@ -3175,10 +3171,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			return 0;
 
  skipped:
-	max_sector = mddev->dev_sectors;
-	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
-	    test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
-		max_sector = mddev->resync_max_sectors;
 	if (sector_nr >= max_sector) {
 		conf->cluster_sync_low = 0;
 		conf->cluster_sync_high = 0;
@@ -3980,12 +3972,17 @@ static int raid10_set_queue_limits(struct mddev *mddev)
 {
 	struct r10conf *conf = mddev->private;
 	struct queue_limits lim;
+	int err;
 
-	blk_set_stacking_limits(&lim);
+	md_init_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
-	mddev_stack_rdev_limits(mddev, &lim);
+	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
+	if (err) {
+		queue_limits_cancel_update(mddev->gendisk->queue);
+		return err;
+	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 

drivers/md/raid5.c

@@ -155,7 +155,7 @@ static int raid6_idx_to_slot(int idx, struct stripe_head *sh,
 	return slot;
 }
 
-static void print_raid5_conf (struct r5conf *conf);
+static void print_raid5_conf(struct r5conf *conf);
 
 static int stripe_operations_active(struct stripe_head *sh)
 {
@@ -5899,6 +5899,39 @@ out:
 	return ret;
 }
 
+enum reshape_loc {
+	LOC_NO_RESHAPE,
+	LOC_AHEAD_OF_RESHAPE,
+	LOC_INSIDE_RESHAPE,
+	LOC_BEHIND_RESHAPE,
+};
+
+static enum reshape_loc get_reshape_loc(struct mddev *mddev,
+		struct r5conf *conf, sector_t logical_sector)
+{
+	sector_t reshape_progress, reshape_safe;
+	/*
+	 * Spinlock is needed as reshape_progress may be
+	 * 64bit on a 32bit platform, and so it might be
+	 * possible to see a half-updated value
+	 * Of course reshape_progress could change after
+	 * the lock is dropped, so once we get a reference
+	 * to the stripe that we think it is, we will have
+	 * to check again.
+	 */
+	spin_lock_irq(&conf->device_lock);
+	reshape_progress = conf->reshape_progress;
+	reshape_safe = conf->reshape_safe;
+	spin_unlock_irq(&conf->device_lock);
+	if (reshape_progress == MaxSector)
+		return LOC_NO_RESHAPE;
+	if (ahead_of_reshape(mddev, logical_sector, reshape_progress))
+		return LOC_AHEAD_OF_RESHAPE;
+	if (ahead_of_reshape(mddev, logical_sector, reshape_safe))
+		return LOC_INSIDE_RESHAPE;
+	return LOC_BEHIND_RESHAPE;
+}
+
 static enum stripe_result make_stripe_request(struct mddev *mddev,
 		struct r5conf *conf, struct stripe_request_ctx *ctx,
 		sector_t logical_sector, struct bio *bi)
@@ -5913,28 +5946,14 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
 	seq = read_seqcount_begin(&conf->gen_lock);
 
 	if (unlikely(conf->reshape_progress != MaxSector)) {
-		/*
+		enum reshape_loc loc = get_reshape_loc(mddev, conf,
-		 * Spinlock is needed as reshape_progress may be
+						       logical_sector);
-		 * 64bit on a 32bit platform, and so it might be
+		if (loc == LOC_INSIDE_RESHAPE) {
-		 * possible to see a half-updated value
+			ret = STRIPE_SCHEDULE_AND_RETRY;
-		 * Of course reshape_progress could change after
+			goto out;
-		 * the lock is dropped, so once we get a reference
-		 * to the stripe that we think it is, we will have
-		 * to check again.
-		 */
-		spin_lock_irq(&conf->device_lock);
-		if (ahead_of_reshape(mddev, logical_sector,
-				     conf->reshape_progress)) {
-			previous = 1;
-		} else {
-			if (ahead_of_reshape(mddev, logical_sector,
-					     conf->reshape_safe)) {
-				spin_unlock_irq(&conf->device_lock);
-				ret = STRIPE_SCHEDULE_AND_RETRY;
-				goto out;
-			}
 		}
-		spin_unlock_irq(&conf->device_lock);
+		if (loc == LOC_AHEAD_OF_RESHAPE)
+			previous = 1;
 	}
 
 	new_sector = raid5_compute_sector(conf, logical_sector, previous,
@@ -6078,8 +6097,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 		ctx.do_flush = bi->bi_opf & REQ_PREFLUSH;
 	}
 
-	if (!md_write_start(mddev, bi))
+	md_write_start(mddev, bi);
-		return false;
 	/*
 	 * If array is degraded, better not do chunk aligned read because
 	 * later we might have to read it again in order to reconstruct
@@ -6113,8 +6131,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 	/* Bail out if conflicts with reshape and REQ_NOWAIT is set */
 	if ((bi->bi_opf & REQ_NOWAIT) &&
 	    (conf->reshape_progress != MaxSector) &&
-	    !ahead_of_reshape(mddev, logical_sector, conf->reshape_progress) &&
+	    get_reshape_loc(mddev, conf, logical_sector) == LOC_INSIDE_RESHAPE) {
-	    ahead_of_reshape(mddev, logical_sector, conf->reshape_safe)) {
 		bio_wouldblock_error(bi);
 		if (rw == WRITE)
 			md_write_end(mddev);
@@ -6255,7 +6272,9 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 	safepos = conf->reshape_safe;
 	sector_div(safepos, data_disks);
 	if (mddev->reshape_backwards) {
-		BUG_ON(writepos < reshape_sectors);
+		if (WARN_ON(writepos < reshape_sectors))
+			return MaxSector;
+
 		writepos -= reshape_sectors;
 		readpos += reshape_sectors;
 		safepos += reshape_sectors;
@@ -6273,14 +6292,18 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 	 * to set 'stripe_addr' which is where we will write to.
 	 */
 	if (mddev->reshape_backwards) {
-		BUG_ON(conf->reshape_progress == 0);
+		if (WARN_ON(conf->reshape_progress == 0))
+			return MaxSector;
+
 		stripe_addr = writepos;
-		BUG_ON((mddev->dev_sectors &
+		if (WARN_ON((mddev->dev_sectors &
-			~((sector_t)reshape_sectors - 1))
+		    ~((sector_t)reshape_sectors - 1)) -
-		       - reshape_sectors - stripe_addr
+		    reshape_sectors - stripe_addr != sector_nr))
-		       != sector_nr);
+			return MaxSector;
 	} else {
-		BUG_ON(writepos != sector_nr + reshape_sectors);
+		if (WARN_ON(writepos != sector_nr + reshape_sectors))
+			return MaxSector;
+
 		stripe_addr = sector_nr;
 	}
 
@@ -6458,11 +6481,10 @@ ret:
 }
 
 static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_nr,
-					  int *skipped)
+					  sector_t max_sector, int *skipped)
 {
 	struct r5conf *conf = mddev->private;
 	struct stripe_head *sh;
-	sector_t max_sector = mddev->dev_sectors;
 	sector_t sync_blocks;
 	int still_degraded = 0;
 	int i;
@@ -7082,12 +7104,14 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
 		err = -ENODEV;
 	else if (new != conf->skip_copy) {
 		struct request_queue *q = mddev->gendisk->queue;
+		struct queue_limits lim = queue_limits_start_update(q);
 
 		conf->skip_copy = new;
 		if (new)
-			blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
+			lim.features |= BLK_FEAT_STABLE_WRITES;
 		else
-			blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);
+			lim.features &= ~BLK_FEAT_STABLE_WRITES;
+		err = queue_limits_commit_update(q, &lim);
 	}
 	mddev_unlock_and_resume(mddev);
 	return err ?: len;
@@ -7562,11 +7586,11 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 		if (test_bit(Replacement, &rdev->flags)) {
 			if (disk->replacement)
 				goto abort;
-			RCU_INIT_POINTER(disk->replacement, rdev);
+			disk->replacement = rdev;
 		} else {
 			if (disk->rdev)
 				goto abort;
-			RCU_INIT_POINTER(disk->rdev, rdev);
+			disk->rdev = rdev;
 		}
 
 		if (test_bit(In_sync, &rdev->flags)) {
@@ -7702,13 +7726,13 @@ static int raid5_set_limits(struct mddev *mddev)
 	 */
 	stripe = roundup_pow_of_two(data_disks * (mddev->chunk_sectors << 9));
 
-	blk_set_stacking_limits(&lim);
+	md_init_stacking_limits(&lim);
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * (conf->raid_disks - conf->max_degraded);
-	lim.raid_partial_stripes_expensive = 1;
+	lim.features |= BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE;
 	lim.discard_granularity = stripe;
 	lim.max_write_zeroes_sectors = 0;
-	mddev_stack_rdev_limits(mddev, &lim);
+	mddev_stack_rdev_limits(mddev, &lim, 0);
 	rdev_for_each(rdev, mddev)
 		queue_limits_stack_bdev(&lim, rdev->bdev, rdev->new_data_offset,
 				mddev->gendisk->disk_name);
@@ -8048,7 +8072,7 @@ static void raid5_status(struct seq_file *seq, struct mddev *mddev)
 	seq_printf (seq, "]");
 }
 
-static void print_raid5_conf (struct r5conf *conf)
+static void print_raid5_conf(struct r5conf *conf)
 {
 	struct md_rdev *rdev;
 	int i;
@@ -8062,15 +8086,13 @@ static void print_raid5_conf (struct r5conf *conf)
 	       conf->raid_disks,
 	       conf->raid_disks - conf->mddev->degraded);
 
-	rcu_read_lock();
 	for (i = 0; i < conf->raid_disks; i++) {
-		rdev = rcu_dereference(conf->disks[i].rdev);
+		rdev = conf->disks[i].rdev;
 		if (rdev)
 			pr_debug(" disk %d, o:%d, dev:%pg\n",
 			       i, !test_bit(Faulty, &rdev->flags),
 			       rdev->bdev);
 	}
-	rcu_read_unlock();
 }
 
 static int raid5_spare_active(struct mddev *mddev)

drivers/mmc/core/block.c

@@ -2466,8 +2466,7 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
 	struct mmc_blk_data *md;
 	int devidx, ret;
 	char cap_str[10];
-	bool cache_enabled = false;
+	unsigned int features = 0;
-	bool fua_enabled = false;
 
 	devidx = ida_alloc_max(&mmc_blk_ida, max_devices - 1, GFP_KERNEL);
 	if (devidx < 0) {
@@ -2499,7 +2498,24 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
 	 */
 	md->read_only = mmc_blk_readonly(card);
 
-	md->disk = mmc_init_queue(&md->queue, card);
+	if (mmc_host_cmd23(card->host)) {
+		if ((mmc_card_mmc(card) &&
+		     card->csd.mmca_vsn >= CSD_SPEC_VER_3) ||
+		    (mmc_card_sd(card) &&
+		     card->scr.cmds & SD_SCR_CMD23_SUPPORT))
+			md->flags |= MMC_BLK_CMD23;
+	}
+
+	if (md->flags & MMC_BLK_CMD23 &&
+	    ((card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN) ||
+	     card->ext_csd.rel_sectors)) {
+		md->flags |= MMC_BLK_REL_WR;
+		features |= (BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA);
+	} else if (mmc_cache_enabled(card->host)) {
+		features |= BLK_FEAT_WRITE_CACHE;
+	}
+
+	md->disk = mmc_init_queue(&md->queue, card, features);
 	if (IS_ERR(md->disk)) {
 		ret = PTR_ERR(md->disk);
 		goto err_kfree;
@@ -2539,26 +2555,6 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
 
 	set_capacity(md->disk, size);
 
-	if (mmc_host_cmd23(card->host)) {
-		if ((mmc_card_mmc(card) &&
-		     card->csd.mmca_vsn >= CSD_SPEC_VER_3) ||
-		    (mmc_card_sd(card) &&
-		     card->scr.cmds & SD_SCR_CMD23_SUPPORT))
-			md->flags |= MMC_BLK_CMD23;
-	}
-
-	if (md->flags & MMC_BLK_CMD23 &&
-	    ((card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN) ||
-	     card->ext_csd.rel_sectors)) {
-		md->flags |= MMC_BLK_REL_WR;
-		fua_enabled = true;
-		cache_enabled = true;
-	}
-	if (mmc_cache_enabled(card->host))
-		cache_enabled  = true;
-
-	blk_queue_write_cache(md->queue.queue, cache_enabled, fua_enabled);
-
 	string_get_size((u64)size, 512, STRING_UNITS_2,
 			cap_str, sizeof(cap_str));
 	pr_info("%s: %s %s %s%s\n",

drivers/mmc/core/queue.c

@@ -344,10 +344,12 @@ static const struct blk_mq_ops mmc_mq_ops = {
 };
 
 static struct gendisk *mmc_alloc_disk(struct mmc_queue *mq,
-		struct mmc_card *card)
+		struct mmc_card *card, unsigned int features)
 {
 	struct mmc_host *host = card->host;
-	struct queue_limits lim = { };
+	struct queue_limits lim = {
+		.features		= features,
+	};
 	struct gendisk *disk;
 
 	if (mmc_can_erase(card))
@@ -376,18 +378,16 @@ static struct gendisk *mmc_alloc_disk(struct mmc_queue *mq,
 		lim.max_segments = host->max_segs;
 	}
 
+	if (mmc_host_is_spi(host) && host->use_spi_crc)
+		lim.features |= BLK_FEAT_STABLE_WRITES;
+
 	disk = blk_mq_alloc_disk(&mq->tag_set, &lim, mq);
 	if (IS_ERR(disk))
 		return disk;
 	mq->queue = disk->queue;
 
-	if (mmc_host_is_spi(host) && host->use_spi_crc)
-		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, mq->queue);
 	blk_queue_rq_timeout(mq->queue, 60 * HZ);
 
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, mq->queue);
-	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, mq->queue);
-
 	dma_set_max_seg_size(mmc_dev(host), queue_max_segment_size(mq->queue));
 
 	INIT_WORK(&mq->recovery_work, mmc_mq_recovery_handler);
@@ -413,10 +413,12 @@ static inline bool mmc_merge_capable(struct mmc_host *host)
  * mmc_init_queue - initialise a queue structure.
  * @mq: mmc queue
  * @card: mmc card to attach this queue
+ * @features: block layer features (BLK_FEAT_*)
  *
  * Initialise a MMC card request queue.
  */
-struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card)
+struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
+		unsigned int features)
 {
 	struct mmc_host *host = card->host;
 	struct gendisk *disk;
@@ -460,7 +462,7 @@ struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card)
 		return ERR_PTR(ret);
 		
 
-	disk = mmc_alloc_disk(mq, card);
+	disk = mmc_alloc_disk(mq, card, features);
 	if (IS_ERR(disk))
 		blk_mq_free_tag_set(&mq->tag_set);
 	return disk;

drivers/mmc/core/queue.h

@@ -94,7 +94,8 @@ struct mmc_queue {
 	struct work_struct	complete_work;
 };
 
-struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card);
+struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
+		unsigned int features);
 extern void mmc_cleanup_queue(struct mmc_queue *);
 extern void mmc_queue_suspend(struct mmc_queue *);
 extern void mmc_queue_resume(struct mmc_queue *);

drivers/mtd/mtd_blkdevs.c

@@ -336,6 +336,8 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 	lim.logical_block_size = tr->blksize;
 	if (tr->discard)
 		lim.max_hw_discard_sectors = UINT_MAX;
+	if (tr->flush)
+		lim.features |= BLK_FEAT_WRITE_CACHE;
 
 	/* Create gendisk */
 	gd = blk_mq_alloc_disk(new->tag_set, &lim, new);
@@ -372,13 +374,6 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 	/* Create the request queue */
 	spin_lock_init(&new->queue_lock);
 	INIT_LIST_HEAD(&new->rq_list);
-
-	if (tr->flush)
-		blk_queue_write_cache(new->rq, true, false);
-
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, new->rq);
-	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, new->rq);
-
 	gd->queue = new->rq;
 
 	if (new->readonly)

drivers/nvdimm/btt.c

@@ -1501,9 +1501,15 @@ static int btt_blk_init(struct btt *btt)
 		.logical_block_size	= btt->sector_size,
 		.max_hw_sectors		= UINT_MAX,
 		.max_integrity_segments	= 1,
+		.features		= BLK_FEAT_SYNCHRONOUS,
 	};
 	int rc;
 
+	if (btt_meta_size(btt) && IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) {
+		lim.integrity.tuple_size = btt_meta_size(btt);
+		lim.integrity.tag_size = btt_meta_size(btt);
+	}
+
 	btt->btt_disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
 	if (IS_ERR(btt->btt_disk))
 		return PTR_ERR(btt->btt_disk);
@@ -1513,17 +1519,6 @@ static int btt_blk_init(struct btt *btt)
 	btt->btt_disk->fops = &btt_fops;
 	btt->btt_disk->private_data = btt;
 
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, btt->btt_disk->queue);
-	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, btt->btt_disk->queue);
-
-	if (btt_meta_size(btt) && IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) {
-		struct blk_integrity bi = {
-			.tuple_size	= btt_meta_size(btt),
-			.tag_size	= btt_meta_size(btt),
-		};
-		blk_integrity_register(btt->btt_disk, &bi);
-	}
-
 	set_capacity(btt->btt_disk, btt->nlba * btt->sector_size >> 9);
 	rc = device_add_disk(&btt->nd_btt->dev, btt->btt_disk, NULL);
 	if (rc)

drivers/nvdimm/pmem.c

@@ -455,6 +455,8 @@ static int pmem_attach_disk(struct device *dev,
 		.logical_block_size	= pmem_sector_size(ndns),
 		.physical_block_size	= PAGE_SIZE,
 		.max_hw_sectors		= UINT_MAX,
+		.features		= BLK_FEAT_WRITE_CACHE |
+					  BLK_FEAT_SYNCHRONOUS,
 	};
 	int nid = dev_to_node(dev), fua;
 	struct resource *res = &nsio->res;
@@ -463,7 +465,6 @@ static int pmem_attach_disk(struct device *dev,
 	struct dax_device *dax_dev;
 	struct nd_pfn_sb *pfn_sb;
 	struct pmem_device *pmem;
-	struct request_queue *q;
 	struct gendisk *disk;
 	void *addr;
 	int rc;
@@ -495,6 +496,10 @@ static int pmem_attach_disk(struct device *dev,
 		dev_warn(dev, "unable to guarantee persistence of writes\n");
 		fua = 0;
 	}
+	if (fua)
+		lim.features |= BLK_FEAT_FUA;
+	if (is_nd_pfn(dev))
+		lim.features |= BLK_FEAT_DAX;
 
 	if (!devm_request_mem_region(dev, res->start, resource_size(res),
 				dev_name(&ndns->dev))) {
@@ -505,7 +510,6 @@ static int pmem_attach_disk(struct device *dev,
 	disk = blk_alloc_disk(&lim, nid);
 	if (IS_ERR(disk))
 		return PTR_ERR(disk);
-	q = disk->queue;
 
 	pmem->disk = disk;
 	pmem->pgmap.owner = pmem;
@@ -543,12 +547,6 @@ static int pmem_attach_disk(struct device *dev,
 	}
 	pmem->virt_addr = addr;
 
-	blk_queue_write_cache(q, true, fua);
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, q);
-	if (pmem->pfn_flags & PFN_MAP)
-		blk_queue_flag_set(QUEUE_FLAG_DAX, q);
-
 	disk->fops		= &pmem_fops;
 	disk->private_data	= pmem;
 	nvdimm_namespace_disk_name(ndns, disk->disk_name);

drivers/nvme/host/Kconfig

@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config NVME_CORE
 	tristate
-	select BLK_DEV_INTEGRITY_T10 if BLK_DEV_INTEGRITY
 
 config BLK_DEV_NVME
 	tristate "NVM Express block device"