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
  ...

Author: torvalds

.mailmap

@@ -690,6 +690,7 @@ Vivien Didelot <[email protected]> <[email protected]>
 Vlad Dogaru <[email protected]> <[email protected]>
 Vladimir Davydov <[email protected]> <[email protected]>
 Vladimir Davydov <[email protected]> <[email protected]>
+Weiwen Hu <[email protected]> <[email protected]>
 WeiXiong Liao <[email protected]> <[email protected]>
 Wen Gong <[email protected]> <[email protected]>
 Wesley Cheng <[email protected]> <[email protected]>

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 <[email protected]>
+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 <[email protected]>
+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 <[email protected]>
+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 <[email protected]>
+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
-disk, each block device has been extended with a block integrity
-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.
+Block devices can set up the integrity information in the integrity
+sub-struture of the queue_limits structure.
 
 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 <[email protected]>

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
---------------------------------------------------------------
+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.
 
-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.
+For devices with volatile write caches the driver needs to tell the block layer
+that it supports flushing caches by setting the
 
+   BLK_FEAT_WRITE_CACHE
 
-Implementation details for request_fn based block drivers
----------------------------------------------------------
+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
 
-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
-driver needs to tell the block layer that it supports flushing caches by
-doing::
+   BLK_FEAT_FUA
+
+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.
 
-	blk_queue_write_cache(sdkp->disk->queue, true, false);
+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.
 
-and handle empty REQ_OP_FLUSH requests in its prep_fn/request_fn.  Note that
-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::
+Implementation details for blk-mq drivers
+-----------------------------------------
 
-	blk_queue_write_cache(sdkp->disk->queue, true, true);
+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.
 
-and the driver must handle write requests that have the REQ_FUA bit set
-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.
+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 <[email protected]>
+R:	Boqun Feng <[email protected]>
+L:	[email protected]
+L:	[email protected]
+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 <[email protected]>
 L:	[email protected]

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_handler(void)
+static void ubd_end_request(struct io_thread_req *io_req)
 {
-	int n;
-	int count;
-
-	while(1){
-		n = bulk_req_safe_read(
-			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);
-		}
+	if (io_req->error == BLK_STS_NOTSUPP) {
+		if (req_op(io_req->req) == REQ_OP_DISCARD)
+			blk_queue_disable_discard(io_req->req->q);
+		else if (req_op(io_req->req) == REQ_OP_WRITE_ZEROES)
+			blk_queue_disable_write_zeroes(io_req->req->q);
 	}
+	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_T10)	+= t10-pi.o
+obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
 obj-$(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