Merge 8ede842f66 ("Merge tag 'rust-6.9' of https://github.com/Rust-for-Linux/linux") into android-mainline

Steps on the way to v6.9-rc1

Signed-off-by: Lee Jones <joneslee@google.com>
Change-Id: I220ed9c77e97302f5a1ce5e521b05c50ecec3f5e

Documentation/RCU/checklist.rst

@@ -68,7 +68,8 @@ over a rather long period of time, but improvements are always welcome!
 	rcu_read_lock_sched(), or by the appropriate update-side lock.
 	Explicit disabling of preemption (preempt_disable(), for example)
 	can serve as rcu_read_lock_sched(), but is less readable and
-	prevents lockdep from detecting locking issues.
+	prevents lockdep from detecting locking issues.  Acquiring a
+	spinlock also enters an RCU read-side critical section.
 
 	Please note that you *cannot* rely on code known to be built
 	only in non-preemptible kernels.  Such code can and will break,
@@ -382,16 +383,17 @@ over a rather long period of time, but improvements are always welcome!
 	must use whatever locking or other synchronization is required
 	to safely access and/or modify that data structure.
 
-	Do not assume that RCU callbacks will be executed on the same
-	CPU that executed the corresponding call_rcu() or call_srcu().
-	For example, if a given CPU goes offline while having an RCU
-	callback pending, then that RCU callback will execute on some
-	surviving CPU.	(If this was not the case, a self-spawning RCU
-	callback would prevent the victim CPU from ever going offline.)
-	Furthermore, CPUs designated by rcu_nocbs= might well *always*
-	have their RCU callbacks executed on some other CPUs, in fact,
-	for some  real-time workloads, this is the whole point of using
-	the rcu_nocbs= kernel boot parameter.
+	Do not assume that RCU callbacks will be executed on
+	the same CPU that executed the corresponding call_rcu(),
+	call_srcu(), call_rcu_tasks(), call_rcu_tasks_rude(), or
+	call_rcu_tasks_trace().  For example, if a given CPU goes offline
+	while having an RCU callback pending, then that RCU callback
+	will execute on some surviving CPU.  (If this was not the case,
+	a self-spawning RCU callback would prevent the victim CPU from
+	ever going offline.)  Furthermore, CPUs designated by rcu_nocbs=
+	might well *always* have their RCU callbacks executed on some
+	other CPUs, in fact, for some  real-time workloads, this is the
+	whole point of using the rcu_nocbs= kernel boot parameter.
 
 	In addition, do not assume that callbacks queued in a given order
 	will be invoked in that order, even if they all are queued on the
@@ -444,7 +446,7 @@ over a rather long period of time, but improvements are always welcome!
 	real-time workloads than is synchronize_rcu_expedited().
 
 	It is also permissible to sleep in RCU Tasks Trace read-side
-	critical, which are delimited by rcu_read_lock_trace() and
+	critical section, which are delimited by rcu_read_lock_trace() and
 	rcu_read_unlock_trace().  However, this is a specialized flavor
 	of RCU, and you should not use it without first checking with
 	its current users.  In most cases, you should instead use SRCU.
@@ -490,6 +492,12 @@ over a rather long period of time, but improvements are always welcome!
 		since the last time that you passed that same object to
 		call_rcu() (or friends).
 
+	CONFIG_RCU_STRICT_GRACE_PERIOD:
+		combine with KASAN to check for pointers leaked out
+		of RCU read-side critical sections.  This Kconfig
+		option is tough on both performance and scalability,
+		and so is limited to four-CPU systems.
+
 	__rcu sparse checks:
 		tag the pointer to the RCU-protected data structure
 		with __rcu, and sparse will warn you if you access that

Documentation/RCU/rcu_dereference.rst

@@ -408,7 +408,10 @@ member of the rcu_dereference() to use in various situations:
 	RCU flavors, an RCU read-side critical section is entered
 	using rcu_read_lock(), anything that disables bottom halves,
 	anything that disables interrupts, or anything that disables
-	preemption.
+	preemption.  Please note that spinlock critical sections
+	are also implied RCU read-side critical sections, even when
+	they are preemptible, as they are in kernels built with
+	CONFIG_PREEMPT_RT=y.
 
 2.	If the access might be within an RCU read-side critical section
 	on the one hand, or protected by (say) my_lock on the other,

Documentation/RCU/whatisRCU.rst

@@ -172,14 +172,25 @@ rcu_read_lock()
 	critical section.  Reference counts may be used in conjunction
 	with RCU to maintain longer-term references to data structures.
 
+	Note that anything that disables bottom halves, preemption,
+	or interrupts also enters an RCU read-side critical section.
+	Acquiring a spinlock also enters an RCU read-side critical
+	sections, even for spinlocks that do not disable preemption,
+	as is the case in kernels built with CONFIG_PREEMPT_RT=y.
+	Sleeplocks do *not* enter RCU read-side critical sections.
+
 rcu_read_unlock()
 ^^^^^^^^^^^^^^^^^
 	void rcu_read_unlock(void);
 
 	This temporal primitives is used by a reader to inform the
 	reclaimer that the reader is exiting an RCU read-side critical
-	section.  Note that RCU read-side critical sections may be nested
-	and/or overlapping.
+	section.  Anything that enables bottom halves, preemption,
+	or interrupts also exits an RCU read-side critical section.
+	Releasing a spinlock also exits an RCU read-side critical section.
+
+	Note that RCU read-side critical sections may be nested and/or
+	overlapping.
 
 synchronize_rcu()
 ^^^^^^^^^^^^^^^^^
@@ -952,8 +963,8 @@ unfortunately any spinlock in a ``SLAB_TYPESAFE_BY_RCU`` object must be
 initialized after each and every call to kmem_cache_alloc(), which renders
 reference-free spinlock acquisition completely unsafe.  Therefore, when
 using ``SLAB_TYPESAFE_BY_RCU``, make proper use of a reference counter.
-(Those willing to use a kmem_cache constructor may also use locking,
-including cache-friendly sequence locking.)
+(Those willing to initialize their locks in a kmem_cache constructor
+may also use locking, including cache-friendly sequence locking.)
 
 With traditional reference counting -- such as that implemented by the
 kref library in Linux -- there is typically code that runs when the last

Documentation/admin-guide/kernel-parameters.rst

@@ -108,6 +108,7 @@ is applicable::
 	CMA	Contiguous Memory Area support is enabled.
 	DRM	Direct Rendering Management support is enabled.
 	DYNAMIC_DEBUG Build in debug messages and enable them at runtime
+	EARLY	Parameter processed too early to be embedded in initrd.
 	EDD	BIOS Enhanced Disk Drive Services (EDD) is enabled
 	EFI	EFI Partitioning (GPT) is enabled
 	EVM	Extended Verification Module

Documentation/process/changes.rst

@@ -31,7 +31,7 @@ you probably needn't concern yourself with pcmciautils.
 ====================== ===============  ========================================
 GNU C                  5.1              gcc --version
 Clang/LLVM (optional)  11.0.0           clang --version
-Rust (optional)        1.74.1           rustc --version
+Rust (optional)        1.76.0           rustc --version
 bindgen (optional)     0.65.1           bindgen --version
 GNU make               3.82             make --version
 bash                   4.2              bash --version

Documentation/rust/general-information.rst

@@ -77,27 +77,3 @@ configuration:
 	#[cfg(CONFIG_X="y")]   // Enabled as a built-in (`y`)
 	#[cfg(CONFIG_X="m")]   // Enabled as a module   (`m`)
 	#[cfg(not(CONFIG_X))]  // Disabled
-
-
-Testing
--------
-
-There are the tests that come from the examples in the Rust documentation
-and get transformed into KUnit tests. These can be run via KUnit. For example
-via ``kunit_tool`` (``kunit.py``) on the command line::
-
-	./tools/testing/kunit/kunit.py run --make_options LLVM=1 --arch x86_64 --kconfig_add CONFIG_RUST=y
-
-Alternatively, KUnit can run them as kernel built-in at boot. Refer to
-Documentation/dev-tools/kunit/index.rst for the general KUnit documentation
-and Documentation/dev-tools/kunit/architecture.rst for the details of kernel
-built-in vs. command line testing.
-
-Additionally, there are the ``#[test]`` tests. These can be run using
-the ``rusttest`` Make target::
-
-	make LLVM=1 rusttest
-
-This requires the kernel ``.config`` and downloads external repositories.
-It runs the ``#[test]`` tests on the host (currently) and thus is fairly
-limited in what these tests can test.

Documentation/rust/index.rst

@@ -40,6 +40,7 @@ configurations.
     general-information
     coding-guidelines
     arch-support
+    testing
 
 .. only::  subproject and html
 

Documentation/rust/testing.rst

@@ -0,0 +1,135 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Testing
+=======
+
+This document contains useful information how to test the Rust code in the
+kernel.
+
+There are two sorts of tests:
+
+- The KUnit tests.
+- The ``#[test]`` tests.
+
+The KUnit tests
+---------------
+
+These are the tests that come from the examples in the Rust documentation. They
+get transformed into KUnit tests.
+
+Usage
+*****
+
+These tests can be run via KUnit. For example via ``kunit_tool`` (``kunit.py``)
+on the command line::
+
+	./tools/testing/kunit/kunit.py run --make_options LLVM=1 --arch x86_64 --kconfig_add CONFIG_RUST=y
+
+Alternatively, KUnit can run them as kernel built-in at boot. Refer to
+Documentation/dev-tools/kunit/index.rst for the general KUnit documentation
+and Documentation/dev-tools/kunit/architecture.rst for the details of kernel
+built-in vs. command line testing.
+
+To use these KUnit doctests, the following must be enabled::
+
+	CONFIG_KUNIT
+	   Kernel hacking -> Kernel Testing and Coverage -> KUnit - Enable support for unit tests
+	CONFIG_RUST_KERNEL_DOCTESTS
+	   Kernel hacking -> Rust hacking -> Doctests for the `kernel` crate
+
+in the kernel config system.
+
+KUnit tests are documentation tests
+***********************************
+
+These documentation tests are typically examples of usage of any item (e.g.
+function, struct, module...).
+
+They are very convenient because they are just written alongside the
+documentation. For instance:
+
+.. code-block:: rust
+
+	/// Sums two numbers.
+	///
+	/// ```
+	/// assert_eq!(mymod::f(10, 20), 30);
+	/// ```
+	pub fn f(a: i32, b: i32) -> i32 {
+	    a + b
+	}
+
+In userspace, the tests are collected and run via ``rustdoc``. Using the tool
+as-is would be useful already, since it allows verifying that examples compile
+(thus enforcing they are kept in sync with the code they document) and as well
+as running those that do not depend on in-kernel APIs.
+
+For the kernel, however, these tests get transformed into KUnit test suites.
+This means that doctests get compiled as Rust kernel objects, allowing them to
+run against a built kernel.
+
+A benefit of this KUnit integration is that Rust doctests get to reuse existing
+testing facilities. For instance, the kernel log would look like::
+
+	KTAP version 1
+	1..1
+	    KTAP version 1
+	    # Subtest: rust_doctests_kernel
+	    1..59
+	    # rust_doctest_kernel_build_assert_rs_0.location: rust/kernel/build_assert.rs:13
+	    ok 1 rust_doctest_kernel_build_assert_rs_0
+	    # rust_doctest_kernel_build_assert_rs_1.location: rust/kernel/build_assert.rs:56
+	    ok 2 rust_doctest_kernel_build_assert_rs_1
+	    # rust_doctest_kernel_init_rs_0.location: rust/kernel/init.rs:122
+	    ok 3 rust_doctest_kernel_init_rs_0
+	    ...
+	    # rust_doctest_kernel_types_rs_2.location: rust/kernel/types.rs:150
+	    ok 59 rust_doctest_kernel_types_rs_2
+	# rust_doctests_kernel: pass:59 fail:0 skip:0 total:59
+	# Totals: pass:59 fail:0 skip:0 total:59
+	ok 1 rust_doctests_kernel
+
+Tests using the `? <https://doc.rust-lang.org/reference/expressions/operator-expr.html#the-question-mark-operator>`_
+operator are also supported as usual, e.g.:
+
+.. code-block:: rust
+
+	/// ```
+	/// # use kernel::{spawn_work_item, workqueue};
+	/// spawn_work_item!(workqueue::system(), || pr_info!("x"))?;
+	/// # Ok::<(), Error>(())
+	/// ```
+
+The tests are also compiled with Clippy under ``CLIPPY=1``, just like normal
+code, thus also benefitting from extra linting.
+
+In order for developers to easily see which line of doctest code caused a
+failure, a KTAP diagnostic line is printed to the log. This contains the
+location (file and line) of the original test (i.e. instead of the location in
+the generated Rust file)::
+
+	# rust_doctest_kernel_types_rs_2.location: rust/kernel/types.rs:150
+
+Rust tests appear to assert using the usual ``assert!`` and ``assert_eq!``
+macros from the Rust standard library (``core``). We provide a custom version
+that forwards the call to KUnit instead. Importantly, these macros do not
+require passing context, unlike those for KUnit testing (i.e.
+``struct kunit *``). This makes them easier to use, and readers of the
+documentation do not need to care about which testing framework is used. In
+addition, it may allow us to test third-party code more easily in the future.
+
+A current limitation is that KUnit does not support assertions in other tasks.
+Thus, we presently simply print an error to the kernel log if an assertion
+actually failed. Additionally, doctests are not run for nonpublic functions.
+
+The ``#[test]`` tests
+---------------------
+
+Additionally, there are the ``#[test]`` tests. These can be run using the
+``rusttest`` Make target::
+
+	make LLVM=1 rusttest
+
+This requires the kernel ``.config`` and downloads external repositories. It
+runs the ``#[test]`` tests on the host (currently) and thus is fairly limited in
+what these tests can test.

Makefile

@@ -1264,7 +1264,7 @@ prepare0: archprepare
 # All the preparing..
 prepare: prepare0
 ifdef CONFIG_RUST
-	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh
+	+$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh
 	$(Q)$(MAKE) $(build)=rust
 endif
 
@@ -1750,7 +1750,7 @@ $(DOC_TARGETS):
 # "Is Rust available?" target
 PHONY += rustavailable
 rustavailable:
-	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh && echo "Rust is available!"
+	+$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh && echo "Rust is available!"
 
 # Documentation target
 #

arch/m68k/emu/nfblock.c

@@ -96,6 +96,9 @@ static const struct block_device_operations nfhd_ops = {
 
 static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
 {
+	struct queue_limits lim = {
+		.logical_block_size	= bsize,
+	};
 	struct nfhd_device *dev;
 	int dev_id = id - NFHD_DEV_OFFSET;
 	int err = -ENOMEM;
@@ -117,9 +120,11 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
 	dev->bsize = bsize;
 	dev->bshift = ffs(bsize) - 10;
 
-	dev->disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!dev->disk)
+	dev->disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(dev->disk)) {
+		err = PTR_ERR(dev->disk);
 		goto free_dev;
+	}
 
 	dev->disk->major = major_num;
 	dev->disk->first_minor = dev_id * 16;
@@ -128,7 +133,6 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
 	dev->disk->private_data = dev;
 	sprintf(dev->disk->disk_name, "nfhd%u", dev_id);
 	set_capacity(dev->disk, (sector_t)blocks * (bsize / 512));
-	blk_queue_logical_block_size(dev->disk->queue, bsize);
 	err = add_disk(dev->disk);
 	if (err)
 		goto out_cleanup_disk;

arch/um/drivers/ubd_kern.c

@@ -108,8 +108,6 @@ static inline void ubd_set_bit(__u64 bit, unsigned char *data)
 static DEFINE_MUTEX(ubd_lock);
 static DEFINE_MUTEX(ubd_mutex); /* replaces BKL, might not be needed */
 
-static int ubd_open(struct gendisk *disk, blk_mode_t mode);
-static void ubd_release(struct gendisk *disk);
 static int ubd_ioctl(struct block_device *bdev, blk_mode_t mode,
 		     unsigned int cmd, unsigned long arg);
 static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo);
@@ -118,16 +116,11 @@ static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo);
 
 static const struct block_device_operations ubd_blops = {
         .owner		= THIS_MODULE,
-        .open		= ubd_open,
-        .release	= ubd_release,
         .ioctl		= ubd_ioctl,
         .compat_ioctl	= blkdev_compat_ptr_ioctl,
 	.getgeo		= ubd_getgeo,
 };
 
-/* Protected by ubd_lock */
-static struct gendisk *ubd_gendisk[MAX_DEV];
-
 #ifdef CONFIG_BLK_DEV_UBD_SYNC
 #define OPEN_FLAGS ((struct openflags) { .r = 1, .w = 1, .s = 1, .c = 0, \
 					 .cl = 1 })
@@ -155,7 +148,6 @@ struct ubd {
 	 * backing or the cow file. */
 	char *file;
 	char *serial;
-	int count;
 	int fd;
 	__u64 size;
 	struct openflags boot_openflags;
@@ -165,7 +157,7 @@ struct ubd {
 	unsigned no_trim:1;
 	struct cow cow;
 	struct platform_device pdev;
-	struct request_queue *queue;
+	struct gendisk *disk;
 	struct blk_mq_tag_set tag_set;
 	spinlock_t lock;
 };
@@ -181,7 +173,6 @@ struct ubd {
 #define DEFAULT_UBD { \
 	.file = 		NULL, \
 	.serial =		NULL, \
-	.count =		0, \
 	.fd =			-1, \
 	.size =			-1, \
 	.boot_openflags =	OPEN_FLAGS, \
@@ -774,8 +765,6 @@ static int ubd_open_dev(struct ubd *ubd_dev)
 	ubd_dev->fd = fd;
 
 	if(ubd_dev->cow.file != NULL){
-		blk_queue_max_hw_sectors(ubd_dev->queue, 8 * sizeof(long));
-
 		err = -ENOMEM;
 		ubd_dev->cow.bitmap = vmalloc(ubd_dev->cow.bitmap_len);
 		if(ubd_dev->cow.bitmap == NULL){
@@ -797,11 +786,6 @@ static int ubd_open_dev(struct ubd *ubd_dev)
 		if(err < 0) goto error;
 		ubd_dev->cow.fd = err;
 	}
-	if (ubd_dev->no_trim == 0) {
-		blk_queue_max_discard_sectors(ubd_dev->queue, UBD_MAX_REQUEST);
-		blk_queue_max_write_zeroes_sectors(ubd_dev->queue, UBD_MAX_REQUEST);
-	}
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, ubd_dev->queue);
 	return 0;
  error:
 	os_close_file(ubd_dev->fd);
@@ -851,27 +835,6 @@ static const struct attribute_group *ubd_attr_groups[] = {
 	NULL,
 };
 
-static int ubd_disk_register(int major, u64 size, int unit,
-			     struct gendisk *disk)
-{
-	disk->major = major;
-	disk->first_minor = unit << UBD_SHIFT;
-	disk->minors = 1 << UBD_SHIFT;
-	disk->fops = &ubd_blops;
-	set_capacity(disk, size / 512);
-	sprintf(disk->disk_name, "ubd%c", 'a' + unit);
-
-	ubd_devs[unit].pdev.id   = unit;
-	ubd_devs[unit].pdev.name = DRIVER_NAME;
-	ubd_devs[unit].pdev.dev.release = ubd_device_release;
-	dev_set_drvdata(&ubd_devs[unit].pdev.dev, &ubd_devs[unit]);
-	platform_device_register(&ubd_devs[unit].pdev);
-
-	disk->private_data = &ubd_devs[unit];
-	disk->queue = ubd_devs[unit].queue;
-	return device_add_disk(&ubd_devs[unit].pdev.dev, disk, ubd_attr_groups);
-}
-
 #define ROUND_BLOCK(n) ((n + (SECTOR_SIZE - 1)) & (-SECTOR_SIZE))
 
 static const struct blk_mq_ops ubd_mq_ops = {
@@ -881,18 +844,36 @@ static const struct blk_mq_ops ubd_mq_ops = {
 static int ubd_add(int n, char **error_out)
 {
 	struct ubd *ubd_dev = &ubd_devs[n];
+	struct queue_limits lim = {
+		.max_segments		= MAX_SG,
+		.seg_boundary_mask	= PAGE_SIZE - 1,
+	};
 	struct gendisk *disk;
 	int err = 0;
 
 	if(ubd_dev->file == NULL)
 		goto out;
 
+	if (ubd_dev->cow.file)
+		lim.max_hw_sectors = 8 * sizeof(long);
+	if (!ubd_dev->no_trim) {
+		lim.max_hw_discard_sectors = UBD_MAX_REQUEST;
+		lim.max_write_zeroes_sectors = UBD_MAX_REQUEST;
+	}
+
 	err = ubd_file_size(ubd_dev, &ubd_dev->size);
 	if(err < 0){
 		*error_out = "Couldn't determine size of device's file";
 		goto out;
 	}
 
+	err = ubd_open_dev(ubd_dev);
+	if (err) {
+		pr_err("ubd%c: Can't open \"%s\": errno = %d\n",
+			'a' + n, ubd_dev->file, -err);
+		goto out;
+	}
+
 	ubd_dev->size = ROUND_BLOCK(ubd_dev->size);
 
 	ubd_dev->tag_set.ops = &ubd_mq_ops;
@@ -904,29 +885,43 @@ static int ubd_add(int n, char **error_out)
 
 	err = blk_mq_alloc_tag_set(&ubd_dev->tag_set);
 	if (err)
-		goto out;
+		goto out_close;
 
-	disk = blk_mq_alloc_disk(&ubd_dev->tag_set, ubd_dev);
+	disk = blk_mq_alloc_disk(&ubd_dev->tag_set, &lim, ubd_dev);
 	if (IS_ERR(disk)) {
 		err = PTR_ERR(disk);
 		goto out_cleanup_tags;
 	}
-	ubd_dev->queue = disk->queue;
 
-	blk_queue_write_cache(ubd_dev->queue, true, false);
-	blk_queue_max_segments(ubd_dev->queue, MAX_SG);
-	blk_queue_segment_boundary(ubd_dev->queue, PAGE_SIZE - 1);
-	err = ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, disk);
+	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;
+	disk->fops = &ubd_blops;
+	set_capacity(disk, ubd_dev->size / 512);
+	sprintf(disk->disk_name, "ubd%c", 'a' + n);
+	disk->private_data = ubd_dev;
+	set_disk_ro(disk, !ubd_dev->openflags.w);
+
+	ubd_dev->pdev.id = n;
+	ubd_dev->pdev.name = DRIVER_NAME;
+	ubd_dev->pdev.dev.release = ubd_device_release;
+	dev_set_drvdata(&ubd_dev->pdev.dev, ubd_dev);
+	platform_device_register(&ubd_dev->pdev);
+
+	err = device_add_disk(&ubd_dev->pdev.dev, disk, ubd_attr_groups);
 	if (err)
 		goto out_cleanup_disk;
 
-	ubd_gendisk[n] = disk;
 	return 0;
 
 out_cleanup_disk:
 	put_disk(disk);
 out_cleanup_tags:
 	blk_mq_free_tag_set(&ubd_dev->tag_set);
+out_close:
+	ubd_close_dev(ubd_dev);
 out:
 	return err;
 }
@@ -1012,7 +1007,6 @@ static int ubd_id(char **str, int *start_out, int *end_out)
 
 static int ubd_remove(int n, char **error_out)
 {
-	struct gendisk *disk = ubd_gendisk[n];
 	struct ubd *ubd_dev;
 	int err = -ENODEV;
 
@@ -1023,15 +1017,15 @@ static int ubd_remove(int n, char **error_out)
 	if(ubd_dev->file == NULL)
 		goto out;
 
-	/* you cannot remove a open disk */
-	err = -EBUSY;
-	if(ubd_dev->count > 0)
-		goto out;
+	if (ubd_dev->disk) {
+		/* you cannot remove a open disk */
+		err = -EBUSY;
+		if (disk_openers(ubd_dev->disk))
+			goto out;
 
-	ubd_gendisk[n] = NULL;
-	if(disk != NULL){
-		del_gendisk(disk);
-		put_disk(disk);
+		del_gendisk(ubd_dev->disk);
+		ubd_close_dev(ubd_dev);
+		put_disk(ubd_dev->disk);
 	}
 
 	err = 0;
@@ -1153,37 +1147,6 @@ static int __init ubd_driver_init(void){
 
 device_initcall(ubd_driver_init);
 
-static int ubd_open(struct gendisk *disk, blk_mode_t mode)
-{
-	struct ubd *ubd_dev = disk->private_data;
-	int err = 0;
-
-	mutex_lock(&ubd_mutex);
-	if(ubd_dev->count == 0){
-		err = ubd_open_dev(ubd_dev);
-		if(err){
-			printk(KERN_ERR "%s: Can't open \"%s\": errno = %d\n",
-			       disk->disk_name, ubd_dev->file, -err);
-			goto out;
-		}
-	}
-	ubd_dev->count++;
-	set_disk_ro(disk, !ubd_dev->openflags.w);
-out:
-	mutex_unlock(&ubd_mutex);
-	return err;
-}
-
-static void ubd_release(struct gendisk *disk)
-{
-	struct ubd *ubd_dev = disk->private_data;
-
-	mutex_lock(&ubd_mutex);
-	if(--ubd_dev->count == 0)
-		ubd_close_dev(ubd_dev);
-	mutex_unlock(&ubd_mutex);
-}
-
 static void cowify_bitmap(__u64 io_offset, int length, unsigned long *cow_mask,
 			  __u64 *cow_offset, unsigned long *bitmap,
 			  __u64 bitmap_offset, unsigned long *bitmap_words,

arch/xtensa/platforms/iss/simdisk.c

@@ -264,16 +264,18 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
 		struct proc_dir_entry *procdir)
 {
 	char tmp[2] = { '0' + which, 0 };
-	int err = -ENOMEM;
+	int err;
 
 	dev->fd = -1;
 	dev->filename = NULL;
 	spin_lock_init(&dev->lock);
 	dev->users = 0;
 
-	dev->gd = blk_alloc_disk(NUMA_NO_NODE);
-	if (!dev->gd)
+	dev->gd = blk_alloc_disk(NULL, NUMA_NO_NODE);
+	if (IS_ERR(dev->gd)) {
+		err = PTR_ERR(dev->gd);
 		goto out;
+	}
 	dev->gd->major = simdisk_major;
 	dev->gd->first_minor = which;
 	dev->gd->minors = SIMDISK_MINORS;

block/bdev.c

@@ -383,7 +383,7 @@ void __init bdev_cache_init(void)
 
 	bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
 			0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
-				SLAB_MEM_SPREAD|SLAB_ACCOUNT|SLAB_PANIC),
+				SLAB_ACCOUNT|SLAB_PANIC),
 			init_once);
 	err = register_filesystem(&bd_type);
 	if (err)

block/bfq-cgroup.c

@@ -127,7 +127,7 @@ static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
 	if (!bfqg_stats_waiting(stats))
 		return;
 
-	now = ktime_get_ns();
+	now = blk_time_get_ns();
 	if (now > stats->start_group_wait_time)
 		bfq_stat_add(&stats->group_wait_time,
 			      now - stats->start_group_wait_time);
@@ -144,7 +144,7 @@ static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
 		return;
 	if (bfqg == curr_bfqg)
 		return;
-	stats->start_group_wait_time = ktime_get_ns();
+	stats->start_group_wait_time = blk_time_get_ns();
 	bfqg_stats_mark_waiting(stats);
 }
 
@@ -156,7 +156,7 @@ static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
 	if (!bfqg_stats_empty(stats))
 		return;
 
-	now = ktime_get_ns();
+	now = blk_time_get_ns();
 	if (now > stats->start_empty_time)
 		bfq_stat_add(&stats->empty_time,
 			      now - stats->start_empty_time);
@@ -183,7 +183,7 @@ void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg)
 	if (bfqg_stats_empty(stats))
 		return;
 
-	stats->start_empty_time = ktime_get_ns();
+	stats->start_empty_time = blk_time_get_ns();
 	bfqg_stats_mark_empty(stats);
 }
 
@@ -192,7 +192,7 @@ void bfqg_stats_update_idle_time(struct bfq_group *bfqg)
 	struct bfqg_stats *stats = &bfqg->stats;
 
 	if (bfqg_stats_idling(stats)) {
-		u64 now = ktime_get_ns();
+		u64 now = blk_time_get_ns();
 
 		if (now > stats->start_idle_time)
 			bfq_stat_add(&stats->idle_time,
@@ -205,7 +205,7 @@ void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg)
 {
 	struct bfqg_stats *stats = &bfqg->stats;
 
-	stats->start_idle_time = ktime_get_ns();
+	stats->start_idle_time = blk_time_get_ns();
 	bfqg_stats_mark_idling(stats);
 }
 
@@ -242,7 +242,7 @@ void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
 				  u64 io_start_time_ns, blk_opf_t opf)
 {
 	struct bfqg_stats *stats = &bfqg->stats;
-	u64 now = ktime_get_ns();
+	u64 now = blk_time_get_ns();
 
 	if (now > io_start_time_ns)
 		blkg_rwstat_add(&stats->service_time, opf,

block/bfq-iosched.c

@@ -1005,7 +1005,7 @@ static struct request *bfq_check_fifo(struct bfq_queue *bfqq,
 
 	rq = rq_entry_fifo(bfqq->fifo.next);
 
-	if (rq == last || ktime_get_ns() < rq->fifo_time)
+	if (rq == last || blk_time_get_ns() < rq->fifo_time)
 		return NULL;
 
 	bfq_log_bfqq(bfqq->bfqd, bfqq, "check_fifo: returned %p", rq);
@@ -1829,7 +1829,7 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
 		 * bfq_bfqq_update_budg_for_activation for
 		 * details on the usage of the next variable.
 		 */
-		arrived_in_time =  ktime_get_ns() <=
+		arrived_in_time =  blk_time_get_ns() <=
 			bfqq->ttime.last_end_request +
 			bfqd->bfq_slice_idle * 3;
 	unsigned int act_idx = bfq_actuator_index(bfqd, rq->bio);
@@ -2208,7 +2208,7 @@ static void bfq_add_request(struct request *rq)
 	struct request *next_rq, *prev;
 	unsigned int old_wr_coeff = bfqq->wr_coeff;
 	bool interactive = false;
-	u64 now_ns = ktime_get_ns();
+	u64 now_ns = blk_time_get_ns();
 
 	bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
 	bfqq->queued[rq_is_sync(rq)]++;
@@ -2262,7 +2262,7 @@ static void bfq_add_request(struct request *rq)
 		      bfqd->rqs_injected && bfqd->tot_rq_in_driver > 0)) &&
 		    time_is_before_eq_jiffies(bfqq->decrease_time_jif +
 					      msecs_to_jiffies(10))) {
-			bfqd->last_empty_occupied_ns = ktime_get_ns();
+			bfqd->last_empty_occupied_ns = blk_time_get_ns();
 			/*
 			 * Start the state machine for measuring the
 			 * total service time of rq: setting
@@ -3294,7 +3294,7 @@ static void bfq_set_budget_timeout(struct bfq_data *bfqd,
 	else
 		timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight;
 
-	bfqd->last_budget_start = ktime_get();
+	bfqd->last_budget_start = blk_time_get();
 
 	bfqq->budget_timeout = jiffies +
 		bfqd->bfq_timeout * timeout_coeff;
@@ -3394,7 +3394,7 @@ static void bfq_arm_slice_timer(struct bfq_data *bfqd)
 	else if (bfqq->wr_coeff > 1)
 		sl = max_t(u32, sl, 20ULL * NSEC_PER_MSEC);
 
-	bfqd->last_idling_start = ktime_get();
+	bfqd->last_idling_start = blk_time_get();
 	bfqd->last_idling_start_jiffies = jiffies;
 
 	hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl),
@@ -3433,7 +3433,7 @@ static void bfq_reset_rate_computation(struct bfq_data *bfqd,
 				       struct request *rq)
 {
 	if (rq != NULL) { /* new rq dispatch now, reset accordingly */
-		bfqd->last_dispatch = bfqd->first_dispatch = ktime_get_ns();
+		bfqd->last_dispatch = bfqd->first_dispatch = blk_time_get_ns();
 		bfqd->peak_rate_samples = 1;
 		bfqd->sequential_samples = 0;
 		bfqd->tot_sectors_dispatched = bfqd->last_rq_max_size =
@@ -3590,7 +3590,7 @@ reset_computation:
  */
 static void bfq_update_peak_rate(struct bfq_data *bfqd, struct request *rq)
 {
-	u64 now_ns = ktime_get_ns();
+	u64 now_ns = blk_time_get_ns();
 
 	if (bfqd->peak_rate_samples == 0) { /* first dispatch */
 		bfq_log(bfqd, "update_peak_rate: goto reset, samples %d",
@@ -4162,7 +4162,7 @@ static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	if (compensate)
 		delta_ktime = bfqd->last_idling_start;
 	else
-		delta_ktime = ktime_get();
+		delta_ktime = blk_time_get();
 	delta_ktime = ktime_sub(delta_ktime, bfqd->last_budget_start);
 	delta_usecs = ktime_to_us(delta_ktime);
 
@@ -5591,7 +5591,7 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 			  struct bfq_io_cq *bic, pid_t pid, int is_sync,
 			  unsigned int act_idx)
 {
-	u64 now_ns = ktime_get_ns();
+	u64 now_ns = blk_time_get_ns();
 
 	bfqq->actuator_idx = act_idx;
 	RB_CLEAR_NODE(&bfqq->entity.rb_node);
@@ -5903,7 +5903,7 @@ static void bfq_update_io_thinktime(struct bfq_data *bfqd,
 	 */
 	if (bfqq->dispatched || bfq_bfqq_busy(bfqq))
 		return;
-	elapsed = ktime_get_ns() - bfqq->ttime.last_end_request;
+	elapsed = blk_time_get_ns() - bfqq->ttime.last_end_request;
 	elapsed = min_t(u64, elapsed, 2ULL * bfqd->bfq_slice_idle);
 
 	ttime->ttime_samples = (7*ttime->ttime_samples + 256) / 8;
@@ -6194,7 +6194,7 @@ static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 	bfq_add_request(rq);
 	idle_timer_disabled = waiting && !bfq_bfqq_wait_request(bfqq);
 
-	rq->fifo_time = ktime_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
+	rq->fifo_time = blk_time_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
 	list_add_tail(&rq->queuelist, &bfqq->fifo);
 
 	bfq_rq_enqueued(bfqd, bfqq, rq);
@@ -6370,7 +6370,7 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 		bfq_weights_tree_remove(bfqq);
 	}
 
-	now_ns = ktime_get_ns();
+	now_ns = blk_time_get_ns();
 
 	bfqq->ttime.last_end_request = now_ns;
 
@@ -6585,7 +6585,7 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 static void bfq_update_inject_limit(struct bfq_data *bfqd,
 				    struct bfq_queue *bfqq)
 {
-	u64 tot_time_ns = ktime_get_ns() - bfqd->last_empty_occupied_ns;
+	u64 tot_time_ns = blk_time_get_ns() - bfqd->last_empty_occupied_ns;
 	unsigned int old_limit = bfqq->inject_limit;
 
 	if (bfqq->last_serv_time_ns > 0 && bfqd->rqs_injected) {

block/bio-integrity.c

@@ -395,6 +395,7 @@ static blk_status_t bio_integrity_process(struct bio *bio,
 	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);

block/bio.c

@@ -16,7 +16,6 @@
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
 #include <linux/highmem.h>
-#include <linux/sched/sysctl.h>
 #include <linux/blk-crypto.h>
 #include <linux/xarray.h>
 
@@ -766,29 +765,31 @@ static inline void bio_put_percpu_cache(struct bio *bio)
 	struct bio_alloc_cache *cache;
 
 	cache = per_cpu_ptr(bio->bi_pool->cache, get_cpu());
-	if (READ_ONCE(cache->nr_irq) + cache->nr > ALLOC_CACHE_MAX) {
-		put_cpu();
-		bio_free(bio);
-		return;
-	}
+	if (READ_ONCE(cache->nr_irq) + cache->nr > ALLOC_CACHE_MAX)
+		goto out_free;
 
-	bio_uninit(bio);
-
-	if ((bio->bi_opf & REQ_POLLED) && !WARN_ON_ONCE(in_interrupt())) {
+	if (in_task()) {
+		bio_uninit(bio);
 		bio->bi_next = cache->free_list;
+		/* Not necessary but helps not to iopoll already freed bios */
 		bio->bi_bdev = NULL;
 		cache->free_list = bio;
 		cache->nr++;
-	} else {
-		unsigned long flags;
+	} else if (in_hardirq()) {
+		lockdep_assert_irqs_disabled();
 
-		local_irq_save(flags);
+		bio_uninit(bio);
 		bio->bi_next = cache->free_list_irq;
 		cache->free_list_irq = bio;
 		cache->nr_irq++;
-		local_irq_restore(flags);
+	} else {
+		goto out_free;
 	}
 	put_cpu();
+	return;
+out_free:
+	put_cpu();
+	bio_free(bio);
 }
 
 /**
@@ -1157,7 +1158,7 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty)
 
 	bio_for_each_folio_all(fi, bio) {
 		struct page *page;
-		size_t done = 0;
+		size_t nr_pages;
 
 		if (mark_dirty) {
 			folio_lock(fi.folio);
@@ -1165,10 +1166,11 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty)
 			folio_unlock(fi.folio);
 		}
 		page = folio_page(fi.folio, fi.offset / PAGE_SIZE);
+		nr_pages = (fi.offset + fi.length - 1) / PAGE_SIZE -
+			   fi.offset / PAGE_SIZE + 1;
 		do {
 			bio_release_page(bio, page++);
-			done += PAGE_SIZE;
-		} while (done < fi.length);
+		} while (--nr_pages != 0);
 	}
 }
 EXPORT_SYMBOL_GPL(__bio_release_pages);
@@ -1374,21 +1376,12 @@ int submit_bio_wait(struct bio *bio)
 {
 	DECLARE_COMPLETION_ONSTACK_MAP(done,
 			bio->bi_bdev->bd_disk->lockdep_map);
-	unsigned long hang_check;
 
 	bio->bi_private = &done;
 	bio->bi_end_io = submit_bio_wait_endio;
 	bio->bi_opf |= REQ_SYNC;
 	submit_bio(bio);
-
-	/* Prevent hang_check timer from firing at us during very long I/O */
-	hang_check = sysctl_hung_task_timeout_secs;
-	if (hang_check)
-		while (!wait_for_completion_io_timeout(&done,
-					hang_check * (HZ/2)))
-			;
-	else
-		wait_for_completion_io(&done);
+	blk_wait_io(&done);
 
 	return blk_status_to_errno(bio->bi_status);
 }

block/blk-cgroup.c

@@ -1846,7 +1846,7 @@ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
 {
 	unsigned long pflags;
 	bool clamp;
-	u64 now = ktime_to_ns(ktime_get());
+	u64 now = blk_time_get_ns();
 	u64 exp;
 	u64 delay_nsec = 0;
 	int tok;

block/blk-cgroup.h

@@ -19,6 +19,7 @@
 #include <linux/kthread.h>
 #include <linux/blk-mq.h>
 #include <linux/llist.h>
+#include "blk.h"
 
 struct blkcg_gq;
 struct blkg_policy_data;

block/blk-core.c

@@ -394,24 +394,34 @@ static void blk_timeout_work(struct work_struct *work)
 {
 }
 
-struct request_queue *blk_alloc_queue(int node_id)
+struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id)
 {
 	struct request_queue *q;
+	int error;
 
 	q = kmem_cache_alloc_node(blk_requestq_cachep, GFP_KERNEL | __GFP_ZERO,
 				  node_id);
 	if (!q)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	q->last_merge = NULL;
 
 	q->id = ida_alloc(&blk_queue_ida, GFP_KERNEL);
-	if (q->id < 0)
+	if (q->id < 0) {
+		error = q->id;
 		goto fail_q;
+	}
 
 	q->stats = blk_alloc_queue_stats();
-	if (!q->stats)
+	if (!q->stats) {
+		error = -ENOMEM;
 		goto fail_id;
+	}
+
+	error = blk_set_default_limits(lim);
+	if (error)
+		goto fail_stats;
+	q->limits = *lim;
 
 	q->node = node_id;
 
@@ -425,6 +435,7 @@ struct request_queue *blk_alloc_queue(int node_id)
 	mutex_init(&q->debugfs_mutex);
 	mutex_init(&q->sysfs_lock);
 	mutex_init(&q->sysfs_dir_lock);
+	mutex_init(&q->limits_lock);
 	mutex_init(&q->rq_qos_mutex);
 	spin_lock_init(&q->queue_lock);
 
@@ -435,12 +446,12 @@ struct request_queue *blk_alloc_queue(int node_id)
 	 * Init percpu_ref in atomic mode so that it's faster to shutdown.
 	 * See blk_register_queue() for details.
 	 */
-	if (percpu_ref_init(&q->q_usage_counter,
+	error = percpu_ref_init(&q->q_usage_counter,
 				blk_queue_usage_counter_release,
-				PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
+				PERCPU_REF_INIT_ATOMIC, GFP_KERNEL);
+	if (error)
 		goto fail_stats;
 
-	blk_set_default_limits(&q->limits);
 	q->nr_requests = BLKDEV_DEFAULT_RQ;
 
 	return q;
@@ -451,7 +462,7 @@ fail_id:
 	ida_free(&blk_queue_ida, q->id);
 fail_q:
 	kmem_cache_free(blk_requestq_cachep, q);
-	return NULL;
+	return ERR_PTR(error);
 }
 
 /**
@@ -1083,6 +1094,7 @@ void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios)
 	if (tsk->plug)
 		return;
 
+	plug->cur_ktime = 0;
 	plug->mq_list = NULL;
 	plug->cached_rq = NULL;
 	plug->nr_ios = min_t(unsigned short, nr_ios, BLK_MAX_REQUEST_COUNT);
@@ -1182,6 +1194,8 @@ void __blk_flush_plug(struct blk_plug *plug, bool from_schedule)
 	 */
 	if (unlikely(!rq_list_empty(plug->cached_rq)))
 		blk_mq_free_plug_rqs(plug);
+
+	current->flags &= ~PF_BLOCK_TS;
 }
 
 /**
@@ -1229,8 +1243,7 @@ int __init blk_dev_init(void)
 	if (!kblockd_workqueue)
 		panic("Failed to create kblockd\n");
 
-	blk_requestq_cachep = kmem_cache_create("request_queue",
-			sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
+	blk_requestq_cachep = KMEM_CACHE(request_queue, SLAB_PANIC);
 
 	blk_debugfs_root = debugfs_create_dir("block", NULL);
 

block/blk-flush.c

@@ -143,7 +143,7 @@ static void blk_account_io_flush(struct request *rq)
 	part_stat_lock();
 	part_stat_inc(part, ios[STAT_FLUSH]);
 	part_stat_add(part, nsecs[STAT_FLUSH],
-		      ktime_get_ns() - rq->start_time_ns);
+		      blk_time_get_ns() - rq->start_time_ns);
 	part_stat_unlock();
 }
 

block/blk-integrity.c

@@ -370,6 +370,7 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template
 	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);
 

block/blk-iocost.c

@@ -829,7 +829,7 @@ static int ioc_autop_idx(struct ioc *ioc, struct gendisk *disk)
 
 	/* step up/down based on the vrate */
 	vrate_pct = div64_u64(ioc->vtime_base_rate * 100, VTIME_PER_USEC);
-	now_ns = ktime_get_ns();
+	now_ns = blk_time_get_ns();
 
 	if (p->too_fast_vrate_pct && p->too_fast_vrate_pct <= vrate_pct) {
 		if (!ioc->autop_too_fast_at)
@@ -1044,7 +1044,7 @@ static void ioc_now(struct ioc *ioc, struct ioc_now *now)
 	unsigned seq;
 	u64 vrate;
 
-	now->now_ns = ktime_get();
+	now->now_ns = blk_time_get_ns();
 	now->now = ktime_to_us(now->now_ns);
 	vrate = atomic64_read(&ioc->vtime_rate);
 
@@ -2817,7 +2817,7 @@ static void ioc_rqos_done(struct rq_qos *rqos, struct request *rq)
 		return;
 	}
 
-	on_q_ns = ktime_get_ns() - rq->alloc_time_ns;
+	on_q_ns = blk_time_get_ns() - rq->alloc_time_ns;
 	rq_wait_ns = rq->start_time_ns - rq->alloc_time_ns;
 	size_nsec = div64_u64(calc_size_vtime_cost(rq, ioc), VTIME_PER_NSEC);
 
@@ -2900,7 +2900,7 @@ static int blk_iocost_init(struct gendisk *disk)
 	ioc->vtime_base_rate = VTIME_PER_USEC;
 	atomic64_set(&ioc->vtime_rate, VTIME_PER_USEC);
 	seqcount_spinlock_init(&ioc->period_seqcount, &ioc->lock);
-	ioc->period_at = ktime_to_us(ktime_get());
+	ioc->period_at = ktime_to_us(blk_time_get());
 	atomic64_set(&ioc->cur_period, 0);
 	atomic_set(&ioc->hweight_gen, 0);
 

block/blk-iolatency.c

@@ -609,7 +609,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio)
 	if (!iolat->blkiolat->enabled)
 		return;
 
-	now = ktime_to_ns(ktime_get());
+	now = blk_time_get_ns();
 	while (blkg && blkg->parent) {
 		iolat = blkg_to_lat(blkg);
 		if (!iolat) {
@@ -661,7 +661,7 @@ static void blkiolatency_timer_fn(struct timer_list *t)
 	struct blk_iolatency *blkiolat = from_timer(blkiolat, t, timer);
 	struct blkcg_gq *blkg;
 	struct cgroup_subsys_state *pos_css;
-	u64 now = ktime_to_ns(ktime_get());
+	u64 now = blk_time_get_ns();
 
 	rcu_read_lock();
 	blkg_for_each_descendant_pre(blkg, pos_css,
@@ -985,7 +985,7 @@ static void iolatency_pd_init(struct blkg_policy_data *pd)
 	struct blkcg_gq *blkg = lat_to_blkg(iolat);
 	struct rq_qos *rqos = iolat_rq_qos(blkg->q);
 	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
-	u64 now = ktime_to_ns(ktime_get());
+	u64 now = blk_time_get_ns();
 	int cpu;
 
 	if (blk_queue_nonrot(blkg->q))

block/blk-lib.c

@@ -35,6 +35,26 @@ static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector)
 	return round_down(UINT_MAX, discard_granularity) >> SECTOR_SHIFT;
 }
 
+static void await_bio_endio(struct bio *bio)
+{
+	complete(bio->bi_private);
+	bio_put(bio);
+}
+
+/*
+ * await_bio_chain - ends @bio and waits for every chained bio to complete
+ */
+static void await_bio_chain(struct bio *bio)
+{
+	DECLARE_COMPLETION_ONSTACK_MAP(done,
+			bio->bi_bdev->bd_disk->lockdep_map);
+
+	bio->bi_private = &done;
+	bio->bi_end_io = await_bio_endio;
+	bio_endio(bio);
+	blk_wait_io(&done);
+}
+
 int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop)
 {
@@ -77,6 +97,10 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		 * is disabled.
 		 */
 		cond_resched();
+		if (fatal_signal_pending(current)) {
+			await_bio_chain(bio);
+			return -EINTR;
+		}
 	}
 
 	*biop = bio;
@@ -120,32 +144,33 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
 		struct bio **biop, unsigned flags)
 {
 	struct bio *bio = *biop;
-	unsigned int max_write_zeroes_sectors;
+	unsigned int max_sectors;
 
 	if (bdev_read_only(bdev))
 		return -EPERM;
 
-	/* Ensure that max_write_zeroes_sectors doesn't overflow bi_size */
-	max_write_zeroes_sectors = bdev_write_zeroes_sectors(bdev);
+	/* Ensure that max_sectors doesn't overflow bi_size */
+	max_sectors = bdev_write_zeroes_sectors(bdev);
 
-	if (max_write_zeroes_sectors == 0)
+	if (max_sectors == 0)
 		return -EOPNOTSUPP;
 
 	while (nr_sects) {
+		unsigned int len = min_t(sector_t, nr_sects, max_sectors);
+
 		bio = blk_next_bio(bio, bdev, 0, REQ_OP_WRITE_ZEROES, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		if (flags & BLKDEV_ZERO_NOUNMAP)
 			bio->bi_opf |= REQ_NOUNMAP;
 
-		if (nr_sects > max_write_zeroes_sectors) {
-			bio->bi_iter.bi_size = max_write_zeroes_sectors << 9;
-			nr_sects -= max_write_zeroes_sectors;
-			sector += max_write_zeroes_sectors;
-		} else {
-			bio->bi_iter.bi_size = nr_sects << 9;
-			nr_sects = 0;
-		}
+		bio->bi_iter.bi_size = len << SECTOR_SHIFT;
+		nr_sects -= len;
+		sector += len;
 		cond_resched();
+		if (fatal_signal_pending(current)) {
+			await_bio_chain(bio);
+			return -EINTR;
+		}
 	}
 
 	*biop = bio;
@@ -190,6 +215,10 @@ static int __blkdev_issue_zero_pages(struct block_device *bdev,
 				break;
 		}
 		cond_resched();
+		if (fatal_signal_pending(current)) {
+			await_bio_chain(bio);
+			return -EINTR;
+		}
 	}
 
 	*biop = bio;
@@ -280,7 +309,7 @@ retry:
 		bio_put(bio);
 	}
 	blk_finish_plug(&plug);
-	if (ret && try_write_zeroes) {
+	if (ret && ret != -EINTR && try_write_zeroes) {
 		if (!(flags & BLKDEV_ZERO_NOFALLBACK)) {
 			try_write_zeroes = false;
 			goto retry;
@@ -322,7 +351,7 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
 		return -EPERM;
 
 	blk_start_plug(&plug);
-	for (;;) {
+	while (nr_sects) {
 		unsigned int len = min_t(sector_t, nr_sects, max_sectors);
 
 		bio = blk_next_bio(bio, bdev, 0, REQ_OP_SECURE_ERASE, gfp);
@@ -331,12 +360,17 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
 
 		sector += len;
 		nr_sects -= len;
-		if (!nr_sects) {
-			ret = submit_bio_wait(bio);
-			bio_put(bio);
+		cond_resched();
+		if (fatal_signal_pending(current)) {
+			await_bio_chain(bio);
+			ret = -EINTR;
+			bio = NULL;
 			break;
 		}
-		cond_resched();
+	}
+	if (bio) {
+		ret = submit_bio_wait(bio);
+		bio_put(bio);
 	}
 	blk_finish_plug(&plug);
 

block/blk-mq.c

@@ -21,7 +21,6 @@
 #include <linux/llist.h>
 #include <linux/cpu.h>
 #include <linux/cache.h>
-#include <linux/sched/sysctl.h>
 #include <linux/sched/topology.h>
 #include <linux/sched/signal.h>
 #include <linux/delay.h>
@@ -322,7 +321,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	RB_CLEAR_NODE(&rq->rb_node);
 	rq->tag = BLK_MQ_NO_TAG;
 	rq->internal_tag = BLK_MQ_NO_TAG;
-	rq->start_time_ns = ktime_get_ns();
+	rq->start_time_ns = blk_time_get_ns();
 	rq->part = NULL;
 	blk_crypto_rq_set_defaults(rq);
 }
@@ -332,7 +331,7 @@ EXPORT_SYMBOL(blk_rq_init);
 static inline void blk_mq_rq_time_init(struct request *rq, u64 alloc_time_ns)
 {
 	if (blk_mq_need_time_stamp(rq))
-		rq->start_time_ns = ktime_get_ns();
+		rq->start_time_ns = blk_time_get_ns();
 	else
 		rq->start_time_ns = 0;
 
@@ -443,7 +442,7 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 
 	/* alloc_time includes depth and tag waits */
 	if (blk_queue_rq_alloc_time(q))
-		alloc_time_ns = ktime_get_ns();
+		alloc_time_ns = blk_time_get_ns();
 
 	if (data->cmd_flags & REQ_NOWAIT)
 		data->flags |= BLK_MQ_REQ_NOWAIT;
@@ -628,7 +627,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 
 	/* alloc_time includes depth and tag waits */
 	if (blk_queue_rq_alloc_time(q))
-		alloc_time_ns = ktime_get_ns();
+		alloc_time_ns = blk_time_get_ns();
 
 	/*
 	 * If the tag allocator sleeps we could get an allocation for a
@@ -1041,7 +1040,7 @@ static inline void __blk_mq_end_request_acct(struct request *rq, u64 now)
 inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
 {
 	if (blk_mq_need_time_stamp(rq))
-		__blk_mq_end_request_acct(rq, ktime_get_ns());
+		__blk_mq_end_request_acct(rq, blk_time_get_ns());
 
 	blk_mq_finish_request(rq);
 
@@ -1084,7 +1083,7 @@ void blk_mq_end_request_batch(struct io_comp_batch *iob)
 	u64 now = 0;
 
 	if (iob->need_ts)
-		now = ktime_get_ns();
+		now = blk_time_get_ns();
 
 	while ((rq = rq_list_pop(&iob->req_list)) != NULL) {
 		prefetch(rq->bio);
@@ -1167,10 +1166,11 @@ static inline bool blk_mq_complete_need_ipi(struct request *rq)
 	if (force_irqthreads())
 		return false;
 
-	/* same CPU or cache domain?  Complete locally */
+	/* same CPU or cache domain and capacity?  Complete locally */
 	if (cpu == rq->mq_ctx->cpu ||
 	    (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags) &&
-	     cpus_share_cache(cpu, rq->mq_ctx->cpu)))
+	     cpus_share_cache(cpu, rq->mq_ctx->cpu) &&
+	     cpus_equal_capacity(cpu, rq->mq_ctx->cpu)))
 		return false;
 
 	/* don't try to IPI to an offline CPU */
@@ -1254,7 +1254,7 @@ void blk_mq_start_request(struct request *rq)
 
 	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags) &&
 	    !blk_rq_is_passthrough(rq)) {
-		rq->io_start_time_ns = ktime_get_ns();
+		rq->io_start_time_ns = blk_time_get_ns();
 		rq->stats_sectors = blk_rq_sectors(rq);
 		rq->rq_flags |= RQF_STATS;
 		rq_qos_issue(q, rq);
@@ -1409,22 +1409,10 @@ blk_status_t blk_execute_rq(struct request *rq, bool at_head)
 	blk_mq_insert_request(rq, at_head ? BLK_MQ_INSERT_AT_HEAD : 0);
 	blk_mq_run_hw_queue(hctx, false);
 
-	if (blk_rq_is_poll(rq)) {
+	if (blk_rq_is_poll(rq))
 		blk_rq_poll_completion(rq, &wait.done);
-	} else {
-		/*
-		 * Prevent hang_check timer from firing at us during very long
-		 * I/O
-		 */
-		unsigned long hang_check = sysctl_hung_task_timeout_secs;
-
-		if (hang_check)
-			while (!wait_for_completion_io_timeout(&wait.done,
-					hang_check * (HZ/2)))
-				;
-		else
-			wait_for_completion_io(&wait.done);
-	}
+	else
+		blk_wait_io(&wait.done);
 
 	return wait.ret;
 }
@@ -2892,9 +2880,6 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 	};
 	struct request *rq;
 
-	if (blk_mq_attempt_bio_merge(q, bio, nsegs))
-		return NULL;
-
 	rq_qos_throttle(q, bio);
 
 	if (plug) {
@@ -2913,23 +2898,32 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 }
 
 /*
- * Check if we can use the passed on request for submitting the passed in bio,
- * and remove it from the request list if it can be used.
+ * Check if there is a suitable cached request and return it.
  */
-static bool blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
+static struct request *blk_mq_peek_cached_request(struct blk_plug *plug,
+		struct request_queue *q, blk_opf_t opf)
+{
+	enum hctx_type type = blk_mq_get_hctx_type(opf);
+	struct request *rq;
+
+	if (!plug)
+		return NULL;
+	rq = rq_list_peek(&plug->cached_rq);
+	if (!rq || rq->q != q)
+		return NULL;
+	if (type != rq->mq_hctx->type &&
+	    (type != HCTX_TYPE_READ || rq->mq_hctx->type != HCTX_TYPE_DEFAULT))
+		return NULL;
+	if (op_is_flush(rq->cmd_flags) != op_is_flush(opf))
+		return NULL;
+	return rq;
+}
+
+static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
 		struct bio *bio)
 {
-	enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf);
-	enum hctx_type hctx_type = rq->mq_hctx->type;
-
 	WARN_ON_ONCE(rq_list_peek(&plug->cached_rq) != rq);
 
-	if (type != hctx_type &&
-	    !(type == HCTX_TYPE_READ && hctx_type == HCTX_TYPE_DEFAULT))
-		return false;
-	if (op_is_flush(rq->cmd_flags) != op_is_flush(bio->bi_opf))
-		return false;
-
 	/*
 	 * If any qos ->throttle() end up blocking, we will have flushed the
 	 * plug and hence killed the cached_rq list as well. Pop this entry
@@ -2941,7 +2935,6 @@ static bool blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
 	blk_mq_rq_time_init(rq, 0);
 	rq->cmd_flags = bio->bi_opf;
 	INIT_LIST_HEAD(&rq->queuelist);
-	return true;
 }
 
 /**
@@ -2963,50 +2956,43 @@ void blk_mq_submit_bio(struct bio *bio)
 	struct blk_plug *plug = blk_mq_plug(bio);
 	const int is_sync = op_is_sync(bio->bi_opf);
 	struct blk_mq_hw_ctx *hctx;
-	struct request *rq = NULL;
 	unsigned int nr_segs = 1;
+	struct request *rq;
 	blk_status_t ret;
 
 	bio = blk_queue_bounce(bio, q);
 
-	if (plug) {
-		rq = rq_list_peek(&plug->cached_rq);
-		if (rq && rq->q != q)
-			rq = NULL;
-	}
-	if (rq) {
-		if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
-			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
-			if (!bio)
-				return;
-		}
-		if (!bio_integrity_prep(bio))
-			return;
-		if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
-			return;
-		if (blk_mq_use_cached_rq(rq, plug, bio))
-			goto done;
-		percpu_ref_get(&q->q_usage_counter);
-	} else {
+	/*
+	 * If the plug has a cached request for this queue, try use it.
+	 *
+	 * The cached request already holds a q_usage_counter reference and we
+	 * don't have to acquire a new one if we use it.
+	 */
+	rq = blk_mq_peek_cached_request(plug, q, bio->bi_opf);
+	if (!rq) {
 		if (unlikely(bio_queue_enter(bio)))
 			return;
-		if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
-			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
-			if (!bio)
-				goto fail;
-		}
-		if (!bio_integrity_prep(bio))
-			goto fail;
 	}
 
-	rq = blk_mq_get_new_requests(q, plug, bio, nr_segs);
-	if (unlikely(!rq)) {
-fail:
-		blk_queue_exit(q);
-		return;
+	if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
+		bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+		if (!bio)
+			goto queue_exit;
+	}
+	if (!bio_integrity_prep(bio))
+		goto queue_exit;
+
+	if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
+		goto queue_exit;
+
+	if (!rq) {
+		rq = blk_mq_get_new_requests(q, plug, bio, nr_segs);
+		if (unlikely(!rq))
+			goto queue_exit;
+	} else {
+		blk_mq_use_cached_rq(rq, plug, bio);
 	}
 
-done:
 	trace_block_getrq(bio);
 
 	rq_qos_track(q, rq, bio);
@@ -3037,6 +3023,15 @@ done:
 	} else {
 		blk_mq_run_dispatch_ops(q, blk_mq_try_issue_directly(hctx, rq));
 	}
+	return;
+
+queue_exit:
+	/*
+	 * Don't drop the queue reference if we were trying to use a cached
+	 * request and thus didn't acquire one.
+	 */
+	if (!rq)
+		blk_queue_exit(q);
 }
 
 #ifdef CONFIG_BLK_MQ_STACKING
@@ -3098,7 +3093,7 @@ blk_status_t blk_insert_cloned_request(struct request *rq)
 	blk_mq_run_dispatch_ops(q,
 			ret = blk_mq_request_issue_directly(rq, true));
 	if (ret)
-		blk_account_io_done(rq, ktime_get_ns());
+		blk_account_io_done(rq, blk_time_get_ns());
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
@@ -4078,15 +4073,16 @@ void blk_mq_release(struct request_queue *q)
 	blk_mq_sysfs_deinit(q);
 }
 
-static struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
-		void *queuedata)
+struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
+		struct queue_limits *lim, void *queuedata)
 {
+	struct queue_limits default_lim = { };
 	struct request_queue *q;
 	int ret;
 
-	q = blk_alloc_queue(set->numa_node);
-	if (!q)
-		return ERR_PTR(-ENOMEM);
+	q = blk_alloc_queue(lim ? lim : &default_lim, set->numa_node);
+	if (IS_ERR(q))
+		return q;
 	q->queuedata = queuedata;
 	ret = blk_mq_init_allocated_queue(set, q);
 	if (ret) {
@@ -4095,20 +4091,15 @@ static struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
 	}
 	return q;
 }
-
-struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
-{
-	return blk_mq_init_queue_data(set, NULL);
-}
-EXPORT_SYMBOL(blk_mq_init_queue);
+EXPORT_SYMBOL(blk_mq_alloc_queue);
 
 /**
  * blk_mq_destroy_queue - shutdown a request queue
  * @q: request queue to shutdown
  *
- * This shuts down a request queue allocated by blk_mq_init_queue(). All future
+ * This shuts down a request queue allocated by blk_mq_alloc_queue(). All future
  * requests will be failed with -ENODEV. The caller is responsible for dropping
- * the reference from blk_mq_init_queue() by calling blk_put_queue().
+ * the reference from blk_mq_alloc_queue() by calling blk_put_queue().
  *
  * Context: can sleep
  */
@@ -4129,13 +4120,14 @@ void blk_mq_destroy_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_mq_destroy_queue);
 
-struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata,
+struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set,
+		struct queue_limits *lim, void *queuedata,
 		struct lock_class_key *lkclass)
 {
 	struct request_queue *q;
 	struct gendisk *disk;
 
-	q = blk_mq_init_queue_data(set, queuedata);
+	q = blk_mq_alloc_queue(set, lim, queuedata);
 	if (IS_ERR(q))
 		return ERR_CAST(q);
 
@@ -4389,7 +4381,7 @@ static void blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 	if (set->nr_maps == 1)
 		set->map[HCTX_TYPE_DEFAULT].nr_queues = set->nr_hw_queues;
 
-	if (set->ops->map_queues && !is_kdump_kernel()) {
+	if (set->ops->map_queues) {
 		int i;
 
 		/*
@@ -4488,14 +4480,12 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 
 	/*
 	 * If a crashdump is active, then we are potentially in a very
-	 * memory constrained environment. Limit us to 1 queue and
-	 * 64 tags to prevent using too much memory.
+	 * memory constrained environment. Limit us to  64 tags to prevent
+	 * using too much memory.
 	 */
-	if (is_kdump_kernel()) {
-		set->nr_hw_queues = 1;
-		set->nr_maps = 1;
+	if (is_kdump_kernel())
 		set->queue_depth = min(64U, set->queue_depth);
-	}
+
 	/*
 	 * There is no use for more h/w queues than cpus if we just have
 	 * a single map
@@ -4525,7 +4515,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 						  GFP_KERNEL, set->numa_node);
 		if (!set->map[i].mq_map)
 			goto out_free_mq_map;
-		set->map[i].nr_queues = is_kdump_kernel() ? 1 : set->nr_hw_queues;
+		set->map[i].nr_queues = set->nr_hw_queues;
 	}
 
 	blk_mq_update_queue_map(set);

block/blk-settings.c

@@ -25,53 +25,22 @@ void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout)
 }
 EXPORT_SYMBOL_GPL(blk_queue_rq_timeout);
 
-/**
- * blk_set_default_limits - reset limits to default values
- * @lim:  the queue_limits structure to reset
- *
- * Description:
- *   Returns a queue_limit struct to its default state.
- */
-void blk_set_default_limits(struct queue_limits *lim)
-{
-	lim->max_segments = BLK_MAX_SEGMENTS;
-	lim->max_discard_segments = 1;
-	lim->max_integrity_segments = 0;
-	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
-	lim->virt_boundary_mask = 0;
-	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
-	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
-	lim->max_user_sectors = lim->max_dev_sectors = 0;
-	lim->chunk_sectors = 0;
-	lim->max_write_zeroes_sectors = 0;
-	lim->max_zone_append_sectors = 0;
-	lim->max_discard_sectors = 0;
-	lim->max_hw_discard_sectors = 0;
-	lim->max_secure_erase_sectors = 0;
-	lim->discard_granularity = 512;
-	lim->discard_alignment = 0;
-	lim->discard_misaligned = 0;
-	lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
-	lim->bounce = BLK_BOUNCE_NONE;
-	lim->alignment_offset = 0;
-	lim->io_opt = 0;
-	lim->misaligned = 0;
-	lim->zoned = false;
-	lim->zone_write_granularity = 0;
-	lim->dma_alignment = 511;
-}
-
 /**
  * blk_set_stacking_limits - set default limits for stacking devices
  * @lim:  the queue_limits structure to reset
  *
- * Description:
- *   Returns a queue_limit struct to its default state. Should be used
- *   by stacking drivers like DM that have no internal limits.
+ * Prepare queue limits for applying limits from underlying devices using
+ * blk_stack_limits().
  */
 void blk_set_stacking_limits(struct queue_limits *lim)
 {
-	blk_set_default_limits(lim);
+	memset(lim, 0, sizeof(*lim));
+	lim->logical_block_size = SECTOR_SIZE;
+	lim->physical_block_size = SECTOR_SIZE;
+	lim->io_min = SECTOR_SIZE;
+	lim->discard_granularity = SECTOR_SIZE;
+	lim->dma_alignment = SECTOR_SIZE - 1;
+	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 
 	/* Inherit limits from component devices */
 	lim->max_segments = USHRT_MAX;
@@ -82,9 +51,239 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	lim->max_dev_sectors = UINT_MAX;
 	lim->max_write_zeroes_sectors = UINT_MAX;
 	lim->max_zone_append_sectors = UINT_MAX;
+	lim->max_user_discard_sectors = UINT_MAX;
 }
 EXPORT_SYMBOL(blk_set_stacking_limits);
 
+static void blk_apply_bdi_limits(struct backing_dev_info *bdi,
+		struct queue_limits *lim)
+{
+	/*
+	 * For read-ahead of large files to be effective, we need to read ahead
+	 * at least twice the optimal I/O size.
+	 */
+	bdi->ra_pages = max(lim->io_opt * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
+	bdi->io_pages = lim->max_sectors >> PAGE_SECTORS_SHIFT;
+}
+
+static int blk_validate_zoned_limits(struct queue_limits *lim)
+{
+	if (!lim->zoned) {
+		if (WARN_ON_ONCE(lim->max_open_zones) ||
+		    WARN_ON_ONCE(lim->max_active_zones) ||
+		    WARN_ON_ONCE(lim->zone_write_granularity) ||
+		    WARN_ON_ONCE(lim->max_zone_append_sectors))
+			return -EINVAL;
+		return 0;
+	}
+
+	if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED)))
+		return -EINVAL;
+
+	if (lim->zone_write_granularity < lim->logical_block_size)
+		lim->zone_write_granularity = lim->logical_block_size;
+
+	if (lim->max_zone_append_sectors) {
+		/*
+		 * The Zone Append size is limited by the maximum I/O size
+		 * and the zone size given that it can't span zones.
+		 */
+		lim->max_zone_append_sectors =
+			min3(lim->max_hw_sectors,
+			     lim->max_zone_append_sectors,
+			     lim->chunk_sectors);
+	}
+
+	return 0;
+}
+
+/*
+ * Check that the limits in lim are valid, initialize defaults for unset
+ * values, and cap values based on others where needed.
+ */
+static int blk_validate_limits(struct queue_limits *lim)
+{
+	unsigned int max_hw_sectors;
+
+	/*
+	 * Unless otherwise specified, default to 512 byte logical blocks and a
+	 * physical block size equal to the logical block size.
+	 */
+	if (!lim->logical_block_size)
+		lim->logical_block_size = SECTOR_SIZE;
+	if (lim->physical_block_size < lim->logical_block_size)
+		lim->physical_block_size = lim->logical_block_size;
+
+	/*
+	 * The minimum I/O size defaults to the physical block size unless
+	 * explicitly overridden.
+	 */
+	if (lim->io_min < lim->physical_block_size)
+		lim->io_min = lim->physical_block_size;
+
+	/*
+	 * max_hw_sectors has a somewhat weird default for historical reason,
+	 * but driver really should set their own instead of relying on this
+	 * value.
+	 *
+	 * The block layer relies on the fact that every driver can
+	 * handle at lest a page worth of data per I/O, and needs the value
+	 * aligned to the logical block size.
+	 */
+	if (!lim->max_hw_sectors)
+		lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
+	if (WARN_ON_ONCE(lim->max_hw_sectors < PAGE_SECTORS))
+		return -EINVAL;
+	lim->max_hw_sectors = round_down(lim->max_hw_sectors,
+			lim->logical_block_size >> SECTOR_SHIFT);
+
+	/*
+	 * The actual max_sectors value is a complex beast and also takes the
+	 * max_dev_sectors value (set by SCSI ULPs) and a user configurable
+	 * value into account.  The ->max_sectors value is always calculated
+	 * from these, so directly setting it won't have any effect.
+	 */
+	max_hw_sectors = min_not_zero(lim->max_hw_sectors,
+				lim->max_dev_sectors);
+	if (lim->max_user_sectors) {
+		if (lim->max_user_sectors > max_hw_sectors ||
+		    lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE)
+			return -EINVAL;
+		lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors);
+	} else {
+		lim->max_sectors = min(max_hw_sectors, BLK_DEF_MAX_SECTORS_CAP);
+	}
+	lim->max_sectors = round_down(lim->max_sectors,
+			lim->logical_block_size >> SECTOR_SHIFT);
+
+	/*
+	 * Random default for the maximum number of segments.  Driver should not
+	 * rely on this and set their own.
+	 */
+	if (!lim->max_segments)
+		lim->max_segments = BLK_MAX_SEGMENTS;
+
+	lim->max_discard_sectors =
+		min(lim->max_hw_discard_sectors, lim->max_user_discard_sectors);
+
+	if (!lim->max_discard_segments)
+		lim->max_discard_segments = 1;
+
+	if (lim->discard_granularity < lim->physical_block_size)
+		lim->discard_granularity = lim->physical_block_size;
+
+	/*
+	 * By default there is no limit on the segment boundary alignment,
+	 * but if there is one it can't be smaller than the page size as
+	 * that would break all the normal I/O patterns.
+	 */
+	if (!lim->seg_boundary_mask)
+		lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
+	if (WARN_ON_ONCE(lim->seg_boundary_mask < PAGE_SIZE - 1))
+		return -EINVAL;
+
+	/*
+	 * Devices that require a virtual boundary do not support scatter/gather
+	 * I/O natively, but instead require a descriptor list entry for each
+	 * page (which might not be identical to the Linux PAGE_SIZE).  Because
+	 * of that they are not limited by our notion of "segment size".
+	 */
+	if (lim->virt_boundary_mask) {
+		if (WARN_ON_ONCE(lim->max_segment_size &&
+				 lim->max_segment_size != UINT_MAX))
+			return -EINVAL;
+		lim->max_segment_size = UINT_MAX;
+	} else {
+		/*
+		 * The maximum segment size has an odd historic 64k default that
+		 * drivers probably should override.  Just like the I/O size we
+		 * require drivers to at least handle a full page per segment.
+		 */
+		if (!lim->max_segment_size)
+			lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
+		if (WARN_ON_ONCE(lim->max_segment_size < PAGE_SIZE))
+			return -EINVAL;
+	}
+
+	/*
+	 * We require drivers to at least do logical block aligned I/O, but
+	 * historically could not check for that due to the separate calls
+	 * to set the limits.  Once the transition is finished the check
+	 * below should be narrowed down to check the logical block size.
+	 */
+	if (!lim->dma_alignment)
+		lim->dma_alignment = SECTOR_SIZE - 1;
+	if (WARN_ON_ONCE(lim->dma_alignment > PAGE_SIZE))
+		return -EINVAL;
+
+	if (lim->alignment_offset) {
+		lim->alignment_offset &= (lim->physical_block_size - 1);
+		lim->misaligned = 0;
+	}
+
+	return blk_validate_zoned_limits(lim);
+}
+
+/*
+ * Set the default limits for a newly allocated queue.  @lim contains the
+ * initial limits set by the driver, which could be no limit in which case
+ * all fields are cleared to zero.
+ */
+int blk_set_default_limits(struct queue_limits *lim)
+{
+	/*
+	 * Most defaults are set by capping the bounds in blk_validate_limits,
+	 * but max_user_discard_sectors is special and needs an explicit
+	 * initialization to the max value here.
+	 */
+	lim->max_user_discard_sectors = UINT_MAX;
+	return blk_validate_limits(lim);
+}
+
+/**
+ * queue_limits_commit_update - commit an atomic update of queue limits
+ * @q:		queue to update
+ * @lim:	limits to apply
+ *
+ * Apply the limits in @lim that were obtained from queue_limits_start_update()
+ * and updated by the caller to @q.
+ *
+ * Returns 0 if successful, else a negative error code.
+ */
+int queue_limits_commit_update(struct request_queue *q,
+		struct queue_limits *lim)
+	__releases(q->limits_lock)
+{
+	int error = blk_validate_limits(lim);
+
+	if (!error) {
+		q->limits = *lim;
+		if (q->disk)
+			blk_apply_bdi_limits(q->disk->bdi, lim);
+	}
+	mutex_unlock(&q->limits_lock);
+	return error;
+}
+EXPORT_SYMBOL_GPL(queue_limits_commit_update);
+
+/**
+ * queue_limits_set - apply queue limits to queue
+ * @q:		queue to update
+ * @lim:	limits to apply
+ *
+ * Apply the limits in @lim that were freshly initialized to @q.
+ * To update existing limits use queue_limits_start_update() and
+ * queue_limits_commit_update() instead.
+ *
+ * Returns 0 if successful, else a negative error code.
+ */
+int queue_limits_set(struct request_queue *q, struct queue_limits *lim)
+{
+	mutex_lock(&q->limits_lock);
+	return queue_limits_commit_update(q, lim);
+}
+EXPORT_SYMBOL_GPL(queue_limits_set);
+
 /**
  * blk_queue_bounce_limit - set bounce buffer limit for queue
  * @q: the request queue for the device
@@ -177,8 +376,11 @@ EXPORT_SYMBOL(blk_queue_chunk_sectors);
 void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors)
 {
-	q->limits.max_hw_discard_sectors = max_discard_sectors;
-	q->limits.max_discard_sectors = 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);
 
@@ -393,15 +595,7 @@ EXPORT_SYMBOL(blk_queue_alignment_offset);
 
 void disk_update_readahead(struct gendisk *disk)
 {
-	struct request_queue *q = disk->queue;
-
-	/*
-	 * For read-ahead of large files to be effective, we need to read ahead
-	 * at least twice the optimal I/O size.
-	 */
-	disk->bdi->ra_pages =
-		max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
-	disk->bdi->io_pages = queue_max_sectors(q) >> (PAGE_SHIFT - 9);
+	blk_apply_bdi_limits(disk->bdi, &disk->queue->limits);
 }
 EXPORT_SYMBOL_GPL(disk_update_readahead);
 
@@ -689,33 +883,38 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->zone_write_granularity = max(t->zone_write_granularity,
 					b->zone_write_granularity);
 	t->zoned = max(t->zoned, b->zoned);
+	if (!t->zoned) {
+		t->zone_write_granularity = 0;
+		t->max_zone_append_sectors = 0;
+	}
 	return ret;
 }
 EXPORT_SYMBOL(blk_stack_limits);
 
 /**
- * disk_stack_limits - adjust queue limits for stacked drivers
- * @disk:  MD/DM gendisk (top)
+ * queue_limits_stack_bdev - adjust queue_limits for stacked devices
+ * @t:	the stacking driver limits (top device)
  * @bdev:  the underlying block device (bottom)
  * @offset:  offset to beginning of data within component device
+ * @pfx: prefix to use for warnings logged
  *
  * Description:
- *    Merges the limits for a top level gendisk and a bottom level
- *    block_device.
+ *    This function is used by stacking drivers like MD and DM to ensure
+ *    that all component devices have compatible block sizes and
+ *    alignments.  The stacking driver must provide a queue_limits
+ *    struct (top) and then iteratively call the stacking function for
+ *    all component (bottom) devices.  The stacking function will
+ *    attempt to combine the values and ensure proper alignment.
  */
-void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
-		       sector_t offset)
+void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
+		sector_t offset, const char *pfx)
 {
-	struct request_queue *t = disk->queue;
-
-	if (blk_stack_limits(&t->limits, &bdev_get_queue(bdev)->limits,
-			get_start_sect(bdev) + (offset >> 9)) < 0)
+	if (blk_stack_limits(t, &bdev_get_queue(bdev)->limits,
+			get_start_sect(bdev) + offset))
 		pr_notice("%s: Warning: Device %pg is misaligned\n",
-			disk->disk_name, bdev);
-
-	disk_update_readahead(disk);
+			pfx, bdev);
 }
-EXPORT_SYMBOL(disk_stack_limits);
+EXPORT_SYMBOL_GPL(queue_limits_stack_bdev);
 
 /**
  * blk_queue_update_dma_pad - update pad mask

block/blk-stat.c

@@ -27,7 +27,7 @@ void blk_rq_stat_init(struct blk_rq_stat *stat)
 /* src is a per-cpu stat, mean isn't initialized */
 void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
 {
-	if (!src->nr_samples)
+	if (dst->nr_samples + src->nr_samples <= dst->nr_samples)
 		return;
 
 	dst->min = min(dst->min, src->min);

block/blk-sysfs.c

@@ -174,23 +174,29 @@ static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
 static ssize_t queue_discard_max_store(struct request_queue *q,
 				       const char *page, size_t count)
 {
-	unsigned long max_discard;
-	ssize_t ret = queue_var_store(&max_discard, page, count);
+	unsigned long max_discard_bytes;
+	struct queue_limits lim;
+	ssize_t ret;
+	int err;
 
+	ret = queue_var_store(&max_discard_bytes, page, count);
 	if (ret < 0)
 		return ret;
 
-	if (max_discard & (q->limits.discard_granularity - 1))
+	if (max_discard_bytes & (q->limits.discard_granularity - 1))
 		return -EINVAL;
 
-	max_discard >>= 9;
-	if (max_discard > UINT_MAX)
+	if ((max_discard_bytes >> SECTOR_SHIFT) > UINT_MAX)
 		return -EINVAL;
 
-	if (max_discard > q->limits.max_hw_discard_sectors)
-		max_discard = q->limits.max_hw_discard_sectors;
+	blk_mq_freeze_queue(q);
+	lim = queue_limits_start_update(q);
+	lim.max_user_discard_sectors = max_discard_bytes >> SECTOR_SHIFT;
+	err = queue_limits_commit_update(q, &lim);
+	blk_mq_unfreeze_queue(q);
 
-	q->limits.max_discard_sectors = max_discard;
+	if (err)
+		return err;
 	return ret;
 }
 
@@ -226,35 +232,22 @@ static ssize_t queue_zone_append_max_show(struct request_queue *q, char *page)
 static ssize_t
 queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 {
-	unsigned long var;
-	unsigned int max_sectors_kb,
-		max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1,
-			page_kb = 1 << (PAGE_SHIFT - 10);
-	ssize_t ret = queue_var_store(&var, page, count);
+	unsigned long max_sectors_kb;
+	struct queue_limits lim;
+	ssize_t ret;
+	int err;
 
+	ret = queue_var_store(&max_sectors_kb, page, count);
 	if (ret < 0)
 		return ret;
 
-	max_sectors_kb = (unsigned int)var;
-	max_hw_sectors_kb = min_not_zero(max_hw_sectors_kb,
-					 q->limits.max_dev_sectors >> 1);
-	if (max_sectors_kb == 0) {
-		q->limits.max_user_sectors = 0;
-		max_sectors_kb = min(max_hw_sectors_kb,
-				     BLK_DEF_MAX_SECTORS_CAP >> 1);
-	} else {
-		if (max_sectors_kb > max_hw_sectors_kb ||
-		    max_sectors_kb < page_kb)
-			return -EINVAL;
-		q->limits.max_user_sectors = max_sectors_kb << 1;
-	}
-
-	spin_lock_irq(&q->queue_lock);
-	q->limits.max_sectors = max_sectors_kb << 1;
-	if (q->disk)
-		q->disk->bdi->io_pages = max_sectors_kb >> (PAGE_SHIFT - 10);
-	spin_unlock_irq(&q->queue_lock);
-
+	blk_mq_freeze_queue(q);
+	lim = queue_limits_start_update(q);
+	lim.max_user_sectors = max_sectors_kb << 1;
+	err = queue_limits_commit_update(q, &lim);
+	blk_mq_unfreeze_queue(q);
+	if (err)
+		return err;
 	return ret;
 }
 

block/blk-throttle.c

@@ -1098,7 +1098,7 @@ static int throtl_dispatch_tg(struct throtl_grp *tg)
 	while ((bio = throtl_peek_queued(&sq->queued[READ])) &&
 	       tg_may_dispatch(tg, bio, NULL)) {
 
-		tg_dispatch_one_bio(tg, bio_data_dir(bio));
+		tg_dispatch_one_bio(tg, READ);
 		nr_reads++;
 
 		if (nr_reads >= max_nr_reads)
@@ -1108,7 +1108,7 @@ static int throtl_dispatch_tg(struct throtl_grp *tg)
 	while ((bio = throtl_peek_queued(&sq->queued[WRITE])) &&
 	       tg_may_dispatch(tg, bio, NULL)) {
 
-		tg_dispatch_one_bio(tg, bio_data_dir(bio));
+		tg_dispatch_one_bio(tg, WRITE);
 		nr_writes++;
 
 		if (nr_writes >= max_nr_writes)
@@ -1815,7 +1815,7 @@ static bool throtl_tg_is_idle(struct throtl_grp *tg)
 	time = min_t(unsigned long, MAX_IDLE_TIME, 4 * tg->idletime_threshold);
 	ret = tg->latency_target == DFL_LATENCY_TARGET ||
 	      tg->idletime_threshold == DFL_IDLE_THRESHOLD ||
-	      (ktime_get_ns() >> 10) - tg->last_finish_time > time ||
+	      (blk_time_get_ns() >> 10) - tg->last_finish_time > time ||
 	      tg->avg_idletime > tg->idletime_threshold ||
 	      (tg->latency_target && tg->bio_cnt &&
 		tg->bad_bio_cnt * 5 < tg->bio_cnt);
@@ -2060,7 +2060,7 @@ static void blk_throtl_update_idletime(struct throtl_grp *tg)
 	if (last_finish_time == 0)
 		return;
 
-	now = ktime_get_ns() >> 10;
+	now = blk_time_get_ns() >> 10;
 	if (now <= last_finish_time ||
 	    last_finish_time == tg->checked_last_finish_time)
 		return;
@@ -2327,7 +2327,7 @@ void blk_throtl_bio_endio(struct bio *bio)
 	if (!tg->td->limit_valid[LIMIT_LOW])
 		return;
 
-	finish_time_ns = ktime_get_ns();
+	finish_time_ns = blk_time_get_ns();
 	tg->last_finish_time = finish_time_ns >> 10;
 
 	start_time = bio_issue_time(&bio->bi_issue) >> 10;

block/blk-wbt.c

@@ -29,6 +29,7 @@
 #include "blk-wbt.h"
 #include "blk-rq-qos.h"
 #include "elevator.h"
+#include "blk.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/wbt.h>
@@ -274,13 +275,12 @@ static inline bool stat_sample_valid(struct blk_rq_stat *stat)
 
 static u64 rwb_sync_issue_lat(struct rq_wb *rwb)
 {
-	u64 now, issue = READ_ONCE(rwb->sync_issue);
+	u64 issue = READ_ONCE(rwb->sync_issue);
 
 	if (!issue || !rwb->sync_cookie)
 		return 0;
 
-	now = ktime_to_ns(ktime_get());
-	return now - issue;
+	return blk_time_get_ns() - issue;
 }
 
 static inline unsigned int wbt_inflight(struct rq_wb *rwb)

block/blk-zoned.c

@@ -11,7 +11,6 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/rbtree.h>
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
 #include <linux/mm.h>
@@ -177,8 +176,7 @@ static int blk_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx,
 	}
 }
 
-static int blkdev_zone_reset_all_emulated(struct block_device *bdev,
-					  gfp_t gfp_mask)
+static int blkdev_zone_reset_all_emulated(struct block_device *bdev)
 {
 	struct gendisk *disk = bdev->bd_disk;
 	sector_t capacity = bdev_nr_sectors(bdev);
@@ -205,7 +203,7 @@ static int blkdev_zone_reset_all_emulated(struct block_device *bdev,
 		}
 
 		bio = blk_next_bio(bio, bdev, 0, REQ_OP_ZONE_RESET | REQ_SYNC,
-				   gfp_mask);
+				   GFP_KERNEL);
 		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
 
@@ -223,7 +221,7 @@ out_free_need_reset:
 	return ret;
 }
 
-static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask)
+static int blkdev_zone_reset_all(struct block_device *bdev)
 {
 	struct bio bio;
 
@@ -238,7 +236,6 @@ static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask)
  * @sector:	Start sector of the first zone to operate on
  * @nr_sectors:	Number of sectors, should be at least the length of one zone and
  *		must be zone size aligned.
- * @gfp_mask:	Memory allocation flags (for bio_alloc)
  *
  * Description:
  *    Perform the specified operation on the range of zones specified by
@@ -248,7 +245,7 @@ static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask)
  *    or finish request.
  */
 int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
-		     sector_t sector, sector_t nr_sectors, gfp_t gfp_mask)
+		     sector_t sector, sector_t nr_sectors)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 	sector_t zone_sectors = bdev_zone_sectors(bdev);
@@ -285,12 +282,12 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
 	 */
 	if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity) {
 		if (!blk_queue_zone_resetall(q))
-			return blkdev_zone_reset_all_emulated(bdev, gfp_mask);
-		return blkdev_zone_reset_all(bdev, gfp_mask);
+			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_mask);
+		bio = blk_next_bio(bio, bdev, 0, op | REQ_SYNC, GFP_KERNEL);
 		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
 
@@ -419,8 +416,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 		return -ENOTTY;
 	}
 
-	ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors,
-			       GFP_KERNEL);
+	ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors);
 
 fail:
 	if (cmd == BLKRESETZONE)

block/blk.h

@@ -4,6 +4,8 @@
 
 #include <linux/blk-crypto.h>
 #include <linux/memblock.h>	/* for max_pfn/max_low_pfn */
+#include <linux/sched/sysctl.h>
+#include <linux/timekeeping.h>
 #include <xen/xen.h>
 #include "blk-crypto-internal.h"
 
@@ -70,6 +72,18 @@ static inline int bio_queue_enter(struct bio *bio)
 	return __bio_queue_enter(q, bio);
 }
 
+static inline void blk_wait_io(struct completion *done)
+{
+	/* Prevent hang_check timer from firing at us during very long I/O */
+	unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2;
+
+	if (timeout)
+		while (!wait_for_completion_io_timeout(done, timeout))
+			;
+	else
+		wait_for_completion_io(done);
+}
+
 #define BIO_INLINE_VECS 4
 struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
 		gfp_t gfp_mask);
@@ -329,7 +343,7 @@ void blk_rq_set_mixed_merge(struct request *rq);
 bool blk_rq_merge_ok(struct request *rq, struct bio *bio);
 enum elv_merge blk_try_merge(struct request *rq, struct bio *bio);
 
-void blk_set_default_limits(struct queue_limits *lim);
+int blk_set_default_limits(struct queue_limits *lim);
 int blk_dev_init(void);
 
 /*
@@ -447,7 +461,7 @@ static inline void bio_release_page(struct bio *bio, struct page *page)
 		unpin_user_page(page);
 }
 
-struct request_queue *blk_alloc_queue(int node_id);
+struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id);
 
 int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode);
 
@@ -516,8 +530,75 @@ static inline int req_ref_read(struct request *req)
 	return atomic_read(&req->ref);
 }
 
+static inline u64 blk_time_get_ns(void)
+{
+	struct blk_plug *plug = current->plug;
+
+	if (!plug)
+		return ktime_get_ns();
+
+	/*
+	 * 0 could very well be a valid time, but rather than flag "this is
+	 * a valid timestamp" separately, just accept that we'll do an extra
+	 * ktime_get_ns() if we just happen to get 0 as the current time.
+	 */
+	if (!plug->cur_ktime) {
+		plug->cur_ktime = ktime_get_ns();
+		current->flags |= PF_BLOCK_TS;
+	}
+	return plug->cur_ktime;
+}
+
+static inline ktime_t blk_time_get(void)
+{
+	return ns_to_ktime(blk_time_get_ns());
+}
+
+/*
+ * From most significant bit:
+ * 1 bit: reserved for other usage, see below
+ * 12 bits: original size of bio
+ * 51 bits: issue time of bio
+ */
+#define BIO_ISSUE_RES_BITS      1
+#define BIO_ISSUE_SIZE_BITS     12
+#define BIO_ISSUE_RES_SHIFT     (64 - BIO_ISSUE_RES_BITS)
+#define BIO_ISSUE_SIZE_SHIFT    (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS)
+#define BIO_ISSUE_TIME_MASK     ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1)
+#define BIO_ISSUE_SIZE_MASK     \
+	(((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT)
+#define BIO_ISSUE_RES_MASK      (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1))
+
+/* Reserved bit for blk-throtl */
+#define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63)
+
+static inline u64 __bio_issue_time(u64 time)
+{
+	return time & BIO_ISSUE_TIME_MASK;
+}
+
+static inline u64 bio_issue_time(struct bio_issue *issue)
+{
+	return __bio_issue_time(issue->value);
+}
+
+static inline sector_t bio_issue_size(struct bio_issue *issue)
+{
+	return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT);
+}
+
+static inline void bio_issue_init(struct bio_issue *issue,
+				       sector_t size)
+{
+	size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1;
+	issue->value = ((issue->value & BIO_ISSUE_RES_MASK) |
+			(blk_time_get_ns() & BIO_ISSUE_TIME_MASK) |
+			((u64)size << BIO_ISSUE_SIZE_SHIFT));
+}
+
 void bdev_release(struct file *bdev_file);
 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);
+
 #endif /* BLK_INTERNAL_H */

block/bsg-lib.c

@@ -383,7 +383,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
 	if (blk_mq_alloc_tag_set(set))
 		goto out_tag_set;
 
-	q = blk_mq_init_queue(set);
+	q = blk_mq_alloc_queue(set, NULL, NULL);
 	if (IS_ERR(q)) {
 		ret = PTR_ERR(q);
 		goto out_queue;

block/genhd.c

@@ -1201,7 +1201,7 @@ static int block_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	return add_uevent_var(env, "DISKSEQ=%llu", disk->diskseq);
 }
 
-struct class block_class = {
+const struct class block_class = {
 	.name		= "block",
 	.dev_uevent	= block_uevent,
 };
@@ -1391,19 +1391,21 @@ out_free_disk:
 	return NULL;
 }
 
-struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass)
+struct gendisk *__blk_alloc_disk(struct queue_limits *lim, int node,
+		struct lock_class_key *lkclass)
 {
+	struct queue_limits default_lim = { };
 	struct request_queue *q;
 	struct gendisk *disk;
 
-	q = blk_alloc_queue(node);
-	if (!q)
-		return NULL;
+	q = blk_alloc_queue(lim ? lim : &default_lim, node);
+	if (IS_ERR(q))
+		return ERR_CAST(q);
 
 	disk = __alloc_disk_node(q, node, lkclass);
 	if (!disk) {
 		blk_put_queue(q);
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	set_bit(GD_OWNS_QUEUE, &disk->state);
 	return disk;

block/holder.c

@@ -8,6 +8,8 @@ struct bd_holder_disk {
 	int			refcnt;
 };
 
+static DEFINE_MUTEX(blk_holder_mutex);
+
 static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev,
 						  struct gendisk *disk)
 {
@@ -80,7 +82,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 	kobject_get(bdev->bd_holder_dir);
 	mutex_unlock(&bdev->bd_disk->open_mutex);
 
-	mutex_lock(&disk->open_mutex);
+	mutex_lock(&blk_holder_mutex);
 	WARN_ON_ONCE(!bdev->bd_holder);
 
 	holder = bd_find_holder_disk(bdev, disk);
@@ -108,7 +110,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 		goto out_del_symlink;
 	list_add(&holder->list, &disk->slave_bdevs);
 
-	mutex_unlock(&disk->open_mutex);
+	mutex_unlock(&blk_holder_mutex);
 	return 0;
 
 out_del_symlink:
@@ -116,7 +118,7 @@ out_del_symlink:
 out_free_holder:
 	kfree(holder);
 out_unlock:
-	mutex_unlock(&disk->open_mutex);
+	mutex_unlock(&blk_holder_mutex);
 	if (ret)
 		kobject_put(bdev->bd_holder_dir);
 	return ret;
@@ -140,7 +142,7 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
 	if (WARN_ON_ONCE(!disk->slave_dir))
 		return;
 
-	mutex_lock(&disk->open_mutex);
+	mutex_lock(&blk_holder_mutex);
 	holder = bd_find_holder_disk(bdev, disk);
 	if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) {
 		del_symlink(disk->slave_dir, bdev_kobj(bdev));
@@ -149,6 +151,6 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
 		list_del_init(&holder->list);
 		kfree(holder);
 	}
-	mutex_unlock(&disk->open_mutex);
+	mutex_unlock(&blk_holder_mutex);
 }
 EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);

block/ioctl.c

@@ -18,7 +18,7 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 {
 	struct gendisk *disk = bdev->bd_disk;
 	struct blkpg_partition p;
-	sector_t start, length;
+	sector_t start, length, capacity, end;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
@@ -41,6 +41,13 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 
 	start = p.start >> SECTOR_SHIFT;
 	length = p.length >> SECTOR_SHIFT;
+	capacity = get_capacity(disk);
+
+	if (check_add_overflow(start, length, &end))
+		return -EINVAL;
+
+	if (start >= capacity || end > capacity)
+		return -EINVAL;
 
 	switch (op) {
 	case BLKPG_ADD_PARTITION:

block/partitions/core.c

@@ -419,21 +419,10 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start,
 int bdev_add_partition(struct gendisk *disk, int partno, sector_t start,
 		sector_t length)
 {
-	sector_t capacity = get_capacity(disk), end;
 	struct block_device *part;
 	int ret;
 
 	mutex_lock(&disk->open_mutex);
-	if (check_add_overflow(start, length, &end)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (start >= capacity || end > capacity) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	if (!disk_live(disk)) {
 		ret = -ENXIO;
 		goto out;

block/partitions/mac.c

@@ -20,6 +20,7 @@ extern void note_bootable_part(dev_t dev, int part, int goodness);
  * Code to understand MacOS partition tables.
  */
 
+#ifdef CONFIG_PPC_PMAC
 static inline void mac_fix_string(char *stg, int len)
 {
 	int i;
@@ -27,6 +28,7 @@ static inline void mac_fix_string(char *stg, int len)
 	for (i = len - 1; i >= 0 && stg[i] == ' '; i--)
 		stg[i] = 0;
 }
+#endif
 
 int mac_partition(struct parsed_partitions *state)
 {

block/sed-opal.c

@@ -1212,7 +1212,7 @@ static int cmd_start(struct opal_dev *dev, const u8 *uid, const u8 *method)
 static int start_opal_session_cont(struct opal_dev *dev)
 {
 	u32 hsn, tsn;
-	int error = 0;
+	int error;
 
 	error = parse_and_check_status(dev);
 	if (error)
@@ -1354,7 +1354,7 @@ static int get_active_key_cont(struct opal_dev *dev)
 {
 	const char *activekey;
 	size_t keylen;
-	int error = 0;
+	int error;
 
 	error = parse_and_check_status(dev);
 	if (error)
@@ -2157,7 +2157,7 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
 	u8 lr_buffer[OPAL_UID_LENGTH];
 	struct opal_lock_unlock *lkul = data;
 	u8 read_locked = 1, write_locked = 1;
-	int err = 0;
+	int err;
 
 	if (build_locking_range(lr_buffer, sizeof(lr_buffer),
 				lkul->session.opal_key.lr) < 0)
@@ -2580,7 +2580,7 @@ static int opal_get_discv(struct opal_dev *dev, struct opal_discovery *discv)
 	const struct opal_step discovery0_step = {
 		opal_discovery0, discv
 	};
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&dev->dev_lock);
 	setup_opal_dev(dev);
@@ -3069,7 +3069,7 @@ bool opal_unlock_from_suspend(struct opal_dev *dev)
 {
 	struct opal_suspend_data *suspend;
 	bool was_failure = false;
-	int ret = 0;
+	int ret;
 
 	if (!dev)
 		return false;
@@ -3112,10 +3112,9 @@ static int opal_read_table(struct opal_dev *dev,
 		{ read_table_data, rw_tbl },
 		{ end_opal_session, }
 	};
-	int ret = 0;
 
 	if (!rw_tbl->size)
-		return ret;
+		return 0;
 
 	return execute_steps(dev, read_table_steps,
 			     ARRAY_SIZE(read_table_steps));
@@ -3129,10 +3128,9 @@ static int opal_write_table(struct opal_dev *dev,
 		{ write_table_data, rw_tbl },
 		{ end_opal_session, }
 	};
-	int ret = 0;
 
 	if (!rw_tbl->size)
-		return ret;
+		return 0;
 
 	return execute_steps(dev, write_table_steps,
 			     ARRAY_SIZE(write_table_steps));

block/t10-pi.c

@@ -12,14 +12,14 @@
 #include <net/checksum.h>
 #include <asm/unaligned.h>
 
-typedef __be16 (csum_fn) (void *, unsigned int);
+typedef __be16 (csum_fn) (__be16, void *, unsigned int);
 
-static __be16 t10_pi_crc_fn(void *data, unsigned int len)
+static __be16 t10_pi_crc_fn(__be16 crc, void *data, unsigned int len)
 {
-	return cpu_to_be16(crc_t10dif(data, len));
+	return cpu_to_be16(crc_t10dif_update(be16_to_cpu(crc), data, len));
 }
 
-static __be16 t10_pi_ip_fn(void *data, unsigned int len)
+static __be16 t10_pi_ip_fn(__be16 csum, void *data, unsigned int len)
 {
 	return (__force __be16)ip_compute_csum(data, len);
 }
@@ -32,12 +32,16 @@ static __be16 t10_pi_ip_fn(void *data, unsigned int len)
 static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter,
 		csum_fn *fn, enum t10_dif_type type)
 {
+	u8 offset = iter->pi_offset;
 	unsigned int i;
 
 	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
-		struct t10_pi_tuple *pi = iter->prot_buf;
+		struct t10_pi_tuple *pi = iter->prot_buf + offset;
 
-		pi->guard_tag = fn(iter->data_buf, iter->interval);
+		pi->guard_tag = fn(0, iter->data_buf, iter->interval);
+		if (offset)
+			pi->guard_tag = fn(pi->guard_tag, iter->prot_buf,
+					   offset);
 		pi->app_tag = 0;
 
 		if (type == T10_PI_TYPE1_PROTECTION)
@@ -56,12 +60,13 @@ static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter,
 static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 		csum_fn *fn, enum t10_dif_type type)
 {
+	u8 offset = iter->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;
+		struct t10_pi_tuple *pi = iter->prot_buf + offset;
 		__be16 csum;
 
 		if (type == T10_PI_TYPE1_PROTECTION ||
@@ -83,7 +88,9 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 				goto next;
 		}
 
-		csum = fn(iter->data_buf, iter->interval);
+		csum = fn(0, iter->data_buf, iter->interval);
+		if (offset)
+			csum = fn(csum, iter->prot_buf, offset);
 
 		if (pi->guard_tag != csum) {
 			pr_err("%s: guard tag error at sector %llu " \
@@ -134,8 +141,10 @@ static blk_status_t t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
  */
 static void t10_pi_type1_prepare(struct request *rq)
 {
-	const int tuple_sz = rq->q->integrity.tuple_size;
+	struct blk_integrity *bi = &rq->q->integrity;
+	const int tuple_sz = bi->tuple_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
+	u8 offset = bi->pi_offset;
 	struct bio *bio;
 
 	__rq_for_each_bio(bio, rq) {
@@ -154,7 +163,7 @@ static void t10_pi_type1_prepare(struct request *rq)
 
 			p = bvec_kmap_local(&iv);
 			for (j = 0; j < iv.bv_len; j += tuple_sz) {
-				struct t10_pi_tuple *pi = p;
+				struct t10_pi_tuple *pi = p + offset;
 
 				if (be32_to_cpu(pi->ref_tag) == virt)
 					pi->ref_tag = cpu_to_be32(ref_tag);
@@ -183,9 +192,11 @@ static void t10_pi_type1_prepare(struct request *rq)
  */
 static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
-	unsigned intervals = nr_bytes >> rq->q->integrity.interval_exp;
-	const int tuple_sz = rq->q->integrity.tuple_size;
+	struct blk_integrity *bi = &rq->q->integrity;
+	unsigned intervals = nr_bytes >> bi->interval_exp;
+	const int tuple_sz = bi->tuple_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
+	u8 offset = bi->pi_offset;
 	struct bio *bio;
 
 	__rq_for_each_bio(bio, rq) {
@@ -200,7 +211,7 @@ static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 
 			p = bvec_kmap_local(&iv);
 			for (j = 0; j < iv.bv_len && intervals; j += tuple_sz) {
-				struct t10_pi_tuple *pi = p;
+				struct t10_pi_tuple *pi = p + offset;
 
 				if (be32_to_cpu(pi->ref_tag) == ref_tag)
 					pi->ref_tag = cpu_to_be32(virt);
@@ -280,20 +291,24 @@ const struct blk_integrity_profile t10_pi_type3_ip = {
 };
 EXPORT_SYMBOL(t10_pi_type3_ip);
 
-static __be64 ext_pi_crc64(void *data, unsigned int len)
+static __be64 ext_pi_crc64(u64 crc, void *data, unsigned int len)
 {
-	return cpu_to_be64(crc64_rocksoft(data, len));
+	return cpu_to_be64(crc64_rocksoft_update(crc, data, len));
 }
 
 static blk_status_t ext_pi_crc64_generate(struct blk_integrity_iter *iter,
 					enum t10_dif_type type)
 {
+	u8 offset = iter->pi_offset;
 	unsigned int i;
 
 	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
-		struct crc64_pi_tuple *pi = iter->prot_buf;
+		struct crc64_pi_tuple *pi = iter->prot_buf + offset;
 
-		pi->guard_tag = ext_pi_crc64(iter->data_buf, iter->interval);
+		pi->guard_tag = ext_pi_crc64(0, iter->data_buf, iter->interval);
+		if (offset)
+			pi->guard_tag = ext_pi_crc64(be64_to_cpu(pi->guard_tag),
+					iter->prot_buf, offset);
 		pi->app_tag = 0;
 
 		if (type == T10_PI_TYPE1_PROTECTION)
@@ -319,10 +334,11 @@ 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)
 {
+	u8 offset = iter->pi_offset;
 	unsigned int i;
 
 	for (i = 0; i < iter->data_size; i += iter->interval) {
-		struct crc64_pi_tuple *pi = iter->prot_buf;
+		struct crc64_pi_tuple *pi = iter->prot_buf + offset;
 		u64 ref, seed;
 		__be64 csum;
 
@@ -343,7 +359,11 @@ static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
 				goto next;
 		}
 
-		csum = ext_pi_crc64(iter->data_buf, iter->interval);
+		csum = ext_pi_crc64(0, iter->data_buf, iter->interval);
+		if (offset)
+			csum = ext_pi_crc64(be64_to_cpu(csum), iter->prot_buf,
+					    offset);
+
 		if (pi->guard_tag != csum) {
 			pr_err("%s: guard tag error at sector %llu " \
 			       "(rcvd %016llx, want %016llx)\n",
@@ -373,8 +393,10 @@ static blk_status_t ext_pi_type1_generate_crc64(struct blk_integrity_iter *iter)
 
 static void ext_pi_type1_prepare(struct request *rq)
 {
-	const int tuple_sz = rq->q->integrity.tuple_size;
+	struct blk_integrity *bi = &rq->q->integrity;
+	const int tuple_sz = bi->tuple_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
+	u8 offset = bi->pi_offset;
 	struct bio *bio;
 
 	__rq_for_each_bio(bio, rq) {
@@ -393,7 +415,7 @@ static void ext_pi_type1_prepare(struct request *rq)
 
 			p = bvec_kmap_local(&iv);
 			for (j = 0; j < iv.bv_len; j += tuple_sz) {
-				struct crc64_pi_tuple *pi = p;
+				struct crc64_pi_tuple *pi = p +  offset;
 				u64 ref = get_unaligned_be48(pi->ref_tag);
 
 				if (ref == virt)
@@ -411,9 +433,11 @@ static void ext_pi_type1_prepare(struct request *rq)
 
 static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
-	unsigned intervals = nr_bytes >> rq->q->integrity.interval_exp;
-	const int tuple_sz = rq->q->integrity.tuple_size;
+	struct blk_integrity *bi = &rq->q->integrity;
+	unsigned intervals = nr_bytes >> bi->interval_exp;
+	const int tuple_sz = bi->tuple_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
+	u8 offset = bi->pi_offset;
 	struct bio *bio;
 
 	__rq_for_each_bio(bio, rq) {
@@ -428,7 +452,7 @@ static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 
 			p = bvec_kmap_local(&iv);
 			for (j = 0; j < iv.bv_len && intervals; j += tuple_sz) {
-				struct crc64_pi_tuple *pi = p;
+				struct crc64_pi_tuple *pi = p + offset;
 				u64 ref = get_unaligned_be48(pi->ref_tag);
 
 				if (ref == ref_tag)

drivers/base/base.h

@@ -207,7 +207,7 @@ static inline int devtmpfs_init(void) { return 0; }
 #endif
 
 #ifdef CONFIG_BLOCK
-extern struct class block_class;
+extern const struct class block_class;
 static inline bool is_blockdev(struct device *dev)
 {
 	return dev->class == &block_class;

drivers/block/amiflop.c

@@ -1779,7 +1779,7 @@ static int fd_alloc_disk(int drive, int system)
 	struct gendisk *disk;
 	int err;
 
-	disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL);
+	disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL, NULL);
 	if (IS_ERR(disk))
 		return PTR_ERR(disk);
 

drivers/block/aoe/aoeblk.c

@@ -24,8 +24,8 @@ static DEFINE_MUTEX(aoeblk_mutex);
 static struct kmem_cache *buf_pool_cache;
 static struct dentry *aoe_debugfs_dir;
 
-/* GPFS needs a larger value than the default. */
-static int aoe_maxsectors;
+/* random default picked from the historic block max_sectors cap */
+static int aoe_maxsectors = 2560;
 module_param(aoe_maxsectors, int, 0644);
 MODULE_PARM_DESC(aoe_maxsectors,
 	"When nonzero, set the maximum number of sectors per I/O request");
@@ -334,6 +334,10 @@ aoeblk_gdalloc(void *vp)
 	mempool_t *mp;
 	struct blk_mq_tag_set *set;
 	sector_t ssize;
+	struct queue_limits lim = {
+		.max_hw_sectors		= aoe_maxsectors,
+		.io_opt			= SZ_2M,
+	};
 	ulong flags;
 	int late = 0;
 	int err;
@@ -371,7 +375,7 @@ aoeblk_gdalloc(void *vp)
 		goto err_mempool;
 	}
 
-	gd = blk_mq_alloc_disk(set, d);
+	gd = blk_mq_alloc_disk(set, &lim, d);
 	if (IS_ERR(gd)) {
 		pr_err("aoe: cannot allocate block queue for %ld.%d\n",
 			d->aoemajor, d->aoeminor);
@@ -384,14 +388,9 @@ aoeblk_gdalloc(void *vp)
 	WARN_ON(d->flags & DEVFL_TKILL);
 	WARN_ON(d->gd);
 	WARN_ON(d->flags & DEVFL_UP);
-	/* random number picked from the history block max_sectors cap */
-	blk_queue_max_hw_sectors(gd->queue, 2560u);
-	blk_queue_io_opt(gd->queue, SZ_2M);
 	d->bufpool = mp;
 	d->blkq = gd->queue;
 	d->gd = gd;
-	if (aoe_maxsectors)
-		blk_queue_max_hw_sectors(gd->queue, aoe_maxsectors);
 	gd->major = AOE_MAJOR;
 	gd->first_minor = d->sysminor;
 	gd->minors = AOE_PARTITIONS;

drivers/block/aoe/aoecmd.c

@@ -419,13 +419,16 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu
 	rcu_read_lock();
 	for_each_netdev_rcu(&init_net, ifp) {
 		dev_hold(ifp);
-		if (!is_aoe_netif(ifp))
-			goto cont;
+		if (!is_aoe_netif(ifp)) {
+			dev_put(ifp);
+			continue;
+		}
 
 		skb = new_skb(sizeof *h + sizeof *ch);
 		if (skb == NULL) {
 			printk(KERN_INFO "aoe: skb alloc failure\n");
-			goto cont;
+			dev_put(ifp);
+			continue;
 		}
 		skb_put(skb, sizeof *h + sizeof *ch);
 		skb->dev = ifp;
@@ -440,9 +443,6 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu
 		h->major = cpu_to_be16(aoemajor);
 		h->minor = aoeminor;
 		h->cmd = AOECMD_CFG;
-
-cont:
-		dev_put(ifp);
 	}
 	rcu_read_unlock();
 }

drivers/block/aoe/aoenet.c

@@ -63,6 +63,7 @@ tx(int id) __must_hold(&txlock)
 			pr_warn("aoe: packet could not be sent on %s.  %s\n",
 				ifp ? ifp->name : "netif",
 				"consider increasing tx_queue_len");
+		dev_put(ifp);
 		spin_lock_irq(&txlock);
 	}
 	return 0;

drivers/block/ataflop.c

@@ -1994,7 +1994,7 @@ static int ataflop_alloc_disk(unsigned int drive, unsigned int type)
 {
 	struct gendisk *disk;
 
-	disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL);
+	disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL, NULL);
 	if (IS_ERR(disk))
 		return PTR_ERR(disk);
 

drivers/block/brd.c

@@ -318,6 +318,16 @@ static int brd_alloc(int i)
 	struct gendisk *disk;
 	char buf[DISK_NAME_LEN];
 	int err = -ENOMEM;
+	struct queue_limits lim = {
+		/*
+		 * This is so fdisk will align partitions on 4k, because of
+		 * direct_access API needing 4k alignment, returning a PFN
+		 * (This is only a problem on very small devices <= 4M,
+		 *  otherwise fdisk will align on 1M. Regardless this call
+		 *  is harmless)
+		 */
+		.physical_block_size	= PAGE_SIZE,
+	};
 
 	list_for_each_entry(brd, &brd_devices, brd_list)
 		if (brd->brd_number == i)
@@ -335,10 +345,11 @@ static int brd_alloc(int i)
 		debugfs_create_u64(buf, 0444, brd_debugfs_dir,
 				&brd->brd_nr_pages);
 
-	disk = brd->brd_disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!disk)
+	disk = brd->brd_disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(disk)) {
+		err = PTR_ERR(disk);
 		goto out_free_dev;
-
+	}
 	disk->major		= RAMDISK_MAJOR;
 	disk->first_minor	= i * max_part;
 	disk->minors		= max_part;
@@ -347,15 +358,6 @@ static int brd_alloc(int i)
 	strscpy(disk->disk_name, buf, DISK_NAME_LEN);
 	set_capacity(disk, rd_size * 2);
 	
-	/*
-	 * This is so fdisk will align partitions on 4k, because of
-	 * direct_access API needing 4k alignment, returning a PFN
-	 * (This is only a problem on very small devices <= 4M,
-	 *  otherwise fdisk will align on 1M. Regardless this call
-	 *  is harmless)
-	 */
-	blk_queue_physical_block_size(disk->queue, PAGE_SIZE);
-
 	/* 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);

drivers/block/drbd/drbd_main.c

@@ -2690,6 +2690,14 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	int id;
 	int vnr = adm_ctx->volume;
 	enum drbd_ret_code err = ERR_NOMEM;
+	struct queue_limits lim = {
+		/*
+		 * Setting the max_hw_sectors to an odd value of 8kibyte here.
+		 * This triggers a max_bio_size message upon first attach or
+		 * connect.
+		 */
+		.max_hw_sectors		= DRBD_MAX_BIO_SIZE_SAFE >> 8,
+	};
 
 	device = minor_to_device(minor);
 	if (device)
@@ -2708,9 +2716,11 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	drbd_init_set_defaults(device);
 
-	disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!disk)
+	disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(disk)) {
+		err = PTR_ERR(disk);
 		goto out_no_disk;
+	}
 
 	device->vdisk = disk;
 	device->rq_queue = disk->queue;
@@ -2727,9 +2737,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);
 	blk_queue_write_cache(disk->queue, true, true);
-	/* Setting the max_hw_sectors to an odd value of 8kibyte here
-	   This triggers a max_bio_size message upon first attach or connect */
-	blk_queue_max_hw_sectors(disk->queue, DRBD_MAX_BIO_SIZE_SAFE >> 8);
 
 	device->md_io.page = alloc_page(GFP_KERNEL);
 	if (!device->md_io.page)

drivers/block/drbd/drbd_nl.c

@@ -1189,9 +1189,31 @@ static int drbd_check_al_size(struct drbd_device *device, struct disk_conf *dc)
 	return 0;
 }
 
-static void blk_queue_discard_granularity(struct request_queue *q, unsigned int granularity)
+static unsigned int drbd_max_peer_bio_size(struct drbd_device *device)
 {
-	q->limits.discard_granularity = granularity;
+	/*
+	 * We may ignore peer limits if the peer is modern enough.  From 8.3.8
+	 * onwards the peer can use multiple BIOs for a single peer_request.
+	 */
+	if (device->state.conn < C_WF_REPORT_PARAMS)
+		return device->peer_max_bio_size;
+
+	if (first_peer_device(device)->connection->agreed_pro_version < 94)
+		return min(device->peer_max_bio_size, DRBD_MAX_SIZE_H80_PACKET);
+
+	/*
+	 * Correct old drbd (up to 8.3.7) if it believes it can do more than
+	 * 32KiB.
+	 */
+	if (first_peer_device(device)->connection->agreed_pro_version == 94)
+		return DRBD_MAX_SIZE_H80_PACKET;
+
+	/*
+	 * drbd 8.3.8 onwards, before 8.4.0
+	 */
+	if (first_peer_device(device)->connection->agreed_pro_version < 100)
+		return DRBD_MAX_BIO_SIZE_P95;
+	return DRBD_MAX_BIO_SIZE;
 }
 
 static unsigned int drbd_max_discard_sectors(struct drbd_connection *connection)
@@ -1204,24 +1226,81 @@ static unsigned int drbd_max_discard_sectors(struct drbd_connection *connection)
 	return AL_EXTENT_SIZE >> 9;
 }
 
-static void decide_on_discard_support(struct drbd_device *device,
+static bool drbd_discard_supported(struct drbd_connection *connection,
 		struct drbd_backing_dev *bdev)
 {
-	struct drbd_connection *connection =
-		first_peer_device(device)->connection;
-	struct request_queue *q = device->rq_queue;
-	unsigned int max_discard_sectors;
-
 	if (bdev && !bdev_max_discard_sectors(bdev->backing_bdev))
-		goto not_supported;
+		return false;
 
 	if (connection->cstate >= C_CONNECTED &&
 	    !(connection->agreed_features & DRBD_FF_TRIM)) {
 		drbd_info(connection,
 			"peer DRBD too old, does not support TRIM: disabling discards\n");
-		goto not_supported;
+		return false;
 	}
 
+	return true;
+}
+
+/* This is the workaround for "bio would need to, but cannot, be split" */
+static unsigned int drbd_backing_dev_max_segments(struct drbd_device *device)
+{
+	unsigned int max_segments;
+
+	rcu_read_lock();
+	max_segments = rcu_dereference(device->ldev->disk_conf)->max_bio_bvecs;
+	rcu_read_unlock();
+
+	if (!max_segments)
+		return BLK_MAX_SEGMENTS;
+	return max_segments;
+}
+
+void drbd_reconsider_queue_parameters(struct drbd_device *device,
+		struct drbd_backing_dev *bdev, struct o_qlim *o)
+{
+	struct drbd_connection *connection =
+		first_peer_device(device)->connection;
+	struct request_queue * const q = device->rq_queue;
+	unsigned int now = queue_max_hw_sectors(q) << 9;
+	struct queue_limits lim;
+	struct request_queue *b = NULL;
+	unsigned int new;
+
+	if (bdev) {
+		b = bdev->backing_bdev->bd_disk->queue;
+
+		device->local_max_bio_size =
+			queue_max_hw_sectors(b) << SECTOR_SHIFT;
+	}
+
+	/*
+	 * We may later detach and re-attach on a disconnected Primary.  Avoid
+	 * decreasing the value in this case.
+	 *
+	 * We want to store what we know the peer DRBD can handle, not what the
+	 * peer IO backend can handle.
+	 */
+	new = min3(DRBD_MAX_BIO_SIZE, device->local_max_bio_size,
+		max(drbd_max_peer_bio_size(device), device->peer_max_bio_size));
+	if (new != now) {
+		if (device->state.role == R_PRIMARY && new < now)
+			drbd_err(device, "ASSERT FAILED new < now; (%u < %u)\n",
+					new, now);
+		drbd_info(device, "max BIO size = %u\n", new);
+	}
+
+	lim = queue_limits_start_update(q);
+	if (bdev) {
+		blk_set_stacking_limits(&lim);
+		lim.max_segments = drbd_backing_dev_max_segments(device);
+	} else {
+		lim.max_segments = BLK_MAX_SEGMENTS;
+	}
+
+	lim.max_hw_sectors = new >> SECTOR_SHIFT;
+	lim.seg_boundary_mask = PAGE_SIZE - 1;
+
 	/*
 	 * We don't care for the granularity, really.
 	 *
@@ -1230,123 +1309,36 @@ static void decide_on_discard_support(struct drbd_device *device,
 	 * problem, really. If you care, you need to use devices with similar
 	 * topology on all peers.
 	 */
-	blk_queue_discard_granularity(q, 512);
-	max_discard_sectors = drbd_max_discard_sectors(connection);
-	blk_queue_max_discard_sectors(q, max_discard_sectors);
-	blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
-	return;
+	if (drbd_discard_supported(connection, bdev)) {
+		lim.discard_granularity = 512;
+		lim.max_hw_discard_sectors =
+			drbd_max_discard_sectors(connection);
+	} else {
+		lim.discard_granularity = 0;
+		lim.max_hw_discard_sectors = 0;
+	}
 
-not_supported:
-	blk_queue_discard_granularity(q, 0);
-	blk_queue_max_discard_sectors(q, 0);
-}
+	if (bdev)
+		blk_stack_limits(&lim, &b->limits, 0);
 
-static void fixup_write_zeroes(struct drbd_device *device, struct request_queue *q)
-{
-	/* Fixup max_write_zeroes_sectors after blk_stack_limits():
-	 * if we can handle "zeroes" efficiently on the protocol,
-	 * we want to do that, even if our backend does not announce
-	 * max_write_zeroes_sectors itself. */
-	struct drbd_connection *connection = first_peer_device(device)->connection;
-	/* If the peer announces WZEROES support, use it.  Otherwise, rather
-	 * send explicit zeroes than rely on some discard-zeroes-data magic. */
+	/*
+	 * If we can handle "zeroes" efficiently on the protocol, we want to do
+	 * that, even if our backend does not announce max_write_zeroes_sectors
+	 * itself.
+	 */
 	if (connection->agreed_features & DRBD_FF_WZEROES)
-		q->limits.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS;
+		lim.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS;
 	else
-		q->limits.max_write_zeroes_sectors = 0;
-}
+		lim.max_write_zeroes_sectors = 0;
 
-static void fixup_discard_support(struct drbd_device *device, struct request_queue *q)
-{
-	unsigned int max_discard = device->rq_queue->limits.max_discard_sectors;
-	unsigned int discard_granularity =
-		device->rq_queue->limits.discard_granularity >> SECTOR_SHIFT;
-
-	if (discard_granularity > max_discard) {
-		blk_queue_discard_granularity(q, 0);
-		blk_queue_max_discard_sectors(q, 0);
-	}
-}
-
-static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backing_dev *bdev,
-				   unsigned int max_bio_size, struct o_qlim *o)
-{
-	struct request_queue * const q = device->rq_queue;
-	unsigned int max_hw_sectors = max_bio_size >> 9;
-	unsigned int max_segments = 0;
-	struct request_queue *b = NULL;
-	struct disk_conf *dc;
-
-	if (bdev) {
-		b = bdev->backing_bdev->bd_disk->queue;
-
-		max_hw_sectors = min(queue_max_hw_sectors(b), max_bio_size >> 9);
-		rcu_read_lock();
-		dc = rcu_dereference(device->ldev->disk_conf);
-		max_segments = dc->max_bio_bvecs;
-		rcu_read_unlock();
-
-		blk_set_stacking_limits(&q->limits);
+	if ((lim.discard_granularity >> SECTOR_SHIFT) >
+	    lim.max_hw_discard_sectors) {
+		lim.discard_granularity = 0;
+		lim.max_hw_discard_sectors = 0;
 	}
 
-	blk_queue_max_hw_sectors(q, max_hw_sectors);
-	/* This is the workaround for "bio would need to, but cannot, be split" */
-	blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS);
-	blk_queue_segment_boundary(q, PAGE_SIZE-1);
-	decide_on_discard_support(device, bdev);
-
-	if (b) {
-		blk_stack_limits(&q->limits, &b->limits, 0);
-		disk_update_readahead(device->vdisk);
-	}
-	fixup_write_zeroes(device, q);
-	fixup_discard_support(device, q);
-}
-
-void drbd_reconsider_queue_parameters(struct drbd_device *device, struct drbd_backing_dev *bdev, struct o_qlim *o)
-{
-	unsigned int now, new, local, peer;
-
-	now = queue_max_hw_sectors(device->rq_queue) << 9;
-	local = device->local_max_bio_size; /* Eventually last known value, from volatile memory */
-	peer = device->peer_max_bio_size; /* Eventually last known value, from meta data */
-
-	if (bdev) {
-		local = queue_max_hw_sectors(bdev->backing_bdev->bd_disk->queue) << 9;
-		device->local_max_bio_size = local;
-	}
-	local = min(local, DRBD_MAX_BIO_SIZE);
-
-	/* We may ignore peer limits if the peer is modern enough.
-	   Because new from 8.3.8 onwards the peer can use multiple
-	   BIOs for a single peer_request */
-	if (device->state.conn >= C_WF_REPORT_PARAMS) {
-		if (first_peer_device(device)->connection->agreed_pro_version < 94)
-			peer = min(device->peer_max_bio_size, DRBD_MAX_SIZE_H80_PACKET);
-			/* Correct old drbd (up to 8.3.7) if it believes it can do more than 32KiB */
-		else if (first_peer_device(device)->connection->agreed_pro_version == 94)
-			peer = DRBD_MAX_SIZE_H80_PACKET;
-		else if (first_peer_device(device)->connection->agreed_pro_version < 100)
-			peer = DRBD_MAX_BIO_SIZE_P95;  /* drbd 8.3.8 onwards, before 8.4.0 */
-		else
-			peer = DRBD_MAX_BIO_SIZE;
-
-		/* We may later detach and re-attach on a disconnected Primary.
-		 * Avoid this setting to jump back in that case.
-		 * We want to store what we know the peer DRBD can handle,
-		 * not what the peer IO backend can handle. */
-		if (peer > device->peer_max_bio_size)
-			device->peer_max_bio_size = peer;
-	}
-	new = min(local, peer);
-
-	if (device->state.role == R_PRIMARY && new < now)
-		drbd_err(device, "ASSERT FAILED new < now; (%u < %u)\n", new, now);
-
-	if (new != now)
-		drbd_info(device, "max BIO size = %u\n", new);
-
-	drbd_setup_queue_param(device, bdev, new, o);
+	if (queue_limits_commit_update(q, &lim))
+		drbd_err(device, "setting new queue limits failed\n");
 }
 
 /* Starts the worker thread */

drivers/block/drbd/drbd_state.c

@@ -1542,9 +1542,10 @@ int drbd_bitmap_io_from_worker(struct drbd_device *device,
 
 int notify_resource_state_change(struct sk_buff *skb,
 				  unsigned int seq,
-				  struct drbd_resource_state_change *resource_state_change,
+				  void *state_change,
 				  enum drbd_notification_type type)
 {
+	struct drbd_resource_state_change *resource_state_change = state_change;
 	struct drbd_resource *resource = resource_state_change->resource;
 	struct resource_info resource_info = {
 		.res_role = resource_state_change->role[NEW],
@@ -1558,13 +1559,14 @@ int notify_resource_state_change(struct sk_buff *skb,
 
 int notify_connection_state_change(struct sk_buff *skb,
 				    unsigned int seq,
-				    struct drbd_connection_state_change *connection_state_change,
+				    void *state_change,
 				    enum drbd_notification_type type)
 {
-	struct drbd_connection *connection = connection_state_change->connection;
+	struct drbd_connection_state_change *p = state_change;
+	struct drbd_connection *connection = p->connection;
 	struct connection_info connection_info = {
-		.conn_connection_state = connection_state_change->cstate[NEW],
-		.conn_role = connection_state_change->peer_role[NEW],
+		.conn_connection_state = p->cstate[NEW],
+		.conn_role = p->peer_role[NEW],
 	};
 
 	return notify_connection_state(skb, seq, connection, &connection_info, type);
@@ -1572,9 +1574,10 @@ int notify_connection_state_change(struct sk_buff *skb,
 
 int notify_device_state_change(struct sk_buff *skb,
 				unsigned int seq,
-				struct drbd_device_state_change *device_state_change,
+				void *state_change,
 				enum drbd_notification_type type)
 {
+	struct drbd_device_state_change *device_state_change = state_change;
 	struct drbd_device *device = device_state_change->device;
 	struct device_info device_info = {
 		.dev_disk_state = device_state_change->disk_state[NEW],
@@ -1585,9 +1588,10 @@ int notify_device_state_change(struct sk_buff *skb,
 
 int notify_peer_device_state_change(struct sk_buff *skb,
 				     unsigned int seq,
-				     struct drbd_peer_device_state_change *p,
+				     void *state_change,
 				     enum drbd_notification_type type)
 {
+	struct drbd_peer_device_state_change *p = state_change;
 	struct drbd_peer_device *peer_device = p->peer_device;
 	struct peer_device_info peer_device_info = {
 		.peer_repl_state = p->repl_state[NEW],
@@ -1605,8 +1609,8 @@ static void broadcast_state_change(struct drbd_state_change *state_change)
 	struct drbd_resource_state_change *resource_state_change = &state_change->resource[0];
 	bool resource_state_has_changed;
 	unsigned int n_device, n_connection, n_peer_device, n_peer_devices;
-	int (*last_func)(struct sk_buff *, unsigned int, void *,
-			  enum drbd_notification_type) = NULL;
+	int (*last_func)(struct sk_buff *, unsigned int,
+		void *, enum drbd_notification_type) = NULL;
 	void *last_arg = NULL;
 
 #define HAS_CHANGED(state) ((state)[OLD] != (state)[NEW])
@@ -1616,7 +1620,7 @@ static void broadcast_state_change(struct drbd_state_change *state_change)
 	})
 #define REMEMBER_STATE_CHANGE(func, arg, type) \
 	({ FINAL_STATE_CHANGE(type | NOTIFY_CONTINUES); \
-	   last_func = (typeof(last_func))func; \
+	   last_func = func; \
 	   last_arg = arg; \
 	 })
 

drivers/block/drbd/drbd_state_change.h

@@ -46,19 +46,19 @@ extern void forget_state_change(struct drbd_state_change *);
 
 extern int notify_resource_state_change(struct sk_buff *,
 					 unsigned int,
-					 struct drbd_resource_state_change *,
+					 void *,
 					 enum drbd_notification_type type);
 extern int notify_connection_state_change(struct sk_buff *,
 					   unsigned int,
-					   struct drbd_connection_state_change *,
+					   void *,
 					   enum drbd_notification_type type);
 extern int notify_device_state_change(struct sk_buff *,
 				       unsigned int,
-				       struct drbd_device_state_change *,
+				       void *,
 				       enum drbd_notification_type type);
 extern int notify_peer_device_state_change(struct sk_buff *,
 					    unsigned int,
-					    struct drbd_peer_device_state_change *,
+					    void *,
 					    enum drbd_notification_type type);
 
 #endif  /* DRBD_STATE_CHANGE_H */

drivers/block/floppy.c

@@ -530,14 +530,13 @@ static struct format_descr format_req;
 static char *floppy_track_buffer;
 static int max_buffer_sectors;
 
-typedef void (*done_f)(int);
 static const struct cont_t {
 	void (*interrupt)(void);
 				/* this is called after the interrupt of the
 				 * main command */
 	void (*redo)(void);	/* this is called to retry the operation */
 	void (*error)(void);	/* this is called to tally an error */
-	done_f done;		/* this is called to say if the operation has
+	void (*done)(int);	/* this is called to say if the operation has
 				 * succeeded/failed */
 } *cont;
 
@@ -985,6 +984,10 @@ static void empty(void)
 {
 }
 
+static void empty_done(int result)
+{
+}
+
 static void (*floppy_work_fn)(void);
 
 static void floppy_work_workfn(struct work_struct *work)
@@ -1998,14 +2001,14 @@ static const struct cont_t wakeup_cont = {
 	.interrupt	= empty,
 	.redo		= do_wakeup,
 	.error		= empty,
-	.done		= (done_f)empty
+	.done		= empty_done,
 };
 
 static const struct cont_t intr_cont = {
 	.interrupt	= empty,
 	.redo		= process_fd_request,
 	.error		= empty,
-	.done		= (done_f)empty
+	.done		= empty_done,
 };
 
 /* schedules handler, waiting for completion. May be interrupted, will then
@@ -4513,13 +4516,15 @@ 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,
+	};
 	struct gendisk *disk;
 
-	disk = blk_mq_alloc_disk(&tag_sets[drive], NULL);
+	disk = blk_mq_alloc_disk(&tag_sets[drive], &lim, NULL);
 	if (IS_ERR(disk))
 		return PTR_ERR(disk);
 
-	blk_queue_max_hw_sectors(disk->queue, 64);
 	disk->major = FLOPPY_MAJOR;
 	disk->first_minor = TOMINOR(drive) | (type << 2);
 	disk->minors = 1;

drivers/block/loop.c

@@ -750,12 +750,13 @@ static void loop_sysfs_exit(struct loop_device *lo)
 				   &loop_attribute_group);
 }
 
-static void loop_config_discard(struct loop_device *lo)
+static void loop_config_discard(struct loop_device *lo,
+		struct queue_limits *lim)
 {
 	struct file *file = lo->lo_backing_file;
 	struct inode *inode = file->f_mapping->host;
-	struct request_queue *q = lo->lo_queue;
-	u32 granularity, max_discard_sectors;
+	u32 granularity = 0, max_discard_sectors = 0;
+	struct kstatfs sbuf;
 
 	/*
 	 * If the backing device is a block device, mirror its zeroing
@@ -775,29 +776,17 @@ static void loop_config_discard(struct loop_device *lo)
 	 * We use punch hole to reclaim the free space used by the
 	 * image a.k.a. discard.
 	 */
-	} else if (!file->f_op->fallocate) {
-		max_discard_sectors = 0;
-		granularity = 0;
-
-	} else {
-		struct kstatfs sbuf;
-
+	} else if (file->f_op->fallocate && !vfs_statfs(&file->f_path, &sbuf)) {
 		max_discard_sectors = UINT_MAX >> 9;
-		if (!vfs_statfs(&file->f_path, &sbuf))
-			granularity = sbuf.f_bsize;
-		else
-			max_discard_sectors = 0;
+		granularity = sbuf.f_bsize;
 	}
 
-	if (max_discard_sectors) {
-		q->limits.discard_granularity = granularity;
-		blk_queue_max_discard_sectors(q, max_discard_sectors);
-		blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
-	} else {
-		q->limits.discard_granularity = 0;
-		blk_queue_max_discard_sectors(q, 0);
-		blk_queue_max_write_zeroes_sectors(q, 0);
-	}
+	lim->max_hw_discard_sectors = max_discard_sectors;
+	lim->max_write_zeroes_sectors = max_discard_sectors;
+	if (max_discard_sectors)
+		lim->discard_granularity = granularity;
+	else
+		lim->discard_granularity = 0;
 }
 
 struct loop_worker {
@@ -986,6 +975,20 @@ loop_set_status_from_info(struct loop_device *lo,
 	return 0;
 }
 
+static int loop_reconfigure_limits(struct loop_device *lo, unsigned short bsize,
+		bool update_discard_settings)
+{
+	struct queue_limits lim;
+
+	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)
+		loop_config_discard(lo, &lim);
+	return queue_limits_commit_update(lo->lo_queue, &lim);
+}
+
 static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 			  struct block_device *bdev,
 			  const struct loop_config *config)
@@ -1083,11 +1086,10 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 	else
 		bsize = 512;
 
-	blk_queue_logical_block_size(lo->lo_queue, bsize);
-	blk_queue_physical_block_size(lo->lo_queue, bsize);
-	blk_queue_io_min(lo->lo_queue, bsize);
+	error = loop_reconfigure_limits(lo, bsize, true);
+	if (WARN_ON_ONCE(error))
+		goto out_unlock;
 
-	loop_config_discard(lo);
 	loop_update_rotational(lo);
 	loop_update_dio(lo);
 	loop_sysfs_init(lo);
@@ -1154,9 +1156,7 @@ 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);
-	blk_queue_logical_block_size(lo->lo_queue, 512);
-	blk_queue_physical_block_size(lo->lo_queue, 512);
-	blk_queue_io_min(lo->lo_queue, 512);
+	loop_reconfigure_limits(lo, 512, false);
 	invalidate_disk(lo->lo_disk);
 	loop_sysfs_exit(lo);
 	/* let user-space know about this change */
@@ -1488,9 +1488,7 @@ 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);
-	blk_queue_logical_block_size(lo->lo_queue, arg);
-	blk_queue_physical_block_size(lo->lo_queue, arg);
-	blk_queue_io_min(lo->lo_queue, arg);
+	err = loop_reconfigure_limits(lo, arg, false);
 	loop_update_dio(lo);
 	blk_mq_unfreeze_queue(lo->lo_queue);
 
@@ -1982,6 +1980,12 @@ static const struct blk_mq_ops loop_mq_ops = {
 
 static int loop_add(int i)
 {
+	struct queue_limits lim = {
+		/*
+		 * Random number picked from the historic block max_sectors cap.
+		 */
+		.max_hw_sectors		= 2560u,
+	};
 	struct loop_device *lo;
 	struct gendisk *disk;
 	int err;
@@ -2025,16 +2029,13 @@ static int loop_add(int i)
 	if (err)
 		goto out_free_idr;
 
-	disk = lo->lo_disk = blk_mq_alloc_disk(&lo->tag_set, lo);
+	disk = lo->lo_disk = blk_mq_alloc_disk(&lo->tag_set, &lim, lo);
 	if (IS_ERR(disk)) {
 		err = PTR_ERR(disk);
 		goto out_cleanup_tags;
 	}
 	lo->lo_queue = lo->lo_disk->queue;
 
-	/* random number picked from the history block max_sectors cap */
-	blk_queue_max_hw_sectors(lo->lo_queue, 2560u);
-
 	/*
 	 * 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

drivers/block/mtip32xx/mtip32xx.c

@@ -3401,6 +3401,12 @@ static const struct blk_mq_ops mtip_mq_ops = {
  */
 static int mtip_block_initialize(struct driver_data *dd)
 {
+	struct queue_limits lim = {
+		.physical_block_size	= 4096,
+		.max_hw_sectors		= 0xffff,
+		.max_segments		= MTIP_MAX_SG,
+		.max_segment_size	= 0x400000,
+	};
 	int rv = 0, wait_for_rebuild = 0;
 	sector_t capacity;
 	unsigned int index = 0;
@@ -3431,7 +3437,7 @@ static int mtip_block_initialize(struct driver_data *dd)
 		goto block_queue_alloc_tag_error;
 	}
 
-	dd->disk = blk_mq_alloc_disk(&dd->tags, dd);
+	dd->disk = blk_mq_alloc_disk(&dd->tags, &lim, dd);
 	if (IS_ERR(dd->disk)) {
 		dev_err(&dd->pdev->dev,
 			"Unable to allocate request queue\n");
@@ -3481,12 +3487,7 @@ skip_create_disk:
 	/* Set device limits. */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, dd->queue);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, dd->queue);
-	blk_queue_max_segments(dd->queue, MTIP_MAX_SG);
-	blk_queue_physical_block_size(dd->queue, 4096);
-	blk_queue_max_hw_sectors(dd->queue, 0xffff);
-	blk_queue_max_segment_size(dd->queue, 0x400000);
 	dma_set_max_seg_size(&dd->pdev->dev, 0x400000);
-	blk_queue_io_min(dd->queue, 4096);
 
 	/* Set the capacity of the device in 512 byte sectors. */
 	if (!(mtip_hw_get_capacity(dd, &capacity))) {

drivers/block/n64cart.c

@@ -114,6 +114,10 @@ static const struct block_device_operations n64cart_fops = {
  */
 static int __init n64cart_probe(struct platform_device *pdev)
 {
+	struct queue_limits lim = {
+		.physical_block_size	= 4096,
+		.logical_block_size	= 4096,
+	};
 	struct gendisk *disk;
 	int err = -ENOMEM;
 
@@ -131,9 +135,11 @@ static int __init n64cart_probe(struct platform_device *pdev)
 	if (IS_ERR(reg_base))
 		return PTR_ERR(reg_base);
 
-	disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!disk)
+	disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(disk)) {
+		err = PTR_ERR(disk);
 		goto out;
+	}
 
 	disk->first_minor = 0;
 	disk->flags = GENHD_FL_NO_PART;
@@ -145,8 +151,6 @@ static int __init n64cart_probe(struct platform_device *pdev)
 	set_disk_ro(disk, 1);
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
-	blk_queue_physical_block_size(disk->queue, 4096);
-	blk_queue_logical_block_size(disk->queue, 4096);
 
 	err = add_disk(disk);
 	if (err)

drivers/block/nbd.c

@@ -316,9 +316,12 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
 	nsock->sent = 0;
 }
 
-static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
+static int __nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
 		loff_t blksize)
 {
+	struct queue_limits lim;
+	int error;
+
 	if (!blksize)
 		blksize = 1u << NBD_DEF_BLKSIZE_BITS;
 
@@ -334,10 +337,16 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
 	if (!nbd->pid)
 		return 0;
 
+	lim = queue_limits_start_update(nbd->disk->queue);
 	if (nbd->config->flags & NBD_FLAG_SEND_TRIM)
-		blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX);
-	blk_queue_logical_block_size(nbd->disk->queue, blksize);
-	blk_queue_physical_block_size(nbd->disk->queue, blksize);
+		lim.max_hw_discard_sectors = UINT_MAX;
+	else
+		lim.max_hw_discard_sectors = 0;
+	lim.logical_block_size = blksize;
+	lim.physical_block_size = blksize;
+	error = queue_limits_commit_update(nbd->disk->queue, &lim);
+	if (error)
+		return error;
 
 	if (max_part)
 		set_bit(GD_NEED_PART_SCAN, &nbd->disk->state);
@@ -346,6 +355,18 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
 	return 0;
 }
 
+static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
+		loff_t blksize)
+{
+	int error;
+
+	blk_mq_freeze_queue(nbd->disk->queue);
+	error = __nbd_set_size(nbd, bytesize, blksize);
+	blk_mq_unfreeze_queue(nbd->disk->queue);
+
+	return error;
+}
+
 static void nbd_complete_rq(struct request *req)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
@@ -1351,7 +1372,6 @@ static void nbd_config_put(struct nbd_device *nbd)
 		nbd->config = NULL;
 
 		nbd->tag_set.timeout = 0;
-		blk_queue_max_discard_sectors(nbd->disk->queue, 0);
 
 		mutex_unlock(&nbd->config_lock);
 		nbd_put(nbd);
@@ -1783,6 +1803,12 @@ static const struct blk_mq_ops nbd_mq_ops = {
 
 static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 {
+	struct queue_limits lim = {
+		.max_hw_sectors		= 65536,
+		.max_user_sectors	= 256,
+		.max_segments		= USHRT_MAX,
+		.max_segment_size	= UINT_MAX,
+	};
 	struct nbd_device *nbd;
 	struct gendisk *disk;
 	int err = -ENOMEM;
@@ -1823,7 +1849,7 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 	if (err < 0)
 		goto out_free_tags;
 
-	disk = blk_mq_alloc_disk(&nbd->tag_set, NULL);
+	disk = blk_mq_alloc_disk(&nbd->tag_set, &lim, NULL);
 	if (IS_ERR(disk)) {
 		err = PTR_ERR(disk);
 		goto out_free_idr;
@@ -1843,11 +1869,6 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 	 * Tell the block layer that we are not a rotational device
 	 */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
-	blk_queue_max_discard_sectors(disk->queue, 0);
-	blk_queue_max_segment_size(disk->queue, UINT_MAX);
-	blk_queue_max_segments(disk->queue, USHRT_MAX);
-	blk_queue_max_hw_sectors(disk->queue, 65536);
-	disk->queue->limits.max_sectors = 256;
 
 	mutex_init(&nbd->config_lock);
 	refcount_set(&nbd->config_refs, 0);
@@ -2433,6 +2454,12 @@ static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	dev_list = nla_nest_start_noflag(reply, NBD_ATTR_DEVICE_LIST);
+	if (!dev_list) {
+		nlmsg_free(reply);
+		ret = -EMSGSIZE;
+		goto out;
+	}
+
 	if (index == -1) {
 		ret = idr_for_each(&nbd_index_idr, &status_cb, reply);
 		if (ret) {

drivers/block/null_blk/main.c

@@ -115,6 +115,18 @@ module_param_string(init_hctx, g_init_hctx_str, sizeof(g_init_hctx_str), 0444);
 MODULE_PARM_DESC(init_hctx, "Fault injection to fail hctx init. init_hctx=<interval>,<probability>,<space>,<times>");
 #endif
 
+/*
+ * Historic queue modes.
+ *
+ * These days nothing but NULL_Q_MQ is actually supported, but we keep it the
+ * enum for error reporting.
+ */
+enum {
+	NULL_Q_BIO	= 0,
+	NULL_Q_RQ	= 1,
+	NULL_Q_MQ	= 2,
+};
+
 static int g_queue_mode = NULL_Q_MQ;
 
 static int null_param_store_val(const char *str, int *val, int min, int max)
@@ -165,8 +177,8 @@ static bool g_blocking;
 module_param_named(blocking, g_blocking, bool, 0444);
 MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");
 
-static bool shared_tags;
-module_param(shared_tags, bool, 0444);
+static bool g_shared_tags;
+module_param_named(shared_tags, g_shared_tags, bool, 0444);
 MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq");
 
 static bool g_shared_tag_bitmap;
@@ -426,6 +438,7 @@ NULLB_DEVICE_ATTR(zone_max_open, uint, NULL);
 NULLB_DEVICE_ATTR(zone_max_active, uint, NULL);
 NULLB_DEVICE_ATTR(virt_boundary, bool, NULL);
 NULLB_DEVICE_ATTR(no_sched, bool, NULL);
+NULLB_DEVICE_ATTR(shared_tags, bool, NULL);
 NULLB_DEVICE_ATTR(shared_tag_bitmap, bool, NULL);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
@@ -571,6 +584,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_zone_offline,
 	&nullb_device_attr_virt_boundary,
 	&nullb_device_attr_no_sched,
+	&nullb_device_attr_shared_tags,
 	&nullb_device_attr_shared_tag_bitmap,
 	NULL,
 };
@@ -653,10 +667,11 @@ static ssize_t memb_group_features_show(struct config_item *item, char *page)
 			"badblocks,blocking,blocksize,cache_size,"
 			"completion_nsec,discard,home_node,hw_queue_depth,"
 			"irqmode,max_sectors,mbps,memory_backed,no_sched,"
-			"poll_queues,power,queue_mode,shared_tag_bitmap,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\n");
+			"poll_queues,power,queue_mode,shared_tag_bitmap,"
+			"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\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -738,6 +753,7 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->zone_max_active = g_zone_max_active;
 	dev->virt_boundary = g_virt_boundary;
 	dev->no_sched = g_no_sched;
+	dev->shared_tags = g_shared_tags;
 	dev->shared_tag_bitmap = g_shared_tag_bitmap;
 	return dev;
 }
@@ -752,98 +768,11 @@ static void null_free_dev(struct nullb_device *dev)
 	kfree(dev);
 }
 
-static void put_tag(struct nullb_queue *nq, unsigned int tag)
-{
-	clear_bit_unlock(tag, nq->tag_map);
-
-	if (waitqueue_active(&nq->wait))
-		wake_up(&nq->wait);
-}
-
-static unsigned int get_tag(struct nullb_queue *nq)
-{
-	unsigned int tag;
-
-	do {
-		tag = find_first_zero_bit(nq->tag_map, nq->queue_depth);
-		if (tag >= nq->queue_depth)
-			return -1U;
-	} while (test_and_set_bit_lock(tag, nq->tag_map));
-
-	return tag;
-}
-
-static void free_cmd(struct nullb_cmd *cmd)
-{
-	put_tag(cmd->nq, cmd->tag);
-}
-
-static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer);
-
-static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq)
-{
-	struct nullb_cmd *cmd;
-	unsigned int tag;
-
-	tag = get_tag(nq);
-	if (tag != -1U) {
-		cmd = &nq->cmds[tag];
-		cmd->tag = tag;
-		cmd->error = BLK_STS_OK;
-		cmd->nq = nq;
-		if (nq->dev->irqmode == NULL_IRQ_TIMER) {
-			hrtimer_init(&cmd->timer, CLOCK_MONOTONIC,
-				     HRTIMER_MODE_REL);
-			cmd->timer.function = null_cmd_timer_expired;
-		}
-		return cmd;
-	}
-
-	return NULL;
-}
-
-static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, struct bio *bio)
-{
-	struct nullb_cmd *cmd;
-	DEFINE_WAIT(wait);
-
-	do {
-		/*
-		 * This avoids multiple return statements, multiple calls to
-		 * __alloc_cmd() and a fast path call to prepare_to_wait().
-		 */
-		cmd = __alloc_cmd(nq);
-		if (cmd) {
-			cmd->bio = bio;
-			return cmd;
-		}
-		prepare_to_wait(&nq->wait, &wait, TASK_UNINTERRUPTIBLE);
-		io_schedule();
-		finish_wait(&nq->wait, &wait);
-	} while (1);
-}
-
-static void end_cmd(struct nullb_cmd *cmd)
-{
-	int queue_mode = cmd->nq->dev->queue_mode;
-
-	switch (queue_mode)  {
-	case NULL_Q_MQ:
-		blk_mq_end_request(cmd->rq, cmd->error);
-		return;
-	case NULL_Q_BIO:
-		cmd->bio->bi_status = cmd->error;
-		bio_endio(cmd->bio);
-		break;
-	}
-
-	free_cmd(cmd);
-}
-
 static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
 {
-	end_cmd(container_of(timer, struct nullb_cmd, timer));
+	struct nullb_cmd *cmd = container_of(timer, struct nullb_cmd, timer);
 
+	blk_mq_end_request(blk_mq_rq_from_pdu(cmd), cmd->error);
 	return HRTIMER_NORESTART;
 }
 
@@ -856,7 +785,9 @@ static void null_cmd_end_timer(struct nullb_cmd *cmd)
 
 static void null_complete_rq(struct request *rq)
 {
-	end_cmd(blk_mq_rq_to_pdu(rq));
+	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
+
+	blk_mq_end_request(rq, cmd->error);
 }
 
 static struct nullb_page *null_alloc_page(void)
@@ -1273,7 +1204,7 @@ static int null_transfer(struct nullb *nullb, struct page *page,
 
 static int null_handle_rq(struct nullb_cmd *cmd)
 {
-	struct request *rq = cmd->rq;
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
 	struct nullb *nullb = cmd->nq->dev->nullb;
 	int err;
 	unsigned int len;
@@ -1298,63 +1229,21 @@ static int null_handle_rq(struct nullb_cmd *cmd)
 	return 0;
 }
 
-static int null_handle_bio(struct nullb_cmd *cmd)
-{
-	struct bio *bio = cmd->bio;
-	struct nullb *nullb = cmd->nq->dev->nullb;
-	int err;
-	unsigned int len;
-	sector_t sector = bio->bi_iter.bi_sector;
-	struct bio_vec bvec;
-	struct bvec_iter iter;
-
-	spin_lock_irq(&nullb->lock);
-	bio_for_each_segment(bvec, bio, iter) {
-		len = bvec.bv_len;
-		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
-				     op_is_write(bio_op(bio)), sector,
-				     bio->bi_opf & REQ_FUA);
-		if (err) {
-			spin_unlock_irq(&nullb->lock);
-			return err;
-		}
-		sector += len >> SECTOR_SHIFT;
-	}
-	spin_unlock_irq(&nullb->lock);
-	return 0;
-}
-
-static void null_stop_queue(struct nullb *nullb)
-{
-	struct request_queue *q = nullb->q;
-
-	if (nullb->dev->queue_mode == NULL_Q_MQ)
-		blk_mq_stop_hw_queues(q);
-}
-
-static void null_restart_queue_async(struct nullb *nullb)
-{
-	struct request_queue *q = nullb->q;
-
-	if (nullb->dev->queue_mode == NULL_Q_MQ)
-		blk_mq_start_stopped_hw_queues(q, true);
-}
-
 static inline blk_status_t null_handle_throttled(struct nullb_cmd *cmd)
 {
 	struct nullb_device *dev = cmd->nq->dev;
 	struct nullb *nullb = dev->nullb;
 	blk_status_t sts = BLK_STS_OK;
-	struct request *rq = cmd->rq;
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
 
 	if (!hrtimer_active(&nullb->bw_timer))
 		hrtimer_restart(&nullb->bw_timer);
 
 	if (atomic_long_sub_return(blk_rq_bytes(rq), &nullb->cur_bytes) < 0) {
-		null_stop_queue(nullb);
+		blk_mq_stop_hw_queues(nullb->q);
 		/* race with timer */
 		if (atomic_long_read(&nullb->cur_bytes) > 0)
-			null_restart_queue_async(nullb);
+			blk_mq_start_stopped_hw_queues(nullb->q, true);
 		/* requeue request */
 		sts = BLK_STS_DEV_RESOURCE;
 	}
@@ -1381,37 +1270,29 @@ static inline blk_status_t null_handle_memory_backed(struct nullb_cmd *cmd,
 						     sector_t nr_sectors)
 {
 	struct nullb_device *dev = cmd->nq->dev;
-	int err;
 
 	if (op == REQ_OP_DISCARD)
 		return null_handle_discard(dev, sector, nr_sectors);
+	return errno_to_blk_status(null_handle_rq(cmd));
 
-	if (dev->queue_mode == NULL_Q_BIO)
-		err = null_handle_bio(cmd);
-	else
-		err = null_handle_rq(cmd);
-
-	return errno_to_blk_status(err);
 }
 
 static void nullb_zero_read_cmd_buffer(struct nullb_cmd *cmd)
 {
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
 	struct nullb_device *dev = cmd->nq->dev;
 	struct bio *bio;
 
-	if (dev->memory_backed)
-		return;
-
-	if (dev->queue_mode == NULL_Q_BIO && bio_op(cmd->bio) == REQ_OP_READ) {
-		zero_fill_bio(cmd->bio);
-	} else if (req_op(cmd->rq) == REQ_OP_READ) {
-		__rq_for_each_bio(bio, cmd->rq)
+	if (!dev->memory_backed && req_op(rq) == REQ_OP_READ) {
+		__rq_for_each_bio(bio, rq)
 			zero_fill_bio(bio);
 	}
 }
 
 static inline void nullb_complete_cmd(struct nullb_cmd *cmd)
 {
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
+
 	/*
 	 * Since root privileges are required to configure the null_blk
 	 * driver, it is fine that this driver does not initialize the
@@ -1425,20 +1306,10 @@ static inline void nullb_complete_cmd(struct nullb_cmd *cmd)
 	/* Complete IO by inline, softirq or timer */
 	switch (cmd->nq->dev->irqmode) {
 	case NULL_IRQ_SOFTIRQ:
-		switch (cmd->nq->dev->queue_mode) {
-		case NULL_Q_MQ:
-			blk_mq_complete_request(cmd->rq);
-			break;
-		case NULL_Q_BIO:
-			/*
-			 * XXX: no proper submitting cpu information available.
-			 */
-			end_cmd(cmd);
-			break;
-		}
+		blk_mq_complete_request(rq);
 		break;
 	case NULL_IRQ_NONE:
-		end_cmd(cmd);
+		blk_mq_end_request(rq, cmd->error);
 		break;
 	case NULL_IRQ_TIMER:
 		null_cmd_end_timer(cmd);
@@ -1499,7 +1370,7 @@ static enum hrtimer_restart nullb_bwtimer_fn(struct hrtimer *timer)
 		return HRTIMER_NORESTART;
 
 	atomic_long_set(&nullb->cur_bytes, mb_per_tick(mbps));
-	null_restart_queue_async(nullb);
+	blk_mq_start_stopped_hw_queues(nullb->q, true);
 
 	hrtimer_forward_now(&nullb->bw_timer, timer_interval);
 
@@ -1516,26 +1387,6 @@ static void nullb_setup_bwtimer(struct nullb *nullb)
 	hrtimer_start(&nullb->bw_timer, timer_interval, HRTIMER_MODE_REL);
 }
 
-static struct nullb_queue *nullb_to_queue(struct nullb *nullb)
-{
-	int index = 0;
-
-	if (nullb->nr_queues != 1)
-		index = raw_smp_processor_id() / ((nr_cpu_ids + nullb->nr_queues - 1) / nullb->nr_queues);
-
-	return &nullb->queues[index];
-}
-
-static void null_submit_bio(struct bio *bio)
-{
-	sector_t sector = bio->bi_iter.bi_sector;
-	sector_t nr_sectors = bio_sectors(bio);
-	struct nullb *nullb = bio->bi_bdev->bd_disk->private_data;
-	struct nullb_queue *nq = nullb_to_queue(nullb);
-
-	null_handle_cmd(alloc_cmd(nq, bio), sector, nr_sectors, bio_op(bio));
-}
-
 #ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
 
 static bool should_timeout_request(struct request *rq)
@@ -1655,7 +1506,7 @@ static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 						blk_rq_sectors(req));
 		if (!blk_mq_add_to_batch(req, iob, (__force int) cmd->error,
 					blk_mq_end_request_batch))
-			end_cmd(cmd);
+			blk_mq_end_request(req, cmd->error);
 		nr++;
 	}
 
@@ -1711,7 +1562,6 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 		hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 		cmd->timer.function = null_cmd_timer_expired;
 	}
-	cmd->rq = rq;
 	cmd->error = BLK_STS_OK;
 	cmd->nq = nq;
 	cmd->fake_timeout = should_timeout_request(rq) ||
@@ -1770,34 +1620,8 @@ static void null_queue_rqs(struct request **rqlist)
 	*rqlist = requeue_list;
 }
 
-static void cleanup_queue(struct nullb_queue *nq)
-{
-	bitmap_free(nq->tag_map);
-	kfree(nq->cmds);
-}
-
-static void cleanup_queues(struct nullb *nullb)
-{
-	int i;
-
-	for (i = 0; i < nullb->nr_queues; i++)
-		cleanup_queue(&nullb->queues[i]);
-
-	kfree(nullb->queues);
-}
-
-static void null_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
-{
-	struct nullb_queue *nq = hctx->driver_data;
-	struct nullb *nullb = nq->dev->nullb;
-
-	nullb->nr_queues--;
-}
-
 static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
 {
-	init_waitqueue_head(&nq->wait);
-	nq->queue_depth = nullb->queue_depth;
 	nq->dev = nullb->dev;
 	INIT_LIST_HEAD(&nq->poll_list);
 	spin_lock_init(&nq->poll_lock);
@@ -1815,7 +1639,6 @@ static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data,
 	nq = &nullb->queues[hctx_idx];
 	hctx->driver_data = nq;
 	null_init_queue(nullb, nq);
-	nullb->nr_queues++;
 
 	return 0;
 }
@@ -1828,7 +1651,6 @@ static const struct blk_mq_ops null_mq_ops = {
 	.poll		= null_poll,
 	.map_queues	= null_map_queues,
 	.init_hctx	= null_init_hctx,
-	.exit_hctx	= null_exit_hctx,
 };
 
 static void null_del_dev(struct nullb *nullb)
@@ -1849,21 +1671,20 @@ static void null_del_dev(struct nullb *nullb)
 	if (test_bit(NULLB_DEV_FL_THROTTLED, &nullb->dev->flags)) {
 		hrtimer_cancel(&nullb->bw_timer);
 		atomic_long_set(&nullb->cur_bytes, LONG_MAX);
-		null_restart_queue_async(nullb);
+		blk_mq_start_stopped_hw_queues(nullb->q, true);
 	}
 
 	put_disk(nullb->disk);
-	if (dev->queue_mode == NULL_Q_MQ &&
-	    nullb->tag_set == &nullb->__tag_set)
+	if (nullb->tag_set == &nullb->__tag_set)
 		blk_mq_free_tag_set(nullb->tag_set);
-	cleanup_queues(nullb);
+	kfree(nullb->queues);
 	if (null_cache_active(nullb))
 		null_free_device_storage(nullb->dev, true);
 	kfree(nullb);
 	dev->nullb = NULL;
 }
 
-static void null_config_discard(struct nullb *nullb)
+static void null_config_discard(struct nullb *nullb, struct queue_limits *lim)
 {
 	if (nullb->dev->discard == false)
 		return;
@@ -1880,43 +1701,14 @@ static void null_config_discard(struct nullb *nullb)
 		return;
 	}
 
-	blk_queue_max_discard_sectors(nullb->q, UINT_MAX >> 9);
+	lim->max_hw_discard_sectors = UINT_MAX >> 9;
 }
 
-static const struct block_device_operations null_bio_ops = {
-	.owner		= THIS_MODULE,
-	.submit_bio	= null_submit_bio,
-	.report_zones	= null_report_zones,
-};
-
-static const struct block_device_operations null_rq_ops = {
+static const struct block_device_operations null_ops = {
 	.owner		= THIS_MODULE,
 	.report_zones	= null_report_zones,
 };
 
-static int setup_commands(struct nullb_queue *nq)
-{
-	struct nullb_cmd *cmd;
-	int i;
-
-	nq->cmds = kcalloc(nq->queue_depth, sizeof(*cmd), GFP_KERNEL);
-	if (!nq->cmds)
-		return -ENOMEM;
-
-	nq->tag_map = bitmap_zalloc(nq->queue_depth, GFP_KERNEL);
-	if (!nq->tag_map) {
-		kfree(nq->cmds);
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < nq->queue_depth; i++) {
-		cmd = &nq->cmds[i];
-		cmd->tag = -1U;
-	}
-
-	return 0;
-}
-
 static int setup_queues(struct nullb *nullb)
 {
 	int nqueues = nr_cpu_ids;
@@ -1929,101 +1721,66 @@ static int setup_queues(struct nullb *nullb)
 	if (!nullb->queues)
 		return -ENOMEM;
 
-	nullb->queue_depth = nullb->dev->hw_queue_depth;
 	return 0;
 }
 
-static int init_driver_queues(struct nullb *nullb)
+static int null_init_tag_set(struct blk_mq_tag_set *set, int poll_queues)
 {
-	struct nullb_queue *nq;
-	int i, ret = 0;
-
-	for (i = 0; i < nullb->dev->submit_queues; i++) {
-		nq = &nullb->queues[i];
-
-		null_init_queue(nullb, nq);
-
-		ret = setup_commands(nq);
-		if (ret)
-			return ret;
-		nullb->nr_queues++;
-	}
-	return 0;
-}
-
-static int null_gendisk_register(struct nullb *nullb)
-{
-	sector_t size = ((sector_t)nullb->dev->size * SZ_1M) >> SECTOR_SHIFT;
-	struct gendisk *disk = nullb->disk;
-
-	set_capacity(disk, size);
-
-	disk->major		= null_major;
-	disk->first_minor	= nullb->index;
-	disk->minors		= 1;
-	if (queue_is_mq(nullb->q))
-		disk->fops		= &null_rq_ops;
-	else
-		disk->fops		= &null_bio_ops;
-	disk->private_data	= nullb;
-	strscpy_pad(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
-
-	if (nullb->dev->zoned) {
-		int ret = null_register_zoned_dev(nullb);
-
-		if (ret)
-			return ret;
-	}
-
-	return add_disk(disk);
-}
-
-static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set)
-{
-	unsigned int flags = BLK_MQ_F_SHOULD_MERGE;
-	int hw_queues, numa_node;
-	unsigned int queue_depth;
-	int poll_queues;
-
-	if (nullb) {
-		hw_queues = nullb->dev->submit_queues;
-		poll_queues = nullb->dev->poll_queues;
-		queue_depth = nullb->dev->hw_queue_depth;
-		numa_node = nullb->dev->home_node;
-		if (nullb->dev->no_sched)
-			flags |= BLK_MQ_F_NO_SCHED;
-		if (nullb->dev->shared_tag_bitmap)
-			flags |= BLK_MQ_F_TAG_HCTX_SHARED;
-		if (nullb->dev->blocking)
-			flags |= BLK_MQ_F_BLOCKING;
-	} else {
-		hw_queues = g_submit_queues;
-		poll_queues = g_poll_queues;
-		queue_depth = g_hw_queue_depth;
-		numa_node = g_home_node;
-		if (g_no_sched)
-			flags |= BLK_MQ_F_NO_SCHED;
-		if (g_shared_tag_bitmap)
-			flags |= BLK_MQ_F_TAG_HCTX_SHARED;
-		if (g_blocking)
-			flags |= BLK_MQ_F_BLOCKING;
-	}
-
 	set->ops = &null_mq_ops;
-	set->cmd_size	= sizeof(struct nullb_cmd);
-	set->flags = flags;
-	set->driver_data = nullb;
-	set->nr_hw_queues = hw_queues;
-	set->queue_depth = queue_depth;
-	set->numa_node = numa_node;
+	set->cmd_size = sizeof(struct nullb_cmd);
+	set->timeout = 5 * HZ;
+	set->nr_maps = 1;
 	if (poll_queues) {
 		set->nr_hw_queues += poll_queues;
-		set->nr_maps = 3;
-	} else {
-		set->nr_maps = 1;
+		set->nr_maps += 2;
+	}
+	return blk_mq_alloc_tag_set(set);
+}
+
+static int null_init_global_tag_set(void)
+{
+	int error;
+
+	if (tag_set.ops)
+		return 0;
+
+	tag_set.nr_hw_queues = g_submit_queues;
+	tag_set.queue_depth = g_hw_queue_depth;
+	tag_set.numa_node = g_home_node;
+	tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	if (g_no_sched)
+		tag_set.flags |= BLK_MQ_F_NO_SCHED;
+	if (g_shared_tag_bitmap)
+		tag_set.flags |= BLK_MQ_F_TAG_HCTX_SHARED;
+	if (g_blocking)
+		tag_set.flags |= BLK_MQ_F_BLOCKING;
+
+	error = null_init_tag_set(&tag_set, g_poll_queues);
+	if (error)
+		tag_set.ops = NULL;
+	return error;
+}
+
+static int null_setup_tagset(struct nullb *nullb)
+{
+	if (nullb->dev->shared_tags) {
+		nullb->tag_set = &tag_set;
+		return null_init_global_tag_set();
 	}
 
-	return blk_mq_alloc_tag_set(set);
+	nullb->tag_set = &nullb->__tag_set;
+	nullb->tag_set->driver_data = nullb;
+	nullb->tag_set->nr_hw_queues = nullb->dev->submit_queues;
+	nullb->tag_set->queue_depth = nullb->dev->hw_queue_depth;
+	nullb->tag_set->numa_node = nullb->dev->home_node;
+	nullb->tag_set->flags = BLK_MQ_F_SHOULD_MERGE;
+	if (nullb->dev->no_sched)
+		nullb->tag_set->flags |= BLK_MQ_F_NO_SCHED;
+	if (nullb->dev->shared_tag_bitmap)
+		nullb->tag_set->flags |= BLK_MQ_F_TAG_HCTX_SHARED;
+	if (nullb->dev->blocking)
+		nullb->tag_set->flags |= BLK_MQ_F_BLOCKING;
+	return null_init_tag_set(nullb->tag_set, nullb->dev->poll_queues);
 }
 
 static int null_validate_conf(struct nullb_device *dev)
@@ -2032,11 +1789,15 @@ static int null_validate_conf(struct nullb_device *dev)
 		pr_err("legacy IO path is no longer available\n");
 		return -EINVAL;
 	}
+	if (dev->queue_mode == NULL_Q_BIO) {
+		pr_err("BIO-based IO path is no longer available, using blk-mq instead.\n");
+		dev->queue_mode = NULL_Q_MQ;
+	}
 
 	dev->blocksize = round_down(dev->blocksize, 512);
 	dev->blocksize = clamp_t(unsigned int, dev->blocksize, 512, 4096);
 
-	if (dev->queue_mode == NULL_Q_MQ && dev->use_per_node_hctx) {
+	if (dev->use_per_node_hctx) {
 		if (dev->submit_queues != nr_online_nodes)
 			dev->submit_queues = nr_online_nodes;
 	} else if (dev->submit_queues > nr_cpu_ids)
@@ -2048,8 +1809,6 @@ static int null_validate_conf(struct nullb_device *dev)
 	if (dev->poll_queues > g_poll_queues)
 		dev->poll_queues = g_poll_queues;
 	dev->prev_poll_queues = dev->poll_queues;
-
-	dev->queue_mode = min_t(unsigned int, dev->queue_mode, NULL_Q_MQ);
 	dev->irqmode = min_t(unsigned int, dev->irqmode, NULL_IRQ_TIMER);
 
 	/* Do memory allocation, so set blocking */
@@ -2060,9 +1819,6 @@ static int null_validate_conf(struct nullb_device *dev)
 	dev->cache_size = min_t(unsigned long, ULONG_MAX / 1024 / 1024,
 						dev->cache_size);
 	dev->mbps = min_t(unsigned int, 1024 * 40, dev->mbps);
-	/* can not stop a queue */
-	if (dev->queue_mode == NULL_Q_BIO)
-		dev->mbps = 0;
 
 	if (dev->zoned &&
 	    (!dev->zone_size || !is_power_of_2(dev->zone_size))) {
@@ -2102,6 +1858,12 @@ static bool null_setup_fault(void)
 
 static int null_add_dev(struct nullb_device *dev)
 {
+	struct queue_limits lim = {
+		.logical_block_size	= dev->blocksize,
+		.physical_block_size	= dev->blocksize,
+		.max_hw_sectors		= dev->max_sectors,
+	};
+
 	struct nullb *nullb;
 	int rv;
 
@@ -2123,37 +1885,26 @@ static int null_add_dev(struct nullb_device *dev)
 	if (rv)
 		goto out_free_nullb;
 
-	if (dev->queue_mode == NULL_Q_MQ) {
-		if (shared_tags) {
-			nullb->tag_set = &tag_set;
-			rv = 0;
-		} else {
-			nullb->tag_set = &nullb->__tag_set;
-			rv = null_init_tag_set(nullb, nullb->tag_set);
-		}
+	rv = null_setup_tagset(nullb);
+	if (rv)
+		goto out_cleanup_queues;
 
+	if (dev->virt_boundary)
+		lim.virt_boundary_mask = PAGE_SIZE - 1;
+	null_config_discard(nullb, &lim);
+	if (dev->zoned) {
+		rv = null_init_zoned_dev(dev, &lim);
 		if (rv)
-			goto out_cleanup_queues;
-
-		nullb->tag_set->timeout = 5 * HZ;
-		nullb->disk = blk_mq_alloc_disk(nullb->tag_set, nullb);
-		if (IS_ERR(nullb->disk)) {
-			rv = PTR_ERR(nullb->disk);
 			goto out_cleanup_tags;
-		}
-		nullb->q = nullb->disk->queue;
-	} else if (dev->queue_mode == NULL_Q_BIO) {
-		rv = -ENOMEM;
-		nullb->disk = blk_alloc_disk(nullb->dev->home_node);
-		if (!nullb->disk)
-			goto out_cleanup_queues;
-
-		nullb->q = nullb->disk->queue;
-		rv = init_driver_queues(nullb);
-		if (rv)
-			goto out_cleanup_disk;
 	}
 
+	nullb->disk = blk_mq_alloc_disk(nullb->tag_set, &lim, nullb);
+	if (IS_ERR(nullb->disk)) {
+		rv = PTR_ERR(nullb->disk);
+		goto out_cleanup_zone;
+	}
+	nullb->q = nullb->disk->queue;
+
 	if (dev->mbps) {
 		set_bit(NULLB_DEV_FL_THROTTLED, &dev->flags);
 		nullb_setup_bwtimer(nullb);
@@ -2164,12 +1915,6 @@ static int null_add_dev(struct nullb_device *dev)
 		blk_queue_write_cache(nullb->q, true, true);
 	}
 
-	if (dev->zoned) {
-		rv = null_init_zoned_dev(dev, nullb->q);
-		if (rv)
-			goto out_cleanup_disk;
-	}
-
 	nullb->q->queuedata = nullb;
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
 
@@ -2177,22 +1922,12 @@ static int null_add_dev(struct nullb_device *dev)
 	rv = ida_alloc(&nullb_indexes, GFP_KERNEL);
 	if (rv < 0) {
 		mutex_unlock(&lock);
-		goto out_cleanup_zone;
+		goto out_cleanup_disk;
 	}
 	nullb->index = rv;
 	dev->index = rv;
 	mutex_unlock(&lock);
 
-	blk_queue_logical_block_size(nullb->q, dev->blocksize);
-	blk_queue_physical_block_size(nullb->q, dev->blocksize);
-	if (dev->max_sectors)
-		blk_queue_max_hw_sectors(nullb->q, dev->max_sectors);
-
-	if (dev->virt_boundary)
-		blk_queue_virt_boundary(nullb->q, PAGE_SIZE - 1);
-
-	null_config_discard(nullb);
-
 	if (config_item_name(&dev->group.cg_item)) {
 		/* Use configfs dir name as the device name */
 		snprintf(nullb->disk_name, sizeof(nullb->disk_name),
@@ -2201,7 +1936,22 @@ static int null_add_dev(struct nullb_device *dev)
 		sprintf(nullb->disk_name, "nullb%d", nullb->index);
 	}
 
-	rv = null_gendisk_register(nullb);
+	set_capacity(nullb->disk,
+		((sector_t)nullb->dev->size * SZ_1M) >> SECTOR_SHIFT);
+	nullb->disk->major = null_major;
+	nullb->disk->first_minor = nullb->index;
+	nullb->disk->minors = 1;
+	nullb->disk->fops = &null_ops;
+	nullb->disk->private_data = nullb;
+	strscpy_pad(nullb->disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
+
+	if (nullb->dev->zoned) {
+		rv = null_register_zoned_dev(nullb);
+		if (rv)
+			goto out_ida_free;
+	}
+
+	rv = add_disk(nullb->disk);
 	if (rv)
 		goto out_ida_free;
 
@@ -2220,10 +1970,10 @@ out_cleanup_zone:
 out_cleanup_disk:
 	put_disk(nullb->disk);
 out_cleanup_tags:
-	if (dev->queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set)
+	if (nullb->tag_set == &nullb->__tag_set)
 		blk_mq_free_tag_set(nullb->tag_set);
 out_cleanup_queues:
-	cleanup_queues(nullb);
+	kfree(nullb->queues);
 out_free_nullb:
 	kfree(nullb);
 	dev->nullb = NULL;
@@ -2299,7 +2049,7 @@ static int __init null_init(void)
 		return -EINVAL;
 	}
 
-	if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) {
+	if (g_use_per_node_hctx) {
 		if (g_submit_queues != nr_online_nodes) {
 			pr_warn("submit_queues param is set to %u.\n",
 				nr_online_nodes);
@@ -2311,18 +2061,12 @@ static int __init null_init(void)
 		g_submit_queues = 1;
 	}
 
-	if (g_queue_mode == NULL_Q_MQ && shared_tags) {
-		ret = null_init_tag_set(NULL, &tag_set);
-		if (ret)
-			return ret;
-	}
-
 	config_group_init(&nullb_subsys.su_group);
 	mutex_init(&nullb_subsys.su_mutex);
 
 	ret = configfs_register_subsystem(&nullb_subsys);
 	if (ret)
-		goto err_tagset;
+		return ret;
 
 	mutex_init(&lock);
 
@@ -2349,9 +2093,6 @@ err_dev:
 	unregister_blkdev(null_major, "nullb");
 err_conf:
 	configfs_unregister_subsystem(&nullb_subsys);
-err_tagset:
-	if (g_queue_mode == NULL_Q_MQ && shared_tags)
-		blk_mq_free_tag_set(&tag_set);
 	return ret;
 }
 
@@ -2370,7 +2111,7 @@ static void __exit null_exit(void)
 	}
 	mutex_unlock(&lock);
 
-	if (g_queue_mode == NULL_Q_MQ && shared_tags)
+	if (tag_set.ops)
 		blk_mq_free_tag_set(&tag_set);
 }
 

drivers/block/null_blk/null_blk.h

@@ -16,11 +16,6 @@
 #include <linux/mutex.h>
 
 struct nullb_cmd {
-	union {
-		struct request *rq;
-		struct bio *bio;
-	};
-	unsigned int tag;
 	blk_status_t error;
 	bool fake_timeout;
 	struct nullb_queue *nq;
@@ -28,16 +23,11 @@ struct nullb_cmd {
 };
 
 struct nullb_queue {
-	unsigned long *tag_map;
-	wait_queue_head_t wait;
-	unsigned int queue_depth;
 	struct nullb_device *dev;
 	unsigned int requeue_selection;
 
 	struct list_head poll_list;
 	spinlock_t poll_lock;
-
-	struct nullb_cmd *cmds;
 };
 
 struct nullb_zone {
@@ -60,13 +50,6 @@ struct nullb_zone {
 	unsigned int capacity;
 };
 
-/* Queue modes */
-enum {
-	NULL_Q_BIO	= 0,
-	NULL_Q_RQ	= 1,
-	NULL_Q_MQ	= 2,
-};
-
 struct nullb_device {
 	struct nullb *nullb;
 	struct config_group group;
@@ -119,6 +102,7 @@ struct nullb_device {
 	bool zoned; /* if device is zoned */
 	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 */
 	bool shared_tag_bitmap; /* use hostwide shared tags */
 };
 
@@ -130,14 +114,12 @@ struct nullb {
 	struct gendisk *disk;
 	struct blk_mq_tag_set *tag_set;
 	struct blk_mq_tag_set __tag_set;
-	unsigned int queue_depth;
 	atomic_long_t cur_bytes;
 	struct hrtimer bw_timer;
 	unsigned long cache_flush_pos;
 	spinlock_t lock;
 
 	struct nullb_queue *queues;
-	unsigned int nr_queues;
 	char disk_name[DISK_NAME_LEN];
 };
 
@@ -147,7 +129,7 @@ blk_status_t null_process_cmd(struct nullb_cmd *cmd, enum req_op op,
 			      sector_t sector, unsigned int nr_sectors);
 
 #ifdef CONFIG_BLK_DEV_ZONED
-int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q);
+int null_init_zoned_dev(struct nullb_device *dev, struct queue_limits *lim);
 int null_register_zoned_dev(struct nullb *nullb);
 void null_free_zoned_dev(struct nullb_device *dev);
 int null_report_zones(struct gendisk *disk, sector_t sector,
@@ -160,7 +142,7 @@ ssize_t zone_cond_store(struct nullb_device *dev, const char *page,
 			size_t count, enum blk_zone_cond cond);
 #else
 static inline int null_init_zoned_dev(struct nullb_device *dev,
-				      struct request_queue *q)
+		struct queue_limits *lim)
 {
 	pr_err("CONFIG_BLK_DEV_ZONED not enabled\n");
 	return -EINVAL;

drivers/block/null_blk/trace.h

@@ -41,10 +41,11 @@ TRACE_EVENT(nullb_zone_op,
 		__field(unsigned int, zone_cond)
 	    ),
 	    TP_fast_assign(
-		__entry->op = req_op(cmd->rq);
+		__entry->op = req_op(blk_mq_rq_from_pdu(cmd));
 		__entry->zone_no = zone_no;
 		__entry->zone_cond = zone_cond;
-		__assign_disk_name(__entry->disk, cmd->rq->q->disk);
+		__assign_disk_name(__entry->disk,
+			blk_mq_rq_from_pdu(cmd)->q->disk);
 	    ),
 	    TP_printk("%s req=%-15s zone_no=%u zone_cond=%-10s",
 		      __print_disk_name(__entry->disk),

drivers/block/null_blk/zoned.c

@@ -58,7 +58,8 @@ static inline void null_unlock_zone(struct nullb_device *dev,
 		mutex_unlock(&zone->mutex);
 }
 
-int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
+int null_init_zoned_dev(struct nullb_device *dev,
+			struct queue_limits *lim)
 {
 	sector_t dev_capacity_sects, zone_capacity_sects;
 	struct nullb_zone *zone;
@@ -151,27 +152,22 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 		sector += dev->zone_size_sects;
 	}
 
+	lim->zoned = true;
+	lim->chunk_sectors = dev->zone_size_sects;
+	lim->max_zone_append_sectors = dev->zone_size_sects;
+	lim->max_open_zones = dev->zone_max_open;
+	lim->max_active_zones = dev->zone_max_active;
 	return 0;
 }
 
 int null_register_zoned_dev(struct nullb *nullb)
 {
-	struct nullb_device *dev = nullb->dev;
 	struct request_queue *q = nullb->q;
 
-	disk_set_zoned(nullb->disk);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
-	blk_queue_chunk_sectors(q, dev->zone_size_sects);
 	nullb->disk->nr_zones = bdev_nr_zones(nullb->disk->part0);
-	blk_queue_max_zone_append_sectors(q, dev->zone_size_sects);
-	disk_set_max_open_zones(nullb->disk, dev->zone_max_open);
-	disk_set_max_active_zones(nullb->disk, dev->zone_max_active);
-
-	if (queue_is_mq(q))
-		return blk_revalidate_disk_zones(nullb->disk, NULL);
-
-	return 0;
+	return blk_revalidate_disk_zones(nullb->disk, NULL);
 }
 
 void null_free_zoned_dev(struct nullb_device *dev)
@@ -394,10 +390,7 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 	 */
 	if (append) {
 		sector = zone->wp;
-		if (dev->queue_mode == NULL_Q_MQ)
-			cmd->rq->__sector = sector;
-		else
-			cmd->bio->bi_iter.bi_sector = sector;
+		blk_mq_rq_from_pdu(cmd)->__sector = sector;
 	} else if (sector != zone->wp) {
 		ret = BLK_STS_IOERR;
 		goto unlock;

drivers/block/pktcdvd.c

@@ -828,6 +828,12 @@ static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd,
  */
 static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio)
 {
+	/*
+	 * Some CDRW drives can not handle writes larger than one packet,
+	 * even if the size is a multiple of the packet size.
+	 */
+	bio->bi_opf |= REQ_NOMERGE;
+
 	spin_lock(&pd->iosched.lock);
 	if (bio_data_dir(bio) == READ)
 		bio_list_add(&pd->iosched.read_queue, bio);
@@ -2191,11 +2197,6 @@ static int pkt_open_dev(struct pktcdvd_device *pd, bool write)
 		ret = pkt_open_write(pd);
 		if (ret)
 			goto out_putdev;
-		/*
-		 * Some CDRW drives can not handle writes larger than one packet,
-		 * even if the size is a multiple of the packet size.
-		 */
-		blk_queue_max_hw_sectors(q, pd->settings.size);
 		set_bit(PACKET_WRITABLE, &pd->flags);
 	} else {
 		pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
@@ -2338,9 +2339,9 @@ static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
 	pkt_queue_bio(pd, cloned_bio);
 }
 
-static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
+static void pkt_make_request_write(struct bio *bio)
 {
-	struct pktcdvd_device *pd = q->queuedata;
+	struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->private_data;
 	sector_t zone;
 	struct packet_data *pkt;
 	int was_empty, blocked_bio;
@@ -2432,7 +2433,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
 
 static void pkt_submit_bio(struct bio *bio)
 {
-	struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata;
+	struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->private_data;
 	struct device *ddev = disk_to_dev(pd->disk);
 	struct bio *split;
 
@@ -2476,7 +2477,7 @@ static void pkt_submit_bio(struct bio *bio)
 			split = bio;
 		}
 
-		pkt_make_request_write(bio->bi_bdev->bd_disk->queue, split);
+		pkt_make_request_write(split);
 	} while (split != bio);
 
 	return;
@@ -2484,15 +2485,6 @@ end_io:
 	bio_io_error(bio);
 }
 
-static void pkt_init_queue(struct pktcdvd_device *pd)
-{
-	struct request_queue *q = pd->disk->queue;
-
-	blk_queue_logical_block_size(q, CD_FRAMESIZE);
-	blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS);
-	q->queuedata = pd;
-}
-
 static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 {
 	struct device *ddev = disk_to_dev(pd->disk);
@@ -2536,8 +2528,6 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	pd->bdev_file = bdev_file;
 	set_blocksize(file_bdev(bdev_file), CD_FRAMESIZE);
 
-	pkt_init_queue(pd);
-
 	atomic_set(&pd->cdrw.pending_bios, 0);
 	pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->disk->disk_name);
 	if (IS_ERR(pd->cdrw.thread)) {
@@ -2634,6 +2624,10 @@ static const struct block_device_operations pktcdvd_ops = {
  */
 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,
+	};
 	int idx;
 	int ret = -ENOMEM;
 	struct pktcdvd_device *pd;
@@ -2673,10 +2667,11 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 	pd->write_congestion_on  = write_congestion_on;
 	pd->write_congestion_off = write_congestion_off;
 
-	ret = -ENOMEM;
-	disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!disk)
+	disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(disk)) {
+		ret = PTR_ERR(disk);
 		goto out_mem;
+	}
 	pd->disk = disk;
 	disk->major = pktdev_major;
 	disk->first_minor = idx;

drivers/block/ps3disk.c

@@ -382,6 +382,14 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 	struct ps3disk_private *priv;
 	int error;
 	unsigned int devidx;
+	struct queue_limits lim = {
+		.logical_block_size	= dev->blk_size,
+		.max_hw_sectors		= dev->bounce_size >> 9,
+		.max_segments		= -1,
+		.max_segment_size	= dev->bounce_size,
+		.dma_alignment		= dev->blk_size - 1,
+	};
+
 	struct request_queue *queue;
 	struct gendisk *gendisk;
 
@@ -431,7 +439,7 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 	if (error)
 		goto fail_teardown;
 
-	gendisk = blk_mq_alloc_disk(&priv->tag_set, dev);
+	gendisk = blk_mq_alloc_disk(&priv->tag_set, &lim, dev);
 	if (IS_ERR(gendisk)) {
 		dev_err(&dev->sbd.core, "%s:%u: blk_mq_alloc_disk failed\n",
 			__func__, __LINE__);
@@ -441,15 +449,8 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 
 	queue = gendisk->queue;
 
-	blk_queue_max_hw_sectors(queue, dev->bounce_size >> 9);
-	blk_queue_dma_alignment(queue, dev->blk_size-1);
-	blk_queue_logical_block_size(queue, dev->blk_size);
-
 	blk_queue_write_cache(queue, true, false);
 
-	blk_queue_max_segments(queue, -1);
-	blk_queue_max_segment_size(queue, dev->bounce_size);
-
 	priv->gendisk = gendisk;
 	gendisk->major = ps3disk_major;
 	gendisk->first_minor = devidx * PS3DISK_MINORS;

drivers/block/ps3vram.c

@@ -730,10 +730,10 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev)
 
 	ps3vram_proc_init(dev);
 
-	gendisk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!gendisk) {
+	gendisk = blk_alloc_disk(NULL, NUMA_NO_NODE);
+	if (IS_ERR(gendisk)) {
 		dev_err(&dev->core, "blk_alloc_disk failed\n");
-		error = -ENOMEM;
+		error = PTR_ERR(gendisk);
 		goto out_cache_cleanup;
 	}
 

drivers/block/rbd.c

@@ -575,7 +575,7 @@ static const struct attribute_group rbd_bus_group = {
 };
 __ATTRIBUTE_GROUPS(rbd_bus);
 
-static struct bus_type rbd_bus_type = {
+static const struct bus_type rbd_bus_type = {
 	.name		= "rbd",
 	.bus_groups	= rbd_bus_groups,
 };
@@ -4952,6 +4952,14 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	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_min			= rbd_dev->opts->alloc_size,
+		.io_opt			= rbd_dev->opts->alloc_size,
+		.max_segments		= USHRT_MAX,
+		.max_segment_size	= UINT_MAX,
+	};
 	int err;
 
 	memset(&rbd_dev->tag_set, 0, sizeof(rbd_dev->tag_set));
@@ -4966,7 +4974,13 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	if (err)
 		return err;
 
-	disk = blk_mq_alloc_disk(&rbd_dev->tag_set, rbd_dev);
+	if (rbd_dev->opts->trim) {
+		lim.discard_granularity = rbd_dev->opts->alloc_size;
+		lim.max_hw_discard_sectors = objset_bytes >> SECTOR_SHIFT;
+		lim.max_write_zeroes_sectors = objset_bytes >> SECTOR_SHIFT;
+	}
+
+	disk = blk_mq_alloc_disk(&rbd_dev->tag_set, &lim, rbd_dev);
 	if (IS_ERR(disk)) {
 		err = PTR_ERR(disk);
 		goto out_tag_set;
@@ -4987,19 +5001,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 	/* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */
 
-	blk_queue_max_hw_sectors(q, objset_bytes >> SECTOR_SHIFT);
-	q->limits.max_sectors = queue_max_hw_sectors(q);
-	blk_queue_max_segments(q, USHRT_MAX);
-	blk_queue_max_segment_size(q, UINT_MAX);
-	blk_queue_io_min(q, rbd_dev->opts->alloc_size);
-	blk_queue_io_opt(q, rbd_dev->opts->alloc_size);
-
-	if (rbd_dev->opts->trim) {
-		q->limits.discard_granularity = rbd_dev->opts->alloc_size;
-		blk_queue_max_discard_sectors(q, objset_bytes >> SECTOR_SHIFT);
-		blk_queue_max_write_zeroes_sectors(q, objset_bytes >> SECTOR_SHIFT);
-	}
-
 	if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
 		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
 

drivers/block/rnbd/rnbd-clt.c

@@ -1329,43 +1329,6 @@ static void rnbd_init_mq_hw_queues(struct rnbd_clt_dev *dev)
 	}
 }
 
-static void setup_request_queue(struct rnbd_clt_dev *dev,
-				struct rnbd_msg_open_rsp *rsp)
-{
-	blk_queue_logical_block_size(dev->queue,
-				     le16_to_cpu(rsp->logical_block_size));
-	blk_queue_physical_block_size(dev->queue,
-				      le16_to_cpu(rsp->physical_block_size));
-	blk_queue_max_hw_sectors(dev->queue,
-				 dev->sess->max_io_size / SECTOR_SIZE);
-
-	/*
-	 * we don't support discards to "discontiguous" segments
-	 * in on request
-	 */
-	blk_queue_max_discard_segments(dev->queue, 1);
-
-	blk_queue_max_discard_sectors(dev->queue,
-				      le32_to_cpu(rsp->max_discard_sectors));
-	dev->queue->limits.discard_granularity =
-					le32_to_cpu(rsp->discard_granularity);
-	dev->queue->limits.discard_alignment =
-					le32_to_cpu(rsp->discard_alignment);
-	if (le16_to_cpu(rsp->secure_discard))
-		blk_queue_max_secure_erase_sectors(dev->queue,
-					le32_to_cpu(rsp->max_discard_sectors));
-	blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue);
-	blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue);
-	blk_queue_max_segments(dev->queue, dev->sess->max_segments);
-	blk_queue_io_opt(dev->queue, dev->sess->max_io_size);
-	blk_queue_virt_boundary(dev->queue, SZ_4K - 1);
-	blk_queue_write_cache(dev->queue,
-			      !!(rsp->cache_policy & RNBD_WRITEBACK),
-			      !!(rsp->cache_policy & RNBD_FUA));
-	blk_queue_max_write_zeroes_sectors(dev->queue,
-					   le32_to_cpu(rsp->max_write_zeroes_sectors));
-}
-
 static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev,
 				   struct rnbd_msg_open_rsp *rsp, int idx)
 {
@@ -1403,18 +1366,41 @@ static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev,
 static int rnbd_client_setup_device(struct rnbd_clt_dev *dev,
 				    struct rnbd_msg_open_rsp *rsp)
 {
+	struct queue_limits lim = {
+		.logical_block_size	= le16_to_cpu(rsp->logical_block_size),
+		.physical_block_size	= le16_to_cpu(rsp->physical_block_size),
+		.io_opt			= dev->sess->max_io_size,
+		.max_hw_sectors		= dev->sess->max_io_size / SECTOR_SIZE,
+		.max_hw_discard_sectors	= le32_to_cpu(rsp->max_discard_sectors),
+		.discard_granularity	= le32_to_cpu(rsp->discard_granularity),
+		.discard_alignment	= le32_to_cpu(rsp->discard_alignment),
+		.max_segments		= dev->sess->max_segments,
+		.virt_boundary_mask	= SZ_4K - 1,
+		.max_write_zeroes_sectors =
+			le32_to_cpu(rsp->max_write_zeroes_sectors),
+	};
 	int idx = dev->clt_device_id;
 
 	dev->size = le64_to_cpu(rsp->nsectors) *
 			le16_to_cpu(rsp->logical_block_size);
 
-	dev->gd = blk_mq_alloc_disk(&dev->sess->tag_set, dev);
+	if (rsp->secure_discard) {
+		lim.max_secure_erase_sectors =
+			le32_to_cpu(rsp->max_discard_sectors);
+	}
+
+	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);
 
-	setup_request_queue(dev, rsp);
+	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/sunvdc.c

@@ -784,6 +784,14 @@ static const struct blk_mq_ops vdc_mq_ops = {
 
 static int probe_disk(struct vdc_port *port)
 {
+	struct queue_limits lim = {
+		.physical_block_size		= port->vdisk_phys_blksz,
+		.max_hw_sectors			= port->max_xfer_size,
+		/* Each segment in a request is up to an aligned page in size. */
+		.seg_boundary_mask		= PAGE_SIZE - 1,
+		.max_segment_size		= PAGE_SIZE,
+		.max_segments			= port->ring_cookies,
+	};
 	struct request_queue *q;
 	struct gendisk *g;
 	int err;
@@ -824,7 +832,7 @@ static int probe_disk(struct vdc_port *port)
 	if (err)
 		return err;
 
-	g = blk_mq_alloc_disk(&port->tag_set, port);
+	g = blk_mq_alloc_disk(&port->tag_set, &lim, port);
 	if (IS_ERR(g)) {
 		printk(KERN_ERR PFX "%s: Could not allocate gendisk.\n",
 		       port->vio.name);
@@ -835,12 +843,6 @@ static int probe_disk(struct vdc_port *port)
 	port->disk = g;
 	q = g->queue;
 
-	/* Each segment in a request is up to an aligned page in size. */
-	blk_queue_segment_boundary(q, PAGE_SIZE - 1);
-	blk_queue_max_segment_size(q, PAGE_SIZE);
-
-	blk_queue_max_segments(q, port->ring_cookies);
-	blk_queue_max_hw_sectors(q, port->max_xfer_size);
 	g->major = vdc_major;
 	g->first_minor = port->vio.vdev->dev_no << PARTITION_SHIFT;
 	g->minors = 1 << PARTITION_SHIFT;
@@ -872,8 +874,6 @@ static int probe_disk(struct vdc_port *port)
 		}
 	}
 
-	blk_queue_physical_block_size(q, port->vdisk_phys_blksz);
-
 	pr_info(PFX "%s: %u sectors (%u MB) protocol %d.%d\n",
 	       g->disk_name,
 	       port->vdisk_size, (port->vdisk_size >> (20 - 9)),

drivers/block/swim.c

@@ -820,7 +820,7 @@ 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,
+			blk_mq_alloc_disk(&swd->unit[drive].tag_set, NULL,
 					  &swd->unit[drive]);
 		if (IS_ERR(swd->unit[drive].disk)) {
 			blk_mq_free_tag_set(&swd->unit[drive].tag_set);
@@ -916,7 +916,7 @@ out:
 	return ret;
 }
 
-static int swim_remove(struct platform_device *dev)
+static void swim_remove(struct platform_device *dev)
 {
 	struct swim_priv *swd = platform_get_drvdata(dev);
 	int drive;
@@ -937,13 +937,11 @@ static int swim_remove(struct platform_device *dev)
 		release_mem_region(res->start, resource_size(res));
 
 	kfree(swd);
-
-	return 0;
 }
 
 static struct platform_driver swim_driver = {
 	.probe  = swim_probe,
-	.remove = swim_remove,
+	.remove_new = swim_remove,
 	.driver   = {
 		.name	= CARDNAME,
 	},

drivers/block/swim3.c

@@ -1210,7 +1210,7 @@ static int swim3_attach(struct macio_dev *mdev,
 	if (rc)
 		goto out_unregister;
 
-	disk = blk_mq_alloc_disk(&fs->tag_set, fs);
+	disk = blk_mq_alloc_disk(&fs->tag_set, NULL, fs);
 	if (IS_ERR(disk)) {
 		rc = PTR_ERR(disk);
 		goto out_free_tag_set;

drivers/block/ublk_drv.c

@@ -246,21 +246,12 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
 	return 0;
 }
 
-static int ublk_dev_param_zoned_apply(struct ublk_device *ub)
+static void ublk_dev_param_zoned_apply(struct ublk_device *ub)
 {
-	const struct ublk_param_zoned *p = &ub->params.zoned;
-
-	disk_set_zoned(ub->ub_disk);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue);
 	blk_queue_required_elevator_features(ub->ub_disk->queue,
 					     ELEVATOR_F_ZBD_SEQ_WRITE);
-	disk_set_max_active_zones(ub->ub_disk, p->max_active_zones);
-	disk_set_max_open_zones(ub->ub_disk, p->max_open_zones);
-	blk_queue_max_zone_append_sectors(ub->ub_disk->queue, p->max_zone_append_sectors);
-
 	ub->ub_disk->nr_zones = ublk_get_nr_zones(ub);
-
-	return 0;
 }
 
 /* Based on virtblk_alloc_report_buffer */
@@ -432,9 +423,8 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
 	return -EOPNOTSUPP;
 }
 
-static int ublk_dev_param_zoned_apply(struct ublk_device *ub)
+static void ublk_dev_param_zoned_apply(struct ublk_device *ub)
 {
-	return -EOPNOTSUPP;
 }
 
 static int ublk_revalidate_disk_zones(struct ublk_device *ub)
@@ -498,11 +488,6 @@ 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_logical_block_size(q, 1 << p->logical_bs_shift);
-	blk_queue_physical_block_size(q, 1 << p->physical_bs_shift);
-	blk_queue_io_min(q, 1 << p->io_min_shift);
-	blk_queue_io_opt(q, 1 << p->io_opt_shift);
-
 	blk_queue_write_cache(q, p->attrs & UBLK_ATTR_VOLATILE_CACHE,
 			p->attrs & UBLK_ATTR_FUA);
 	if (p->attrs & UBLK_ATTR_ROTATIONAL)
@@ -510,29 +495,12 @@ static void ublk_dev_param_basic_apply(struct ublk_device *ub)
 	else
 		blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 
-	blk_queue_max_hw_sectors(q, p->max_sectors);
-	blk_queue_chunk_sectors(q, p->chunk_sectors);
-	blk_queue_virt_boundary(q, p->virt_boundary_mask);
-
 	if (p->attrs & UBLK_ATTR_READ_ONLY)
 		set_disk_ro(ub->ub_disk, true);
 
 	set_capacity(ub->ub_disk, p->dev_sectors);
 }
 
-static void ublk_dev_param_discard_apply(struct ublk_device *ub)
-{
-	struct request_queue *q = ub->ub_disk->queue;
-	const struct ublk_param_discard *p = &ub->params.discard;
-
-	q->limits.discard_alignment = p->discard_alignment;
-	q->limits.discard_granularity = p->discard_granularity;
-	blk_queue_max_discard_sectors(q, p->max_discard_sectors);
-	blk_queue_max_write_zeroes_sectors(q,
-			p->max_write_zeroes_sectors);
-	blk_queue_max_discard_segments(q, p->max_discard_segments);
-}
-
 static int ublk_validate_params(const struct ublk_device *ub)
 {
 	/* basic param is the only one which must be set */
@@ -576,20 +544,12 @@ static int ublk_validate_params(const struct ublk_device *ub)
 	return 0;
 }
 
-static int ublk_apply_params(struct ublk_device *ub)
+static void ublk_apply_params(struct ublk_device *ub)
 {
-	if (!(ub->params.types & UBLK_PARAM_TYPE_BASIC))
-		return -EINVAL;
-
 	ublk_dev_param_basic_apply(ub);
 
-	if (ub->params.types & UBLK_PARAM_TYPE_DISCARD)
-		ublk_dev_param_discard_apply(ub);
-
 	if (ub->params.types & UBLK_PARAM_TYPE_ZONED)
-		return ublk_dev_param_zoned_apply(ub);
-
-	return 0;
+		ublk_dev_param_zoned_apply(ub);
 }
 
 static inline bool ublk_support_user_copy(const struct ublk_queue *ubq)
@@ -645,14 +605,16 @@ static inline bool ublk_need_get_data(const struct ublk_queue *ubq)
 	return ubq->flags & UBLK_F_NEED_GET_DATA;
 }
 
-static struct ublk_device *ublk_get_device(struct ublk_device *ub)
+/* Called in slow path only, keep it noinline for trace purpose */
+static noinline struct ublk_device *ublk_get_device(struct ublk_device *ub)
 {
 	if (kobject_get_unless_zero(&ub->cdev_dev.kobj))
 		return ub;
 	return NULL;
 }
 
-static void ublk_put_device(struct ublk_device *ub)
+/* Called in slow path only, keep it noinline for trace purpose */
+static noinline void ublk_put_device(struct ublk_device *ub)
 {
 	put_device(&ub->cdev_dev);
 }
@@ -711,7 +673,7 @@ static void ublk_free_disk(struct gendisk *disk)
 	struct ublk_device *ub = disk->private_data;
 
 	clear_bit(UB_STATE_USED, &ub->state);
-	put_device(&ub->cdev_dev);
+	ublk_put_device(ub);
 }
 
 static void ublk_store_owner_uid_gid(unsigned int *owner_uid,
@@ -2182,7 +2144,7 @@ static void ublk_remove(struct ublk_device *ub)
 	cancel_work_sync(&ub->stop_work);
 	cancel_work_sync(&ub->quiesce_work);
 	cdev_device_del(&ub->cdev, &ub->cdev_dev);
-	put_device(&ub->cdev_dev);
+	ublk_put_device(ub);
 	ublks_added--;
 }
 
@@ -2205,12 +2167,47 @@ static struct ublk_device *ublk_get_device_from_id(int idx)
 static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 {
 	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
+	const struct ublk_param_basic *p = &ub->params.basic;
 	int ublksrv_pid = (int)header->data[0];
+	struct queue_limits lim = {
+		.logical_block_size	= 1 << p->logical_bs_shift,
+		.physical_block_size	= 1 << p->physical_bs_shift,
+		.io_min			= 1 << p->io_min_shift,
+		.io_opt			= 1 << p->io_opt_shift,
+		.max_hw_sectors		= p->max_sectors,
+		.chunk_sectors		= p->chunk_sectors,
+		.virt_boundary_mask	= p->virt_boundary_mask,
+
+	};
 	struct gendisk *disk;
 	int ret = -EINVAL;
 
 	if (ublksrv_pid <= 0)
 		return -EINVAL;
+	if (!(ub->params.types & UBLK_PARAM_TYPE_BASIC))
+		return -EINVAL;
+
+	if (ub->params.types & UBLK_PARAM_TYPE_DISCARD) {
+		const struct ublk_param_discard *pd = &ub->params.discard;
+
+		lim.discard_alignment = pd->discard_alignment;
+		lim.discard_granularity = pd->discard_granularity;
+		lim.max_hw_discard_sectors = pd->max_discard_sectors;
+		lim.max_write_zeroes_sectors = pd->max_write_zeroes_sectors;
+		lim.max_discard_segments = pd->max_discard_segments;
+	}
+
+	if (ub->params.types & UBLK_PARAM_TYPE_ZONED) {
+		const struct ublk_param_zoned *p = &ub->params.zoned;
+
+		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED))
+			return -EOPNOTSUPP;
+
+		lim.zoned = true;
+		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 (wait_for_completion_interruptible(&ub->completion) != 0)
 		return -EINTR;
@@ -2222,7 +2219,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 		goto out_unlock;
 	}
 
-	disk = blk_mq_alloc_disk(&ub->tag_set, NULL);
+	disk = blk_mq_alloc_disk(&ub->tag_set, &lim, NULL);
 	if (IS_ERR(disk)) {
 		ret = PTR_ERR(disk);
 		goto out_unlock;
@@ -2234,15 +2231,13 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 	ub->dev_info.ublksrv_pid = ublksrv_pid;
 	ub->ub_disk = disk;
 
-	ret = ublk_apply_params(ub);
-	if (ret)
-		goto out_put_disk;
+	ublk_apply_params(ub);
 
 	/* don't probe partitions if any one ubq daemon is un-trusted */
 	if (ub->nr_privileged_daemon != ub->nr_queues_ready)
 		set_bit(GD_SUPPRESS_PART_SCAN, &disk->state);
 
-	get_device(&ub->cdev_dev);
+	ublk_get_device(ub);
 	ub->dev_info.state = UBLK_S_DEV_LIVE;
 
 	if (ublk_dev_is_zoned(ub)) {
@@ -2262,7 +2257,6 @@ out_put_cdev:
 		ub->dev_info.state = UBLK_S_DEV_DEAD;
 		ublk_put_device(ub);
 	}
-out_put_disk:
 	if (ret)
 		put_disk(disk);
 out_unlock:
@@ -2474,7 +2468,7 @@ static inline bool ublk_idr_freed(int id)
 	return ptr == NULL;
 }
 
-static int ublk_ctrl_del_dev(struct ublk_device **p_ub)
+static int ublk_ctrl_del_dev(struct ublk_device **p_ub, bool wait)
 {
 	struct ublk_device *ub = *p_ub;
 	int idx = ub->ub_number;
@@ -2508,7 +2502,7 @@ static int ublk_ctrl_del_dev(struct ublk_device **p_ub)
 	 * - the device number is freed already, we will not find this
 	 *   device via ublk_get_device_from_id()
 	 */
-	if (wait_event_interruptible(ublk_idr_wq, ublk_idr_freed(idx)))
+	if (wait && wait_event_interruptible(ublk_idr_wq, ublk_idr_freed(idx)))
 		return -EINTR;
 	return 0;
 }
@@ -2907,7 +2901,10 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 		ret = ublk_ctrl_add_dev(cmd);
 		break;
 	case UBLK_CMD_DEL_DEV:
-		ret = ublk_ctrl_del_dev(&ub);
+		ret = ublk_ctrl_del_dev(&ub, true);
+		break;
+	case UBLK_U_CMD_DEL_DEV_ASYNC:
+		ret = ublk_ctrl_del_dev(&ub, false);
 		break;
 	case UBLK_CMD_GET_QUEUE_AFFINITY:
 		ret = ublk_ctrl_get_queue_affinity(ub, cmd);

drivers/block/virtio_blk.c

@@ -720,25 +720,24 @@ fail_report:
 	return ret;
 }
 
-static int virtblk_probe_zoned_device(struct virtio_device *vdev,
-				       struct virtio_blk *vblk,
-				       struct request_queue *q)
+static int virtblk_read_zoned_limits(struct virtio_blk *vblk,
+		struct queue_limits *lim)
 {
+	struct virtio_device *vdev = vblk->vdev;
 	u32 v, wg;
 
 	dev_dbg(&vdev->dev, "probing host-managed zoned device\n");
 
-	disk_set_zoned(vblk->disk);
-	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
+	lim->zoned = true;
 
 	virtio_cread(vdev, struct virtio_blk_config,
 		     zoned.max_open_zones, &v);
-	disk_set_max_open_zones(vblk->disk, v);
+	lim->max_open_zones = v;
 	dev_dbg(&vdev->dev, "max open zones = %u\n", v);
 
 	virtio_cread(vdev, struct virtio_blk_config,
 		     zoned.max_active_zones, &v);
-	disk_set_max_active_zones(vblk->disk, v);
+	lim->max_active_zones = v;
 	dev_dbg(&vdev->dev, "max active zones = %u\n", v);
 
 	virtio_cread(vdev, struct virtio_blk_config,
@@ -747,8 +746,8 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev,
 		dev_warn(&vdev->dev, "zero write granularity reported\n");
 		return -ENODEV;
 	}
-	blk_queue_physical_block_size(q, wg);
-	blk_queue_io_min(q, wg);
+	lim->physical_block_size = wg;
+	lim->io_min = wg;
 
 	dev_dbg(&vdev->dev, "write granularity = %u\n", wg);
 
@@ -764,13 +763,13 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev,
 			vblk->zone_sectors);
 		return -ENODEV;
 	}
-	blk_queue_chunk_sectors(q, vblk->zone_sectors);
+	lim->chunk_sectors = vblk->zone_sectors;
 	dev_dbg(&vdev->dev, "zone sectors = %u\n", vblk->zone_sectors);
 
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) {
 		dev_warn(&vblk->vdev->dev,
 			 "ignoring negotiated F_DISCARD for zoned device\n");
-		blk_queue_max_discard_sectors(q, 0);
+		lim->max_hw_discard_sectors = 0;
 	}
 
 	virtio_cread(vdev, struct virtio_blk_config,
@@ -785,25 +784,21 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev,
 			wg, v);
 		return -ENODEV;
 	}
-	blk_queue_max_zone_append_sectors(q, v);
+	lim->max_zone_append_sectors = v;
 	dev_dbg(&vdev->dev, "max append sectors = %u\n", v);
 
-	return blk_revalidate_disk_zones(vblk->disk, NULL);
+	return 0;
 }
-
 #else
-
 /*
- * Zoned block device support is not configured in this kernel.
- * Host-managed zoned devices can't be supported, but others are
- * good to go as regular block devices.
+ * Zoned block device support is not configured in this kernel, host-managed
+ * zoned devices can't be supported.
  */
 #define virtblk_report_zones       NULL
-
-static inline int virtblk_probe_zoned_device(struct virtio_device *vdev,
-			struct virtio_blk *vblk, struct request_queue *q)
+static inline int virtblk_read_zoned_limits(struct virtio_blk *vblk,
+		struct queue_limits *lim)
 {
-	dev_err(&vdev->dev,
+	dev_err(&vblk->vdev->dev,
 		"virtio_blk: zoned devices are not supported");
 	return -EOPNOTSUPP;
 }
@@ -1248,31 +1243,17 @@ static const struct blk_mq_ops virtio_mq_ops = {
 static unsigned int virtblk_queue_depth;
 module_param_named(queue_depth, virtblk_queue_depth, uint, 0444);
 
-static int virtblk_probe(struct virtio_device *vdev)
+static int virtblk_read_limits(struct virtio_blk *vblk,
+		struct queue_limits *lim)
 {
-	struct virtio_blk *vblk;
-	struct request_queue *q;
-	int err, index;
-
+	struct virtio_device *vdev = vblk->vdev;
 	u32 v, blk_size, max_size, sg_elems, opt_io_size;
 	u32 max_discard_segs = 0;
 	u32 discard_granularity = 0;
 	u16 min_io_size;
 	u8 physical_block_exp, alignment_offset;
-	unsigned int queue_depth;
 	size_t max_dma_size;
-
-	if (!vdev->config->get) {
-		dev_err(&vdev->dev, "%s failure: config access disabled\n",
-			__func__);
-		return -EINVAL;
-	}
-
-	err = ida_alloc_range(&vd_index_ida, 0,
-			      minor_to_index(1 << MINORBITS) - 1, GFP_KERNEL);
-	if (err < 0)
-		goto out;
-	index = err;
+	int err;
 
 	/* We need to know how many segments before we allocate. */
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_SEG_MAX,
@@ -1286,6 +1267,203 @@ static int virtblk_probe(struct virtio_device *vdev)
 	/* Prevent integer overflows and honor max vq size */
 	sg_elems = min_t(u32, sg_elems, VIRTIO_BLK_MAX_SG_ELEMS - 2);
 
+	/* We can handle whatever the host told us to handle. */
+	lim->max_segments = sg_elems;
+
+	/* No real sector limit. */
+	lim->max_hw_sectors = UINT_MAX;
+
+	max_dma_size = virtio_max_dma_size(vdev);
+	max_size = max_dma_size > U32_MAX ? U32_MAX : max_dma_size;
+
+	/* Host can optionally specify maximum segment size and number of
+	 * segments. */
+	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_SIZE_MAX,
+				   struct virtio_blk_config, size_max, &v);
+	if (!err)
+		max_size = min(max_size, v);
+
+	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,
+				   struct virtio_blk_config, blk_size,
+				   &blk_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);
+
+	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;
+
+	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;
+
+	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;
+
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) {
+		virtio_cread(vdev, struct virtio_blk_config,
+			     discard_sector_alignment, &discard_granularity);
+
+		virtio_cread(vdev, struct virtio_blk_config,
+			     max_discard_sectors, &v);
+		lim->max_hw_discard_sectors = v ? v : UINT_MAX;
+
+		virtio_cread(vdev, struct virtio_blk_config, max_discard_seg,
+			     &max_discard_segs);
+	}
+
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) {
+		virtio_cread(vdev, struct virtio_blk_config,
+			     max_write_zeroes_sectors, &v);
+		lim->max_write_zeroes_sectors = v ? v : UINT_MAX;
+	}
+
+	/* The discard and secure erase limits are combined since the Linux
+	 * block layer uses the same limit for both commands.
+	 *
+	 * If both VIRTIO_BLK_F_SECURE_ERASE and VIRTIO_BLK_F_DISCARD features
+	 * are negotiated, we will use the minimum between the limits.
+	 *
+	 * discard sector alignment is set to the minimum between discard_sector_alignment
+	 * and secure_erase_sector_alignment.
+	 *
+	 * max discard sectors is set to the minimum between max_discard_seg and
+	 * max_secure_erase_seg.
+	 */
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_SECURE_ERASE)) {
+
+		virtio_cread(vdev, struct virtio_blk_config,
+			     secure_erase_sector_alignment, &v);
+
+		/* secure_erase_sector_alignment should not be zero, the device should set a
+		 * valid number of sectors.
+		 */
+		if (!v) {
+			dev_err(&vdev->dev,
+				"virtio_blk: secure_erase_sector_alignment can't be 0\n");
+			return -EINVAL;
+		}
+
+		discard_granularity = min_not_zero(discard_granularity, v);
+
+		virtio_cread(vdev, struct virtio_blk_config,
+			     max_secure_erase_sectors, &v);
+
+		/* max_secure_erase_sectors should not be zero, the device should set a
+		 * valid number of sectors.
+		 */
+		if (!v) {
+			dev_err(&vdev->dev,
+				"virtio_blk: max_secure_erase_sectors can't be 0\n");
+			return -EINVAL;
+		}
+
+		lim->max_secure_erase_sectors = v;
+
+		virtio_cread(vdev, struct virtio_blk_config,
+			     max_secure_erase_seg, &v);
+
+		/* max_secure_erase_seg should not be zero, the device should set a
+		 * valid number of segments
+		 */
+		if (!v) {
+			dev_err(&vdev->dev,
+				"virtio_blk: max_secure_erase_seg can't be 0\n");
+			return -EINVAL;
+		}
+
+		max_discard_segs = min_not_zero(max_discard_segs, v);
+	}
+
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD) ||
+	    virtio_has_feature(vdev, VIRTIO_BLK_F_SECURE_ERASE)) {
+		/* max_discard_seg and discard_granularity will be 0 only
+		 * if max_discard_seg and discard_sector_alignment fields in the virtio
+		 * config are 0 and VIRTIO_BLK_F_SECURE_ERASE feature is not negotiated.
+		 * In this case, we use default values.
+		 */
+		if (!max_discard_segs)
+			max_discard_segs = sg_elems;
+
+		lim->max_discard_segments =
+			min(max_discard_segs, MAX_DISCARD_SEGMENTS);
+
+		if (discard_granularity)
+			lim->discard_granularity =
+				discard_granularity << SECTOR_SHIFT;
+		else
+			lim->discard_granularity = blk_size;
+	}
+
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_ZONED)) {
+		u8 model;
+
+		virtio_cread(vdev, struct virtio_blk_config, zoned.model, &model);
+		switch (model) {
+		case VIRTIO_BLK_Z_NONE:
+		case VIRTIO_BLK_Z_HA:
+			/* treat host-aware devices as non-zoned */
+			return 0;
+		case VIRTIO_BLK_Z_HM:
+			err = virtblk_read_zoned_limits(vblk, lim);
+			if (err)
+				return err;
+			break;
+		default:
+			dev_err(&vdev->dev, "unsupported zone model %d\n", model);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int virtblk_probe(struct virtio_device *vdev)
+{
+	struct virtio_blk *vblk;
+	struct queue_limits lim = { };
+	int err, index;
+	unsigned int queue_depth;
+
+	if (!vdev->config->get) {
+		dev_err(&vdev->dev, "%s failure: config access disabled\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	err = ida_alloc_range(&vd_index_ida, 0,
+			      minor_to_index(1 << MINORBITS) - 1, GFP_KERNEL);
+	if (err < 0)
+		goto out;
+	index = err;
+
 	vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);
 	if (!vblk) {
 		err = -ENOMEM;
@@ -1330,12 +1508,15 @@ static int virtblk_probe(struct virtio_device *vdev)
 	if (err)
 		goto out_free_vq;
 
-	vblk->disk = blk_mq_alloc_disk(&vblk->tag_set, vblk);
+	err = virtblk_read_limits(vblk, &lim);
+	if (err)
+		goto out_free_tags;
+
+	vblk->disk = blk_mq_alloc_disk(&vblk->tag_set, &lim, vblk);
 	if (IS_ERR(vblk->disk)) {
 		err = PTR_ERR(vblk->disk);
 		goto out_free_tags;
 	}
-	q = vblk->disk->queue;
 
 	virtblk_name_format("vd", index, vblk->disk->disk_name, DISK_NAME_LEN);
 
@@ -1353,164 +1534,6 @@ static int virtblk_probe(struct virtio_device *vdev)
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
 		set_disk_ro(vblk->disk, 1);
 
-	/* We can handle whatever the host told us to handle. */
-	blk_queue_max_segments(q, sg_elems);
-
-	/* No real sector limit. */
-	blk_queue_max_hw_sectors(q, UINT_MAX);
-
-	max_dma_size = virtio_max_dma_size(vdev);
-	max_size = max_dma_size > U32_MAX ? U32_MAX : max_dma_size;
-
-	/* Host can optionally specify maximum segment size and number of
-	 * segments. */
-	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_SIZE_MAX,
-				   struct virtio_blk_config, size_max, &v);
-	if (!err)
-		max_size = min(max_size, v);
-
-	blk_queue_max_segment_size(q, max_size);
-
-	/* Host can optionally specify the block size of the device */
-	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_BLK_SIZE,
-				   struct virtio_blk_config, blk_size,
-				   &blk_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);
-			goto out_cleanup_disk;
-		}
-
-		blk_queue_logical_block_size(q, blk_size);
-	} else
-		blk_size = queue_logical_block_size(q);
-
-	/* 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)
-		blk_queue_physical_block_size(q,
-				blk_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)
-		blk_queue_alignment_offset(q, blk_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)
-		blk_queue_io_min(q, blk_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)
-		blk_queue_io_opt(q, blk_size * opt_io_size);
-
-	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) {
-		virtio_cread(vdev, struct virtio_blk_config,
-			     discard_sector_alignment, &discard_granularity);
-
-		virtio_cread(vdev, struct virtio_blk_config,
-			     max_discard_sectors, &v);
-		blk_queue_max_discard_sectors(q, v ? v : UINT_MAX);
-
-		virtio_cread(vdev, struct virtio_blk_config, max_discard_seg,
-			     &max_discard_segs);
-	}
-
-	if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) {
-		virtio_cread(vdev, struct virtio_blk_config,
-			     max_write_zeroes_sectors, &v);
-		blk_queue_max_write_zeroes_sectors(q, v ? v : UINT_MAX);
-	}
-
-	/* The discard and secure erase limits are combined since the Linux
-	 * block layer uses the same limit for both commands.
-	 *
-	 * If both VIRTIO_BLK_F_SECURE_ERASE and VIRTIO_BLK_F_DISCARD features
-	 * are negotiated, we will use the minimum between the limits.
-	 *
-	 * discard sector alignment is set to the minimum between discard_sector_alignment
-	 * and secure_erase_sector_alignment.
-	 *
-	 * max discard sectors is set to the minimum between max_discard_seg and
-	 * max_secure_erase_seg.
-	 */
-	if (virtio_has_feature(vdev, VIRTIO_BLK_F_SECURE_ERASE)) {
-
-		virtio_cread(vdev, struct virtio_blk_config,
-			     secure_erase_sector_alignment, &v);
-
-		/* secure_erase_sector_alignment should not be zero, the device should set a
-		 * valid number of sectors.
-		 */
-		if (!v) {
-			dev_err(&vdev->dev,
-				"virtio_blk: secure_erase_sector_alignment can't be 0\n");
-			err = -EINVAL;
-			goto out_cleanup_disk;
-		}
-
-		discard_granularity = min_not_zero(discard_granularity, v);
-
-		virtio_cread(vdev, struct virtio_blk_config,
-			     max_secure_erase_sectors, &v);
-
-		/* max_secure_erase_sectors should not be zero, the device should set a
-		 * valid number of sectors.
-		 */
-		if (!v) {
-			dev_err(&vdev->dev,
-				"virtio_blk: max_secure_erase_sectors can't be 0\n");
-			err = -EINVAL;
-			goto out_cleanup_disk;
-		}
-
-		blk_queue_max_secure_erase_sectors(q, v);
-
-		virtio_cread(vdev, struct virtio_blk_config,
-			     max_secure_erase_seg, &v);
-
-		/* max_secure_erase_seg should not be zero, the device should set a
-		 * valid number of segments
-		 */
-		if (!v) {
-			dev_err(&vdev->dev,
-				"virtio_blk: max_secure_erase_seg can't be 0\n");
-			err = -EINVAL;
-			goto out_cleanup_disk;
-		}
-
-		max_discard_segs = min_not_zero(max_discard_segs, v);
-	}
-
-	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD) ||
-	    virtio_has_feature(vdev, VIRTIO_BLK_F_SECURE_ERASE)) {
-		/* max_discard_seg and discard_granularity will be 0 only
-		 * if max_discard_seg and discard_sector_alignment fields in the virtio
-		 * config are 0 and VIRTIO_BLK_F_SECURE_ERASE feature is not negotiated.
-		 * In this case, we use default values.
-		 */
-		if (!max_discard_segs)
-			max_discard_segs = sg_elems;
-
-		blk_queue_max_discard_segments(q,
-					       min(max_discard_segs, MAX_DISCARD_SEGMENTS));
-
-		if (discard_granularity)
-			q->limits.discard_granularity = discard_granularity << SECTOR_SHIFT;
-		else
-			q->limits.discard_granularity = blk_size;
-	}
-
 	virtblk_update_capacity(vblk, false);
 	virtio_device_ready(vdev);
 
@@ -1518,27 +1541,11 @@ 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 (virtio_has_feature(vdev, VIRTIO_BLK_F_ZONED)) {
-		u8 model;
-
-		virtio_cread(vdev, struct virtio_blk_config, zoned.model,
-				&model);
-		switch (model) {
-		case VIRTIO_BLK_Z_NONE:
-		case VIRTIO_BLK_Z_HA:
-			/* Present the host-aware device as non-zoned */
-			break;
-		case VIRTIO_BLK_Z_HM:
-			err = virtblk_probe_zoned_device(vdev, vblk, q);
-			if (err)
-				goto out_cleanup_disk;
-			break;
-		default:
-			dev_err(&vdev->dev, "unsupported zone model %d\n",
-				model);
-			err = -EINVAL;
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && lim.zoned) {
+		blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, vblk->disk->queue);
+		err = blk_revalidate_disk_zones(vblk->disk, NULL);
+		if (err)
 			goto out_cleanup_disk;
-		}
 	}
 
 	err = device_add_disk(&vdev->dev, vblk->disk, virtblk_attr_groups);

drivers/block/xen-blkfront.c

@@ -941,39 +941,35 @@ static const struct blk_mq_ops blkfront_mq_ops = {
 	.complete = blkif_complete_rq,
 };
 
-static void blkif_set_queue_limits(struct blkfront_info *info)
+static void blkif_set_queue_limits(const struct blkfront_info *info,
+		struct queue_limits *lim)
 {
-	struct request_queue *rq = info->rq;
-	struct gendisk *gd = info->gd;
 	unsigned int segments = info->max_indirect_segments ? :
 				BLKIF_MAX_SEGMENTS_PER_REQUEST;
 
-	blk_queue_flag_set(QUEUE_FLAG_VIRT, rq);
-
 	if (info->feature_discard) {
-		blk_queue_max_discard_sectors(rq, get_capacity(gd));
-		rq->limits.discard_granularity = info->discard_granularity ?:
-						 info->physical_sector_size;
-		rq->limits.discard_alignment = info->discard_alignment;
+		lim->max_hw_discard_sectors = UINT_MAX;
+		if (info->discard_granularity)
+			lim->discard_granularity = info->discard_granularity;
+		lim->discard_alignment = info->discard_alignment;
 		if (info->feature_secdiscard)
-			blk_queue_max_secure_erase_sectors(rq,
-							   get_capacity(gd));
+			lim->max_secure_erase_sectors = UINT_MAX;
 	}
 
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
-	blk_queue_logical_block_size(rq, info->sector_size);
-	blk_queue_physical_block_size(rq, info->physical_sector_size);
-	blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
+	lim->logical_block_size = info->sector_size;
+	lim->physical_block_size = info->physical_sector_size;
+	lim->max_hw_sectors = (segments * XEN_PAGE_SIZE) / 512;
 
 	/* Each segment in a request is up to an aligned page in size. */
-	blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
-	blk_queue_max_segment_size(rq, PAGE_SIZE);
+	lim->seg_boundary_mask = PAGE_SIZE - 1;
+	lim->max_segment_size = PAGE_SIZE;
 
 	/* Ensure a merged request will fit in a single I/O ring slot. */
-	blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
+	lim->max_segments = segments / GRANTS_PER_PSEG;
 
 	/* Make sure buffer addresses are sector-aligned. */
-	blk_queue_dma_alignment(rq, 511);
+	lim->dma_alignment = 511;
 }
 
 static const char *flush_info(struct blkfront_info *info)
@@ -1070,6 +1066,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 		struct blkfront_info *info, u16 sector_size,
 		unsigned int physical_sector_size)
 {
+	struct queue_limits lim = {};
 	struct gendisk *gd;
 	int nr_minors = 1;
 	int err;
@@ -1136,11 +1133,13 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	if (err)
 		goto out_release_minors;
 
-	gd = blk_mq_alloc_disk(&info->tag_set, info);
+	blkif_set_queue_limits(info, &lim);
+	gd = blk_mq_alloc_disk(&info->tag_set, &lim, info);
 	if (IS_ERR(gd)) {
 		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);
@@ -1162,7 +1161,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	info->gd = gd;
 	info->sector_size = sector_size;
 	info->physical_sector_size = physical_sector_size;
-	blkif_set_queue_limits(info);
 
 	xlvbd_flush(info);
 
@@ -2006,18 +2004,19 @@ static int blkfront_probe(struct xenbus_device *dev,
 
 static int blkif_recover(struct blkfront_info *info)
 {
+	struct queue_limits lim;
 	unsigned int r_index;
 	struct request *req, *n;
 	int rc;
 	struct bio *bio;
-	unsigned int segs;
 	struct blkfront_ring_info *rinfo;
 
+	lim = queue_limits_start_update(info->rq);
 	blkfront_gather_backend_features(info);
-	/* Reset limits changed by blk_mq_update_nr_hw_queues(). */
-	blkif_set_queue_limits(info);
-	segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
-	blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG);
+	blkif_set_queue_limits(info, &lim);
+	rc = queue_limits_commit_update(info->rq, &lim);
+	if (rc)
+		return rc;
 
 	for_each_rinfo(info, rinfo, r_index) {
 		rc = blkfront_setup_indirect(rinfo);
@@ -2037,7 +2036,9 @@ static int blkif_recover(struct blkfront_info *info)
 	list_for_each_entry_safe(req, n, &info->requests, queuelist) {
 		/* Requeue pending requests (flush or discard) */
 		list_del_init(&req->queuelist);
-		BUG_ON(req->nr_phys_segments > segs);
+		BUG_ON(req->nr_phys_segments >
+		       (info->max_indirect_segments ? :
+			BLKIF_MAX_SEGMENTS_PER_REQUEST));
 		blk_mq_requeue_request(req, false);
 	}
 	blk_mq_start_stopped_hw_queues(info->rq, true);

drivers/block/z2ram.c

@@ -318,7 +318,7 @@ static int z2ram_register_disk(int minor)
 	struct gendisk *disk;
 	int err;
 
-	disk = blk_mq_alloc_disk(&tag_set, NULL);
+	disk = blk_mq_alloc_disk(&tag_set, NULL, NULL);
 	if (IS_ERR(disk))
 		return PTR_ERR(disk);
 

drivers/block/zram/zram_drv.c

@@ -2177,6 +2177,28 @@ ATTRIBUTE_GROUPS(zram_disk);
  */
 static int zram_add(void)
 {
+	struct queue_limits lim = {
+		.logical_block_size		= ZRAM_LOGICAL_BLOCK_SIZE,
+		/*
+		 * To ensure that we always get PAGE_SIZE aligned and
+		 * n*PAGE_SIZED sized I/O requests.
+		 */
+		.physical_block_size		= PAGE_SIZE,
+		.io_min				= PAGE_SIZE,
+		.io_opt				= PAGE_SIZE,
+		.max_hw_discard_sectors		= UINT_MAX,
+		/*
+		 * zram_bio_discard() will clear all logical blocks if logical
+		 * block size is identical with physical block size(PAGE_SIZE).
+		 * But if it is different, we will skip discarding some parts of
+		 * logical blocks in the part of the request range which isn't
+		 * aligned to physical block size.  So we can't ensure that all
+		 * discarded logical blocks are zeroed.
+		 */
+#if ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE
+		.max_write_zeroes_sectors	= UINT_MAX,
+#endif
+	};
 	struct zram *zram;
 	int ret, device_id;
 
@@ -2195,11 +2217,11 @@ static int zram_add(void)
 #endif
 
 	/* gendisk structure */
-	zram->disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!zram->disk) {
+	zram->disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(zram->disk)) {
 		pr_err("Error allocating disk structure for device %d\n",
 			device_id);
-		ret = -ENOMEM;
+		ret = PTR_ERR(zram->disk);
 		goto out_free_idr;
 	}
 
@@ -2216,29 +2238,6 @@ static int zram_add(void)
 	/* 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);
-
-	/*
-	 * To ensure that we always get PAGE_SIZE aligned
-	 * and n*PAGE_SIZED sized I/O requests.
-	 */
-	blk_queue_physical_block_size(zram->disk->queue, PAGE_SIZE);
-	blk_queue_logical_block_size(zram->disk->queue,
-					ZRAM_LOGICAL_BLOCK_SIZE);
-	blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
-	blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
-	blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
-
-	/*
-	 * zram_bio_discard() will clear all logical blocks if logical block
-	 * size is identical with physical block size(PAGE_SIZE). But if it is
-	 * different, we will skip discarding some parts of logical blocks in
-	 * the part of the request range which isn't aligned to physical block
-	 * size.  So we can't ensure that all discarded logical blocks are
-	 * zeroed.
-	 */
-	if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
-		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
-
 	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue);
 	ret = device_add_disk(NULL, zram->disk, zram_disk_groups);
 	if (ret)

drivers/cdrom/gdrom.c

@@ -724,11 +724,6 @@ static void probe_gdrom_setupdisk(void)
 
 static int probe_gdrom_setupqueue(void)
 {
-	blk_queue_logical_block_size(gd.gdrom_rq, GDROM_HARD_SECTOR);
-	/* using DMA so memory will need to be contiguous */
-	blk_queue_max_segments(gd.gdrom_rq, 1);
-	/* set a large max size to get most from DMA */
-	blk_queue_max_segment_size(gd.gdrom_rq, 0x40000);
 	gd.disk->queue = gd.gdrom_rq;
 	return gdrom_init_dma_mode();
 }
@@ -743,6 +738,13 @@ static const struct blk_mq_ops gdrom_mq_ops = {
  */
 static int probe_gdrom(struct platform_device *devptr)
 {
+	struct queue_limits lim = {
+		.logical_block_size		= GDROM_HARD_SECTOR,
+		/* using DMA so memory will need to be contiguous */
+		.max_segments			= 1,
+		/* set a large max size to get most from DMA */
+		.max_segment_size		= 0x40000,
+	};
 	int err;
 
 	/*
@@ -778,7 +780,7 @@ static int probe_gdrom(struct platform_device *devptr)
 	if (err)
 		goto probe_fail_free_cd_info;
 
-	gd.disk = blk_mq_alloc_disk(&gd.tag_set, NULL);
+	gd.disk = blk_mq_alloc_disk(&gd.tag_set, &lim, NULL);
 	if (IS_ERR(gd.disk)) {
 		err = PTR_ERR(gd.disk);
 		goto probe_fail_free_tag_set;
@@ -829,7 +831,7 @@ probe_fail_no_mem:
 	return err;
 }
 
-static int remove_gdrom(struct platform_device *devptr)
+static void remove_gdrom(struct platform_device *devptr)
 {
 	blk_mq_free_tag_set(&gd.tag_set);
 	free_irq(HW_EVENT_GDROM_CMD, &gd);
@@ -840,13 +842,11 @@ static int remove_gdrom(struct platform_device *devptr)
 	unregister_cdrom(gd.cd_info);
 	kfree(gd.cd_info);
 	kfree(gd.toc);
-
-	return 0;
 }
 
 static struct platform_driver gdrom_driver = {
 	.probe = probe_gdrom,
-	.remove = remove_gdrom,
+	.remove_new = remove_gdrom,
 	.driver = {
 			.name = GDROM_DEV_NAME,
 	},

drivers/md/bcache/super.c

@@ -900,9 +900,23 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	struct request_queue *q;
 	const size_t max_stripes = min_t(size_t, INT_MAX,
 					 SIZE_MAX / sizeof(atomic_t));
+	struct queue_limits lim = {
+		.max_hw_sectors		= UINT_MAX,
+		.max_sectors		= UINT_MAX,
+		.max_segment_size	= UINT_MAX,
+		.max_segments		= BIO_MAX_VECS,
+		.max_hw_discard_sectors	= UINT_MAX,
+		.io_min			= block_size,
+		.logical_block_size	= block_size,
+		.physical_block_size	= block_size,
+	};
 	uint64_t n;
 	int idx;
 
+	if (cached_bdev) {
+		d->stripe_size = bdev_io_opt(cached_bdev) >> SECTOR_SHIFT;
+		lim.io_opt = umax(block_size, bdev_io_opt(cached_bdev));
+	}
 	if (!d->stripe_size)
 		d->stripe_size = 1 << 31;
 	else if (d->stripe_size < BCH_MIN_STRIPE_SZ)
@@ -935,8 +949,21 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
 		goto out_ida_remove;
 
-	d->disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!d->disk)
+	if (lim.logical_block_size > PAGE_SIZE && cached_bdev) {
+		/*
+		 * This should only happen with BCACHE_SB_VERSION_BDEV.
+		 * Block/page size is checked for BCACHE_SB_VERSION_CDEV.
+		 */
+		pr_info("bcache%i: sb/logical block size (%u) greater than page size (%lu) falling back to device logical block size (%u)\n",
+			idx, lim.logical_block_size,
+			PAGE_SIZE, bdev_logical_block_size(cached_bdev));
+
+		/* This also adjusts physical block size/min io size if needed */
+		lim.logical_block_size = bdev_logical_block_size(cached_bdev);
+	}
+
+	d->disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(d->disk))
 		goto out_bioset_exit;
 
 	set_capacity(d->disk, sectors);
@@ -949,27 +976,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	d->disk->private_data	= d;
 
 	q = d->disk->queue;
-	q->limits.max_hw_sectors	= UINT_MAX;
-	q->limits.max_sectors		= UINT_MAX;
-	q->limits.max_segment_size	= UINT_MAX;
-	q->limits.max_segments		= BIO_MAX_VECS;
-	blk_queue_max_discard_sectors(q, UINT_MAX);
-	q->limits.io_min		= block_size;
-	q->limits.logical_block_size	= block_size;
-	q->limits.physical_block_size	= block_size;
-
-	if (q->limits.logical_block_size > PAGE_SIZE && cached_bdev) {
-		/*
-		 * This should only happen with BCACHE_SB_VERSION_BDEV.
-		 * Block/page size is checked for BCACHE_SB_VERSION_CDEV.
-		 */
-		pr_info("%s: sb/logical block size (%u) greater than page size (%lu) falling back to device logical block size (%u)\n",
-			d->disk->disk_name, q->limits.logical_block_size,
-			PAGE_SIZE, bdev_logical_block_size(cached_bdev));
-
-		/* This also adjusts physical block size/min io size if needed */
-		blk_queue_logical_block_size(q, bdev_logical_block_size(cached_bdev));
-	}
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, d->disk->queue);
 
@@ -1416,9 +1422,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 		hlist_add_head(&io->hash, dc->io_hash + RECENT_IO);
 	}
 
-	dc->disk.stripe_size = q->limits.io_opt >> 9;
-
-	if (dc->disk.stripe_size)
+	if (bdev_io_opt(dc->bdev))
 		dc->partial_stripes_expensive =
 			q->limits.raid_partial_stripes_expensive;
 
@@ -1428,9 +1432,6 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 	if (ret)
 		return ret;
 
-	blk_queue_io_opt(dc->disk.disk->queue,
-		max(queue_io_opt(dc->disk.disk->queue), queue_io_opt(q)));
-
 	atomic_set(&dc->io_errors, 0);
 	dc->io_disable = false;
 	dc->error_limit = DEFAULT_CACHED_DEV_ERROR_LIMIT;

drivers/md/dm-raid.c

@@ -213,6 +213,7 @@ struct raid_dev {
 #define RT_FLAG_RS_IN_SYNC		6
 #define RT_FLAG_RS_RESYNCING		7
 #define RT_FLAG_RS_GROW			8
+#define RT_FLAG_RS_FROZEN		9
 
 /* Array elements of 64 bit needed for rebuild/failed disk bits */
 #define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8)
@@ -3240,11 +3241,12 @@ size_check:
 	rs->md.ro = 1;
 	rs->md.in_sync = 1;
 
-	/* Keep array frozen until resume. */
-	set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
-
 	/* Has to be held on running the array */
 	mddev_suspend_and_lock_nointr(&rs->md);
+
+	/* Keep array frozen until resume. */
+	md_frozen_sync_thread(&rs->md);
+
 	r = md_run(&rs->md);
 	rs->md.in_sync = 0; /* Assume already marked dirty */
 	if (r) {
@@ -3339,7 +3341,8 @@ static int raid_map(struct dm_target *ti, struct bio *bio)
 	if (unlikely(bio_end_sector(bio) > mddev->array_sectors))
 		return DM_MAPIO_REQUEUE;
 
-	md_handle_request(mddev, bio);
+	if (unlikely(!md_handle_request(mddev, bio)))
+		return DM_MAPIO_REQUEUE;
 
 	return DM_MAPIO_SUBMITTED;
 }
@@ -3718,21 +3721,33 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
 {
 	struct raid_set *rs = ti->private;
 	struct mddev *mddev = &rs->md;
+	int ret = 0;
 
 	if (!mddev->pers || !mddev->pers->sync_request)
 		return -EINVAL;
 
-	if (!strcasecmp(argv[0], "frozen"))
-		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	else
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	if (test_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags) ||
+	    test_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags))
+		return -EBUSY;
 
-	if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) {
-		if (mddev->sync_thread) {
-			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			md_reap_sync_thread(mddev);
-		}
-	} else if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
+	if (!strcasecmp(argv[0], "frozen")) {
+		ret = mddev_lock(mddev);
+		if (ret)
+			return ret;
+
+		md_frozen_sync_thread(mddev);
+		mddev_unlock(mddev);
+	} else if (!strcasecmp(argv[0], "idle")) {
+		ret = mddev_lock(mddev);
+		if (ret)
+			return ret;
+
+		md_idle_sync_thread(mddev);
+		mddev_unlock(mddev);
+	}
+
+	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
 		return -EBUSY;
 	else if (!strcasecmp(argv[0], "resync"))
 		; /* MD_RECOVERY_NEEDED set below */
@@ -3791,15 +3806,46 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs));
 }
 
+static void raid_presuspend(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+	struct mddev *mddev = &rs->md;
+
+	/*
+	 * From now on, disallow raid_message() to change sync_thread until
+	 * resume, raid_postsuspend() is too late.
+	 */
+	set_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
+
+	if (!reshape_interrupted(mddev))
+		return;
+
+	/*
+	 * For raid456, if reshape is interrupted, IO across reshape position
+	 * will never make progress, while caller will wait for IO to be done.
+	 * Inform raid456 to handle those IO to prevent deadlock.
+	 */
+	if (mddev->pers && mddev->pers->prepare_suspend)
+		mddev->pers->prepare_suspend(mddev);
+}
+
+static void raid_presuspend_undo(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+
+	clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
+}
+
 static void raid_postsuspend(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
 
 	if (!test_and_set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) {
-		/* Writes have to be stopped before suspending to avoid deadlocks. */
-		if (!test_bit(MD_RECOVERY_FROZEN, &rs->md.recovery))
-			md_stop_writes(&rs->md);
-
+		/*
+		 * sync_thread must be stopped during suspend, and writes have
+		 * to be stopped before suspending to avoid deadlocks.
+		 */
+		md_stop_writes(&rs->md);
 		mddev_suspend(&rs->md, false);
 	}
 }
@@ -4012,8 +4058,6 @@ static int raid_preresume(struct dm_target *ti)
 	}
 
 	/* Check for any resize/reshape on @rs and adjust/initiate */
-	/* Be prepared for mddev_resume() in raid_resume() */
-	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	if (mddev->recovery_cp && mddev->recovery_cp < MaxSector) {
 		set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
 		mddev->resync_min = mddev->recovery_cp;
@@ -4047,7 +4091,9 @@ static void raid_resume(struct dm_target *ti)
 		 * Take this opportunity to check whether any failed
 		 * devices are reachable again.
 		 */
+		mddev_lock_nointr(mddev);
 		attempt_restore_of_faulty_devices(rs);
+		mddev_unlock(mddev);
 	}
 
 	if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) {
@@ -4055,10 +4101,13 @@ static void raid_resume(struct dm_target *ti)
 		if (mddev->delta_disks < 0)
 			rs_set_capacity(rs);
 
+		WARN_ON_ONCE(!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery));
+		WARN_ON_ONCE(test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
+		clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
 		mddev_lock_nointr(mddev);
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		mddev->ro = 0;
 		mddev->in_sync = 0;
+		md_unfrozen_sync_thread(mddev);
 		mddev_unlock_and_resume(mddev);
 	}
 }
@@ -4074,6 +4123,8 @@ static struct target_type raid_target = {
 	.message = raid_message,
 	.iterate_devices = raid_iterate_devices,
 	.io_hints = raid_io_hints,
+	.presuspend = raid_presuspend,
+	.presuspend_undo = raid_presuspend_undo,
 	.postsuspend = raid_postsuspend,
 	.preresume = raid_preresume,
 	.resume = raid_resume,

drivers/md/dm-table.c

@@ -2027,26 +2027,27 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	bool wc = false, fua = false;
 	int r;
 
-	/*
-	 * Copy table's limits to the DM device's request_queue
-	 */
-	q->limits = *limits;
-
 	if (dm_table_supports_nowait(t))
 		blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
 	else
 		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q);
 
 	if (!dm_table_supports_discards(t)) {
-		q->limits.max_discard_sectors = 0;
-		q->limits.max_hw_discard_sectors = 0;
-		q->limits.discard_granularity = 0;
-		q->limits.discard_alignment = 0;
-		q->limits.discard_misaligned = 0;
+		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))
+		limits->max_write_zeroes_sectors = 0;
+
 	if (!dm_table_supports_secure_erase(t))
-		q->limits.max_secure_erase_sectors = 0;
+		limits->max_secure_erase_sectors = 0;
+
+	r = queue_limits_set(q, limits);
+	if (r)
+		return r;
 
 	if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) {
 		wc = true;
@@ -2071,9 +2072,6 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	else
 		blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 
-	if (!dm_table_supports_write_zeroes(t))
-		q->limits.max_write_zeroes_sectors = 0;
-
 	dm_table_verify_integrity(t);
 
 	/*
@@ -2111,7 +2109,6 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	}
 
 	dm_update_crypto_profile(q, t);
-	disk_update_readahead(t->md->disk);
 
 	/*
 	 * Check for request-based device is left to

drivers/md/dm-zoned-metadata.c

@@ -1655,10 +1655,13 @@ static int dmz_reset_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 
 	if (!dmz_is_empty(zone) || dmz_seq_write_err(zone)) {
 		struct dmz_dev *dev = zone->dev;
+		unsigned int noio_flag;
 
+		noio_flag = memalloc_noio_save();
 		ret = blkdev_zone_mgmt(dev->bdev, REQ_OP_ZONE_RESET,
 				       dmz_start_sect(zmd, zone),
-				       zmd->zone_nr_sectors, GFP_NOIO);
+				       zmd->zone_nr_sectors);
+		memalloc_noio_restore(noio_flag);
 		if (ret) {
 			dmz_dev_err(dev, "Reset zone %u failed %d",
 				    zone->id, ret);

drivers/md/dm.c

@@ -2101,8 +2101,8 @@ static struct mapped_device *alloc_dev(int minor)
 	 * established. If request-based table is loaded: blk-mq will
 	 * override accordingly.
 	 */
-	md->disk = blk_alloc_disk(md->numa_node_id);
-	if (!md->disk)
+	md->disk = blk_alloc_disk(NULL, md->numa_node_id);
+	if (IS_ERR(md->disk))
 		goto bad;
 	md->queue = md->disk->queue;
 

drivers/md/md-bitmap.c

@@ -234,7 +234,8 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap,
 	sector_t doff;
 
 	bdev = (rdev->meta_bdev) ? rdev->meta_bdev : rdev->bdev;
-	if (pg_index == store->file_pages - 1) {
+	/* we compare length (page numbers), not page offset. */
+	if ((pg_index - store->sb_index) == store->file_pages - 1) {
 		unsigned int last_page_size = store->bytes & (PAGE_SIZE - 1);
 
 		if (last_page_size == 0)
@@ -438,8 +439,8 @@ static void filemap_write_page(struct bitmap *bitmap, unsigned long pg_index,
 	struct page *page = store->filemap[pg_index];
 
 	if (mddev_is_clustered(bitmap->mddev)) {
-		pg_index += bitmap->cluster_slot *
-			DIV_ROUND_UP(store->bytes, PAGE_SIZE);
+		/* go to node bitmap area starting point */
+		pg_index += store->sb_index;
 	}
 
 	if (store->file)
@@ -952,6 +953,7 @@ static void md_bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 	unsigned long index = file_page_index(store, chunk);
 	unsigned long node_offset = 0;
 
+	index += store->sb_index;
 	if (mddev_is_clustered(bitmap->mddev))
 		node_offset = bitmap->cluster_slot * store->file_pages;
 
@@ -982,6 +984,7 @@ static void md_bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block)
 	unsigned long index = file_page_index(store, chunk);
 	unsigned long node_offset = 0;
 
+	index += store->sb_index;
 	if (mddev_is_clustered(bitmap->mddev))
 		node_offset = bitmap->cluster_slot * store->file_pages;
 
@@ -1043,9 +1046,8 @@ void md_bitmap_unplug(struct bitmap *bitmap)
 		if (dirty || need_write) {
 			if (!writing) {
 				md_bitmap_wait_writes(bitmap);
-				if (bitmap->mddev->queue)
-					blk_add_trace_msg(bitmap->mddev->queue,
-							  "md bitmap_unplug");
+				mddev_add_trace_msg(bitmap->mddev,
+					"md bitmap_unplug");
 			}
 			clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING);
 			filemap_write_page(bitmap, i, false);
@@ -1316,9 +1318,7 @@ void md_bitmap_daemon_work(struct mddev *mddev)
 	}
 	bitmap->allclean = 1;
 
-	if (bitmap->mddev->queue)
-		blk_add_trace_msg(bitmap->mddev->queue,
-				  "md bitmap_daemon_work");
+	mddev_add_trace_msg(bitmap->mddev, "md bitmap_daemon_work");
 
 	/* Any file-page which is PENDING now needs to be written.
 	 * So set NEEDWRITE now, then after we make any last-minute changes

drivers/md/md-linear.h

@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINEAR_H
-#define _LINEAR_H
-
-struct dev_info {
-	struct md_rdev	*rdev;
-	sector_t	end_sector;
-};
-
-struct linear_conf
-{
-	struct rcu_head		rcu;
-	sector_t		array_sectors;
-	int			raid_disks; /* a copy of mddev->raid_disks */
-	struct dev_info		disks[] __counted_by(raid_disks);
-};
-#endif

drivers/md/md-multipath.h

@@ -1,32 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _MULTIPATH_H
-#define _MULTIPATH_H
-
-struct multipath_info {
-	struct md_rdev	*rdev;
-};
-
-struct mpconf {
-	struct mddev			*mddev;
-	struct multipath_info	*multipaths;
-	int			raid_disks;
-	spinlock_t		device_lock;
-	struct list_head	retry_list;
-
-	mempool_t		pool;
-};
-
-/*
- * this is our 'private' 'collective' MULTIPATH buffer head.
- * it contains information about what kind of IO operations were started
- * for this MULTIPATH operation, and about their status:
- */
-
-struct multipath_bh {
-	struct mddev			*mddev;
-	struct bio		*master_bio;
-	struct bio		bio;
-	int			path;
-	struct list_head	retry_list;
-};
-#endif

drivers/md/md.c

@@ -65,7 +65,6 @@
 #include <linux/percpu-refcount.h>
 #include <linux/part_stat.h>
 
-#include <trace/events/block.h>
 #include "md.h"
 #include "md-bitmap.h"
 #include "md-cluster.h"
@@ -99,18 +98,6 @@ static void mddev_detach(struct mddev *mddev);
 static void export_rdev(struct md_rdev *rdev, struct mddev *mddev);
 static void md_wakeup_thread_directly(struct md_thread __rcu *thread);
 
-enum md_ro_state {
-	MD_RDWR,
-	MD_RDONLY,
-	MD_AUTO_READ,
-	MD_MAX_STATE
-};
-
-static bool md_is_rdwr(struct mddev *mddev)
-{
-	return (mddev->ro == MD_RDWR);
-}
-
 /*
  * Default number of read corrections we'll attempt on an rdev
  * before ejecting it from the array. We divide the read error
@@ -378,7 +365,7 @@ static bool is_suspended(struct mddev *mddev, struct bio *bio)
 	return true;
 }
 
-void md_handle_request(struct mddev *mddev, struct bio *bio)
+bool md_handle_request(struct mddev *mddev, struct bio *bio)
 {
 check_suspended:
 	if (is_suspended(mddev, bio)) {
@@ -386,7 +373,7 @@ check_suspended:
 		/* Bail out if REQ_NOWAIT is set for the bio */
 		if (bio->bi_opf & REQ_NOWAIT) {
 			bio_wouldblock_error(bio);
-			return;
+			return true;
 		}
 		for (;;) {
 			prepare_to_wait(&mddev->sb_wait, &__wait,
@@ -402,10 +389,13 @@ check_suspended:
 
 	if (!mddev->pers->make_request(mddev, bio)) {
 		percpu_ref_put(&mddev->active_io);
+		if (!mddev->gendisk && mddev->pers->prepare_suspend)
+			return false;
 		goto check_suspended;
 	}
 
 	percpu_ref_put(&mddev->active_io);
+	return true;
 }
 EXPORT_SYMBOL(md_handle_request);
 
@@ -529,6 +519,24 @@ void mddev_resume(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(mddev_resume);
 
+/* sync bdev before setting device to readonly or stopping raid*/
+static int mddev_set_closing_and_sync_blockdev(struct mddev *mddev, int opener_num)
+{
+	mutex_lock(&mddev->open_mutex);
+	if (mddev->pers && atomic_read(&mddev->openers) > opener_num) {
+		mutex_unlock(&mddev->open_mutex);
+		return -EBUSY;
+	}
+	if (test_and_set_bit(MD_CLOSING, &mddev->flags)) {
+		mutex_unlock(&mddev->open_mutex);
+		return -EBUSY;
+	}
+	mutex_unlock(&mddev->open_mutex);
+
+	sync_blockdev(mddev->gendisk->part0);
+	return 0;
+}
+
 /*
  * Generic flush handling for md
  */
@@ -2406,7 +2414,7 @@ int md_integrity_register(struct mddev *mddev)
 
 	if (list_empty(&mddev->disks))
 		return 0; /* nothing to do */
-	if (!mddev->gendisk || blk_get_integrity(mddev->gendisk))
+	if (mddev_is_dm(mddev) || blk_get_integrity(mddev->gendisk))
 		return 0; /* shouldn't register, or already is */
 	rdev_for_each(rdev, mddev) {
 		/* skip spares and non-functional disks */
@@ -2459,7 +2467,7 @@ int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev)
 {
 	struct blk_integrity *bi_mddev;
 
-	if (!mddev->gendisk)
+	if (mddev_is_dm(mddev))
 		return 0;
 
 	bi_mddev = blk_get_integrity(mddev->gendisk);
@@ -2566,6 +2574,7 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
  fail:
 	pr_warn("md: failed to register dev-%s for %s\n",
 		b, mdname(mddev));
+	mddev_destroy_serial_pool(mddev, rdev);
 	return err;
 }
 
@@ -2595,7 +2604,7 @@ static void md_kick_rdev_from_array(struct md_rdev *rdev)
 	list_del_rcu(&rdev->same_set);
 	pr_debug("md: unbind<%pg>\n", rdev->bdev);
 	mddev_destroy_serial_pool(rdev->mddev, rdev);
-	rdev->mddev = NULL;
+	WRITE_ONCE(rdev->mddev, NULL);
 	sysfs_remove_link(&rdev->kobj, "block");
 	sysfs_put(rdev->sysfs_state);
 	sysfs_put(rdev->sysfs_unack_badblocks);
@@ -2851,8 +2860,7 @@ repeat:
 	pr_debug("md: updating %s RAID superblock on device (in sync %d)\n",
 		 mdname(mddev), mddev->in_sync);
 
-	if (mddev->queue)
-		blk_add_trace_msg(mddev->queue, "md md_update_sb");
+	mddev_add_trace_msg(mddev, "md md_update_sb");
 rewrite:
 	md_bitmap_update_sb(mddev->bitmap);
 	rdev_for_each(rdev, mddev) {
@@ -2933,7 +2941,6 @@ static int add_bound_rdev(struct md_rdev *rdev)
 		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_new_event();
-	md_wakeup_thread(mddev->thread);
 	return 0;
 }
 
@@ -3048,10 +3055,8 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 
 			if (err == 0) {
 				md_kick_rdev_from_array(rdev);
-				if (mddev->pers) {
+				if (mddev->pers)
 					set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
-					md_wakeup_thread(mddev->thread);
-				}
 				md_new_event();
 			}
 		}
@@ -3081,7 +3086,6 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 		clear_bit(BlockedBadBlocks, &rdev->flags);
 		wake_up(&rdev->blocked_wait);
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
-		md_wakeup_thread(rdev->mddev->thread);
 
 		err = 0;
 	} else if (cmd_match(buf, "insync") && rdev->raid_disk == -1) {
@@ -3119,7 +3123,6 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 		    !test_bit(Replacement, &rdev->flags))
 			set_bit(WantReplacement, &rdev->flags);
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
-		md_wakeup_thread(rdev->mddev->thread);
 		err = 0;
 	} else if (cmd_match(buf, "-want_replacement")) {
 		/* Clearing 'want_replacement' is always allowed.
@@ -3249,7 +3252,6 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len)
 		if (rdev->raid_disk >= 0)
 			return -EBUSY;
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
-		md_wakeup_thread(rdev->mddev->thread);
 	} else if (rdev->mddev->pers) {
 		/* Activating a spare .. or possibly reactivating
 		 * if we ever get bitmaps working here.
@@ -3343,8 +3345,7 @@ static ssize_t new_offset_store(struct md_rdev *rdev,
 	if (kstrtoull(buf, 10, &new_offset) < 0)
 		return -EINVAL;
 
-	if (mddev->sync_thread ||
-	    test_bit(MD_RECOVERY_RUNNING,&mddev->recovery))
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
 		return -EBUSY;
 	if (new_offset == rdev->data_offset)
 		/* reset is always permitted */
@@ -3675,7 +3676,7 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr,
 	struct kernfs_node *kn = NULL;
 	bool suspend = false;
 	ssize_t rv;
-	struct mddev *mddev = rdev->mddev;
+	struct mddev *mddev = READ_ONCE(rdev->mddev);
 
 	if (!entry->store)
 		return -EIO;
@@ -4017,8 +4018,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	 */
 
 	rv = -EBUSY;
-	if (mddev->sync_thread ||
-	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
 	    mddev->reshape_position != MaxSector ||
 	    mddev->sysfs_active)
 		goto out_unlock;
@@ -4168,7 +4168,6 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 		mddev->in_sync = 1;
 		del_timer_sync(&mddev->safemode_timer);
 	}
-	blk_set_stacking_limits(&mddev->queue->limits);
 	pers->run(mddev);
 	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 	if (!mddev->thread)
@@ -4475,8 +4474,8 @@ array_state_show(struct mddev *mddev, char *page)
 	return sprintf(page, "%s\n", array_states[st]);
 }
 
-static int do_md_stop(struct mddev *mddev, int ro, struct block_device *bdev);
-static int md_set_readonly(struct mddev *mddev, struct block_device *bdev);
+static int do_md_stop(struct mddev *mddev, int ro);
+static int md_set_readonly(struct mddev *mddev);
 static int restart_array(struct mddev *mddev);
 
 static ssize_t
@@ -4493,6 +4492,17 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	case broken:		/* cannot be set */
 	case bad_word:
 		return -EINVAL;
+	case clear:
+	case readonly:
+	case inactive:
+	case read_auto:
+		if (!mddev->pers || !md_is_rdwr(mddev))
+			break;
+		/* write sysfs will not open mddev and opener should be 0 */
+		err = mddev_set_closing_and_sync_blockdev(mddev, 0);
+		if (err)
+			return err;
+		break;
 	default:
 		break;
 	}
@@ -4526,14 +4536,14 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	case inactive:
 		/* stop an active array, return 0 otherwise */
 		if (mddev->pers)
-			err = do_md_stop(mddev, 2, NULL);
+			err = do_md_stop(mddev, 2);
 		break;
 	case clear:
-		err = do_md_stop(mddev, 0, NULL);
+		err = do_md_stop(mddev, 0);
 		break;
 	case readonly:
 		if (mddev->pers)
-			err = md_set_readonly(mddev, NULL);
+			err = md_set_readonly(mddev);
 		else {
 			mddev->ro = MD_RDONLY;
 			set_disk_ro(mddev->gendisk, 1);
@@ -4543,7 +4553,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	case read_auto:
 		if (mddev->pers) {
 			if (md_is_rdwr(mddev))
-				err = md_set_readonly(mddev, NULL);
+				err = md_set_readonly(mddev);
 			else if (mddev->ro == MD_RDONLY)
 				err = restart_array(mddev);
 			if (err == 0) {
@@ -4592,6 +4602,11 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	}
 	mddev_unlock(mddev);
+
+	if (st == readonly || st == read_auto || st == inactive ||
+	    (err && st == clear))
+		clear_bit(MD_CLOSING, &mddev->flags);
+
 	return err ?: len;
 }
 static struct md_sysfs_entry md_array_state =
@@ -4919,6 +4934,35 @@ static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq)
 		mddev_lock_nointr(mddev);
 }
 
+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);
+}
+EXPORT_SYMBOL_GPL(md_idle_sync_thread);
+
+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);
+}
+EXPORT_SYMBOL_GPL(md_frozen_sync_thread);
+
+void md_unfrozen_sync_thread(struct mddev *mddev)
+{
+	lockdep_assert_held(&mddev->reconfig_mutex);
+
+	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	md_wakeup_thread(mddev->thread);
+	sysfs_notify_dirent_safe(mddev->sysfs_action);
+}
+EXPORT_SYMBOL_GPL(md_unfrozen_sync_thread);
+
 static void idle_sync_thread(struct mddev *mddev)
 {
 	mutex_lock(&mddev->sync_mutex);
@@ -5710,6 +5754,51 @@ 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)
+{
+	struct md_rdev *rdev;
+
+	rdev_for_each(rdev, mddev) {
+		queue_limits_stack_bdev(lim, rdev->bdev, rdev->data_offset,
+					mddev->gendisk->disk_name);
+	}
+}
+EXPORT_SYMBOL_GPL(mddev_stack_rdev_limits);
+
+/* apply the extra stacking limits from a new rdev into mddev */
+int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev)
+{
+	struct queue_limits lim;
+
+	if (mddev_is_dm(mddev))
+		return 0;
+
+	lim = queue_limits_start_update(mddev->gendisk->queue);
+	queue_limits_stack_bdev(&lim, rdev->bdev, rdev->data_offset,
+				mddev->gendisk->disk_name);
+	return queue_limits_commit_update(mddev->gendisk->queue, &lim);
+}
+EXPORT_SYMBOL_GPL(mddev_stack_new_rdev);
+
+/* update the optimal I/O size after a reshape */
+void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes)
+{
+	struct queue_limits lim;
+
+	if (mddev_is_dm(mddev))
+		return;
+
+	/* don't bother updating io_opt if we can't suspend the array */
+	if (mddev_suspend(mddev, false) < 0)
+		return;
+	lim = queue_limits_start_update(mddev->gendisk->queue);
+	lim.io_opt = lim.io_min * nr_stripes;
+	queue_limits_commit_update(mddev->gendisk->queue, &lim);
+	mddev_resume(mddev);
+}
+EXPORT_SYMBOL_GPL(mddev_update_io_opt);
+
 static void mddev_delayed_delete(struct work_struct *ws)
 {
 	struct mddev *mddev = container_of(ws, struct mddev, del_work);
@@ -5774,10 +5863,11 @@ struct mddev *md_alloc(dev_t dev, char *name)
 		 */
 		mddev->hold_active = UNTIL_STOP;
 
-	error = -ENOMEM;
-	disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!disk)
+	disk = blk_alloc_disk(NULL, NUMA_NO_NODE);
+	if (IS_ERR(disk)) {
+		error = PTR_ERR(disk);
 		goto out_free_mddev;
+	}
 
 	disk->major = MAJOR(mddev->unit);
 	disk->first_minor = unit << shift;
@@ -5791,9 +5881,7 @@ struct mddev *md_alloc(dev_t dev, char *name)
 	disk->fops = &md_fops;
 	disk->private_data = mddev;
 
-	mddev->queue = disk->queue;
-	blk_set_stacking_limits(&mddev->queue->limits);
-	blk_queue_write_cache(mddev->queue, true, true);
+	blk_queue_write_cache(disk->queue, true, true);
 	disk->events |= DISK_EVENT_MEDIA_CHANGE;
 	mddev->gendisk = disk;
 	error = add_disk(disk);
@@ -5935,7 +6023,7 @@ int md_run(struct mddev *mddev)
 		invalidate_bdev(rdev->bdev);
 		if (mddev->ro != MD_RDONLY && rdev_read_only(rdev)) {
 			mddev->ro = MD_RDONLY;
-			if (mddev->gendisk)
+			if (!mddev_is_dm(mddev))
 				set_disk_ro(mddev->gendisk, 1);
 		}
 
@@ -6038,7 +6126,10 @@ int md_run(struct mddev *mddev)
 			pr_warn("True protection against single-disk failure might be compromised.\n");
 	}
 
-	mddev->recovery = 0;
+	/* dm-raid expect sync_thread to be frozen until resume */
+	if (mddev->gendisk)
+		mddev->recovery = 0;
+
 	/* may be over-ridden by personality */
 	mddev->resync_max_sectors = mddev->dev_sectors;
 
@@ -6094,7 +6185,8 @@ int md_run(struct mddev *mddev)
 		}
 	}
 
-	if (mddev->queue) {
+	if (!mddev_is_dm(mddev)) {
+		struct request_queue *q = mddev->gendisk->queue;
 		bool nonrot = true;
 
 		rdev_for_each(rdev, mddev) {
@@ -6106,14 +6198,14 @@ int md_run(struct mddev *mddev)
 		if (mddev->degraded)
 			nonrot = false;
 		if (nonrot)
-			blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue);
+			blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 		else
-			blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue);
-		blk_queue_flag_set(QUEUE_FLAG_IO_STAT, mddev->queue);
+			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, mddev->queue);
+			blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
 	}
 	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
@@ -6192,7 +6284,6 @@ int do_md_run(struct mddev *mddev)
 	/* run start up tasks that require md_thread */
 	md_start(mddev);
 
-	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
 	set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
@@ -6213,7 +6304,6 @@ int md_start(struct mddev *mddev)
 
 	if (mddev->pers->start) {
 		set_bit(MD_RECOVERY_WAIT, &mddev->recovery);
-		md_wakeup_thread(mddev->thread);
 		ret = mddev->pers->start(mddev);
 		clear_bit(MD_RECOVERY_WAIT, &mddev->recovery);
 		md_wakeup_thread(mddev->sync_thread);
@@ -6258,7 +6348,6 @@ static int restart_array(struct mddev *mddev)
 	pr_debug("md: %s switched to read-write mode.\n", mdname(mddev));
 	/* Kick recovery or resync if necessary */
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread);
 	sysfs_notify_dirent_safe(mddev->sysfs_state);
 	return 0;
@@ -6278,7 +6367,15 @@ static void md_clean(struct mddev *mddev)
 	mddev->persistent = 0;
 	mddev->level = LEVEL_NONE;
 	mddev->clevel[0] = 0;
-	mddev->flags = 0;
+	/*
+	 * Don't clear MD_CLOSING, or mddev can be opened again.
+	 * 'hold_active != 0' means mddev is still in the creation
+	 * process and will be used later.
+	 */
+	if (mddev->hold_active)
+		mddev->flags = 0;
+	else
+		mddev->flags &= BIT_ULL_MASK(MD_CLOSING);
 	mddev->sb_flags = 0;
 	mddev->ro = MD_RDWR;
 	mddev->metadata_type[0] = 0;
@@ -6315,7 +6412,6 @@ static void md_clean(struct mddev *mddev)
 
 static void __md_stop_writes(struct mddev *mddev)
 {
-	stop_sync_thread(mddev, true, false);
 	del_timer_sync(&mddev->safemode_timer);
 
 	if (mddev->pers && mddev->pers->quiesce) {
@@ -6340,6 +6436,8 @@ static void __md_stop_writes(struct mddev *mddev)
 void md_stop_writes(struct mddev *mddev)
 {
 	mddev_lock_nointr(mddev);
+	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	stop_sync_thread(mddev, true, false);
 	__md_stop_writes(mddev);
 	mddev_unlock(mddev);
 }
@@ -6353,8 +6451,10 @@ static void mddev_detach(struct mddev *mddev)
 		mddev->pers->quiesce(mddev, 0);
 	}
 	md_unregister_thread(mddev, &mddev->thread);
-	if (mddev->queue)
-		blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
+
+	/* the unplug fn references 'conf' */
+	if (!mddev_is_dm(mddev))
+		blk_sync_queue(mddev->gendisk->queue);
 }
 
 static void __md_stop(struct mddev *mddev)
@@ -6391,7 +6491,8 @@ void md_stop(struct mddev *mddev)
 
 EXPORT_SYMBOL_GPL(md_stop);
 
-static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
+/* ensure 'mddev->pers' exist before calling md_set_readonly() */
+static int md_set_readonly(struct mddev *mddev)
 {
 	int err = 0;
 	int did_freeze = 0;
@@ -6402,7 +6503,6 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 	if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) {
 		did_freeze = 1;
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-		md_wakeup_thread(mddev->thread);
 	}
 
 	stop_sync_thread(mddev, false, false);
@@ -6410,36 +6510,29 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 	mddev_lock_nointr(mddev);
 
-	mutex_lock(&mddev->open_mutex);
-	if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
-	    mddev->sync_thread ||
-	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		pr_warn("md: %s still in use.\n",mdname(mddev));
 		err = -EBUSY;
 		goto out;
 	}
 
-	if (mddev->pers) {
-		__md_stop_writes(mddev);
+	__md_stop_writes(mddev);
 
-		if (mddev->ro == MD_RDONLY) {
-			err  = -ENXIO;
-			goto out;
-		}
-
-		mddev->ro = MD_RDONLY;
-		set_disk_ro(mddev->gendisk, 1);
+	if (mddev->ro == MD_RDONLY) {
+		err  = -ENXIO;
+		goto out;
 	}
 
+	mddev->ro = MD_RDONLY;
+	set_disk_ro(mddev->gendisk, 1);
+
 out:
-	if ((mddev->pers && !err) || did_freeze) {
+	if (!err || did_freeze) {
 		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-		md_wakeup_thread(mddev->thread);
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	}
 
-	mutex_unlock(&mddev->open_mutex);
 	return err;
 }
 
@@ -6447,8 +6540,7 @@ out:
  *   0 - completely stop and dis-assemble array
  *   2 - stop but do not disassemble array
  */
-static int do_md_stop(struct mddev *mddev, int mode,
-		      struct block_device *bdev)
+static int do_md_stop(struct mddev *mddev, int mode)
 {
 	struct gendisk *disk = mddev->gendisk;
 	struct md_rdev *rdev;
@@ -6457,22 +6549,16 @@ static int do_md_stop(struct mddev *mddev, int mode,
 	if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) {
 		did_freeze = 1;
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-		md_wakeup_thread(mddev->thread);
 	}
 
 	stop_sync_thread(mddev, true, false);
 
-	mutex_lock(&mddev->open_mutex);
-	if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
-	    mddev->sysfs_active ||
-	    mddev->sync_thread ||
+	if (mddev->sysfs_active ||
 	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		pr_warn("md: %s still in use.\n",mdname(mddev));
-		mutex_unlock(&mddev->open_mutex);
 		if (did_freeze) {
 			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-			md_wakeup_thread(mddev->thread);
 		}
 		return -EBUSY;
 	}
@@ -6491,13 +6577,11 @@ static int do_md_stop(struct mddev *mddev, int mode,
 				sysfs_unlink_rdev(mddev, rdev);
 
 		set_capacity_and_notify(disk, 0);
-		mutex_unlock(&mddev->open_mutex);
 		mddev->changed = 1;
 
 		if (!md_is_rdwr(mddev))
 			mddev->ro = MD_RDWR;
-	} else
-		mutex_unlock(&mddev->open_mutex);
+	}
 	/*
 	 * Free resources if final stop
 	 */
@@ -6543,7 +6627,7 @@ static void autorun_array(struct mddev *mddev)
 	err = do_md_run(mddev);
 	if (err) {
 		pr_warn("md: do_md_run() returned %d\n", err);
-		do_md_stop(mddev, 0, NULL);
+		do_md_stop(mddev, 0);
 	}
 }
 
@@ -7013,9 +7097,7 @@ kick_rdev:
 
 	md_kick_rdev_from_array(rdev);
 	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
-	if (mddev->thread)
-		md_wakeup_thread(mddev->thread);
-	else
+	if (!mddev->thread)
 		md_update_sb(mddev, 1);
 	md_new_event();
 
@@ -7090,14 +7172,13 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
 	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->queue);
+		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->gendisk->queue);
 	}
 	/*
 	 * Kick recovery, maybe this spare has to be added to the
 	 * array immediately.
 	 */
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	md_wakeup_thread(mddev->thread);
 	md_new_event();
 	return 0;
 
@@ -7311,8 +7392,7 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 	 * of each device.  If num_sectors is zero, we find the largest size
 	 * that fits.
 	 */
-	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
-	    mddev->sync_thread)
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
 		return -EBUSY;
 	if (!md_is_rdwr(mddev))
 		return -EROFS;
@@ -7329,10 +7409,9 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 	if (!rv) {
 		if (mddev_is_clustered(mddev))
 			md_cluster_ops->update_size(mddev, old_dev_sectors);
-		else if (mddev->queue) {
+		else if (!mddev_is_dm(mddev))
 			set_capacity_and_notify(mddev->gendisk,
 						mddev->array_sectors);
-		}
 	}
 	return rv;
 }
@@ -7349,8 +7428,7 @@ static int update_raid_disks(struct mddev *mddev, int raid_disks)
 	if (raid_disks <= 0 ||
 	    (mddev->max_disks && raid_disks >= mddev->max_disks))
 		return -EINVAL;
-	if (mddev->sync_thread ||
-	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
 	    test_bit(MD_RESYNCING_REMOTE, &mddev->recovery) ||
 	    mddev->reshape_position != MaxSector)
 		return -EBUSY;
@@ -7546,16 +7624,17 @@ static int md_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return 0;
 }
 
-static inline bool md_ioctl_valid(unsigned int cmd)
+static inline int md_ioctl_valid(unsigned int cmd)
 {
 	switch (cmd) {
-	case ADD_NEW_DISK:
 	case GET_ARRAY_INFO:
-	case GET_BITMAP_FILE:
 	case GET_DISK_INFO:
+	case RAID_VERSION:
+		return 0;
+	case ADD_NEW_DISK:
+	case GET_BITMAP_FILE:
 	case HOT_ADD_DISK:
 	case HOT_REMOVE_DISK:
-	case RAID_VERSION:
 	case RESTART_ARRAY_RW:
 	case RUN_ARRAY:
 	case SET_ARRAY_INFO:
@@ -7564,9 +7643,11 @@ static inline bool md_ioctl_valid(unsigned int cmd)
 	case STOP_ARRAY:
 	case STOP_ARRAY_RO:
 	case CLUSTERED_DISK_NACK:
-		return true;
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+		return 0;
 	default:
-		return false;
+		return -ENOTTY;
 	}
 }
 
@@ -7624,31 +7705,17 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 	int err = 0;
 	void __user *argp = (void __user *)arg;
 	struct mddev *mddev = NULL;
-	bool did_set_md_closing = false;
 
-	if (!md_ioctl_valid(cmd))
-		return -ENOTTY;
-
-	switch (cmd) {
-	case RAID_VERSION:
-	case GET_ARRAY_INFO:
-	case GET_DISK_INFO:
-		break;
-	default:
-		if (!capable(CAP_SYS_ADMIN))
-			return -EACCES;
-	}
+	err = md_ioctl_valid(cmd);
+	if (err)
+		return err;
 
 	/*
 	 * Commands dealing with the RAID driver but not any
 	 * particular array:
 	 */
-	switch (cmd) {
-	case RAID_VERSION:
-		err = get_version(argp);
-		goto out;
-	default:;
-	}
+	if (cmd == RAID_VERSION)
+		return get_version(argp);
 
 	/*
 	 * Commands creating/starting a new array:
@@ -7656,35 +7723,23 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 
 	mddev = bdev->bd_disk->private_data;
 
-	if (!mddev) {
-		BUG();
-		goto out;
-	}
-
 	/* Some actions do not requires the mutex */
 	switch (cmd) {
 	case GET_ARRAY_INFO:
 		if (!mddev->raid_disks && !mddev->external)
-			err = -ENODEV;
-		else
-			err = get_array_info(mddev, argp);
-		goto out;
+			return -ENODEV;
+		return get_array_info(mddev, argp);
 
 	case GET_DISK_INFO:
 		if (!mddev->raid_disks && !mddev->external)
-			err = -ENODEV;
-		else
-			err = get_disk_info(mddev, argp);
-		goto out;
+			return -ENODEV;
+		return get_disk_info(mddev, argp);
 
 	case SET_DISK_FAULTY:
-		err = set_disk_faulty(mddev, new_decode_dev(arg));
-		goto out;
+		return set_disk_faulty(mddev, new_decode_dev(arg));
 
 	case GET_BITMAP_FILE:
-		err = get_bitmap_file(mddev, argp);
-		goto out;
-
+		return get_bitmap_file(mddev, argp);
 	}
 
 	if (cmd == HOT_REMOVE_DISK)
@@ -7697,20 +7752,9 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 		/* Need to flush page cache, and ensure no-one else opens
 		 * and writes
 		 */
-		mutex_lock(&mddev->open_mutex);
-		if (mddev->pers && atomic_read(&mddev->openers) > 1) {
-			mutex_unlock(&mddev->open_mutex);
-			err = -EBUSY;
-			goto out;
-		}
-		if (test_and_set_bit(MD_CLOSING, &mddev->flags)) {
-			mutex_unlock(&mddev->open_mutex);
-			err = -EBUSY;
-			goto out;
-		}
-		did_set_md_closing = true;
-		mutex_unlock(&mddev->open_mutex);
-		sync_blockdev(bdev);
+		err = mddev_set_closing_and_sync_blockdev(mddev, 1);
+		if (err)
+			return err;
 	}
 
 	if (!md_is_rdwr(mddev))
@@ -7751,11 +7795,12 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 		goto unlock;
 
 	case STOP_ARRAY:
-		err = do_md_stop(mddev, 0, bdev);
+		err = do_md_stop(mddev, 0);
 		goto unlock;
 
 	case STOP_ARRAY_RO:
-		err = md_set_readonly(mddev, bdev);
+		if (mddev->pers)
+			err = md_set_readonly(mddev);
 		goto unlock;
 
 	case HOT_REMOVE_DISK:
@@ -7850,7 +7895,7 @@ unlock:
 				     mddev_unlock(mddev);
 
 out:
-	if(did_set_md_closing)
+	if (cmd == STOP_ARRAY_RO || (err && cmd == STOP_ARRAY))
 		clear_bit(MD_CLOSING, &mddev->flags);
 	return err;
 }
@@ -8687,10 +8732,7 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 
 	bio_chain(discard_bio, bio);
 	bio_clone_blkg_association(discard_bio, bio);
-	if (mddev->gendisk)
-		trace_block_bio_remap(discard_bio,
-				disk_devt(mddev->gendisk),
-				bio->bi_iter.bi_sector);
+	mddev_trace_remap(mddev, discard_bio, bio->bi_iter.bi_sector);
 	submit_bio_noacct(discard_bio);
 }
 EXPORT_SYMBOL_GPL(md_submit_discard_bio);
@@ -8737,6 +8779,23 @@ void md_account_bio(struct mddev *mddev, struct bio **bio)
 }
 EXPORT_SYMBOL_GPL(md_account_bio);
 
+void md_free_cloned_bio(struct bio *bio)
+{
+	struct md_io_clone *md_io_clone = bio->bi_private;
+	struct bio *orig_bio = md_io_clone->orig_bio;
+	struct mddev *mddev = md_io_clone->mddev;
+
+	if (bio->bi_status && !orig_bio->bi_status)
+		orig_bio->bi_status = bio->bi_status;
+
+	if (md_io_clone->start_time)
+		bio_end_io_acct(orig_bio, md_io_clone->start_time);
+
+	bio_put(bio);
+	percpu_ref_put(&mddev->active_io);
+}
+EXPORT_SYMBOL_GPL(md_free_cloned_bio);
+
 /* md_allow_write(mddev)
  * Calling this ensures that the array is marked 'active' so that writes
  * may proceed without blocking.  It is important to call this before
@@ -9170,7 +9229,7 @@ void md_do_sync(struct md_thread *thread)
 			mddev->delta_disks > 0 &&
 			mddev->pers->finish_reshape &&
 			mddev->pers->size &&
-			mddev->queue) {
+			!mddev_is_dm(mddev)) {
 		mddev_lock_nointr(mddev);
 		md_set_array_sectors(mddev, mddev->pers->size(mddev, 0, 0));
 		mddev_unlock(mddev);
@@ -9270,9 +9329,14 @@ static bool md_spares_need_change(struct mddev *mddev)
 {
 	struct md_rdev *rdev;
 
-	rdev_for_each(rdev, mddev)
-		if (rdev_removeable(rdev) || rdev_addable(rdev))
+	rcu_read_lock();
+	rdev_for_each_rcu(rdev, mddev) {
+		if (rdev_removeable(rdev) || rdev_addable(rdev)) {
+			rcu_read_unlock();
 			return true;
+		}
+	}
+	rcu_read_unlock();
 	return false;
 }
 

drivers/md/md.h

@@ -18,6 +18,7 @@
 #include <linux/timer.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
+#include <trace/events/block.h>
 #include "md-cluster.h"
 
 #define MaxSector (~(sector_t)0)
@@ -207,6 +208,7 @@ enum flag_bits {
 				 * check if there is collision between raid1
 				 * serial bios.
 				 */
+	Nonrot,			/* non-rotational device (SSD) */
 };
 
 static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,
@@ -222,6 +224,16 @@ static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,
 	}
 	return 0;
 }
+
+static inline int rdev_has_badblock(struct md_rdev *rdev, sector_t s,
+				    int sectors)
+{
+	sector_t first_bad;
+	int bad_sectors;
+
+	return is_badblock(rdev, s, sectors, &first_bad, &bad_sectors);
+}
+
 extern int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 			      int is_new);
 extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
@@ -468,7 +480,6 @@ struct mddev {
 	struct timer_list		safemode_timer;
 	struct percpu_ref		writes_pending;
 	int				sync_checkers;	/* # of threads checking writes_pending */
-	struct request_queue		*queue;	/* for plugging ... */
 
 	struct bitmap			*bitmap; /* the bitmap for the device */
 	struct {
@@ -558,6 +569,37 @@ enum recovery_flags {
 	MD_RESYNCING_REMOTE,	/* remote node is running resync thread */
 };
 
+enum md_ro_state {
+	MD_RDWR,
+	MD_RDONLY,
+	MD_AUTO_READ,
+	MD_MAX_STATE
+};
+
+static inline bool md_is_rdwr(struct mddev *mddev)
+{
+	return (mddev->ro == MD_RDWR);
+}
+
+static inline bool reshape_interrupted(struct mddev *mddev)
+{
+	/* reshape never start */
+	if (mddev->reshape_position == MaxSector)
+		return false;
+
+	/* interrupted */
+	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+		return true;
+
+	/* running reshape will be interrupted soon. */
+	if (test_bit(MD_RECOVERY_WAIT, &mddev->recovery) ||
+	    test_bit(MD_RECOVERY_INTR, &mddev->recovery) ||
+	    test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+		return true;
+
+	return false;
+}
+
 static inline int __must_check mddev_lock(struct mddev *mddev)
 {
 	return mutex_lock_interruptible(&mddev->reconfig_mutex);
@@ -617,6 +659,7 @@ struct md_personality
 	int (*start_reshape) (struct mddev *mddev);
 	void (*finish_reshape) (struct mddev *mddev);
 	void (*update_reshape_pos) (struct mddev *mddev);
+	void (*prepare_suspend) (struct mddev *mddev);
 	/* quiesce suspends or resumes internal processing.
 	 * 1 - stop new actions and wait for action io to complete
 	 * 0 - return to normal behaviour
@@ -750,6 +793,7 @@ extern void md_finish_reshape(struct mddev *mddev);
 void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 			struct bio *bio, sector_t start, sector_t size);
 void md_account_bio(struct mddev *mddev, struct bio **bio);
+void md_free_cloned_bio(struct bio *bio);
 
 extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
@@ -778,9 +822,12 @@ extern void md_stop_writes(struct mddev *mddev);
 extern int md_rdev_init(struct md_rdev *rdev);
 extern void md_rdev_clear(struct md_rdev *rdev);
 
-extern void md_handle_request(struct mddev *mddev, struct bio *bio);
+extern bool md_handle_request(struct mddev *mddev, struct bio *bio);
 extern int mddev_suspend(struct mddev *mddev, bool interruptible);
 extern void mddev_resume(struct mddev *mddev);
+extern void md_idle_sync_thread(struct mddev *mddev);
+extern void md_frozen_sync_thread(struct mddev *mddev);
+extern void md_unfrozen_sync_thread(struct mddev *mddev);
 
 extern void md_reload_sb(struct mddev *mddev, int raid_disk);
 extern void md_update_sb(struct mddev *mddev, int force);
@@ -821,7 +868,7 @@ static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio
 {
 	if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
 	    !bio->bi_bdev->bd_disk->queue->limits.max_write_zeroes_sectors)
-		mddev->queue->limits.max_write_zeroes_sectors = 0;
+		mddev->gendisk->queue->limits.max_write_zeroes_sectors = 0;
 }
 
 static inline int mddev_suspend_and_lock(struct mddev *mddev)
@@ -860,7 +907,31 @@ 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);
+int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev);
+void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes);
 
 extern const struct block_device_operations md_fops;
 
+/*
+ * MD devices can be used undeneath by DM, in which case ->gendisk is NULL.
+ */
+static inline bool mddev_is_dm(struct mddev *mddev)
+{
+	return !mddev->gendisk;
+}
+
+static inline void mddev_trace_remap(struct mddev *mddev, struct bio *bio,
+		sector_t sector)
+{
+	if (!mddev_is_dm(mddev))
+		trace_block_bio_remap(bio, disk_devt(mddev->gendisk), sector);
+}
+
+#define mddev_add_trace_msg(mddev, fmt, args...)			\
+do {									\
+	if (!mddev_is_dm(mddev))					\
+		blk_add_trace_msg((mddev)->gendisk->queue, fmt, ##args); \
+} while (0)
+
 #endif /* _MD_MD_H */

drivers/md/raid0.c

@@ -379,6 +379,19 @@ static void raid0_free(struct mddev *mddev, void *priv)
 	free_conf(mddev, conf);
 }
 
+static int raid0_set_limits(struct mddev *mddev)
+{
+	struct queue_limits lim;
+
+	blk_set_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);
+	return queue_limits_set(mddev->gendisk->queue, &lim);
+}
+
 static int raid0_run(struct mddev *mddev)
 {
 	struct r0conf *conf;
@@ -399,20 +412,10 @@ static int raid0_run(struct mddev *mddev)
 		mddev->private = conf;
 	}
 	conf = mddev->private;
-	if (mddev->queue) {
-		struct md_rdev *rdev;
-
-		blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
-		blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors);
-
-		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
-		blk_queue_io_opt(mddev->queue,
-				 (mddev->chunk_sectors << 9) * mddev->raid_disks);
-
-		rdev_for_each(rdev, mddev) {
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-		}
+	if (!mddev_is_dm(mddev)) {
+		ret = raid0_set_limits(mddev);
+		if (ret)
+			goto out_free_conf;
 	}
 
 	/* calculate array device size */
@@ -426,8 +429,10 @@ static int raid0_run(struct mddev *mddev)
 
 	ret = md_integrity_register(mddev);
 	if (ret)
-		free_conf(mddev, conf);
-
+		goto out_free_conf;
+	return 0;
+out_free_conf:
+	free_conf(mddev, conf);
 	return ret;
 }
 
@@ -578,10 +583,7 @@ static void raid0_map_submit_bio(struct mddev *mddev, struct bio *bio)
 	bio_set_dev(bio, tmp_dev->bdev);
 	bio->bi_iter.bi_sector = sector + zone->dev_start +
 		tmp_dev->data_offset;
-
-	if (mddev->gendisk)
-		trace_block_bio_remap(bio, disk_devt(mddev->gendisk),
-				      bio_sector);
+	mddev_trace_remap(mddev, bio, bio_sector);
 	mddev_check_write_zeroes(mddev, bio);
 	submit_bio_noacct(bio);
 }

drivers/md/raid1-10.c

@@ -227,3 +227,72 @@ static inline bool exceed_read_errors(struct mddev *mddev, struct md_rdev *rdev)
 
 	return false;
 }
+
+/**
+ * raid1_check_read_range() - check a given read range for bad blocks,
+ * available read length is returned;
+ * @rdev: the rdev to read;
+ * @this_sector: read position;
+ * @len: read length;
+ *
+ * helper function for read_balance()
+ *
+ * 1) If there are no bad blocks in the range, @len is returned;
+ * 2) If the range are all bad blocks, 0 is returned;
+ * 3) If there are partial bad blocks:
+ *  - If the bad block range starts after @this_sector, the length of first
+ *  good region is returned;
+ *  - If the bad block range starts before @this_sector, 0 is returned and
+ *  the @len is updated to the offset into the region before we get to the
+ *  good blocks;
+ */
+static inline int raid1_check_read_range(struct md_rdev *rdev,
+					 sector_t this_sector, int *len)
+{
+	sector_t first_bad;
+	int bad_sectors;
+
+	/* no bad block overlap */
+	if (!is_badblock(rdev, this_sector, *len, &first_bad, &bad_sectors))
+		return *len;
+
+	/*
+	 * bad block range starts offset into our range so we can return the
+	 * number of sectors before the bad blocks start.
+	 */
+	if (first_bad > this_sector)
+		return first_bad - this_sector;
+
+	/* read range is fully consumed by bad blocks. */
+	if (this_sector + *len <= first_bad + bad_sectors)
+		return 0;
+
+	/*
+	 * final case, bad block range starts before or at the start of our
+	 * range but does not cover our entire range so we still return 0 but
+	 * update the length with the number of sectors before we get to the
+	 * good ones.
+	 */
+	*len = first_bad + bad_sectors - this_sector;
+	return 0;
+}
+
+/*
+ * Check if read should choose the first rdev.
+ *
+ * Balance on the whole device if no resync is going on (recovery is ok) or
+ * below the resync window. Otherwise, take the first readable disk.
+ */
+static inline bool raid1_should_read_first(struct mddev *mddev,
+					   sector_t this_sector, int len)
+{
+	if ((mddev->recovery_cp < this_sector + len))
+		return true;
+
+	if (mddev_is_clustered(mddev) &&
+	    md_cluster_ops->area_resyncing(mddev, READ, this_sector,
+					   this_sector + len))
+		return true;
+
+	return false;
+}

drivers/md/raid1.c

@@ -46,9 +46,6 @@
 static void allow_barrier(struct r1conf *conf, sector_t sector_nr);
 static void lower_barrier(struct r1conf *conf, sector_t sector_nr);
 
-#define raid1_log(md, fmt, args...)				\
-	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0)
-
 #define RAID_1_10_NAME "raid1"
 #include "raid1-10.c"
 
@@ -498,9 +495,6 @@ static void raid1_end_write_request(struct bio *bio)
 		 * to user-side. So if something waits for IO, then it
 		 * will wait for the 'master' bio.
 		 */
-		sector_t first_bad;
-		int bad_sectors;
-
 		r1_bio->bios[mirror] = NULL;
 		to_put = bio;
 		/*
@@ -516,8 +510,8 @@ static void raid1_end_write_request(struct bio *bio)
 			set_bit(R1BIO_Uptodate, &r1_bio->state);
 
 		/* Maybe we can clear some bad blocks. */
-		if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
-				&first_bad, &bad_sectors) && !discard_error) {
+		if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) &&
+		    !discard_error) {
 			r1_bio->bios[mirror] = IO_MADE_GOOD;
 			set_bit(R1BIO_MadeGood, &r1_bio->state);
 		}
@@ -582,211 +576,312 @@ static sector_t align_to_barrier_unit_end(sector_t start_sector,
 	return len;
 }
 
-/*
- * This routine returns the disk from which the requested read should
- * be done. There is a per-array 'next expected sequential IO' sector
- * number - if this matches on the next IO then we use the last disk.
- * There is also a per-disk 'last know head position' sector that is
- * maintained from IRQ contexts, both the normal and the resync IO
- * completion handlers update this position correctly. If there is no
- * perfect sequential match then we pick the disk whose head is closest.
- *
- * If there are 2 mirrors in the same 2 devices, performance degrades
- * because position is mirror, not device based.
- *
- * The rdev for the device selected will have nr_pending incremented.
- */
-static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sectors)
+static void update_read_sectors(struct r1conf *conf, int disk,
+				sector_t this_sector, int len)
 {
-	const sector_t this_sector = r1_bio->sector;
-	int sectors;
-	int best_good_sectors;
-	int best_disk, best_dist_disk, best_pending_disk;
-	int has_nonrot_disk;
+	struct raid1_info *info = &conf->mirrors[disk];
+
+	atomic_inc(&info->rdev->nr_pending);
+	if (info->next_seq_sect != this_sector)
+		info->seq_start = this_sector;
+	info->next_seq_sect = this_sector + len;
+}
+
+static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+			     int *max_sectors)
+{
+	sector_t this_sector = r1_bio->sector;
+	int len = r1_bio->sectors;
 	int disk;
-	sector_t best_dist;
-	unsigned int min_pending;
-	struct md_rdev *rdev;
-	int choose_first;
-	int choose_next_idle;
-
-	/*
-	 * Check if we can balance. We can balance on the whole
-	 * device if no resync is going on, or below the resync window.
-	 * We take the first readable disk when above the resync window.
-	 */
- retry:
-	sectors = r1_bio->sectors;
-	best_disk = -1;
-	best_dist_disk = -1;
-	best_dist = MaxSector;
-	best_pending_disk = -1;
-	min_pending = UINT_MAX;
-	best_good_sectors = 0;
-	has_nonrot_disk = 0;
-	choose_next_idle = 0;
-	clear_bit(R1BIO_FailFast, &r1_bio->state);
-
-	if ((conf->mddev->recovery_cp < this_sector + sectors) ||
-	    (mddev_is_clustered(conf->mddev) &&
-	    md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
-		    this_sector + sectors)))
-		choose_first = 1;
-	else
-		choose_first = 0;
 
 	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
-		sector_t dist;
-		sector_t first_bad;
-		int bad_sectors;
-		unsigned int pending;
-		bool nonrot;
+		struct md_rdev *rdev;
+		int read_len;
+
+		if (r1_bio->bios[disk] == IO_BLOCKED)
+			continue;
 
 		rdev = conf->mirrors[disk].rdev;
-		if (r1_bio->bios[disk] == IO_BLOCKED
-		    || rdev == NULL
-		    || test_bit(Faulty, &rdev->flags))
-			continue;
-		if (!test_bit(In_sync, &rdev->flags) &&
-		    rdev->recovery_offset < this_sector + sectors)
-			continue;
-		if (test_bit(WriteMostly, &rdev->flags)) {
-			/* Don't balance among write-mostly, just
-			 * use the first as a last resort */
-			if (best_dist_disk < 0) {
-				if (is_badblock(rdev, this_sector, sectors,
-						&first_bad, &bad_sectors)) {
-					if (first_bad <= this_sector)
-						/* Cannot use this */
-						continue;
-					best_good_sectors = first_bad - this_sector;
-				} else
-					best_good_sectors = sectors;
-				best_dist_disk = disk;
-				best_pending_disk = disk;
-			}
-			continue;
-		}
-		/* This is a reasonable device to use.  It might
-		 * even be best.
-		 */
-		if (is_badblock(rdev, this_sector, sectors,
-				&first_bad, &bad_sectors)) {
-			if (best_dist < MaxSector)
-				/* already have a better device */
-				continue;
-			if (first_bad <= this_sector) {
-				/* cannot read here. If this is the 'primary'
-				 * device, then we must not read beyond
-				 * bad_sectors from another device..
-				 */
-				bad_sectors -= (this_sector - first_bad);
-				if (choose_first && sectors > bad_sectors)
-					sectors = bad_sectors;
-				if (best_good_sectors > sectors)
-					best_good_sectors = sectors;
-
-			} else {
-				sector_t good_sectors = first_bad - this_sector;
-				if (good_sectors > best_good_sectors) {
-					best_good_sectors = good_sectors;
-					best_disk = disk;
-				}
-				if (choose_first)
-					break;
-			}
-			continue;
-		} else {
-			if ((sectors > best_good_sectors) && (best_disk >= 0))
-				best_disk = -1;
-			best_good_sectors = sectors;
-		}
-
-		if (best_disk >= 0)
-			/* At least two disks to choose from so failfast is OK */
-			set_bit(R1BIO_FailFast, &r1_bio->state);
-
-		nonrot = bdev_nonrot(rdev->bdev);
-		has_nonrot_disk |= nonrot;
-		pending = atomic_read(&rdev->nr_pending);
-		dist = abs(this_sector - conf->mirrors[disk].head_position);
-		if (choose_first) {
-			best_disk = disk;
-			break;
-		}
-		/* Don't change to another disk for sequential reads */
-		if (conf->mirrors[disk].next_seq_sect == this_sector
-		    || dist == 0) {
-			int opt_iosize = bdev_io_opt(rdev->bdev) >> 9;
-			struct raid1_info *mirror = &conf->mirrors[disk];
-
-			best_disk = disk;
-			/*
-			 * If buffered sequential IO size exceeds optimal
-			 * iosize, check if there is idle disk. If yes, choose
-			 * the idle disk. read_balance could already choose an
-			 * idle disk before noticing it's a sequential IO in
-			 * this disk. This doesn't matter because this disk
-			 * will idle, next time it will be utilized after the
-			 * first disk has IO size exceeds optimal iosize. In
-			 * this way, iosize of the first disk will be optimal
-			 * iosize at least. iosize of the second disk might be
-			 * small, but not a big deal since when the second disk
-			 * starts IO, the first disk is likely still busy.
-			 */
-			if (nonrot && opt_iosize > 0 &&
-			    mirror->seq_start != MaxSector &&
-			    mirror->next_seq_sect > opt_iosize &&
-			    mirror->next_seq_sect - opt_iosize >=
-			    mirror->seq_start) {
-				choose_next_idle = 1;
-				continue;
-			}
-			break;
-		}
-
-		if (choose_next_idle)
+		if (!rdev || test_bit(Faulty, &rdev->flags))
 			continue;
 
-		if (min_pending > pending) {
-			min_pending = pending;
-			best_pending_disk = disk;
-		}
-
-		if (dist < best_dist) {
-			best_dist = dist;
-			best_dist_disk = disk;
+		/* choose the first disk even if it has some bad blocks. */
+		read_len = raid1_check_read_range(rdev, this_sector, &len);
+		if (read_len > 0) {
+			update_read_sectors(conf, disk, this_sector, read_len);
+			*max_sectors = read_len;
+			return disk;
 		}
 	}
 
+	return -1;
+}
+
+static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+			  int *max_sectors)
+{
+	sector_t this_sector = r1_bio->sector;
+	int best_disk = -1;
+	int best_len = 0;
+	int disk;
+
+	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
+		struct md_rdev *rdev;
+		int len;
+		int read_len;
+
+		if (r1_bio->bios[disk] == IO_BLOCKED)
+			continue;
+
+		rdev = conf->mirrors[disk].rdev;
+		if (!rdev || test_bit(Faulty, &rdev->flags) ||
+		    test_bit(WriteMostly, &rdev->flags))
+			continue;
+
+		/* keep track of the disk with the most readable sectors. */
+		len = r1_bio->sectors;
+		read_len = raid1_check_read_range(rdev, this_sector, &len);
+		if (read_len > best_len) {
+			best_disk = disk;
+			best_len = read_len;
+		}
+	}
+
+	if (best_disk != -1) {
+		*max_sectors = best_len;
+		update_read_sectors(conf, best_disk, this_sector, best_len);
+	}
+
+	return best_disk;
+}
+
+static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+			    int *max_sectors)
+{
+	sector_t this_sector = r1_bio->sector;
+	int bb_disk = -1;
+	int bb_read_len = 0;
+	int disk;
+
+	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
+		struct md_rdev *rdev;
+		int len;
+		int read_len;
+
+		if (r1_bio->bios[disk] == IO_BLOCKED)
+			continue;
+
+		rdev = conf->mirrors[disk].rdev;
+		if (!rdev || test_bit(Faulty, &rdev->flags) ||
+		    !test_bit(WriteMostly, &rdev->flags))
+			continue;
+
+		/* there are no bad blocks, we can use this disk */
+		len = r1_bio->sectors;
+		read_len = raid1_check_read_range(rdev, this_sector, &len);
+		if (read_len == r1_bio->sectors) {
+			update_read_sectors(conf, disk, this_sector, read_len);
+			return disk;
+		}
+
+		/*
+		 * there are partial bad blocks, choose the rdev with largest
+		 * read length.
+		 */
+		if (read_len > bb_read_len) {
+			bb_disk = disk;
+			bb_read_len = read_len;
+		}
+	}
+
+	if (bb_disk != -1) {
+		*max_sectors = bb_read_len;
+		update_read_sectors(conf, bb_disk, this_sector, bb_read_len);
+	}
+
+	return bb_disk;
+}
+
+static bool is_sequential(struct r1conf *conf, int disk, struct r1bio *r1_bio)
+{
+	/* TODO: address issues with this check and concurrency. */
+	return conf->mirrors[disk].next_seq_sect == r1_bio->sector ||
+	       conf->mirrors[disk].head_position == r1_bio->sector;
+}
+
+/*
+ * If buffered sequential IO size exceeds optimal iosize, check if there is idle
+ * disk. If yes, choose the idle disk.
+ */
+static bool should_choose_next(struct r1conf *conf, int disk)
+{
+	struct raid1_info *mirror = &conf->mirrors[disk];
+	int opt_iosize;
+
+	if (!test_bit(Nonrot, &mirror->rdev->flags))
+		return false;
+
+	opt_iosize = bdev_io_opt(mirror->rdev->bdev) >> 9;
+	return opt_iosize > 0 && mirror->seq_start != MaxSector &&
+	       mirror->next_seq_sect > opt_iosize &&
+	       mirror->next_seq_sect - opt_iosize >= mirror->seq_start;
+}
+
+static bool rdev_readable(struct md_rdev *rdev, struct r1bio *r1_bio)
+{
+	if (!rdev || test_bit(Faulty, &rdev->flags))
+		return false;
+
+	/* still in recovery */
+	if (!test_bit(In_sync, &rdev->flags) &&
+	    rdev->recovery_offset < r1_bio->sector + r1_bio->sectors)
+		return false;
+
+	/* don't read from slow disk unless have to */
+	if (test_bit(WriteMostly, &rdev->flags))
+		return false;
+
+	/* don't split IO for bad blocks unless have to */
+	if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors))
+		return false;
+
+	return true;
+}
+
+struct read_balance_ctl {
+	sector_t closest_dist;
+	int closest_dist_disk;
+	int min_pending;
+	int min_pending_disk;
+	int sequential_disk;
+	int readable_disks;
+};
+
+static int choose_best_rdev(struct r1conf *conf, struct r1bio *r1_bio)
+{
+	int disk;
+	struct read_balance_ctl ctl = {
+		.closest_dist_disk      = -1,
+		.closest_dist           = MaxSector,
+		.min_pending_disk       = -1,
+		.min_pending            = UINT_MAX,
+		.sequential_disk	= -1,
+	};
+
+	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
+		struct md_rdev *rdev;
+		sector_t dist;
+		unsigned int pending;
+
+		if (r1_bio->bios[disk] == IO_BLOCKED)
+			continue;
+
+		rdev = conf->mirrors[disk].rdev;
+		if (!rdev_readable(rdev, r1_bio))
+			continue;
+
+		/* At least two disks to choose from so failfast is OK */
+		if (ctl.readable_disks++ == 1)
+			set_bit(R1BIO_FailFast, &r1_bio->state);
+
+		pending = atomic_read(&rdev->nr_pending);
+		dist = abs(r1_bio->sector - conf->mirrors[disk].head_position);
+
+		/* Don't change to another disk for sequential reads */
+		if (is_sequential(conf, disk, r1_bio)) {
+			if (!should_choose_next(conf, disk))
+				return disk;
+
+			/*
+			 * Add 'pending' to avoid choosing this disk if
+			 * there is other idle disk.
+			 */
+			pending++;
+			/*
+			 * If there is no other idle disk, this disk
+			 * will be chosen.
+			 */
+			ctl.sequential_disk = disk;
+		}
+
+		if (ctl.min_pending > pending) {
+			ctl.min_pending = pending;
+			ctl.min_pending_disk = disk;
+		}
+
+		if (ctl.closest_dist > dist) {
+			ctl.closest_dist = dist;
+			ctl.closest_dist_disk = disk;
+		}
+	}
+
+	/*
+	 * sequential IO size exceeds optimal iosize, however, there is no other
+	 * idle disk, so choose the sequential disk.
+	 */
+	if (ctl.sequential_disk != -1 && ctl.min_pending != 0)
+		return ctl.sequential_disk;
+
 	/*
 	 * If all disks are rotational, choose the closest disk. If any disk is
 	 * non-rotational, choose the disk with less pending request even the
 	 * disk is rotational, which might/might not be optimal for raids with
 	 * mixed ratation/non-rotational disks depending on workload.
 	 */
-	if (best_disk == -1) {
-		if (has_nonrot_disk || min_pending == 0)
-			best_disk = best_pending_disk;
-		else
-			best_disk = best_dist_disk;
+	if (ctl.min_pending_disk != -1 &&
+	    (READ_ONCE(conf->nonrot_disks) || ctl.min_pending == 0))
+		return ctl.min_pending_disk;
+	else
+		return ctl.closest_dist_disk;
+}
+
+/*
+ * This routine returns the disk from which the requested read should be done.
+ *
+ * 1) If resync is in progress, find the first usable disk and use it even if it
+ * has some bad blocks.
+ *
+ * 2) Now that there is no resync, loop through all disks and skipping slow
+ * disks and disks with bad blocks for now. Only pay attention to key disk
+ * choice.
+ *
+ * 3) If we've made it this far, now look for disks with bad blocks and choose
+ * the one with most number of sectors.
+ *
+ * 4) If we are all the way at the end, we have no choice but to use a disk even
+ * if it is write mostly.
+ *
+ * The rdev for the device selected will have nr_pending incremented.
+ */
+static int read_balance(struct r1conf *conf, struct r1bio *r1_bio,
+			int *max_sectors)
+{
+	int disk;
+
+	clear_bit(R1BIO_FailFast, &r1_bio->state);
+
+	if (raid1_should_read_first(conf->mddev, r1_bio->sector,
+				    r1_bio->sectors))
+		return choose_first_rdev(conf, r1_bio, max_sectors);
+
+	disk = choose_best_rdev(conf, r1_bio);
+	if (disk >= 0) {
+		*max_sectors = r1_bio->sectors;
+		update_read_sectors(conf, disk, r1_bio->sector,
+				    r1_bio->sectors);
+		return disk;
 	}
 
-	if (best_disk >= 0) {
-		rdev = conf->mirrors[best_disk].rdev;
-		if (!rdev)
-			goto retry;
-		atomic_inc(&rdev->nr_pending);
-		sectors = best_good_sectors;
+	/*
+	 * If we are here it means we didn't find a perfectly good disk so
+	 * now spend a bit more time trying to find one with the most good
+	 * sectors.
+	 */
+	disk = choose_bb_rdev(conf, r1_bio, max_sectors);
+	if (disk >= 0)
+		return disk;
 
-		if (conf->mirrors[best_disk].next_seq_sect != this_sector)
-			conf->mirrors[best_disk].seq_start = this_sector;
-
-		conf->mirrors[best_disk].next_seq_sect = this_sector + sectors;
-	}
-	*max_sectors = sectors;
-
-	return best_disk;
+	return choose_slow_rdev(conf, r1_bio, max_sectors);
 }
 
 static void wake_up_barrier(struct r1conf *conf)
@@ -1098,7 +1193,7 @@ static void freeze_array(struct r1conf *conf, int extra)
 	 */
 	spin_lock_irq(&conf->resync_lock);
 	conf->array_frozen = 1;
-	raid1_log(conf->mddev, "wait freeze");
+	mddev_add_trace_msg(conf->mddev, "raid1 wait freeze");
 	wait_event_lock_irq_cmd(
 		conf->wait_barrier,
 		get_unqueued_pending(conf) == extra,
@@ -1287,7 +1382,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 		 * Reading from a write-mostly device must take care not to
 		 * over-take any writes that are 'behind'
 		 */
-		raid1_log(mddev, "wait behind writes");
+		mddev_add_trace_msg(mddev, "raid1 wait behind writes");
 		wait_event(bitmap->behind_wait,
 			   atomic_read(&bitmap->behind_writes) == 0);
 	}
@@ -1320,11 +1415,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	    test_bit(R1BIO_FailFast, &r1_bio->state))
 	        read_bio->bi_opf |= MD_FAILFAST;
 	read_bio->bi_private = r1_bio;
-
-	if (mddev->gendisk)
-	        trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk),
-				      r1_bio->sector);
-
+	mddev_trace_remap(mddev, read_bio, r1_bio->sector);
 	submit_bio_noacct(read_bio);
 }
 
@@ -1474,7 +1565,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			bio_wouldblock_error(bio);
 			return;
 		}
-		raid1_log(mddev, "wait rdev %d blocked", blocked_rdev->raid_disk);
+		mddev_add_trace_msg(mddev, "raid1 wait rdev %d blocked",
+				blocked_rdev->raid_disk);
 		md_wait_for_blocked_rdev(blocked_rdev, mddev);
 		wait_barrier(conf, bio->bi_iter.bi_sector, false);
 		goto retry_write;
@@ -1557,10 +1649,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		mbio->bi_private = r1_bio;
 
 		atomic_inc(&r1_bio->remaining);
-
-		if (mddev->gendisk)
-			trace_block_bio_remap(mbio, disk_devt(mddev->gendisk),
-					      r1_bio->sector);
+		mddev_trace_remap(mddev, mbio, r1_bio->sector);
 		/* flush_pending_writes() needs access to the rdev so...*/
 		mbio->bi_bdev = (void *)rdev;
 		if (!raid1_add_bio_to_plug(mddev, mbio, raid1_unplug, disks)) {
@@ -1760,6 +1849,52 @@ static int raid1_spare_active(struct mddev *mddev)
 	return count;
 }
 
+static bool raid1_add_conf(struct r1conf *conf, struct md_rdev *rdev, int disk,
+			   bool replacement)
+{
+	struct raid1_info *info = conf->mirrors + disk;
+
+	if (replacement)
+		info += conf->raid_disks;
+
+	if (info->rdev)
+		return false;
+
+	if (bdev_nonrot(rdev->bdev)) {
+		set_bit(Nonrot, &rdev->flags);
+		WRITE_ONCE(conf->nonrot_disks, conf->nonrot_disks + 1);
+	}
+
+	rdev->raid_disk = disk;
+	info->head_position = 0;
+	info->seq_start = MaxSector;
+	WRITE_ONCE(info->rdev, rdev);
+
+	return true;
+}
+
+static bool raid1_remove_conf(struct r1conf *conf, int disk)
+{
+	struct raid1_info *info = conf->mirrors + disk;
+	struct md_rdev *rdev = info->rdev;
+
+	if (!rdev || test_bit(In_sync, &rdev->flags) ||
+	    atomic_read(&rdev->nr_pending))
+		return false;
+
+	/* Only remove non-faulty devices if recovery is not possible. */
+	if (!test_bit(Faulty, &rdev->flags) &&
+	    rdev->mddev->recovery_disabled != conf->recovery_disabled &&
+	    rdev->mddev->degraded < conf->raid_disks)
+		return false;
+
+	if (test_and_clear_bit(Nonrot, &rdev->flags))
+		WRITE_ONCE(conf->nonrot_disks, conf->nonrot_disks - 1);
+
+	WRITE_ONCE(info->rdev, NULL);
+	return true;
+}
+
 static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct r1conf *conf = mddev->private;
@@ -1791,19 +1926,16 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	for (mirror = first; mirror <= last; mirror++) {
 		p = conf->mirrors + mirror;
 		if (!p->rdev) {
-			if (mddev->gendisk)
-				disk_stack_limits(mddev->gendisk, rdev->bdev,
-						  rdev->data_offset << 9);
+			err = mddev_stack_new_rdev(mddev, rdev);
+			if (err)
+				return err;
 
-			p->head_position = 0;
-			rdev->raid_disk = mirror;
-			err = 0;
+			raid1_add_conf(conf, rdev, mirror, false);
 			/* As all devices are equivalent, we don't need a full recovery
 			 * if this was recently any drive of the array
 			 */
 			if (rdev->saved_raid_disk < 0)
 				conf->fullsync = 1;
-			WRITE_ONCE(p->rdev, rdev);
 			break;
 		}
 		if (test_bit(WantReplacement, &p->rdev->flags) &&
@@ -1813,13 +1945,11 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 
 	if (err && repl_slot >= 0) {
 		/* Add this device as a replacement */
-		p = conf->mirrors + repl_slot;
 		clear_bit(In_sync, &rdev->flags);
 		set_bit(Replacement, &rdev->flags);
-		rdev->raid_disk = repl_slot;
+		raid1_add_conf(conf, rdev, repl_slot, true);
 		err = 0;
 		conf->fullsync = 1;
-		WRITE_ONCE(p[conf->raid_disks].rdev, rdev);
 	}
 
 	print_conf(conf);
@@ -1836,27 +1966,20 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (unlikely(number >= conf->raid_disks))
 		goto abort;
 
-	if (rdev != p->rdev)
-		p = conf->mirrors + conf->raid_disks + number;
+	if (rdev != p->rdev) {
+		number += conf->raid_disks;
+		p = conf->mirrors + number;
+	}
 
 	print_conf(conf);
 	if (rdev == p->rdev) {
-		if (test_bit(In_sync, &rdev->flags) ||
-		    atomic_read(&rdev->nr_pending)) {
+		if (!raid1_remove_conf(conf, number)) {
 			err = -EBUSY;
 			goto abort;
 		}
-		/* Only remove non-faulty devices if recovery
-		 * is not possible.
-		 */
-		if (!test_bit(Faulty, &rdev->flags) &&
-		    mddev->recovery_disabled != conf->recovery_disabled &&
-		    mddev->degraded < conf->raid_disks) {
-			err = -EBUSY;
-			goto abort;
-		}
-		WRITE_ONCE(p->rdev, NULL);
-		if (conf->mirrors[conf->raid_disks + number].rdev) {
+
+		if (number < conf->raid_disks &&
+		    conf->mirrors[conf->raid_disks + number].rdev) {
 			/* We just removed a device that is being replaced.
 			 * Move down the replacement.  We drain all IO before
 			 * doing this to avoid confusion.
@@ -1944,8 +2067,6 @@ static void end_sync_write(struct bio *bio)
 	struct r1bio *r1_bio = get_resync_r1bio(bio);
 	struct mddev *mddev = r1_bio->mddev;
 	struct r1conf *conf = mddev->private;
-	sector_t first_bad;
-	int bad_sectors;
 	struct md_rdev *rdev = conf->mirrors[find_bio_disk(r1_bio, bio)].rdev;
 
 	if (!uptodate) {
@@ -1955,14 +2076,11 @@ static void end_sync_write(struct bio *bio)
 			set_bit(MD_RECOVERY_NEEDED, &
 				mddev->recovery);
 		set_bit(R1BIO_WriteError, &r1_bio->state);
-	} else if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
-			       &first_bad, &bad_sectors) &&
-		   !is_badblock(conf->mirrors[r1_bio->read_disk].rdev,
-				r1_bio->sector,
-				r1_bio->sectors,
-				&first_bad, &bad_sectors)
-		)
+	} else if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) &&
+		   !rdev_has_badblock(conf->mirrors[r1_bio->read_disk].rdev,
+				      r1_bio->sector, r1_bio->sectors)) {
 		set_bit(R1BIO_MadeGood, &r1_bio->state);
+	}
 
 	put_sync_write_buf(r1_bio, uptodate);
 }
@@ -2279,16 +2397,12 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 			s = PAGE_SIZE >> 9;
 
 		do {
-			sector_t first_bad;
-			int bad_sectors;
-
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
 			    (test_bit(In_sync, &rdev->flags) ||
 			     (!test_bit(Faulty, &rdev->flags) &&
 			      rdev->recovery_offset >= sect + s)) &&
-			    is_badblock(rdev, sect, s,
-					&first_bad, &bad_sectors) == 0) {
+			    rdev_has_badblock(rdev, sect, s) == 0) {
 				atomic_inc(&rdev->nr_pending);
 				if (sync_page_io(rdev, sect, s<<9,
 					 conf->tmppage, REQ_OP_READ, false))
@@ -3006,23 +3120,17 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 
 	err = -EINVAL;
 	spin_lock_init(&conf->device_lock);
+	conf->raid_disks = mddev->raid_disks;
 	rdev_for_each(rdev, mddev) {
 		int disk_idx = rdev->raid_disk;
-		if (disk_idx >= mddev->raid_disks
-		    || disk_idx < 0)
-			continue;
-		if (test_bit(Replacement, &rdev->flags))
-			disk = conf->mirrors + mddev->raid_disks + disk_idx;
-		else
-			disk = conf->mirrors + disk_idx;
 
-		if (disk->rdev)
+		if (disk_idx >= conf->raid_disks || disk_idx < 0)
+			continue;
+
+		if (!raid1_add_conf(conf, rdev, disk_idx,
+				    test_bit(Replacement, &rdev->flags)))
 			goto abort;
-		disk->rdev = rdev;
-		disk->head_position = 0;
-		disk->seq_start = MaxSector;
 	}
-	conf->raid_disks = mddev->raid_disks;
 	conf->mddev = mddev;
 	INIT_LIST_HEAD(&conf->retry_list);
 	INIT_LIST_HEAD(&conf->bio_end_io_list);
@@ -3086,12 +3194,21 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 	return ERR_PTR(err);
 }
 
+static int raid1_set_limits(struct mddev *mddev)
+{
+	struct queue_limits lim;
+
+	blk_set_stacking_limits(&lim);
+	lim.max_write_zeroes_sectors = 0;
+	mddev_stack_rdev_limits(mddev, &lim);
+	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;
 	int i;
-	struct md_rdev *rdev;
 	int ret;
 
 	if (mddev->level != 1) {
@@ -3118,14 +3235,10 @@ static int raid1_run(struct mddev *mddev)
 	if (IS_ERR(conf))
 		return PTR_ERR(conf);
 
-	if (mddev->queue)
-		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-
-	rdev_for_each(rdev, mddev) {
-		if (!mddev->gendisk)
-			continue;
-		disk_stack_limits(mddev->gendisk, rdev->bdev,
-				  rdev->data_offset << 9);
+	if (!mddev_is_dm(mddev)) {
+		ret = raid1_set_limits(mddev);
+		if (ret)
+			goto abort;
 	}
 
 	mddev->degraded = 0;

drivers/md/raid1.h

@@ -71,6 +71,7 @@ struct r1conf {
 						 * allow for replacements.
 						 */
 	int			raid_disks;
+	int			nonrot_disks;
 
 	spinlock_t		device_lock;
 

drivers/md/raid10.c

@@ -76,9 +76,6 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio);
 static void end_reshape_write(struct bio *bio);
 static void end_reshape(struct r10conf *conf);
 
-#define raid10_log(md, fmt, args...)				\
-	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid10 " fmt, ##args); } while (0)
-
 #include "raid1-10.c"
 
 #define NULL_CMD
@@ -518,11 +515,7 @@ static void raid10_end_write_request(struct bio *bio)
 		 * The 'master' represents the composite IO operation to
 		 * user-side. So if something waits for IO, then it will
 		 * wait for the 'master' bio.
-		 */
-		sector_t first_bad;
-		int bad_sectors;
-
-		/*
+		 *
 		 * Do not set R10BIO_Uptodate if the current device is
 		 * rebuilding or Faulty. This is because we cannot use
 		 * such device for properly reading the data back (we could
@@ -535,10 +528,9 @@ static void raid10_end_write_request(struct bio *bio)
 			set_bit(R10BIO_Uptodate, &r10_bio->state);
 
 		/* Maybe we can clear some bad blocks. */
-		if (is_badblock(rdev,
-				r10_bio->devs[slot].addr,
-				r10_bio->sectors,
-				&first_bad, &bad_sectors) && !discard_error) {
+		if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr,
+				      r10_bio->sectors) &&
+		    !discard_error) {
 			bio_put(bio);
 			if (repl)
 				r10_bio->devs[slot].repl_bio = IO_MADE_GOOD;
@@ -753,17 +745,8 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 	best_good_sectors = 0;
 	do_balance = 1;
 	clear_bit(R10BIO_FailFast, &r10_bio->state);
-	/*
-	 * Check if we can balance. We can balance on the whole
-	 * device if no resync is going on (recovery is ok), or below
-	 * the resync window. We take the first readable disk when
-	 * above the resync window.
-	 */
-	if ((conf->mddev->recovery_cp < MaxSector
-	     && (this_sector + sectors >= conf->next_resync)) ||
-	    (mddev_is_clustered(conf->mddev) &&
-	     md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
-					    this_sector + sectors)))
+
+	if (raid1_should_read_first(conf->mddev, this_sector, sectors))
 		do_balance = 0;
 
 	for (slot = 0; slot < conf->copies ; slot++) {
@@ -1033,7 +1016,7 @@ static bool wait_barrier(struct r10conf *conf, bool nowait)
 			ret = false;
 		} else {
 			conf->nr_waiting++;
-			raid10_log(conf->mddev, "wait barrier");
+			mddev_add_trace_msg(conf->mddev, "raid10 wait barrier");
 			wait_event_barrier(conf, stop_waiting_barrier(conf));
 			conf->nr_waiting--;
 		}
@@ -1152,7 +1135,7 @@ static bool regular_request_wait(struct mddev *mddev, struct r10conf *conf,
 			bio_wouldblock_error(bio);
 			return false;
 		}
-		raid10_log(conf->mddev, "wait reshape");
+		mddev_add_trace_msg(conf->mddev, "raid10 wait reshape");
 		wait_event(conf->wait_barrier,
 			   conf->reshape_progress <= bio->bi_iter.bi_sector ||
 			   conf->reshape_progress >= bio->bi_iter.bi_sector +
@@ -1249,10 +1232,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	    test_bit(R10BIO_FailFast, &r10_bio->state))
 	        read_bio->bi_opf |= MD_FAILFAST;
 	read_bio->bi_private = r10_bio;
-
-	if (mddev->gendisk)
-	        trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk),
-	                              r10_bio->sector);
+	mddev_trace_remap(mddev, read_bio, r10_bio->sector);
 	submit_bio_noacct(read_bio);
 	return;
 }
@@ -1288,10 +1268,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 			 && enough(conf, devnum))
 		mbio->bi_opf |= MD_FAILFAST;
 	mbio->bi_private = r10_bio;
-
-	if (conf->mddev->gendisk)
-		trace_block_bio_remap(mbio, disk_devt(conf->mddev->gendisk),
-				      r10_bio->sector);
+	mddev_trace_remap(mddev, mbio, r10_bio->sector);
 	/* flush_pending_writes() needs access to the rdev so...*/
 	mbio->bi_bdev = (void *)rdev;
 
@@ -1330,10 +1307,7 @@ retry_wait:
 		}
 
 		if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
-			sector_t first_bad;
 			sector_t dev_sector = r10_bio->devs[i].addr;
-			int bad_sectors;
-			int is_bad;
 
 			/*
 			 * Discard request doesn't care the write result
@@ -1342,9 +1316,8 @@ retry_wait:
 			if (!r10_bio->sectors)
 				continue;
 
-			is_bad = is_badblock(rdev, dev_sector, r10_bio->sectors,
-					     &first_bad, &bad_sectors);
-			if (is_bad < 0) {
+			if (rdev_has_badblock(rdev, dev_sector,
+					      r10_bio->sectors) < 0) {
 				/*
 				 * Mustn't write here until the bad block
 				 * is acknowledged
@@ -1360,8 +1333,9 @@ retry_wait:
 	if (unlikely(blocked_rdev)) {
 		/* Have to wait for this device to get unblocked, then retry */
 		allow_barrier(conf);
-		raid10_log(conf->mddev, "%s wait rdev %d blocked",
-				__func__, blocked_rdev->raid_disk);
+		mddev_add_trace_msg(conf->mddev,
+			"raid10 %s wait rdev %d blocked",
+			__func__, blocked_rdev->raid_disk);
 		md_wait_for_blocked_rdev(blocked_rdev, mddev);
 		wait_barrier(conf, false);
 		goto retry_wait;
@@ -1416,7 +1390,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 			bio_wouldblock_error(bio);
 			return;
 		}
-		raid10_log(conf->mddev, "wait reshape metadata");
+		mddev_add_trace_msg(conf->mddev,
+			"raid10 wait reshape metadata");
 		wait_event(mddev->sb_wait,
 			   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 
@@ -2131,10 +2106,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			continue;
 		}
 
-		if (mddev->gendisk)
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-
+		err = mddev_stack_new_rdev(mddev, rdev);
+		if (err)
+			return err;
 		p->head_position = 0;
 		p->recovery_disabled = mddev->recovery_disabled - 1;
 		rdev->raid_disk = mirror;
@@ -2150,10 +2124,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		clear_bit(In_sync, &rdev->flags);
 		set_bit(Replacement, &rdev->flags);
 		rdev->raid_disk = repl_slot;
-		err = 0;
-		if (mddev->gendisk)
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
+		err = mddev_stack_new_rdev(mddev, rdev);
+		if (err)
+			return err;
 		conf->fullsync = 1;
 		WRITE_ONCE(p->replacement, rdev);
 	}
@@ -2290,8 +2263,6 @@ static void end_sync_write(struct bio *bio)
 	struct mddev *mddev = r10_bio->mddev;
 	struct r10conf *conf = mddev->private;
 	int d;
-	sector_t first_bad;
-	int bad_sectors;
 	int slot;
 	int repl;
 	struct md_rdev *rdev = NULL;
@@ -2312,11 +2283,10 @@ static void end_sync_write(struct bio *bio)
 					&rdev->mddev->recovery);
 			set_bit(R10BIO_WriteError, &r10_bio->state);
 		}
-	} else if (is_badblock(rdev,
-			     r10_bio->devs[slot].addr,
-			     r10_bio->sectors,
-			     &first_bad, &bad_sectors))
+	} else if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr,
+				     r10_bio->sectors)) {
 		set_bit(R10BIO_MadeGood, &r10_bio->state);
+	}
 
 	rdev_dec_pending(rdev, mddev);
 
@@ -2597,11 +2567,8 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector,
 			    int sectors, struct page *page, enum req_op op)
 {
-	sector_t first_bad;
-	int bad_sectors;
-
-	if (is_badblock(rdev, sector, sectors, &first_bad, &bad_sectors)
-	    && (op == REQ_OP_READ || test_bit(WriteErrorSeen, &rdev->flags)))
+	if (rdev_has_badblock(rdev, sector, sectors) &&
+	    (op == REQ_OP_READ || test_bit(WriteErrorSeen, &rdev->flags)))
 		return -1;
 	if (sync_page_io(rdev, sector, sectors << 9, page, op, false))
 		/* success */
@@ -2658,16 +2625,14 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			s = PAGE_SIZE >> 9;
 
 		do {
-			sector_t first_bad;
-			int bad_sectors;
-
 			d = r10_bio->devs[sl].devnum;
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
 			    test_bit(In_sync, &rdev->flags) &&
 			    !test_bit(Faulty, &rdev->flags) &&
-			    is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
-					&first_bad, &bad_sectors) == 0) {
+			    rdev_has_badblock(rdev,
+					      r10_bio->devs[sl].addr + sect,
+					      s) == 0) {
 				atomic_inc(&rdev->nr_pending);
 				success = sync_page_io(rdev,
 						       r10_bio->devs[sl].addr +
@@ -4002,14 +3967,26 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 	return ERR_PTR(err);
 }
 
-static void raid10_set_io_opt(struct r10conf *conf)
+static unsigned int raid10_nr_stripes(struct r10conf *conf)
 {
-	int raid_disks = conf->geo.raid_disks;
+	unsigned int raid_disks = conf->geo.raid_disks;
 
-	if (!(conf->geo.raid_disks % conf->geo.near_copies))
-		raid_disks /= conf->geo.near_copies;
-	blk_queue_io_opt(conf->mddev->queue, (conf->mddev->chunk_sectors << 9) *
-			 raid_disks);
+	if (conf->geo.raid_disks % conf->geo.near_copies)
+		return raid_disks;
+	return raid_disks / conf->geo.near_copies;
+}
+
+static int raid10_set_queue_limits(struct mddev *mddev)
+{
+	struct r10conf *conf = mddev->private;
+	struct queue_limits lim;
+
+	blk_set_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);
+	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
 static int raid10_run(struct mddev *mddev)
@@ -4021,6 +3998,7 @@ static int raid10_run(struct mddev *mddev)
 	sector_t size;
 	sector_t min_offset_diff = 0;
 	int first = 1;
+	int ret = -EIO;
 
 	if (mddev->private == NULL) {
 		conf = setup_conf(mddev);
@@ -4047,12 +4025,6 @@ static int raid10_run(struct mddev *mddev)
 		}
 	}
 
-	if (mddev->queue) {
-		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
-		raid10_set_io_opt(conf);
-	}
-
 	rdev_for_each(rdev, mddev) {
 		long long diff;
 
@@ -4081,14 +4053,16 @@ static int raid10_run(struct mddev *mddev)
 		if (first || diff < min_offset_diff)
 			min_offset_diff = diff;
 
-		if (mddev->gendisk)
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-
 		disk->head_position = 0;
 		first = 0;
 	}
 
+	if (!mddev_is_dm(conf->mddev)) {
+		ret = raid10_set_queue_limits(mddev);
+		if (ret)
+			goto out_free_conf;
+	}
+
 	/* need to check that every block has at least one working mirror */
 	if (!enough(conf, -1)) {
 		pr_err("md/raid10:%s: not enough operational mirrors.\n",
@@ -4185,7 +4159,7 @@ out_free_conf:
 	raid10_free_conf(conf);
 	mddev->private = NULL;
 out:
-	return -EIO;
+	return ret;
 }
 
 static void raid10_free(struct mddev *mddev, void *priv)
@@ -4954,8 +4928,7 @@ static void end_reshape(struct r10conf *conf)
 	conf->reshape_safe = MaxSector;
 	spin_unlock_irq(&conf->device_lock);
 
-	if (conf->mddev->queue)
-		raid10_set_io_opt(conf);
+	mddev_update_io_opt(conf->mddev, raid10_nr_stripes(conf));
 	conf->fullsync = 0;
 }
 

drivers/md/raid5-ppl.c

@@ -1393,7 +1393,8 @@ int ppl_init_log(struct r5conf *conf)
 		ppl_conf->signature = ~crc32c_le(~0, mddev->uuid, sizeof(mddev->uuid));
 		ppl_conf->block_size = 512;
 	} else {
-		ppl_conf->block_size = queue_logical_block_size(mddev->queue);
+		ppl_conf->block_size =
+			queue_logical_block_size(mddev->gendisk->queue);
 	}
 
 	for (i = 0; i < ppl_conf->count; i++) {

drivers/md/raid5.c

@@ -36,6 +36,7 @@
  */
 
 #include <linux/blkdev.h>
+#include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/async_tx.h>
@@ -760,6 +761,7 @@ enum stripe_result {
 	STRIPE_RETRY,
 	STRIPE_SCHEDULE_AND_RETRY,
 	STRIPE_FAIL,
+	STRIPE_WAIT_RESHAPE,
 };
 
 struct stripe_request_ctx {
@@ -1210,10 +1212,8 @@ again:
 		 */
 		while (op_is_write(op) && rdev &&
 		       test_bit(WriteErrorSeen, &rdev->flags)) {
-			sector_t first_bad;
-			int bad_sectors;
-			int bad = is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf),
-					      &first_bad, &bad_sectors);
+			int bad = rdev_has_badblock(rdev, sh->sector,
+						    RAID5_STRIPE_SECTORS(conf));
 			if (!bad)
 				break;
 
@@ -1295,10 +1295,7 @@ again:
 			if (rrdev)
 				set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
 
-			if (conf->mddev->gendisk)
-				trace_block_bio_remap(bi,
-						disk_devt(conf->mddev->gendisk),
-						sh->dev[i].sector);
+			mddev_trace_remap(conf->mddev, bi, sh->dev[i].sector);
 			if (should_defer && op_is_write(op))
 				bio_list_add(&pending_bios, bi);
 			else
@@ -1342,10 +1339,7 @@ again:
 			 */
 			if (op == REQ_OP_DISCARD)
 				rbi->bi_vcnt = 0;
-			if (conf->mddev->gendisk)
-				trace_block_bio_remap(rbi,
-						disk_devt(conf->mddev->gendisk),
-						sh->dev[i].sector);
+			mddev_trace_remap(conf->mddev, rbi, sh->dev[i].sector);
 			if (should_defer && op_is_write(op))
 				bio_list_add(&pending_bios, rbi);
 			else
@@ -2412,7 +2406,7 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
 	atomic_inc(&conf->active_stripes);
 
 	raid5_release_stripe(sh);
-	conf->max_nr_stripes++;
+	WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes + 1);
 	return 1;
 }
 
@@ -2422,12 +2416,12 @@ static int grow_stripes(struct r5conf *conf, int num)
 	size_t namelen = sizeof(conf->cache_name[0]);
 	int devs = max(conf->raid_disks, conf->previous_raid_disks);
 
-	if (conf->mddev->gendisk)
-		snprintf(conf->cache_name[0], namelen,
-			"raid%d-%s", conf->level, mdname(conf->mddev));
-	else
+	if (mddev_is_dm(conf->mddev))
 		snprintf(conf->cache_name[0], namelen,
 			"raid%d-%p", conf->level, conf->mddev);
+	else
+		snprintf(conf->cache_name[0], namelen,
+			"raid%d-%s", conf->level, mdname(conf->mddev));
 	snprintf(conf->cache_name[1], namelen, "%.27s-alt", conf->cache_name[0]);
 
 	conf->active_name = 0;
@@ -2707,7 +2701,7 @@ static int drop_one_stripe(struct r5conf *conf)
 	shrink_buffers(sh);
 	free_stripe(conf->slab_cache, sh);
 	atomic_dec(&conf->active_stripes);
-	conf->max_nr_stripes--;
+	WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes - 1);
 	return 1;
 }
 
@@ -2855,8 +2849,6 @@ static void raid5_end_write_request(struct bio *bi)
 	struct r5conf *conf = sh->raid_conf;
 	int disks = sh->disks, i;
 	struct md_rdev *rdev;
-	sector_t first_bad;
-	int bad_sectors;
 	int replacement = 0;
 
 	for (i = 0 ; i < disks; i++) {
@@ -2888,9 +2880,8 @@ static void raid5_end_write_request(struct bio *bi)
 	if (replacement) {
 		if (bi->bi_status)
 			md_error(conf->mddev, rdev);
-		else if (is_badblock(rdev, sh->sector,
-				     RAID5_STRIPE_SECTORS(conf),
-				     &first_bad, &bad_sectors))
+		else if (rdev_has_badblock(rdev, sh->sector,
+					   RAID5_STRIPE_SECTORS(conf)))
 			set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
 	} else {
 		if (bi->bi_status) {
@@ -2900,9 +2891,8 @@ static void raid5_end_write_request(struct bio *bi)
 			if (!test_and_set_bit(WantReplacement, &rdev->flags))
 				set_bit(MD_RECOVERY_NEEDED,
 					&rdev->mddev->recovery);
-		} else if (is_badblock(rdev, sh->sector,
-				       RAID5_STRIPE_SECTORS(conf),
-				       &first_bad, &bad_sectors)) {
+		} else if (rdev_has_badblock(rdev, sh->sector,
+					     RAID5_STRIPE_SECTORS(conf))) {
 			set_bit(R5_MadeGood, &sh->dev[i].flags);
 			if (test_bit(R5_ReadError, &sh->dev[i].flags))
 				/* That was a successful write so make
@@ -4205,10 +4195,9 @@ static int handle_stripe_dirtying(struct r5conf *conf,
 	set_bit(STRIPE_HANDLE, &sh->state);
 	if ((rmw < rcw || (rmw == rcw && conf->rmw_level == PARITY_PREFER_RMW)) && rmw > 0) {
 		/* prefer read-modify-write, but need to get some data */
-		if (conf->mddev->queue)
-			blk_add_trace_msg(conf->mddev->queue,
-					  "raid5 rmw %llu %d",
-					  (unsigned long long)sh->sector, rmw);
+		mddev_add_trace_msg(conf->mddev, "raid5 rmw %llu %d",
+				sh->sector, rmw);
+
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
 			if (test_bit(R5_InJournal, &dev->flags) &&
@@ -4285,10 +4274,11 @@ static int handle_stripe_dirtying(struct r5conf *conf,
 					set_bit(STRIPE_DELAYED, &sh->state);
 			}
 		}
-		if (rcw && conf->mddev->queue)
-			blk_add_trace_msg(conf->mddev->queue, "raid5 rcw %llu %d %d %d",
-					  (unsigned long long)sh->sector,
-					  rcw, qread, test_bit(STRIPE_DELAYED, &sh->state));
+		if (rcw && !mddev_is_dm(conf->mddev))
+			blk_add_trace_msg(conf->mddev->gendisk->queue,
+				"raid5 rcw %llu %d %d %d",
+				(unsigned long long)sh->sector, rcw, qread,
+				test_bit(STRIPE_DELAYED, &sh->state));
 	}
 
 	if (rcw > disks && rmw > disks &&
@@ -4674,8 +4664,6 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 	/* Now to look around and see what can be done */
 	for (i=disks; i--; ) {
 		struct md_rdev *rdev;
-		sector_t first_bad;
-		int bad_sectors;
 		int is_bad = 0;
 
 		dev = &sh->dev[i];
@@ -4719,8 +4707,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		rdev = conf->disks[i].replacement;
 		if (rdev && !test_bit(Faulty, &rdev->flags) &&
 		    rdev->recovery_offset >= sh->sector + RAID5_STRIPE_SECTORS(conf) &&
-		    !is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf),
-				 &first_bad, &bad_sectors))
+		    !rdev_has_badblock(rdev, sh->sector,
+				       RAID5_STRIPE_SECTORS(conf)))
 			set_bit(R5_ReadRepl, &dev->flags);
 		else {
 			if (rdev && !test_bit(Faulty, &rdev->flags))
@@ -4733,8 +4721,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		if (rdev && test_bit(Faulty, &rdev->flags))
 			rdev = NULL;
 		if (rdev) {
-			is_bad = is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf),
-					     &first_bad, &bad_sectors);
+			is_bad = rdev_has_badblock(rdev, sh->sector,
+						   RAID5_STRIPE_SECTORS(conf));
 			if (s->blocked_rdev == NULL
 			    && (test_bit(Blocked, &rdev->flags)
 				|| is_bad < 0)) {
@@ -5463,8 +5451,8 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 	struct r5conf *conf = mddev->private;
 	struct bio *align_bio;
 	struct md_rdev *rdev;
-	sector_t sector, end_sector, first_bad;
-	int bad_sectors, dd_idx;
+	sector_t sector, end_sector;
+	int dd_idx;
 	bool did_inc;
 
 	if (!in_chunk_boundary(mddev, raid_bio)) {
@@ -5493,8 +5481,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 
 	atomic_inc(&rdev->nr_pending);
 
-	if (is_badblock(rdev, sector, bio_sectors(raid_bio), &first_bad,
-			&bad_sectors)) {
+	if (rdev_has_badblock(rdev, sector, bio_sectors(raid_bio))) {
 		rdev_dec_pending(rdev, mddev);
 		return 0;
 	}
@@ -5530,9 +5517,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 		spin_unlock_irq(&conf->device_lock);
 	}
 
-	if (mddev->gendisk)
-		trace_block_bio_remap(align_bio, disk_devt(mddev->gendisk),
-				      raid_bio->bi_iter.bi_sector);
+	mddev_trace_remap(mddev, align_bio, raid_bio->bi_iter.bi_sector);
 	submit_bio_noacct(align_bio);
 	return 1;
 }
@@ -5701,8 +5686,8 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
 	}
 	release_inactive_stripe_list(conf, cb->temp_inactive_list,
 				     NR_STRIPE_HASH_LOCKS);
-	if (mddev->queue)
-		trace_block_unplug(mddev->queue, cnt, !from_schedule);
+	if (!mddev_is_dm(mddev))
+		trace_block_unplug(mddev->gendisk->queue, cnt, !from_schedule);
 	kfree(cb);
 }
 
@@ -5946,7 +5931,8 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
 			if (ahead_of_reshape(mddev, logical_sector,
 					     conf->reshape_safe)) {
 				spin_unlock_irq(&conf->device_lock);
-				return STRIPE_SCHEDULE_AND_RETRY;
+				ret = STRIPE_SCHEDULE_AND_RETRY;
+				goto out;
 			}
 		}
 		spin_unlock_irq(&conf->device_lock);
@@ -6025,6 +6011,12 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
 
 out_release:
 	raid5_release_stripe(sh);
+out:
+	if (ret == STRIPE_SCHEDULE_AND_RETRY && reshape_interrupted(mddev)) {
+		bi->bi_status = BLK_STS_RESOURCE;
+		ret = STRIPE_WAIT_RESHAPE;
+		pr_err_ratelimited("dm-raid456: io across reshape position while reshape can't make progress");
+	}
 	return ret;
 }
 
@@ -6146,7 +6138,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 	while (1) {
 		res = make_stripe_request(mddev, conf, &ctx, logical_sector,
 					  bi);
-		if (res == STRIPE_FAIL)
+		if (res == STRIPE_FAIL || res == STRIPE_WAIT_RESHAPE)
 			break;
 
 		if (res == STRIPE_RETRY)
@@ -6184,6 +6176,11 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 
 	if (rw == WRITE)
 		md_write_end(mddev);
+	if (res == STRIPE_WAIT_RESHAPE) {
+		md_free_cloned_bio(bi);
+		return false;
+	}
+
 	bio_endio(bi);
 	return true;
 }
@@ -6773,7 +6770,18 @@ static void raid5d(struct md_thread *thread)
 			spin_unlock_irq(&conf->device_lock);
 			md_check_recovery(mddev);
 			spin_lock_irq(&conf->device_lock);
+
+			/*
+			 * Waiting on MD_SB_CHANGE_PENDING below may deadlock
+			 * seeing md_check_recovery() is needed to clear
+			 * the flag when using mdmon.
+			 */
+			continue;
 		}
+
+		wait_event_lock_irq(mddev->sb_wait,
+			!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
+			conf->device_lock);
 	}
 	pr_debug("%d stripes handled\n", handled);
 
@@ -6820,7 +6828,7 @@ raid5_set_cache_size(struct mddev *mddev, int size)
 	if (size <= 16 || size > 32768)
 		return -EINVAL;
 
-	conf->min_nr_stripes = size;
+	WRITE_ONCE(conf->min_nr_stripes, size);
 	mutex_lock(&conf->cache_size_mutex);
 	while (size < conf->max_nr_stripes &&
 	       drop_one_stripe(conf))
@@ -6832,7 +6840,7 @@ raid5_set_cache_size(struct mddev *mddev, int size)
 	mutex_lock(&conf->cache_size_mutex);
 	while (size > conf->max_nr_stripes)
 		if (!grow_one_stripe(conf, GFP_KERNEL)) {
-			conf->min_nr_stripes = conf->max_nr_stripes;
+			WRITE_ONCE(conf->min_nr_stripes, conf->max_nr_stripes);
 			result = -ENOMEM;
 			break;
 		}
@@ -6967,10 +6975,8 @@ raid5_store_stripe_size(struct mddev  *mddev, const char *page, size_t len)
 	pr_debug("md/raid: change stripe_size from %lu to %lu\n",
 			conf->stripe_size, new);
 
-	if (mddev->sync_thread ||
-		test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
-		mddev->reshape_position != MaxSector ||
-		mddev->sysfs_active) {
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+	    mddev->reshape_position != MaxSector || mddev->sysfs_active) {
 		err = -EBUSY;
 		goto out_unlock;
 	}
@@ -7084,7 +7090,7 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
 	if (!conf)
 		err = -ENODEV;
 	else if (new != conf->skip_copy) {
-		struct request_queue *q = mddev->queue;
+		struct request_queue *q = mddev->gendisk->queue;
 
 		conf->skip_copy = new;
 		if (new)
@@ -7390,11 +7396,13 @@ static unsigned long raid5_cache_count(struct shrinker *shrink,
 				       struct shrink_control *sc)
 {
 	struct r5conf *conf = shrink->private_data;
+	int max_stripes = READ_ONCE(conf->max_nr_stripes);
+	int min_stripes = READ_ONCE(conf->min_nr_stripes);
 
-	if (conf->max_nr_stripes < conf->min_nr_stripes)
+	if (max_stripes < min_stripes)
 		/* unlikely, but not impossible */
 		return 0;
-	return conf->max_nr_stripes - conf->min_nr_stripes;
+	return max_stripes - min_stripes;
 }
 
 static struct r5conf *setup_conf(struct mddev *mddev)
@@ -7684,10 +7692,65 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded
 	return 0;
 }
 
-static void raid5_set_io_opt(struct r5conf *conf)
+static int raid5_set_limits(struct mddev *mddev)
 {
-	blk_queue_io_opt(conf->mddev->queue, (conf->chunk_sectors << 9) *
-			 (conf->raid_disks - conf->max_degraded));
+	struct r5conf *conf = mddev->private;
+	struct queue_limits lim;
+	int data_disks, stripe;
+	struct md_rdev *rdev;
+
+	/*
+	 * The read-ahead size must cover two whole stripes, which is
+	 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices.
+	 */
+	data_disks = conf->previous_raid_disks - conf->max_degraded;
+
+	/*
+	 * We can only discard a whole stripe. It doesn't make sense to
+	 * discard data disk but write parity disk
+	 */
+	stripe = roundup_pow_of_two(data_disks * (mddev->chunk_sectors << 9));
+
+	blk_set_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.discard_granularity = stripe;
+	lim.max_write_zeroes_sectors = 0;
+	mddev_stack_rdev_limits(mddev, &lim);
+	rdev_for_each(rdev, mddev)
+		queue_limits_stack_bdev(&lim, rdev->bdev, rdev->new_data_offset,
+				mddev->gendisk->disk_name);
+
+	/*
+	 * Zeroing is required for discard, otherwise data could be lost.
+	 *
+	 * Consider a scenario: discard a stripe (the stripe could be
+	 * inconsistent if discard_zeroes_data is 0); write one disk of the
+	 * stripe (the stripe could be inconsistent again depending on which
+	 * disks are used to calculate parity); the disk is broken; The stripe
+	 * data of this disk is lost.
+	 *
+	 * We only allow DISCARD if the sysadmin has confirmed that only safe
+	 * devices are in use by setting a module parameter.  A better idea
+	 * might be to turn DISCARD into WRITE_ZEROES requests, as that is
+	 * required to be safe.
+	 */
+	if (!devices_handle_discard_safely ||
+	    lim.max_discard_sectors < (stripe >> 9) ||
+	    lim.discard_granularity < stripe)
+		lim.max_hw_discard_sectors = 0;
+
+	/*
+	 * Requests require having a bitmap for each stripe.
+	 * Limit the max sectors based on this.
+	 */
+	lim.max_hw_sectors = RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf);
+
+	/* No restrictions on the number of segments in the request */
+	lim.max_segments = USHRT_MAX;
+
+	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
 static int raid5_run(struct mddev *mddev)
@@ -7700,6 +7763,7 @@ static int raid5_run(struct mddev *mddev)
 	int i;
 	long long min_offset_diff = 0;
 	int first = 1;
+	int ret = -EIO;
 
 	if (mddev->recovery_cp != MaxSector)
 		pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
@@ -7948,66 +8012,10 @@ static int raid5_run(struct mddev *mddev)
 			mdname(mddev));
 	md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
 
-	if (mddev->queue) {
-		int chunk_size;
-		/* read-ahead size must cover two whole stripes, which
-		 * is 2 * (datadisks) * chunksize where 'n' is the
-		 * number of raid devices
-		 */
-		int data_disks = conf->previous_raid_disks - conf->max_degraded;
-		int stripe = data_disks *
-			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-
-		chunk_size = mddev->chunk_sectors << 9;
-		blk_queue_io_min(mddev->queue, chunk_size);
-		raid5_set_io_opt(conf);
-		mddev->queue->limits.raid_partial_stripes_expensive = 1;
-		/*
-		 * We can only discard a whole stripe. It doesn't make sense to
-		 * discard data disk but write parity disk
-		 */
-		stripe = stripe * PAGE_SIZE;
-		stripe = roundup_pow_of_two(stripe);
-		mddev->queue->limits.discard_granularity = stripe;
-
-		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-
-		rdev_for_each(rdev, mddev) {
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->new_data_offset << 9);
-		}
-
-		/*
-		 * zeroing is required, otherwise data
-		 * could be lost. Consider a scenario: discard a stripe
-		 * (the stripe could be inconsistent if
-		 * discard_zeroes_data is 0); write one disk of the
-		 * stripe (the stripe could be inconsistent again
-		 * depending on which disks are used to calculate
-		 * parity); the disk is broken; The stripe data of this
-		 * disk is lost.
-		 *
-		 * We only allow DISCARD if the sysadmin has confirmed that
-		 * only safe devices are in use by setting a module parameter.
-		 * A better idea might be to turn DISCARD into WRITE_ZEROES
-		 * requests, as that is required to be safe.
-		 */
-		if (!devices_handle_discard_safely ||
-		    mddev->queue->limits.max_discard_sectors < (stripe >> 9) ||
-		    mddev->queue->limits.discard_granularity < stripe)
-			blk_queue_max_discard_sectors(mddev->queue, 0);
-
-		/*
-		 * Requests require having a bitmap for each stripe.
-		 * Limit the max sectors based on this.
-		 */
-		blk_queue_max_hw_sectors(mddev->queue,
-			RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf));
-
-		/* No restrictions on the number of segments in the request */
-		blk_queue_max_segments(mddev->queue, USHRT_MAX);
+	if (!mddev_is_dm(mddev)) {
+		ret = raid5_set_limits(mddev);
+		if (ret)
+			goto abort;
 	}
 
 	if (log_init(conf, journal_dev, raid5_has_ppl(conf)))
@@ -8020,7 +8028,7 @@ abort:
 	free_conf(conf);
 	mddev->private = NULL;
 	pr_warn("md/raid:%s: failed to run raid set.\n", mdname(mddev));
-	return -EIO;
+	return ret;
 }
 
 static void raid5_free(struct mddev *mddev, void *priv)
@@ -8531,8 +8539,8 @@ static void end_reshape(struct r5conf *conf)
 		spin_unlock_irq(&conf->device_lock);
 		wake_up(&conf->wait_for_overlap);
 
-		if (conf->mddev->queue)
-			raid5_set_io_opt(conf);
+		mddev_update_io_opt(conf->mddev,
+			conf->raid_disks - conf->max_degraded);
 	}
 }
 
@@ -8909,6 +8917,18 @@ static int raid5_start(struct mddev *mddev)
 	return r5l_start(conf->log);
 }
 
+/*
+ * This is only used for dm-raid456, caller already frozen sync_thread, hence
+ * if rehsape is still in progress, io that is waiting for reshape can never be
+ * done now, hence wake up and handle those IO.
+ */
+static void raid5_prepare_suspend(struct mddev *mddev)
+{
+	struct r5conf *conf = mddev->private;
+
+	wake_up(&conf->wait_for_overlap);
+}
+
 static struct md_personality raid6_personality =
 {
 	.name		= "raid6",
@@ -8932,6 +8952,7 @@ static struct md_personality raid6_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
+	.prepare_suspend = raid5_prepare_suspend,
 };
 static struct md_personality raid5_personality =
 {
@@ -8956,6 +8977,7 @@ static struct md_personality raid5_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
+	.prepare_suspend = raid5_prepare_suspend,
 };
 
 static struct md_personality raid4_personality =
@@ -8981,6 +9003,7 @@ static struct md_personality raid4_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid4_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
+	.prepare_suspend = raid5_prepare_suspend,
 };
 
 static int __init raid5_init(void)

drivers/memstick/core/ms_block.c

@@ -2078,6 +2078,12 @@ static const struct blk_mq_ops msb_mq_ops = {
 static int msb_init_disk(struct memstick_dev *card)
 {
 	struct msb_data *msb = memstick_get_drvdata(card);
+	struct queue_limits lim = {
+		.logical_block_size	= msb->page_size,
+		.max_hw_sectors		= MS_BLOCK_MAX_PAGES,
+		.max_segments		= MS_BLOCK_MAX_SEGS,
+		.max_segment_size	= MS_BLOCK_MAX_PAGES * msb->page_size,
+	};
 	int rc;
 	unsigned long capacity;
 
@@ -2093,19 +2099,13 @@ static int msb_init_disk(struct memstick_dev *card)
 	if (rc)
 		goto out_release_id;
 
-	msb->disk = blk_mq_alloc_disk(&msb->tag_set, card);
+	msb->disk = blk_mq_alloc_disk(&msb->tag_set, &lim, card);
 	if (IS_ERR(msb->disk)) {
 		rc = PTR_ERR(msb->disk);
 		goto out_free_tag_set;
 	}
 	msb->queue = msb->disk->queue;
 
-	blk_queue_max_hw_sectors(msb->queue, MS_BLOCK_MAX_PAGES);
-	blk_queue_max_segments(msb->queue, MS_BLOCK_MAX_SEGS);
-	blk_queue_max_segment_size(msb->queue,
-				   MS_BLOCK_MAX_PAGES * msb->page_size);
-	blk_queue_logical_block_size(msb->queue, msb->page_size);
-
 	sprintf(msb->disk->disk_name, "msblk%d", msb->disk_id);
 	msb->disk->fops = &msb_bdops;
 	msb->disk->private_data = msb;

drivers/memstick/core/mspro_block.c

@@ -1103,6 +1103,12 @@ static const struct blk_mq_ops mspro_mq_ops = {
 static int mspro_block_init_disk(struct memstick_dev *card)
 {
 	struct mspro_block_data *msb = memstick_get_drvdata(card);
+	struct queue_limits lim = {
+		.logical_block_size	= msb->page_size,
+		.max_hw_sectors		= MSPRO_BLOCK_MAX_PAGES,
+		.max_segments		= MSPRO_BLOCK_MAX_SEGS,
+		.max_segment_size	= MSPRO_BLOCK_MAX_PAGES * msb->page_size,
+	};
 	struct mspro_devinfo *dev_info = NULL;
 	struct mspro_sys_info *sys_info = NULL;
 	struct mspro_sys_attr *s_attr = NULL;
@@ -1138,18 +1144,13 @@ static int mspro_block_init_disk(struct memstick_dev *card)
 	if (rc)
 		goto out_release_id;
 
-	msb->disk = blk_mq_alloc_disk(&msb->tag_set, card);
+	msb->disk = blk_mq_alloc_disk(&msb->tag_set, &lim, card);
 	if (IS_ERR(msb->disk)) {
 		rc = PTR_ERR(msb->disk);
 		goto out_free_tag_set;
 	}
 	msb->queue = msb->disk->queue;
 
-	blk_queue_max_hw_sectors(msb->queue, MSPRO_BLOCK_MAX_PAGES);
-	blk_queue_max_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS);
-	blk_queue_max_segment_size(msb->queue,
-				   MSPRO_BLOCK_MAX_PAGES * msb->page_size);
-
 	msb->disk->major = major;
 	msb->disk->first_minor = disk_id << MSPRO_BLOCK_PART_SHIFT;
 	msb->disk->minors = 1 << MSPRO_BLOCK_PART_SHIFT;
@@ -1158,8 +1159,6 @@ static int mspro_block_init_disk(struct memstick_dev *card)
 
 	sprintf(msb->disk->disk_name, "mspblk%d", disk_id);
 
-	blk_queue_logical_block_size(msb->queue, msb->page_size);
-
 	capacity = be16_to_cpu(sys_info->user_block_count);
 	capacity *= be16_to_cpu(sys_info->block_size);
 	capacity *= msb->page_size >> 9;

drivers/mmc/core/queue.c

@@ -174,8 +174,8 @@ static struct scatterlist *mmc_alloc_sg(unsigned short sg_len, gfp_t gfp)
 	return sg;
 }
 
-static void mmc_queue_setup_discard(struct request_queue *q,
-				    struct mmc_card *card)
+static void mmc_queue_setup_discard(struct mmc_card *card,
+		struct queue_limits *lim)
 {
 	unsigned max_discard;
 
@@ -183,15 +183,17 @@ static void mmc_queue_setup_discard(struct request_queue *q,
 	if (!max_discard)
 		return;
 
-	blk_queue_max_discard_sectors(q, max_discard);
-	q->limits.discard_granularity = card->pref_erase << 9;
+	lim->max_hw_discard_sectors = max_discard;
+	if (mmc_can_secure_erase_trim(card))
+		lim->max_secure_erase_sectors = max_discard;
+	if (mmc_can_trim(card) && card->erased_byte == 0)
+		lim->max_write_zeroes_sectors = max_discard;
+
 	/* granularity must not be greater than max. discard */
 	if (card->pref_erase > max_discard)
-		q->limits.discard_granularity = SECTOR_SIZE;
-	if (mmc_can_secure_erase_trim(card))
-		blk_queue_max_secure_erase_sectors(q, max_discard);
-	if (mmc_can_trim(card) && card->erased_byte == 0)
-		blk_queue_max_write_zeroes_sectors(q, max_discard);
+		lim->discard_granularity = SECTOR_SIZE;
+	else
+		lim->discard_granularity = card->pref_erase << 9;
 }
 
 static unsigned short mmc_get_max_segments(struct mmc_host *host)
@@ -341,40 +343,53 @@ static const struct blk_mq_ops mmc_mq_ops = {
 	.timeout	= mmc_mq_timed_out,
 };
 
-static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
+static struct gendisk *mmc_alloc_disk(struct mmc_queue *mq,
+		struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
-	unsigned block_size = 512;
+	struct queue_limits lim = { };
+	struct gendisk *disk;
+
+	if (mmc_can_erase(card))
+		mmc_queue_setup_discard(card, &lim);
+
+	if (!mmc_dev(host)->dma_mask || !*mmc_dev(host)->dma_mask)
+		lim.bounce = BLK_BOUNCE_HIGH;
+
+	lim.max_hw_sectors = min(host->max_blk_count, host->max_req_size / 512);
+
+	if (mmc_card_mmc(card) && card->ext_csd.data_sector_size)
+		lim.logical_block_size = card->ext_csd.data_sector_size;
+	else
+		lim.logical_block_size = 512;
+
+	WARN_ON_ONCE(lim.logical_block_size != 512 &&
+		     lim.logical_block_size != 4096);
+
+	/*
+	 * Setting a virt_boundary implicity sets a max_segment_size, so try
+	 * to set the hardware one here.
+	 */
+	if (host->can_dma_map_merge) {
+		lim.virt_boundary_mask = dma_get_merge_boundary(mmc_dev(host));
+		lim.max_segments = MMC_DMA_MAP_MERGE_SEGMENTS;
+	} else {
+		lim.max_segment_size =
+			round_down(host->max_seg_size, lim.logical_block_size);
+		lim.max_segments = host->max_segs;
+	}
+
+	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);
-	if (mmc_can_erase(card))
-		mmc_queue_setup_discard(mq->queue, card);
-
-	if (!mmc_dev(host)->dma_mask || !*mmc_dev(host)->dma_mask)
-		blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_HIGH);
-	blk_queue_max_hw_sectors(mq->queue,
-		min(host->max_blk_count, host->max_req_size / 512));
-	if (host->can_dma_map_merge)
-		WARN(!blk_queue_can_use_dma_map_merging(mq->queue,
-							mmc_dev(host)),
-		     "merging was advertised but not possible");
-	blk_queue_max_segments(mq->queue, mmc_get_max_segments(host));
-
-	if (mmc_card_mmc(card) && card->ext_csd.data_sector_size) {
-		block_size = card->ext_csd.data_sector_size;
-		WARN_ON(block_size != 512 && block_size != 4096);
-	}
-
-	blk_queue_logical_block_size(mq->queue, block_size);
-	/*
-	 * After blk_queue_can_use_dma_map_merging() was called with succeed,
-	 * since it calls blk_queue_virt_boundary(), the mmc should not call
-	 * both blk_queue_max_segment_size().
-	 */
-	if (!host->can_dma_map_merge)
-		blk_queue_max_segment_size(mq->queue,
-			round_down(host->max_seg_size, block_size));
 
 	dma_set_max_seg_size(mmc_dev(host), queue_max_segment_size(mq->queue));
 
@@ -386,6 +401,7 @@ static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
 	init_waitqueue_head(&mq->wait);
 
 	mmc_crypto_setup_queue(mq->queue, host);
+	return disk;
 }
 
 static inline bool mmc_merge_capable(struct mmc_host *host)
@@ -447,18 +463,9 @@ struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card)
 		return ERR_PTR(ret);
 		
 
-	disk = blk_mq_alloc_disk(&mq->tag_set, mq);
-	if (IS_ERR(disk)) {
+	disk = mmc_alloc_disk(mq, card);
+	if (IS_ERR(disk))
 		blk_mq_free_tag_set(&mq->tag_set);
-		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);
-
-	mmc_setup_queue(mq, card);
 	return disk;
 }
 

drivers/mtd/mtd_blkdevs.c

@@ -277,6 +277,7 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 {
 	struct mtd_blktrans_ops *tr = new->tr;
 	struct mtd_blktrans_dev *d;
+	struct queue_limits lim = { };
 	int last_devnum = -1;
 	struct gendisk *gd;
 	int ret;
@@ -331,9 +332,13 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 			BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING);
 	if (ret)
 		goto out_kfree_tag_set;
+	
+	lim.logical_block_size = tr->blksize;
+	if (tr->discard)
+		lim.max_hw_discard_sectors = UINT_MAX;
 
 	/* Create gendisk */
-	gd = blk_mq_alloc_disk(new->tag_set, new);
+	gd = blk_mq_alloc_disk(new->tag_set, &lim, new);
 	if (IS_ERR(gd)) {
 		ret = PTR_ERR(gd);
 		goto out_free_tag_set;
@@ -371,14 +376,9 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 	if (tr->flush)
 		blk_queue_write_cache(new->rq, true, false);
 
-	blk_queue_logical_block_size(new->rq, tr->blksize);
-
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, new->rq);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, new->rq);
 
-	if (tr->discard)
-		blk_queue_max_discard_sectors(new->rq, UINT_MAX);
-
 	gd->queue = new->rq;
 
 	if (new->readonly)

drivers/mtd/ubi/block.c

@@ -348,6 +348,9 @@ static int calc_disk_capacity(struct ubi_volume_info *vi, u64 *disk_capacity)
 
 int ubiblock_create(struct ubi_volume_info *vi)
 {
+	struct queue_limits lim = {
+		.max_segments		= UBI_MAX_SG_COUNT,
+	};
 	struct ubiblock *dev;
 	struct gendisk *gd;
 	u64 disk_capacity;
@@ -393,7 +396,7 @@ int ubiblock_create(struct ubi_volume_info *vi)
 
 
 	/* Initialize the gendisk of this ubiblock device */
-	gd = blk_mq_alloc_disk(&dev->tag_set, dev);
+	gd = blk_mq_alloc_disk(&dev->tag_set, &lim, dev);
 	if (IS_ERR(gd)) {
 		ret = PTR_ERR(gd);
 		goto out_free_tags;
@@ -416,7 +419,6 @@ int ubiblock_create(struct ubi_volume_info *vi)
 	dev->gd = gd;
 
 	dev->rq = gd->queue;
-	blk_queue_max_segments(dev->rq, UBI_MAX_SG_COUNT);
 
 	list_add_tail(&dev->list, &ubiblock_devices);
 

drivers/nvdimm/btt.c

@@ -1496,19 +1496,21 @@ static int btt_blk_init(struct btt *btt)
 {
 	struct nd_btt *nd_btt = btt->nd_btt;
 	struct nd_namespace_common *ndns = nd_btt->ndns;
-	int rc = -ENOMEM;
+	struct queue_limits lim = {
+		.logical_block_size	= btt->sector_size,
+		.max_hw_sectors		= UINT_MAX,
+	};
+	int rc;
 
-	btt->btt_disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!btt->btt_disk)
-		return -ENOMEM;
+	btt->btt_disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(btt->btt_disk))
+		return PTR_ERR(btt->btt_disk);
 
 	nvdimm_namespace_disk_name(ndns, btt->btt_disk->disk_name);
 	btt->btt_disk->first_minor = 0;
 	btt->btt_disk->fops = &btt_fops;
 	btt->btt_disk->private_data = btt;
 
-	blk_queue_logical_block_size(btt->btt_disk->queue, btt->sector_size);
-	blk_queue_max_hw_sectors(btt->btt_disk->queue, UINT_MAX);
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, btt->btt_disk->queue);
 	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, btt->btt_disk->queue);
 

drivers/nvdimm/pmem.c

@@ -451,6 +451,11 @@ static int pmem_attach_disk(struct device *dev,
 {
 	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
 	struct nd_region *nd_region = to_nd_region(dev->parent);
+	struct queue_limits lim = {
+		.logical_block_size	= pmem_sector_size(ndns),
+		.physical_block_size	= PAGE_SIZE,
+		.max_hw_sectors		= UINT_MAX,
+	};
 	int nid = dev_to_node(dev), fua;
 	struct resource *res = &nsio->res;
 	struct range bb_range;
@@ -497,9 +502,9 @@ static int pmem_attach_disk(struct device *dev,
 		return -EBUSY;
 	}
 
-	disk = blk_alloc_disk(nid);
-	if (!disk)
-		return -ENOMEM;
+	disk = blk_alloc_disk(&lim, nid);
+	if (IS_ERR(disk))
+		return PTR_ERR(disk);
 	q = disk->queue;
 
 	pmem->disk = disk;
@@ -539,9 +544,6 @@ static int pmem_attach_disk(struct device *dev,
 	pmem->virt_addr = addr;
 
 	blk_queue_write_cache(q, true, fua);
-	blk_queue_physical_block_size(q, PAGE_SIZE);
-	blk_queue_logical_block_size(q, pmem_sector_size(ndns));
-	blk_queue_max_hw_sectors(q, UINT_MAX);
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, q);
 	if (pmem->pfn_flags & PFN_MAP)