Merge tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Two NVMe pull requests:
     - ana log parse fix from Anton
     - nvme quirks support for Apple devices from Ben
     - fix missing bio completion tracing for multipath stack devices
       from Hannes and Mikhail
     - IP TOS settings for nvme rdma and tcp transports from Israel
     - rq_dma_dir cleanups from Israel
     - tracing for Get LBA Status command from Minwoo
     - Some nvme-tcp cleanups from Minwoo, Potnuri and Myself
     - Some consolidation between the fabrics transports for handling
       the CAP register
     - reset race with ns scanning fix for fabrics (move fabrics
       commands to a dedicated request queue with a different lifetime
       from the admin request queue)."
     - controller reset and namespace scan races fixes
     - nvme discovery log change uevent support
     - naming improvements from Keith
     - multiple discovery controllers reject fix from James
     - some regular cleanups from various people

 - Series fixing (and re-fixing) null_blk debug printing and nr_devices
   checks (André)

 - A few pull requests from Song, with fixes from Andy, Guoqing,
   Guilherme, Neil, Nigel, and Yufen.

 - REQ_OP_ZONE_RESET_ALL support (Chaitanya)

 - Bio merge handling unification (Christoph)

 - Pick default elevator correctly for devices with special needs
   (Damien)

 - Block stats fixes (Hou)

 - Timeout and support devices nbd fixes (Mike)

 - Series fixing races around elevator switching and device add/remove
   (Ming)

 - sed-opal cleanups (Revanth)

 - Per device weight support for BFQ (Fam)

 - Support for blk-iocost, a new model that can properly account cost of
   IO workloads. (Tejun)

 - blk-cgroup writeback fixes (Tejun)

 - paride queue init fixes (zhengbin)

 - blk_set_runtime_active() cleanup (Stanley)

 - Block segment mapping optimizations (Bart)

 - lightnvm fixes (Hans/Minwoo/YueHaibing)

 - Various little fixes and cleanups

* tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block: (186 commits)
  null_blk: format pr_* logs with pr_fmt
  null_blk: match the type of parameter nr_devices
  null_blk: do not fail the module load with zero devices
  block: also check RQF_STATS in blk_mq_need_time_stamp()
  block: make rq sector size accessible for block stats
  bfq: Fix bfq linkage error
  raid5: use bio_end_sector in r5_next_bio
  raid5: remove STRIPE_OPS_REQ_PENDING
  md: add feature flag MD_FEATURE_RAID0_LAYOUT
  md/raid0: avoid RAID0 data corruption due to layout confusion.
  raid5: don't set STRIPE_HANDLE to stripe which is in batch list
  raid5: don't increment read_errors on EILSEQ return
  nvmet: fix a wrong error status returned in error log page
  nvme: send discovery log page change events to userspace
  nvme: add uevent variables for controller devices
  nvme: enable aen regardless of the presence of I/O queues
  nvme-fabrics: allow discovery subsystems accept a kato
  nvmet: Use PTR_ERR_OR_ZERO() in nvmet_init_discovery()
  nvme: Remove redundant assignment of cq vector
  nvme: Assign subsys instance from first ctrl
  ...

Documentation/admin-guide/cgroup-v2.rst

@@ -1469,6 +1469,103 @@ IO Interface Files
 	  8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353 dbytes=0 dios=0
 	  8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252 dbytes=50331648 dios=3021
 
+  io.cost.qos
+	A read-write nested-keyed file with exists only on the root
+	cgroup.
+
+	This file configures the Quality of Service of the IO cost
+	model based controller (CONFIG_BLK_CGROUP_IOCOST) which
+	currently implements "io.weight" proportional control.  Lines
+	are keyed by $MAJ:$MIN device numbers and not ordered.  The
+	line for a given device is populated on the first write for
+	the device on "io.cost.qos" or "io.cost.model".  The following
+	nested keys are defined.
+
+	  ======	=====================================
+	  enable	Weight-based control enable
+	  ctrl		"auto" or "user"
+	  rpct		Read latency percentile    [0, 100]
+	  rlat		Read latency threshold
+	  wpct		Write latency percentile   [0, 100]
+	  wlat		Write latency threshold
+	  min		Minimum scaling percentage [1, 10000]
+	  max		Maximum scaling percentage [1, 10000]
+	  ======	=====================================
+
+	The controller is disabled by default and can be enabled by
+	setting "enable" to 1.  "rpct" and "wpct" parameters default
+	to zero and the controller uses internal device saturation
+	state to adjust the overall IO rate between "min" and "max".
+
+	When a better control quality is needed, latency QoS
+	parameters can be configured.  For example::
+
+	  8:16 enable=1 ctrl=auto rpct=95.00 rlat=75000 wpct=95.00 wlat=150000 min=50.00 max=150.0
+
+	shows that on sdb, the controller is enabled, will consider
+	the device saturated if the 95th percentile of read completion
+	latencies is above 75ms or write 150ms, and adjust the overall
+	IO issue rate between 50% and 150% accordingly.
+
+	The lower the saturation point, the better the latency QoS at
+	the cost of aggregate bandwidth.  The narrower the allowed
+	adjustment range between "min" and "max", the more conformant
+	to the cost model the IO behavior.  Note that the IO issue
+	base rate may be far off from 100% and setting "min" and "max"
+	blindly can lead to a significant loss of device capacity or
+	control quality.  "min" and "max" are useful for regulating
+	devices which show wide temporary behavior changes - e.g. a
+	ssd which accepts writes at the line speed for a while and
+	then completely stalls for multiple seconds.
+
+	When "ctrl" is "auto", the parameters are controlled by the
+	kernel and may change automatically.  Setting "ctrl" to "user"
+	or setting any of the percentile and latency parameters puts
+	it into "user" mode and disables the automatic changes.  The
+	automatic mode can be restored by setting "ctrl" to "auto".
+
+  io.cost.model
+	A read-write nested-keyed file with exists only on the root
+	cgroup.
+
+	This file configures the cost model of the IO cost model based
+	controller (CONFIG_BLK_CGROUP_IOCOST) which currently
+	implements "io.weight" proportional control.  Lines are keyed
+	by $MAJ:$MIN device numbers and not ordered.  The line for a
+	given device is populated on the first write for the device on
+	"io.cost.qos" or "io.cost.model".  The following nested keys
+	are defined.
+
+	  =====		================================
+	  ctrl		"auto" or "user"
+	  model		The cost model in use - "linear"
+	  =====		================================
+
+	When "ctrl" is "auto", the kernel may change all parameters
+	dynamically.  When "ctrl" is set to "user" or any other
+	parameters are written to, "ctrl" become "user" and the
+	automatic changes are disabled.
+
+	When "model" is "linear", the following model parameters are
+	defined.
+
+	  =============	========================================
+	  [r|w]bps	The maximum sequential IO throughput
+	  [r|w]seqiops	The maximum 4k sequential IOs per second
+	  [r|w]randiops	The maximum 4k random IOs per second
+	  =============	========================================
+
+	From the above, the builtin linear model determines the base
+	costs of a sequential and random IO and the cost coefficient
+	for the IO size.  While simple, this model can cover most
+	common device classes acceptably.
+
+	The IO cost model isn't expected to be accurate in absolute
+	sense and is scaled to the device behavior dynamically.
+
+	If needed, tools/cgroup/iocost_coef_gen.py can be used to
+	generate device-specific coefficients.
+
   io.weight
 	A read-write flat-keyed file which exists on non-root cgroups.
 	The default is "default 100".

Documentation/admin-guide/kernel-parameters.txt

@@ -1201,12 +1201,6 @@
 			See comment before function elanfreq_setup() in
 			arch/x86/kernel/cpu/cpufreq/elanfreq.c.
 
-	elevator=	[IOSCHED]
-			Format: { "mq-deadline" | "kyber" | "bfq" }
-			See Documentation/block/deadline-iosched.rst,
-			Documentation/block/kyber-iosched.rst and
-			Documentation/block/bfq-iosched.rst for details.
-
 	elfcorehdr=[size[KMG]@]offset[KMG] [IA64,PPC,SH,X86,S390]
 			Specifies physical address of start of kernel core
 			image elf header and optionally the size. Generally

Documentation/admin-guide/kernel-per-CPU-kthreads.rst

@@ -274,9 +274,7 @@ To reduce its OS jitter, do any of the following:
 		(based on an earlier one from Gilad Ben-Yossef) that
 		reduces or even eliminates vmstat overhead for some
 		workloads at https://lkml.org/lkml/2013/9/4/379.
-	e.	Boot with "elevator=noop" to avoid workqueue use by
-		the block layer.
-	f.	If running on high-end powerpc servers, build with
+	e.	If running on high-end powerpc servers, build with
 		CONFIG_PPC_RTAS_DAEMON=n.  This prevents the RTAS
 		daemon from running on each CPU every second or so.
 		(This will require editing Kconfig files and will defeat
@@ -284,12 +282,12 @@ To reduce its OS jitter, do any of the following:
 		due to the rtas_event_scan() function.
 		WARNING:  Please check your CPU specifications to
 		make sure that this is safe on your particular system.
-	g.	If running on Cell Processor, build your kernel with
+	f.	If running on Cell Processor, build your kernel with
 		CBE_CPUFREQ_SPU_GOVERNOR=n to avoid OS jitter from
 		spu_gov_work().
 		WARNING:  Please check your CPU specifications to
 		make sure that this is safe on your particular system.
-	h.	If running on PowerMAC, build your kernel with
+	g.	If running on PowerMAC, build your kernel with
 		CONFIG_PMAC_RACKMETER=n to disable the CPU-meter,
 		avoiding OS jitter from rackmeter_do_timer().
 

Documentation/block/null_blk.rst

+.. SPDX-License-Identifier: GPL-2.0
+
 ========================
 Null block device driver
 ========================
 
-1. Overview
-===========
+Overview
+========
 
-The null block device (/dev/nullb*) is used for benchmarking the various
+The null block device (``/dev/nullb*``) is used for benchmarking the various
 block-layer implementations. It emulates a block device of X gigabytes in size.
-The following instances are possible:
-
-  Single-queue block-layer
-
-    - Request-based.
-    - Single submission queue per device.
-    - Implements IO scheduling algorithms (CFQ, Deadline, noop).
+It does not execute any read/write operation, just mark them as complete in
+the request queue. The following instances are possible:
 
   Multi-queue block-layer
 
@@ -27,15 +24,15 @@ The following instances are possible:
 
 All of them have a completion queue for each core in the system.
 
-2. Module parameters applicable for all instances
-=================================================
+Module parameters
+=================
 
 queue_mode=[0-2]: Default: 2-Multi-queue
   Selects which block-layer the module should instantiate with.
 
   =  ============
   0  Bio-based
-  1  Single-queue
+  1  Single-queue (deprecated)
   2  Multi-queue
   =  ============
 
@@ -67,7 +64,7 @@ irqmode=[0-2]: Default: 1-Soft-irq
 completion_nsec=[ns]: Default: 10,000ns
   Combined with irqmode=2 (timer). The time each completion event must wait.
 
-submit_queues=[1..nr_cpus]:
+submit_queues=[1..nr_cpus]: Default: 1
   The number of submission queues attached to the device driver. If unset, it
   defaults to 1. For multi-queue, it is ignored when use_per_node_hctx module
   parameter is 1.
@@ -75,9 +72,11 @@ submit_queues=[1..nr_cpus]:
 hw_queue_depth=[0..qdepth]: Default: 64
   The hardware queue depth of the device.
 
-III: Multi-queue specific parameters
+Multi-queue specific parameters
+-------------------------------
 
 use_per_node_hctx=[0/1]: Default: 0
+  Number of hardware context queues.
 
   =  =====================================================================
   0  The number of submit queues are set to the value of the submit_queues
@@ -87,6 +86,7 @@ use_per_node_hctx=[0/1]: Default: 0
   =  =====================================================================
 
 no_sched=[0/1]: Default: 0
+  Enable/disable the io scheduler.
 
   =  ======================================
   0  nullb* use default blk-mq io scheduler
@@ -94,6 +94,7 @@ no_sched=[0/1]: Default: 0
   =  ======================================
 
 blocking=[0/1]: Default: 0
+  Blocking behavior of the request queue.
 
   =  ===============================================================
   0  Register as a non-blocking blk-mq driver device.
@@ -103,6 +104,7 @@ blocking=[0/1]: Default: 0
   =  ===============================================================
 
 shared_tags=[0/1]: Default: 0
+  Sharing tags between devices.
 
   =  ================================================================
   0  Tag set is not shared.
@@ -111,6 +113,7 @@ shared_tags=[0/1]: Default: 0
   =  ================================================================
 
 zoned=[0/1]: Default: 0
+  Device is a random-access or a zoned block device.
 
   =  ======================================================================
   0  Block device is exposed as a random-access block device.

Documentation/block/switching-sched.rst

@@ -2,10 +2,6 @@
 Switching Scheduler
 ===================
 
-To choose IO schedulers at boot time, use the argument 'elevator=deadline'.
-'noop' and 'cfq' (the default) are also available. IO schedulers are assigned
-globally at boot time only presently.
-
 Each io queue has a set of io scheduler tunables associated with it. These
 tunables control how the io scheduler works. You can find these entries
 in::

block/Kconfig

@@ -26,6 +26,9 @@ menuconfig BLOCK
 
 if BLOCK
 
+config BLK_RQ_ALLOC_TIME
+	bool
+
 config BLK_SCSI_REQUEST
 	bool
 
@@ -132,6 +135,16 @@ config BLK_CGROUP_IOLATENCY
 
 	Note, this is an experimental interface and could be changed someday.
 
+config BLK_CGROUP_IOCOST
+	bool "Enable support for cost model based cgroup IO controller"
+	depends on BLK_CGROUP=y
+	select BLK_RQ_ALLOC_TIME
+	---help---
+	Enabling this option enables the .weight interface for cost
+	model based proportional IO control.  The IO controller
+	distributes IO capacity between different groups based on
+	their share of the overall weight distribution.
+
 config BLK_WBT_MQ
 	bool "Multiqueue writeback throttling"
 	default y

block/Makefile

@@ -18,6 +18,7 @@ obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
 obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
 obj-$(CONFIG_BLK_CGROUP_IOLATENCY)	+= blk-iolatency.o
+obj-$(CONFIG_BLK_CGROUP_IOCOST)	+= blk-iocost.o
 obj-$(CONFIG_MQ_IOSCHED_DEADLINE)	+= mq-deadline.o
 obj-$(CONFIG_MQ_IOSCHED_KYBER)	+= kyber-iosched.o
 bfq-y				:= bfq-iosched.o bfq-wf2q.o bfq-cgroup.o

block/bfq-cgroup.c

@@ -501,11 +501,12 @@ static void bfq_cpd_free(struct blkcg_policy_data *cpd)
 	kfree(cpd_to_bfqgd(cpd));
 }
 
-static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node)
+static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, struct request_queue *q,
+					     struct blkcg *blkcg)
 {
 	struct bfq_group *bfqg;
 
-	bfqg = kzalloc_node(sizeof(*bfqg), gfp, node);
+	bfqg = kzalloc_node(sizeof(*bfqg), gfp, q->node);
 	if (!bfqg)
 		return NULL;
 
@@ -904,7 +905,7 @@ void bfq_end_wr_async(struct bfq_data *bfqd)
 	bfq_end_wr_async_queues(bfqd, bfqd->root_group);
 }
 
-static int bfq_io_show_weight(struct seq_file *sf, void *v)
+static int bfq_io_show_weight_legacy(struct seq_file *sf, void *v)
 {
 	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
 	struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
@@ -918,6 +919,60 @@ static int bfq_io_show_weight(struct seq_file *sf, void *v)
 	return 0;
 }
 
+static u64 bfqg_prfill_weight_device(struct seq_file *sf,
+				     struct blkg_policy_data *pd, int off)
+{
+	struct bfq_group *bfqg = pd_to_bfqg(pd);
+
+	if (!bfqg->entity.dev_weight)
+		return 0;
+	return __blkg_prfill_u64(sf, pd, bfqg->entity.dev_weight);
+}
+
+static int bfq_io_show_weight(struct seq_file *sf, void *v)
+{
+	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+	struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
+
+	seq_printf(sf, "default %u\n", bfqgd->weight);
+	blkcg_print_blkgs(sf, blkcg, bfqg_prfill_weight_device,
+			  &blkcg_policy_bfq, 0, false);
+	return 0;
+}
+
+static void bfq_group_set_weight(struct bfq_group *bfqg, u64 weight, u64 dev_weight)
+{
+	weight = dev_weight ?: weight;
+
+	bfqg->entity.dev_weight = dev_weight;
+	/*
+	 * Setting the prio_changed flag of the entity
+	 * to 1 with new_weight == weight would re-set
+	 * the value of the weight to its ioprio mapping.
+	 * Set the flag only if necessary.
+	 */
+	if ((unsigned short)weight != bfqg->entity.new_weight) {
+		bfqg->entity.new_weight = (unsigned short)weight;
+		/*
+		 * Make sure that the above new value has been
+		 * stored in bfqg->entity.new_weight before
+		 * setting the prio_changed flag. In fact,
+		 * this flag may be read asynchronously (in
+		 * critical sections protected by a different
+		 * lock than that held here), and finding this
+		 * flag set may cause the execution of the code
+		 * for updating parameters whose value may
+		 * depend also on bfqg->entity.new_weight (in
+		 * __bfq_entity_update_weight_prio).
+		 * This barrier makes sure that the new value
+		 * of bfqg->entity.new_weight is correctly
+		 * seen in that code.
+		 */
+		smp_wmb();
+		bfqg->entity.prio_changed = 1;
+	}
+}
+
 static int bfq_io_set_weight_legacy(struct cgroup_subsys_state *css,
 				    struct cftype *cftype,
 				    u64 val)
@@ -936,55 +991,72 @@ static int bfq_io_set_weight_legacy(struct cgroup_subsys_state *css,
 	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
 		struct bfq_group *bfqg = blkg_to_bfqg(blkg);
 
-		if (!bfqg)
-			continue;
-		/*
-		 * Setting the prio_changed flag of the entity
-		 * to 1 with new_weight == weight would re-set
-		 * the value of the weight to its ioprio mapping.
-		 * Set the flag only if necessary.
-		 */
-		if ((unsigned short)val != bfqg->entity.new_weight) {
-			bfqg->entity.new_weight = (unsigned short)val;
-			/*
-			 * Make sure that the above new value has been
-			 * stored in bfqg->entity.new_weight before
-			 * setting the prio_changed flag. In fact,
-			 * this flag may be read asynchronously (in
-			 * critical sections protected by a different
-			 * lock than that held here), and finding this
-			 * flag set may cause the execution of the code
-			 * for updating parameters whose value may
-			 * depend also on bfqg->entity.new_weight (in
-			 * __bfq_entity_update_weight_prio).
-			 * This barrier makes sure that the new value
-			 * of bfqg->entity.new_weight is correctly
-			 * seen in that code.
-			 */
-			smp_wmb();
-			bfqg->entity.prio_changed = 1;
-		}
+		if (bfqg)
+			bfq_group_set_weight(bfqg, val, 0);
 	}
 	spin_unlock_irq(&blkcg->lock);
 
 	return ret;
 }
 
-static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
-				 char *buf, size_t nbytes,
-				 loff_t off)
+static ssize_t bfq_io_set_device_weight(struct kernfs_open_file *of,
+					char *buf, size_t nbytes,
+					loff_t off)
 {
-	u64 weight;
-	/* First unsigned long found in the file is used */
-	int ret = kstrtoull(strim(buf), 0, &weight);
+	int ret;
+	struct blkg_conf_ctx ctx;
+	struct blkcg *blkcg = css_to_blkcg(of_css(of));
+	struct bfq_group *bfqg;
+	u64 v;
 
+	ret = blkg_conf_prep(blkcg, &blkcg_policy_bfq, buf, &ctx);
 	if (ret)
 		return ret;
 
-	ret = bfq_io_set_weight_legacy(of_css(of), NULL, weight);
+	if (sscanf(ctx.body, "%llu", &v) == 1) {
+		/* require "default" on dfl */
+		ret = -ERANGE;
+		if (!v)
+			goto out;
+	} else if (!strcmp(strim(ctx.body), "default")) {
+		v = 0;
+	} else {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	bfqg = blkg_to_bfqg(ctx.blkg);
+
+	ret = -ERANGE;
+	if (!v || (v >= BFQ_MIN_WEIGHT && v <= BFQ_MAX_WEIGHT)) {
+		bfq_group_set_weight(bfqg, bfqg->entity.weight, v);
+		ret = 0;
+	}
+out:
+	blkg_conf_finish(&ctx);
 	return ret ?: nbytes;
 }
 
+static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
+				 char *buf, size_t nbytes,
+				 loff_t off)
+{
+	char *endp;
+	int ret;
+	u64 v;
+
+	buf = strim(buf);
+
+	/* "WEIGHT" or "default WEIGHT" sets the default weight */
+	v = simple_strtoull(buf, &endp, 0);
+	if (*endp == '\0' || sscanf(buf, "default %llu", &v) == 1) {
+		ret = bfq_io_set_weight_legacy(of_css(of), NULL, v);
+		return ret ?: nbytes;
+	}
+
+	return bfq_io_set_device_weight(of, buf, nbytes, off);
+}
+
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 static int bfqg_print_stat(struct seq_file *sf, void *v)
 {
@@ -1141,9 +1213,15 @@ struct cftype bfq_blkcg_legacy_files[] = {
 	{
 		.name = "bfq.weight",
 		.flags = CFTYPE_NOT_ON_ROOT,
-		.seq_show = bfq_io_show_weight,
+		.seq_show = bfq_io_show_weight_legacy,
 		.write_u64 = bfq_io_set_weight_legacy,
 	},
+	{
+		.name = "bfq.weight_device",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = bfq_io_show_weight,
+		.write = bfq_io_set_weight,
+	},
 
 	/* statistics, covers only the tasks in the bfqg */
 	{

block/bfq-iosched.h

@@ -168,6 +168,9 @@ struct bfq_entity {
 	/* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */
 	int budget;
 
+	/* device weight, if non-zero, it overrides the default weight of
+	 * bfq_group_data */
+	int dev_weight;
 	/* weight of the queue */
 	int weight;
 	/* next weight if a change is in progress */

block/bfq-wf2q.c

@@ -744,6 +744,8 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
 		}
 #endif
 
+		/* Matches the smp_wmb() in bfq_group_set_weight. */
+		smp_rmb();
 		old_st->wsum -= entity->weight;
 
 		if (entity->new_weight != entity->orig_weight) {

block/bio.c

@@ -646,25 +646,20 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
 	return true;
 }
 
-/*
- * Check if the @page can be added to the current segment(@bv), and make
- * sure to call it only if page_is_mergeable(@bv, @page) is true
- */
-static bool can_add_page_to_seg(struct request_queue *q,
-		struct bio_vec *bv, struct page *page, unsigned len,
-		unsigned offset)
+static bool bio_try_merge_pc_page(struct request_queue *q, struct bio *bio,
+		struct page *page, unsigned len, unsigned offset,
+		bool *same_page)
 {
+	struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 	unsigned long mask = queue_segment_boundary(q);
 	phys_addr_t addr1 = page_to_phys(bv->bv_page) + bv->bv_offset;
 	phys_addr_t addr2 = page_to_phys(page) + offset + len - 1;
 
 	if ((addr1 | mask) != (addr2 | mask))
 		return false;
-
 	if (bv->bv_len + len > queue_max_segment_size(q))
 		return false;
-
-	return true;
+	return __bio_try_merge_page(bio, page, len, offset, same_page);
 }
 
 /**
@@ -674,7 +669,7 @@ static bool can_add_page_to_seg(struct request_queue *q,
  *	@page: page to add
  *	@len: vec entry length
  *	@offset: vec entry offset
- *	@put_same_page: put the page if it is same with last added page
+ *	@same_page: return if the merge happen inside the same page
  *
  *	Attempt to add a page to the bio_vec maplist. This can fail for a
  *	number of reasons, such as the bio being full or target block device
@@ -685,10 +680,9 @@ static bool can_add_page_to_seg(struct request_queue *q,
  */
 static int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset,
-		bool put_same_page)
+		bool *same_page)
 {
 	struct bio_vec *bvec;
-	bool same_page = false;
 
 	/*
 	 * cloned bio must not modify vec list
@@ -700,28 +694,16 @@ static int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
 		return 0;
 
 	if (bio->bi_vcnt > 0) {
-		bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
-
-		if (page == bvec->bv_page &&
-		    offset == bvec->bv_offset + bvec->bv_len) {
-			if (put_same_page)
-				put_page(page);
-			bvec->bv_len += len;
-			goto done;
-		}
+		if (bio_try_merge_pc_page(q, bio, page, len, offset, same_page))
+			return len;
 
 		/*
-		 * If the queue doesn't support SG gaps and adding this
-		 * offset would create a gap, disallow it.
+		 * If the queue doesn't support SG gaps and adding this segment
+		 * would create a gap, disallow it.
 		 */
+		bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
 		if (bvec_gap_to_prev(q, bvec, offset))
 			return 0;
-
-		if (page_is_mergeable(bvec, page, len, offset, &same_page) &&
-		    can_add_page_to_seg(q, bvec, page, len, offset)) {
-			bvec->bv_len += len;
-			goto done;
-		}
 	}
 
 	if (bio_full(bio, len))
@@ -735,7 +717,6 @@ static int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
 	bvec->bv_len = len;
 	bvec->bv_offset = offset;
 	bio->bi_vcnt++;
- done:
 	bio->bi_iter.bi_size += len;
 	return len;
 }
@@ -743,7 +724,8 @@ static int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
 int bio_add_pc_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset)
 {
-	return __bio_add_pc_page(q, bio, page, len, offset, false);
+	bool same_page = false;
+	return __bio_add_pc_page(q, bio, page, len, offset, &same_page);
 }
 EXPORT_SYMBOL(bio_add_pc_page);
 
@@ -806,6 +788,9 @@ void __bio_add_page(struct bio *bio, struct page *page,
 
 	bio->bi_iter.bi_size += len;
 	bio->bi_vcnt++;
+
+	if (!bio_flagged(bio, BIO_WORKINGSET) && unlikely(PageWorkingset(page)))
+		bio_set_flag(bio, BIO_WORKINGSET);
 }
 EXPORT_SYMBOL_GPL(__bio_add_page);
 
@@ -1384,13 +1369,17 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 			for (j = 0; j < npages; j++) {
 				struct page *page = pages[j];
 				unsigned int n = PAGE_SIZE - offs;
+				bool same_page = false;
 
 				if (n > bytes)
 					n = bytes;
 
 				if (!__bio_add_pc_page(q, bio, page, n, offs,
-							true))
+						&same_page)) {
+					if (same_page)
+						put_page(page);
 					break;
+				}
 
 				added += n;
 				bytes -= n;
@@ -1521,7 +1510,6 @@ struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
 	bio->bi_end_io = bio_map_kern_endio;
 	return bio;
 }
-EXPORT_SYMBOL(bio_map_kern);
 
 static void bio_copy_kern_endio(struct bio *bio)
 {
@@ -1842,8 +1830,8 @@ EXPORT_SYMBOL(bio_endio);
  * @bio, and updates @bio to represent the remaining sectors.
  *
  * Unless this is a discard request the newly allocated bio will point
- * to @bio's bi_io_vec; it is the caller's responsibility to ensure that
- * @bio is not freed before the split.
+ * to @bio's bi_io_vec. It is the caller's responsibility to ensure that
+ * neither @bio nor @bs are freed before the split bio.
  */
 struct bio *bio_split(struct bio *bio, int sectors,
 		      gfp_t gfp, struct bio_set *bs)

block/blk-cgroup.c

@@ -175,7 +175,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 			continue;
 
 		/* alloc per-policy data and attach it to blkg */
-		pd = pol->pd_alloc_fn(gfp_mask, q->node);
+		pd = pol->pd_alloc_fn(gfp_mask, q, blkcg);
 		if (!pd)
 			goto err_free;
 
@@ -753,6 +753,44 @@ static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg,
 	return __blkg_lookup(blkcg, q, true /* update_hint */);
 }
 
+/**
+ * blkg_conf_prep - parse and prepare for per-blkg config update
+ * @inputp: input string pointer
+ *
+ * Parse the device node prefix part, MAJ:MIN, of per-blkg config update
+ * from @input and get and return the matching gendisk.  *@inputp is
+ * updated to point past the device node prefix.  Returns an ERR_PTR()
+ * value on error.
+ *
+ * Use this function iff blkg_conf_prep() can't be used for some reason.
+ */
+struct gendisk *blkcg_conf_get_disk(char **inputp)
+{
+	char *input = *inputp;
+	unsigned int major, minor;
+	struct gendisk *disk;
+	int key_len, part;
+
+	if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2)
+		return ERR_PTR(-EINVAL);
+
+	input += key_len;
+	if (!isspace(*input))
+		return ERR_PTR(-EINVAL);
+	input = skip_spaces(input);
+
+	disk = get_gendisk(MKDEV(major, minor), &part);
+	if (!disk)
+		return ERR_PTR(-ENODEV);
+	if (part) {
+		put_disk_and_module(disk);
+		return ERR_PTR(-ENODEV);
+	}
+
+	*inputp = input;
+	return disk;
+}
+
 /**
  * blkg_conf_prep - parse and prepare for per-blkg config update
  * @blkcg: target block cgroup
@@ -772,25 +810,11 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	struct gendisk *disk;
 	struct request_queue *q;
 	struct blkcg_gq *blkg;
-	unsigned int major, minor;
-	int key_len, part, ret;
-	char *body;
-
-	if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2)
-		return -EINVAL;
-
-	body = input + key_len;
-	if (!isspace(*body))
-		return -EINVAL;
-	body = skip_spaces(body);
+	int ret;
 
-	disk = get_gendisk(MKDEV(major, minor), &part);
-	if (!disk)
-		return -ENODEV;
-	if (part) {
-		ret = -ENODEV;
-		goto fail;
-	}
+	disk = blkcg_conf_get_disk(&input);
+	if (IS_ERR(disk))
+		return PTR_ERR(disk);
 
 	q = disk->queue;
 
@@ -856,7 +880,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 success:
 	ctx->disk = disk;
 	ctx->blkg = blkg;
-	ctx->body = body;
+	ctx->body = input;
 	return 0;
 
 fail_unlock:
@@ -876,6 +900,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	}
 	return ret;
 }
+EXPORT_SYMBOL_GPL(blkg_conf_prep);
 
 /**
  * blkg_conf_finish - finish up per-blkg config update
@@ -891,6 +916,7 @@ void blkg_conf_finish(struct blkg_conf_ctx *ctx)
 	rcu_read_unlock();
 	put_disk_and_module(ctx->disk);
 }
+EXPORT_SYMBOL_GPL(blkg_conf_finish);
 
 static int blkcg_print_stat(struct seq_file *sf, void *v)
 {
@@ -1346,7 +1372,7 @@ int blkcg_activate_policy(struct request_queue *q,
 		blk_mq_freeze_queue(q);
 pd_prealloc:
 	if (!pd_prealloc) {
-		pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q->node);
+		pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q, &blkcg_root);
 		if (!pd_prealloc) {
 			ret = -ENOMEM;
 			goto out_bypass_end;
@@ -1362,7 +1388,7 @@ int blkcg_activate_policy(struct request_queue *q,
 		if (blkg->pd[pol->plid])
 			continue;
 
-		pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q->node);
+		pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q, &blkcg_root);
 		if (!pd)
 			swap(pd, pd_prealloc);
 		if (!pd) {
@@ -1475,7 +1501,8 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 			blkcg->cpd[pol->plid] = cpd;
 			cpd->blkcg = blkcg;
 			cpd->plid = pol->plid;
-			pol->cpd_init_fn(cpd);
+			if (pol->cpd_init_fn)
+				pol->cpd_init_fn(cpd);
 		}
 	}
 

block/blk-core.c

@@ -36,6 +36,7 @@
 #include <linux/blk-cgroup.h>
 #include <linux/debugfs.h>
 #include <linux/bpf.h>
+#include <linux/psi.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/block.h>
@@ -129,6 +130,7 @@ static const char *const blk_op_name[] = {
 	REQ_OP_NAME(DISCARD),
 	REQ_OP_NAME(SECURE_ERASE),
 	REQ_OP_NAME(ZONE_RESET),
+	REQ_OP_NAME(ZONE_RESET_ALL),
 	REQ_OP_NAME(WRITE_SAME),
 	REQ_OP_NAME(WRITE_ZEROES),
 	REQ_OP_NAME(SCSI_IN),
@@ -344,7 +346,8 @@ void blk_cleanup_queue(struct request_queue *q)
 
 	/*
 	 * Drain all requests queued before DYING marking. Set DEAD flag to
-	 * prevent that q->request_fn() gets invoked after draining finished.
+	 * prevent that blk_mq_run_hw_queues() accesses the hardware queues
+	 * after draining finished.
 	 */
 	blk_freeze_queue(q);
 
@@ -479,7 +482,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (!q)
 		return NULL;
 
-	INIT_LIST_HEAD(&q->queue_head);
 	q->last_merge = NULL;
 
 	q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask);
@@ -518,6 +520,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	mutex_init(&q->blk_trace_mutex);
 #endif
 	mutex_init(&q->sysfs_lock);
+	mutex_init(&q->sysfs_dir_lock);
 	spin_lock_init(&q->queue_lock);
 
 	init_waitqueue_head(&q->mq_freeze_wq);
@@ -601,6 +604,7 @@ bool bio_attempt_back_merge(struct request *req, struct bio *bio,
 		return false;
 
 	trace_block_bio_backmerge(req->q, req, bio);
+	rq_qos_merge(req->q, req, bio);
 
 	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
 		blk_rq_set_mixed_merge(req);
@@ -622,6 +626,7 @@ bool bio_attempt_front_merge(struct request *req, struct bio *bio,
 		return false;
 
 	trace_block_bio_frontmerge(req->q, req, bio);
+	rq_qos_merge(req->q, req, bio);
 
 	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
 		blk_rq_set_mixed_merge(req);
@@ -647,6 +652,8 @@ bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
 	    blk_rq_get_max_sectors(req, blk_rq_pos(req)))
 		goto no_merge;
 
+	rq_qos_merge(q, req, bio);
+
 	req->biotail->bi_next = bio;
 	req->biotail = bio;
 	req->__data_len += bio->bi_iter.bi_size;
@@ -931,6 +938,10 @@ generic_make_request_checks(struct bio *bio)
 		if (!blk_queue_is_zoned(q))
 			goto not_supported;
 		break;
+	case REQ_OP_ZONE_RESET_ALL:
+		if (!blk_queue_is_zoned(q) || !blk_queue_zone_resetall(q))
+			goto not_supported;
+		break;
 	case REQ_OP_WRITE_ZEROES:
 		if (!q->limits.max_write_zeroes_sectors)
 			goto not_supported;
@@ -1128,6 +1139,10 @@ EXPORT_SYMBOL_GPL(direct_make_request);
  */
 blk_qc_t submit_bio(struct bio *bio)
 {
+	bool workingset_read = false;
+	unsigned long pflags;
+	blk_qc_t ret;
+
 	if (blkcg_punt_bio_submit(bio))
 		return BLK_QC_T_NONE;
 
@@ -1146,6 +1161,8 @@ blk_qc_t submit_bio(struct bio *bio)
 		if (op_is_write(bio_op(bio))) {
 			count_vm_events(PGPGOUT, count);
 		} else {
+			if (bio_flagged(bio, BIO_WORKINGSET))
+				workingset_read = true;
 			task_io_account_read(bio->bi_iter.bi_size);
 			count_vm_events(PGPGIN, count);
 		}
@@ -1160,7 +1177,21 @@ blk_qc_t submit_bio(struct bio *bio)
 		}
 	}
 
-	return generic_make_request(bio);
+	/*
+	 * If we're reading data that is part of the userspace
+	 * workingset, count submission time as memory stall. When the
+	 * device is congested, or the submitting cgroup IO-throttled,
+	 * submission can be a significant part of overall IO time.
+	 */
+	if (workingset_read)
+		psi_memstall_enter(&pflags);
+
+	ret = generic_make_request(bio);
+
+	if (workingset_read)
+		psi_memstall_leave(&pflags);
+
+	return ret;
 }
 EXPORT_SYMBOL(submit_bio);
 

block/blk-iolatency.c

@@ -725,7 +725,7 @@ int blk_iolatency_init(struct request_queue *q)
 		return -ENOMEM;
 
 	rqos = &blkiolat->rqos;
-	rqos->id = RQ_QOS_CGROUP;
+	rqos->id = RQ_QOS_LATENCY;
 	rqos->ops = &blkcg_iolatency_ops;
 	rqos->q = q;
 
@@ -934,11 +934,13 @@ static size_t iolatency_pd_stat(struct blkg_policy_data *pd, char *buf,
 }
 
 
-static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp, int node)
+static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp,
+						   struct request_queue *q,
+						   struct blkcg *blkcg)
 {
 	struct iolatency_grp *iolat;
 
-	iolat = kzalloc_node(sizeof(*iolat), gfp, node);
+	iolat = kzalloc_node(sizeof(*iolat), gfp, q->node);
 	if (!iolat)
 		return NULL;
 	iolat->stats = __alloc_percpu_gfp(sizeof(struct latency_stat),

block/blk-merge.c

@@ -132,19 +132,32 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q,
 	return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs);
 }
 
+/*
+ * Return the maximum number of sectors from the start of a bio that may be
+ * submitted as a single request to a block device. If enough sectors remain,
+ * align the end to the physical block size. Otherwise align the end to the
+ * logical block size. This approach minimizes the number of non-aligned
+ * requests that are submitted to a block device if the start of a bio is not
+ * aligned to a physical block boundary.
+ */
 static inline unsigned get_max_io_size(struct request_queue *q,
 				       struct bio *bio)
 {
 	unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
-	unsigned mask = queue_logical_block_size(q) - 1;
+	unsigned max_sectors = sectors;
+	unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT;
+	unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT;
+	unsigned start_offset = bio->bi_iter.bi_sector & (pbs - 1);
 
-	/* aligned to logical block size */
-	sectors &= ~(mask >> 9);
+	max_sectors += start_offset;
+	max_sectors &= ~(pbs - 1);
+	if (max_sectors > start_offset)
+		return max_sectors - start_offset;
 
-	return sectors;
+	return sectors & (lbs - 1);
 }
 
-static unsigned get_max_segment_size(struct request_queue *q,
+static unsigned get_max_segment_size(const struct request_queue *q,
 				     unsigned offset)
 {
 	unsigned long mask = queue_segment_boundary(q);
@@ -157,26 +170,41 @@ static unsigned get_max_segment_size(struct request_queue *q,
 		     queue_max_segment_size(q));
 }
 
-/*
- * Split the bvec @bv into segments, and update all kinds of
- * variables.
+/**
+ * bvec_split_segs - verify whether or not a bvec should be split in the middle
+ * @q:        [in] request queue associated with the bio associated with @bv
+ * @bv:       [in] bvec to examine
+ * @nsegs:    [in,out] Number of segments in the bio being built. Incremented
+ *            by the number of segments from @bv that may be appended to that
+ *            bio without exceeding @max_segs
+ * @sectors:  [in,out] Number of sectors in the bio being built. Incremented
+ *            by the number of sectors from @bv that may be appended to that
+ *            bio without exceeding @max_sectors
+ * @max_segs: [in] upper bound for *@nsegs
+ * @max_sectors: [in] upper bound for *@sectors
+ *
+ * When splitting a bio, it can happen that a bvec is encountered that is too
+ * big to fit in a single segment and hence that it has to be split in the
+ * middle. This function verifies whether or not that should happen. The value
+ * %true is returned if and only if appending the entire @bv to a bio with
+ * *@nsegs segments and *@sectors sectors would make that bio unacceptable for
+ * the block driver.
  */
-static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv,
-		unsigned *nsegs, unsigned *sectors, unsigned max_segs)
+static bool bvec_split_segs(const struct request_queue *q,
+			    const struct bio_vec *bv, unsigned *nsegs,
+			    unsigned *sectors, unsigned max_segs,
+			    unsigned max_sectors)
 {
-	unsigned len = bv->bv_len;
+	unsigned max_len = (min(max_sectors, UINT_MAX >> 9) - *sectors) << 9;
+	unsigned len = min(bv->bv_len, max_len);
 	unsigned total_len = 0;
-	unsigned new_nsegs = 0, seg_size = 0;
+	unsigned seg_size = 0;
 
-	/*
-	 * Multi-page bvec may be too big to hold in one segment, so the
-	 * current bvec has to be splitted as multiple segments.
-	 */
-	while (len && new_nsegs + *nsegs < max_segs) {
+	while (len && *nsegs < max_segs) {
 		seg_size = get_max_segment_size(q, bv->bv_offset + total_len);
 		seg_size = min(seg_size, len);
 
-		new_nsegs++;
+		(*nsegs)++;
 		total_len += seg_size;
 		len -= seg_size;
 
@@ -184,16 +212,31 @@ static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv,
 			break;
 	}
 
-	if (new_nsegs) {
-		*nsegs += new_nsegs;
-		if (sectors)
-			*sectors += total_len >> 9;
-	}
+	*sectors += total_len >> 9;
 
-	/* split in the middle of the bvec if len != 0 */
-	return !!len;
+	/* tell the caller to split the bvec if it is too big to fit */
+	return len > 0 || bv->bv_len > max_len;
 }
 
+/**
+ * blk_bio_segment_split - split a bio in two bios
+ * @q:    [in] request queue pointer
+ * @bio:  [in] bio to be split
+ * @bs:	  [in] bio set to allocate the clone from
+ * @segs: [out] number of segments in the bio with the first half of the sectors
+ *
+ * Clone @bio, update the bi_iter of the clone to represent the first sectors
+ * of @bio and update @bio->bi_iter to represent the remaining sectors. The
+ * following is guaranteed for the cloned bio:
+ * - That it has at most get_max_io_size(@q, @bio) sectors.
+ * - That it has at most queue_max_segments(@q) segments.
+ *
+ * Except for discard requests the cloned bio will point at the bi_io_vec of
+ * the original bio. It is the responsibility of the caller to ensure that the
+ * original bio is not freed before the cloned bio. The caller is also
+ * responsible for ensuring that @bs is only destroyed after processing of the
+ * split bio has finished.
+ */
 static struct bio *blk_bio_segment_split(struct request_queue *q,
 					 struct bio *bio,
 					 struct bio_set *bs,
@@ -213,34 +256,18 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 		if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset))
 			goto split;
 
-		if (sectors + (bv.bv_len >> 9) > max_sectors) {
-			/*
-			 * Consider this a new segment if we're splitting in
-			 * the middle of this vector.
-			 */
-			if (nsegs < max_segs &&
-			    sectors < max_sectors) {
-				/* split in the middle of bvec */
-				bv.bv_len = (max_sectors - sectors) << 9;
-				bvec_split_segs(q, &bv, &nsegs,
-						&sectors, max_segs);
-			}
+		if (nsegs < max_segs &&
+		    sectors + (bv.bv_len >> 9) <= max_sectors &&
+		    bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
+			nsegs++;
+			sectors += bv.bv_len >> 9;
+		} else if (bvec_split_segs(q, &bv, &nsegs, &sectors, max_segs,
+					 max_sectors)) {
 			goto split;
 		}
 
-		if (nsegs == max_segs)
-			goto split;
-
 		bvprv = bv;
 		bvprvp = &bvprv;
-
-		if (bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
-			nsegs++;
-			sectors += bv.bv_len >> 9;
-		} else if (bvec_split_segs(q, &bv, &nsegs, &sectors,
-				max_segs)) {
-			goto split;
-		}
 	}
 
 	*segs = nsegs;
@@ -250,6 +277,19 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 	return bio_split(bio, sectors, GFP_NOIO, bs);
 }
 
+/**
+ * __blk_queue_split - split a bio and submit the second half
+ * @q:       [in] request queue pointer
+ * @bio:     [in, out] bio to be split
+ * @nr_segs: [out] number of segments in the first bio
+ *
+ * Split a bio into two bios, chain the two bios, submit the second half and
+ * store a pointer to the first half in *@bio. If the second bio is still too
+ * big it will be split by a recursive call to this function. Since this
+ * function may allocate a new bio from @q->bio_split, it is the responsibility
+ * of the caller to ensure that @q is only released after processing of the
+ * split bio has finished.
+ */
 void __blk_queue_split(struct request_queue *q, struct bio **bio,
 		unsigned int *nr_segs)
 {
@@ -294,6 +334,17 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio,
 	}
 }
 
+/**
+ * blk_queue_split - split a bio and submit the second half
+ * @q:   [in] request queue pointer
+ * @bio: [in, out] bio to be split
+ *
+ * Split a bio into two bios, chains the two bios, submit the second half and
+ * store a pointer to the first half in *@bio. Since this function may allocate
+ * a new bio from @q->bio_split, it is the responsibility of the caller to
+ * ensure that @q is only released after processing of the split bio has
+ * finished.
+ */
 void blk_queue_split(struct request_queue *q, struct bio **bio)
 {
 	unsigned int nr_segs;
@@ -305,6 +356,7 @@ EXPORT_SYMBOL(blk_queue_split);
 unsigned int blk_recalc_rq_segments(struct request *rq)
 {
 	unsigned int nr_phys_segs = 0;
+	unsigned int nr_sectors = 0;
 	struct req_iterator iter;
 	struct bio_vec bv;
 
@@ -321,7 +373,8 @@ unsigned int blk_recalc_rq_segments(struct request *rq)
 	}
 
 	rq_for_each_bvec(bv, rq, iter)
-		bvec_split_segs(rq->q, &bv, &nr_phys_segs, NULL, UINT_MAX);
+		bvec_split_segs(rq->q, &bv, &nr_phys_segs, &nr_sectors,
+				UINT_MAX, UINT_MAX);
 	return nr_phys_segs;
 }
 

block/blk-mq-cpumap.c

@@ -15,10 +15,10 @@
 #include "blk.h"
 #include "blk-mq.h"
 
-static int cpu_to_queue_index(struct blk_mq_queue_map *qmap,
-			      unsigned int nr_queues, const int cpu)
+static int queue_index(struct blk_mq_queue_map *qmap,
+		       unsigned int nr_queues, const int q)
 {
-	return qmap->queue_offset + (cpu % nr_queues);
+	return qmap->queue_offset + (q % nr_queues);
 }
 
 static int get_first_sibling(unsigned int cpu)
@@ -36,21 +36,36 @@ int blk_mq_map_queues(struct blk_mq_queue_map *qmap)
 {
 	unsigned int *map = qmap->mq_map;
 	unsigned int nr_queues = qmap->nr_queues;
-	unsigned int cpu, first_sibling;
+	unsigned int cpu, first_sibling, q = 0;
+
+	for_each_possible_cpu(cpu)
+		map[cpu] = -1;
+
+	/*
+	 * Spread queues among present CPUs first for minimizing
+	 * count of dead queues which are mapped by all un-present CPUs
+	 */
+	for_each_present_cpu(cpu) {
+		if (q >= nr_queues)
+			break;
+		map[cpu] = queue_index(qmap, nr_queues, q++);
+	}
 
 	for_each_possible_cpu(cpu) {
+		if (map[cpu] != -1)
+			continue;
 		/*
 		 * First do sequential mapping between CPUs and queues.
 		 * In case we still have CPUs to map, and we have some number of
 		 * threads per cores then map sibling threads to the same queue
 		 * for performance optimizations.
 		 */
-		if (cpu < nr_queues) {
-			map[cpu] = cpu_to_queue_index(qmap, nr_queues, cpu);
+		if (q < nr_queues) {
+			map[cpu] = queue_index(qmap, nr_queues, q++);
 		} else {
 			first_sibling = get_first_sibling(cpu);
 			if (first_sibling == cpu)
-				map[cpu] = cpu_to_queue_index(qmap, nr_queues, cpu);
+				map[cpu] = queue_index(qmap, nr_queues, q++);
 			else
 				map[cpu] = map[first_sibling];
 		}

block/blk-mq-sysfs.c

@@ -270,7 +270,7 @@ void blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
-	lockdep_assert_held(&q->sysfs_lock);
+	lockdep_assert_held(&q->sysfs_dir_lock);
 
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
@@ -320,7 +320,7 @@ int __blk_mq_register_dev(struct device *dev, struct request_queue *q)
 	int ret, i;
 
 	WARN_ON_ONCE(!q->kobj.parent);
-	lockdep_assert_held(&q->sysfs_lock);
+	lockdep_assert_held(&q->sysfs_dir_lock);
 
 	ret = kobject_add(q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
 	if (ret < 0)
@@ -349,23 +349,12 @@ int __blk_mq_register_dev(struct device *dev, struct request_queue *q)
 	return ret;
 }
 
-int blk_mq_register_dev(struct device *dev, struct request_queue *q)
-{
-	int ret;
-
-	mutex_lock(&q->sysfs_lock);
-	ret = __blk_mq_register_dev(dev, q);
-	mutex_unlock(&q->sysfs_lock);
-
-	return ret;
-}
-
 void blk_mq_sysfs_unregister(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
-	mutex_lock(&q->sysfs_lock);
+	mutex_lock(&q->sysfs_dir_lock);
 	if (!q->mq_sysfs_init_done)
 		goto unlock;
 
@@ -373,7 +362,7 @@ void blk_mq_sysfs_unregister(struct request_queue *q)
 		blk_mq_unregister_hctx(hctx);
 
 unlock:
-	mutex_unlock(&q->sysfs_lock);
+	mutex_unlock(&q->sysfs_dir_lock);
 }
 
 int blk_mq_sysfs_register(struct request_queue *q)
@@ -381,7 +370,7 @@ int blk_mq_sysfs_register(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i, ret = 0;
 
-	mutex_lock(&q->sysfs_lock);
+	mutex_lock(&q->sysfs_dir_lock);
 	if (!q->mq_sysfs_init_done)
 		goto unlock;
 
@@ -392,7 +381,7 @@ int blk_mq_sysfs_register(struct request_queue *q)
 	}
 
 unlock:
-	mutex_unlock(&q->sysfs_lock);
+	mutex_unlock(&q->sysfs_dir_lock);
 
 	return ret;
 }

block/blk-mq-tag.c

@@ -10,6 +10,7 @@
 #include <linux/module.h>
 
 #include <linux/blk-mq.h>
+#include <linux/delay.h>
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
@@ -354,6 +355,37 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 }
 EXPORT_SYMBOL(blk_mq_tagset_busy_iter);
 
+static bool blk_mq_tagset_count_completed_rqs(struct request *rq,
+		void *data, bool reserved)
+{
+	unsigned *count = data;
+
+	if (blk_mq_request_completed(rq))
+		(*count)++;
+	return true;
+}
+
+/**
+ * blk_mq_tagset_wait_completed_request - wait until all completed req's
+ * complete funtion is run
+ * @tagset:	Tag set to drain completed request
+ *
+ * Note: This function has to be run after all IO queues are shutdown
+ */
+void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset)
+{
+	while (true) {
+		unsigned count = 0;
+
+		blk_mq_tagset_busy_iter(tagset,
+				blk_mq_tagset_count_completed_rqs, &count);
+		if (!count)
+			break;
+		msleep(5);
+	}
+}
+EXPORT_SYMBOL(blk_mq_tagset_wait_completed_request);
+
 /**
  * blk_mq_queue_tag_busy_iter - iterate over all requests with a driver tag
  * @q:		Request queue to examine.

block/blk-mq.c

@@ -44,12 +44,12 @@ static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
 
 static int blk_mq_poll_stats_bkt(const struct request *rq)
 {
-	int ddir, bytes, bucket;
+	int ddir, sectors, bucket;
 
 	ddir = rq_data_dir(rq);
-	bytes = blk_rq_bytes(rq);
+	sectors = blk_rq_stats_sectors(rq);
 
-	bucket = ddir + 2*(ilog2(bytes) - 9);
+	bucket = ddir + 2 * ilog2(sectors);
 
 	if (bucket < 0)
 		return -1;
@@ -282,16 +282,16 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
 EXPORT_SYMBOL(blk_mq_can_queue);
 
 /*
- * Only need start/end time stamping if we have stats enabled, or using
- * an IO scheduler.
+ * Only need start/end time stamping if we have iostat or
+ * blk stats enabled, or using an IO scheduler.
  */
 static inline bool blk_mq_need_time_stamp(struct request *rq)
 {
-	return (rq->rq_flags & RQF_IO_STAT) || rq->q->elevator;
+	return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS)) || rq->q->elevator;
 }
 
 static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
-		unsigned int tag, unsigned int op)
+		unsigned int tag, unsigned int op, u64 alloc_time_ns)
 {
 	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
 	struct request *rq = tags->static_rqs[tag];
@@ -325,11 +325,15 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	RB_CLEAR_NODE(&rq->rb_node);
 	rq->rq_disk = NULL;
 	rq->part = NULL;
+#ifdef CONFIG_BLK_RQ_ALLOC_TIME
+	rq->alloc_time_ns = alloc_time_ns;
+#endif
 	if (blk_mq_need_time_stamp(rq))
 		rq->start_time_ns = ktime_get_ns();
 	else
 		rq->start_time_ns = 0;
 	rq->io_start_time_ns = 0;
+	rq->stats_sectors = 0;
 	rq->nr_phys_segments = 0;
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 	rq->nr_integrity_segments = 0;
@@ -356,8 +360,14 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 	struct request *rq;
 	unsigned int tag;
 	bool clear_ctx_on_error = false;
+	u64 alloc_time_ns = 0;
 
 	blk_queue_enter_live(q);
+
+	/* alloc_time includes depth and tag waits */
+	if (blk_queue_rq_alloc_time(q))
+		alloc_time_ns = ktime_get_ns();
+
 	data->q = q;
 	if (likely(!data->ctx)) {
 		data->ctx = blk_mq_get_ctx(q);
@@ -393,7 +403,7 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 		return NULL;
 	}
 
-	rq = blk_mq_rq_ctx_init(data, tag, data->cmd_flags);
+	rq = blk_mq_rq_ctx_init(data, tag, data->cmd_flags, alloc_time_ns);
 	if (!op_is_flush(data->cmd_flags)) {
 		rq->elv.icq = NULL;
 		if (e && e->type->ops.prepare_request) {
@@ -652,19 +662,18 @@ bool blk_mq_complete_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
-void blk_mq_complete_request_sync(struct request *rq)
-{
-	WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
-	rq->q->mq_ops->complete(rq);
-}
-EXPORT_SYMBOL_GPL(blk_mq_complete_request_sync);
-
 int blk_mq_request_started(struct request *rq)
 {
 	return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
 }
 EXPORT_SYMBOL_GPL(blk_mq_request_started);
 
+int blk_mq_request_completed(struct request *rq)
+{
+	return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE;
+}
+EXPORT_SYMBOL_GPL(blk_mq_request_completed);
+
 void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
@@ -673,9 +682,7 @@ void blk_mq_start_request(struct request *rq)
 
 	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
 		rq->io_start_time_ns = ktime_get_ns();
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-		rq->throtl_size = blk_rq_sectors(rq);
-#endif
+		rq->stats_sectors = blk_rq_sectors(rq);
 		rq->rq_flags |= RQF_STATS;
 		rq_qos_issue(q, rq);
 	}
@@ -2453,11 +2460,6 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	struct blk_mq_ctx *ctx;
 	struct blk_mq_tag_set *set = q->tag_set;
 
-	/*
-	 * Avoid others reading imcomplete hctx->cpumask through sysfs
-	 */
-	mutex_lock(&q->sysfs_lock);
-
 	queue_for_each_hw_ctx(q, hctx, i) {
 		cpumask_clear(hctx->cpumask);
 		hctx->nr_ctx = 0;
@@ -2518,8 +2520,6 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 					HCTX_TYPE_DEFAULT, i);
 	}
 
-	mutex_unlock(&q->sysfs_lock);
-
 	queue_for_each_hw_ctx(q, hctx, i) {
 		/*
 		 * If no software queues are mapped to this hardware queue,
@@ -2688,7 +2688,11 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 	if (!uninit_q)
 		return ERR_PTR(-ENOMEM);
 
-	q = blk_mq_init_allocated_queue(set, uninit_q);
+	/*
+	 * Initialize the queue without an elevator. device_add_disk() will do
+	 * the initialization.
+	 */
+	q = blk_mq_init_allocated_queue(set, uninit_q, false);
 	if (IS_ERR(q))
 		blk_cleanup_queue(uninit_q);
 
@@ -2839,7 +2843,8 @@ static unsigned int nr_hw_queues(struct blk_mq_tag_set *set)
 }
 
 struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
-						  struct request_queue *q)
+						  struct request_queue *q,
+						  bool elevator_init)
 {
 	/* mark the queue as mq asap */
 	q->mq_ops = set->ops;
@@ -2901,18 +2906,14 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	blk_mq_add_queue_tag_set(set, q);
 	blk_mq_map_swqueue(q);
 
-	if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
-		int ret;
-
-		ret = elevator_init_mq(q);
-		if (ret)
-			return ERR_PTR(ret);
-	}
+	if (elevator_init)
+		elevator_init_mq(q);
 
 	return q;
 
 err_hctxs:
 	kfree(q->queue_hw_ctx);
+	q->nr_hw_queues = 0;
 err_sys_init:
 	blk_mq_sysfs_deinit(q);
 err_poll:

block/blk-pm.c

@@ -207,10 +207,12 @@ EXPORT_SYMBOL(blk_post_runtime_resume);
  */
 void blk_set_runtime_active(struct request_queue *q)
 {
-	spin_lock_irq(&q->queue_lock);
-	q->rpm_status = RPM_ACTIVE;
-	pm_runtime_mark_last_busy(q->dev);
-	pm_request_autosuspend(q->dev);
-	spin_unlock_irq(&q->queue_lock);
+	if (q->dev) {
+		spin_lock_irq(&q->queue_lock);
+		q->rpm_status = RPM_ACTIVE;
+		pm_runtime_mark_last_busy(q->dev);
+		pm_request_autosuspend(q->dev);
+		spin_unlock_irq(&q->queue_lock);
+	}
 }
 EXPORT_SYMBOL(blk_set_runtime_active);

block/blk-rq-qos.c

@@ -83,6 +83,15 @@ void __rq_qos_track(struct rq_qos *rqos, struct request *rq, struct bio *bio)
 	} while (rqos);
 }
 
+void __rq_qos_merge(struct rq_qos *rqos, struct request *rq, struct bio *bio)
+{
+	do {
+		if (rqos->ops->merge)
+			rqos->ops->merge(rqos, rq, bio);
+		rqos = rqos->next;
+	} while (rqos);
+}
+
 void __rq_qos_done_bio(struct rq_qos *rqos, struct bio *bio)
 {
 	do {
@@ -92,6 +101,15 @@ void __rq_qos_done_bio(struct rq_qos *rqos, struct bio *bio)
 	} while (rqos);
 }
 
+void __rq_qos_queue_depth_changed(struct rq_qos *rqos)
+{
+	do {
+		if (rqos->ops->queue_depth_changed)
+			rqos->ops->queue_depth_changed(rqos);
+		rqos = rqos->next;
+	} while (rqos);
+}
+
 /*
  * Return true, if we can't increase the depth further by scaling
  */

block/blk-rq-qos.h

@@ -14,7 +14,8 @@ struct blk_mq_debugfs_attr;
 
 enum rq_qos_id {
 	RQ_QOS_WBT,
-	RQ_QOS_CGROUP,
+	RQ_QOS_LATENCY,
+	RQ_QOS_COST,
 };
 
 struct rq_wait {
@@ -35,11 +36,13 @@ struct rq_qos {
 struct rq_qos_ops {
 	void (*throttle)(struct rq_qos *, struct bio *);
 	void (*track)(struct rq_qos *, struct request *, struct bio *);
+	void (*merge)(struct rq_qos *, struct request *, struct bio *);
 	void (*issue)(struct rq_qos *, struct request *);
 	void (*requeue)(struct rq_qos *, struct request *);
 	void (*done)(struct rq_qos *, struct request *);
 	void (*done_bio)(struct rq_qos *, struct bio *);
 	void (*cleanup)(struct rq_qos *, struct bio *);
+	void (*queue_depth_changed)(struct rq_qos *);
 	void (*exit)(struct rq_qos *);
 	const struct blk_mq_debugfs_attr *debugfs_attrs;
 };
@@ -72,7 +75,7 @@ static inline struct rq_qos *wbt_rq_qos(struct request_queue *q)
 
 static inline struct rq_qos *blkcg_rq_qos(struct request_queue *q)
 {
-	return rq_qos_id(q, RQ_QOS_CGROUP);
+	return rq_qos_id(q, RQ_QOS_LATENCY);
 }
 
 static inline const char *rq_qos_id_to_name(enum rq_qos_id id)
@@ -80,8 +83,10 @@ static inline const char *rq_qos_id_to_name(enum rq_qos_id id)
 	switch (id) {
 	case RQ_QOS_WBT:
 		return "wbt";
-	case RQ_QOS_CGROUP:
-		return "cgroup";
+	case RQ_QOS_LATENCY:
+		return "latency";
+	case RQ_QOS_COST:
+		return "cost";
 	}
 	return "unknown";
 }
@@ -135,7 +140,9 @@ void __rq_qos_issue(struct rq_qos *rqos, struct request *rq);
 void __rq_qos_requeue(struct rq_qos *rqos, struct request *rq);
 void __rq_qos_throttle(struct rq_qos *rqos, struct bio *bio);
 void __rq_qos_track(struct rq_qos *rqos, struct request *rq, struct bio *bio);
+void __rq_qos_merge(struct rq_qos *rqos, struct request *rq, struct bio *bio);
 void __rq_qos_done_bio(struct rq_qos *rqos, struct bio *bio);
+void __rq_qos_queue_depth_changed(struct rq_qos *rqos);
 
 static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio)
 {
@@ -185,6 +192,19 @@ static inline void rq_qos_track(struct request_queue *q, struct request *rq,
 		__rq_qos_track(q->rq_qos, rq, bio);
 }
 
+static inline void rq_qos_merge(struct request_queue *q, struct request *rq,
+				struct bio *bio)
+{
+	if (q->rq_qos)
+		__rq_qos_merge(q->rq_qos, rq, bio);
+}
+
+static inline void rq_qos_queue_depth_changed(struct request_queue *q)
+{
+	if (q->rq_qos)
+		__rq_qos_queue_depth_changed(q->rq_qos);
+}
+
 void rq_qos_exit(struct request_queue *);
 
 #endif

block/blk-settings.c

@@ -805,7 +805,7 @@ EXPORT_SYMBOL(blk_queue_update_dma_alignment);
 void blk_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
 	q->queue_depth = depth;
-	wbt_set_queue_depth(q, depth);
+	rq_qos_queue_depth_changed(q);
 }
 EXPORT_SYMBOL(blk_set_queue_depth);
 
@@ -832,6 +832,22 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
 }
 EXPORT_SYMBOL_GPL(blk_queue_write_cache);
 
+/**
+ * blk_queue_required_elevator_features - Set a queue required elevator features
+ * @q:		the request queue for the target device
+ * @features:	Required elevator features OR'ed together
+ *
+ * Tell the block layer that for the device controlled through @q, only the
+ * only elevators that can be used are those that implement at least the set of
+ * features specified by @features.
+ */
+void blk_queue_required_elevator_features(struct request_queue *q,
+					  unsigned int features)
+{
+	q->required_elevator_features = features;
+}
+EXPORT_SYMBOL_GPL(blk_queue_required_elevator_features);
+
 static int __init blk_settings_init(void)
 {
 	blk_max_low_pfn = max_low_pfn - 1;

block/blk-sysfs.c

@@ -941,14 +941,14 @@ int blk_register_queue(struct gendisk *disk)
 	int ret;
 	struct device *dev = disk_to_dev(disk);
 	struct request_queue *q = disk->queue;
+	bool has_elevator = false;
 
 	if (WARN_ON(!q))
 		return -ENXIO;
 
-	WARN_ONCE(test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags),
+	WARN_ONCE(blk_queue_registered(q),
 		  "%s is registering an already registered queue\n",
 		  kobject_name(&dev->kobj));
-	blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
 
 	/*
 	 * SCSI probing may synchronously create and destroy a lot of
@@ -968,8 +968,7 @@ int blk_register_queue(struct gendisk *disk)
 	if (ret)
 		return ret;
 
-	/* Prevent changes through sysfs until registration is completed. */
-	mutex_lock(&q->sysfs_lock);
+	mutex_lock(&q->sysfs_dir_lock);
 
 	ret = kobject_add(&q->kobj, kobject_get(&dev->kobj), "%s", "queue");
 	if (ret < 0) {
@@ -990,26 +989,36 @@ int blk_register_queue(struct gendisk *disk)
 		blk_mq_debugfs_register(q);
 	}
 
-	kobject_uevent(&q->kobj, KOBJ_ADD);
-
-	wbt_enable_default(q);
-
-	blk_throtl_register_queue(q);
-
+	/*
+	 * The flag of QUEUE_FLAG_REGISTERED isn't set yet, so elevator
+	 * switch won't happen at all.
+	 */
 	if (q->elevator) {
-		ret = elv_register_queue(q);
+		ret = elv_register_queue(q, false);
 		if (ret) {
-			mutex_unlock(&q->sysfs_lock);
-			kobject_uevent(&q->kobj, KOBJ_REMOVE);
+			mutex_unlock(&q->sysfs_dir_lock);
 			kobject_del(&q->kobj);
 			blk_trace_remove_sysfs(dev);
 			kobject_put(&dev->kobj);
 			return ret;
 		}
+		has_elevator = true;
 	}
+
+	mutex_lock(&q->sysfs_lock);
+	blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
+	wbt_enable_default(q);
+	blk_throtl_register_queue(q);
+
+	/* Now everything is ready and send out KOBJ_ADD uevent */
+	kobject_uevent(&q->kobj, KOBJ_ADD);
+	if (has_elevator)
+		kobject_uevent(&q->elevator->kobj, KOBJ_ADD);
+	mutex_unlock(&q->sysfs_lock);
+
 	ret = 0;
 unlock:
-	mutex_unlock(&q->sysfs_lock);
+	mutex_unlock(&q->sysfs_dir_lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_register_queue);
@@ -1029,7 +1038,7 @@ void blk_unregister_queue(struct gendisk *disk)
 		return;
 
 	/* Return early if disk->queue was never registered. */
-	if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
+	if (!blk_queue_registered(q))
 		return;
 
 	/*
@@ -1038,25 +1047,28 @@ void blk_unregister_queue(struct gendisk *disk)
 	 * concurrent elv_iosched_store() calls.
 	 */
 	mutex_lock(&q->sysfs_lock);
-
 	blk_queue_flag_clear(QUEUE_FLAG_REGISTERED, q);
+	mutex_unlock(&q->sysfs_lock);
 
+	mutex_lock(&q->sysfs_dir_lock);
 	/*
 	 * Remove the sysfs attributes before unregistering the queue data
 	 * structures that can be modified through sysfs.
 	 */
 	if (queue_is_mq(q))
 		blk_mq_unregister_dev(disk_to_dev(disk), q);
-	mutex_unlock(&q->sysfs_lock);
 
 	kobject_uevent(&q->kobj, KOBJ_REMOVE);
 	kobject_del(&q->kobj);
 	blk_trace_remove_sysfs(disk_to_dev(disk));
 
-	mutex_lock(&q->sysfs_lock);
+	/*
+	 * q->kobj has been removed, so it is safe to check if elevator
+	 * exists without holding q->sysfs_lock.
+	 */
 	if (q->elevator)
 		elv_unregister_queue(q);
-	mutex_unlock(&q->sysfs_lock);
+	mutex_unlock(&q->sysfs_dir_lock);
 
 	kobject_put(&disk_to_dev(disk)->kobj);
 }

block/blk-throttle.c

@@ -478,12 +478,14 @@ static void throtl_service_queue_init(struct throtl_service_queue *sq)
 	timer_setup(&sq->pending_timer, throtl_pending_timer_fn, 0);
 }
 
-static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, int node)
+static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp,
+						struct request_queue *q,
+						struct blkcg *blkcg)
 {
 	struct throtl_grp *tg;
 	int rw;
 
-	tg = kzalloc_node(sizeof(*tg), gfp, node);
+	tg = kzalloc_node(sizeof(*tg), gfp, q->node);
 	if (!tg)
 		return NULL;
 
@@ -2246,7 +2248,8 @@ void blk_throtl_stat_add(struct request *rq, u64 time_ns)
 	struct request_queue *q = rq->q;
 	struct throtl_data *td = q->td;
 
-	throtl_track_latency(td, rq->throtl_size, req_op(rq), time_ns >> 10);
+	throtl_track_latency(td, blk_rq_stats_sectors(rq), req_op(rq),
+			     time_ns >> 10);
 }
 
 void blk_throtl_bio_endio(struct bio *bio)

block/blk-wbt.c

@@ -629,15 +629,6 @@ static void wbt_requeue(struct rq_qos *rqos, struct request *rq)
 	}
 }
 
-void wbt_set_queue_depth(struct request_queue *q, unsigned int depth)
-{
-	struct rq_qos *rqos = wbt_rq_qos(q);
-	if (rqos) {
-		RQWB(rqos)->rq_depth.queue_depth = depth;
-		__wbt_update_limits(RQWB(rqos));
-	}
-}
-
 void wbt_set_write_cache(struct request_queue *q, bool write_cache_on)
 {
 	struct rq_qos *rqos = wbt_rq_qos(q);
@@ -656,7 +647,7 @@ void wbt_enable_default(struct request_queue *q)
 		return;
 
 	/* Queue not registered? Maybe shutting down... */
-	if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
+	if (!blk_queue_registered(q))
 		return;
 
 	if (queue_is_mq(q) && IS_ENABLED(CONFIG_BLK_WBT_MQ))
@@ -689,6 +680,12 @@ static int wbt_data_dir(const struct request *rq)
 	return -1;
 }
 
+static void wbt_queue_depth_changed(struct rq_qos *rqos)
+{
+	RQWB(rqos)->rq_depth.queue_depth = blk_queue_depth(rqos->q);
+	__wbt_update_limits(RQWB(rqos));
+}
+
 static void wbt_exit(struct rq_qos *rqos)
 {
 	struct rq_wb *rwb = RQWB(rqos);
@@ -811,6 +808,7 @@ static struct rq_qos_ops wbt_rqos_ops = {
 	.requeue = wbt_requeue,
 	.done = wbt_done,
 	.cleanup = wbt_cleanup,
+	.queue_depth_changed = wbt_queue_depth_changed,
 	.exit = wbt_exit,
 #ifdef CONFIG_BLK_DEBUG_FS
 	.debugfs_attrs = wbt_debugfs_attrs,
@@ -853,7 +851,7 @@ int wbt_init(struct request_queue *q)
 
 	rwb->min_lat_nsec = wbt_default_latency_nsec(q);
 
-	wbt_set_queue_depth(q, blk_queue_depth(q));
+	wbt_queue_depth_changed(&rwb->rqos);
 	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 
 	return 0;

block/blk-wbt.h

@@ -95,7 +95,6 @@ void wbt_enable_default(struct request_queue *);
 u64 wbt_get_min_lat(struct request_queue *q);
 void wbt_set_min_lat(struct request_queue *q, u64 val);
 
-void wbt_set_queue_depth(struct request_queue *, unsigned int);
 void wbt_set_write_cache(struct request_queue *, bool);
 
 u64 wbt_default_latency_nsec(struct request_queue *);
@@ -118,9 +117,6 @@ static inline void wbt_disable_default(struct request_queue *q)
 static inline void wbt_enable_default(struct request_queue *q)
 {
 }
-static inline void wbt_set_queue_depth(struct request_queue *q, unsigned int depth)
-{
-}
 static inline void wbt_set_write_cache(struct request_queue *q, bool wc)
 {
 }

block/blk-zoned.c

@@ -202,6 +202,42 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(blkdev_report_zones);
 
+/*
+ * Special case of zone reset operation to reset all zones in one command,
+ * useful for applications like mkfs.
+ */
+static int __blkdev_reset_all_zones(struct block_device *bdev, gfp_t gfp_mask)
+{
+	struct bio *bio = bio_alloc(gfp_mask, 0);
+	int ret;
+
+	/* across the zones operations, don't need any sectors */
+	bio_set_dev(bio, bdev);
+	bio_set_op_attrs(bio, REQ_OP_ZONE_RESET_ALL, 0);
+
+	ret = submit_bio_wait(bio);
+	bio_put(bio);
+
+	return ret;
+}
+
+static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev,
+						sector_t nr_sectors)
+{
+	if (!blk_queue_zone_resetall(bdev_get_queue(bdev)))
+		return false;
+
+	if (nr_sectors != part_nr_sects_read(bdev->bd_part))
+		return false;
+	/*
+	 * REQ_OP_ZONE_RESET_ALL can be executed only if the block device is
+	 * the entire disk, that is, if the blocks device start offset is 0 and
+	 * its capacity is the same as the entire disk.
+	 */
+	return get_start_sect(bdev) == 0 &&
+	       part_nr_sects_read(bdev->bd_part) == get_capacity(bdev->bd_disk);
+}
+
 /**
  * blkdev_reset_zones - Reset zones write pointer
  * @bdev:	Target block device
@@ -235,6 +271,9 @@ int blkdev_reset_zones(struct block_device *bdev,
 		/* Out of range */
 		return -EINVAL;
 
+	if (blkdev_allow_reset_all_zones(bdev, nr_sectors))
+		return  __blkdev_reset_all_zones(bdev, gfp_mask);
+
 	/* Check alignment (handle eventual smaller last zone) */
 	zone_sectors = blk_queue_zone_sectors(q);
 	if (sector & (zone_sectors - 1))

block/blk.h

@@ -184,11 +184,11 @@ void blk_account_io_done(struct request *req, u64 now);
 
 void blk_insert_flush(struct request *rq);
 
-int elevator_init_mq(struct request_queue *q);
+void elevator_init_mq(struct request_queue *q);
 int elevator_switch_mq(struct request_queue *q,
 			      struct elevator_type *new_e);
 void __elevator_exit(struct request_queue *, struct elevator_queue *);
-int elv_register_queue(struct request_queue *q);
+int elv_register_queue(struct request_queue *q, bool uevent);
 void elv_unregister_queue(struct request_queue *q);
 
 static inline void elevator_exit(struct request_queue *q,

block/genhd.c

@@ -695,6 +695,15 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk,
 	dev_t devt;
 	int retval;
 
+	/*
+	 * The disk queue should now be all set with enough information about
+	 * the device for the elevator code to pick an adequate default
+	 * elevator if one is needed, that is, for devices requesting queue
+	 * registration.
+	 */
+	if (register_queue)
+		elevator_init_mq(disk->queue);
+
 	/* minors == 0 indicates to use ext devt from part0 and should
 	 * be accompanied with EXT_DEVT flag.  Make sure all
 	 * parameters make sense.

block/mq-deadline.c

@@ -377,13 +377,6 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd)
  * hardware queue, but we may return a request that is for a
  * different hardware queue. This is because mq-deadline has shared
  * state for all hardware queues, in terms of sorting, FIFOs, etc.
- *
- * For a zoned block device, __dd_dispatch_request() may return NULL
- * if all the queued write requests are directed at zones that are already
- * locked due to on-going write requests. In this case, make sure to mark
- * the queue as needing a restart to ensure that the queue is run again
- * and the pending writes dispatched once the target zones for the ongoing
- * write requests are unlocked in dd_finish_request().
  */
 static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 {
@@ -392,9 +385,6 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 
 	spin_lock(&dd->lock);
 	rq = __dd_dispatch_request(dd);
-	if (!rq && blk_queue_is_zoned(hctx->queue) &&
-	    !list_empty(&dd->fifo_list[WRITE]))
-		blk_mq_sched_mark_restart_hctx(hctx);
 	spin_unlock(&dd->lock);
 
 	return rq;
@@ -561,6 +551,13 @@ static void dd_prepare_request(struct request *rq, struct bio *bio)
  * spinlock so that the zone is never unlocked while deadline_fifo_request()
  * or deadline_next_request() are executing. This function is called for
  * all requests, whether or not these requests complete successfully.
+ *
+ * For a zoned block device, __dd_dispatch_request() may have stopped
+ * dispatching requests if all the queued requests are write requests directed
+ * at zones that are already locked due to on-going write requests. To ensure
+ * write request dispatch progress in this case, mark the queue as needing a
+ * restart to ensure that the queue is run again after completion of the
+ * request and zones being unlocked.
  */
 static void dd_finish_request(struct request *rq)
 {
@@ -572,6 +569,8 @@ static void dd_finish_request(struct request *rq)
 
 		spin_lock_irqsave(&dd->zone_lock, flags);
 		blk_req_zone_write_unlock(rq);
+		if (!list_empty(&dd->fifo_list[WRITE]))
+			blk_mq_sched_mark_restart_hctx(rq->mq_hctx);
 		spin_unlock_irqrestore(&dd->zone_lock, flags);
 	}
 }
@@ -795,6 +794,7 @@ static struct elevator_type mq_deadline = {
 	.elevator_attrs = deadline_attrs,
 	.elevator_name = "mq-deadline",
 	.elevator_alias = "deadline",
+	.elevator_features = ELEVATOR_F_ZBD_SEQ_WRITE,
 	.elevator_owner = THIS_MODULE,
 };
 MODULE_ALIAS("mq-deadline-iosched");

block/opal_proto.h

@@ -119,8 +119,6 @@ enum opal_uid {
 	OPAL_UID_HEXFF,
 };
 
-#define OPAL_METHOD_LENGTH 8
-
 /* Enum for indexing the OPALMETHOD array */
 enum opal_method {
 	OPAL_PROPERTIES,
@@ -167,7 +165,6 @@ enum opal_token {
 	OPAL_TABLE_LASTID = 0x0A,
 	OPAL_TABLE_MIN = 0x0B,
 	OPAL_TABLE_MAX = 0x0C,
-
 	/* authority table */
 	OPAL_PIN = 0x03,
 	/* locking tokens */
@@ -182,7 +179,7 @@ enum opal_token {
 	OPAL_LIFECYCLE = 0x06,
 	/* locking info table */
 	OPAL_MAXRANGES = 0x04,
-	 /* mbr control */
+	/* mbr control */
 	OPAL_MBRENABLE = 0x01,
 	OPAL_MBRDONE = 0x02,
 	/* properties */

drivers/block/floppy.c

@@ -3780,7 +3780,7 @@ static int compat_getdrvprm(int drive,
 	v.native_format = UDP->native_format;
 	mutex_unlock(&floppy_mutex);
 
-	if (copy_from_user(arg, &v, sizeof(struct compat_floppy_drive_params)))
+	if (copy_to_user(arg, &v, sizeof(struct compat_floppy_drive_params)))
 		return -EFAULT;
 	return 0;
 }
@@ -3816,7 +3816,7 @@ static int compat_getdrvstat(int drive, bool poll,
 	v.bufblocks = UDRS->bufblocks;
 	mutex_unlock(&floppy_mutex);
 
-	if (copy_from_user(arg, &v, sizeof(struct compat_floppy_drive_struct)))
+	if (copy_to_user(arg, &v, sizeof(struct compat_floppy_drive_struct)))
 		return -EFAULT;
 	return 0;
 Eintr:

drivers/block/loop.c

@@ -1755,6 +1755,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 	case LOOP_SET_FD:
 	case LOOP_CHANGE_FD:
 	case LOOP_SET_BLOCK_SIZE:
+	case LOOP_SET_DIRECT_IO:
 		err = lo_ioctl(bdev, mode, cmd, arg);
 		break;
 	default:

drivers/block/null_blk.h

@@ -2,6 +2,9 @@
 #ifndef __BLK_NULL_BLK_H
 #define __BLK_NULL_BLK_H
 
+#undef pr_fmt
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/blkdev.h>
 #include <linux/slab.h>
 #include <linux/blk-mq.h>
@@ -90,13 +93,13 @@ int null_zone_init(struct nullb_device *dev);
 void null_zone_exit(struct nullb_device *dev);
 int null_zone_report(struct gendisk *disk, sector_t sector,
 		     struct blk_zone *zones, unsigned int *nr_zones);
-void null_zone_write(struct nullb_cmd *cmd, sector_t sector,
-			unsigned int nr_sectors);
-void null_zone_reset(struct nullb_cmd *cmd, sector_t sector);
+blk_status_t null_handle_zoned(struct nullb_cmd *cmd,
+				enum req_opf op, sector_t sector,
+				sector_t nr_sectors);
 #else
 static inline int null_zone_init(struct nullb_device *dev)
 {
-	pr_err("null_blk: CONFIG_BLK_DEV_ZONED not enabled\n");
+	pr_err("CONFIG_BLK_DEV_ZONED not enabled\n");
 	return -EINVAL;
 }
 static inline void null_zone_exit(struct nullb_device *dev) {}
@@ -106,10 +109,11 @@ static inline int null_zone_report(struct gendisk *disk, sector_t sector,
 {
 	return -EOPNOTSUPP;
 }
-static inline void null_zone_write(struct nullb_cmd *cmd, sector_t sector,
-				   unsigned int nr_sectors)
+static inline blk_status_t null_handle_zoned(struct nullb_cmd *cmd,
+					     enum req_opf op, sector_t sector,
+					     sector_t nr_sectors)
 {
+	return BLK_STS_NOTSUPP;
 }
-static inline void null_zone_reset(struct nullb_cmd *cmd, sector_t sector) {}
 #endif /* CONFIG_BLK_DEV_ZONED */
 #endif /* __NULL_BLK_H */

drivers/block/null_blk_zoned.c

@@ -17,7 +17,7 @@ int null_zone_init(struct nullb_device *dev)
 	unsigned int i;
 
 	if (!is_power_of_2(dev->zone_size)) {
-		pr_err("null_blk: zone_size must be power-of-two\n");
+		pr_err("zone_size must be power-of-two\n");
 		return -EINVAL;
 	}
 
@@ -31,7 +31,7 @@ int null_zone_init(struct nullb_device *dev)
 
 	if (dev->zone_nr_conv >= dev->nr_zones) {
 		dev->zone_nr_conv = dev->nr_zones - 1;
-		pr_info("null_blk: changed the number of conventional zones to %u",
+		pr_info("changed the number of conventional zones to %u",
 			dev->zone_nr_conv);
 	}
 
@@ -84,7 +84,7 @@ int null_zone_report(struct gendisk *disk, sector_t sector,
 	return 0;
 }
 
-void null_zone_write(struct nullb_cmd *cmd, sector_t sector,
+static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 		     unsigned int nr_sectors)
 {
 	struct nullb_device *dev = cmd->nq->dev;
@@ -95,14 +95,12 @@ void null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 	case BLK_ZONE_COND_FULL:
 		/* Cannot write to a full zone */
 		cmd->error = BLK_STS_IOERR;
-		break;
+		return BLK_STS_IOERR;
 	case BLK_ZONE_COND_EMPTY:
 	case BLK_ZONE_COND_IMP_OPEN:
 		/* Writes must be at the write pointer position */
-		if (sector != zone->wp) {
-			cmd->error = BLK_STS_IOERR;
-			break;
-		}
+		if (sector != zone->wp)
+			return BLK_STS_IOERR;
 
 		if (zone->cond == BLK_ZONE_COND_EMPTY)
 			zone->cond = BLK_ZONE_COND_IMP_OPEN;
@@ -115,22 +113,51 @@ void null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 		break;
 	default:
 		/* Invalid zone condition */
-		cmd->error = BLK_STS_IOERR;
-		break;
+		return BLK_STS_IOERR;
 	}
+	return BLK_STS_OK;
 }
 
-void null_zone_reset(struct nullb_cmd *cmd, sector_t sector)
+static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector)
 {
 	struct nullb_device *dev = cmd->nq->dev;
 	unsigned int zno = null_zone_no(dev, sector);
 	struct blk_zone *zone = &dev->zones[zno];
+	size_t i;
+
+	switch (req_op(cmd->rq)) {
+	case REQ_OP_ZONE_RESET_ALL:
+		for (i = 0; i < dev->nr_zones; i++) {
+			if (zone[i].type == BLK_ZONE_TYPE_CONVENTIONAL)
+				continue;
+			zone[i].cond = BLK_ZONE_COND_EMPTY;
+			zone[i].wp = zone[i].start;
+		}
+		break;
+	case REQ_OP_ZONE_RESET:
+		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+			return BLK_STS_IOERR;
 
-	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) {
-		cmd->error = BLK_STS_IOERR;
-		return;
+		zone->cond = BLK_ZONE_COND_EMPTY;
+		zone->wp = zone->start;
+		break;
+	default:
+		cmd->error = BLK_STS_NOTSUPP;
+		break;
 	}
+	return BLK_STS_OK;
+}
 
-	zone->cond = BLK_ZONE_COND_EMPTY;
-	zone->wp = zone->start;
+blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op,
+			       sector_t sector, sector_t nr_sectors)
+{
+	switch (op) {
+	case REQ_OP_WRITE:
+		return null_zone_write(cmd, sector, nr_sectors);
+	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_RESET_ALL:
+		return null_zone_reset(cmd, sector);
+	default:
+		return BLK_STS_OK;
+	}
 }

drivers/block/paride/pcd.c

@@ -314,8 +314,8 @@ static void pcd_init_units(void)
 		disk->queue = blk_mq_init_sq_queue(&cd->tag_set, &pcd_mq_ops,
 						   1, BLK_MQ_F_SHOULD_MERGE);
 		if (IS_ERR(disk->queue)) {
-			put_disk(disk);
 			disk->queue = NULL;
+			put_disk(disk);
 			continue;
 		}
 
@@ -723,9 +723,9 @@ static int pcd_detect(void)
 	k = 0;
 	if (pcd_drive_count == 0) { /* nothing spec'd - so autoprobe for 1 */
 		cd = pcd;
-		if (pi_init(cd->pi, 1, -1, -1, -1, -1, -1, pcd_buffer,
-			    PI_PCD, verbose, cd->name)) {
-			if (!pcd_probe(cd, -1, id) && cd->disk) {
+		if (cd->disk && pi_init(cd->pi, 1, -1, -1, -1, -1, -1,
+			    pcd_buffer, PI_PCD, verbose, cd->name)) {
+			if (!pcd_probe(cd, -1, id)) {
 				cd->present = 1;
 				k++;
 			} else
@@ -736,11 +736,13 @@ static int pcd_detect(void)
 			int *conf = *drives[unit];
 			if (!conf[D_PRT])
 				continue;
+			if (!cd->disk)
+				continue;
 			if (!pi_init(cd->pi, 0, conf[D_PRT], conf[D_MOD],
 				     conf[D_UNI], conf[D_PRO], conf[D_DLY],
 				     pcd_buffer, PI_PCD, verbose, cd->name)) 
 				continue;
-			if (!pcd_probe(cd, conf[D_SLV], id) && cd->disk) {
+			if (!pcd_probe(cd, conf[D_SLV], id)) {
 				cd->present = 1;
 				k++;
 			} else

drivers/block/paride/pf.c

@@ -300,8 +300,8 @@ static void __init pf_init_units(void)
 		disk->queue = blk_mq_init_sq_queue(&pf->tag_set, &pf_mq_ops,
 							1, BLK_MQ_F_SHOULD_MERGE);
 		if (IS_ERR(disk->queue)) {
-			put_disk(disk);
 			disk->queue = NULL;
+			put_disk(disk);
 			continue;
 		}
 

drivers/md/bcache/closure.c

@@ -105,8 +105,14 @@ struct closure_syncer {
 
 static void closure_sync_fn(struct closure *cl)
 {
-	cl->s->done = 1;
-	wake_up_process(cl->s->task);
+	struct closure_syncer *s = cl->s;
+	struct task_struct *p;
+
+	rcu_read_lock();
+	p = READ_ONCE(s->task);
+	s->done = 1;
+	wake_up_process(p);
+	rcu_read_unlock();
 }
 
 void __sched __closure_sync(struct closure *cl)

drivers/md/bcache/debug.c

@@ -178,10 +178,9 @@ static ssize_t bch_dump_read(struct file *file, char __user *buf,
 	while (size) {
 		struct keybuf_key *w;
 		unsigned int bytes = min(i->bytes, size);
-		int err = copy_to_user(buf, i->buf, bytes);
 
-		if (err)
-			return err;
+		if (copy_to_user(buf, i->buf, bytes))
+			return -EFAULT;
 
 		ret	 += bytes;
 		buf	 += bytes;

drivers/md/bcache/sysfs.c

@@ -964,6 +964,7 @@ KTYPE(bch_cache_set_internal);
 
 static int __bch_cache_cmp(const void *l, const void *r)
 {
+	cond_resched();
 	return *((uint16_t *)r) - *((uint16_t *)l);
 }