Merge tag 'for-6.4/block-2023-04-21' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - drbd patches, bringing us closer to unifying the out-of-tree version
   and the in tree one (Andreas, Christoph)

 - support for auto-quiesce for the s390 dasd driver (Stefan)

 - MD pull request via Song:
      - md/bitmap: Optimal last page size (Jon Derrick)
      - Various raid10 fixes (Yu Kuai, Li Nan)
      - md: add error_handlers for raid0 and linear (Mariusz Tkaczyk)

 - NVMe pull request via Christoph:
      - Drop redundant pci_enable_pcie_error_reporting (Bjorn Helgaas)
      - Validate nvmet module parameters (Chaitanya Kulkarni)
      - Fence TCP socket on receive error (Chris Leech)
      - Fix async event trace event (Keith Busch)
      - Minor cleanups (Chaitanya Kulkarni, zhenwei pi)
      - Fix and cleanup nvmet Identify handling (Damien Le Moal,
        Christoph Hellwig)
      - Fix double blk_mq_complete_request race in the timeout handler
        (Lei Yin)
      - Fix irq locking in nvme-fcloop (Ming Lei)
      - Remove queue mapping helper for rdma devices (Sagi Grimberg)

 - use structured request attribute checks for nbd (Jakub)

 - fix blk-crypto race conditions between keyslot management (Eric)

 - add sed-opal support for reading read locking range attributes
   (Ondrej)

 - make fault injection configurable for null_blk (Akinobu)

 - clean up the request insertion API (Christoph)

 - clean up the queue running API (Christoph)

 - blkg config helper cleanups (Tejun)

 - lazy init support for blk-iolatency (Tejun)

 - various fixes and tweaks to ublk (Ming)

 - remove hybrid polling. It hasn't really been useful since we got
   async polled IO support, and these days we don't support sync polled
   IO at all (Keith)

 - misc fixes, cleanups, improvements (Zhong, Ondrej, Colin, Chengming,
   Chaitanya, me)

* tag 'for-6.4/block-2023-04-21' of git://git.kernel.dk/linux: (118 commits)
  nbd: fix incomplete validation of ioctl arg
  ublk: don't return 0 in case of any failure
  sed-opal: geometry feature reporting command
  null_blk: Always check queue mode setting from configfs
  block: ublk: switch to ioctl command encoding
  blk-mq: fix the blk_mq_add_to_requeue_list call in blk_kick_flush
  block, bfq: Fix division by zero error on zero wsum
  fault-inject: fix build error when FAULT_INJECTION_CONFIGFS=y and CONFIGFS_FS=m
  block: store bdev->bd_disk->fops->submit_bio state in bdev
  block: re-arrange the struct block_device fields for better layout
  md/raid5: remove unused working_disks variable
  md/raid10: don't call bio_start_io_acct twice for bio which experienced read error
  md/raid10: fix memleak of md thread
  md/raid10: fix memleak for 'conf->bio_split'
  md/raid10: fix leak of 'r10bio->remaining' for recovery
  md/raid10: don't BUG_ON() in raise_barrier()
  md: fix soft lockup in status_resync
  md: add error_handlers for raid0 and linear
  md: Use optimal I/O size for last bitmap page
  md: Fix types in sb writer
  ...

block/Kconfig

@@ -215,11 +215,6 @@ config BLK_MQ_VIRTIO
 	depends on VIRTIO
 	default y
 
-config BLK_MQ_RDMA
-	bool
-	depends on INFINIBAND
-	default y
-
 config BLK_PM
 	def_bool PM
 

block/Makefile

@@ -30,7 +30,6 @@ obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY_T10)	+= t10-pi.o
 obj-$(CONFIG_BLK_MQ_PCI)	+= blk-mq-pci.o
 obj-$(CONFIG_BLK_MQ_VIRTIO)	+= blk-mq-virtio.o
-obj-$(CONFIG_BLK_MQ_RDMA)	+= blk-mq-rdma.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
 obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o

block/bdev.c

@@ -419,6 +419,7 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	bdev->bd_inode = inode;
 	bdev->bd_queue = disk->queue;
 	bdev->bd_stats = alloc_percpu(struct disk_stats);
+	bdev->bd_has_submit_bio = false;
 	if (!bdev->bd_stats) {
 		iput(inode);
 		return NULL;

block/bfq-cgroup.c

@@ -497,17 +497,11 @@ static struct blkcg_policy_data *bfq_cpd_alloc(gfp_t gfp)
 	bgd = kzalloc(sizeof(*bgd), gfp);
 	if (!bgd)
 		return NULL;
+
+	bgd->weight = CGROUP_WEIGHT_DFL;
 	return &bgd->pd;
 }
 
-static void bfq_cpd_init(struct blkcg_policy_data *cpd)
-{
-	struct bfq_group_data *d = cpd_to_bfqgd(cpd);
-
-	d->weight = cgroup_subsys_on_dfl(io_cgrp_subsys) ?
-		CGROUP_WEIGHT_DFL : BFQ_WEIGHT_LEGACY_DFL;
-}
-
 static void bfq_cpd_free(struct blkcg_policy_data *cpd)
 {
 	kfree(cpd_to_bfqgd(cpd));
@@ -1111,9 +1105,11 @@ static ssize_t bfq_io_set_device_weight(struct kernfs_open_file *of,
 	struct bfq_group *bfqg;
 	u64 v;
 
-	ret = blkg_conf_prep(blkcg, &blkcg_policy_bfq, buf, &ctx);
+	blkg_conf_init(&ctx, buf);
+
+	ret = blkg_conf_prep(blkcg, &blkcg_policy_bfq, &ctx);
 	if (ret)
-		return ret;
+		goto out;
 
 	if (sscanf(ctx.body, "%llu", &v) == 1) {
 		/* require "default" on dfl */
@@ -1135,7 +1131,7 @@ static ssize_t bfq_io_set_device_weight(struct kernfs_open_file *of,
 		ret = 0;
 	}
 out:
-	blkg_conf_finish(&ctx);
+	blkg_conf_exit(&ctx);
 	return ret ?: nbytes;
 }
 
@@ -1301,8 +1297,6 @@ struct blkcg_policy blkcg_policy_bfq = {
 	.legacy_cftypes		= bfq_blkcg_legacy_files,
 
 	.cpd_alloc_fn		= bfq_cpd_alloc,
-	.cpd_init_fn		= bfq_cpd_init,
-	.cpd_bind_fn	        = bfq_cpd_init,
 	.cpd_free_fn		= bfq_cpd_free,
 
 	.pd_alloc_fn		= bfq_pd_alloc,

block/bfq-iosched.c

@@ -129,7 +129,6 @@
 #include "elevator.h"
 #include "blk.h"
 #include "blk-mq.h"
-#include "blk-mq-tag.h"
 #include "blk-mq-sched.h"
 #include "bfq-iosched.h"
 #include "blk-wbt.h"
@@ -649,6 +648,8 @@ retry:
 					sched_data->service_tree[i].wsum;
 			}
 		}
+		if (!wsum)
+			continue;
 		limit = DIV_ROUND_CLOSEST(limit * entity->weight, wsum);
 		if (entity->allocated >= limit) {
 			bfq_log_bfqq(bfqq->bfqd, bfqq,
@@ -6232,7 +6233,7 @@ static inline void bfq_update_insert_stats(struct request_queue *q,
 static struct bfq_queue *bfq_init_rq(struct request *rq);
 
 static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
-			       bool at_head)
+			       blk_insert_t flags)
 {
 	struct request_queue *q = hctx->queue;
 	struct bfq_data *bfqd = q->elevator->elevator_data;
@@ -6255,11 +6256,10 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 
 	trace_block_rq_insert(rq);
 
-	if (!bfqq || at_head) {
-		if (at_head)
-			list_add(&rq->queuelist, &bfqd->dispatch);
-		else
-			list_add_tail(&rq->queuelist, &bfqd->dispatch);
+	if (flags & BLK_MQ_INSERT_AT_HEAD) {
+		list_add(&rq->queuelist, &bfqd->dispatch);
+	} else if (!bfqq) {
+		list_add_tail(&rq->queuelist, &bfqd->dispatch);
 	} else {
 		idle_timer_disabled = __bfq_insert_request(bfqd, rq);
 		/*
@@ -6289,14 +6289,15 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 }
 
 static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
-				struct list_head *list, bool at_head)
+				struct list_head *list,
+				blk_insert_t flags)
 {
 	while (!list_empty(list)) {
 		struct request *rq;
 
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		bfq_insert_request(hctx, rq, at_head);
+		bfq_insert_request(hctx, rq, flags);
 	}
 }
 

block/bfq-iosched.h

@@ -20,7 +20,6 @@
 
 #define BFQ_DEFAULT_QUEUE_IOPRIO	4
 
-#define BFQ_WEIGHT_LEGACY_DFL	100
 #define BFQ_DEFAULT_GRP_IOPRIO	0
 #define BFQ_DEFAULT_GRP_CLASS	IOPRIO_CLASS_BE
 

block/blk-cgroup.c

@@ -33,7 +33,6 @@
 #include "blk-cgroup.h"
 #include "blk-ioprio.h"
 #include "blk-throttle.h"
-#include "blk-rq-qos.h"
 
 /*
  * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation.
@@ -693,69 +692,93 @@ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v)
 EXPORT_SYMBOL_GPL(__blkg_prfill_u64);
 
 /**
- * blkcg_conf_open_bdev - parse and open bdev for per-blkg config update
- * @inputp: input string pointer
+ * blkg_conf_init - initialize a blkg_conf_ctx
+ * @ctx: blkg_conf_ctx to initialize
+ * @input: input string
  *
- * Parse the device node prefix part, MAJ:MIN, of per-blkg config update
- * from @input and get and return the matching bdev.  *@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.
+ * Initialize @ctx which can be used to parse blkg config input string @input.
+ * Once initialized, @ctx can be used with blkg_conf_open_bdev() and
+ * blkg_conf_prep(), and must be cleaned up with blkg_conf_exit().
  */
-struct block_device *blkcg_conf_open_bdev(char **inputp)
+void blkg_conf_init(struct blkg_conf_ctx *ctx, char *input)
 {
-	char *input = *inputp;
+	*ctx = (struct blkg_conf_ctx){ .input = input };
+}
+EXPORT_SYMBOL_GPL(blkg_conf_init);
+
+/**
+ * blkg_conf_open_bdev - parse and open bdev for per-blkg config update
+ * @ctx: blkg_conf_ctx initialized with blkg_conf_init()
+ *
+ * Parse the device node prefix part, MAJ:MIN, of per-blkg config update from
+ * @ctx->input and get and store the matching bdev in @ctx->bdev. @ctx->body is
+ * set to point past the device node prefix.
+ *
+ * This function may be called multiple times on @ctx and the extra calls become
+ * NOOPs. blkg_conf_prep() implicitly calls this function. Use this function
+ * explicitly if bdev access is needed without resolving the blkcg / policy part
+ * of @ctx->input. Returns -errno on error.
+ */
+int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx)
+{
+	char *input = ctx->input;
 	unsigned int major, minor;
 	struct block_device *bdev;
 	int key_len;
 
+	if (ctx->bdev)
+		return 0;
+
 	if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	input += key_len;
 	if (!isspace(*input))
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 	input = skip_spaces(input);
 
 	bdev = blkdev_get_no_open(MKDEV(major, minor));
 	if (!bdev)
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 	if (bdev_is_partition(bdev)) {
 		blkdev_put_no_open(bdev);
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 	}
 
-	*inputp = input;
-	return bdev;
+	ctx->body = input;
+	ctx->bdev = bdev;
+	return 0;
 }
 
 /**
  * blkg_conf_prep - parse and prepare for per-blkg config update
  * @blkcg: target block cgroup
  * @pol: target policy
- * @input: input string
- * @ctx: blkg_conf_ctx to be filled
+ * @ctx: blkg_conf_ctx initialized with blkg_conf_init()
  *
- * Parse per-blkg config update from @input and initialize @ctx with the
- * result.  @ctx->blkg points to the blkg to be updated and @ctx->body the
- * part of @input following MAJ:MIN.  This function returns with RCU read
- * lock and queue lock held and must be paired with blkg_conf_finish().
+ * Parse per-blkg config update from @ctx->input and initialize @ctx
+ * accordingly. On success, @ctx->body points to the part of @ctx->input
+ * following MAJ:MIN, @ctx->bdev points to the target block device and
+ * @ctx->blkg to the blkg being configured.
+ *
+ * blkg_conf_open_bdev() may be called on @ctx beforehand. On success, this
+ * function returns with queue lock held and must be followed by
+ * blkg_conf_exit().
  */
 int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
-		   char *input, struct blkg_conf_ctx *ctx)
-	__acquires(rcu) __acquires(&bdev->bd_queue->queue_lock)
+		   struct blkg_conf_ctx *ctx)
+	__acquires(&bdev->bd_queue->queue_lock)
 {
-	struct block_device *bdev;
 	struct gendisk *disk;
 	struct request_queue *q;
 	struct blkcg_gq *blkg;
 	int ret;
 
-	bdev = blkcg_conf_open_bdev(&input);
-	if (IS_ERR(bdev))
-		return PTR_ERR(bdev);
-	disk = bdev->bd_disk;
+	ret = blkg_conf_open_bdev(ctx);
+	if (ret)
+		return ret;
+
+	disk = ctx->bdev->bd_disk;
 	q = disk->queue;
 
 	/*
@@ -766,7 +789,6 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	if (ret)
 		goto fail;
 
-	rcu_read_lock();
 	spin_lock_irq(&q->queue_lock);
 
 	if (!blkcg_policy_enabled(q, pol)) {
@@ -795,7 +817,6 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 
 		/* Drop locks to do new blkg allocation with GFP_KERNEL. */
 		spin_unlock_irq(&q->queue_lock);
-		rcu_read_unlock();
 
 		new_blkg = blkg_alloc(pos, disk, GFP_KERNEL);
 		if (unlikely(!new_blkg)) {
@@ -809,7 +830,6 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 			goto fail_exit_queue;
 		}
 
-		rcu_read_lock();
 		spin_lock_irq(&q->queue_lock);
 
 		if (!blkcg_policy_enabled(q, pol)) {
@@ -836,20 +856,16 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	}
 success:
 	blk_queue_exit(q);
-	ctx->bdev = bdev;
 	ctx->blkg = blkg;
-	ctx->body = input;
 	return 0;
 
 fail_preloaded:
 	radix_tree_preload_end();
 fail_unlock:
 	spin_unlock_irq(&q->queue_lock);
-	rcu_read_unlock();
 fail_exit_queue:
 	blk_queue_exit(q);
 fail:
-	blkdev_put_no_open(bdev);
 	/*
 	 * If queue was bypassing, we should retry.  Do so after a
 	 * short msleep().  It isn't strictly necessary but queue
@@ -865,20 +881,27 @@ fail:
 EXPORT_SYMBOL_GPL(blkg_conf_prep);
 
 /**
- * blkg_conf_finish - finish up per-blkg config update
- * @ctx: blkg_conf_ctx initialized by blkg_conf_prep()
+ * blkg_conf_exit - clean up per-blkg config update
+ * @ctx: blkg_conf_ctx initialized with blkg_conf_init()
  *
- * Finish up after per-blkg config update.  This function must be paired
- * with blkg_conf_prep().
+ * Clean up after per-blkg config update. This function must be called on all
+ * blkg_conf_ctx's initialized with blkg_conf_init().
  */
-void blkg_conf_finish(struct blkg_conf_ctx *ctx)
-	__releases(&ctx->bdev->bd_queue->queue_lock) __releases(rcu)
+void blkg_conf_exit(struct blkg_conf_ctx *ctx)
+	__releases(&ctx->bdev->bd_queue->queue_lock)
 {
-	spin_unlock_irq(&bdev_get_queue(ctx->bdev)->queue_lock);
-	rcu_read_unlock();
-	blkdev_put_no_open(ctx->bdev);
+	if (ctx->blkg) {
+		spin_unlock_irq(&bdev_get_queue(ctx->bdev)->queue_lock);
+		ctx->blkg = NULL;
+	}
+
+	if (ctx->bdev) {
+		blkdev_put_no_open(ctx->bdev);
+		ctx->body = NULL;
+		ctx->bdev = NULL;
+	}
 }
-EXPORT_SYMBOL_GPL(blkg_conf_finish);
+EXPORT_SYMBOL_GPL(blkg_conf_exit);
 
 static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src)
 {
@@ -1289,8 +1312,6 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 		blkcg->cpd[i] = cpd;
 		cpd->blkcg = blkcg;
 		cpd->plid = i;
-		if (pol->cpd_init_fn)
-			pol->cpd_init_fn(cpd);
 	}
 
 	spin_lock_init(&blkcg->lock);
@@ -1368,14 +1389,8 @@ int blkcg_init_disk(struct gendisk *disk)
 	if (ret)
 		goto err_ioprio_exit;
 
-	ret = blk_iolatency_init(disk);
-	if (ret)
-		goto err_throtl_exit;
-
 	return 0;
 
-err_throtl_exit:
-	blk_throtl_exit(disk);
 err_ioprio_exit:
 	blk_ioprio_exit(disk);
 err_destroy_all:
@@ -1391,30 +1406,9 @@ err_unlock:
 void blkcg_exit_disk(struct gendisk *disk)
 {
 	blkg_destroy_all(disk);
-	rq_qos_exit(disk->queue);
 	blk_throtl_exit(disk);
 }
 
-static void blkcg_bind(struct cgroup_subsys_state *root_css)
-{
-	int i;
-
-	mutex_lock(&blkcg_pol_mutex);
-
-	for (i = 0; i < BLKCG_MAX_POLS; i++) {
-		struct blkcg_policy *pol = blkcg_policy[i];
-		struct blkcg *blkcg;
-
-		if (!pol || !pol->cpd_bind_fn)
-			continue;
-
-		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node)
-			if (blkcg->cpd[pol->plid])
-				pol->cpd_bind_fn(blkcg->cpd[pol->plid]);
-	}
-	mutex_unlock(&blkcg_pol_mutex);
-}
-
 static void blkcg_exit(struct task_struct *tsk)
 {
 	if (tsk->throttle_disk)
@@ -1428,7 +1422,6 @@ struct cgroup_subsys io_cgrp_subsys = {
 	.css_offline = blkcg_css_offline,
 	.css_free = blkcg_css_free,
 	.css_rstat_flush = blkcg_rstat_flush,
-	.bind = blkcg_bind,
 	.dfl_cftypes = blkcg_files,
 	.legacy_cftypes = blkcg_legacy_files,
 	.legacy_name = "blkio",
@@ -1666,8 +1659,6 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 			blkcg->cpd[pol->plid] = cpd;
 			cpd->blkcg = blkcg;
 			cpd->plid = pol->plid;
-			if (pol->cpd_init_fn)
-				pol->cpd_init_fn(cpd);
 		}
 	}
 

block/blk-cgroup.h

@@ -174,9 +174,7 @@ struct blkcg_policy {
 
 	/* operations */
 	blkcg_pol_alloc_cpd_fn		*cpd_alloc_fn;
-	blkcg_pol_init_cpd_fn		*cpd_init_fn;
 	blkcg_pol_free_cpd_fn		*cpd_free_fn;
-	blkcg_pol_bind_cpd_fn		*cpd_bind_fn;
 
 	blkcg_pol_alloc_pd_fn		*pd_alloc_fn;
 	blkcg_pol_init_pd_fn		*pd_init_fn;
@@ -209,15 +207,17 @@ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
 u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v);
 
 struct blkg_conf_ctx {
+	char				*input;
+	char				*body;
 	struct block_device		*bdev;
 	struct blkcg_gq			*blkg;
-	char				*body;
 };
 
-struct block_device *blkcg_conf_open_bdev(char **inputp);
+void blkg_conf_init(struct blkg_conf_ctx *ctx, char *input);
+int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx);
 int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
-		   char *input, struct blkg_conf_ctx *ctx);
-void blkg_conf_finish(struct blkg_conf_ctx *ctx);
+		   struct blkg_conf_ctx *ctx);
+void blkg_conf_exit(struct blkg_conf_ctx *ctx);
 
 /**
  * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg

block/blk-core.c

@@ -263,13 +263,7 @@ static void blk_free_queue_rcu(struct rcu_head *rcu_head)
 
 static void blk_free_queue(struct request_queue *q)
 {
-	if (q->poll_stat)
-		blk_stat_remove_callback(q, q->poll_cb);
-	blk_stat_free_callback(q->poll_cb);
-
 	blk_free_queue_stats(q->stats);
-	kfree(q->poll_stat);
-
 	if (queue_is_mq(q))
 		blk_mq_release(q);
 
@@ -593,14 +587,14 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 
 static void __submit_bio(struct bio *bio)
 {
-	struct gendisk *disk = bio->bi_bdev->bd_disk;
-
 	if (unlikely(!blk_crypto_bio_prep(&bio)))
 		return;
 
-	if (!disk->fops->submit_bio) {
+	if (!bio->bi_bdev->bd_has_submit_bio) {
 		blk_mq_submit_bio(bio);
 	} else if (likely(bio_queue_enter(bio) == 0)) {
+		struct gendisk *disk = bio->bi_bdev->bd_disk;
+
 		disk->fops->submit_bio(bio);
 		blk_queue_exit(disk->queue);
 	}
@@ -704,7 +698,7 @@ void submit_bio_noacct_nocheck(struct bio *bio)
 	 */
 	if (current->bio_list)
 		bio_list_add(&current->bio_list[0], bio);
-	else if (!bio->bi_bdev->bd_disk->fops->submit_bio)
+	else if (!bio->bi_bdev->bd_has_submit_bio)
 		__submit_bio_noacct_mq(bio);
 	else
 		__submit_bio_noacct(bio);

block/blk-crypto-internal.h

@@ -65,6 +65,11 @@ static inline bool blk_crypto_rq_is_encrypted(struct request *rq)
 	return rq->crypt_ctx;
 }
 
+static inline bool blk_crypto_rq_has_keyslot(struct request *rq)
+{
+	return rq->crypt_keyslot;
+}
+
 blk_status_t blk_crypto_get_keyslot(struct blk_crypto_profile *profile,
 				    const struct blk_crypto_key *key,
 				    struct blk_crypto_keyslot **slot_ptr);
@@ -119,6 +124,11 @@ static inline bool blk_crypto_rq_is_encrypted(struct request *rq)
 	return false;
 }
 
+static inline bool blk_crypto_rq_has_keyslot(struct request *rq)
+{
+	return false;
+}
+
 #endif /* CONFIG_BLK_INLINE_ENCRYPTION */
 
 void __bio_crypt_advance(struct bio *bio, unsigned int bytes);
@@ -153,14 +163,21 @@ static inline bool blk_crypto_bio_prep(struct bio **bio_ptr)
 	return true;
 }
 
-blk_status_t __blk_crypto_init_request(struct request *rq);
-static inline blk_status_t blk_crypto_init_request(struct request *rq)
+blk_status_t __blk_crypto_rq_get_keyslot(struct request *rq);
+static inline blk_status_t blk_crypto_rq_get_keyslot(struct request *rq)
 {
 	if (blk_crypto_rq_is_encrypted(rq))
-		return __blk_crypto_init_request(rq);
+		return __blk_crypto_rq_get_keyslot(rq);
 	return BLK_STS_OK;
 }
 
+void __blk_crypto_rq_put_keyslot(struct request *rq);
+static inline void blk_crypto_rq_put_keyslot(struct request *rq)
+{
+	if (blk_crypto_rq_has_keyslot(rq))
+		__blk_crypto_rq_put_keyslot(rq);
+}
+
 void __blk_crypto_free_request(struct request *rq);
 static inline void blk_crypto_free_request(struct request *rq)
 {
@@ -188,21 +205,6 @@ static inline int blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio,
 	return 0;
 }
 
-/**
- * blk_crypto_insert_cloned_request - Prepare a cloned request to be inserted
- *				      into a request queue.
- * @rq: the request being queued
- *
- * Return: BLK_STS_OK on success, nonzero on error.
- */
-static inline blk_status_t blk_crypto_insert_cloned_request(struct request *rq)
-{
-
-	if (blk_crypto_rq_is_encrypted(rq))
-		return blk_crypto_init_request(rq);
-	return BLK_STS_OK;
-}
-
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK
 
 int blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num);

block/blk-crypto-profile.c

@@ -227,14 +227,13 @@ EXPORT_SYMBOL_GPL(blk_crypto_keyslot_index);
  * @profile: the crypto profile of the device the key will be used on
  * @key: the key that will be used
  * @slot_ptr: If a keyslot is allocated, an opaque pointer to the keyslot struct
- *	      will be stored here; otherwise NULL will be stored here.
+ *	      will be stored here.  blk_crypto_put_keyslot() must be called
+ *	      later to release it.  Otherwise, NULL will be stored here.
  *
  * If the device has keyslots, this gets a keyslot that's been programmed with
  * the specified key.  If the key is already in a slot, this reuses it;
  * otherwise this waits for a slot to become idle and programs the key into it.
  *
- * This must be paired with a call to blk_crypto_put_keyslot().
- *
  * Context: Process context. Takes and releases profile->lock.
  * Return: BLK_STS_OK on success, meaning that either a keyslot was allocated or
  *	   one wasn't needed; or a blk_status_t error on failure.
@@ -312,20 +311,15 @@ success:
 
 /**
  * blk_crypto_put_keyslot() - Release a reference to a keyslot
- * @slot: The keyslot to release the reference of (may be NULL).
+ * @slot: The keyslot to release the reference of
  *
  * Context: Any context.
  */
 void blk_crypto_put_keyslot(struct blk_crypto_keyslot *slot)
 {
-	struct blk_crypto_profile *profile;
+	struct blk_crypto_profile *profile = slot->profile;
 	unsigned long flags;
 
-	if (!slot)
-		return;
-
-	profile = slot->profile;
-
 	if (atomic_dec_and_lock_irqsave(&slot->slot_refs,
 					&profile->idle_slots_lock, flags)) {
 		list_add_tail(&slot->idle_slot_node, &profile->idle_slots);
@@ -354,28 +348,16 @@ bool __blk_crypto_cfg_supported(struct blk_crypto_profile *profile,
 	return true;
 }
 
-/**
- * __blk_crypto_evict_key() - Evict a key from a device.
- * @profile: the crypto profile of the device
- * @key: the key to evict.  It must not still be used in any I/O.
- *
- * If the device has keyslots, this finds the keyslot (if any) that contains the
- * specified key and calls the driver's keyslot_evict function to evict it.
- *
- * Otherwise, this just calls the driver's keyslot_evict function if it is
- * implemented, passing just the key (without any particular keyslot).  This
- * allows layered devices to evict the key from their underlying devices.
- *
- * Context: Process context. Takes and releases profile->lock.
- * Return: 0 on success or if there's no keyslot with the specified key, -EBUSY
- *	   if the keyslot is still in use, or another -errno value on other
- *	   error.
+/*
+ * This is an internal function that evicts a key from an inline encryption
+ * device that can be either a real device or the blk-crypto-fallback "device".
+ * It is used only by blk_crypto_evict_key(); see that function for details.
  */
 int __blk_crypto_evict_key(struct blk_crypto_profile *profile,
 			   const struct blk_crypto_key *key)
 {
 	struct blk_crypto_keyslot *slot;
-	int err = 0;
+	int err;
 
 	if (profile->num_slots == 0) {
 		if (profile->ll_ops.keyslot_evict) {
@@ -389,22 +371,30 @@ int __blk_crypto_evict_key(struct blk_crypto_profile *profile,
 
 	blk_crypto_hw_enter(profile);
 	slot = blk_crypto_find_keyslot(profile, key);
-	if (!slot)
-		goto out_unlock;
+	if (!slot) {
+		/*
+		 * Not an error, since a key not in use by I/O is not guaranteed
+		 * to be in a keyslot.  There can be more keys than keyslots.
+		 */
+		err = 0;
+		goto out;
+	}
 
 	if (WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)) {
+		/* BUG: key is still in use by I/O */
 		err = -EBUSY;
-		goto out_unlock;
+		goto out_remove;
 	}
 	err = profile->ll_ops.keyslot_evict(profile, key,
 					    blk_crypto_keyslot_index(slot));
-	if (err)
-		goto out_unlock;
-
+out_remove:
+	/*
+	 * Callers free the key even on error, so unlink the key from the hash
+	 * table and clear slot->key even on error.
+	 */
 	hlist_del(&slot->hash_node);
 	slot->key = NULL;
-	err = 0;
-out_unlock:
+out:
 	blk_crypto_hw_exit(profile);
 	return err;
 }

block/blk-crypto.c

@@ -13,6 +13,7 @@
 #include <linux/blkdev.h>
 #include <linux/blk-crypto-profile.h>
 #include <linux/module.h>
+#include <linux/ratelimit.h>
 #include <linux/slab.h>
 
 #include "blk-crypto-internal.h"
@@ -224,27 +225,27 @@ static bool bio_crypt_check_alignment(struct bio *bio)
 	return true;
 }
 
-blk_status_t __blk_crypto_init_request(struct request *rq)
+blk_status_t __blk_crypto_rq_get_keyslot(struct request *rq)
 {
 	return blk_crypto_get_keyslot(rq->q->crypto_profile,
 				      rq->crypt_ctx->bc_key,
 				      &rq->crypt_keyslot);
 }
 
-/**
- * __blk_crypto_free_request - Uninitialize the crypto fields of a request.
- *
- * @rq: The request whose crypto fields to uninitialize.
- *
- * Completely uninitializes the crypto fields of a request. If a keyslot has
- * been programmed into some inline encryption hardware, that keyslot is
- * released. The rq->crypt_ctx is also freed.
- */
-void __blk_crypto_free_request(struct request *rq)
+void __blk_crypto_rq_put_keyslot(struct request *rq)
 {
 	blk_crypto_put_keyslot(rq->crypt_keyslot);
+	rq->crypt_keyslot = NULL;
+}
+
+void __blk_crypto_free_request(struct request *rq)
+{
+	/* The keyslot, if one was needed, should have been released earlier. */
+	if (WARN_ON_ONCE(rq->crypt_keyslot))
+		__blk_crypto_rq_put_keyslot(rq);
+
 	mempool_free(rq->crypt_ctx, bio_crypt_ctx_pool);
-	blk_crypto_rq_set_defaults(rq);
+	rq->crypt_ctx = NULL;
 }
 
 /**
@@ -399,30 +400,39 @@ int blk_crypto_start_using_key(struct block_device *bdev,
 }
 
 /**
- * blk_crypto_evict_key() - Evict a key from any inline encryption hardware
- *			    it may have been programmed into
- * @bdev: The block_device who's associated inline encryption hardware this key
- *     might have been programmed into
- * @key: The key to evict
+ * blk_crypto_evict_key() - Evict a blk_crypto_key from a block_device
+ * @bdev: a block_device on which I/O using the key may have been done
+ * @key: the key to evict
  *
- * Upper layers (filesystems) must call this function to ensure that a key is
- * evicted from any hardware that it might have been programmed into.  The key
- * must not be in use by any in-flight IO when this function is called.
+ * For a given block_device, this function removes the given blk_crypto_key from
+ * the keyslot management structures and evicts it from any underlying hardware
+ * keyslot(s) or blk-crypto-fallback keyslot it may have been programmed into.
  *
- * Return: 0 on success or if the key wasn't in any keyslot; -errno on error.
+ * Upper layers must call this before freeing the blk_crypto_key.  It must be
+ * called for every block_device the key may have been used on.  The key must no
+ * longer be in use by any I/O when this function is called.
+ *
+ * Context: May sleep.
  */
-int blk_crypto_evict_key(struct block_device *bdev,
-			 const struct blk_crypto_key *key)
+void blk_crypto_evict_key(struct block_device *bdev,
+			  const struct blk_crypto_key *key)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
+	int err;
 
 	if (blk_crypto_config_supported_natively(bdev, &key->crypto_cfg))
-		return __blk_crypto_evict_key(q->crypto_profile, key);
-
+		err = __blk_crypto_evict_key(q->crypto_profile, key);
+	else
+		err = blk_crypto_fallback_evict_key(key);
 	/*
-	 * If the block_device didn't support the key, then blk-crypto-fallback
-	 * may have been used, so try to evict the key from blk-crypto-fallback.
+	 * An error can only occur here if the key failed to be evicted from a
+	 * keyslot (due to a hardware or driver issue) or is allegedly still in
+	 * use by I/O (due to a kernel bug).  Even in these cases, the key is
+	 * still unlinked from the keyslot management structures, and the caller
+	 * is allowed and expected to free it right away.  There's nothing
+	 * callers can do to handle errors, so just log them and return void.
 	 */
-	return blk_crypto_fallback_evict_key(key);
+	if (err)
+		pr_warn_ratelimited("%pg: error %d evicting key\n", bdev, err);
 }
 EXPORT_SYMBOL_GPL(blk_crypto_evict_key);

block/blk-flush.c

@@ -68,12 +68,10 @@
 #include <linux/bio.h>
 #include <linux/blkdev.h>
 #include <linux/gfp.h>
-#include <linux/blk-mq.h>
 #include <linux/part_stat.h>
 
 #include "blk.h"
 #include "blk-mq.h"
-#include "blk-mq-tag.h"
 #include "blk-mq-sched.h"
 
 /* PREFLUSH/FUA sequences */
@@ -138,11 +136,6 @@ static void blk_flush_restore_request(struct request *rq)
 	rq->end_io = rq->flush.saved_end_io;
 }
 
-static void blk_flush_queue_rq(struct request *rq, bool add_front)
-{
-	blk_mq_add_to_requeue_list(rq, add_front, true);
-}
-
 static void blk_account_io_flush(struct request *rq)
 {
 	struct block_device *part = rq->q->disk->part0;
@@ -195,7 +188,8 @@ static void blk_flush_complete_seq(struct request *rq,
 
 	case REQ_FSEQ_DATA:
 		list_move_tail(&rq->flush.list, &fq->flush_data_in_flight);
-		blk_flush_queue_rq(rq, true);
+		blk_mq_add_to_requeue_list(rq, BLK_MQ_INSERT_AT_HEAD);
+		blk_mq_kick_requeue_list(q);
 		break;
 
 	case REQ_FSEQ_DONE:
@@ -352,7 +346,8 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
 	smp_wmb();
 	req_ref_set(flush_rq, 1);
 
-	blk_flush_queue_rq(flush_rq, false);
+	blk_mq_add_to_requeue_list(flush_rq, 0);
+	blk_mq_kick_requeue_list(q);
 }
 
 static enum rq_end_io_ret mq_flush_data_end_io(struct request *rq,
@@ -396,6 +391,7 @@ void blk_insert_flush(struct request *rq)
 	unsigned long fflags = q->queue_flags;	/* may change, cache */
 	unsigned int policy = blk_flush_policy(fflags, rq);
 	struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx);
+	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
 	/*
 	 * @policy now records what operations need to be done.  Adjust
@@ -432,7 +428,8 @@ void blk_insert_flush(struct request *rq)
 	 */
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
-		blk_mq_request_bypass_insert(rq, false, true);
+		blk_mq_request_bypass_insert(rq, 0);
+		blk_mq_run_hw_queue(hctx, false);
 		return;
 	}
 

block/blk-iocost.c

@@ -3106,9 +3106,11 @@ static ssize_t ioc_weight_write(struct kernfs_open_file *of, char *buf,
 		return nbytes;
 	}
 
-	ret = blkg_conf_prep(blkcg, &blkcg_policy_iocost, buf, &ctx);
+	blkg_conf_init(&ctx, buf);
+
+	ret = blkg_conf_prep(blkcg, &blkcg_policy_iocost, &ctx);
 	if (ret)
-		return ret;
+		goto err;
 
 	iocg = blkg_to_iocg(ctx.blkg);
 
@@ -3127,12 +3129,14 @@ static ssize_t ioc_weight_write(struct kernfs_open_file *of, char *buf,
 	weight_updated(iocg, &now);
 	spin_unlock(&iocg->ioc->lock);
 
-	blkg_conf_finish(&ctx);
+	blkg_conf_exit(&ctx);
 	return nbytes;
 
 einval:
-	blkg_conf_finish(&ctx);
-	return -EINVAL;
+	ret = -EINVAL;
+err:
+	blkg_conf_exit(&ctx);
+	return ret;
 }
 
 static u64 ioc_qos_prfill(struct seq_file *sf, struct blkg_policy_data *pd,
@@ -3189,19 +3193,22 @@ static const match_table_t qos_tokens = {
 static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
 			     size_t nbytes, loff_t off)
 {
-	struct block_device *bdev;
+	struct blkg_conf_ctx ctx;
 	struct gendisk *disk;
 	struct ioc *ioc;
 	u32 qos[NR_QOS_PARAMS];
 	bool enable, user;
-	char *p;
+	char *body, *p;
 	int ret;
 
-	bdev = blkcg_conf_open_bdev(&input);
-	if (IS_ERR(bdev))
-		return PTR_ERR(bdev);
+	blkg_conf_init(&ctx, input);
 
-	disk = bdev->bd_disk;
+	ret = blkg_conf_open_bdev(&ctx);
+	if (ret)
+		goto err;
+
+	body = ctx.body;
+	disk = ctx.bdev->bd_disk;
 	if (!queue_is_mq(disk->queue)) {
 		ret = -EOPNOTSUPP;
 		goto err;
@@ -3223,7 +3230,7 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
 	enable = ioc->enabled;
 	user = ioc->user_qos_params;
 
-	while ((p = strsep(&input, " \t\n"))) {
+	while ((p = strsep(&body, " \t\n"))) {
 		substring_t args[MAX_OPT_ARGS];
 		char buf[32];
 		int tok;
@@ -3313,7 +3320,7 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
 	blk_mq_unquiesce_queue(disk->queue);
 	blk_mq_unfreeze_queue(disk->queue);
 
-	blkdev_put_no_open(bdev);
+	blkg_conf_exit(&ctx);
 	return nbytes;
 einval:
 	spin_unlock_irq(&ioc->lock);
@@ -3323,7 +3330,7 @@ einval:
 
 	ret = -EINVAL;
 err:
-	blkdev_put_no_open(bdev);
+	blkg_conf_exit(&ctx);
 	return ret;
 }
 
@@ -3376,19 +3383,22 @@ static const match_table_t i_lcoef_tokens = {
 static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 				    size_t nbytes, loff_t off)
 {
-	struct block_device *bdev;
+	struct blkg_conf_ctx ctx;
 	struct request_queue *q;
 	struct ioc *ioc;
 	u64 u[NR_I_LCOEFS];
 	bool user;
-	char *p;
+	char *body, *p;
 	int ret;
 
-	bdev = blkcg_conf_open_bdev(&input);
-	if (IS_ERR(bdev))
-		return PTR_ERR(bdev);
+	blkg_conf_init(&ctx, input);
 
-	q = bdev_get_queue(bdev);
+	ret = blkg_conf_open_bdev(&ctx);
+	if (ret)
+		goto err;
+
+	body = ctx.body;
+	q = bdev_get_queue(ctx.bdev);
 	if (!queue_is_mq(q)) {
 		ret = -EOPNOTSUPP;
 		goto err;
@@ -3396,7 +3406,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 
 	ioc = q_to_ioc(q);
 	if (!ioc) {
-		ret = blk_iocost_init(bdev->bd_disk);
+		ret = blk_iocost_init(ctx.bdev->bd_disk);
 		if (ret)
 			goto err;
 		ioc = q_to_ioc(q);
@@ -3409,7 +3419,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 	memcpy(u, ioc->params.i_lcoefs, sizeof(u));
 	user = ioc->user_cost_model;
 
-	while ((p = strsep(&input, " \t\n"))) {
+	while ((p = strsep(&body, " \t\n"))) {
 		substring_t args[MAX_OPT_ARGS];
 		char buf[32];
 		int tok;
@@ -3456,7 +3466,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 	blk_mq_unquiesce_queue(q);
 	blk_mq_unfreeze_queue(q);
 
-	blkdev_put_no_open(bdev);
+	blkg_conf_exit(&ctx);
 	return nbytes;
 
 einval:
@@ -3467,7 +3477,7 @@ einval:
 
 	ret = -EINVAL;
 err:
-	blkdev_put_no_open(bdev);
+	blkg_conf_exit(&ctx);
 	return ret;
 }
 

block/blk-iolatency.c

@@ -755,7 +755,7 @@ static void blkiolatency_enable_work_fn(struct work_struct *work)
 	}
 }
 
-int blk_iolatency_init(struct gendisk *disk)
+static int blk_iolatency_init(struct gendisk *disk)
 {
 	struct blk_iolatency *blkiolat;
 	int ret;
@@ -824,6 +824,29 @@ static void iolatency_clear_scaling(struct blkcg_gq *blkg)
 	}
 }
 
+static int blk_iolatency_try_init(struct blkg_conf_ctx *ctx)
+{
+	static DEFINE_MUTEX(init_mutex);
+	int ret;
+
+	ret = blkg_conf_open_bdev(ctx);
+	if (ret)
+		return ret;
+
+	/*
+	 * blk_iolatency_init() may fail after rq_qos_add() succeeds which can
+	 * confuse iolat_rq_qos() test. Make the test and init atomic.
+	 */
+	mutex_lock(&init_mutex);
+
+	if (!iolat_rq_qos(ctx->bdev->bd_queue))
+		ret = blk_iolatency_init(ctx->bdev->bd_disk);
+
+	mutex_unlock(&init_mutex);
+
+	return ret;
+}
+
 static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf,
 			     size_t nbytes, loff_t off)
 {
@@ -836,9 +859,15 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf,
 	u64 oldval;
 	int ret;
 
-	ret = blkg_conf_prep(blkcg, &blkcg_policy_iolatency, buf, &ctx);
+	blkg_conf_init(&ctx, buf);
+
+	ret = blk_iolatency_try_init(&ctx);
 	if (ret)
-		return ret;
+		goto out;
+
+	ret = blkg_conf_prep(blkcg, &blkcg_policy_iolatency, &ctx);
+	if (ret)
+		goto out;
 
 	iolat = blkg_to_lat(ctx.blkg);
 	p = ctx.body;
@@ -874,7 +903,7 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf,
 		iolatency_clear_scaling(blkg);
 	ret = 0;
 out:
-	blkg_conf_finish(&ctx);
+	blkg_conf_exit(&ctx);
 	return ret ?: nbytes;
 }
 
@@ -967,7 +996,7 @@ static void iolatency_pd_init(struct blkg_policy_data *pd)
 {
 	struct iolatency_grp *iolat = pd_to_lat(pd);
 	struct blkcg_gq *blkg = lat_to_blkg(iolat);
-	struct rq_qos *rqos = blkcg_rq_qos(blkg->q);
+	struct rq_qos *rqos = iolat_rq_qos(blkg->q);
 	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
 	u64 now = ktime_to_ns(ktime_get());
 	int cpu;

block/blk-merge.c

@@ -867,6 +867,8 @@ static struct request *attempt_merge(struct request_queue *q,
 	if (!blk_discard_mergable(req))
 		elv_merge_requests(q, req, next);
 
+	blk_crypto_rq_put_keyslot(next);
+
 	/*
 	 * 'next' is going away, so update stats accordingly
 	 */

block/blk-mq-cpumap.c

@@ -12,7 +12,6 @@
 #include <linux/cpu.h>
 #include <linux/group_cpus.h>
 
-#include <linux/blk-mq.h>
 #include "blk.h"
 #include "blk-mq.h"
 

block/blk-mq-debugfs.c

@@ -7,41 +7,14 @@
 #include <linux/blkdev.h>
 #include <linux/debugfs.h>
 
-#include <linux/blk-mq.h>
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-debugfs.h"
 #include "blk-mq-sched.h"
-#include "blk-mq-tag.h"
 #include "blk-rq-qos.h"
 
-static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
-{
-	if (stat->nr_samples) {
-		seq_printf(m, "samples=%d, mean=%llu, min=%llu, max=%llu",
-			   stat->nr_samples, stat->mean, stat->min, stat->max);
-	} else {
-		seq_puts(m, "samples=0");
-	}
-}
-
 static int queue_poll_stat_show(void *data, struct seq_file *m)
 {
-	struct request_queue *q = data;
-	int bucket;
-
-	if (!q->poll_stat)
-		return 0;
-
-	for (bucket = 0; bucket < (BLK_MQ_POLL_STATS_BKTS / 2); bucket++) {
-		seq_printf(m, "read  (%d Bytes): ", 1 << (9 + bucket));
-		print_stat(m, &q->poll_stat[2 * bucket]);
-		seq_puts(m, "\n");
-
-		seq_printf(m, "write (%d Bytes): ",  1 << (9 + bucket));
-		print_stat(m, &q->poll_stat[2 * bucket + 1]);
-		seq_puts(m, "\n");
-	}
 	return 0;
 }
 
@@ -282,7 +255,6 @@ static const char *const rqf_name[] = {
 	RQF_NAME(STATS),
 	RQF_NAME(SPECIAL_PAYLOAD),
 	RQF_NAME(ZONE_WRITE_LOCKED),
-	RQF_NAME(MQ_POLL_SLEPT),
 	RQF_NAME(TIMED_OUT),
 	RQF_NAME(ELV),
 	RQF_NAME(RESV),

block/blk-mq-pci.c

@@ -4,7 +4,6 @@
  */
 #include <linux/kobject.h>
 #include <linux/blkdev.h>
-#include <linux/blk-mq.h>
 #include <linux/blk-mq-pci.h>
 #include <linux/pci.h>
 #include <linux/module.h>

block/blk-mq-rdma.c

@@ -1,44 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (c) 2017 Sagi Grimberg.
- */
-#include <linux/blk-mq.h>
-#include <linux/blk-mq-rdma.h>
-#include <rdma/ib_verbs.h>
-
-/**
- * blk_mq_rdma_map_queues - provide a default queue mapping for rdma device
- * @map:	CPU to hardware queue map.
- * @dev:	rdma device to provide a mapping for.
- * @first_vec:	first interrupt vectors to use for queues (usually 0)
- *
- * This function assumes the rdma device @dev has at least as many available
- * interrupt vetors as @set has queues.  It will then query it's affinity mask
- * and built queue mapping that maps a queue to the CPUs that have irq affinity
- * for the corresponding vector.
- *
- * In case either the driver passed a @dev with less vectors than
- * @set->nr_hw_queues, or @dev does not provide an affinity mask for a
- * vector, we fallback to the naive mapping.
- */
-void blk_mq_rdma_map_queues(struct blk_mq_queue_map *map,
-		struct ib_device *dev, int first_vec)
-{
-	const struct cpumask *mask;
-	unsigned int queue, cpu;
-
-	for (queue = 0; queue < map->nr_queues; queue++) {
-		mask = ib_get_vector_affinity(dev, first_vec + queue);
-		if (!mask)
-			goto fallback;
-
-		for_each_cpu(cpu, mask)
-			map->mq_map[cpu] = map->queue_offset + queue;
-	}
-
-	return;
-
-fallback:
-	blk_mq_map_queues(map);
-}
-EXPORT_SYMBOL_GPL(blk_mq_rdma_map_queues);

block/blk-mq-sched.c

@@ -6,7 +6,6 @@
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/blk-mq.h>
 #include <linux/list_sort.h>
 
 #include <trace/events/block.h>
@@ -15,7 +14,6 @@
 #include "blk-mq.h"
 #include "blk-mq-debugfs.h"
 #include "blk-mq-sched.h"
-#include "blk-mq-tag.h"
 #include "blk-wbt.h"
 
 /*
@@ -271,9 +269,7 @@ static int blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)
 
 static int __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 {
-	struct request_queue *q = hctx->queue;
-	const bool has_sched = q->elevator;
-	int ret = 0;
+	bool need_dispatch = false;
 	LIST_HEAD(rq_list);
 
 	/*
@@ -302,23 +298,22 @@ static int __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	 */
 	if (!list_empty(&rq_list)) {
 		blk_mq_sched_mark_restart_hctx(hctx);
-		if (blk_mq_dispatch_rq_list(hctx, &rq_list, 0)) {
-			if (has_sched)
-				ret = blk_mq_do_dispatch_sched(hctx);
-			else
-				ret = blk_mq_do_dispatch_ctx(hctx);
-		}
-	} else if (has_sched) {
-		ret = blk_mq_do_dispatch_sched(hctx);
-	} else if (hctx->dispatch_busy) {
-		/* dequeue request one by one from sw queue if queue is busy */
-		ret = blk_mq_do_dispatch_ctx(hctx);
+		if (!blk_mq_dispatch_rq_list(hctx, &rq_list, 0))
+			return 0;
+		need_dispatch = true;
 	} else {
-		blk_mq_flush_busy_ctxs(hctx, &rq_list);
-		blk_mq_dispatch_rq_list(hctx, &rq_list, 0);
+		need_dispatch = hctx->dispatch_busy;
 	}
 
-	return ret;
+	if (hctx->queue->elevator)
+		return blk_mq_do_dispatch_sched(hctx);
+
+	/* dequeue request one by one from sw queue if queue is busy */
+	if (need_dispatch)
+		return blk_mq_do_dispatch_ctx(hctx);
+	blk_mq_flush_busy_ctxs(hctx, &rq_list);
+	blk_mq_dispatch_rq_list(hctx, &rq_list, 0);
+	return 0;
 }
 
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
@@ -384,116 +379,6 @@ bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq,
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_try_insert_merge);
 
-static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx,
-				       struct request *rq)
-{
-	/*
-	 * dispatch flush and passthrough rq directly
-	 *
-	 * passthrough request has to be added to hctx->dispatch directly.
-	 * For some reason, device may be in one situation which can't
-	 * handle FS request, so STS_RESOURCE is always returned and the
-	 * FS request will be added to hctx->dispatch. However passthrough
-	 * request may be required at that time for fixing the problem. If
-	 * passthrough request is added to scheduler queue, there isn't any
-	 * chance to dispatch it given we prioritize requests in hctx->dispatch.
-	 */
-	if ((rq->rq_flags & RQF_FLUSH_SEQ) || blk_rq_is_passthrough(rq))
-		return true;
-
-	return false;
-}
-
-void blk_mq_sched_insert_request(struct request *rq, bool at_head,
-				 bool run_queue, bool async)
-{
-	struct request_queue *q = rq->q;
-	struct elevator_queue *e = q->elevator;
-	struct blk_mq_ctx *ctx = rq->mq_ctx;
-	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
-
-	WARN_ON(e && (rq->tag != BLK_MQ_NO_TAG));
-
-	if (blk_mq_sched_bypass_insert(hctx, rq)) {
-		/*
-		 * Firstly normal IO request is inserted to scheduler queue or
-		 * sw queue, meantime we add flush request to dispatch queue(
-		 * hctx->dispatch) directly and there is at most one in-flight
-		 * flush request for each hw queue, so it doesn't matter to add
-		 * flush request to tail or front of the dispatch queue.
-		 *
-		 * Secondly in case of NCQ, flush request belongs to non-NCQ
-		 * command, and queueing it will fail when there is any
-		 * in-flight normal IO request(NCQ command). When adding flush
-		 * rq to the front of hctx->dispatch, it is easier to introduce
-		 * extra time to flush rq's latency because of S_SCHED_RESTART
-		 * compared with adding to the tail of dispatch queue, then
-		 * chance of flush merge is increased, and less flush requests
-		 * will be issued to controller. It is observed that ~10% time
-		 * is saved in blktests block/004 on disk attached to AHCI/NCQ
-		 * drive when adding flush rq to the front of hctx->dispatch.
-		 *
-		 * Simply queue flush rq to the front of hctx->dispatch so that
-		 * intensive flush workloads can benefit in case of NCQ HW.
-		 */
-		at_head = (rq->rq_flags & RQF_FLUSH_SEQ) ? true : at_head;
-		blk_mq_request_bypass_insert(rq, at_head, false);
-		goto run;
-	}
-
-	if (e) {
-		LIST_HEAD(list);
-
-		list_add(&rq->queuelist, &list);
-		e->type->ops.insert_requests(hctx, &list, at_head);
-	} else {
-		spin_lock(&ctx->lock);
-		__blk_mq_insert_request(hctx, rq, at_head);
-		spin_unlock(&ctx->lock);
-	}
-
-run:
-	if (run_queue)
-		blk_mq_run_hw_queue(hctx, async);
-}
-
-void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx,
-				  struct blk_mq_ctx *ctx,
-				  struct list_head *list, bool run_queue_async)
-{
-	struct elevator_queue *e;
-	struct request_queue *q = hctx->queue;
-
-	/*
-	 * blk_mq_sched_insert_requests() is called from flush plug
-	 * context only, and hold one usage counter to prevent queue
-	 * from being released.
-	 */
-	percpu_ref_get(&q->q_usage_counter);
-
-	e = hctx->queue->elevator;
-	if (e) {
-		e->type->ops.insert_requests(hctx, list, false);
-	} else {
-		/*
-		 * try to issue requests directly if the hw queue isn't
-		 * busy in case of 'none' scheduler, and this way may save
-		 * us one extra enqueue & dequeue to sw queue.
-		 */
-		if (!hctx->dispatch_busy && !run_queue_async) {
-			blk_mq_run_dispatch_ops(hctx->queue,
-				blk_mq_try_issue_list_directly(hctx, list));
-			if (list_empty(list))
-				goto out;
-		}
-		blk_mq_insert_requests(hctx, ctx, list);
-	}
-
-	blk_mq_run_hw_queue(hctx, run_queue_async);
- out:
-	percpu_ref_put(&q->q_usage_counter);
-}
-
 static int blk_mq_sched_alloc_map_and_rqs(struct request_queue *q,
 					  struct blk_mq_hw_ctx *hctx,
 					  unsigned int hctx_idx)

block/blk-mq-sched.h

@@ -4,7 +4,6 @@
 
 #include "elevator.h"
 #include "blk-mq.h"
-#include "blk-mq-tag.h"
 
 #define MAX_SCHED_RQ (16 * BLKDEV_DEFAULT_RQ)
 
@@ -17,12 +16,6 @@ bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq,
 void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx);
 void __blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx);
 
-void blk_mq_sched_insert_request(struct request *rq, bool at_head,
-				 bool run_queue, bool async);
-void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx,
-				  struct blk_mq_ctx *ctx,
-				  struct list_head *list, bool run_queue_async);
-
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
 
 int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e);

block/blk-mq-sysfs.c

@@ -10,10 +10,8 @@
 #include <linux/workqueue.h>
 #include <linux/smp.h>
 
-#include <linux/blk-mq.h>
 #include "blk.h"
 #include "blk-mq.h"
-#include "blk-mq-tag.h"
 
 static void blk_mq_sysfs_release(struct kobject *kobj)
 {

block/blk-mq-tag.c

@@ -9,12 +9,10 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 
-#include <linux/blk-mq.h>
 #include <linux/delay.h>
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-sched.h"
-#include "blk-mq-tag.h"
 
 /*
  * Recalculate wakeup batch when tag is shared by hctx.

block/blk-mq-tag.h

@@ -1,73 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef INT_BLK_MQ_TAG_H
-#define INT_BLK_MQ_TAG_H
-
-struct blk_mq_alloc_data;
-
-extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags,
-					unsigned int reserved_tags,
-					int node, int alloc_policy);
-extern void blk_mq_free_tags(struct blk_mq_tags *tags);
-extern int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags,
-			       struct sbitmap_queue *breserved_tags,
-			       unsigned int queue_depth,
-			       unsigned int reserved,
-			       int node, int alloc_policy);
-
-extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
-unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags,
-			      unsigned int *offset);
-extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
-			   unsigned int tag);
-void blk_mq_put_tags(struct blk_mq_tags *tags, int *tag_array, int nr_tags);
-extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
-					struct blk_mq_tags **tags,
-					unsigned int depth, bool can_grow);
-extern void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set,
-					     unsigned int size);
-extern void blk_mq_tag_update_sched_shared_tags(struct request_queue *q);
-
-extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
-void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn,
-		void *priv);
-void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
-		void *priv);
-
-static inline struct sbq_wait_state *bt_wait_ptr(struct sbitmap_queue *bt,
-						 struct blk_mq_hw_ctx *hctx)
-{
-	if (!hctx)
-		return &bt->ws[0];
-	return sbq_wait_ptr(bt, &hctx->wait_index);
-}
-
-enum {
-	BLK_MQ_NO_TAG		= -1U,
-	BLK_MQ_TAG_MIN		= 1,
-	BLK_MQ_TAG_MAX		= BLK_MQ_NO_TAG - 1,
-};
-
-extern void __blk_mq_tag_busy(struct blk_mq_hw_ctx *);
-extern void __blk_mq_tag_idle(struct blk_mq_hw_ctx *);
-
-static inline void blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
-{
-	if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
-		__blk_mq_tag_busy(hctx);
-}
-
-static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
-{
-	if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
-		return;
-
-	__blk_mq_tag_idle(hctx);
-}
-
-static inline bool blk_mq_tag_is_reserved(struct blk_mq_tags *tags,
-					  unsigned int tag)
-{
-	return tag < tags->nr_reserved_tags;
-}
-
-#endif

block/blk-mq-virtio.c

@@ -3,7 +3,6 @@
  * Copyright (c) 2016 Christoph Hellwig.
  */
 #include <linux/device.h>
-#include <linux/blk-mq.h>
 #include <linux/blk-mq-virtio.h>
 #include <linux/virtio_config.h>
 #include <linux/module.h>

block/blk-mq.c

@@ -32,12 +32,10 @@
 
 #include <trace/events/block.h>
 
-#include <linux/blk-mq.h>
 #include <linux/t10-pi.h>
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-debugfs.h"
-#include "blk-mq-tag.h"
 #include "blk-pm.h"
 #include "blk-stat.h"
 #include "blk-mq-sched.h"
@@ -46,51 +44,19 @@
 
 static DEFINE_PER_CPU(struct llist_head, blk_cpu_done);
 
-static void blk_mq_poll_stats_start(struct request_queue *q);
-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, sectors, bucket;
-
-	ddir = rq_data_dir(rq);
-	sectors = blk_rq_stats_sectors(rq);
-
-	bucket = ddir + 2 * ilog2(sectors);
-
-	if (bucket < 0)
-		return -1;
-	else if (bucket >= BLK_MQ_POLL_STATS_BKTS)
-		return ddir + BLK_MQ_POLL_STATS_BKTS - 2;
-
-	return bucket;
-}
-
-#define BLK_QC_T_SHIFT		16
-#define BLK_QC_T_INTERNAL	(1U << 31)
+static void blk_mq_insert_request(struct request *rq, blk_insert_t flags);
+static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
+		struct list_head *list);
 
 static inline struct blk_mq_hw_ctx *blk_qc_to_hctx(struct request_queue *q,
 		blk_qc_t qc)
 {
-	return xa_load(&q->hctx_table,
-			(qc & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT);
-}
-
-static inline struct request *blk_qc_to_rq(struct blk_mq_hw_ctx *hctx,
-		blk_qc_t qc)
-{
-	unsigned int tag = qc & ((1U << BLK_QC_T_SHIFT) - 1);
-
-	if (qc & BLK_QC_T_INTERNAL)
-		return blk_mq_tag_to_rq(hctx->sched_tags, tag);
-	return blk_mq_tag_to_rq(hctx->tags, tag);
+	return xa_load(&q->hctx_table, qc);
 }
 
 static inline blk_qc_t blk_rq_to_qc(struct request *rq)
 {
-	return (rq->mq_hctx->queue_num << BLK_QC_T_SHIFT) |
-		(rq->tag != -1 ?
-		 rq->tag : (rq->internal_tag | BLK_QC_T_INTERNAL));
+	return rq->mq_hctx->queue_num;
 }
 
 /*
@@ -840,6 +806,12 @@ static void blk_complete_request(struct request *req)
 		req->q->integrity.profile->complete_fn(req, total_bytes);
 #endif
 
+	/*
+	 * Upper layers may call blk_crypto_evict_key() anytime after the last
+	 * bio_endio().  Therefore, the keyslot must be released before that.
+	 */
+	blk_crypto_rq_put_keyslot(req);
+
 	blk_account_io_completion(req, total_bytes);
 
 	do {
@@ -905,6 +877,13 @@ bool blk_update_request(struct request *req, blk_status_t error,
 		req->q->integrity.profile->complete_fn(req, nr_bytes);
 #endif
 
+	/*
+	 * Upper layers may call blk_crypto_evict_key() anytime after the last
+	 * bio_endio().  Therefore, the keyslot must be released before that.
+	 */
+	if (blk_crypto_rq_has_keyslot(req) && nr_bytes >= blk_rq_bytes(req))
+		__blk_crypto_rq_put_keyslot(req);
+
 	if (unlikely(error && !blk_rq_is_passthrough(req) &&
 		     !(req->rq_flags & RQF_QUIET)) &&
 		     !test_bit(GD_DEAD, &req->q->disk->state)) {
@@ -976,17 +955,6 @@ bool blk_update_request(struct request *req, blk_status_t error,
 }
 EXPORT_SYMBOL_GPL(blk_update_request);
 
-static void __blk_account_io_done(struct request *req, u64 now)
-{
-	const int sgrp = op_stat_group(req_op(req));
-
-	part_stat_lock();
-	update_io_ticks(req->part, jiffies, true);
-	part_stat_inc(req->part, ios[sgrp]);
-	part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
-	part_stat_unlock();
-}
-
 static inline void blk_account_io_done(struct request *req, u64 now)
 {
 	/*
@@ -995,40 +963,41 @@ static inline void blk_account_io_done(struct request *req, u64 now)
 	 * containing request is enough.
 	 */
 	if (blk_do_io_stat(req) && req->part &&
-	    !(req->rq_flags & RQF_FLUSH_SEQ))
-		__blk_account_io_done(req, now);
-}
+	    !(req->rq_flags & RQF_FLUSH_SEQ)) {
+		const int sgrp = op_stat_group(req_op(req));
 
-static void __blk_account_io_start(struct request *rq)
-{
-	/*
-	 * All non-passthrough requests are created from a bio with one
-	 * exception: when a flush command that is part of a flush sequence
-	 * generated by the state machine in blk-flush.c is cloned onto the
-	 * lower device by dm-multipath we can get here without a bio.
-	 */
-	if (rq->bio)
-		rq->part = rq->bio->bi_bdev;
-	else
-		rq->part = rq->q->disk->part0;
-
-	part_stat_lock();
-	update_io_ticks(rq->part, jiffies, false);
-	part_stat_unlock();
+		part_stat_lock();
+		update_io_ticks(req->part, jiffies, true);
+		part_stat_inc(req->part, ios[sgrp]);
+		part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
+		part_stat_unlock();
+	}
 }
 
 static inline void blk_account_io_start(struct request *req)
 {
-	if (blk_do_io_stat(req))
-		__blk_account_io_start(req);
+	if (blk_do_io_stat(req)) {
+		/*
+		 * All non-passthrough requests are created from a bio with one
+		 * exception: when a flush command that is part of a flush sequence
+		 * generated by the state machine in blk-flush.c is cloned onto the
+		 * lower device by dm-multipath we can get here without a bio.
+		 */
+		if (req->bio)
+			req->part = req->bio->bi_bdev;
+		else
+			req->part = req->q->disk->part0;
+
+		part_stat_lock();
+		update_io_ticks(req->part, jiffies, false);
+		part_stat_unlock();
+	}
 }
 
 static inline void __blk_mq_end_request_acct(struct request *rq, u64 now)
 {
-	if (rq->rq_flags & RQF_STATS) {
-		blk_mq_poll_stats_start(rq->q);
+	if (rq->rq_flags & RQF_STATS)
 		blk_stat_add(rq, now);
-	}
 
 	blk_mq_sched_completed_request(rq, now);
 	blk_account_io_done(rq, now);
@@ -1322,6 +1291,8 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
  */
 void blk_execute_rq_nowait(struct request *rq, bool at_head)
 {
+	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
 	WARN_ON(irqs_disabled());
 	WARN_ON(!blk_rq_is_passthrough(rq));
 
@@ -1332,10 +1303,13 @@ void blk_execute_rq_nowait(struct request *rq, bool at_head)
 	 * device, directly accessing the plug instead of using blk_mq_plug()
 	 * should not have any consequences.
 	 */
-	if (current->plug)
+	if (current->plug && !at_head) {
 		blk_add_rq_to_plug(current->plug, rq);
-	else
-		blk_mq_sched_insert_request(rq, at_head, true, false);
+		return;
+	}
+
+	blk_mq_insert_request(rq, at_head ? BLK_MQ_INSERT_AT_HEAD : 0);
+	blk_mq_run_hw_queue(hctx, false);
 }
 EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
 
@@ -1383,6 +1357,7 @@ static void blk_rq_poll_completion(struct request *rq, struct completion *wait)
  */
 blk_status_t blk_execute_rq(struct request *rq, bool at_head)
 {
+	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 	struct blk_rq_wait wait = {
 		.done = COMPLETION_INITIALIZER_ONSTACK(wait.done),
 	};
@@ -1394,7 +1369,8 @@ blk_status_t blk_execute_rq(struct request *rq, bool at_head)
 	rq->end_io = blk_end_sync_rq;
 
 	blk_account_io_start(rq);
-	blk_mq_sched_insert_request(rq, at_head, true, false);
+	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)) {
 		blk_rq_poll_completion(rq, &wait.done);
@@ -1434,12 +1410,17 @@ static void __blk_mq_requeue_request(struct request *rq)
 
 void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list)
 {
+	struct request_queue *q = rq->q;
+
 	__blk_mq_requeue_request(rq);
 
 	/* this request will be re-inserted to io scheduler queue */
 	blk_mq_sched_requeue_request(rq);
 
-	blk_mq_add_to_requeue_list(rq, true, kick_requeue_list);
+	blk_mq_add_to_requeue_list(rq, BLK_MQ_INSERT_AT_HEAD);
+
+	if (kick_requeue_list)
+		blk_mq_kick_requeue_list(q);
 }
 EXPORT_SYMBOL(blk_mq_requeue_request);
 
@@ -1455,33 +1436,33 @@ static void blk_mq_requeue_work(struct work_struct *work)
 	spin_unlock_irq(&q->requeue_lock);
 
 	list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
-		if (!(rq->rq_flags & (RQF_SOFTBARRIER | RQF_DONTPREP)))
-			continue;
-
-		rq->rq_flags &= ~RQF_SOFTBARRIER;
-		list_del_init(&rq->queuelist);
 		/*
-		 * If RQF_DONTPREP, rq has contained some driver specific
-		 * data, so insert it to hctx dispatch list to avoid any
-		 * merge.
+		 * If RQF_DONTPREP ist set, the request has been started by the
+		 * driver already and might have driver-specific data allocated
+		 * already.  Insert it into the hctx dispatch list to avoid
+		 * block layer merges for the request.
 		 */
-		if (rq->rq_flags & RQF_DONTPREP)
-			blk_mq_request_bypass_insert(rq, false, false);
-		else
-			blk_mq_sched_insert_request(rq, true, false, false);
+		if (rq->rq_flags & RQF_DONTPREP) {
+			rq->rq_flags &= ~RQF_SOFTBARRIER;
+			list_del_init(&rq->queuelist);
+			blk_mq_request_bypass_insert(rq, 0);
+		} else if (rq->rq_flags & RQF_SOFTBARRIER) {
+			rq->rq_flags &= ~RQF_SOFTBARRIER;
+			list_del_init(&rq->queuelist);
+			blk_mq_insert_request(rq, BLK_MQ_INSERT_AT_HEAD);
+		}
 	}
 
 	while (!list_empty(&rq_list)) {
 		rq = list_entry(rq_list.next, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		blk_mq_sched_insert_request(rq, false, false, false);
+		blk_mq_insert_request(rq, 0);
 	}
 
 	blk_mq_run_hw_queues(q, false);
 }
 
-void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
-				bool kick_requeue_list)
+void blk_mq_add_to_requeue_list(struct request *rq, blk_insert_t insert_flags)
 {
 	struct request_queue *q = rq->q;
 	unsigned long flags;
@@ -1493,16 +1474,13 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
 	BUG_ON(rq->rq_flags & RQF_SOFTBARRIER);
 
 	spin_lock_irqsave(&q->requeue_lock, flags);
-	if (at_head) {
+	if (insert_flags & BLK_MQ_INSERT_AT_HEAD) {
 		rq->rq_flags |= RQF_SOFTBARRIER;
 		list_add(&rq->queuelist, &q->requeue_list);
 	} else {
 		list_add_tail(&rq->queuelist, &q->requeue_list);
 	}
 	spin_unlock_irqrestore(&q->requeue_lock, flags);
-
-	if (kick_requeue_list)
-		blk_mq_kick_requeue_list(q);
 }
 
 void blk_mq_kick_requeue_list(struct request_queue *q)
@@ -2158,24 +2136,6 @@ out:
 	return true;
 }
 
-/**
- * __blk_mq_run_hw_queue - Run a hardware queue.
- * @hctx: Pointer to the hardware queue to run.
- *
- * Send pending requests to the hardware.
- */
-static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
-{
-	/*
-	 * We can't run the queue inline with ints disabled. Ensure that
-	 * we catch bad users of this early.
-	 */
-	WARN_ON_ONCE(in_interrupt());
-
-	blk_mq_run_dispatch_ops(hctx->queue,
-			blk_mq_sched_dispatch_requests(hctx));
-}
-
 static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
 {
 	int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask);
@@ -2231,32 +2191,6 @@ select_cpu:
 	return next_cpu;
 }
 
-/**
- * __blk_mq_delay_run_hw_queue - Run (or schedule to run) a hardware queue.
- * @hctx: Pointer to the hardware queue to run.
- * @async: If we want to run the queue asynchronously.
- * @msecs: Milliseconds of delay to wait before running the queue.
- *
- * If !@async, try to run the queue now. Else, run the queue asynchronously and
- * with a delay of @msecs.
- */
-static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
-					unsigned long msecs)
-{
-	if (unlikely(blk_mq_hctx_stopped(hctx)))
-		return;
-
-	if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
-		if (cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) {
-			__blk_mq_run_hw_queue(hctx);
-			return;
-		}
-	}
-
-	kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work,
-				    msecs_to_jiffies(msecs));
-}
-
 /**
  * blk_mq_delay_run_hw_queue - Run a hardware queue asynchronously.
  * @hctx: Pointer to the hardware queue to run.
@@ -2266,7 +2200,10 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
  */
 void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 {
-	__blk_mq_delay_run_hw_queue(hctx, true, msecs);
+	if (unlikely(blk_mq_hctx_stopped(hctx)))
+		return;
+	kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work,
+				    msecs_to_jiffies(msecs));
 }
 EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
 
@@ -2283,6 +2220,11 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 {
 	bool need_run;
 
+	/*
+	 * We can't run the queue inline with interrupts disabled.
+	 */
+	WARN_ON_ONCE(!async && in_interrupt());
+
 	/*
 	 * When queue is quiesced, we may be switching io scheduler, or
 	 * updating nr_hw_queues, or other things, and we can't run queue
@@ -2295,8 +2237,17 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 		need_run = !blk_queue_quiesced(hctx->queue) &&
 		blk_mq_hctx_has_pending(hctx));
 
-	if (need_run)
-		__blk_mq_delay_run_hw_queue(hctx, async, 0);
+	if (!need_run)
+		return;
+
+	if (async || (hctx->flags & BLK_MQ_F_BLOCKING) ||
+	    !cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) {
+		blk_mq_delay_run_hw_queue(hctx, 0);
+		return;
+	}
+
+	blk_mq_run_dispatch_ops(hctx->queue,
+				blk_mq_sched_dispatch_requests(hctx));
 }
 EXPORT_SYMBOL(blk_mq_run_hw_queue);
 
@@ -2461,79 +2412,51 @@ EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues);
 
 static void blk_mq_run_work_fn(struct work_struct *work)
 {
-	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_hw_ctx *hctx =
+		container_of(work, struct blk_mq_hw_ctx, run_work.work);
 
-	hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work);
-
-	/*
-	 * If we are stopped, don't run the queue.
-	 */
-	if (blk_mq_hctx_stopped(hctx))
-		return;
-
-	__blk_mq_run_hw_queue(hctx);
-}
-
-static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
-					    struct request *rq,
-					    bool at_head)
-{
-	struct blk_mq_ctx *ctx = rq->mq_ctx;
-	enum hctx_type type = hctx->type;
-
-	lockdep_assert_held(&ctx->lock);
-
-	trace_block_rq_insert(rq);
-
-	if (at_head)
-		list_add(&rq->queuelist, &ctx->rq_lists[type]);
-	else
-		list_add_tail(&rq->queuelist, &ctx->rq_lists[type]);
-}
-
-void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
-			     bool at_head)
-{
-	struct blk_mq_ctx *ctx = rq->mq_ctx;
-
-	lockdep_assert_held(&ctx->lock);
-
-	__blk_mq_insert_req_list(hctx, rq, at_head);
-	blk_mq_hctx_mark_pending(hctx, ctx);
+	blk_mq_run_dispatch_ops(hctx->queue,
+				blk_mq_sched_dispatch_requests(hctx));
 }
 
 /**
  * blk_mq_request_bypass_insert - Insert a request at dispatch list.
  * @rq: Pointer to request to be inserted.
- * @at_head: true if the request should be inserted at the head of the list.
- * @run_queue: If we should run the hardware queue after inserting the request.
+ * @flags: BLK_MQ_INSERT_*
  *
  * Should only be used carefully, when the caller knows we want to
  * bypass a potential IO scheduler on the target device.
  */
-void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
-				  bool run_queue)
+void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags)
 {
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
 	spin_lock(&hctx->lock);
-	if (at_head)
+	if (flags & BLK_MQ_INSERT_AT_HEAD)
 		list_add(&rq->queuelist, &hctx->dispatch);
 	else
 		list_add_tail(&rq->queuelist, &hctx->dispatch);
 	spin_unlock(&hctx->lock);
-
-	if (run_queue)
-		blk_mq_run_hw_queue(hctx, false);
 }
 
-void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
-			    struct list_head *list)
-
+static void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx,
+		struct blk_mq_ctx *ctx, struct list_head *list,
+		bool run_queue_async)
 {
 	struct request *rq;
 	enum hctx_type type = hctx->type;
 
+	/*
+	 * Try to issue requests directly if the hw queue isn't busy to save an
+	 * extra enqueue & dequeue to the sw queue.
+	 */
+	if (!hctx->dispatch_busy && !run_queue_async) {
+		blk_mq_run_dispatch_ops(hctx->queue,
+			blk_mq_try_issue_list_directly(hctx, list));
+		if (list_empty(list))
+			goto out;
+	}
+
 	/*
 	 * preemption doesn't flush plug list, so it's possible ctx->cpu is
 	 * offline now
@@ -2547,6 +2470,70 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 	list_splice_tail_init(list, &ctx->rq_lists[type]);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 	spin_unlock(&ctx->lock);
+out:
+	blk_mq_run_hw_queue(hctx, run_queue_async);
+}
+
+static void blk_mq_insert_request(struct request *rq, blk_insert_t flags)
+{
+	struct request_queue *q = rq->q;
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
+	if (blk_rq_is_passthrough(rq)) {
+		/*
+		 * Passthrough request have to be added to hctx->dispatch
+		 * directly.  The device may be in a situation where it can't
+		 * handle FS request, and always returns BLK_STS_RESOURCE for
+		 * them, which gets them added to hctx->dispatch.
+		 *
+		 * If a passthrough request is required to unblock the queues,
+		 * and it is added to the scheduler queue, there is no chance to
+		 * dispatch it given we prioritize requests in hctx->dispatch.
+		 */
+		blk_mq_request_bypass_insert(rq, flags);
+	} else if (rq->rq_flags & RQF_FLUSH_SEQ) {
+		/*
+		 * Firstly normal IO request is inserted to scheduler queue or
+		 * sw queue, meantime we add flush request to dispatch queue(
+		 * hctx->dispatch) directly and there is at most one in-flight
+		 * flush request for each hw queue, so it doesn't matter to add
+		 * flush request to tail or front of the dispatch queue.
+		 *
+		 * Secondly in case of NCQ, flush request belongs to non-NCQ
+		 * command, and queueing it will fail when there is any
+		 * in-flight normal IO request(NCQ command). When adding flush
+		 * rq to the front of hctx->dispatch, it is easier to introduce
+		 * extra time to flush rq's latency because of S_SCHED_RESTART
+		 * compared with adding to the tail of dispatch queue, then
+		 * chance of flush merge is increased, and less flush requests
+		 * will be issued to controller. It is observed that ~10% time
+		 * is saved in blktests block/004 on disk attached to AHCI/NCQ
+		 * drive when adding flush rq to the front of hctx->dispatch.
+		 *
+		 * Simply queue flush rq to the front of hctx->dispatch so that
+		 * intensive flush workloads can benefit in case of NCQ HW.
+		 */
+		blk_mq_request_bypass_insert(rq, BLK_MQ_INSERT_AT_HEAD);
+	} else if (q->elevator) {
+		LIST_HEAD(list);
+
+		WARN_ON_ONCE(rq->tag != BLK_MQ_NO_TAG);
+
+		list_add(&rq->queuelist, &list);
+		q->elevator->type->ops.insert_requests(hctx, &list, flags);
+	} else {
+		trace_block_rq_insert(rq);
+
+		spin_lock(&ctx->lock);
+		if (flags & BLK_MQ_INSERT_AT_HEAD)
+			list_add(&rq->queuelist, &ctx->rq_lists[hctx->type]);
+		else
+			list_add_tail(&rq->queuelist,
+				      &ctx->rq_lists[hctx->type]);
+		blk_mq_hctx_mark_pending(hctx, ctx);
+		spin_unlock(&ctx->lock);
+	}
 }
 
 static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
@@ -2600,49 +2587,19 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
 	return ret;
 }
 
-static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
-						struct request *rq,
-						bool bypass_insert, bool last)
+static bool blk_mq_get_budget_and_tag(struct request *rq)
 {
-	struct request_queue *q = rq->q;
-	bool run_queue = true;
 	int budget_token;
 
-	/*
-	 * RCU or SRCU read lock is needed before checking quiesced flag.
-	 *
-	 * When queue is stopped or quiesced, ignore 'bypass_insert' from
-	 * blk_mq_request_issue_directly(), and return BLK_STS_OK to caller,
-	 * and avoid driver to try to dispatch again.
-	 */
-	if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)) {
-		run_queue = false;
-		bypass_insert = false;
-		goto insert;
-	}
-
-	if ((rq->rq_flags & RQF_ELV) && !bypass_insert)
-		goto insert;
-
-	budget_token = blk_mq_get_dispatch_budget(q);
+	budget_token = blk_mq_get_dispatch_budget(rq->q);
 	if (budget_token < 0)
-		goto insert;
-
+		return false;
 	blk_mq_set_rq_budget_token(rq, budget_token);
-
 	if (!blk_mq_get_driver_tag(rq)) {
-		blk_mq_put_dispatch_budget(q, budget_token);
-		goto insert;
+		blk_mq_put_dispatch_budget(rq->q, budget_token);
+		return false;
 	}
-
-	return __blk_mq_issue_directly(hctx, rq, last);
-insert:
-	if (bypass_insert)
-		return BLK_STS_RESOURCE;
-
-	blk_mq_sched_insert_request(rq, false, run_queue, false);
-
-	return BLK_STS_OK;
+	return true;
 }
 
 /**
@@ -2658,18 +2615,46 @@ insert:
 static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 		struct request *rq)
 {
-	blk_status_t ret =
-		__blk_mq_try_issue_directly(hctx, rq, false, true);
+	blk_status_t ret;
 
-	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
-		blk_mq_request_bypass_insert(rq, false, true);
-	else if (ret != BLK_STS_OK)
+	if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) {
+		blk_mq_insert_request(rq, 0);
+		return;
+	}
+
+	if ((rq->rq_flags & RQF_ELV) || !blk_mq_get_budget_and_tag(rq)) {
+		blk_mq_insert_request(rq, 0);
+		blk_mq_run_hw_queue(hctx, false);
+		return;
+	}
+
+	ret = __blk_mq_issue_directly(hctx, rq, true);
+	switch (ret) {
+	case BLK_STS_OK:
+		break;
+	case BLK_STS_RESOURCE:
+	case BLK_STS_DEV_RESOURCE:
+		blk_mq_request_bypass_insert(rq, 0);
+		blk_mq_run_hw_queue(hctx, false);
+		break;
+	default:
 		blk_mq_end_request(rq, ret);
+		break;
+	}
 }
 
 static blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
 {
-	return __blk_mq_try_issue_directly(rq->mq_hctx, rq, true, last);
+	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
+	if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) {
+		blk_mq_insert_request(rq, 0);
+		return BLK_STS_OK;
+	}
+
+	if (!blk_mq_get_budget_and_tag(rq))
+		return BLK_STS_RESOURCE;
+	return __blk_mq_issue_directly(hctx, rq, last);
 }
 
 static void blk_mq_plug_issue_direct(struct blk_plug *plug)
@@ -2697,7 +2682,8 @@ static void blk_mq_plug_issue_direct(struct blk_plug *plug)
 			break;
 		case BLK_STS_RESOURCE:
 		case BLK_STS_DEV_RESOURCE:
-			blk_mq_request_bypass_insert(rq, false, true);
+			blk_mq_request_bypass_insert(rq, 0);
+			blk_mq_run_hw_queue(hctx, false);
 			goto out;
 		default:
 			blk_mq_end_request(rq, ret);
@@ -2743,7 +2729,16 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)
 
 	plug->mq_list = requeue_list;
 	trace_block_unplug(this_hctx->queue, depth, !from_sched);
-	blk_mq_sched_insert_requests(this_hctx, this_ctx, &list, from_sched);
+
+	percpu_ref_get(&this_hctx->queue->q_usage_counter);
+	if (this_hctx->queue->elevator) {
+		this_hctx->queue->elevator->type->ops.insert_requests(this_hctx,
+				&list, 0);
+		blk_mq_run_hw_queue(this_hctx, from_sched);
+	} else {
+		blk_mq_insert_requests(this_hctx, this_ctx, &list, from_sched);
+	}
+	percpu_ref_put(&this_hctx->queue->q_usage_counter);
 }
 
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
@@ -2789,7 +2784,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	} while (!rq_list_empty(plug->mq_list));
 }
 
-void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
+static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		struct list_head *list)
 {
 	int queued = 0;
@@ -2807,8 +2802,9 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 			break;
 		case BLK_STS_RESOURCE:
 		case BLK_STS_DEV_RESOURCE:
-			blk_mq_request_bypass_insert(rq, false,
-						     list_empty(list));
+			blk_mq_request_bypass_insert(rq, 0);
+			if (list_empty(list))
+				blk_mq_run_hw_queue(hctx, false);
 			goto out;
 		default:
 			blk_mq_end_request(rq, ret);
@@ -2934,6 +2930,7 @@ void blk_mq_submit_bio(struct bio *bio)
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 	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;
 	unsigned int nr_segs = 1;
 	blk_status_t ret;
@@ -2965,7 +2962,7 @@ void blk_mq_submit_bio(struct bio *bio)
 
 	blk_mq_bio_to_request(rq, bio, nr_segs);
 
-	ret = blk_crypto_init_request(rq);
+	ret = blk_crypto_rq_get_keyslot(rq);
 	if (ret != BLK_STS_OK) {
 		bio->bi_status = ret;
 		bio_endio(bio);
@@ -2978,15 +2975,19 @@ void blk_mq_submit_bio(struct bio *bio)
 		return;
 	}
 
-	if (plug)
+	if (plug) {
 		blk_add_rq_to_plug(plug, rq);
-	else if ((rq->rq_flags & RQF_ELV) ||
-		 (rq->mq_hctx->dispatch_busy &&
-		  (q->nr_hw_queues == 1 || !is_sync)))
-		blk_mq_sched_insert_request(rq, false, true, true);
-	else
-		blk_mq_run_dispatch_ops(rq->q,
-				blk_mq_try_issue_directly(rq->mq_hctx, rq));
+		return;
+	}
+
+	hctx = rq->mq_hctx;
+	if ((rq->rq_flags & RQF_ELV) ||
+	    (hctx->dispatch_busy && (q->nr_hw_queues == 1 || !is_sync))) {
+		blk_mq_insert_request(rq, 0);
+		blk_mq_run_hw_queue(hctx, true);
+	} else {
+		blk_mq_run_dispatch_ops(q, blk_mq_try_issue_directly(hctx, rq));
+	}
 }
 
 #ifdef CONFIG_BLK_MQ_STACKING
@@ -3034,8 +3035,9 @@ blk_status_t blk_insert_cloned_request(struct request *rq)
 	if (q->disk && should_fail_request(q->disk->part0, blk_rq_bytes(rq)))
 		return BLK_STS_IOERR;
 
-	if (blk_crypto_insert_cloned_request(rq))
-		return BLK_STS_IOERR;
+	ret = blk_crypto_rq_get_keyslot(rq);
+	if (ret != BLK_STS_OK)
+		return ret;
 
 	blk_account_io_start(rq);
 
@@ -4206,14 +4208,8 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	/* mark the queue as mq asap */
 	q->mq_ops = set->ops;
 
-	q->poll_cb = blk_stat_alloc_callback(blk_mq_poll_stats_fn,
-					     blk_mq_poll_stats_bkt,
-					     BLK_MQ_POLL_STATS_BKTS, q);
-	if (!q->poll_cb)
-		goto err_exit;
-
 	if (blk_mq_alloc_ctxs(q))
-		goto err_poll;
+		goto err_exit;
 
 	/* init q->mq_kobj and sw queues' kobjects */
 	blk_mq_sysfs_init(q);
@@ -4241,11 +4237,6 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 
 	q->nr_requests = set->queue_depth;
 
-	/*
-	 * Default to classic polling
-	 */
-	q->poll_nsec = BLK_MQ_POLL_CLASSIC;
-
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
 	blk_mq_add_queue_tag_set(set, q);
 	blk_mq_map_swqueue(q);
@@ -4253,9 +4244,6 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 
 err_hctxs:
 	blk_mq_release(q);
-err_poll:
-	blk_stat_free_callback(q->poll_cb);
-	q->poll_cb = NULL;
 err_exit:
 	q->mq_ops = NULL;
 	return -ENOMEM;
@@ -4752,138 +4740,8 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 }
 EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
 
-/* Enable polling stats and return whether they were already enabled. */
-static bool blk_poll_stats_enable(struct request_queue *q)
-{
-	if (q->poll_stat)
-		return true;
-
-	return blk_stats_alloc_enable(q);
-}
-
-static void blk_mq_poll_stats_start(struct request_queue *q)
-{
-	/*
-	 * We don't arm the callback if polling stats are not enabled or the
-	 * callback is already active.
-	 */
-	if (!q->poll_stat || blk_stat_is_active(q->poll_cb))
-		return;
-
-	blk_stat_activate_msecs(q->poll_cb, 100);
-}
-
-static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb)
-{
-	struct request_queue *q = cb->data;
-	int bucket;
-
-	for (bucket = 0; bucket < BLK_MQ_POLL_STATS_BKTS; bucket++) {
-		if (cb->stat[bucket].nr_samples)
-			q->poll_stat[bucket] = cb->stat[bucket];
-	}
-}
-
-static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
-				       struct request *rq)
-{
-	unsigned long ret = 0;
-	int bucket;
-
-	/*
-	 * If stats collection isn't on, don't sleep but turn it on for
-	 * future users
-	 */
-	if (!blk_poll_stats_enable(q))
-		return 0;
-
-	/*
-	 * As an optimistic guess, use half of the mean service time
-	 * for this type of request. We can (and should) make this smarter.
-	 * For instance, if the completion latencies are tight, we can
-	 * get closer than just half the mean. This is especially
-	 * important on devices where the completion latencies are longer
-	 * than ~10 usec. We do use the stats for the relevant IO size
-	 * if available which does lead to better estimates.
-	 */
-	bucket = blk_mq_poll_stats_bkt(rq);
-	if (bucket < 0)
-		return ret;
-
-	if (q->poll_stat[bucket].nr_samples)
-		ret = (q->poll_stat[bucket].mean + 1) / 2;
-
-	return ret;
-}
-
-static bool blk_mq_poll_hybrid(struct request_queue *q, blk_qc_t qc)
-{
-	struct blk_mq_hw_ctx *hctx = blk_qc_to_hctx(q, qc);
-	struct request *rq = blk_qc_to_rq(hctx, qc);
-	struct hrtimer_sleeper hs;
-	enum hrtimer_mode mode;
-	unsigned int nsecs;
-	ktime_t kt;
-
-	/*
-	 * If a request has completed on queue that uses an I/O scheduler, we
-	 * won't get back a request from blk_qc_to_rq.
-	 */
-	if (!rq || (rq->rq_flags & RQF_MQ_POLL_SLEPT))
-		return false;
-
-	/*
-	 * If we get here, hybrid polling is enabled. Hence poll_nsec can be:
-	 *
-	 *  0:	use half of prev avg
-	 * >0:	use this specific value
-	 */
-	if (q->poll_nsec > 0)
-		nsecs = q->poll_nsec;
-	else
-		nsecs = blk_mq_poll_nsecs(q, rq);
-
-	if (!nsecs)
-		return false;
-
-	rq->rq_flags |= RQF_MQ_POLL_SLEPT;
-
-	/*
-	 * This will be replaced with the stats tracking code, using
-	 * 'avg_completion_time / 2' as the pre-sleep target.
-	 */
-	kt = nsecs;
-
-	mode = HRTIMER_MODE_REL;
-	hrtimer_init_sleeper_on_stack(&hs, CLOCK_MONOTONIC, mode);
-	hrtimer_set_expires(&hs.timer, kt);
-
-	do {
-		if (blk_mq_rq_state(rq) == MQ_RQ_COMPLETE)
-			break;
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		hrtimer_sleeper_start_expires(&hs, mode);
-		if (hs.task)
-			io_schedule();
-		hrtimer_cancel(&hs.timer);
-		mode = HRTIMER_MODE_ABS;
-	} while (hs.task && !signal_pending(current));
-
-	__set_current_state(TASK_RUNNING);
-	destroy_hrtimer_on_stack(&hs.timer);
-
-	/*
-	 * If we sleep, have the caller restart the poll loop to reset the
-	 * state.  Like for the other success return cases, the caller is
-	 * responsible for checking if the IO completed.  If the IO isn't
-	 * complete, we'll get called again and will go straight to the busy
-	 * poll loop.
-	 */
-	return true;
-}
-
-static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie,
-			       struct io_comp_batch *iob, unsigned int flags)
+int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob,
+		unsigned int flags)
 {
 	struct blk_mq_hw_ctx *hctx = blk_qc_to_hctx(q, cookie);
 	long state = get_current_state();
@@ -4910,17 +4768,6 @@ static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie,
 	return 0;
 }
 
-int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob,
-		unsigned int flags)
-{
-	if (!(flags & BLK_POLL_NOSLEEP) &&
-	    q->poll_nsec != BLK_MQ_POLL_CLASSIC) {
-		if (blk_mq_poll_hybrid(q, cookie))
-			return 1;
-	}
-	return blk_mq_poll_classic(q, cookie, iob, flags);
-}
-
 unsigned int blk_mq_rq_cpu(struct request *rq)
 {
 	return rq->mq_ctx->cpu;

block/blk-mq.h

@@ -2,8 +2,8 @@
 #ifndef INT_BLK_MQ_H
 #define INT_BLK_MQ_H
 
+#include <linux/blk-mq.h>
 #include "blk-stat.h"
-#include "blk-mq-tag.h"
 
 struct blk_mq_tag_set;
 
@@ -30,6 +30,15 @@ struct blk_mq_ctx {
 	struct kobject		kobj;
 } ____cacheline_aligned_in_smp;
 
+enum {
+	BLK_MQ_NO_TAG		= -1U,
+	BLK_MQ_TAG_MIN		= 1,
+	BLK_MQ_TAG_MAX		= BLK_MQ_NO_TAG - 1,
+};
+
+typedef unsigned int __bitwise blk_insert_t;
+#define BLK_MQ_INSERT_AT_HEAD		((__force blk_insert_t)0x01)
+
 void blk_mq_submit_bio(struct bio *bio);
 int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob,
 		unsigned int flags);
@@ -38,8 +47,7 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
 bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *,
 			     unsigned int);
-void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
-				bool kick_requeue_list);
+void blk_mq_add_to_requeue_list(struct request *rq, blk_insert_t insert_flags);
 void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
 struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_ctx *start);
@@ -59,14 +67,7 @@ void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set,
 /*
  * Internal helpers for request insertion into sw queues
  */
-void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
-				bool at_head);
-void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
-				  bool run_queue);
-void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
-				struct list_head *list);
-void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
-				    struct list_head *list);
+void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags);
 
 /*
  * CPU -> queue mappings
@@ -164,6 +165,60 @@ struct blk_mq_alloc_data {
 	struct blk_mq_hw_ctx *hctx;
 };
 
+struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags,
+		unsigned int reserved_tags, int node, int alloc_policy);
+void blk_mq_free_tags(struct blk_mq_tags *tags);
+int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags,
+		struct sbitmap_queue *breserved_tags, unsigned int queue_depth,
+		unsigned int reserved, int node, int alloc_policy);
+
+unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
+unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags,
+		unsigned int *offset);
+void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
+		unsigned int tag);
+void blk_mq_put_tags(struct blk_mq_tags *tags, int *tag_array, int nr_tags);
+int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
+		struct blk_mq_tags **tags, unsigned int depth, bool can_grow);
+void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set,
+		unsigned int size);
+void blk_mq_tag_update_sched_shared_tags(struct request_queue *q);
+
+void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
+void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn,
+		void *priv);
+void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
+		void *priv);
+
+static inline struct sbq_wait_state *bt_wait_ptr(struct sbitmap_queue *bt,
+						 struct blk_mq_hw_ctx *hctx)
+{
+	if (!hctx)
+		return &bt->ws[0];
+	return sbq_wait_ptr(bt, &hctx->wait_index);
+}
+
+void __blk_mq_tag_busy(struct blk_mq_hw_ctx *);
+void __blk_mq_tag_idle(struct blk_mq_hw_ctx *);
+
+static inline void blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
+{
+	if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
+		__blk_mq_tag_busy(hctx);
+}
+
+static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
+{
+	if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
+		__blk_mq_tag_idle(hctx);
+}
+
+static inline bool blk_mq_tag_is_reserved(struct blk_mq_tags *tags,
+					  unsigned int tag)
+{
+	return tag < tags->nr_reserved_tags;
+}
+
 static inline bool blk_mq_is_shared_tags(unsigned int flags)
 {
 	return flags & BLK_MQ_F_TAG_HCTX_SHARED;

block/blk-pm.c

@@ -1,11 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/blk-mq.h>
 #include <linux/blk-pm.h>
 #include <linux/blkdev.h>
 #include <linux/pm_runtime.h>
 #include "blk-mq.h"
-#include "blk-mq-tag.h"
 
 /**
  * blk_pm_runtime_init - Block layer runtime PM initialization routine

block/blk-rq-qos.h

@@ -74,7 +74,7 @@ static inline struct rq_qos *wbt_rq_qos(struct request_queue *q)
 	return rq_qos_id(q, RQ_QOS_WBT);
 }
 
-static inline struct rq_qos *blkcg_rq_qos(struct request_queue *q)
+static inline struct rq_qos *iolat_rq_qos(struct request_queue *q)
 {
 	return rq_qos_id(q, RQ_QOS_LATENCY);
 }

block/blk-stat.c

@@ -6,7 +6,6 @@
  */
 #include <linux/kernel.h>
 #include <linux/rculist.h>
-#include <linux/blk-mq.h>
 
 #include "blk-stat.h"
 #include "blk-mq.h"
@@ -190,7 +189,7 @@ void blk_stat_disable_accounting(struct request_queue *q)
 	unsigned long flags;
 
 	spin_lock_irqsave(&q->stats->lock, flags);
-	if (!--q->stats->accounting)
+	if (!--q->stats->accounting && list_empty(&q->stats->callbacks))
 		blk_queue_flag_clear(QUEUE_FLAG_STATS, q);
 	spin_unlock_irqrestore(&q->stats->lock, flags);
 }
@@ -201,7 +200,7 @@ void blk_stat_enable_accounting(struct request_queue *q)
 	unsigned long flags;
 
 	spin_lock_irqsave(&q->stats->lock, flags);
-	if (!q->stats->accounting++)
+	if (!q->stats->accounting++ && list_empty(&q->stats->callbacks))
 		blk_queue_flag_set(QUEUE_FLAG_STATS, q);
 	spin_unlock_irqrestore(&q->stats->lock, flags);
 }
@@ -231,21 +230,3 @@ void blk_free_queue_stats(struct blk_queue_stats *stats)
 
 	kfree(stats);
 }
-
-bool blk_stats_alloc_enable(struct request_queue *q)
-{
-	struct blk_rq_stat *poll_stat;
-
-	poll_stat = kcalloc(BLK_MQ_POLL_STATS_BKTS, sizeof(*poll_stat),
-				GFP_ATOMIC);
-	if (!poll_stat)
-		return false;
-
-	if (cmpxchg(&q->poll_stat, NULL, poll_stat) != NULL) {
-		kfree(poll_stat);
-		return true;
-	}
-
-	blk_stat_add_callback(q, q->poll_cb);
-	return false;
-}

block/blk-sysfs.c

@@ -9,7 +9,6 @@
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/blktrace_api.h>
-#include <linux/blk-mq.h>
 #include <linux/debugfs.h>
 
 #include "blk.h"
@@ -408,35 +407,12 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
 
 static ssize_t queue_poll_delay_show(struct request_queue *q, char *page)
 {
-	int val;
-
-	if (q->poll_nsec == BLK_MQ_POLL_CLASSIC)
-		val = BLK_MQ_POLL_CLASSIC;
-	else
-		val = q->poll_nsec / 1000;
-
-	return sprintf(page, "%d\n", val);
+	return sprintf(page, "%d\n", -1);
 }
 
 static ssize_t queue_poll_delay_store(struct request_queue *q, const char *page,
 				size_t count)
 {
-	int err, val;
-
-	if (!q->mq_ops || !q->mq_ops->poll)
-		return -EINVAL;
-
-	err = kstrtoint(page, 10, &val);
-	if (err < 0)
-		return err;
-
-	if (val == BLK_MQ_POLL_CLASSIC)
-		q->poll_nsec = BLK_MQ_POLL_CLASSIC;
-	else if (val >= 0)
-		q->poll_nsec = val * 1000;
-	else
-		return -EINVAL;
-
 	return count;
 }
 

block/blk-throttle.c

@@ -1368,9 +1368,11 @@ static ssize_t tg_set_conf(struct kernfs_open_file *of,
 	int ret;
 	u64 v;
 
-	ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, buf, &ctx);
+	blkg_conf_init(&ctx, buf);
+
+	ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, &ctx);
 	if (ret)
-		return ret;
+		goto out_finish;
 
 	ret = -EINVAL;
 	if (sscanf(ctx.body, "%llu", &v) != 1)
@@ -1389,7 +1391,7 @@ static ssize_t tg_set_conf(struct kernfs_open_file *of,
 	tg_conf_updated(tg, false);
 	ret = 0;
 out_finish:
-	blkg_conf_finish(&ctx);
+	blkg_conf_exit(&ctx);
 	return ret ?: nbytes;
 }
 
@@ -1561,9 +1563,11 @@ static ssize_t tg_set_limit(struct kernfs_open_file *of,
 	int ret;
 	int index = of_cft(of)->private;
 
-	ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, buf, &ctx);
+	blkg_conf_init(&ctx, buf);
+
+	ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, &ctx);
 	if (ret)
-		return ret;
+		goto out_finish;
 
 	tg = blkg_to_tg(ctx.blkg);
 	tg_update_carryover(tg);
@@ -1662,7 +1666,7 @@ static ssize_t tg_set_limit(struct kernfs_open_file *of,
 		tg->td->limit_valid[LIMIT_LOW]);
 	ret = 0;
 out_finish:
-	blkg_conf_finish(&ctx);
+	blkg_conf_exit(&ctx);
 	return ret ?: nbytes;
 }
 
@@ -2439,11 +2443,12 @@ void blk_throtl_register(struct gendisk *disk)
 #ifndef CONFIG_BLK_DEV_THROTTLING_LOW
 	/* if no low limit, use previous default */
 	td->throtl_slice = DFL_THROTL_SLICE_HD;
-#endif
 
+#else
 	td->track_bio_latency = !queue_is_mq(q);
 	if (!td->track_bio_latency)
 		blk_stat_enable_accounting(q);
+#endif
 }
 
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW

block/blk.h

@@ -399,12 +399,6 @@ static inline struct bio *blk_queue_bounce(struct bio *bio,
 	return bio;
 }
 
-#ifdef CONFIG_BLK_CGROUP_IOLATENCY
-int blk_iolatency_init(struct gendisk *disk);
-#else
-static inline int blk_iolatency_init(struct gendisk *disk) { return 0; };
-#endif
-
 #ifdef CONFIG_BLK_DEV_ZONED
 void disk_free_zone_bitmaps(struct gendisk *disk);
 void disk_clear_zone_settings(struct gendisk *disk);

block/elevator.h

@@ -4,6 +4,7 @@
 
 #include <linux/percpu.h>
 #include <linux/hashtable.h>
+#include "blk-mq.h"
 
 struct io_cq;
 struct elevator_type;
@@ -37,7 +38,8 @@ struct elevator_mq_ops {
 	void (*limit_depth)(blk_opf_t, struct blk_mq_alloc_data *);
 	void (*prepare_request)(struct request *);
 	void (*finish_request)(struct request *);
-	void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool);
+	void (*insert_requests)(struct blk_mq_hw_ctx *hctx, struct list_head *list,
+			blk_insert_t flags);
 	struct request *(*dispatch_request)(struct blk_mq_hw_ctx *);
 	bool (*has_work)(struct blk_mq_hw_ctx *);
 	void (*completed_request)(struct request *, u64);

block/genhd.c

@@ -426,6 +426,9 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 	 */
 	elevator_init_mq(disk->queue);
 
+	/* Mark bdev as having a submit_bio, if needed */
+	disk->part0->bd_has_submit_bio = disk->fops->submit_bio != NULL;
+
 	/*
 	 * If the driver provides an explicit major number it also must provide
 	 * the number of minors numbers supported, and those will be used to

block/kyber-iosched.c

@@ -8,7 +8,6 @@
 
 #include <linux/kernel.h>
 #include <linux/blkdev.h>
-#include <linux/blk-mq.h>
 #include <linux/module.h>
 #include <linux/sbitmap.h>
 
@@ -19,7 +18,6 @@
 #include "blk-mq.h"
 #include "blk-mq-debugfs.h"
 #include "blk-mq-sched.h"
-#include "blk-mq-tag.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/kyber.h>
@@ -590,7 +588,8 @@ static void kyber_prepare_request(struct request *rq)
 }
 
 static void kyber_insert_requests(struct blk_mq_hw_ctx *hctx,
-				  struct list_head *rq_list, bool at_head)
+				  struct list_head *rq_list,
+				  blk_insert_t flags)
 {
 	struct kyber_hctx_data *khd = hctx->sched_data;
 	struct request *rq, *next;
@@ -602,7 +601,7 @@ static void kyber_insert_requests(struct blk_mq_hw_ctx *hctx,
 
 		spin_lock(&kcq->lock);
 		trace_block_rq_insert(rq);
-		if (at_head)
+		if (flags & BLK_MQ_INSERT_AT_HEAD)
 			list_move(&rq->queuelist, head);
 		else
 			list_move_tail(&rq->queuelist, head);

block/mq-deadline.c

@@ -8,7 +8,6 @@
 #include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/blkdev.h>
-#include <linux/blk-mq.h>
 #include <linux/bio.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -23,7 +22,6 @@
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-debugfs.h"
-#include "blk-mq-tag.h"
 #include "blk-mq-sched.h"
 
 /*
@@ -768,7 +766,7 @@ static bool dd_bio_merge(struct request_queue *q, struct bio *bio,
  * add rq to rbtree and fifo
  */
 static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
-			      bool at_head)
+			      blk_insert_t flags)
 {
 	struct request_queue *q = hctx->queue;
 	struct deadline_data *dd = q->elevator->elevator_data;
@@ -801,7 +799,7 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 
 	trace_block_rq_insert(rq);
 
-	if (at_head) {
+	if (flags & BLK_MQ_INSERT_AT_HEAD) {
 		list_add(&rq->queuelist, &per_prio->dispatch);
 		rq->fifo_time = jiffies;
 	} else {
@@ -822,10 +820,11 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 }
 
 /*
- * Called from blk_mq_sched_insert_request() or blk_mq_sched_insert_requests().
+ * Called from blk_mq_insert_request() or blk_mq_dispatch_plug_list().
  */
 static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
-			       struct list_head *list, bool at_head)
+			       struct list_head *list,
+			       blk_insert_t flags)
 {
 	struct request_queue *q = hctx->queue;
 	struct deadline_data *dd = q->elevator->elevator_data;
@@ -836,7 +835,7 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
 
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		dd_insert_request(hctx, rq, at_head);
+		dd_insert_request(hctx, rq, flags);
 	}
 	spin_unlock(&dd->lock);
 }

block/opal_proto.h

@@ -86,6 +86,15 @@ enum opal_response_token {
 #define OPAL_MSID_KEYLEN 15
 #define OPAL_UID_LENGTH_HALF 4
 
+/*
+ * Boolean operators from TCG Core spec 2.01 Section:
+ * 5.1.3.11
+ * Table 61
+ */
+#define OPAL_BOOLEAN_AND 0
+#define OPAL_BOOLEAN_OR  1
+#define OPAL_BOOLEAN_NOT 2
+
 /* Enum to index OPALUID array */
 enum opal_uid {
 	/* users */
@@ -105,6 +114,7 @@ enum opal_uid {
 	/* tables */
 	OPAL_TABLE_TABLE,
 	OPAL_LOCKINGRANGE_GLOBAL,
+	OPAL_LOCKINGRANGE_ACE_START_TO_KEY,
 	OPAL_LOCKINGRANGE_ACE_RDLOCKED,
 	OPAL_LOCKINGRANGE_ACE_WRLOCKED,
 	OPAL_MBRCONTROL,

block/sed-opal.c

@@ -83,8 +83,10 @@ struct opal_dev {
 	u16 comid;
 	u32 hsn;
 	u32 tsn;
-	u64 align;
+	u64 align; /* alignment granularity */
 	u64 lowest_lba;
+	u32 logical_block_size;
+	u8  align_required; /* ALIGN: 0 or 1 */
 
 	size_t pos;
 	u8 *cmd;
@@ -132,6 +134,8 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = {
 		{ 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x01 },
 	[OPAL_LOCKINGRANGE_GLOBAL] =
 		{ 0x00, 0x00, 0x08, 0x02, 0x00, 0x00, 0x00, 0x01 },
+	[OPAL_LOCKINGRANGE_ACE_START_TO_KEY] =
+		{ 0x00, 0x00, 0x00, 0x08, 0x00, 0x03, 0xD0, 0x01 },
 	[OPAL_LOCKINGRANGE_ACE_RDLOCKED] =
 		{ 0x00, 0x00, 0x00, 0x08, 0x00, 0x03, 0xE0, 0x01 },
 	[OPAL_LOCKINGRANGE_ACE_WRLOCKED] =
@@ -407,6 +411,8 @@ static void check_geometry(struct opal_dev *dev, const void *data)
 
 	dev->align = be64_to_cpu(geo->alignment_granularity);
 	dev->lowest_lba = be64_to_cpu(geo->lowest_aligned_lba);
+	dev->logical_block_size = be32_to_cpu(geo->logical_block_size);
+	dev->align_required = geo->reserved01 & 1;
 }
 
 static int execute_step(struct opal_dev *dev,
@@ -1147,12 +1153,8 @@ static int finalize_and_send(struct opal_dev *dev, cont_fn cont)
 	return opal_send_recv(dev, cont);
 }
 
-/*
- * request @column from table @table on device @dev. On success, the column
- * data will be available in dev->resp->tok[4]
- */
-static int generic_get_column(struct opal_dev *dev, const u8 *table,
-			      u64 column)
+static int generic_get_columns(struct opal_dev *dev, const u8 *table,
+			       u64 start_column, u64 end_column)
 {
 	int err;
 
@@ -1162,12 +1164,12 @@ static int generic_get_column(struct opal_dev *dev, const u8 *table,
 
 	add_token_u8(&err, dev, OPAL_STARTNAME);
 	add_token_u8(&err, dev, OPAL_STARTCOLUMN);
-	add_token_u64(&err, dev, column);
+	add_token_u64(&err, dev, start_column);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
 
 	add_token_u8(&err, dev, OPAL_STARTNAME);
 	add_token_u8(&err, dev, OPAL_ENDCOLUMN);
-	add_token_u64(&err, dev, column);
+	add_token_u64(&err, dev, end_column);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
 
 	add_token_u8(&err, dev, OPAL_ENDLIST);
@@ -1178,6 +1180,16 @@ static int generic_get_column(struct opal_dev *dev, const u8 *table,
 	return finalize_and_send(dev, parse_and_check_status);
 }
 
+/*
+ * request @column from table @table on device @dev. On success, the column
+ * data will be available in dev->resp->tok[4]
+ */
+static int generic_get_column(struct opal_dev *dev, const u8 *table,
+			      u64 column)
+{
+	return generic_get_columns(dev, table, column, column);
+}
+
 /*
  * see TCG SAS 5.3.2.3 for a description of the available columns
  *
@@ -1437,6 +1449,129 @@ static int setup_locking_range(struct opal_dev *dev, void *data)
 	return finalize_and_send(dev, parse_and_check_status);
 }
 
+static int response_get_column(const struct parsed_resp *resp,
+			       int *iter,
+			       u8 column,
+			       u64 *value)
+{
+	const struct opal_resp_tok *tok;
+	int n = *iter;
+	u64 val;
+
+	tok = response_get_token(resp, n);
+	if (IS_ERR(tok))
+		return PTR_ERR(tok);
+
+	if (!response_token_matches(tok, OPAL_STARTNAME)) {
+		pr_debug("Unexpected response token type %d.\n", n);
+		return OPAL_INVAL_PARAM;
+	}
+	n++;
+
+	if (response_get_u64(resp, n) != column) {
+		pr_debug("Token %d does not match expected column %u.\n",
+			 n, column);
+		return OPAL_INVAL_PARAM;
+	}
+	n++;
+
+	val = response_get_u64(resp, n);
+	n++;
+
+	tok = response_get_token(resp, n);
+	if (IS_ERR(tok))
+		return PTR_ERR(tok);
+
+	if (!response_token_matches(tok, OPAL_ENDNAME)) {
+		pr_debug("Unexpected response token type %d.\n", n);
+		return OPAL_INVAL_PARAM;
+	}
+	n++;
+
+	*value = val;
+	*iter = n;
+
+	return 0;
+}
+
+static int locking_range_status(struct opal_dev *dev, void *data)
+{
+	u8 lr_buffer[OPAL_UID_LENGTH];
+	u64 resp;
+	bool rlocked, wlocked;
+	int err, tok_n = 2;
+	struct opal_lr_status *lrst = data;
+
+	err = build_locking_range(lr_buffer, sizeof(lr_buffer),
+				  lrst->session.opal_key.lr);
+	if (err)
+		return err;
+
+	err = generic_get_columns(dev, lr_buffer, OPAL_RANGESTART,
+				  OPAL_WRITELOCKED);
+	if (err) {
+		pr_debug("Couldn't get lr %u table columns %d to %d.\n",
+			 lrst->session.opal_key.lr, OPAL_RANGESTART,
+			 OPAL_WRITELOCKED);
+		return err;
+	}
+
+	/* range start */
+	err = response_get_column(&dev->parsed, &tok_n, OPAL_RANGESTART,
+				  &lrst->range_start);
+	if (err)
+		return err;
+
+	/* range length */
+	err = response_get_column(&dev->parsed, &tok_n, OPAL_RANGELENGTH,
+				  &lrst->range_length);
+	if (err)
+		return err;
+
+	/* RLE */
+	err = response_get_column(&dev->parsed, &tok_n, OPAL_READLOCKENABLED,
+				  &resp);
+	if (err)
+		return err;
+
+	lrst->RLE = !!resp;
+
+	/* WLE */
+	err = response_get_column(&dev->parsed, &tok_n, OPAL_WRITELOCKENABLED,
+				  &resp);
+	if (err)
+		return err;
+
+	lrst->WLE = !!resp;
+
+	/* read locked */
+	err = response_get_column(&dev->parsed, &tok_n, OPAL_READLOCKED, &resp);
+	if (err)
+		return err;
+
+	rlocked = !!resp;
+
+	/* write locked */
+	err = response_get_column(&dev->parsed, &tok_n, OPAL_WRITELOCKED, &resp);
+	if (err)
+		return err;
+
+	wlocked = !!resp;
+
+	/* opal_lock_state can not map 'read locked' only state. */
+	lrst->l_state = OPAL_RW;
+	if (rlocked && wlocked)
+		lrst->l_state = OPAL_LK;
+	else if (wlocked)
+		lrst->l_state = OPAL_RO;
+	else if (rlocked) {
+		pr_debug("Can not report read locked only state.\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int start_generic_opal_session(struct opal_dev *dev,
 				      enum opal_uid auth,
 				      enum opal_uid sp_type,
@@ -1759,25 +1894,43 @@ static int set_sid_cpin_pin(struct opal_dev *dev, void *data)
 	return finalize_and_send(dev, parse_and_check_status);
 }
 
-static int add_user_to_lr(struct opal_dev *dev, void *data)
+static void add_authority_object_ref(int *err,
+				     struct opal_dev *dev,
+				     const u8 *uid,
+				     size_t uid_len)
+{
+	add_token_u8(err, dev, OPAL_STARTNAME);
+	add_token_bytestring(err, dev,
+			     opaluid[OPAL_HALF_UID_AUTHORITY_OBJ_REF],
+			     OPAL_UID_LENGTH/2);
+	add_token_bytestring(err, dev, uid, uid_len);
+	add_token_u8(err, dev, OPAL_ENDNAME);
+}
+
+static void add_boolean_object_ref(int *err,
+				   struct opal_dev *dev,
+				   u8 boolean_op)
+{
+	add_token_u8(err, dev, OPAL_STARTNAME);
+	add_token_bytestring(err, dev, opaluid[OPAL_HALF_UID_BOOLEAN_ACE],
+			     OPAL_UID_LENGTH/2);
+	add_token_u8(err, dev, boolean_op);
+	add_token_u8(err, dev, OPAL_ENDNAME);
+}
+
+static int set_lr_boolean_ace(struct opal_dev *dev,
+			      unsigned int opal_uid,
+			      u8 lr,
+			      const u8 *users,
+			      size_t users_len)
 {
 	u8 lr_buffer[OPAL_UID_LENGTH];
 	u8 user_uid[OPAL_UID_LENGTH];
-	struct opal_lock_unlock *lkul = data;
+	u8 u;
 	int err;
 
-	memcpy(lr_buffer, opaluid[OPAL_LOCKINGRANGE_ACE_RDLOCKED],
-	       OPAL_UID_LENGTH);
-
-	if (lkul->l_state == OPAL_RW)
-		memcpy(lr_buffer, opaluid[OPAL_LOCKINGRANGE_ACE_WRLOCKED],
-		       OPAL_UID_LENGTH);
-
-	lr_buffer[7] = lkul->session.opal_key.lr;
-
-	memcpy(user_uid, opaluid[OPAL_USER1_UID], OPAL_UID_LENGTH);
-
-	user_uid[7] = lkul->session.who;
+	memcpy(lr_buffer, opaluid[opal_uid], OPAL_UID_LENGTH);
+	lr_buffer[7] = lr;
 
 	err = cmd_start(dev, lr_buffer, opalmethod[OPAL_SET]);
 
@@ -1790,35 +1943,49 @@ static int add_user_to_lr(struct opal_dev *dev, void *data)
 
 	add_token_u8(&err, dev, OPAL_STARTLIST);
 
+	for (u = 0; u < users_len; u++) {
+		if (users[u] == OPAL_ADMIN1)
+			memcpy(user_uid, opaluid[OPAL_ADMIN1_UID],
+			       OPAL_UID_LENGTH);
+		else {
+			memcpy(user_uid, opaluid[OPAL_USER1_UID],
+			       OPAL_UID_LENGTH);
+			user_uid[7] = users[u];
+		}
 
-	add_token_u8(&err, dev, OPAL_STARTNAME);
-	add_token_bytestring(&err, dev,
-			     opaluid[OPAL_HALF_UID_AUTHORITY_OBJ_REF],
-			     OPAL_UID_LENGTH/2);
-	add_token_bytestring(&err, dev, user_uid, OPAL_UID_LENGTH);
-	add_token_u8(&err, dev, OPAL_ENDNAME);
-
-
-	add_token_u8(&err, dev, OPAL_STARTNAME);
-	add_token_bytestring(&err, dev,
-			     opaluid[OPAL_HALF_UID_AUTHORITY_OBJ_REF],
-			     OPAL_UID_LENGTH/2);
-	add_token_bytestring(&err, dev, user_uid, OPAL_UID_LENGTH);
-	add_token_u8(&err, dev, OPAL_ENDNAME);
-
-
-	add_token_u8(&err, dev, OPAL_STARTNAME);
-	add_token_bytestring(&err, dev, opaluid[OPAL_HALF_UID_BOOLEAN_ACE],
-			     OPAL_UID_LENGTH/2);
-	add_token_u8(&err, dev, 1);
-	add_token_u8(&err, dev, OPAL_ENDNAME);
+		add_authority_object_ref(&err, dev, user_uid, sizeof(user_uid));
 
+		/*
+		 * Add boolean operator in postfix only with
+		 * two or more authorities being added in ACE
+		 * expresion.
+		 * */
+		if (u > 0)
+			add_boolean_object_ref(&err, dev, OPAL_BOOLEAN_OR);
+	}
 
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 	add_token_u8(&err, dev, OPAL_ENDNAME);
 
+	return err;
+}
+
+static int add_user_to_lr(struct opal_dev *dev, void *data)
+{
+	int err;
+	struct opal_lock_unlock *lkul = data;
+	const u8 users[] = {
+		lkul->session.who
+	};
+
+	err = set_lr_boolean_ace(dev,
+				 lkul->l_state == OPAL_RW ?
+					OPAL_LOCKINGRANGE_ACE_WRLOCKED :
+					OPAL_LOCKINGRANGE_ACE_RDLOCKED,
+				 lkul->session.opal_key.lr, users,
+				 ARRAY_SIZE(users));
 	if (err) {
 		pr_debug("Error building add user to locking range command.\n");
 		return err;
@@ -1827,6 +1994,27 @@ static int add_user_to_lr(struct opal_dev *dev, void *data)
 	return finalize_and_send(dev, parse_and_check_status);
 }
 
+static int add_user_to_lr_ace(struct opal_dev *dev, void *data)
+{
+	int err;
+	struct opal_lock_unlock *lkul = data;
+	const u8 users[] = {
+		OPAL_ADMIN1,
+		lkul->session.who
+	};
+
+	err = set_lr_boolean_ace(dev, OPAL_LOCKINGRANGE_ACE_START_TO_KEY,
+				 lkul->session.opal_key.lr, users,
+				 ARRAY_SIZE(users));
+
+	if (err) {
+		pr_debug("Error building add user to locking ranges ACEs.\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
 static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
 {
 	u8 lr_buffer[OPAL_UID_LENGTH];
@@ -2364,6 +2552,7 @@ static int opal_add_user_to_lr(struct opal_dev *dev,
 	const struct opal_step steps[] = {
 		{ start_admin1LSP_opal_session, &lk_unlk->session.opal_key },
 		{ add_user_to_lr, lk_unlk },
+		{ add_user_to_lr_ace, lk_unlk },
 		{ end_opal_session, }
 	};
 	int ret;
@@ -2580,6 +2769,33 @@ static int opal_setup_locking_range(struct opal_dev *dev,
 	return ret;
 }
 
+static int opal_locking_range_status(struct opal_dev *dev,
+			  struct opal_lr_status *opal_lrst,
+			  void __user *data)
+{
+	const struct opal_step lr_steps[] = {
+		{ start_auth_opal_session, &opal_lrst->session },
+		{ locking_range_status, opal_lrst },
+		{ end_opal_session, }
+	};
+	int ret;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev);
+	ret = execute_steps(dev, lr_steps, ARRAY_SIZE(lr_steps));
+	mutex_unlock(&dev->dev_lock);
+
+	/* skip session info when copying back to uspace */
+	if (!ret && copy_to_user(data + offsetof(struct opal_lr_status, range_start),
+				(void *)opal_lrst + offsetof(struct opal_lr_status, range_start),
+				sizeof(*opal_lrst) - offsetof(struct opal_lr_status, range_start))) {
+		pr_debug("Error copying status to userspace\n");
+		return -EFAULT;
+	}
+
+	return ret;
+}
+
 static int opal_set_new_pw(struct opal_dev *dev, struct opal_new_pw *opal_pw)
 {
 	const struct opal_step pw_steps[] = {
@@ -2744,6 +2960,26 @@ static int opal_get_status(struct opal_dev *dev, void __user *data)
 	return 0;
 }
 
+static int opal_get_geometry(struct opal_dev *dev, void __user *data)
+{
+	struct opal_geometry geo = {0};
+
+	if (check_opal_support(dev))
+		return -EINVAL;
+
+	geo.align = dev->align_required;
+	geo.logical_block_size = dev->logical_block_size;
+	geo.alignment_granularity =  dev->align;
+	geo.lowest_aligned_lba = dev->lowest_lba;
+
+	if (copy_to_user(data, &geo, sizeof(geo))) {
+		pr_debug("Error copying geometry data to userspace\n");
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
 int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
 {
 	void *p;
@@ -2814,6 +3050,12 @@ int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
 	case IOC_OPAL_GET_STATUS:
 		ret = opal_get_status(dev, arg);
 		break;
+	case IOC_OPAL_GET_LR_STATUS:
+		ret = opal_locking_range_status(dev, p, arg);
+		break;
+	case IOC_OPAL_GET_GEOMETRY:
+		ret = opal_get_geometry(dev, arg);
+		break;
 	default:
 		break;
 	}