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 lockin...

Documentation/ABI/stable/sysfs-block

@@ -336,18 +336,11 @@ What:		/sys/block/<disk>/queue/io_poll_delay
 Date:		November 2016
 Contact:	linux-block@vger.kernel.org
 Description:
-		[RW] If polling is enabled, this controls what kind of polling
-		will be performed. It defaults to -1, which is classic polling.
+		[RW] This was used to control what kind of polling will be
+		performed.  It is now fixed to -1, which is classic polling.
 		In this mode, the CPU will repeatedly ask for completions
-		without giving up any time.  If set to 0, a hybrid polling mode
-		is used, where the kernel will attempt to make an educated guess
-		at when the IO will complete. Based on this guess, the kernel
-		will put the process issuing IO to sleep for an amount of time,
-		before entering a classic poll loop. This mode might be a little
-		slower than pure classic polling, but it will be more efficient.
-		If set to a value larger than 0, the kernel will put the process
-		issuing IO to sleep for this amount of microseconds before
-		entering classic polling.
+		without giving up any time.
+		<deprecated>
 
 
 What:		/sys/block/<disk>/queue/io_timeout

Documentation/block/inline-encryption.rst

@@ -270,8 +270,7 @@ Request queue based layered devices like dm-rq that wish to support inline
 encryption need to create their own blk_crypto_profile for their request_queue,
 and expose whatever functionality they choose. When a layered device wants to
 pass a clone of that request to another request_queue, blk-crypto will
-initialize and prepare the clone as necessary; see
-``blk_crypto_insert_cloned_request()``.
+initialize and prepare the clone as necessary.
 
 Interaction between inline encryption and blk integrity
 =======================================================

Documentation/fault-injection/fault-injection.rst

@@ -52,6 +52,14 @@ Available fault injection capabilities
   status code is NVME_SC_INVALID_OPCODE with no retry. The status code and
   retry flag can be set via the debugfs.
 
+- Null test block driver fault injection
+
+  inject IO timeouts by setting config items under
+  /sys/kernel/config/nullb/<disk>/timeout_inject,
+  inject requeue requests by setting config items under
+  /sys/kernel/config/nullb/<disk>/requeue_inject, and
+  inject init_hctx() errors by setting config items under
+  /sys/kernel/config/nullb/<disk>/init_hctx_fault_inject.
 
 Configure fault-injection capabilities behavior
 -----------------------------------------------

arch/s390/include/uapi/asm/dasd.h

@@ -78,6 +78,7 @@ typedef struct dasd_information2_t {
  * 0x040: give access to raw eckd data
  * 0x080: enable discard support
  * 0x100: enable autodisable for IFCC errors (default)
+ * 0x200: enable requeue of all requests on autoquiesce
  */
 #define DASD_FEATURE_READONLY	      0x001
 #define DASD_FEATURE_USEDIAG	      0x002
@@ -88,6 +89,7 @@ typedef struct dasd_information2_t {
 #define DASD_FEATURE_USERAW	      0x040
 #define DASD_FEATURE_DISCARD	      0x080
 #define DASD_FEATURE_PATH_AUTODISABLE 0x100
+#define DASD_FEATURE_REQUEUEQUIESCE   0x200
 #define DASD_FEATURE_DEFAULT	      DASD_FEATURE_PATH_AUTODISABLE
 
 #define DASD_PARTN_BITS 2

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

@@ -497,15 +497,9 @@ static struct blkcg_policy_data *bfq_cpd_alloc(gfp_t gfp)
 	bgd = kzalloc(sizeof(*bgd), gfp);
 	if (!bgd)
 		return NULL;
-	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;
+	bgd->weight = CGROUP_WEIGHT_DFL;
+	return &bgd->pd;
 }
 
 static void bfq_cpd_free(struct blkcg_policy_data *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 @@ static bool bfqq_request_over_limit(struct bfq_queue *bfqq, int limit)
 					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.
+ * 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().
+ */
+void blkg_conf_init(struct blkg_conf_ctx *ctx, char *input)
+{
+	*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()
  *
- * Use this function iff blkg_conf_prep() can't be used for some reason.
+ * 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.
  */
-struct block_device *blkcg_conf_open_bdev(char **inputp)
+int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx)
 {
-	char *input = *inputp;
+	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 @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.
  *
- * 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().
+ * 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 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 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 @@ int blkcg_init_disk(struct gendisk *disk)
 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 @@ blk_status_t blk_crypto_get_keyslot(struct blk_crypto_profile *profile,
 
 /**
  * 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
+ *
+ * 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.
  *
- * 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.
+ * 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.
  *
- * Return: 0 on success or if the key wasn't in any keyslot; -errno on error.
+ * 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 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
 
 	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);
+
+	ret = blkg_conf_open_bdev(&ctx);
+	if (ret)
+		goto err;
 
-	q = bdev_get_queue(bdev);
+	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 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 
 	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
 	 */