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
  ...

Documentation/ABI/stable/sysfs-block

@@ -336,18 +336,11 @@ What:		/sys/block/<disk>/queue/io_poll_delay
 Date:		November 2016
 Contact:	[email protected]
 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