Merge tag 'block-5.11-2020-12-23' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A few stragglers in here, but mostly just straight fixes. In
  particular:

   - Set of rnbd fixes for issues around changes for the merge window
     (Gioh, Jack, Md Haris Iqbal)

   - iocost tracepoint addition (Baolin)

   - Copyright/maintainers update (Christoph)

   - Remove old blk-mq fast path CPU warning (Daniel)

   - loop max_part fix (Josh)

   - Remote IPI threaded IRQ fix (Sebastian)

   - dasd stable fixes (Stefan)

   - bcache merge window fixup and style fixup (Yi, Zheng)"

* tag 'block-5.11-2020-12-23' of git://git.kernel.dk/linux-block:
  md/bcache: convert comma to semicolon
  bcache:remove a superfluous check in register_bcache
  block: update some copyrights
  block: remove a pointless self-reference in block_dev.c
  MAINTAINERS: add fs/block_dev.c to the block section
  blk-mq: Don't complete on a remote CPU in force threaded mode
  s390/dasd: fix list corruption of lcu list
  s390/dasd: fix list corruption of pavgroup group list
  s390/dasd: prevent inconsistent LCU device data
  s390/dasd: fix hanging device offline processing
  blk-iocost: Add iocg idle state tracepoint
  nbd: Respect max_part for all partition scans
  block/rnbd-clt: Does not request pdu to rtrs-clt
  block/rnbd-clt: Dynamically allocate sglist for rnbd_iu
  block/rnbd: Set write-back cache and fua same to the target device
  block/rnbd: Fix typos
  block/rnbd-srv: Protect dev session sysfs removal
  block/rnbd-clt: Fix possible memleak
  block/rnbd-clt: Get rid of warning regarding size argument in strlcpy
  blk-mq: Remove 'running from the wrong CPU' warning

MAINTAINERS

@@ -3199,6 +3199,7 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
 F:	block/
 F:	drivers/block/
+F:	fs/block_dev.c
 F:	include/linux/blk*
 F:	kernel/trace/blktrace.c
 F:	lib/sbitmap.c

block/blk-iocost.c

@@ -2185,6 +2185,9 @@ static int ioc_check_iocgs(struct ioc *ioc, struct ioc_now *now)
 							    WEIGHT_ONE);
 			}
 
+			TRACE_IOCG_PATH(iocg_idle, iocg, now,
+					atomic64_read(&iocg->active_period),
+					atomic64_read(&ioc->cur_period), vtime);
 			__propagate_weights(iocg, 0, 0, false, now);
 			list_del_init(&iocg->active_list);
 		}

block/blk-mq.c

@@ -650,6 +650,14 @@ static inline bool blk_mq_complete_need_ipi(struct request *rq)
 	if (!IS_ENABLED(CONFIG_SMP) ||
 	    !test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags))
 		return false;
+	/*
+	 * With force threaded interrupts enabled, raising softirq from an SMP
+	 * function call will always result in waking the ksoftirqd thread.
+	 * This is probably worse than completing the request on a different
+	 * cache domain.
+	 */
+	if (force_irqthreads)
+		return false;
 
 	/* same CPU or cache domain?  Complete locally */
 	if (cpu == rq->mq_ctx->cpu ||
@@ -1495,31 +1503,6 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
 	int srcu_idx;
 
-	/*
-	 * We should be running this queue from one of the CPUs that
-	 * are mapped to it.
-	 *
-	 * There are at least two related races now between setting
-	 * hctx->next_cpu from blk_mq_hctx_next_cpu() and running
-	 * __blk_mq_run_hw_queue():
-	 *
-	 * - hctx->next_cpu is found offline in blk_mq_hctx_next_cpu(),
-	 *   but later it becomes online, then this warning is harmless
-	 *   at all
-	 *
-	 * - hctx->next_cpu is found online in blk_mq_hctx_next_cpu(),
-	 *   but later it becomes offline, then the warning can't be
-	 *   triggered, and we depend on blk-mq timeout handler to
-	 *   handle dispatched requests to this hctx
-	 */
-	if (!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
-		cpu_online(hctx->next_cpu)) {
-		printk(KERN_WARNING "run queue from wrong CPU %d, hctx %s\n",
-			raw_smp_processor_id(),
-			cpumask_empty(hctx->cpumask) ? "inactive": "active");
-		dump_stack();
-	}
-
 	/*
 	 * We can't run the queue inline with ints disabled. Ensure that
 	 * we catch bad users of this early.

block/genhd.c

 // SPDX-License-Identifier: GPL-2.0
 /*
  *  gendisk handling
+ *
+ * Portions Copyright (C) 2020 Christoph Hellwig
  */
 
 #include <linux/module.h>

block/partitions/core.c

@@ -2,6 +2,7 @@
 /*
  * Copyright (C) 1991-1998  Linus Torvalds
  * Re-organised Feb 1998 Russell King
+ * Copyright (C) 2020 Christoph Hellwig
  */
 #include <linux/fs.h>
 #include <linux/slab.h>

drivers/block/nbd.c

@@ -318,6 +318,7 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
 	blk_queue_logical_block_size(nbd->disk->queue, blksize);
 	blk_queue_physical_block_size(nbd->disk->queue, blksize);
 
+	if (max_part)
 		set_bit(GD_NEED_PART_SCAN, &nbd->disk->state);
 	if (!set_capacity_and_notify(nbd->disk, bytesize >> 9))
 		kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
@@ -1476,8 +1477,10 @@ static int nbd_open(struct block_device *bdev, fmode_t mode)
 		refcount_set(&nbd->config_refs, 1);
 		refcount_inc(&nbd->refs);
 		mutex_unlock(&nbd->config_lock);
+		if (max_part)
 			set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
 	} else if (nbd_disconnected(nbd->config)) {
+		if (max_part)
 			set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
 	}
 out:

drivers/block/rnbd/rnbd-clt-sysfs.c

@@ -432,7 +432,7 @@ void rnbd_clt_remove_dev_symlink(struct rnbd_clt_dev *dev)
 	 * i.e. rnbd_clt_unmap_dev_store() leading to a sysfs warning because
 	 * of sysfs link already was removed already.
 	 */
-	if (strlen(dev->blk_symlink_name) && try_module_get(THIS_MODULE)) {
+	if (dev->blk_symlink_name && try_module_get(THIS_MODULE)) {
 		sysfs_remove_link(rnbd_devs_kobj, dev->blk_symlink_name);
 		kfree(dev->blk_symlink_name);
 		module_put(THIS_MODULE);
@@ -521,7 +521,8 @@ static int rnbd_clt_add_dev_symlink(struct rnbd_clt_dev *dev)
 	return 0;
 
 out_err:
-	dev->blk_symlink_name[0] = '\0';
+	kfree(dev->blk_symlink_name);
+	dev->blk_symlink_name = NULL ;
 	return ret;
 }
 

drivers/block/rnbd/rnbd-clt.h

@@ -44,6 +44,13 @@ struct rnbd_iu_comp {
 	int errno;
 };
 
+#ifdef CONFIG_ARCH_NO_SG_CHAIN
+#define RNBD_INLINE_SG_CNT 0
+#else
+#define RNBD_INLINE_SG_CNT 2
+#endif
+#define RNBD_RDMA_SGL_SIZE (sizeof(struct scatterlist) * RNBD_INLINE_SG_CNT)
+
 struct rnbd_iu {
 	union {
 		struct request *rq; /* for block io */
@@ -56,11 +63,12 @@ struct rnbd_iu {
 		/* use to send msg associated with a sess */
 		struct rnbd_clt_session *sess;
 	};
-	struct scatterlist	sglist[BMAX_SEGMENTS];
+	struct sg_table		sgt;
 	struct work_struct	work;
 	int			errno;
 	struct rnbd_iu_comp	comp;
 	atomic_t		refcount;
+	struct scatterlist	first_sgl[]; /* must be the last one */
 };
 
 struct rnbd_cpu_qlist {
@@ -112,6 +120,8 @@ struct rnbd_clt_dev {
 	enum rnbd_access_mode	access_mode;
 	bool			read_only;
 	bool			rotational;
+	bool			wc;
+	bool			fua;
 	u32			max_hw_sectors;
 	u32			max_write_same_sectors;
 	u32			max_discard_sectors;

drivers/block/rnbd/rnbd-proto.h

@@ -108,6 +108,11 @@ struct rnbd_msg_close {
 	__le32		device_id;
 };
 
+enum rnbd_cache_policy {
+	RNBD_FUA = 1 << 0,
+	RNBD_WRITEBACK = 1 << 1,
+};
+
 /**
  * struct rnbd_msg_open_rsp - response message to RNBD_MSG_OPEN
  * @hdr:		message header
@@ -124,6 +129,7 @@ struct rnbd_msg_close {
  * @max_segments:	max segments hardware support in one transfer
  * @secure_discard:	supports secure discard
  * @rotation:		is a rotational disc?
+ * @cache_policy: 	support write-back caching or FUA?
  */
 struct rnbd_msg_open_rsp {
 	struct rnbd_msg_hdr	hdr;
@@ -139,7 +145,8 @@ struct rnbd_msg_open_rsp {
 	__le16			max_segments;
 	__le16			secure_discard;
 	u8			rotational;
-	u8			reserved[11];
+	u8			cache_policy;
+	u8			reserved[10];
 };
 
 /**

drivers/block/rnbd/rnbd-srv.c

@@ -338,9 +338,10 @@ static int rnbd_srv_link_ev(struct rtrs_srv *rtrs,
 
 void rnbd_srv_sess_dev_force_close(struct rnbd_srv_sess_dev *sess_dev)
 {
+	mutex_lock(&sess_dev->sess->lock);
 	rnbd_srv_destroy_dev_session_sysfs(sess_dev);
+	mutex_unlock(&sess_dev->sess->lock);
 	sess_dev->keep_id = true;
-
 }
 
 static int process_msg_close(struct rtrs_srv *rtrs,
@@ -549,6 +550,7 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp,
 					struct rnbd_srv_sess_dev *sess_dev)
 {
 	struct rnbd_dev *rnbd_dev = sess_dev->rnbd_dev;
+	struct request_queue *q = bdev_get_queue(rnbd_dev->bdev);
 
 	rsp->hdr.type = cpu_to_le16(RNBD_MSG_OPEN_RSP);
 	rsp->device_id =
@@ -573,8 +575,12 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp,
 		cpu_to_le32(rnbd_dev_get_discard_alignment(rnbd_dev));
 	rsp->secure_discard =
 		cpu_to_le16(rnbd_dev_get_secure_discard(rnbd_dev));
-	rsp->rotational =
-		!blk_queue_nonrot(bdev_get_queue(rnbd_dev->bdev));
+	rsp->rotational = !blk_queue_nonrot(q);
+	rsp->cache_policy = 0;
+	if (test_bit(QUEUE_FLAG_WC, &q->queue_flags))
+		rsp->cache_policy |= RNBD_WRITEBACK;
+	if (blk_queue_fua(q))
+		rsp->cache_policy |= RNBD_FUA;
 }
 
 static struct rnbd_srv_sess_dev *

drivers/infiniband/ulp/rtrs/rtrs-clt.c

@@ -157,12 +157,6 @@ void rtrs_clt_put_permit(struct rtrs_clt *clt, struct rtrs_permit *permit)
 }
 EXPORT_SYMBOL(rtrs_clt_put_permit);
 
-void *rtrs_permit_to_pdu(struct rtrs_permit *permit)
-{
-	return permit + 1;
-}
-EXPORT_SYMBOL(rtrs_permit_to_pdu);
-
 /**
  * rtrs_permit_to_clt_con() - returns RDMA connection pointer by the permit
  * @sess: client session pointer

drivers/infiniband/ulp/rtrs/rtrs.h

@@ -63,13 +63,6 @@ struct rtrs_clt *rtrs_clt_open(struct rtrs_clt_ops *ops,
 
 void rtrs_clt_close(struct rtrs_clt *sess);
 
-/**
- * rtrs_permit_to_pdu() - converts rtrs_permit to opaque pdu pointer
- * @permit: RTRS permit pointer, it associates the memory allocation for future
- *          RDMA operation.
- */
-void *rtrs_permit_to_pdu(struct rtrs_permit *permit);
-
 enum {
 	RTRS_PERMIT_NOWAIT = 0,
 	RTRS_PERMIT_WAIT   = 1,

drivers/md/bcache/super.c

@@ -2535,8 +2535,6 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 			else
 				err = "device busy";
 			mutex_unlock(&bch_register_lock);
-			if (!IS_ERR(bdev))
-				bdput(bdev);
 			if (attr == &ksysfs_register_quiet)
 				goto done;
 		}

drivers/md/bcache/sysfs.c

@@ -404,7 +404,7 @@ STORE(__cached_dev)
 		if (!env)
 			return -ENOMEM;
 		add_uevent_var(env, "DRIVER=bcache");
-		add_uevent_var(env, "CACHED_UUID=%pU", dc->sb.uuid),
+		add_uevent_var(env, "CACHED_UUID=%pU", dc->sb.uuid);
 		add_uevent_var(env, "CACHED_LABEL=%s", buf);
 		kobject_uevent_env(&disk_to_dev(dc->disk.disk)->kobj,
 				   KOBJ_CHANGE,

drivers/s390/block/dasd_alias.c

@@ -256,7 +256,6 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device)
 		return;
 	device->discipline->get_uid(device, &uid);
 	spin_lock_irqsave(&lcu->lock, flags);
-	list_del_init(&device->alias_list);
 	/* make sure that the workers don't use this device */
 	if (device == lcu->suc_data.device) {
 		spin_unlock_irqrestore(&lcu->lock, flags);
@@ -283,6 +282,7 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device)
 
 	spin_lock_irqsave(&aliastree.lock, flags);
 	spin_lock(&lcu->lock);
+	list_del_init(&device->alias_list);
 	if (list_empty(&lcu->grouplist) &&
 	    list_empty(&lcu->active_devices) &&
 	    list_empty(&lcu->inactive_devices)) {
@@ -462,11 +462,19 @@ static int read_unit_address_configuration(struct dasd_device *device,
 	spin_unlock_irqrestore(&lcu->lock, flags);
 
 	rc = dasd_sleep_on(cqr);
-	if (rc && !suborder_not_supported(cqr)) {
+	if (!rc)
+		goto out;
+
+	if (suborder_not_supported(cqr)) {
+		/* suborder not supported or device unusable for IO */
+		rc = -EOPNOTSUPP;
+	} else {
+		/* IO failed but should be retried */
 		spin_lock_irqsave(&lcu->lock, flags);
 		lcu->flags |= NEED_UAC_UPDATE;
 		spin_unlock_irqrestore(&lcu->lock, flags);
 	}
+out:
 	dasd_sfree_request(cqr, cqr->memdev);
 	return rc;
 }
@@ -503,6 +511,14 @@ static int _lcu_update(struct dasd_device *refdev, struct alias_lcu *lcu)
 		return rc;
 
 	spin_lock_irqsave(&lcu->lock, flags);
+	/*
+	 * there is another update needed skip the remaining handling
+	 * the data might already be outdated
+	 * but especially do not add the device to an LCU with pending
+	 * update
+	 */
+	if (lcu->flags & NEED_UAC_UPDATE)
+		goto out;
 	lcu->pav = NO_PAV;
 	for (i = 0; i < MAX_DEVICES_PER_LCU; ++i) {
 		switch (lcu->uac->unit[i].ua_type) {
@@ -521,6 +537,7 @@ static int _lcu_update(struct dasd_device *refdev, struct alias_lcu *lcu)
 				 alias_list) {
 		_add_device_to_lcu(lcu, device, refdev);
 	}
+out:
 	spin_unlock_irqrestore(&lcu->lock, flags);
 	return 0;
 }
@@ -625,6 +642,7 @@ int dasd_alias_add_device(struct dasd_device *device)
 	}
 	if (lcu->flags & UPDATE_PENDING) {
 		list_move(&device->alias_list, &lcu->active_devices);
+		private->pavgroup = NULL;
 		_schedule_lcu_update(lcu, device);
 	}
 	spin_unlock_irqrestore(&lcu->lock, flags);

fs/block_dev.c

 // SPDX-License-Identifier: GPL-2.0-only
 /*
- *  linux/fs/block_dev.c
- *
  *  Copyright (C) 1991, 1992  Linus Torvalds
  *  Copyright (C) 2001  Andrea Arcangeli <andrea@suse.de> SuSE
+ *  Copyright (C) 2016 - 2020 Christoph Hellwig
  */
 
 #include <linux/init.h>

include/trace/events/iocost.h

@@ -11,7 +11,7 @@ struct ioc_gq;
 
 #include <linux/tracepoint.h>
 
-TRACE_EVENT(iocost_iocg_activate,
+DECLARE_EVENT_CLASS(iocost_iocg_state,
 
 	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
 		u64 last_period, u64 cur_period, u64 vtime),
@@ -59,6 +59,20 @@ TRACE_EVENT(iocost_iocg_activate,
 	)
 );
 
+DEFINE_EVENT(iocost_iocg_state, iocost_iocg_activate,
+	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+		 u64 last_period, u64 cur_period, u64 vtime),
+
+	TP_ARGS(iocg, path, now, last_period, cur_period, vtime)
+);
+
+DEFINE_EVENT(iocost_iocg_state, iocost_iocg_idle,
+	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+		 u64 last_period, u64 cur_period, u64 vtime),
+
+	TP_ARGS(iocg, path, now, last_period, cur_period, vtime)
+);
+
 DECLARE_EVENT_CLASS(iocg_inuse_update,
 
 	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,