Merge tag 'block-6.1-2022-10-20' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - NVMe pull request via Christoph:
      - fix nvme-hwmon for DMA non-cohehrent architectures (Serge Semin)
      - add a nvme-hwmong maintainer (Christoph Hellwig)
      - fix error pointer dereference in error handling (Dan Carpenter)
      - fix invalid memory reference in nvmet_subsys_attr_qid_max_show
        (Daniel Wagner)
      - don't limit the DMA segment size in nvme-apple (Russell King)
      - fix workqueue MEM_RECLAIM flushing dependency (Sagi Grimberg)
      - disable write zeroes on various Kingston SSDs (Xander Li)

 - fix a memory leak with block device tracing (Ye)

 - flexible-array fix for ublk (Yushan)

 - document the ublk recovery feature from this merge window
   (ZiyangZhang)

 - remove dead bfq variable in struct (Yuwei)

 - error handling rq clearing fix (Yu)

 - add an IRQ safety check for the cached bio freeing (Pavel)

 - drbd bio cloning fix (Christoph)

* tag 'block-6.1-2022-10-20' of git://git.kernel.dk/linux:
  blktrace: remove unnessary stop block trace in 'blk_trace_shutdown'
  blktrace: fix possible memleak in '__blk_trace_remove'
  blktrace: introduce 'blk_trace_{start,stop}' helper
  bio: safeguard REQ_ALLOC_CACHE bio put
  block, bfq: remove unused variable for bfq_queue
  drbd: only clone bio if we have a backing device
  ublk_drv: use flexible-array member instead of zero-length array
  nvmet: fix invalid memory reference in nvmet_subsys_attr_qid_max_show
  nvmet: fix workqueue MEM_RECLAIM flushing dependency
  nvme-hwmon: kmalloc the NVME SMART log buffer
  nvme-hwmon: consistently ignore errors from nvme_hwmon_init
  nvme: add Guenther as nvme-hwmon maintainer
  nvme-apple: don't limit DMA segement size
  nvme-pci: disable write zeroes on various Kingston SSD
  nvme: fix error pointer dereference in error handling
  Documentation: document ublk user recovery feature
  blk-mq: fix null pointer dereference in blk_mq_clear_rq_mapping()

Documentation/block/ublk.rst

@@ -144,6 +144,42 @@ managing and controlling ublk devices with help of several control commands:
   For retrieving device info via ``ublksrv_ctrl_dev_info``. It is the server's
   responsibility to save IO target specific info in userspace.
 
+- ``UBLK_CMD_START_USER_RECOVERY``
+
+  This command is valid if ``UBLK_F_USER_RECOVERY`` feature is enabled. This
+  command is accepted after the old process has exited, ublk device is quiesced
+  and ``/dev/ublkc*`` is released. User should send this command before he starts
+  a new process which re-opens ``/dev/ublkc*``. When this command returns, the
+  ublk device is ready for the new process.
+
+- ``UBLK_CMD_END_USER_RECOVERY``
+
+  This command is valid if ``UBLK_F_USER_RECOVERY`` feature is enabled. This
+  command is accepted after ublk device is quiesced and a new process has
+  opened ``/dev/ublkc*`` and get all ublk queues be ready. When this command
+  returns, ublk device is unquiesced and new I/O requests are passed to the
+  new process.
+
+- user recovery feature description
+
+  Two new features are added for user recovery: ``UBLK_F_USER_RECOVERY`` and
+  ``UBLK_F_USER_RECOVERY_REISSUE``.
+
+  With ``UBLK_F_USER_RECOVERY`` set, after one ubq_daemon(ublk server's io
+  handler) is dying, ublk does not delete ``/dev/ublkb*`` during the whole
+  recovery stage and ublk device ID is kept. It is ublk server's
+  responsibility to recover the device context by its own knowledge.
+  Requests which have not been issued to userspace are requeued. Requests
+  which have been issued to userspace are aborted.
+
+  With ``UBLK_F_USER_RECOVERY_REISSUE`` set, after one ubq_daemon(ublk
+  server's io handler) is dying, contrary to ``UBLK_F_USER_RECOVERY``,
+  requests which have been issued to userspace are requeued and will be
+  re-issued to the new process after handling ``UBLK_CMD_END_USER_RECOVERY``.
+  ``UBLK_F_USER_RECOVERY_REISSUE`` is designed for backends who tolerate
+  double-write since the driver may issue the same I/O request twice. It
+  might be useful to a read-only FS or a VM backend.
+
 Data plane
 ----------
 

MAINTAINERS

@@ -14713,6 +14713,12 @@ F:	drivers/nvme/target/auth.c
 F:	drivers/nvme/target/fabrics-cmd-auth.c
 F:	include/linux/nvme-auth.h
 
+NVM EXPRESS HARDWARE MONITORING SUPPORT
+M:	Guenter Roeck <linux@roeck-us.net>
+L:	linux-nvme@lists.infradead.org
+S:	Supported
+F:	drivers/nvme/host/hwmon.c
+
 NVM EXPRESS FC TRANSPORT DRIVERS
 M:	James Smart <james.smart@broadcom.com>
 L:	linux-nvme@lists.infradead.org

block/bfq-iosched.h

@@ -369,12 +369,8 @@ struct bfq_queue {
 	unsigned long split_time; /* time of last split */
 
 	unsigned long first_IO_time; /* time of first I/O for this queue */
-
 	unsigned long creation_time; /* when this queue is created */
 
-	/* max service rate measured so far */
-	u32 max_service_rate;
-
 	/*
 	 * Pointer to the waker queue for this queue, i.e., to the
 	 * queue Q such that this queue happens to get new I/O right

block/bio.c

@@ -741,7 +741,7 @@ void bio_put(struct bio *bio)
 			return;
 	}
 
-	if (bio->bi_opf & REQ_ALLOC_CACHE) {
+	if ((bio->bi_opf & REQ_ALLOC_CACHE) && !WARN_ON_ONCE(in_interrupt())) {
 		struct bio_alloc_cache *cache;
 
 		bio_uninit(bio);

block/blk-mq.c

@@ -3112,8 +3112,11 @@ static void blk_mq_clear_rq_mapping(struct blk_mq_tags *drv_tags,
 	struct page *page;
 	unsigned long flags;
 
-	/* There is no need to clear a driver tags own mapping */
-	if (drv_tags == tags)
+	/*
+	 * There is no need to clear mapping if driver tags is not initialized
+	 * or the mapping belongs to the driver tags.
+	 */
+	if (!drv_tags || drv_tags == tags)
 		return;
 
 	list_for_each_entry(page, &tags->page_list, lru) {

drivers/block/drbd/drbd_req.c

@@ -30,11 +30,6 @@ static struct drbd_request *drbd_req_new(struct drbd_device *device, struct bio
 		return NULL;
 	memset(req, 0, sizeof(*req));
 
-	req->private_bio = bio_alloc_clone(device->ldev->backing_bdev, bio_src,
-					   GFP_NOIO, &drbd_io_bio_set);
-	req->private_bio->bi_private = req;
-	req->private_bio->bi_end_io = drbd_request_endio;
-
 	req->rq_state = (bio_data_dir(bio_src) == WRITE ? RQ_WRITE : 0)
 		      | (bio_op(bio_src) == REQ_OP_WRITE_ZEROES ? RQ_ZEROES : 0)
 		      | (bio_op(bio_src) == REQ_OP_DISCARD ? RQ_UNMAP : 0);
@@ -1219,9 +1214,12 @@ drbd_request_prepare(struct drbd_device *device, struct bio *bio)
 	/* Update disk stats */
 	req->start_jif = bio_start_io_acct(req->master_bio);
 
-	if (!get_ldev(device)) {
-		bio_put(req->private_bio);
-		req->private_bio = NULL;
+	if (get_ldev(device)) {
+		req->private_bio = bio_alloc_clone(device->ldev->backing_bdev,
+						   bio, GFP_NOIO,
+						   &drbd_io_bio_set);
+		req->private_bio->bi_private = req;
+		req->private_bio->bi_end_io = drbd_request_endio;
 	}
 
 	/* process discards always from our submitter thread */

drivers/block/ublk_drv.c

@@ -124,7 +124,7 @@ struct ublk_queue {
 	bool force_abort;
 	unsigned short nr_io_ready;	/* how many ios setup */
 	struct ublk_device *dev;
-	struct ublk_io ios[0];
+	struct ublk_io ios[];
 };
 
 #define UBLK_DAEMON_MONITOR_PERIOD	(5 * HZ)

drivers/nvme/host/apple.c

@@ -1039,6 +1039,8 @@ static void apple_nvme_reset_work(struct work_struct *work)
 					 dma_max_mapping_size(anv->dev) >> 9);
 	anv->ctrl.max_segments = NVME_MAX_SEGS;
 
+	dma_set_max_seg_size(anv->dev, 0xffffffff);
+
 	/*
 	 * Enable NVMMU and linear submission queues.
 	 * While we could keep those disabled and pretend this is slightly

drivers/nvme/host/core.c

@@ -3262,8 +3262,12 @@ int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl)
 		return ret;
 
 	if (!ctrl->identified && !nvme_discovery_ctrl(ctrl)) {
+		/*
+		 * Do not return errors unless we are in a controller reset,
+		 * the controller works perfectly fine without hwmon.
+		 */
 		ret = nvme_hwmon_init(ctrl);
-		if (ret < 0)
+		if (ret == -EINTR)
 			return ret;
 	}
 
@@ -4846,7 +4850,7 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 	return 0;
 
 out_cleanup_admin_q:
-	blk_mq_destroy_queue(ctrl->fabrics_q);
+	blk_mq_destroy_queue(ctrl->admin_q);
 out_free_tagset:
 	blk_mq_free_tag_set(ctrl->admin_tagset);
 	return ret;

drivers/nvme/host/hwmon.c

@@ -12,7 +12,7 @@
 
 struct nvme_hwmon_data {
 	struct nvme_ctrl *ctrl;
-	struct nvme_smart_log log;
+	struct nvme_smart_log *log;
 	struct mutex read_lock;
 };
 
@@ -60,14 +60,14 @@ static int nvme_set_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under,
 static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data)
 {
 	return nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0,
-			   NVME_CSI_NVM, &data->log, sizeof(data->log), 0);
+			   NVME_CSI_NVM, data->log, sizeof(*data->log), 0);
 }
 
 static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
 			   u32 attr, int channel, long *val)
 {
 	struct nvme_hwmon_data *data = dev_get_drvdata(dev);
-	struct nvme_smart_log *log = &data->log;
+	struct nvme_smart_log *log = data->log;
 	int temp;
 	int err;
 
@@ -163,7 +163,7 @@ static umode_t nvme_hwmon_is_visible(const void *_data,
 	case hwmon_temp_max:
 	case hwmon_temp_min:
 		if ((!channel && data->ctrl->wctemp) ||
-		    (channel && data->log.temp_sensor[channel - 1])) {
+		    (channel && data->log->temp_sensor[channel - 1])) {
 			if (data->ctrl->quirks &
 			    NVME_QUIRK_NO_TEMP_THRESH_CHANGE)
 				return 0444;
@@ -176,7 +176,7 @@ static umode_t nvme_hwmon_is_visible(const void *_data,
 		break;
 	case hwmon_temp_input:
 	case hwmon_temp_label:
-		if (!channel || data->log.temp_sensor[channel - 1])
+		if (!channel || data->log->temp_sensor[channel - 1])
 			return 0444;
 		break;
 	default:
@@ -230,7 +230,13 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl)
 
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
-		return 0;
+		return -ENOMEM;
+
+	data->log = kzalloc(sizeof(*data->log), GFP_KERNEL);
+	if (!data->log) {
+		err = -ENOMEM;
+		goto err_free_data;
+	}
 
 	data->ctrl = ctrl;
 	mutex_init(&data->read_lock);
@@ -238,8 +244,7 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl)
 	err = nvme_hwmon_get_smart_log(data);
 	if (err) {
 		dev_warn(dev, "Failed to read smart log (error %d)\n", err);
-		kfree(data);
-		return err;
+		goto err_free_log;
 	}
 
 	hwmon = hwmon_device_register_with_info(dev, "nvme",
@@ -247,11 +252,17 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl)
 						NULL);
 	if (IS_ERR(hwmon)) {
 		dev_warn(dev, "Failed to instantiate hwmon device\n");
-		kfree(data);
-		return PTR_ERR(hwmon);
+		err = PTR_ERR(hwmon);
+		goto err_free_log;
 	}
 	ctrl->hwmon_device = hwmon;
 	return 0;
+
+err_free_log:
+	kfree(data->log);
+err_free_data:
+	kfree(data);
+	return err;
 }
 
 void nvme_hwmon_exit(struct nvme_ctrl *ctrl)
@@ -262,6 +273,7 @@ void nvme_hwmon_exit(struct nvme_ctrl *ctrl)
 
 		hwmon_device_unregister(ctrl->hwmon_device);
 		ctrl->hwmon_device = NULL;
+		kfree(data->log);
 		kfree(data);
 	}
 }

drivers/nvme/host/pci.c

@@ -3511,6 +3511,16 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
 	{ PCI_DEVICE(0x2646, 0x2263),   /* KINGSTON A2000 NVMe SSD  */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
+	{ PCI_DEVICE(0x2646, 0x5018),   /* KINGSTON OM8SFP4xxxxP OS21012 NVMe SSD */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x2646, 0x5016),   /* KINGSTON OM3PGP4xxxxP OS21011 NVMe SSD */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x2646, 0x501A),   /* KINGSTON OM8PGP4xxxxP OS21005 NVMe SSD */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x2646, 0x501B),   /* KINGSTON OM8PGP4xxxxQ OS21005 NVMe SSD */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x2646, 0x501E),   /* KINGSTON OM3PGP4xxxxQ OS21011 NVMe SSD */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1e4B, 0x1001),   /* MAXIO MAP1001 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1e4B, 0x1002),   /* MAXIO MAP1002 */

drivers/nvme/target/configfs.c

@@ -1290,12 +1290,8 @@ static ssize_t nvmet_subsys_attr_qid_max_show(struct config_item *item,
 static ssize_t nvmet_subsys_attr_qid_max_store(struct config_item *item,
 					       const char *page, size_t cnt)
 {
-	struct nvmet_port *port = to_nvmet_port(item);
 	u16 qid_max;
 
-	if (nvmet_is_port_enabled(port, __func__))
-		return -EACCES;
-
 	if (sscanf(page, "%hu\n", &qid_max) != 1)
 		return -EINVAL;
 

drivers/nvme/target/core.c

@@ -1176,7 +1176,7 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl)
 	 * reset the keep alive timer when the controller is enabled.
 	 */
 	if (ctrl->kato)
-		mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ);
+		mod_delayed_work(nvmet_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
 static void nvmet_clear_ctrl(struct nvmet_ctrl *ctrl)

kernel/trace/blktrace.c

@@ -346,8 +346,40 @@ static void put_probe_ref(void)
 	mutex_unlock(&blk_probe_mutex);
 }
 
+static int blk_trace_start(struct blk_trace *bt)
+{
+	if (bt->trace_state != Blktrace_setup &&
+	    bt->trace_state != Blktrace_stopped)
+		return -EINVAL;
+
+	blktrace_seq++;
+	smp_mb();
+	bt->trace_state = Blktrace_running;
+	raw_spin_lock_irq(&running_trace_lock);
+	list_add(&bt->running_list, &running_trace_list);
+	raw_spin_unlock_irq(&running_trace_lock);
+	trace_note_time(bt);
+
+	return 0;
+}
+
+static int blk_trace_stop(struct blk_trace *bt)
+{
+	if (bt->trace_state != Blktrace_running)
+		return -EINVAL;
+
+	bt->trace_state = Blktrace_stopped;
+	raw_spin_lock_irq(&running_trace_lock);
+	list_del_init(&bt->running_list);
+	raw_spin_unlock_irq(&running_trace_lock);
+	relay_flush(bt->rchan);
+
+	return 0;
+}
+
 static void blk_trace_cleanup(struct request_queue *q, struct blk_trace *bt)
 {
+	blk_trace_stop(bt);
 	synchronize_rcu();
 	blk_trace_free(q, bt);
 	put_probe_ref();
@@ -362,7 +394,6 @@ static int __blk_trace_remove(struct request_queue *q)
 	if (!bt)
 		return -EINVAL;
 
-	if (bt->trace_state != Blktrace_running)
 	blk_trace_cleanup(q, bt);
 
 	return 0;
@@ -658,7 +689,6 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
 
 static int __blk_trace_startstop(struct request_queue *q, int start)
 {
-	int ret;
 	struct blk_trace *bt;
 
 	bt = rcu_dereference_protected(q->blk_trace,
@@ -666,36 +696,10 @@ static int __blk_trace_startstop(struct request_queue *q, int start)
 	if (bt == NULL)
 		return -EINVAL;
 
-	/*
-	 * For starting a trace, we can transition from a setup or stopped
-	 * trace. For stopping a trace, the state must be running
-	 */
-	ret = -EINVAL;
-	if (start) {
-		if (bt->trace_state == Blktrace_setup ||
-		    bt->trace_state == Blktrace_stopped) {
-			blktrace_seq++;
-			smp_mb();
-			bt->trace_state = Blktrace_running;
-			raw_spin_lock_irq(&running_trace_lock);
-			list_add(&bt->running_list, &running_trace_list);
-			raw_spin_unlock_irq(&running_trace_lock);
-
-			trace_note_time(bt);
-			ret = 0;
-		}
-	} else {
-		if (bt->trace_state == Blktrace_running) {
-			bt->trace_state = Blktrace_stopped;
-			raw_spin_lock_irq(&running_trace_lock);
-			list_del_init(&bt->running_list);
-			raw_spin_unlock_irq(&running_trace_lock);
-			relay_flush(bt->rchan);
-			ret = 0;
-		}
-	}
-
-	return ret;
+	if (start)
+		return blk_trace_start(bt);
+	else
+		return blk_trace_stop(bt);
 }
 
 int blk_trace_startstop(struct request_queue *q, int start)
@@ -772,10 +776,8 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 void blk_trace_shutdown(struct request_queue *q)
 {
 	if (rcu_dereference_protected(q->blk_trace,
-				      lockdep_is_held(&q->debugfs_mutex))) {
-		__blk_trace_startstop(q, 0);
+				      lockdep_is_held(&q->debugfs_mutex)))
 		__blk_trace_remove(q);
-	}
 }
 
 #ifdef CONFIG_BLK_CGROUP
@@ -1614,13 +1616,7 @@ static int blk_trace_remove_queue(struct request_queue *q)
 	if (bt == NULL)
 		return -EINVAL;
 
-	if (bt->trace_state == Blktrace_running) {
-		bt->trace_state = Blktrace_stopped;
-		raw_spin_lock_irq(&running_trace_lock);
-		list_del_init(&bt->running_list);
-		raw_spin_unlock_irq(&running_trace_lock);
-		relay_flush(bt->rchan);
-	}
+	blk_trace_stop(bt);
 
 	put_probe_ref();
 	synchronize_rcu();