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
  ...

5 files changed, 202 insertions, 33 deletions

diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index a9c2a8d76c45..9fbfce735d56 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -73,7 +73,8 @@ static void dasd_profile_init(struct dasd_profile *, struct dentry *);
 static void dasd_profile_exit(struct dasd_profile *);
 static void dasd_hosts_init(struct dentry *, struct dasd_device *);
 static void dasd_hosts_exit(struct dasd_device *);
-
+static int dasd_handle_autoquiesce(struct dasd_device *, struct dasd_ccw_req *,
+				   unsigned int);
 /*
  * SECTION: Operations on the device structure.
  */
@@ -1451,6 +1452,8 @@ int dasd_start_IO(struct dasd_ccw_req *cqr)
 	case -ENODEV:
 		DBF_DEV_EVENT(DBF_WARNING, device, "%s",
 			      "start_IO: -ENODEV device gone, retry");
+		/* this is equivalent to CC=3 for SSCH report this to EER */
+		dasd_handle_autoquiesce(device, cqr, DASD_EER_STARTIO);
 		break;
 	case -EIO:
 		DBF_DEV_EVENT(DBF_WARNING, device, "%s",
@@ -1953,6 +1956,16 @@ static void __dasd_device_process_final_queue(struct dasd_device *device,
 }
 
 /*
+ * check if device should be autoquiesced due to too many timeouts
+ */
+static void __dasd_device_check_autoquiesce_timeout(struct dasd_device *device,
+						    struct dasd_ccw_req *cqr)
+{
+	if ((device->default_retries - cqr->retries) >= device->aq_timeouts)
+		dasd_handle_autoquiesce(device, cqr, DASD_EER_TIMEOUTS);
+}
+
+/*
  * Take a look at the first request on the ccw queue and check
  * if it reached its expire time. If so, terminate the IO.
  */
@@ -1986,6 +1999,7 @@ static void __dasd_device_check_expire(struct dasd_device *device)
 				"remaining\n", cqr, (cqr->expires/HZ),
 				cqr->retries);
 		}
+		__dasd_device_check_autoquiesce_timeout(device, cqr);
 	}
 }
 
@@ -2325,7 +2339,7 @@ static int _dasd_sleep_on(struct dasd_ccw_req *maincqr, int interruptible)
 		/* Non-temporary stop condition will trigger fail fast */
 		if (device->stopped & ~DASD_STOPPED_PENDING &&
 		    test_bit(DASD_CQR_FLAGS_FAILFAST, &cqr->flags) &&
-		    (!dasd_eer_enabled(device))) {
+		    !dasd_eer_enabled(device) && device->aq_mask == 0) {
 			cqr->status = DASD_CQR_FAILED;
 			cqr->intrc = -ENOLINK;
 			continue;
@@ -2801,20 +2815,18 @@ restart:
 			dasd_log_sense(cqr, &cqr->irb);
 		}
 
-		/* First of all call extended error reporting. */
-		if (dasd_eer_enabled(base) &&
-		    cqr->status == DASD_CQR_FAILED) {
-			dasd_eer_write(base, cqr, DASD_EER_FATALERROR);
-
-			/* restart request  */
+		/*
+		 * First call extended error reporting and check for autoquiesce
+		 */
+		spin_lock_irqsave(get_ccwdev_lock(base->cdev), flags);
+		if (cqr->status == DASD_CQR_FAILED &&
+		    dasd_handle_autoquiesce(base, cqr, DASD_EER_FATALERROR)) {
 			cqr->status = DASD_CQR_FILLED;
 			cqr->retries = 255;
-			spin_lock_irqsave(get_ccwdev_lock(base->cdev), flags);
-			dasd_device_set_stop_bits(base, DASD_STOPPED_QUIESCE);
-			spin_unlock_irqrestore(get_ccwdev_lock(base->cdev),
-					       flags);
+			spin_unlock_irqrestore(get_ccwdev_lock(base->cdev), flags);
 			goto restart;
 		}
+		spin_unlock_irqrestore(get_ccwdev_lock(base->cdev), flags);
 
 		/* Process finished ERP request. */
 		if (cqr->refers) {
@@ -2856,7 +2868,7 @@ static void __dasd_block_start_head(struct dasd_block *block)
 		/* Non-temporary stop condition will trigger fail fast */
 		if (block->base->stopped & ~DASD_STOPPED_PENDING &&
 		    test_bit(DASD_CQR_FLAGS_FAILFAST, &cqr->flags) &&
-		    (!dasd_eer_enabled(block->base))) {
+		    !dasd_eer_enabled(block->base) && block->base->aq_mask == 0) {
 			cqr->status = DASD_CQR_FAILED;
 			cqr->intrc = -ENOLINK;
 			dasd_schedule_block_bh(block);
@@ -2941,7 +2953,7 @@ static int _dasd_requeue_request(struct dasd_ccw_req *cqr)
 		return 0;
 	spin_lock_irq(&cqr->dq->lock);
 	req = (struct request *) cqr->callback_data;
-	blk_mq_requeue_request(req, false);
+	blk_mq_requeue_request(req, true);
 	spin_unlock_irq(&cqr->dq->lock);
 
 	return 0;
@@ -3670,8 +3682,8 @@ int dasd_generic_last_path_gone(struct dasd_device *device)
 	dev_warn(&device->cdev->dev, "No operational channel path is left "
 		 "for the device\n");
 	DBF_DEV_EVENT(DBF_WARNING, device, "%s", "last path gone");
-	/* First of all call extended error reporting. */
-	dasd_eer_write(device, NULL, DASD_EER_NOPATH);
+	/* First call extended error reporting and check for autoquiesce. */
+	dasd_handle_autoquiesce(device, NULL, DASD_EER_NOPATH);
 
 	if (device->state < DASD_STATE_BASIC)
 		return 0;
@@ -3803,7 +3815,8 @@ void dasd_generic_path_event(struct ccw_device *cdev, int *path_event)
 			 "No verified channel paths remain for the device\n");
 		DBF_DEV_EVENT(DBF_WARNING, device,
 			      "%s", "last verified path gone");
-		dasd_eer_write(device, NULL, DASD_EER_NOPATH);
+		/* First call extended error reporting and check for autoquiesce. */
+		dasd_handle_autoquiesce(device, NULL, DASD_EER_NOPATH);
 		dasd_device_set_stop_bits(device,
 					  DASD_STOPPED_DC_WAIT);
 	}
@@ -3825,7 +3838,8 @@ EXPORT_SYMBOL_GPL(dasd_generic_verify_path);
 void dasd_generic_space_exhaust(struct dasd_device *device,
 				struct dasd_ccw_req *cqr)
 {
-	dasd_eer_write(device, NULL, DASD_EER_NOSPC);
+	/* First call extended error reporting and check for autoquiesce. */
+	dasd_handle_autoquiesce(device, NULL, DASD_EER_NOSPC);
 
 	if (device->state < DASD_STATE_BASIC)
 		return;
@@ -3958,6 +3972,31 @@ void dasd_schedule_requeue(struct dasd_device *device)
 }
 EXPORT_SYMBOL(dasd_schedule_requeue);
 
+static int dasd_handle_autoquiesce(struct dasd_device *device,
+				   struct dasd_ccw_req *cqr,
+				   unsigned int reason)
+{
+	/* in any case write eer message with reason */
+	if (dasd_eer_enabled(device))
+		dasd_eer_write(device, cqr, reason);
+
+	if (!test_bit(reason, &device->aq_mask))
+		return 0;
+
+	/* notify eer about autoquiesce */
+	if (dasd_eer_enabled(device))
+		dasd_eer_write(device, NULL, DASD_EER_AUTOQUIESCE);
+
+	pr_info("%s: The DASD has been put in the quiesce state\n",
+		dev_name(&device->cdev->dev));
+	dasd_device_set_stop_bits(device, DASD_STOPPED_QUIESCE);
+
+	if (device->features & DASD_FEATURE_REQUEUEQUIESCE)
+		dasd_schedule_requeue(device);
+
+	return 1;
+}
+
 static struct dasd_ccw_req *dasd_generic_build_rdc(struct dasd_device *device,
 						   int rdc_buffer_size,
 						   int magic)
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index df17f0f9cb0f..620fab01b710 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -50,6 +50,7 @@ struct dasd_devmap {
         unsigned short features;
 	struct dasd_device *device;
 	struct dasd_copy_relation *copy;
+	unsigned int aq_mask;
 };
 
 /*
@@ -1476,6 +1477,128 @@ dasd_eer_store(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR(eer_enabled, 0644, dasd_eer_show, dasd_eer_store);
 
 /*
+ * aq_mask controls if the DASD should be quiesced on certain triggers
+ * The aq_mask attribute is interpreted as bitmap of the DASD_EER_* triggers.
+ */
+static ssize_t dasd_aq_mask_show(struct device *dev, struct device_attribute *attr,
+				 char *buf)
+{
+	struct dasd_devmap *devmap;
+	unsigned int aq_mask = 0;
+
+	devmap = dasd_find_busid(dev_name(dev));
+	if (!IS_ERR(devmap))
+		aq_mask = devmap->aq_mask;
+
+	return sysfs_emit(buf, "%d\n", aq_mask);
+}
+
+static ssize_t dasd_aq_mask_store(struct device *dev, struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct dasd_devmap *devmap;
+	unsigned int val;
+
+	if (kstrtouint(buf, 0, &val) || val > DASD_EER_VALID)
+		return -EINVAL;
+
+	devmap = dasd_devmap_from_cdev(to_ccwdev(dev));
+	if (IS_ERR(devmap))
+		return PTR_ERR(devmap);
+
+	spin_lock(&dasd_devmap_lock);
+	devmap->aq_mask = val;
+	if (devmap->device)
+		devmap->device->aq_mask = devmap->aq_mask;
+	spin_unlock(&dasd_devmap_lock);
+
+	return count;
+}
+
+static DEVICE_ATTR(aq_mask, 0644, dasd_aq_mask_show, dasd_aq_mask_store);
+
+/*
+ * aq_requeue controls if requests are returned to the blocklayer on quiesce
+ * or if requests are only not started
+ */
+static ssize_t dasd_aqr_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	struct dasd_devmap *devmap;
+	int flag;
+
+	devmap = dasd_find_busid(dev_name(dev));
+	if (!IS_ERR(devmap))
+		flag = (devmap->features & DASD_FEATURE_REQUEUEQUIESCE) != 0;
+	else
+		flag = (DASD_FEATURE_DEFAULT &
+			DASD_FEATURE_REQUEUEQUIESCE) != 0;
+	return sysfs_emit(buf, "%d\n", flag);
+}
+
+static ssize_t dasd_aqr_store(struct device *dev, struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	bool val;
+	int rc;
+
+	if (kstrtobool(buf, &val))
+		return -EINVAL;
+
+	rc = dasd_set_feature(to_ccwdev(dev), DASD_FEATURE_REQUEUEQUIESCE, val);
+
+	return rc ? : count;
+}
+
+static DEVICE_ATTR(aq_requeue, 0644, dasd_aqr_show, dasd_aqr_store);
+
+/*
+ * aq_timeouts controls how much retries have to time out until
+ * a device gets autoquiesced
+ */
+static ssize_t
+dasd_aq_timeouts_show(struct device *dev, struct device_attribute *attr,
+		      char *buf)
+{
+	struct dasd_device *device;
+	int len;
+
+	device = dasd_device_from_cdev(to_ccwdev(dev));
+	if (IS_ERR(device))
+		return -ENODEV;
+	len = sysfs_emit(buf, "%u\n", device->aq_timeouts);
+	dasd_put_device(device);
+	return len;
+}
+
+static ssize_t
+dasd_aq_timeouts_store(struct device *dev, struct device_attribute *attr,
+		       const char *buf, size_t count)
+{
+	struct dasd_device *device;
+	unsigned int val;
+
+	device = dasd_device_from_cdev(to_ccwdev(dev));
+	if (IS_ERR(device))
+		return -ENODEV;
+
+	if ((kstrtouint(buf, 10, &val) != 0) ||
+	    val > DASD_RETRIES_MAX || val == 0) {
+		dasd_put_device(device);
+		return -EINVAL;
+	}
+
+	if (val)
+		device->aq_timeouts = val;
+
+	dasd_put_device(device);
+	return count;
+}
+
+static DEVICE_ATTR(aq_timeouts, 0644, dasd_aq_timeouts_show,
+		   dasd_aq_timeouts_store);
+
+/*
  * expiration time for default requests
  */
 static ssize_t
@@ -2324,6 +2447,9 @@ static struct attribute * dasd_attrs[] = {
 	&dev_attr_copy_pair.attr,
 	&dev_attr_copy_role.attr,
 	&dev_attr_ping.attr,
+	&dev_attr_aq_mask.attr,
+	&dev_attr_aq_requeue.attr,
+	&dev_attr_aq_timeouts.attr,
 	NULL,
 };
 
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 1a69f97e88fb..ade1369fe5ed 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -2109,6 +2109,7 @@ dasd_eckd_check_characteristics(struct dasd_device *device)
 	device->default_retries = DASD_RETRIES;
 	device->path_thrhld = DASD_ECKD_PATH_THRHLD;
 	device->path_interval = DASD_ECKD_PATH_INTERVAL;
+	device->aq_timeouts = DASD_RETRIES_MAX;
 
 	if (private->conf.gneq) {
 		value = 1;
diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c
index a4cc772208a6..c956de711cf7 100644
--- a/drivers/s390/block/dasd_eer.c
+++ b/drivers/s390/block/dasd_eer.c
@@ -387,6 +387,7 @@ void dasd_eer_write(struct dasd_device *device, struct dasd_ccw_req *cqr,
 		break;
 	case DASD_EER_NOPATH:
 	case DASD_EER_NOSPC:
+	case DASD_EER_AUTOQUIESCE:
 		dasd_eer_write_standard_trigger(device, NULL, id);
 		break;
 	case DASD_EER_STATECHANGE:
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index 97adc8a7ae6b..33f812f0e515 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -444,22 +444,22 @@ struct dasd_discipline {
 
 extern struct dasd_discipline *dasd_diag_discipline_pointer;
 
-/*
- * Notification numbers for extended error reporting notifications:
- * The DASD_EER_DISABLE notification is sent before a dasd_device (and it's
- * eer pointer) is freed. The error reporting module needs to do all necessary
- * cleanup steps.
- * The DASD_EER_TRIGGER notification sends the actual error reports (triggers).
- */
-#define DASD_EER_DISABLE 0
-#define DASD_EER_TRIGGER 1
+/* Trigger IDs for extended error reporting DASD EER and autoquiesce */
+enum eer_trigger {
+	DASD_EER_FATALERROR = 1,
+	DASD_EER_NOPATH,
+	DASD_EER_STATECHANGE,
+	DASD_EER_PPRCSUSPEND,
+	DASD_EER_NOSPC,
+	DASD_EER_TIMEOUTS,
+	DASD_EER_STARTIO,
+
+	/* enum end marker, only add new trigger above */
+	DASD_EER_MAX,
+	DASD_EER_AUTOQUIESCE = 31, /* internal only */
+};
 
-/* Trigger IDs for extended error reporting DASD_EER_TRIGGER notification */
-#define DASD_EER_FATALERROR  1
-#define DASD_EER_NOPATH      2
-#define DASD_EER_STATECHANGE 3
-#define DASD_EER_PPRCSUSPEND 4
-#define DASD_EER_NOSPC	     5
+#define DASD_EER_VALID ((1U << DASD_EER_MAX) - 1)
 
 /* DASD path handling */
 
@@ -637,6 +637,8 @@ struct dasd_device {
 	struct dasd_format_entry format_entry;
 	struct kset *paths_info;
 	struct dasd_copy_relation *copy;
+	unsigned long aq_mask;
+	unsigned int aq_timeouts;
 };
 
 struct dasd_block {