Merge tag 'for-6.2/block-2022-12-08' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull requests via Christoph:
      - Support some passthrough commands without CAP_SYS_ADMIN (Kanchan
        Joshi)
      - Refactor PCIe probing and reset (Christoph Hellwig)
      - Various fabrics authentication fixes and improvements (Sagi
        Grimberg)
      - Avoid fallback to sequential scan due to transient issues (Uday
        Shankar)
      - Implement support for the DEAC bit in Write Zeroes (Christoph
        Hellwig)
      - Allow overriding the IEEE OUI and firmware revision in configfs
        for nvmet (Aleksandr Miloserdov)
      - Force reconnect when number of queue changes in nvmet (Daniel
        Wagner)
      - Minor fixes and improvements (Uros Bizjak, Joel Granados, Sagi
        Grimberg, Christoph Hellwig, Christophe JAILLET)
      - Fix and cleanup nvme-fc req allocation (Chaitanya Kulkarni)
      - Use the common tagset helpers in nvme-pci driver (Christoph
        Hellwig)
      - Cleanup the nvme-pci removal path (Christoph Hellwig)
      - Use kstrtobool() instead of strtobool (Christophe JAILLET)
      - Allow unprivileged passthrough of Identify Controller (Joel
        Granados)
      - Support io stats on the mpath device (Sagi Grimberg)
      - Minor nvmet cleanup (Sagi Grimberg)

 - MD pull requests via Song:
      - Code cleanups (Christoph)
      - Various fixes

 - Floppy pull request from Denis:
      - Fix a memory leak in the init error path (Yuan)

 - Series fixing some batch wakeup issues with sbitmap (Gabriel)

 - Removal of the pktcdvd driver that was deprecated more than 5 years
   ago, and subsequent removal of the devnode callback in struct
   block_device_operations as no users are now left (Greg)

 - Fix for partition read on an exclusively opened bdev (Jan)

 - Series of elevator API cleanups (Jinlong, Christoph)

 - Series of fixes and cleanups for blk-iocost (Kemeng)

 - Series of fixes and cleanups for blk-throttle (Kemeng)

 - Series adding concurrent support for sync queues in BFQ (Yu)

 - Series bringing drbd a bit closer to the out-of-tree maintained
   version (Christian, Joel, Lars, Philipp)

 - Misc drbd fixes (Wang)

 - blk-wbt fixes and tweaks for enable/disable (Yu)

 - Fixes for mq-deadline for zoned devices (Damien)

 - Add support for read-only and offline zones for null_blk
   (Shin'ichiro)

 - Series fixing the delayed holder tracking, as used by DM (Yu,
   Christoph)

 - Series enabling bio alloc caching for IRQ based IO (Pavel)

 - Series enabling userspace peer-to-peer DMA (Logan)

 - BFQ waker fixes (Khazhismel)

 - Series fixing elevator refcount issues (Christoph, Jinlong)

 - Series cleaning up references around queue destruction (Christoph)

 - Series doing quiesce by tagset, enabling cleanups in drivers
   (Christoph, Chao)

 - Series untangling the queue kobject and queue references (Christoph)

 - Misc fixes and cleanups (Bart, David, Dawei, Jinlong, Kemeng, Ye,
   Yang, Waiman, Shin'ichiro, Randy, Pankaj, Christoph)

* tag 'for-6.2/block-2022-12-08' of git://git.kernel.dk/linux: (247 commits)
  blktrace: Fix output non-blktrace event when blk_classic option enabled
  block: sed-opal: Don't include <linux/kernel.h>
  sed-opal: allow using IOC_OPAL_SAVE for locking too
  blk-cgroup: Fix typo in comment
  block: remove bio_set_op_attrs
  nvmet: don't open-code NVME_NS_ATTR_RO enumeration
  nvme-pci: use the tagset alloc/free helpers
  nvme: add the Apple shared tag workaround to nvme_alloc_io_tag_set
  nvme: only set reserved_tags in nvme_alloc_io_tag_set for fabrics controllers
  nvme: consolidate setting the tagset flags
  nvme: pass nr_maps explicitly to nvme_alloc_io_tag_set
  block: bio_copy_data_iter
  nvme-pci: split out a nvme_pci_ctrl_is_dead helper
  nvme-pci: return early on ctrl state mismatch in nvme_reset_work
  nvme-pci: rename nvme_disable_io_queues
  nvme-pci: cleanup nvme_suspend_queue
  nvme-pci: remove nvme_pci_disable
  nvme-pci: remove nvme_disable_admin_queue
  nvme: merge nvme_shutdown_ctrl into nvme_disable_ctrl
  nvme: use nvme_wait_ready in nvme_shutdown_ctrl
  ...

1 files changed, 92 insertions, 3 deletions

diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c
index 55a69e48ef8b..635ce0648133 100644
--- a/drivers/block/null_blk/zoned.c
+++ b/drivers/block/null_blk/zoned.c
@@ -384,8 +384,10 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 
 	null_lock_zone(dev, zone);
 
-	if (zone->cond == BLK_ZONE_COND_FULL) {
-		/* Cannot write to a full zone */
+	if (zone->cond == BLK_ZONE_COND_FULL ||
+	    zone->cond == BLK_ZONE_COND_READONLY ||
+	    zone->cond == BLK_ZONE_COND_OFFLINE) {
+		/* Cannot write to the zone */
 		ret = BLK_STS_IOERR;
 		goto unlock;
 	}
@@ -613,7 +615,9 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_op op,
 		for (i = dev->zone_nr_conv; i < dev->nr_zones; i++) {
 			zone = &dev->zones[i];
 			null_lock_zone(dev, zone);
-			if (zone->cond != BLK_ZONE_COND_EMPTY) {
+			if (zone->cond != BLK_ZONE_COND_EMPTY &&
+			    zone->cond != BLK_ZONE_COND_READONLY &&
+			    zone->cond != BLK_ZONE_COND_OFFLINE) {
 				null_reset_zone(dev, zone);
 				trace_nullb_zone_op(cmd, i, zone->cond);
 			}
@@ -627,6 +631,12 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_op op,
 
 	null_lock_zone(dev, zone);
 
+	if (zone->cond == BLK_ZONE_COND_READONLY ||
+	    zone->cond == BLK_ZONE_COND_OFFLINE) {
+		ret = BLK_STS_IOERR;
+		goto unlock;
+	}
+
 	switch (op) {
 	case REQ_OP_ZONE_RESET:
 		ret = null_reset_zone(dev, zone);
@@ -648,6 +658,7 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_op op,
 	if (ret == BLK_STS_OK)
 		trace_nullb_zone_op(cmd, zone_no, zone->cond);
 
+unlock:
 	null_unlock_zone(dev, zone);
 
 	return ret;
@@ -674,6 +685,8 @@ blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_op op,
 	default:
 		dev = cmd->nq->dev;
 		zone = &dev->zones[null_zone_no(dev, sector)];
+		if (zone->cond == BLK_ZONE_COND_OFFLINE)
+			return BLK_STS_IOERR;
 
 		null_lock_zone(dev, zone);
 		sts = null_process_cmd(cmd, op, sector, nr_sectors);
@@ -681,3 +694,79 @@ blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_op op,
 		return sts;
 	}
 }
+
+/*
+ * Set a zone in the read-only or offline condition.
+ */
+static void null_set_zone_cond(struct nullb_device *dev,
+			       struct nullb_zone *zone, enum blk_zone_cond cond)
+{
+	if (WARN_ON_ONCE(cond != BLK_ZONE_COND_READONLY &&
+			 cond != BLK_ZONE_COND_OFFLINE))
+		return;
+
+	null_lock_zone(dev, zone);
+
+	/*
+	 * If the read-only condition is requested again to zones already in
+	 * read-only condition, restore back normal empty condition. Do the same
+	 * if the offline condition is requested for offline zones. Otherwise,
+	 * set the specified zone condition to the zones. Finish the zones
+	 * beforehand to free up zone resources.
+	 */
+	if (zone->cond == cond) {
+		zone->cond = BLK_ZONE_COND_EMPTY;
+		zone->wp = zone->start;
+		if (dev->memory_backed)
+			null_handle_discard(dev, zone->start, zone->len);
+	} else {
+		if (zone->cond != BLK_ZONE_COND_READONLY &&
+		    zone->cond != BLK_ZONE_COND_OFFLINE)
+			null_finish_zone(dev, zone);
+		zone->cond = cond;
+		zone->wp = (sector_t)-1;
+	}
+
+	null_unlock_zone(dev, zone);
+}
+
+/*
+ * Identify a zone from the sector written to configfs file. Then set zone
+ * condition to the zone.
+ */
+ssize_t zone_cond_store(struct nullb_device *dev, const char *page,
+			size_t count, enum blk_zone_cond cond)
+{
+	unsigned long long sector;
+	unsigned int zone_no;
+	int ret;
+
+	if (!dev->zoned) {
+		pr_err("null_blk device is not zoned\n");
+		return -EINVAL;
+	}
+
+	if (!dev->zones) {
+		pr_err("null_blk device is not yet powered\n");
+		return -EINVAL;
+	}
+
+	ret = kstrtoull(page, 0, &sector);
+	if (ret < 0)
+		return ret;
+
+	zone_no = null_zone_no(dev, sector);
+	if (zone_no >= dev->nr_zones) {
+		pr_err("Sector out of range\n");
+		return -EINVAL;
+	}
+
+	if (dev->zones[zone_no].type == BLK_ZONE_TYPE_CONVENTIONAL) {
+		pr_err("Can not change condition of conventional zones\n");
+		return -EINVAL;
+	}
+
+	null_set_zone_cond(dev, &dev->zones[zone_no], cond);
+
+	return count;
+}