block-5.10-2020-10-24

-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAl+UQjkQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpvN9D/9iHU7Vgi8J3SiLrHYUiDtMSI5VnEmSBo6K
 Ej/wbbrk4tm2UYi550krOk0dMaHxWD3XWSTlpnrE0sUfjs69G676yzxrlnPt50f5
 XbcMc0YOHZfffeu9xXykUO8Q2918PTPC08eLaTK1I8lhKAuuTFCT/syGYu+prfd7
 AogyuczaDok8nqJEK9QNr0iaEUbe17GQwmvpWyjHl/qfKhWvV2r6jCZZf6pzQj2c
 zv3kbiT3u6xw9OEuhY0sgpTEfhAHEXbNIln6Ob4qVgxmOjwgiZdU/QXyw1i2s6pc
 ks7e28P43r3VfNYGBfr/hQCeAJT9gOeUG5yBiQr7ooX6uNPL6GOCG7DO/g5y2thQ
 NkV4hub/FjYWbSmRzDlJGj1fWn4L+3r/O8g5nMr+F1L3JYeaW0hOyStqBQ4O74Cj
 04tvWQ8ndXdPQrm/iDhM6KxfCvR5TC6k4fy9XPpRW8JOxauhIwTZQJyEQUnXTH3v
 pwv3IxRmuWGa3mrJZ5kGhsNAEGHdZCL5soLI+BXAD2MUW2IB5v2HpD/z1bvWL/51
 uYiVIt/2LxgLkF7BXP40PnY0qqTsOwGxdd6wQhi5Jn9Et+JkmAAR6cVwXx4AhuQg
 FT5mq7ZTQBZrErQu4Mr1k3UyqBFm4MB+mbJhWrVWnUnnyA6pcr1NUsUTz5JcyrWz
 jWI7T1Si7w==
 =dFJi
 -----END PGP SIGNATURE-----

Merge tag 'block-5.10-2020-10-24' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request from Christoph
     - rdma error handling fixes (Chao Leng)
     - fc error handling and reconnect fixes (James Smart)
     - fix the qid displace when tracing ioctl command (Keith Busch)
     - don't use BLK_MQ_REQ_NOWAIT for passthru (Chaitanya Kulkarni)
     - fix MTDT for passthru (Logan Gunthorpe)
     - blacklist Write Same on more devices (Kai-Heng Feng)
     - fix an uninitialized work struct (zhenwei pi)"

 - lightnvm out-of-bounds fix (Colin)

 - SG allocation leak fix (Doug)

 - rnbd fixes (Gioh, Guoqing, Jack)

 - zone error translation fixes (Keith)

 - kerneldoc markup fix (Mauro)

 - zram lockdep fix (Peter)

 - Kill unused io_context members (Yufen)

 - NUMA memory allocation cleanup (Xianting)

 - NBD config wakeup fix (Xiubo)

* tag 'block-5.10-2020-10-24' of git://git.kernel.dk/linux-block: (27 commits)
  block: blk-mq: fix a kernel-doc markup
  nvme-fc: shorten reconnect delay if possible for FC
  nvme-fc: wait for queues to freeze before calling update_hr_hw_queues
  nvme-fc: fix error loop in create_hw_io_queues
  nvme-fc: fix io timeout to abort I/O
  null_blk: use zone status for max active/open
  nvmet: don't use BLK_MQ_REQ_NOWAIT for passthru
  nvmet: cleanup nvmet_passthru_map_sg()
  nvmet: limit passthru MTDS by BIO_MAX_PAGES
  nvmet: fix uninitialized work for zero kato
  nvme-pci: disable Write Zeroes on Sandisk Skyhawk
  nvme: use queuedata for nvme_req_qid
  nvme-rdma: fix crash due to incorrect cqe
  nvme-rdma: fix crash when connect rejected
  block: remove unused members for io_context
  blk-mq: remove the calling of local_memory_node()
  zram: Fix __zram_bvec_{read,write}() locking order
  skd_main: remove unused including <linux/version.h>
  sgl_alloc_order: fix memory leak
  lightnvm: fix out-of-bounds write to array devices->info[]
  ...

Documentation/block/queue-sysfs.rst

@@ -124,6 +124,10 @@ For zoned block devices (zoned attribute indicating "host-managed" or
 EXPLICIT OPEN, IMPLICIT OPEN or CLOSED, is limited by this value.
 If this value is 0, there is no limit.
 
+If the host attempts to exceed this limit, the driver should report this error
+with BLK_STS_ZONE_ACTIVE_RESOURCE, which user space may see as the EOVERFLOW
+errno.
+
 max_open_zones (RO)
 -------------------
 For zoned block devices (zoned attribute indicating "host-managed" or
@@ -131,6 +135,10 @@ For zoned block devices (zoned attribute indicating "host-managed" or
 EXPLICIT OPEN or IMPLICIT OPEN, is limited by this value.
 If this value is 0, there is no limit.
 
+If the host attempts to exceed this limit, the driver should report this error
+with BLK_STS_ZONE_OPEN_RESOURCE, which user space may see as the ETOOMANYREFS
+errno.
+
 max_sectors_kb (RW)
 -------------------
 This is the maximum number of kilobytes that the block layer will allow

block/blk-core.c

@@ -186,6 +186,10 @@ static const struct {
 	/* device mapper special case, should not leak out: */
 	[BLK_STS_DM_REQUEUE]	= { -EREMCHG, "dm internal retry" },
 
+	/* zone device specific errors */
+	[BLK_STS_ZONE_OPEN_RESOURCE]	= { -ETOOMANYREFS, "open zones exceeded" },
+	[BLK_STS_ZONE_ACTIVE_RESOURCE]	= { -EOVERFLOW, "active zones exceeded" },
+
 	/* everything else not covered above: */
 	[BLK_STS_IOERR]		= { -EIO,	"I/O" },
 };

block/blk-mq-cpumap.c

@@ -89,7 +89,7 @@ int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int index)
 
 	for_each_possible_cpu(i) {
 		if (index == qmap->mq_map[i])
-			return local_memory_node(cpu_to_node(i));
+			return cpu_to_node(i);
 	}
 
 	return NUMA_NO_NODE;

block/blk-mq.c

@@ -1664,7 +1664,7 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 EXPORT_SYMBOL(blk_mq_run_hw_queue);
 
 /**
- * blk_mq_run_hw_queue - Run all hardware queues in a request queue.
+ * blk_mq_run_hw_queues - Run all hardware queues in a request queue.
  * @q: Pointer to the request queue to run.
  * @async: If we want to run the queue asynchronously.
  */
@@ -2743,7 +2743,7 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 		for (j = 0; j < set->nr_maps; j++) {
 			hctx = blk_mq_map_queue_type(q, j, i);
 			if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE)
-				hctx->numa_node = local_memory_node(cpu_to_node(i));
+				hctx->numa_node = cpu_to_node(i);
 		}
 	}
 }

drivers/block/nbd.c

@@ -802,9 +802,9 @@ static void recv_work(struct work_struct *work)
 		if (likely(!blk_should_fake_timeout(rq->q)))
 			blk_mq_complete_request(rq);
 	}
+	nbd_config_put(nbd);
 	atomic_dec(&config->recv_threads);
 	wake_up(&config->recv_wq);
-	nbd_config_put(nbd);
 	kfree(args);
 }
 

drivers/block/null_blk_zoned.c

@@ -220,29 +220,34 @@ static void null_close_first_imp_zone(struct nullb_device *dev)
 	}
 }
 
-static bool null_can_set_active(struct nullb_device *dev)
+static blk_status_t null_check_active(struct nullb_device *dev)
 {
 	if (!dev->zone_max_active)
-		return true;
+		return BLK_STS_OK;
 
-	return dev->nr_zones_exp_open + dev->nr_zones_imp_open +
+	if (dev->nr_zones_exp_open + dev->nr_zones_imp_open +
-	       dev->nr_zones_closed < dev->zone_max_active;
+			dev->nr_zones_closed < dev->zone_max_active)
+		return BLK_STS_OK;
+
+	return BLK_STS_ZONE_ACTIVE_RESOURCE;
 }
 
-static bool null_can_open(struct nullb_device *dev)
+static blk_status_t null_check_open(struct nullb_device *dev)
 {
 	if (!dev->zone_max_open)
-		return true;
+		return BLK_STS_OK;
 
 	if (dev->nr_zones_exp_open + dev->nr_zones_imp_open < dev->zone_max_open)
-		return true;
+		return BLK_STS_OK;
 
-	if (dev->nr_zones_imp_open && null_can_set_active(dev)) {
+	if (dev->nr_zones_imp_open) {
-		null_close_first_imp_zone(dev);
+		if (null_check_active(dev) == BLK_STS_OK) {
-		return true;
+			null_close_first_imp_zone(dev);
+			return BLK_STS_OK;
+		}
 	}
 
-	return false;
+	return BLK_STS_ZONE_OPEN_RESOURCE;
 }
 
 /*
@@ -258,19 +263,22 @@ static bool null_can_open(struct nullb_device *dev)
  * it is not certain that closing an implicit open zone will allow a new zone
  * to be opened, since we might already be at the active limit capacity.
  */
-static bool null_has_zone_resources(struct nullb_device *dev, struct blk_zone *zone)
+static blk_status_t null_check_zone_resources(struct nullb_device *dev, struct blk_zone *zone)
 {
+	blk_status_t ret;
+
 	switch (zone->cond) {
 	case BLK_ZONE_COND_EMPTY:
-		if (!null_can_set_active(dev))
+		ret = null_check_active(dev);
-			return false;
+		if (ret != BLK_STS_OK)
+			return ret;
 		fallthrough;
 	case BLK_ZONE_COND_CLOSED:
-		return null_can_open(dev);
+		return null_check_open(dev);
 	default:
 		/* Should never be called for other states */
 		WARN_ON(1);
-		return false;
+		return BLK_STS_IOERR;
 	}
 }
 
@@ -293,8 +301,9 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 		return BLK_STS_IOERR;
 	case BLK_ZONE_COND_EMPTY:
 	case BLK_ZONE_COND_CLOSED:
-		if (!null_has_zone_resources(dev, zone))
+		ret = null_check_zone_resources(dev, zone);
-			return BLK_STS_IOERR;
+		if (ret != BLK_STS_OK)
+			return ret;
 		break;
 	case BLK_ZONE_COND_IMP_OPEN:
 	case BLK_ZONE_COND_EXP_OPEN:
@@ -349,6 +358,8 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 
 static blk_status_t null_open_zone(struct nullb_device *dev, struct blk_zone *zone)
 {
+	blk_status_t ret;
+
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
 		return BLK_STS_IOERR;
 
@@ -357,15 +368,17 @@ static blk_status_t null_open_zone(struct nullb_device *dev, struct blk_zone *zo
 		/* open operation on exp open is not an error */
 		return BLK_STS_OK;
 	case BLK_ZONE_COND_EMPTY:
-		if (!null_has_zone_resources(dev, zone))
+		ret = null_check_zone_resources(dev, zone);
-			return BLK_STS_IOERR;
+		if (ret != BLK_STS_OK)
+			return ret;
 		break;
 	case BLK_ZONE_COND_IMP_OPEN:
 		dev->nr_zones_imp_open--;
 		break;
 	case BLK_ZONE_COND_CLOSED:
-		if (!null_has_zone_resources(dev, zone))
+		ret = null_check_zone_resources(dev, zone);
-			return BLK_STS_IOERR;
+		if (ret != BLK_STS_OK)
+			return ret;
 		dev->nr_zones_closed--;
 		break;
 	case BLK_ZONE_COND_FULL:
@@ -381,6 +394,8 @@ static blk_status_t null_open_zone(struct nullb_device *dev, struct blk_zone *zo
 
 static blk_status_t null_finish_zone(struct nullb_device *dev, struct blk_zone *zone)
 {
+	blk_status_t ret;
+
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
 		return BLK_STS_IOERR;
 
@@ -389,8 +404,9 @@ static blk_status_t null_finish_zone(struct nullb_device *dev, struct blk_zone *
 		/* finish operation on full is not an error */
 		return BLK_STS_OK;
 	case BLK_ZONE_COND_EMPTY:
-		if (!null_has_zone_resources(dev, zone))
+		ret = null_check_zone_resources(dev, zone);
-			return BLK_STS_IOERR;
+		if (ret != BLK_STS_OK)
+			return ret;
 		break;
 	case BLK_ZONE_COND_IMP_OPEN:
 		dev->nr_zones_imp_open--;
@@ -399,8 +415,9 @@ static blk_status_t null_finish_zone(struct nullb_device *dev, struct blk_zone *
 		dev->nr_zones_exp_open--;
 		break;
 	case BLK_ZONE_COND_CLOSED:
-		if (!null_has_zone_resources(dev, zone))
+		ret = null_check_zone_resources(dev, zone);
-			return BLK_STS_IOERR;
+		if (ret != BLK_STS_OK)
+			return ret;
 		dev->nr_zones_closed--;
 		break;
 	default:

drivers/block/rnbd/rnbd-clt.c

@@ -91,11 +91,6 @@ static int rnbd_clt_set_dev_attr(struct rnbd_clt_dev *dev,
 	dev->max_hw_sectors = sess->max_io_size / SECTOR_SIZE;
 	dev->max_segments = BMAX_SEGMENTS;
 
-	dev->max_hw_sectors = min_t(u32, dev->max_hw_sectors,
-				    le32_to_cpu(rsp->max_hw_sectors));
-	dev->max_segments = min_t(u16, dev->max_segments,
-				  le16_to_cpu(rsp->max_segments));
-
 	return 0;
 }
 
@@ -427,7 +422,7 @@ enum wait_type {
 };
 
 static int send_usr_msg(struct rtrs_clt *rtrs, int dir,
-			struct rnbd_iu *iu, struct kvec *vec, size_t nr,
+			struct rnbd_iu *iu, struct kvec *vec,
 			size_t len, struct scatterlist *sg, unsigned int sg_len,
 			void (*conf)(struct work_struct *work),
 			int *errno, enum wait_type wait)
@@ -441,7 +436,7 @@ static int send_usr_msg(struct rtrs_clt *rtrs, int dir,
 		.conf_fn = msg_conf,
 	};
 	err = rtrs_clt_request(dir, &req_ops, rtrs, iu->permit,
-				vec, nr, len, sg, sg_len);
+				vec, 1, len, sg, sg_len);
 	if (!err && wait) {
 		wait_event(iu->comp.wait, iu->comp.errno != INT_MAX);
 		*errno = iu->comp.errno;
@@ -486,7 +481,7 @@ static int send_msg_close(struct rnbd_clt_dev *dev, u32 device_id, bool wait)
 	msg.device_id	= cpu_to_le32(device_id);
 
 	WARN_ON(!rnbd_clt_get_dev(dev));
-	err = send_usr_msg(sess->rtrs, WRITE, iu, &vec, 1, 0, NULL, 0,
+	err = send_usr_msg(sess->rtrs, WRITE, iu, &vec, 0, NULL, 0,
 			   msg_close_conf, &errno, wait);
 	if (err) {
 		rnbd_clt_put_dev(dev);
@@ -575,7 +570,7 @@ static int send_msg_open(struct rnbd_clt_dev *dev, bool wait)
 
 	WARN_ON(!rnbd_clt_get_dev(dev));
 	err = send_usr_msg(sess->rtrs, READ, iu,
-			   &vec, 1, sizeof(*rsp), iu->sglist, 1,
+			   &vec, sizeof(*rsp), iu->sglist, 1,
 			   msg_open_conf, &errno, wait);
 	if (err) {
 		rnbd_clt_put_dev(dev);
@@ -629,7 +624,7 @@ static int send_msg_sess_info(struct rnbd_clt_session *sess, bool wait)
 		goto put_iu;
 	}
 	err = send_usr_msg(sess->rtrs, READ, iu,
-			   &vec, 1, sizeof(*rsp), iu->sglist, 1,
+			   &vec, sizeof(*rsp), iu->sglist, 1,
 			   msg_sess_info_conf, &errno, wait);
 	if (err) {
 		rnbd_clt_put_sess(sess);
@@ -1514,7 +1509,7 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname,
 			      "map_device: Failed to configure device, err: %d\n",
 			      ret);
 		mutex_unlock(&dev->lock);
-		goto del_dev;
+		goto send_close;
 	}
 
 	rnbd_clt_info(dev,
@@ -1533,6 +1528,8 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname,
 
 	return dev;
 
+send_close:
+	send_msg_close(dev, dev->device_id, WAIT);
 del_dev:
 	delete_dev(dev);
 put_dev:

drivers/block/skd_main.c

@@ -25,7 +25,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/completion.h>
 #include <linux/scatterlist.h>
-#include <linux/version.h>
 #include <linux/err.h>
 #include <linux/aer.h>
 #include <linux/wait.h>

drivers/block/zram/zram_drv.c

@@ -1218,10 +1218,11 @@ static void zram_free_page(struct zram *zram, size_t index)
 static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
 				struct bio *bio, bool partial_io)
 {
-	int ret;
+	struct zcomp_strm *zstrm;
 	unsigned long handle;
 	unsigned int size;
 	void *src, *dst;
+	int ret;
 
 	zram_slot_lock(zram, index);
 	if (zram_test_flag(zram, index, ZRAM_WB)) {
@@ -1252,6 +1253,9 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
 
 	size = zram_get_obj_size(zram, index);
 
+	if (size != PAGE_SIZE)
+		zstrm = zcomp_stream_get(zram->comp);
+
 	src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO);
 	if (size == PAGE_SIZE) {
 		dst = kmap_atomic(page);
@@ -1259,8 +1263,6 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
 		kunmap_atomic(dst);
 		ret = 0;
 	} else {
-		struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp);
-
 		dst = kmap_atomic(page);
 		ret = zcomp_decompress(zstrm, src, size, dst);
 		kunmap_atomic(dst);

drivers/lightnvm/core.c

@@ -1311,8 +1311,9 @@ static long nvm_ioctl_get_devices(struct file *file, void __user *arg)
 		strlcpy(info->bmname, "gennvm", sizeof(info->bmname));
 		i++;
 
-		if (i > 31) {
+		if (i >= ARRAY_SIZE(devices->info)) {
-			pr_err("max 31 devices can be reported.\n");
+			pr_err("max %zd devices can be reported.\n",
+			       ARRAY_SIZE(devices->info));
 			break;
 		}
 	}

drivers/nvme/host/core.c

@@ -248,6 +248,10 @@ static blk_status_t nvme_error_status(u16 status)
 		return BLK_STS_NEXUS;
 	case NVME_SC_HOST_PATH_ERROR:
 		return BLK_STS_TRANSPORT;
+	case NVME_SC_ZONE_TOO_MANY_ACTIVE:
+		return BLK_STS_ZONE_ACTIVE_RESOURCE;
+	case NVME_SC_ZONE_TOO_MANY_OPEN:
+		return BLK_STS_ZONE_OPEN_RESOURCE;
 	default:
 		return BLK_STS_IOERR;
 	}

drivers/nvme/host/fc.c

@@ -26,6 +26,10 @@ enum nvme_fc_queue_flags {
 };
 
 #define NVME_FC_DEFAULT_DEV_LOSS_TMO	60	/* seconds */
+#define NVME_FC_DEFAULT_RECONNECT_TMO	2	/* delay between reconnects
+						 * when connected and a
+						 * connection failure.
+						 */
 
 struct nvme_fc_queue {
 	struct nvme_fc_ctrl	*ctrl;
@@ -1837,8 +1841,10 @@ __nvme_fc_abort_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_fcp_op *op)
 	opstate = atomic_xchg(&op->state, FCPOP_STATE_ABORTED);
 	if (opstate != FCPOP_STATE_ACTIVE)
 		atomic_set(&op->state, opstate);
-	else if (test_bit(FCCTRL_TERMIO, &ctrl->flags))
+	else if (test_bit(FCCTRL_TERMIO, &ctrl->flags)) {
+		op->flags |= FCOP_FLAGS_TERMIO;
 		ctrl->iocnt++;
+	}
 	spin_unlock_irqrestore(&ctrl->lock, flags);
 
 	if (opstate != FCPOP_STATE_ACTIVE)
@@ -1874,7 +1880,8 @@ __nvme_fc_fcpop_chk_teardowns(struct nvme_fc_ctrl *ctrl,
 
 	if (opstate == FCPOP_STATE_ABORTED) {
 		spin_lock_irqsave(&ctrl->lock, flags);
-		if (test_bit(FCCTRL_TERMIO, &ctrl->flags)) {
+		if (test_bit(FCCTRL_TERMIO, &ctrl->flags) &&
+		    op->flags & FCOP_FLAGS_TERMIO) {
 			if (!--ctrl->iocnt)
 				wake_up(&ctrl->ioabort_wait);
 		}
@@ -2314,7 +2321,7 @@ nvme_fc_create_hw_io_queues(struct nvme_fc_ctrl *ctrl, u16 qsize)
 	return 0;
 
 delete_queues:
-	for (; i >= 0; i--)
+	for (; i > 0; i--)
 		__nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[i], i);
 	return ret;
 }
@@ -2433,7 +2440,7 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 		return;
 
 	dev_warn(ctrl->ctrl.device,
-		"NVME-FC{%d}: transport association error detected: %s\n",
+		"NVME-FC{%d}: transport association event: %s\n",
 		ctrl->cnum, errmsg);
 	dev_warn(ctrl->ctrl.device,
 		"NVME-FC{%d}: resetting controller\n", ctrl->cnum);
@@ -2446,15 +2453,20 @@ nvme_fc_timeout(struct request *rq, bool reserved)
 {
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
 	struct nvme_fc_ctrl *ctrl = op->ctrl;
+	struct nvme_fc_cmd_iu *cmdiu = &op->cmd_iu;
+	struct nvme_command *sqe = &cmdiu->sqe;
 
 	/*
-	 * we can't individually ABTS an io without affecting the queue,
+	 * Attempt to abort the offending command. Command completion
-	 * thus killing the queue, and thus the association.
+	 * will detect the aborted io and will fail the connection.
-	 * So resolve by performing a controller reset, which will stop
-	 * the host/io stack, terminate the association on the link,
-	 * and recreate an association on the link.
 	 */
-	nvme_fc_error_recovery(ctrl, "io timeout error");
+	dev_info(ctrl->ctrl.device,
+		"NVME-FC{%d.%d}: io timeout: opcode %d fctype %d w10/11: "
+		"x%08x/x%08x\n",
+		ctrl->cnum, op->queue->qnum, sqe->common.opcode,
+		sqe->connect.fctype, sqe->common.cdw10, sqe->common.cdw11);
+	if (__nvme_fc_abort_op(ctrl, op))
+		nvme_fc_error_recovery(ctrl, "io timeout abort failed");
 
 	/*
 	 * the io abort has been initiated. Have the reset timer
@@ -2726,6 +2738,7 @@ nvme_fc_complete_rq(struct request *rq)
 	struct nvme_fc_ctrl *ctrl = op->ctrl;
 
 	atomic_set(&op->state, FCPOP_STATE_IDLE);
+	op->flags &= ~FCOP_FLAGS_TERMIO;
 
 	nvme_fc_unmap_data(ctrl, rq, op);
 	nvme_complete_rq(rq);
@@ -2876,11 +2889,14 @@ nvme_fc_recreate_io_queues(struct nvme_fc_ctrl *ctrl)
 	if (ret)
 		goto out_delete_hw_queues;
 
-	if (prior_ioq_cnt != nr_io_queues)
+	if (prior_ioq_cnt != nr_io_queues) {
 		dev_info(ctrl->ctrl.device,
 			"reconnect: revising io queue count from %d to %d\n",
 			prior_ioq_cnt, nr_io_queues);
-	blk_mq_update_nr_hw_queues(&ctrl->tag_set, nr_io_queues);
+		nvme_wait_freeze(&ctrl->ctrl);
+		blk_mq_update_nr_hw_queues(&ctrl->tag_set, nr_io_queues);
+		nvme_unfreeze(&ctrl->ctrl);
+	}
 
 	return 0;
 
@@ -3090,6 +3106,61 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	return ret;
 }
 
+
+/*
+ * This routine runs through all outstanding commands on the association
+ * and aborts them.  This routine is typically be called by the
+ * delete_association routine. It is also called due to an error during
+ * reconnect. In that scenario, it is most likely a command that initializes
+ * the controller, including fabric Connect commands on io queues, that
+ * may have timed out or failed thus the io must be killed for the connect
+ * thread to see the error.
+ */
+static void
+__nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues)
+{
+	/*
+	 * If io queues are present, stop them and terminate all outstanding
+	 * ios on them. As FC allocates FC exchange for each io, the
+	 * transport must contact the LLDD to terminate the exchange,
+	 * thus releasing the FC exchange. We use blk_mq_tagset_busy_itr()
+	 * to tell us what io's are busy and invoke a transport routine
+	 * to kill them with the LLDD.  After terminating the exchange
+	 * the LLDD will call the transport's normal io done path, but it
+	 * will have an aborted status. The done path will return the
+	 * io requests back to the block layer as part of normal completions
+	 * (but with error status).
+	 */
+	if (ctrl->ctrl.queue_count > 1) {
+		nvme_stop_queues(&ctrl->ctrl);
+		blk_mq_tagset_busy_iter(&ctrl->tag_set,
+				nvme_fc_terminate_exchange, &ctrl->ctrl);
+		blk_mq_tagset_wait_completed_request(&ctrl->tag_set);
+		if (start_queues)
+			nvme_start_queues(&ctrl->ctrl);
+	}
+
+	/*
+	 * Other transports, which don't have link-level contexts bound
+	 * to sqe's, would try to gracefully shutdown the controller by
+	 * writing the registers for shutdown and polling (call
+	 * nvme_shutdown_ctrl()). Given a bunch of i/o was potentially
+	 * just aborted and we will wait on those contexts, and given
+	 * there was no indication of how live the controlelr is on the
+	 * link, don't send more io to create more contexts for the
+	 * shutdown. Let the controller fail via keepalive failure if
+	 * its still present.
+	 */
+
+	/*
+	 * clean up the admin queue. Same thing as above.
+	 */
+	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
+				nvme_fc_terminate_exchange, &ctrl->ctrl);
+	blk_mq_tagset_wait_completed_request(&ctrl->admin_tag_set);
+}
+
 /*
  * This routine stops operation of the controller on the host side.
  * On the host os stack side: Admin and IO queues are stopped,
@@ -3110,46 +3181,7 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl)
 	ctrl->iocnt = 0;
 	spin_unlock_irqrestore(&ctrl->lock, flags);
 
-	/*
+	__nvme_fc_abort_outstanding_ios(ctrl, false);
-	 * If io queues are present, stop them and terminate all outstanding
-	 * ios on them. As FC allocates FC exchange for each io, the
-	 * transport must contact the LLDD to terminate the exchange,
-	 * thus releasing the FC exchange. We use blk_mq_tagset_busy_itr()
-	 * to tell us what io's are busy and invoke a transport routine
-	 * to kill them with the LLDD.  After terminating the exchange
-	 * the LLDD will call the transport's normal io done path, but it
-	 * will have an aborted status. The done path will return the
-	 * io requests back to the block layer as part of normal completions
-	 * (but with error status).
-	 */
-	if (ctrl->ctrl.queue_count > 1) {
-		nvme_stop_queues(&ctrl->ctrl);
-		blk_mq_tagset_busy_iter(&ctrl->tag_set,
-				nvme_fc_terminate_exchange, &ctrl->ctrl);
-		blk_mq_tagset_wait_completed_request(&ctrl->tag_set);
-	}
-
-	/*
-	 * Other transports, which don't have link-level contexts bound
-	 * to sqe's, would try to gracefully shutdown the controller by
-	 * writing the registers for shutdown and polling (call
-	 * nvme_shutdown_ctrl()). Given a bunch of i/o was potentially
-	 * just aborted and we will wait on those contexts, and given
-	 * there was no indication of how live the controlelr is on the
-	 * link, don't send more io to create more contexts for the
-	 * shutdown. Let the controller fail via keepalive failure if
-	 * its still present.
-	 */
-
-	/*
-	 * clean up the admin queue. Same thing as above.
-	 * use blk_mq_tagset_busy_itr() and the transport routine to
-	 * terminate the exchanges.
-	 */
-	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
-	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
-				nvme_fc_terminate_exchange, &ctrl->ctrl);
-	blk_mq_tagset_wait_completed_request(&ctrl->admin_tag_set);
 
 	/* kill the aens as they are a separate path */
 	nvme_fc_abort_aen_ops(ctrl);
@@ -3263,22 +3295,27 @@ static void
 __nvme_fc_terminate_io(struct nvme_fc_ctrl *ctrl)
 {
 	/*
-	 * if state is connecting - the error occurred as part of a
+	 * if state is CONNECTING - the error occurred as part of a
-	 * reconnect attempt. The create_association error paths will
+	 * reconnect attempt. Abort any ios on the association and
-	 * clean up any outstanding io.
+	 * let the create_association error paths resolve things.
-	 *
-	 * if it's a different state - ensure all pending io is
-	 * terminated. Given this can delay while waiting for the
-	 * aborted io to return, we recheck adapter state below
-	 * before changing state.
 	 */
-	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING) {
+	if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
-		nvme_stop_keep_alive(&ctrl->ctrl);
+		__nvme_fc_abort_outstanding_ios(ctrl, true);
-
+		return;
-		/* will block will waiting for io to terminate */
-		nvme_fc_delete_association(ctrl);
 	}
 
+	/*
+	 * For any other state, kill the association. As this routine
+	 * is a common io abort routine for resetting and such, after
+	 * the association is terminated, ensure that the state is set
+	 * to CONNECTING.
+	 */
+
+	nvme_stop_keep_alive(&ctrl->ctrl);
+
+	/* will block will waiting for io to terminate */
+	nvme_fc_delete_association(ctrl);
+
 	if (ctrl->ctrl.state != NVME_CTRL_CONNECTING &&
 	    !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING))
 		dev_err(ctrl->ctrl.device,
@@ -3403,7 +3440,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 {
 	struct nvme_fc_ctrl *ctrl;
 	unsigned long flags;
-	int ret, idx;
+	int ret, idx, ctrl_loss_tmo;
 
 	if (!(rport->remoteport.port_role &
 	    (FC_PORT_ROLE_NVME_DISCOVERY | FC_PORT_ROLE_NVME_TARGET))) {
@@ -3429,6 +3466,19 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 		goto out_free_ctrl;
 	}
 
+	/*
+	 * if ctrl_loss_tmo is being enforced and the default reconnect delay
+	 * is being used, change to a shorter reconnect delay for FC.
+	 */
+	if (opts->max_reconnects != -1 &&
+	    opts->reconnect_delay == NVMF_DEF_RECONNECT_DELAY &&
+	    opts->reconnect_delay > NVME_FC_DEFAULT_RECONNECT_TMO) {
+		ctrl_loss_tmo = opts->max_reconnects * opts->reconnect_delay;
+		opts->reconnect_delay = NVME_FC_DEFAULT_RECONNECT_TMO;
+		opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo,
+						opts->reconnect_delay);
+	}
+
 	ctrl->ctrl.opts = opts;
 	ctrl->ctrl.nr_reconnects = 0;
 	if (lport->dev)

drivers/nvme/host/nvme.h

@@ -176,7 +176,7 @@ static inline struct nvme_request *nvme_req(struct request *req)
 
 static inline u16 nvme_req_qid(struct request *req)
 {
-	if (!req->rq_disk)
+	if (!req->q->queuedata)
 		return 0;
 	return blk_mq_unique_tag_to_hwq(blk_mq_unique_tag(req)) + 1;
 }

drivers/nvme/host/pci.c

@@ -3185,6 +3185,8 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x1c5c, 0x1504),   /* SK Hynix PC400 */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x15b7, 0x2001),   /*  Sandisk Skyhawk */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001),
 		.driver_data = NVME_QUIRK_SINGLE_VECTOR },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },

drivers/nvme/host/rdma.c

@@ -1730,10 +1730,11 @@ static void nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue,
 	req->result = cqe->result;
 
 	if (wc->wc_flags & IB_WC_WITH_INVALIDATE) {
-		if (unlikely(wc->ex.invalidate_rkey != req->mr->rkey)) {
+		if (unlikely(!req->mr ||
+			     wc->ex.invalidate_rkey != req->mr->rkey)) {
 			dev_err(queue->ctrl->ctrl.device,
 				"Bogus remote invalidation for rkey %#x\n",
-				req->mr->rkey);
+				req->mr ? req->mr->rkey : 0);
 			nvme_rdma_error_recovery(queue->ctrl);
 		}
 	} else if (req->mr) {
@@ -1926,7 +1927,6 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
 		complete(&queue->cm_done);
 		return 0;
 	case RDMA_CM_EVENT_REJECTED:
-		nvme_rdma_destroy_queue_ib(queue);
 		cm_error = nvme_rdma_conn_rejected(queue, ev);
 		break;
 	case RDMA_CM_EVENT_ROUTE_ERROR:

drivers/nvme/target/core.c

@@ -1126,7 +1126,8 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl)
 	 * in case a host died before it enabled the controller.  Hence, simply
 	 * reset the keep alive timer when the controller is enabled.
 	 */
-	mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ);
+	if (ctrl->kato)
+		mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ);
 }
 
 static void nvmet_clear_ctrl(struct nvmet_ctrl *ctrl)

drivers/nvme/target/passthru.c

@@ -26,7 +26,7 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
 	struct nvme_ctrl *pctrl = ctrl->subsys->passthru_ctrl;
 	u16 status = NVME_SC_SUCCESS;
 	struct nvme_id_ctrl *id;
-	u32 max_hw_sectors;
+	int max_hw_sectors;
 	int page_shift;
 
 	id = kzalloc(sizeof(*id), GFP_KERNEL);
@@ -48,6 +48,13 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
 	max_hw_sectors = min_not_zero(pctrl->max_segments << (PAGE_SHIFT - 9),
 				      pctrl->max_hw_sectors);
 
+	/*
+	 * nvmet_passthru_map_sg is limitted to using a single bio so limit
+	 * the mdts based on BIO_MAX_PAGES as well
+	 */
+	max_hw_sectors = min_not_zero(BIO_MAX_PAGES << (PAGE_SHIFT - 9),
+				      max_hw_sectors);
+
 	page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;
 
 	id->mdts = ilog2(max_hw_sectors) + 9 - page_shift;
@@ -180,18 +187,20 @@ static void nvmet_passthru_req_done(struct request *rq,
 
 static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)
 {
-	int sg_cnt = req->sg_cnt;
 	struct scatterlist *sg;
 	int op_flags = 0;
 	struct bio *bio;
 	int i, ret;
 
+	if (req->sg_cnt > BIO_MAX_PAGES)
+		return -EINVAL;
+
 	if (req->cmd->common.opcode == nvme_cmd_flush)
 		op_flags = REQ_FUA;
 	else if (nvme_is_write(req->cmd))
 		op_flags = REQ_SYNC | REQ_IDLE;
 
-	bio = bio_alloc(GFP_KERNEL, min(sg_cnt, BIO_MAX_PAGES));
+	bio = bio_alloc(GFP_KERNEL, req->sg_cnt);
 	bio->bi_end_io = bio_put;
 	bio->bi_opf = req_op(rq) | op_flags;
 
@@ -201,7 +210,6 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)
 			bio_put(bio);
 			return -EINVAL;
 		}
-		sg_cnt--;
 	}
 
 	ret = blk_rq_append_bio(rq, &bio);
@@ -236,7 +244,7 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
 		q = ns->queue;
 	}
 
-	rq = nvme_alloc_request(q, req->cmd, BLK_MQ_REQ_NOWAIT, NVME_QID_ANY);
+	rq = nvme_alloc_request(q, req->cmd, 0, NVME_QID_ANY);
 	if (IS_ERR(rq)) {
 		status = NVME_SC_INTERNAL;
 		goto out_put_ns;

drivers/scsi/scsi_lib.c

@@ -777,6 +777,15 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
 			/* See SSC3rXX or current. */
 			action = ACTION_FAIL;
 			break;
+		case DATA_PROTECT:
+			action = ACTION_FAIL;
+			if ((sshdr.asc == 0x0C && sshdr.ascq == 0x12) ||
+			    (sshdr.asc == 0x55 &&
+			     (sshdr.ascq == 0x0E || sshdr.ascq == 0x0F))) {
+				/* Insufficient zone resources */
+				blk_stat = BLK_STS_ZONE_OPEN_RESOURCE;
+			}
+			break;
 		default:
 			action = ACTION_FAIL;
 			break;

include/linux/blk_types.h

@@ -104,6 +104,24 @@ typedef u8 __bitwise blk_status_t;
  */
 #define BLK_STS_ZONE_RESOURCE	((__force blk_status_t)14)
 
+/*
+ * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion
+ * path if the device returns a status indicating that too many zone resources
+ * are currently open. The same command should be successful if resubmitted
+ * after the number of open zones decreases below the device's limits, which is
+ * reported in the request_queue's max_open_zones.
+ */
+#define BLK_STS_ZONE_OPEN_RESOURCE	((__force blk_status_t)15)
+
+/*
+ * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion
+ * path if the device returns a status indicating that too many zone resources
+ * are currently active. The same command should be successful if resubmitted
+ * after the number of active zones decreases below the device's limits, which
+ * is reported in the request_queue's max_active_zones.
+ */
+#define BLK_STS_ZONE_ACTIVE_RESOURCE	((__force blk_status_t)16)
+
 /**
  * blk_path_error - returns true if error may be path related
  * @error: status the request was completed with

include/linux/iocontext.h

@@ -106,12 +106,6 @@ struct io_context {
 
 	unsigned short ioprio;
 
-	/*
-	 * For request batching
-	 */
-	int nr_batch_requests;     /* Number of requests left in the batch */
-	unsigned long last_waited; /* Time last woken after wait for request */
-
 	struct radix_tree_root	icq_tree;
 	struct io_cq __rcu	*icq_hint;
 	struct hlist_head	icq_list;

lib/scatterlist.c

@@ -595,7 +595,7 @@ struct scatterlist *sgl_alloc_order(unsigned long long length,
 		elem_len = min_t(u64, length, PAGE_SIZE << order);
 		page = alloc_pages(gfp, order);
 		if (!page) {
-			sgl_free(sgl);
+			sgl_free_order(sgl, order);
 			return NULL;
 		}