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, 103 insertions, 92 deletions

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 80099df37314..39cb570f833d 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -668,21 +668,11 @@ out:
 	nvmet_req_complete(req, status);
 }
 
-static bool nvmet_handle_identify_desclist(struct nvmet_req *req)
+static void nvmet_execute_identify_ctrl_nvm(struct nvmet_req *req)
 {
-	switch (req->cmd->identify.csi) {
-	case NVME_CSI_NVM:
-		nvmet_execute_identify_desclist(req);
-		return true;
-	case NVME_CSI_ZNS:
-		if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
-			nvmet_execute_identify_desclist(req);
-			return true;
-		}
-		return false;
-	default:
-		return false;
-	}
+	/* Not supported: return zeroes */
+	nvmet_req_complete(req,
+		   nvmet_zero_sgl(req, 0, sizeof(struct nvme_id_ctrl_nvm)));
 }
 
 static void nvmet_execute_identify(struct nvmet_req *req)
@@ -692,54 +682,49 @@ static void nvmet_execute_identify(struct nvmet_req *req)
 
 	switch (req->cmd->identify.cns) {
 	case NVME_ID_CNS_NS:
+		nvmet_execute_identify_ns(req);
+		return;
+	case NVME_ID_CNS_CTRL:
+		nvmet_execute_identify_ctrl(req);
+		return;
+	case NVME_ID_CNS_NS_ACTIVE_LIST:
+		nvmet_execute_identify_nslist(req);
+		return;
+	case NVME_ID_CNS_NS_DESC_LIST:
+		nvmet_execute_identify_desclist(req);
+		return;
+	case NVME_ID_CNS_CS_NS:
 		switch (req->cmd->identify.csi) {
 		case NVME_CSI_NVM:
-			return nvmet_execute_identify_ns(req);
-		default:
+			/* Not supported */
 			break;
-		}
-		break;
-	case NVME_ID_CNS_CS_NS:
-		if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
-			switch (req->cmd->identify.csi) {
-			case NVME_CSI_ZNS:
-				return nvmet_execute_identify_cns_cs_ns(req);
-			default:
-				break;
+		case NVME_CSI_ZNS:
+			if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
+				nvmet_execute_identify_ns_zns(req);
+				return;
 			}
-		}
-		break;
-	case NVME_ID_CNS_CTRL:
-		switch (req->cmd->identify.csi) {
-		case NVME_CSI_NVM:
-			return nvmet_execute_identify_ctrl(req);
+			break;
 		}
 		break;
 	case NVME_ID_CNS_CS_CTRL:
-		if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
-			switch (req->cmd->identify.csi) {
-			case NVME_CSI_ZNS:
-				return nvmet_execute_identify_cns_cs_ctrl(req);
-			default:
-				break;
-			}
-		}
-		break;
-	case NVME_ID_CNS_NS_ACTIVE_LIST:
 		switch (req->cmd->identify.csi) {
 		case NVME_CSI_NVM:
-			return nvmet_execute_identify_nslist(req);
-		default:
+			nvmet_execute_identify_ctrl_nvm(req);
+			return;
+		case NVME_CSI_ZNS:
+			if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
+				nvmet_execute_identify_ctrl_zns(req);
+				return;
+			}
 			break;
 		}
 		break;
-	case NVME_ID_CNS_NS_DESC_LIST:
-		if (nvmet_handle_identify_desclist(req) == true)
-			return;
-		break;
 	}
 
-	nvmet_req_cns_error_complete(req);
+	pr_debug("unhandled identify cns %d on qid %d\n",
+	       req->cmd->identify.cns, req->sq->qid);
+	req->error_loc = offsetof(struct nvme_identify, cns);
+	nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
 }
 
 /*
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index 5c16372f3b53..c780af36c1d4 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -614,10 +614,11 @@ fcloop_fcp_recv_work(struct work_struct *work)
 	struct fcloop_fcpreq *tfcp_req =
 		container_of(work, struct fcloop_fcpreq, fcp_rcv_work);
 	struct nvmefc_fcp_req *fcpreq = tfcp_req->fcpreq;
+	unsigned long flags;
 	int ret = 0;
 	bool aborted = false;
 
-	spin_lock_irq(&tfcp_req->reqlock);
+	spin_lock_irqsave(&tfcp_req->reqlock, flags);
 	switch (tfcp_req->inistate) {
 	case INI_IO_START:
 		tfcp_req->inistate = INI_IO_ACTIVE;
@@ -626,11 +627,11 @@ fcloop_fcp_recv_work(struct work_struct *work)
 		aborted = true;
 		break;
 	default:
-		spin_unlock_irq(&tfcp_req->reqlock);
+		spin_unlock_irqrestore(&tfcp_req->reqlock, flags);
 		WARN_ON(1);
 		return;
 	}
-	spin_unlock_irq(&tfcp_req->reqlock);
+	spin_unlock_irqrestore(&tfcp_req->reqlock, flags);
 
 	if (unlikely(aborted))
 		ret = -ECANCELED;
@@ -655,8 +656,9 @@ fcloop_fcp_abort_recv_work(struct work_struct *work)
 		container_of(work, struct fcloop_fcpreq, abort_rcv_work);
 	struct nvmefc_fcp_req *fcpreq;
 	bool completed = false;
+	unsigned long flags;
 
-	spin_lock_irq(&tfcp_req->reqlock);
+	spin_lock_irqsave(&tfcp_req->reqlock, flags);
 	fcpreq = tfcp_req->fcpreq;
 	switch (tfcp_req->inistate) {
 	case INI_IO_ABORTED:
@@ -665,11 +667,11 @@ fcloop_fcp_abort_recv_work(struct work_struct *work)
 		completed = true;
 		break;
 	default:
-		spin_unlock_irq(&tfcp_req->reqlock);
+		spin_unlock_irqrestore(&tfcp_req->reqlock, flags);
 		WARN_ON(1);
 		return;
 	}
-	spin_unlock_irq(&tfcp_req->reqlock);
+	spin_unlock_irqrestore(&tfcp_req->reqlock, flags);
 
 	if (unlikely(completed)) {
 		/* remove reference taken in original abort downcall */
@@ -681,9 +683,9 @@ fcloop_fcp_abort_recv_work(struct work_struct *work)
 		nvmet_fc_rcv_fcp_abort(tfcp_req->tport->targetport,
 					&tfcp_req->tgt_fcp_req);
 
-	spin_lock_irq(&tfcp_req->reqlock);
+	spin_lock_irqsave(&tfcp_req->reqlock, flags);
 	tfcp_req->fcpreq = NULL;
-	spin_unlock_irq(&tfcp_req->reqlock);
+	spin_unlock_irqrestore(&tfcp_req->reqlock, flags);
 
 	fcloop_call_host_done(fcpreq, tfcp_req, -ECANCELED);
 	/* call_host_done releases reference for abort downcall */
@@ -699,11 +701,12 @@ fcloop_tgt_fcprqst_done_work(struct work_struct *work)
 	struct fcloop_fcpreq *tfcp_req =
 		container_of(work, struct fcloop_fcpreq, tio_done_work);
 	struct nvmefc_fcp_req *fcpreq;
+	unsigned long flags;
 
-	spin_lock_irq(&tfcp_req->reqlock);
+	spin_lock_irqsave(&tfcp_req->reqlock, flags);
 	fcpreq = tfcp_req->fcpreq;
 	tfcp_req->inistate = INI_IO_COMPLETED;
-	spin_unlock_irq(&tfcp_req->reqlock);
+	spin_unlock_irqrestore(&tfcp_req->reqlock, flags);
 
 	fcloop_call_host_done(fcpreq, tfcp_req, tfcp_req->status);
 }
@@ -807,13 +810,14 @@ fcloop_fcp_op(struct nvmet_fc_target_port *tgtport,
 	u32 rsplen = 0, xfrlen = 0;
 	int fcp_err = 0, active, aborted;
 	u8 op = tgt_fcpreq->op;
+	unsigned long flags;
 
-	spin_lock_irq(&tfcp_req->reqlock);
+	spin_lock_irqsave(&tfcp_req->reqlock, flags);
 	fcpreq = tfcp_req->fcpreq;
 	active = tfcp_req->active;
 	aborted = tfcp_req->aborted;
 	tfcp_req->active = true;
-	spin_unlock_irq(&tfcp_req->reqlock);
+	spin_unlock_irqrestore(&tfcp_req->reqlock, flags);
 
 	if (unlikely(active))
 		/* illegal - call while i/o active */
@@ -821,9 +825,9 @@ fcloop_fcp_op(struct nvmet_fc_target_port *tgtport,
 
 	if (unlikely(aborted)) {
 		/* target transport has aborted i/o prior */
-		spin_lock_irq(&tfcp_req->reqlock);
+		spin_lock_irqsave(&tfcp_req->reqlock, flags);
 		tfcp_req->active = false;
-		spin_unlock_irq(&tfcp_req->reqlock);
+		spin_unlock_irqrestore(&tfcp_req->reqlock, flags);
 		tgt_fcpreq->transferred_length = 0;
 		tgt_fcpreq->fcp_error = -ECANCELED;
 		tgt_fcpreq->done(tgt_fcpreq);
@@ -880,9 +884,9 @@ fcloop_fcp_op(struct nvmet_fc_target_port *tgtport,
 		break;
 	}
 
-	spin_lock_irq(&tfcp_req->reqlock);
+	spin_lock_irqsave(&tfcp_req->reqlock, flags);
 	tfcp_req->active = false;
-	spin_unlock_irq(&tfcp_req->reqlock);
+	spin_unlock_irqrestore(&tfcp_req->reqlock, flags);
 
 	tgt_fcpreq->transferred_length = xfrlen;
 	tgt_fcpreq->fcp_error = fcp_err;
@@ -896,15 +900,16 @@ fcloop_tgt_fcp_abort(struct nvmet_fc_target_port *tgtport,
 			struct nvmefc_tgt_fcp_req *tgt_fcpreq)
 {
 	struct fcloop_fcpreq *tfcp_req = tgt_fcp_req_to_fcpreq(tgt_fcpreq);
+	unsigned long flags;
 
 	/*
 	 * mark aborted only in case there were 2 threads in transport
 	 * (one doing io, other doing abort) and only kills ops posted
 	 * after the abort request
 	 */
-	spin_lock_irq(&tfcp_req->reqlock);
+	spin_lock_irqsave(&tfcp_req->reqlock, flags);
 	tfcp_req->aborted = true;
-	spin_unlock_irq(&tfcp_req->reqlock);
+	spin_unlock_irqrestore(&tfcp_req->reqlock, flags);
 
 	tfcp_req->status = NVME_SC_INTERNAL;
 
@@ -946,6 +951,7 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport,
 	struct fcloop_ini_fcpreq *inireq = fcpreq->private;
 	struct fcloop_fcpreq *tfcp_req;
 	bool abortio = true;
+	unsigned long flags;
 
 	spin_lock(&inireq->inilock);
 	tfcp_req = inireq->tfcp_req;
@@ -958,7 +964,7 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport,
 		return;
 
 	/* break initiator/target relationship for io */
-	spin_lock_irq(&tfcp_req->reqlock);
+	spin_lock_irqsave(&tfcp_req->reqlock, flags);
 	switch (tfcp_req->inistate) {
 	case INI_IO_START:
 	case INI_IO_ACTIVE:
@@ -968,11 +974,11 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport,
 		abortio = false;
 		break;
 	default:
-		spin_unlock_irq(&tfcp_req->reqlock);
+		spin_unlock_irqrestore(&tfcp_req->reqlock, flags);
 		WARN_ON(1);
 		return;
 	}
-	spin_unlock_irq(&tfcp_req->reqlock);
+	spin_unlock_irqrestore(&tfcp_req->reqlock, flags);
 
 	if (abortio)
 		/* leave the reference while the work item is scheduled */
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 89bedfcd974c..dc60a22646f7 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -581,8 +581,8 @@ bool nvmet_ns_revalidate(struct nvmet_ns *ns);
 u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts);
 
 bool nvmet_bdev_zns_enable(struct nvmet_ns *ns);
-void nvmet_execute_identify_cns_cs_ctrl(struct nvmet_req *req);
-void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req);
+void nvmet_execute_identify_ctrl_zns(struct nvmet_req *req);
+void nvmet_execute_identify_ns_zns(struct nvmet_req *req);
 void nvmet_bdev_execute_zone_mgmt_recv(struct nvmet_req *req);
 void nvmet_bdev_execute_zone_mgmt_send(struct nvmet_req *req);
 void nvmet_bdev_execute_zone_append(struct nvmet_req *req);
@@ -687,14 +687,6 @@ static inline bool nvmet_use_inline_bvec(struct nvmet_req *req)
 	       req->sg_cnt <= NVMET_MAX_INLINE_BIOVEC;
 }
 
-static inline void nvmet_req_cns_error_complete(struct nvmet_req *req)
-{
-	pr_debug("unhandled identify cns %d on qid %d\n",
-	       req->cmd->identify.cns, req->sq->qid);
-	req->error_loc = offsetof(struct nvme_identify, cns);
-	nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
-}
-
 static inline void nvmet_req_bio_put(struct nvmet_req *req, struct bio *bio)
 {
 	if (bio != &req->b.inline_bio)
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 66e8f9fd0ca7..ed98df72c76b 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -20,6 +20,31 @@
 
 #define NVMET_TCP_DEF_INLINE_DATA_SIZE	(4 * PAGE_SIZE)
 
+static int param_store_val(const char *str, int *val, int min, int max)
+{
+	int ret, new_val;
+
+	ret = kstrtoint(str, 10, &new_val);
+	if (ret)
+		return -EINVAL;
+
+	if (new_val < min || new_val > max)
+		return -EINVAL;
+
+	*val = new_val;
+	return 0;
+}
+
+static int set_params(const char *str, const struct kernel_param *kp)
+{
+	return param_store_val(str, kp->arg, 0, INT_MAX);
+}
+
+static const struct kernel_param_ops set_param_ops = {
+	.set	= set_params,
+	.get	= param_get_int,
+};
+
 /* Define the socket priority to use for connections were it is desirable
  * that the NIC consider performing optimized packet processing or filtering.
  * A non-zero value being sufficient to indicate general consideration of any
@@ -27,8 +52,8 @@
  * values that may be unique for some NIC implementations.
  */
 static int so_priority;
-module_param(so_priority, int, 0644);
-MODULE_PARM_DESC(so_priority, "nvmet tcp socket optimize priority");
+device_param_cb(so_priority, &set_param_ops, &so_priority, 0644);
+MODULE_PARM_DESC(so_priority, "nvmet tcp socket optimize priority: Default 0");
 
 /* Define a time period (in usecs) that io_work() shall sample an activated
  * queue before determining it to be idle.  This optional module behavior
@@ -36,9 +61,10 @@ MODULE_PARM_DESC(so_priority, "nvmet tcp socket optimize priority");
  * using advanced interrupt moderation techniques.
  */
 static int idle_poll_period_usecs;
-module_param(idle_poll_period_usecs, int, 0644);
+device_param_cb(idle_poll_period_usecs, &set_param_ops,
+		&idle_poll_period_usecs, 0644);
 MODULE_PARM_DESC(idle_poll_period_usecs,
-		"nvmet tcp io_work poll till idle time period in usecs");
+		"nvmet tcp io_work poll till idle time period in usecs: Default 0");
 
 #define NVMET_TCP_RECV_BUDGET		8
 #define NVMET_TCP_SEND_BUDGET		8
diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c
index 7e4292d88016..5b5c1e481722 100644
--- a/drivers/nvme/target/zns.c
+++ b/drivers/nvme/target/zns.c
@@ -70,7 +70,7 @@ bool nvmet_bdev_zns_enable(struct nvmet_ns *ns)
 	return true;
 }
 
-void nvmet_execute_identify_cns_cs_ctrl(struct nvmet_req *req)
+void nvmet_execute_identify_ctrl_zns(struct nvmet_req *req)
 {
 	u8 zasl = req->sq->ctrl->subsys->zasl;
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -95,9 +95,9 @@ out:
 	nvmet_req_complete(req, status);
 }
 
-void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req)
+void nvmet_execute_identify_ns_zns(struct nvmet_req *req)
 {
-	struct nvme_id_ns_zns *id_zns;
+	struct nvme_id_ns_zns *id_zns = NULL;
 	u64 zsze;
 	u16 status;
 	u32 mar, mor;
@@ -118,16 +118,18 @@ void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req)
 	if (status)
 		goto done;
 
-	if (!bdev_is_zoned(req->ns->bdev)) {
-		req->error_loc = offsetof(struct nvme_identify, nsid);
-		goto done;
-	}
-
 	if (nvmet_ns_revalidate(req->ns)) {
 		mutex_lock(&req->ns->subsys->lock);
 		nvmet_ns_changed(req->ns->subsys, req->ns->nsid);
 		mutex_unlock(&req->ns->subsys->lock);
 	}
+
+	if (!bdev_is_zoned(req->ns->bdev)) {
+		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		req->error_loc = offsetof(struct nvme_identify, nsid);
+		goto out;
+	}
+
 	zsze = (bdev_zone_sectors(req->ns->bdev) << 9) >>
 					req->ns->blksize_shift;
 	id_zns->lbafe[0].zsze = cpu_to_le64(zsze);
@@ -148,8 +150,8 @@ void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req)
 
 done:
 	status = nvmet_copy_to_sgl(req, 0, id_zns, sizeof(*id_zns));
-	kfree(id_zns);
 out:
+	kfree(id_zns);
 	nvmet_req_complete(req, status);
 }