Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi

Pull more SCSI updates from James Bottomley:
 "Mostly small bug fixes and trivial updates.

  The major new core update is a change to the way device, target and
  host reference counting is done to try to make it more robust (this
  change has soaked for a while to try to winkle out any bugs)"

* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi:
  scsi: pm8001: Fix typo 'the the' in comment
  scsi: megaraid_sas: Remove redundant variable cmd_type
  scsi: FlashPoint: Remove redundant variable bm_int_st
  scsi: zfcp: Fix missing auto port scan and thus missing target ports
  scsi: core: Call blk_mq_free_tag_set() earlier
  scsi: core: Simplify LLD module reference counting
  scsi: core: Make sure that hosts outlive targets
  scsi: core: Make sure that targets outlive devices
  scsi: ufs: ufs-pci: Correct check for RESET DSM
  scsi: target: core: De-RCU of se_lun and se_lun acl
  scsi: target: core: Fix race during ACL removal
  scsi: ufs: core: Correct ufshcd_shutdown() flow
  scsi: ufs: core: Increase the maximum data buffer size
  scsi: lpfc: Check the return value of alloc_workqueue()

21 files changed, 124 insertions, 99 deletions

diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c
index 511bf8e0a436..b61acbb09be3 100644
--- a/drivers/s390/scsi/zfcp_fc.c
+++ b/drivers/s390/scsi/zfcp_fc.c
@@ -145,27 +145,33 @@ void zfcp_fc_enqueue_event(struct zfcp_adapter *adapter,
 
 static int zfcp_fc_wka_port_get(struct zfcp_fc_wka_port *wka_port)
 {
+	int ret = -EIO;
+
 	if (mutex_lock_interruptible(&wka_port->mutex))
 		return -ERESTARTSYS;
 
 	if (wka_port->status == ZFCP_FC_WKA_PORT_OFFLINE ||
 	    wka_port->status == ZFCP_FC_WKA_PORT_CLOSING) {
 		wka_port->status = ZFCP_FC_WKA_PORT_OPENING;
-		if (zfcp_fsf_open_wka_port(wka_port))
+		if (zfcp_fsf_open_wka_port(wka_port)) {
+			/* could not even send request, nothing to wait for */
 			wka_port->status = ZFCP_FC_WKA_PORT_OFFLINE;
+			goto out;
+		}
 	}
 
-	mutex_unlock(&wka_port->mutex);
-
-	wait_event(wka_port->completion_wq,
+	wait_event(wka_port->opened,
 		   wka_port->status == ZFCP_FC_WKA_PORT_ONLINE ||
 		   wka_port->status == ZFCP_FC_WKA_PORT_OFFLINE);
 
 	if (wka_port->status == ZFCP_FC_WKA_PORT_ONLINE) {
 		atomic_inc(&wka_port->refcount);
-		return 0;
+		ret = 0;
+		goto out;
 	}
-	return -EIO;
+out:
+	mutex_unlock(&wka_port->mutex);
+	return ret;
 }
 
 static void zfcp_fc_wka_port_offline(struct work_struct *work)
@@ -181,9 +187,12 @@ static void zfcp_fc_wka_port_offline(struct work_struct *work)
 
 	wka_port->status = ZFCP_FC_WKA_PORT_CLOSING;
 	if (zfcp_fsf_close_wka_port(wka_port)) {
+		/* could not even send request, nothing to wait for */
 		wka_port->status = ZFCP_FC_WKA_PORT_OFFLINE;
-		wake_up(&wka_port->completion_wq);
+		goto out;
 	}
+	wait_event(wka_port->closed,
+		   wka_port->status == ZFCP_FC_WKA_PORT_OFFLINE);
 out:
 	mutex_unlock(&wka_port->mutex);
 }
@@ -193,13 +202,15 @@ static void zfcp_fc_wka_port_put(struct zfcp_fc_wka_port *wka_port)
 	if (atomic_dec_return(&wka_port->refcount) != 0)
 		return;
 	/* wait 10 milliseconds, other reqs might pop in */
-	schedule_delayed_work(&wka_port->work, HZ / 100);
+	queue_delayed_work(wka_port->adapter->work_queue, &wka_port->work,
+			   msecs_to_jiffies(10));
 }
 
 static void zfcp_fc_wka_port_init(struct zfcp_fc_wka_port *wka_port, u32 d_id,
 				  struct zfcp_adapter *adapter)
 {
-	init_waitqueue_head(&wka_port->completion_wq);
+	init_waitqueue_head(&wka_port->opened);
+	init_waitqueue_head(&wka_port->closed);
 
 	wka_port->adapter = adapter;
 	wka_port->d_id = d_id;
diff --git a/drivers/s390/scsi/zfcp_fc.h b/drivers/s390/scsi/zfcp_fc.h
index 8aaf409ce9cb..97755407ce1b 100644
--- a/drivers/s390/scsi/zfcp_fc.h
+++ b/drivers/s390/scsi/zfcp_fc.h
@@ -185,7 +185,8 @@ enum zfcp_fc_wka_status {
 /**
  * struct zfcp_fc_wka_port - representation of well-known-address (WKA) FC port
  * @adapter: Pointer to adapter structure this WKA port belongs to
- * @completion_wq: Wait for completion of open/close command
+ * @opened: Wait for completion of open command
+ * @closed: Wait for completion of close command
  * @status: Current status of WKA port
  * @refcount: Reference count to keep port open as long as it is in use
  * @d_id: FC destination id or well-known-address
@@ -195,7 +196,8 @@ enum zfcp_fc_wka_status {
  */
 struct zfcp_fc_wka_port {
 	struct zfcp_adapter	*adapter;
-	wait_queue_head_t	completion_wq;
+	wait_queue_head_t	opened;
+	wait_queue_head_t	closed;
 	enum zfcp_fc_wka_status	status;
 	atomic_t		refcount;
 	u32			d_id;
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index 4f1e4385ce58..19223b075568 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -1907,7 +1907,7 @@ static void zfcp_fsf_open_wka_port_handler(struct zfcp_fsf_req *req)
 		wka_port->status = ZFCP_FC_WKA_PORT_ONLINE;
 	}
 out:
-	wake_up(&wka_port->completion_wq);
+	wake_up(&wka_port->opened);
 }
 
 /**
@@ -1966,7 +1966,7 @@ static void zfcp_fsf_close_wka_port_handler(struct zfcp_fsf_req *req)
 	}
 
 	wka_port->status = ZFCP_FC_WKA_PORT_OFFLINE;
-	wake_up(&wka_port->completion_wq);
+	wake_up(&wka_port->closed);
 }
 
 /**
diff --git a/drivers/scsi/FlashPoint.c b/drivers/scsi/FlashPoint.c
index 90253208a72f..3d9c56ac8224 100644
--- a/drivers/scsi/FlashPoint.c
+++ b/drivers/scsi/FlashPoint.c
@@ -1712,7 +1712,7 @@ static unsigned char FlashPoint_InterruptPending(void *pCurrCard)
 static int FlashPoint_HandleInterrupt(void *pcard)
 {
 	struct sccb *currSCCB;
-	unsigned char thisCard, result, bm_status, bm_int_st;
+	unsigned char thisCard, result, bm_status;
 	unsigned short hp_int;
 	unsigned char i, target;
 	struct sccb_card *pCurrCard = pcard;
@@ -1723,7 +1723,7 @@ static int FlashPoint_HandleInterrupt(void *pcard)
 
 	MDISABLE_INT(ioport);
 
-	if ((bm_int_st = RD_HARPOON(ioport + hp_int_status)) & EXT_STATUS_ON)
+	if (RD_HARPOON(ioport + hp_int_status) & EXT_STATUS_ON)
 		bm_status = RD_HARPOON(ioport + hp_ext_status) &
 					(unsigned char)BAD_EXT_STATUS;
 	else
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 26bf3b153595..0738238ed6cc 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -190,6 +190,15 @@ void scsi_remove_host(struct Scsi_Host *shost)
 	transport_unregister_device(&shost->shost_gendev);
 	device_unregister(&shost->shost_dev);
 	device_del(&shost->shost_gendev);
+
+	/*
+	 * After scsi_remove_host() has returned the scsi LLD module can be
+	 * unloaded and/or the host resources can be released. Hence wait until
+	 * the dependent SCSI targets and devices are gone before returning.
+	 */
+	wait_event(shost->targets_wq, atomic_read(&shost->target_count) == 0);
+
+	scsi_mq_destroy_tags(shost);
 }
 EXPORT_SYMBOL(scsi_remove_host);
 
@@ -300,8 +309,8 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 	return error;
 
 	/*
-	 * Any host allocation in this function will be freed in
-	 * scsi_host_dev_release().
+	 * Any resources associated with the SCSI host in this function except
+	 * the tag set will be freed by scsi_host_dev_release().
 	 */
  out_del_dev:
 	device_del(&shost->shost_dev);
@@ -317,6 +326,7 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 	pm_runtime_disable(&shost->shost_gendev);
 	pm_runtime_set_suspended(&shost->shost_gendev);
 	pm_runtime_put_noidle(&shost->shost_gendev);
+	scsi_mq_destroy_tags(shost);
  fail:
 	return error;
 }
@@ -350,9 +360,6 @@ static void scsi_host_dev_release(struct device *dev)
 		kfree(dev_name(&shost->shost_dev));
 	}
 
-	if (shost->tag_set.tags)
-		scsi_mq_destroy_tags(shost);
-
 	kfree(shost->shost_data);
 
 	ida_free(&host_index_ida, shost->host_no);
@@ -399,6 +406,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 	INIT_LIST_HEAD(&shost->starved_list);
 	init_waitqueue_head(&shost->host_wait);
 	mutex_init(&shost->scan_mutex);
+	init_waitqueue_head(&shost->targets_wq);
 
 	index = ida_alloc(&host_index_ida, GFP_KERNEL);
 	if (index < 0) {
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 4a0eadd1c22c..c69c5a0979ec 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -7948,6 +7948,8 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 
 	/* The lpfc_wq workqueue for deferred irq use */
 	phba->wq = alloc_workqueue("lpfc_wq", WQ_MEM_RECLAIM, 0);
+	if (!phba->wq)
+		return -ENOMEM;
 
 	/*
 	 * Initialize timers used by driver
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 5b5885d9732b..e48d4261d0bc 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -3199,7 +3199,6 @@ megasas_build_io_fusion(struct megasas_instance *instance,
 			struct megasas_cmd_fusion *cmd)
 {
 	int sge_count;
-	u8  cmd_type;
 	u16 pd_index = 0;
 	u8 drive_type = 0;
 	struct MPI2_RAID_SCSI_IO_REQUEST *io_request = cmd->io_request;
@@ -3225,7 +3224,7 @@ megasas_build_io_fusion(struct megasas_instance *instance,
 	 */
 	io_request->IoFlags = cpu_to_le16(scp->cmd_len);
 
-	switch (cmd_type = megasas_cmd_type(scp)) {
+	switch (megasas_cmd_type(scp)) {
 	case READ_WRITE_LDIO:
 		megasas_build_ldio_fusion(instance, scp, cmd);
 		break;
diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c
index 4acaff479916..91d78d0a38fe 100644
--- a/drivers/scsi/pm8001/pm8001_hwi.c
+++ b/drivers/scsi/pm8001/pm8001_hwi.c
@@ -3138,7 +3138,7 @@ int pm8001_mpi_local_phy_ctl(struct pm8001_hba_info *pm8001_ha, void *piomb)
  *
  * when HBA driver received the identify done event or initiate FIS received
  * event(for SATA), it will invoke this function to notify the sas layer that
- * the sas toplogy has formed, please discover the the whole sas domain,
+ * the sas toplogy has formed, please discover the whole sas domain,
  * while receive a broadcast(change) primitive just tell the sas
  * layer to discover the changed domain rather than the whole domain.
  */
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index c59eac7a32f2..086ec5b5862d 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -586,10 +586,13 @@ EXPORT_SYMBOL(scsi_device_get);
  */
 void scsi_device_put(struct scsi_device *sdev)
 {
-	struct module *mod = sdev->host->hostt->module;
-
+	/*
+	 * Decreasing the module reference count before the device reference
+	 * count is safe since scsi_remove_host() only returns after all
+	 * devices have been removed.
+	 */
+	module_put(sdev->host->hostt->module);
 	put_device(&sdev->sdev_gendev);
-	module_put(mod);
 }
 EXPORT_SYMBOL(scsi_device_put);
 
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 91ac901a6682..ac6059702d13 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -406,9 +406,14 @@ static void scsi_target_destroy(struct scsi_target *starget)
 static void scsi_target_dev_release(struct device *dev)
 {
 	struct device *parent = dev->parent;
+	struct Scsi_Host *shost = dev_to_shost(parent);
 	struct scsi_target *starget = to_scsi_target(dev);
 
 	kfree(starget);
+
+	if (atomic_dec_return(&shost->target_count) == 0)
+		wake_up(&shost->targets_wq);
+
 	put_device(parent);
 }
 
@@ -521,6 +526,10 @@ static struct scsi_target *scsi_alloc_target(struct device *parent,
 	starget->state = STARGET_CREATED;
 	starget->scsi_level = SCSI_2;
 	starget->max_target_blocked = SCSI_DEFAULT_TARGET_BLOCKED;
+	init_waitqueue_head(&starget->sdev_wq);
+
+	atomic_inc(&shost->target_count);
+
  retry:
 	spin_lock_irqsave(shost->host_lock, flags);
 
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index aa70d9282161..9dad2fd5297f 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -443,18 +443,15 @@ static void scsi_device_cls_release(struct device *class_dev)
 
 static void scsi_device_dev_release_usercontext(struct work_struct *work)
 {
-	struct scsi_device *sdev;
+	struct scsi_device *sdev = container_of(work, struct scsi_device,
+						ew.work);
+	struct scsi_target *starget = sdev->sdev_target;
 	struct device *parent;
 	struct list_head *this, *tmp;
 	struct scsi_vpd *vpd_pg80 = NULL, *vpd_pg83 = NULL;
 	struct scsi_vpd *vpd_pg0 = NULL, *vpd_pg89 = NULL;
 	struct scsi_vpd *vpd_pgb0 = NULL, *vpd_pgb1 = NULL, *vpd_pgb2 = NULL;
 	unsigned long flags;
-	struct module *mod;
-
-	sdev = container_of(work, struct scsi_device, ew.work);
-
-	mod = sdev->host->hostt->module;
 
 	scsi_dh_release_device(sdev);
 
@@ -516,19 +513,16 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)
 	kfree(sdev->inquiry);
 	kfree(sdev);
 
+	if (starget && atomic_dec_return(&starget->sdev_count) == 0)
+		wake_up(&starget->sdev_wq);
+
 	if (parent)
 		put_device(parent);
-	module_put(mod);
 }
 
 static void scsi_device_dev_release(struct device *dev)
 {
 	struct scsi_device *sdp = to_scsi_device(dev);
-
-	/* Set module pointer as NULL in case of module unloading */
-	if (!try_module_get(sdp->host->hostt->module))
-		sdp->host->hostt->module = NULL;
-
 	execute_in_process_context(scsi_device_dev_release_usercontext,
 				   &sdp->ew);
 }
@@ -1535,6 +1529,14 @@ static void __scsi_remove_target(struct scsi_target *starget)
 		goto restart;
 	}
 	spin_unlock_irqrestore(shost->host_lock, flags);
+
+	/*
+	 * After scsi_remove_target() returns its caller can remove resources
+	 * associated with @starget, e.g. an rport or session. Wait until all
+	 * devices associated with @starget have been removed to prevent that
+	 * a SCSI error handling callback function triggers a use-after-free.
+	 */
+	wait_event(starget->sdev_wq, atomic_read(&starget->sdev_count) == 0);
 }
 
 /**
@@ -1645,6 +1647,9 @@ void scsi_sysfs_device_initialize(struct scsi_device *sdev)
 	list_add_tail(&sdev->same_target_siblings, &starget->devices);
 	list_add_tail(&sdev->siblings, &shost->__devices);
 	spin_unlock_irqrestore(shost->host_lock, flags);
+
+	atomic_inc(&starget->sdev_count);
+
 	/*
 	 * device can now only be removed via __scsi_remove_device() so hold
 	 * the target.  Target will be held in CREATED state until something
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index 58df0145e8d0..fb91423a4e2e 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -934,8 +934,7 @@ static void core_alua_queue_state_change_ua(struct t10_alua_tg_pt_gp *tg_pt_gp)
 
 		spin_lock(&lun->lun_deve_lock);
 		list_for_each_entry(se_deve, &lun->lun_deve_list, lun_link) {
-			lacl = rcu_dereference_check(se_deve->se_lun_acl,
-					lockdep_is_held(&lun->lun_deve_lock));
+			lacl = se_deve->se_lun_acl;
 
 			/*
 			 * spc4r37 p.242:
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 086ac9c9343c..b7f16ee8aa0e 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -75,7 +75,7 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd)
 			return TCM_WRITE_PROTECTED;
 		}
 
-		se_lun = rcu_dereference(deve->se_lun);
+		se_lun = deve->se_lun;
 
 		if (!percpu_ref_tryget_live(&se_lun->lun_ref)) {
 			se_lun = NULL;
@@ -152,7 +152,7 @@ int transport_lookup_tmr_lun(struct se_cmd *se_cmd)
 	rcu_read_lock();
 	deve = target_nacl_find_deve(nacl, se_cmd->orig_fe_lun);
 	if (deve) {
-		se_lun = rcu_dereference(deve->se_lun);
+		se_lun = deve->se_lun;
 
 		if (!percpu_ref_tryget_live(&se_lun->lun_ref)) {
 			se_lun = NULL;
@@ -216,7 +216,7 @@ struct se_dev_entry *core_get_se_deve_from_rtpi(
 
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(deve, &nacl->lun_entry_hlist, link) {
-		lun = rcu_dereference(deve->se_lun);
+		lun = deve->se_lun;
 		if (!lun) {
 			pr_err("%s device entries device pointer is"
 				" NULL, but Initiator has access.\n",
@@ -243,11 +243,8 @@ void core_free_device_list_for_node(
 	struct se_dev_entry *deve;
 
 	mutex_lock(&nacl->lun_entry_mutex);
-	hlist_for_each_entry_rcu(deve, &nacl->lun_entry_hlist, link) {
-		struct se_lun *lun = rcu_dereference_check(deve->se_lun,
-					lockdep_is_held(&nacl->lun_entry_mutex));
-		core_disable_device_list_for_node(lun, deve, nacl, tpg);
-	}
+	hlist_for_each_entry_rcu(deve, &nacl->lun_entry_hlist, link)
+		core_disable_device_list_for_node(deve->se_lun, deve, nacl, tpg);
 	mutex_unlock(&nacl->lun_entry_mutex);
 }
 
@@ -334,8 +331,7 @@ int core_enable_device_list_for_node(
 	mutex_lock(&nacl->lun_entry_mutex);
 	orig = target_nacl_find_deve(nacl, mapped_lun);
 	if (orig && orig->se_lun) {
-		struct se_lun *orig_lun = rcu_dereference_check(orig->se_lun,
-					lockdep_is_held(&nacl->lun_entry_mutex));
+		struct se_lun *orig_lun = orig->se_lun;
 
 		if (orig_lun != lun) {
 			pr_err("Existing orig->se_lun doesn't match new lun"
@@ -355,8 +351,8 @@ int core_enable_device_list_for_node(
 			return -EINVAL;
 		}
 
-		rcu_assign_pointer(new->se_lun, lun);
-		rcu_assign_pointer(new->se_lun_acl, lun_acl);
+		new->se_lun = lun;
+		new->se_lun_acl = lun_acl;
 		hlist_del_rcu(&orig->link);
 		hlist_add_head_rcu(&new->link, &nacl->lun_entry_hlist);
 		mutex_unlock(&nacl->lun_entry_mutex);
@@ -374,8 +370,8 @@ int core_enable_device_list_for_node(
 		return 0;
 	}
 
-	rcu_assign_pointer(new->se_lun, lun);
-	rcu_assign_pointer(new->se_lun_acl, lun_acl);
+	new->se_lun = lun;
+	new->se_lun_acl = lun_acl;
 	hlist_add_head_rcu(&new->link, &nacl->lun_entry_hlist);
 	mutex_unlock(&nacl->lun_entry_mutex);
 
@@ -434,9 +430,6 @@ void core_disable_device_list_for_node(
 	kref_put(&orig->pr_kref, target_pr_kref_release);
 	wait_for_completion(&orig->pr_comp);
 
-	rcu_assign_pointer(orig->se_lun, NULL);
-	rcu_assign_pointer(orig->se_lun_acl, NULL);
-
 	kfree_rcu(orig, rcu_head);
 
 	core_scsi3_free_pr_reg_from_nacl(dev, nacl);
@@ -457,10 +450,7 @@ void core_clear_lun_from_tpg(struct se_lun *lun, struct se_portal_group *tpg)
 
 		mutex_lock(&nacl->lun_entry_mutex);
 		hlist_for_each_entry_rcu(deve, &nacl->lun_entry_hlist, link) {
-			struct se_lun *tmp_lun = rcu_dereference_check(deve->se_lun,
-					lockdep_is_held(&nacl->lun_entry_mutex));
-
-			if (lun != tmp_lun)
+			if (lun != deve->se_lun)
 				continue;
 
 			core_disable_device_list_for_node(lun, deve, nacl, tpg);
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 3829b61b56c1..a1d67554709f 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -739,8 +739,7 @@ static struct t10_pr_registration *__core_scsi3_alloc_registration(
 			if (!deve_tmp->se_lun_acl)
 				continue;
 
-			lacl_tmp = rcu_dereference_check(deve_tmp->se_lun_acl,
-						lockdep_is_held(&lun_tmp->lun_deve_lock));
+			lacl_tmp = deve_tmp->se_lun_acl;
 			nacl_tmp = lacl_tmp->se_lun_nacl;
 			/*
 			 * Skip the matching struct se_node_acl that is allocated
@@ -784,8 +783,7 @@ static struct t10_pr_registration *__core_scsi3_alloc_registration(
 			 * the original *pr_reg is processed in
 			 * __core_scsi3_add_registration()
 			 */
-			dest_lun = rcu_dereference_check(deve_tmp->se_lun,
-				kref_read(&deve_tmp->pr_kref) != 0);
+			dest_lun = deve_tmp->se_lun;
 
 			pr_reg_atp = __core_scsi3_do_alloc_registration(dev,
 						nacl_tmp, dest_lun, deve_tmp,
@@ -1437,34 +1435,26 @@ static void core_scsi3_nodeacl_undepend_item(struct se_node_acl *nacl)
 
 static int core_scsi3_lunacl_depend_item(struct se_dev_entry *se_deve)
 {
-	struct se_lun_acl *lun_acl;
-
 	/*
 	 * For nacl->dynamic_node_acl=1
 	 */
-	lun_acl = rcu_dereference_check(se_deve->se_lun_acl,
-				kref_read(&se_deve->pr_kref) != 0);
-	if (!lun_acl)
+	if (!se_deve->se_lun_acl)
 		return 0;
 
-	return target_depend_item(&lun_acl->se_lun_group.cg_item);
+	return target_depend_item(&se_deve->se_lun_acl->se_lun_group.cg_item);
 }
 
 static void core_scsi3_lunacl_undepend_item(struct se_dev_entry *se_deve)
 {
-	struct se_lun_acl *lun_acl;
-
 	/*
 	 * For nacl->dynamic_node_acl=1
 	 */
-	lun_acl = rcu_dereference_check(se_deve->se_lun_acl,
-				kref_read(&se_deve->pr_kref) != 0);
-	if (!lun_acl) {
+	if (!se_deve->se_lun_acl) {
 		kref_put(&se_deve->pr_kref, target_pr_kref_release);
 		return;
 	}
 
-	target_undepend_item(&lun_acl->se_lun_group.cg_item);
+	target_undepend_item(&se_deve->se_lun_acl->se_lun_group.cg_item);
 	kref_put(&se_deve->pr_kref, target_pr_kref_release);
 }
 
@@ -1751,8 +1741,7 @@ core_scsi3_decode_spec_i_port(
 		 * and then call __core_scsi3_add_registration() in the
 		 * 2nd loop which will never fail.
 		 */
-		dest_lun = rcu_dereference_check(dest_se_deve->se_lun,
-				kref_read(&dest_se_deve->pr_kref) != 0);
+		dest_lun = dest_se_deve->se_lun;
 
 		dest_pr_reg = __core_scsi3_alloc_registration(cmd->se_dev,
 					dest_node_acl, dest_lun, dest_se_deve,
@@ -3446,8 +3435,7 @@ after_iport_check:
 	dest_pr_reg = __core_scsi3_locate_pr_reg(dev, dest_node_acl,
 					iport_ptr);
 	if (!dest_pr_reg) {
-		struct se_lun *dest_lun = rcu_dereference_check(dest_se_deve->se_lun,
-				kref_read(&dest_se_deve->pr_kref) != 0);
+		struct se_lun *dest_lun = dest_se_deve->se_lun;
 
 		spin_unlock(&dev->dev_reservation_lock);
 		if (core_scsi3_alloc_registration(cmd->se_dev, dest_node_acl,
diff --git a/drivers/target/target_core_stat.c b/drivers/target/target_core_stat.c
index 62d15bcc3d93..f85ee5b0fd80 100644
--- a/drivers/target/target_core_stat.c
+++ b/drivers/target/target_core_stat.c
@@ -877,7 +877,6 @@ static ssize_t target_stat_auth_dev_show(struct config_item *item,
 	struct se_lun_acl *lacl = auth_to_lacl(item);
 	struct se_node_acl *nacl = lacl->se_lun_nacl;
 	struct se_dev_entry *deve;
-	struct se_lun *lun;
 	ssize_t ret;
 
 	rcu_read_lock();
@@ -886,9 +885,9 @@ static ssize_t target_stat_auth_dev_show(struct config_item *item,
 		rcu_read_unlock();
 		return -ENODEV;
 	}
-	lun = rcu_dereference(deve->se_lun);
+
 	/* scsiDeviceIndex */
-	ret = snprintf(page, PAGE_SIZE, "%u\n", lun->lun_index);
+	ret = snprintf(page, PAGE_SIZE, "%u\n", deve->se_lun->lun_index);
 	rcu_read_unlock();
 	return ret;
 }
@@ -1217,7 +1216,6 @@ static ssize_t target_stat_iport_dev_show(struct config_item *item,
 	struct se_lun_acl *lacl = iport_to_lacl(item);
 	struct se_node_acl *nacl = lacl->se_lun_nacl;
 	struct se_dev_entry *deve;
-	struct se_lun *lun;
 	ssize_t ret;
 
 	rcu_read_lock();
@@ -1226,9 +1224,9 @@ static ssize_t target_stat_iport_dev_show(struct config_item *item,
 		rcu_read_unlock();
 		return -ENODEV;
 	}
-	lun = rcu_dereference(deve->se_lun);
+
 	/* scsiDeviceIndex */
-	ret = snprintf(page, PAGE_SIZE, "%u\n", lun->lun_index);
+	ret = snprintf(page, PAGE_SIZE, "%u\n", deve->se_lun->lun_index);
 	rcu_read_unlock();
 	return ret;
 }
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 6bb20aa9c5bc..8713cda0c2fb 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -88,7 +88,7 @@ static int target_xcopy_locate_se_dev_e4(struct se_session *sess,
 		struct se_device *this_dev;
 		int rc;
 
-		this_lun = rcu_dereference(deve->se_lun);
+		this_lun = deve->se_lun;
 		this_dev = rcu_dereference_raw(this_lun->lun_se_dev);
 
 		rc = target_xcopy_locate_se_dev_e4_iter(this_dev, dev_wwn);
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 3bc0709a5dc2..6bc679d22927 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -8326,6 +8326,7 @@ static struct scsi_host_template ufshcd_driver_template = {
 	.cmd_per_lun		= UFSHCD_CMD_PER_LUN,
 	.can_queue		= UFSHCD_CAN_QUEUE,
 	.max_segment_size	= PRDT_DATA_BYTE_COUNT_MAX,
+	.max_sectors		= (1 << 20) / SECTOR_SIZE, /* 1 MiB */
 	.max_host_blocked	= 1,
 	.track_queue_depth	= 1,
 	.sdev_groups		= ufshcd_driver_groups,
@@ -9508,12 +9509,8 @@ EXPORT_SYMBOL(ufshcd_runtime_resume);
 int ufshcd_shutdown(struct ufs_hba *hba)
 {
 	if (ufshcd_is_ufs_dev_poweroff(hba) && ufshcd_is_link_off(hba))
-		goto out;
-
-	pm_runtime_get_sync(hba->dev);
+		ufshcd_suspend(hba);
 
-	ufshcd_suspend(hba);
-out:
 	hba->is_powered = false;
 	/* allow force shutdown even in case of errors */
 	return 0;
diff --git a/drivers/ufs/host/ufshcd-pci.c b/drivers/ufs/host/ufshcd-pci.c
index 24af1f389bf2..1c91f43e15c8 100644
--- a/drivers/ufs/host/ufshcd-pci.c
+++ b/drivers/ufs/host/ufshcd-pci.c
@@ -24,7 +24,7 @@ struct ufs_host {
 	void (*late_init)(struct ufs_hba *hba);
 };
 
-enum {
+enum intel_ufs_dsm_func_id {
 	INTEL_DSM_FNS		=  0,
 	INTEL_DSM_RESET		=  1,
 };
@@ -42,6 +42,15 @@ static const guid_t intel_dsm_guid =
 	GUID_INIT(0x1A4832A0, 0x7D03, 0x43CA,
 		  0xB0, 0x20, 0xF6, 0xDC, 0xD1, 0x2A, 0x19, 0x50);
 
+static bool __intel_dsm_supported(struct intel_host *host,
+				  enum intel_ufs_dsm_func_id fn)
+{
+	return fn < 32 && fn >= 0 && (host->dsm_fns & (1u << fn));
+}
+
+#define INTEL_DSM_SUPPORTED(host, name) \
+	__intel_dsm_supported(host, INTEL_DSM_##name)
+
 static int __intel_dsm(struct intel_host *intel_host, struct device *dev,
 		       unsigned int fn, u32 *result)
 {
@@ -71,7 +80,7 @@ out:
 static int intel_dsm(struct intel_host *intel_host, struct device *dev,
 		     unsigned int fn, u32 *result)
 {
-	if (fn > 31 || !(intel_host->dsm_fns & (1 << fn)))
+	if (!__intel_dsm_supported(intel_host, fn))
 		return -EOPNOTSUPP;
 
 	return __intel_dsm(intel_host, dev, fn, result);
@@ -300,7 +309,7 @@ static int ufs_intel_device_reset(struct ufs_hba *hba)
 {
 	struct intel_host *host = ufshcd_get_variant(hba);
 
-	if (host->dsm_fns & INTEL_DSM_RESET) {
+	if (INTEL_DSM_SUPPORTED(host, RESET)) {
 		u32 result = 0;
 		int err;
 
@@ -342,7 +351,7 @@ static int ufs_intel_common_init(struct ufs_hba *hba)
 		return -ENOMEM;
 	ufshcd_set_variant(hba, host);
 	intel_dsm_init(host, hba->dev);
-	if (host->dsm_fns & INTEL_DSM_RESET) {
+	if (INTEL_DSM_SUPPORTED(host, RESET)) {
 		if (hba->vops->device_reset)
 			hba->caps |= UFSHCD_CAP_DEEPSLEEP;
 	} else {
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 2493bd65351a..3113471ca375 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -309,6 +309,8 @@ struct scsi_target {
 	struct list_head	devices;
 	struct device		dev;
 	struct kref		reap_ref; /* last put renders target invisible */
+	atomic_t		sdev_count;
+	wait_queue_head_t	sdev_wq;
 	unsigned int		channel;
 	unsigned int		id; /* target id ... replace
 				     * scsi_device.id eventually */
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index b6e41ee3d566..aa7b7496c93a 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -690,6 +690,9 @@ struct Scsi_Host {
 	/* ldm bits */
 	struct device		shost_gendev, shost_dev;
 
+	atomic_t		target_count;
+	wait_queue_head_t	targets_wq;
+
 	/*
 	 * Points to the transport data (if any) which is allocated
 	 * separately
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index c2b36f7d917d..8c920456edd9 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -665,9 +665,9 @@ struct se_dev_entry {
 	/* Used for PR SPEC_I_PT=1 and REGISTER_AND_MOVE */
 	struct kref		pr_kref;
 	struct completion	pr_comp;
-	struct se_lun_acl __rcu	*se_lun_acl;
+	struct se_lun_acl	*se_lun_acl;
 	spinlock_t		ua_lock;
-	struct se_lun __rcu	*se_lun;
+	struct se_lun		*se_lun;
 #define DEF_PR_REG_ACTIVE		1
 	unsigned long		deve_flags;
 	struct list_head	alua_port_list;