1 files changed, 97 insertions, 40 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 7da80f375315..b2dd4e391f5c 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1113,15 +1113,15 @@ static struct nvme_id_ns *nvme_identify_ns(struct nvme_ctrl *ctrl,
 	return id;
 }
 
-static int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
-		      void *buffer, size_t buflen, u32 *result)
+static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid,
+		unsigned int dword11, void *buffer, size_t buflen, u32 *result)
 {
 	struct nvme_command c;
 	union nvme_result res;
 	int ret;
 
 	memset(&c, 0, sizeof(c));
-	c.features.opcode = nvme_admin_set_features;
+	c.features.opcode = op;
 	c.features.fid = cpu_to_le32(fid);
 	c.features.dword11 = cpu_to_le32(dword11);
 
@@ -1132,6 +1132,24 @@ static int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword
 	return ret;
 }
 
+int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid,
+		      unsigned int dword11, void *buffer, size_t buflen,
+		      u32 *result)
+{
+	return nvme_features(dev, nvme_admin_set_features, fid, dword11, buffer,
+			     buflen, result);
+}
+EXPORT_SYMBOL_GPL(nvme_set_features);
+
+int nvme_get_features(struct nvme_ctrl *dev, unsigned int fid,
+		      unsigned int dword11, void *buffer, size_t buflen,
+		      u32 *result)
+{
+	return nvme_features(dev, nvme_admin_get_features, fid, dword11, buffer,
+			     buflen, result);
+}
+EXPORT_SYMBOL_GPL(nvme_get_features);
+
 int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
 {
 	u32 q_count = (*count - 1) | ((*count - 1) << 16);
@@ -1257,9 +1275,9 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 		return 0;
 	}
 
-	effects |= nvme_known_admin_effects(opcode);
 	if (ctrl->effects)
 		effects = le32_to_cpu(ctrl->effects->acs[opcode]);
+	effects |= nvme_known_admin_effects(opcode);
 
 	/*
 	 * For simplicity, IO to all namespaces is quiesced even if the command
@@ -1361,9 +1379,14 @@ static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
 {
 #ifdef CONFIG_NVME_MULTIPATH
 	if (disk->fops == &nvme_ns_head_ops) {
+		struct nvme_ns *ns;
+
 		*head = disk->private_data;
 		*srcu_idx = srcu_read_lock(&(*head)->srcu);
-		return nvme_find_path(*head);
+		ns = nvme_find_path(*head);
+		if (!ns)
+			srcu_read_unlock(&(*head)->srcu, *srcu_idx);
+		return ns;
 	}
 #endif
 	*head = NULL;
@@ -1377,42 +1400,56 @@ static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
 		srcu_read_unlock(&head->srcu, idx);
 }
 
-static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned cmd, unsigned long arg)
+static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
+		unsigned int cmd, unsigned long arg)
 {
+	struct nvme_ns_head *head = NULL;
+	void __user *argp = (void __user *)arg;
+	struct nvme_ns *ns;
+	int srcu_idx, ret;
+
+	ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
+	if (unlikely(!ns))
+		return -EWOULDBLOCK;
+
+	/*
+	 * Handle ioctls that apply to the controller instead of the namespace
+	 * seperately and drop the ns SRCU reference early.  This avoids a
+	 * deadlock when deleting namespaces using the passthrough interface.
+	 */
+	if (cmd == NVME_IOCTL_ADMIN_CMD || is_sed_ioctl(cmd)) {
+		struct nvme_ctrl *ctrl = ns->ctrl;
+
+		nvme_get_ctrl(ns->ctrl);
+		nvme_put_ns_from_disk(head, srcu_idx);
+
+		if (cmd == NVME_IOCTL_ADMIN_CMD)
+			ret = nvme_user_cmd(ctrl, NULL, argp);
+		else
+			ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
+
+		nvme_put_ctrl(ctrl);
+		return ret;
+	}
+
 	switch (cmd) {
 	case NVME_IOCTL_ID:
 		force_successful_syscall_return();
-		return ns->head->ns_id;
-	case NVME_IOCTL_ADMIN_CMD:
-		return nvme_user_cmd(ns->ctrl, NULL, (void __user *)arg);
+		ret = ns->head->ns_id;
+		break;
 	case NVME_IOCTL_IO_CMD:
-		return nvme_user_cmd(ns->ctrl, ns, (void __user *)arg);
+		ret = nvme_user_cmd(ns->ctrl, ns, argp);
+		break;
 	case NVME_IOCTL_SUBMIT_IO:
-		return nvme_submit_io(ns, (void __user *)arg);
+		ret = nvme_submit_io(ns, argp);
+		break;
 	default:
-#ifdef CONFIG_NVM
 		if (ns->ndev)
-			return nvme_nvm_ioctl(ns, cmd, arg);
-#endif
-		if (is_sed_ioctl(cmd))
-			return sed_ioctl(ns->ctrl->opal_dev, cmd,
-					 (void __user *) arg);
-		return -ENOTTY;
+			ret = nvme_nvm_ioctl(ns, cmd, arg);
+		else
+			ret = -ENOTTY;
 	}
-}
 
-static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
-		unsigned int cmd, unsigned long arg)
-{
-	struct nvme_ns_head *head = NULL;
-	struct nvme_ns *ns;
-	int srcu_idx, ret;
-
-	ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
-	if (unlikely(!ns))
-		ret = -EWOULDBLOCK;
-	else
-		ret = nvme_ns_ioctl(ns, cmd, arg);
 	nvme_put_ns_from_disk(head, srcu_idx);
 	return ret;
 }
@@ -2557,6 +2594,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 
 	ctrl->oacs = le16_to_cpu(id->oacs);
 	ctrl->oncs = le16_to_cpu(id->oncs);
+	ctrl->mtfa = le16_to_cpu(id->mtfa);
 	ctrl->oaes = le32_to_cpu(id->oaes);
 	atomic_set(&ctrl->abort_limit, id->acl + 1);
 	ctrl->vwc = id->vwc;
@@ -3298,7 +3336,7 @@ static int nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	device_add_disk(ctrl->device, ns->disk, nvme_ns_id_attr_groups);
 
 	nvme_mpath_add_disk(ns, id);
-	nvme_fault_inject_init(ns);
+	nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name);
 	kfree(id);
 
 	return 0;
@@ -3323,7 +3361,15 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
 		return;
 
-	nvme_fault_inject_fini(ns);
+	nvme_fault_inject_fini(&ns->fault_inject);
+
+	mutex_lock(&ns->ctrl->subsys->lock);
+	list_del_rcu(&ns->siblings);
+	mutex_unlock(&ns->ctrl->subsys->lock);
+	synchronize_rcu(); /* guarantee not available in head->list */
+	nvme_mpath_clear_current_path(ns);
+	synchronize_srcu(&ns->head->srcu); /* wait for concurrent submissions */
+
 	if (ns->disk && ns->disk->flags & GENHD_FL_UP) {
 		del_gendisk(ns->disk);
 		blk_cleanup_queue(ns->queue);
@@ -3331,16 +3377,10 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 			blk_integrity_unregister(ns->disk);
 	}
 
-	mutex_lock(&ns->ctrl->subsys->lock);
-	list_del_rcu(&ns->siblings);
-	nvme_mpath_clear_current_path(ns);
-	mutex_unlock(&ns->ctrl->subsys->lock);
-
 	down_write(&ns->ctrl->namespaces_rwsem);
 	list_del_init(&ns->list);
 	up_write(&ns->ctrl->namespaces_rwsem);
 
-	synchronize_srcu(&ns->head->srcu);
 	nvme_mpath_check_last_path(ns);
 	nvme_put_ns(ns);
 }
@@ -3380,7 +3420,8 @@ static int nvme_scan_ns_list(struct nvme_ctrl *ctrl, unsigned nn)
 {
 	struct nvme_ns *ns;
 	__le32 *ns_list;
-	unsigned i, j, nsid, prev = 0, num_lists = DIV_ROUND_UP(nn, 1024);
+	unsigned i, j, nsid, prev = 0;
+	unsigned num_lists = DIV_ROUND_UP_ULL((u64)nn, 1024);
 	int ret = 0;
 
 	ns_list = kzalloc(NVME_IDENTIFY_DATA_SIZE, GFP_KERNEL);
@@ -3681,6 +3722,8 @@ EXPORT_SYMBOL_GPL(nvme_start_ctrl);
 
 void nvme_uninit_ctrl(struct nvme_ctrl *ctrl)
 {
+	nvme_fault_inject_fini(&ctrl->fault_inject);
+	dev_pm_qos_hide_latency_tolerance(ctrl->device);
 	cdev_device_del(&ctrl->cdev, ctrl->device);
 }
 EXPORT_SYMBOL_GPL(nvme_uninit_ctrl);
@@ -3775,6 +3818,8 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	dev_pm_qos_update_user_latency_tolerance(ctrl->device,
 		min(default_ps_max_latency_us, (unsigned long)S32_MAX));
 
+	nvme_fault_inject_init(&ctrl->fault_inject, dev_name(ctrl->device));
+
 	return 0;
 out_free_name:
 	kfree_const(ctrl->device->kobj.name);
@@ -3880,6 +3925,18 @@ void nvme_start_queues(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_start_queues);
 
+
+void nvme_sync_queues(struct nvme_ctrl *ctrl)
+{
+	struct nvme_ns *ns;
+
+	down_read(&ctrl->namespaces_rwsem);
+	list_for_each_entry(ns, &ctrl->namespaces, list)
+		blk_sync_queue(ns->queue);
+	up_read(&ctrl->namespaces_rwsem);
+}
+EXPORT_SYMBOL_GPL(nvme_sync_queues);
+
 /*
  * Check we didn't inadvertently grow the command structure sizes:
  */