Merge tag 'block-5.14-2021-07-16' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe fixes via Christoph:
      - fix various races in nvme-pci when shutting down just after
        probing (Casey Chen)
      - fix a net_device leak in nvme-tcp (Prabhakar Kushwaha)

 - Fix regression in xen-blkfront by cleaning up the removal state
   machine (Christoph)

 - Fix tag_set and queue cleanup ordering regression in nbd (Wang)

 - Fix tag_set and queue cleanup ordering regression in pd (Guoqing)

* tag 'block-5.14-2021-07-16' of git://git.kernel.dk/linux-block:
  xen-blkfront: sanitize the removal state machine
  nbd: fix order of cleaning up the queue and freeing the tagset
  pd: fix order of cleaning up the queue and freeing the tagset
  nvme-pci: do not call nvme_dev_remove_admin from nvme_remove
  nvme-pci: fix multiple races in nvme_setup_io_queues
  nvme-tcp: use __dev_get_by_name instead dev_get_by_name for OPT_HOST_IFACE

2 files changed, 59 insertions, 12 deletions

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index d3c5086673bc..320051f5a3dd 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1554,6 +1554,28 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
 	wmb(); /* ensure the first interrupt sees the initialization */
 }
 
+/*
+ * Try getting shutdown_lock while setting up IO queues.
+ */
+static int nvme_setup_io_queues_trylock(struct nvme_dev *dev)
+{
+	/*
+	 * Give up if the lock is being held by nvme_dev_disable.
+	 */
+	if (!mutex_trylock(&dev->shutdown_lock))
+		return -ENODEV;
+
+	/*
+	 * Controller is in wrong state, fail early.
+	 */
+	if (dev->ctrl.state != NVME_CTRL_CONNECTING) {
+		mutex_unlock(&dev->shutdown_lock);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled)
 {
 	struct nvme_dev *dev = nvmeq->dev;
@@ -1582,8 +1604,11 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled)
 		goto release_cq;
 
 	nvmeq->cq_vector = vector;
-	nvme_init_queue(nvmeq, qid);
 
+	result = nvme_setup_io_queues_trylock(dev);
+	if (result)
+		return result;
+	nvme_init_queue(nvmeq, qid);
 	if (!polled) {
 		result = queue_request_irq(nvmeq);
 		if (result < 0)
@@ -1591,10 +1616,12 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled)
 	}
 
 	set_bit(NVMEQ_ENABLED, &nvmeq->flags);
+	mutex_unlock(&dev->shutdown_lock);
 	return result;
 
 release_sq:
 	dev->online_queues--;
+	mutex_unlock(&dev->shutdown_lock);
 	adapter_delete_sq(dev, qid);
 release_cq:
 	adapter_delete_cq(dev, qid);
@@ -2167,7 +2194,18 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	if (nr_io_queues == 0)
 		return 0;
 
-	clear_bit(NVMEQ_ENABLED, &adminq->flags);
+	/*
+	 * Free IRQ resources as soon as NVMEQ_ENABLED bit transitions
+	 * from set to unset. If there is a window to it is truely freed,
+	 * pci_free_irq_vectors() jumping into this window will crash.
+	 * And take lock to avoid racing with pci_free_irq_vectors() in
+	 * nvme_dev_disable() path.
+	 */
+	result = nvme_setup_io_queues_trylock(dev);
+	if (result)
+		return result;
+	if (test_and_clear_bit(NVMEQ_ENABLED, &adminq->flags))
+		pci_free_irq(pdev, 0, adminq);
 
 	if (dev->cmb_use_sqes) {
 		result = nvme_cmb_qdepth(dev, nr_io_queues,
@@ -2183,14 +2221,17 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 		result = nvme_remap_bar(dev, size);
 		if (!result)
 			break;
-		if (!--nr_io_queues)
-			return -ENOMEM;
+		if (!--nr_io_queues) {
+			result = -ENOMEM;
+			goto out_unlock;
+		}
 	} while (1);
 	adminq->q_db = dev->dbs;
 
  retry:
 	/* Deregister the admin queue's interrupt */
-	pci_free_irq(pdev, 0, adminq);
+	if (test_and_clear_bit(NVMEQ_ENABLED, &adminq->flags))
+		pci_free_irq(pdev, 0, adminq);
 
 	/*
 	 * If we enable msix early due to not intx, disable it again before
@@ -2199,8 +2240,10 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	pci_free_irq_vectors(pdev);
 
 	result = nvme_setup_irqs(dev, nr_io_queues);
-	if (result <= 0)
-		return -EIO;
+	if (result <= 0) {
+		result = -EIO;
+		goto out_unlock;
+	}
 
 	dev->num_vecs = result;
 	result = max(result - 1, 1);
@@ -2214,8 +2257,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	 */
 	result = queue_request_irq(adminq);
 	if (result)
-		return result;
+		goto out_unlock;
 	set_bit(NVMEQ_ENABLED, &adminq->flags);
+	mutex_unlock(&dev->shutdown_lock);
 
 	result = nvme_create_io_queues(dev);
 	if (result || dev->online_queues < 2)
@@ -2224,6 +2268,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	if (dev->online_queues - 1 < dev->max_qid) {
 		nr_io_queues = dev->online_queues - 1;
 		nvme_disable_io_queues(dev);
+		result = nvme_setup_io_queues_trylock(dev);
+		if (result)
+			return result;
 		nvme_suspend_io_queues(dev);
 		goto retry;
 	}
@@ -2232,6 +2279,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 					dev->io_queues[HCTX_TYPE_READ],
 					dev->io_queues[HCTX_TYPE_POLL]);
 	return 0;
+out_unlock:
+	mutex_unlock(&dev->shutdown_lock);
+	return result;
 }
 
 static void nvme_del_queue_end(struct request *req, blk_status_t error)
@@ -2962,7 +3012,6 @@ static void nvme_remove(struct pci_dev *pdev)
 	if (!pci_device_is_present(pdev)) {
 		nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DEAD);
 		nvme_dev_disable(dev, true);
-		nvme_dev_remove_admin(dev);
 	}
 
 	flush_work(&dev->ctrl.reset_work);
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 12acfe05cd68..8cb15ee5b249 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -123,7 +123,6 @@ struct nvme_tcp_ctrl {
 	struct blk_mq_tag_set	admin_tag_set;
 	struct sockaddr_storage addr;
 	struct sockaddr_storage src_addr;
-	struct net_device	*ndev;
 	struct nvme_ctrl	ctrl;
 
 	struct work_struct	err_work;
@@ -2533,8 +2532,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 	}
 
 	if (opts->mask & NVMF_OPT_HOST_IFACE) {
-		ctrl->ndev = dev_get_by_name(&init_net, opts->host_iface);
-		if (!ctrl->ndev) {
+		if (!__dev_get_by_name(&init_net, opts->host_iface)) {
 			pr_err("invalid interface passed: %s\n",
 			       opts->host_iface);
 			ret = -ENODEV;