summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--drivers/nvme/host/pci.c66
1 files changed, 58 insertions, 8 deletions
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index d3c5086673bc..46698cabef81 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)