nvme-pci: fix race condition between reset and nvme_dev_disable()

nvme_dev_disable() modifies the dev->online_queues field, therefore
nvme_pci_update_nr_queues() should avoid racing against it, otherwise
we could end up passing invalid values to blk_mq_update_nr_hw_queues().

 WARNING: CPU: 39 PID: 61303 at drivers/pci/msi/api.c:347
          pci_irq_get_affinity+0x187/0x210
 Workqueue: nvme-reset-wq nvme_reset_work [nvme]
 RIP: 0010:pci_irq_get_affinity+0x187/0x210
 Call Trace:
  <TASK>
  ? blk_mq_pci_map_queues+0x87/0x3c0
  ? pci_irq_get_affinity+0x187/0x210
  blk_mq_pci_map_queues+0x87/0x3c0
  nvme_pci_map_queues+0x189/0x460 [nvme]
  blk_mq_update_nr_hw_queues+0x2a/0x40
  nvme_reset_work+0x1be/0x2a0 [nvme]

Fix the bug by locking the shutdown_lock mutex before using
dev->online_queues. Give up if nvme_dev_disable() is running or if
it has been executed already.

Fixes: 949928c1c731 ("NVMe: Fix possible queue use after freed")
Tested-by: Yi Zhang <yi.zhang@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 7990c3f22ecf660a5c82825cf1d372dc180e34f7..4b9fda0b1d9a33af4d7030b72532835b205e9cbb 100644 (file)
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2506,17 +2506,29 @@ static unsigned int nvme_pci_nr_maps(struct nvme_dev *dev)
        return 1;
 }
 
-static void nvme_pci_update_nr_queues(struct nvme_dev *dev)
+static bool nvme_pci_update_nr_queues(struct nvme_dev *dev)
 {
        if (!dev->ctrl.tagset) {
                nvme_alloc_io_tag_set(&dev->ctrl, &dev->tagset, &nvme_mq_ops,
                                nvme_pci_nr_maps(dev), sizeof(struct nvme_iod));
-               return;
+               return true;
+       }
+
+       /* Give up if we are racing with nvme_dev_disable() */
+       if (!mutex_trylock(&dev->shutdown_lock))
+               return false;
+
+       /* Check if nvme_dev_disable() has been executed already */
+       if (!dev->online_queues) {
+               mutex_unlock(&dev->shutdown_lock);
+               return false;
        }
 
        blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1);
        /* free previously allocated queues that are no longer usable */
        nvme_free_queues(dev, dev->online_queues);
+       mutex_unlock(&dev->shutdown_lock);
+       return true;
 }
 
 static int nvme_pci_enable(struct nvme_dev *dev)
@@ -2797,7 +2809,8 @@ static void nvme_reset_work(struct work_struct *work)
                nvme_dbbuf_set(dev);
                nvme_unquiesce_io_queues(&dev->ctrl);
                nvme_wait_freeze(&dev->ctrl);
-               nvme_pci_update_nr_queues(dev);
+               if (!nvme_pci_update_nr_queues(dev))
+                       goto out;
                nvme_unfreeze(&dev->ctrl);
        } else {
                dev_warn(dev->ctrl.device, "IO queues lost\n");