[PATCH] nvme-pci: disable accessible controller on error paths

[Eduard Zateev]

nvme_dev_disable() skips nvme_disable_ctrl() when the controller reports
a fatal status or is not ready. PCI MMIO can still be accessible in this
state, allowing the controller to complete commands while the driver
cancels outstanding requests. This can race with blk-mq requeueing.

Separate PCI accessibility from controller health. Delete I/O queues
only for a healthy controller, but clear CC.EN whenever the PCI function
and channel remain accessible. Keep graceful shutdown and IRQ polling
limited to a healthy controller.

Reported-by: syzbot+f4353e96f7004ae5a09e@xxxxxxxxxxxxxxxxxxxxxxxxx
Link: https://syzkaller.appspot.com/bug?extid=f4353e96f7004ae5a09e
Assisted-by: LLM
Signed-off-by: Eduard Zateev <hackerowskiy@xxxxxxxxx>
---
 drivers/nvme/host/pci.c | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 77317e5d00f..777615b4d25 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3296,14 +3296,19 @@ static void nvme_dev_unmap(struct nvme_dev *dev)
 	pci_release_mem_regions(to_pci_dev(dev->dev));
 }
 
-static bool nvme_pci_ctrl_is_dead(struct nvme_dev *dev)
+static bool nvme_pci_ctrl_is_accessible(struct nvme_dev *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
+
+	return pci_is_enabled(pdev) && pci_device_is_present(pdev) &&
+		pdev->error_state == pci_channel_io_normal;
+}
+
+static bool nvme_pci_ctrl_is_dead(struct nvme_dev *dev)
+{
 	u32 csts;
 
-	if (!pci_is_enabled(pdev) || !pci_device_is_present(pdev))
-		return true;
-	if (pdev->error_state != pci_channel_io_normal)
+	if (!nvme_pci_ctrl_is_accessible(dev))
 		return true;
 
 	csts = readl(dev->bar + NVME_REG_CSTS);
@@ -3331,10 +3336,16 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 
 	nvme_quiesce_io_queues(&dev->ctrl);
 
-	if (!dead && dev->ctrl.queue_count > 0) {
+	if (!dead && dev->ctrl.queue_count > 0)
 		nvme_delete_io_queues(dev);
-		nvme_disable_ctrl(&dev->ctrl, shutdown);
-		nvme_poll_irqdisable(&dev->queues[0]);
+	if (dev->ctrl.queue_count > 0 && nvme_pci_ctrl_is_accessible(dev)) {
+		/*
+		 * Stop an accessible controller even if it reports itself dead.
+		 * Otherwise it may complete requests after they have been cancelled.
+		 */
+		nvme_disable_ctrl(&dev->ctrl, shutdown && !dead);
+		if (!dead)
+			nvme_poll_irqdisable(&dev->queues[0]);
 	}
 	nvme_suspend_io_queues(dev);
 	nvme_suspend_queue(dev, 0);
-- 
2.55.0