nvme-pci: Fix AER reset handling

The nvme timeout handling doesn't do anything if the pci channel is
offline, which is the case when recovering from PCI error event, so it
was a bad idea to sync the controller reset in this state. This patch
flushes the reset work in the error_resume callback instead when the
channel is back to online. This keeps AER handling serialized and
can recover from timeouts.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=199757
Fixes: cc1d5e749a2e ("nvme/pci: Sync controller reset for AER slot_reset")
Reported-by: Alex Gagniuc <mr.nuke.me@gmail.com>
Tested-by: Alex Gagniuc <mr.nuke.me@gmail.com>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 41880cb..79b4805 100644 (file)
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2706,19 +2706,15 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
 
        dev_info(dev->ctrl.device, "restart after slot reset\n");
        pci_restore_state(pdev);
-       nvme_reset_ctrl_sync(&dev->ctrl);
-
-       switch (dev->ctrl.state) {
-       case NVME_CTRL_LIVE:
-       case NVME_CTRL_ADMIN_ONLY:
-               return PCI_ERS_RESULT_RECOVERED;
-       default:
-               return PCI_ERS_RESULT_DISCONNECT;
-       }
+       nvme_reset_ctrl(&dev->ctrl);
+       return PCI_ERS_RESULT_RECOVERED;
 }
 
 static void nvme_error_resume(struct pci_dev *pdev)
 {
+       struct nvme_dev *dev = pci_get_drvdata(pdev);
+
+       flush_work(&dev->ctrl.reset_work);
        pci_cleanup_aer_uncorrect_error_status(pdev);
 }