[PATCH] nvme-pci: fix resume after AER recovery

[Christoph Hellwig]

All I/O on a nvme controllers hangs after injecting a malformed TLP error
using aer-inject with an error file like:

--- snip ---
AER
PCI_ID WWWW:XX.YY.Z
UNCOR_STATUS COMP_TIME
HEADER_LOG 0 1 2 3
--- snip ---

This is because in this case the ->resume method will be called after
->error_injected and not ->slot_reset, leaving the controller in disabled
state and the queue frozen.  Fix this by doing a controller reset to
resume as well.

Fixes: a0a3408ee614 ("NVMe: Add pci error handlers")
Reported-by: Maciej Grochowski <Maciej.Grochowski at sony.com>
Signed-off-by: Christoph Hellwig <hch at lst.de>
Tested-by: Maciej Grochowski <Maciej.Grochowski at sony.com>
---
 drivers/nvme/host/pci.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c734934c407ccf..ec1e95d1a8c236 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3336,21 +3336,19 @@ static pci_ers_result_t nvme_error_detected(struct pci_dev *pdev,
 	return PCI_ERS_RESULT_NEED_RESET;
 }
 
-static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
+static void nvme_error_resume(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
 
 	dev_info(dev->ctrl.device, "restart after slot reset\n");
 	pci_restore_state(pdev);
 	nvme_reset_ctrl(&dev->ctrl);
-	return PCI_ERS_RESULT_RECOVERED;
 }
 
-static void nvme_error_resume(struct pci_dev *pdev)
+static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
 {
-	struct nvme_dev *dev = pci_get_drvdata(pdev);
-
-	flush_work(&dev->ctrl.reset_work);
+	nvme_error_resume(pdev);
+	return PCI_ERS_RESULT_RECOVERED;
 }
 
 static const struct pci_error_handlers nvme_err_handler = {
-- 
2.39.0