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: cc1d5e749a
("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>
This commit is contained in:
parent
a8e3e0bb74
commit
72cd4cc28e
|
@ -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");
|
dev_info(dev->ctrl.device, "restart after slot reset\n");
|
||||||
pci_restore_state(pdev);
|
pci_restore_state(pdev);
|
||||||
nvme_reset_ctrl_sync(&dev->ctrl);
|
nvme_reset_ctrl(&dev->ctrl);
|
||||||
|
return PCI_ERS_RESULT_RECOVERED;
|
||||||
switch (dev->ctrl.state) {
|
|
||||||
case NVME_CTRL_LIVE:
|
|
||||||
case NVME_CTRL_ADMIN_ONLY:
|
|
||||||
return PCI_ERS_RESULT_RECOVERED;
|
|
||||||
default:
|
|
||||||
return PCI_ERS_RESULT_DISCONNECT;
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
static void nvme_error_resume(struct pci_dev *pdev)
|
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);
|
pci_cleanup_aer_uncorrect_error_status(pdev);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue