@@ -1349,6 +1349,22 @@ static int aer_probe(struct pcie_device *dev)
return 0;
}
+static int aer_suspend(struct pcie_device *dev)
+{
+ struct aer_rpc *rpc = get_service_data(dev);
+
+ aer_disable_rootport(rpc);
+ return 0;
+}
+
+static int aer_resume(struct pcie_device *dev)
+{
+ struct aer_rpc *rpc = get_service_data(dev);
+
+ aer_enable_rootport(rpc);
+ return 0;
+}
+
/**
* aer_root_reset - reset link on Root Port
* @dev: pointer to Root Port's pci_dev data structure
@@ -1388,6 +1404,8 @@ static struct pcie_port_service_driver aerdriver = {
.service = PCIE_PORT_SERVICE_AER,
.probe = aer_probe,
+ .suspend = aer_suspend,
+ .resume = aer_resume,
.remove = aer_remove,
};
BugLink: https://bugs.launchpad.net/bugs/1913691 Commit 50310600ebda ("iommu/vt-d: Enable PCI ACS for platform opt in hint") enables ACS, and some platforms lose its NVMe after resume from firmware: [ 50.947816] pcieport 0000:00:1b.0: DPC: containment event, status:0x1f01 source:0x0000 [ 50.947817] pcieport 0000:00:1b.0: DPC: unmasked uncorrectable error detected [ 50.947829] pcieport 0000:00:1b.0: PCIe Bus Error: severity=Uncorrected (Non-Fatal), type=Transaction Layer, (Receiver ID) [ 50.947830] pcieport 0000:00:1b.0: device [8086:06ac] error status/mask=00200000/00010000 [ 50.947831] pcieport 0000:00:1b.0: [21] ACSViol (First) [ 50.947841] pcieport 0000:00:1b.0: AER: broadcast error_detected message [ 50.947843] nvme nvme0: frozen state error detected, reset controller It happens right after ACS gets enabled during resume. To prevent that from happening, disable AER interrupt and enable it on system suspend and resume, respectively. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=209149 Fixes: 50310600ebda ("iommu/vt-d: Enable PCI ACS for platform opt in hint") Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com> --- drivers/pci/pcie/aer.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)