@Marks,
This is the testing kernel with the patch below applied:
https://people.canonical.com/~hwang4/lp2111521/test12/
Please add "dyndbg="file drivers/pci/* +p" and collect a dmesg.txt,
thanks.
BTW, I was OOO the past week, so it is a bit late to respond.
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e9448d55113b..c9abb18988b0 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1268,6 +1268,8 @@ static int pci_dev_wait(struct pci_dev *dev, char
*reset_type, int timeout)
bool retrain = false;
struct pci_dev *root, *bridge;
+ pci_dbg(dev, "%s: %s timeout %d\n", __func__, reset_type, timeout);
+
root = pcie_find_root_port(dev);
if (pci_is_pcie(dev)) {
@@ -1305,14 +1307,32 @@ static int pci_dev_wait(struct pci_dev *dev, char
*reset_type, int timeout)
if (root && root->config_rrs_sv) {
pci_read_config_dword(dev, PCI_VENDOR_ID, &id);
- if (!pci_bus_rrs_vendor_id(id))
- break;
+ pci_dbg(dev, "%s: vf %d read %#06x\n", __func__,
+ dev->is_virtfn, id);
+ if (pci_bus_rrs_vendor_id(id))
+ goto retry;
+
+ /*
+ * We might read 0xffff if the device is a VF and
+ * the read was successful (the VF Vendor ID is
+ * 0xffff per spec).
+ *
+ * If the device is not a VF, 0xffff likely means
+ * there was an error on PCIe. E.g., maybe the
+ * device couldn't even respond with RRS status,
+ * and the RC timed out and synthesized ~0 data.
+ */
+ if (PCI_POSSIBLE_ERROR(id) && !dev->is_virtfn)
+ goto retry;
+
+ break;
} else {
pci_read_config_dword(dev, PCI_COMMAND, &id);
if (!PCI_POSSIBLE_ERROR(id))
break;
}
+retry:
if (delay > timeout) {
pci_warn(dev, "not ready %dms after %s; giving up\n",
delay - 1, reset_type);
@@ -4760,6 +4780,8 @@ static bool pcie_wait_for_link_delay(struct pci_dev
*pdev, bool active,
* Some controllers might not implement link active reporting. In this
* case, we wait for 1000 ms + any delay requested by the caller.
*/
+ pci_dbg(pdev, "%s: active %d delay %d link_active_reporting %d\n",
+ __func__, active, delay, pdev->link_active_reporting);
if (!pdev->link_active_reporting) {
msleep(PCIE_LINK_RETRAIN_TIMEOUT_MS + delay);
return true;
(END)
--
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/2111521
Title:
nvme no longer detected on boot after upgrade to 6.8.0-60
To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2111521/+subscriptions
--
ubuntu-bugs mailing list
[email protected]
https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
