The _RST is a standard method specified in the ACPI specification. It
provides a function level reset when it is described in the acpi_device
context associated with PCI-device.
Implement a new reset function pci_dev_acpi_reset() for probing RST
method and execute if it is defined in the firmware.
The ACPI based reset is called after the device-specific reset and
before standard PCI hardware resets.
Signed-off-by: Shanker Donthineni <[email protected]>
---
- Fix typo in the commit text
drivers/pci/pci.c | 35 +++++++++++++++++++++++++++++++++++
1 file changed, 35 insertions(+)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 16a17215f633..6dadb19848c2 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -5054,6 +5054,35 @@ static void pci_dev_restore(struct pci_dev *dev)
err_handler->reset_done(dev);
}
+/**
+ * pci_dev_acpi_reset - do a function level reset using _RST method
+ * @dev: device to reset
+ * @probe: check if _RST method is included in the acpi_device context.
+ */
+static int pci_dev_acpi_reset(struct pci_dev *dev, int probe)
+{
+#ifdef CONFIG_ACPI
+ acpi_handle handle = ACPI_HANDLE(&dev->dev);
+
+ /* Return -ENOTTY if _RST method is not included in the dev context */
+ if (!handle || !acpi_has_method(handle, "_RST"))
+ return -ENOTTY;
+
+ /* Return 0 for probe phase indicating that we can reset this device */
+ if (probe)
+ return 0;
+
+ /* Invoke _RST() method to perform a function level reset */
+ if (ACPI_FAILURE(acpi_evaluate_object(handle, "_RST", NULL, NULL))) {
+ pci_warn(dev, "Failed to reset the device\n");
+ return -EINVAL;
+ }
+ return 0;
+#else
+ return -ENOTTY;
+#endif
+}
+
/**
* __pci_reset_function_locked - reset a PCI device function while holding
* the @dev mutex lock.
@@ -5089,6 +5118,9 @@ int __pci_reset_function_locked(struct pci_dev *dev)
* reset mechanisms might be broken on the device.
*/
rc = pci_dev_specific_reset(dev, 0);
+ if (rc != -ENOTTY)
+ return rc;
+ rc = pci_dev_acpi_reset(dev, 0);
if (rc != -ENOTTY)
return rc;
if (pcie_has_flr(dev)) {
@@ -5127,6 +5159,9 @@ int pci_probe_reset_function(struct pci_dev *dev)
might_sleep();
rc = pci_dev_specific_reset(dev, 1);
+ if (rc != -ENOTTY)
+ return rc;
+ rc = pci_dev_acpi_reset(dev, 1);
if (rc != -ENOTTY)
return rc;
if (pcie_has_flr(dev))
--
2.17.1
On select platforms, some Nvidia GPU devices do not work with SBR.
Triggering SBR would leave the device inoperable for the current
system boot. It requires a system hard-reboot to get the GPU device
back to normal operating condition post-SBR. For the affected
devices, enable NO_BUS_RESET quirk to fix the issue.
This issue will be fixed in the next generation of hardware.
Signed-off-by: Shanker Donthineni <[email protected]>
---
Changes since v1:
- Split patch into 2, code for handling _RST and SBR specific quirk
- The RST based reset is called as a first-class mechanism in the reset code path
drivers/pci/quirks.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 653660e3ba9e..1da80e772ee1 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3913,6 +3913,18 @@ static int delay_250ms_after_flr(struct pci_dev *dev, int probe)
return 0;
}
+/*
+ * Some Nvidia GPU devices do not work with bus reset, SBR needs to be
+ * prevented for those affected devices.
+ */
+static void quirk_nvidia_no_bus_reset(struct pci_dev *dev)
+{
+ if ((dev->device & 0xffc0) == 0x2340)
+ dev->dev_flags |= PCI_DEV_FLAGS_NO_BUS_RESET;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
+ quirk_nvidia_no_bus_reset);
+
static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82599_SFP_VF,
reset_intel_82599_sfp_virtfn },
--
2.17.1
Thanks Amey,
On 4/27/21 10:05 AM, Amey Narkhede wrote:
> Would you like to rebase this patch on [1]?
> Or should I send the v3?
>
> [1]: https://lore.kernel.org/linux-pci/[email protected]/
I'll rebase and post updated patches.