PCI: Mark some NVIDIA GPUs to avoid bus reset
authorShanker Donthineni <sdonthineni@nvidia.com>
Tue, 8 Jun 2021 05:48:56 +0000 (11:18 +0530)
committerBjorn Helgaas <bhelgaas@google.com>
Fri, 18 Jun 2021 15:32:35 +0000 (10:32 -0500)
Some NVIDIA GPU devices do not work with SBR.  Triggering SBR leaves 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 avoid the
issue.

This issue will be fixed in the next generation of hardware.

Link: https://lore.kernel.org/r/20210608054857.18963-8-ameynarkhede03@gmail.com
Signed-off-by: Shanker Donthineni <sdonthineni@nvidia.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Sinan Kaya <okaya@kernel.org>
Cc: stable@vger.kernel.org
drivers/pci/quirks.c

index de0c110029f37ca8e374596225a147eb23652d48..08a87161f3c8c658c3c5ae6ec8e6d935317388fb 100644 (file)
@@ -3546,6 +3546,18 @@ static void quirk_no_bus_reset(struct pci_dev *dev)
        dev->dev_flags |= PCI_DEV_FLAGS_NO_BUS_RESET;
 }
 
+/*
+ * 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)
+               quirk_no_bus_reset(dev);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
+                        quirk_nvidia_no_bus_reset);
+
 /*
  * Some Atheros AR9xxx and QCA988x chips do not behave after a bus reset.
  * The device will throw a Link Down error on AER-capable systems and