On systems where PCI bus renumbering occurs (e.g. pci=realloc,
resource conflicts), the runtime bus number may differ from the
BIOS POST bus number recorded in the VFCT table. This causes
amdgpu_acpi_vfct_bios() to fail finding the VBIOS even though
the correct device entry exists.
Introduce amdgpu_acpi_vfct_match() which treats the bus number
as a soft filter: vendor/device/function identity is the hard
requirement, while exact bus match is the preferred path. When
bus numbers disagree but device identity matches, accept the
VFCT entry and log a dev_notice for diagnostics.
Reported-by: Oz Tiram <[email protected]>
Closes:
https://lore.kernel.org/amd-gfx/[email protected]/
Signed-off-by: Mario Limonciello <[email protected]>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c | 45 +++++++++++++++++++++---
1 file changed, 40 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
index 3ebdd792feec1..d8fd047295d9d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
@@ -377,6 +377,45 @@ static bool amdgpu_read_disabled_bios(struct amdgpu_device
*adev)
false : amdgpu_asic_read_disabled_bios(adev);
}
+/**
+ * amdgpu_acpi_vfct_match() - Check if a VFCT entry matches the device
+ * @adev: AMDGPU device
+ * @vhdr: VFCT image header to check
+ *
+ * VFCT entries contain the PCI bus number as recorded during BIOS POST.
+ * On systems where the kernel renumbers PCI buses (e.g. pci=realloc or
+ * resource conflicts), the runtime bus number may differ from the POST
+ * value. Match by device identity (vendor + device + function) and use
+ * the bus number as a preference: exact bus match is preferred, but when
+ * the bus numbers disagree we accept the entry if the device identity
+ * matches.
+ *
+ * Returns: 0 on match, -ENODEV on no match
+ */
+static int amdgpu_acpi_vfct_match(struct amdgpu_device *adev,
+ VFCT_IMAGE_HEADER *vhdr)
+{
+ /* Vendor and device IDs must always match */
+ if (vhdr->VendorID != adev->pdev->vendor ||
+ vhdr->DeviceID != adev->pdev->device)
+ return -ENODEV;
+
+ if (vhdr->PCIDevice != PCI_SLOT(adev->pdev->devfn) ||
+ vhdr->PCIFunction != PCI_FUNC(adev->pdev->devfn))
+ return -ENODEV;
+
+ /* Exact bus number match - preferred */
+ if (vhdr->PCIBus == adev->pdev->bus->number)
+ return 0;
+
+ /* Bus mismatch but device identity matches (PCI renumbering case) */
+ dev_notice(adev->dev,
+ "VFCT bus number mismatch: table %u != runtime %u, matching by
device identity (vendor 0x%04x device 0x%04x)\n",
+ vhdr->PCIBus, adev->pdev->bus->number,
+ adev->pdev->vendor, adev->pdev->device);
+ return 0;
+}
+
#ifdef CONFIG_ACPI
static bool amdgpu_acpi_vfct_bios(struct amdgpu_device *adev)
{
@@ -413,11 +452,7 @@ static bool amdgpu_acpi_vfct_bios(struct amdgpu_device
*adev)
}
if (vhdr->ImageLength &&
- vhdr->PCIBus == adev->pdev->bus->number &&
- vhdr->PCIDevice == PCI_SLOT(adev->pdev->devfn) &&
- vhdr->PCIFunction == PCI_FUNC(adev->pdev->devfn) &&
- vhdr->VendorID == adev->pdev->vendor &&
- vhdr->DeviceID == adev->pdev->device) {
+ !amdgpu_acpi_vfct_match(adev, vhdr)) {
adev->bios = kmemdup(&vbios->VbiosContent,
vhdr->ImageLength,
GFP_KERNEL);
