drm/amdgpu: Fix VFCT bus number matching with soft filter

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 <oz@shift-computing.de>
Closes: https://lore.kernel.org/amd-gfx/20260621173211.28443-1-oz@shift-computing.de/
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patch.msgid.link/20260708193518.702584-2-mario.limonciello@amd.com
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 11c141672045ffc0187aa604f2c0f597bc334fb2)
Cc: stable@vger.kernel.org

1 files 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 aa039e148a5e..fbe350a45871 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
@@ -372,6 +372,45 @@ static bool amdgpu_read_disabled_bios(struct amdgpu_device *adev)
 }
 
 #ifdef CONFIG_ACPI
+/**
+ * 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;
+}
+
 static bool amdgpu_acpi_vfct_bios(struct amdgpu_device *adev)
 {
 	struct acpi_table_header *hdr;
@@ -407,11 +446,7 @@ 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);