--- /dev/null
+From 85371c5ef502d10add72eab38711e191dccea981 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
+Date: Mon, 13 Jul 2026 08:14:43 +0200
+Subject: drm/amd/pm/ci: Don't disable MCLK DPM on Bonaire 0x6658 (R7 260X)
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: Timur Kristóf <timur.kristof@gmail.com>
+
+commit 85371c5ef502d10add72eab38711e191dccea981 upstream.
+
+The old radeon driver has a documented workaround in ci_dpm.c
+which claims that Bonaire 0x6658 with old memory controller
+firmware is unstable with MCLK DPM, so as a precaution I
+disabled MCLK DPM on this ASIC in amdgpu.
+
+Note that the old MC firmware is not actually used with
+amdgpu, but in theory it's possible that the VBIOS sets
+up the ASIC with an old MC firmware that is already running
+when amdgpu initializes (in which case amdgpu doesn't
+load its own firmware).
+
+What I expected to happen is that the GPU would simply use
+its maximum memory clock, and indeed this is what seemed
+to happen according to amdgpu_pm_info which reads the
+current MCLK value from the SMU.
+However, some users reported a huge perf regression
+and upon a closer look it seems that the GPU seems to
+not actually use the highest MCLK value, despite the SMU
+reporting that it does.
+
+Let's not disable MCLK DPM on Bonaire 0x6658 (R7 260X).
+
+Keep MCLK DPM disabled on R9 M380 in the 2015 iMac
+because that still hangs if we enable it.
+
+Fixes: 9851f29cb06c ("drm/amd/pm/ci: Disable MCLK DPM on problematic CI ASICs")
+Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
+Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
+(cherry picked from commit d34acad064ee7d82bd18f5d87592c422d4d323ac)
+Cc: stable@vger.kernel.org
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr.c | 7 ++-----
+ 1 file changed, 2 insertions(+), 5 deletions(-)
+
+--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hwmgr.c
+@@ -110,11 +110,8 @@ int hwmgr_early_init(struct pp_hwmgr *hw
+ hwmgr->od_enabled = false;
+ switch (hwmgr->chip_id) {
+ case CHIP_BONAIRE:
+- /* R9 M380 in iMac 2015: SMU hangs when enabling MCLK DPM
+- * R7 260X cards with old MC ucode: MCLK DPM is unstable
+- */
+- if (adev->pdev->subsystem_vendor == 0x106B ||
+- adev->pdev->device == 0x6658) {
++ /* R9 M380 in iMac 2015: SMU hangs when enabling MCLK DPM */
++ if (adev->pdev->subsystem_vendor == 0x106B) {
+ dev_info(adev->dev, "disabling MCLK DPM on quirky ASIC");
+ adev->pm.pp_feature &= ~PP_MCLK_DPM_MASK;
+ hwmgr->feature_mask &= ~PP_MCLK_DPM_MASK;
--- /dev/null
+From db7e8108809a2245f0a17ba323f027cac0941ffb Mon Sep 17 00:00:00 2001
+From: Mario Limonciello <mario.limonciello@amd.com>
+Date: Wed, 8 Jul 2026 14:35:14 -0500
+Subject: drm/amdgpu: Fix VFCT bus number matching with soft filter
+
+From: Mario Limonciello <mario.limonciello@amd.com>
+
+commit db7e8108809a2245f0a17ba323f027cac0941ffb upstream.
+
+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
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c | 45 +++++++++++++++++++++++++++----
+ 1 file changed, 40 insertions(+), 5 deletions(-)
+
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
+@@ -358,6 +358,45 @@ static bool amdgpu_read_disabled_bios(st
+ }
+
+ #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;
+@@ -393,11 +432,7 @@ static bool amdgpu_acpi_vfct_bios(struct
+ }
+
+ 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);
projects / thirdparty / kernel / stable-queue.git / commitdiff
