kernel/linux.git/drivers/gpu/drm/amd/amdgpu, branch v6.1.175

drm/amdgpu/gfx6: Support harvested SI chips with disabled TCCs (v2)

2026-06-01T15:39:27+00:00

[ Upstream commit fe2b84f9228e2a0903221a4d0d8c350b018e9c0c ] This commit fixes amdgpu to work on the Radeon HD 7870 XT which has never worked with the Linux open source drivers before. Some boards have "harvested" chips, meaning that some parts of the chip are disabled and fused, and it's sold for cheaper and under a different marketing name. On a harvested chip, any of the following can be disabled: - CUs (Compute Units) - RBs (Render Backend, aka. ROP) - Memory channels (ie. the chip has a lower bandwidth) - TCCs (ie. less L2 cache) Handle chips with harvested TCCs by patching the registers that configure how TCCs are mapped. If some TCCs are disabled, we need to make sure that the disabled TCCs are not used, and the remaining TCCs are used optimally. TCP_CHAN_STEER_LO/HI control which TCC is used by TCP channels. TCP_ADDR_CONFIG.NUM_TCC_BANKS controls how many channels are used. Note that the TCC configuration is highly relevant to performance. Suboptimal configuration (eg. CHAN_STEER=0) can significantly reduce gaming performance. For optimal performance: - Rely on the CHAN_STEER from the golden registers table, only skip disabled TCCs but keep the mapping order. - Limit NUM_TCC_BANKS to number of active TCCs to avoid thrashing, which performs better than using the same TCC twice. v2: - Also consider CGTS_USER_TCC_DISABLE for disabled TCCs. Link: https://bugs.freedesktop.org/show_bug.cgi?id=60879 Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/2664 Fixes: 2cd46ad22383 ("drm/amdgpu: add graphic pipeline implementation for si v8") Signed-off-by: Timur Kristóf Reviewed-by: Christian König Signed-off-by: Alex Deucher (cherry picked from commit 00218d15528fab9f6b31241fe5904eea4fcaa30d) Signed-off-by: Sasha Levin

drm/amdgpu/uvd3.1: Don't validate the firmware when already validated

2026-06-01T15:39:27+00:00

[ Upstream commit 13e4cf116dbf7a1fb8123a59bea2c098f30d3736 ] UVD 3.1 firmware validation seems to always fail after attempting it when it had already been validated. (This works similarly with the VCE 1.0 as well.) Don't attempt repeating the validation when it's already done. This caused issues in situations when the system isn't able to suspend the GPU properly and so the GPU isn't actually powered down. Then amdgpu would fail when calling the IP block resume function. Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/2887 Fixes: bb7978111dd3 ("drm/amdgpu: fix SI UVD firmware validate resume fail") Signed-off-by: Timur Kristóf Reviewed-by: Christian König Signed-off-by: Alex Deucher (cherry picked from commit 889a2cfd889c4a4dd9d0c89ce9a8e60b78be71dd) Signed-off-by: Sasha Levin

drm/amdgpu: fix spelling typos

2026-06-01T15:39:27+00:00

[ Upstream commit ce43abd7ec9464cf954f90e1c69e11768b02fa0a ] Found some typos while exploring amdgpu code. Signed-off-by: Alexandre Demers Signed-off-by: Alex Deucher Stable-dep-of: 13e4cf116dbf ("drm/amdgpu/uvd3.1: Don't validate the firmware when already validated") Signed-off-by: Sasha Levin

drm/amdgpu/gfx10: look at the right prop for gfx queue priority

2026-06-01T15:39:10+00:00

[ Upstream commit 355d96cdec5c61fd83f7eb54f1a28e38809645d6 ] Look at hqd_queue_priority rather than hqd_pipe_priority. In practice, it didn't matter as both were always set for kernel queues, but that will change in the future. Fixes: b07d1d73b09e ("drm/amd/amdgpu: Enable high priority gfx queue") Reviewed-by：Jesse Zhang Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdgpu: Add default case in DVI mode validation

2026-06-01T15:39:10+00:00

[ Upstream commit e6020a55b8e364d15eac27f9c788e13114eec6b7 ] amdgpu_connector_dvi_mode_valid() assigns max_digital_pixel_clock_khz based on connector_object_id using a switch statement that lacks a default case. In practice this code path should never be hit because the existing cases already cover all digital connector types that this function is used for. This is also legacy display code which is not used for new hardware. Add a default case returning MODE_BAD to make the switch exhaustive and silence the static analyzer smatch error. The new branch is effectively defensive and should never be reached during normal operation. Fixes: 585b2f685c56 ("drm/amdgpu: Respect max pixel clock for HDMI and DVI-D (v2)") Cc: Dan Carpenter Cc: Timur Kristóf Cc: Alex Deucher Cc: Christian König Signed-off-by: Srinivasan Shanmugam Acked-by: Alex Deucher Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdgpu/vcn4: Avoid overflow on msg bound check

2026-06-01T15:39:04+00:00

commit 65bce27ea6192320448c30267ffc17ffa094e713 upstream. As pointed out by SDL, the previous condition may be vulnerable to overflow. Fixes: 0a78f2bac142 ("drm/amdgpu/vcn4: Prevent OOB reads when parsing dec msg") Cc: SDL Signed-off-by: Benjamin Cheng Reviewed-by: Ruijing Dong Signed-off-by: Alex Deucher (cherry picked from commit 3c5367d950140d4ec7af830b2268a5a6fdaa3885) Signed-off-by: Greg Kroah-Hartman

drm/amdgpu/vcn3: Avoid overflow on msg bound check

2026-06-01T15:39:04+00:00

commit e6e9faba8100628990cccd13f0f044a648c303cf upstream. As pointed out by SDL, the previous condition may be vulnerable to overflow. Fixes: b193019860d6 ("drm/amdgpu/vcn3: Prevent OOB reads when parsing dec msg") Cc: SDL Signed-off-by: Benjamin Cheng Reviewed-by: Ruijing Dong Signed-off-by: Alex Deucher (cherry picked from commit db00257ac9e4a51eb2515aaea161a019f7125e10) Signed-off-by: Greg Kroah-Hartman

drm/amdgpu/sdma4: replace BUG_ON with WARN_ON in fence emission

2026-06-01T15:39:03+00:00

commit 78d2e624fa073c14970aa097adcf3ea31c157a66 upstream. sdma_v4_0_ring_emit_fence() contains two BUG_ON(addr & 0x3) assertions that verify fence writeback addresses are dword-aligned. These assertions can be reached from unprivileged userspace via crafted DRM_IOCTL_AMDGPU_CS submissions, causing a fatal kernel panic in a scheduler worker thread. Replace both BUG_ON() calls with WARN_ON() to log the condition without crashing the kernel. A misaligned fence address at this point indicates a driver bug, but crashing the kernel is never the correct response when the assertion is reachable from userspace. The CS IOCTL path is the correct place to filter invalid submissions; the ring emission callback is too late to do anything about it. Fixes: 2130f89ced2c ("drm/amdgpu: add SDMA v4.0 implementation (v2)") Reviewed-by: Christian König Signed-off-by: John B. Moore Signed-off-by: Alex Deucher (cherry picked from commit b90250bd933afd1ba94d86d6b13821997b22b18e) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdgpu/gfx9: drop unnecessary 64-bit fence flag check in KIQ

2026-06-01T15:39:02+00:00

commit 7bbfb2559bcec39d1a4e1182d931a2046112c352 upstream. Remove the BUG_ON(flags & AMDGPU_FENCE_FLAG_64BIT) assertion from gfx_v9_0_ring_emit_fence_kiq(). The KIQ hardware supports 64-bit fence writes; the 32-bit writeback address constraint is an upper-layer convention, not a hardware limitation. The check serves no purpose and should not be present. Found by code inspection while investigating related BUG_ON assertions in the GFX and compute ring emission paths. Reviewed-by: Christian König Signed-off-by: John B. Moore Signed-off-by: Alex Deucher (cherry picked from commit 1b1101a46a426bb4328116bb5273c326a2780389) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdgpu: zero-initialize GART table on allocation

2026-06-01T15:39:02+00:00

commit e6c2e6c2e1fa066968a16aca1cb66cd1bdde7741 upstream. GART TLB is flushed after unmapping but not after mapping. Since amdgpu_bo_create_kernel() does not zero-initialize the buffer, when a single PTE is written the TLB may speculatively load other uninitialized entries from the same cacheline. Those garbage entries can appear valid, and a subsequent write to another PTE in the same cacheline may cause the GPU to use a stale garbage PTE from the TLB. Fix this by calling memset_io() to zero-initialize the GART table with gart_pte_flags immediately after allocation. Using AMDGPU_GEM_CREATE_VRAM_CLEARED, SDMA-based clear will not work since SDMA needs GART to be initialized to work. Suggested-by: Felix Kuehling Signed-off-by: Philip Yang Reviewed-by: Christian König Signed-off-by: Alex Deucher (cherry picked from commit d9af8263b82b6eaa60c5718e0c6631c5037e4b24) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman