kernel/linux.git/drivers/gpu/drm/amd/amdgpu, branch v5.15.209

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

2026-06-01T15:35:41+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

2026-06-01T15:35:41+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

2026-06-01T15:35:41+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/vcn3: Avoid overflow on msg bound check

2026-06-01T15:35:26+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

2026-06-01T15:35:26+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

2026-06-01T15:35:25+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/vcn3: Prevent OOB reads when parsing dec msg

2026-06-01T15:35:25+00:00

commit b193019860d61e92da395eae2011f2f6716b182f upstream. Check bounds against the end of the BO whenever we access the msg. Signed-off-by: Benjamin Cheng Reviewed-by: Christian König Reviewed-by: Ruijing Dong Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdgpu: fix zero-size GDS range init on RDNA4

2026-06-01T15:35:18+00:00

commit 095a8b0ad3c3b5cdc3850d961adb8a8f735220bb upstream. RDNA4 (GFX 12) hardware removes the GDS, GWS, and OA on-chip memory resources. The gfx_v12_0 initialisation code correctly leaves adev->gds.gds_size, adev->gds.gws_size, and adev->gds.oa_size at zero to reflect this. amdgpu_ttm_init() unconditionally calls amdgpu_ttm_init_on_chip() for each of these resources regardless of size. When the size is zero, amdgpu_ttm_init_on_chip() forwards the call to ttm_range_man_init(), which calls drm_mm_init(mm, 0, 0). drm_mm_init() immediately fires DRM_MM_BUG_ON(start + size <= start) -- trivially true when size is zero -- crashing the kernel during modprobe of amdgpu on an RX 9070 XT. Guard against this by returning 0 early from amdgpu_ttm_init_on_chip() when size_in_page is zero. This skips TTM resource manager registration for hardware resources that are absent, without affecting any other GPU type. DRM_MM_BUG_ON() only asserts if CONFIG_DRM_DEBUG_MM is enabled in the kernel config. This is apparently rarely enabled as these chips have been in the market for over a year and this issue was only reported now. Link: https://lore.kernel.org/all/bug-221376-2300@https.bugzilla.kernel.org%2F/ Link: https://bugzilla.kernel.org/show_bug.cgi?id=221376 Oops-Analysis: http://oops.fenrus.org/reports/bugzilla.korg/221376/report.html Assisted-by: GitHub Copilot:Claude Sonnet 4.6 linux-kernel-oops-x86. Signed-off-by: Arjan van de Ven Cc: Alex Deucher Cc: "Christian König" Cc: amd-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Alex Deucher (cherry picked from commit 5719ce5865279cad4fd5f01011fe037168503f2d) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdgpu: unmap and remove csa_va properly

2026-06-01T15:35:10+00:00

[ Upstream commit 5daff15cd013422bc6d1efcfe82b586800025384 ] Root PD BO should be reserved before unmap and remove a bo_va from VM otherwise lockdep will complain. v2: check fpriv->csa_va is not NULL instead of amdgpu_mcbp (christian) [14616.936827] WARNING: CPU: 6 PID: 1711 at drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1762 amdgpu_vm_bo_del+0x399/0x3f0 [amdgpu] [14616.937096] Call Trace: [14616.937097] [14616.937102] amdgpu_driver_postclose_kms+0x249/0x2f0 [amdgpu] [14616.937187] drm_file_free+0x1d6/0x300 [drm] [14616.937207] drm_close_helper.isra.0+0x62/0x70 [drm] [14616.937220] drm_release+0x5e/0x100 [drm] [14616.937234] __fput+0x9f/0x280 [14616.937239] ____fput+0xe/0x20 [14616.937241] task_work_run+0x61/0x90 [14616.937246] exit_to_user_mode_prepare+0x215/0x220 [14616.937251] syscall_exit_to_user_mode+0x2a/0x60 [14616.937254] do_syscall_64+0x48/0x90 [14616.937257] entry_SYSCALL_64_after_hwframe+0x63/0xcd Signed-off-by: Lang Yu Acked-by: Christian König Signed-off-by: Alex Deucher [ The context change is due to the commit e56694f718f0 ("drm/amdgpu: rename amdgpu_vm_bo_rmv to _del") in v5.18 and the proper adoption is done which is irrelevant to the logic of this patch. ] Signed-off-by: Johnny Hao Signed-off-by: Greg Kroah-Hartman

drm/amdgpu: Fix use-after-free race in VM acquire

2026-04-18T08:33:15+00:00

commit 2c1030f2e84885cc58bffef6af67d5b9d2e7098f upstream. Replace non-atomic vm->process_info assignment with cmpxchg() to prevent race when parent/child processes sharing a drm_file both try to acquire the same VM after fork(). Reviewed-by: Harish Kasiviswanathan Signed-off-by: Alysa Liu Signed-off-by: Alex Deucher (cherry picked from commit c7c573275ec20db05be769288a3e3bb2250ec618) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman