- 10 Nov, 2023 8 commits
-
-
https://gitlab.freedesktop.org/agd5f/linuxDaniel Vetter authored
amd-drm-next-6.7-2023-11-10: amdgpu: - SR-IOV fixes - DMCUB fixes - DCN3.5 fixes - DP2 fixes - SubVP fixes - SMU14 fixes - SDMA4.x fixes - Suspend/resume fixes - AGP regression fix - UAF fixes for some error cases - SMU 13.0.6 fixes - Documentation fixes - RAS fixes - Hotplug fixes - Scheduling entity ordering fix - GPUVM fixes Signed-off-by:
Daniel Vetter <daniel.vetter@ffwll.ch> From: Alex Deucher <alexander.deucher@amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/20231110190703.4741-1-alexander.deucher@amd.com
-
Christian König authored
When clearing the root PD fails we need to properly release it again. Signed-off-by:
Christian König <christian.koenig@amd.com> Acked-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
-
Felix Kuehling authored
mem = bo->tbo.resource may be NULL in amdgpu_vm_bo_update. Fixes: 18025378 ("drm/ttm: stop allocating dummy resources during BO creation") Signed-off-by:
Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by:
-
Alex Deucher authored
We need kernel scheduling entities to deal with handle clean up if apps are not cleaned up properly. With commit 56e44960 ("drm/sched: Convert the GPU scheduler to variable number of run-queues") the scheduler entities have to be created after scheduler init, so change the ordering to fix this. v2: Leave logic in UVD and VCE code Fixes: 56e44960 ("drm/sched: Convert the GPU scheduler to variable number of run-queues") Reviewed-by:
Luben Tuikov <ltuikov89@gmail.com> Signed-off-by:
-
Tim Huang authored
The kfd_resume needs to touch GC registers to enable the interrupts, it needs to be done before GFXOFF is enabled to ensure that the GFX is not off and GC registers can be touched. So move kfd_resume before the amdgpu_device_ip_late_init which enables the CGPG/GFXOFF. Signed-off-by:
Tim Huang <Tim.Huang@amd.com> Reviewed-by:
Yifan Zhang <yifan1.zhang@amd.com> Signed-off-by:
-
Mario Limonciello authored
If a user has disabled GFXOFF this may cause problems for the suspend sequence. Ensure that it is enabled in amdgpu_acpi_is_s0ix_active(). The system won't reach the deepest state but it also won't hang. Signed-off-by:
Mario Limonciello <mario.limonciello@amd.com> Reviewed-by:
-
git://anongit.freedesktop.org/drm/drm-miscDaniel Vetter authored
drm-misc-fixes for v6.7-rc1: qxl: - qxl memory leak fix. syncobj: - Fix waiting for DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE vc4: - Fix UAF in mock helpers Signed-off-by:
-
Daniel Vetter authored
Merge tag 'drm-intel-next-fixes-2023-11-08' of git://anongit.freedesktop.org/drm/drm-intel into drm-next drm/i915 fixes for v6.7-rc1: - Fix null dereference when perf interface is not available - Fix a -Wstringop-overflow warning - Fix a -Wformat-truncation warning in intel_tc_port_init - Flush WC GGTT only on required platforms - Fix MTL HBR3 rate support on C10 phy and eDP - Fix MTL notify_guc for multi-GT - Bump GLK CDCLK frequency when driving multiple pipes - Fix potential spectre vulnerability Signed-off-by:
-
- 09 Nov, 2023 25 commits
-
-
Victor Lu authored
W/RREG32_RLC is hardedcoded to use instance 0. W/RREG32_SOC15_RLC should be used instead when inst != 0. v2: rebase Signed-off-by:
Victor Lu <victorchengchi.lu@amd.com> Reviewed-by:
Lijo Lazar <lijo.lazar@amd.com> Signed-off-by:
-
Victor Lu authored
amdgpu_kiq_wreg/rreg is hardcoded to use MEC engine 0. Add an xcc_id parameter to amdgpu_kiq_wreg/rreg, define W/RREG32_XCC and amdgpu_device_xcc_wreg/rreg to use the new xcc_id parameter. Using amdgpu_sriov_runtime to determine whether to access via kiq or RLC is sufficient for now. v5: add condition in amdgpu_device_xcc_w/rreg, remove trace func call v4: avoid using amdgpu_sriov_w/rreg v3: use W/RREG32_XCC to handle non-kiq case v2: define amdgpu_device_xcc_wreg/rreg instead of changing parameters of amdgpu_device_wreg/rreg Signed-off-by: -
Yang Wang authored
add pcs xgmi ras error query support for smu v13.0.6. Signed-off-by:
Yang Wang <kevinyang.wang@amd.com> Reviewed-by:
Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by:
-
Vitaly Prosyak authored
When software 'pci unplug' using IGT is executed we got a sysfs directory entry is NULL for differant ras blocks like hdp, umc, etc. Before call 'sysfs_remove_file_from_group' and 'sysfs_remove_group' check that 'sd' is not NULL. [ +0.000001] RIP: 0010:sysfs_remove_group+0x83/0x90 [ +0.000002] Code: 31 c0 31 d2 31 f6 31 ff e9 9a a8 b4 00 4c 89 e7 e8 f2 a2 ff ff eb c2 49 8b 55 00 48 8b 33 48 c7 c7 80 65 94 82 e8 cd 82 bb ff <0f> 0b eb cc 66 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 [ +0.000001] RSP: 0018:ffffc90002067c90 EFLAGS: 00010246 [ +0.000002] RAX: 0000000000000000 RBX: ffffffff824ea180 RCX: 0000000000000000 [ +0.000001] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 [ +0.000001] RBP: ffffc90002067ca8 R08: 0000000000000000 R09: 0000000000000000 [ +0.000001] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 [ +0.000001] R13: ffff88810a395f48 R14: ffff888101aab0d0 R15: 0000000000000000 [ +0.000001] FS: 00007f5ddaa43a00(0000) GS:ffff88841e800000(0000) knlGS:0000000000000000 [ +0.000002] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ +0.000001] CR2: 00007f8ffa61ba50 CR3: 0000000106432000 CR4: 0000000000350ef0 [ +0.000001] Call Trace: [ +0.000001] <TASK> [ +0.000001] ? show_regs+0x72/0x90 [ +0.000002] ? sysfs_remove_group+0x83/0x90 [ +0.000002] ? __warn+0x8d/0x160 [ +0.000001] ? sysfs_remove_group+0x83/0x90 [ +0.000001] ? report_bug+0x1bb/0x1d0 [ +0.000003] ? handle_bug+0x46/0x90 [ +0.000001] ? exc_invalid_op+0x19/0x80 [ +0.000002] ? asm_exc_invalid_op+0x1b/0x20 [ +0.000003] ? sysfs_remove_group+0x83/0x90 [ +0.000001] dpm_sysfs_remove+0x61/0x70 [ +0.000002] device_del+0xa3/0x3d0 [ +0.000002] ? ktime_get_mono_fast_ns+0x46/0xb0 [ +0.000002] device_unregister+0x18/0x70 [ +0.000001] i2c_del_adapter+0x26d/0x330 [ +0.000002] arcturus_i2c_control_fini+0x25/0x50 [amdgpu] [ +0.000236] smu_sw_fini+0x38/0x260 [amdgpu] [ +0.000241] amdgpu_device_fini_sw+0x116/0x670 [amdgpu] [ +0.000186] ? mutex_lock+0x13/0x50 [ +0.000003] amdgpu_driver_release_kms+0x16/0x40 [amdgpu] [ +0.000192] drm_minor_release+0x4f/0x80 [drm] [ +0.000025] drm_release+0xfe/0x150 [drm] [ +0.000027] __fput+0x9f/0x290 [ +0.000002] ____fput+0xe/0x20 [ +0.000002] task_work_run+0x61/0xa0 [ +0.000002] exit_to_user_mode_prepare+0x150/0x170 [ +0.000002] syscall_exit_to_user_mode+0x2a/0x50 Cc: Hawking Zhang <hawking.zhang@amd.com> Cc: Luben Tuikov <luben.tuikov@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Christian Koenig <christian.koenig@amd.com> Signed-off-by:
Vitaly Prosyak <vitaly.prosyak@amd.com> Reviewed-by:
Luben Tuikov <luben.tuikov@amd.com> Signed-off-by:
-
José Pekkarinen authored
Spotted by coccicheck, there is a redundant check for v->SourcePixelFormat[k] != dm_444_16. This patch will remove it. The corresponding output follows. drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c:5130:86-122: duplicated argument to && or || Signed-off-by:
José Pekkarinen <jose.pekkarinen@foxhound.fi> Reviewed-by:
Aurabindo Pillai <aurabindo.pillai@amd.com> Signed-off-by:
-
Yang Wang authored
avoid driver to touch invalid mca reg. Signed-off-by:
-
Hawking Zhang authored
So driver doesn't touch invalid aca entries. Signed-off-by:
-
Yang Wang authored
add pcs xgmi v6.4.0 ras support Signed-off-by:
-
David Yat Sin authored
Change local memory type to MTYPE_UC on revision id 0 Signed-off-by:
David Yat Sin <David.YatSin@amd.com> Reviewed-by:
-
Yang Wang authored
disable mca debug mode for smu v13.0.6 by default. Signed-off-by:
-
Hawking Zhang authored
Direct error query mode and firmware error query mode are supported for now. Signed-off-by:
-
Yang Wang authored
refine smu mca driver to support query ras error from pmfw path. - correct gfx smu bank hwid (from mp5 to smu bank) - retire unused callback function in amdgpu_mca_smu_funcs{} - add new mca_bank_set{} structure to collect mca bank - move enum mca_reg_idx into amdgpu_mca.h header - add mca status register field decode macro Signed-off-by: -
Victor Lu authored
The following regs can only be programmed by the PF: HDP_MISC_CNTL HDP_NONSURFACE_BASE HDP_NONSURFACE_BASE_HI v2: update commit message Signed-off-by:
Samir Dhume <samir.dhume@amd.com> Signed-off-by:
-
Victor Lu authored
PCTL0_MMHUB_DEEPSLEEP_IB is blocked for VF access Signed-off-by:
-
Hunter Chasens authored
Resolves Sphinx unexpected indentation warning when compiling documentation (e.g. `make htmldocs`). Replaces tabs with spaces and adds a literal block to keep vertical formatting of the example power state list. Reviewed-by:
Hunter Chasens <hunter.chasens18@ncf.edu> Signed-off-by:
-
Yang Wang authored
correct smu v13.0.0 umc ras error check Signed-off-by:
-
Victor Lu authored
WREG32/RREG32_SOC15_IP_NO_KIQ and amdgpu_virt_kiq_reg_write_reg_wait are not using the correct rlcg interface or mec engine, respectively. Add xcc instance parameter to them. v4: Use GET_INST and squash commit with: "drm/amdgpu: Add xcc_inst param to amdgpu_virt_kiq_reg_write_reg_wait" v3: xcc not needed for MMMHUB v2: rebase Signed-off-by:
-
Victor Lu authored
The "rlcg_reg_access_supported" flag is missing. Add it back in. Signed-off-by:
-
Le Ma authored
The DS clock may exceed the limit as sclk dfll divider is 16 to target freq. Signed-off-by:
Le Ma <le.ma@amd.com> Reviewed-by:
-
Yang Wang authored
correct following amdgpu ip block version information: - gfx_v9_4_3 - sdma_v4_4_2 Signed-off-by:
Kenneth Feng <kenneth.feng@amd.com> Reviewed-by:
-
Lijo Lazar authored
Hide PCIe DPM attribute on SOCs with GC v9.4.2 and GC v9.4.3. Signed-off-by:
Asad Kamal <asad.kamal@amd.com> Signed-off-by:
-
Tao Zhou authored
set_xgmi_plpd_mode may be unsupported and this isn't error, no need to print warning for it. v2: add ret2 to save the status of psp_ras_trigger_error. Suggested-by: lijo.lazar@amd.com Signed-off-by:
Tao Zhou <tao.zhou1@amd.com> Reviewed-by:
-
Christian König authored
Otherwise userspace can spam the logs by using incorrect input values. Signed-off-by:
-
Christian König authored
We should not leak the pointer where we couldn't grab the reference on to the caller because it can be that the error handling still tries to put the reference then. Signed-off-by:
-
Alex Deucher authored
The default AGP settings were overwriting the IP selected ones since the default was getting set after the IP ones were selected. Fixes: de59b699 ("drm/amdgpu/gmc: set a default disable value for AGP") Link: https://lists.freedesktop.org/archives/amd-gfx/2023-November/100966.htmlTested-by:
Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com> Reviewed-by:
-
- 07 Nov, 2023 7 commits
-
-
Tao Zhou authored
Reset/query RAS error status and count. v2: use XGMI IP version instead of WAFL version. Signed-off-by:
-
Tao Zhou authored
The UE registe list is larger than CE list. Reported-by: yipeng.chai@amd.com Signed-off-by:
Stanley.Yang <Stanley.Yang@amd.com> Signed-off-by:
-
Tim Huang authored
For IMU enabled APUs, after sending the PrepareMp1ForUnload message to SMU in system_features_control, the RLC registers can't be touched. The driver to stop the rlc in suspending is no longer required. Signed-off-by:
-
Bragatheswaran Manickavel authored
The member variable enable_hpo_pg_support is already initialized and hence the reinitialization instruction can be removed. Issue identified using the doubleinit.cocci Coccinelle semantic patch script. Signed-off-by:
Bragatheswaran Manickavel <bragathemanick0908@gmail.com> Signed-off-by:
-
Lijo Lazar authored
Change return code to EOPNOTSUPP for unsupported functions. Use the error code information to hide sysfs nodes not valid for the SOC. Signed-off-by:
-
Lijo Lazar authored
Doorbell rptr/wptr can be set through multiple ways including direct register initialization. Disable doorbell during hw_fini once the ring is disabled so that during next module reload direct initialization takes effect. Also, move the direct initialization after minor update is set to 1 since rptr/wptr are reinitialized back to 0 which could be lower than the previous doorbell value (ex: cases like module reload). Signed-off-by:
-
Jiadong Zhu authored
Set the default reset method to mode2 for SMU IP v14.0.0 Signed-off-by:
Jiadong Zhu <Jiadong.Zhu@amd.com> Reviewed-by:
-
