- 13 Apr, 2023 4 commits
-
-
Mukul Joshi authored
Rework retry fault removal from the software filter by storing an expired timestamp for a fault that is being removed. When a new fault comes, and it matches an entry in the sw filter, it will be added as a new fault only when its timestamp is greater than the timestamp expiry of the fault in the sw filter. This helps in avoiding stale faults being added back into the filter and preventing legitimate faults from being handled. Suggested-by:
Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by:
Mukul Joshi <mukul.joshi@amd.com> Reviewed-by:
Philip Yang <Philip.Yang@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Mukul Joshi authored
This patch enables the IH retry CAM on GFX9 series cards. This retry filter is used to prevent sending lots of retry interrupts in a short span of time and overflowing the IH ring buffer. This will also help reduce CPU interrupt workload. Signed-off-by:
-
Tom Rix authored
clang with W=1 reports drivers/gpu/drm/amd/amdgpu/../pm/swsmu/amdgpu_smu.c:1700:6: error: variable 'num_of_active_display' set but not used [-Werror,-Wunused-but-set-variable] int num_of_active_display = 0; ^ This variable is not used so remove it. Fixes: 75145aab ("drm/amdgpu/swsmu: clean up a bunch of stale interfaces") Reviewed-by:Nick Desaulniers <ndesaulniers@google.com> Reviewed-by:
Evan Quan <evan.quan@amd.com> Signed-off-by:
Tom Rix <trix@redhat.com> Signed-off-by:
-
Alex Deucher authored
All chips that support RAS also support IP discovery, so use the IP versions rather than a mix of IP versions and asic types. Checking the validity of the atom_ctx pointer is not required as the vbios is already fetched at this point. v2: add comments to id asic types based on feedback from Luben Reviewed-by:
Luben Tuikov <luben.tuikov@amd.com> Signed-off-by:
-
- 11 Apr, 2023 36 commits
-
-
Graham Sider authored
Enable SDMA queue empty context switching. SDMA context switch due to quantum programming no longer done here (as of sdma v6), so re-name sdma_v6_0_ctx_switch_enable to sdma_v6_0_ctxempty_int_enable to reflect this. Also program SDMAx_QUEUEx_SCHEDULE_CNTL for context switch due to quantum in KFD. Set to amdgpu_sdma_phase_quantum (defaults to 32 i.e. 3200us). Signed-off-by:
Graham Sider <Graham.Sider@amd.com> Reviewed-by:
Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Reviewed-by:
Stanley Yang <Stanley.Yang@amd.com> Signed-off-by:
-
Sreekant Somasekharan authored
CP_HQD_HQ_STATUS0[29] bit will be used by CPFW to acknowledge whether PCIe atomics are supported. The default value of this bit is set to 0. Driver will check whether PCIe atomics are supported and set the bit to 1 if supported. This will force CPFW to use real atomic ops. If the bit is not set, CPFW will default to read/modify/write using the firmware itself. This is applicable only to GFX11 RS64 CP with MEC FW >= 509. If MEC FW < 509 and for all GFX11 F32 CP, PCIe atomics needs to be supported else it will skip the device. This commit also involves moving amdgpu_amdkfd_device_probe() function call after per-IP early_init loop in amdgpu_device_ip_early_init() function so as to check for RS64 enabled device. Signed-off-by:
Sreekant Somasekharan <sreekant.somasekharan@amd.com> Reviewed-by:
-
Srinivasan Shanmugam authored
Add some more logging for DP link traning test pattern seqeunces for better debugging. Cc: Fangzhi Zuo <Jerry.Zuo@amd.com> Cc: Harry Wentland <harry.wentland@amd.com> Cc: Leo Li <sunpeng.li@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Reviewed-by:
Fangzhi Zuo <Jerry.Zuo@amd.com> Signed-off-by:
-
Stanley.Yang authored
XGMI RAS should be according to the gmc xgmi physical nodes number, XGMI RAS should not be enabled if xgmi num_physical_nodes is zero. Signed-off-by:
Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by:
-
Stanley.Yang authored
Aldebaran supports VCN and JPEG RAS, it reports unexpected block id message during VCN and JPEG RAS initialization if VCN and JPEG block id not defined. Signed-off-by:
-
Pierre-Eric Pelloux-Prayer authored
This achieves the same result as the sequence used in emit_flush_gpu_tlb but the invalidation is now a single packet instead of the 3 packets required to implement reg_write_reg_wait. Signed-off-by:
Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com> Reviewed-by:
Christian König <christian.koenig@amd.com> Reviewed-by:
Monk Liu <monk.liu@amd.com> Reviewed-by:
-
Srinivasan Shanmugam authored
Update the existing log with DP LT downspread info: [Downstream devices shall support down spreading of the link clock. The down-spread amplitude shall either be disabled (0.0%) or up to 0.5%, as written by the upstream device to the DOWNSPREAD_CTRL register (DPCD 00107h). The modulation frequency range shall be 30 to 33 kHz] Besides, fix checkpatch warning: CHECK: Alignment should match open parenthesis Cc: Mario Limonciello <mario.limonciello@amd.com> Cc: Harry Wentland <harry.wentland@amd.com> Cc: Leo Li <sunpeng.li@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Aurabindo Pillai <aurabindo.pillai@amd.com> Signed-off-by:
-
Tom Rix authored
clang with W=1 reports drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_link_enc_cfg.c:625:6: error: variable 'matching_stream_ptrs' set but not used [-Werror,-Wunused-but-set-variable] int matching_stream_ptrs = 0; ^ This variable is not used so remove it. Reviewed-by:Hamza Mahfooz <hamza.mahfooz@amd.com> Signed-off-by:
-
Tom Rix authored
smatch reports drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:44:24: warning: symbol 'dml20_funcs' was not declared. Should it be static? drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:51:24: warning: symbol 'dml20v2_funcs' was not declared. Should it be static? drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:58:24: warning: symbol 'dml21_funcs' was not declared. Should it be static? drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:65:24: warning: symbol 'dml30_funcs' was not declared. Should it be static? drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:72:24: warning: symbol 'dml31_funcs' was not declared. Should it be static? drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:79:24: warning: symbol 'dml314_funcs' was not declared. Should it be static? drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.c:86:24: warning: symbol 'dml32_funcs' was not declared. Should it be static? These variables are only used in one file so should be static. Cleanup whitespace, use tabs consistently for indents. Signed-off-by:
-
Tom Rix authored
drm/amd/display: set variables aperture_default_system and context0_default_system storage-class-specifier to static smatch reports drivers/gpu/drm/amd/amdgpu/../display/dc/dcn10/dcn10_hubp.c:758:10: warning: symbol 'aperture_default_system' was not declared. Should it be static? drivers/gpu/drm/amd/amdgpu/../display/dc/dcn10/dcn10_hubp.c:759:10: warning: symbol 'context0_default_system' was not declared. Should it be static? These variables are only used in one file so should be static. Signed-off-by:
-
Tom Rix authored
smatch reports drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn314/dcn314_fpu.c:100:37: warning: symbol 'dcn3_14_soc' was not declared. Should it be static? This variable is only used in one file so should be static. Signed-off-by:
-
Lijo Lazar authored
Fix below warning due to incompatible types in conditional operator ../pm/swsmu/smu13/smu_v13_0_6_ppt.c:315:17: sparse: sparse: incompatible types in conditional expression (different base types): Signed-off-by:
Lijo Lazar <lijo.lazar@amd.com> Reported-by:
kernel test robot <lkp@intel.com> Reviewed-by:
Guchun Chen <guchun.chen@amd.com> Link: https://lore.kernel.org/oe-kbuild-all/202303082135.NjdX1Bij-lkp@intel.com/Signed-off-by:
-
Horatio Zhang authored
Correct the max shader clock reporting on SMU 13.0.7. Signed-off-by:
Horatio Zhang <Hongkun.Zhang@amd.com> Reviewed-by:
Kenneth Feng <kenneth.feng@amd.com> Signed-off-by:
-
Horatio Zhang authored
Correct the pstate standard/peak profiling mode clock settings for SMU13.0.7. Signed-off-by:
-
Tong Liu01 authored
[why] regGOLDEN_TSC_COUNT_LOWER/regGOLDEN_TSC_COUNT_UPPER are protected and unaccessible under sriov. The clock counter high bit may update during reading process. [How] Replace regGOLDEN_TSC_COUNT_LOWER/regGOLDEN_TSC_COUNT_UPPER with regCP_MES_MTIME_LO/regCP_MES_MTIME_HI to get gpu clock under sriov. Refine get gpu clock counter method to make the result more precise. Signed-off-by:
Tong Liu01 <Tong.Liu01@amd.com> Acked-by:
-
YiPeng Chai authored
Optimize redundant code in umc_v6_7. Signed-off-by:
YiPeng Chai <YiPeng.Chai@amd.com> Reviewed-by:
Tao Zhou <tao.zhou1@amd.com> Signed-off-by:
-
lyndonli authored
Fix sdma v4 sw fini error for sdma 4.2.2 to solve the following general protection fault [ +0.108196] general protection fault, probably for non-canonical address 0xd5e5a4ae79d24a32: 0000 [#1] PREEMPT SMP PTI [ +0.000018] RIP: 0010:free_fw_priv+0xd/0x70 [ +0.000022] Call Trace: [ +0.000012] <TASK> [ +0.000011] release_firmware+0x55/0x80 [ +0.000021] amdgpu_ucode_release+0x11/0x20 [amdgpu] [ +0.000415] amdgpu_sdma_destroy_inst_ctx+0x4f/0x90 [amdgpu] [ +0.000360] sdma_v4_0_sw_fini+0xce/0x110 [amdgpu] Signed-off-by:
lyndonli <Lyndon.Li@amd.com> Reviewed-by:
Likun Gao <Likun.Gao@amd.com> Reviewed-by:
Feifei Xu <Feifei.Xu@amd.com> Signed-off-by:
-
Shane Xiao authored
For DMA-MAP userptr on other GPUs, the dma address array will be populated in amdgpu_ttm_backend_bind. Remove the redundant call from the driver. v2: update the comment Signed-off-by:
Shane Xiao <shane.xiao@amd.com> Reviewed-by:
-
YiPeng Chai authored
Optimize redundant code in umc_v8_10 Signed-off-by:
-
Shane Xiao authored
For SG BO to DMA-map userptrs on other GPUs, the SG BO need inherit MTYPEs in PTEs from original BO. If we set the flags, the device can be coherent with the CPUs and other GPUs. v2: 1. Drop unnecessary flags check 2. Remove local variable align Signed-off-by:
-
Guilherme G. Piccoli authored
The comment mentions that power1 cap attributes are not supported on Vangogh, but the opposite is indeed valid: for APUs, only Vangogh is supported. While at it, also fixed the Renoir comment below (thanks Melissa for noticing that!). Cc: Lijo Lazar <lijo.lazar@amd.com> Cc: Melissa Wen <mwen@igalia.com> Signed-off-by:
Guilherme G. Piccoli <gpiccoli@igalia.com> Signed-off-by:
-
Shane Xiao authored
For userptr bo with iommu on, multiple GPUs use same system memory dma mapping address when both adev and bo_adev are in identity mode or in the same iommu group. If RAM direct map to one GPU, other GPUs can share the original BO in order to reduce dma address array usage when RAM can direct map to these GPUs. However, we should explicit check whether RAM can direct map to all these GPUs. This patch fixes a potential issue that where RAM is direct mapped on some but not all GPUs. v2: 1. Update comment 2. Add helper function reuse_dmamap Signed-off-by:
-
Srinivasan Shanmugam authored
The driver doesn't resubmit jobs on hangs any more, hence drop the hang limit parameter - amdgpu_job_hang_limit, wherever it is used. Suggested-by:
Mario Limonciello <mario.limonciello@amd.com> Signed-off-by:
-
Igor Artemiev authored
The adev->dm.dc pointer can be NULL and dereferenced in amdgpu_dm_fini() without checking. Add a NULL pointer check before calling dc_dmub_srv_destroy(). Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 9a71c7d3 ("drm/amd/display: Register DMUB service with DC") Signed-off-by:
Igor Artemiev <Igor.A.Artemiev@mcst.ru> Signed-off-by:
-
Aric Cyr authored
This DC version brings along: - FW Release 0.0.161.0 - Improvements on FPO/FAMS - Correction to DML calculation - Fix to multiple clock related issues Acked-by:
Qingqing Zhuo <qingqing.zhuo@amd.com> Signed-off-by:
Aric Cyr <aric.cyr@amd.com> Tested-by:
Daniel Wheeler <daniel.wheeler@amd.com> Signed-off-by:
-
Mario Limonciello authored
The array is hardcoded to 8 in atomfirmware.h, but firmware provides a bigger one sometimes. Deferencing the larger array causes an out of bounds error. commit 4fc1ba4a ("drm/amd/display: fix array index out of bound error in bios parser") fixed some of this, but there are two other cases not covered by it. Fix those as well. Reported-by: erhard_f@mailbox.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=214853 Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2473Signed-off-by:
Harry Wentland <harry.wentland@amd.com> Signed-off-by:
-
Anthony Koo authored
- Add command to idle opt. - Rename d3 entry event and add idle trigger param on notify event. - Add bit to fw boot status to notify status when hardware is powered up. Reviewed-by:
Anthony Koo <Anthony.Koo@amd.com> Tested-by:
-
Michael Strauss authored
[WHY] New sequence for transparent mode DP1.x link training was provided by LTTPR vendor [HOW] Implement new FIXED_VS sequence, increase LT retry count to minimize any potential intermittent lightup failures Reviewed-by:
Jun Lei <Jun.Lei@amd.com> Acked-by:
Michael Strauss <michael.strauss@amd.com> Tested-by:
-
Yifan Zha authored
[Why] As MES KIQ is dequeued, tell RLC that KIQ is inactive [How] Clear the RLC_CP_SCHEDULERS Active bit which RLC checks KIQ status In addition, driver can halt MES under SRIOV when unloading driver v2: Use scheduler0 mask to clear KIQ portion of RLC_CP_SCHEDULERS Signed-off-by:
Yifan Zha <Yifan.Zha@amd.com> Reviewed-by:
Horace Chen <horace.chen@amd.com> Signed-off-by:
-
Charlene Liu authored
[why] based on dscclk instance offset check conditiona program dscclk Reviewed-by:
Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com> Acked-by:
Charlene Liu <Charlene.Liu@amd.com> Tested-by:
-
Alvin Lee authored
[Description] - On init if a display is connected, we need to maintain the DISPCLK frequency - Even though DPG_EN=1, the display still requires the correct timing or it could cause audio corruption (if DISPCLK freq is reduced) - Read the current DISPCLK freq and request the same value to ensure the timing is valid and unchanged - However, add option to do a full pipe power down (including link) which will also avoid audio related issues - Disabled for the time being on dcn32 Reviewed-by:
Alvin Lee <Alvin.Lee2@amd.com> Tested-by:
-
Alvin Lee authored
[Description] - When determining FPO support, include FPO + VActive support - Support FPO + VActive if one display meets regular requirements for FPO and the second display is able to switch in VACTIVE with a given amount of margin Reviewed-by:
-
Paul Hsieh authored
[Why] In 2560x1600@240p eDP panel, driver use lowest voltage level to play 1080p video cause underflow. According to HW SPEC, the senario should use high voltage level. [How] ChromaPre value is zero when bandwidth validation. Correct ChromaPre calculation. Reviewed-by:
Paul Hsieh <Paul.Hsieh@amd.com> Tested-by:
-
Hamza Mahfooz authored
To enable root clock optimizations, we need a number of register writes and need to account for the difference in DPSTREAMCLK between DCN31 and DCN314. To prevent issues, add a number of register writes to DCCG_MASK_SH_LIST_DCN314_COMMON(), and define dccg314_init() which is mostly in alignment with dccg31_init() but accounts for the new DPSTREAMCLK sequence. Reviewed-by:
-
Zhikai Zhai authored
[WHY] It will introduce the extra warnning log on some asic that doesn't register [HOW] Add the register on dcn32 Reviewed-by:
Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com> Acked-by:
Zhikai Zhai <zhikai.zhai@amd.com> Tested-by:
-
Alvin Lee authored
[Description] - If we find that applying FAMS doesn't reduce the voltage level, we will not use it - Ensure to clear the stream flags indicating FAMS if we hit this case Reviewed-by:
-
