- 02 Aug, 2019 16 commits
-
-
KyleMahlkuch authored
During kexec some adapters hit an EEH since they are not properly shut down in the radeon_pci_shutdown() function. Adding radeon_suspend_kms() fixes this issue. Signed-off-by:
KyleMahlkuch <kmahlkuc@linux.vnet.ibm.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Jay Cornwall authored
Following bitmap layout logic introduced by: "drm/amdgpu: support get_cu_info for Arcturus". v2: squash in fixup for gfx_v9_0.c (Alex) v3: squash in debug print output fix Signed-off-by:
Jay Cornwall <Jay.Cornwall@amd.com> Signed-off-by:
-
Le Ma authored
This change is because SE/SH layout on Arcturus is 8*1, different from 4*2(or 4*1) on Vega ASICs. Currently the cu bitmap array is 4x4 size, and besides the bitmap is used widely across SW stack. To mostly reduce the scale of impact, we make the cu bitmap array compatible with SE/SH layout on Arcturus. Then the store of cu bits of each shader array for Arcturus will be like below: SE0,SH0 --> bitmap[0][0] SE1,SH0 --> bitmap[1][0] SE2,SH0 --> bitmap[2][0] SE3,SH0 --> bitmap[3][0] SE4,SH0 --> bitmap[0][1] SE5,SH0 --> bitmap[1][1] SE6,SH0 --> bitmap[2][1] SE7,SH0 --> bitmap[3][1] Signed-off-by:Le Ma <le.ma@amd.com> Reviewed-by:
Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by:
-
Kent Russell authored
The registers used for VG20 are different in that certain performance counters were split off to TXCLK3/4. Vega10/12 doesn't have this, so add a new vg20_get_pcie_usage to reflect this change. Signed-off-by:
Kent Russell <kent.russell@amd.com> Reviewed-by:
-
Kent Russell authored
These are added for VG20, and are needed for PCIe bandwidth. Signed-off-by:
-
Andrey Grodzovsky authored
Fixes GPU reset crash. Signed-off-by:
Andrey Grodzovsky <andrey.grodzovsky@amd.com> Reviewed-by:
-
Felix Kuehling authored
Memory used by KFD applications can contain sensitive information that should not be leaked to other processes. The current approach to prevent leaks is to clear VRAM at allocation time. This is not effective because memory can be reused in other ways without being cleared. Synchronously clearing memory on the allocation path also carries a significant performance penalty. Stop clearing memory at allocation time. Instead mark the memory for wipe on release. Signed-off-by:
Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by:
Christian König <christian.koenig@amd.com> Signed-off-by:
-
Felix Kuehling authored
Wipe VRAM memory containing sensitive data when moving or releasing BOs. Clearing the memory is pipelined to minimize any impact on subsequent memory allocation latency. Use of a poison value should help debug future use-after-free bugs. When moving BOs, the existing ttm_bo_pipelined_move ensures that the memory won't be reused before being wiped. When releasing BOs, the BO is fenced with the memory fill operation, which results in queuing the BO for a delayed delete. v2: Move amdgpu_amdkfd_unreserve_memory_limit into amdgpu_bo_release_notify so that KFD can use memory that's still being cleared in the background Signed-off-by:
-
Felix Kuehling authored
This memory allocation flag will be used to indicate BOs containing sensitive data that should not be leaked to other processes. Signed-off-by:
-
Felix Kuehling authored
This notifies the driver that a BO is about to be released. Releasing a BO also invokes the move_notify callback from ttm_bo_cleanup_memtype_use, but that happens too late for anything that would add fences to the BO and require a delayed delete. Signed-off-by:
-
Leo Li authored
Using a static int array will cause errors if the given dm_pp_clk_type is out-of-bounds. For robustness, use a switch table, with a default case to handle all invalid values. v2: 0 is a valid clock type for smu_clk_type. Return SMU_CLK_COUNT instead on invalid mapping. Signed-off-by:Leo Li <sunpeng.li@amd.com> Reviewed-by:
Nicholas Kazlauskas <nicholas.kazlauskas@amd.com> Signed-off-by:
-
Nathan Chancellor authored
clang warns: drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_pp_smu.c:336:8: warning: implicit conversion from enumeration type 'enum smu_clk_type' to different enumeration type 'enum amd_pp_clock_type' [-Wenum-conversion] dc_to_smu_clock_type(clk_type), ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_pp_smu.c:421:14: warning: implicit conversion from enumeration type 'enum amd_pp_clock_type' to different enumeration type 'enum smu_clk_type' [-Wenum-conversion] dc_to_pp_clock_type(clk_type), ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ There are functions to properly convert between all of these types, use them so there are no longer any warnings. Fixes: a43913ea ("drm/amd/powerplay: add function get_clock_by_type_with_latency for navi10") Fixes: e5e4e223 ("drm/amd/powerplay: add interface to get clock by type with latency for display (v2)") Link: https://github.com/ClangBuiltLinux/linux/issues/586Signed-off-by:Nathan Chancellor <natechancellor@gmail.com> Reviewed-by:
-
Monk Liu authored
previously the ucode loading of PSP was repreated, one executed in phase_1 init/re-init/resume and the other in fw_loading routine Avoid this double loading by clearing ip_blocks.status.hw in suspend or reset prior to the FW loading and any block's hw_init/resume v2: still do the smu fw loading since it is needed by bare-metal v3: drop the change in reinit_early_sriov, just clear all block's status.hw in the head place and set the status.hw after hw_init done is enough Signed-off-by:
Monk Liu <Monk.Liu@amd.com> Reviewed-by:
Emily Deng <Emily.Deng@amd.com> Reviewed-by:
-
Monk Liu authored
for SRIOV the SOS fw of PSP is loaded in hypervisor thus guest won't tell the version of it, and judging feature by reading the sos fw version in guest side is completely wrong Signed-off-by:
-
Monk Liu authored
we can simplify all those unnecessary function under SRIOV for vega10 since: 1) PSP L1 policy is by force enabled in SRIOV 2) original logic always set all flags which make itself a dummy step besides, 1) the ih_doorbell_range set should also be skipped for VEGA10 SRIOV. 2) the gfx_common registers should also be skipped for VEGA10 SRIOV. Signed-off-by:
-
Kevin Wang authored
before this change, the pp_feature sysfs show feature enable state by logic feature id, it is not easy to read. this change will sort pp_features show index by asic feature id. before: features high: 0x00000623 low: 0xb3cdaffb 00. DPM_PREFETCHER ( 0) : enabeld 01. DPM_GFXCLK ( 1) : enabeld 02. DPM_UCLK ( 3) : enabeld 03. DPM_SOCCLK ( 4) : enabeld 04. DPM_MP0CLK ( 5) : enabeld 05. DPM_LINK ( 6) : enabeld 06. DPM_DCEFCLK ( 7) : enabeld 07. DS_GFXCLK (10) : enabeld 08. DS_SOCCLK (11) : enabeld 09. DS_LCLK (12) : disabled 10. PPT (23) : enabeld 11. TDC (24) : enabeld 12. THERMAL (33) : enabeld 13. RM (35) : disabled ...... after: features high: 0x00000623 low: 0xb3cdaffb 00. DPM_PREFETCHER ( 0) : enabeld 01. DPM_GFXCLK ( 1) : enabeld 02. DPM_GFX_PACE ( 2) : disabled 03. DPM_UCLK ( 3) : enabeld 04. DPM_SOCCLK ( 4) : enabeld 05. DPM_MP0CLK ( 5) : enabeld 06. DPM_LINK ( 6) : enabeld 07. DPM_DCEFCLK ( 7) : enabeld 08. MEM_VDDCI_SCALING ( 8) : enabeld 09. MEM_MVDD_SCALING ( 9) : enabeld 10. DS_GFXCLK (10) : enabeld 11. DS_SOCCLK (11) : enabeld 12. DS_LCLK (12) : disabled 13. DS_DCEFCLK (13) : enabeld ...... Signed-off-by:
Kevin Wang <kevin1.wang@amd.com> Reviewed-by:
Kenneth Feng <kenneth.feng@amd.com> Reviewed-by:
Evan Quan <evan.quan@amd.com> Signed-off-by:
-
- 31 Jul, 2019 24 commits
-
-
Alex Deucher authored
Same as navi10. Reviewed-by:
Xiaojie Yuan <xiaojie.yuan@amd.com> Signed-off-by:
-
Dennis Li authored
some subblocks of gfx fail in inject test, disable them Signed-off-by:
Dennis Li <Dennis.Li@amd.com> Reviewed-by:
Tao Zhou <tao.zhou1@amd.com> Reviewed-by:
-
Dennis Li authored
check gfx error count in both ras querry function and ras interrupt handler. gfx ras is still disabled by default due to known stability issue found in gpu reset. Signed-off-by:
-
Dennis Li authored
Add functions for RAS error inject and query error counter Signed-off-by:
-
Dennis Li authored
Signed-off-by:
-
Dennis Li authored
Signed-off-by:
-
Dennis Li authored
Add EDC registers to support VEGA20 RAS Signed-off-by:
-
Tao Zhou authored
error injection address is not in gpu address space Signed-off-by:
-
Tao Zhou authored
only ue and ce errors are supported Signed-off-by:
-
Tao Zhou authored
add err_data parameter in interrupt cb for ras clients Signed-off-by:
-
Tao Zhou authored
add error data as parameter for ras interrupt cb and process it Signed-off-by:
-
Tao Zhou authored
query umc ras error address, translate it to gpu 4k page view and save it. Signed-off-by:
-
Tao Zhou authored
add related registers, callback function and channel index table Signed-off-by:
-
Tao Zhou authored
more than one error address may be recorded in one query Signed-off-by:
-
Tao Zhou authored
remove the check of ErrorCodeExt v2: refine the if condition for ue counting Signed-off-by:
-
Tao Zhou authored
create new amdgpu_umc structure to for more umc settings in future and switch to the new structure Signed-off-by:
-
Tao Zhou authored
replace some 32bit macros with 64bit operations to simplify code Signed-off-by:
-
Tao Zhou authored
add 64 bits register access functions v2: implement 64 bit functions in low level Signed-off-by:
-
Tao Zhou authored
v1: increase ras ce/ue error count v2: log the number of correctable and uncorrectable errors Signed-off-by:
-
Hawking Zhang authored
check umc error count in both ras querry function and ras interrupt handler Signed-off-by:
-
Hawking Zhang authored
init umc callback function for vega20 in sw early init phase Signed-off-by:
-
Hawking Zhang authored
Implement umc query_ras_error_count function to support querry both correctable and uncorrectable error Signed-off-by:
-
Hawking Zhang authored
the change introduces IP headers for unified memory controller (umc) Signed-off-by:
-
Hawking Zhang authored
remote smu (rsmu) is a sub-block used as ip register interface, error handling, reset generation.etc Signed-off-by:
-
