aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/pm
AgeCommit message (Collapse)AuthorFilesLines
2023-10-09drm/amdgpu: Refactor FRU product informationLijo Lazar5-12/+0
Keep FRU related information together in a separate structure. Signed-off-by: Lijo Lazar <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-10-09drm/amdgpu: Enable SMU 13.0.0 optimizations when ROCm is active (v2)Alex Deucher1-1/+16
When ROCm is active enable additional SMU 13.0.0 optimizations. This reuses the unused powersave profile on PMFW. v2: move to the swsmu code since we need both bits active in the workload mask. Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-10-09drm/amd: Fix UBSAN array-index-out-of-bounds for Polaris and TongaMario Limonciello1-6/+6
For pptable structs that use flexible array sizes, use flexible arrays. Link: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2036742 Signed-off-by: Mario Limonciello <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-10-09drm/amd: Fix UBSAN array-index-out-of-bounds for SMU7Mario Limonciello1-2/+2
For pptable structs that use flexible array sizes, use flexible arrays. Suggested-by: Felix Held <[email protected]> Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2874 Signed-off-by: Mario Limonciello <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-10-05drm/amd/pm: Remove set df cstate for SMUv13.0.6Asad Kamal1-8/+0
Remove set df cstate as disallow df state is not required for SMUv13.0.6 Signed-off-by: Asad Kamal <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-10-05drm/amd/pm: Annotate struct smu10_voltage_dependency_table with __counted_byKees Cook1-1/+1
Prepare for the coming implementation by GCC and Clang of the __counted_by attribute. Flexible array members annotated with __counted_by can have their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS (for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family functions). As found with Coccinelle[1], add __counted_by for struct smu10_voltage_dependency_table. [1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci Cc: Evan Quan <[email protected]> Cc: Alex Deucher <[email protected]> Cc: "Christian König" <[email protected]> Cc: "Pan, Xinhui" <[email protected]> Cc: David Airlie <[email protected]> Cc: Daniel Vetter <[email protected]> Cc: Xiaojian Du <[email protected]> Cc: Huang Rui <[email protected]> Cc: Kevin Wang <[email protected]> Cc: [email protected] Cc: [email protected] Signed-off-by: Kees Cook <[email protected]> Acked-by: Alex Deucher <[email protected]> Reviewed-by: Gustavo A. R. Silva <[email protected]> Signed-off-by: Christian König <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2023-10-04drm/amd/pm: Add GC v9.4.3 thermal limits to hwmonLijo Lazar1-7/+12
Publish max operating temperature of SOC and memory as temp*_emergency nodes in hwmon. temp*_crit will show the throttle temperature limits. Signed-off-by: Lijo Lazar <[email protected]> Reviewed-by: Asad Kamal <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-10-04drm/amd/pm: Add throttle limit for SMU v13.0.6Lijo Lazar1-7/+27
CTF limit represents the max operating temperature and thermal limit gives the limit at which throttling starts. Add support for both limits. SOC and HBM may have different limit values.*_emergency_max gives max operating temperature and *_crit_max value represents throttle limit. Signed-off-by: Lijo Lazar <[email protected]> Reviewed-by: Asad Kamal <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-10-04drm/amd: Drop all hand-built MIN and MAX macros in the amdgpu base driverMario Limonciello10-26/+22
Several files declare MIN() or MAX() macros that ignore the types of the values being compared. Drop these macros and switch to min() min_t(), and max() from `linux/minmax.h`. Suggested-by: Hamza Mahfooz <[email protected]> Signed-off-by: Mario Limonciello <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-10-04drm/amd: Update `update_pcie_parameters` functions to use uint8_t argumentsMario Limonciello6-12/+12
The matching values for `pcie_gen_cap` and `pcie_width_cap` when fetched from powerplay tables are 1 byte, so narrow the arguments to match to ensure min() and max() comparisons without casts. Signed-off-by: Mario Limonciello <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-10-03drm/amd: Fix logic error in sienna_cichlid_update_pcie_parameters()Mario Limonciello1-18/+23
While aligning SMU11 with SMU13 implementation an assumption was made that `dpm_context->dpm_tables.pcie_table` was populated in dpm table initialization like in SMU13 but it isn't. So restore some of the original logic and instead just check for amdgpu_device_pcie_dynamic_switching_supported() to decide whether to hardcode values; erring on the side of performance. Cc: [email protected] # 6.1+ Reported-and-tested-by: Umio Yasuno <[email protected]> Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/1447#note_2101382 Fixes: e701156ccc6c ("drm/amd: Align SMU11 SMU_MSG_OverridePcieParameters implementation with SMU13") Signed-off-by: Mario Limonciello <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-10-03drm/amd/pm: delete dead codeDan Carpenter1-3/+0
"ret" was checked earlier inside the loop, so we know it is zero here. No need to check a second time. Reviewed-by: Yang Wang <[email protected]> Signed-off-by: Dan Carpenter <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-28drm/amd/pm: Disallow managing power profiles on SRIOV for gc11.0.3Victor Zhao1-1/+2
disable pp_power_profile_mode for sriov on gc11.0.3 as not supported by smu Signed-off-by: Victor Zhao <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-28drm/amd/pm: fix the print_clk_levels issue for SMU v13.0.6Le Ma1-12/+12
Pass the correct size to smu_v13_0_6_print_clks, otherwise the same place in buf will be re-written. Signed-off-by: Le Ma <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-28drm/amd/pm: deprecate allow_xgmi_power_down interfaceLe Ma4-41/+0
Replace with set_plpd_mode uniformly for places to use. Signed-off-by: Le Ma <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-28drm/amd/pm: integrate plpd allow/disallow into select_xgmi_plpd_policy in ↵Le Ma3-28/+38
ppt level The allow_xgmi_power_down(true/false) will be generally replaced by: - allow: select_xgmi_plpd_policy(XGMI_PLPD_DEFAULT) - disallow: select_xgmi_plpd_policy(XGMI_PLPD_DISALLOW) Signed-off-by: Le Ma <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-28drm/amd/pm: init plpd_mode properly for different asicsLe Ma1-0/+17
Assign DEFAULT mode if it supports plpd, otherwise keeps NONE v2: reduce ip version checks Signed-off-by: Le Ma <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-26drm/amd/pm: add xgmi_plpd_policy sysfs node for user to change plpd policyLe Ma3-0/+116
Add xgmi_plpd_policy sysfs node for users to check and select xgmi per-link power down policy: - arg 0: disallow plpd - arg 1: default policy - arg 2: optimized policy v2: split from smu v13.0.6 code and miscellaneous updates v3: add usage comments around set/get functions Signed-off-by: Le Ma <[email protected]> Reviewed-by: Asad Kamal <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-26drm/amd/pm: add xgmi plpd mode selecting interface for smu v13.0.6Le Ma4-1/+66
Add the interface to change xgmi per-link power down policy. v2: split from sysfs interface code and miscellaneous updates v3: check against XGMI_PLPD_DEFAULT/XGMI_PLPD_OPTIMIZED and pass PPSMC param Signed-off-by: Le Ma <[email protected]> Reviewed-by: Asad Kamal <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-26drm/amd/pm: add plpd_mode in smu_context to indicate current modeLe Ma1-0/+2
Add enum pp_xgmi_plpd_mode to describe PLPD policies. v2: move the enum from amdgpu_smu.h to kgd_pp_interface.h Signed-off-by: Le Ma <[email protected]> Reviewed-by: Asad Kamal <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-26drm/amd/pm: update pmfw headers for version 85.73.0Le Ma1-0/+5
To add message to select PLPD mode. Signed-off-by: Le Ma <[email protected]> Reviewed-by: Asad Kamal <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-26drm/amd/pm: Add reset option for fan_curve on smu13_0_0Ma Jun2-4/+47
Add reset option for fan_curve. User can use command "echo r > fan_cure" to reset the fan_curve to boot value Signed-off-by: Ma Jun <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-26drm/amd/pm: add unique_id for gc 11.0.3Kenneth Feng1-0/+1
add unique_id for gc 11.0.3 Signed-off-by: Kenneth Feng <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-20drm/amd/pm: Remove SMUv13.0.6 unsupported featureLijo Lazar1-1/+0
Selectively updating feature mask is not supported in SMU v13.0.6. Remove the callback corresponding to that. Signed-off-by: Lijo Lazar <[email protected]> Reviewed-by: Yang Wang <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-20drm/amd/pm: Round Q10 format values in SMU v13.0.6Lijo Lazar1-34/+36
Instead of neglecting fractional part, round the Q10 format values in SMU v13.0.6 metrics table. Signed-off-by: Lijo Lazar <[email protected]> Reviewed-by: Asad Kamal <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-20drm/amd/pm: add smu_13_0_6 mca dump supportYang Wang1-0/+531
v1: implement smu_v13_0_6 mca bank interface. v2: - remove unnecessary lock - move MCMP1_* macros to mp_13_0_6_sh_mask.h file Signed-off-by: Yang Wang <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-20drm/amd/pm: update smu_v13_0_6 ppsmc headerYang Wang4-2/+100
update smu header to support mca dump interface. Signed-off-by: Yang Wang <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-20Documentation/amdgpu: Modify pp_dpm_*clk detailsLijo Lazar1-1/+9
pp_dpm_*clk nodes also could show the frequencies when a clock is in 'sleep' state. Add documentation related to that. Signed-off-by: Lijo Lazar <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-20drm/amd/pm:Fix GFX deep sleep clock reportingLijo Lazar1-1/+9
For SMU v13.0.6, keep GFX deep sleep clock reporting style consistent with that of other clocks. Sample format below. S: 78Mhz * 0: 600Mhz 1: 800Mhz Signed-off-by: Lijo Lazar <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Reviewed-by: Evan Quan <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-20drm/amd/pm: Fix clock reporting for SMUv13.0.6Lijo Lazar1-97/+62
On SMU v13.0.6, effective clocks are reported by FW which won't exactly match with DPM level. Report the current clock based on the values matching closest to the effective clock. Also, when deep sleep is applied to a clock, report it with a special level "S:" as in sample clock levels below S: 19Mhz * 0: 615Mhz 1: 800Mhz 2: 888Mhz 3: 1000Mhz Signed-off-by: Lijo Lazar <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Reviewed-by: Evan Quan <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-20drm/amdgpu: Use function for IP version checkLijo Lazar10-101/+130
Use an inline function for version check. Gives more flexibility to handle any format changes. Signed-off-by: Lijo Lazar <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-11drm/amdgpu: fix retry loop testDan Carpenter1-1/+1
This loop will exit with "retry" set to -1 if it fails but the code checks for if "retry" is zero. Fix this by changing post-op to a pre-op. --retry vs retry--. Fixes: e01eeffc3f86 ("drm/amd/pm: avoid driver getting empty metrics table for the first time") Reviewed-by: Evan Quan <[email protected]> Signed-off-by: Dan Carpenter <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-11drm/amdgpu: fix retry loop testDan Carpenter1-1/+1
This loop will exit with "retry" set to -1 if it fails but the code checks for if "retry" is zero. Fix this by changing post-op to a pre-op. --retry vs retry--. Fixes: e01eeffc3f86 ("drm/amd/pm: avoid driver getting empty metrics table for the first time") Reviewed-by: Evan Quan <[email protected]> Signed-off-by: Dan Carpenter <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-11drm/amd/pm: enable smu_v13_0_6 mca debug mode when UMC RAS feature is enabledYang Wang2-1/+28
v1: enable smu_v13_0_6 mca debug mode when UMC RAS feature is enabled. v2: use amdgpu_ras_is_supported() helper function instead bitmask check. Signed-off-by: Yang Wang <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-11drm/amd/pm: update smu_v13_0_6 smu headerYang Wang2-1/+5
update smu firmware header to support smu mca debug feature. Signed-off-by: Yang Wang <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-06amdgpu/pm: Optimize emit_clock_levels for aldebaran - part 3Darren Powell1-55/+27
split switch statement into two and consolidate the common code for printing most of the types of clock speeds Signed-off-by: Darren Powell <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-06amdgpu/pm: Optimize emit_clock_levels for aldebaran - part 2Darren Powell1-14/+13
Use variables to remove ternary expression in print statement and improve readability. This will help to optimize the code duplication in the switch statement Also Changed: replaced single_dpm_table->count as iterator in for loops with safer clocks_num_levels value replaced dpm_table.value usage with local var clocks_mhz Signed-off-by: Darren Powell <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-06amdgpu/pm: Optimize emit_clock_levels for aldebaran - part 1Darren Powell1-68/+57
Use variables to remove the multiple nested ternary expressions and improve readability. This will help to optimize the code duplication in the switch statement Also Changed: Modify function aldebaran_get_clk_table to void function as it always returns 0 Use const string "attempt_string" to cut down on repetition Signed-off-by: Darren Powell <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-06amdgpu/pm: Replace print_clock_levels with emit_clock_levels for aldebaranDarren Powell1-32/+31
Replace print_clock_levels with emit_clock_levels for aldebaran * replace .print_clk_levels with .emit_clk_levels in aldebaran_ppt_funcs * added extra parameter int *offset * removed var size, uses arg *offset instead * removed call to smu_cmn_get_sysfs_buf * errors are returned to caller * returns 0 on success additional incidental changes * changed type of vars i, now to remove comparing mismatch types * renamed var s/now/cur_value/ * switch statement default now returns -EINVAL * RAS Recovery returns -EBUSY Based on commit b06b48d7ddae ("amdgpu/pm: Implement emit_clk_levels for navi10") Signed-off-by: Darren Powell <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-06drm/amd/pm: only poweron/off vcn/jpeg when they are valid.Yifan Zhang1-0/+23
If vcn is disabled in kernel parameters, don't touch vcn, otherwise it may cause vcn hang. v2: delete unnecessary logs v3: move "is_vcn_enabled" check to smu_dpm_setvcn/jpeg_enable (Evan) Signed-off-by: Yifan Zhang <[email protected]> Reviewed-by: Evan Quan <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-08-31drm/amdgpu: Add SMU v13.0.6 default reset methodsLijo Lazar1-2/+1
For APUs with SMU v13.0.6, mode-2 reset is kept as default and for others mode-1 is the default reset method. Signed-off-by: Lijo Lazar <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Reviewed-by: Asad Kamal <[email protected]> Tested-by: Asad Kamal <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-08-31drm/amd/pm: fix debugfs pm_info outputAlex Deucher1-0/+3
Print both input and avg power. Fixes: 47f1724db4fe ("drm/amd: Introduce `AMDGPU_PP_SENSOR_GPU_INPUT_POWER`") Reviewed-by: Guchun Chen <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-08-31drm/amd/pm: Fix critical temp unit of SMU v13.0.6Asad Kamal1-4/+5
Critical Temperature needs to be reported in millidegree Celsius. Signed-off-by: Asad Kamal <[email protected]> Reviewed-by: Yang Wang <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-08-31drm/amd/pm: Add critical temp for GC v9.4.3Asad Kamal3-4/+55
Add critical temperature message support func for smu v13.0.6 and expose critical temperature as part of hw mon attributes for GC v9.4.3 v2: Added comment for pmfw version requirement & move the check to get_thermal_temperature_range function Signed-off-by: Asad Kamal <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-08-31drm/amd/pm: Update SMUv13.0.6 PMFW headersAsad Kamal2-3/+17
Update PMFW interface headers for updated metrics table and critical temperature message Signed-off-by: Asad Kamal <[email protected]> Reviewed-by: Lijo Lazar <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-08-31drm/amdgpu/pm: Add notification for no DC supportBokun Zhang5-12/+11
- There is a DPM issue where if DC is not present, FCLK will stay at low level. We need to send a SMU message to configure the DPM - Reuse smu_v13_0_notify_display_change() for this purpose Reviewed-by: Evan Quan <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Bokun Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-08-31Revert "drm/amd/pm: disable the SMU13 OD feature support temporarily"Evan Quan2-24/+6
This reverts commit 510d242f498a00f4701b77c6f42df880abacb3bd. The enablement for the new OD mechanism completed. Also, the support for fan control related OD feature has been added via this new mechanism. Thus, it is time to bring back the SMU13 OD support. Signed-off-by: Evan Quan <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-08-31drm/amd/pm: add fan minimum pwm OD setting support for SMU13Evan Quan6-2/+169
Add SMU13 fan minimum pwm OD setting support. Signed-off-by: Evan Quan <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-08-31drm/amd/pm: add fan target temperature OD setting support for SMU13Evan Quan6-2/+171
Add SMU13 fan target temperature OD setting support. Signed-off-by: Evan Quan <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-08-31drm/amd/pm: add fan acoustic target OD setting support for SMU13Evan Quan6-2/+170
Add SMU13 fan acoustic target OD setting support. Signed-off-by: Evan Quan <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.