aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu
AgeCommit message (Collapse)AuthorFilesLines
2019-03-19drm/amdgpu: Cosmetic change for calling func amdgpu_gmc_vram_locationOak Zeng4-4/+4
Use function parameter mc as the second parameter of amdgpu_gmc_vram_location, so codes look more consistent. Signed-off-by: Oak Zeng <[email protected]> Reviewed-by: Christian Konig <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: Move IB pool init and fini v2Andrey Grodzovsky1-8/+8
Problem: Using SDMA for TLB invalidation in certain ASICs exposed a problem of IB pool not being ready while SDMA already up on Init and already shutt down while SDMA still running on Fini. This caused IB allocation failure. Temproary fix was commited into a bringup branch but this is the generic fix. Fix: Init IB pool rigth after GMC is ready but before SDMA is ready. Do th opposite for Fini. v2: Remove restriction on SDMA early init and move amdgpu_ib_pool_fini Reviewed-by: Christian König <[email protected]> Signed-off-by: Andrey Grodzovsky <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: apply Vega20 BACO workaroundEvan Quan2-0/+3
Applied vdci flush workaround for Vega20 BACO. Signed-off-by: Evan Quan <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: XGMI pstate switch initial supportshaoyunl6-1/+53
Driver vote low to high pstate switch whenever there is an outstanding XGMI mapping request. Driver vote high to low pstate when all the outstanding XGMI mapping is terminated. Signed-off-by: shaoyunl <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: Enable XGMI mapping for peer deviceshaoyunl1-4/+9
Adjust vram base offset for XGMI mapping when update the PT entry so the address will fall into correct XGMI aperture for peer device Signed-off-by: shaoyunl <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: Add sysfs entries for xgmi hive v2.Andrey Grodzovsky2-5/+146
For each device a file xgmi_device_id is created. On the first device a subdirectory named xgmi_hive_info is created, It contains a file named hive_id and symlinks named node 1-4 linking to each device in the hive. v2: Return error codes instead of '-1' and few misspellings. Signed-off-by: Andrey Grodzovsky <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: allow huge invalid mappings on GMC8Christian König1-1/+2
Only GMC9 supports true huge pages, but we can still free invalid mappings on GMC8. Signed-off-by: Christian König <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Acked-by: Huang Rui <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: drop the huge page flagChristian König2-14/+1
Not needed any more since we now free PDs/PTs on demand. Signed-off-by: Christian König <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Acked-by: Huang Rui <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: free PDs/PTs on demandChristian König1-18/+53
When something is unmapped we now free the affected PDs/PTs again. Signed-off-by: Christian König <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Acked-by: Huang Rui <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: allocate VM PDs/PTs on demandChristian König5-129/+39
Let's start to allocate VM PDs/PTs on demand instead of pre-allocating them during mapping. Signed-off-by: Christian König <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Acked-by: Huang Rui <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: let amdgpu_vm_clear_bo figure out ats status v2Christian König1-25/+47
Instead of providing it from outside figure out the ats status in the function itself from the data structures. v2: simplify finding the right level v3: partially revert changes from v2, more cleanup and split code into more functions. Signed-off-by: Christian König <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Acked-by: Huang Rui <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: rework shadow handling during PD clear v3Christian König1-28/+39
This way we only deal with the real BO in here. v2: use a do { ... } while loop instead v3: fix NULL pointer in v2 Signed-off-by: Christian König <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Acked-by: Huang Rui <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: fix missing assignment of error return code to variable retColin Ian King1-1/+2
An earlier commit replaced ttm_bo_wait with amdgpu_bo_sync_wait and removed the error return assignment to variable ret. Fix this by adding the assignment back. Also break line to clean up checkpatch overly long line warning. Detected by CoverityScan, CID#1477327 ("Logically dead code") Fixes: c60cd590cb7d ("drm/amdgpu: Replace ttm_bo_wait with amdgpu_bo_sync_wait") Signed-off-by: Colin Ian King <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: also reroute VMC and UMD to IH ring 1 on Vega 20Christian König1-0/+36
Same patch we alredy did for Vega10. Just re-route page faults to a separate ring to avoid drowning in interrupts. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: reroute VMC and UMD to IH ring 1Christian König2-0/+37
Page faults can easily overwhelm the interrupt handler. So to make sure that we never lose valuable interrupts on the primary ring we re-route page faults to IH ring 1. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: add thick tile mode settings for Oland of gfx6Tao Zhou1-0/+19
Adding thick tile mode for Oland to prevent UMD from getting mode value 0 Signed-off-by: Tao Zhou <[email protected]> Tested-by: Hui.Deng <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu/gfx_v8_0: Mark expected switch fall-throughGustavo A. R. Silva1-0/+1
In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. This patch fixes the following warning: drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c: In function ‘gfx_v8_0_tiling_mode_table_init’: ./include/linux/device.h:1487:2: warning: this statement may fall through [-Wimplicit-fallthrough=] _dev_warn(dev, dev_fmt(fmt), ##__VA_ARGS__) ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c:3236:3: note: in expansion of macro ‘dev_warn’ dev_warn(adev->dev, ^~~~~~~~ drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c:3240:2: note: here case CHIP_CARRIZO: ^~~~ Warning level 3 was used: -Wimplicit-fallthrough=3 This patch is part of the ongoing efforts to enable -Wimplicit-fallthrough. Signed-off-by: Gustavo A. R. Silva <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: Bump amdgpu version for per-flip plane tiling updatesNicholas Kazlauskas1-1/+2
To help xf86-video-amdgpu and mesa know DC supports updating the tiling attributes for a framebuffer per-flip. Cc: Michel Dänzer <[email protected]> Signed-off-by: Nicholas Kazlauskas <[email protected]> Acked-by: Alex Deucher <[email protected]> Reviewed-by: Marek Olšák <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amdgpu: Add sysfs files for returning VRAM/GTT info v2Kent Russell2-0/+168
Add 6 files that return (in bytes): The total amount of VRAM/visible VRAM/GTT and the current total used VRAM/visible VRAM/GTT v2: Split used and total into separate files Reviewed-by: Christian König <[email protected]> Signed-off-by: Kent Russell <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: add limit of pp_feature for smu (v3)Likun Gao7-7/+11
Move pp_feature from the struct of amd_powerplay to amdgpu_device. Add pp_feature limit for overdrive interface. v2: put pp_feature into struct amdgpu_pm. v3: merge feature_mask with pp_feature. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Suggested-by: Alex Deucher <[email protected]> Suggested-by: Huang Rui <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Huang Rui <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: support sysfs to set socclk, fclk, dcefclkLikun Gao1-3/+9
Add sys interface to set socclk, fclk and dcefclk for smu. Add feature_mask parameter for smu_upload_dpm_level as socclk, fclk and dcefclk have dependency, without feature_mask to point out specific clk will make it fail to set some clk. Fix the function of smu_unforce_dpm_levels. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Gui Chengming <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: support sysfs to get socclk, fclk, dcefclkLikun Gao1-3/+9
Add sys interface to get socclk, fclk and dcefclk for smu. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Gui Chengming <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: set fan target interface for hwmonLikun Gao1-2/+10
Add fan1_target set interface to set fan speed for hwmon. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Reviewed-by: Huang Rui <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: implement fan1_enable hwmon interface for SMU11 (v2)Chengming Gui1-7/+14
set the fan1_enable hwmon interface to call smu_get_fan_control_mode and smu_set_fan_control_mode. v2: fix print value. Signed-off-by: Chengming Gui <[email protected]> Reviewed-by: Huang Rui <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: implement pwm1_enable hwmon interface for SMU11 (v2)Chengming Gui1-10/+21
1, set get_pwm1_enable and set_pwm1_enable functions to call smu_get_fan_control_mode and smu_set_fan_control_mode for SMU11 2, implement set_fan_control_mode function v2: add return value in set_fan_control_mode function Signed-off-by: Chengming Gui <[email protected]> Reviewed-by: Huang Rui <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: implement pwm1 hwmon interface for SMU11 (v2)Chengming Gui1-4/+14
added main functions: get_fan_speed_percent set_fan_speed_percent. added dependent functions: smc_fan_control set_fan_static_mode get_fan_speed_percent v2: fix coding style issue Signed-off-by: Chengming Gui <[email protected]> Reviewed-by: Huang Rui <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: implement power1_cap and power1_cap_max interface for ↵Chengming Gui1-3/+11
SMU11 (v2) add get_power_limit and set_power_limit functions to support hwmon for SMU11. v2: fix the code style issue. Signed-off-by: Chengming Gui <[email protected]> Reviewed-by: Huang Rui <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: add fan input interface for hwmonLikun Gao1-2/+10
Add fan1_input and fan1_target interface to get fan speed info for hwmon. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Reviewed-by: Huang Rui <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: debugfs don't check powerplay when SW SMU is enabled.Kevin Wang1-1/+1
when sw smu is enabled, the powerplay interface isn't implemented. Signed-off-by: Kevin Wang <[email protected]> Reviewed-by: Huang Rui <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: add function to get sclk and mclkLikun Gao2-6/+20
Add function to get sclk and mclk for smu11. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: Unify smu handle task function (v2)Likun Gao1-18/+28
Unify power stade adjust function into smu_handle_task by the judgment of task_id. Move functions which have no relationship with smu version into the file of amdgpu_smu. Modified the function of smu_display_config_changed into two part. Unify some similiar function. v2: Correct the operation of upload dpm level when force dpm limit value. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: implement dpm enable functions of uvd & vce for smuKevin Wang1-2/+14
add function of dpm enable uvd & vce for extern module use. Signed-off-by: Kevin Wang <[email protected]> Reviewed-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: hwmon don't check powerplay when sw smu is enabledKevin Wang1-26/+30
when sw-smu is enabled, the driver won't init powerplay structure. Signed-off-by: Kevin Wang <[email protected]> Reviewed-by: Huang Rui <[email protected]> Reviewed-by: Likun Gao <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: add sys interface to set pp_od_clk_voltage for smuLikun Gao1-10/+20
Add sys interface to set pp_od_clk_voltage for smu. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Huang Rui <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: add sys interface for set sclk_od/mclk_od for smuLikun Gao1-12/+22
Add sys interface for set pp_sclk_od and pp_mclk_od for smu. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Huang Rui <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: add sys interface for pcie for smuLikun Gao1-2/+6
Add sys interface for set/get PCIE info for SMU. The related operate will do nothing as vega20 do not support it now. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Huang Rui <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: implement power_dpm_force_performance_level for SMU11Chengming Gui1-3/+20
add get_performance_level and force_performance_level to implement the sys interface for SMU11. Signed-off-by: Chengming Gui <[email protected]> Reviewed-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: implement pp_power_profile_mode sys inerface for SMU11Chengming Gui1-3/+6
Add set/get power profile mode functions. Added dependency interfaces: 1) vega20_set_activity_monitor_coeff 2) vega20_get_activity_monitor_coeff 3) conv_power_profile_to_pplib_workload Signed-off-by: Chengming Gui <[email protected]> Reviewed-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: implement power_dpm_state sys interface for SMU11Chengming Gui2-1/+9
Add functions to get/set dpm state for SMU11. Signed-off-by: Chengming Gui <[email protected]> Acked-by: Alex Deucher <[email protected]> Acked-by: Kevin Wang <[email protected]> Reviewd-by: Evan Quan <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: don't check hwmgr while using the sw smuHuang Rui1-1/+1
While using the sw smu path, driver won't init hwmgr structure. Signed-off-by: Huang Rui <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Reviewed-by: Likun Gao <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: get overdrive clock and voltage informationLikun Gao1-1/+7
Add sys interface to get overdrive clock and voltage information for smu11. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Reviewed-by: Evan Quan <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: print overdrive percentage information for smu11Likun Gao1-2/+6
Add function to get sclk or mclk overdrive percentage information for smu11. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Reviewed-by: Evan Quan <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: implement sysfs of pp_force_state for sw-smuKevin Wang1-0/+2
the SMU v11 doesn’t support pp_force_state so far, so we didn’t implement it. Signed-off-by: Kevin Wang <[email protected]> Reviewed-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: implement sysfs of pp_cur_state functionKevin Wang1-9/+15
add function of smu_get_currente_state for sw-smu. v2: fix code typo error if (ret); Signed-off-by: Kevin Wang <[email protected]> Reviewed-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: implement sysfs of get num states functionKevin Wang1-2/+6
add function smu_get_power_num_state function for sw-smu. it's only for sysfs interface, the power state feature is not ready for sw-smu. Signed-off-by: Kevin Wang <[email protected]> Reviewed-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: force clock levels for smu11Likun Gao1-2/+6
Add function to set sclk or mclk level for smu11. Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Evan Quan <[email protected]> Reviewed-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: implement sysfs of pp_table for smu11 (v2)Kevin Wang1-2/+12
add pp_table sysfs interface for new sw-smu. get: return pptable raw data set: write pptable raw data to pptable, then reset smu (hw_fini -> hw_init) v2: fix mutex lock issue Signed-off-by: Kevin Wang <[email protected]> Reviewed-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: implement sysfs of amdgpu_get_busy_percent for smu11Kevin Wang3-46/+28
add interface amdgpu_get_busy_percent for smu11 v2: convert data pointer type to uint32_t *. Signed-off-by: Kevin Wang <[email protected]> Reviewed-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: implement is_support_sw_smu function for new smuKevin Wang2-3/+3
add this helper to check new sw-smu support. Signed-off-by: Kevin Wang <[email protected]> Reviewed-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-03-19drm/amd/powerplay: print clock levels for smu11 (v2)Likun Gao1-2/+7
Add function to print current levels for smu11. v2: expose get_current_clk_freq for smu v11. (Kevin) Signed-off-by: Likun Gao <[email protected]> Signed-off-by: Kevin Wang <[email protected]> Reviewed-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.