- 30 Mar, 2017 40 commits
-
-
Nicolai Hähnle authored
This reverts commit 38fc4856, which introduces a use-after-free. The underlying bug should be properly fixed with "drm/ttm: never add BO that failed to validate to the LRU list". Cc: zhoucm1 <david1.zhou@amd.com> Signed-off-by:
Nicolai Hähnle <nicolai.haehnle@amd.com> Tested-by:
Samuel Pitoiset <samuel.pitoiset@gmail.com> Reviewed-by:
Christian König <christian.koenig@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Nicolai Hähnle authored
Fixes a potential race condition in amdgpu that looks as follows: Task 1: attempt ttm_bo_init, but ttm_bo_validate fails Task 1: add BO to global list anyway Task 2: grabs hold of the BO, waits on its reservation lock Task 1: releases its reference of the BO; never gives up the reservation lock The patch "drm/amdgpu: fix a potential deadlock in amdgpu_bo_create_restricted()" attempts to fix that by releasing the reservation lock in amdgpu code; unfortunately, it introduces a use-after-free when this race _doesn't_ happen. This patch should fix the race properly by never adding the BO to the global list in the first place. Cc: zhoucm1 <david1.zhou@amd.com> Signed-off-by: -
Alex Deucher authored
This includes shader/memory clocks, temperature, GPU load, etc. v2: - add sub-queries for AMDPGU_INFO_GPU_SENSOR_* - do not break the ABI v3: - return -ENOENT when amdgpu_dpm == 0 - expose more sensor queries v4: - s/GPU_POWER/GPU_AVG_POWER/ - improve VDDNB/VDDGFX query description - fix amdgpu_dpm check v5: - agd: fix warning v6: - agd: bump version Signed-off-by: -
Samuel Pitoiset authored
read_sensor() has been recently implemented for dpm based boards which means amdgpu_sensors can now be exposed. v2: - make sure read_sensor is not NULL on dpm chips - keep sanity check for powerplay chips v3: - make sure amdgpu_dpm != 0 Cc: Tom St Denis <tom.stdenis@amd.com> Reviewed-by:Tom St Denis <tom.stdenis@amd.com> Signed-off-by:
-
Samuel Pitoiset authored
Add the GPU temperature, the shader clock and eventually the memory clock (as well as the GPU load on CI). The main goal is to expose this info to the userspace like Radeon. v2: - add AMDGPU_PP_SENSOR_GPU_LOAD on CI - update the commit description Signed-off-by: -
Marek Olšák authored
Set alignment mode to unaligned on CIK to align with amdgpu. This is needed for unaligned loads to work properly in mesa. The current setting requires dword alignment. Signed-off-by:
Marek Olšák <marek.olsak@amd.com> Reviewed-by:
-
Christian König authored
v2: new approach fixing this by registering a fence callback for all users of the VM on teardown v3: agd: rebase Signed-off-by: -
Christian König authored
Don't assume kmalloc will always succeed. v2: agd: rebase Signed-off-by:
-
Christian König authored
When two VMs stop using PRT support at the same time we might not disable it in the right order otherwise. v2: agd: rebase Signed-off-by:
-
Alex Xie authored
Reviewed-by:
Alex Xie <AlexBin.Xie@amd.com> Signed-off-by:
-
Christian König authored
Those should be 64bit, even on a 32bit system. Signed-off-by:
Junwei Zhang <Jerry.Zhang@amd.com> Signed-off-by:
-
Tom St Denis authored
This update allows sensors to return more than 1 value and indicates to the caller how many bytes are written. The debugfs interface has been updated to handle reading all of the values. Simply seek to the enum value (multiplied by 4) and then read as many bytes as the sensor provides. (v2): Don't set size to 4 before reading GPU_POWER (v3): agd: rebase Signed-off-by:
-
Christian König authored
Enable/disable the handling globally for now and print a warning when we enable it for the first time. v2: set correct register Signed-off-by:
-
Christian König authored
Enable/disable the handling globally for now and print a warning when we enable it for the first time. v2: set correct register Signed-off-by:
-
Christian König authored
Enable/disable the handling globally for now and print a warning when we enable it for the first time. v2: write to the correct register, adjust bits to that hw generation v3: fix compilation, add the missing register bit definitions Signed-off-by:
-
Junwei Zhang authored
Till GFX8 we can only enable PRT support globally, but with the next hardware generation we can do this on a per page basis. Keep the interface consistent by adding PRT mappings and enable support globally on current hardware when the first mapping is made. v2: disable PRT support delayed and on all error paths v3: PRT and other permissions are mutal exclusive, PRT mappings don't need a BO. v4: update PRT mappings durign CS as well, make va_flags 64bit Signed-off-by: -
Christian König authored
Future hardware generations can handle PRT flags on a per page basis, but current hardware can only turn it on globally. Add the basic handling for both, a global callback to enable/disable triggered by setting a per mapping flag. v2: agd: rebase fixes Signed-off-by:
-
Christian König authored
For PRT support we need mappings which aren't backed by any memory. v2: fix parameter checking Signed-off-by:
-
Monk Liu authored
no suspend invoked so after VF FLR by host, we just call hw_init to reinitialize IPs. Signed-off-by:
Monk Liu <Monk.Liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com Signed-off-by:
-
Eric Huang authored
Signed-off-by:
Eric Huang <JinHuiEric.Huang@amd.com> Reviewed-by:
-
Eric Huang authored
The additional output are: vddc power in Watt; vddci power in Watt; max gpu power in Watt; average gpu power in Watt. Signed-off-by:
-
Eric Huang authored
As well as fix print format for uint32_t type. Signed-off-by:
-
Eric Huang authored
Signed-off-by:
Rex Zhu <Rex.Zhu@amd.com> Acked-by:
-
Eric Huang authored
Signed-off-by:
-
Eric Huang authored
Signed-off-by:
-
Eric Huang authored
Signed-off-by:
-
Eric Huang authored
Signed-off-by:
-
Eric Huang authored
Signed-off-by:
-
Eric Huang authored
Add the sysfs entries pp_gfx_power_profile and pp_compute_power_profile which give user a way to set power profile through parameters minimum sclk, minimum mclk, activity threshold, up hysteresis and down hysteresis only when the entry power_dpm_force_performance_level is in default value "auto". It is read and write. Example: echo 500 800 20 0 5 > /sys/class/drm/card0/device/pp_*_power_profile cat /sys/class/drm/card0/device/pp_*_power_profile 500 800 20 0 5 Note: first parameter is sclk in MHz, second is mclk in MHz, third is activity threshold in percentage, fourth is up hysteresis in ms and fifth is down hysteresis in ms. echo set > /sys/class/drm/card0/device/pp_*_power_profile To set power profile state if it exists. echo reset > /sys/class/drm/card0/device/pp_*_power_profile To restore default state and clear previous setting. Signed-off-by:
-
Monk Liu authored
Signed-off-by:
-
Monk Liu authored
Signed-off-by:
-
Monk Liu authored
this lock is used for sriov_gpu_reset, only get this mutex can run into sriov_gpu_reset. we have couple source triggers gpu_reset for SRIOV: 1) submit timedout and trigger reset voluntarily 2) invalid instruction detected by ENGINE and trigger reset voluntarily 2) hypervisor found world switch hang and trigger flr and notify guest to do reset. all need take care and we need a mutex to protect the consistency of reset routine. Signed-off-by:
-
Monk Liu authored
Signed-off-by:
-
Monk Liu authored
implement SRIOV gpu_reset for future use. it wil be called from: 1) job timeout 2) privl access or instruction error interrupt 3) hypervisor detect VF hang v2: agd: rebase on upstream Signed-off-by:
-
Monk Liu authored
sw part only invoked once during sw_init. hw part invoked during first drv load and resume later. that way we cannot alloc mqd in hw/resume, we only keep mqd allocted in sw_init routine. and hw_init routine only kmap and set it. Signed-off-by:
-
Monk Liu authored
Signed-off-by:
-
Monk Liu authored
We ultimately want to re-use this for bare metal, so no need to have vf checks in the KIQ code itself since kiq itself is currently only used in VF cases. Signed-off-by:
-
Monk Liu authored
Signed-off-by:
-
Monk Liu authored
this is for SRIOV fix: mqd soft init/fini will be invoked by sw_init to allocate BO for compute MQD resource, instead of original scheme that hw_init allocates MQD. because if hw_init allocates MQD, then resume will allocate MQD, and that lead to memory leak after driver recovered from hang. Signed-off-by:
-
Monk Liu authored
introduce a new mqd member in ring is for later usage. we need keep a clean version of MQD for the purpose of recovering compute rings from hang. Signed-off-by:
-
