- 09 Jul, 2019 5 commits
-
-
Alex Deucher authored
We need to serialize access to the psp ring if there are multiple callers at runtime. Reviewed-by:
Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Query the metrics table for the current uclk activity. Reviewed-by:
Evan Quan <evan.quan@amd.com> Signed-off-by:
-
Alex Deucher authored
It's only available on navi and newer. Reviewed-by:
Xiaojie Yuan <xiaojie.yuan@amd.com> Signed-off-by:
-
Alex Deucher authored
New parameters added for navi lack documentation. Reviewed-by:
-
Marek Olšák authored
This RELEASE_MEM use has the Release semantic, which means we should write back but not invalidate. Invalidations only make sense with the Acquire semantic (ACQUIRE_MEM), or when RELEASE_MEM is used to do the combined Acquire-Release semantic, which is a barrier, not a fence. The undesirable side effect of doing invalidations for the Release semantic is that it invalidates caches while shaders are running, because the Release can execute in the middle of the next IB. UMDs should use ACQUIRE_MEM at the beginning of IBs. Doing cache invalidations for a fence (like in this case) doesn't do anything for correctness. Signed-off-by:
Marek Olšák <marek.olsak@amd.com> Acked-by:
-
- 08 Jul, 2019 13 commits
-
-
Arnd Bergmann authored
On 32-bit architectures, dividing a 64-bit integer in the kernel leads to a link error: ERROR: "__udivdi3" [drivers/gpu/drm/amd/amdgpu/amdgpu.ko] undefined! ERROR: "__divdi3" [drivers/gpu/drm/amd/amdgpu/amdgpu.ko] undefined! Change the two recently introduced instances to a multiply+shift operation that is also much cheaper on 32-bit architectures. We can do that here, since both of them are really 32-bit numbers that change a few percent. Fixes: bedbbe6a ("drm/amd/display: Move link functions from dc to dc_link") Fixes: f18bc4e5 ("drm/amd/display: update calculated bounding box logic for NV") Acked-by:
Slava Abramov <slava.abramov@amd.com> Tested-by:
Arnd Bergmann <arnd@arndb.de> Signed-off-by:
-
Alex Deucher authored
Split it between navi10 and newer and everything before navi10. Reviewed-by:
-
Alex Deucher authored
Need to add appropriate ifdef. Acked-by:
Leo Li <sunpeng.li@amd.com> Reviewed-by:
Nicholas Kazlauskas <nicholas.kazlauskas@amd.com> Signed-off-by:
-
Arnd Bergmann authored
If smu_get_current_rpm() fails, we can't use the output, as that may be uninitialized: drivers/gpu/drm/amd/amdgpu/../powerplay/vega20_ppt.c:3023:8: error: variable 'current_rpm' is used uninitialized whenever '?:' condition is false [-Werror,-Wsometimes-uninitialized] ret = smu_get_current_rpm(smu, ¤t_rpm); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/amd/amdgpu/../powerplay/inc/amdgpu_smu.h:735:3: note: expanded from macro 'smu_get_current_rpm' ((smu)->funcs->get_current_rpm ? (smu)->funcs->get_current_rpm((smu), (speed)) : 0) ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/amd/amdgpu/../powerplay/vega20_ppt.c:3024:12: note: uninitialized use occurs here percent = current_rpm * 100 / pptable->FanMaximumRpm; ^~~~~~~~~~~ drivers/gpu/drm/amd/amdgpu/../powerplay/vega20_ppt.c:3023:8: note: remove the '?:' if its condition is always true ret = smu_get_current_rpm(smu, ¤t_rpm); ^ drivers/gpu/drm/amd/amdgpu/../powerplay/inc/amdgpu_smu.h:735:3: note: expanded from macro 'smu_get_current_rpm' ((smu)->funcs->get_current_rpm ? (smu)->funcs->get_current_rpm((smu), (speed)) : 0) ^ drivers/gpu/drm/amd/amdgpu/../powerplay/vega20_ppt.c:3020:22: note: initialize the variable 'current_rpm' to silence this warning uint32_t current_rpm; Propagate the error code in that case. Fixes: ee0db820 ("drm/amd/powerplay: move PPTable_t uses into asic level") Signed-off-by: -
Arnd Bergmann authored
Without this header, we get a compiler error in some configurations: .../dc/dcn20/dcn20_hwseq.c: In function 'dcn20_hwss_wait_for_blank_complete': .../dc/dcn20/dcn20_hwseq.c:1493:3: error: implicit declaration of function 'udelay' [-Werror=implicit-function-declaration] Note: the use of udelay itself may be problematic, as can occupy the CPU for 200ms in a busy-loop here. Fixes: 7ed4e635 ("drm/amd/display: Add DCN2 HW Sequencer and Resource") Signed-off-by:
-
Arnd Bergmann authored
When CONFIG_PERF_EVENTS is disabled, we cannot compile the pmu portion of the amdgpu driver: drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c:48:38: error: no member named 'hw' in 'struct perf_event' struct hw_perf_event *hwc = &event->hw; ~~~~~ ^ drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c:51:13: error: no member named 'attr' in 'struct perf_event' if (event->attr.type != event->pmu->type) ~~~~~ ^ ... Use conditional compilation for this file. Fixes: 9c7c85f7 ("drm/amdgpu: add pmu counters") Signed-off-by: -
Nathan Chancellor authored
clang warns (trimmed for brevity): drivers/gpu/drm/amd/amdgpu/../powerplay/vega20_ppt.c:3023:8: warning: variable 'current_rpm' is used uninitialized whenever '?:' condition is false [-Wsometimes-uninitialized] ret = smu_get_current_rpm(smu, ¤t_rpm); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ smu_get_current_rpm expands to a ternary operator conditional on smu->funcs->get_current_rpm being not NULL. When this is false, current_rpm will be uninitialized. Zero initialize current_rpm to avoid using random stack values if that ever happens. Fixes: ee0db820 ("drm/amd/powerplay: move PPTable_t uses into asic level") Link: https://github.com/ClangBuiltLinux/linux/issues/588Signed-off-by:Nathan Chancellor <natechancellor@gmail.com> Signed-off-by:
-
Nathan Chancellor authored
clang warns (trimmed for brevity): drivers/gpu/drm/amd/amdgpu/../powerplay/smu_v11_0.c:1098:10: warning: variable 'freq' is used uninitialized whenever '?:' condition is false [-Wsometimes-uninitialized] ret = smu_get_current_clk_freq_by_table(smu, clk_id, &freq); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ If get_current_clk_freq_by_table is ever NULL, freq will fail to be properly initialized. Zero initialize it to avoid using uninitialized stack values. smu_get_current_clk_freq_by_table expands to a ternary operator conditional on smu->funcs->get_current_clk_freq_by_table being not NULL. When this is false, freq will be uninitialized. Zero initialize freq to avoid using random stack values if that ever happens. Fixes: e3618249 ("drm/amd/powerplay: fix dpm freq unit error (10KHz -> Mhz)") Link: https://github.com/ClangBuiltLinux/linux/issues/585Signed-off-by: -
Nathan Chancellor authored
clang warns: drivers/gpu/drm/amd/amdgpu/../powerplay/navi10_ppt.c:601:33: warning: suggest braces around initialization of subobject [-Wmissing-braces] static SmuMetrics_t metrics = {0}; ^ {} drivers/gpu/drm/amd/amdgpu/../powerplay/navi10_ppt.c:905:26: warning: suggest braces around initialization of subobject [-Wmissing-braces] SmuMetrics_t metrics = {0}; ^ {} 2 warnings generated. One way to fix these warnings is to add additional braces like clang suggests; however, there has been a bit of push back from some maintainers[1][2], who just prefer memset as it is unambiguous, doesn't depend on a particular compiler version[3], and properly initializes all subobjects. Do that here so there are no more warnings. [1]: https://lore.kernel.org/lkml/022e41c0-8465-dc7a-a45c-64187ecd9684@amd.com/ [2]: https://lore.kernel.org/lkml/20181128.215241.702406654469517539.davem@davemloft.net/ [3]: https://lore.kernel.org/lkml/20181116150432.2408a075@redhat.com/ Fixes: 98e1a543 ("drm/amd/powerplay: add function get current clock freq interface for navi10") Fixes: ab43c4bf ("drm/amd/powerplay: fix fan speed show error (for hwmon pwm)") Link: https://github.com/ClangBuiltLinux/linux/issues/583Signed-off-by: -
Nathan Chancellor authored
clang warns: In file included from drivers/gpu/drm/amd/amdgpu/nv.c:53: drivers/gpu/drm/amd/amdgpu/../amdgpu/mes_v10_1.h:24:9: warning: '__MES_V10_1_H__' is used as a header guard here, followed by #define of a different macro [-Wheader-guard] #ifndef __MES_V10_1_H__ ^~~~~~~~~~~~~~~ drivers/gpu/drm/amd/amdgpu/../amdgpu/mes_v10_1.h:25:9: note: '__MES_v10_1_H__' is defined here; did you mean '__MES_V10_1_H__'? #define __MES_v10_1_H__ ^~~~~~~~~~~~~~~ __MES_V10_1_H__ 1 warning generated. Capitalize the V. Fixes: 886f82aa ("drm/amdgpu/mes10.1: add ip block mes10.1 (v2)") Link: https://github.com/ClangBuiltLinux/linux/issues/582Signed-off-by: -
Kevin Wang authored
the hwmon interface need temperature sensor type support. 1. SENSOR_HOTSPOT_TEMP 2. SENSOR_EDGE_TEMP(SENSOR_GPU_TEMP) 3. SENSOR_MEM_TEMP Signed-off-by:
Kevin Wang <kevin1.wang@amd.com> Reviewed-by:
-
Flora Cui authored
scheduler timeout is in jiffies v2: move timeout check to amdgpu_device_get_job_timeout_settings after parsing the value v3: add lockup_timeout param check. 0: keep default value. negative: infinity timeout. v4: refactor codes. Signed-off-by:
Flora Cui <flora.cui@amd.com> Reviewed-by:
Feifei Xu <Feifei.Xu@amd.com> Signed-off-by:
-
Philip Yang authored
An upcoming change in the hmm_range_register API requires passing in a pointer to an hmm_mirror instead of mm_struct. To access the hmm_mirror we need pass bo instead of ttm to amdgpu_ttm_tt_get_user_pages because mirror is part of amdgpu_mn structure, which is accessible from bo. v2: fix building without CONFIG_HMM_MIRROR (Arnd) Signed-off-by:
Philip Yang <Philip.Yang@amd.com> Signed-off-by:
Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by:
-
- 05 Jul, 2019 6 commits
-
-
Kevin Wang authored
add mode1 (by psp) reset for navi asic. Signed-off-by:
-
xinhui pan authored
Perform a ras_suspend to disable ras on all IPs to workaround some ROCm stability issue. Signed-off-by:
xinhui pan <xinhui.pan@amd.com> Acked-by:
Andrey Grodzovsky <andrey.grodzovsky@amd.com> Signed-off-by:
-
Kevin Wang authored
add baco reset support for smu11. it can help gpu do asic reset when gpu recovery. Signed-off-by:
-
Jack Xiao authored
We observed some SMU commands take more time for execution, so increase waiting time for response. Signed-off-by:
Jack Xiao <Jack.Xiao@amd.com> Reviewed-by:
-
Yrjan Skrimstad authored
This driver currently contains a repeated 500ms blocking delay call which causes frequent major buffer underruns in PulseAudio. This patch fixes this issue by replacing the blocking delay with a non-blocking sleep call. Signed-off-by:
Yrjan Skrimstad <yrjan@skrimstad.net> Signed-off-by:
-
Fuqian Huang authored
kmemdup is introduced to duplicate a region of memory in a neat way. Rather than kmalloc/kzalloc + memcpy, which the programmer needs to write the size twice (sometimes lead to mistakes), kmemdup improves readability, leads to smaller code and also reduce the chances of mistakes. Suggestion to use kmemdup rather than using kmalloc/kzalloc + memcpy. Reviewed-by:
Christian König <Christian.Koenig@amd.com> Reviewed-by:
Emil Velikov <emil.velikov@collabora.com> Signed-off-by:
Fuqian Huang <huangfq.daxian@gmail.com> Signed-off-by:
-
- 03 Jul, 2019 5 commits
-
-
Felix Kuehling authored
This works around difficult-to-reproduce soft hangs on oversubscribed runlists. Signed-off-by:
Oak Zeng <Oak.Zeng@amd.com> Signed-off-by:
-
Felix Kuehling authored
New flag to disable an idle runlist optimization that is causing soft hangs with some diffult-to-reproduce customer workloads. This will serve as a workaround until the problem can be reproduced and the root-cause determined. Signed-off-by:
-
Felix Kuehling authored
Restore the code that resets mem->invalid. Othewise so mapping userptrs after they got an MMU notifiers would always be skipped. This also avoids unnecessarily calling get_user_pages on BOs that have not been invalidated since the last try. Signed-off-by:
-
Felix Kuehling authored
We don't want eviction fences to trigger when waiting for page table updates to complete during restore. In theory there shouldn't be any unsignaled eviction fences in the PD reservation object, but I'm seeing them in instrumented code for reasons not fully understood. Signed-off-by:
-
Felix Kuehling authored
Oversubscription of queues or processes results in poor performance mostly because HWS blinbly schedules busy and idle queues, resulting in poor occupancy if many queues are idle. Let users know with a warning message when transitioning from a non-oversubscribed to an oversubscribed runlist. Signed-off-by:
-
- 02 Jul, 2019 2 commits
-
-
Jack Xiao authored
Just for cleanup. Reviewed-by:
Prike Liang <Prike.Liang@amd.com> Reviewed-by:
-
Alex Deucher authored
All asics newer than vega10 use client ids, so simplify the check. Reviewed-by:
-
- 01 Jul, 2019 9 commits
-
-
Jack Xiao authored
Since amdgpu has always requested PCIE atomics, kfd don't need duplicated PCIE atomics enablement. Referring to amdgpu request result is enough. Signed-off-by:
-
Jack Xiao authored
GPU atomics operation depends on PCIE atomics support. Always enable PCIE atomics ops support in case that it hasn't been enabled. Signed-off-by:
-
Jack Xiao authored
The new field in amdgpu device is used to record whether the system has PCIE atomics support. The field can be exposed to UMD or kfd whether PCIE atomics have supported. Signed-off-by:
-
Evan Quan authored
Otherwise, you may get divided-by-zero error or corrput the SMU fan control feature. Signed-off-by:
-
Evan Quan authored
MGPU fan boost feature should not be enabled until all the devices from the same hive are all back from reset. Signed-off-by:
-
Marek Olšák authored
Add the gfx10 equivalent of the gfx9 code. Signed-off-by:
-
Marek Olšák authored
v2: update emit_ib_size (though it's still wrong because it was wrong before) Signed-off-by:
-
Alex Deucher authored
Recommended by the hw team. Reviewed-and-Tested-by:
Huang Rui <ray.huang@amd.com> Signed-off-by:
-
Alex Deucher authored
Recommended by the hw team. Reviewed-and-Tested-by:
-
