From testing on sc7180-trogdor devices, reading the GMU registers
needs the GMU clocks to be enabled. Those clocks get turned on in
a6xx_gmu_resume(). Confusingly enough, that function is called as a
result of the runtime_pm of the GPU "struct device", not the GMU
"struct device".
Let's grab a reference to the correct device. Incidentally, this makes
us match the a5xx routine more closely.
This is easily shown to fix crashes that happen if we change the GPU's
pm_runtime usage to not use autosuspend. It's also believed to fix
some long tail GPU crashes even with autosuspend.
NOTE: the crashes I've seen were fixed by _only_ fixing
a6xx_gpu_busy(). However, I believe that the same arguments should be
made to a6xx_gmu_set_freq() so I've changed that function too.
Fixes: eadf79286a4b ("drm/msm: Check for powered down HW in the devfreq callbacks")
Signed-off-by: Douglas Anderson <[email protected]>
---
drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 6 +++---
drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 4 ++--
2 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 9f76f5b15759..b79ad2e0649c 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -129,13 +129,13 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
* This can get called from devfreq while the hardware is idle. Don't
* bring up the power if it isn't already active
*/
- if (pm_runtime_get_if_in_use(gmu->dev) == 0)
+ if (pm_runtime_get_if_in_use(&gpu->pdev->dev) == 0)
return;
if (!gmu->legacy) {
a6xx_hfi_set_freq(gmu, perf_index);
dev_pm_opp_set_opp(&gpu->pdev->dev, opp);
- pm_runtime_put(gmu->dev);
+ pm_runtime_put(&gpu->pdev->dev);
return;
}
@@ -159,7 +159,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
dev_err(gmu->dev, "GMU set GPU frequency error: %d\n", ret);
dev_pm_opp_set_opp(&gpu->pdev->dev, opp);
- pm_runtime_put(gmu->dev);
+ pm_runtime_put(&gpu->pdev->dev);
}
unsigned long a6xx_gmu_get_freq(struct msm_gpu *gpu)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 841e47a0b06b..87568d0b6ef8 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1659,7 +1659,7 @@ static u64 a6xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate)
*out_sample_rate = 19200000;
/* Only read the gpu busy if the hardware is already active */
- if (pm_runtime_get_if_in_use(a6xx_gpu->gmu.dev) == 0)
+ if (pm_runtime_get_if_in_use(&gpu->pdev->dev) == 0)
return 0;
busy_cycles = gmu_read64(&a6xx_gpu->gmu,
@@ -1667,7 +1667,7 @@ static u64 a6xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate)
REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H);
- pm_runtime_put(a6xx_gpu->gmu.dev);
+ pm_runtime_put(&gpu->pdev->dev);
return busy_cycles;
}
--
2.36.1.255.ge46751e96f-goog
On Thu, Jun 9, 2022 at 7:34 AM Douglas Anderson <[email protected]> wrote:
>
> From testing on sc7180-trogdor devices, reading the GMU registers
> needs the GMU clocks to be enabled. Those clocks get turned on in
> a6xx_gmu_resume(). Confusingly enough, that function is called as a
> result of the runtime_pm of the GPU "struct device", not the GMU
> "struct device".
>
> Let's grab a reference to the correct device. Incidentally, this makes
> us match the a5xx routine more closely.
>
> This is easily shown to fix crashes that happen if we change the GPU's
> pm_runtime usage to not use autosuspend. It's also believed to fix
> some long tail GPU crashes even with autosuspend.
>
> NOTE: the crashes I've seen were fixed by _only_ fixing
> a6xx_gpu_busy(). However, I believe that the same arguments should be
> made to a6xx_gmu_set_freq() so I've changed that function too.
>
> Fixes: eadf79286a4b ("drm/msm: Check for powered down HW in the devfreq callbacks")
> Signed-off-by: Douglas Anderson <[email protected]>
> ---
>
> drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 6 +++---
> drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 4 ++--
> 2 files changed, 5 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
> index 9f76f5b15759..b79ad2e0649c 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
> @@ -129,13 +129,13 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
> * This can get called from devfreq while the hardware is idle. Don't
> * bring up the power if it isn't already active
> */
> - if (pm_runtime_get_if_in_use(gmu->dev) == 0)
> + if (pm_runtime_get_if_in_use(&gpu->pdev->dev) == 0)
IMHO, if we do end up using the GPU's runpm instead of the GMU's, we
should probably just move this _get_if_in_use() into msm_gpu_devfreq,
etc. (And probably also this should be "<= 0".. I have that change
locally but haven't sent a patch yet
BR,
-R
> return;
>
> if (!gmu->legacy) {
> a6xx_hfi_set_freq(gmu, perf_index);
> dev_pm_opp_set_opp(&gpu->pdev->dev, opp);
> - pm_runtime_put(gmu->dev);
> + pm_runtime_put(&gpu->pdev->dev);
> return;
> }
>
> @@ -159,7 +159,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
> dev_err(gmu->dev, "GMU set GPU frequency error: %d\n", ret);
>
> dev_pm_opp_set_opp(&gpu->pdev->dev, opp);
> - pm_runtime_put(gmu->dev);
> + pm_runtime_put(&gpu->pdev->dev);
> }
>
> unsigned long a6xx_gmu_get_freq(struct msm_gpu *gpu)
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> index 841e47a0b06b..87568d0b6ef8 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> @@ -1659,7 +1659,7 @@ static u64 a6xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate)
> *out_sample_rate = 19200000;
>
> /* Only read the gpu busy if the hardware is already active */
> - if (pm_runtime_get_if_in_use(a6xx_gpu->gmu.dev) == 0)
> + if (pm_runtime_get_if_in_use(&gpu->pdev->dev) == 0)
> return 0;
>
> busy_cycles = gmu_read64(&a6xx_gpu->gmu,
> @@ -1667,7 +1667,7 @@ static u64 a6xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate)
> REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H);
>
>
> - pm_runtime_put(a6xx_gpu->gmu.dev);
> + pm_runtime_put(&gpu->pdev->dev);
>
> return busy_cycles;
> }
> --
> 2.36.1.255.ge46751e96f-goog
>
On 6/9/2022 9:24 PM, Rob Clark wrote:
> On Thu, Jun 9, 2022 at 7:34 AM Douglas Anderson <[email protected]> wrote:
>> From testing on sc7180-trogdor devices, reading the GMU registers
>> needs the GMU clocks to be enabled. Those clocks get turned on in
>> a6xx_gmu_resume(). Confusingly enough, that function is called as a
>> result of the runtime_pm of the GPU "struct device", not the GMU
>> "struct device".
>>
>> Let's grab a reference to the correct device. Incidentally, this makes
>> us match the a5xx routine more closely.
>>
>> This is easily shown to fix crashes that happen if we change the GPU's
>> pm_runtime usage to not use autosuspend. It's also believed to fix
>> some long tail GPU crashes even with autosuspend.
>>
>> NOTE: the crashes I've seen were fixed by _only_ fixing
>> a6xx_gpu_busy(). However, I believe that the same arguments should be
>> made to a6xx_gmu_set_freq() so I've changed that function too.
>>
>> Fixes: eadf79286a4b ("drm/msm: Check for powered down HW in the devfreq callbacks")
>> Signed-off-by: Douglas Anderson <[email protected]>
>> ---
>>
>> drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 6 +++---
>> drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 4 ++--
>> 2 files changed, 5 insertions(+), 5 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
>> index 9f76f5b15759..b79ad2e0649c 100644
>> --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
>> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
>> @@ -129,13 +129,13 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
>> * This can get called from devfreq while the hardware is idle. Don't
>> * bring up the power if it isn't already active
>> */
>> - if (pm_runtime_get_if_in_use(gmu->dev) == 0)
>> + if (pm_runtime_get_if_in_use(&gpu->pdev->dev) == 0)
> IMHO, if we do end up using the GPU's runpm instead of the GMU's, we
> should probably just move this _get_if_in_use() into msm_gpu_devfreq,
+ 1 this.
> etc. (And probably also this should be "<= 0".. I have that change
> locally but haven't sent a patch yet
.. and skip return here when CONFIG_PM is disabled.
-Akhil.
>
> BR,
> -R
>
>> return;
>>
>> if (!gmu->legacy) {
>> a6xx_hfi_set_freq(gmu, perf_index);
>> dev_pm_opp_set_opp(&gpu->pdev->dev, opp);
>> - pm_runtime_put(gmu->dev);
>> + pm_runtime_put(&gpu->pdev->dev);
>> return;
>> }
>>
>> @@ -159,7 +159,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
>> dev_err(gmu->dev, "GMU set GPU frequency error: %d\n", ret);
>>
>> dev_pm_opp_set_opp(&gpu->pdev->dev, opp);
>> - pm_runtime_put(gmu->dev);
>> + pm_runtime_put(&gpu->pdev->dev);
>> }
>>
>> unsigned long a6xx_gmu_get_freq(struct msm_gpu *gpu)
>> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> index 841e47a0b06b..87568d0b6ef8 100644
>> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> @@ -1659,7 +1659,7 @@ static u64 a6xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate)
>> *out_sample_rate = 19200000;
>>
>> /* Only read the gpu busy if the hardware is already active */
>> - if (pm_runtime_get_if_in_use(a6xx_gpu->gmu.dev) == 0)
>> + if (pm_runtime_get_if_in_use(&gpu->pdev->dev) == 0)
>> return 0;
>>
>> busy_cycles = gmu_read64(&a6xx_gpu->gmu,
>> @@ -1667,7 +1667,7 @@ static u64 a6xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate)
>> REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H);
>>
>>
>> - pm_runtime_put(a6xx_gpu->gmu.dev);
>> + pm_runtime_put(&gpu->pdev->dev);
>>
>> return busy_cycles;
>> }
>> --
>> 2.36.1.255.ge46751e96f-goog
>>
On 6/9/2022 8:03 PM, Douglas Anderson wrote:
> >From testing on sc7180-trogdor devices, reading the GMU registers
">" ??
> needs the GMU clocks to be enabled. Those clocks get turned on in
> a6xx_gmu_resume(). Confusingly enough, that function is called as a
> result of the runtime_pm of the GPU "struct device", not the GMU
> "struct device".
>
> Let's grab a reference to the correct device. Incidentally, this makes
> us match the a5xx routine more closely.
>
> This is easily shown to fix crashes that happen if we change the GPU's
> pm_runtime usage to not use autosuspend. It's also believed to fix
> some long tail GPU crashes even with autosuspend.
>
> NOTE: the crashes I've seen were fixed by _only_ fixing
> a6xx_gpu_busy(). However, I believe that the same arguments should be
> made to a6xx_gmu_set_freq() so I've changed that function too.
>
> Fixes: eadf79286a4b ("drm/msm: Check for powered down HW in the devfreq callbacks")
> Signed-off-by: Douglas Anderson <[email protected]>
> ---
>
> drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 6 +++---
> drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 4 ++--
> 2 files changed, 5 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
> index 9f76f5b15759..b79ad2e0649c 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
> @@ -129,13 +129,13 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
> * This can get called from devfreq while the hardware is idle. Don't
> * bring up the power if it isn't already active
> */
> - if (pm_runtime_get_if_in_use(gmu->dev) == 0)
> + if (pm_runtime_get_if_in_use(&gpu->pdev->dev) == 0)
Wouldn't we return early here when this fn is called from a6xx_gmu_set_initial_freq()?
-Akhil.
> return;
>
> if (!gmu->legacy) {
> a6xx_hfi_set_freq(gmu, perf_index);
> dev_pm_opp_set_opp(&gpu->pdev->dev, opp);
> - pm_runtime_put(gmu->dev);
> + pm_runtime_put(&gpu->pdev->dev);
> return;
> }
>
> @@ -159,7 +159,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
> dev_err(gmu->dev, "GMU set GPU frequency error: %d\n", ret);
>
> dev_pm_opp_set_opp(&gpu->pdev->dev, opp);
> - pm_runtime_put(gmu->dev);
> + pm_runtime_put(&gpu->pdev->dev);
> }
>
> unsigned long a6xx_gmu_get_freq(struct msm_gpu *gpu)
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> index 841e47a0b06b..87568d0b6ef8 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> @@ -1659,7 +1659,7 @@ static u64 a6xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate)
> *out_sample_rate = 19200000;
>
> /* Only read the gpu busy if the hardware is already active */
> - if (pm_runtime_get_if_in_use(a6xx_gpu->gmu.dev) == 0)
> + if (pm_runtime_get_if_in_use(&gpu->pdev->dev) == 0)
> return 0;
>
> busy_cycles = gmu_read64(&a6xx_gpu->gmu,
> @@ -1667,7 +1667,7 @@ static u64 a6xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate)
> REG_A6XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H);
>
>
> - pm_runtime_put(a6xx_gpu->gmu.dev);
> + pm_runtime_put(&gpu->pdev->dev);
>
> return busy_cycles;
> }