[AMD Official Use Only]
>> And a preempt_enable(); here. This way the critical section is also not interrupted by a task switch.
Do you mean put a "preempt_disable()" here ?
Thanks
------------------------------------------
Monk Liu | Cloud-GPU Core team
------------------------------------------
-----Original Message-----
From: Christian König <ckoenig.leichtzumerken@xxxxxxxxx>
Sent: Wednesday, June 30, 2021 7:15 PM
To: Wang, YuBiao <YuBiao.Wang@xxxxxxx>; amd-gfx@xxxxxxxxxxxxxxxxxxxxx
Cc: Grodzovsky, Andrey <Andrey.Grodzovsky@xxxxxxx>; Xiao, Jack <Jack.Xiao@xxxxxxx>; Xu, Feifei <Feifei.Xu@xxxxxxx>; Chen, Horace <Horace.Chen@xxxxxxx>; Wang, Kevin(Yang) <Kevin1.Wang@xxxxxxx>; Tuikov, Luben <Luben.Tuikov@xxxxxxx>; Deucher, Alexander <Alexander.Deucher@xxxxxxx>; Quan, Evan <Evan.Quan@xxxxxxx>; Koenig, Christian <Christian.Koenig@xxxxxxx>; Liu, Monk <Monk.Liu@xxxxxxx>; Zhang, Hawking <Hawking.Zhang@xxxxxxx>
Subject: Re: [PATCH 1/1] drm/amdgpu: Read clock counter via MMIO to reduce delay (v4)
Am 30.06.21 um 12:10 schrieb YuBiao Wang:
> [Why]
> GPU timing counters are read via KIQ under sriov, which will introduce
> a delay.
>
> [How]
> It could be directly read by MMIO.
>
> v2: Add additional check to prevent carryover issue.
> v3: Only check for carryover for once to prevent performance issue.
> v4: Add comments of the rough frequency where carryover happens.
>
> Signed-off-by: YuBiao Wang <YuBiao.Wang@xxxxxxx>
> Acked-by: Horace Chen <horace.chen@xxxxxxx>
> ---
> drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 13 ++++++++++---
> 1 file changed, 10 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
> b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
> index ff7e9f49040e..9355494002a1 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
> @@ -7609,7 +7609,7 @@ static int gfx_v10_0_soft_reset(void *handle)
>
> static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev)
> {
> - uint64_t clock;
> + uint64_t clock, clock_lo, clock_hi, hi_check;
>
> amdgpu_gfx_off_ctrl(adev, false);
> mutex_lock(&adev->gfx.gpu_clock_mutex);
> @@ -7620,8 +7620,15 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev)
> ((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh) << 32ULL);
> break;
> default:
> - clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER) |
> - ((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER) << 32ULL);
If you want to be extra sure you could add a preempt_disable(); here.
> + clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER);
> + clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER);
> + hi_check = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER);
> + /* Carryover happens every 4 Giga time cycles counts which is roughly 42 secs */
> + if (hi_check != clock_hi) {
> + clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER);
> + clock_hi = hi_check;
> + }
And a preempt_enable(); here. This way the critical section is also not interrupted by a task switch.
But either way the patch is Reviewed-by: Christian König <christian.koenig@xxxxxxx>
Regards,
Christian.
> + clock = (uint64_t)clock_lo | ((uint64_t)clock_hi << 32ULL);
> break;
> }
> mutex_unlock(&adev->gfx.gpu_clock_mutex);
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
