[PATCH v7] drm/i915/selftests: Implement frequency logging for energy reading validation

[Nilawar, Badal]

On 29-11-2024 21:17, Sk Anirban wrote:
> Add RC6 & RC0 frequency printing to ensure accurate energy
> readings aimed at addressing GPU energy leaks and power
> measurement failures.
> Also update sleep time for RC6 mode to match RC0.
> 
> v2:
>    - Improved commit message.
> v3:
>    - Used pr_err log to display frequency (Anshuman)
>    - Sorted headers alphabetically (Sai Teja)
> v4:
>    - Improved commit message.
>    - Fix pr_err log (Sai Teja)
> v5:
>    - Add error & debug logging for RC0 power and frequency checks (Anshuman)
> v6:
>    - Modify debug logging for RC0 power and frequency checks (Sai Teja)
> v7:
>    - Use pr_debug if RC0 power isn't measured but frequency is (Anshuman)
>    - Improved commit message (Badal)
>    - Change API to read actual frequency without applying forcewake (Badal)
>    - Update sleep time for RC6 mode (Anshuman)
> 
> Signed-off-by: Sk Anirban <sk.anirban at intel.com>
> Reviewed-by: Sai Teja Pottumuttu <sai.teja.pottumuttu at intel.com>
> ---
>   drivers/gpu/drm/i915/gt/selftest_rc6.c | 17 ++++++++++++++---
>   1 file changed, 14 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.c b/drivers/gpu/drm/i915/gt/selftest_rc6.c
> index 1aa1446c8fb0..27b6d51ef145 100644
> --- a/drivers/gpu/drm/i915/gt/selftest_rc6.c
> +++ b/drivers/gpu/drm/i915/gt/selftest_rc6.c
> @@ -8,6 +8,7 @@
>   #include "intel_gpu_commands.h"
>   #include "intel_gt_requests.h"
>   #include "intel_ring.h"
> +#include "intel_rps.h"
>   #include "selftest_rc6.h"
>   
>   #include "selftests/i915_random.h"
> @@ -38,6 +39,9 @@ int live_rc6_manual(void *arg)
>   	ktime_t dt;
>   	u64 res[2];
>   	int err = 0;
> +	u32 rc0_freq = 0;
> +	u32 rc6_freq = 0;
> +	struct intel_rps *rps = &gt->rps;
>   
>   	/*
>   	 * Our claim is that we can "encourage" the GPU to enter rc6 at will.
> @@ -66,6 +70,7 @@ int live_rc6_manual(void *arg)
>   	rc0_power = librapl_energy_uJ() - rc0_power;
>   	dt = ktime_sub(ktime_get(), dt);
>   	res[1] = rc6_residency(rc6);
> +	rc0_freq = intel_rps_read_actual_frequency_fw(rps);
>   	if ((res[1] - res[0]) >> 10) {
>   		pr_err("RC6 residency increased by %lldus while disabled for 1000ms!\n",
>   		       (res[1] - res[0]) >> 10);
> @@ -77,7 +82,11 @@ int live_rc6_manual(void *arg)
>   		rc0_power = div64_u64(NSEC_PER_SEC * rc0_power,
>   				      ktime_to_ns(dt));
>   		if (!rc0_power) {
> -			pr_err("No power measured while in RC0\n");
> +			if (rc0_freq)
> +				pr_debug("No power measured while in RC0! GPU Freq: %u in RC0\n",
> +					 rc0_freq);
> +			else
> +				pr_err("No power and freq measured while in RC0\n");
>   			err = -EINVAL;
>   			goto out_unlock;
>   		}
> @@ -90,7 +99,8 @@ int live_rc6_manual(void *arg)
>   	intel_uncore_forcewake_flush(rc6_to_uncore(rc6), FORCEWAKE_ALL);
>   	dt = ktime_get();
>   	rc6_power = librapl_energy_uJ();
> -	msleep(100);
> +	msleep(1000);
> +	rc6_freq = intel_rps_read_actual_frequency_fw(rps);
>   	rc6_power = librapl_energy_uJ() - rc6_power;
>   	dt = ktime_sub(ktime_get(), dt);
>   	res[1] = rc6_residency(rc6);
> @@ -108,7 +118,8 @@ int live_rc6_manual(void *arg)
>   		pr_info("GPU consumed %llduW in RC0 and %llduW in RC6\n",
>   			rc0_power, rc6_power);
>   		if (2 * rc6_power > rc0_power) {
> -			pr_err("GPU leaked energy while in RC6!\n");
> +			pr_err("GPU leaked energy while in RC6! GPU Freq: %u in RC6 and %u in RC0\n",
> +			       rc6_freq, rc0_freq);


LGTM
Reviewed-by: Badal Nilawar <badal.nilawar at intel.com>

Regards,
Badal

>   			err = -EINVAL;
>   			goto out_unlock;
>   		}