Re: [PATCH 1/3] Revert "drm/amd/powerply: fix power reading on Fiji"
If it is verified by SMU team, I am OK with it. Regards, Eric On 2018-04-11 01:19 PM, Alex Deucher wrote: On Wed, Apr 11, 2018 at 2:31 AM, Rex Zhuwrote: we don't have limit of [50ms, 4sec] sampling period. smu calculate average gpu power in real time. we can read average gpu power through smu message or read special register. This reverts commit 462d8dcc9fec0d89f1ff6a1f93f1d4f670878c71. Signed-off-by: Rex Zhu If Eric is ok with this, Acked-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index 21c021b..388184e 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3364,8 +3364,7 @@ static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr, "Failed to start pm status log!", return -1); - /* Sampling period from 50ms to 4sec */ - msleep_interruptible(200); + msleep_interruptible(20); PP_ASSERT_WITH_CODE(!smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PmStatusLogSample), -- 1.9.1 ___ amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx ___ amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx ___ amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Re: [PATCH 1/3] Revert "drm/amd/powerply: fix power reading on Fiji"
On Wed, Apr 11, 2018 at 2:31 AM, Rex Zhuwrote: > we don't have limit of [50ms, 4sec] sampling period. > smu calculate average gpu power in real time. > we can read average gpu power through smu message or > read special register. > > This reverts commit 462d8dcc9fec0d89f1ff6a1f93f1d4f670878c71. > > Signed-off-by: Rex Zhu If Eric is ok with this, Acked-by: Alex Deucher > --- > drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 3 +-- > 1 file changed, 1 insertion(+), 2 deletions(-) > > diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c > b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c > index 21c021b..388184e 100644 > --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c > +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c > @@ -3364,8 +3364,7 @@ static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr, > "Failed to start pm status log!", > return -1); > > - /* Sampling period from 50ms to 4sec */ > - msleep_interruptible(200); > + msleep_interruptible(20); > > PP_ASSERT_WITH_CODE(!smum_send_msg_to_smc(hwmgr, > PPSMC_MSG_PmStatusLogSample), > -- > 1.9.1 > > ___ > amd-gfx mailing list > amd-gfx@lists.freedesktop.org > https://lists.freedesktop.org/mailman/listinfo/amd-gfx ___ amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx
[PATCH 1/3] Revert "drm/amd/powerply: fix power reading on Fiji"
we don't have limit of [50ms, 4sec] sampling period. smu calculate average gpu power in real time. we can read average gpu power through smu message or read special register. This reverts commit 462d8dcc9fec0d89f1ff6a1f93f1d4f670878c71. Signed-off-by: Rex Zhu--- drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index 21c021b..388184e 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3364,8 +3364,7 @@ static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr, "Failed to start pm status log!", return -1); - /* Sampling period from 50ms to 4sec */ - msleep_interruptible(200); + msleep_interruptible(20); PP_ASSERT_WITH_CODE(!smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PmStatusLogSample), -- 1.9.1 ___ amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Re: [PATCH 1/3] Revert "drm/amd/powerply: fix power reading on Fiji"
Did you contact tools team about this? Since the smc messages PPSMC_MSG_PmStatusLogStart and PPSMC_MSG_PmStatusLogSample are exclusively used by tools, driver just shared it. And AGT gets different result as driver if you change it back to 20ms. To keep consistent result as AGT, please verify it through full test cases. Regards, Eric On 2018-04-04 04:25 AM, Rex Zhu wrote: we don't have limit of [50ms, 4sec] sampling period. only confused the average power and max power. so don't need to increase delay time. This reverts commit 462d8dcc9fec0d89f1ff6a1f93f1d4f670878c71. Signed-off-by: Rex Zhu--- drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index aaa9f5b..40f2f87 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3368,8 +3368,7 @@ static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr, "Failed to start pm status log!", return -1); - /* Sampling period from 50ms to 4sec */ - msleep_interruptible(200); + msleep_interruptible(20); PP_ASSERT_WITH_CODE(!smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PmStatusLogSample), ___ amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx
[PATCH 1/3] Revert "drm/amd/powerply: fix power reading on Fiji"
we don't have limit of [50ms, 4sec] sampling period. only confused the average power and max power. so don't need to increase delay time. This reverts commit 462d8dcc9fec0d89f1ff6a1f93f1d4f670878c71. Signed-off-by: Rex Zhu--- drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index aaa9f5b..40f2f87 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3368,8 +3368,7 @@ static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr, "Failed to start pm status log!", return -1); - /* Sampling period from 50ms to 4sec */ - msleep_interruptible(200); + msleep_interruptible(20); PP_ASSERT_WITH_CODE(!smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PmStatusLogSample), -- 1.9.1 ___ amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx