On Wed, Dec 13, 2017 at 4:52 AM, Rex Zhu <Rex.Zhu at amd.com> wrote:
> Change-Id: I344731cc6398c40976e08a125808bbfa85cb59a3
> Signed-off-by: Rex Zhu <Rex.Zhu at amd.com>
Please include a better patch description. Something like:
Flag the stable pstate clocks in sysfs so userspace knows what clocks
are in use when stable pstate is selected for profiling.
We also probably need to handles APUs.
Alex
> ---
> drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 43 +++++++++++++---------
> drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 36 ++++++++++++++----
> drivers/gpu/drm/amd/powerplay/inc/hwmgr.h | 2 +
> 3 files changed, 56 insertions(+), 25 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
> index 8edb0c4..ecf9449 100644
> --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
> +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
> @@ -2590,8 +2590,10 @@ static int smu7_get_profiling_clk(struct pp_hwmgr *hwmgr, enum amd_dpm_forced_le
> break;
> }
> }
> - if (count < 0 || level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK)
> + if (count < 0 || level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) {
> *sclk_mask = 0;
> + tmp_sclk = table_info->vdd_dep_on_sclk->entries[0].clk;
> + }
>
> if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
> *sclk_mask = table_info->vdd_dep_on_sclk->count - 1;
> @@ -2603,6 +2605,10 @@ static int smu7_get_profiling_clk(struct pp_hwmgr *hwmgr, enum amd_dpm_forced_le
> *mclk_mask = golden_dpm_table->mclk_table.count - 1;
>
> *pcie_mask = data->dpm_table.pcie_speed_table.count - 1;
> +
> + hwmgr->pstate_sclk = tmp_sclk;
> + hwmgr->pstate_mclk = tmp_mclk;
> +
> return 0;
> }
>
> @@ -2614,6 +2620,10 @@ static int smu7_force_dpm_level(struct pp_hwmgr *hwmgr,
> uint32_t mclk_mask = 0;
> uint32_t pcie_mask = 0;
>
> + ret = smu7_get_profiling_clk(hwmgr, level, &sclk_mask, &mclk_mask, &pcie_mask);
> + if (ret)
> + return ret;
> +
> switch (level) {
> case AMD_DPM_FORCED_LEVEL_HIGH:
> ret = smu7_force_dpm_highest(hwmgr);
> @@ -2628,9 +2638,6 @@ static int smu7_force_dpm_level(struct pp_hwmgr *hwmgr,
> case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
> case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
> case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
> - ret = smu7_get_profiling_clk(hwmgr, level, &sclk_mask, &mclk_mask, &pcie_mask);
> - if (ret)
> - return ret;
> smu7_force_clock_level(hwmgr, PP_SCLK, 1<<sclk_mask);
> smu7_force_clock_level(hwmgr, PP_MCLK, 1<<mclk_mask);
> smu7_force_clock_level(hwmgr, PP_PCIE, 1<<pcie_mask);
> @@ -4292,7 +4299,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
> struct smu7_single_dpm_table *sclk_table = &(data->dpm_table.sclk_table);
> struct smu7_single_dpm_table *mclk_table = &(data->dpm_table.mclk_table);
> struct smu7_single_dpm_table *pcie_table = &(data->dpm_table.pcie_speed_table);
> - int i, now, size = 0;
> + int i, now, p, size = 0;
> uint32_t clock, pcie_speed;
>
> switch (type) {
> @@ -4301,32 +4308,34 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
> clock = cgs_read_register(hwmgr->device, mmSMC_MSG_ARG_0);
>
> for (i = 0; i < sclk_table->count; i++) {
> - if (clock > sclk_table->dpm_levels[i].value)
> - continue;
> - break;
> + if (hwmgr->pstate_sclk == sclk_table->dpm_levels[i].value)
> + p = i;
> + if (clock <= sclk_table->dpm_levels[i].value)
> + now = i;
> }
> - now = i;
>
> for (i = 0; i < sclk_table->count; i++)
> - size += sprintf(buf + size, "%d: %uMhz %s\n",
> + size += sprintf(buf + size, "%d: %uMhz %s %s\n",
> i, sclk_table->dpm_levels[i].value / 100,
> - (i == now) ? "*" : "");
> + (i == now) ? "*" : "",
> + (i == p) ? "P" : "");
> break;
> case PP_MCLK:
> smum_send_msg_to_smc(hwmgr, PPSMC_MSG_API_GetMclkFrequency);
> clock = cgs_read_register(hwmgr->device, mmSMC_MSG_ARG_0);
>
> for (i = 0; i < mclk_table->count; i++) {
> - if (clock > mclk_table->dpm_levels[i].value)
> - continue;
> - break;
> + if (hwmgr->pstate_mclk == mclk_table->dpm_levels[i].value)
> + p = i;
> + if (clock <= mclk_table->dpm_levels[i].value)
> + now = i;
> }
> - now = i;
>
> for (i = 0; i < mclk_table->count; i++)
> - size += sprintf(buf + size, "%d: %uMhz %s\n",
> + size += sprintf(buf + size, "%d: %uMhz %s %s\n",
> i, mclk_table->dpm_levels[i].value / 100,
> - (i == now) ? "*" : "");
> + (i == now) ? "*" : "",
> + (i == p) ? "P" : "");
> break;
> case PP_PCIE:
> pcie_speed = smu7_get_current_pcie_speed(hwmgr);
> diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
> index 07d256d..82c56f7 100644
> --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
> +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
> @@ -4207,6 +4207,8 @@ static int vega10_get_profiling_clk_mask(struct pp_hwmgr *hwmgr, enum amd_dpm_fo
> *sclk_mask = VEGA10_UMD_PSTATE_GFXCLK_LEVEL;
> *soc_mask = VEGA10_UMD_PSTATE_SOCCLK_LEVEL;
> *mclk_mask = VEGA10_UMD_PSTATE_MCLK_LEVEL;
> + hwmgr->pstate_sclk = table_info->vdd_dep_on_sclk->entries[VEGA10_UMD_PSTATE_GFXCLK_LEVEL].clk;
> + hwmgr->pstate_mclk = table_info->vdd_dep_on_mclk->entries[VEGA10_UMD_PSTATE_MCLK_LEVEL].clk;
> }
>
> if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) {
> @@ -4218,6 +4220,7 @@ static int vega10_get_profiling_clk_mask(struct pp_hwmgr *hwmgr, enum amd_dpm_fo
> *soc_mask = table_info->vdd_dep_on_socclk->count - 1;
> *mclk_mask = table_info->vdd_dep_on_mclk->count - 1;
> }
> +
> return 0;
> }
>
> @@ -4248,6 +4251,10 @@ static int vega10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
> uint32_t mclk_mask = 0;
> uint32_t soc_mask = 0;
>
> + ret = vega10_get_profiling_clk_mask(hwmgr, level, &sclk_mask, &mclk_mask, &soc_mask);
> + if (ret)
> + return ret;
> +
> switch (level) {
> case AMD_DPM_FORCED_LEVEL_HIGH:
> ret = vega10_force_dpm_highest(hwmgr);
> @@ -4262,9 +4269,6 @@ static int vega10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
> case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
> case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
> case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
> - ret = vega10_get_profiling_clk_mask(hwmgr, level, &sclk_mask, &mclk_mask, &soc_mask);
> - if (ret)
> - return ret;
> vega10_force_clock_level(hwmgr, PP_SCLK, 1<<sclk_mask);
> vega10_force_clock_level(hwmgr, PP_MCLK, 1<<mclk_mask);
> break;
> @@ -4594,13 +4598,20 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
> struct vega10_single_dpm_table *sclk_table = &(data->dpm_table.gfx_table);
> struct vega10_single_dpm_table *mclk_table = &(data->dpm_table.mem_table);
> struct vega10_pcie_table *pcie_table = &(data->dpm_table.pcie_table);
> - int i, now, size = 0;
> + int i, p, now, size = 0;
>
> switch (type) {
> case PP_SCLK:
> if (data->registry_data.sclk_dpm_key_disabled)
> break;
>
> + for (i = 0; i < sclk_table->count; i++) {
> + if (hwmgr->pstate_sclk == sclk_table->dpm_levels[i].value) {
> + p = i;
> + break;
> + }
> + }
> +
> PP_ASSERT_WITH_CODE(!smum_send_msg_to_smc(hwmgr,
> PPSMC_MSG_GetCurrentGfxclkIndex),
> "Attempt to get current sclk index Failed!",
> @@ -4611,14 +4622,22 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
> return -1);
>
> for (i = 0; i < sclk_table->count; i++)
> - size += sprintf(buf + size, "%d: %uMhz %s\n",
> + size += sprintf(buf + size, "%d: %uMhz %s %s\n",
> i, sclk_table->dpm_levels[i].value / 100,
> - (i == now) ? "*" : "");
> + (i == now) ? "*" : "",
> + (i == p) ? "P" : "");
> break;
> case PP_MCLK:
> if (data->registry_data.mclk_dpm_key_disabled)
> break;
>
> + for (i = 0; i < mclk_table->count; i++) {
> + if (hwmgr->pstate_mclk == mclk_table->dpm_levels[i].value) {
> + p = i;
> + break;
> + }
> + }
> +
> PP_ASSERT_WITH_CODE(!smum_send_msg_to_smc(hwmgr,
> PPSMC_MSG_GetCurrentUclkIndex),
> "Attempt to get current mclk index Failed!",
> @@ -4629,9 +4648,10 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
> return -1);
>
> for (i = 0; i < mclk_table->count; i++)
> - size += sprintf(buf + size, "%d: %uMhz %s\n",
> + size += sprintf(buf + size, "%d: %uMhz %s %s\n",
> i, mclk_table->dpm_levels[i].value / 100,
> - (i == now) ? "*" : "");
> + (i == now) ? "*" : "",
> + (i == p) ? "P" : "");
> break;
> case PP_PCIE:
> PP_ASSERT_WITH_CODE(!smum_send_msg_to_smc(hwmgr,
> diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
> index 004a40e..568f56c 100644
> --- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
> +++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
> @@ -780,6 +780,8 @@ struct pp_hwmgr {
> struct amd_pp_profile default_compute_power_profile;
> enum amd_pp_profile_type current_power_profile;
> bool en_umd_pstate;
> + uint32_t pstate_sclk;
> + uint32_t pstate_mclk;
> };
>
> struct cgs_irq_src_funcs {
> --
> 1.9.1
>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
