| Message ID | 20220810000306.5476-1-vinay.belgaumkar@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | drm/i915/guc/slpc: Allow SLPC to use efficient frequency | expand |
On Tue, Aug 09, 2022 at 05:03:06PM -0700, Vinay Belgaumkar wrote: > Host Turbo operates at efficient frequency when GT is not idle unless > the user or workload has forced it to a higher level. Replicate the same > behavior in SLPC by allowing the algorithm to use efficient frequency. > We had disabled it during boot due to concerns that it might break > kernel ABI for min frequency. However, this is not the case, since > SLPC will still abide by the (min,max) range limits and pcode forces > frequency to 0 anyways when GT is in C6. > > We also see much better perf numbers with benchmarks like glmark2 with > efficient frequency usage enabled. > > Fixes: 025cb07bebfa ("drm/i915/guc/slpc: Cache platform frequency limits") > > Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com> I'm honestly surprised that our CI passed cleanly. What happens when user request both min and max < rpe? I'm sure that in this case GuC SLPC will put us to rpe ignoring our requests. Or is this good enough for the users expectation because of the soft limits showing the requested freq and we not asking to guc what it currently has as minimal? I just want to be sure that we are not causing any confusion for end users out there in the case they request some min/max below RPe and start seeing mismatches on the expectation because GuC is forcing the real min request to RPe. My suggestion is to ignore the RPe whenever we have a min request below it. So GuC respects our (and users) chosen min. And restore whenever min request is abobe rpe. Thanks, Rodrigo. > --- > drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c | 52 --------------------- > 1 file changed, 52 deletions(-) > > diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c > index e1fa1f32f29e..4b824da3048a 100644 > --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c > +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c > @@ -137,17 +137,6 @@ static int guc_action_slpc_set_param(struct intel_guc *guc, u8 id, u32 value) > return ret > 0 ? -EPROTO : ret; > } > > -static int guc_action_slpc_unset_param(struct intel_guc *guc, u8 id) > -{ > - u32 request[] = { > - GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST, > - SLPC_EVENT(SLPC_EVENT_PARAMETER_UNSET, 1), > - id, > - }; > - > - return intel_guc_send(guc, request, ARRAY_SIZE(request)); > -} > - > static bool slpc_is_running(struct intel_guc_slpc *slpc) > { > return slpc_get_state(slpc) == SLPC_GLOBAL_STATE_RUNNING; > @@ -201,16 +190,6 @@ static int slpc_set_param(struct intel_guc_slpc *slpc, u8 id, u32 value) > return ret; > } > > -static int slpc_unset_param(struct intel_guc_slpc *slpc, > - u8 id) > -{ > - struct intel_guc *guc = slpc_to_guc(slpc); > - > - GEM_BUG_ON(id >= SLPC_MAX_PARAM); > - > - return guc_action_slpc_unset_param(guc, id); > -} > - > static int slpc_force_min_freq(struct intel_guc_slpc *slpc, u32 freq) > { > struct drm_i915_private *i915 = slpc_to_i915(slpc); > @@ -597,29 +576,6 @@ static int slpc_set_softlimits(struct intel_guc_slpc *slpc) > return 0; > } > > -static int slpc_ignore_eff_freq(struct intel_guc_slpc *slpc, bool ignore) > -{ > - int ret = 0; > - > - if (ignore) { > - ret = slpc_set_param(slpc, > - SLPC_PARAM_IGNORE_EFFICIENT_FREQUENCY, > - ignore); > - if (!ret) > - return slpc_set_param(slpc, > - SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ, > - slpc->min_freq); > - } else { > - ret = slpc_unset_param(slpc, > - SLPC_PARAM_IGNORE_EFFICIENT_FREQUENCY); > - if (!ret) > - return slpc_unset_param(slpc, > - SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ); > - } > - > - return ret; > -} > - > static int slpc_use_fused_rp0(struct intel_guc_slpc *slpc) > { > /* Force SLPC to used platform rp0 */ > @@ -679,14 +635,6 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc) > > slpc_get_rp_values(slpc); > > - /* Ignore efficient freq and set min to platform min */ > - ret = slpc_ignore_eff_freq(slpc, true); > - if (unlikely(ret)) { > - i915_probe_error(i915, "Failed to set SLPC min to RPn (%pe)\n", > - ERR_PTR(ret)); > - return ret; > - } > - > /* Set SLPC max limit to RP0 */ > ret = slpc_use_fused_rp0(slpc); > if (unlikely(ret)) { > -- > 2.35.1 >
On 8/15/2022 9:51 AM, Rodrigo Vivi wrote: > On Tue, Aug 09, 2022 at 05:03:06PM -0700, Vinay Belgaumkar wrote: >> Host Turbo operates at efficient frequency when GT is not idle unless >> the user or workload has forced it to a higher level. Replicate the same >> behavior in SLPC by allowing the algorithm to use efficient frequency. >> We had disabled it during boot due to concerns that it might break >> kernel ABI for min frequency. However, this is not the case, since >> SLPC will still abide by the (min,max) range limits and pcode forces >> frequency to 0 anyways when GT is in C6. >> >> We also see much better perf numbers with benchmarks like glmark2 with >> efficient frequency usage enabled. >> >> Fixes: 025cb07bebfa ("drm/i915/guc/slpc: Cache platform frequency limits") >> >> Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com> > I'm honestly surprised that our CI passed cleanly. What happens when user > request both min and max < rpe? > > I'm sure that in this case GuC SLPC will put us to rpe ignoring our requests. > Or is this good enough for the users expectation because of the soft limits > showing the requested freq and we not asking to guc what it currently has as > minimal? > > I just want to be sure that we are not causing any confusion for end users > out there in the case they request some min/max below RPe and start seeing > mismatches on the expectation because GuC is forcing the real min request > to RPe. > > My suggestion is to ignore the RPe whenever we have a min request below it. > So GuC respects our (and users) chosen min. And restore whenever min request > is abobe rpe. Yup, I have already sent a patch yesterday with that change, doesn't look like CI has run on it yet. This was the old version. Thanks, Vinay. > > Thanks, > Rodrigo. > >> --- >> drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c | 52 --------------------- >> 1 file changed, 52 deletions(-) >> >> diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c >> index e1fa1f32f29e..4b824da3048a 100644 >> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c >> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c >> @@ -137,17 +137,6 @@ static int guc_action_slpc_set_param(struct intel_guc *guc, u8 id, u32 value) >> return ret > 0 ? -EPROTO : ret; >> } >> >> -static int guc_action_slpc_unset_param(struct intel_guc *guc, u8 id) >> -{ >> - u32 request[] = { >> - GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST, >> - SLPC_EVENT(SLPC_EVENT_PARAMETER_UNSET, 1), >> - id, >> - }; >> - >> - return intel_guc_send(guc, request, ARRAY_SIZE(request)); >> -} >> - >> static bool slpc_is_running(struct intel_guc_slpc *slpc) >> { >> return slpc_get_state(slpc) == SLPC_GLOBAL_STATE_RUNNING; >> @@ -201,16 +190,6 @@ static int slpc_set_param(struct intel_guc_slpc *slpc, u8 id, u32 value) >> return ret; >> } >> >> -static int slpc_unset_param(struct intel_guc_slpc *slpc, >> - u8 id) >> -{ >> - struct intel_guc *guc = slpc_to_guc(slpc); >> - >> - GEM_BUG_ON(id >= SLPC_MAX_PARAM); >> - >> - return guc_action_slpc_unset_param(guc, id); >> -} >> - >> static int slpc_force_min_freq(struct intel_guc_slpc *slpc, u32 freq) >> { >> struct drm_i915_private *i915 = slpc_to_i915(slpc); >> @@ -597,29 +576,6 @@ static int slpc_set_softlimits(struct intel_guc_slpc *slpc) >> return 0; >> } >> >> -static int slpc_ignore_eff_freq(struct intel_guc_slpc *slpc, bool ignore) >> -{ >> - int ret = 0; >> - >> - if (ignore) { >> - ret = slpc_set_param(slpc, >> - SLPC_PARAM_IGNORE_EFFICIENT_FREQUENCY, >> - ignore); >> - if (!ret) >> - return slpc_set_param(slpc, >> - SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ, >> - slpc->min_freq); >> - } else { >> - ret = slpc_unset_param(slpc, >> - SLPC_PARAM_IGNORE_EFFICIENT_FREQUENCY); >> - if (!ret) >> - return slpc_unset_param(slpc, >> - SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ); >> - } >> - >> - return ret; >> -} >> - >> static int slpc_use_fused_rp0(struct intel_guc_slpc *slpc) >> { >> /* Force SLPC to used platform rp0 */ >> @@ -679,14 +635,6 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc) >> >> slpc_get_rp_values(slpc); >> >> - /* Ignore efficient freq and set min to platform min */ >> - ret = slpc_ignore_eff_freq(slpc, true); >> - if (unlikely(ret)) { >> - i915_probe_error(i915, "Failed to set SLPC min to RPn (%pe)\n", >> - ERR_PTR(ret)); >> - return ret; >> - } >> - >> /* Set SLPC max limit to RP0 */ >> ret = slpc_use_fused_rp0(slpc); >> if (unlikely(ret)) { >> -- >> 2.35.1 >>
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c index e1fa1f32f29e..4b824da3048a 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c @@ -137,17 +137,6 @@ static int guc_action_slpc_set_param(struct intel_guc *guc, u8 id, u32 value) return ret > 0 ? -EPROTO : ret; } -static int guc_action_slpc_unset_param(struct intel_guc *guc, u8 id) -{ - u32 request[] = { - GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST, - SLPC_EVENT(SLPC_EVENT_PARAMETER_UNSET, 1), - id, - }; - - return intel_guc_send(guc, request, ARRAY_SIZE(request)); -} - static bool slpc_is_running(struct intel_guc_slpc *slpc) { return slpc_get_state(slpc) == SLPC_GLOBAL_STATE_RUNNING; @@ -201,16 +190,6 @@ static int slpc_set_param(struct intel_guc_slpc *slpc, u8 id, u32 value) return ret; } -static int slpc_unset_param(struct intel_guc_slpc *slpc, - u8 id) -{ - struct intel_guc *guc = slpc_to_guc(slpc); - - GEM_BUG_ON(id >= SLPC_MAX_PARAM); - - return guc_action_slpc_unset_param(guc, id); -} - static int slpc_force_min_freq(struct intel_guc_slpc *slpc, u32 freq) { struct drm_i915_private *i915 = slpc_to_i915(slpc); @@ -597,29 +576,6 @@ static int slpc_set_softlimits(struct intel_guc_slpc *slpc) return 0; } -static int slpc_ignore_eff_freq(struct intel_guc_slpc *slpc, bool ignore) -{ - int ret = 0; - - if (ignore) { - ret = slpc_set_param(slpc, - SLPC_PARAM_IGNORE_EFFICIENT_FREQUENCY, - ignore); - if (!ret) - return slpc_set_param(slpc, - SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ, - slpc->min_freq); - } else { - ret = slpc_unset_param(slpc, - SLPC_PARAM_IGNORE_EFFICIENT_FREQUENCY); - if (!ret) - return slpc_unset_param(slpc, - SLPC_PARAM_GLOBAL_MIN_GT_UNSLICE_FREQ_MHZ); - } - - return ret; -} - static int slpc_use_fused_rp0(struct intel_guc_slpc *slpc) { /* Force SLPC to used platform rp0 */ @@ -679,14 +635,6 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc) slpc_get_rp_values(slpc); - /* Ignore efficient freq and set min to platform min */ - ret = slpc_ignore_eff_freq(slpc, true); - if (unlikely(ret)) { - i915_probe_error(i915, "Failed to set SLPC min to RPn (%pe)\n", - ERR_PTR(ret)); - return ret; - } - /* Set SLPC max limit to RP0 */ ret = slpc_use_fused_rp0(slpc); if (unlikely(ret)) {
Host Turbo operates at efficient frequency when GT is not idle unless the user or workload has forced it to a higher level. Replicate the same behavior in SLPC by allowing the algorithm to use efficient frequency. We had disabled it during boot due to concerns that it might break kernel ABI for min frequency. However, this is not the case, since SLPC will still abide by the (min,max) range limits and pcode forces frequency to 0 anyways when GT is in C6. We also see much better perf numbers with benchmarks like glmark2 with efficient frequency usage enabled. Fixes: 025cb07bebfa ("drm/i915/guc/slpc: Cache platform frequency limits") Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com> --- drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c | 52 --------------------- 1 file changed, 52 deletions(-)