[PATCH 4/8] drm/i915/perf: lock powergating configuration to default when active

[Chris Wilson]

From: Lionel Landwerlin <lionel.g.landwerlin at intel.com>

If some of the contexts submitting workloads to the GPU have been
configured to shutdown slices/subslices, we might loose the NOA
configurations written in the NOA muxes.

One possible solution to this problem is to reprogram the NOA muxes
when we switch to a new context. We initially tried this in the
workaround batchbuffer but some concerns where raised about the cost
of reprogramming at every context switch. This solution is also not
without consequences from the userspace point of view. Reprogramming
of the muxes can only happen once the powergating configuration has
changed (which happens after context switch). This means for a window
of time during the recording, counters recorded by the OA unit might
be invalid. This requires userspace dealing with OA reports to discard
the invalid values.

Minimizing the reprogramming could be implemented by tracking of the
last programmed configuration somewhere in GGTT and use MI_PREDICATE
to discard some of the programming commands, but the command streamer
would still have to parse all the MI_LRI instructions in the
workaround batchbuffer.

Another solution, which this change implements, is to simply disregard
the user requested configuration for the period of time when i915/perf
is active. There is no known issue with this apart from a performance
penality for some media workloads that benefit from running on a
partially powergated GPU. We already prevent RC6 from affecting the
programming so it doesn't sound completely unreasonable to hold on
powergating for the same reason.

v2: Leave RPCS programming in intel_lrc.c (Lionel)

v3: Update for s/union intel_sseu/struct intel_sseu/ (Lionel)
    More to_intel_context() (Tvrtko)
    s/dev_priv/i915/ (Tvrtko)

Tvrtko Ursulin:

v4:
 * Rebase for make_rpcs changes.

v5:
 * Apply OA restriction from make_rpcs directly.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/i915_perf.c |  5 +++++
 drivers/gpu/drm/i915/intel_lrc.c | 30 ++++++++++++++++++++----------
 drivers/gpu/drm/i915/intel_lrc.h |  3 +++
 3 files changed, 28 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index ccb20230df2c..dd65b72bddd4 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1677,6 +1677,11 @@ static void gen8_update_reg_state_unlocked(struct i915_gem_context *ctx,
 
 		CTX_REG(reg_state, state_offset, flex_regs[i], value);
 	}
+
+	CTX_REG(reg_state, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE,
+		gen8_make_rpcs(dev_priv,
+			       &to_intel_context(ctx,
+						 dev_priv->engine[RCS])->sseu));
 }
 
 /*
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 51f00cc51a81..ae835ac349f0 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1303,9 +1303,6 @@ static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma)
 	return i915_vma_pin(vma, 0, 0, flags);
 }
 
-static u32 make_rpcs(struct drm_i915_private *dev_priv,
-		     struct intel_sseu *ctx_sseu);
-
 static struct intel_context *
 __execlists_context_pin(struct intel_engine_cs *engine,
 			struct i915_gem_context *ctx,
@@ -1344,7 +1341,7 @@ __execlists_context_pin(struct intel_engine_cs *engine,
 	/* RPCS */
 	ce->lrc_reg_state[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
 	CTX_REG(ce->lrc_reg_state, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE,
-		make_rpcs(engine->i915, &ce->sseu));
+		gen8_make_rpcs(engine->i915, &ce->sseu));
 
 	ce->state->obj->pin_global++;
 	i915_gem_context_get(ctx);
@@ -2485,15 +2482,28 @@ int logical_xcs_ring_init(struct intel_engine_cs *engine)
 	return logical_ring_init(engine);
 }
 
-static u32 make_rpcs(struct drm_i915_private *dev_priv,
-		     struct intel_sseu *ctx_sseu)
+u32 gen8_make_rpcs(struct drm_i915_private *dev_priv,
+		   struct intel_sseu *req_sseu)
 {
 	const struct sseu_dev_info *sseu = &INTEL_INFO(dev_priv)->sseu;
 	bool subslice_pg = sseu->has_subslice_pg;
-	u8 slices = hweight8(ctx_sseu->slice_mask);
-	u8 subslices = hweight8(ctx_sseu->subslice_mask);
+	struct intel_sseu ctx_sseu;
+	u8 slices, subslices;
 	u32 rpcs = 0;
 
+	/*
+	 * If i915/perf is active, we want a stable powergating configuration
+	 * on the system. The most natural configuration to take in that case
+	 * is the default (i.e maximum the hardware can do).
+	 */
+	if (unlikely(dev_priv->perf.oa.exclusive_stream))
+		ctx_sseu = intel_device_default_sseu(dev_priv);
+	else
+		ctx_sseu = *req_sseu;
+
+	slices = hweight8(ctx_sseu.slice_mask);
+	subslices = hweight8(ctx_sseu.subslice_mask);
+
 	/*
 	 * Since the SScount bitfield in GEN8_R_PWR_CLK_STATE is only three bits
 	 * wide and Icelake has up to eight subslices, specfial programming is
@@ -2563,13 +2573,13 @@ static u32 make_rpcs(struct drm_i915_private *dev_priv,
 	if (sseu->has_eu_pg) {
 		u32 val;
 
-		val = ctx_sseu->min_eus_per_subslice << GEN8_RPCS_EU_MIN_SHIFT;
+		val = ctx_sseu.min_eus_per_subslice << GEN8_RPCS_EU_MIN_SHIFT;
 		GEM_BUG_ON(val & ~GEN8_RPCS_EU_MIN_MASK);
 		val &= GEN8_RPCS_EU_MIN_MASK;
 
 		rpcs |= val;
 
-		val = ctx_sseu->max_eus_per_subslice << GEN8_RPCS_EU_MAX_SHIFT;
+		val = ctx_sseu.max_eus_per_subslice << GEN8_RPCS_EU_MAX_SHIFT;
 		GEM_BUG_ON(val & ~GEN8_RPCS_EU_MAX_MASK);
 		val &= GEN8_RPCS_EU_MAX_MASK;
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index f5a5502ecf70..11da6fc0002d 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -104,4 +104,7 @@ void intel_lr_context_resume(struct drm_i915_private *dev_priv);
 
 void intel_execlists_set_default_submission(struct intel_engine_cs *engine);
 
+u32 gen8_make_rpcs(struct drm_i915_private *dev_priv,
+		   struct intel_sseu *ctx_sseu);
+
 #endif /* _INTEL_LRC_H_ */
-- 
2.19.0.rc1