drm/i915/perf: lock powergating configuration to default when active

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.

On most platforms there are no issues 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.

On Icelake however there would a functional problem if the slices not-
containing the VME block were left enabled with a running media workload
which explicitly disabled them. To avoid a GPU hang in this case, on
Icelake we lock the enablement to only slices which contain VME blocks.
Downside is that it means degraded GPU performance when OA is active but
there is no known alternative solution for this.

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.

v6:
 * Rebase for context image setup changes.

v7:
 * Move stream assignment before metric enable.

v8-9:
 * Rebase.

v10:
 * Squashed with ICL support patch.

Bspec: 21140
Co-developed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> # v9
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-2-tvrtko.ursulin@linux.intel.com

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));
 }
 
 /*
@@ -2098,21 +2103,21 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	if (ret)
 		goto err_lock;
 
+	stream->ops = &i915_oa_stream_ops;
+	dev_priv->perf.oa.exclusive_stream = stream;
+
 	ret = dev_priv->perf.oa.ops.enable_metric_set(stream);
 	if (ret) {
 		DRM_DEBUG("Unable to enable metric set\n");
 		goto err_enable;
 	}
 
-	stream->ops = &i915_oa_stream_ops;
-
-	dev_priv->perf.oa.exclusive_stream = stream;
-
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	return 0;
 
 err_enable:
+	dev_priv->perf.oa.exclusive_stream = NULL;
 	dev_priv->perf.oa.ops.disable_metric_set(dev_priv);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 

drivers/gpu/drm/i915/intel_lrc.c

@@ -1266,9 +1266,6 @@ 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 *i915, struct intel_sseu *ctx_sseu);
-
 static void
 __execlists_update_reg_state(struct intel_engine_cs *engine,
 			     struct intel_context *ce)
@@ -1282,8 +1279,8 @@ __execlists_update_reg_state(struct intel_engine_cs *engine,
 
 	/* RPCS */
 	if (engine->class == RENDER_CLASS)
-		regs[CTX_R_PWR_CLK_STATE + 1] = make_rpcs(engine->i915,
-							  &ce->sseu);
+		regs[CTX_R_PWR_CLK_STATE + 1] = gen8_make_rpcs(engine->i915,
+							       &ce->sseu);
 }
 
 static struct intel_context *
@@ -2433,13 +2430,12 @@ int logical_xcs_ring_init(struct intel_engine_cs *engine)
 	return logical_ring_init(engine);
 }
 
-static u32
-make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu)
+u32 gen8_make_rpcs(struct drm_i915_private *i915, struct intel_sseu *req_sseu)
 {
 	const struct sseu_dev_info *sseu = &RUNTIME_INFO(i915)->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;
 
 	/*
@@ -2449,6 +2445,34 @@ make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu)
 	if (INTEL_GEN(i915) < 9)
 		return 0;
 
+	/*
+	 * If i915/perf is active, we want a stable powergating configuration
+	 * on the system.
+	 *
+	 * We could choose full enablement, but on ICL we know there are use
+	 * cases which disable slices for functional, apart for performance
+	 * reasons. So in this case we select a known stable subset.
+	 */
+	if (!i915->perf.oa.exclusive_stream) {
+		ctx_sseu = *req_sseu;
+	} else {
+		ctx_sseu = intel_device_default_sseu(i915);
+
+		if (IS_GEN(i915, 11)) {
+			/*
+			 * We only need subslice count so it doesn't matter
+			 * which ones we select - just turn off low bits in the
+			 * amount of half of all available subslices per slice.
+			 */
+			ctx_sseu.subslice_mask =
+				~(~0 << (hweight8(ctx_sseu.subslice_mask) / 2));
+			ctx_sseu.slice_mask = 0x1;
+		}
+	}
+
+	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
@@ -2518,13 +2542,13 @@ make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu)
 	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;
 

drivers/gpu/drm/i915/intel_lrc.h

@@ -112,4 +112,6 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 							const char *prefix),
 				   unsigned int max);
 
+u32 gen8_make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu);
+
 #endif /* _INTEL_LRC_H_ */