Per context dynamic (sub)slice power-gating

index 1c9748f391fe..75d90918cac4 100644
@@ -1170,6 +1170,24 @@ 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);
+
+static void
+__execlists_update_reg_state(struct intel_engine_cs *engine,
+			     struct intel_context *ce)
+{
+	u32 *regs = ce->lrc_reg_state;
+	struct intel_ring *ring = ce->ring;
+
+	regs[CTX_RING_BUFFER_START + 1] = i915_ggtt_offset(ring->vma);
+	regs[CTX_RING_HEAD + 1] = ring->head;
+	regs[CTX_RING_TAIL + 1] = ring->tail;
+
+	/* RPCS */
+	if (engine->class == RENDER_CLASS)
+		regs[CTX_R_PWR_CLK_STATE + 1] = make_rpcs(engine->i915);
+}
+
 static struct intel_context *
 __execlists_context_pin(struct intel_engine_cs *engine,
 			struct i915_gem_context *ctx,

@@ -1208,10 +1226,8 @@ __execlists_context_pin(struct intel_engine_cs *engine,
 	GEM_BUG_ON(!intel_ring_offset_valid(ce->ring, ce->ring->head));
 
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
-	ce->lrc_reg_state[CTX_RING_BUFFER_START+1] =
-		i915_ggtt_offset(ce->ring->vma);
-	ce->lrc_reg_state[CTX_RING_HEAD + 1] = ce->ring->head;
-	ce->lrc_reg_state[CTX_RING_TAIL + 1] = ce->ring->tail;
+
+	__execlists_update_reg_state(engine, ce);
 
 	ce->state->obj->pin_global++;
 	i915_gem_context_get(ctx);

@@ -1835,14 +1851,14 @@ static void execlists_reset(struct intel_engine_cs *engine,
 		       engine->pinned_default_state + LRC_STATE_PN * PAGE_SIZE,
 		       engine->context_size - PAGE_SIZE);
 	}
-	execlists_init_reg_state(regs,
-				 request->gem_context, engine, request->ring);
 
 	/* Move the RING_HEAD onto the breadcrumb, past the hanging batch */
-	regs[CTX_RING_BUFFER_START + 1] = i915_ggtt_offset(request->ring->vma);
-
 	request->ring->head = intel_ring_wrap(request->ring, request->postfix);
-	regs[CTX_RING_HEAD + 1] = request->ring->head;
+
+	execlists_init_reg_state(regs, request->gem_context, engine,
+				 request->ring);
+
+	__execlists_update_reg_state(engine, request->hw_context);
 
 	intel_ring_update_space(request->ring);
 

@@ -2526,8 +2542,7 @@ static void execlists_init_reg_state(u32 *regs,
 
 	if (rcs) {
 		regs[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
-		CTX_REG(regs, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE,
-			make_rpcs(dev_priv));
+		CTX_REG(regs, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE, 0);
 
 		i915_oa_init_reg_state(engine, ctx, regs);
 	}

@@ -2688,12 +2703,8 @@ void intel_lr_context_resume(struct drm_i915_private *i915)
 
 			intel_ring_reset(ce->ring, 0);
 
-			if (ce->pin_count) { /* otherwise done in context_pin */
-				u32 *regs = ce->lrc_reg_state;
-
-				regs[CTX_RING_HEAD + 1] = ce->ring->head;
-				regs[CTX_RING_TAIL + 1] = ce->ring->tail;
-			}
+			if (ce->pin_count) /* otherwise done in context_pin */
+				__execlists_update_reg_state(engine, ce);
 		}
 	}
 }

index c34198f51b13..f834602ed157 100644
@@ -3302,6 +3302,20 @@ mkwrite_device_info(struct drm_i915_private *dev_priv)
 	return (struct intel_device_info *)&dev_priv->info;
 }
 
+static inline struct intel_sseu
+intel_device_default_sseu(struct drm_i915_private *i915)
+{
+	const struct sseu_dev_info *sseu = &INTEL_INFO(i915)->sseu;
+	struct intel_sseu value = {
+		.slice_mask = sseu->slice_mask,
+		.subslice_mask = sseu->subslice_mask[0],
+		.min_eus_per_subslice = sseu->max_eus_per_subslice,
+		.max_eus_per_subslice = sseu->max_eus_per_subslice,
+	};
+
+	return value;
+}
+
 /* modesetting */
 extern void intel_modeset_init_hw(struct drm_device *dev);
 extern int intel_modeset_init(struct drm_device *dev);

index 5905b6d8f291..a565643e9a26 100644
@@ -343,6 +343,8 @@ __create_hw_context(struct drm_i915_private *dev_priv,
 		struct intel_context *ce = &ctx->__engine[n];
 
 		ce->gem_context = ctx;
+		/* Use the whole device by default */
+		ce->sseu = intel_device_default_sseu(dev_priv);
 	}
 
 	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);

index f6d870b1f73e..ef04e422cf9a 100644
@@ -31,6 +31,7 @@
 
 #include "i915_gem.h"
 #include "i915_scheduler.h"
+#include "intel_device_info.h"
 
 struct pid;
 

@@ -171,6 +172,9 @@ struct i915_gem_context {
 		int pin_count;
 
 		const struct intel_context_ops *ops;
+
+		/** sseu: Control eu/slice partitioning */
+		struct intel_sseu sseu;
 	} __engine[I915_NUM_ENGINES];
 
 	/** ring_size: size for allocating the per-engine ring buffer */

index 90e9d170a0cd..07aaf9b43716 100644
@@ -39,6 +39,16 @@ struct drm_i915_gem_object;
 struct i915_request;
 struct i915_timeline;
 
+/*
+ * Powergating configuration for a particular (context,engine).
+ */
+struct intel_sseu {
+	u8 slice_mask;
+	u8 subslice_mask;
+	u8 min_eus_per_subslice;
+	u8 max_eus_per_subslice;
+};
+
 struct intel_wait {
 	struct rb_node node;
 	struct task_struct *tsk;

index 75d90918cac4..bfc31ccf5382 100644
@@ -1170,7 +1170,8 @@ 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);
+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,

@@ -1185,7 +1186,8 @@ __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);
+		regs[CTX_R_PWR_CLK_STATE + 1] = make_rpcs(engine->i915,
+							  &ce->sseu);
 }
 
 static struct intel_context *

@@ -2318,18 +2320,19 @@ int logical_xcs_ring_init(struct intel_engine_cs *engine)
 }
 
 static u32
-make_rpcs(struct drm_i915_private *dev_priv)
+make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu)
 {
-	bool subslice_pg = INTEL_INFO(dev_priv)->sseu.has_subslice_pg;
-	u8 slices = hweight8(INTEL_INFO(dev_priv)->sseu.slice_mask);
-	u8 subslices = hweight8(INTEL_INFO(dev_priv)->sseu.subslice_mask[0]);
+	const struct sseu_dev_info *sseu = &INTEL_INFO(i915)->sseu;
+	bool subslice_pg = sseu->has_subslice_pg;
+	u8 slices = hweight8(ctx_sseu->slice_mask);
+	u8 subslices = hweight8(ctx_sseu->subslice_mask);
 	u32 rpcs = 0;
 
 	/*
 	 * No explicit RPCS request is needed to ensure full
 	 * slice/subslice/EU enablement prior to Gen9.
 	*/
-	if (INTEL_GEN(dev_priv) < 9)
+	if (INTEL_GEN(i915) < 9)
 		return 0;
 
 	/*

@@ -2357,7 +2360,7 @@ make_rpcs(struct drm_i915_private *dev_priv)
 	 * subslices are enabled, or a count between one and four on the first
 	 * slice.
 	 */
-	if (IS_GEN(dev_priv, 11) && slices == 1 && subslices >= 4) {
+	if (IS_GEN(i915, 11) && slices == 1 && subslices >= 4) {
 		GEM_BUG_ON(subslices & 1);
 
 		subslice_pg = false;

@@ -2370,10 +2373,10 @@ make_rpcs(struct drm_i915_private *dev_priv)
 	 * must make an explicit request through RPCS for full
 	 * enablement.
 	*/
-	if (INTEL_INFO(dev_priv)->sseu.has_slice_pg) {
+	if (sseu->has_slice_pg) {
 		u32 mask, val = slices;
 
-		if (INTEL_GEN(dev_priv) >= 11) {
+		if (INTEL_GEN(i915) >= 11) {
 			mask = GEN11_RPCS_S_CNT_MASK;
 			val <<= GEN11_RPCS_S_CNT_SHIFT;
 		} else {

@@ -2398,18 +2401,16 @@ make_rpcs(struct drm_i915_private *dev_priv)
 		rpcs |= GEN8_RPCS_ENABLE | GEN8_RPCS_SS_CNT_ENABLE | val;
 	}
 
-	if (INTEL_INFO(dev_priv)->sseu.has_eu_pg) {
+	if (sseu->has_eu_pg) {
 		u32 val;
 
-		val = INTEL_INFO(dev_priv)->sseu.eu_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 = INTEL_INFO(dev_priv)->sseu.eu_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;
 

index 4288c0e02f0c..7ac76c7aa4bf 100644
@@ -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);
 

index bfc31ccf5382..59e90d3e76f6 100644
@@ -1170,9 +1170,6 @@ 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)

@@ -1186,8 +1183,8 @@ __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 *

@@ -2319,13 +2316,12 @@ 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 = &INTEL_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;
 
 	/*

@@ -2335,6 +2331,19 @@ 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. The most natural configuration to take in that case
+	 * is the default (i.e maximum the hardware can do).
+	 */
+	if (unlikely(i915->perf.oa.exclusive_stream))
+		ctx_sseu = intel_device_default_sseu(i915);
+	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

@@ -2404,13 +2413,13 @@ 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;
 

index f5a5502ecf70..a4e28cc55fda 100644
@@ -104,4 +104,6 @@ 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 *i915, struct intel_sseu *ctx_sseu);
+
 #endif /* _INTEL_LRC_H_ */

index 637909c59f1f..48c615db1810 100644
@@ -566,6 +566,15 @@ submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 	return NOTIFY_DONE;
 }
 
+static int add_timeline_barrier(struct i915_request *rq)
+{
+	struct i915_request *barrier =
+		i915_gem_active_raw(&rq->timeline->barrier,
+				    &rq->i915->drm.struct_mutex);
+
+	return barrier ? i915_request_await_dma_fence(rq, &barrier->fence) : 0;
+}
+
 /**
  * i915_request_alloc - allocate a request structure
  *

@@ -719,6 +728,10 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	 */
 	rq->head = rq->ring->emit;
 
+	ret = add_timeline_barrier(rq);
+	if (ret)
+		goto err_unwind;
+
 	ret = engine->request_alloc(rq);
 	if (ret)
 		goto err_unwind;

index 4667cc08c416..5a87c5bd5154 100644
@@ -37,6 +37,8 @@ void i915_timeline_init(struct drm_i915_private *i915,
 	INIT_LIST_HEAD(&timeline->requests);
 
 	i915_syncmap_init(&timeline->sync);
+
+	init_request_active(&timeline->barrier, NULL);
 }
 
 /**

@@ -69,6 +71,7 @@ void i915_timelines_park(struct drm_i915_private *i915)
 void i915_timeline_fini(struct i915_timeline *timeline)
 {
 	GEM_BUG_ON(!list_empty(&timeline->requests));
+	GEM_BUG_ON(i915_gem_active_isset(&timeline->barrier));
 
 	i915_syncmap_free(&timeline->sync);
 

index ebd71b487220..6ee301f20bab 100644
@@ -72,6 +72,16 @@ struct i915_timeline {
 	 */
 	u32 global_sync[I915_NUM_ENGINES];
 
+	/**
+	 * Barrier provides the ability to serialize ordering between different
+	 * timelines.
+	 *
+	 * Users can call i915_timeline_set_barrier which will make all
+	 * subsequent submissions be executed only after this barrier has been
+	 * completed.
+	 */
+	struct i915_gem_active barrier;
+
 	struct list_head link;
 	const char *name;
 

@@ -144,4 +154,21 @@ static inline bool i915_timeline_sync_is_later(struct i915_timeline *tl,
 
 void i915_timelines_park(struct drm_i915_private *i915);
 
+/**
+ * i915_timeline_set_barrier - orders submission between different timelines
+ * @timeline: timeline to set the barrier on
+ * @rq: request after which new submissions can proceed
+ *
+ * Sets the passed in request as the serialization point for all subsequent
+ * submissions on @timeline. Subsequent requests will not be submitted to GPU
+ * until the barrier has been completed.
+ */
+static inline void
+i915_timeline_set_barrier(struct i915_timeline *timeline,
+			  struct i915_request *rq)
+{
+	GEM_BUG_ON(timeline->fence_context == rq->timeline->fence_context);
+	i915_gem_active_set(&timeline->barrier, rq);
+}
+
 #endif

index dcf3b16f5a07..a718b64c988e 100644
@@ -19,6 +19,8 @@ void mock_timeline_init(struct i915_timeline *timeline, u64 context)
 
 	i915_syncmap_init(&timeline->sync);
 
+	init_request_active(&timeline->barrier, NULL);
+
 	INIT_LIST_HEAD(&timeline->link);
 }
 

index a565643e9a26..78d449b6245e 100644
@@ -90,6 +90,7 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 #include "i915_trace.h"
+#include "intel_lrc_reg.h"
 #include "intel_workarounds.h"
 
 #define ALL_L3_SLICES(dev) (1 << NUM_L3_SLICES(dev)) - 1

@@ -322,6 +323,15 @@ static u32 default_desc_template(const struct drm_i915_private *i915,
 	return desc;
 }
 
+static void intel_context_retire(struct i915_gem_active *active,
+				 struct i915_request *rq)
+{
+	struct intel_context *ce =
+		container_of(active, typeof(*ce), active_tracker);
+
+	intel_context_unpin(ce);
+}
+
 static struct i915_gem_context *
 __create_hw_context(struct drm_i915_private *dev_priv,
 		    struct drm_i915_file_private *file_priv)

@@ -345,6 +355,8 @@ __create_hw_context(struct drm_i915_private *dev_priv,
 		ce->gem_context = ctx;
 		/* Use the whole device by default */
 		ce->sseu = intel_device_default_sseu(dev_priv);
+
+		init_request_active(&ce->active_tracker, intel_context_retire);
 	}
 
 	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);

@@ -842,6 +854,56 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }
 
+static int get_sseu(struct i915_gem_context *ctx,
+		    struct drm_i915_gem_context_param *args)
+{
+	struct drm_i915_gem_context_param_sseu user_sseu;
+	struct intel_engine_cs *engine;
+	struct intel_context *ce;
+	int ret;
+
+	if (args->size == 0)
+		goto out;
+	else if (args->size < sizeof(user_sseu))
+		return -EINVAL;
+
+	if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value),
+			   sizeof(user_sseu)))
+		return -EFAULT;
+
+	if (user_sseu.rsvd1 || user_sseu.rsvd2)
+		return -EINVAL;
+
+	engine = intel_engine_lookup_user(ctx->i915,
+					  user_sseu.class,
+					  user_sseu.instance);
+	if (!engine)
+		return -EINVAL;
+
+	/* Only use for mutex here is to serialize get_param and set_param. */
+	ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
+	if (ret)
+		return ret;
+
+	ce = to_intel_context(ctx, engine);
+
+	user_sseu.slice_mask = ce->sseu.slice_mask;
+	user_sseu.subslice_mask = ce->sseu.subslice_mask;
+	user_sseu.min_eus_per_subslice = ce->sseu.min_eus_per_subslice;
+	user_sseu.max_eus_per_subslice = ce->sseu.max_eus_per_subslice;
+
+	mutex_unlock(&ctx->i915->drm.struct_mutex);
+
+	if (copy_to_user(u64_to_user_ptr(args->value), &user_sseu,
+			 sizeof(user_sseu)))
+		return -EFAULT;
+
+out:
+	args->size = sizeof(user_sseu);
+
+	return 0;
+}
+
 int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 				    struct drm_file *file)
 {

@@ -854,15 +916,17 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 	if (!ctx)
 		return -ENOENT;
 
-	args->size = 0;
 	switch (args->param) {
 	case I915_CONTEXT_PARAM_BAN_PERIOD:
 		ret = -EINVAL;
 		break;
 	case I915_CONTEXT_PARAM_NO_ZEROMAP:
+		args->size = 0;
 		args->value = test_bit(UCONTEXT_NO_ZEROMAP, &ctx->user_flags);
 		break;
 	case I915_CONTEXT_PARAM_GTT_SIZE:
+		args->size = 0;
+
 		if (ctx->ppgtt)
 			args->value = ctx->ppgtt->vm.total;
 		else if (to_i915(dev)->mm.aliasing_ppgtt)

@@ -871,14 +935,20 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 			args->value = to_i915(dev)->ggtt.vm.total;
 		break;
 	case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
+		args->size = 0;
 		args->value = i915_gem_context_no_error_capture(ctx);
 		break;
 	case I915_CONTEXT_PARAM_BANNABLE:
+		args->size = 0;
 		args->value = i915_gem_context_is_bannable(ctx);
 		break;
 	case I915_CONTEXT_PARAM_PRIORITY:
+		args->size = 0;
 		args->value = ctx->sched.priority >> I915_USER_PRIORITY_SHIFT;
 		break;
+	case I915_CONTEXT_PARAM_SSEU:
+		ret = get_sseu(ctx, args);
+		break;
 	default:
 		ret = -EINVAL;
 		break;

@@ -888,6 +958,271 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 	return ret;
 }
 
+static int gen8_emit_rpcs_config(struct i915_request *rq,
+				 struct intel_context *ce,
+				 struct intel_sseu sseu)
+{
+	u64 offset;
+	u32 *cs;
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	offset = ce->state->node.start +
+		LRC_STATE_PN * PAGE_SIZE +
+		(CTX_R_PWR_CLK_STATE + 1) * 4;
+
+	*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
+	*cs++ = lower_32_bits(offset);
+	*cs++ = upper_32_bits(offset);
+	*cs++ = gen8_make_rpcs(rq->i915, &sseu);
+
+	intel_ring_advance(rq, cs);
+
+	return 0;
+}
+
+static int
+gen8_modify_rpcs_gpu(struct intel_context *ce,
+		     struct intel_engine_cs *engine,
+		     struct intel_sseu sseu)
+{
+	struct drm_i915_private *i915 = engine->i915;
+	struct i915_request *rq, *prev;
+	int ret;
+
+	GEM_BUG_ON(!ce->pin_count);
+
+	lockdep_assert_held(&i915->drm.struct_mutex);
+
+	/* Submitting requests etc needs the hw awake. */
+	intel_runtime_pm_get(i915);
+
+	rq = i915_request_alloc(engine, i915->kernel_context);
+	if (IS_ERR(rq)) {
+		ret = PTR_ERR(rq);
+		goto out_put;
+	}
+
+	/* Queue this switch after all other activity by this context. */
+	prev = i915_gem_active_raw(&ce->ring->timeline->last_request,
+				   &i915->drm.struct_mutex);
+	if (prev && !i915_request_completed(prev)) {
+		ret = i915_sw_fence_await_sw_fence_gfp(&rq->submit,
+						       &prev->submit,
+						       I915_FENCE_GFP);
+		if (ret < 0)
+			goto out_add;
+	}
+
+	ret = gen8_emit_rpcs_config(rq, ce, sseu);
+	if (ret)
+		goto out_add;
+
+	/* Order all following requests to be after. */
+	i915_timeline_set_barrier(ce->ring->timeline, rq);
+
+	/*
+	 * Guarantee context image and the timeline remains pinned until the
+	 * modifying request is retired by setting the ce activity tracker.
+	 *
+	 * But we only need to take one pin on the account of it. Or in other
+	 * words transfer the pinned ce object to tracked active request.
+	 */
+	if (!i915_gem_active_isset(&ce->active_tracker))
+		__intel_context_pin(ce);
+	i915_gem_active_set(&ce->active_tracker, rq);
+
+out_add:
+	i915_request_add(rq);
+out_put:
+	intel_runtime_pm_put(i915);
+
+	return ret;
+}
+
+static int
+i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
+				  struct intel_engine_cs *engine,
+				  struct intel_sseu sseu)
+{
+	struct intel_context *ce = to_intel_context(ctx, engine);
+	int ret;
+
+	GEM_BUG_ON(INTEL_GEN(ctx->i915) < 8);
+	GEM_BUG_ON(engine->id != RCS);
+
+	ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
+	if (ret)
+		return ret;
+
+	/* Nothing to do if unmodified. */
+	if (!memcmp(&ce->sseu, &sseu, sizeof(sseu)))
+		goto out;
+
+	/*
+	 * If context is not idle we have to submit an ordered request to modify
+	 * its context image via the kernel context. Pristine and idle contexts
+	 * will be configured on pinning.
+	 */
+	if (ce->pin_count)
+		ret = gen8_modify_rpcs_gpu(ce, engine, sseu);
+
+	if (!ret)
+		ce->sseu = sseu;
+
+out:
+	mutex_unlock(&ctx->i915->drm.struct_mutex);
+
+	return ret;
+}
+
+static int
+user_to_context_sseu(struct drm_i915_private *i915,
+		     const struct drm_i915_gem_context_param_sseu *user,
+		     struct intel_sseu *context)
+{
+	const struct sseu_dev_info *device = &INTEL_INFO(i915)->sseu;
+
+	/* No zeros in any field. */
+	if (!user->slice_mask || !user->subslice_mask ||
+	    !user->min_eus_per_subslice || !user->max_eus_per_subslice)
+		return -EINVAL;
+
+	/* Max > min. */
+	if (user->max_eus_per_subslice < user->min_eus_per_subslice)
+		return -EINVAL;
+
+	/* Check validity against hardware. */
+	if (user->slice_mask & ~device->slice_mask)
+		return -EINVAL;
+
+	if (user->subslice_mask & ~device->subslice_mask[0])
+		return -EINVAL;
+
+	if (user->max_eus_per_subslice > device->max_eus_per_subslice)
+		return -EINVAL;
+
+	/*
+	 * Some future proofing on the types since the uAPI is wider than the
+	 * current internal implementation.
+	 */
+	if (WARN_ON((fls(user->slice_mask) >
+		     sizeof(context->slice_mask) * BITS_PER_BYTE) ||
+		    (fls(user->subslice_mask) >
+		     sizeof(context->subslice_mask) * BITS_PER_BYTE) ||
+		    overflows_type(user->min_eus_per_subslice,
+				   context->min_eus_per_subslice) ||
+		    overflows_type(user->max_eus_per_subslice,
+				   context->max_eus_per_subslice)))
+		return -EINVAL;
+
+	context->slice_mask = user->slice_mask;
+	context->subslice_mask = user->subslice_mask;
+	context->min_eus_per_subslice = user->min_eus_per_subslice;
+	context->max_eus_per_subslice = user->max_eus_per_subslice;
+
+	/* Part specific restrictions. */
+	if (IS_GEN(i915, 11)) {
+		unsigned int hw_s = hweight8(device->slice_mask);
+		unsigned int hw_ss_per_s = hweight8(device->subslice_mask[0]);
+		unsigned int req_s = hweight8(context->slice_mask);
+		unsigned int req_ss = hweight8(context->subslice_mask);
+
+		/*
+		 * Only full subslice enablement is possible if more than one
+		 * slice is turned on.
+		 */
+		if (req_s > 1 && req_ss != hw_ss_per_s)
+			return -EINVAL;
+
+		/*
+		 * If more than four (SScount bitfield limit) subslices are
+		 * requested then the number has to be even.
+		 */
+		if (req_ss > 4 && (req_ss & 1))
+			return -EINVAL;
+
+		/*
+		 * If only one slice is enabled and subslice count is below the
+		 * device full enablement, it must be at most half of the all
+		 * available subslices.
+		 */
+		if (req_s == 1 && req_ss < hw_ss_per_s &&
+		    req_ss > (hw_ss_per_s / 2))
+			return -EINVAL;
+
+		/* ABI restriction - VME use case only. */
+
+		/* All slices or one slice only. */
+		if (req_s != 1 && req_s != hw_s)
+			return -EINVAL;
+
+		/*
+		 * Half subslices or full enablement only when one slice is
+		 * enabled.
+		 */
+		if (req_s == 1 &&
+		    (req_ss != hw_ss_per_s && req_ss != (hw_ss_per_s / 2)))
+			return -EINVAL;
+
+		/* No EU configuration changes. */
+		if ((user->min_eus_per_subslice !=
+		     device->max_eus_per_subslice) ||
+		    (user->max_eus_per_subslice !=
+		     device->max_eus_per_subslice))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int set_sseu(struct i915_gem_context *ctx,
+		    struct drm_i915_gem_context_param *args)
+{
+	struct drm_i915_private *i915 = ctx->i915;
+	struct drm_i915_gem_context_param_sseu user_sseu;
+	struct intel_engine_cs *engine;
+	struct intel_sseu sseu;
+	int ret;
+
+	if (args->size < sizeof(user_sseu))
+		return -EINVAL;
+
+	if (!IS_GEN(i915, 11))
+		return -ENODEV;
+
+	if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value),
+			   sizeof(user_sseu)))
+		return -EFAULT;
+
+	if (user_sseu.rsvd1 || user_sseu.rsvd2)
+		return -EINVAL;
+
+	engine = intel_engine_lookup_user(i915,
+					  user_sseu.class,
+					  user_sseu.instance);
+	if (!engine)
+		return -EINVAL;
+
+	/* Only render engine supports RPCS configuration. */
+	if (engine->class != RENDER_CLASS)
+		return -ENODEV;
+
+	ret = user_to_context_sseu(i915, &user_sseu, &sseu);
+	if (ret)
+		return ret;
+
+	ret = i915_gem_context_reconfigure_sseu(ctx, engine, sseu);
+	if (ret)
+		return ret;
+
+	args->size = sizeof(user_sseu);
+
+	return 0;
+}
+
 int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 				    struct drm_file *file)
 {

@@ -950,7 +1285,9 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 					I915_USER_PRIORITY(priority);
 		}
 		break;
-
+	case I915_CONTEXT_PARAM_SSEU:
+		ret = set_sseu(ctx, args);
+		break;
 	default:
 		ret = -EINVAL;
 		break;

index ef04e422cf9a..2ded4b8c9b9f 100644
@@ -171,6 +171,12 @@ struct i915_gem_context {
 		u64 lrc_desc;
 		int pin_count;
 
+		/**
+		 * active_tracker: Active tracker for the external rq activity
+		 * on this intel_context object.
+		 */
+		struct i915_gem_active active_tracker;
+
 		const struct intel_context_ops *ops;
 
 		/** sseu: Control eu/slice partitioning */

index 59e90d3e76f6..d392c2cef1d7 100644
@@ -2369,7 +2369,9 @@ u32 gen8_make_rpcs(struct drm_i915_private *i915, struct intel_sseu *req_sseu)
 	 * subslices are enabled, or a count between one and four on the first
 	 * slice.
 	 */
-	if (IS_GEN(i915, 11) && slices == 1 && subslices >= 4) {
+	if (IS_GEN(i915, 11) &&
+	    slices == 1 &&
+	    subslices > min_t(u8, 4, hweight8(sseu->subslice_mask[0]) / 2)) {
 		GEM_BUG_ON(subslices & 1);
 
 		subslice_pg = false;

52 lines not on this page · raw message

index d392c2cef1d7..57a43d3d07f1 100644
@@ -2333,13 +2333,28 @@ u32 gen8_make_rpcs(struct drm_i915_private *i915, struct intel_sseu *req_sseu)
 
 	/*
 	 * 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).
+	 * 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 (unlikely(i915->perf.oa.exclusive_stream))
-		ctx_sseu = intel_device_default_sseu(i915);
-	else
+	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);

index 78d449b6245e..fcb19b6f635e 100644
@@ -1042,24 +1042,23 @@ gen8_modify_rpcs_gpu(struct intel_context *ce,
 	return ret;
 }
 
-static int
-i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
-				  struct intel_engine_cs *engine,
-				  struct intel_sseu sseu)
+#if !IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+static
+#endif
+int
+__i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
+				    struct intel_engine_cs *engine,
+				    struct intel_sseu sseu)
 {
 	struct intel_context *ce = to_intel_context(ctx, engine);
-	int ret;
+	int ret = 0;
 
 	GEM_BUG_ON(INTEL_GEN(ctx->i915) < 8);
 	GEM_BUG_ON(engine->id != RCS);
 
-	ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
-	if (ret)
-		return ret;
-
 	/* Nothing to do if unmodified. */
 	if (!memcmp(&ce->sseu, &sseu, sizeof(sseu)))
-		goto out;
+		return 0;
 
 	/*
 	 * If context is not idle we have to submit an ordered request to modify

@@ -1072,7 +1071,22 @@ i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
 	if (!ret)
 		ce->sseu = sseu;
 
-out:
+	return ret;
+}
+
+static int
+i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
+				  struct intel_engine_cs *engine,
+				  struct intel_sseu sseu)
+{
+	int ret;
+
+	ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
+	if (ret)
+		return ret;
+
+	ret = __i915_gem_context_reconfigure_sseu(ctx, engine, sseu);
+
 	mutex_unlock(&ctx->i915->drm.struct_mutex);
 
 	return ret;

507 lines not on this page · raw message