Skip to contentSkip to conversation

Per context dynamic (sub)slice power-gating

PATCH In review Tvrtko Ursulin 4 participants 14 messages Sep 14, 2018 – Sep 17, 2018

Subsystems (3)
lore
Share & tools
lore

Tvrtko Ursulin

author maintainer
#0 lore raw

cover Per context dynamic (sub)slice power-gating

From: Tvrtko Ursulin <[email protected]>

More review feedback, some fixes and some refactoring due drm-tip changes.

Lionel Landwerlin (2):
drm/i915: Record the sseu configuration per-context & engine drm/i915/perf: lock powergating configuration to default when active

Tvrtko Ursulin (4):
drm/i915/execlists: Move RPCS setup to context pin drm/i915: Add timeline barrier support
drm/i915: Expose RPCS (SSEU) configuration to userspace drm/i915/icl: Support co-existance between per-context SSEU and OA

 drivers/gpu/drm/i915/i915_drv.h               |  14 +
 drivers/gpu/drm/i915/i915_gem_context.c       | 315 +++++++++++++++++-
 drivers/gpu/drm/i915/i915_gem_context.h       |  10 +
 drivers/gpu/drm/i915/i915_perf.c              |  13 +-
 drivers/gpu/drm/i915/i915_request.c           |  13 +
 drivers/gpu/drm/i915/i915_request.h           |  10 +
 drivers/gpu/drm/i915/i915_timeline.c          |   3 +
 drivers/gpu/drm/i915/i915_timeline.h          |  27 ++
 drivers/gpu/drm/i915/intel_lrc.c              | 101 ++++--
 drivers/gpu/drm/i915/intel_lrc.h              |   2 +
 .../gpu/drm/i915/selftests/mock_timeline.c    |   2 +
 include/uapi/drm/i915_drm.h                   |  43 +++
 12 files changed, 516 insertions(+), 37 deletions(-)
Signature · 6 lines
2.17.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
author maintainer
#1 lore raw

PATCH 1/6 drm/i915/execlists: Move RPCS setup to context pin

From: Tvrtko Ursulin <[email protected]>

Configuring RPCS in context image just before pin is sufficient and will come extra handy in one of the following patches.

v2:
* Split image setup a bit differently. (Chris Wilson)

v3:
* Update context image after reset as well - otherwise the application of pinned default state clears the RPCS.

---
 drivers/gpu/drm/i915/intel_lrc.c | 47 ++++++++++++++++++++------------
 1 file changed, 30 insertions(+), 17 deletions(-)
drivers/gpu/drm/i915/intel_lrc.c +30 -17
index a51be16ddaac..4fcff1be91c9 100644
@@ -1305,6 +1305,26 @@ 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) {
+		ce->lrc_reg_state[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,
@@ -1343,10 +1363,8 @@ __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);
@@ -1955,14 +1973,14 @@ 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);
 
@@ -2710,8 +2728,7 @@ 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);
 	}
@@ -2872,12 +2889,8 @@ 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);
 		}
 	}
 }
Signature · 6 lines
2.17.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#2 lore raw

Re: [PATCH 1/6] drm/i915/execlists: Move RPCS setup to context pin

Quoting Tvrtko Ursulin (2018-09-14 17:09:27)

Quoted 35 lines

From: Tvrtko Ursulin <[email protected]>

Configuring RPCS in context image just before pin is sufficient and will come extra handy in one of the following patches.

v2:
* Split image setup a bit differently. (Chris Wilson)

v3:
* Update context image after reset as well - otherwise the application of pinned default state clears the RPCS.

---
 drivers/gpu/drm/i915/intel_lrc.c | 47 ++++++++++++++++++++------------
 1 file changed, 30 insertions(+), 17 deletions(-)
drivers/gpu/drm/i915/intel_lrc.c +7 -0
index a51be16ddaac..4fcff1be91c9 100644
@@ -1305,6 +1305,26 @@ 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;

drivers/gpu/drm/i915/intel_lrc.c static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma) · line 1324

Quoted 10 lines
drivers/gpu/drm/i915/intel_lrc.c +10 -0
+       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) {
+               ce->lrc_reg_state[CTX_R_PWR_CLK_STATE + 1] =
+                       make_rpcs(engine->i915);

regs[CTX_R_PWR_CLK_STATE + 1] = make_rpcs(engine->i915);

Looks like the plan is coming together.
-Chris
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

author maintainer
#3 lore raw

PATCH 2/6 drm/i915: Record the sseu configuration per-context & engine

In reply to Tvrtko Ursulin

From: Lionel Landwerlin <[email protected]>

We want to expose the ability to reconfigure the slices, subslice and eu per context and per engine. To facilitate that, store the current configuration on the context for each engine, which is initially set to the device default upon creation.

v2: record sseu configuration per context & engine (Chris)

v3: introduce the i915_gem_context_sseu to store powergating
programming, sseu_dev_info has grown quite a bit (Lionel)

v4: rename i915_gem_sseu into intel_sseu (Chris)
use to_intel_context() (Chris)

v5: More to_intel_context() (Tvrtko)
Switch intel_sseu from union to struct (Tvrtko) Move context default sseu in existing loop (Chris)

v6: s/intel_sseu_from_device_sseu/intel_device_default_sseu/ (Tvrtko)

Tvrtko Ursulin:

v7:
* Pass intel_sseu by pointer instead of value to make_rpcs.
* Rebase for make_rpcs changes.

v8:
* Rebase for RPCS edit on pin.

v9:
* Rebase for context image setup changes.

v10:
* Rename dev_priv to i915. (Chris Wilson)

---
 drivers/gpu/drm/i915/i915_drv.h         | 14 ++++++++++++
 drivers/gpu/drm/i915/i915_gem_context.c |  2 ++
 drivers/gpu/drm/i915/i915_gem_context.h |  4 ++++
 drivers/gpu/drm/i915/i915_request.h     | 10 +++++++++
 drivers/gpu/drm/i915/intel_lrc.c        | 30 ++++++++++++-------------
 5 files changed, 45 insertions(+), 15 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +14 -0
index 7d4daa7412f1..6b7ae63e47c3 100644
@@ -3479,6 +3479,20 @@ 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);
drivers/gpu/drm/i915/i915_gem_context.c +2 -0
index f772593b99ab..0b8cc748648b 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);
drivers/gpu/drm/i915/i915_gem_context.h +4 -0
index 08165f6a0a84..7510de738b35 100644
@@ -31,6 +31,7 @@
 
 #include "i915_gem.h"
 #include "i915_scheduler.h"
+#include "intel_device_info.h"
 
 struct pid;
 
@@ -170,6 +171,9 @@ 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 */
drivers/gpu/drm/i915/i915_request.h +10 -0
index 7fa94b024968..3a4be20ea74a 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;
drivers/gpu/drm/i915/intel_lrc.c +15 -15
index 4fcff1be91c9..1c9cf41dab3f 100644
@@ -1305,7 +1305,8 @@ 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,
@@ -1321,7 +1322,7 @@ __execlists_update_reg_state(struct intel_engine_cs *engine,
 	/* RPCS */
 	if (engine->class == RENDER_CLASS) {
 		ce->lrc_reg_state[CTX_R_PWR_CLK_STATE + 1] =
-			make_rpcs(engine->i915);
+			make_rpcs(engine->i915, &ce->sseu);
 	}
 }
 
@@ -2508,18 +2509,19 @@ 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;
 
 	/*
@@ -2547,7 +2549,7 @@ make_rpcs(struct drm_i915_private *dev_priv)
 	 * subslices are enabled, or a count between one and four on the first
 	 * slice.
 	 */
-	if (IS_GEN11(dev_priv) && slices == 1 && subslices >= 4) {
+	if (IS_GEN11(i915) && slices == 1 && subslices >= 4) {
 		GEM_BUG_ON(subslices & 1);
 
 		subslice_pg = false;
@@ -2560,10 +2562,10 @@ 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 {
@@ -2588,18 +2590,16 @@ 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;
 
Signature · 6 lines
2.17.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
author maintainer
#4 lore raw

PATCH 3/6 drm/i915/perf: lock powergating configuration to default when active

In reply to Tvrtko Ursulin

From: Lionel Landwerlin <[email protected]>

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.

v6:
* Rebase for context image setup changes.

v7:
* Move stream assignment before metric enable.

---
 drivers/gpu/drm/i915/i915_perf.c | 13 +++++++++----
 drivers/gpu/drm/i915/intel_lrc.c | 29 +++++++++++++++++++----------
 drivers/gpu/drm/i915/intel_lrc.h |  2 ++
 3 files changed, 30 insertions(+), 14 deletions(-)
drivers/gpu/drm/i915/i915_perf.c +9 -4
index 664b96bb65a3..46ddd1913fee 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));
 }
 
 /*
@@ -2092,6 +2097,9 @@ 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(dev_priv,
 						      stream->oa_config);
 	if (ret) {
@@ -2099,15 +2107,12 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		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 +19 -10
index 1c9cf41dab3f..3b379c7295a3 100644
@@ -1305,9 +1305,6 @@ 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)
@@ -1322,7 +1319,7 @@ __execlists_update_reg_state(struct intel_engine_cs *engine,
 	/* RPCS */
 	if (engine->class == RENDER_CLASS) {
 		ce->lrc_reg_state[CTX_R_PWR_CLK_STATE + 1] =
-			make_rpcs(engine->i915, &ce->sseu);
+			gen8_make_rpcs(engine->i915, &ce->sseu);
 	}
 }
 
@@ -2508,13 +2505,12 @@ 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;
 
 	/*
@@ -2524,6 +2520,19 @@ 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
@@ -2593,13 +2602,13 @@ 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 +2 -0
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_ */
Signature · 6 lines
2.17.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
author maintainer
#5 lore raw

PATCH 4/6 drm/i915: Add timeline barrier support

In reply to Tvrtko Ursulin

From: Tvrtko Ursulin <[email protected]>

Timeline barrier allows serialization between different timelines.

After calling i915_timeline_set_barrier with a request, all following submissions on this timeline will be set up as depending on this request, or barrier. Once the barrier has been completed it automatically gets cleared and things continue as normal.

This facility will be used by the upcoming context SSEU code.

v2:
* Assert barrier has been retired on timeline_fini. (Chris Wilson)
* Fix mock_timeline.

---
 drivers/gpu/drm/i915/i915_request.c           | 13 +++++++++
 drivers/gpu/drm/i915/i915_timeline.c          |  3 +++
 drivers/gpu/drm/i915/i915_timeline.h          | 27 +++++++++++++++++++
 .../gpu/drm/i915/selftests/mock_timeline.c    |  2 ++
 4 files changed, 45 insertions(+)
drivers/gpu/drm/i915/i915_request.c +13 -0
index a492385b2089..76fc80330c85 100644
@@ -644,6 +644,15 @@ 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
  *
@@ -808,6 +817,10 @@ 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;
+
 	/* Unconditionally invalidate GPU caches and TLBs. */
 	ret = engine->emit_flush(rq, EMIT_INVALIDATE);
 	if (ret)
drivers/gpu/drm/i915/i915_timeline.c +3 -0
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);
 
drivers/gpu/drm/i915/i915_timeline.h +27 -0
index a2c2c3ab5fb0..c8526ab44dbc 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;
 
@@ -125,4 +135,21 @@ 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
drivers/gpu/drm/i915/selftests/mock_timeline.c +2 -0
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);
 }
 
Signature · 6 lines
2.17.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
author maintainer
#6 lore raw

PATCH 5/6 drm/i915: Expose RPCS (SSEU) configuration to userspace

In reply to Tvrtko Ursulin

From: Tvrtko Ursulin <[email protected]>

We want to allow userspace to reconfigure the subslice configuration for its own use case. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use, the adjustment is for "free"; otherwise if the context is active we flush the context off the GPU (stalling all users) and forcing the GPU to save the context to memory where we can modify it and so ensure that the register is reloaded on next execution.

The overhead of managing additional EU subslices can be significant, especially in multi-context workloads. Non-GPGPU contexts should preferably disable the subslices it is not using, and others should fine-tune the number to match their workload.

We expose complete control over the RPCS register, allowing configuration of slice/subslice, via masks packed into a u64 for simplicity. For example,

	struct drm_i915_gem_context_param arg;
	struct drm_i915_gem_context_param_sseu sseu = { .class = 0,
	                                                .instance = 0, };

	memset(&arg, 0, sizeof(arg));
	arg.ctx_id = ctx;
	arg.param = I915_CONTEXT_PARAM_SSEU;
	arg.value = (uintptr_t) &sseu;
	if (drmIoctl(fd, DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM, &arg) == 0) {
		sseu.packed.subslice_mask = 0;

		drmIoctl(fd, DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM, &arg);
	}

could be used to disable all subslices where supported.

v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel)

v3: Add ability to program this per engine (Chris)

v4: Move most get_sseu() into i915_gem_context.c (Lionel)

v5: Validate sseu configuration against the device's capabilities (Lionel)

v6: Change context powergating settings through MI_SDM on kernel context (Chris)

v7: Synchronize the requests following a powergating setting change using a global
dependency (Chris)
Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko)

v8: s/union intel_sseu/struct intel_sseu/ (Lionel)
s/dev_priv/i915/ (Tvrtko)
Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel)
Don't return EPERM when dynamic sseu is disabled (Tvrtko)

v9: Import context image into kernel context's ppgtt only when
reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel)

Tvrtko Ursulin:

v10:
* Update for upstream changes.
* Request submit needs a RPM reference.
* Reject on !FULL_PPGTT for simplicity.
* Pull out get/set param to helpers for readability and less indent.
* Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON.
* No need to explicitly assign a NULL pointer to engine in legacy mode.
* No need to move gen8_make_rpcs up.
* Factored out global barrier as prep patch.
* Allow to only CAP_SYS_ADMIN if !Gen11.

v11:
* Remove engine vfunc in favour of local helper. (Chris Wilson)
* Stop retiring requests before updates since it is not needed (Chris Wilson)
* Implement direct CPU update path for idle contexts. (Chris Wilson)
* Left side dependency needs only be on the same context timeline. (Chris Wilson)
* It is sufficient to order the timeline. (Chris Wilson)
* Reject !RCS configuration attempts with -ENODEV for now.

v12:
* Rebase for make_rpcs.

v13:
* Centralize SSEU normalization to make_rpcs.
* Type width checking (uAPI <-> implementation).
* Gen11 restrictions uAPI checks.
* Gen11 subslice count differences handling.
Chris Wilson:
* args->size handling fixes.
* Update context image from GGTT.
* Postpone context image update to pinning.
* Use i915_gem_active_raw instead of last_request_on_engine.

v14:
* Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson)

v15:
* Fix context pin leak if no space in ring by simplifying the context pinning sequence.

v16:
* Rebase for context get/set param locking changes.
* Just -ENODEV on !Gen11. (Joonas)

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634
Issue: https://github.com/intel/media-driver/issues/267

---
 drivers/gpu/drm/i915/i915_gem_context.c | 313 +++++++++++++++++++++++-
 drivers/gpu/drm/i915/i915_gem_context.h |   6 +
 drivers/gpu/drm/i915/intel_lrc.c        |   4 +-
 include/uapi/drm/i915_drm.h             |  43 ++++
 4 files changed, 363 insertions(+), 3 deletions(-)
drivers/gpu/drm/i915/i915_gem_context.c +311 -2
index 0b8cc748648b..092c282a8ec2 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 +323,14 @@ 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);
+
+	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 +354,8 @@ __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, intel_context_retire);
 	}
 
 	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
@@ -846,6 +857,56 @@ 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)
 {
@@ -858,15 +919,17 @@ 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)
@@ -875,14 +938,20 @@ 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;
 		break;
+	case I915_CONTEXT_PARAM_SSEU:
+		ret = get_sseu(ctx, args);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -892,6 +961,244 @@ 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;
+	}
+
+	ret = gen8_emit_rpcs_config(rq, ce, sseu);
+	if (ret)
+		goto out_add;
+
+	/* 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))
+		i915_sw_fence_await_sw_fence_gfp(&rq->submit,
+						 &prev->submit,
+						 I915_FENCE_GFP);
+
+	/* 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))
+		__intel_context_pin(ce);
+	i915_gem_active_set(&ce->active, 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_GEN11(i915)) {
+		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 subslice count must be at most
+		 * half of the all available subslices.
+		 */
+		if (req_s == 1 && req_ss > (hw_ss_per_s / 2))
+			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_GEN11(i915))
+		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)
 {
@@ -953,7 +1260,9 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 				ctx->sched.priority = priority;
 		}
 		break;
-
+	case I915_CONTEXT_PARAM_SSEU:
+		ret = set_sseu(ctx, args);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
drivers/gpu/drm/i915/i915_gem_context.h +6 -0
index 7510de738b35..c4aebfe7d4d2 100644
@@ -170,6 +170,12 @@ struct i915_gem_context {
 		u64 lrc_desc;
 		int pin_count;
 
+		/**
+		 * active: Active tracker for the external rq activity on this
+		 * intel_context object.
+		 */
+		struct i915_gem_active active;
+
 		const struct intel_context_ops *ops;
 
 		/** sseu: Control eu/slice partitioning */
drivers/gpu/drm/i915/intel_lrc.c +3 -1
index 3b379c7295a3..0cfa99a13522 100644
@@ -2558,7 +2558,9 @@ 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_GEN11(i915) && slices == 1 && subslices >= 4) {
+	if (IS_GEN11(i915) &&
+	    slices == 1 &&
+	    subslices > min_t(u8, 4, hweight8(sseu->subslice_mask[0]) / 2)) {
 		GEM_BUG_ON(subslices & 1);
 
 		subslice_pg = false;
include/uapi/drm/i915_drm.h +43 -0

52 lines not on this page · raw message

Signature · 6 lines
2.17.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#7 lore raw

Re: [PATCH 5/6] drm/i915: Expose RPCS (SSEU) configuration to userspace

Quoting Tvrtko Ursulin (2018-09-14 17:09:31)

Quoted 23 lines
drivers/gpu/drm/i915/i915_gem_context.c +23 -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;
+       }
+
+       ret = gen8_emit_rpcs_config(rq, ce, sseu);

drivers/gpu/drm/i915/i915_gem_context.c int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, · line 1021

Quoted 10 lines
drivers/gpu/drm/i915/i915_gem_context.c +10 -0
+       if (ret)
+               goto out_add;
+
+       /* 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))
+               i915_sw_fence_await_sw_fence_gfp(&rq->submit,
+                                                &prev->submit,
+                                                I915_FENCE_GFP);

I guess we really should be respecting the potential error here. We should do the await before the emit, and out_add on err < 0.

Quoted 31 lines
drivers/gpu/drm/i915/i915_gem_context.c +31 -0
+
+       /* 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))
+               __intel_context_pin(ce);
+       i915_gem_active_set(&ce->active, 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;
+

drivers/gpu/drm/i915/i915_gem_context.c int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, · line 1062

Quoted 10 lines
drivers/gpu/drm/i915/i915_gem_context.c +10 -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;

/* If oa is active, it has already overridden the per-context setting */ if (oa->active)

	goto set;

drivers/gpu/drm/i915/i915_gem_context.c int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, · line 1072

Quoted 10 lines
drivers/gpu/drm/i915/i915_gem_context.c +10 -0
+
+       /*
+        * 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)

set:

drivers/gpu/drm/i915/i915_gem_context.c int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, · line 1078

Quoted 6 lines
drivers/gpu/drm/i915/i915_gem_context.c +6 -0
+               ce->sseu = sseu;
+
+out:
+       mutex_unlock(&ctx->i915->drm.struct_mutex);
+
+       return ret;

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#8 lore raw

Re: [PATCH 5/6] drm/i915: Expose RPCS (SSEU) configuration to userspace

Quoted 29 lines · Chris Wilson

Quoting Tvrtko Ursulin (2018-09-14 17:09:31)

Quoted 28 lines
drivers/gpu/drm/i915/i915_gem_context.c +28 -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;
+       }
+
+       ret = gen8_emit_rpcs_config(rq, ce, sseu);
+       if (ret)
+               goto out_add;
+
+       /* Queue this switch after all other activity by this context. */
+       prev = i915_gem_active_raw(&ce->ring->timeline->last_request,
Quoted 8 lines

drivers/gpu/drm/i915/i915_gem_context.c int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, · line 1021

Quoted 5 lines
drivers/gpu/drm/i915/i915_gem_context.c +5 -0
+                                  &i915->drm.struct_mutex);
+       if (prev && !i915_request_completed(prev))
+               i915_sw_fence_await_sw_fence_gfp(&rq->submit,
+                                                &prev->submit,
+                                                I915_FENCE_GFP);

I guess we really should be respecting the potential error here. We should do the await before the emit, and out_add on err < 0.

Yep, completely missed it can return error even though GFP_KERNEL should have been a clue enough.

Quoted 44 lines
Quoted 31 lines
drivers/gpu/drm/i915/i915_gem_context.c +31 -0
+
+       /* 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))
+               __intel_context_pin(ce);
+       i915_gem_active_set(&ce->active, 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;
+

drivers/gpu/drm/i915/i915_gem_context.c int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, · line 1062

Quoted 10 lines
drivers/gpu/drm/i915/i915_gem_context.c +10 -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;

/* If oa is active, it has already overridden the per-context setting */ if (oa->active)

Quoted 1 line
	goto set;

I don't like sprinkling knowledge of OA to more places than is unavoidable. As such I prefer to centralize it to gen8_make_rpcs. Only downside to not do it is an useless re-configuration request, but I don't think we should care to optimize for the OA enabled case. If anything it could make the overall system perform better when analysed than when not. :)

Regards,

Tvrtko

Quoted 13 lines

drivers/gpu/drm/i915/i915_gem_context.c int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, · line 1072

Quoted 10 lines
drivers/gpu/drm/i915/i915_gem_context.c +10 -0
+
+       /*
+        * 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)

set:

Quoted 11 lines

drivers/gpu/drm/i915/i915_gem_context.c int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, · line 1078

Quoted 6 lines
drivers/gpu/drm/i915/i915_gem_context.c +6 -0
+               ce->sseu = sseu;
+
+out:
+       mutex_unlock(&ctx->i915->drm.struct_mutex);
+
+       return ret;

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

author maintainer
#9 lore raw

PATCH 6/6 drm/i915/icl: Support co-existance between per-context SSEU and OA

In reply to Tvrtko Ursulin

From: Tvrtko Ursulin <[email protected]>

When OA is active we want to lock the powergating configuration, but on Icelake users like media stack will have issues if we lock to the full device configuration.

Instead lock to a subset of (sub)slices which are currently a known working configuration for all users.

Cc Lionel Landwerlin <[email protected]>
---
 drivers/gpu/drm/i915/intel_lrc.c | 25 ++++++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)
drivers/gpu/drm/i915/intel_lrc.c +20 -5
index 0cfa99a13522..2aaf2237a2b0 100644
@@ -2522,13 +2522,28 @@ 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_GEN11(i915)) {
+			/*
+			 * We only need subslice count so it doesn't matter
+			 * which ones we select - just turn of 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);
Signature · 6 lines
2.17.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#10 lore raw

✗ Fi.CI.CHECKPATCH: warning for Per context dynamic (sub)slice power-gating (rev3)

In reply to Tvrtko Ursulin
== Series Details ==

== Series Details ==

Series: Per context dynamic (sub)slice power-gating (rev3)
URL : https://patchwork.freedesktop.org/series/48194/
State : warning

== Summary ==

$ dim checkpatch origin/drm-tip
1c5fbd789ec4 drm/i915/execlists: Move RPCS setup to context pin
7bdb7605a619 drm/i915: Record the sseu configuration per-context & engine
cb0997071642 drm/i915/perf: lock powergating configuration to default when active
5dd5511a2f86 drm/i915: Add timeline barrier support
769a1cfec93c drm/i915: Expose RPCS (SSEU) configuration to userspace
-:40: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line)
#40: 
v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel)

total: 0 errors, 1 warnings, 0 checks, 451 lines checked c660f495e4ae drm/i915/icl: Support co-existance between per-context SSEU and OA -:4: WARNING:TYPO_SPELLING: 'existance' may be misspelled - perhaps 'existence'? #4:
Subject: [PATCH] drm/i915/icl: Support co-existance between per-context SSEU

total: 0 errors, 1 warnings, 0 checks, 33 lines checked

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#11 lore raw

✗ Fi.CI.SPARSE: warning for Per context dynamic (sub)slice power-gating (rev3)

In reply to Tvrtko Ursulin
== Series Details ==

== Series Details ==

Series: Per context dynamic (sub)slice power-gating (rev3)
URL : https://patchwork.freedesktop.org/series/48194/
State : warning

== Summary ==

$ dim sparse origin/drm-tip
Commit: drm/i915/execlists: Move RPCS setup to context pin
Okay!

Commit: drm/i915: Record the sseu configuration per-context & engine -drivers/gpu/drm/i915/selftests/../i915_drv.h:3718:16: warning: expression using sizeof(void) +drivers/gpu/drm/i915/selftests/../i915_drv.h:3732:16: warning: expression using sizeof(void)

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

Commit: drm/i915: Add timeline barrier support
Okay!

Commit: drm/i915: Expose RPCS (SSEU) configuration to userspace +drivers/gpu/drm/i915/intel_lrc.c:2563:25: warning: expression using sizeof(void)

Commit: drm/i915/icl: Support co-existance between per-context SSEU and OA Okay!

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#12 lore raw

✓ Fi.CI.BAT: success for Per context dynamic (sub)slice power-gating (rev3)

In reply to Tvrtko Ursulin
== Series Details ==

== Series Details ==

Series: Per context dynamic (sub)slice power-gating (rev3)
URL : https://patchwork.freedesktop.org/series/48194/
State : success

== Summary ==

= CI Bug Log - changes from CI_DRM_4827 -> Patchwork_10195 =

== Summary - SUCCESS ==

No regressions found.

External URL: https://patchwork.freedesktop.org/api/1.0/series/48194/revisions/3/mbox/

== Known issues ==

Here are the changes found in Patchwork_10195 that come from known issues:

=== IGT changes ===

    ==== Issues hit ====

    igt@drv_selftest@mock_hugepages:
      fi-bwr-2160:        PASS -> DMESG-FAIL (fdo#107930)

    igt@kms_pipe_crc_basic@nonblocking-crc-pipe-b-frame-sequence:
      fi-byt-clapper:     PASS -> FAIL (fdo#107362, fdo#103191)

    igt@prime_vgem@basic-fence-flip:
      fi-ilk-650:         PASS -> FAIL (fdo#104008)

    
    ==== Possible fixes ====

    igt@gem_exec_suspend@basic-s3:
      fi-blb-e6850:       INCOMPLETE (fdo#107718) -> PASS

    igt@kms_pipe_crc_basic@read-crc-pipe-a-frame-sequence:
      fi-byt-clapper:     FAIL (fdo#107362, fdo#103191) -> PASS

    igt@kms_psr@primary_page_flip:
      fi-kbl-r:           FAIL (fdo#107336) -> PASS

fdo#103191 https://bugs.freedesktop.org/show_bug.cgi?id=103191
fdo#104008 https://bugs.freedesktop.org/show_bug.cgi?id=104008
fdo#107336 https://bugs.freedesktop.org/show_bug.cgi?id=107336
fdo#107362 https://bugs.freedesktop.org/show_bug.cgi?id=107362
fdo#107718 https://bugs.freedesktop.org/show_bug.cgi?id=107718
fdo#107930 https://bugs.freedesktop.org/show_bug.cgi?id=107930

== Participating hosts (48 -> 43) ==

Missing (5): fi-byt-j1900 fi-ilk-m540 fi-byt-squawks fi-bsw-cyan fi-hsw-4200u

== Build changes ==

* Linux: CI_DRM_4827 -> Patchwork_10195

CI_DRM_4827: 8b1968f143e8bf65acf0ea6f7ce9120259043521 @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_4642: 7b3ea4efb9713cd67e17e33202fa9d0681a284d1 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
Patchwork_10195: c660f495e4ae059926730ac2e8474087d2a7e1cc @ git://anongit.freedesktop.org/gfx-ci/linux

== Linux commits ==

c660f495e4ae drm/i915/icl: Support co-existance between per-context SSEU and OA 769a1cfec93c drm/i915: Expose RPCS (SSEU) configuration to userspace 5dd5511a2f86 drm/i915: Add timeline barrier support
cb0997071642 drm/i915/perf: lock powergating configuration to default when active 7bdb7605a619 drm/i915: Record the sseu configuration per-context & engine 1c5fbd789ec4 drm/i915/execlists: Move RPCS setup to context pin

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_10195/issues.html
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#13 lore raw

✗ Fi.CI.IGT: failure for Per context dynamic (sub)slice power-gating (rev3)

In reply to Tvrtko Ursulin
== Series Details ==

== Series Details ==

Series: Per context dynamic (sub)slice power-gating (rev3)
URL : https://patchwork.freedesktop.org/series/48194/
State : failure

== Summary ==

= CI Bug Log - changes from CI_DRM_4827_full -> Patchwork_10195_full =

== Summary - FAILURE ==

Serious unknown changes coming with Patchwork_10195_full absolutely need to be verified manually.

If you think the reported changes have nothing to do with the changes introduced in Patchwork_10195_full, please notify your bug team to allow them to document this new failure mode, which will reduce false positives in CI.

== Possible new issues ==

Here are the unknown changes that may have been introduced in Patchwork_10195_full:

=== IGT changes ===

    ==== Possible regressions ====

    igt@gem_ctx_param@invalid-param-get:
      shard-apl:          PASS -> FAIL
      shard-glk:          PASS -> FAIL
      shard-snb:          PASS -> FAIL
      shard-hsw:          PASS -> FAIL
      shard-kbl:          PASS -> FAIL

    
    ==== Warnings ====

    igt@perf_pmu@rc6:
      shard-kbl:          SKIP -> PASS

== Known issues ==

Here are the changes found in Patchwork_10195_full that come from known issues:

=== IGT changes ===

    ==== Issues hit ====

    igt@kms_sysfs_edid_timing:
      shard-hsw:          PASS -> WARN (fdo#100047)

    
    ==== Possible fixes ====

    igt@kms_frontbuffer_tracking@fbc-2p-primscrn-cur-indfb-draw-mmap-cpu:
      shard-glk:          FAIL (fdo#103167) -> PASS

    igt@kms_setmode@basic:
      shard-apl:          FAIL (fdo#99912) -> PASS
      shard-kbl:          FAIL (fdo#99912) -> PASS

    igt@kms_vblank@pipe-b-wait-forked-busy-hang:
      shard-glk:          DMESG-WARN (fdo#106538, fdo#105763) -> PASS +3

    igt@testdisplay:
      shard-apl:          DMESG-WARN (fdo#103558, fdo#105602) -> PASS

fdo#100047 https://bugs.freedesktop.org/show_bug.cgi?id=100047
fdo#103167 https://bugs.freedesktop.org/show_bug.cgi?id=103167
fdo#103558 https://bugs.freedesktop.org/show_bug.cgi?id=103558
fdo#105602 https://bugs.freedesktop.org/show_bug.cgi?id=105602
fdo#105763 https://bugs.freedesktop.org/show_bug.cgi?id=105763
fdo#106538 https://bugs.freedesktop.org/show_bug.cgi?id=106538
fdo#99912 https://bugs.freedesktop.org/show_bug.cgi?id=99912

== Participating hosts (5 -> 5) ==

No changes in participating hosts

== Build changes ==

* Linux: CI_DRM_4827 -> Patchwork_10195

CI_DRM_4827: 8b1968f143e8bf65acf0ea6f7ce9120259043521 @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_4642: 7b3ea4efb9713cd67e17e33202fa9d0681a284d1 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
Patchwork_10195: c660f495e4ae059926730ac2e8474087d2a7e1cc @ git://anongit.freedesktop.org/gfx-ci/linux
piglit_4509: fdc5a4ca11124ab8413c7988896eec4c97336694 @ git://anongit.freedesktop.org/piglit

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_10195/shards.html
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx