1 files changed, 77 insertions, 43 deletions

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 2ae14bc14931..3b6b913bd27a 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -387,6 +387,8 @@ struct i915_oa_config_bo {
 	struct i915_vma *vma;
 };
 
+static struct ctl_table_header *sysctl_header;
+
 static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer);
 
 void i915_oa_config_release(struct kref *ref)
@@ -1777,6 +1779,8 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
 	*cs++ = MI_MATH_ADD;
 	*cs++ = MI_MATH_STOREINV(MI_MATH_REG(JUMP_PREDICATE), MI_MATH_REG_CF);
 
+	*cs++ = MI_ARB_CHECK;
+
 	/*
 	 * Transfer the result into the predicate register to be used for the
 	 * predicated jump.
@@ -1950,9 +1954,10 @@ out:
 	return i915_vma_get(oa_bo->vma);
 }
 
-static int emit_oa_config(struct i915_perf_stream *stream,
-			  struct i915_oa_config *oa_config,
-			  struct intel_context *ce)
+static struct i915_request *
+emit_oa_config(struct i915_perf_stream *stream,
+	       struct i915_oa_config *oa_config,
+	       struct intel_context *ce)
 {
 	struct i915_request *rq;
 	struct i915_vma *vma;
@@ -1960,13 +1965,15 @@ static int emit_oa_config(struct i915_perf_stream *stream,
 
 	vma = get_oa_vma(stream, oa_config);
 	if (IS_ERR(vma))
-		return PTR_ERR(vma);
+		return ERR_CAST(vma);
 
 	err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
 	if (err)
 		goto err_vma_put;
 
+	intel_engine_pm_get(ce->engine);
 	rq = i915_request_create(ce);
+	intel_engine_pm_put(ce->engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_vma_unpin;
@@ -1983,13 +1990,17 @@ static int emit_oa_config(struct i915_perf_stream *stream,
 	err = rq->engine->emit_bb_start(rq,
 					vma->node.start, 0,
 					I915_DISPATCH_SECURE);
+	if (err)
+		goto err_add_request;
+
+	i915_request_get(rq);
 err_add_request:
 	i915_request_add(rq);
 err_vma_unpin:
 	i915_vma_unpin(vma);
 err_vma_put:
 	i915_vma_put(vma);
-	return err;
+	return err ? ERR_PTR(err) : rq;
 }
 
 static struct intel_context *oa_context(struct i915_perf_stream *stream)
@@ -1997,7 +2008,8 @@ static struct intel_context *oa_context(struct i915_perf_stream *stream)
 	return stream->pinned_ctx ?: stream->engine->kernel_context;
 }
 
-static int hsw_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+hsw_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 
@@ -2153,9 +2165,7 @@ static int gen8_modify_context(struct intel_context *ce,
 	struct i915_request *rq;
 	int err;
 
-	lockdep_assert_held(&ce->pin_mutex);
-
-	rq = i915_request_create(ce->engine->kernel_context);
+	rq = intel_engine_create_kernel_request(ce->engine);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
@@ -2197,17 +2207,14 @@ static int gen8_configure_context(struct i915_gem_context *ctx,
 		if (ce->engine->class != RENDER_CLASS)
 			continue;
 
-		err = intel_context_lock_pinned(ce);
-		if (err)
-			break;
+		/* Otherwise OA settings will be set upon first use */
+		if (!intel_context_pin_if_active(ce))
+			continue;
 
 		flex->value = intel_sseu_make_rpcs(ctx->i915, &ce->sseu);
+		err = gen8_modify_context(ce, flex, count);
 
-		/* Otherwise OA settings will be set upon first use */
-		if (intel_context_is_pinned(ce))
-			err = gen8_modify_context(ce, flex, count);
-
-		intel_context_unlock_pinned(ce);
+		intel_context_unpin(ce);
 		if (err)
 			break;
 	}
@@ -2317,9 +2324,6 @@ static int oa_configure_all_contexts(struct i915_perf_stream *stream,
 	 */
 	spin_lock(&i915->gem.contexts.lock);
 	list_for_each_entry_safe(ctx, cn, &i915->gem.contexts.list, link) {
-		if (ctx == i915->kernel_context)
-			continue;
-
 		if (!kref_get_unless_zero(&ctx->ref))
 			continue;
 
@@ -2408,7 +2412,8 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,
 	return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs));
 }
 
-static int gen8_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+gen8_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 	struct i915_oa_config *oa_config = stream->oa_config;
@@ -2450,12 +2455,20 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 	 */
 	ret = lrc_configure_all_contexts(stream, oa_config);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
 	return emit_oa_config(stream, oa_config, oa_context(stream));
 }
 
-static int gen12_enable_metric_set(struct i915_perf_stream *stream)
+static u32 oag_report_ctx_switches(const struct i915_perf_stream *stream)
+{
+	return _MASKED_FIELD(GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS,
+			     (stream->sample_flags & SAMPLE_OA_REPORT) ?
+			     0 : GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS);
+}
+
+static struct i915_request *
+gen12_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 	struct i915_oa_config *oa_config = stream->oa_config;
@@ -2468,12 +2481,10 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 			   _MASKED_BIT_ENABLE(GEN12_OAG_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS |
 					      GEN12_OAG_OA_DEBUG_INCLUDE_CLK_RATIO) |
 			   /*
-			    * If the user didn't require OA reports, instruct the
-			    * hardware not to emit ctx switch reports.
+			    * If the user didn't require OA reports, instruct
+			    * the hardware not to emit ctx switch reports.
 			    */
-			   !(stream->sample_flags & SAMPLE_OA_REPORT) ?
-			   _MASKED_BIT_ENABLE(GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS) :
-			   _MASKED_BIT_DISABLE(GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS));
+			   oag_report_ctx_switches(stream));
 
 	intel_uncore_write(uncore, GEN12_OAG_OAGLBCTXCTRL, periodic ?
 			   (GEN12_OAG_OAGLBCTXCTRL_COUNTER_RESUME |
@@ -2488,7 +2499,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 	 */
 	ret = gen12_configure_all_contexts(stream, oa_config);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
 	/*
 	 * For Gen12, performance counters are context
@@ -2498,7 +2509,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 	if (stream->ctx) {
 		ret = gen12_configure_oar_context(stream, true);
 		if (ret)
-			return ret;
+			return ERR_PTR(ret);
 	}
 
 	return emit_oa_config(stream, oa_config, oa_context(stream));
@@ -2693,6 +2704,20 @@ static const struct i915_perf_stream_ops i915_oa_stream_ops = {
 	.read = i915_oa_read,
 };
 
+static int i915_perf_stream_enable_sync(struct i915_perf_stream *stream)
+{
+	struct i915_request *rq;
+
+	rq = stream->perf->ops.enable_metric_set(stream);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
+	i915_request_put(rq);
+
+	return 0;
+}
+
 /**
  * i915_oa_stream_init - validate combined props for OA stream and init
  * @stream: An i915 perf stream
@@ -2826,7 +2851,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	stream->ops = &i915_oa_stream_ops;
 	perf->exclusive_stream = stream;
 
-	ret = perf->ops.enable_metric_set(stream);
+	ret = i915_perf_stream_enable_sync(stream);
 	if (ret) {
 		DRM_DEBUG("Unable to enable metric set\n");
 		goto err_enable;
@@ -3101,7 +3126,7 @@ static void i915_perf_enable_locked(struct i915_perf_stream *stream)
 		stream->ops->enable(stream);
 
 	if (stream->hold_preemption)
-		i915_gem_context_set_nopreempt(stream->ctx);
+		intel_context_set_nopreempt(stream->pinned_ctx);
 }
 
 /**
@@ -3127,7 +3152,7 @@ static void i915_perf_disable_locked(struct i915_perf_stream *stream)
 	stream->enabled = false;
 
 	if (stream->hold_preemption)
-		i915_gem_context_clear_nopreempt(stream->ctx);
+		intel_context_clear_nopreempt(stream->pinned_ctx);
 
 	if (stream->ops->disable)
 		stream->ops->disable(stream);
@@ -3144,7 +3169,7 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
 		return -EINVAL;
 
 	if (config != stream->oa_config) {
-		int err;
+		struct i915_request *rq;
 
 		/*
 		 * If OA is bound to a specific context, emit the
@@ -3155,11 +3180,13 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
 		 * When set globally, we use a low priority kernel context,
 		 * so it will effectively take effect when idle.
 		 */
-		err = emit_oa_config(stream, config, oa_context(stream));
-		if (err == 0)
+		rq = emit_oa_config(stream, config, oa_context(stream));
+		if (!IS_ERR(rq)) {
 			config = xchg(&stream->oa_config, config);
-		else
-			ret = err;
+			i915_request_put(rq);
+		} else {
+			ret = PTR_ERR(rq);
+		}
 	}
 
 	i915_oa_config_put(config);
@@ -3981,7 +4008,7 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 	struct i915_perf *perf = &to_i915(dev)->perf;
 	struct drm_i915_perf_oa_config *args = data;
 	struct i915_oa_config *oa_config, *tmp;
-	static struct i915_oa_reg *regs;
+	struct i915_oa_reg *regs;
 	int err, id;
 
 	if (!perf->i915) {
@@ -4219,7 +4246,7 @@ static struct ctl_table dev_root[] = {
 };
 
 /**
- * i915_perf_init - initialize i915-perf state on module load
+ * i915_perf_init - initialize i915-perf state on module bind
  * @i915: i915 device instance
  *
  * Initializes i915-perf state without exposing anything to userspace.
@@ -4336,7 +4363,6 @@ void i915_perf_init(struct drm_i915_private *i915)
 
 		oa_sample_rate_hard_limit = 1000 *
 			(RUNTIME_INFO(i915)->cs_timestamp_frequency_khz / 2);
-		perf->sysctl_header = register_sysctl_table(dev_root);
 
 		mutex_init(&perf->metrics_lock);
 		idr_init(&perf->metrics_idr);
@@ -4372,6 +4398,16 @@ static int destroy_config(int id, void *p, void *data)
 	return 0;
 }
 
+void i915_perf_sysctl_register(void)
+{
+	sysctl_header = register_sysctl_table(dev_root);
+}
+
+void i915_perf_sysctl_unregister(void)
+{
+	unregister_sysctl_table(sysctl_header);
+}
+
 /**
  * i915_perf_fini - Counter part to i915_perf_init()
  * @i915: i915 device instance
@@ -4386,8 +4422,6 @@ void i915_perf_fini(struct drm_i915_private *i915)
 	idr_for_each(&perf->metrics_idr, destroy_config, perf);
 	idr_destroy(&perf->metrics_idr);
 
-	unregister_sysctl_table(perf->sysctl_header);
-
 	memset(&perf->ops, 0, sizeof(perf->ops));
 	perf->i915 = NULL;
 }