1 files changed, 108 insertions, 53 deletions

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 0f556d80ba36..551be589d6f4 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -555,8 +555,9 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 				aging_tail = hw_tail;
 			stream->oa_buffer.aging_timestamp = now;
 		} else {
-			DRM_ERROR("Ignoring spurious out of range OA buffer tail pointer = %x\n",
-				  hw_tail);
+			drm_err(&stream->perf->i915->drm,
+				"Ignoring spurious out of range OA buffer tail pointer = %x\n",
+				hw_tail);
 		}
 	}
 
@@ -686,7 +687,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 	u32 taken;
 	int ret = 0;
 
-	if (WARN_ON(!stream->enabled))
+	if (drm_WARN_ON(&uncore->i915->drm, !stream->enabled))
 		return -EIO;
 
 	spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags);
@@ -718,10 +719,11 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 	 * only be incremented by multiples of the report size (notably also
 	 * all a power of two).
 	 */
-	if (WARN_ONCE(head > OA_BUFFER_SIZE || head % report_size ||
-		      tail > OA_BUFFER_SIZE || tail % report_size,
-		      "Inconsistent OA buffer pointers: head = %u, tail = %u\n",
-		      head, tail))
+	if (drm_WARN_ONCE(&uncore->i915->drm,
+			  head > OA_BUFFER_SIZE || head % report_size ||
+			  tail > OA_BUFFER_SIZE || tail % report_size,
+			  "Inconsistent OA buffer pointers: head = %u, tail = %u\n",
+			  head, tail))
 		return -EIO;
 
 
@@ -742,8 +744,10 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 * here would imply a driver bug that would result
 		 * in an overrun.
 		 */
-		if (WARN_ON((OA_BUFFER_SIZE - head) < report_size)) {
-			DRM_ERROR("Spurious OA head ptr: non-integral report offset\n");
+		if (drm_WARN_ON(&uncore->i915->drm,
+				(OA_BUFFER_SIZE - head) < report_size)) {
+			drm_err(&uncore->i915->drm,
+				"Spurious OA head ptr: non-integral report offset\n");
 			break;
 		}
 
@@ -896,7 +900,7 @@ static int gen8_oa_read(struct i915_perf_stream *stream,
 	i915_reg_t oastatus_reg;
 	int ret;
 
-	if (WARN_ON(!stream->oa_buffer.vaddr))
+	if (drm_WARN_ON(&uncore->i915->drm, !stream->oa_buffer.vaddr))
 		return -EIO;
 
 	oastatus_reg = IS_GEN(stream->perf->i915, 12) ?
@@ -986,7 +990,7 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 	u32 taken;
 	int ret = 0;
 
-	if (WARN_ON(!stream->enabled))
+	if (drm_WARN_ON(&uncore->i915->drm, !stream->enabled))
 		return -EIO;
 
 	spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags);
@@ -1015,10 +1019,11 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 	 * only be incremented by multiples of the report size (notably also
 	 * all a power of two).
 	 */
-	if (WARN_ONCE(head > OA_BUFFER_SIZE || head % report_size ||
-		      tail > OA_BUFFER_SIZE || tail % report_size,
-		      "Inconsistent OA buffer pointers: head = %u, tail = %u\n",
-		      head, tail))
+	if (drm_WARN_ONCE(&uncore->i915->drm,
+			  head > OA_BUFFER_SIZE || head % report_size ||
+			  tail > OA_BUFFER_SIZE || tail % report_size,
+			  "Inconsistent OA buffer pointers: head = %u, tail = %u\n",
+			  head, tail))
 		return -EIO;
 
 
@@ -1036,8 +1041,10 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 		 * here would imply a driver bug that would result
 		 * in an overrun.
 		 */
-		if (WARN_ON((OA_BUFFER_SIZE - head) < report_size)) {
-			DRM_ERROR("Spurious OA head ptr: non-integral report offset\n");
+		if (drm_WARN_ON(&uncore->i915->drm,
+				(OA_BUFFER_SIZE - head) < report_size)) {
+			drm_err(&uncore->i915->drm,
+				"Spurious OA head ptr: non-integral report offset\n");
 			break;
 		}
 
@@ -1110,7 +1117,7 @@ static int gen7_oa_read(struct i915_perf_stream *stream,
 	u32 oastatus1;
 	int ret;
 
-	if (WARN_ON(!stream->oa_buffer.vaddr))
+	if (drm_WARN_ON(&uncore->i915->drm, !stream->oa_buffer.vaddr))
 		return -EIO;
 
 	oastatus1 = intel_uncore_read(uncore, GEN7_OASTATUS1);
@@ -1319,7 +1326,13 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 	case 12: {
 		stream->specific_ctx_id_mask =
 			((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
-		stream->specific_ctx_id = stream->specific_ctx_id_mask;
+		/*
+		 * Pick an unused context id
+		 * 0 - (NUM_CONTEXT_TAG - 1) are used by other contexts
+		 * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
+		 */
+		stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
+		BUILD_BUG_ON((GEN12_MAX_CONTEXT_HW_ID - 1) < NUM_CONTEXT_TAG);
 		break;
 	}
 
@@ -1327,11 +1340,12 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		MISSING_CASE(INTEL_GEN(ce->engine->i915));
 	}
 
-	ce->tag = stream->specific_ctx_id_mask;
+	ce->tag = stream->specific_ctx_id;
 
-	DRM_DEBUG_DRIVER("filtering on ctx_id=0x%x ctx_id_mask=0x%x\n",
-			 stream->specific_ctx_id,
-			 stream->specific_ctx_id_mask);
+	drm_dbg(&stream->perf->i915->drm,
+		"filtering on ctx_id=0x%x ctx_id_mask=0x%x\n",
+		stream->specific_ctx_id,
+		stream->specific_ctx_id_mask);
 
 	return 0;
 }
@@ -1391,8 +1405,10 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 	/*
 	 * Unset exclusive_stream first, it will be checked while disabling
 	 * the metric set on gen8+.
+	 *
+	 * See i915_oa_init_reg_state() and lrc_configure_all_contexts()
 	 */
-	perf->exclusive_stream = NULL;
+	WRITE_ONCE(perf->exclusive_stream, NULL);
 	perf->ops.disable_metric_set(stream);
 
 	free_oa_buffer(stream);
@@ -1575,11 +1591,12 @@ static void gen12_init_oa_buffer(struct i915_perf_stream *stream)
 
 static int alloc_oa_buffer(struct i915_perf_stream *stream)
 {
+	struct drm_i915_private *i915 = stream->perf->i915;
 	struct drm_i915_gem_object *bo;
 	struct i915_vma *vma;
 	int ret;
 
-	if (WARN_ON(stream->oa_buffer.vma))
+	if (drm_WARN_ON(&i915->drm, stream->oa_buffer.vma))
 		return -ENODEV;
 
 	BUILD_BUG_ON_NOT_POWER_OF_2(OA_BUFFER_SIZE);
@@ -1587,7 +1604,7 @@ static int alloc_oa_buffer(struct i915_perf_stream *stream)
 
 	bo = i915_gem_object_create_shmem(stream->perf->i915, OA_BUFFER_SIZE);
 	if (IS_ERR(bo)) {
-		DRM_ERROR("Failed to allocate OA buffer\n");
+		drm_err(&i915->drm, "Failed to allocate OA buffer\n");
 		return PTR_ERR(bo);
 	}
 
@@ -1669,7 +1686,8 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
 
 	bo = i915_gem_object_create_internal(i915, 4096);
 	if (IS_ERR(bo)) {
-		DRM_ERROR("Failed to allocate NOA wait batchbuffer\n");
+		drm_err(&i915->drm,
+			"Failed to allocate NOA wait batchbuffer\n");
 		return PTR_ERR(bo);
 	}
 
@@ -1954,9 +1972,10 @@ 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;
@@ -1964,7 +1983,7 @@ 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)
@@ -1989,13 +2008,17 @@ 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)
@@ -2003,7 +2026,8 @@ 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;
 
@@ -2178,7 +2202,9 @@ static int gen8_modify_self(struct intel_context *ce,
 	struct i915_request *rq;
 	int err;
 
+	intel_engine_pm_get(ce->engine);
 	rq = i915_request_create(ce);
+	intel_engine_pm_put(ce->engine);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
@@ -2406,7 +2432,8 @@ 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;
@@ -2448,7 +2475,7 @@ 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));
 }
@@ -2460,7 +2487,8 @@ static u32 oag_report_ctx_switches(const struct i915_perf_stream *stream)
 			     0 : GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS);
 }
 
-static int gen12_enable_metric_set(struct i915_perf_stream *stream)
+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;
@@ -2491,7 +2519,7 @@ 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
@@ -2501,7 +2529,7 @@ 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));
@@ -2645,7 +2673,8 @@ static void gen7_oa_disable(struct i915_perf_stream *stream)
 	if (intel_wait_for_register(uncore,
 				    GEN7_OACONTROL, GEN7_OACONTROL_ENABLE, 0,
 				    50))
-		DRM_ERROR("wait for OA to be disabled timed out\n");
+		drm_err(&stream->perf->i915->drm,
+			"wait for OA to be disabled timed out\n");
 }
 
 static void gen8_oa_disable(struct i915_perf_stream *stream)
@@ -2656,7 +2685,8 @@ static void gen8_oa_disable(struct i915_perf_stream *stream)
 	if (intel_wait_for_register(uncore,
 				    GEN8_OACONTROL, GEN8_OA_COUNTER_ENABLE, 0,
 				    50))
-		DRM_ERROR("wait for OA to be disabled timed out\n");
+		drm_err(&stream->perf->i915->drm,
+			"wait for OA to be disabled timed out\n");
 }
 
 static void gen12_oa_disable(struct i915_perf_stream *stream)
@@ -2668,7 +2698,16 @@ static void gen12_oa_disable(struct i915_perf_stream *stream)
 				    GEN12_OAG_OACONTROL,
 				    GEN12_OAG_OACONTROL_OA_COUNTER_ENABLE, 0,
 				    50))
-		DRM_ERROR("wait for OA to be disabled timed out\n");
+		drm_err(&stream->perf->i915->drm,
+			"wait for OA to be disabled timed out\n");
+
+	intel_uncore_write(uncore, GEN12_OA_TLB_INV_CR, 1);
+	if (intel_wait_for_register(uncore,
+				    GEN12_OA_TLB_INV_CR,
+				    1, 0,
+				    50))
+		drm_err(&stream->perf->i915->drm,
+			"wait for OA tlb invalidate timed out\n");
 }
 
 /**
@@ -2696,6 +2735,20 @@ 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
@@ -2718,6 +2771,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 			       struct drm_i915_perf_open_param *param,
 			       struct perf_open_properties *props)
 {
+	struct drm_i915_private *i915 = stream->perf->i915;
 	struct i915_perf *perf = stream->perf;
 	int format_size;
 	int ret;
@@ -2774,7 +2828,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	stream->sample_size += format_size;
 
 	stream->oa_buffer.format_size = format_size;
-	if (WARN_ON(stream->oa_buffer.format_size == 0))
+	if (drm_WARN_ON(&i915->drm, stream->oa_buffer.format_size == 0))
 		return -EINVAL;
 
 	stream->hold_preemption = props->hold_preemption;
@@ -2827,9 +2881,9 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		goto err_oa_buf_alloc;
 
 	stream->ops = &i915_oa_stream_ops;
-	perf->exclusive_stream = stream;
+	WRITE_ONCE(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;
@@ -2847,7 +2901,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	return 0;
 
 err_enable:
-	perf->exclusive_stream = NULL;
+	WRITE_ONCE(perf->exclusive_stream, NULL);
 	perf->ops.disable_metric_set(stream);
 
 	free_oa_buffer(stream);
@@ -2873,12 +2927,11 @@ void i915_oa_init_reg_state(const struct intel_context *ce,
 {
 	struct i915_perf_stream *stream;
 
-	/* perf.exclusive_stream serialised by lrc_configure_all_contexts() */
-
 	if (engine->class != RENDER_CLASS)
 		return;
 
-	stream = engine->i915->perf.exclusive_stream;
+	/* perf.exclusive_stream serialised by lrc_configure_all_contexts() */
+	stream = READ_ONCE(engine->i915->perf.exclusive_stream);
 	/*
 	 * For gen12, only CTX_R_PWR_CLK_STATE needs update, but the caller
 	 * is already doing that, so nothing to be done for gen12 here.
@@ -3147,7 +3200,7 @@ 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
@@ -3158,11 +3211,13 @@ 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);