1 files changed, 107 insertions, 2 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 6819fe5612d9..e7a010b7ca1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -331,10 +331,13 @@ static int amdgpu_ctx_query(struct amdgpu_device *adev,
 	return 0;
 }
 
+#define AMDGPU_RAS_COUNTE_DELAY_MS 3000
+
 static int amdgpu_ctx_query2(struct amdgpu_device *adev,
-	struct amdgpu_fpriv *fpriv, uint32_t id,
-	union drm_amdgpu_ctx_out *out)
+			     struct amdgpu_fpriv *fpriv, uint32_t id,
+			     union drm_amdgpu_ctx_out *out)
 {
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct amdgpu_ctx *ctx;
 	struct amdgpu_ctx_mgr *mgr;
 
@@ -361,6 +364,30 @@ static int amdgpu_ctx_query2(struct amdgpu_device *adev,
 	if (atomic_read(&ctx->guilty))
 		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_GUILTY;
 
+	if (adev->ras_enabled && con) {
+		/* Return the cached values in O(1),
+		 * and schedule delayed work to cache
+		 * new vaues.
+		 */
+		int ce_count, ue_count;
+
+		ce_count = atomic_read(&con->ras_ce_count);
+		ue_count = atomic_read(&con->ras_ue_count);
+
+		if (ce_count != ctx->ras_counter_ce) {
+			ctx->ras_counter_ce = ce_count;
+			out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_RAS_CE;
+		}
+
+		if (ue_count != ctx->ras_counter_ue) {
+			ctx->ras_counter_ue = ue_count;
+			out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_RAS_UE;
+		}
+
+		schedule_delayed_work(&con->ras_counte_delay_work,
+				      msecs_to_jiffies(AMDGPU_RAS_COUNTE_DELAY_MS));
+	}
+
 	mutex_unlock(&mgr->lock);
 	return 0;
 }
@@ -635,3 +662,81 @@ void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr)
 	idr_destroy(&mgr->ctx_handles);
 	mutex_destroy(&mgr->lock);
 }
+
+static void amdgpu_ctx_fence_time(struct amdgpu_ctx *ctx,
+		struct amdgpu_ctx_entity *centity, ktime_t *total, ktime_t *max)
+{
+	ktime_t now, t1;
+	uint32_t i;
+
+	*total = *max = 0;
+
+	now = ktime_get();
+	for (i = 0; i < amdgpu_sched_jobs; i++) {
+		struct dma_fence *fence;
+		struct drm_sched_fence *s_fence;
+
+		spin_lock(&ctx->ring_lock);
+		fence = dma_fence_get(centity->fences[i]);
+		spin_unlock(&ctx->ring_lock);
+		if (!fence)
+			continue;
+		s_fence = to_drm_sched_fence(fence);
+		if (!dma_fence_is_signaled(&s_fence->scheduled)) {
+			dma_fence_put(fence);
+			continue;
+		}
+		t1 = s_fence->scheduled.timestamp;
+		if (!ktime_before(t1, now)) {
+			dma_fence_put(fence);
+			continue;
+		}
+		if (dma_fence_is_signaled(&s_fence->finished) &&
+			s_fence->finished.timestamp < now)
+			*total += ktime_sub(s_fence->finished.timestamp, t1);
+		else
+			*total += ktime_sub(now, t1);
+		t1 = ktime_sub(now, t1);
+		dma_fence_put(fence);
+		*max = max(t1, *max);
+	}
+}
+
+ktime_t amdgpu_ctx_mgr_fence_usage(struct amdgpu_ctx_mgr *mgr, uint32_t hwip,
+		uint32_t idx, uint64_t *elapsed)
+{
+	struct idr *idp;
+	struct amdgpu_ctx *ctx;
+	uint32_t id;
+	struct amdgpu_ctx_entity *centity;
+	ktime_t total = 0, max = 0;
+
+	if (idx >= AMDGPU_MAX_ENTITY_NUM)
+		return 0;
+	idp = &mgr->ctx_handles;
+	mutex_lock(&mgr->lock);
+	idr_for_each_entry(idp, ctx, id) {
+		ktime_t ttotal, tmax;
+
+		if (!ctx->entities[hwip][idx])
+			continue;
+
+		centity = ctx->entities[hwip][idx];
+		amdgpu_ctx_fence_time(ctx, centity, &ttotal, &tmax);
+
+		/* Harmonic mean approximation diverges for very small
+		 * values. If ratio < 0.01% ignore
+		 */
+		if (AMDGPU_CTX_FENCE_USAGE_MIN_RATIO(tmax, ttotal))
+			continue;
+
+		total = ktime_add(total, ttotal);
+		max = ktime_after(tmax, max) ? tmax : max;
+	}
+
+	mutex_unlock(&mgr->lock);
+	if (elapsed)
+		*elapsed = max;
+
+	return total;
+}