drm/i915: Use request retirement as context progress

As hangcheck score was removed, the active decay of score
was removed also. This removed feature for hangcheck to detect
if the gpu client was accidentally or maliciously causing intermittent
hangs. Reinstate the scoring as a per context property, so that if
one context starts to act unfavourably, ban it.

v2: ban_period_secs as a gate to score check (Chris)
v3: decay in proper spot. scores as tunables (Chris)

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>

drivers/gpu/drm/i915/i915_drv.h

@@ -919,6 +919,11 @@ struct i915_ctx_hang_stats {
 
 	/* This context is banned to submit more work */
 	bool banned;
+
+#define CONTEXT_SCORE_GUILTY		10
+#define CONTEXT_SCORE_BAN_THRESHOLD	40
+	/* Accumulated score of hangs caused by this context */
+	int ban_score;
 };
 
 /* This must match up with the value previously used for execbuf2.rsvd1. */

drivers/gpu/drm/i915/i915_gem.c

@@ -2622,33 +2622,45 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 
 static bool i915_context_is_banned(const struct i915_gem_context *ctx)
 {
+	const struct i915_ctx_hang_stats *hs = &ctx->hang_stats;
 	unsigned long elapsed;
 
-	if (ctx->hang_stats.banned)
+	if (hs->banned)
 		return true;
 
-	elapsed = get_seconds() - ctx->hang_stats.guilty_ts;
-	if (ctx->hang_stats.ban_period_seconds &&
-	    elapsed <= ctx->hang_stats.ban_period_seconds) {
+	if (!hs->ban_period_seconds)
+		return false;
+
+	elapsed = get_seconds() - hs->guilty_ts;
+	if (elapsed <= hs->ban_period_seconds) {
 		DRM_DEBUG("context hanging too fast, banning!\n");
 		return true;
 	}
 
+	if (hs->ban_score >= CONTEXT_SCORE_BAN_THRESHOLD) {
+		DRM_DEBUG("context hanging too often, banning!\n");
+		return true;
+	}
+
 	return false;
 }
 
-static void i915_set_reset_status(struct i915_gem_context *ctx,
-				  const bool guilty)
+static void i915_gem_context_mark_guilty(struct i915_gem_context *ctx)
 {
 	struct i915_ctx_hang_stats *hs = &ctx->hang_stats;
 
-	if (guilty) {
-		hs->banned = i915_context_is_banned(ctx);
-		hs->batch_active++;
-		hs->guilty_ts = get_seconds();
-	} else {
-		hs->batch_pending++;
-	}
+	hs->ban_score += CONTEXT_SCORE_GUILTY;
+
+	hs->banned = i915_context_is_banned(ctx);
+	hs->batch_active++;
+	hs->guilty_ts = get_seconds();
+}
+
+static void i915_gem_context_mark_innocent(struct i915_gem_context *ctx)
+{
+	struct i915_ctx_hang_stats *hs = &ctx->hang_stats;
+
+	hs->batch_pending++;
 }
 
 struct drm_i915_gem_request *
@@ -2713,7 +2725,11 @@ static void i915_gem_reset_engine(struct intel_engine_cs *engine)
 		ring_hung = false;
 	}
 
-	i915_set_reset_status(request->ctx, ring_hung);
+	if (ring_hung)
+		i915_gem_context_mark_guilty(request->ctx);
+	else
+		i915_gem_context_mark_innocent(request->ctx);
+
 	if (!ring_hung)
 		return;
 

drivers/gpu/drm/i915/i915_gem_request.c

@@ -263,6 +263,10 @@ static void i915_gem_request_retire(struct drm_i915_gem_request *request)
 					       request->engine);
 	}
 
+	/* Retirement decays the ban score as it is a sign of ctx progress */
+	if (request->ctx->hang_stats.ban_score > 0)
+		request->ctx->hang_stats.ban_score--;
+
 	i915_gem_context_put(request->ctx);
 
 	dma_fence_signal(&request->fence);