drm/i915: Fix context ban and hang accounting for client

If client is smart or lucky enough to create a new context
after each hang, our context banning mechanism will never
catch up, and as a result of that it will be saved from
client banning. This can result in a never ending streak of
gpu hangs caused by bad or malicious client, preventing
access from other legit gpu clients.

Fix this by always incrementing per client ban score if
it hangs in short successions regardless of context ban
scoring. The exception are non bannable contexts. They remain
detached from client ban scoring mechanism.

v2: xchg timestamp, tidyup (Chris)
v3: comment, bannable & banned together (Chris)

Fixes: b083a0870c79 ("drm/i915: Add per client max context ban limit")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180615104429.31477-1-mika.kuoppala@linux.intel.com

1 files changed, 40 insertions, 17 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 8dd4d35655af..977982a987c8 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2941,32 +2941,54 @@ i915_gem_object_pwrite_gtt(struct drm_i915_gem_object *obj,
 	return 0;
 }
 
+static void i915_gem_client_mark_guilty(struct drm_i915_file_private *file_priv,
+					const struct i915_gem_context *ctx)
+{
+	unsigned int score;
+	unsigned long prev_hang;
+
+	if (i915_gem_context_is_banned(ctx))
+		score = I915_CLIENT_SCORE_CONTEXT_BAN;
+	else
+		score = 0;
+
+	prev_hang = xchg(&file_priv->hang_timestamp, jiffies);
+	if (time_before(jiffies, prev_hang + I915_CLIENT_FAST_HANG_JIFFIES))
+		score += I915_CLIENT_SCORE_HANG_FAST;
+
+	if (score) {
+		atomic_add(score, &file_priv->ban_score);
+
+		DRM_DEBUG_DRIVER("client %s: gained %u ban score, now %u\n",
+				 ctx->name, score,
+				 atomic_read(&file_priv->ban_score));
+	}
+}
+
 static void i915_gem_context_mark_guilty(struct i915_gem_context *ctx)
 {
-	bool banned;
+	unsigned int score;
+	bool banned, bannable;
 
 	atomic_inc(&ctx->guilty_count);
 
-	banned = false;
-	if (i915_gem_context_is_bannable(ctx)) {
-		unsigned int score;
+	bannable = i915_gem_context_is_bannable(ctx);
+	score = atomic_add_return(CONTEXT_SCORE_GUILTY, &ctx->ban_score);
+	banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
 
-		score = atomic_add_return(CONTEXT_SCORE_GUILTY,
-					  &ctx->ban_score);
-		banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
+	DRM_DEBUG_DRIVER("context %s: guilty %d, score %u, ban %s\n",
+			 ctx->name, atomic_read(&ctx->guilty_count),
+			 score, yesno(banned && bannable));
 
-		DRM_DEBUG_DRIVER("context %s marked guilty (score %d) banned? %s\n",
-				 ctx->name, score, yesno(banned));
-	}
-	if (!banned)
+	/* Cool contexts don't accumulate client ban score */
+	if (!bannable)
 		return;
 
-	i915_gem_context_set_banned(ctx);
-	if (!IS_ERR_OR_NULL(ctx->file_priv)) {
-		atomic_inc(&ctx->file_priv->context_bans);
-		DRM_DEBUG_DRIVER("client %s has had %d context banned\n",
-				 ctx->name, atomic_read(&ctx->file_priv->context_bans));
-	}
+	if (banned)
+		i915_gem_context_set_banned(ctx);
+
+	if (!IS_ERR_OR_NULL(ctx->file_priv))
+		i915_gem_client_mark_guilty(ctx->file_priv, ctx);
 }
 
 static void i915_gem_context_mark_innocent(struct i915_gem_context *ctx)
@@ -5820,6 +5842,7 @@ int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file)
 	INIT_LIST_HEAD(&file_priv->mm.request_list);
 
 	file_priv->bsd_engine = -1;
+	file_priv->hang_timestamp = jiffies;
 
 	ret = i915_gem_context_open(i915, file);
 	if (ret)