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: b083a0870c ("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
(cherry picked from commit 14921f3cef)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>

drivers/gpu/drm/i915/i915_drv.h

@@ -340,14 +340,21 @@ struct drm_i915_file_private {
 
 	unsigned int bsd_engine;
 
-/* Client can have a maximum of 3 contexts banned before
+/*
- * it is denied of creating new contexts. As one context
+ * Every context ban increments per client ban score. Also
- * ban needs 4 consecutive hangs, and more if there is
+ * hangs in short succession increments ban score. If ban threshold
- * progress in between, this is a last resort stop gap measure
+ * is reached, client is considered banned and submitting more work
- * to limit the badly behaving clients access to gpu.
+ * will fail. This is a stop gap measure to limit the badly behaving
+ * clients access to gpu. Note that unbannable contexts never increment
+ * the client ban score.
  */
-#define I915_MAX_CLIENT_CONTEXT_BANS 3
+#define I915_CLIENT_SCORE_HANG_FAST	1
-	atomic_t context_bans;
+#define   I915_CLIENT_FAST_HANG_JIFFIES (60 * HZ)
+#define I915_CLIENT_SCORE_CONTEXT_BAN   3
+#define I915_CLIENT_SCORE_BANNED	9
+	/** ban_score: Accumulated score of all ctx bans and fast hangs. */
+	atomic_t ban_score;
+	unsigned long hang_timestamp;
 };
 
 /* Interface history:

drivers/gpu/drm/i915/i915_gem.c

@@ -2933,32 +2933,54 @@ 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;
+	bannable = i915_gem_context_is_bannable(ctx);
-	if (i915_gem_context_is_bannable(ctx)) {
+	score = atomic_add_return(CONTEXT_SCORE_GUILTY, &ctx->ban_score);
-		unsigned int score;
+	banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
 
-		score = atomic_add_return(CONTEXT_SCORE_GUILTY,
+	DRM_DEBUG_DRIVER("context %s: guilty %d, score %u, ban %s\n",
-					  &ctx->ban_score);
+			 ctx->name, atomic_read(&ctx->guilty_count),
-		banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
+			 score, yesno(banned && bannable));
 
-		DRM_DEBUG_DRIVER("context %s marked guilty (score %d) banned? %s\n",
+	/* Cool contexts don't accumulate client ban score */
-				 ctx->name, score, yesno(banned));
+	if (!bannable)
-	}
-	if (!banned)
 		return;
 
-	i915_gem_context_set_banned(ctx);
+	if (banned)
-	if (!IS_ERR_OR_NULL(ctx->file_priv)) {
+		i915_gem_context_set_banned(ctx);
-		atomic_inc(&ctx->file_priv->context_bans);
+
-		DRM_DEBUG_DRIVER("client %s has had %d context banned\n",
+	if (!IS_ERR_OR_NULL(ctx->file_priv))
-				 ctx->name, atomic_read(&ctx->file_priv->context_bans));
+		i915_gem_client_mark_guilty(ctx->file_priv, ctx);
-	}
 }
 
 static void i915_gem_context_mark_innocent(struct i915_gem_context *ctx)
@@ -5736,6 +5758,7 @@ 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)

drivers/gpu/drm/i915/i915_gem_context.c

@@ -652,7 +652,7 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv)
 
 static bool client_is_banned(struct drm_i915_file_private *file_priv)
 {
-	return atomic_read(&file_priv->context_bans) > I915_MAX_CLIENT_CONTEXT_BANS;
+	return atomic_read(&file_priv->ban_score) >= I915_CLIENT_SCORE_BANNED;
 }
 
 int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,