[Intel-gfx] [PATCH 5/6] drm/i915: Add per client max context ban limit

[Mika Kuoppala]

If we have a bad client submitting unfavourably across different
contexts, creating new ones, the per context scoring of badness
doesn't remove the root cause, the offending client.
To counter, keep track of per client context bans. Deny access if
client is responsible for more than 3 context bans in
it's lifetime.

v2: move ban check to context create ioctl (Chris)
v3: add commentary about hangs needed to reach client ban (Chris)

Cc: Chris Wilson <chris at chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris at chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h         | 10 ++++++++++
 drivers/gpu/drm/i915/i915_gem.c         | 14 ++++++++++++++
 drivers/gpu/drm/i915/i915_gem_context.c | 13 +++++++++++++
 drivers/gpu/drm/i915/i915_gpu_error.c   | 10 ++++++----
 4 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 837abdf..304e4c9 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -416,6 +416,15 @@ struct drm_i915_file_private {
 	} rps;
 
 	unsigned int bsd_engine;
+
+/* Client can have a maximum of 3 contexts banned before
+ * it is denied of creating new contexts. As one context
+ * ban needs 4 consecutive hangs, and more if there is
+ * progress in between, this is a last resort stop gap measure
+ * to limit the badly behaving clients access to gpu.
+ */
+#define I915_MAX_CLIENT_CONTEXT_BANS 3
+	int context_bans;
 };
 
 /* Used by dp and fdi links */
@@ -872,6 +881,7 @@ struct drm_i915_error_state {
 
 		pid_t pid;
 		char comm[TASK_COMM_LEN];
+		int context_bans;
 	} engine[I915_NUM_ENGINES];
 
 	struct drm_i915_error_buffer {
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 734b270..dd015bc 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2644,6 +2644,20 @@ static void i915_gem_context_mark_guilty(struct i915_gem_context *ctx)
 
 	hs->banned = i915_context_is_banned(ctx);
 	hs->batch_active++;
+
+	DRM_DEBUG_DRIVER("context %s marked guilty (score %d) banned? %s\n",
+			 ctx->name, hs->ban_score, yesno(hs->banned));
+
+	if (!ctx->file_priv)
+		return;
+
+	if (hs->banned) {
+		ctx->file_priv->context_bans++;
+
+		DRM_DEBUG_DRIVER("client %s has has %d context banned\n",
+				 ctx->name,
+				 ctx->file_priv->context_bans);
+	}
 }
 
 static void i915_gem_context_mark_innocent(struct i915_gem_context *ctx)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index bc1b232..4f88f03 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -1003,6 +1003,11 @@ static bool contexts_enabled(struct drm_device *dev)
 	return i915.enable_execlists || to_i915(dev)->hw_context_size;
 }
 
+static bool client_is_banned(struct drm_i915_file_private *file_priv)
+{
+	return file_priv->context_bans > I915_MAX_CLIENT_CONTEXT_BANS;
+}
+
 int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file)
 {
@@ -1017,6 +1022,14 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 	if (args->pad != 0)
 		return -EINVAL;
 
+	if (client_is_banned(file_priv)) {
+		DRM_DEBUG("client %s[%d] banned from creating ctx\n",
+			  current->comm,
+			  pid_nr(get_task_pid(current, PIDTYPE_PID)));
+
+		return -EIO;
+	}
+
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index fa988a0..af4f0ef 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -538,10 +538,11 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	for (i = 0; i < ARRAY_SIZE(error->engine); i++) {
 		if (error->engine[i].hangcheck_stalled &&
 		    error->engine[i].pid != -1) {
-			err_printf(m, "Active process (on ring %s): %s [%d]\n",
+			err_printf(m, "Active process (on ring %s): %s [%d], context bans %d\n",
 				   engine_str(i),
 				   error->engine[i].comm,
-				   error->engine[i].pid);
+				   error->engine[i].pid,
+				   error->engine[i].context_bans);
 		}
 	}
 	err_printf(m, "Reset count: %u\n", error->reset_count);
@@ -632,9 +633,10 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 		if (obj) {
 			err_puts(m, dev_priv->engine[i]->name);
 			if (ee->pid != -1)
-				err_printf(m, " (submitted by %s [%d])",
+				err_printf(m, " (submitted by %s [%d], bans %d)",
 					   ee->comm,
-					   ee->pid);
+					   ee->pid,
+					   ee->context_bans);
 			err_printf(m, " --- gtt_offset = 0x%08x %08x\n",
 				   upper_32_bits(obj->gtt_offset),
 				   lower_32_bits(obj->gtt_offset));
-- 
2.7.4