[PATCH 29/74] drm/i915: Allow userspace to request no-error-capture upon GPU hangs

[Chris Wilson]

igt likes to inject GPU hangs into its command streams. However, as we
expect these hangs, we don't actually want them recorded in the dmesg
output or stored in the i915_error_state (usually). To accomodate this
allow userspace to set a flag on the context that any hang emanating
from that context will not be recorded. We still do the error capture
(otherwise how do we find the guilty context and know its intent?) as
part of the reason for random GPU hang injection is to exercise the race
conditions between the error capture and normal execution.

v2: Split out the request->ringbuf error capture changes.
v3: Move the flag defines next to the intel_context->flags definition

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Acked-by: Daniel Vetter <daniel.vetter at ffwll.ch>
Reviewed-by: Dave Gordon <david.s.gordon at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h         |  6 ++++--
 drivers/gpu/drm/i915/i915_gem_context.c | 13 +++++++++++++
 drivers/gpu/drm/i915/i915_gpu_error.c   | 14 +++++++++-----
 include/uapi/drm/i915_drm.h             |  1 +
 4 files changed, 27 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 499003218100..d54e7daa7d6c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -462,6 +462,7 @@ struct drm_i915_error_state {
 	struct timeval time;
 
 	char error_msg[128];
+	bool simulated;
 	int iommu;
 	u32 reset_count;
 	u32 suspend_count;
@@ -821,7 +822,6 @@ struct i915_ctx_hang_stats {
 /* This must match up with the value previously used for execbuf2.rsvd1. */
 #define DEFAULT_CONTEXT_HANDLE 0
 
-#define CONTEXT_NO_ZEROMAP (1<<0)
 /**
  * struct intel_context - as the name implies, represents a context.
  * @ref: reference count.
@@ -846,13 +846,15 @@ struct intel_context {
 	int user_handle;
 	uint8_t remap_slice;
 	struct drm_i915_private *i915;
-	int flags;
 	struct drm_i915_file_private *file_priv;
 	struct i915_ctx_hang_stats hang_stats;
 	struct i915_hw_ppgtt *ppgtt;
 
 	/* Unique identifier for this context, used by the hw for tracking */
 	unsigned hw_id;
+	unsigned flags;
+#define CONTEXT_NO_ZEROMAP		(1<<0)
+#define CONTEXT_NO_ERROR_CAPTURE	(1<<1)
 
 	/* Legacy ring buffer submission */
 	struct {
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 2dcf18cfc809..1dfa46ec4e06 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -987,6 +987,9 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 		else
 			args->value = to_i915(dev)->ggtt.base.total;
 		break;
+	case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
+		args->value = !!(ctx->flags & CONTEXT_NO_ERROR_CAPTURE);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -1032,6 +1035,16 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 			ctx->flags |= args->value ? CONTEXT_NO_ZEROMAP : 0;
 		}
 		break;
+	case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
+		if (args->size) {
+			ret = -EINVAL;
+		} else {
+			if (args->value)
+				ctx->flags |= CONTEXT_NO_ERROR_CAPTURE;
+			else
+				ctx->flags &= ~CONTEXT_NO_ERROR_CAPTURE;
+		}
+		break;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 6c313563e77f..33e4f2531fe2 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1067,6 +1067,8 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 				rcu_read_unlock();
 			}
 
+			error->simulated |= request->ctx->flags & CONTEXT_NO_ERROR_CAPTURE;
+
 			rb = request->ringbuf;
 			error->ring[i].cpu_ring_head = rb->head;
 			error->ring[i].cpu_ring_tail = rb->tail;
@@ -1366,12 +1368,14 @@ void i915_capture_error_state(struct drm_i915_private *dev_priv,
 	i915_error_capture_msg(dev_priv, error, engine_mask, error_msg);
 	DRM_INFO("%s\n", error->error_msg);
 
-	spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
-	if (dev_priv->gpu_error.first_error == NULL) {
-		dev_priv->gpu_error.first_error = error;
-		error = NULL;
+	if (!error->simulated) {
+		spin_lock_irqsave(&dev_priv->gpu_error.lock, flags);
+		if (dev_priv->gpu_error.first_error == NULL) {
+			dev_priv->gpu_error.first_error = error;
+			error = NULL;
+		}
+		spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
 	}
-	spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
 
 	if (error) {
 		i915_error_state_free(&error->ref);
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index a5524cc95ff8..99095732ffb9 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1167,6 +1167,7 @@ struct drm_i915_gem_context_param {
 #define I915_CONTEXT_PARAM_BAN_PERIOD	0x1
 #define I915_CONTEXT_PARAM_NO_ZEROMAP	0x2
 #define I915_CONTEXT_PARAM_GTT_SIZE	0x3
+#define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE	0x4
 	__u64 value;
 };
 
-- 
2.8.1