drm/i915: Individual request cancellation

Currently, we cancel outstanding requests within a context when the
context is closed. We may also want to cancel individual requests using
the same graceful preemption mechanism.

v2 (Tvrtko):
 * Cancel waiters carefully considering no timeline lock and RCU.
 * Fixed selftests.

v3 (Tvrtko):
 * Remove error propagation to waiters for now.

v4 (Tvrtko):
 * Rebase for extracted i915_request_active_engine. (Matt)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
[danvet: Resolve conflict because intel_engine_flush_scheduler is
still called intel_engine_flush_submission]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210324121335.2307063-3-tvrtko.ursulin@linux.intel.com

1 files changed, 30 insertions, 3 deletions

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index d23186016fc6..a031b86f8508 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -33,7 +33,10 @@
 #include "gem/i915_gem_context.h"
 #include "gt/intel_breadcrumbs.h"
 #include "gt/intel_context.h"
+#include "gt/intel_engine.h"
+#include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_gpu_commands.h"
+#include "gt/intel_reset.h"
 #include "gt/intel_ring.h"
 #include "gt/intel_rps.h"
 
@@ -542,20 +545,22 @@ void __i915_request_skip(struct i915_request *rq)
 	rq->infix = rq->postfix;
 }
 
-void i915_request_set_error_once(struct i915_request *rq, int error)
+bool i915_request_set_error_once(struct i915_request *rq, int error)
 {
 	int old;
 
 	GEM_BUG_ON(!IS_ERR_VALUE((long)error));
 
 	if (i915_request_signaled(rq))
-		return;
+		return false;
 
 	old = READ_ONCE(rq->fence.error);
 	do {
 		if (fatal_error(old))
-			return;
+			return false;
 	} while (!try_cmpxchg(&rq->fence.error, &old, error));
+
+	return true;
 }
 
 void i915_request_mark_eio(struct i915_request *rq)
@@ -722,6 +727,28 @@ void i915_request_unsubmit(struct i915_request *request)
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
 
+static void __cancel_request(struct i915_request *rq)
+{
+	struct intel_engine_cs *engine = NULL;
+
+	i915_request_active_engine(rq, &engine);
+
+	if (engine && intel_engine_pulse(engine))
+		intel_gt_handle_error(engine->gt, engine->mask, 0,
+				      "request cancellation by %s",
+				      current->comm);
+}
+
+void i915_request_cancel(struct i915_request *rq, int error)
+{
+	if (!i915_request_set_error_once(rq, error))
+		return;
+
+	set_bit(I915_FENCE_FLAG_SENTINEL, &rq->fence.flags);
+
+	__cancel_request(rq);
+}
+
 static int __i915_sw_fence_call
 submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 {