drm/i915/gt: Cancel submitted requests upon context reset

Since we process schedule-in of a context after submitting the request,
if we decide to reset the context at that time, we also have to cancel
the requets we have marked for submission.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201230220028.17089-1-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index f08ba2d..33c5bba 100644 (file)
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -215,22 +215,32 @@ static void mark_eio(struct i915_request *rq)
 }
 
 static struct i915_request *
-active_request(const struct intel_timeline * const tl, struct i915_request *rq)
+__active_request(const struct intel_timeline * const tl,
+                struct i915_request *rq,
+                int error)
 {
        struct i915_request *active = rq;
 
-       rcu_read_lock();
-       list_for_each_entry_continue_reverse(rq, &tl->requests, link) {
+       list_for_each_entry_from_reverse(rq, &tl->requests, link) {
                if (__i915_request_is_complete(rq))
                        break;
 
+               if (error) {
+                       i915_request_set_error_once(rq, error);
+                       __i915_request_skip(rq);
+               }
                active = rq;
        }
-       rcu_read_unlock();
 
        return active;
 }
 
+static struct i915_request *
+active_request(const struct intel_timeline * const tl, struct i915_request *rq)
+{
+       return __active_request(tl, rq, 0);
+}
+
 static inline void
 ring_set_paused(const struct intel_engine_cs *engine, int state)
 {
@@ -487,14 +497,14 @@ static void reset_active(struct i915_request *rq,
         * remain correctly ordered. And we defer to __i915_request_submit()
         * so that all asynchronous waits are correctly handled.
         */
-       ENGINE_TRACE(engine, "{ rq=%llx:%lld }\n",
+       ENGINE_TRACE(engine, "{ reset rq=%llx:%lld }\n",
                     rq->fence.context, rq->fence.seqno);
 
        /* On resubmission of the active request, payload will be scrubbed */
        if (__i915_request_is_complete(rq))
                head = rq->tail;
        else
-               head = active_request(ce->timeline, rq)->head;
+               head = __active_request(ce->timeline, rq, -EIO)->head;
        head = intel_ring_wrap(ce->ring, head);
 
        /* Scrub the context image to prevent replaying the previous batch */

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 6578faf..ad3b6a4 100644 (file)
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -490,6 +490,8 @@ void __i915_request_skip(struct i915_request *rq)
        if (rq->infix == rq->postfix)
                return;
 
+       RQ_TRACE(rq, "error: %d\n", rq->fence.error);
+
        /*
         * As this request likely depends on state from the lost
         * context, clear out all the user operations leaving the