Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> writes:
> If we receive the error interrupt before the CS interrupt, we may find
> ourselves without an active request to reset, skipping the GPU reset.
> All because the attempt to reset was too early.
>
With the tracing, we will see the the out of sync situations
so
Reviewed-by: Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx>
> Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
> ---
> drivers/gpu/drm/i915/gt/intel_lrc.c | 41 ++++++++++++++++++++++++++++-
> 1 file changed, 40 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
> index 3479cda37fdc..f028114714cd 100644
> --- a/drivers/gpu/drm/i915/gt/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
> @@ -2804,6 +2804,45 @@ static struct execlists_capture *capture_regs(struct intel_engine_cs *engine)
> return NULL;
> }
>
> +static struct i915_request *
> +active_context(struct intel_engine_cs *engine, u32 ccid)
> +{
> + const struct intel_engine_execlists * const el = &engine->execlists;
> + struct i915_request * const *port, *rq;
> +
> + /*
> + * Use the most recent result from process_csb(), but just in case
> + * we trigger an error (via interrupt) before the first CS event has
> + * been written, peek at the next submission.
> + */
> +
> + for (port = el->active; (rq = *port); port++) {
> + if (upper_32_bits(rq->context->lrc_desc) == ccid) {
> + ENGINE_TRACE(engine,
> + "ccid found at active:%zd\n",
> + port - el->active);
> + return rq;
> + }
> + }
> +
> + for (port = el->pending; (rq = *port); port++) {
> + if (upper_32_bits(rq->context->lrc_desc) == ccid) {
> + ENGINE_TRACE(engine,
> + "ccid found at pending:%zd\n",
> + port - el->pending);
> + return rq;
> + }
> + }
> +
> + ENGINE_TRACE(engine, "ccid:%x not found\n", ccid);
> + return NULL;
> +}
> +
> +static u32 active_ccid(struct intel_engine_cs *engine)
> +{
> + return ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI);
> +}
> +
> static bool execlists_capture(struct intel_engine_cs *engine)
> {
> struct execlists_capture *cap;
> @@ -2821,7 +2860,7 @@ static bool execlists_capture(struct intel_engine_cs *engine)
> return true;
>
> spin_lock_irq(&engine->active.lock);
> - cap->rq = execlists_active(&engine->execlists);
> + cap->rq = active_context(engine, active_ccid(engine));
> if (cap->rq) {
> cap->rq = active_request(cap->rq->context->timeline, cap->rq);
> cap->rq = i915_request_get_rcu(cap->rq);
> --
> 2.20.1
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
