Chris Wilson <[email protected]> writes: > We dropped calling process_csb prior to handling direct submission in > order to avoid the nesting of spinlocks and lift process_csb() and the > majority of the tasklet out of irq-off. However, we do want to avoid > ksoftirqd latency in the fast path, so try and pull the interrupt-bh > local to direct submission if we can acquire the tasklet's lock. > > v2: Tweak the balance to avoid over submitting lite-restores > > Signed-off-by: Chris Wilson <[email protected]> > Cc: Francisco Jerez <[email protected]> > Cc: Tvrtko Ursulin <[email protected]> > --- > drivers/gpu/drm/i915/gt/intel_lrc.c | 44 ++++++++++++++++++++------ > drivers/gpu/drm/i915/gt/selftest_lrc.c | 2 +- > 2 files changed, 36 insertions(+), 10 deletions(-) > > diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c > b/drivers/gpu/drm/i915/gt/intel_lrc.c > index f09dd87324b9..dceb65a0088f 100644 > --- a/drivers/gpu/drm/i915/gt/intel_lrc.c > +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c > @@ -2884,17 +2884,17 @@ static void queue_request(struct intel_engine_cs > *engine, > set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags); > } > > -static void __submit_queue_imm(struct intel_engine_cs *engine) > +static bool pending_csb(const struct intel_engine_execlists *el) > { > - struct intel_engine_execlists * const execlists = &engine->execlists; > + return READ_ONCE(*el->csb_write) != READ_ONCE(el->csb_head); > +} > > - if (reset_in_progress(execlists)) > - return; /* defer until we restart the engine following reset */ > +static bool skip_lite_restore(struct intel_engine_execlists *el, > + const struct i915_request *rq) > +{ > + struct i915_request *inflight = execlists_active(el); > > - if (execlists->tasklet.func == execlists_submission_tasklet) > - __execlists_submission_tasklet(engine); > - else > - tasklet_hi_schedule(&execlists->tasklet); > + return inflight && inflight->context == rq->context; > } > > static void submit_queue(struct intel_engine_cs *engine, > @@ -2905,8 +2905,34 @@ static void submit_queue(struct intel_engine_cs > *engine, > if (rq_prio(rq) <= execlists->queue_priority_hint) > return; > > + if (reset_in_progress(execlists)) > + return; /* defer until we restart the engine following reset */ > + > + /* > + * Suppress immediate lite-restores, leave that to the tasklet. > + * > + * However, we leave the queue_priority_hint unset so that if we do > + * submit a second context, we push that into ELSP[1] immediately. > + */ > + if (skip_lite_restore(execlists, rq)) > + return; > + Why do you need to treat lite-restore specially here?
Anyway, trying this out now in combination with my patches now.
> + /* Hopefully we clear execlists->pending[] to let us through */
> + if (execlists->pending[0] && tasklet_trylock(&execlists->tasklet)) {
> + process_csb(engine);
> + tasklet_unlock(&execlists->tasklet);
> + if (skip_lite_restore(execlists, rq))
> + return;
> + }
> +
> execlists->queue_priority_hint = rq_prio(rq);
> - __submit_queue_imm(engine);
> + __execlists_submission_tasklet(engine);
> +
> + /* Try and pull an interrupt-bh queued on another CPU to here */
> + if (pending_csb(execlists) && tasklet_trylock(&execlists->tasklet)) {
> + process_csb(engine);
> + tasklet_unlock(&execlists->tasklet);
> + }
> }
>
> static bool ancestor_on_hold(const struct intel_engine_cs *engine,
> diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c
> b/drivers/gpu/drm/i915/gt/selftest_lrc.c
> index 6f06ba750a0a..c5c4b07a7d5f 100644
> --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
> +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
> @@ -1028,7 +1028,7 @@ static int live_timeslice_rewind(void *arg)
> if (IS_ERR(rq[1]))
> goto err;
>
> - err = wait_for_submit(engine, rq[1], HZ / 2);
> + err = wait_for_submit(engine, rq[0], HZ / 2);
> if (err) {
> pr_err("%s: failed to submit first context\n",
> engine->name);
> --
> 2.20.1
signature.asc
Description: PGP signature
_______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
