Francisco Jerez <currojerez@xxxxxxxxxx> writes:
> Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> 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 <chris@xxxxxxxxxxxxxxxxxx>
>> Cc: Francisco Jerez <currojerez@xxxxxxxxxx>
>> Cc: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxxxxxxxx>
>> ---
>> 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.
>
This didn't seem to help (together with your other suggestion to move
the overload accounting to __execlists_schedule_in/out). And it makes
the current -5% SynMark OglMultithread regression with my series go down
to -10%. My previous suggestion of moving the
intel_gt_pm_active_begin() call to process_csb() when the submission is
ACK'ed by the hardware does seem to help (and it roughly halves the
OglMultithread regression), possibly because that way we're able to
determine whether the first context was actually overlapping at the
point that the second was received by the hardware -- I haven't tested
it extensively yet though.
>> + /* 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
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Attachment:
signature.asc
Description: PGP signature
_______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
