Commit d78d3343 authored by Chris Wilson's avatar Chris Wilson

drm/i915/execlists: Move the assertion we have the rpm wakeref down

There's a race between idling the engine and finishing off the last
tasklet (as we may kick the tasklets after declaring an individual
engine idle). However, since we do not need to access the device until
we try to submit to the ELSP register (processing the CSB just requires
normal CPU access to the HWSP, and when idle we should not need to
submit!) we can defer the assertion unto that point. The assertion is
still useful as it does verify that we do hold the longterm GT wakeref
taken from request allocation until request completion.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107274
Fixes: 9512f985 ("drm/i915/execlists: Direct submission of new requests (avoid tasklet/ksoftirqd)")
Signed-off-by: default avatarChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: default avatarTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180719075029.28643-1-chris@chris-wilson.co.uk
parent 46b1063f
...@@ -452,6 +452,16 @@ static void execlists_submit_ports(struct intel_engine_cs *engine) ...@@ -452,6 +452,16 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
struct execlist_port *port = execlists->port; struct execlist_port *port = execlists->port;
unsigned int n; unsigned int n;
/*
* We can skip acquiring intel_runtime_pm_get() here as it was taken
* on our behalf by the request (see i915_gem_mark_busy()) and it will
* not be relinquished until the device is idle (see
* i915_gem_idle_work_handler()). As a precaution, we make sure
* that all ELSP are drained i.e. we have processed the CSB,
* before allowing ourselves to idle and calling intel_runtime_pm_put().
*/
GEM_BUG_ON(!engine->i915->gt.awake);
/* /*
* ELSQ note: the submit queue is not cleared after being submitted * ELSQ note: the submit queue is not cleared after being submitted
* to the HW so we need to make sure we always clean it up. This is * to the HW so we need to make sure we always clean it up. This is
...@@ -1043,16 +1053,6 @@ static void __execlists_submission_tasklet(struct intel_engine_cs *const engine) ...@@ -1043,16 +1053,6 @@ static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
{ {
lockdep_assert_held(&engine->timeline.lock); lockdep_assert_held(&engine->timeline.lock);
/*
* We can skip acquiring intel_runtime_pm_get() here as it was taken
* on our behalf by the request (see i915_gem_mark_busy()) and it will
* not be relinquished until the device is idle (see
* i915_gem_idle_work_handler()). As a precaution, we make sure
* that all ELSP are drained i.e. we have processed the CSB,
* before allowing ourselves to idle and calling intel_runtime_pm_put().
*/
GEM_BUG_ON(!engine->i915->gt.awake);
process_csb(engine); process_csb(engine);
if (!execlists_is_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT)) if (!execlists_is_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT))
execlists_dequeue(engine); execlists_dequeue(engine);
...@@ -1073,10 +1073,7 @@ static void execlists_submission_tasklet(unsigned long data) ...@@ -1073,10 +1073,7 @@ static void execlists_submission_tasklet(unsigned long data)
engine->execlists.active); engine->execlists.active);
spin_lock_irqsave(&engine->timeline.lock, flags); spin_lock_irqsave(&engine->timeline.lock, flags);
if (engine->i915->gt.awake) /* we may be delayed until after we idle! */
__execlists_submission_tasklet(engine); __execlists_submission_tasklet(engine);
spin_unlock_irqrestore(&engine->timeline.lock, flags); spin_unlock_irqrestore(&engine->timeline.lock, flags);
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment