Record the initial active element we use when building the next ELSP
submission, so that we can compare against it latter to see if there's
no change.
Fixes: 44d0a9c05bc0 ("drm/i915/execlists: Skip redundant resubmission")
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/gt/intel_lrc.c | 17 ++++++++++++-----
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 6266ef2ae6a0..a9d77b0e4e27 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1674,16 +1674,21 @@ static void virtual_xfer_breadcrumbs(struct virtual_engine *ve,
}
static struct i915_request *
-last_active(const struct intel_engine_execlists *execlists)
+__last_active(const struct intel_engine_execlists *execlists,
+ struct i915_request * const *last)
{
- struct i915_request * const *last = READ_ONCE(execlists->active);
-
while (*last && i915_request_completed(*last))
last++;
return *last;
}
+static struct i915_request *
+last_active(const struct intel_engine_execlists *execlists)
+{
+ return __last_active(execlists, READ_ONCE(execlists->active));
+}
+
#define for_each_waiter(p__, rq__) \
list_for_each_entry_lockless(p__, \
&(rq__)->sched.waiters_list, \
@@ -1852,6 +1857,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
struct intel_engine_execlists * const execlists = &engine->execlists;
struct i915_request **port = execlists->pending;
struct i915_request ** const last_port = port + execlists->port_mask;
+ struct i915_request * const *active;
struct i915_request *last;
struct rb_node *rb;
bool submit = false;
@@ -1906,7 +1912,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
* i.e. we will retrigger preemption following the ack in case
* of trouble.
*/
- last = last_active(execlists);
+ active = READ_ONCE(execlists->active);
+ last = __last_active(execlists, active);
if (last) {
if (need_preempt(engine, last, rb)) {
ENGINE_TRACE(engine,
@@ -2191,7 +2198,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
* Skip if we ended up with exactly the same set of requests,
* e.g. trying to timeslice a pair of ordered contexts
*/
- if (!memcmp(execlists->active, execlists->pending,
+ if (!memcmp(active, execlists->pending,
(port - execlists->pending + 1) * sizeof(*port))) {
do
execlists_schedule_out(fetch_and_zero(port));
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
