We have a hole in our busy-stat accounting if the pmu is enabled during
a long running batch, the pmu will not start accumulating busy-time
until the next context switch. This then fails tests that are only
sampling a single batch.

v2: Count each active port just once (context in/out events are only on
the first and last assigment to a port).

Testcase: igt/perf_pmu/busy-start
Testcase: igt/perf_pmu/busy-double-start
Signed-off-by: Chris Wilson <[email protected]>
Cc: Tvrtko Ursulin <[email protected]>
---
 drivers/gpu/drm/i915/intel_engine_cs.c  | 10 +++++++++-
 drivers/gpu/drm/i915/intel_ringbuffer.h |  2 +-
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c 
b/drivers/gpu/drm/i915/intel_engine_cs.c
index 6bb51a502b8b..3a11602e60c7 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1951,8 +1951,16 @@ int intel_enable_engine_stats(struct intel_engine_cs 
*engine)
        spin_lock_irqsave(&engine->stats.lock, flags);
        if (engine->stats.enabled == ~0)
                goto busy;
-       if (engine->stats.enabled++ == 0)
+       if (engine->stats.enabled++ == 0) {
                engine->stats.enabled_at = ktime_get();
+
+               /* XXX submission method oblivious? */
+               engine->stats.active =
+                       port_isset(&engine->execlists.port[1]) +
+                       port_isset(&engine->execlists.port[0]);
+               if (engine->stats.active)
+                       engine->stats.start = engine->stats.enabled_at;
+       }
        spin_unlock_irqrestore(&engine->stats.lock, flags);
 
        return 0;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h 
b/drivers/gpu/drm/i915/intel_ringbuffer.h
index c5ff203e42d6..37cf665692e5 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -225,7 +225,7 @@ struct intel_engine_execlists {
 #define port_pack(rq, count) ptr_pack_bits(rq, count, EXECLIST_COUNT_BITS)
 #define port_unpack(p, count) ptr_unpack_bits((p)->request_count, count, 
EXECLIST_COUNT_BITS)
 #define port_set(p, packed) ((p)->request_count = (packed))
-#define port_isset(p) ((p)->request_count)
+#define port_isset(p) (((p)->request_count) != NULL)
 #define port_index(p, execlists) ((p) - (execlists)->port)
 
                /**
-- 
2.15.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Reply via email to