From: John Harrison <John.C.Harrison@xxxxxxxxx>
Added trace points to the scheduler to track all the various events,
node state transitions and other interesting things that occur.
v2: Updated for new request completion tracking implementation.
Change-Id: I9886390cfc7897bc1faf50a104bc651d8baed8a5
For: VIZ-1587
Signed-off-by: John Harrison <John.C.Harrison@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +
drivers/gpu/drm/i915/i915_scheduler.c | 24 ++++
drivers/gpu/drm/i915/i915_trace.h | 190 +++++++++++++++++++++++++++++
drivers/gpu/drm/i915/intel_lrc.c | 2 +
4 files changed, 218 insertions(+)
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index a247d50..e748fd3 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1226,6 +1226,8 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
i915_gem_execbuffer_move_to_active(vmas, params->request);
+ trace_i915_gem_ring_queue(ring, params);
+
qe = container_of(params, typeof(*qe), params);
ret = i915_scheduler_queue_execbuffer(qe);
if (ret)
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index ddd21b2..098f69a 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -97,6 +97,8 @@ int i915_scheduler_queue_execbuffer(struct i915_scheduler_queue_entry *qe)
if (i915.scheduler_override & i915_so_direct_submit) {
int ret;
+ trace_i915_scheduler_queue(qe->params.ring, qe);
+
WARN_ON(qe->params.fence_wait &&
(!sync_fence_is_signaled(qe->params.fence_wait)));
@@ -248,6 +250,9 @@ int i915_scheduler_queue_execbuffer(struct i915_scheduler_queue_entry *qe)
not_flying = i915_scheduler_count_flying(scheduler, ring) <
scheduler->min_flying;
+ trace_i915_scheduler_queue(ring, node);
+ trace_i915_scheduler_node_state_change(ring, node);
+
spin_unlock_irqrestore(&scheduler->lock, flags);
if (not_flying)
@@ -275,6 +280,9 @@ static int i915_scheduler_fly_node(struct i915_scheduler_queue_entry *node)
node->status = i915_sqs_flying;
+ trace_i915_scheduler_fly(ring, node);
+ trace_i915_scheduler_node_state_change(ring, node);
+
if (!(scheduler->flags[ring->id] & i915_sf_interrupts_enabled)) {
bool success = true;
@@ -340,6 +348,8 @@ static void i915_scheduler_node_requeue(struct i915_scheduler_queue_entry *node)
node->status = i915_sqs_queued;
node->params.request->seqno = 0;
+ trace_i915_scheduler_unfly(node->params.ring, node);
+ trace_i915_scheduler_node_state_change(node->params.ring, node);
}
/* Give up on a popped node completely. For example, because it is causing the
@@ -350,6 +360,8 @@ static void i915_scheduler_node_kill(struct i915_scheduler_queue_entry *node)
BUG_ON(!I915_SQS_IS_FLYING(node));
node->status = i915_sqs_dead;
+ trace_i915_scheduler_unfly(node->params.ring, node);
+ trace_i915_scheduler_node_state_change(node->params.ring, node);
}
/*
@@ -369,6 +381,8 @@ bool i915_scheduler_notify_request(struct drm_i915_gem_request *req)
struct i915_scheduler_queue_entry *node = req->scheduler_qe;
unsigned long flags;
+ trace_i915_scheduler_landing(req);
+
if (!node)
return false;
@@ -382,6 +396,8 @@ bool i915_scheduler_notify_request(struct drm_i915_gem_request *req)
else
node->status = i915_sqs_complete;
+ trace_i915_scheduler_node_state_change(req->ring, node);
+
spin_unlock_irqrestore(&scheduler->lock, flags);
return true;
@@ -524,6 +540,8 @@ static int i915_scheduler_remove(struct intel_engine_cs *ring)
/* Launch more packets now? */
do_submit = (queued > 0) && (flying < scheduler->min_flying);
+ trace_i915_scheduler_remove(ring, min_seqno, do_submit);
+
spin_unlock_irqrestore(&scheduler->lock, flags);
if (!do_submit && list_empty(&remove))
@@ -538,6 +556,8 @@ static int i915_scheduler_remove(struct intel_engine_cs *ring)
node = list_first_entry(&remove, typeof(*node), link);
list_del(&node->link);
+ trace_i915_scheduler_destroy(ring, node);
+
if (node->params.fence_wait)
sync_fence_put(node->params.fence_wait);
@@ -952,6 +972,8 @@ static int i915_scheduler_pop_from_queue_locked(struct intel_engine_cs *ring,
INIT_LIST_HEAD(&best->link);
best->status = i915_sqs_popped;
+ trace_i915_scheduler_node_state_change(ring, best);
+
ret = 0;
} else {
/* Can only get here if:
@@ -1005,6 +1027,8 @@ static int i915_scheduler_pop_from_queue_locked(struct intel_engine_cs *ring,
spin_lock_irqsave(&scheduler->lock, *flags);
}
+ trace_i915_scheduler_pop_from_queue(ring, best);
+
*pop_node = best;
return ret;
}
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 76b08fa..73b0ee9 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -9,6 +9,7 @@
#include "i915_drv.h"
#include "intel_drv.h"
#include "intel_ringbuffer.h"
+#include "i915_scheduler.h"
#undef TRACE_SYSTEM
#define TRACE_SYSTEM i915
@@ -822,6 +823,195 @@ TRACE_EVENT(switch_mm,
__entry->dev, __entry->ring, __entry->to, __entry->vm)
);
+TRACE_EVENT(i915_scheduler_queue,
+ TP_PROTO(struct intel_engine_cs *ring,
+ struct i915_scheduler_queue_entry *node),
+ TP_ARGS(ring, node),
+
+ TP_STRUCT__entry(
+ __field(u32, ring)
+ __field(u32, uniq)
+ __field(u32, seqno)
+ ),
+
+ TP_fast_assign(
+ __entry->ring = ring->id;
+ __entry->uniq = node ? node->params.request->uniq : 0;
+ __entry->seqno = node ? node->params.request->seqno : 0;
+ ),
+
+ TP_printk("ring=%d, uniq=%d, seqno=%d",
+ __entry->ring, __entry->uniq, __entry->seqno)
+);
+
+TRACE_EVENT(i915_scheduler_fly,
+ TP_PROTO(struct intel_engine_cs *ring,
+ struct i915_scheduler_queue_entry *node),
+ TP_ARGS(ring, node),
+
+ TP_STRUCT__entry(
+ __field(u32, ring)
+ __field(u32, uniq)
+ __field(u32, seqno)
+ ),
+
+ TP_fast_assign(
+ __entry->ring = ring->id;
+ __entry->uniq = node ? node->params.request->uniq : 0;
+ __entry->seqno = node ? node->params.request->seqno : 0;
+ ),
+
+ TP_printk("ring=%d, uniq=%d, seqno=%d",
+ __entry->ring, __entry->uniq, __entry->seqno)
+);
+
+TRACE_EVENT(i915_scheduler_unfly,
+ TP_PROTO(struct intel_engine_cs *ring,
+ struct i915_scheduler_queue_entry *node),
+ TP_ARGS(ring, node),
+
+ TP_STRUCT__entry(
+ __field(u32, ring)
+ __field(u32, uniq)
+ __field(u32, seqno)
+ ),
+
+ TP_fast_assign(
+ __entry->ring = ring->id;
+ __entry->uniq = node ? node->params.request->uniq : 0;
+ __entry->seqno = node ? node->params.request->seqno : 0;
+ ),
+
+ TP_printk("ring=%d, uniq=%d, seqno=%d",
+ __entry->ring, __entry->uniq, __entry->seqno)
+);
+
+TRACE_EVENT(i915_scheduler_landing,
+ TP_PROTO(struct drm_i915_gem_request *req),
+ TP_ARGS(req),
+
+ TP_STRUCT__entry(
+ __field(u32, ring)
+ __field(u32, uniq)
+ __field(u32, seqno)
+ __field(u32, status)
+ ),
+
+ TP_fast_assign(
+ __entry->ring = req->ring->id;
+ __entry->uniq = req->uniq;
+ __entry->seqno = req->seqno;
+ __entry->status = req->scheduler_qe ? req->scheduler_qe->status : ~0U;
+ ),
+
+ TP_printk("ring=%d, uniq=%d, seqno=%d, status=%d",
+ __entry->ring, __entry->uniq, __entry->seqno, __entry->status)
+);
+
+TRACE_EVENT(i915_scheduler_remove,
+ TP_PROTO(struct intel_engine_cs *ring,
+ u32 min_seqno, bool do_submit),
+ TP_ARGS(ring, min_seqno, do_submit),
+
+ TP_STRUCT__entry(
+ __field(u32, ring)
+ __field(u32, min_seqno)
+ __field(bool, do_submit)
+ ),
+
+ TP_fast_assign(
+ __entry->ring = ring->id;
+ __entry->min_seqno = min_seqno;
+ __entry->do_submit = do_submit;
+ ),
+
+ TP_printk("ring=%d, min_seqno = %d, do_submit=%d",
+ __entry->ring, __entry->min_seqno, __entry->do_submit)
+);
+
+TRACE_EVENT(i915_scheduler_destroy,
+ TP_PROTO(struct intel_engine_cs *ring,
+ struct i915_scheduler_queue_entry *node),
+ TP_ARGS(ring, node),
+
+ TP_STRUCT__entry(
+ __field(u32, ring)
+ __field(u32, uniq)
+ __field(u32, seqno)
+ ),
+
+ TP_fast_assign(
+ __entry->ring = ring->id;
+ __entry->uniq = node ? node->params.request->uniq : 0;
+ __entry->seqno = node ? node->params.request->seqno : 0;
+ ),
+
+ TP_printk("ring=%d, uniq=%d, seqno=%d",
+ __entry->ring, __entry->uniq, __entry->seqno)
+);
+
+TRACE_EVENT(i915_scheduler_pop_from_queue,
+ TP_PROTO(struct intel_engine_cs *ring,
+ struct i915_scheduler_queue_entry *node),
+ TP_ARGS(ring, node),
+
+ TP_STRUCT__entry(
+ __field(u32, ring)
+ __field(u32, uniq)
+ __field(u32, seqno)
+ ),
+
+ TP_fast_assign(
+ __entry->ring = ring->id;
+ __entry->uniq = node ? node->params.request->uniq : 0;
+ __entry->seqno = node ? node->params.request->seqno : 0;
+ ),
+
+ TP_printk("ring=%d, uniq=%d, seqno=%d",
+ __entry->ring, __entry->uniq, __entry->seqno)
+);
+
+TRACE_EVENT(i915_scheduler_node_state_change,
+ TP_PROTO(struct intel_engine_cs *ring,
+ struct i915_scheduler_queue_entry *node),
+ TP_ARGS(ring, node),
+
+ TP_STRUCT__entry(
+ __field(u32, ring)
+ __field(u32, uniq)
+ __field(u32, seqno)
+ __field(u32, status)
+ ),
+
+ TP_fast_assign(
+ __entry->ring = ring->id;
+ __entry->uniq = node ? node->params.request->uniq : 0;
+ __entry->seqno = node->params.request->seqno;
+ __entry->status = node->status;
+ ),
+
+ TP_printk("ring=%d, uniq=%d, seqno=%d, status=%d",
+ __entry->ring, __entry->uniq, __entry->seqno, __entry->status)
+);
+
+TRACE_EVENT(i915_gem_ring_queue,
+ TP_PROTO(struct intel_engine_cs *ring,
+ struct i915_execbuffer_params *params),
+ TP_ARGS(ring, params),
+
+ TP_STRUCT__entry(
+ __field(u32, ring)
+ __field(u32, seqno)
+ ),
+
+ TP_fast_assign(
+ __entry->ring = ring->id;
+ __entry->seqno = params->request->seqno;
+ ),
+
+ TP_printk("ring=%d, seqno=%d", __entry->ring, __entry->seqno)
+);
+
#endif /* _I915_TRACE_H_ */
/* This part must be outside protection */
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 41e20ba..6c01f6c 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -910,6 +910,8 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
i915_gem_execbuffer_move_to_active(vmas, params->request);
+ trace_i915_gem_ring_queue(ring, params);
+
qe = container_of(params, typeof(*qe), params);
ret = i915_scheduler_queue_execbuffer(qe);
if (ret)
--
1.9.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
