[Intel-gfx] [PATCH 16/24] drm/i915/gt: Mark context->active_count as protected by timeline->mutex

[Chris Wilson]

We use timeline->mutex to protect modifications to
context->active_count, and the associated enable/disable callbacks.
Due to complications with engine-pm barrier there is a path where we used
a "superlock" to provide serialised protect and so could not
unconditionally assert with lockdep that it was always held. However,
we can mark the mutex as taken (noting that we may be nested underneath
ourselves) which means we can be reassured the right timeline->mutex is
always treated as held and let lockdep roam free.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/gt/intel_context.h       |  3 +++
 drivers/gpu/drm/i915/gt/intel_context_types.h |  2 +-
 drivers/gpu/drm/i915/gt/intel_engine_pm.c     | 12 ++++++++++++
 drivers/gpu/drm/i915/gt/intel_timeline.c      |  4 ++++
 4 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index 8429a97a3911..02bab98f2c72 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -88,17 +88,20 @@ void intel_context_exit_engine(struct intel_context *ce);
 
 static inline void intel_context_enter(struct intel_context *ce)
 {
+	lockdep_assert_held(&ce->ring->timeline->mutex);
 	if (!ce->active_count++)
 		ce->ops->enter(ce);
 }
 
 static inline void intel_context_mark_active(struct intel_context *ce)
 {
+	lockdep_assert_held(&ce->ring->timeline->mutex);
 	++ce->active_count;
 }
 
 static inline void intel_context_exit(struct intel_context *ce)
 {
+	lockdep_assert_held(&ce->ring->timeline->mutex);
 	GEM_BUG_ON(!ce->active_count);
 	if (!--ce->active_count)
 		ce->ops->exit(ce);
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index 4c0e211c715d..c00419e38a77 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -53,7 +53,7 @@ struct intel_context {
 	u32 *lrc_reg_state;
 	u64 lrc_desc;
 
-	unsigned int active_count; /* notionally protected by timeline->mutex */
+	unsigned int active_count; /* protected by timeline->mutex */
 
 	atomic_t pin_count;
 	struct mutex pin_mutex; /* guards pinning and associated on-gpuing */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 76c828d11b05..1218b7d53b88 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -59,6 +59,16 @@ void intel_engine_park(struct intel_engine_cs *engine)
 	}
 }
 
+static inline void __timeline_mark_lock(struct intel_context *ce)
+{
+	mutex_acquire(&ce->ring->timeline->mutex.dep_map, 2, 0, _THIS_IP_);
+}
+
+static inline void __timeline_mark_unlock(struct intel_context *ce)
+{
+	mutex_release(&ce->ring->timeline->mutex.dep_map, 0, _THIS_IP_);
+}
+
 static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 {
 	struct i915_request *rq;
@@ -83,6 +93,7 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	 * retiring the last request, thus all rings should be empty and
 	 * all timelines idle.
 	 */
+	__timeline_mark_lock(engine->kernel_context);
 	rq = __i915_request_create(engine->kernel_context, GFP_NOWAIT);
 	if (IS_ERR(rq))
 		/* Context switch failed, hope for the best! Maybe reset? */
@@ -94,6 +105,7 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 
 	i915_request_add_barriers(rq);
 	__i915_request_commit(rq);
+	__timeline_mark_unlock(engine->kernel_context);
 
 	return false;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 7b476cd55dac..eafd94d5e211 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -338,6 +338,8 @@ void intel_timeline_enter(struct intel_timeline *tl)
 {
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
 
+	lockdep_assert_held(&tl->mutex);
+
 	GEM_BUG_ON(!atomic_read(&tl->pin_count));
 	if (tl->active_count++)
 		return;
@@ -352,6 +354,8 @@ void intel_timeline_exit(struct intel_timeline *tl)
 {
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
 
+	lockdep_assert_held(&tl->mutex);
+
 	GEM_BUG_ON(!tl->active_count);
 	if (--tl->active_count)
 		return;
-- 
2.22.0