[Intel-gfx] [PATCH 07/33] drm/i915: Move active request tracking to a vfunc
Move active request tracking to a backend vfunc rather than assuming all
backends want to do this in the manner. In the of case execlists /
ring submission the tracking is on the physical engine while with GuC
submission it is on the context.
Signed-off-by: Matthew Brost
Reviewed-by: John Harrison
---
drivers/gpu/drm/i915/gt/intel_context.c | 3 ++
drivers/gpu/drm/i915/gt/intel_context_types.h | 7
drivers/gpu/drm/i915/gt/intel_engine_types.h | 6 +++
.../drm/i915/gt/intel_execlists_submission.c | 40 ++
.../gpu/drm/i915/gt/intel_ring_submission.c | 22 ++
drivers/gpu/drm/i915/gt/mock_engine.c | 30 ++
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 33 +++
drivers/gpu/drm/i915/i915_request.c | 41 ++-
drivers/gpu/drm/i915/i915_request.h | 2 +
9 files changed, 147 insertions(+), 37 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c
b/drivers/gpu/drm/i915/gt/intel_context.c
index baa05fddd690..0bf4a13e9759 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -393,6 +393,9 @@ intel_context_init(struct intel_context *ce, struct
intel_engine_cs *engine)
spin_lock_init(>guc_state.lock);
INIT_LIST_HEAD(>guc_state.fences);
+ spin_lock_init(>guc_active.lock);
+ INIT_LIST_HEAD(>guc_active.requests);
+
ce->guc_id = GUC_INVALID_LRC_ID;
INIT_LIST_HEAD(>guc_id_link);
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h
b/drivers/gpu/drm/i915/gt/intel_context_types.h
index 542c98418771..035108c10b2c 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -162,6 +162,13 @@ struct intel_context {
struct list_head fences;
} guc_state;
+ struct {
+ /** lock: protects everything in guc_active */
+ spinlock_t lock;
+ /** requests: active requests on this context */
+ struct list_head requests;
+ } guc_active;
+
/* GuC scheduling state flags that do not require a lock. */
atomic_t guc_sched_state_no_lock;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h
b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index e55776e27a2a..1c7e2724cdae 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -414,6 +414,12 @@ struct intel_engine_cs {
void(*release)(struct intel_engine_cs *engine);
+ /*
+* Add / remove request from engine active tracking
+*/
+ void(*add_active_request)(struct i915_request *rq);
+ void(*remove_active_request)(struct i915_request *rq);
+
struct intel_engine_execlists execlists;
/*
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 6e4959ee5065..b4a876736074 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -3157,6 +3157,42 @@ static void execlists_park(struct intel_engine_cs
*engine)
cancel_timer(>execlists.preempt);
}
+static void add_to_engine(struct i915_request *rq)
+{
+ lockdep_assert_held(>engine->sched_engine->lock);
+ list_move_tail(>sched.link, >engine->sched_engine->requests);
+}
+
+static void remove_from_engine(struct i915_request *rq)
+{
+ struct intel_engine_cs *engine, *locked;
+
+ /*
+* Virtual engines complicate acquiring the engine timeline lock,
+* as their rq->engine pointer is not stable until under that
+* engine lock. The simple ploy we use is to take the lock then
+* check that the rq still belongs to the newly locked engine.
+*/
+ locked = READ_ONCE(rq->engine);
+ spin_lock_irq(>sched_engine->lock);
+ while (unlikely(locked != (engine = READ_ONCE(rq->engine {
+ spin_unlock(>sched_engine->lock);
+ spin_lock(>sched_engine->lock);
+ locked = engine;
+ }
+ list_del_init(>sched.link);
+
+ clear_bit(I915_FENCE_FLAG_PQUEUE, >fence.flags);
+ clear_bit(I915_FENCE_FLAG_HOLD, >fence.flags);
+
+ /* Prevent further __await_execution() registering a cb, then flush */
+ set_bit(I915_FENCE_FLAG_ACTIVE, >fence.flags);
+
+ spin_unlock_irq(>sched_engine->lock);
+
+ i915_request_notify_execute_cb_imm(rq);
+}
+
static bool can_preempt(struct intel_engine_cs *engine)
{
if (GRAPHICS_VER(engine->i915) > 8)
@@ -3251,6 +3287,8 @@ logical_ring_default_vfuncs(struct intel_engine_cs
*engine)
engine->cops = _context_ops;
engine->request_alloc = execlists_request_alloc;
+ engine->add_active_request = add_to_engine;
+ engine->remove_active_request = remove_from_engine;
[Intel-gfx] [PATCH 07/33] drm/i915: Move active request tracking to a vfunc
Move active request tracking to a backend vfunc rather than assuming all
backends want to do this in the manner. In the of case execlists /
ring submission the tracking is on the physical engine while with GuC
submission it is on the context.
Signed-off-by: Matthew Brost
Reviewed-by: John Harrison
---
drivers/gpu/drm/i915/gt/intel_context.c | 3 ++
drivers/gpu/drm/i915/gt/intel_context_types.h | 7
drivers/gpu/drm/i915/gt/intel_engine_types.h | 6 +++
.../drm/i915/gt/intel_execlists_submission.c | 40 ++
.../gpu/drm/i915/gt/intel_ring_submission.c | 22 ++
drivers/gpu/drm/i915/gt/mock_engine.c | 30 ++
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 33 +++
drivers/gpu/drm/i915/i915_request.c | 41 ++-
drivers/gpu/drm/i915/i915_request.h | 2 +
9 files changed, 147 insertions(+), 37 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c
b/drivers/gpu/drm/i915/gt/intel_context.c
index baa05fddd690..0bf4a13e9759 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -393,6 +393,9 @@ intel_context_init(struct intel_context *ce, struct
intel_engine_cs *engine)
spin_lock_init(>guc_state.lock);
INIT_LIST_HEAD(>guc_state.fences);
+ spin_lock_init(>guc_active.lock);
+ INIT_LIST_HEAD(>guc_active.requests);
+
ce->guc_id = GUC_INVALID_LRC_ID;
INIT_LIST_HEAD(>guc_id_link);
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h
b/drivers/gpu/drm/i915/gt/intel_context_types.h
index 542c98418771..035108c10b2c 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -162,6 +162,13 @@ struct intel_context {
struct list_head fences;
} guc_state;
+ struct {
+ /** lock: protects everything in guc_active */
+ spinlock_t lock;
+ /** requests: active requests on this context */
+ struct list_head requests;
+ } guc_active;
+
/* GuC scheduling state flags that do not require a lock. */
atomic_t guc_sched_state_no_lock;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h
b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 03a81e8d87f4..950fc73ed6af 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -420,6 +420,12 @@ struct intel_engine_cs {
void(*release)(struct intel_engine_cs *engine);
+ /*
+* Add / remove request from engine active tracking
+*/
+ void(*add_active_request)(struct i915_request *rq);
+ void(*remove_active_request)(struct i915_request *rq);
+
struct intel_engine_execlists execlists;
/*
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 605dd7cb2901..60427b106bad 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -3157,6 +3157,42 @@ static void execlists_park(struct intel_engine_cs
*engine)
cancel_timer(>execlists.preempt);
}
+static void add_to_engine(struct i915_request *rq)
+{
+ lockdep_assert_held(>engine->sched_engine->lock);
+ list_move_tail(>sched.link, >engine->sched_engine->requests);
+}
+
+static void remove_from_engine(struct i915_request *rq)
+{
+ struct intel_engine_cs *engine, *locked;
+
+ /*
+* Virtual engines complicate acquiring the engine timeline lock,
+* as their rq->engine pointer is not stable until under that
+* engine lock. The simple ploy we use is to take the lock then
+* check that the rq still belongs to the newly locked engine.
+*/
+ locked = READ_ONCE(rq->engine);
+ spin_lock_irq(>sched_engine->lock);
+ while (unlikely(locked != (engine = READ_ONCE(rq->engine {
+ spin_unlock(>sched_engine->lock);
+ spin_lock(>sched_engine->lock);
+ locked = engine;
+ }
+ list_del_init(>sched.link);
+
+ clear_bit(I915_FENCE_FLAG_PQUEUE, >fence.flags);
+ clear_bit(I915_FENCE_FLAG_HOLD, >fence.flags);
+
+ /* Prevent further __await_execution() registering a cb, then flush */
+ set_bit(I915_FENCE_FLAG_ACTIVE, >fence.flags);
+
+ spin_unlock_irq(>sched_engine->lock);
+
+ i915_request_notify_execute_cb_imm(rq);
+}
+
static bool can_preempt(struct intel_engine_cs *engine)
{
if (GRAPHICS_VER(engine->i915) > 8)
@@ -3251,6 +3287,8 @@ logical_ring_default_vfuncs(struct intel_engine_cs
*engine)
engine->cops = _context_ops;
engine->request_alloc = execlists_request_alloc;
+ engine->add_active_request = add_to_engine;
+ engine->remove_active_request = remove_from_engine;
