[Intel-gfx] [RFC PATCH 19/42] drm/i915/guc: Ensure GuC schedule operations do not operate on child contexts

[Matthew Brost]

In GuC parent-child contexts the parent context controls the scheduling,
ensure only the parent does the scheduling operations.

Signed-off-by: Matthew Brost <matthew.brost at intel.com>
---
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 48 +++++++++++++++----
 1 file changed, 38 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 0045895e0fa0..f60a46704ac5 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -402,6 +402,18 @@ static inline void clr_context_banned(struct intel_context *ce)
 	ce->guc_state.sched_state &= ~SCHED_STATE_BANNED;
 }
 
+static inline struct intel_context *
+to_parent(struct intel_context *ce)
+{
+	return intel_context_is_child(ce) ? ce->parent : ce;
+}
+
+static inline struct intel_context *
+request_to_scheduling_context(struct i915_request *rq)
+{
+	return to_parent(rq->context);
+}
+
 static inline bool context_guc_id_invalid(struct intel_context *ce)
 {
 	return (ce->guc_id == GUC_INVALID_LRC_ID);
@@ -2341,6 +2353,7 @@ static void __guc_context_sched_disable(struct intel_guc *guc,
 	GEM_BUG_ON(guc_id == GUC_INVALID_LRC_ID);
 #endif
 
+	GEM_BUG_ON(intel_context_is_child(ce));
 	trace_intel_context_sched_disable(ce);
 
 	guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action),
@@ -2546,6 +2559,8 @@ static void guc_context_sched_disable(struct intel_context *ce)
 	u16 guc_id;
 	bool enabled;
 
+	GEM_BUG_ON(intel_context_is_child(ce));
+
 	if (submission_disabled(guc) || context_guc_id_invalid(ce) ||
 	    !lrc_desc_registered(guc, ce->guc_id)) {
 		clr_context_enabled(ce);
@@ -2941,6 +2956,8 @@ static void guc_signal_context_fence(struct intel_context *ce)
 {
 	unsigned long flags;
 
+	GEM_BUG_ON(intel_context_is_child(ce));
+
 	spin_lock_irqsave(&ce->guc_state.lock, flags);
 	clr_context_wait_for_deregister_to_register(ce);
 	__guc_signal_context_fence(ce);
@@ -3026,10 +3043,21 @@ static bool context_needs_lrc_desc_pin(struct intel_context *ce, bool new_guc_id
 		!submission_disabled(ce_to_guc(ce));
 }
 
+static void clear_lrca_dirty(struct intel_context *ce)
+{
+	struct intel_context *child;
+
+	GEM_BUG_ON(intel_context_is_child(ce));
+
+	clear_bit(CONTEXT_LRCA_DIRTY, &ce->flags);
+	for_each_child(ce, child)
+		clear_bit(CONTEXT_LRCA_DIRTY, &child->flags);
+}
+
 static int tasklet_pin_guc_id(struct guc_submit_engine *gse,
 			      struct i915_request *rq)
 {
-	struct intel_context *ce = rq->context;
+	struct intel_context *ce = request_to_scheduling_context(rq);
 	int ret = 0;
 
 	lockdep_assert_held(&gse->sched_engine.lock);
@@ -3061,7 +3089,7 @@ static int tasklet_pin_guc_id(struct guc_submit_engine *gse,
 		gse->submission_stall_reason = STALL_SCHED_DISABLE;
 	}
 
-	clear_bit(CONTEXT_LRCA_DIRTY, &ce->flags);
+	clear_lrca_dirty(ce);
 out:
 	gse->total_num_rq_with_no_guc_id -= ce->guc_num_rq_submit_no_id;
 	GEM_BUG_ON(gse->total_num_rq_with_no_guc_id < 0);
@@ -3092,7 +3120,7 @@ static int tasklet_pin_guc_id(struct guc_submit_engine *gse,
 
 static int guc_request_alloc(struct i915_request *rq)
 {
-	struct intel_context *ce = rq->context;
+	struct intel_context *ce = request_to_scheduling_context(rq);
 	struct intel_guc *guc = ce_to_guc(ce);
 	struct guc_submit_engine *gse = ce_to_gse(ce);
 	unsigned long flags;
@@ -3143,11 +3171,12 @@ static int guc_request_alloc(struct i915_request *rq)
 	 * persistent until the generated request is retired. Thus, sealing these
 	 * race conditions.
 	 *
-	 * There is no need for a lock here as the timeline mutex ensures at
-	 * most one context can be executing this code path at once. The
-	 * guc_id_ref is incremented once for every request in flight and
-	 * decremented on each retire. When it is zero, a lock around the
-	 * increment (in pin_guc_id) is needed to seal a race with unpin_guc_id.
+	 * There is no need for a lock here as the timeline mutex (or
+	 * parallel_submit mutex in the case of multi-lrc) ensures at most one
+	 * context can be executing this code path at once. The guc_id_ref is
+	 * incremented once for every request in flight and decremented on each
+	 * retire. When it is zero, a lock around the increment (in pin_guc_id)
+	 * is needed to seal a race with unpin_guc_id.
 	 */
 	if (atomic_add_unless(&ce->guc_id_ref, 1, 0))
 		goto out;
@@ -3185,8 +3214,7 @@ static int guc_request_alloc(struct i915_request *rq)
 		}
 	}
 
-	clear_bit(CONTEXT_LRCA_DIRTY, &ce->flags);
-
+	clear_lrca_dirty(ce);
 out:
 	incr_num_rq_not_ready(ce);
 
-- 
2.28.0