[PATCH 11/11] rq

[Chris Wilson]

---
 drivers/gpu/drm/i915/i915_request.c |  7 ++++++-
 drivers/gpu/drm/i915/i915_request.h | 11 +++++++++++
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 3dd1d8cbacc9..b8eb537d0889 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -722,6 +722,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	rq->timeline = tl;
 	GEM_BUG_ON(rq->timeline == &engine->timeline);
 	rq->hwsp_seqno = tl->hwsp_seqno;
+	rq->hwsp_cacheline = tl->hwsp_cacheline;
 	rq->rcustate = get_state_synchronize_rcu(); /* acts as smp_mb() */
 
 	spin_lock_init(&rq->lock);
@@ -808,7 +809,11 @@ emit_semaphore_wait(struct i915_request *to,
 	GEM_BUG_ON(INTEL_GEN(to->i915) < 8);
 
 	/* We need to pin the signaler's HWSP until we are finished reading. */
-	err = i915_timeline_read_lock(from->timeline, to);
+	mutex_lock_nested(&from->timeline->mutex, SINGLE_DEPTH_NESTING);
+	err = i915_request_completed(from);
+	if (!err)
+		err = i915_timeline_read_lock(from->hwsp_cacheline, to);
+	mutex_unlock(&from->timeline->mutex);
 	if (err)
 		return err;
 
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index df52776b26cf..63f60386ddb4 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -38,6 +38,7 @@ struct drm_file;
 struct drm_i915_gem_object;
 struct i915_request;
 struct i915_timeline;
+struct i915_timeline_cacheline;
 
 struct i915_capture_list {
 	struct i915_capture_list *next;
@@ -149,6 +150,16 @@ struct i915_request {
 	 */
 	const u32 *hwsp_seqno;
 
+	/*
+	 * If we need to access the timeline's seqno for this request in
+	 * another request, we need to keep a read reference to this associated
+	 * cacheline, so that we do not free and recycle it before the foriegn
+	 * observers have completed. Hence, we keep a pointer to the cacheline
+	 * inside the timeline's HWSP vma, but it is only valid while this
+	 * request has not completed and guarded by the timeline mutex.
+	 */
+	struct i915_timeline_cacheline *hwsp_cacheline;
+
 	/**
 	 * GEM sequence number associated with this request on the
 	 * global execution timeline. It is zero when the request is not
-- 
2.20.1