[Intel-gfx] [PATCH 19/25] drm/i915: Introduce i915_timeline.mutex

[Chris Wilson]

A simple mutex used for guarding the flow of requests in and out of the
timeline. In the short-term, it will be used only to guard the addition
of requests into the timeline, taken on alloc and released on commit so
that only one caller can construct a request into the timeline
(important as the seqno and ring pointers must be serialised). This will
be used by observers to ensure that the seqno/hwsp is stable. Later,
when we have reduced retiring to only operate on a single timeline at a
time, we can then use the mutex as the sole guard required for retiring.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_request.c            | 6 +++++-
 drivers/gpu/drm/i915/i915_timeline.c           | 1 +
 drivers/gpu/drm/i915/i915_timeline.h           | 2 ++
 drivers/gpu/drm/i915/selftests/i915_request.c  | 2 --
 drivers/gpu/drm/i915/selftests/mock_timeline.c | 1 +
 5 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 7de4abbbc226..40053232b794 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -562,6 +562,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 		return ERR_CAST(ce);
 
 	reserve_gt(i915);
+	mutex_lock(&ce->ring->timeline->mutex);
 
 	/* Move our oldest request to the slab-cache (if not in use!) */
 	rq = list_first_entry(&ce->ring->request_list, typeof(*rq), ring_link);
@@ -687,6 +688,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 
 	kmem_cache_free(global.slab_requests, rq);
 err_unreserve:
+	mutex_unlock(&ce->ring->timeline->mutex);
 	unreserve_gt(i915);
 	intel_context_unpin(ce);
 	return ERR_PTR(ret);
@@ -879,7 +881,7 @@ void i915_request_add(struct i915_request *request)
 	GEM_TRACE("%s fence %llx:%lld\n",
 		  engine->name, request->fence.context, request->fence.seqno);
 
-	lockdep_assert_held(&request->i915->drm.struct_mutex);
+	lockdep_assert_held(&request->timeline->mutex);
 	trace_i915_request_add(request);
 
 	/*
@@ -990,6 +992,8 @@ void i915_request_add(struct i915_request *request)
 	 */
 	if (prev && i915_request_completed(prev))
 		i915_request_retire_upto(prev);
+
+	mutex_unlock(&request->timeline->mutex);
 }
 
 static unsigned long local_clock_us(unsigned int *cpu)
diff --git a/drivers/gpu/drm/i915/i915_timeline.c b/drivers/gpu/drm/i915/i915_timeline.c
index b2202d2e58a2..87a80558da28 100644
--- a/drivers/gpu/drm/i915/i915_timeline.c
+++ b/drivers/gpu/drm/i915/i915_timeline.c
@@ -162,6 +162,7 @@ int i915_timeline_init(struct drm_i915_private *i915,
 	timeline->fence_context = dma_fence_context_alloc(1);
 
 	spin_lock_init(&timeline->lock);
+	mutex_init(&timeline->mutex);
 
 	INIT_ACTIVE_REQUEST(&timeline->barrier);
 	INIT_ACTIVE_REQUEST(&timeline->last_request);
diff --git a/drivers/gpu/drm/i915/i915_timeline.h b/drivers/gpu/drm/i915/i915_timeline.h
index 7bec7d2e45bf..36c3849f7108 100644
--- a/drivers/gpu/drm/i915/i915_timeline.h
+++ b/drivers/gpu/drm/i915/i915_timeline.h
@@ -44,6 +44,8 @@ struct i915_timeline {
 #define TIMELINE_CLIENT 0 /* default subclass */
 #define TIMELINE_ENGINE 1
 
+	struct mutex mutex; /* protects the flow of requests */
+
 	unsigned int pin_count;
 	const u32 *hwsp_seqno;
 	struct i915_vma *hwsp_ggtt;
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 074d393f4a02..afa66f51c239 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -141,14 +141,12 @@ static int igt_fence_wait(void *arg)
 		err = -ENOMEM;
 		goto out_locked;
 	}
-	mutex_unlock(&i915->drm.struct_mutex); /* safe as we are single user */
 
 	if (dma_fence_wait_timeout(&request->fence, false, T) != -ETIME) {
 		pr_err("fence wait success before submit (expected timeout)!\n");
 		goto out_device;
 	}
 
-	mutex_lock(&i915->drm.struct_mutex);
 	i915_request_add(request);
 	mutex_unlock(&i915->drm.struct_mutex);
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_timeline.c b/drivers/gpu/drm/i915/selftests/mock_timeline.c
index d2de9ece2118..416d85233263 100644
--- a/drivers/gpu/drm/i915/selftests/mock_timeline.c
+++ b/drivers/gpu/drm/i915/selftests/mock_timeline.c
@@ -14,6 +14,7 @@ void mock_timeline_init(struct i915_timeline *timeline, u64 context)
 	timeline->fence_context = context;
 
 	spin_lock_init(&timeline->lock);
+	mutex_init(&timeline->mutex);
 
 	INIT_ACTIVE_REQUEST(&timeline->barrier);
 	INIT_ACTIVE_REQUEST(&timeline->last_request);
-- 
2.20.1