drm/i915: Protect request retirement with timeline->mutex

Forgo the struct_mutex requirement for request retirement as we have
been transitioning over to only using the timeline->mutex for
controlling the lifetime of a request on that timeline.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190815205709.24285-4-chris@chris-wilson.co.uk

9 files changed, 33 insertions, 23 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index 9fa8b588f18e..053a1307ecb4 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -12,6 +12,7 @@
 #include "i915_active.h"
 #include "intel_context_types.h"
 #include "intel_engine_types.h"
+#include "intel_timeline_types.h"
 
 void intel_context_init(struct intel_context *ce,
 			struct i915_gem_context *ctx,
@@ -118,17 +119,24 @@ static inline void intel_context_put(struct intel_context *ce)
 	kref_put(&ce->ref, ce->ops->destroy);
 }
 
-static inline int __must_check
+static inline struct intel_timeline *__must_check
 intel_context_timeline_lock(struct intel_context *ce)
 	__acquires(&ce->timeline->mutex)
 {
-	return mutex_lock_interruptible(&ce->timeline->mutex);
+	struct intel_timeline *tl = ce->timeline;
+	int err;
+
+	err = mutex_lock_interruptible(&tl->mutex);
+	if (err)
+		return ERR_PTR(err);
+
+	return tl;
 }
 
-static inline void intel_context_timeline_unlock(struct intel_context *ce)
-	__releases(&ce->timeline->mutex)
+static inline void intel_context_timeline_unlock(struct intel_timeline *tl)
+	__releases(&tl->mutex)
 {
-	mutex_unlock(&ce->timeline->mutex);
+	mutex_unlock(&tl->mutex);
 }
 
 int intel_context_prepare_remote_request(struct intel_context *ce,
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index d20750e420c0..957f27a2ec97 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -679,7 +679,6 @@ static int measure_breadcrumb_dw(struct intel_engine_cs *engine)
 				engine->status_page.vma))
 		goto out_frame;
 
-	INIT_LIST_HEAD(&frame->ring.request_list);
 	frame->ring.vaddr = frame->cs;
 	frame->ring.size = sizeof(frame->cs);
 	frame->ring.effective_size = frame->ring.size;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index a0f372807dd4..9965a32601d6 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -69,9 +69,6 @@ struct intel_ring {
 	struct i915_vma *vma;
 	void *vaddr;
 
-	struct list_head request_list;
-	struct list_head active_link;
-
 	/*
 	 * As we have two types of rings, one global to the engine used
 	 * by ringbuffer submission and those that are exclusive to a
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 914bd2db3bc7..d48ec9a76ed1 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -15,8 +15,6 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 
 	spin_lock_init(&gt->irq_lock);
 
-	INIT_LIST_HEAD(&gt->active_rings);
-
 	INIT_LIST_HEAD(&gt->closed_vma);
 	spin_lock_init(&gt->closed_lock);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index 143b2d78c2cc..f882e2cf159c 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -48,8 +48,6 @@ struct intel_gt {
 		struct list_head hwsp_free_list;
 	} timelines;
 
-	struct list_head active_rings;
-
 	struct intel_wakeref wakeref;
 
 	struct list_head closed_vma;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index b4c2662dbc75..e9863f4d826b 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1583,6 +1583,7 @@ static void execlists_context_unpin(struct intel_context *ce)
 {
 	i915_gem_context_unpin_hw_id(ce->gem_context);
 	i915_gem_object_unpin_map(ce->state->obj);
+	intel_ring_reset(ce->ring, ce->ring->tail);
 }
 
 static void
diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
index 409d764f8c6d..1d9c125b76d0 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
@@ -1250,7 +1250,7 @@ void intel_ring_unpin(struct intel_ring *ring)
 		return;
 
 	/* Discard any unused bytes beyond that submitted to hw. */
-	intel_ring_reset(ring, ring->tail);
+	intel_ring_reset(ring, ring->emit);
 
 	i915_vma_unset_ggtt_write(vma);
 	if (i915_vma_is_map_and_fenceable(vma))
@@ -1311,7 +1311,6 @@ intel_engine_create_ring(struct intel_engine_cs *engine, int size)
 		return ERR_PTR(-ENOMEM);
 
 	kref_init(&ring->ref);
-	INIT_LIST_HEAD(&ring->request_list);
 
 	ring->size = size;
 	/* Workaround an erratum on the i830 which causes a hang if
@@ -1865,7 +1864,10 @@ static int ring_request_alloc(struct i915_request *request)
 	return 0;
 }
 
-static noinline int wait_for_space(struct intel_ring *ring, unsigned int bytes)
+static noinline int
+wait_for_space(struct intel_ring *ring,
+	       struct intel_timeline *tl,
+	       unsigned int bytes)
 {
 	struct i915_request *target;
 	long timeout;
@@ -1873,15 +1875,18 @@ static noinline int wait_for_space(struct intel_ring *ring, unsigned int bytes)
 	if (intel_ring_update_space(ring) >= bytes)
 		return 0;
 
-	GEM_BUG_ON(list_empty(&ring->request_list));
-	list_for_each_entry(target, &ring->request_list, ring_link) {
+	GEM_BUG_ON(list_empty(&tl->requests));
+	list_for_each_entry(target, &tl->requests, link) {
+		if (target->ring != ring)
+			continue;
+
 		/* Would completion of this request free enough space? */
 		if (bytes <= __intel_ring_space(target->postfix,
 						ring->emit, ring->size))
 			break;
 	}
 
-	if (WARN_ON(&target->ring_link == &ring->request_list))
+	if (GEM_WARN_ON(&target->link == &tl->requests))
 		return -ENOSPC;
 
 	timeout = i915_request_wait(target,
@@ -1948,7 +1953,7 @@ u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords)
 		 */
 		GEM_BUG_ON(!rq->reserved_space);
 
-		ret = wait_for_space(ring, total_bytes);
+		ret = wait_for_space(ring, rq->timeline, total_bytes);
 		if (unlikely(ret))
 			return ERR_PTR(ret);
 	}
diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index 54a11dde3076..5d43cbc3f345 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -58,7 +58,6 @@ static struct intel_ring *mock_ring(struct intel_engine_cs *engine)
 	ring->vaddr = (void *)(ring + 1);
 	atomic_set(&ring->pin_count, 1);
 
-	INIT_LIST_HEAD(&ring->request_list);
 	intel_ring_update_space(ring);
 
 	return ring;
diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c
index da9c49e2adaf..6fbc72bc290e 100644
--- a/drivers/gpu/drm/i915/gt/selftest_context.c
+++ b/drivers/gpu/drm/i915/gt/selftest_context.c
@@ -20,10 +20,13 @@ static int request_sync(struct i915_request *rq)
 
 	i915_request_add(rq);
 	timeout = i915_request_wait(rq, 0, HZ / 10);
-	if (timeout < 0)
+	if (timeout < 0) {
 		err = timeout;
-	else
+	} else {
+		mutex_lock(&rq->timeline->mutex);
 		i915_request_retire_upto(rq);
+		mutex_unlock(&rq->timeline->mutex);
+	}
 
 	i915_request_put(rq);
 
@@ -35,6 +38,7 @@ static int context_sync(struct intel_context *ce)
 	struct intel_timeline *tl = ce->timeline;
 	int err = 0;
 
+	mutex_lock(&tl->mutex);
 	do {
 		struct i915_request *rq;
 		long timeout;
@@ -55,6 +59,7 @@ static int context_sync(struct intel_context *ce)
 
 		i915_request_put(rq);
 	} while (!err);
+	mutex_unlock(&tl->mutex);
 
 	return err;
 }