drm/i915: Pass intel_context to i915_request_create()

Start acquiring the logical intel_context and using that as our primary
means for request allocation. This is the initial step to allow us to
avoid requiring struct_mutex for request allocation along the
perma-pinned kernel context, but it also provides a foundation for
breaking up the complex request allocation to handle different scenarios
inside execbuf.

For the purpose of emitting a request from inside retirement (see the
next patch for engine power management), we also need to lift control
over the timeline mutex to the caller.

v2: Note that the request carries the active reference upon construction.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190424200717.1686-4-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/gt/intel_context.h

@@ -105,4 +105,16 @@ static inline void intel_context_put(struct intel_context *ce)
 	kref_put(&ce->ref, ce->ops->destroy);
 }
 
+static inline void intel_context_timeline_lock(struct intel_context *ce)
+	__acquires(&ce->ring->timeline->mutex)
+{
+	mutex_lock(&ce->ring->timeline->mutex);
+}
+
+static inline void intel_context_timeline_unlock(struct intel_context *ce)
+	__releases(&ce->ring->timeline->mutex)
+{
+	mutex_unlock(&ce->ring->timeline->mutex);
+}
+
 #endif /* __INTEL_CONTEXT_H__ */

drivers/gpu/drm/i915/gt/intel_reset.c

@@ -783,7 +783,7 @@ static void restart_work(struct work_struct *work)
 		if (!intel_engine_is_idle(engine))
 			continue;
 
-		rq = i915_request_alloc(engine, i915->kernel_context);
+		rq = i915_request_create(engine->kernel_context);
 		if (!IS_ERR(rq))
 			i915_request_add(rq);
 	}

drivers/gpu/drm/i915/gt/intel_ringbuffer.c

@@ -1772,7 +1772,6 @@ static int switch_context(struct i915_request *rq)
 	u32 hw_flags = 0;
 	int ret, i;
 
-	lockdep_assert_held(&rq->i915->drm.struct_mutex);
 	GEM_BUG_ON(HAS_EXECLISTS(rq->i915));
 
 	if (ppgtt) {
@@ -1902,8 +1901,6 @@ static noinline int wait_for_space(struct intel_ring *ring, unsigned int bytes)
 	struct i915_request *target;
 	long timeout;
 
-	lockdep_assert_held(&ring->vma->vm->i915->drm.struct_mutex);
-
 	if (intel_ring_update_space(ring) >= bytes)
 		return 0;
 

drivers/gpu/drm/i915/gt/intel_workarounds.c

@@ -1356,7 +1356,7 @@ static int engine_wa_list_verify(struct intel_engine_cs *engine,
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	rq = i915_request_alloc(engine, engine->kernel_context->gem_context);
+	rq = i915_request_create(engine->kernel_context);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_vma;

drivers/gpu/drm/i915/i915_gem_context.c

@@ -942,7 +942,7 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915,
 		struct intel_ring *ring;
 		struct i915_request *rq;
 
-		rq = i915_request_alloc(engine, i915->kernel_context);
+		rq = i915_request_create(engine->kernel_context);
 		if (IS_ERR(rq))
 			return PTR_ERR(rq);
 
@@ -1188,7 +1188,7 @@ gen8_modify_rpcs(struct intel_context *ce, struct intel_sseu sseu)
 	/* Submitting requests etc needs the hw awake. */
 	wakeref = intel_runtime_pm_get(i915);
 
-	rq = i915_request_alloc(ce->engine, i915->kernel_context);
+	rq = i915_request_create(ce->engine->kernel_context);
 	if (IS_ERR(rq)) {
 		ret = PTR_ERR(rq);
 		goto out_put;

drivers/gpu/drm/i915/i915_perf.c

@@ -1762,7 +1762,7 @@ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv,
 	 * Apply the configuration by doing one context restore of the edited
 	 * context image.
 	 */
-	rq = i915_request_alloc(engine, dev_priv->kernel_context);
+	rq = i915_request_create(engine->kernel_context);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 

drivers/gpu/drm/i915/i915_request.h

@@ -239,6 +239,13 @@ static inline bool dma_fence_is_i915(const struct dma_fence *fence)
 	return fence->ops == &i915_fence_ops;
 }
 
+struct i915_request * __must_check
+__i915_request_create(struct intel_context *ce, gfp_t gfp);
+struct i915_request * __must_check
+i915_request_create(struct intel_context *ce);
+
+struct i915_request *__i915_request_commit(struct i915_request *request);
+
 struct i915_request * __must_check
 i915_request_alloc(struct intel_engine_cs *engine,
 		   struct i915_gem_context *ctx);

drivers/gpu/drm/i915/intel_overlay.c

@@ -235,10 +235,9 @@ static int intel_overlay_do_wait_request(struct intel_overlay *overlay,
 
 static struct i915_request *alloc_request(struct intel_overlay *overlay)
 {
-	struct drm_i915_private *dev_priv = overlay->i915;
-	struct intel_engine_cs *engine = dev_priv->engine[RCS0];
+	struct intel_engine_cs *engine = overlay->i915->engine[RCS0];
 
-	return i915_request_alloc(engine, dev_priv->kernel_context);
+	return i915_request_create(engine->kernel_context);
 }
 
 /* overlay needs to be disable in OCMD reg */

drivers/gpu/drm/i915/selftests/i915_active.c

@@ -46,7 +46,7 @@ static int __live_active_setup(struct drm_i915_private *i915,
 	for_each_engine(engine, i915, id) {
 		struct i915_request *rq;
 
-		rq = i915_request_alloc(engine, i915->kernel_context);
+		rq = i915_request_create(engine->kernel_context);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
 			break;

drivers/gpu/drm/i915/selftests/i915_gem_coherency.c

@@ -202,7 +202,7 @@ static int gpu_set(struct drm_i915_gem_object *obj,
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	rq = i915_request_alloc(i915->engine[RCS0], i915->kernel_context);
+	rq = i915_request_create(i915->engine[RCS0]->kernel_context);
 	if (IS_ERR(rq)) {
 		i915_vma_unpin(vma);
 		return PTR_ERR(rq);

drivers/gpu/drm/i915/selftests/i915_gem_object.c

@@ -468,7 +468,7 @@ static int make_obj_busy(struct drm_i915_gem_object *obj)
 	if (err)
 		return err;
 
-	rq = i915_request_alloc(i915->engine[RCS0], i915->kernel_context);
+	rq = i915_request_create(i915->engine[RCS0]->kernel_context);
 	if (IS_ERR(rq)) {
 		i915_vma_unpin(vma);
 		return PTR_ERR(rq);

drivers/gpu/drm/i915/selftests/i915_request.c

@@ -551,8 +551,7 @@ static int live_nop_request(void *arg)
 			times[1] = ktime_get_raw();
 
 			for (n = 0; n < prime; n++) {
-				request = i915_request_alloc(engine,
-							     i915->kernel_context);
+				request = i915_request_create(engine->kernel_context);
 				if (IS_ERR(request)) {
 					err = PTR_ERR(request);
 					goto out_unlock;
@@ -649,7 +648,7 @@ empty_request(struct intel_engine_cs *engine,
 	struct i915_request *request;
 	int err;
 
-	request = i915_request_alloc(engine, engine->i915->kernel_context);
+	request = i915_request_create(engine->kernel_context);
 	if (IS_ERR(request))
 		return request;
 
@@ -853,7 +852,7 @@ static int live_all_engines(void *arg)
 	}
 
 	for_each_engine(engine, i915, id) {
-		request[id] = i915_request_alloc(engine, i915->kernel_context);
+		request[id] = i915_request_create(engine->kernel_context);
 		if (IS_ERR(request[id])) {
 			err = PTR_ERR(request[id]);
 			pr_err("%s: Request allocation failed with err=%d\n",
@@ -962,7 +961,7 @@ static int live_sequential_engines(void *arg)
 			goto out_unlock;
 		}
 
-		request[id] = i915_request_alloc(engine, i915->kernel_context);
+		request[id] = i915_request_create(engine->kernel_context);
 		if (IS_ERR(request[id])) {
 			err = PTR_ERR(request[id]);
 			pr_err("%s: Request allocation failed for %s with err=%d\n",

drivers/gpu/drm/i915/selftests/i915_timeline.c

@@ -454,7 +454,7 @@ tl_write(struct i915_timeline *tl, struct intel_engine_cs *engine, u32 value)
 		goto out;
 	}
 
-	rq = i915_request_alloc(engine, engine->i915->kernel_context);
+	rq = i915_request_create(engine->kernel_context);
 	if (IS_ERR(rq))
 		goto out_unpin;
 
@@ -678,7 +678,7 @@ static int live_hwsp_wrap(void *arg)
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
-		rq = i915_request_alloc(engine, i915->kernel_context);
+		rq = i915_request_create(engine->kernel_context);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
 			goto out;