drm/i915: Make for_each_engine_masked work on intel_gt

Medium term goal is to eliminate the i915->engine[] array and to get there
we have recently introduced equivalent array in intel_gt. Now we need to
migrate the code further towards this state.

This next step is to eliminate usage of i915->engines[] from the
for_each_engine_masked iterator.

For this to work we also need to use engine->id as index when populating
the gt->engine[] array and adjust the default engine set indexing to use
engine->legacy_idx instead of assuming gt->engines[] indexing.

v2:
  * Populate gt->engine[] earlier.
  * Check that we don't duplicate engine->legacy_idx

v3:
  * Work around the initialization order issue between default_engines()
    and intel_engines_driver_register() which sets engine->legacy_idx for
    now. It will be fixed properly later.

v4:
  * Merge with forgotten v2.5.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191017161852.8836-1-tvrtko.ursulin@linux.intel.com

drivers/gpu/drm/i915/gem/i915_gem_context.c

@@ -203,15 +203,22 @@ static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx)
 	for_each_engine(engine, gt, id) {
 		struct intel_context *ce;
 
+		if (engine->legacy_idx == INVALID_ENGINE)
+			continue;
+
+		GEM_BUG_ON(engine->legacy_idx >= I915_NUM_ENGINES);
+		GEM_BUG_ON(e->engines[engine->legacy_idx]);
+
 		ce = intel_context_create(ctx, engine);
 		if (IS_ERR(ce)) {
-			__free_engines(e, id);
+			__free_engines(e, e->num_engines + 1);
 			return ERR_CAST(ce);
 		}
 
-		e->engines[id] = ce;
-		e->num_engines = id + 1;
+		e->engines[engine->legacy_idx] = ce;
+		e->num_engines = max(e->num_engines, engine->legacy_idx);
 	}
+	e->num_engines++;
 
 	return e;
 }

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

@@ -277,6 +277,9 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	BUILD_BUG_ON(MAX_ENGINE_CLASS >= BIT(GEN11_ENGINE_CLASS_WIDTH));
 	BUILD_BUG_ON(MAX_ENGINE_INSTANCE >= BIT(GEN11_ENGINE_INSTANCE_WIDTH));
 
+	if (GEM_DEBUG_WARN_ON(id >= ARRAY_SIZE(gt->engine)))
+		return -EINVAL;
+
 	if (GEM_DEBUG_WARN_ON(info->class > MAX_ENGINE_CLASS))
 		return -EINVAL;
 
@@ -293,6 +296,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	BUILD_BUG_ON(BITS_PER_TYPE(engine->mask) < I915_NUM_ENGINES);
 
 	engine->id = id;
+	engine->legacy_idx = INVALID_ENGINE;
 	engine->mask = BIT(id);
 	engine->i915 = gt->i915;
 	engine->gt = gt;
@@ -328,6 +332,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	intel_engine_sanitize_mmio(engine);
 
 	gt->engine_class[info->class][info->instance] = engine;
+	gt->engine[id] = engine;
 
 	intel_engine_add_user(engine);
 	gt->i915->engine[id] = engine;

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

@@ -148,6 +148,7 @@ enum intel_engine_id {
 	VECS1,
 #define _VECS(n) (VECS0 + (n))
 	I915_NUM_ENGINES
+#define INVALID_ENGINE ((enum intel_engine_id)-1)
 };
 
 struct st_preempt_hang {

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

@@ -160,10 +160,10 @@ static int legacy_ring_idx(const struct legacy_ring *ring)
 	};
 
 	if (GEM_DEBUG_WARN_ON(ring->class >= ARRAY_SIZE(map)))
-		return -1;
+		return INVALID_ENGINE;
 
 	if (GEM_DEBUG_WARN_ON(ring->instance >= map[ring->class].max))
-		return -1;
+		return INVALID_ENGINE;
 
 	return map[ring->class].base + ring->instance;
 }
@@ -171,23 +171,15 @@ static int legacy_ring_idx(const struct legacy_ring *ring)
 static void add_legacy_ring(struct legacy_ring *ring,
 			    struct intel_engine_cs *engine)
 {
-	int idx;
-
 	if (engine->gt != ring->gt || engine->class != ring->class) {
 		ring->gt = engine->gt;
 		ring->class = engine->class;
 		ring->instance = 0;
 	}
 
-	idx = legacy_ring_idx(ring);
-	if (unlikely(idx == -1))
-		return;
-
-	GEM_BUG_ON(idx >= ARRAY_SIZE(ring->gt->engine));
-	ring->gt->engine[idx] = engine;
-	ring->instance++;
-
-	engine->legacy_idx = idx;
+	engine->legacy_idx = legacy_ring_idx(ring);
+	if (engine->legacy_idx != INVALID_ENGINE)
+		ring->instance++;
 }
 
 void intel_engines_driver_register(struct drm_i915_private *i915)

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

@@ -186,7 +186,7 @@ intel_gt_clear_error_registers(struct intel_gt *gt,
 		struct intel_engine_cs *engine;
 		enum intel_engine_id id;
 
-		for_each_engine_masked(engine, i915, engine_mask, id)
+		for_each_engine_masked(engine, gt, engine_mask, id)
 			gen8_clear_engine_error_register(engine);
 	}
 }

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

@@ -237,7 +237,7 @@ static void hangcheck_declare_hang(struct intel_gt *gt,
 		hung &= ~stuck;
 	len = scnprintf(msg, sizeof(msg),
 			"%s on ", stuck == hung ? "no progress" : "hang");
-	for_each_engine_masked(engine, gt->i915, hung, tmp)
+	for_each_engine_masked(engine, gt, hung, tmp)
 		len += scnprintf(msg + len, sizeof(msg) - len,
 				 "%s, ", engine->name);
 	msg[len-2] = '\0';

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

@@ -298,7 +298,7 @@ static int gen6_reset_engines(struct intel_gt *gt,
 		intel_engine_mask_t tmp;
 
 		hw_mask = 0;
-		for_each_engine_masked(engine, gt->i915, engine_mask, tmp) {
+		for_each_engine_masked(engine, gt, engine_mask, tmp) {
 			GEM_BUG_ON(engine->id >= ARRAY_SIZE(hw_engine_mask));
 			hw_mask |= hw_engine_mask[engine->id];
 		}
@@ -432,7 +432,7 @@ static int gen11_reset_engines(struct intel_gt *gt,
 		hw_mask = GEN11_GRDOM_FULL;
 	} else {
 		hw_mask = 0;
-		for_each_engine_masked(engine, gt->i915, engine_mask, tmp) {
+		for_each_engine_masked(engine, gt, engine_mask, tmp) {
 			GEM_BUG_ON(engine->id >= ARRAY_SIZE(hw_engine_mask));
 			hw_mask |= hw_engine_mask[engine->id];
 			ret = gen11_lock_sfc(engine, &hw_mask);
@@ -451,7 +451,7 @@ static int gen11_reset_engines(struct intel_gt *gt,
 	 * expiration).
 	 */
 	if (engine_mask != ALL_ENGINES)
-		for_each_engine_masked(engine, gt->i915, engine_mask, tmp)
+		for_each_engine_masked(engine, gt, engine_mask, tmp)
 			gen11_unlock_sfc(engine);
 
 	return ret;
@@ -510,7 +510,7 @@ static int gen8_reset_engines(struct intel_gt *gt,
 	intel_engine_mask_t tmp;
 	int ret;
 
-	for_each_engine_masked(engine, gt->i915, engine_mask, tmp) {
+	for_each_engine_masked(engine, gt, engine_mask, tmp) {
 		ret = gen8_engine_reset_prepare(engine);
 		if (ret && !reset_non_ready)
 			goto skip_reset;
@@ -536,7 +536,7 @@ static int gen8_reset_engines(struct intel_gt *gt,
 		ret = gen6_reset_engines(gt, engine_mask, retry);
 
 skip_reset:
-	for_each_engine_masked(engine, gt->i915, engine_mask, tmp)
+	for_each_engine_masked(engine, gt, engine_mask, tmp)
 		gen8_engine_reset_cancel(engine);
 
 	return ret;
@@ -1206,7 +1206,7 @@ void intel_gt_handle_error(struct intel_gt *gt,
 	 * single reset fails.
 	 */
 	if (intel_has_reset_engine(gt) && !intel_gt_is_wedged(gt)) {
-		for_each_engine_masked(engine, gt->i915, engine_mask, tmp) {
+		for_each_engine_masked(engine, gt, engine_mask, tmp) {
 			BUILD_BUG_ON(I915_RESET_MODESET >= I915_RESET_ENGINE);
 			if (test_and_set_bit(I915_RESET_ENGINE + engine->id,
 					     &gt->reset.flags))

drivers/gpu/drm/i915/gvt/execlist.c

@@ -534,7 +534,7 @@ static void clean_execlist(struct intel_vgpu *vgpu,
 	struct intel_vgpu_submission *s = &vgpu->submission;
 	intel_engine_mask_t tmp;
 
-	for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
+	for_each_engine_masked(engine, &dev_priv->gt, engine_mask, tmp) {
 		kfree(s->ring_scan_buffer[engine->id]);
 		s->ring_scan_buffer[engine->id] = NULL;
 		s->ring_scan_buffer_size[engine->id] = 0;
@@ -548,7 +548,7 @@ static void reset_execlist(struct intel_vgpu *vgpu,
 	struct intel_engine_cs *engine;
 	intel_engine_mask_t tmp;
 
-	for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
+	for_each_engine_masked(engine, &dev_priv->gt, engine_mask, tmp)
 		init_vgpu_execlist(vgpu, engine->id);
 }
 

drivers/gpu/drm/i915/gvt/scheduler.c

@@ -887,7 +887,7 @@ void intel_vgpu_clean_workloads(struct intel_vgpu *vgpu,
 	intel_engine_mask_t tmp;
 
 	/* free the unsubmited workloads in the queues. */
-	for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
+	for_each_engine_masked(engine, &dev_priv->gt, engine_mask, tmp) {
 		list_for_each_entry_safe(pos, n,
 			&s->workload_q_head[engine->id], list) {
 			list_del_init(&pos->list);

drivers/gpu/drm/i915/i915_active.c

@@ -590,8 +590,8 @@ static struct active_node *reuse_idle_barrier(struct i915_active *ref, u64 idx)
 int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 					    struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *i915 = engine->i915;
 	intel_engine_mask_t tmp, mask = engine->mask;
+	struct intel_gt *gt = engine->gt;
 	struct llist_node *pos, *next;
 	int err;
 
@@ -603,7 +603,7 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 	 * We can then use the preallocated nodes in
 	 * i915_active_acquire_barrier()
 	 */
-	for_each_engine_masked(engine, i915, mask, tmp) {
+	for_each_engine_masked(engine, gt, mask, tmp) {
 		u64 idx = engine->kernel_context->timeline->fence_context;
 		struct active_node *node;
 

drivers/gpu/drm/i915/i915_drv.h

@@ -1415,10 +1415,10 @@ static inline struct drm_i915_private *pdev_to_i915(struct pci_dev *pdev)
 		for_each_if ((engine__) = (dev_priv__)->engine[(id__)])
 
 /* Iterator over subset of engines selected by mask */
-#define for_each_engine_masked(engine__, dev_priv__, mask__, tmp__) \
-	for ((tmp__) = (mask__) & INTEL_INFO(dev_priv__)->engine_mask; \
+#define for_each_engine_masked(engine__, gt__, mask__, tmp__) \
+	for ((tmp__) = (mask__) & INTEL_INFO((gt__)->i915)->engine_mask; \
 	     (tmp__) ? \
-	     ((engine__) = (dev_priv__)->engine[__mask_next_bit(tmp__)]), 1 : \
+	     ((engine__) = (gt__)->engine[__mask_next_bit(tmp__)]), 1 : \
 	     0;)
 
 #define rb_to_uabi_engine(rb) \