drm/i915: Strip out internal priorities

Since we are not using any internal priority levels, and in the next few
patches will introduce a new index for which the optimisation is not so
lear cut, discard the small table within the priolist.

Signed-off-by: Chris Wilson <[e-mail]>
Reviewed-by: Andi Shyti <[e-mail]>
Link: https://patchwork.freedesktop.org/patch/msgid/[e-mail]
Signed-off-by: Daniel Vetter <[e-mail]>

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

···
 			 * low latency and no jitter] the chance to naturally
 			 * complete before being preempted.
 			 */
-			attr.priority = I915_PRIORITY_MASK;
+			attr.priority = 0;
 			if (rq->sched.attr.priority >= attr.priority)
 				attr.priority |= I915_USER_PRIORITY(I915_PRIORITY_HEARTBEAT);
 			if (rq->sched.attr.priority >= attr.priority)

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

···
 
 static int queue_prio(const struct intel_engine_execlists *execlists)
 {
-	struct i915_priolist *p;
 	struct rb_node *rb;
 
 	rb = rb_first_cached(&execlists->queue);
 	if (!rb)
 		return INT_MIN;
 
-	/*
-	 * As the priolist[] are inverted, with the highest priority in [0],
-	 * we have to flip the index value to become priority.
-	 */
-	p = to_priolist(rb);
-	if (!I915_USER_PRIORITY_SHIFT)
-		return p->priority;
-
-	return ((p->priority + 1) << I915_USER_PRIORITY_SHIFT) - ffs(p->used);
+	return to_priolist(rb)->priority;
 }
 
 static int virtual_prio(const struct intel_engine_execlists *el)
···
 	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
-		int i;
 
-		priolist_for_each_request_consume(rq, rn, p, i) {
+		priolist_for_each_request_consume(rq, rn, p) {
 			bool merge = true;
 
 			/*
···
 	/* Flush the queued requests to the timeline list (for retiring). */
 	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
-		int i;
 
-		priolist_for_each_request_consume(rq, rn, p, i) {
+		priolist_for_each_request_consume(rq, rn, p) {
 			i915_request_mark_eio(rq);
 			__i915_request_submit(rq);
 		}
···
 
 static struct list_head *virtual_queue(struct virtual_engine *ve)
 {
-	return &ve->base.execlists.default_priolist.requests[0];
+	return &ve->base.execlists.default_priolist.requests;
 }
 
 static void rcu_virtual_context_destroy(struct work_struct *wrk)
···
 	count = 0;
 	for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) {
 		struct i915_priolist *p = rb_entry(rb, typeof(*p), node);
-		int i;
 
-		priolist_for_each_request(rq, p, i) {
+		priolist_for_each_request(rq, p) {
 			if (count++ < max - 1)
 				show_request(m, rq, "\t\t", 0);
 			else

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

···
 
 	intel_ring_advance(rq, cs);
 
-	rq->sched.attr.priority = I915_PRIORITY_MASK;
 	err = 0;
 err:
 	i915_request_get(rq);

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

···
 
 	intel_ring_advance(rq, cs);
 
-	rq->sched.attr.priority = I915_PRIORITY_MASK;
 	err = 0;
 err:
 	i915_request_get(rq);

drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c

···
 	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
-		int i;
 
-		priolist_for_each_request_consume(rq, rn, p, i) {
+		priolist_for_each_request_consume(rq, rn, p) {
 			if (last && rq->context != last->context) {
 				if (port == last_port)
 					goto done;
···
 	/* Flush the queued requests to the timeline list (for retiring). */
 	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
-		int i;
 
-		priolist_for_each_request_consume(rq, rn, p, i) {
+		priolist_for_each_request_consume(rq, rn, p) {
 			list_del_init(&rq->sched.link);
 			__i915_request_submit(rq);
 			dma_fence_set_error(&rq->fence, -EIO);

drivers/gpu/drm/i915/i915_priolist_types.h

···
 #define I915_USER_PRIORITY_SHIFT 0
 #define I915_USER_PRIORITY(x) ((x) << I915_USER_PRIORITY_SHIFT)
 
-#define I915_PRIORITY_COUNT BIT(I915_USER_PRIORITY_SHIFT)
-#define I915_PRIORITY_MASK (I915_PRIORITY_COUNT - 1)
-
 /* Smallest priority value that cannot be bumped. */
-#define I915_PRIORITY_INVALID (INT_MIN | (u8)I915_PRIORITY_MASK)
+#define I915_PRIORITY_INVALID (INT_MIN)
 
 /*
  * Requests containing performance queries must not be preempted by
···
 #define I915_PRIORITY_BARRIER (I915_PRIORITY_UNPREEMPTABLE - 1)
 
 struct i915_priolist {
-	struct list_head requests[I915_PRIORITY_COUNT];
+	struct list_head requests;
 	struct rb_node node;
-	unsigned long used;
 	int priority;
 };
 

drivers/gpu/drm/i915/i915_scheduler.c

···
 static void assert_priolists(struct intel_engine_execlists * const execlists)
 {
 	struct rb_node *rb;
-	long last_prio, i;
+	long last_prio;
 
 	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		return;
···
 
 		GEM_BUG_ON(p->priority > last_prio);
 		last_prio = p->priority;
-
-		GEM_BUG_ON(!p->used);
-		for (i = 0; i < ARRAY_SIZE(p->requests); i++) {
-			if (list_empty(&p->requests[i]))
-				continue;
-
-			GEM_BUG_ON(!(p->used & BIT(i)));
-		}
 	}
 }
 
···
 	struct i915_priolist *p;
 	struct rb_node **parent, *rb;
 	bool first = true;
-	int idx, i;
 
 	lockdep_assert_held(&engine->active.lock);
 	assert_priolists(execlists);
 
-	/* buckets sorted from highest [in slot 0] to lowest priority */
-	idx = I915_PRIORITY_COUNT - (prio & I915_PRIORITY_MASK) - 1;
 	prio >>= I915_USER_PRIORITY_SHIFT;
 	if (unlikely(execlists->no_priolist))
 		prio = I915_PRIORITY_NORMAL;
···
 			parent = &rb->rb_right;
 			first = false;
 		} else {
-			goto out;
+			return &p->requests;
 		}
 	}
 
···
 	}
 
 	p->priority = prio;
-	for (i = 0; i < ARRAY_SIZE(p->requests); i++)
-		INIT_LIST_HEAD(&p->requests[i]);
+	INIT_LIST_HEAD(&p->requests);
+
 	rb_link_node(&p->node, rb, parent);
 	rb_insert_color_cached(&p->node, &execlists->queue, first);
-	p->used = 0;
 
-out:
-	p->used |= BIT(idx);
-	return &p->requests[idx];
+	return &p->requests;
 }
 
 void __i915_priolist_free(struct i915_priolist *p)
···
 	spin_unlock_irq(&schedule_lock);
 }
 
-static void __bump_priority(struct i915_sched_node *node, unsigned int bump)
-{
-	struct i915_sched_attr attr = node->attr;
-
-	if (attr.priority & bump)
-		return;
-
-	attr.priority |= bump;
-	__i915_schedule(node, &attr);
-}
-
-void i915_schedule_bump_priority(struct i915_request *rq, unsigned int bump)
-{
-	unsigned long flags;
-
-	GEM_BUG_ON(bump & ~I915_PRIORITY_MASK);
-	if (READ_ONCE(rq->sched.attr.priority) & bump)
-		return;
-
-	spin_lock_irqsave(&schedule_lock, flags);
-	__bump_priority(&rq->sched, bump);
-	spin_unlock_irqrestore(&schedule_lock, flags);
-}
-
 void i915_sched_node_init(struct i915_sched_node *node)
 {
 	INIT_LIST_HEAD(&node->signalers_list);
···
 	if (!global.slab_dependencies)
 		return -ENOMEM;
 
-	global.slab_priorities = KMEM_CACHE(i915_priolist,
-					    SLAB_HWCACHE_ALIGN);
+	global.slab_priorities = KMEM_CACHE(i915_priolist, 0);
 	if (!global.slab_priorities)
 		goto err_priorities;
 

drivers/gpu/drm/i915/i915_scheduler.h

···
 
 struct drm_printer;
 
-#define priolist_for_each_request(it, plist, idx) \
-	for (idx = 0; idx < ARRAY_SIZE((plist)->requests); idx++) \
-		list_for_each_entry(it, &(plist)->requests[idx], sched.link)
+#define priolist_for_each_request(it, plist) \
+	list_for_each_entry(it, &(plist)->requests, sched.link)
 
-#define priolist_for_each_request_consume(it, n, plist, idx) \
-	for (; \
-	     (plist)->used ? (idx = __ffs((plist)->used)), 1 : 0; \
-	     (plist)->used &= ~BIT(idx)) \
-		list_for_each_entry_safe(it, n, \
-					 &(plist)->requests[idx], \
-					 sched.link)
+#define priolist_for_each_request_consume(it, n, plist) \
+	list_for_each_entry_safe(it, n, &(plist)->requests, sched.link)
 
 void i915_sched_node_init(struct i915_sched_node *node);
 void i915_sched_node_reinit(struct i915_sched_node *node);
···
 
 void i915_schedule(struct i915_request *request,
 		   const struct i915_sched_attr *attr);
-
-void i915_schedule_bump_priority(struct i915_request *rq, unsigned int bump);
 
 struct list_head *
 i915_sched_lookup_priolist(struct intel_engine_cs *engine, int prio);