drm/i915: Stop storing the ring size in the ring pointer (v3)

Previously, we were storing the ring size in the ring pointer before it
was actually allocated.  We would then guard setting the ring size on
checking for CONTEXT_ALLOC_BIT.  This is error-prone at best and really
only saves us a few bytes on something that already burns at least 4K.
Instead, this patch adds a new ring_size field and makes everything use
that.

v2 (Daniel Vetter):
 - Replace 512 * SZ_4K with SZ_2M

v2 (Jason Ekstrand):
 - Rebase on top of page migration code

Signed-off-by: Jason Ekstrand <[email protected]>
Reviewed-by: Daniel Vetter <[email protected]>
Signed-off-by: Daniel Vetter <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: gfxstrand

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

@@ -211,8 +211,7 @@ static void intel_context_set_gem(struct intel_context *ce,
 	GEM_BUG_ON(rcu_access_pointer(ce->gem_context));
 	RCU_INIT_POINTER(ce->gem_context, ctx);
 
-	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))
-		ce->ring = __intel_context_ring_size(SZ_16K);
+	ce->ring_size = SZ_16K;
 
 	if (rcu_access_pointer(ctx->vm)) {
 		struct i915_address_space *vm;

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

@@ -371,7 +371,8 @@ intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine)
 	ce->engine = engine;
 	ce->ops = engine->cops;
 	ce->sseu = engine->sseu;
-	ce->ring = __intel_context_ring_size(SZ_4K);
+	ce->ring = NULL;
+	ce->ring_size = SZ_4K;
 
 	ewma_runtime_init(&ce->runtime.avg);
 

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

@@ -175,11 +175,6 @@ int intel_context_prepare_remote_request(struct intel_context *ce,
 
 struct i915_request *intel_context_create_request(struct intel_context *ce);
 
-static inline struct intel_ring *__intel_context_ring_size(u64 sz)
-{
-	return u64_to_ptr(struct intel_ring, sz);
-}
-
 static inline bool intel_context_is_barrier(const struct intel_context *ce)
 {
 	return test_bit(CONTEXT_BARRIER_BIT, &ce->flags);

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

@@ -82,6 +82,7 @@ struct intel_context {
 	spinlock_t signal_lock; /* protects signals, the list of requests */
 
 	struct i915_vma *state;
+	u32 ring_size;
 	struct intel_ring *ring;
 	struct intel_timeline *timeline;
 

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

@@ -807,7 +807,8 @@ intel_engine_create_pinned_context(struct intel_engine_cs *engine,
 
 	__set_bit(CONTEXT_BARRIER_BIT, &ce->flags);
 	ce->timeline = page_pack_bits(NULL, hwsp);
-	ce->ring = __intel_context_ring_size(ring_size);
+	ce->ring = NULL;
+	ce->ring_size = ring_size;
 
 	i915_vm_put(ce->vm);
 	ce->vm = i915_vm_get(vm);

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

@@ -845,7 +845,7 @@ int lrc_alloc(struct intel_context *ce, struct intel_engine_cs *engine)
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	ring = intel_engine_create_ring(engine, (unsigned long)ce->ring);
+	ring = intel_engine_create_ring(engine, ce->ring_size);
 	if (IS_ERR(ring)) {
 		err = PTR_ERR(ring);
 		goto err_vma;

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

@@ -232,7 +232,8 @@ struct intel_context *intel_migrate_create_context(struct intel_migrate *m)
 	if (IS_ERR(ce))
 		return ce;
 
-	ce->ring = __intel_context_ring_size(SZ_256K);
+	ce->ring = NULL;
+	ce->ring_size = SZ_256K;
 
 	i915_vm_put(ce->vm);
 	ce->vm = i915_vm_get(m->context->vm);

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

@@ -2810,7 +2810,7 @@ static int __live_preempt_ring(struct intel_engine_cs *engine,
 			goto err_ce;
 		}
 
-		tmp->ring = __intel_context_ring_size(ring_sz);
+		tmp->ring_size = ring_sz;
 
 		err = intel_context_pin(tmp);
 		if (err) {

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

@@ -28,7 +28,7 @@ static struct intel_context *mocs_context_create(struct intel_engine_cs *engine)
 		return ce;
 
 	/* We build large requests to read the registers from the ring */
-	ce->ring = __intel_context_ring_size(SZ_16K);
+	ce->ring_size = SZ_16K;
 
 	return ce;
 }

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

@@ -874,7 +874,7 @@ static int create_watcher(struct hwsp_watcher *w,
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
-	ce->ring = __intel_context_ring_size(ringsz);
+	ce->ring_size = ringsz;
 	w->rq = intel_context_create_request(ce);
 	intel_context_put(ce);
 	if (IS_ERR(w->rq))