drm/i915: Allocate intel_engine_cs structure only for the enabled engines

With the possibility of addition of many more number of rings in future,
the drm_i915_private structure could bloat as an array, of type
intel_engine_cs, is embedded inside it.
	struct intel_engine_cs engine[I915_NUM_ENGINES];
Though this is still fine as generally there is only a single instance of
drm_i915_private structure used, but not all of the possible rings would be
enabled or active on most of the platforms. Some memory can be saved by
allocating intel_engine_cs structure only for the enabled/active engines.
Currently the engine/ring ID is kept static and dev_priv->engine[] is simply
indexed using the enums defined in intel_engine_id.
To save memory and continue using the static engine/ring IDs, 'engine' is
defined as an array of pointers.
	struct intel_engine_cs *engine[I915_NUM_ENGINES];
dev_priv->engine[engine_ID] will be NULL for disabled engine instances.

There is a text size reduction of 928 bytes, from 1028200 to 1027272, for
i915.o file (but for i915.ko file text size remain same as 1193131 bytes).

v2:
- Remove the engine iterator field added in drm_i915_private structure,
  instead pass a local iterator variable to the for_each_engine**
  macros. (Chris)
- Do away with intel_engine_initialized() and instead directly use the
  NULL pointer check on engine pointer. (Chris)

v3:
- Remove for_each_engine_id() macro, as the updated macro for_each_engine()
  can be used in place of it. (Chris)
- Protect the access to Render engine Fault register with a NULL check, as
  engine specific init is done later in Driver load sequence.

v4:
- Use !!dev_priv->engine[VCS] style for the engine check in getparam. (Chris)
- Kill the superfluous init_engine_lists().

v5:
- Cleanup the intel_engines_init() & intel_engines_setup(), with respect to
  allocation of intel_engine_cs structure. (Chris)

v6:
- Rebase.

v7:
- Optimize the for_each_engine_masked() macro. (Chris)
- Change the type of 'iter' local variable to enum intel_engine_id. (Chris)
- Rebase.

v8: Rebase.

v9: Rebase.

v10:
- For index calculation use engine ID instead of pointer based arithmetic in
  intel_engine_sync_index() as engine pointers are not contiguous now (Chris)
- For appropriateness, rename local enum variable 'iter' to 'id'. (Joonas)
- Use for_each_engine macro for cleanup in intel_engines_init() and remove
  check for NULL engine pointer in cleanup() routines. (Joonas)

v11: Rebase.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Akash Goel <akash.goel@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1476378888-7372-1-git-send-email-akash.goel@intel.com

1 files changed, 8 insertions, 7 deletions

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 729f373782e2..e107455b0168 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1228,7 +1228,7 @@ static int gen8_rcs_signal(struct drm_i915_gem_request *req)
 	if (ret)
 		return ret;
 
-	for_each_engine_id(waiter, dev_priv, id) {
+	for_each_engine(waiter, dev_priv, id) {
 		u64 gtt_offset = req->engine->semaphore.signal_ggtt[id];
 		if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
 			continue;
@@ -1265,7 +1265,7 @@ static int gen8_xcs_signal(struct drm_i915_gem_request *req)
 	if (ret)
 		return ret;
 
-	for_each_engine_id(waiter, dev_priv, id) {
+	for_each_engine(waiter, dev_priv, id) {
 		u64 gtt_offset = req->engine->semaphore.signal_ggtt[id];
 		if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
 			continue;
@@ -1292,6 +1292,7 @@ static int gen6_signal(struct drm_i915_gem_request *req)
 	struct intel_ring *ring = req->ring;
 	struct drm_i915_private *dev_priv = req->i915;
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int ret, num_rings;
 
 	num_rings = INTEL_INFO(dev_priv)->num_rings;
@@ -1299,7 +1300,7 @@ static int gen6_signal(struct drm_i915_gem_request *req)
 	if (ret)
 		return ret;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		i915_reg_t mbox_reg;
 
 		if (!(BIT(engine->hw_id) & GEN6_SEMAPHORES_MASK))
@@ -2091,9 +2092,6 @@ void intel_engine_cleanup(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv;
 
-	if (!intel_engine_initialized(engine))
-		return;
-
 	dev_priv = engine->i915;
 
 	if (engine->buffer) {
@@ -2120,13 +2118,16 @@ void intel_engine_cleanup(struct intel_engine_cs *engine)
 	intel_ring_context_unpin(dev_priv->kernel_context, engine);
 
 	engine->i915 = NULL;
+	dev_priv->engine[engine->id] = NULL;
+	kfree(engine);
 }
 
 void intel_legacy_submission_resume(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
-	for_each_engine(engine, dev_priv) {
+	for_each_engine(engine, dev_priv, id) {
 		engine->buffer->head = engine->buffer->tail;
 		engine->buffer->last_retired_head = -1;
 	}