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
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 3808138..15f21c6 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5367,6 +5367,7 @@
static void gen9_enable_rc6(struct drm_i915_private *dev_priv)
{
struct intel_engine_cs *engine;
+ enum intel_engine_id id;
uint32_t rc6_mask = 0;
/* 1a: Software RC state - RC0 */
@@ -5388,7 +5389,7 @@
I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16);
I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
- for_each_engine(engine, dev_priv)
+ for_each_engine(engine, dev_priv, id)
I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
if (HAS_GUC(dev_priv))
@@ -5433,6 +5434,7 @@
static void gen8_enable_rps(struct drm_i915_private *dev_priv)
{
struct intel_engine_cs *engine;
+ enum intel_engine_id id;
uint32_t rc6_mask = 0;
/* 1a: Software RC state - RC0 */
@@ -5449,7 +5451,7 @@
I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
- for_each_engine(engine, dev_priv)
+ for_each_engine(engine, dev_priv, id)
I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
I915_WRITE(GEN6_RC_SLEEP, 0);
if (IS_BROADWELL(dev_priv))
@@ -5509,6 +5511,7 @@
static void gen6_enable_rps(struct drm_i915_private *dev_priv)
{
struct intel_engine_cs *engine;
+ enum intel_engine_id id;
u32 rc6vids, rc6_mask = 0;
u32 gtfifodbg;
int rc6_mode;
@@ -5542,7 +5545,7 @@
I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000);
I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25);
- for_each_engine(engine, dev_priv)
+ for_each_engine(engine, dev_priv, id)
I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
I915_WRITE(GEN6_RC_SLEEP, 0);
@@ -5991,6 +5994,7 @@
static void cherryview_enable_rps(struct drm_i915_private *dev_priv)
{
struct intel_engine_cs *engine;
+ enum intel_engine_id id;
u32 gtfifodbg, val, rc6_mode = 0, pcbr;
WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
@@ -6017,7 +6021,7 @@
I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
- for_each_engine(engine, dev_priv)
+ for_each_engine(engine, dev_priv, id)
I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
I915_WRITE(GEN6_RC_SLEEP, 0);
@@ -6079,6 +6083,7 @@
static void valleyview_enable_rps(struct drm_i915_private *dev_priv)
{
struct intel_engine_cs *engine;
+ enum intel_engine_id id;
u32 gtfifodbg, val, rc6_mode = 0;
WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
@@ -6118,7 +6123,7 @@
I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000);
I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25);
- for_each_engine(engine, dev_priv)
+ for_each_engine(engine, dev_priv, id)
I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
I915_WRITE(GEN6_RC6_THRESHOLD, 0x557);
@@ -6801,7 +6806,7 @@
if (READ_ONCE(dev_priv->rps.enabled))
goto out;
- rcs = &dev_priv->engine[RCS];
+ rcs = dev_priv->engine[RCS];
if (rcs->last_context)
goto out;