Re: [Intel-gfx] [PATCH 70/73] drm/i915: Move obj->active:5 to obj->flags

[Joonas Lahtinen]

On ma, 2016-08-01 at 10:11 +0100, Chris Wilson wrote:
> We are motivated to avoid using a bitfield for obj->active for a couple
> of reasons. Firstly, we wish to document our lockless read of obj->active
> using READ_ONCE inside i915_gem_busy_ioctl() and that requires an
> integral type (i.e. not a bitfield). Secondly, gcc produces abysmal code
> when presented with a bitfield and that shows up high on the profiles of
> request tracking (mainly due to excess memory traffic as it converts
> the bitfield to a register and back and generates frequent AGI in the
> process).
> 
> v2: BIT, break up a long line in compute the other engines, new paint
> for i915_gem_object_is_active (now i915_gem_object_get_active).
> 
> Signed-off-by: Chris Wilson 

Patch reads much better now,

Reviewed-by: Joonas Lahtinen 

Regards, Joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
___
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 70/73] drm/i915: Move obj->active:5 to obj->flags

[Chris Wilson]

We are motivated to avoid using a bitfield for obj->active for a couple
of reasons. Firstly, we wish to document our lockless read of obj->active
using READ_ONCE inside i915_gem_busy_ioctl() and that requires an
integral type (i.e. not a bitfield). Secondly, gcc produces abysmal code
when presented with a bitfield and that shows up high on the profiles of
request tracking (mainly due to excess memory traffic as it converts
the bitfield to a register and back and generates frequent AGI in the
process).

v2: BIT, break up a long line in compute the other engines, new paint
for i915_gem_object_is_active (now i915_gem_object_get_active).

Signed-off-by: Chris Wilson 
---
 drivers/gpu/drm/i915/i915_debugfs.c|  2 +-
 drivers/gpu/drm/i915/i915_drv.h| 37 +-
 drivers/gpu/drm/i915/i915_gem.c| 16 ++---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 20 
 drivers/gpu/drm/i915/i915_gem_shrinker.c   |  5 ++--
 drivers/gpu/drm/i915/i915_gem_userptr.c|  2 +-
 6 files changed, 64 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c 
b/drivers/gpu/drm/i915/i915_debugfs.c
index 10a346237795..920a2de95cd5 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -91,7 +91,7 @@ static int i915_capabilities(struct seq_file *m, void *data)
 
 static char get_active_flag(struct drm_i915_gem_object *obj)
 {
-   return obj->active ? '*' : ' ';
+   return i915_gem_object_is_active(obj) ? '*' : ' ';
 }
 
 static char get_pin_flag(struct drm_i915_gem_object *obj)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 3de75e82ca76..db5dc5bd78d8 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2155,12 +2155,16 @@ struct drm_i915_gem_object {
 
struct list_head batch_pool_link;
 
+   unsigned long flags;
/**
 * This is set if the object is on the active lists (has pending
 * rendering and so a non-zero seqno), and is not set if it i s on
 * inactive (ready to be unbound) list.
 */
-   unsigned int active:I915_NUM_ENGINES;
+#define I915_BO_ACTIVE_SHIFT 0
+#define I915_BO_ACTIVE_MASK ((1 << I915_NUM_ENGINES) - 1)
+#define __I915_BO_ACTIVE(bo) \
+   ((READ_ONCE((bo)->flags) >> I915_BO_ACTIVE_SHIFT) & I915_BO_ACTIVE_MASK)
 
/**
 * This is set if the object has been written to since last bound
@@ -2325,6 +2329,37 @@ i915_gem_object_has_struct_page(const struct 
drm_i915_gem_object *obj)
return obj->ops->flags & I915_GEM_OBJECT_HAS_STRUCT_PAGE;
 }
 
+static inline unsigned long
+i915_gem_object_get_active(const struct drm_i915_gem_object *obj)
+{
+   return (obj->flags >> I915_BO_ACTIVE_SHIFT) & I915_BO_ACTIVE_MASK;
+}
+
+static inline bool
+i915_gem_object_is_active(const struct drm_i915_gem_object *obj)
+{
+   return i915_gem_object_get_active(obj);
+}
+
+static inline void
+i915_gem_object_set_active(struct drm_i915_gem_object *obj, int engine)
+{
+   obj->flags |= BIT(engine + I915_BO_ACTIVE_SHIFT);
+}
+
+static inline void
+i915_gem_object_clear_active(struct drm_i915_gem_object *obj, int engine)
+{
+   obj->flags &= ~BIT(engine + I915_BO_ACTIVE_SHIFT);
+}
+
+static inline bool
+i915_gem_object_has_active_engine(const struct drm_i915_gem_object *obj,
+ int engine)
+{
+   return obj->flags & BIT(engine + I915_BO_ACTIVE_SHIFT);
+}
+
 /*
  * Optimised SGL iterator for GEM objects
  */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index c4e5c7c1891b..b44a8e036373 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1354,7 +1354,7 @@ i915_gem_object_wait_rendering(struct drm_i915_gem_object 
*obj,
 
if (!readonly) {
active = obj->last_read;
-   active_mask = obj->active;
+   active_mask = i915_gem_object_get_active(obj);
} else {
active_mask = 1;
active = >last_write;
@@ -1398,7 +1398,7 @@ i915_gem_object_wait_rendering__nonblocking(struct 
drm_i915_gem_object *obj,
BUG_ON(!mutex_is_locked(>struct_mutex));
BUG_ON(!dev_priv->mm.interruptible);
 
-   active_mask = obj->active;
+   active_mask = i915_gem_object_get_active(obj);
if (!active_mask)
return 0;
 
@@ -2361,10 +2361,10 @@ i915_gem_object_retire__read(struct i915_gem_active 
*active,
struct drm_i915_gem_object *obj =
container_of(active, struct drm_i915_gem_object, 
last_read[idx]);
 
-   GEM_BUG_ON((obj->active & (1 << idx)) == 0);
+   GEM_BUG_ON(!i915_gem_object_has_active_engine(obj, idx));
 
-   obj->active &= ~(1 << idx);
-   if (obj->active)
+   i915_gem_object_clear_active(obj, idx);
+   if (i915_gem_object_is_active(obj))
return;