[Intel-gfx] [PATCH 01/17] drm/i915: Skip holding an object reference for execbuf preparation

[Chris Wilson]

This is a golden oldie! We can shave a couple of locked instructions for
about 10% of the per-object overhead by not taking an extra kref whilst
reserving objects for an execbuf. Due to lock management this is safe,
as we cannot lose the original object reference without the lock.
Equally, because this relies on the heavy BKL^W struct_mutex, it is also
likely to be only a temporary optimisation until we have fine grained
locking. (That's what we said 5 years ago, so there's probably another
10 years before we get around to finer grained locking!)

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 601156c353cc..6baad503764d 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -164,7 +164,6 @@ eb_lookup_vmas(struct eb_vmas *eb,
 			goto err;
 		}
 
-		i915_gem_object_get(obj);
 		list_add_tail(&obj->obj_exec_link, &objects);
 	}
 	spin_unlock(&file->table_lock);
@@ -275,7 +274,6 @@ static void eb_destroy(struct eb_vmas *eb)
 				       exec_list);
 		list_del_init(&vma->exec_list);
 		i915_gem_execbuffer_unreserve_vma(vma);
-		i915_vma_put(vma);
 	}
 	kfree(eb);
 }
@@ -1017,7 +1015,6 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 		vma = list_first_entry(&eb->vmas, struct i915_vma, exec_list);
 		list_del_init(&vma->exec_list);
 		i915_gem_execbuffer_unreserve_vma(vma);
-		i915_vma_put(vma);
 	}
 
 	mutex_unlock(&dev->struct_mutex);
@@ -1424,7 +1421,6 @@ i915_gem_execbuffer_parse(struct intel_engine_cs *engine,
 
 	vma->exec_entry = shadow_exec_entry;
 	vma->exec_entry->flags = __EXEC_OBJECT_HAS_PIN;
-	i915_gem_object_get(shadow_batch_obj);
 	list_add_tail(&vma->exec_list, &eb->vmas);
 
 out:
-- 
2.9.3