[Intel-gfx] [PATCH 3/5] drm/i915: Make ptr_unpack_bits() more function-like

Chris Wilson chris at chris-wilson.co.uk
Mon Apr 10 08:55:54 UTC 2017


ptr_unpack_bits() is a function-like macro, as such it is meant to be
replaceable by a function. In this case, we should be passing in the
out-param as a pointer.

Bizarrely this does affect code generation:

function                                     old     new   delta
i915_gem_object_pin_map                      409     389     -20

An improvement(?) in this case, but one can't help wonder what
strict-aliasing optimisations we are preventing.

The generated code looks identical in using ptr_unpack_bits (no extra
motions to stack, the pointer and bits appear to be kept in registers),
the difference appears to be code ordering and with a reorder it is able
to use smaller forward jumps.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c   | 2 +-
 drivers/gpu/drm/i915/i915_utils.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 79b5eab5ae83..f39b36a8622a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2560,7 +2560,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 	}
 	GEM_BUG_ON(!obj->mm.pages);
 
-	ptr = ptr_unpack_bits(obj->mm.mapping, has_type);
+	ptr = ptr_unpack_bits(obj->mm.mapping, &has_type);
 	if (ptr && has_type != type) {
 		if (pinned) {
 			ret = -EBUSY;
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index c5455d36b617..aca11aad5da7 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -77,7 +77,7 @@
 
 #define ptr_unpack_bits(ptr, bits) ({					\
 	unsigned long __v = (unsigned long)(ptr);			\
-	(bits) = __v & ~PAGE_MASK;					\
+	*(bits) = __v & ~PAGE_MASK;					\
 	(typeof(ptr))(__v & PAGE_MASK);					\
 })
 
-- 
2.11.0



More information about the Intel-gfx mailing list