cacheable_memzero uses dcbz instruction and is more efficient than
memset(0) when the destination is in RAM
This patch renames memset as generic_memset, and defines memset
as a prolog to cacheable_memzero. This prolog checks if the byte
to set is 0. If not, it falls back to generic_memcpy()
cacheable_memzero disappears as it is not referenced anywhere anymore
Signed-off-by: Christophe Leroy <christophe.le...@c-s.fr>
---
arch/powerpc/lib/copy_32.S | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index 55f19f9..0b4f954 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -74,9 +74,9 @@ CACHELINE_MASK = (L1_CACHE_BYTES-1)
* to set them to zero. This requires that the destination
* area is cacheable. -- paulus
*/
-_GLOBAL(cacheable_memzero)
- mr r5,r4
- li r4,0
+_GLOBAL(memset)
+ cmplwi r4,0
+ bne- generic_memset
addi r6,r3,-4
cmplwi 0,r5,4
blt 7f
@@ -117,7 +117,7 @@ _GLOBAL(cacheable_memzero)
bdnz 8b
blr
-_GLOBAL(memset)
+_GLOBAL(generic_memset)
rlwimi r4,r4,8,16,23
rlwimi r4,r4,16,0,15
addi r6,r3,-4
--
2.1.0
_______________________________________________
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev
