powerpc/32: Merge the new memset() with the old one
cacheable_memzero() which has become the new memset() and the old
memset() are quite similar, so just merge them.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index 0b4f954..9262071 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -75,8 +75,9 @@
* area is cacheable. -- paulus
*/
_GLOBAL(memset)
- cmplwi r4,0
- bne- generic_memset
+ rlwimi r4,r4,8,16,23
+ rlwimi r4,r4,16,0,15
+
addi r6,r3,-4
cmplwi 0,r5,4
blt 7f
@@ -85,6 +86,9 @@
andi. r0,r6,3
add r5,r0,r5
subf r6,r0,r6
+ cmplwi 0,r4,0
+ bne 2f /* Use normal procedure if r4 is not zero */
+
clrlwi r7,r6,32-LG_CACHELINE_BYTES
add r8,r7,r5
srwi r9,r8,LG_CACHELINE_BYTES
@@ -103,32 +107,8 @@
bdnz 10b
clrlwi r5,r8,32-LG_CACHELINE_BYTES
addi r5,r5,4
-2: srwi r0,r5,2
- mtctr r0
- bdz 6f
-1: stwu r4,4(r6)
- bdnz 1b
-6: andi. r5,r5,3
-7: cmpwi 0,r5,0
- beqlr
- mtctr r5
- addi r6,r6,3
-8: stbu r4,1(r6)
- bdnz 8b
- blr
-_GLOBAL(generic_memset)
- rlwimi r4,r4,8,16,23
- rlwimi r4,r4,16,0,15
- addi r6,r3,-4
- cmplwi 0,r5,4
- blt 7f
- stwu r4,4(r6)
- beqlr
- andi. r0,r6,3
- add r5,r0,r5
- subf r6,r0,r6
- srwi r0,r5,2
+2: srwi r0,r5,2
mtctr r0
bdz 6f
1: stwu r4,4(r6)