[Xen-devel] [PATCH 4/4] x86/memcpy: Reduce code size

[Andrew Cooper <andrew.cooper3@xxxxxxxxxx>]

'n % BYTES_PER_LONG' is at most 7, and doesn't need a 64bit register mov.

Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
CC: Jan Beulich <JBeulich@xxxxxxxx>

---
Admittedly very trivial, but no need to be wasteful
---
 xen/arch/x86/string.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/xen/arch/x86/string.c b/xen/arch/x86/string.c
index 3af0ea8..043ae66 100644
--- a/xen/arch/x86/string.c
+++ b/xen/arch/x86/string.c
@@ -15,7 +15,7 @@ void *memcpy(void *dest, const void *src, size_t n)
 
     asm volatile (
         "   rep ; movs"__OS" ; "
-        "   mov %4,%3        ; "
+        "   mov %k4,%k3      ; "
         "   rep ; movsb        "
         : "=&c" (d0), "=&D" (d1), "=&S" (d2)
         : "0" (n/BYTES_PER_LONG), "r" (n%BYTES_PER_LONG), "1" (dest), "2" (src)
-- 
1.7.10.4


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel