x86, mem: Don't implement forward memmove() as memcpy()

memmove() allow source and destination address to be overlap, but
there is no such limitation for memcpy().  Therefore, explicitly
implement memmove() in both the forwards and backward directions, to
give us the ability to optimize memcpy().

Signed-off-by: Ma Ling <ling.ma@intel.com>
LKML-Reference: <C10D3FB0CD45994C8A51FEC1227CE22F0E483AD86A@shsmsx502.ccr.corp.intel.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

1 files changed, 27 insertions, 11 deletions

diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c
index 5415a9d06f53..be424dfcf365 100644
--- a/arch/x86/lib/memcpy_32.c
+++ b/arch/x86/lib/memcpy_32.c
@@ -25,19 +25,35 @@ void *memmove(void *dest, const void *src, size_t n)
         int d0, d1, d2;
 
         if (dest < src) {
-                memcpy(dest, src, n);
+                if ((dest + n) < src)
+                         return memcpy(dest, src, n);
+                else
+                        __asm__ __volatile__(
+                                "rep\n\t"
+                                "movsb\n\t"
+                                : "=&c" (d0), "=&S" (d1), "=&D" (d2)
+                                :"0" (n),
+                                 "1" (src),
+                                 "2" (dest)
+                                :"memory");
+
         } else {
-                __asm__ __volatile__(
-                        "std\n\t"
-                        "rep\n\t"
-                        "movsb\n\t"
-                        "cld"
-                        : "=&c" (d0), "=&S" (d1), "=&D" (d2)
-                        :"0" (n),
-                         "1" (n-1+src),
-                         "2" (n-1+dest)
-                        :"memory");
+
+                if((src + count) < dest)
+                        return memcpy(dest, src, count);
+                else
+                        __asm__ __volatile__(
+                                "std\n\t"
+                                "rep\n\t"
+                                "movsb\n\t"
+                                "cld"
+                                : "=&c" (d0), "=&S" (d1), "=&D" (d2)
+                                :"0" (n),
+                                 "1" (n-1+src),
+                                 "2" (n-1+dest)
+                                :"memory");
         }
+
         return dest;
 }
 EXPORT_SYMBOL(memmove);