Add mempcpy implementation

A GNU extension that returns dst + size instead of dst. It's a nice
shortcut when copying strings with a known size or back-to-back blocks
and you have to do it often.

May of course be called directly or alternately through
__builtin_mempcpy in some compiler versions.

For ASM on native targets, it is implemented as an alternate entrypoint
to memcpy which adds minimal code and overhead.

Change-Id: I4cbb3483f6df3c1007247fe0a95fd7078737462b

1 files changed, 9 insertions, 1 deletions

diff --git a/firmware/asm/arm/memcpy.S b/firmware/asm/arm/memcpy.S
index 2a55fb5656..83d43293e6 100644
--- a/firmware/asm/arm/memcpy.S
+++ b/firmware/asm/arm/memcpy.S
@@ -36,17 +36,25 @@
 #endif
 
 /* Prototype: void *memcpy(void *dest, const void *src, size_t n); */
+/* Prototype: void *mempcpy(void *dest, const void *src, size_t n); */
 
     .section    .icode,"ax",%progbits
 
     .align      2
     .global     memcpy
     .type       memcpy,%function
+    .global     mempcpy
+    .type       mempcpy,%function
+
+mempcpy:
+        add     r3, r0, r2
+        stmfd   sp!, {r3, r4, lr}
+        b   0f
 
 memcpy:
         stmfd   sp!, {r0, r4, lr}
 
-        subs    r2, r2, #4
+0:      subs    r2, r2, #4
         blt 8f
         ands    ip, r0, #3
         bne 9f