[PATCH 3/7] x86: re-work memset()

[Jan Beulich <jbeulich@xxxxxxxx>]

Move the function to its own assembly file. Having it in C just for the
entire body to be an asm() isn't really helpful. Then have two flavors:
A "basic" version using qword steps for the bulk of the operation, and an
ERMS version for modern hardware, to be substituted in via alternatives
patching.

Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
---
We may want to consider branching over the REP STOSQ as well, if the
number of qwords turns out to be zero.
We may also want to consider using non-REP STOS{L,W,B} for the tail.

--- a/xen/arch/x86/Makefile
+++ b/xen/arch/x86/Makefile
@@ -43,6 +43,7 @@ obj-$(CONFIG_INDIRECT_THUNK) += indirect
 obj-y += ioport_emulate.o
 obj-y += irq.o
 obj-$(CONFIG_KEXEC) += machine_kexec.o
+obj-y += memset.o
 obj-y += mm.o x86_64/mm.o
 obj-$(CONFIG_HVM) += monitor.o
 obj-y += mpparse.o
--- /dev/null
+++ b/xen/arch/x86/memset.S
@@ -0,0 +1,31 @@
+#include <asm/asm_defns.h>
+
+.macro memset
+        and     $7, %edx
+        shr     $3, %rcx
+        movzbl  %sil, %esi
+        mov     $0x0101010101010101, %rax
+        imul    %rsi, %rax
+        mov     %rdi, %rsi
+        rep stosq
+        or      %edx, %ecx
+        jz      0f
+        rep stosb
+0:
+        mov     %rsi, %rax
+        ret
+.endm
+
+.macro memset_erms
+        mov     %esi, %eax
+        mov     %rdi, %rsi
+        rep stosb
+        mov     %rsi, %rax
+        ret
+.endm
+
+ENTRY(memset)
+        mov     %rdx, %rcx
+        ALTERNATIVE memset, memset_erms, X86_FEATURE_ERMS
+        .type memset, @function
+        .size memset, . - memset
--- a/xen/arch/x86/string.c
+++ b/xen/arch/x86/string.c
@@ -22,19 +22,6 @@ void *(memcpy)(void *dest, const void *s
     return dest;
 }
 
-void *(memset)(void *s, int c, size_t n)
-{
-    long d0, d1;
-
-    asm volatile (
-        "rep stosb"
-        : "=&c" (d0), "=&D" (d1)
-        : "a" (c), "1" (s), "0" (n)
-        : "memory");
-
-    return s;
-}
-
 void *(memmove)(void *dest, const void *src, size_t n)
 {
     long d0, d1, d2;