[PATCH nolibc 07/19] tools/nolibc: x86-64: Use `rep stosb` for `memset()`

[Paul E. McKenney]

From: Ammar Faizi <ammarfaizi2@xxxxxxxxxxx>

Simplify memset() on the x86-64 arch.

The x86-64 arch has a 'rep stosb' instruction, which can perform
memset() using only a single instruction, given:

    %al  = value (just like the second argument of memset())
    %rdi = destination
    %rcx = length

Before this patch:
```
  00000000000010c9 <memset>:
    10c9: 48 89 f8              mov    %rdi,%rax
    10cc: 48 85 d2              test   %rdx,%rdx
    10cf: 74 0e                 je     10df <memset+0x16>
    10d1: 31 c9                 xor    %ecx,%ecx
    10d3: 40 88 34 08           mov    %sil,(%rax,%rcx,1)
    10d7: 48 ff c1              inc    %rcx
    10da: 48 39 ca              cmp    %rcx,%rdx
    10dd: 75 f4                 jne    10d3 <memset+0xa>
    10df: c3                    ret
```

After this patch:
```
  0000000000001511 <memset>:
    1511: 96                    xchg   %eax,%esi
    1512: 48 89 d1              mov    %rdx,%rcx
    1515: 57                    push   %rdi
    1516: f3 aa                 rep stos %al,%es:(%rdi)
    1518: 58                    pop    %rax
    1519: c3                    ret
```

v2:
  - Use pushq %rdi / popq %rax (Alviro).
  - Use xchg %eax, %esi (Willy).

Link: https://lore.kernel.org/lkml/ZO9e6h2jjVIMpBJP@xxxxxx
Suggested-by: Alviro Iskandar Setiawan <alviro.iskandar@xxxxxxxxxxx>
Suggested-by: Willy Tarreau <w@xxxxxx>
Signed-off-by: Ammar Faizi <ammarfaizi2@xxxxxxxxxxx>
Reviewed-by: Alviro Iskandar Setiawan <alviro.iskandar@xxxxxxxxxxx>
Signed-off-by: Willy Tarreau <w@xxxxxx>
Signed-off-by: Thomas Weißschuh <linux@xxxxxxxxxxxxxx>
---
 tools/include/nolibc/arch-x86_64.h | 13 +++++++++++++
 tools/include/nolibc/string.h      |  2 ++
 2 files changed, 15 insertions(+)

diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h
index aece7d895153..68609f421934 100644
--- a/tools/include/nolibc/arch-x86_64.h
+++ b/tools/include/nolibc/arch-x86_64.h
@@ -179,6 +179,9 @@ void *memmove(void *dst, const void *src, size_t len);
 #define NOLIBC_ARCH_HAS_MEMCPY
 void *memcpy(void *dst, const void *src, size_t len);
 
+#define NOLIBC_ARCH_HAS_MEMSET
+void *memset(void *dst, int c, size_t len);
+
 __asm__ (
 ".section .text.nolibc_memmove_memcpy\n"
 ".weak memmove\n"
@@ -200,6 +203,16 @@ __asm__ (
 	"rep movsb\n\t"
 	"cld\n\t"
 	"retq\n"
+
+".section .text.nolibc_memset\n"
+".weak memset\n"
+"memset:\n"
+	"xchgl %eax, %esi\n\t"
+	"movq  %rdx, %rcx\n\t"
+	"pushq %rdi\n\t"
+	"rep stosb\n\t"
+	"popq  %rax\n\t"
+	"retq\n"
 );
 
 #endif /* _NOLIBC_ARCH_X86_64_H */
diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h
index 6eca267ec6fa..1bad6121ef8c 100644
--- a/tools/include/nolibc/string.h
+++ b/tools/include/nolibc/string.h
@@ -84,6 +84,7 @@ void *memcpy(void *dst, const void *src, size_t len)
 }
 #endif /* #ifndef NOLIBC_ARCH_HAS_MEMCPY */
 
+#ifndef NOLIBC_ARCH_HAS_MEMSET
 /* might be ignored by the compiler without -ffreestanding, then found as
  * missing.
  */
@@ -99,6 +100,7 @@ void *memset(void *dst, int b, size_t len)
 	}
 	return dst;
 }
+#endif /* #ifndef NOLIBC_ARCH_HAS_MEMSET */
 
 static __attribute__((unused))
 char *strchr(const char *s, int c)
-- 
2.40.1