[RFC PATCH v2 2/4] tools/nolibc: x86-64: Use `rep stosb` for `memset()`

[Ammar Faizi]

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 code size shrink:
  - 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>
---
 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 297ffa364b2312eb..ed01b130e25c6740 100644
--- a/tools/include/nolibc/arch-x86_64.h
+++ b/tools/include/nolibc/arch-x86_64.h
@@ -162,50 +162,63 @@
  *
  */
 void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
 {
 	__asm__ volatile (
 		"xor  %ebp, %ebp\n"       /* zero the stack frame                            */
 		"mov  %rsp, %rdi\n"       /* save stack pointer to %rdi, as arg1 of _start_c */
 		"and  $-16, %rsp\n"       /* %rsp must be 16-byte aligned before call        */
 		"call _start_c\n"         /* transfer to c runtime                           */
 		"hlt\n"                   /* ensure it does not return                       */
 	);
 	__builtin_unreachable();
 }
 
 #define NOLIBC_ARCH_HAS_MEMMOVE
 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\n"
 ".weak memmove\n"
 "memmove:\n"
 	"movq %rdx, %rcx\n"
 	"movq %rdi, %rdx\n"
 	"movq %rdi, %rax\n"
 	"subq %rsi, %rdx\n"
 	"cmpq %rcx, %rdx\n"
 	"jnb  .Lforward_copy\n"
 	"leaq -1(%rdi, %rcx, 1), %rdi\n"
 	"leaq -1(%rsi, %rcx, 1), %rsi\n"
 	"std\n"
 	"rep movsb\n"
 	"cld\n"
 	"retq\n"
 ".Lforward_copy:\n"
 	"rep movsb\n"
 	"retq\n"
 
 ".section .text.nolibc_memcpy\n"
 ".weak memcpy\n"
 "memcpy:\n"
 	"movq %rdi, %rax\n"
 	"movq %rdx, %rcx\n"
 	"rep movsb\n"
 	"retq\n"
+
+".section .text.nolibc_memset\n"
+".weak memset\n"
+"memset:\n"
+	"xchg  %eax, %esi\n"
+	"movq  %rdx, %rcx\n"
+	"pushq %rdi\n"
+	"rep stosb\n"
+	"popq  %rax\n"
+	"retq\n"
 );
 
 #endif /* _NOLIBC_ARCH_X86_64_H */
diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h
index 6eca267ec6fa7177..1bad6121ef8c4ab5 100644
--- a/tools/include/nolibc/string.h
+++ b/tools/include/nolibc/string.h
@@ -67,55 +67,57 @@ void *memmove(void *dst, const void *src, size_t len)
 	}
 
 	while (len) {
 		pos += dir;
 		((char *)dst)[pos] = ((const char *)src)[pos];
 		len--;
 	}
 	return dst;
 }
 #endif /* #ifndef NOLIBC_ARCH_HAS_MEMMOVE */
 
 #ifndef NOLIBC_ARCH_HAS_MEMCPY
 /* must be exported, as it's used by libgcc on ARM */
 __attribute__((weak,unused,section(".text.nolibc_memcpy")))
 void *memcpy(void *dst, const void *src, size_t len)
 {
 	return _nolibc_memcpy_up(dst, src, len);
 }
 #endif /* #ifndef NOLIBC_ARCH_HAS_MEMCPY */
 
+#ifndef NOLIBC_ARCH_HAS_MEMSET
 /* might be ignored by the compiler without -ffreestanding, then found as
  * missing.
  */
 __attribute__((weak,unused,section(".text.nolibc_memset")))
 void *memset(void *dst, int b, size_t len)
 {
 	char *p = dst;
 
 	while (len--) {
 		/* prevent gcc from recognizing memset() here */
 		__asm__ volatile("");
 		*(p++) = b;
 	}
 	return dst;
 }
+#endif /* #ifndef NOLIBC_ARCH_HAS_MEMSET */
 
 static __attribute__((unused))
 char *strchr(const char *s, int c)
 {
 	while (*s) {
 		if (*s == (char)c)
 			return (char *)s;
 		s++;
 	}
 	return NULL;
 }
 
 static __attribute__((unused))
 int strcmp(const char *a, const char *b)
 {
 	unsigned int c;
 	int diff;
 
 	while (!(diff = (unsigned char)*a++ - (c = (unsigned char)*b++)) && c)
 		;
-- 
Ammar Faizi