| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Wed, 30 Aug 2023 20:57:22 +0700
From: Ammar Faizi <ammarfaizi2@...weeb.org>
To: Willy Tarreau <w@....eu>,
Thomas Weißschuh <linux@...ssschuh.net>
Cc: Ammar Faizi <ammarfaizi2@...weeb.org>,
Nicholas Rosenberg <inori@...x.org>,
Alviro Iskandar Setiawan <alviro.iskandar@...weeb.org>,
Michael William Jonathan <moe@...weeb.org>,
GNU/Weeb Mailing List <gwml@...r.gnuweeb.org>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: [RFC PATCH v1 1/5] tools/nolibc: x86-64: Use `rep movsb` for `memcpy()` and `memmove()`
Simplify memcpy() and memmove() on the x86-64 arch.
The x86-64 arch has a 'rep movsb' instruction, which can perform
memcpy() using only a single instruction, given:
%rdi = destination
%rsi = source
%rcx = length
Additionally, it can also handle the overlapping case by setting DF=1
(backward copy), which can be used as the memmove() implementation.
Before this patch:
```
00000000000010ab <memmove>:
10ab: 48 89 f8 mov %rdi,%rax
10ae: 31 c9 xor %ecx,%ecx
10b0: 48 39 f7 cmp %rsi,%rdi
10b3: 48 83 d1 ff adc $0xffffffffffffffff,%rcx
10b7: 48 85 d2 test %rdx,%rdx
10ba: 74 25 je 10e1 <memmove+0x36>
10bc: 48 83 c9 01 or $0x1,%rcx
10c0: 48 39 f0 cmp %rsi,%rax
10c3: 48 c7 c7 ff ff ff ff mov $0xffffffffffffffff,%rdi
10ca: 48 0f 43 fa cmovae %rdx,%rdi
10ce: 48 01 cf add %rcx,%rdi
10d1: 44 8a 04 3e mov (%rsi,%rdi,1),%r8b
10d5: 44 88 04 38 mov %r8b,(%rax,%rdi,1)
10d9: 48 01 cf add %rcx,%rdi
10dc: 48 ff ca dec %rdx
10df: 75 f0 jne 10d1 <memmove+0x26>
10e1: c3 ret
00000000000010e2 <memcpy>:
10e2: 48 89 f8 mov %rdi,%rax
10e5: 48 85 d2 test %rdx,%rdx
10e8: 74 12 je 10fc <memcpy+0x1a>
10ea: 31 c9 xor %ecx,%ecx
10ec: 40 8a 3c 0e mov (%rsi,%rcx,1),%dil
10f0: 40 88 3c 08 mov %dil,(%rax,%rcx,1)
10f4: 48 ff c1 inc %rcx
10f7: 48 39 ca cmp %rcx,%rdx
10fa: 75 f0 jne 10ec <memcpy+0xa>
10fc: c3 ret
```
After this patch:
```
0000000000001093 <memmove>:
1093: 48 89 f8 mov %rdi,%rax
1096: 48 89 d1 mov %rdx,%rcx
1099: 48 8d 7c 0f ff lea -0x1(%rdi,%rcx,1),%rdi
109e: 48 8d 74 0e ff lea -0x1(%rsi,%rcx,1),%rsi
10a3: fd std
10a4: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi)
10a6: fc cld
10a7: c3 ret
00000000000010a8 <memcpy>:
10a8: 48 89 f8 mov %rdi,%rax
10ab: 48 89 d1 mov %rdx,%rcx
10ae: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi)
10b0: c3 ret
```
Signed-off-by: Ammar Faizi <ammarfaizi2@...weeb.org>
---
tools/include/nolibc/arch-x86_64.h | 28 ++++++++++++++++++++++++++++
tools/include/nolibc/string.h | 4 ++++
2 files changed, 32 insertions(+)
diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h
index e5ccb926c90306b6..c5162170a2ccdff1 100644
--- a/tools/include/nolibc/arch-x86_64.h
+++ b/tools/include/nolibc/arch-x86_64.h
@@ -173,4 +173,32 @@ void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_
__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);
+
+__asm__ (
+".section .text.nolibc_memmove\n"
+".weak memmove\n"
+"memmove:\n"
+ "movq %rdi, %rax\n"
+ "movq %rdx, %rcx\n"
+ "leaq -1(%rdi, %rcx), %rdi\n"
+ "leaq -1(%rsi, %rcx), %rsi\n"
+ "std\n"
+ "rep movsb\n"
+ "cld\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"
+);
+
#endif /* _NOLIBC_ARCH_X86_64_H */
diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h
index 0c2e06c7c4772bc6..6eca267ec6fa7177 100644
--- a/tools/include/nolibc/string.h
+++ b/tools/include/nolibc/string.h
@@ -49,6 +49,7 @@ void *_nolibc_memcpy_down(void *dst, const void *src, size_t len)
return dst;
}
+#ifndef NOLIBC_ARCH_HAS_MEMMOVE
/* might be ignored by the compiler without -ffreestanding, then found as
* missing.
*/
@@ -72,13 +73,16 @@ void *memmove(void *dst, const void *src, size_t 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 */
/* might be ignored by the compiler without -ffreestanding, then found as
* missing.
--
Ammar Faizi
Powered by blists - more mailing lists