From 5278f6def4248391a481382bd7b0042b04c829f2 Mon Sep 17 00:00:00 2001
From: Richard Qin <richard.qin.x@gmail.com>
Date: Tue, 21 Apr 2026 23:16:50 +0800
Subject: feat: add string manipulation functions derived from musl libc

This commit introduces a variety of string manipulation functions, including:
- `memmem`: Searches for a substring in a memory area.
- `memmove`: Safely copies memory areas, handling overlaps.
- `mempcpy`: Copies memory and returns a pointer to the end of the destination.
- `memrchr`: Finds the last occurrence of a character in a memory area.
- `memset`: Fills a memory area with a specified value.
- `rindex`: Returns the last occurrence of a character in a string.
- `stpcpy` and `stpncpy`: Copies strings and returns a pointer to the end.
- `strcat`, `strchr`, `strcspn`, `strlcat`, `strlcpy`, `strlen`, `strncat`, `strncmp`, `strncpy`, `strnlen`, `strpbrk`, `strrchr`, `strstr`, `strtok`, and `strtok_r`: Various string manipulation functions for concatenation, searching, and tokenization.

Assembly implementations for `memcpy`, `memmove`, and `memset` are also included for optimized performance on x86_64 architectures.
---
 na/lib/string/memset.c | 93 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 93 insertions(+)
 create mode 100644 na/lib/string/memset.c

(limited to 'na/lib/string/memset.c')

diff --git a/na/lib/string/memset.c b/na/lib/string/memset.c
new file mode 100644
index 0000000..e780c71
--- /dev/null
+++ b/na/lib/string/memset.c
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: MIT */
+/* Derived from musl libc (Copyright © 2005-2020 Rich Felker, et al.) */
+
+#include <string.h>
+#include <stdint.h>
+
+void *memset(void *dest, int c, size_t n)
+{
+	unsigned char *s = dest;
+	size_t k;
+
+	/* Fill head and tail with minimal branching. Each
+	 * conditional ensures that all the subsequently used
+	 * offsets are well-defined and in the dest region. */
+
+	if (!n) return dest;
+	s[0] = c;
+	s[n-1] = c;
+	if (n <= 2) return dest;
+	s[1] = c;
+	s[2] = c;
+	s[n-2] = c;
+	s[n-3] = c;
+	if (n <= 6) return dest;
+	s[3] = c;
+	s[n-4] = c;
+	if (n <= 8) return dest;
+
+	/* Advance pointer to align it at a 4-byte boundary,
+	 * and truncate n to a multiple of 4. The previous code
+	 * already took care of any head/tail that get cut off
+	 * by the alignment. */
+
+	k = -(uintptr_t)s & 3;
+	s += k;
+	n -= k;
+	n &= -4;
+
+#ifdef __GNUC__
+	typedef uint32_t __attribute__((__may_alias__)) u32;
+	typedef uint64_t __attribute__((__may_alias__)) u64;
+
+	u32 c32 = ((u32)-1)/255 * (unsigned char)c;
+
+	/* In preparation to copy 32 bytes at a time, aligned on
+	 * an 8-byte bounary, fill head/tail up to 28 bytes each.
+	 * As in the initial byte-based head/tail fill, each
+	 * conditional below ensures that the subsequent offsets
+	 * are valid (e.g. !(n<=24) implies n>=28). */
+
+	*(u32 *)(s+0) = c32;
+	*(u32 *)(s+n-4) = c32;
+	if (n <= 8) return dest;
+	*(u32 *)(s+4) = c32;
+	*(u32 *)(s+8) = c32;
+	*(u32 *)(s+n-12) = c32;
+	*(u32 *)(s+n-8) = c32;
+	if (n <= 24) return dest;
+	*(u32 *)(s+12) = c32;
+	*(u32 *)(s+16) = c32;
+	*(u32 *)(s+20) = c32;
+	*(u32 *)(s+24) = c32;
+	*(u32 *)(s+n-28) = c32;
+	*(u32 *)(s+n-24) = c32;
+	*(u32 *)(s+n-20) = c32;
+	*(u32 *)(s+n-16) = c32;
+
+	/* Align to a multiple of 8 so we can fill 64 bits at a time,
+	 * and avoid writing the same bytes twice as much as is
+	 * practical without introducing additional branching. */
+
+	k = 24 + ((uintptr_t)s & 4);
+	s += k;
+	n -= k;
+
+	/* If this loop is reached, 28 tail bytes have already been
+	 * filled, so any remainder when n drops below 32 can be
+	 * safely ignored. */
+
+	u64 c64 = c32 | ((u64)c32 << 32);
+	for (; n >= 32; n-=32, s+=32) {
+		*(u64 *)(s+0) = c64;
+		*(u64 *)(s+8) = c64;
+		*(u64 *)(s+16) = c64;
+		*(u64 *)(s+24) = c64;
+	}
+#else
+	/* Pure C fallback with no aliasing violations. */
+	for (; n; n--, s++) *s = c;
+#endif
+
+	return dest;
+}
-- 
cgit v1.2.3