#ifdef HAVE_CONFIG_H
#include <config.h>
#endif

#include <string.h>

/*
 * Copy n bytes from src to dst. The regions must not overlap (restrict).
 * Word-at-a-time: copy whole unsigned long words once dst is aligned, with
 * a byte head and tail. Word loads and stores go through __builtin_memcpy
 * so unaligned src is handled without undefined behavior.
 *
 * The word-copy loop below is the canonical memcpy idiom; GCC's
 * -ftree-loop-distribute-patterns (on by default at -O2 and -O3) rewrites
 * it into a call to memcpy() — this very function — causing infinite
 * self-recursion and stack overflow. Disable that one transformation for
 * this function only.
 */
__attribute__((optimize("no-tree-loop-distribute-patterns"))) void *
memcpy(void *restrict dst, const void *restrict src, size_t n) // NOLINT(bugprone-*)
{
    const unsigned long word = sizeof(unsigned long);
    unsigned char *d = dst;
    const unsigned char *s = src;

    /* Copy the unaligned head byte-wise. */
    for (; (unsigned long)d % word != 0 && n != 0; n--)
    {
        *d++ = *s++;
    }

    /* Copy whole words. */
    while (n >= word)
    {
        unsigned long w;

        __builtin_memcpy(&w, s, sizeof w); // NOLINT(clang-analyzer-security.insecureAPI.*)
        __builtin_memcpy(d, &w, sizeof w); // NOLINT(clang-analyzer-security.insecureAPI.*)
        d += word;
        s += word;
        n -= word;
    }

    /* Copy the remaining tail byte-wise. */
    while (n != 0)
    {
        *d++ = *s++;
        n--;
    }

    return dst;
}