[musl] realpath without procfs -- should be ready for inclusion

[Rich Felker <dalias@libc.org>]

[-- Attachment #1: Type: text/plain, Size: 1218 bytes --]

I put this aside for a while, but realpath without procfs was one of
the things I wanted to get in this release cycle, and I had it
essentially finished back in September. Here's the latest version.
Compared to the earlier draft, it handles // more consistently (//.
and //.. both resolve to //) and expands getcwd only as a final step
if needed, rather than doing it first. In the case where an absolute
symlink is reached via a relative path, this saves a syscall, avoids
repeated absolute path traversal at each step, and avoids spuriously
erroring out with ENAMETOOLONG when the working directory is deeper
than PATH_MAX but the absolute link target has a valid absolute
pathname.

To recap, the motivation for the rewrite without procfs dependency was
having things work before procfs is mounted or in chroot/namespace
where it's intentionally unavailable.

I originally considered keeping the procfs based version and only
using the new one as a fallback, but I discovered there are cases
(involving chroot, namespaces, etc.) where the answer from procfs is
wrong and validating it requires basically the same procedure as
implementing it manually (walking and performing readlink on each path
component).

Rich

[-- Attachment #2: realpath8.c --]
[-- Type: text/plain, Size: 2392 bytes --]

#define _GNU_SOURCE
#include <stdlib.h>
#include <limits.h>
#include <errno.h>
#include <unistd.h>
#include <string.h>

static inline int at_dotdot(const char *end, size_t len)
{
	if (len<2) return 0;
	if (len>2 && end[-3]!='/') return 0;
	return end[-1]=='.' && end[-2]=='.';
}

char *realpath(const char *restrict filename, char *restrict resolved)
{
	char stack[PATH_MAX];
	char buf[resolved ? 1 : PATH_MAX];
	char *output = resolved ? resolved : buf;
	size_t p, q, l, cnt=0;

	l = strnlen(filename, sizeof stack + 1);
	if (!l) {
		errno = ENOENT;
		return 0;
	}
	if (l >= sizeof stack) goto toolong;
	p = sizeof stack - l - 1;
	q = 0;
	memcpy(stack+p, filename, l+1);

	while (stack[p]) {
		int up = 0;
		if (stack[p] == '/') {
			q=0;
			output[q++] = '/';
			p++;
			/* Initial // is special. */
			if (stack[p] == '/' && stack[p+1] != '/') {
				output[q++] = '/';
			}
			while (stack[p] == '/') p++;
			continue;
		}
		char *z = __strchrnul(stack+p, '/');
		l = z-(stack+p);
		if (l==1 && stack[p]=='.') {
			p += l;
			while (stack[p] == '/') p++;
			continue;
		}
		if (at_dotdot(stack+p+l, l)) {
			if (q && !at_dotdot(output+q, q)) {
				while(q && output[q-1]!='/') q--;
				if (q>1 && (q>2 || output[0]!='/')) q--;
				p += l;
				while (stack[p] == '/') p++;
				continue;
			}
			up = 1;
		}
		if (q && output[q-1] != '/') {
			if (!p) goto toolong;
			stack[--p] = '/';
			l++;
		}
		if (q+l >= PATH_MAX) goto toolong;
		memcpy(output+q, stack+p, l);
		output[q+l] = 0;
		p += l;
		if (up) goto notlink;
		ssize_t k = readlink(output, stack, p);
		if (k==-1) {
			if (errno == EINVAL) {
notlink:
				q += l;
				while (stack[p] == '/') p++;
				continue;
			}
			return 0;
		}
		if (k==p) goto toolong;
		if (++cnt == SYMLOOP_MAX) {
			errno = ELOOP;
			return 0;
		}
		p -= k;
		memmove(stack+p, stack, k);
	}

	output[q] = 0;

	if (output[0] != '/') {
		if (!getcwd(stack, sizeof stack)) return 0;
		l = strlen(stack);
		/* Cancel any initial .. components. */
		p = 0;
		while (q-p>=2 && at_dotdot(output+p+2, p+2)) {
			while(l>1 && stack[l-1]!='/') l--;
			if (l>1) l--;
			p += 2;
			if (p<q) p++;
		}
		if (q-p && stack[l-1]!='/') output[--p] = '/';
		if (l + (q-p) + 1 >= PATH_MAX) goto toolong;
		memmove(output + l, output + p, q - p + 1);
		memcpy(output, stack, l);
	}

	return resolved ? resolved : strdup(output);

toolong:
	errno = ENAMETOOLONG;
	return 0;
}