SchOS/cmd/memfdtest/main.c

// SPDX-License-Identifier: GPL-2.0-or-later
//
// memfdtest -- two processes map the same memfd, one writes, the other sees it.
//
// That sentence is docs/architecture/kernel.md's own acceptance criterion for
// item 2, and it is the check a permissive implementation cannot pass: an
// mmap that quietly returns private zeroed pages satisfies every return code
// here and fails the one assertion that matters, because the reader is a
// *different process* and the pages would not be the same pages.
//
// The lifecycle is the one a Wayland client performs, in order:
//
//     fd = memfd_create("buf", 0);
//     ftruncate(fd, size);
//     p  = mmap(0, size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
//
// and the reason it had to wait for SCM_RIGHTS is that the *other* process
// gets the same object by being handed the descriptor, not by naming it.

#include "core/types.h"
#include "uapi/user.h"
#include "uapi/fcntl.h"
#include "uapi/stat.h"
#include "uapi/posix.h"
#include "net/socket.h"

static int failures;

static void
puts_(const char *s)
{
    int n = 0;
    while (s[n]) n++;
    write(1, (void *)s, n);
}

// mmap returns -errno in the pointer on this system's own ABI -- musl turns
// that into MAP_FAILED, but a first-party binary sees the raw value. Anything
// in the top page is an error, not an address.
static int
mmap_failed(void *p)
{
    return (uint64)p >= (uint64)-4096;
}

static void
check(const char *what, int ok)
{
    puts_(ok ? "[ok]   " : "[FAIL] ");
    puts_(what);
    puts_("\n");
    if (!ok) failures++;
}

#define SIZE 8192

static void memset_(void *d, int c, int n) { char *p = d; while (n-- > 0) *p++ = (char)c; }
static void memmove_(void *d, const void *s, int n)
{ char *a = d; const char *b = s; while (n-- > 0) *a++ = *b++; }

// Send one descriptor over a socket, the way a Wayland client hands its buffer
// to the compositor. Same shape as cmd/socktest's helper; kept local so this
// test stands on its own.
static int
sendfd(int sock, int fd)
{
    struct msghdr m;
    struct iovec iv;
    char cbuf[CMSG_SPACE(sizeof(int))];
    struct cmsghdr *c;
    char tag = 'x';

    memset_(&m, 0, sizeof(m));
    memset_(cbuf, 0, sizeof(cbuf));
    iv.iov_base = &tag; iv.iov_len = 1;
    m.msg_iov = &iv; m.msg_iovlen = 1;
    m.msg_control = cbuf; m.msg_controllen = sizeof(cbuf);
    c = (struct cmsghdr *)cbuf;
    c->cmsg_len   = CMSG_LEN(sizeof(int));
    c->cmsg_level = SOL_SOCKET;
    c->cmsg_type  = SCM_RIGHTS;
    memmove_(CMSG_DATA(c), &fd, sizeof(int));
    return sendmsg(sock, &m, 0);
}

static int
recvfd(int sock)
{
    struct msghdr m;
    struct iovec iv;
    char cbuf[CMSG_SPACE(sizeof(int))];
    struct cmsghdr *c;
    char tag = 0;
    int got = -1;

    memset_(&m, 0, sizeof(m));
    memset_(cbuf, 0, sizeof(cbuf));
    iv.iov_base = &tag; iv.iov_len = 1;
    m.msg_iov = &iv; m.msg_iovlen = 1;
    m.msg_control = cbuf; m.msg_controllen = CMSG_LEN(sizeof(int));
    if (recvmsg(sock, &m, 0) < 0)
        return -1;
    c = CMSG_FIRSTHDR(&m);
    if (c && c->cmsg_level == SOL_SOCKET && c->cmsg_type == SCM_RIGHTS)
        memmove_(&got, CMSG_DATA(c), sizeof(int));
    return got;
}

int
main(void)
{
    int fd, pfd[2], st = 0;
    char *p;
    struct stat sb;

    puts_("memfdtest: a shareable memory object\n\n");

    fd = memfd_create("test-buffer", 0);
    check("memfd_create returns a descriptor", fd >= 0);
    if (fd < 0) { puts_("\nmemfdtest: FAILED\n"); return 1; }

    // A fresh memfd is empty. Mapping it before it has a size must fail --
    // there are no pages yet, and handing back anonymous ones would be the
    // lie this whole object exists to avoid.
    check("a new memfd has size 0",
          fstat(fd, &sb) == 0 && sb.size == 0);
    check("mapping a memfd that has no size yet is refused",
          mmap_failed(mmap(0, SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0)));

    check("ftruncate gives it a size", ftruncate(fd, SIZE) == 0);
    check("and fstat reports it back",
          fstat(fd, &sb) == 0 && sb.size == SIZE);

    p = mmap(0, SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
    check("mmap(MAP_SHARED) returns a mapping", !mmap_failed(p));
    if (mmap_failed(p)) { puts_("\nmemfdtest: FAILED\n"); return 1; }

    // Readable and writable by this process at all, before anything about
    // sharing is claimed.
    p[0] = 'A';
    p[SIZE - 1] = 'Z';
    check("the mapping is writable and reads back",
          p[0] == 'A' && p[SIZE - 1] == 'Z');

    // MAP_PRIVATE is refused rather than silently copied.
    check("MAP_PRIVATE on a memfd is refused",
          mmap_failed(mmap(0, SIZE, PROT_READ, MAP_PRIVATE, fd, 0)));

    // --- the assertion this test exists for ------------------------------
    //
    // fork(), then have the child map the *same* descriptor independently and
    // write through its own mapping. The parent must see it through its own.
    // A private mapping passes everything above and fails here.
    if (pipe(pfd) < 0) { puts_("[FAIL] pipe\n"); return 1; }

    int pid = fork();
    if (pid == 0) {
        char *q = mmap(0, SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
        char ok = mmap_failed(q) ? 0 : 1;
        if (ok) {
            // Prove the child sees what the parent wrote before the fork...
            if (q[0] != 'A' || q[SIZE - 1] != 'Z')
                ok = 0;
            // ...then write something of its own, in a different place.
            q[100] = 'C';
            q[SIZE / 2] = 'M';
        }
        write(pfd[1], &ok, 1);
        close(pfd[1]);
        exit();
    }
    close(pfd[1]);
    {
        char ok = 0;
        read(pfd[0], &ok, 1);
        close(pfd[0]);
        check("a second process maps the same fd and sees the parent's bytes",
              ok == 1);
    }
    wait();
    (void)st;

    check("and the parent sees what the child wrote",
          p[100] == 'C' && p[SIZE / 2] == 'M');
    check("without disturbing anything else in the mapping",
          p[0] == 'A' && p[SIZE - 1] == 'Z' && p[101] == 0);

    // --- read()/write() reach the same bytes -------------------------------
    {
        char buf[4] = { 0, 0, 0, 0 };
        lseek(fd, 100, 0 /* SEEK_SET */);
        check("read() sees what mmap wrote",
              read(fd, buf, 1) == 1 && buf[0] == 'C');
        lseek(fd, 200, 0 /* SEEK_SET */);
        buf[0] = 'W';
        check("write() is visible through the mapping",
              write(fd, buf, 1) == 1 && p[200] == 'W');
    }

    // --- shrinking while mapped is refused, not faked ----------------------
    check("shrinking a mapped memfd is refused", ftruncate(fd, 4096) < 0);
    check("growing it is allowed", ftruncate(fd, SIZE * 2) == 0);

    // --- the combination this was all for ---------------------------------
    //
    // A forked child inherits the descriptor, which proves the *pages* are
    // shared but not that the *object* travels. The Wayland case is an
    // unrelated process that is handed the descriptor over a socket and has
    // no other way to name it. So: send the memfd through a socketpair, and
    // have the receiver close every inherited copy before it maps.
    {
        int sv[2], cpid, rp[2];
        char ok = 0;

        if (socketpair(AF_UNIX, SOCK_STREAM, 0, sv) < 0 || pipe(rp) < 0) {
            check("socketpair for the descriptor-passing check", 0);
        } else if ((cpid = fork()) == 0) {
            int got;
            char *q;
            close(sv[0]); close(rp[0]);
            got = recvfd(sv[1]);
            // Close the inherited copy, so the only route to the object is
            // the descriptor that arrived over the socket.
            close(fd);
            q = (got >= 0) ? mmap(0, SIZE, PROT_READ | PROT_WRITE,
                                  MAP_SHARED, got, 0) : (char *)-1;
            ok = (got >= 0 && !mmap_failed(q) && q[100] == 'C') ? 1 : 0;
            if (ok) q[300] = 'S';
            write(rp[1], &ok, 1);
            close(rp[1]);
            exit();
        } else {
            close(sv[1]); close(rp[1]);
            sendfd(sv[0], fd);
            read(rp[0], &ok, 1);
            close(rp[0]); close(sv[0]);
            wait();
            check("a memfd passed over a socket maps in the receiver", ok == 1);
            check("and the sender sees what the receiver wrote", p[300] == 'S');
        }
    }

    close(fd);

    puts_("\n");
    puts_(failures ? "memfdtest: FAILED\n" : "memfdtest: all checks passed\n");
    return failures ? 1 : 0;
}