// socktest -- prove that Unix domain sockets carry data between processes.
//
// Every part of a socket is invisible from a return value. bind() returning 0
// proves nothing; a socket layer that accepts every call and drops every byte
// would pass a test built on return codes alone. So each check here has one
// process write and a *different* process read, and compares the bytes.
//
//   socktest        run every check
//
// Prints one line per check and a final verdict a script can grep for.

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

static int failures;

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

static void
putn_(int v)
{
    char buf[12];
    int i = 0, neg = 0;
    if (v < 0) { neg = 1; v = -v; }
    if (v == 0) buf[i++] = '0';
    while (v) { buf[i++] = '0' + (v % 10); v /= 10; }
    if (neg) buf[i++] = '-';
    while (i--) write(1, &buf[i], 1);
}

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

static int
streq(const char *a, const char *b)
{
    while (*a && *a == *b) { a++; b++; }
    return *a == *b;
}

// Fill a sockaddr_un and return the length to pass to bind/connect: the
// family plus the path plus its NUL, which is what musl computes and what the
// kernel side is written to expect.
// Every bind() here is preceded by an unlink(), which is not tidiness: a bound
// socket is a *file* now, and it outlives the process that bound it. Rebinding
// a path that already has a node is EADDRINUSE, exactly as on Linux, so every
// real server removes the stale one first. Before this change the name lived
// only in the kernel's socket table and vanished when the process did, so a
// test could bind the same path on every run and never notice.
static int
mkaddr(struct sockaddr_un *sa, const char *path)
{
    int i = 0;
    for (i = 0; i < UNIX_PATH_MAX - 1 && path[i]; i++)
        sa->sun_path[i] = path[i];
    sa->sun_path[i] = '\0';
    sa->sun_family = AF_UNIX;
    return (int)sizeof(sa->sun_family) + i + 1;
}

// ---------------------------------------------------------------------------
// 1. A round trip over a named socket, between two processes.
// ---------------------------------------------------------------------------
static void
test_roundtrip(void)
{
    struct sockaddr_un sa;
    int len;

    unlink("/tmp/socktest");   // a stale node from an earlier run
    len = mkaddr(&sa, "/tmp/socktest");
    int srv, pid, cli, n;
    char buf[64];

    puts_("named socket, two processes:\n");

    srv = socket(AF_UNIX, SOCK_STREAM, 0);
    check(srv >= 0, "socket() returns a descriptor");
    if (srv < 0) return;

    check(bind(srv, (struct sockaddr *)&sa, len) == 0, "bind() to /tmp/socktest");
    check(listen(srv, 4) == 0, "listen()");

    // A second bind to the same name must be refused, or two servers can
    // silently steal each other's clients.
    {
        int dup_ = socket(AF_UNIX, SOCK_STREAM, 0);
        check(bind(dup_, (struct sockaddr *)&sa, len) < 0,
              "a second bind to the same name is refused");
        close(dup_);
    }

    pid = fork();
    if (pid == 0) {
        // Child: the client. Connects, sends a question, reads the answer.
        int c = socket(AF_UNIX, SOCK_STREAM, 0);
        char reply[64];
        int r;

        close(srv);
        if (connect(c, (struct sockaddr *)&sa, len) < 0) {
            puts_("  FAIL: child connect()\n");
            exit();
        }
        write(c, "ping", 4);

        r = read(c, reply, sizeof(reply) - 1);
        if (r < 0) r = 0;
        reply[r] = '\0';
        if (!streq(reply, "pong"))
            puts_("  FAIL: child did not receive pong\n");
        close(c);
        exit();
    }

    cli = accept(srv, 0, 0);
    check(cli >= 0, "accept() returns a connection");
    if (cli < 0) { close(srv); wait(); return; }

    n = read(cli, buf, sizeof(buf) - 1);
    if (n < 0) n = 0;
    buf[n] = '\0';
    check(streq(buf, "ping"), "server read the client's bytes");

    check(write(cli, "pong", 4) == 4, "server replied on the same socket");

    close(cli);
    close(srv);
    wait();
}

// ---------------------------------------------------------------------------
// 2. Errors that must actually be errors.
// ---------------------------------------------------------------------------
static void
test_errors(void)
{
    struct sockaddr_un sa;
    int len;

    unlink("/tmp/nobody-listening");   // a stale node from an earlier run
    len = mkaddr(&sa, "/tmp/nobody-listening");
    int s;

    puts_("error paths:\n");

    s = socket(AF_UNIX, SOCK_STREAM, 0);
    check(connect(s, (struct sockaddr *)&sa, len) < 0,
          "connect() to a name nobody bound fails");
    close(s);

    // This used to assert that AF_INET was *refused*, which was true when this
    // file was written and stopped being true the day AF_INET landed. It kept
    // passing anyway, and the reason is worth keeping: socktest runs seconds
    // after boot, DHCP had not bound yet, and inet_new() refused every socket
    // until it did -- reported as ENFILE. So the check saw "< 0" and called it
    // a pass for a reason that had nothing to do with what it was testing.
    //
    // Two lessons, both already written down elsewhere in this tree and both
    // learned again here: a test that asserts a *failure* has to say which
    // failure, and a green suite is not evidence until something has checked
    // that it can go red.
    //
    // What is left are the refusals that are unconditionally true, whatever the
    // link is doing.
    check(socket(99, SOCK_STREAM, 0) < 0, "an unknown address family is refused");
    check(socket(AF_INET, SOCK_STREAM, 99) < 0,
          "AF_INET with a nonsense protocol is refused");
    check(socket(AF_UNIX, SOCK_DGRAM, 0) < 0, "SOCK_DGRAM is refused, not faked");

    // read/write on a plain file descriptor must not be mistaken for a socket,
    // and socket calls on one must be refused.
    check(listen(1, 4) < 0, "listen() on a non-socket fd fails");
}

// ---------------------------------------------------------------------------
// 3. End-of-file. A reader whose peer closes must be told, not left hanging.
// ---------------------------------------------------------------------------
static void
test_eof(void)
{
    struct sockaddr_un sa;
    int len;

    unlink("/tmp/socktest-eof");   // a stale node from an earlier run
    len = mkaddr(&sa, "/tmp/socktest-eof");
    int srv, cli, pid, n;
    char buf[16];

    puts_("end of file:\n");

    srv = socket(AF_UNIX, SOCK_STREAM, 0);
    bind(srv, (struct sockaddr *)&sa, len);
    listen(srv, 4);

    pid = fork();
    if (pid == 0) {
        int c = socket(AF_UNIX, SOCK_STREAM, 0);
        close(srv);
        connect(c, (struct sockaddr *)&sa, len);
        write(c, "x", 1);
        close(c);               // the peer goes away with the byte still unread
        exit();
    }

    cli = accept(srv, 0, 0);
    n = read(cli, buf, sizeof(buf));
    check(n == 1, "the byte sent before close() is still delivered");

    n = read(cli, buf, sizeof(buf));
    check(n == 0, "the next read returns 0 rather than blocking");

    close(cli);
    close(srv);
    wait();
}

// ---------------------------------------------------------------------------
// 4. socketpair: bidirectional, no name, no listener.
// ---------------------------------------------------------------------------
static void
test_socketpair(void)
{
    int sv[2], n;
    char buf[16];

    puts_("socketpair:\n");

    if (socketpair(AF_UNIX, SOCK_STREAM, 0, sv) < 0) {
        check(0, "socketpair() succeeds");
        return;
    }
    check(1, "socketpair() succeeds");

    write(sv[0], "a", 1);
    n = read(sv[1], buf, sizeof(buf));
    check(n == 1 && buf[0] == 'a', "0 -> 1 carries a byte");

    write(sv[1], "b", 1);
    n = read(sv[0], buf, sizeof(buf));
    check(n == 1 && buf[0] == 'b', "1 -> 0 carries a byte, on the same pair");

    close(sv[0]);
    close(sv[1]);
}

// ---------------------------------------------------------------------------
// 5. A message longer than the socket buffer, so the writer has to block and
//    the reader has to drain in more than one go.
// ---------------------------------------------------------------------------
#define BIG 12000

static void
test_big(void)
{
    int sv[2], pid, got = 0, ok = 1, i;
    static char out[BIG], in[BIG];

    puts_("a transfer larger than the buffer:\n");

    for (i = 0; i < BIG; i++)
        out[i] = (char)('A' + (i % 26));

    if (socketpair(AF_UNIX, SOCK_STREAM, 0, sv) < 0) {
        check(0, "socketpair() for the big transfer");
        return;
    }

    pid = fork();
    if (pid == 0) {
        int sent = 0, r;
        close(sv[1]);
        while (sent < BIG) {
            r = write(sv[0], out + sent, BIG - sent);
            if (r <= 0) break;
            sent += r;
        }
        close(sv[0]);
        exit();
    }

    close(sv[0]);
    while (got < BIG) {
        int r = read(sv[1], in + got, BIG - got);
        if (r <= 0) break;
        got += r;
    }
    close(sv[1]);
    wait();

    check(got == BIG, "every byte arrived");
    if (got != BIG) {
        puts_("        got ");
        putn_(got);
        puts_(" of ");
        putn_(BIG);
        puts_("\n");
    }
    for (i = 0; i < got; i++)
        if (in[i] != out[i]) { ok = 0; break; }
    check(ok, "and in the right order");
}


// ---------------------------------------------------------------------------
// Socket options.
//
// Both calls used to succeed unconditionally: setsockopt was `return 0;` and
// getsockopt wrote a zero for whatever was asked. So the only check that proves
// anything is a *round trip* -- set a value, read it back, and see the value
// rather than a zero -- plus one option that must be refused. A stub passes
// "does setsockopt return 0"; it cannot pass both of these at once.
// ---------------------------------------------------------------------------

#define T_SOL_SOCKET   1
#define T_SO_REUSEADDR 2
#define T_SO_TYPE      3
#define T_SO_RCVBUF    8
#define T_SO_NOSUCH    0x7ffe        // not an option Linux defines either

static void
test_sockopt(void)
{
    int fd = socket(AF_UNIX, SOCK_STREAM, 0);
    int val, len;

    puts_("-- socket options\n");
    if (fd < 0) { check(0, "socket()"); return; }

    // SO_TYPE must report what this socket actually is, not zero.
    val = -1; len = sizeof(val);
    check(getsockopt(fd, T_SOL_SOCKET, T_SO_TYPE, &val, &len) == 0 &&
          val == SOCK_STREAM, "getsockopt SO_TYPE says SOCK_STREAM");

    // The round trip. A stub that ignores the set and zeroes the get fails here.
    val = 1;
    check(setsockopt(fd, T_SOL_SOCKET, T_SO_REUSEADDR, &val, sizeof(val)) == 0,
          "setsockopt SO_REUSEADDR accepted");
    val = -1; len = sizeof(val);
    check(getsockopt(fd, T_SOL_SOCKET, T_SO_REUSEADDR, &val, &len) == 0 &&
          val == 1, "getsockopt SO_REUSEADDR reads back 1");

    // And back off again, so the answer is not just "always non-zero".
    val = 0;
    setsockopt(fd, T_SOL_SOCKET, T_SO_REUSEADDR, &val, sizeof(val));
    val = -1; len = sizeof(val);
    check(getsockopt(fd, T_SOL_SOCKET, T_SO_REUSEADDR, &val, &len) == 0 &&
          val == 0, "and reads back 0 once cleared");

    // A real buffer size, not zero.
    val = -1; len = sizeof(val);
    check(getsockopt(fd, T_SOL_SOCKET, T_SO_RCVBUF, &val, &len) == 0 && val > 0,
          "getsockopt SO_RCVBUF is a real size");

    // The refusal. This is the half that a permissive stub cannot fake.
    val = 1;
    check(setsockopt(fd, T_SOL_SOCKET, T_SO_NOSUCH, &val, sizeof(val)) < 0,
          "setsockopt of an unknown option is refused");
    len = sizeof(val);
    check(getsockopt(fd, T_SOL_SOCKET, T_SO_NOSUCH, &val, &len) < 0,
          "getsockopt of an unknown option is refused");

    close(fd);
}

// ---------------------------------------------------------------------------
// SOCK_NONBLOCK, end to end.
//
// Checking that socket() accepts the flag proves nothing -- it was accepted
// before, and discarded. What proves it is a read that *returns* on a socket
// with nothing in it, where a blocking socket would sleep forever.
// ---------------------------------------------------------------------------

#define T_SOCK_NONBLOCK 0x800
#define T_F_GETFL       3
#define T_O_NONBLOCK    04000

static void
test_nonblock(void)
{
    int sv[2];
    char c;

    puts_("-- SOCK_NONBLOCK\n");

    if (socketpair(AF_UNIX, SOCK_STREAM | T_SOCK_NONBLOCK, 0, sv) < 0) {
        check(0, "socketpair(SOCK_NONBLOCK)");
        return;
    }

    check((fcntl(sv[0], T_F_GETFL, 0) & T_O_NONBLOCK) != 0,
          "fcntl(F_GETFL) reports O_NONBLOCK");

    // Nothing has been written, so a blocking read would never return. If this
    // test hangs, the flag was dropped -- which is exactly what it used to be.
    check(read(sv[0], &c, 1) < 0, "read on an empty non-blocking socket returns");

    // And it still carries data, so the flag did not break the socket.
    write(sv[1], "x", 1);
    c = 0;
    check(read(sv[0], &c, 1) == 1 && c == 'x', "and still delivers a byte");

    close(sv[0]);
    close(sv[1]);
}



// The user library has no string.h; these three are all this file needs.
static void
memset_(void *p, int c, int n)
{
    char *d = p;
    while (n-- > 0) *d++ = (char)c;
}

static void
memmove_(void *dst, const void *src, int n)
{
    char *d = dst;
    const char *s = src;
    while (n-- > 0) *d++ = *s++;
}

static int
strneq_(const char *a, const char *b, int n)
{
    while (n-- > 0 && *a == *b && *a) { a++; b++; }
    return n < 0 || *a == *b;
}

// ---------------------------------------------------------------------------
// 8. SCM_RIGHTS: a descriptor crossing between processes.
//
// docs/architecture/kernel.md item 1, docs/architecture/devices.md mechanism 1. The thing
// being proved is not that recvmsg returns a number -- it is that the number
// names the *same open file* the other process had, which is why every check
// below moves data through the descriptor rather than inspecting it.
//
// The descriptor passed is always a pipe end, for one reason: a pipe announces
// its own lifetime. A read of a pipe whose every write end is closed returns 0,
// and that turns "was the kernel's reference released" -- which userspace
// cannot otherwise see -- into a value a test can compare.
// ---------------------------------------------------------------------------
#define T_F_SETFL 4

// Send `fd` with one byte of data on it.
static int
sendfd(int sock, int fd, char tag)
{
    struct msghdr m;
    struct iovec iv;
    char cbuf[CMSG_SPACE(sizeof(int))];
    struct cmsghdr *c;

    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);
}

// Receive into `fds`, up to `want` of them. Returns the byte count; *ngot is
// how many descriptors arrived and *flags the kernel's msg_flags.
static int
recvfd(int sock, char *tag, int *fds, int want, int *ngot, int *flags)
{
    struct msghdr m;
    struct iovec iv;
    char cbuf[CMSG_SPACE(SCM_MAXFD * sizeof(int))];
    struct cmsghdr *c;
    int n;

    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;
    // CMSG_LEN, not CMSG_SPACE: the trailing padding only matters if another
    // header follows, and sizing by it would leave room for a descriptor the
    // caller did not ask for -- which is exactly what makes a truncation test
    // pass by accident.
    m.msg_controllen = CMSG_LEN(want * sizeof(int));

    *ngot = 0;
    n = recvmsg(sock, &m, 0);
    if (flags)
        *flags = m.msg_flags;
    if (n < 0)
        return n;

    c = CMSG_FIRSTHDR(&m);
    if (c && c->cmsg_level == SOL_SOCKET && c->cmsg_type == SCM_RIGHTS) {
        int k = (int)((c->cmsg_len - CMSG_LEN(0)) / sizeof(int));
        for (*ngot = 0; *ngot < k && *ngot < want; (*ngot)++)
            memmove_(&fds[*ngot], CMSG_DATA(c) + *ngot * sizeof(int), sizeof(int));
    }
    return n;
}

// Is every write end of this pipe gone? Non-blocking, so a descriptor that
// leaked reports itself instead of hanging the test.
static int
pipe_at_eof(int rfd)
{
    char c;
    fcntl(rfd, T_F_SETFL, T_O_NONBLOCK);
    return read(rfd, &c, 1) == 0;
}

static void
test_fdpass(void)
{
    int sv[2], p[2], pid, got = 0, fds[SCM_MAXFD], n;
    char tag = 0, buf[32];

    puts_("SCM_RIGHTS:\n");

    if (socketpair(AF_UNIX, SOCK_STREAM, 0, sv) < 0 || pipe(p) < 0) {
        check(0, "socketpair() and pipe() for the descriptor tests");
        return;
    }

    pid = fork();
    if (pid == 0) {
        close(sv[0]);
        write(p[1], "through a passed descriptor", 27);
        sendfd(sv[1], p[0], 'F');
        // Every process-held reference is gone from here on. If the kernel is
        // not holding one of its own, the parent receives a dead descriptor.
        close(p[0]);
        close(p[1]);
        close(sv[1]);
        exit();
    }

    close(sv[1]);
    close(p[0]);
    close(p[1]);
    wait();

    n = recvfd(sv[0], &tag, fds, SCM_MAXFD, &got, 0);
    check(n == 1 && tag == 'F', "recvmsg returns the byte the descriptor rode on");
    check(got == 1, "and one descriptor with it");

    if (got == 1) {
        n = read(fds[0], buf, sizeof(buf));
        check(n == 27 && strneq_(buf, "through a passed descriptor", 27),
              "the descriptor is the sender's pipe, and still has its data");
        close(fds[0]);
    }
    close(sv[0]);
}

// Two messages, each carrying a descriptor, read with a buffer big enough for
// both. A read that ran past the second message's first byte would hand back
// one message's descriptors with two messages' bytes, and nothing in the
// result would say so -- which is why the kernel stops the read at the
// boundary instead.
static void
test_fdpass_boundary(void)
{
    int sv[2], a[2], b[2], got = 0, fds[SCM_MAXFD], n, flags = 0;
    char tag = 0;
    struct msghdr m;
    struct iovec iv;
    char big[8];

    if (socketpair(AF_UNIX, SOCK_STREAM, 0, sv) < 0 ||
        pipe(a) < 0 || pipe(b) < 0) {
        check(0, "sockets and pipes for the boundary test");
        return;
    }

    sendfd(sv[1], a[0], '1');
    sendfd(sv[1], b[0], '2');

    // Ask for eight bytes. Two are available.
    memset_(&m, 0, sizeof(m));
    iv.iov_base = big;
    iv.iov_len  = sizeof(big);
    m.msg_iov    = &iv;
    m.msg_iovlen = 1;
    n = recvmsg(sv[0], &m, 0);
    check(n == 1, "a read spanning two messages stops at the second's boundary");

    n = recvfd(sv[0], &tag, fds, SCM_MAXFD, &got, &flags);
    check(n == 1 && tag == '2' && got == 1,
          "so the next read starts there, and gets that message's descriptor");
    if (got == 1)
        close(fds[0]);

    close(sv[0]); close(sv[1]);
    close(a[0]); close(a[1]); close(b[0]); close(b[1]);
}

// A plain read(2) of a message carrying descriptors. There is nowhere to put
// them, so they are closed -- the alternative is the kernel holding references
// for a receiver that has proved it is not looking.
static void
test_fdpass_dropped(void)
{
    int sv[2], p[2];
    char c;

    if (socketpair(AF_UNIX, SOCK_STREAM, 0, sv) < 0 || pipe(p) < 0) {
        check(0, "sockets and a pipe for the dropped-descriptor test");
        return;
    }

    sendfd(sv[1], p[1], 'D');
    close(p[1]);                     // the kernel's reference is the last one

    check(read(sv[0], &c, 1) == 1 && c == 'D',
          "read(2) of a message carrying a descriptor returns its bytes");
    check(pipe_at_eof(p[0]),
          "and closes the descriptor rather than holding it for nobody");

    close(p[0]); close(sv[0]); close(sv[1]);
}

// A message with descriptors that is never received at all. The socket is
// closed with them still queued, and the kernel holds the only references --
// so if close does not drain the queue they are unreachable and permanent.
static void
test_fdpass_orphaned(void)
{
    int sv[2], p[2];

    if (socketpair(AF_UNIX, SOCK_STREAM, 0, sv) < 0 || pipe(p) < 0) {
        check(0, "sockets and a pipe for the orphaned-descriptor test");
        return;
    }

    sendfd(sv[1], p[1], 'O');
    close(p[1]);
    close(sv[0]);                    // never received
    close(sv[1]);

    check(pipe_at_eof(p[0]),
          "closing a socket closes the descriptors still queued on it");
    close(p[0]);
}

// More descriptors than the receiver left room for. The ones that do not fit
// are closed, and MSG_CTRUNC is how the caller is told it happened.
static void
test_fdpass_truncated(void)
{
    int sv[2], a[2], b[2], got = 0, fds[SCM_MAXFD], flags = 0;
    char tag = 0;
    struct msghdr m;
    struct iovec iv;
    char cbuf[CMSG_SPACE(2 * sizeof(int))];
    struct cmsghdr *c;
    int two[2];

    if (socketpair(AF_UNIX, SOCK_STREAM, 0, sv) < 0 ||
        pipe(a) < 0 || pipe(b) < 0) {
        check(0, "sockets and pipes for the truncation test");
        return;
    }

    // One message, two descriptors.
    memset_(&m, 0, sizeof(m));
    memset_(cbuf, 0, sizeof(cbuf));
    tag = 'T';
    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(2 * sizeof(int));
    c->cmsg_level = SOL_SOCKET;
    c->cmsg_type  = SCM_RIGHTS;
    two[0] = a[1];
    two[1] = b[1];
    memmove_(CMSG_DATA(c), two, sizeof(two));
    check(sendmsg(sv[1], &m, 0) == 1, "sendmsg carries two descriptors at once");
    close(a[1]);
    close(b[1]);

    // Receive with room for one.
    tag = 0;
    recvfd(sv[0], &tag, fds, 1, &got, &flags);
    check(got == 1, "a receiver with room for one gets one");
    check((flags & MSG_CTRUNC) != 0, "and MSG_CTRUNC says the rest were dropped");
    check(pipe_at_eof(b[0]) || pipe_at_eof(a[0]),
          "the descriptor that did not fit was closed, not leaked");

    if (got == 1)
        close(fds[0]);
    close(a[0]); close(b[0]); close(sv[0]); close(sv[1]);
}

// Descriptors with no bytes to ride on. Delivery pins them to the position of
// a first byte, so a message with no bytes has no position at which anyone
// could ever be handed them; saying so beats accepting it and losing them.
static void
test_fdpass_nodata(void)
{
    int sv[2], p[2];
    struct msghdr m;
    char cbuf[CMSG_SPACE(sizeof(int))];
    struct cmsghdr *c;

    if (socketpair(AF_UNIX, SOCK_STREAM, 0, sv) < 0 || pipe(p) < 0) {
        check(0, "sockets and a pipe for the no-data test");
        return;
    }

    memset_(&m, 0, sizeof(m));
    memset_(cbuf, 0, sizeof(cbuf));
    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), &p[1], sizeof(int));

    check(sendmsg(sv[1], &m, 0) < 0,
          "sendmsg refuses descriptors with no data to carry them");
    close(p[1]);
    check(pipe_at_eof(p[0]),
          "and does not keep the reference it took while trying");

    close(p[0]); close(sv[0]); close(sv[1]);
}

// ---------------------------------------------------------------------------
// 15. A bound socket is a file.
//
// docs/architecture/kernel.md item 3, in its own words: bind() a socket, then
// stat() and `ls -l` the path and see an `s`, then unlink() it.
//
// The reason it matters is not tidiness. A Wayland client finds its compositor
// by bind()ing a real path and libwayland locks the file beside it; a name
// table in the kernel can express neither. These checks are what a name table
// cannot pass -- every one of them asks the *filesystem* about the socket,
// not the socket layer.
// ---------------------------------------------------------------------------
static void
test_fsnames(void)
{
    struct sockaddr_un sa;
    struct stat st;
    int len, sv, c;

    puts_("a bound socket is a file:\n");

    unlink("/tmp/socktest-fs");           // from a previous run

    sv = socket(AF_UNIX, SOCK_STREAM, 0);
    len = mkaddr(&sa, "/tmp/socktest-fs");
    check(sv >= 0, "socket()");
    check(bind(sv, (struct sockaddr *)&sa, len) == 0, "bind creates the path");
    check(stat("/tmp/socktest-fs", &st) == 0, "and it can be stat()ed");
    check(st.type == T_SOCK, "as a socket, not a regular file");

    // Binding the same path twice is EADDRINUSE, and it has to come from the
    // directory -- a socket file left by a crashed server must refuse a
    // rebind for the same reason a running one does.
    {
        int s2 = socket(AF_UNIX, SOCK_STREAM, 0);
        check(s2 >= 0 && bind(s2, (struct sockaddr *)&sa, len) < 0,
              "a second bind to the same path is refused");
        if (s2 >= 0) close(s2);
    }

    // Connecting to a path that is not a socket must be refused rather than
    // matched by name. A name table could not tell the difference.
    {
        struct sockaddr_un sb;
        int lb = mkaddr(&sb, "/tmp/socktest-notasock");
        int fd = open("/tmp/socktest-notasock", O_CREATE | O_RDWR);
        if (fd >= 0) close(fd);
        c = socket(AF_UNIX, SOCK_STREAM, 0);
        check(c >= 0 && connect(c, (struct sockaddr *)&sb, lb) < 0,
              "connecting to a regular file is refused");
        if (c >= 0) close(c);
        unlink("/tmp/socktest-notasock");
    }

    check(unlink("/tmp/socktest-fs") == 0, "unlink removes it");
    check(stat("/tmp/socktest-fs", &st) < 0, "and it is gone from the filesystem");

    // The path is free again. On Linux the old socket keeps working for
    // anyone already connected; it is simply no longer findable by name.
    {
        int s3 = socket(AF_UNIX, SOCK_STREAM, 0);
        check(s3 >= 0 && bind(s3, (struct sockaddr *)&sa, len) == 0,
              "and the path is free to bind again");
        if (s3 >= 0) close(s3);
        unlink("/tmp/socktest-fs");
    }

    close(sv);
}

int
main(void)
{
    puts_("socktest: unix domain sockets\n");

    test_roundtrip();
    test_errors();
    test_eof();
    test_socketpair();
    test_big();
    test_sockopt();
    test_nonblock();
    test_fdpass();
    test_fdpass_boundary();
    test_fdpass_dropped();
    test_fdpass_orphaned();
    test_fdpass_truncated();
    test_fdpass_nodata();
    test_fsnames();

    if (failures == 0)
        puts_("socktest: ALL CHECKS PASSED\n");
    else {
        puts_("socktest: ");
        putn_(failures);
        puts_(" CHECK(S) FAILED\n");
    }
    exit();
}