// SPDX-License-Identifier: GPL-2.0-or-later
//
// sigtest -- the SIGCHLD/sigsuspend contract every shell is built on.
//
// This is not one shell's quirk. It is what POSIX says to do and what zsh,
// mksh, bash and dash all do to wait for a child:
//
//     sigprocmask(SIG_BLOCK, {SIGCHLD}, &old);   // close the window
//     pid = fork();                               // child may exit at once
//     while (!flag)                               // flag set by the handler
//         sigsuspend(&old_without_SIGCHLD);       // unblock and wait, atomically
//     sigprocmask(SIG_SETMASK, &old, 0);
//
// Blocking first is the whole point: the child can exit *before* the parent
// reaches sigsuspend. Blocked, the signal stays pending; sigsuspend then
// unblocks and waits in one step, so a pending signal is delivered at once and
// the wait returns immediately. Get that wrong in either direction and the
// parent waits for a signal that has already happened -- which is a hang, in
// every shell, on every `$(command substitution)`.
//
// Written against the raw syscalls rather than a libc, because the thing under
// test is the kernel's half of the contract. **The user-facing sigset has
// signal N at bit N-1** (Linux's layout); the kernel converts at the boundary.
// Getting that backwards is a real bug this tree has had, so the masks below
// are spelled out rather than built by a macro.

#include "types.h"
#include "user.h"
#include "posix.h"

#define U_SIGCHLD_BIT   (1ULL << (SIGCHLD - 1))

// rt_sigaction takes a pointer to Linux's struct sigaction, not a function
// pointer: the handler is at offset 0 and the restorer at 144. The kernel
// reads exactly those two words (SA_HANDLER_OFF / SA_RESTORER_OFF in
// kernel/sys/sys_sig.c), so a 152-byte zeroed block with the handler written
// into the first word is the whole of what it needs.
#define SA_SIZE 152

static int failures;
static volatile int handler_runs;

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

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

static void
on_chld(int sig)
{
    (void)sig;
    handler_runs++;
}

// A bounded wait. A wrong answer here is a hang, so nothing may wait for ever:
// sigsuspend returns -EINTR each time a signal is delivered, and a kernel that
// never delivers spins out instead of stopping the test dead.
#define SPINS 300

int
main(void)
{
    uint64 blocked, unblocked, old = 0;
    int pid, status, i;

    puts_("sigtest: the SIGCHLD/sigsuspend contract\n\n");

    {
        static char act[SA_SIZE];
        *(uint64 *)act = (uint64)(void *)on_chld;
        rt_sigaction(SIGCHLD, act, 0, 8);
    }

    // --- 1. blocking actually blocks --------------------------------------
    blocked = U_SIGCHLD_BIT;
    sigprocmask(SIG_BLOCK, (const sigset_t *)&blocked, (sigset_t *)&old);

    handler_runs = 0;
    pid = fork();
    if (pid == 0)
        exit_group(0);

    // Every chance for the child to exit and for the kernel to deliver
    // wrongly. If the mask is honoured, the handler has not run.
    for (i = 0; i < 50; i++)
        getpid();
    sleep(10);
    check("SIGCHLD stays pending while blocked", handler_runs == 0);

    // --- 2. sigsuspend delivers what is already pending --------------------
    // The case that matters, and the one that hangs: the child is already
    // gone, so nothing new will ever arrive. sigsuspend has to deliver what is
    // *pending*, not wait for the next one.
    unblocked = ~U_SIGCHLD_BIT;
    for (i = 0; i < SPINS && handler_runs == 0; i++)
        rt_sigsuspend(&unblocked);

    check("sigsuspend delivers a signal that was already pending",
          handler_runs > 0);
    check("and it did not have to spin to get it", i <= 1);
    check("the handler ran exactly once", handler_runs == 1);

    // --- 3. the mask survives ----------------------------------------------
    {
        uint64 now = 0;
        sigprocmask(SIG_BLOCK, 0, (sigset_t *)&now);
        check("sigsuspend restores the mask it was called with",
              (now & U_SIGCHLD_BIT) != 0);
    }

    sigprocmask(SIG_SETMASK, (const sigset_t *)&old, 0);

    // --- 4. the child is still reapable ------------------------------------
    status = -1;
    check("the child can still be reaped after the handler ran",
          waitpid(pid, &status, 0) == pid);
    check("and its status says it exited cleanly", status == 0);

    // --- 5. the other order: the signal arrives while waiting ---------------
    handler_runs = 0;
    sigprocmask(SIG_BLOCK, (const sigset_t *)&blocked, (sigset_t *)&old);
    pid = fork();
    if (pid == 0) {
        sleep(30);                    // let the parent reach sigsuspend first
        exit_group(0);
    }
    for (i = 0; i < SPINS && handler_runs == 0; i++)
        rt_sigsuspend(&unblocked);
    check("sigsuspend wakes for a signal that arrives while it waits",
          handler_runs > 0);
    sigprocmask(SIG_SETMASK, (const sigset_t *)&old, 0);
    waitpid(pid, &status, 0);

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