// https://syzkaller.appspot.com/bug?id=7c85d8274ab1bccc0b9a7837e5f0e713e863e102
// Copyright 2026 syzkaller project authors. All rights reserved.
// Use of this source code is governed by Apache 2 LICENSE that can be found in the LICENSE file.

// IMPORTANT: Do not copy the macros or definitions below directly into your reproducer.
// Instead, add the following line to your reproducer:
// #include "race_toolkit.h"

// --- Race Condition Toolkit ---
// Macros and snippets for CPU pinning, memory barriers, and userfaultfd.

#define _GNU_SOURCE
#include <errno.h>
#include <fcntl.h>
#include <linux/futex.h>
#include <linux/userfaultfd.h>
#include <poll.h>
#include <pthread.h>
#include <sched.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <sys/ioctl.h>
#include <sys/syscall.h>
#include <time.h>
#include <unistd.h>

// Unbuffered I/O: Ensure logs are written immediately.
#define SETUP_UNBUFFERED_IO() setvbuf(stdout, NULL, _IONBF, 0)

// CPU Pinning: Pin the current thread to a specific CPU core.
#define PIN_TO_CPU(cpu)                                                \
	do {                                                           \
		cpu_set_t mask;                                        \
		CPU_ZERO(&mask);                                       \
		CPU_SET(cpu, &mask);                                   \
		if (sched_setaffinity(0, sizeof(mask), &mask) == -1) { \
			perror("sched_setaffinity");                   \
		}                                                      \
	} while (0)

// Memory Barrier: Ensure memory ordering.
#define MB() __atomic_thread_fence(__ATOMIC_SEQ_CST)

// Spin-wait Barrier: Wait until a memory location has a specific value.
// Best for tight race windows (low latency, no context switches).
#define WAIT_ON(addr, val)                                               \
	do {                                                             \
		while (__atomic_load_n(addr, __ATOMIC_ACQUIRE) != (val)) \
			;                                                \
	} while (0)

// Signal: Set a memory location to a specific value to release a WAIT_ON.
#define SIGNAL(addr, val) __atomic_store_n(addr, val, __ATOMIC_RELEASE)

// --- Timing Primitives ---
// Robust timing loops in VM environments (using CLOCK_MONOTONIC to avoid time(NULL) jumps).

static inline double timer_elapsed_sec(struct timespec* start)
{
	struct timespec now;
	if (clock_gettime(CLOCK_MONOTONIC, &now) == -1) {
		perror("clock_gettime(CLOCK_MONOTONIC) elapsed");
		exit(1);
	}
	return (double)(now.tv_sec - start->tv_sec) + (double)(now.tv_nsec - start->tv_nsec) / 1e9;
}

// Initialize a monotonic timer variable.
#define TIMER_START(t)                                          \
	struct timespec t;                                      \
	if (clock_gettime(CLOCK_MONOTONIC, &t) == -1) {         \
		perror("clock_gettime(CLOCK_MONOTONIC) start"); \
		exit(1);                                        \
	}

// Check if the elapsed time since 't' is less than 'sec' seconds.
#define TIMER_NOT_EXPIRED(t, sec) (timer_elapsed_sec(&(t)) < (double)(sec))

// Futex-based Event: Shared with syzkaller executor.
// Best for general synchronization or longer waits to save CPU.
typedef struct {
	int state;
} event_t;

static void event_init(event_t* ev)
{
	ev->state = 0;
}
static void event_reset(event_t* ev)
{
	ev->state = 0;
}

static void event_set(event_t* ev)
{
	if (__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE)) {
		fprintf(stderr, "event already set\n");
		exit(1);
	}
	__atomic_store_n(&ev->state, 1, __ATOMIC_RELEASE);
	syscall(SYS_futex, &ev->state, FUTEX_WAKE | FUTEX_PRIVATE_FLAG, 1000000);
}

static void event_wait(event_t* ev)
{
	while (!__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE))
		syscall(SYS_futex, &ev->state, FUTEX_WAIT | FUTEX_PRIVATE_FLAG, 0, 0);
}

// userfaultfd setup: Register a memory range for page fault handling.
static int setup_uffd(void* addr, size_t len)
{
	int uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
	if (uffd == -1)
		return -1;
	struct uffdio_api api = {.api = UFFD_API, .features = 0};
	if (ioctl(uffd, UFFDIO_API, &api) == -1) {
		close(uffd);
		return -1;
	}
	struct uffdio_register reg = {
	    .range = {.start = (uintptr_t)addr, .len = len},
	    .mode = UFFDIO_REGISTER_MODE_MISSING};
	if (ioctl(uffd, UFFDIO_REGISTER, &reg) == -1) {
		close(uffd);
		return -1;
	}
	return uffd;
}

// --- Guidance on Usage ---
// 1. Use WAIT_ON/SIGNAL for tight race conditions to avoid scheduling overhead.
// 2. Use event_t (futexes) for general coordination or when waiting for longer periods.
// 3. Always use PIN_TO_CPU to increase race probability on multi-core systems.
// 4. Use setup_uffd to register a memory range for page fault handling. This allows you to
//    pause a thread accessing that memory until you handle the fault, creating a reliable
//    and controllable race window.
// 5. Call SETUP_UNBUFFERED_IO() at the start of main() to ensure that logs are printed
//    immediately. This is essential for understanding the exact interleaving of events
//    when debugging race conditions.
// 6. For timing-based loops (e.g., running a race for 10 seconds), do NOT use time(NULL)
//    or loops relying on real-time clocks, as VM clocks are highly unreliable and can fail or drift.
//    Instead, use the robust monotonic timing primitives TIMER_START and TIMER_NOT_EXPIRED:
//        TIMER_START(start);
//        while (TIMER_NOT_EXPIRED(start, 10.0)) {
//            // Your race logic here
//        }

#include <sys/mount.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <fcntl.h>
#include <sched.h>
#include <linux/futex.h>
#include <sys/syscall.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <signal.h>
#include <sys/mman.h>
#include <string.h>
#include <errno.h>

#define NUM_MOUNTS 16

int *start_event;

static void shared_event_set(int *state)
{
	__atomic_store_n(state, 1, __ATOMIC_RELEASE);
	syscall(SYS_futex, state, 1 /* FUTEX_WAKE */, 1000000, NULL, NULL, 0);
}

static void shared_event_wait(int *state)
{
	while (!__atomic_load_n(state, __ATOMIC_ACQUIRE))
		syscall(SYS_futex, state, 0 /* FUTEX_WAIT */, 0, NULL, NULL, 0);
}

void worker(char *mnt) {
    // Wait for the signal to maximize concurrency
    shared_event_wait(start_event);
    
    // Accessing the direct mount triggers autofs_d_automount -> autofs_wait
    if (chdir(mnt) < 0) {
        // It's expected to block or fail if the daemon doesn't respond.
    }
    exit(0);
}

int main() {
    SETUP_UNBUFFERED_IO();
    
    start_event = mmap(NULL, sizeof(int), PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0);
    if (start_event == MAP_FAILED) {
        printf("[-] mmap failed: %s\n", strerror(errno));
        exit(1);
    }
    
    pid_t parent_pid = getpid();
    
    pid_t worker_manager = fork();
    if (worker_manager < 0) {
        printf("[-] fork failed: %s\n", strerror(errno));
        exit(1);
    }
    if (worker_manager > 0) {
        waitpid(worker_manager, NULL, 0);
        printf("[+] Reproducer finished.\n");
        return 0;
    }
    
    if (setpgid(0, 0) < 0) {
        printf("[-] setpgid failed: %s\n", strerror(errno));
    }
    
    TIMER_START(start);
    while (TIMER_NOT_EXPIRED(start, 5.0)) {
        *start_event = 0;
        
        pid_t workers[NUM_MOUNTS];
        char mnts[NUM_MOUNTS][32];
        int pipes[NUM_MOUNTS][2];
        int mounted[NUM_MOUNTS] = {0};
        
        for (int i = 0; i < NUM_MOUNTS; i++) {
            if (pipe(pipes[i]) < 0) continue;
            
            sprintf(mnts[i], "./mnt%d", i);
            mkdir(mnts[i], 0777);
            
            char opts[128];
            sprintf(opts, "fd=%d,pgrp=%d,direct", pipes[i][1], parent_pid);
            
            if (mount("none", mnts[i], "autofs", 0, opts) == 0) {
                mounted[i] = 1;
                pid_t w = fork();
                if (w == 0) {
                    worker(mnts[i]);
                } else if (w > 0) {
                    workers[i] = w;
                }
            } else {
                close(pipes[i][0]);
                close(pipes[i][1]);
            }
        }
        
        usleep(10000);
        
        shared_event_set(start_event);
        
        usleep(10000);
        
        for (int i = 0; i < NUM_MOUNTS; i++) {
            if (mounted[i]) {
                kill(workers[i], SIGKILL);
                waitpid(workers[i], NULL, 0);
                
                umount2(mnts[i], MNT_DETACH);
                close(pipes[i][0]);
                close(pipes[i][1]);
            }
        }
    }
    
    return 0;
}