// https://syzkaller.appspot.com/bug?id=8b27acc89069e0e6bd0c2c309fd0853fc624d961
#define _GNU_SOURCE
#include <sched.h>
#include <sys/wait.h>
#include <sys/mman.h>
#include <signal.h>
#include <stdlib.h>
#include <unistd.h>
#include <stdio.h>
#include <stdatomic.h>
#include <string.h>
#include <errno.h>
// 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
//        }


#define NUM_ZOMBIES 40

struct sync_data {
    atomic_int sync_state;
    atomic_int forks_started;
    atomic_int total_forks;
};

int main() {
    SETUP_UNBUFFERED_IO();

    printf("[+] Starting KCSAN race reproducer...\n");

    // Pin Main to CPU 0
    cpu_set_t set;
    CPU_ZERO(&set);
    CPU_SET(0, &set);
    if (sched_setaffinity(0, sizeof(set), &set) < 0) {
        printf("[-] Failed to sched_setaffinity main: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] sched_setaffinity main successful.\n");

    // Allocate shared memory for sync_data
    struct sync_data *sync = mmap(NULL, sizeof(struct sync_data), PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0);
    if (sync == MAP_FAILED) {
        printf("[-] Failed to mmap: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] mmap successful.\n");

    TIMER_START(start);
    int iterations = 0;

    while (TIMER_NOT_EXPIRED(start, 10.0)) {
        pid_t z_before[NUM_ZOMBIES];
        pid_t z_after[NUM_ZOMBIES];
        pid_t forker;
        
        atomic_store(&sync->sync_state, 0);
        atomic_store(&sync->forks_started, 0);
        atomic_store(&sync->total_forks, 0);

        // Create z_before array
        int before_count = 0;
        for (int i = 0; i < NUM_ZOMBIES; i++) {
            pid_t pid = fork();
            if (pid < 0) {
                if (errno == EAGAIN) break;
                printf("[-] Failed to fork z_before: %s\n", strerror(errno));
                exit(1);
            }
            if (pid == 0) exit(0);
            z_before[before_count++] = pid;
            
            // Wait for it to become a zombie WITHOUT reaping it
            siginfo_t infop;
            memset(&infop, 0, sizeof(infop));
            if (waitid(P_PID, pid, &infop, WEXITED | WNOWAIT) < 0) {
                printf("[-] Failed to waitid z_before: %s\n", strerror(errno));
                exit(1);
            }
        }

        // Create Forker
        forker = fork();
        if (forker < 0) {
            printf("[-] Failed to fork forker: %s\n", strerror(errno));
            exit(1);
        }
        if (forker == 0) {
            // Pin Forker to CPU 1
            cpu_set_t fset;
            CPU_ZERO(&fset);
            CPU_SET(1, &fset);
            if (sched_setaffinity(0, sizeof(fset), &fset) < 0) {
                printf("[-] Failed to sched_setaffinity forker: %s\n", strerror(errno));
                exit(1);
            }

            // Signal ready
            atomic_store(&sync->sync_state, 1);
            
            // Wait for Main to say GO
            while (atomic_load(&sync->sync_state) != 2) {}
            
            int total = atomic_load(&sync->total_forks);
            
            // Acknowledge GO and start forking immediately
            atomic_store(&sync->sync_state, 3);

            for (int k = 0; k < total; k++) {
                atomic_store(&sync->forks_started, k + 1);
                pid_t child = fork();
                if (child == 0) exit(0);
            }
            
            // Reap all children after the loop
            while (wait(NULL) > 0);
            exit(0);
        }

        // Create z_after array
        int after_count = 0;
        for (int i = 0; i < NUM_ZOMBIES; i++) {
            pid_t pid = fork();
            if (pid < 0) {
                if (errno == EAGAIN) break;
                printf("[-] Failed to fork z_after: %s\n", strerror(errno));
                exit(1);
            }
            if (pid == 0) exit(0);
            z_after[after_count++] = pid;
            
            // Wait for it to become a zombie WITHOUT reaping it
            siginfo_t infop;
            memset(&infop, 0, sizeof(infop));
            if (waitid(P_PID, pid, &infop, WEXITED | WNOWAIT) < 0) {
                printf("[-] Failed to waitid z_after: %s\n", strerror(errno));
                exit(1);
            }
        }
        
        // Wait for Forker to be ready
        while (atomic_load(&sync->sync_state) != 1) {}

        atomic_store(&sync->total_forks, before_count + after_count);

        // Signal Forker to GO
        atomic_store(&sync->sync_state, 2);
        
        // Wait for Forker to acknowledge
        while (atomic_load(&sync->sync_state) != 3) {}
        
        // CRITICAL REAPING ORDER with 1-to-1 synchronization:
        // Reap z_before in REVERSE order to continuously update Forker->tasks.prev
        for (int i = 0; i < before_count; i++) {
            while (atomic_load(&sync->forks_started) <= i) {}
            for (volatile int d = 0; d < 50; d++) {} // Tiny delay to let fork enter kernel
            if (waitpid(z_before[before_count - 1 - i], NULL, 0) < 0) {
                printf("[-] Failed to waitpid z_before: %s\n", strerror(errno));
                exit(1);
            }
        }
        
        // Reap z_after in FORWARD order to continuously update Forker->tasks.next
        for (int i = 0; i < after_count; i++) {
            while (atomic_load(&sync->forks_started) <= before_count + i) {}
            for (volatile int d = 0; d < 50; d++) {} // Tiny delay to let fork enter kernel
            if (waitpid(z_after[i], NULL, 0) < 0) {
                printf("[-] Failed to waitpid z_after: %s\n", strerror(errno));
                exit(1);
            }
        }
        
        // Wait for Forker to finish
        if (waitpid(forker, NULL, 0) < 0) {
            printf("[-] Failed to waitpid forker: %s\n", strerror(errno));
            exit(1);
        }

        iterations++;
        if (iterations % 100 == 0) {
            printf("[+] Completed %d iterations.\n", iterations);
        }
    }

    printf("[+] Reproducer finished. Iterations: %d\n", iterations);
    return 0;
}