// https://syzkaller.appspot.com/bug?id=7349616606afa3c986c377792f7ccbf9daae1142
#define _GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include <pthread.h>
#include <sched.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <sys/ioctl.h>
#include <net/if.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
//        }


void write_file(const char *path, const char *val, int exit_on_fail) {
    int fd = open(path, O_WRONLY);
    if (fd < 0) {
        printf("[-] open(%s) failed: %s\n", path, strerror(errno));
        if (exit_on_fail) exit(1);
        return;
    }
    if (write(fd, val, strlen(val)) < 0) {
        printf("[-] write(%s) failed: %s\n", path, strerror(errno));
        if (exit_on_fail) exit(1);
    }
    close(fd);
    printf("[+] Wrote %s to %s\n", val, path);
}

void *sender_thread(void *arg) {
    int cpu = (int)(long)arg;
    PIN_TO_CPU(cpu);

    int sock = socket(AF_INET, SOCK_DGRAM, 0);
    if (sock < 0) {
        printf("[-] socket failed: %s\n", strerror(errno));
        exit(1);
    }
    
    if (setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE, "lo", 2) < 0) {
        printf("[-] SO_BINDTODEVICE failed: %s\n", strerror(errno));
    }
    
    struct in_addr localInterface;
    localInterface.s_addr = inet_addr("127.0.0.1");
    if (setsockopt(sock, IPPROTO_IP, IP_MULTICAST_IF, &localInterface, sizeof(localInterface)) < 0) {
        printf("[-] IP_MULTICAST_IF failed: %s\n", strerror(errno));
    }

    struct sockaddr_in addr;
    addr.sin_family = AF_INET;
    addr.sin_port = htons(12345);
    addr.sin_addr.s_addr = inet_addr("224.0.0.1");

    char buf[64] = "hello";
    
    // Use sendmmsg to flood packets as fast as possible
    struct mmsghdr msgs[32];
    struct iovec iovecs[32];
    for (int i = 0; i < 32; i++) {
        iovecs[i].iov_base = buf;
        iovecs[i].iov_len = sizeof(buf);
        msgs[i].msg_hdr.msg_name = &addr;
        msgs[i].msg_hdr.msg_namelen = sizeof(addr);
        msgs[i].msg_hdr.msg_iov = &iovecs[i];
        msgs[i].msg_hdr.msg_iovlen = 1;
        msgs[i].msg_hdr.msg_control = NULL;
        msgs[i].msg_hdr.msg_controllen = 0;
        msgs[i].msg_hdr.msg_flags = 0;
    }

    while (1) {
        sendmmsg(sock, msgs, 32, 0);
    }
    return NULL;
}

int main() {
    SETUP_UNBUFFERED_IO();

    // 1. Set massive quotas to prevent process_backlog from yielding
    write_file("/proc/sys/net/core/dev_weight", "2000000000", 1);
    write_file("/proc/sys/net/core/netdev_max_backlog", "100000", 1);
    
    // 2. Enable RPS on lo to forward all packets to CPU 0
    write_file("/sys/class/net/lo/queues/rx-0/rps_cpus", "1", 0);
    
    // 3. Bring lo up and assign IP
    int sock = socket(AF_INET, SOCK_DGRAM, 0);
    if (sock < 0) {
        printf("[-] socket failed: %s\n", strerror(errno));
        exit(1);
    }
    struct ifreq ifr;
    strncpy(ifr.ifr_name, "lo", IFNAMSIZ);
    if (ioctl(sock, SIOCGIFFLAGS, &ifr) < 0) {
        printf("[-] ioctl(SIOCGIFFLAGS) failed: %s\n", strerror(errno));
        exit(1);
    }
    ifr.ifr_flags |= IFF_UP | IFF_RUNNING | IFF_MULTICAST;
    if (ioctl(sock, SIOCSIFFLAGS, &ifr) < 0) {
        printf("[-] ioctl(SIOCSIFFLAGS) failed: %s\n", strerror(errno));
        exit(1);
    }
    
    // Assign 127.0.0.1 to lo (usually already assigned, but just in case)
    struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr;
    sin->sin_family = AF_INET;
    sin->sin_addr.s_addr = inet_addr("127.0.0.1");
    ioctl(sock, SIOCSIFADDR, &ifr);
    close(sock);
    printf("[+] Brought lo up\n");

    // 4. Create multiple multicast receivers to amplify RX work
    // This ensures CPU 0 (RX) is much slower than CPU 1 (TX), keeping the backlog queue permanently non-empty.
    printf("[+] Creating multicast receivers...\n");
    for (int i = 0; i < 100; i++) {
        int s = socket(AF_INET, SOCK_DGRAM, 0);
        if (s < 0) continue;
        int opt = 1;
        setsockopt(s, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt));
        
        struct sockaddr_in addr;
        addr.sin_family = AF_INET;
        addr.sin_port = htons(12345);
        addr.sin_addr.s_addr = inet_addr("224.0.0.1");
        if (bind(s, (struct sockaddr *)&addr, sizeof(addr)) < 0) {
            close(s);
            continue;
        }
        
        struct ip_mreq mreq;
        mreq.imr_multiaddr.s_addr = inet_addr("224.0.0.1");
        mreq.imr_interface.s_addr = inet_addr("127.0.0.1");
        setsockopt(s, IPPROTO_IP, IP_ADD_MEMBERSHIP, &mreq, sizeof(mreq));
    }

    // 5. Spawn threads on other CPUs to flood CPU 0's backlog
    int num_cpus = sysconf(_SC_NPROCESSORS_ONLN);
    int num_threads = 4;
    printf("[+] Spawning %d sender threads\n", num_threads);
    for (int i = 0; i < num_threads; i++) {
        pthread_t t;
        int target_cpu = num_cpus > 1 ? (i % (num_cpus - 1)) + 1 : 0;
        if (pthread_create(&t, NULL, sender_thread, (void *)(long)target_cpu) != 0) {
            printf("[-] pthread_create failed: %s\n", strerror(errno));
            exit(1);
        }
    }

    // 6. Wait for soft lockup to trigger (watchdog threshold is usually 20s)
    printf("[+] Waiting for soft lockup...\n");
    sleep(150);
    return 0;
}