// https://syzkaller.appspot.com/bug?id=20a0f004a11f8375d28283c91ef5dd3f42228aae
#define _GNU_SOURCE
#include <pthread.h>
#include <sys/mount.h>
#include <sys/mman.h>
#include <sys/syscall.h>
#include <sys/stat.h>
#include <sys/ioctl.h>
#include <fcntl.h>
#include <unistd.h>
#include <linux/loop.h>
#include <string.h>
#include <stdio.h>
#include <stdlib.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
//        }


#ifndef MS_SILENT
#define MS_SILENT 32768
#endif

char loop_name[64];

// Set up a loop device with a 1MB zeroed backing file.
// This ensures that the mount attempt reads blocks and populates the bh_lrus cache,
// even though the ext4 filesystem validation will subsequently fail.
void setup_loop() {
    int ctl_fd = open("/dev/loop-control", O_RDWR);
    int dev_nr = -1;
    if (ctl_fd >= 0) {
        dev_nr = ioctl(ctl_fd, LOOP_CTL_GET_FREE);
        if (dev_nr < 0) {
            printf("[-] Failed to ioctl LOOP_CTL_GET_FREE: %s\n", strerror(errno));
            exit(1);
        }
        printf("[+] ioctl LOOP_CTL_GET_FREE successful.\n");
        if (close(ctl_fd) < 0) {
            printf("[-] Failed to close /dev/loop-control: %s\n", strerror(errno));
            exit(1);
        }
        printf("[+] close /dev/loop-control successful.\n");
    }
    
    if (dev_nr >= 0) {
        sprintf(loop_name, "/dev/loop%d", dev_nr);
    } else {
        strcpy(loop_name, "/dev/loop0");
    }

    int fd = open("/tmp/backing_file", O_RDWR | O_CREAT, 0644);
    if (fd < 0) {
        printf("[-] Failed to open /tmp/backing_file: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] open /tmp/backing_file successful.\n");

    if (ftruncate(fd, 1024 * 1024) < 0) {
        printf("[-] Failed to ftruncate /tmp/backing_file: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] ftruncate /tmp/backing_file successful.\n");
    
    int loop_fd = open(loop_name, O_RDWR);
    if (loop_fd < 0) {
        printf("[-] Failed to open %s: %s\n", loop_name, strerror(errno));
        exit(1);
    }
    printf("[+] open %s successful.\n", loop_name);
    
    // Ignore error on LOOP_CLR_FD just in case it's not set
    ioctl(loop_fd, LOOP_CLR_FD, 0);
    
    if (ioctl(loop_fd, LOOP_SET_FD, fd) < 0) {
        printf("[-] Failed to ioctl LOOP_SET_FD: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] ioctl LOOP_SET_FD successful.\n");
    
    if (close(loop_fd) < 0) {
        printf("[-] Failed to close loop_fd: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] close loop_fd successful.\n");

    if (close(fd) < 0) {
        printf("[-] Failed to close backing_file fd: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] close backing_file fd successful.\n");
}

// Thread 1: Pinned to CPU 0. Repeatedly attempt to mount the loop device.
// The mount will read blocks (populating bh_lrus), fail validation, 
// and close the block device. The close triggers kill_bdev() -> invalidate_bh_lrus(),
// which clears the bh_lrus cache on CPU 0.
void *thread_mount(void *arg) {
    PIN_TO_CPU(0);
    if (mkdir("/tmp/mnt", 0777) < 0 && errno != EEXIST) {
        printf("[-] Failed to mkdir /tmp/mnt: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] mkdir /tmp/mnt successful.\n");
    umount("/tmp/mnt"); // Ensure it's not already mounted
    
    while (1) {
        // MS_SILENT suppresses console errors
        if (mount(loop_name, "/tmp/mnt", "ext4", MS_SILENT, NULL) == 0) {
            umount("/tmp/mnt");
        }
    }
    return NULL;
}

// Thread 2: Pinned to CPU 1. Repeatedly call mbind() with MPOL_MF_MOVE to trigger 
// lru_cache_disable() and __lru_add_drain_all(), which iterates over all CPUs and 
// calls has_bh_in_lru() on remote CPUs (including CPU 0).
void *thread_mbind(void *arg) {
    PIN_TO_CPU(1);
    void *p = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
    if (p == MAP_FAILED) {
        printf("[-] Failed to mmap: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] mmap successful.\n");
    
    while (1) {
        // mode = 0 (MPOL_DEFAULT), maxnode = 1, flags = 2 (MPOL_MF_MOVE)
        syscall(__NR_mbind, p, 4096, 0, NULL, 1, 2);
    }
    return NULL;
}

int main() {
    SETUP_UNBUFFERED_IO();
    setup_loop();
    
    pthread_t t1, t2;
    if (pthread_create(&t1, NULL, thread_mount, NULL) != 0) {
        printf("[-] Failed to pthread_create t1: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] pthread_create t1 successful.\n");

    if (pthread_create(&t2, NULL, thread_mbind, NULL) != 0) {
        printf("[-] Failed to pthread_create t2: %s\n", strerror(errno));
        exit(1);
    }
    printf("[+] pthread_create t2 successful.\n");
    
    // Sleep infinitely to prevent voluntary exit, avoiding the do_notify_parent_cldstop collision.
    // The syzkaller executor will eventually terminate this process with SIGKILL.
    while (1) {
        sleep(1);
    }
    
    return 0;
}