// https://syzkaller.appspot.com/bug?id=5e0091d9bc564bf3177c0f92e8ca0977018a38ca
#define _GNU_SOURCE
// 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>

#define PIPEFS_DIR "/tmp/pipefs"
#define NUM_NFS_WORKERS 4

static int stop_racing = 0;

struct nfs_worker_args {
	int id;
	int cpu;
};

static void *pipefs_worker(void *arg)
{
	(void)arg;
	PIN_TO_CPU(0);

	while (!__atomic_load_n(&stop_racing, __ATOMIC_ACQUIRE)) {
		int res = mount(NULL, PIPEFS_DIR, "rpc_pipefs", 0, NULL);
		if (res == 0) {
			umount2(PIPEFS_DIR, MNT_DETACH);
		}
	}
	return NULL;
}

static void *nfs_worker(void *arg)
{
	struct nfs_worker_args *wargs = (struct nfs_worker_args *)arg;
	PIN_TO_CPU(wargs->cpu);

	char target[64];
	snprintf(target, sizeof(target), "/tmp/nfs%d", wargs->id);

	unsigned int iter = 0;
	while (!__atomic_load_n(&stop_racing, __ATOMIC_ACQUIRE)) {
		char src[64];
		char opts[128];
		unsigned int ip_last = (iter % 250) + 1;
		snprintf(src, sizeof(src), "127.0.%d.%u:/", wargs->id, ip_last);
		snprintf(opts, sizeof(opts),
			 "vers=4,addr=127.0.%d.%u,clientaddr=127.0.0.1,timeo=1,retrans=1",
			 wargs->id, ip_last);

		int res = mount(src, target, "nfs", 0, opts);
		if (res == 0) {
			umount2(target, MNT_DETACH);
		}
		iter++;
	}
	return NULL;
}

int main(void)
{
	SETUP_UNBUFFERED_IO();

	printf("[*] Starting reproducer for KASAN slab-use-after-free in rpc_create_client_dir...\n");

	/* Step 1: Create isolated network and mount namespaces */
	int res = unshare(CLONE_NEWNS | CLONE_NEWNET);
	if (res < 0) {
		printf("[-] Failed to unshare(CLONE_NEWNS | CLONE_NEWNET): %s\n", strerror(errno));
		exit(1);
	}
	printf("[+] unshare(CLONE_NEWNS | CLONE_NEWNET) successful.\n");

	/* Step 2: Create directory for rpc_pipefs mount */
	res = mkdir(PIPEFS_DIR, 0777);
	if (res < 0 && errno != EEXIST) {
		printf("[-] Failed to mkdir %s: %s\n", PIPEFS_DIR, strerror(errno));
		exit(1);
	}
	printf("[+] mkdir %s successful.\n", PIPEFS_DIR);

	/* Step 3: Create directories for NFS worker mounts */
	for (int i = 0; i < NUM_NFS_WORKERS; i++) {
		char target[64];
		snprintf(target, sizeof(target), "/tmp/nfs%d", i);
		res = mkdir(target, 0777);
		if (res < 0 && errno != EEXIST) {
			printf("[-] Failed to mkdir %s: %s\n", target, strerror(errno));
			exit(1);
		}
		printf("[+] mkdir %s successful.\n", target);
	}

	/* Step 4: Verify initial mount and umount of rpc_pipefs */
	res = mount(NULL, PIPEFS_DIR, "rpc_pipefs", 0, NULL);
	if (res < 0) {
		printf("[-] Failed to verify mount %s: %s\n", PIPEFS_DIR, strerror(errno));
		exit(1);
	}
	printf("[+] Verify mount %s successful.\n", PIPEFS_DIR);

	res = umount2(PIPEFS_DIR, MNT_DETACH);
	if (res < 0) {
		printf("[-] Failed to verify umount %s: %s\n", PIPEFS_DIR, strerror(errno));
		exit(1);
	}
	printf("[+] Verify umount %s successful.\n", PIPEFS_DIR);

	/* Step 5: Detect available online CPUs */
	long ncpus = sysconf(_SC_NPROCESSORS_ONLN);
	if (ncpus < 1) {
		printf("[-] Failed to get online CPUs: %s\n", strerror(errno));
		exit(1);
	}
	printf("[+] Online CPUs detected: %ld\n", ncpus);

	/* Step 6: Start PipeFS mounting worker thread */
	pthread_t pipefs_th;
	res = pthread_create(&pipefs_th, NULL, pipefs_worker, NULL);
	if (res != 0) {
		printf("[-] Failed to pthread_create pipefs_worker: %s\n", strerror(res));
		exit(1);
	}
	printf("[+] Started pipefs_worker thread (pinned to CPU 0).\n");

	/* Step 7: Start NFS client creation worker threads */
	pthread_t nfs_th[NUM_NFS_WORKERS];
	struct nfs_worker_args wargs[NUM_NFS_WORKERS];
	for (int i = 0; i < NUM_NFS_WORKERS; i++) {
		wargs[i].id = i;
		wargs[i].cpu = (int)((i + 1) % ncpus);
		res = pthread_create(&nfs_th[i], NULL, nfs_worker, &wargs[i]);
		if (res != 0) {
			printf("[-] Failed to pthread_create nfs_worker %d: %s\n", i, strerror(res));
			exit(1);
		}
		printf("[+] Started nfs_worker thread %d (pinned to CPU %d).\n", i, wargs[i].cpu);
	}

	/* Step 8: Race execution loop */
	printf("[*] Racing PipeFS mount against NFS client creation for 25 seconds...\n");
	TIMER_START(start);
	int elapsed = 0;
	while (TIMER_NOT_EXPIRED(start, 25.0)) {
		sleep(1);
		elapsed++;
		if (elapsed % 5 == 0) {
			printf("[*] Race in progress: %d/25 seconds...\n", elapsed);
		}
	}
	printf("[+] Race duration completed.\n");

	/* Step 9: Signal stop and join threads */
	__atomic_store_n(&stop_racing, 1, __ATOMIC_RELEASE);

	res = pthread_join(pipefs_th, NULL);
	if (res != 0) {
		printf("[-] Failed to join pipefs_worker: %s\n", strerror(res));
		exit(1);
	}
	printf("[+] Joined pipefs_worker thread.\n");

	for (int i = 0; i < NUM_NFS_WORKERS; i++) {
		res = pthread_join(nfs_th[i], NULL);
		if (res != 0) {
			printf("[-] Failed to join nfs_worker %d: %s\n", i, strerror(res));
			exit(1);
		}
		printf("[+] Joined nfs_worker thread %d.\n", i);
	}

	/* Step 10: Cleanup directories */
	res = rmdir(PIPEFS_DIR);
	if (res < 0) {
		printf("[-] Failed to rmdir %s: %s\n", PIPEFS_DIR, strerror(errno));
		exit(1);
	}
	printf("[+] rmdir %s successful.\n", PIPEFS_DIR);

	for (int i = 0; i < NUM_NFS_WORKERS; i++) {
		char target[64];
		snprintf(target, sizeof(target), "/tmp/nfs%d", i);
		res = rmdir(target);
		if (res < 0) {
			printf("[-] Failed to rmdir %s: %s\n", target, strerror(errno));
			exit(1);
		}
		printf("[+] rmdir %s successful.\n", target);
	}

	printf("[+] Reproducer finished without crash.\n");
	return 0;
}