// https://syzkaller.appspot.com/bug?id=62db7f0b628381f621ab352d501352f0cb359ba1
// 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 <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/socket.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <sched.h>
#include <sys/wait.h>
#include <sys/ioctl.h>
#include <net/if.h>
#include <signal.h>
#include <errno.h>
#include <time.h>

#define NETLINK_RDMA 20
#define RDMA_NL_NLDEV 5
#define RDMA_NLDEV_CMD_NEWLINK 3
#define RDMA_NLDEV_ATTR_DEV_NAME 2
#define RDMA_NLDEV_ATTR_NDEV_NAME 51
#define RDMA_NLDEV_ATTR_LINK_TYPE 65

static int create_dummy_interface(const char *name) {
    int fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
    if (fd < 0) return -1;

    struct {
        struct nlmsghdr nlh;
        struct ifinfomsg ifm;
        char buf[1024];
    } req = {0};

    req.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
    req.nlh.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL | NLM_F_ACK;
    req.nlh.nlmsg_type = RTM_NEWLINK;
    req.nlh.nlmsg_seq = 1;

    req.ifm.ifi_family = AF_UNSPEC;

    struct rtattr *rta;

    rta = (struct rtattr *)(((char *)&req) + NLMSG_ALIGN(req.nlh.nlmsg_len));
    rta->rta_type = IFLA_IFNAME;
    rta->rta_len = RTA_LENGTH(strlen(name) + 1);
    strcpy(RTA_DATA(rta), name);
    req.nlh.nlmsg_len = NLMSG_ALIGN(req.nlh.nlmsg_len) + RTA_ALIGN(rta->rta_len);

    struct rtattr *linkinfo = (struct rtattr *)(((char *)&req) + NLMSG_ALIGN(req.nlh.nlmsg_len));
    linkinfo->rta_type = IFLA_LINKINFO;
    linkinfo->rta_len = RTA_LENGTH(0);

    rta = (struct rtattr *)(((char *)linkinfo) + RTA_ALIGN(linkinfo->rta_len));
    rta->rta_type = IFLA_INFO_KIND;
    rta->rta_len = RTA_LENGTH(strlen("dummy") + 1);
    strcpy(RTA_DATA(rta), "dummy");
    
    linkinfo->rta_len += RTA_ALIGN(rta->rta_len);
    req.nlh.nlmsg_len = NLMSG_ALIGN(req.nlh.nlmsg_len) + RTA_ALIGN(linkinfo->rta_len);

    struct sockaddr_nl sa = { .nl_family = AF_NETLINK };
    sendto(fd, &req, req.nlh.nlmsg_len, 0, (struct sockaddr *)&sa, sizeof(sa));
    
    struct {
        struct nlmsghdr nlh;
        struct nlmsgerr err;
    } resp;
    recv(fd, &resp, sizeof(resp), 0);
    close(fd);
    return resp.err.error;
}

static int delete_interface(const char *name) {
    int fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
    if (fd < 0) return -1;

    struct {
        struct nlmsghdr nlh;
        struct ifinfomsg ifm;
        char buf[1024];
    } req = {0};

    req.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
    req.nlh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
    req.nlh.nlmsg_type = RTM_DELLINK;
    req.nlh.nlmsg_seq = 1;

    req.ifm.ifi_family = AF_UNSPEC;

    struct rtattr *rta;

    rta = (struct rtattr *)(((char *)&req) + NLMSG_ALIGN(req.nlh.nlmsg_len));
    rta->rta_type = IFLA_IFNAME;
    rta->rta_len = RTA_LENGTH(strlen(name) + 1);
    strcpy(RTA_DATA(rta), name);
    req.nlh.nlmsg_len = NLMSG_ALIGN(req.nlh.nlmsg_len) + RTA_ALIGN(rta->rta_len);

    struct sockaddr_nl sa = { .nl_family = AF_NETLINK };
    sendto(fd, &req, req.nlh.nlmsg_len, 0, (struct sockaddr *)&sa, sizeof(sa));
    
    struct {
        struct nlmsghdr nlh;
        struct nlmsgerr err;
    } resp;
    recv(fd, &resp, sizeof(resp), 0);
    close(fd);
    return resp.err.error;
}

static void bring_up_interface(const char *name) {
    int fd = socket(AF_INET, SOCK_DGRAM, 0);
    if (fd < 0) return;
    struct ifreq ifr;
    strcpy(ifr.ifr_name, name);
    if (ioctl(fd, SIOCGIFFLAGS, &ifr) == 0) {
        ifr.ifr_flags |= IFF_UP;
        ioctl(fd, SIOCSIFFLAGS, &ifr);
    }
    close(fd);
}

static int send_rdma_newlink(const char *ibdev_name, const char *link_type, const char *ndev_name) {
    int fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_RDMA);
    if (fd < 0) return -1;

    struct {
        struct nlmsghdr nlh;
        char buf[1024];
    } req = {0};

    req.nlh.nlmsg_len = NLMSG_LENGTH(0);
    req.nlh.nlmsg_type = (RDMA_NL_NLDEV << 10) | RDMA_NLDEV_CMD_NEWLINK;
    req.nlh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
    req.nlh.nlmsg_seq = 1;

    struct rtattr *rta;

    rta = (struct rtattr *)(((char *)&req) + NLMSG_ALIGN(req.nlh.nlmsg_len));
    rta->rta_type = RDMA_NLDEV_ATTR_DEV_NAME;
    rta->rta_len = RTA_LENGTH(strlen(ibdev_name) + 1);
    strcpy(RTA_DATA(rta), ibdev_name);
    req.nlh.nlmsg_len = NLMSG_ALIGN(req.nlh.nlmsg_len) + RTA_ALIGN(rta->rta_len);

    rta = (struct rtattr *)(((char *)&req) + NLMSG_ALIGN(req.nlh.nlmsg_len));
    rta->rta_type = RDMA_NLDEV_ATTR_LINK_TYPE;
    rta->rta_len = RTA_LENGTH(strlen(link_type) + 1);
    strcpy(RTA_DATA(rta), link_type);
    req.nlh.nlmsg_len = NLMSG_ALIGN(req.nlh.nlmsg_len) + RTA_ALIGN(rta->rta_len);

    rta = (struct rtattr *)(((char *)&req) + NLMSG_ALIGN(req.nlh.nlmsg_len));
    rta->rta_type = RDMA_NLDEV_ATTR_NDEV_NAME;
    rta->rta_len = RTA_LENGTH(strlen(ndev_name) + 1);
    strcpy(RTA_DATA(rta), ndev_name);
    req.nlh.nlmsg_len = NLMSG_ALIGN(req.nlh.nlmsg_len) + RTA_ALIGN(rta->rta_len);

    struct sockaddr_nl sa = { .nl_family = AF_NETLINK };
    sendto(fd, &req, req.nlh.nlmsg_len, 0, (struct sockaddr *)&sa, sizeof(sa));
    
    struct {
        struct nlmsghdr nlh;
        struct nlmsgerr err;
    } resp;
    recv(fd, &resp, sizeof(resp), 0);
    close(fd);
    return resp.err.error;
}

int main() {
    SETUP_UNBUFFERED_IO();
    TIMER_START(start);
    srand(time(NULL) ^ getpid());
    
    int iter = 0;
    while (TIMER_NOT_EXPIRED(start, 10.0)) {
        char dummy_name[32];
        char rxe_name[32];
        sprintf(dummy_name, "dummy%d", iter);
        sprintf(rxe_name, "rxe%d", iter);
        
        int res = create_dummy_interface(dummy_name);
        if (res < 0 && res != -EEXIST) {
            printf("[-] Failed to create dummy interface: %d\n", res);
            exit(1);
        }
        
        bring_up_interface(dummy_name);
        
        res = send_rdma_newlink(rxe_name, "rxe", dummy_name);
        if (res < 0) {
            printf("[-] Failed to create RXE device: %d\n", res);
        }
        
        int p[2];
        if (pipe(p) < 0) {
            exit(1);
        }
        
        pid_t pid = fork();
        if (pid == 0) {
            close(p[0]);
            if (unshare(CLONE_NEWNET) < 0) {
                exit(1);
            }
            // Signal parent that we are in new netns
            if (write(p[1], "1", 1) != 1) {}
            
            // Wait for parent to signal us to exit
            char c;
            if (read(p[1], &c, 1) != 1) {}
            
            // Exit, triggering cleanup_net
            exit(0);
        }
        
        close(p[1]);
        char c;
        // Wait for child to unshare
        if (read(p[0], &c, 1) != 1) {}
        close(p[0]);
        
        // Signal child to exit
        kill(pid, SIGKILL);
        
        // Random delay between 0 and 50ms to hit the race window
        // cleanup_net blocks on synchronize_rcu() which takes some time
        usleep(rand() % 50000);
        
        // Immediately delete the dummy interface to trigger ib_unregister_work
        delete_interface(dummy_name);
        
        waitpid(pid, NULL, 0);
        
        // Wait a bit for workqueues to finish
        usleep(50000);
        
        iter++;
    }
    
    printf("[+] Reproducer finished.\n");
    return 0;
}