Re: UBSAN: Undefined behaviour in drivers/tty/vt/keyboard.c

[Kyungtae Kim]

On Tue, Mar 24, 2020 at 01:12:36PM +0100, Greg KH wrote:
> On Mon, Mar 23, 2020 at 04:44:31PM -0400, Kyungtae Kim wrote:
> > On Mon, Mar 23, 2020 at 07:46:16AM +0100, Greg KH wrote:
> > > On Sun, Mar 22, 2020 at 11:34:01PM -0400, Kyungtae Kim wrote:
> > > > We report a bug (in linux-5.5.11) found by FuzzUSB (modified version
> > > > of syzkaller)
> > > >
> > > > Seems the variable "npadch" has a very large value (i.e., 333333333)
> > > > as a result of multiple executions of the function "k_ascii" (keyboard.c:888)
> > > > while the variable "base" has 10.
> > > > So their multiplication at line 888 in "k_ascii" will become
> > > > larger than the max of type int, causing such an integer overflow.
> > > >
> > > > I believe this can be solved by checking for overflow ahead of operations
> > > > e.g., using check_mul_overflow().
> > > >
> > > > kernel config: https://kt0755.github.io/etc/config_v5.5.11
> > >
> > > Great, can you send a patch for this?
> > >
> > > thanks,
> > >
> > > greg k-h
> >
> > I'm not sure the following works best.
> >
> > diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
> > index 15d33fa0c925..c1ae9d2e6970 100644
> > --- a/drivers/tty/vt/keyboard.c
> > +++ b/drivers/tty/vt/keyboard.c
> > @@ -869,6 +869,7 @@ static void k_meta(struct vc_data *vc, unsigned
> > char value, char up_flag)
> >  static void k_ascii(struct vc_data *vc, unsigned char value, char up_flag)
> >  {
> >         int base;
> > +       int bytes, res;
> >
> >         if (up_flag)
> >                 return;
> > @@ -884,6 +885,8 @@ static void k_ascii(struct vc_data *vc, unsigned
> > char value, char up_flag)
> >
> >         if (npadch == -1)
> >                 npadch = value;
> > +       else if (check_mul_overflow(npadch, base, &bytes) ||
> > check_add_overflow(bytes, value, &res))
> > +               return;
> >         else
> >                 npadch = npadch * base + value;
> >  }
>
> Does this solve the issue for you?  If so, can you fix it up and resend
> it in a format that I can apply it in?
>
> thanks,
>
> greg k-h

I tested the fixed code using a repro (attached), and observed no such
a crash occurred anymore.
Anyway I will send a patch in a separate email.

Thanks,
Kyungtae Kim
// autogenerated by syzkaller (https://github.com/google/syzkaller)

//gcc [-o /tmp/syz-executor153879897 -DGOOS_linux=1 -DGOARCH_amd64=1 -DHOSTGOOS_linux=1 -x c - -O2 -pthread -Wall -Werror -Wparentheses -Wunused-const-variable -Wframe-larger-than=8192 -m64 -static -fpermissive -w]
//gcc -O2 -pthread -static 


#define _GNU_SOURCE 

#include <arpa/inet.h>
#include <dirent.h>
#include <endian.h>
#include <errno.h>
#include <fcntl.h>
#include <net/if.h>
#include <net/if_arp.h>
#include <netinet/in.h>
#include <pthread.h>
#include <sched.h>
#include <setjmp.h>
#include <signal.h>
#include <stdarg.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/ioctl.h>
#include <sys/mount.h>
#include <sys/prctl.h>
#include <sys/resource.h>
#include <sys/socket.h>
#include <sys/stat.h>
#include <sys/syscall.h>
#include <sys/time.h>
#include <sys/types.h>
#include <sys/uio.h>
#include <sys/wait.h>
#include <time.h>
#include <unistd.h>

#include <linux/capability.h>
#include <linux/futex.h>
#include <linux/genetlink.h>
#include <linux/if_addr.h>
#include <linux/if_ether.h>
#include <linux/if_link.h>
#include <linux/if_tun.h>
#include <linux/in6.h>
#include <linux/ip.h>
#include <linux/neighbour.h>
#include <linux/net.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <linux/tcp.h>
#include <linux/veth.h>

unsigned long long procid;

static __thread int skip_segv;
static __thread jmp_buf segv_env;

static void segv_handler(int sig, siginfo_t* info, void* ctx)
{
	uintptr_t addr = (uintptr_t)info->si_addr;
	const uintptr_t prog_start = 1 << 20;
	const uintptr_t prog_end = 100 << 20;
	if (__atomic_load_n(&skip_segv, __ATOMIC_RELAXED) && (addr < prog_start || addr > prog_end)) {
		_longjmp(segv_env, 1);
	}
	exit(sig);
}

static void install_segv_handler(void)
{
	struct sigaction sa;
	memset(&sa, 0, sizeof(sa));
	sa.sa_handler = SIG_IGN;
	syscall(SYS_rt_sigaction, 0x20, &sa, NULL, 8);
	syscall(SYS_rt_sigaction, 0x21, &sa, NULL, 8);
	memset(&sa, 0, sizeof(sa));
	sa.sa_sigaction = segv_handler;
	sa.sa_flags = SA_NODEFER | SA_SIGINFO;
	sigaction(SIGSEGV, &sa, NULL);
	sigaction(SIGBUS, &sa, NULL);
}

#define NONFAILING(...) { __atomic_fetch_add(&skip_segv, 1, __ATOMIC_SEQ_CST); if (_setjmp(segv_env) == 0) { __VA_ARGS__; } __atomic_fetch_sub(&skip_segv, 1, __ATOMIC_SEQ_CST); }

static void sleep_ms(uint64_t ms)
{
	usleep(ms * 1000);
}

static uint64_t current_time_ms(void)
{
	struct timespec ts;
	if (clock_gettime(CLOCK_MONOTONIC, &ts))
	exit(1);
	return (uint64_t)ts.tv_sec * 1000 + (uint64_t)ts.tv_nsec / 1000000;
}

static void use_temporary_dir(void)
{
	char tmpdir_template[] = "./syzkaller.XXXXXX";
	char* tmpdir = mkdtemp(tmpdir_template);
	if (!tmpdir)
	exit(1);
	if (chmod(tmpdir, 0777))
	exit(1);
	if (chdir(tmpdir))
	exit(1);
}

static void thread_start(void* (*fn)(void*), void* arg)
{
	pthread_t th;
	pthread_attr_t attr;
	pthread_attr_init(&attr);
	pthread_attr_setstacksize(&attr, 128 << 10);
	int i;
	for (i = 0; i < 100; i++) {
		if (pthread_create(&th, &attr, fn, arg) == 0) {
			pthread_attr_destroy(&attr);
			return;
		}
		if (errno == EAGAIN) {
			usleep(50);
			continue;
		}
		break;
	}
	exit(1);
}

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 (ev->state)
	exit(1);
	__atomic_store_n(&ev->state, 1, __ATOMIC_RELEASE);
	syscall(SYS_futex, &ev->state, FUTEX_WAKE | FUTEX_PRIVATE_FLAG);
}

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);
}

static int event_isset(event_t* ev)
{
	return __atomic_load_n(&ev->state, __ATOMIC_ACQUIRE);
}

static int event_timedwait(event_t* ev, uint64_t timeout)
{
	uint64_t start = current_time_ms();
	uint64_t now = start;
	for (;;) {
		uint64_t remain = timeout - (now - start);
		struct timespec ts;
		ts.tv_sec = remain / 1000;
		ts.tv_nsec = (remain % 1000) * 1000 * 1000;
		syscall(SYS_futex, &ev->state, FUTEX_WAIT | FUTEX_PRIVATE_FLAG, 0, &ts);
		if (__atomic_load_n(&ev->state, __ATOMIC_RELAXED))
			return 1;
		now = current_time_ms();
		if (now - start > timeout)
			return 0;
	}
}

static bool write_file(const char* file, const char* what, ...)
{
	char buf[1024];
	va_list args;
	va_start(args, what);
	vsnprintf(buf, sizeof(buf), what, args);
	va_end(args);
	buf[sizeof(buf) - 1] = 0;
	int len = strlen(buf);
	int fd = open(file, O_WRONLY | O_CLOEXEC);
	if (fd == -1)
		return false;
	if (write(fd, buf, len) != len) {
		int err = errno;
		close(fd);
		errno = err;
		return false;
	}
	close(fd);
	return true;
}

struct nlmsg {
	char* pos;
	int nesting;
	struct nlattr* nested[8];
	char buf[1024];
};

static struct nlmsg nlmsg;

static void netlink_init(struct nlmsg* nlmsg, int typ, int flags,
			 const void* data, int size)
{
	memset(nlmsg, 0, sizeof(*nlmsg));
	struct nlmsghdr* hdr = (struct nlmsghdr*)nlmsg->buf;
	hdr->nlmsg_type = typ;
	hdr->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | flags;
	memcpy(hdr + 1, data, size);
	nlmsg->pos = (char*)(hdr + 1) + NLMSG_ALIGN(size);
}

static void netlink_attr(struct nlmsg* nlmsg, int typ,
			 const void* data, int size)
{
	struct nlattr* attr = (struct nlattr*)nlmsg->pos;
	attr->nla_len = sizeof(*attr) + size;
	attr->nla_type = typ;
	memcpy(attr + 1, data, size);
	nlmsg->pos += NLMSG_ALIGN(attr->nla_len);
}

static void netlink_nest(struct nlmsg* nlmsg, int typ)
{
	struct nlattr* attr = (struct nlattr*)nlmsg->pos;
	attr->nla_type = typ;
	nlmsg->pos += sizeof(*attr);
	nlmsg->nested[nlmsg->nesting++] = attr;
}

static void netlink_done(struct nlmsg* nlmsg)
{
	struct nlattr* attr = nlmsg->nested[--nlmsg->nesting];
	attr->nla_len = nlmsg->pos - (char*)attr;
}

static int netlink_send_ext(struct nlmsg* nlmsg, int sock,
			    uint16_t reply_type, int* reply_len)
{
	if (nlmsg->pos > nlmsg->buf + sizeof(nlmsg->buf) || nlmsg->nesting)
	exit(1);
	struct nlmsghdr* hdr = (struct nlmsghdr*)nlmsg->buf;
	hdr->nlmsg_len = nlmsg->pos - nlmsg->buf;
	struct sockaddr_nl addr;
	memset(&addr, 0, sizeof(addr));
	addr.nl_family = AF_NETLINK;
	unsigned n = sendto(sock, nlmsg->buf, hdr->nlmsg_len, 0, (struct sockaddr*)&addr, sizeof(addr));
	if (n != hdr->nlmsg_len)
	exit(1);
	n = recv(sock, nlmsg->buf, sizeof(nlmsg->buf), 0);
	if (hdr->nlmsg_type == NLMSG_DONE) {
		*reply_len = 0;
		return 0;
	}
	if (n < sizeof(struct nlmsghdr))
	exit(1);
	if (reply_len && hdr->nlmsg_type == reply_type) {
		*reply_len = n;
		return 0;
	}
	if (n < sizeof(struct nlmsghdr) + sizeof(struct nlmsgerr))
	exit(1);
	if (hdr->nlmsg_type != NLMSG_ERROR)
	exit(1);
	return -((struct nlmsgerr*)(hdr + 1))->error;
}

static int netlink_send(struct nlmsg* nlmsg, int sock)
{
	return netlink_send_ext(nlmsg, sock, 0, NULL);
}

static int netlink_next_msg(struct nlmsg* nlmsg, unsigned int offset,
			    unsigned int total_len)
{
	struct nlmsghdr* hdr = (struct nlmsghdr*)(nlmsg->buf + offset);
	if (offset == total_len || offset + hdr->nlmsg_len > total_len)
		return -1;
	return hdr->nlmsg_len;
}

static void netlink_add_device_impl(struct nlmsg* nlmsg, const char* type,
				    const char* name)
{
	struct ifinfomsg hdr;
	memset(&hdr, 0, sizeof(hdr));
	netlink_init(nlmsg, RTM_NEWLINK, NLM_F_EXCL | NLM_F_CREATE, &hdr, sizeof(hdr));
	if (name)
		netlink_attr(nlmsg, IFLA_IFNAME, name, strlen(name));
	netlink_nest(nlmsg, IFLA_LINKINFO);
	netlink_attr(nlmsg, IFLA_INFO_KIND, type, strlen(type));
}

static void netlink_add_device(struct nlmsg* nlmsg, int sock, const char* type,
			       const char* name)
{
	netlink_add_device_impl(nlmsg, type, name);
	netlink_done(nlmsg);
	int err = netlink_send(nlmsg, sock);
	(void)err;
}

static void netlink_add_veth(struct nlmsg* nlmsg, int sock, const char* name,
			     const char* peer)
{
	netlink_add_device_impl(nlmsg, "veth", name);
	netlink_nest(nlmsg, IFLA_INFO_DATA);
	netlink_nest(nlmsg, VETH_INFO_PEER);
	nlmsg->pos += sizeof(struct ifinfomsg);
	netlink_attr(nlmsg, IFLA_IFNAME, peer, strlen(peer));
	netlink_done(nlmsg);
	netlink_done(nlmsg);
	netlink_done(nlmsg);
	int err = netlink_send(nlmsg, sock);
	(void)err;
}

static void netlink_add_hsr(struct nlmsg* nlmsg, int sock, const char* name,
			    const char* slave1, const char* slave2)
{
	netlink_add_device_impl(nlmsg, "hsr", name);
	netlink_nest(nlmsg, IFLA_INFO_DATA);
	int ifindex1 = if_nametoindex(slave1);
	netlink_attr(nlmsg, IFLA_HSR_SLAVE1, &ifindex1, sizeof(ifindex1));
	int ifindex2 = if_nametoindex(slave2);
	netlink_attr(nlmsg, IFLA_HSR_SLAVE2, &ifindex2, sizeof(ifindex2));
	netlink_done(nlmsg);
	netlink_done(nlmsg);
	int err = netlink_send(nlmsg, sock);
	(void)err;
}

static void netlink_device_change(struct nlmsg* nlmsg, int sock, const char* name, bool up,
				  const char* master, const void* mac, int macsize,
				  const char* new_name)
{
	struct ifinfomsg hdr;
	memset(&hdr, 0, sizeof(hdr));
	if (up)
		hdr.ifi_flags = hdr.ifi_change = IFF_UP;
	hdr.ifi_index = if_nametoindex(name);
	netlink_init(nlmsg, RTM_NEWLINK, 0, &hdr, sizeof(hdr));
	if (new_name)
		netlink_attr(nlmsg, IFLA_IFNAME, new_name, strlen(new_name));
	if (master) {
		int ifindex = if_nametoindex(master);
		netlink_attr(nlmsg, IFLA_MASTER, &ifindex, sizeof(ifindex));
	}
	if (macsize)
		netlink_attr(nlmsg, IFLA_ADDRESS, mac, macsize);
	int err = netlink_send(nlmsg, sock);
	(void)err;
}

static int netlink_add_addr(struct nlmsg* nlmsg, int sock, const char* dev,
			    const void* addr, int addrsize)
{
	struct ifaddrmsg hdr;
	memset(&hdr, 0, sizeof(hdr));
	hdr.ifa_family = addrsize == 4 ? AF_INET : AF_INET6;
	hdr.ifa_prefixlen = addrsize == 4 ? 24 : 120;
	hdr.ifa_scope = RT_SCOPE_UNIVERSE;
	hdr.ifa_index = if_nametoindex(dev);
	netlink_init(nlmsg, RTM_NEWADDR, NLM_F_CREATE | NLM_F_REPLACE, &hdr, sizeof(hdr));
	netlink_attr(nlmsg, IFA_LOCAL, addr, addrsize);
	netlink_attr(nlmsg, IFA_ADDRESS, addr, addrsize);
	return netlink_send(nlmsg, sock);
}

static void netlink_add_addr4(struct nlmsg* nlmsg, int sock,
			      const char* dev, const char* addr)
{
	struct in_addr in_addr;
	inet_pton(AF_INET, addr, &in_addr);
	int err = netlink_add_addr(nlmsg, sock, dev, &in_addr, sizeof(in_addr));
	(void)err;
}

static void netlink_add_addr6(struct nlmsg* nlmsg, int sock,
			      const char* dev, const char* addr)
{
	struct in6_addr in6_addr;
	inet_pton(AF_INET6, addr, &in6_addr);
	int err = netlink_add_addr(nlmsg, sock, dev, &in6_addr, sizeof(in6_addr));
	(void)err;
}

static void netlink_add_neigh(struct nlmsg* nlmsg, int sock, const char* name,
			      const void* addr, int addrsize, const void* mac, int macsize)
{
	struct ndmsg hdr;
	memset(&hdr, 0, sizeof(hdr));
	hdr.ndm_family = addrsize == 4 ? AF_INET : AF_INET6;
	hdr.ndm_ifindex = if_nametoindex(name);
	hdr.ndm_state = NUD_PERMANENT;
	netlink_init(nlmsg, RTM_NEWNEIGH, NLM_F_EXCL | NLM_F_CREATE, &hdr, sizeof(hdr));
	netlink_attr(nlmsg, NDA_DST, addr, addrsize);
	netlink_attr(nlmsg, NDA_LLADDR, mac, macsize);
	int err = netlink_send(nlmsg, sock);
	(void)err;
}

static int tunfd = -1;
static int tun_frags_enabled;

#define TUN_IFACE "syz_tun"

#define LOCAL_MAC 0xaaaaaaaaaaaa
#define REMOTE_MAC 0xaaaaaaaaaabb

#define LOCAL_IPV4 "172.20.20.170"
#define REMOTE_IPV4 "172.20.20.187"

#define LOCAL_IPV6 "fe80::aa"
#define REMOTE_IPV6 "fe80::bb"

#define IFF_NAPI 0x0010
#define IFF_NAPI_FRAGS 0x0020

static void initialize_tun(void)
{
	tunfd = open("/dev/net/tun", O_RDWR | O_NONBLOCK);
	if (tunfd == -1) {
		printf("tun: can't open /dev/net/tun: please enable CONFIG_TUN=y\n");
		printf("otherwise fuzzing or reproducing might not work as intended\n");
		return;
	}
	const int kTunFd = 240;
	if (dup2(tunfd, kTunFd) < 0)
	exit(1);
	close(tunfd);
	tunfd = kTunFd;
	struct ifreq ifr;
	memset(&ifr, 0, sizeof(ifr));
	strncpy(ifr.ifr_name, TUN_IFACE, IFNAMSIZ);
	ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_NAPI | IFF_NAPI_FRAGS;
	if (ioctl(tunfd, TUNSETIFF, (void*)&ifr) < 0) {
		ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
		if (ioctl(tunfd, TUNSETIFF, (void*)&ifr) < 0)
	exit(1);
	}
	if (ioctl(tunfd, TUNGETIFF, (void*)&ifr) < 0)
	exit(1);
	tun_frags_enabled = (ifr.ifr_flags & IFF_NAPI_FRAGS) != 0;
	char sysctl[64];
	sprintf(sysctl, "/proc/sys/net/ipv6/conf/%s/accept_dad", TUN_IFACE);
	write_file(sysctl, "0");
	sprintf(sysctl, "/proc/sys/net/ipv6/conf/%s/router_solicitations", TUN_IFACE);
	write_file(sysctl, "0");
	int sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
	if (sock == -1)
	exit(1);
	netlink_add_addr4(&nlmsg, sock, TUN_IFACE, LOCAL_IPV4);
	netlink_add_addr6(&nlmsg, sock, TUN_IFACE, LOCAL_IPV6);
	uint64_t macaddr = REMOTE_MAC;
	struct in_addr in_addr;
	inet_pton(AF_INET, REMOTE_IPV4, &in_addr);
	netlink_add_neigh(&nlmsg, sock, TUN_IFACE, &in_addr, sizeof(in_addr), &macaddr, ETH_ALEN);
	struct in6_addr in6_addr;
	inet_pton(AF_INET6, REMOTE_IPV6, &in6_addr);
	netlink_add_neigh(&nlmsg, sock, TUN_IFACE, &in6_addr, sizeof(in6_addr), &macaddr, ETH_ALEN);
	macaddr = LOCAL_MAC;
	netlink_device_change(&nlmsg, sock, TUN_IFACE, true, 0, &macaddr, ETH_ALEN, NULL);
	close(sock);
}

const int kInitNetNsFd = 239;

#define DEVLINK_FAMILY_NAME "devlink"

#define DEVLINK_CMD_PORT_GET 5
#define DEVLINK_CMD_RELOAD 37
#define DEVLINK_ATTR_BUS_NAME 1
#define DEVLINK_ATTR_DEV_NAME 2
#define DEVLINK_ATTR_NETDEV_NAME 7
#define DEVLINK_ATTR_NETNS_FD 137

static int netlink_devlink_id_get(struct nlmsg* nlmsg, int sock)
{
	struct genlmsghdr genlhdr;
	struct nlattr* attr;
	int err, n;
	uint16_t id = 0;
	memset(&genlhdr, 0, sizeof(genlhdr));
	genlhdr.cmd = CTRL_CMD_GETFAMILY;
	netlink_init(nlmsg, GENL_ID_CTRL, 0, &genlhdr, sizeof(genlhdr));
	netlink_attr(nlmsg, CTRL_ATTR_FAMILY_NAME, DEVLINK_FAMILY_NAME, strlen(DEVLINK_FAMILY_NAME) + 1);
	err = netlink_send_ext(nlmsg, sock, GENL_ID_CTRL, &n);
	if (err) {
		return -1;
	}
	attr = (struct nlattr*)(nlmsg->buf + NLMSG_HDRLEN + NLMSG_ALIGN(sizeof(genlhdr)));
	for (; (char*)attr < nlmsg->buf + n; attr = (struct nlattr*)((char*)attr + NLMSG_ALIGN(attr->nla_len))) {
		if (attr->nla_type == CTRL_ATTR_FAMILY_ID) {
			id = *(uint16_t*)(attr + 1);
			break;
		}
	}
	if (!id) {
		return -1;
	}
	recv(sock, nlmsg->buf, sizeof(nlmsg->buf), 0); /* recv ack */
	return id;
}

static void netlink_devlink_netns_move(const char* bus_name, const char* dev_name, int netns_fd)
{
	struct genlmsghdr genlhdr;
	int sock;
	int id;
	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC);
	if (sock == -1)
	exit(1);
	id = netlink_devlink_id_get(&nlmsg, sock);
	if (id == -1)
		goto error;
	memset(&genlhdr, 0, sizeof(genlhdr));
	genlhdr.cmd = DEVLINK_CMD_RELOAD;
	netlink_init(&nlmsg, id, 0, &genlhdr, sizeof(genlhdr));
	netlink_attr(&nlmsg, DEVLINK_ATTR_BUS_NAME, bus_name, strlen(bus_name) + 1);
	netlink_attr(&nlmsg, DEVLINK_ATTR_DEV_NAME, dev_name, strlen(dev_name) + 1);
	netlink_attr(&nlmsg, DEVLINK_ATTR_NETNS_FD, &netns_fd, sizeof(netns_fd));
	netlink_send(&nlmsg, sock);
error:
	close(sock);
}

static struct nlmsg nlmsg2;

static void initialize_devlink_ports(const char* bus_name, const char* dev_name,
				     const char* netdev_prefix)
{
	struct genlmsghdr genlhdr;
	int len, total_len, id, err, offset;
	uint16_t netdev_index;
	int sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC);
	if (sock == -1)
	exit(1);
	int rtsock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
	if (rtsock == -1)
	exit(1);
	id = netlink_devlink_id_get(&nlmsg, sock);
	if (id == -1)
		goto error;
	memset(&genlhdr, 0, sizeof(genlhdr));
	genlhdr.cmd = DEVLINK_CMD_PORT_GET;
	netlink_init(&nlmsg, id, NLM_F_DUMP, &genlhdr, sizeof(genlhdr));
	netlink_attr(&nlmsg, DEVLINK_ATTR_BUS_NAME, bus_name, strlen(bus_name) + 1);
	netlink_attr(&nlmsg, DEVLINK_ATTR_DEV_NAME, dev_name, strlen(dev_name) + 1);
	err = netlink_send_ext(&nlmsg, sock, id, &total_len);
	if (err) {
		goto error;
	}
	offset = 0;
	netdev_index = 0;
	while ((len = netlink_next_msg(&nlmsg, offset, total_len)) != -1) {
		struct nlattr* attr = (struct nlattr*)(nlmsg.buf + offset + NLMSG_HDRLEN + NLMSG_ALIGN(sizeof(genlhdr)));
		for (; (char*)attr < nlmsg.buf + offset + len; attr = (struct nlattr*)((char*)attr + NLMSG_ALIGN(attr->nla_len))) {
			if (attr->nla_type == DEVLINK_ATTR_NETDEV_NAME) {
				char* port_name;
				char netdev_name[IFNAMSIZ];
				port_name = (char*)(attr + 1);
				snprintf(netdev_name, sizeof(netdev_name), "%s%d", netdev_prefix, netdev_index);
				netlink_device_change(&nlmsg2, rtsock, port_name, true, 0, 0, 0, netdev_name);
				break;
			}
		}
		offset += len;
		netdev_index++;
	}
error:
	close(rtsock);
	close(sock);
}

static void initialize_devlink_pci(void)
{
	int netns = open("/proc/self/ns/net", O_RDONLY);
	if (netns == -1)
	exit(1);
	int ret = setns(kInitNetNsFd, 0);
	if (ret == -1)
	exit(1);
	netlink_devlink_netns_move("pci", "0000:00:10.0", netns);
	ret = setns(netns, 0);
	if (ret == -1)
	exit(1);
	close(netns);
	initialize_devlink_ports("pci", "0000:00:10.0", "netpci");
}

#define DEV_IPV4 "172.20.20.%d"
#define DEV_IPV6 "fe80::%02x"
#define DEV_MAC 0x00aaaaaaaaaa

static void netdevsim_add(unsigned int addr, unsigned int port_count)
{
	char buf[16];
	sprintf(buf, "%u %u", addr, port_count);
	write_file("/sys/bus/netdevsim/new_device", buf);
	snprintf(buf, sizeof(buf), "netdevsim%d", addr);
	initialize_devlink_ports("netdevsim", buf, "netdevsim");
}
static void initialize_netdevices(void)
{
	char netdevsim[16];
	sprintf(netdevsim, "netdevsim%d", (int)procid);
	struct {
		const char* type;
		const char* dev;
	} devtypes[] = {
	    {"ip6gretap", "ip6gretap0"},
	    {"bridge", "bridge0"},
	    {"vcan", "vcan0"},
	    {"bond", "bond0"},
	    {"team", "team0"},
	    {"dummy", "dummy0"},
	    {"nlmon", "nlmon0"},
	    {"caif", "caif0"},
	    {"batadv", "batadv0"},
	    {"vxcan", "vxcan1"},
	    {"netdevsim", netdevsim},
	    {"veth", 0},
	};
	const char* devmasters[] = {"bridge", "bond", "team"};
	struct {
		const char* name;
		int macsize;
		bool noipv6;
	} devices[] = {
	    {"lo", ETH_ALEN},
	    {"sit0", 0},
	    {"bridge0", ETH_ALEN},
	    {"vcan0", 0, true},
	    {"tunl0", 0},
	    {"gre0", 0},
	    {"gretap0", ETH_ALEN},
	    {"ip_vti0", 0},
	    {"ip6_vti0", 0},
	    {"ip6tnl0", 0},
	    {"ip6gre0", 0},
	    {"ip6gretap0", ETH_ALEN},
	    {"erspan0", ETH_ALEN},
	    {"bond0", ETH_ALEN},
	    {"veth0", ETH_ALEN},
	    {"veth1", ETH_ALEN},
	    {"team0", ETH_ALEN},
	    {"veth0_to_bridge", ETH_ALEN},
	    {"veth1_to_bridge", ETH_ALEN},
	    {"veth0_to_bond", ETH_ALEN},
	    {"veth1_to_bond", ETH_ALEN},
	    {"veth0_to_team", ETH_ALEN},
	    {"veth1_to_team", ETH_ALEN},
	    {"veth0_to_hsr", ETH_ALEN},
	    {"veth1_to_hsr", ETH_ALEN},
	    {"hsr0", 0},
	    {"dummy0", ETH_ALEN},
	    {"nlmon0", 0},
	    {"vxcan0", 0, true},
	    {"vxcan1", 0, true},
	    {"caif0", ETH_ALEN},
	    {"batadv0", ETH_ALEN},
	    {netdevsim, ETH_ALEN},
	};
	int sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
	if (sock == -1)
	exit(1);
	unsigned i;
	for (i = 0; i < sizeof(devtypes) / sizeof(devtypes[0]); i++)
		netlink_add_device(&nlmsg, sock, devtypes[i].type, devtypes[i].dev);
	for (i = 0; i < sizeof(devmasters) / (sizeof(devmasters[0])); i++) {
		char master[32], slave0[32], veth0[32], slave1[32], veth1[32];
		sprintf(slave0, "%s_slave_0", devmasters[i]);
		sprintf(veth0, "veth0_to_%s", devmasters[i]);
		netlink_add_veth(&nlmsg, sock, slave0, veth0);
		sprintf(slave1, "%s_slave_1", devmasters[i]);
		sprintf(veth1, "veth1_to_%s", devmasters[i]);
		netlink_add_veth(&nlmsg, sock, slave1, veth1);
		sprintf(master, "%s0", devmasters[i]);
		netlink_device_change(&nlmsg, sock, slave0, false, master, 0, 0, NULL);
		netlink_device_change(&nlmsg, sock, slave1, false, master, 0, 0, NULL);
	}
	netlink_device_change(&nlmsg, sock, "bridge_slave_0", true, 0, 0, 0, NULL);
	netlink_device_change(&nlmsg, sock, "bridge_slave_1", true, 0, 0, 0, NULL);
	netlink_add_veth(&nlmsg, sock, "hsr_slave_0", "veth0_to_hsr");
	netlink_add_veth(&nlmsg, sock, "hsr_slave_1", "veth1_to_hsr");
	netlink_add_hsr(&nlmsg, sock, "hsr0", "hsr_slave_0", "hsr_slave_1");
	netlink_device_change(&nlmsg, sock, "hsr_slave_0", true, 0, 0, 0, NULL);
	netlink_device_change(&nlmsg, sock, "hsr_slave_1", true, 0, 0, 0, NULL);
	netdevsim_add((int)procid, 4);
	for (i = 0; i < sizeof(devices) / (sizeof(devices[0])); i++) {
		char addr[32];
		sprintf(addr, DEV_IPV4, i + 10);
		netlink_add_addr4(&nlmsg, sock, devices[i].name, addr);
		if (!devices[i].noipv6) {
			sprintf(addr, DEV_IPV6, i + 10);
			netlink_add_addr6(&nlmsg, sock, devices[i].name, addr);
		}
		uint64_t macaddr = DEV_MAC + ((i + 10ull) << 40);
		netlink_device_change(&nlmsg, sock, devices[i].name, true, 0, &macaddr, devices[i].macsize, NULL);
	}
	close(sock);
}
static void initialize_netdevices_init(void)
{
	int sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
	if (sock == -1)
	exit(1);
	struct {
		const char* type;
		int macsize;
		bool noipv6;
		bool noup;
	} devtypes[] = {
	    {"nr", 7, true},
	    {"rose", 5, true, true},
	};
	unsigned i;
	for (i = 0; i < sizeof(devtypes) / sizeof(devtypes[0]); i++) {
		char dev[32], addr[32];
		sprintf(dev, "%s%d", devtypes[i].type, (int)procid);
		sprintf(addr, "172.30.%d.%d", i, (int)procid + 1);
		netlink_add_addr4(&nlmsg, sock, dev, addr);
		if (!devtypes[i].noipv6) {
			sprintf(addr, "fe88::%02x:%02x", i, (int)procid + 1);
			netlink_add_addr6(&nlmsg, sock, dev, addr);
		}
		int macsize = devtypes[i].macsize;
		uint64_t macaddr = 0xbbbbbb + ((unsigned long long)i << (8 * (macsize - 2))) +
				 (procid << (8 * (macsize - 1)));
		netlink_device_change(&nlmsg, sock, dev, !devtypes[i].noup, 0, &macaddr, macsize, NULL);
	}
	close(sock);
}

static int read_tun(char* data, int size)
{
	if (tunfd < 0)
		return -1;
	int rv = read(tunfd, data, size);
	if (rv < 0) {
		if (errno == EAGAIN)
			return -1;
		if (errno == EBADFD)
			return -1;
	exit(1);
	}
	return rv;
}

static void flush_tun()
{
	char data[1000];
	while (read_tun(&data[0], sizeof(data)) != -1) {
	}
}

#define MAX_FDS 30

#define XT_TABLE_SIZE 1536
#define XT_MAX_ENTRIES 10

struct xt_counters {
	uint64_t pcnt, bcnt;
};

struct ipt_getinfo {
	char name[32];
	unsigned int valid_hooks;
	unsigned int hook_entry[5];
	unsigned int underflow[5];
	unsigned int num_entries;
	unsigned int size;
};

struct ipt_get_entries {
	char name[32];
	unsigned int size;
	void* entrytable[XT_TABLE_SIZE / sizeof(void*)];
};

struct ipt_replace {
	char name[32];
	unsigned int valid_hooks;
	unsigned int num_entries;
	unsigned int size;
	unsigned int hook_entry[5];
	unsigned int underflow[5];
	unsigned int num_counters;
	struct xt_counters* counters;
	char entrytable[XT_TABLE_SIZE];
};

struct ipt_table_desc {
	const char* name;
	struct ipt_getinfo info;
	struct ipt_replace replace;
};

static struct ipt_table_desc ipv4_tables[] = {
    {.name = "filter"},
    {.name = "nat"},
    {.name = "mangle"},
    {.name = "raw"},
    {.name = "security"},
};

static struct ipt_table_desc ipv6_tables[] = {
    {.name = "filter"},
    {.name = "nat"},
    {.name = "mangle"},
    {.name = "raw"},
    {.name = "security"},
};

#define IPT_BASE_CTL 64
#define IPT_SO_SET_REPLACE (IPT_BASE_CTL)
#define IPT_SO_GET_INFO (IPT_BASE_CTL)
#define IPT_SO_GET_ENTRIES (IPT_BASE_CTL + 1)

struct arpt_getinfo {
	char name[32];
	unsigned int valid_hooks;
	unsigned int hook_entry[3];
	unsigned int underflow[3];
	unsigned int num_entries;
	unsigned int size;
};

struct arpt_get_entries {
	char name[32];
	unsigned int size;
	void* entrytable[XT_TABLE_SIZE / sizeof(void*)];
};

struct arpt_replace {
	char name[32];
	unsigned int valid_hooks;
	unsigned int num_entries;
	unsigned int size;
	unsigned int hook_entry[3];
	unsigned int underflow[3];
	unsigned int num_counters;
	struct xt_counters* counters;
	char entrytable[XT_TABLE_SIZE];
};

struct arpt_table_desc {
	const char* name;
	struct arpt_getinfo info;
	struct arpt_replace replace;
};

static struct arpt_table_desc arpt_tables[] = {
    {.name = "filter"},
};

#define ARPT_BASE_CTL 96
#define ARPT_SO_SET_REPLACE (ARPT_BASE_CTL)
#define ARPT_SO_GET_INFO (ARPT_BASE_CTL)
#define ARPT_SO_GET_ENTRIES (ARPT_BASE_CTL + 1)

static void checkpoint_iptables(struct ipt_table_desc* tables, int num_tables, int family, int level)
{
	struct ipt_get_entries entries;
	socklen_t optlen;
	int fd, i;
	fd = socket(family, SOCK_STREAM, IPPROTO_TCP);
	if (fd == -1) {
		switch (errno) {
		case EAFNOSUPPORT:
		case ENOPROTOOPT:
			return;
		}
	exit(1);
	}
	for (i = 0; i < num_tables; i++) {
		struct ipt_table_desc* table = &tables[i];
		strcpy(table->info.name, table->name);
		strcpy(table->replace.name, table->name);
		optlen = sizeof(table->info);
		if (getsockopt(fd, level, IPT_SO_GET_INFO, &table->info, &optlen)) {
			switch (errno) {
			case EPERM:
			case ENOENT:
			case ENOPROTOOPT:
				continue;
			}
	exit(1);
		}
		if (table->info.size > sizeof(table->replace.entrytable))
	exit(1);
		if (table->info.num_entries > XT_MAX_ENTRIES)
	exit(1);
		memset(&entries, 0, sizeof(entries));
		strcpy(entries.name, table->name);
		entries.size = table->info.size;
		optlen = sizeof(entries) - sizeof(entries.entrytable) + table->info.size;
		if (getsockopt(fd, level, IPT_SO_GET_ENTRIES, &entries, &optlen))
	exit(1);
		table->replace.valid_hooks = table->info.valid_hooks;
		table->replace.num_entries = table->info.num_entries;
		table->replace.size = table->info.size;
		memcpy(table->replace.hook_entry, table->info.hook_entry, sizeof(table->replace.hook_entry));
		memcpy(table->replace.underflow, table->info.underflow, sizeof(table->replace.underflow));
		memcpy(table->replace.entrytable, entries.entrytable, table->info.size);
	}
	close(fd);
}

static void reset_iptables(struct ipt_table_desc* tables, int num_tables, int family, int level)
{
	struct xt_counters counters[XT_MAX_ENTRIES];
	struct ipt_get_entries entries;
	struct ipt_getinfo info;
	socklen_t optlen;
	int fd, i;
	fd = socket(family, SOCK_STREAM, IPPROTO_TCP);
	if (fd == -1) {
		switch (errno) {
		case EAFNOSUPPORT:
		case ENOPROTOOPT:
			return;
		}
	exit(1);
	}
	for (i = 0; i < num_tables; i++) {
		struct ipt_table_desc* table = &tables[i];
		if (table->info.valid_hooks == 0)
			continue;
		memset(&info, 0, sizeof(info));
		strcpy(info.name, table->name);
		optlen = sizeof(info);
		if (getsockopt(fd, level, IPT_SO_GET_INFO, &info, &optlen))
	exit(1);
		if (memcmp(&table->info, &info, sizeof(table->info)) == 0) {
			memset(&entries, 0, sizeof(entries));
			strcpy(entries.name, table->name);
			entries.size = table->info.size;
			optlen = sizeof(entries) - sizeof(entries.entrytable) + entries.size;
			if (getsockopt(fd, level, IPT_SO_GET_ENTRIES, &entries, &optlen))
	exit(1);
			if (memcmp(table->replace.entrytable, entries.entrytable, table->info.size) == 0)
				continue;
		}
		table->replace.num_counters = info.num_entries;
		table->replace.counters = counters;
		optlen = sizeof(table->replace) - sizeof(table->replace.entrytable) + table->replace.size;
		if (setsockopt(fd, level, IPT_SO_SET_REPLACE, &table->replace, optlen))
	exit(1);
	}
	close(fd);
}

static void checkpoint_arptables(void)
{
	struct arpt_get_entries entries;
	socklen_t optlen;
	unsigned i;
	int fd;
	fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
	if (fd == -1) {
		switch (errno) {
		case EAFNOSUPPORT:
		case ENOPROTOOPT:
			return;
		}
	exit(1);
	}
	for (i = 0; i < sizeof(arpt_tables) / sizeof(arpt_tables[0]); i++) {
		struct arpt_table_desc* table = &arpt_tables[i];
		strcpy(table->info.name, table->name);
		strcpy(table->replace.name, table->name);
		optlen = sizeof(table->info);
		if (getsockopt(fd, SOL_IP, ARPT_SO_GET_INFO, &table->info, &optlen)) {
			switch (errno) {
			case EPERM:
			case ENOENT:
			case ENOPROTOOPT:
				continue;
			}
	exit(1);
		}
		if (table->info.size > sizeof(table->replace.entrytable))
	exit(1);
		if (table->info.num_entries > XT_MAX_ENTRIES)
	exit(1);
		memset(&entries, 0, sizeof(entries));
		strcpy(entries.name, table->name);
		entries.size = table->info.size;
		optlen = sizeof(entries) - sizeof(entries.entrytable) + table->info.size;
		if (getsockopt(fd, SOL_IP, ARPT_SO_GET_ENTRIES, &entries, &optlen))
	exit(1);
		table->replace.valid_hooks = table->info.valid_hooks;
		table->replace.num_entries = table->info.num_entries;
		table->replace.size = table->info.size;
		memcpy(table->replace.hook_entry, table->info.hook_entry, sizeof(table->replace.hook_entry));
		memcpy(table->replace.underflow, table->info.underflow, sizeof(table->replace.underflow));
		memcpy(table->replace.entrytable, entries.entrytable, table->info.size);
	}
	close(fd);
}

static void reset_arptables()
{
	struct xt_counters counters[XT_MAX_ENTRIES];
	struct arpt_get_entries entries;
	struct arpt_getinfo info;
	socklen_t optlen;
	unsigned i;
	int fd;
	fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
	if (fd == -1) {
		switch (errno) {
		case EAFNOSUPPORT:
		case ENOPROTOOPT:
			return;
		}
	exit(1);
	}
	for (i = 0; i < sizeof(arpt_tables) / sizeof(arpt_tables[0]); i++) {
		struct arpt_table_desc* table = &arpt_tables[i];
		if (table->info.valid_hooks == 0)
			continue;
		memset(&info, 0, sizeof(info));
		strcpy(info.name, table->name);
		optlen = sizeof(info);
		if (getsockopt(fd, SOL_IP, ARPT_SO_GET_INFO, &info, &optlen))
	exit(1);
		if (memcmp(&table->info, &info, sizeof(table->info)) == 0) {
			memset(&entries, 0, sizeof(entries));
			strcpy(entries.name, table->name);
			entries.size = table->info.size;
			optlen = sizeof(entries) - sizeof(entries.entrytable) + entries.size;
			if (getsockopt(fd, SOL_IP, ARPT_SO_GET_ENTRIES, &entries, &optlen))
	exit(1);
			if (memcmp(table->replace.entrytable, entries.entrytable, table->info.size) == 0)
				continue;
		} else {
		}
		table->replace.num_counters = info.num_entries;
		table->replace.counters = counters;
		optlen = sizeof(table->replace) - sizeof(table->replace.entrytable) + table->replace.size;
		if (setsockopt(fd, SOL_IP, ARPT_SO_SET_REPLACE, &table->replace, optlen))
	exit(1);
	}
	close(fd);
}

#define NF_BR_NUMHOOKS 6
#define EBT_TABLE_MAXNAMELEN 32
#define EBT_CHAIN_MAXNAMELEN 32
#define EBT_BASE_CTL 128
#define EBT_SO_SET_ENTRIES (EBT_BASE_CTL)
#define EBT_SO_GET_INFO (EBT_BASE_CTL)
#define EBT_SO_GET_ENTRIES (EBT_SO_GET_INFO + 1)
#define EBT_SO_GET_INIT_INFO (EBT_SO_GET_ENTRIES + 1)
#define EBT_SO_GET_INIT_ENTRIES (EBT_SO_GET_INIT_INFO + 1)

struct ebt_replace {
	char name[EBT_TABLE_MAXNAMELEN];
	unsigned int valid_hooks;
	unsigned int nentries;
	unsigned int entries_size;
	struct ebt_entries* hook_entry[NF_BR_NUMHOOKS];
	unsigned int num_counters;
	struct ebt_counter* counters;
	char* entries;
};

struct ebt_entries {
	unsigned int distinguisher;
	char name[EBT_CHAIN_MAXNAMELEN];
	unsigned int counter_offset;
	int policy;
	unsigned int nentries;
	char data[0] __attribute__((aligned(__alignof__(struct ebt_replace))));
};

struct ebt_table_desc {
	const char* name;
	struct ebt_replace replace;
	char entrytable[XT_TABLE_SIZE];
};

static struct ebt_table_desc ebt_tables[] = {
    {.name = "filter"},
    {.name = "nat"},
    {.name = "broute"},
};

static void checkpoint_ebtables(void)
{
	socklen_t optlen;
	unsigned i;
	int fd;
	fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
	if (fd == -1) {
		switch (errno) {
		case EAFNOSUPPORT:
		case ENOPROTOOPT:
			return;
		}
	exit(1);
	}
	for (i = 0; i < sizeof(ebt_tables) / sizeof(ebt_tables[0]); i++) {
		struct ebt_table_desc* table = &ebt_tables[i];
		strcpy(table->replace.name, table->name);
		optlen = sizeof(table->replace);
		if (getsockopt(fd, SOL_IP, EBT_SO_GET_INIT_INFO, &table->replace, &optlen)) {
			switch (errno) {
			case EPERM:
			case ENOENT:
			case ENOPROTOOPT:
				continue;
			}
	exit(1);
		}
		if (table->replace.entries_size > sizeof(table->entrytable))
	exit(1);
		table->replace.num_counters = 0;
		table->replace.entries = table->entrytable;
		optlen = sizeof(table->replace) + table->replace.entries_size;
		if (getsockopt(fd, SOL_IP, EBT_SO_GET_INIT_ENTRIES, &table->replace, &optlen))
	exit(1);
	}
	close(fd);
}

static void reset_ebtables()
{
	struct ebt_replace replace;
	char entrytable[XT_TABLE_SIZE];
	socklen_t optlen;
	unsigned i, j, h;
	int fd;
	fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
	if (fd == -1) {
		switch (errno) {
		case EAFNOSUPPORT:
		case ENOPROTOOPT:
			return;
		}
	exit(1);
	}
	for (i = 0; i < sizeof(ebt_tables) / sizeof(ebt_tables[0]); i++) {
		struct ebt_table_desc* table = &ebt_tables[i];
		if (table->replace.valid_hooks == 0)
			continue;
		memset(&replace, 0, sizeof(replace));
		strcpy(replace.name, table->name);
		optlen = sizeof(replace);
		if (getsockopt(fd, SOL_IP, EBT_SO_GET_INFO, &replace, &optlen))
	exit(1);
		replace.num_counters = 0;
		table->replace.entries = 0;
		for (h = 0; h < NF_BR_NUMHOOKS; h++)
			table->replace.hook_entry[h] = 0;
		if (memcmp(&table->replace, &replace, sizeof(table->replace)) == 0) {
			memset(&entrytable, 0, sizeof(entrytable));
			replace.entries = entrytable;
			optlen = sizeof(replace) + replace.entries_size;
			if (getsockopt(fd, SOL_IP, EBT_SO_GET_ENTRIES, &replace, &optlen))
	exit(1);
			if (memcmp(table->entrytable, entrytable, replace.entries_size) == 0)
				continue;
		}
		for (j = 0, h = 0; h < NF_BR_NUMHOOKS; h++) {
			if (table->replace.valid_hooks & (1 << h)) {
				table->replace.hook_entry[h] = (struct ebt_entries*)table->entrytable + j;
				j++;
			}
		}
		table->replace.entries = table->entrytable;
		optlen = sizeof(table->replace) + table->replace.entries_size;
		if (setsockopt(fd, SOL_IP, EBT_SO_SET_ENTRIES, &table->replace, optlen))
	exit(1);
	}
	close(fd);
}

static void checkpoint_net_namespace(void)
{
	checkpoint_ebtables();
	checkpoint_arptables();
	checkpoint_iptables(ipv4_tables, sizeof(ipv4_tables) / sizeof(ipv4_tables[0]), AF_INET, SOL_IP);
	checkpoint_iptables(ipv6_tables, sizeof(ipv6_tables) / sizeof(ipv6_tables[0]), AF_INET6, SOL_IPV6);
}

static void reset_net_namespace(void)
{
	reset_ebtables();
	reset_arptables();
	reset_iptables(ipv4_tables, sizeof(ipv4_tables) / sizeof(ipv4_tables[0]), AF_INET, SOL_IP);
	reset_iptables(ipv6_tables, sizeof(ipv6_tables) / sizeof(ipv6_tables[0]), AF_INET6, SOL_IPV6);
}

static void setup_cgroups()
{
	if (mkdir("/syzcgroup", 0777)) {
	}
	if (mkdir("/syzcgroup/unified", 0777)) {
	}
	if (mount("none", "/syzcgroup/unified", "cgroup2", 0, NULL)) {
	}
	if (chmod("/syzcgroup/unified", 0777)) {
	}
	write_file("/syzcgroup/unified/cgroup.subtree_control", "+cpu +memory +io +pids +rdma");
	if (mkdir("/syzcgroup/cpu", 0777)) {
	}
	if (mount("none", "/syzcgroup/cpu", "cgroup", 0, "cpuset,cpuacct,perf_event,hugetlb")) {
	}
	write_file("/syzcgroup/cpu/cgroup.clone_children", "1");
	if (chmod("/syzcgroup/cpu", 0777)) {
	}
	if (mkdir("/syzcgroup/net", 0777)) {
	}
	if (mount("none", "/syzcgroup/net", "cgroup", 0, "net_cls,net_prio,devices,freezer")) {
	}
	if (chmod("/syzcgroup/net", 0777)) {
	}
}

static void setup_cgroups_loop()
{
	int pid = getpid();
	char file[128];
	char cgroupdir[64];
	snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/unified/syz%llu", procid);
	if (mkdir(cgroupdir, 0777)) {
	}
	snprintf(file, sizeof(file), "%s/pids.max", cgroupdir);
	write_file(file, "32");
	snprintf(file, sizeof(file), "%s/memory.low", cgroupdir);
	write_file(file, "%d", 298 << 20);
	snprintf(file, sizeof(file), "%s/memory.high", cgroupdir);
	write_file(file, "%d", 299 << 20);
	snprintf(file, sizeof(file), "%s/memory.max", cgroupdir);
	write_file(file, "%d", 300 << 20);
	snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir);
	write_file(file, "%d", pid);
	snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/cpu/syz%llu", procid);
	if (mkdir(cgroupdir, 0777)) {
	}
	snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir);
	write_file(file, "%d", pid);
	snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/net/syz%llu", procid);
	if (mkdir(cgroupdir, 0777)) {
	}
	snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir);
	write_file(file, "%d", pid);
}

static void setup_cgroups_test()
{
	char cgroupdir[64];
	snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/unified/syz%llu", procid);
	if (symlink(cgroupdir, "./cgroup")) {
	}
	snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/cpu/syz%llu", procid);
	if (symlink(cgroupdir, "./cgroup.cpu")) {
	}
	snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/net/syz%llu", procid);
	if (symlink(cgroupdir, "./cgroup.net")) {
	}
}

static void setup_common()
{
	if (mount(0, "/sys/fs/fuse/connections", "fusectl", 0, 0)) {
	}
	setup_cgroups();
}

static void loop();

static void sandbox_common()
{
	prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
	setpgrp();
	setsid();
	int netns = open("/proc/self/ns/net", O_RDONLY);
	if (netns == -1)
	exit(1);
	if (dup2(netns, kInitNetNsFd) < 0)
	exit(1);
	close(netns);
	struct rlimit rlim;
	rlim.rlim_cur = rlim.rlim_max = (200 << 20);
	setrlimit(RLIMIT_AS, &rlim);
	rlim.rlim_cur = rlim.rlim_max = 32 << 20;
	setrlimit(RLIMIT_MEMLOCK, &rlim);
	rlim.rlim_cur = rlim.rlim_max = 136 << 20;
	setrlimit(RLIMIT_FSIZE, &rlim);
	rlim.rlim_cur = rlim.rlim_max = 1 << 20;
	setrlimit(RLIMIT_STACK, &rlim);
	rlim.rlim_cur = rlim.rlim_max = 0;
	setrlimit(RLIMIT_CORE, &rlim);
	rlim.rlim_cur = rlim.rlim_max = 256;
	setrlimit(RLIMIT_NOFILE, &rlim);
	if (unshare(CLONE_NEWNS)) {
	}
	if (unshare(CLONE_NEWIPC)) {
	}
	if (unshare(0x02000000)) {
	}
	if (unshare(CLONE_NEWUTS)) {
	}
	if (unshare(CLONE_SYSVSEM)) {
	}
	typedef struct {
		const char* name;
		const char* value;
	} sysctl_t;
	static const sysctl_t sysctls[] = {
	    {"/proc/sys/kernel/shmmax", "16777216"},
	    {"/proc/sys/kernel/shmall", "536870912"},
	    {"/proc/sys/kernel/shmmni", "1024"},
	    {"/proc/sys/kernel/msgmax", "8192"},
	    {"/proc/sys/kernel/msgmni", "1024"},
	    {"/proc/sys/kernel/msgmnb", "1024"},
	    {"/proc/sys/kernel/sem", "1024 1048576 500 1024"},
	};
	unsigned i;
	for (i = 0; i < sizeof(sysctls) / sizeof(sysctls[0]); i++)
		write_file(sysctls[i].name, sysctls[i].value);
}

int wait_for_loop(int pid)
{
	if (pid < 0)
	exit(1);
	int status = 0;
	while (waitpid(-1, &status, __WALL) != pid) {
	}
	return WEXITSTATUS(status);
}

static void drop_caps(void)
{
	struct __user_cap_header_struct cap_hdr = {};
	struct __user_cap_data_struct cap_data[2] = {};
	cap_hdr.version = _LINUX_CAPABILITY_VERSION_3;
	cap_hdr.pid = getpid();
	if (syscall(SYS_capget, &cap_hdr, &cap_data))
	exit(1);
	const int drop = (1 << CAP_SYS_PTRACE) | (1 << CAP_SYS_NICE);
	cap_data[0].effective &= ~drop;
	cap_data[0].permitted &= ~drop;
	cap_data[0].inheritable &= ~drop;
	if (syscall(SYS_capset, &cap_hdr, &cap_data))
	exit(1);
}

static int do_sandbox_none(void)
{
	if (unshare(CLONE_NEWPID)) {
	}
	int pid = fork();
	if (pid != 0)
		return wait_for_loop(pid);
	setup_common();
	sandbox_common();
	drop_caps();
	initialize_netdevices_init();
	if (unshare(CLONE_NEWNET)) {
	}
	initialize_devlink_pci();
	initialize_tun();
	initialize_netdevices();
	loop();
	exit(1);
}

#define FS_IOC_SETFLAGS _IOW('f', 2, long)
static void remove_dir(const char* dir)
{
	DIR* dp;
	struct dirent* ep;
	int iter = 0;
retry:
	while (umount2(dir, MNT_DETACH) == 0) {
	}
	dp = opendir(dir);
	if (dp == NULL) {
		if (errno == EMFILE) {
	exit(1);
		}
	exit(1);
	}
	while ((ep = readdir(dp))) {
		if (strcmp(ep->d_name, ".") == 0 || strcmp(ep->d_name, "..") == 0)
			continue;
		char filename[FILENAME_MAX];
		snprintf(filename, sizeof(filename), "%s/%s", dir, ep->d_name);
		while (umount2(filename, MNT_DETACH) == 0) {
		}
		struct stat st;
		if (lstat(filename, &st))
	exit(1);
		if (S_ISDIR(st.st_mode)) {
			remove_dir(filename);
			continue;
		}
		int i;
		for (i = 0;; i++) {
			if (unlink(filename) == 0)
				break;
			if (errno == EPERM) {
				int fd = open(filename, O_RDONLY);
				if (fd != -1) {
					long flags = 0;
					if (ioctl(fd, FS_IOC_SETFLAGS, &flags) == 0)
					close(fd);
					continue;
				}
			}
			if (errno == EROFS) {
				break;
			}
			if (errno != EBUSY || i > 100)
	exit(1);
			if (umount2(filename, MNT_DETACH))
	exit(1);
		}
	}
	closedir(dp);
	int i;
	for (i = 0;; i++) {
		if (rmdir(dir) == 0)
			break;
		if (i < 100) {
			if (errno == EPERM) {
				int fd = open(dir, O_RDONLY);
				if (fd != -1) {
					long flags = 0;
					if (ioctl(fd, FS_IOC_SETFLAGS, &flags) == 0)
					close(fd);
					continue;
				}
			}
			if (errno == EROFS) {
				break;
			}
			if (errno == EBUSY) {
				if (umount2(dir, MNT_DETACH))
	exit(1);
				continue;
			}
			if (errno == ENOTEMPTY) {
				if (iter < 100) {
					iter++;
					goto retry;
				}
			}
		}
	exit(1);
	}
}

static void kill_and_wait(int pid, int* status)
{
	kill(-pid, SIGKILL);
	kill(pid, SIGKILL);
	int i;
	for (i = 0; i < 100; i++) {
		if (waitpid(-1, status, WNOHANG | __WALL) == pid)
			return;
		usleep(1000);
	}
	DIR* dir = opendir("/sys/fs/fuse/connections");
	if (dir) {
		for (;;) {
			struct dirent* ent = readdir(dir);
			if (!ent)
				break;
			if (strcmp(ent->d_name, ".") == 0 || strcmp(ent->d_name, "..") == 0)
				continue;
			char abort[300];
			snprintf(abort, sizeof(abort), "/sys/fs/fuse/connections/%s/abort", ent->d_name);
			int fd = open(abort, O_WRONLY);
			if (fd == -1) {
				continue;
			}
			if (write(fd, abort, 1) < 0) {
			}
			close(fd);
		}
		closedir(dir);
	} else {
	}
	while (waitpid(-1, status, __WALL) != pid) {
	}
}

static void setup_loop()
{
	setup_cgroups_loop();
	checkpoint_net_namespace();
}

static void reset_loop()
{
	reset_net_namespace();
}

static void setup_test()
{
	prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
	setpgrp();
	setup_cgroups_test();
	write_file("/proc/self/oom_score_adj", "1000");
	flush_tun();
}

static void close_fds()
{
	int fd;
	for (fd = 3; fd < MAX_FDS; fd++)
		close(fd);
}

static void setup_binfmt_misc()
{
	if (mount(0, "/proc/sys/fs/binfmt_misc", "binfmt_misc", 0, 0)) {
	}
	write_file("/proc/sys/fs/binfmt_misc/register", ":syz0:M:0:\x01::./file0:");
	write_file("/proc/sys/fs/binfmt_misc/register", ":syz1:M:1:\x02::./file0:POC");
}

struct thread_t {
	int created, call;
	event_t ready, done;
};

static struct thread_t threads[16];
static void execute_call(int call);
static int running;

static void* thr(void* arg)
{
	struct thread_t* th = (struct thread_t*)arg;
	for (;;) {
		event_wait(&th->ready);
		event_reset(&th->ready);
		execute_call(th->call);
		__atomic_fetch_sub(&running, 1, __ATOMIC_RELAXED);
		event_set(&th->done);
	}
	return 0;
}

static void execute_one(void)
{
	if (write(1, "executing program\n", sizeof("executing program\n") - 1)) {
	}
	int i, call, thread;
	int collide = 0;
again:
	for (call = 0; call < 3; call++) {
		for (thread = 0; thread < (int)(sizeof(threads) / sizeof(threads[0])); thread++) {
			struct thread_t* th = &threads[thread];
			if (!th->created) {
				th->created = 1;
				event_init(&th->ready);
				event_init(&th->done);
				event_set(&th->done);
				thread_start(thr, th);
			}
			if (!event_isset(&th->done))
				continue;
			event_reset(&th->done);
			th->call = call;
			__atomic_fetch_add(&running, 1, __ATOMIC_RELAXED);
			event_set(&th->ready);
			if (collide && (call % 2) == 0)
				break;
			event_timedwait(&th->done, 45);
			break;
		}
	}
	for (i = 0; i < 100 && __atomic_load_n(&running, __ATOMIC_RELAXED); i++)
		sleep_ms(1);
	close_fds();
	if (!collide) {
		collide = 1;
		goto again;
	}
}

static void execute_one(void);

#define WAIT_FLAGS __WALL

static void loop(void)
{
	setup_loop();
	int iter;
	for (iter = 0;; iter++) {
		char cwdbuf[32];
		sprintf(cwdbuf, "./%d", iter);
		if (mkdir(cwdbuf, 0777))
	exit(1);
		reset_loop();
		int pid = fork();
		if (pid < 0)
	exit(1);
		if (pid == 0) {
			if (chdir(cwdbuf))
	exit(1);
			setup_test();
			execute_one();
			exit(0);
		}
		int status = 0;
		uint64_t start = current_time_ms();
		for (;;) {
			if (waitpid(-1, &status, WNOHANG | WAIT_FLAGS) == pid)
				break;
			sleep_ms(1);
			if (current_time_ms() - start < 5 * 1000)
				continue;
			kill_and_wait(pid, &status);
			break;
		}
		remove_dir(cwdbuf);
	}
}

uint64_t r[1] = {0xffffffffffffffff};

unsigned char report_desc[] = {
    0x05, 0x01, /* USAGE_PAGE (Generic Desktop)	          */
    0x09, 0x06, /* USAGE (Keyboard)                       */
    0xa1, 0x01, /* COLLECTION (Application)               */
    0x05, 0x07, /*   USAGE_PAGE (Keyboard)                */
    0x19, 0xe0, /*   USAGE_MINIMUM (Keyboard LeftControl) */
    0x29, 0xe7, /*   USAGE_MAXIMUM (Keyboard Right GUI)   */
    0x15, 0x00, /*   LOGICAL_MINIMUM (0)                  */
    0x25, 0x01, /*   LOGICAL_MAXIMUM (1)                  */
    0x75, 0x01, /*   REPORT_SIZE (1)                      */
    0x95, 0x08, /*   REPORT_COUNT (8)                     */
    0x81, 0x02, /*   INPUT (Data,Var,Abs)                 */
    0x95, 0x01, /*   REPORT_COUNT (1)                     */
    0x75, 0x08, /*   REPORT_SIZE (8)                      */
    0x81, 0x03, /*   INPUT (Cnst,Var,Abs)                 */
    0x95, 0x05, /*   REPORT_COUNT (5)                     */
    0x75, 0x01, /*   REPORT_SIZE (1)                      */
    0x05, 0x08, /*   USAGE_PAGE (LEDs)                    */
    0x19, 0x01, /*   USAGE_MINIMUM (Num Lock)             */
    0x29, 0x05, /*   USAGE_MAXIMUM (Kana)                 */
    0x91, 0x02, /*   OUTPUT (Data,Var,Abs)                */
    0x95, 0x01, /*   REPORT_COUNT (1)                     */
    0x75, 0x03, /*   REPORT_SIZE (3)                      */
    0x91, 0x03, /*   OUTPUT (Cnst,Var,Abs)                */
    0x95, 0x06, /*   REPORT_COUNT (6)                     */
    0x75, 0x08, /*   REPORT_SIZE (8)                      */
    0x15, 0x00, /*   LOGICAL_MINIMUM (0)                  */
    0x25, 0x65, /*   LOGICAL_MAXIMUM (101)                */
    0x05, 0x07, /*   USAGE_PAGE (Keyboard)                */
    0x19, 0x00, /*   USAGE_MINIMUM (Reserved)             */
    0x29, 0x65, /*   USAGE_MAXIMUM (Keyboard Application) */
    0x81, 0x00, /*   INPUT (Data,Ary,Abs)                 */
    0xc0 /* END_COLLECTION                         */
};

static void syz_usb_configfs_hid()
{
	int fd_gadget, ret;

	struct stat st;
	stat("/sys/kernel/config/usb_gadget/g1", &st);
	if (S_ISDIR(st.st_mode)) {
		return;
	}

	ret = mkdir("/sys/kernel/config/usb_gadget/g1", O_RDWR);
	fd_gadget = open("/sys/kernel/config/usb_gadget/g1/idVendor", O_RDWR);
	ret = write(fd_gadget, "0x41e", 6);
	close(fd_gadget);
	fd_gadget = open("/sys/kernel/config/usb_gadget/g1/idProduct", O_RDWR);
	ret = write(fd_gadget, "0x2801", 7);
	close(fd_gadget);

	ret = mkdir("/sys/kernel/config/usb_gadget/g1/configs/c.1", O_RDWR);
	ret = mkdir("/sys/kernel/config/usb_gadget/g1/functions/hid.usb0", O_RDWR);
	fd_gadget = open("/sys/kernel/config/usb_gadget/g1/functions/hid.usb0/subclass", O_RDWR);
	ret = write(fd_gadget, "1", 2);
	close(fd_gadget);
	fd_gadget = open("/sys/kernel/config/usb_gadget/g1/functions/hid.usb0/protocol", O_RDWR);
	ret = write(fd_gadget, "1", 2);
	close(fd_gadget);
	fd_gadget = open("/sys/kernel/config/usb_gadget/g1/functions/hid.usb0/report_length", O_RDWR);
	ret = write(fd_gadget, "8", 2);
	close(fd_gadget);
	fd_gadget = open("/sys/kernel/config/usb_gadget/g1/functions/hid.usb0/report_desc", O_RDWR);
	ret = write(fd_gadget, report_desc, sizeof(report_desc));
	close(fd_gadget);

	fd_gadget = open("/sys/kernel/config/usb_gadget/g1/", O_RDONLY | O_DIRECTORY);
	ret = symlinkat("/sys/kernel/config/usb_gadget/g1/functions/hid.usb0", fd_gadget, "configs/c.1/hid.usb0");
	if (ret < 0)
		printf("syz_usb_configfs_hid fail symlink..%d\n", ret);
	close(fd_gadget);

	fd_gadget = open("/sys/kernel/config/usb_gadget/g1/UDC", O_RDWR);
	ret = write(fd_gadget, "dummy_udc.0", 12);
	close(fd_gadget);
}
void execute_call(int call)
{
		intptr_t res;	switch (call) {
	case 0:
		syz_usb_configfs_hid();
		break;
	case 1:
		NONFAILING(memcpy((void*)0x20002580, "/dev/hidg0\000", 11));
		res = syscall(__NR_open, 0x20002580ul, 2ul, 0x150ul);
		if (res != -1)
				r[0] = res;
		break;
	case 2:
		NONFAILING(memcpy((void*)0x200025c0, "\x40\xca\x1a\x1a\x2b\x61\x5b\x8b\x51\x5e\x35\x53\xc6\x02\x6d\x19\x34\x50\x17\xf3\xa4\xdb\x30\x09\x05\xbb\x30\x03\x1d\xda\x94\x68\x92\x1a\x65\x37\x1a\x25\x24\x6c\x7f\xad\x5b\xa4\x67\x45\xc1\x84\x34\xf5\xa0\x7f\xab\xdb\x24\xa2\x9f\xdb\xe0\xe5\xaf\x8e\xb1\xad\x6a\x25\x8c\xd1\x47\x5a\x28\x07\x1d\x72\x2f\xe0\x2d\x30\xcd\x4c\xf9\x02\xc2\x56\xfd\x29\xae\xd8\x17\xd2\xa8\x33\xf1\x16\xec\xb9\x98\x63\x44\xab\xe7\x65\x5c\x29\x3d\xc8\xbd\xb5\xa5\xc1\x5f\xaa\xb9\xe8\x4e\x60\x63\xdf\x7a\x47\xc5\xce", 122));
		syscall(__NR_write, r[0], 0x200025c0ul, 0x7aul);
		break;
	}

}
int main(void)
{
		syscall(__NR_mmap, 0x20000000ul, 0x1000000ul, 3ul, 0x32ul, -1, 0);
	setup_binfmt_misc();
	install_segv_handler();
	for (procid = 0; procid < 8; procid++) {
		if (fork() == 0) {
			use_temporary_dir();
			do_sandbox_none();
		}
	}
	sleep(1000000);
	return 0;
}