0d24148bd2
Blamed commit broke the assumption used by ping sendmsg() that allocated skb would have MAX_HEADER bytes in skb->head. This patch changes the way ping works, by making sure the skb head contains space for the icmp header, and adjusting ping_getfrag() which was desperate about going past the icmp header :/ This is adopting what UDP does, mostly. syzbot is able to crash a host using both kfence and following repro in a loop. fd = socket(AF_INET6, SOCK_DGRAM, IPPROTO_ICMPV6) connect(fd, {sa_family=AF_INET6, sin6_port=htons(0), sin6_flowinfo=htonl(0), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_scope_id=0}, 28 sendmsg(fd, {msg_name=NULL, msg_namelen=0, msg_iov=[ {iov_base="\200\0\0\0\23\0\0\0\0\0\0\0\0\0"..., iov_len=65496}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0 When kfence triggers, skb->head only has 64 bytes, immediately followed by struct skb_shared_info (no extra headroom based on ksize(ptr)) Then icmpv6_push_pending_frames() is overwriting first bytes of skb_shinfo(skb), making nr_frags bigger than MAX_SKB_FRAGS, and/or setting shinfo->gso_size to a non zero value. If nr_frags is mangled, a crash happens in skb_release_data() If gso_size is mangled, we have the following report: lo: caps=(0x00000516401d7c69, 0x00000516401d7c69) WARNING: CPU: 0 PID: 7548 at net/core/dev.c:3239 skb_warn_bad_offload+0x119/0x230 net/core/dev.c:3239 Modules linked in: CPU: 0 PID: 7548 Comm: syz-executor268 Not tainted 6.0.0-syzkaller-02754-g557f050166e5 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/22/2022 RIP: 0010:skb_warn_bad_offload+0x119/0x230 net/core/dev.c:3239 Code: 70 03 00 00 e8 58 c3 24 fa 4c 8d a5 e8 00 00 00 e8 4c c3 24 fa 4c 89 e9 4c 89 e2 4c 89 f6 48 c7 c7 00 53 f5 8a e8 13 ac e7 01 <0f> 0b 5b 5d 41 5c 41 5d 41 5e e9 28 c3 24 fa e8 23 c3 24 fa 48 89 RSP: 0018:ffffc9000366f3e8 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff88807a9d9d00 RCX: 0000000000000000 RDX: ffff8880780c0000 RSI: ffffffff8160f6f8 RDI: fffff520006cde6f RBP: ffff888079952000 R08: 0000000000000005 R09: 0000000000000000 R10: 0000000000000400 R11: 0000000000000000 R12: ffff8880799520e8 R13: ffff88807a9da070 R14: ffff888079952000 R15: 0000000000000000 FS: 0000555556be6300(0000) GS:ffff8880b9a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020010000 CR3: 000000006eb7b000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> gso_features_check net/core/dev.c:3521 [inline] netif_skb_features+0x83e/0xb90 net/core/dev.c:3554 validate_xmit_skb+0x2b/0xf10 net/core/dev.c:3659 __dev_queue_xmit+0x998/0x3ad0 net/core/dev.c:4248 dev_queue_xmit include/linux/netdevice.h:3008 [inline] neigh_hh_output include/net/neighbour.h:530 [inline] neigh_output include/net/neighbour.h:544 [inline] ip6_finish_output2+0xf97/0x1520 net/ipv6/ip6_output.c:134 __ip6_finish_output net/ipv6/ip6_output.c:195 [inline] ip6_finish_output+0x690/0x1160 net/ipv6/ip6_output.c:206 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip6_output+0x1ed/0x540 net/ipv6/ip6_output.c:227 dst_output include/net/dst.h:445 [inline] ip6_local_out+0xaf/0x1a0 net/ipv6/output_core.c:161 ip6_send_skb+0xb7/0x340 net/ipv6/ip6_output.c:1966 ip6_push_pending_frames+0xdd/0x100 net/ipv6/ip6_output.c:1986 icmpv6_push_pending_frames+0x2af/0x490 net/ipv6/icmp.c:303 ping_v6_sendmsg+0xc44/0x1190 net/ipv6/ping.c:190 inet_sendmsg+0x99/0xe0 net/ipv4/af_inet.c:819 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:734 ____sys_sendmsg+0x712/0x8c0 net/socket.c:2482 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2536 __sys_sendmsg+0xf3/0x1c0 net/socket.c:2565 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f21aab42b89 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 41 15 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fff1729d038 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f21aab42b89 RDX: 0000000000000000 RSI: 0000000020000180 RDI: 0000000000000003 RBP: 0000000000000000 R08: 000000000000000d R09: 000000000000000d R10: 000000000000000d R11: 0000000000000246 R12: 00007fff1729d050 R13: 00000000000f4240 R14: 0000000000021dd1 R15: 00007fff1729d044 </TASK> Fixes: 47cf88993c91 ("net: unify alloclen calculation for paged requests") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Pavel Begunkov <asml.silence@gmail.com> Cc: Lorenzo Colitti <lorenzo@google.com> Cc: Willem de Bruijn <willemb@google.com> Cc: Maciej Żenczykowski <maze@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
313 lines
8.1 KiB
C
313 lines
8.1 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/*
|
|
* INET An implementation of the TCP/IP protocol suite for the LINUX
|
|
* operating system. INET is implemented using the BSD Socket
|
|
* interface as the means of communication with the user level.
|
|
*
|
|
* "Ping" sockets
|
|
*
|
|
* Based on ipv4/ping.c code.
|
|
*
|
|
* Authors: Lorenzo Colitti (IPv6 support)
|
|
* Vasiliy Kulikov / Openwall (IPv4 implementation, for Linux 2.6),
|
|
* Pavel Kankovsky (IPv4 implementation, for Linux 2.4.32)
|
|
*/
|
|
|
|
#include <net/addrconf.h>
|
|
#include <net/ipv6.h>
|
|
#include <net/ip6_route.h>
|
|
#include <net/protocol.h>
|
|
#include <net/udp.h>
|
|
#include <net/transp_v6.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/bpf-cgroup.h>
|
|
#include <net/ping.h>
|
|
|
|
static void ping_v6_destroy(struct sock *sk)
|
|
{
|
|
inet6_destroy_sock(sk);
|
|
}
|
|
|
|
/* Compatibility glue so we can support IPv6 when it's compiled as a module */
|
|
static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
|
|
int *addr_len)
|
|
{
|
|
return -EAFNOSUPPORT;
|
|
}
|
|
static void dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
|
|
struct sk_buff *skb)
|
|
{
|
|
}
|
|
static int dummy_icmpv6_err_convert(u8 type, u8 code, int *err)
|
|
{
|
|
return -EAFNOSUPPORT;
|
|
}
|
|
static void dummy_ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
|
|
__be16 port, u32 info, u8 *payload) {}
|
|
static int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
|
|
const struct net_device *dev, int strict)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static int ping_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
|
|
int addr_len)
|
|
{
|
|
/* This check is replicated from __ip6_datagram_connect() and
|
|
* intended to prevent BPF program called below from accessing
|
|
* bytes that are out of the bound specified by user in addr_len.
|
|
*/
|
|
|
|
if (addr_len < SIN6_LEN_RFC2133)
|
|
return -EINVAL;
|
|
|
|
return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr);
|
|
}
|
|
|
|
static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
|
|
{
|
|
struct inet_sock *inet = inet_sk(sk);
|
|
struct ipv6_pinfo *np = inet6_sk(sk);
|
|
struct icmp6hdr user_icmph;
|
|
int addr_type;
|
|
struct in6_addr *daddr;
|
|
int oif = 0;
|
|
struct flowi6 fl6;
|
|
int err;
|
|
struct dst_entry *dst;
|
|
struct rt6_info *rt;
|
|
struct pingfakehdr pfh;
|
|
struct ipcm6_cookie ipc6;
|
|
|
|
err = ping_common_sendmsg(AF_INET6, msg, len, &user_icmph,
|
|
sizeof(user_icmph));
|
|
if (err)
|
|
return err;
|
|
|
|
memset(&fl6, 0, sizeof(fl6));
|
|
|
|
if (msg->msg_name) {
|
|
DECLARE_SOCKADDR(struct sockaddr_in6 *, u, msg->msg_name);
|
|
if (msg->msg_namelen < sizeof(*u))
|
|
return -EINVAL;
|
|
if (u->sin6_family != AF_INET6) {
|
|
return -EAFNOSUPPORT;
|
|
}
|
|
daddr = &(u->sin6_addr);
|
|
if (np->sndflow)
|
|
fl6.flowlabel = u->sin6_flowinfo & IPV6_FLOWINFO_MASK;
|
|
if (__ipv6_addr_needs_scope_id(ipv6_addr_type(daddr)))
|
|
oif = u->sin6_scope_id;
|
|
} else {
|
|
if (sk->sk_state != TCP_ESTABLISHED)
|
|
return -EDESTADDRREQ;
|
|
daddr = &sk->sk_v6_daddr;
|
|
fl6.flowlabel = np->flow_label;
|
|
}
|
|
|
|
if (!oif)
|
|
oif = sk->sk_bound_dev_if;
|
|
|
|
if (!oif)
|
|
oif = np->sticky_pktinfo.ipi6_ifindex;
|
|
|
|
if (!oif && ipv6_addr_is_multicast(daddr))
|
|
oif = np->mcast_oif;
|
|
else if (!oif)
|
|
oif = np->ucast_oif;
|
|
|
|
addr_type = ipv6_addr_type(daddr);
|
|
if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) ||
|
|
(addr_type & IPV6_ADDR_MAPPED) ||
|
|
(oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if))
|
|
return -EINVAL;
|
|
|
|
ipcm6_init_sk(&ipc6, np);
|
|
ipc6.sockc.tsflags = sk->sk_tsflags;
|
|
ipc6.sockc.mark = sk->sk_mark;
|
|
|
|
fl6.flowi6_oif = oif;
|
|
|
|
if (msg->msg_controllen) {
|
|
struct ipv6_txoptions opt = {};
|
|
|
|
opt.tot_len = sizeof(opt);
|
|
ipc6.opt = &opt;
|
|
|
|
err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6);
|
|
if (err < 0)
|
|
return err;
|
|
|
|
/* Changes to txoptions and flow info are not implemented, yet.
|
|
* Drop the options.
|
|
*/
|
|
ipc6.opt = NULL;
|
|
}
|
|
|
|
fl6.flowi6_proto = IPPROTO_ICMPV6;
|
|
fl6.saddr = np->saddr;
|
|
fl6.daddr = *daddr;
|
|
fl6.flowi6_mark = ipc6.sockc.mark;
|
|
fl6.flowi6_uid = sk->sk_uid;
|
|
fl6.fl6_icmp_type = user_icmph.icmp6_type;
|
|
fl6.fl6_icmp_code = user_icmph.icmp6_code;
|
|
security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
|
|
|
|
fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
|
|
|
|
dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, false);
|
|
if (IS_ERR(dst))
|
|
return PTR_ERR(dst);
|
|
rt = (struct rt6_info *) dst;
|
|
|
|
if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
|
|
fl6.flowi6_oif = np->mcast_oif;
|
|
else if (!fl6.flowi6_oif)
|
|
fl6.flowi6_oif = np->ucast_oif;
|
|
|
|
pfh.icmph.type = user_icmph.icmp6_type;
|
|
pfh.icmph.code = user_icmph.icmp6_code;
|
|
pfh.icmph.checksum = 0;
|
|
pfh.icmph.un.echo.id = inet->inet_sport;
|
|
pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence;
|
|
pfh.msg = msg;
|
|
pfh.wcheck = 0;
|
|
pfh.family = AF_INET6;
|
|
|
|
if (ipc6.hlimit < 0)
|
|
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
|
|
|
|
lock_sock(sk);
|
|
err = ip6_append_data(sk, ping_getfrag, &pfh, len,
|
|
sizeof(struct icmp6hdr), &ipc6, &fl6, rt,
|
|
MSG_DONTWAIT);
|
|
|
|
if (err) {
|
|
ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev,
|
|
ICMP6_MIB_OUTERRORS);
|
|
ip6_flush_pending_frames(sk);
|
|
} else {
|
|
icmpv6_push_pending_frames(sk, &fl6,
|
|
(struct icmp6hdr *)&pfh.icmph, len);
|
|
}
|
|
release_sock(sk);
|
|
|
|
dst_release(dst);
|
|
|
|
if (err)
|
|
return err;
|
|
|
|
return len;
|
|
}
|
|
|
|
struct proto pingv6_prot = {
|
|
.name = "PINGv6",
|
|
.owner = THIS_MODULE,
|
|
.init = ping_init_sock,
|
|
.close = ping_close,
|
|
.destroy = ping_v6_destroy,
|
|
.pre_connect = ping_v6_pre_connect,
|
|
.connect = ip6_datagram_connect_v6_only,
|
|
.disconnect = __udp_disconnect,
|
|
.setsockopt = ipv6_setsockopt,
|
|
.getsockopt = ipv6_getsockopt,
|
|
.sendmsg = ping_v6_sendmsg,
|
|
.recvmsg = ping_recvmsg,
|
|
.bind = ping_bind,
|
|
.backlog_rcv = ping_queue_rcv_skb,
|
|
.hash = ping_hash,
|
|
.unhash = ping_unhash,
|
|
.get_port = ping_get_port,
|
|
.put_port = ping_unhash,
|
|
.obj_size = sizeof(struct raw6_sock),
|
|
};
|
|
EXPORT_SYMBOL_GPL(pingv6_prot);
|
|
|
|
static struct inet_protosw pingv6_protosw = {
|
|
.type = SOCK_DGRAM,
|
|
.protocol = IPPROTO_ICMPV6,
|
|
.prot = &pingv6_prot,
|
|
.ops = &inet6_sockraw_ops,
|
|
.flags = INET_PROTOSW_REUSE,
|
|
};
|
|
|
|
#ifdef CONFIG_PROC_FS
|
|
static void *ping_v6_seq_start(struct seq_file *seq, loff_t *pos)
|
|
{
|
|
return ping_seq_start(seq, pos, AF_INET6);
|
|
}
|
|
|
|
static int ping_v6_seq_show(struct seq_file *seq, void *v)
|
|
{
|
|
if (v == SEQ_START_TOKEN) {
|
|
seq_puts(seq, IPV6_SEQ_DGRAM_HEADER);
|
|
} else {
|
|
int bucket = ((struct ping_iter_state *) seq->private)->bucket;
|
|
struct inet_sock *inet = inet_sk(v);
|
|
__u16 srcp = ntohs(inet->inet_sport);
|
|
__u16 destp = ntohs(inet->inet_dport);
|
|
ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static const struct seq_operations ping_v6_seq_ops = {
|
|
.start = ping_v6_seq_start,
|
|
.show = ping_v6_seq_show,
|
|
.next = ping_seq_next,
|
|
.stop = ping_seq_stop,
|
|
};
|
|
|
|
static int __net_init ping_v6_proc_init_net(struct net *net)
|
|
{
|
|
if (!proc_create_net("icmp6", 0444, net->proc_net, &ping_v6_seq_ops,
|
|
sizeof(struct ping_iter_state)))
|
|
return -ENOMEM;
|
|
return 0;
|
|
}
|
|
|
|
static void __net_exit ping_v6_proc_exit_net(struct net *net)
|
|
{
|
|
remove_proc_entry("icmp6", net->proc_net);
|
|
}
|
|
|
|
static struct pernet_operations ping_v6_net_ops = {
|
|
.init = ping_v6_proc_init_net,
|
|
.exit = ping_v6_proc_exit_net,
|
|
};
|
|
#endif
|
|
|
|
int __init pingv6_init(void)
|
|
{
|
|
#ifdef CONFIG_PROC_FS
|
|
int ret = register_pernet_subsys(&ping_v6_net_ops);
|
|
if (ret)
|
|
return ret;
|
|
#endif
|
|
pingv6_ops.ipv6_recv_error = ipv6_recv_error;
|
|
pingv6_ops.ip6_datagram_recv_common_ctl = ip6_datagram_recv_common_ctl;
|
|
pingv6_ops.ip6_datagram_recv_specific_ctl =
|
|
ip6_datagram_recv_specific_ctl;
|
|
pingv6_ops.icmpv6_err_convert = icmpv6_err_convert;
|
|
pingv6_ops.ipv6_icmp_error = ipv6_icmp_error;
|
|
pingv6_ops.ipv6_chk_addr = ipv6_chk_addr;
|
|
return inet6_register_protosw(&pingv6_protosw);
|
|
}
|
|
|
|
/* This never gets called because it's not possible to unload the ipv6 module,
|
|
* but just in case.
|
|
*/
|
|
void pingv6_exit(void)
|
|
{
|
|
pingv6_ops.ipv6_recv_error = dummy_ipv6_recv_error;
|
|
pingv6_ops.ip6_datagram_recv_common_ctl = dummy_ip6_datagram_recv_ctl;
|
|
pingv6_ops.ip6_datagram_recv_specific_ctl = dummy_ip6_datagram_recv_ctl;
|
|
pingv6_ops.icmpv6_err_convert = dummy_icmpv6_err_convert;
|
|
pingv6_ops.ipv6_icmp_error = dummy_ipv6_icmp_error;
|
|
pingv6_ops.ipv6_chk_addr = dummy_ipv6_chk_addr;
|
|
#ifdef CONFIG_PROC_FS
|
|
unregister_pernet_subsys(&ping_v6_net_ops);
|
|
#endif
|
|
inet6_unregister_protosw(&pingv6_protosw);
|
|
}
|