linux/net/ipv4/syncookies.c
Eric Dumazet c92e8c02fe tcp/dccp: fix ireq->opt races
syzkaller found another bug in DCCP/TCP stacks [1]

For the reasons explained in commit ce1050089c ("tcp/dccp: fix
ireq->pktopts race"), we need to make sure we do not access
ireq->opt unless we own the request sock.

Note the opt field is renamed to ireq_opt to ease grep games.

[1]
BUG: KASAN: use-after-free in ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474
Read of size 1 at addr ffff8801c951039c by task syz-executor5/3295

CPU: 1 PID: 3295 Comm: syz-executor5 Not tainted 4.14.0-rc4+ #80
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 print_address_description+0x73/0x250 mm/kasan/report.c:252
 kasan_report_error mm/kasan/report.c:351 [inline]
 kasan_report+0x25b/0x340 mm/kasan/report.c:409
 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:427
 ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474
 tcp_transmit_skb+0x1ab7/0x3840 net/ipv4/tcp_output.c:1135
 tcp_send_ack.part.37+0x3bb/0x650 net/ipv4/tcp_output.c:3587
 tcp_send_ack+0x49/0x60 net/ipv4/tcp_output.c:3557
 __tcp_ack_snd_check+0x2c6/0x4b0 net/ipv4/tcp_input.c:5072
 tcp_ack_snd_check net/ipv4/tcp_input.c:5085 [inline]
 tcp_rcv_state_process+0x2eff/0x4850 net/ipv4/tcp_input.c:6071
 tcp_child_process+0x342/0x990 net/ipv4/tcp_minisocks.c:816
 tcp_v4_rcv+0x1827/0x2f80 net/ipv4/tcp_ipv4.c:1682
 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
 dst_input include/net/dst.h:464 [inline]
 ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
 netif_receive_skb+0xae/0x390 net/core/dev.c:4611
 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
 call_write_iter include/linux/fs.h:1770 [inline]
 new_sync_write fs/read_write.c:468 [inline]
 __vfs_write+0x68a/0x970 fs/read_write.c:481
 vfs_write+0x18f/0x510 fs/read_write.c:543
 SYSC_write fs/read_write.c:588 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:580
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x40c341
RSP: 002b:00007f469523ec10 EFLAGS: 00000293 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 000000000040c341
RDX: 0000000000000037 RSI: 0000000020004000 RDI: 0000000000000015
RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000
R10: 00000000000f4240 R11: 0000000000000293 R12: 00000000004b7fd1
R13: 00000000ffffffff R14: 0000000020000000 R15: 0000000000025000

Allocated by task 3295:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551
 __do_kmalloc mm/slab.c:3725 [inline]
 __kmalloc+0x162/0x760 mm/slab.c:3734
 kmalloc include/linux/slab.h:498 [inline]
 tcp_v4_save_options include/net/tcp.h:1962 [inline]
 tcp_v4_init_req+0x2d3/0x3e0 net/ipv4/tcp_ipv4.c:1271
 tcp_conn_request+0xf6d/0x3410 net/ipv4/tcp_input.c:6283
 tcp_v4_conn_request+0x157/0x210 net/ipv4/tcp_ipv4.c:1313
 tcp_rcv_state_process+0x8ea/0x4850 net/ipv4/tcp_input.c:5857
 tcp_v4_do_rcv+0x55c/0x7d0 net/ipv4/tcp_ipv4.c:1482
 tcp_v4_rcv+0x2d10/0x2f80 net/ipv4/tcp_ipv4.c:1711
 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
 dst_input include/net/dst.h:464 [inline]
 ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
 netif_receive_skb+0xae/0x390 net/core/dev.c:4611
 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
 call_write_iter include/linux/fs.h:1770 [inline]
 new_sync_write fs/read_write.c:468 [inline]
 __vfs_write+0x68a/0x970 fs/read_write.c:481
 vfs_write+0x18f/0x510 fs/read_write.c:543
 SYSC_write fs/read_write.c:588 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:580
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Freed by task 3306:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524
 __cache_free mm/slab.c:3503 [inline]
 kfree+0xca/0x250 mm/slab.c:3820
 inet_sock_destruct+0x59d/0x950 net/ipv4/af_inet.c:157
 __sk_destruct+0xfd/0x910 net/core/sock.c:1560
 sk_destruct+0x47/0x80 net/core/sock.c:1595
 __sk_free+0x57/0x230 net/core/sock.c:1603
 sk_free+0x2a/0x40 net/core/sock.c:1614
 sock_put include/net/sock.h:1652 [inline]
 inet_csk_complete_hashdance+0xd5/0xf0 net/ipv4/inet_connection_sock.c:959
 tcp_check_req+0xf4d/0x1620 net/ipv4/tcp_minisocks.c:765
 tcp_v4_rcv+0x17f6/0x2f80 net/ipv4/tcp_ipv4.c:1675
 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
 dst_input include/net/dst.h:464 [inline]
 ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
 netif_receive_skb+0xae/0x390 net/core/dev.c:4611
 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
 call_write_iter include/linux/fs.h:1770 [inline]
 new_sync_write fs/read_write.c:468 [inline]
 __vfs_write+0x68a/0x970 fs/read_write.c:481
 vfs_write+0x18f/0x510 fs/read_write.c:543
 SYSC_write fs/read_write.c:588 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:580
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Fixes: e994b2f0fb ("tcp: do not lock listener to process SYN packets")
Fixes: 079096f103 ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-21 01:33:19 +01:00

404 lines
12 KiB
C

/*
* Syncookies implementation for the Linux kernel
*
* Copyright (C) 1997 Andi Kleen
* Based on ideas by D.J.Bernstein and Eric Schenk.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/tcp.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/siphash.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <net/secure_seq.h>
#include <net/tcp.h>
#include <net/route.h>
static siphash_key_t syncookie_secret[2] __read_mostly;
#define COOKIEBITS 24 /* Upper bits store count */
#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
/* TCP Timestamp: 6 lowest bits of timestamp sent in the cookie SYN-ACK
* stores TCP options:
*
* MSB LSB
* | 31 ... 6 | 5 | 4 | 3 2 1 0 |
* | Timestamp | ECN | SACK | WScale |
*
* When we receive a valid cookie-ACK, we look at the echoed tsval (if
* any) to figure out which TCP options we should use for the rebuilt
* connection.
*
* A WScale setting of '0xf' (which is an invalid scaling value)
* means that original syn did not include the TCP window scaling option.
*/
#define TS_OPT_WSCALE_MASK 0xf
#define TS_OPT_SACK BIT(4)
#define TS_OPT_ECN BIT(5)
/* There is no TS_OPT_TIMESTAMP:
* if ACK contains timestamp option, we already know it was
* requested/supported by the syn/synack exchange.
*/
#define TSBITS 6
#define TSMASK (((__u32)1 << TSBITS) - 1)
static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
u32 count, int c)
{
net_get_random_once(syncookie_secret, sizeof(syncookie_secret));
return siphash_4u32((__force u32)saddr, (__force u32)daddr,
(__force u32)sport << 16 | (__force u32)dport,
count, &syncookie_secret[c]);
}
/*
* when syncookies are in effect and tcp timestamps are enabled we encode
* tcp options in the lower bits of the timestamp value that will be
* sent in the syn-ack.
* Since subsequent timestamps use the normal tcp_time_stamp value, we
* must make sure that the resulting initial timestamp is <= tcp_time_stamp.
*/
u64 cookie_init_timestamp(struct request_sock *req)
{
struct inet_request_sock *ireq;
u32 ts, ts_now = tcp_time_stamp_raw();
u32 options = 0;
ireq = inet_rsk(req);
options = ireq->wscale_ok ? ireq->snd_wscale : TS_OPT_WSCALE_MASK;
if (ireq->sack_ok)
options |= TS_OPT_SACK;
if (ireq->ecn_ok)
options |= TS_OPT_ECN;
ts = ts_now & ~TSMASK;
ts |= options;
if (ts > ts_now) {
ts >>= TSBITS;
ts--;
ts <<= TSBITS;
ts |= options;
}
return (u64)ts * (USEC_PER_SEC / TCP_TS_HZ);
}
static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
__be16 dport, __u32 sseq, __u32 data)
{
/*
* Compute the secure sequence number.
* The output should be:
* HASH(sec1,saddr,sport,daddr,dport,sec1) + sseq + (count * 2^24)
* + (HASH(sec2,saddr,sport,daddr,dport,count,sec2) % 2^24).
* Where sseq is their sequence number and count increases every
* minute by 1.
* As an extra hack, we add a small "data" value that encodes the
* MSS into the second hash value.
*/
u32 count = tcp_cookie_time();
return (cookie_hash(saddr, daddr, sport, dport, 0, 0) +
sseq + (count << COOKIEBITS) +
((cookie_hash(saddr, daddr, sport, dport, count, 1) + data)
& COOKIEMASK));
}
/*
* This retrieves the small "data" value from the syncookie.
* If the syncookie is bad, the data returned will be out of
* range. This must be checked by the caller.
*
* The count value used to generate the cookie must be less than
* MAX_SYNCOOKIE_AGE minutes in the past.
* The return value (__u32)-1 if this test fails.
*/
static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr,
__be16 sport, __be16 dport, __u32 sseq)
{
u32 diff, count = tcp_cookie_time();
/* Strip away the layers from the cookie */
cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
/* Cookie is now reduced to (count * 2^24) ^ (hash % 2^24) */
diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS);
if (diff >= MAX_SYNCOOKIE_AGE)
return (__u32)-1;
return (cookie -
cookie_hash(saddr, daddr, sport, dport, count - diff, 1))
& COOKIEMASK; /* Leaving the data behind */
}
/*
* MSS Values are chosen based on the 2011 paper
* 'An Analysis of TCP Maximum Segement Sizes' by S. Alcock and R. Nelson.
* Values ..
* .. lower than 536 are rare (< 0.2%)
* .. between 537 and 1299 account for less than < 1.5% of observed values
* .. in the 1300-1349 range account for about 15 to 20% of observed mss values
* .. exceeding 1460 are very rare (< 0.04%)
*
* 1460 is the single most frequently announced mss value (30 to 46% depending
* on monitor location). Table must be sorted.
*/
static __u16 const msstab[] = {
536,
1300,
1440, /* 1440, 1452: PPPoE */
1460,
};
/*
* Generate a syncookie. mssp points to the mss, which is returned
* rounded down to the value encoded in the cookie.
*/
u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
u16 *mssp)
{
int mssind;
const __u16 mss = *mssp;
for (mssind = ARRAY_SIZE(msstab) - 1; mssind ; mssind--)
if (mss >= msstab[mssind])
break;
*mssp = msstab[mssind];
return secure_tcp_syn_cookie(iph->saddr, iph->daddr,
th->source, th->dest, ntohl(th->seq),
mssind);
}
EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence);
__u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mssp)
{
const struct iphdr *iph = ip_hdr(skb);
const struct tcphdr *th = tcp_hdr(skb);
return __cookie_v4_init_sequence(iph, th, mssp);
}
/*
* Check if a ack sequence number is a valid syncookie.
* Return the decoded mss if it is, or 0 if not.
*/
int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
u32 cookie)
{
__u32 seq = ntohl(th->seq) - 1;
__u32 mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr,
th->source, th->dest, seq);
return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
}
EXPORT_SYMBOL_GPL(__cookie_v4_check);
struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst, u32 tsoff)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct sock *child;
bool own_req;
child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
NULL, &own_req);
if (child) {
refcount_set(&req->rsk_refcnt, 1);
tcp_sk(child)->tsoffset = tsoff;
sock_rps_save_rxhash(child, skb);
inet_csk_reqsk_queue_add(sk, req, child);
} else {
reqsk_free(req);
}
return child;
}
EXPORT_SYMBOL(tcp_get_cookie_sock);
/*
* when syncookies are in effect and tcp timestamps are enabled we stored
* additional tcp options in the timestamp.
* This extracts these options from the timestamp echo.
*
* return false if we decode a tcp option that is disabled
* on the host.
*/
bool cookie_timestamp_decode(const struct net *net,
struct tcp_options_received *tcp_opt)
{
/* echoed timestamp, lowest bits contain options */
u32 options = tcp_opt->rcv_tsecr;
if (!tcp_opt->saw_tstamp) {
tcp_clear_options(tcp_opt);
return true;
}
if (!net->ipv4.sysctl_tcp_timestamps)
return false;
tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0;
if (tcp_opt->sack_ok && !net->ipv4.sysctl_tcp_sack)
return false;
if ((options & TS_OPT_WSCALE_MASK) == TS_OPT_WSCALE_MASK)
return true; /* no window scaling */
tcp_opt->wscale_ok = 1;
tcp_opt->snd_wscale = options & TS_OPT_WSCALE_MASK;
return net->ipv4.sysctl_tcp_window_scaling != 0;
}
EXPORT_SYMBOL(cookie_timestamp_decode);
bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt,
const struct net *net, const struct dst_entry *dst)
{
bool ecn_ok = tcp_opt->rcv_tsecr & TS_OPT_ECN;
if (!ecn_ok)
return false;
if (net->ipv4.sysctl_tcp_ecn)
return true;
return dst_feature(dst, RTAX_FEATURE_ECN);
}
EXPORT_SYMBOL(cookie_ecn_ok);
/* On input, sk is a listener.
* Output is listener if incoming packet would not create a child
* NULL if memory could not be allocated.
*/
struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
{
struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
struct tcp_options_received tcp_opt;
struct inet_request_sock *ireq;
struct tcp_request_sock *treq;
struct tcp_sock *tp = tcp_sk(sk);
const struct tcphdr *th = tcp_hdr(skb);
__u32 cookie = ntohl(th->ack_seq) - 1;
struct sock *ret = sk;
struct request_sock *req;
int mss;
struct rtable *rt;
__u8 rcv_wscale;
struct flowi4 fl4;
u32 tsoff = 0;
if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
goto out;
if (tcp_synq_no_recent_overflow(sk))
goto out;
mss = __cookie_v4_check(ip_hdr(skb), th, cookie);
if (mss == 0) {
__NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESFAILED);
goto out;
}
__NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV);
/* check for timestamp cookie support */
memset(&tcp_opt, 0, sizeof(tcp_opt));
tcp_parse_options(sock_net(sk), skb, &tcp_opt, 0, NULL);
if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) {
tsoff = secure_tcp_ts_off(sock_net(sk),
ip_hdr(skb)->daddr,
ip_hdr(skb)->saddr);
tcp_opt.rcv_tsecr -= tsoff;
}
if (!cookie_timestamp_decode(sock_net(sk), &tcp_opt))
goto out;
ret = NULL;
req = inet_reqsk_alloc(&tcp_request_sock_ops, sk, false); /* for safety */
if (!req)
goto out;
ireq = inet_rsk(req);
treq = tcp_rsk(req);
treq->rcv_isn = ntohl(th->seq) - 1;
treq->snt_isn = cookie;
treq->ts_off = 0;
treq->txhash = net_tx_rndhash();
req->mss = mss;
ireq->ir_num = ntohs(th->dest);
ireq->ir_rmt_port = th->source;
sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
ireq->ir_mark = inet_request_mark(sk, skb);
ireq->snd_wscale = tcp_opt.snd_wscale;
ireq->sack_ok = tcp_opt.sack_ok;
ireq->wscale_ok = tcp_opt.wscale_ok;
ireq->tstamp_ok = tcp_opt.saw_tstamp;
req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
treq->snt_synack = 0;
treq->tfo_listener = false;
ireq->ir_iif = inet_request_bound_dev_if(sk, skb);
/* We throwed the options of the initial SYN away, so we hope
* the ACK carries the same options again (see RFC1122 4.2.3.8)
*/
RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(sock_net(sk), skb));
if (security_inet_conn_request(sk, skb, req)) {
reqsk_free(req);
goto out;
}
req->num_retrans = 0;
/*
* We need to lookup the route here to get at the correct
* window size. We should better make sure that the window size
* hasn't changed since we received the original syn, but I see
* no easy way to do this.
*/
flowi4_init_output(&fl4, ireq->ir_iif, ireq->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
inet_sk_flowi_flags(sk),
opt->srr ? opt->faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(&fl4));
rt = ip_route_output_key(sock_net(sk), &fl4);
if (IS_ERR(rt)) {
reqsk_free(req);
goto out;
}
/* Try to redo what tcp_v4_send_synack did. */
req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
tcp_select_initial_window(tcp_full_space(sk), req->mss,
&req->rsk_rcv_wnd, &req->rsk_window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(&rt->dst, RTAX_INITRWND));
ireq->rcv_wscale = rcv_wscale;
ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), &rt->dst);
ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst, tsoff);
/* ip_queue_xmit() depends on our flow being setup
* Normal sockets get it right from inet_csk_route_child_sock()
*/
if (ret)
inet_sk(ret)->cork.fl.u.ip4 = fl4;
out: return ret;
}