mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 19:00:25 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
-----BEGIN PGP SIGNATURE----- iQJIBAABCAAyFiEES0KozwfymdVUl37v6iDy2pc3iXMFAl/YBtEUHHBhdWxAcGF1 bC1tb29yZS5jb20ACgkQ6iDy2pc3iXNnwA/9Ek8DG/1t8CEoJxpoRvwovQxNo+bi 0rCT9vqvx9PeCwoZi/0Vp6oKmpE1HADvbeB/+e00VrbLYnzE3oRY6VkpjoZRofKS vc0/MzHSFxFUR1OTHwCefcXlPLK+bfitQbX5jEMeVyQCXNXXIrN7CnJf1LmCeLTR kQBPlEN9lt7HyNVAi34FhOD/TQbWnFHgl2z5puffgri6cWnc+TALKMYytUZ+rYex NYndDJW5b3g5kTat2eErn0FruxfzloGs0xMIiWb+z2i9kl41D+dkKPdAN7idqCSC Jv0nJP/bDftzA0wOe9szmGaLQzu7YnCN5kiWcSspatZVnon42Cy/tp9tiuPGLRFU XtelDfpyX6o3CLN0tX7LQEO+GYxPzvM6iaR2OrsChWPozUIIR3TLQg7jJN4bvNKl TR6gCGZCoAeS5JLNGjzVKxT/oKQY+tCLLlYXQdQY6swNFi3EKmPr+K1D9lgm98fO f3d1QmWiZZNmtxxoVogT0qoQYjkfgpnm3dVx813Vt+lwHlVpHGMEPpO27iD3/RYb w2yWOJaGKwMD8iL0l+Cm6CPW0/nE5FFISQjWgC8b4Vgxlyan6+L9eViqGICkrUQ2 Edo0i1YFFZ4utHYkDf1VYBbJ+36KyCtdktgLAcbgnePiPB3E1XBsXTIIStSUIbVQ iEbTkBlsCG4GIeU= =6Cqb -----END PGP SIGNATURE----- Merge tag 'selinux-pr-20201214' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux Pull selinux updates from Paul Moore: "While we have a small number of SELinux patches for v5.11, there are a few changes worth highlighting: - Change the LSM network hooks to pass flowi_common structs instead of the parent flowi struct as the LSMs do not currently need the full flowi struct and they do not have enough information to use it safely (missing information on the address family). This patch was discussed both with Herbert Xu (representing team netdev) and James Morris (representing team LSMs-other-than-SELinux). - Fix how we handle errors in inode_doinit_with_dentry() so that we attempt to properly label the inode on following lookups instead of continuing to treat it as unlabeled. - Tweak the kernel logic around allowx, auditallowx, and dontauditx SELinux policy statements such that the auditx/dontauditx are effective even without the allowx statement. Everything passes our test suite" * tag 'selinux-pr-20201214' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux: lsm,selinux: pass flowi_common instead of flowi to the LSM hooks selinux: Fix fall-through warnings for Clang selinux: drop super_block backpointer from superblock_security_struct selinux: fix inode_doinit_with_dentry() LABEL_INVALID error handling selinux: allow dontauditx and auditallowx rules to take effect without allowx selinux: fix error initialization in inode_doinit_with_dentry()
451 lines
13 KiB
C
451 lines
13 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/*
|
|
* Syncookies implementation for the Linux kernel
|
|
*
|
|
* Copyright (C) 1997 Andi Kleen
|
|
* Based on ideas by D.J.Bernstein and Eric Schenk.
|
|
*/
|
|
|
|
#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, u64 now)
|
|
{
|
|
struct inet_request_sock *ireq;
|
|
u32 ts, ts_now = tcp_ns_to_ts(now);
|
|
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 * (NSEC_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);
|
|
|
|
if (rsk_drop_req(req)) {
|
|
reqsk_put(req);
|
|
return child;
|
|
}
|
|
|
|
if (inet_csk_reqsk_queue_add(sk, req, child))
|
|
return child;
|
|
|
|
bh_unlock_sock(child);
|
|
sock_put(child);
|
|
}
|
|
__reqsk_free(req);
|
|
|
|
return NULL;
|
|
}
|
|
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);
|
|
|
|
struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
|
|
struct sock *sk,
|
|
struct sk_buff *skb)
|
|
{
|
|
struct tcp_request_sock *treq;
|
|
struct request_sock *req;
|
|
|
|
#ifdef CONFIG_MPTCP
|
|
if (sk_is_mptcp(sk))
|
|
ops = &mptcp_subflow_request_sock_ops;
|
|
#endif
|
|
|
|
req = inet_reqsk_alloc(ops, sk, false);
|
|
if (!req)
|
|
return NULL;
|
|
|
|
treq = tcp_rsk(req);
|
|
treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;
|
|
#if IS_ENABLED(CONFIG_MPTCP)
|
|
treq->is_mptcp = sk_is_mptcp(sk);
|
|
if (treq->is_mptcp) {
|
|
int err = mptcp_subflow_init_cookie_req(req, sk, skb);
|
|
|
|
if (err) {
|
|
reqsk_free(req);
|
|
return NULL;
|
|
}
|
|
}
|
|
#endif
|
|
|
|
return req;
|
|
}
|
|
EXPORT_SYMBOL_GPL(cookie_tcp_reqsk_alloc);
|
|
|
|
/* 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 full_space, 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 = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb);
|
|
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;
|
|
|
|
if (IS_ENABLED(CONFIG_SMC))
|
|
ireq->smc_ok = 0;
|
|
|
|
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_common(&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);
|
|
/* limit the window selection if the user enforce a smaller rx buffer */
|
|
full_space = tcp_full_space(sk);
|
|
if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
|
|
(req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
|
|
req->rsk_window_clamp = full_space;
|
|
|
|
tcp_select_initial_window(sk, full_space, 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;
|
|
}
|