linux/net/ipv6/syncookies.c

267 lines
7.4 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* IPv6 Syncookies implementation for the Linux kernel
*
* Authors:
* Glenn Griffin <ggriffin.kernel@gmail.com>
*
* Based on IPv4 implementation by Andi Kleen
* linux/net/ipv4/syncookies.c
*/
#include <linux/tcp.h>
#include <linux/random.h>
#include <linux/siphash.h>
#include <linux/kernel.h>
#include <net/secure_seq.h>
#include <net/ipv6.h>
#include <net/tcp.h>
#define COOKIEBITS 24 /* Upper bits store count */
#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
static siphash_aligned_key_t syncookie6_secret[2];
/* RFC 2460, Section 8.3:
* [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..]
*
* Due to IPV6_MIN_MTU=1280 the lowest possible MSS is 1220, which allows
* using higher values than ipv4 tcp syncookies.
* The other values are chosen based on ethernet (1500 and 9k MTU), plus
* one that accounts for common encap (PPPoe) overhead. Table must be sorted.
*/
static __u16 const msstab[] = {
1280 - 60, /* IPV6_MIN_MTU - 60 */
1480 - 60,
1500 - 60,
9000 - 60,
};
static u32 cookie_hash(const struct in6_addr *saddr,
const struct in6_addr *daddr,
__be16 sport, __be16 dport, u32 count, int c)
{
const struct {
struct in6_addr saddr;
struct in6_addr daddr;
u32 count;
__be16 sport;
__be16 dport;
} __aligned(SIPHASH_ALIGNMENT) combined = {
.saddr = *saddr,
.daddr = *daddr,
.count = count,
.sport = sport,
.dport = dport
};
net_get_random_once(syncookie6_secret, sizeof(syncookie6_secret));
return siphash(&combined, offsetofend(typeof(combined), dport),
&syncookie6_secret[c]);
}
static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
const struct in6_addr *daddr,
__be16 sport, __be16 dport, __u32 sseq,
__u32 data)
{
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));
}
static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr,
const struct in6_addr *daddr, __be16 sport,
__be16 dport, __u32 sseq)
{
__u32 diff, count = tcp_cookie_time();
cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
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;
}
u32 __cookie_v6_init_sequence(const struct ipv6hdr *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_v6_init_sequence);
__u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mssp)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
const struct tcphdr *th = tcp_hdr(skb);
return __cookie_v6_init_sequence(iph, th, mssp);
}
int __cookie_v6_check(const struct ipv6hdr *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_v6_check);
struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
{
struct tcp_options_received tcp_opt;
struct inet_request_sock *ireq;
struct tcp_request_sock *treq;
struct ipv6_pinfo *np = inet6_sk(sk);
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 dst_entry *dst;
__u8 rcv_wscale;
u32 tsoff = 0;
if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) ||
!th->ack || th->rst)
goto out;
if (tcp_synq_no_recent_overflow(sk))
goto out;
mss = __cookie_v6_check(ipv6_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_tcpv6_ts_off(sock_net(sk),
ipv6_hdr(skb)->daddr.s6_addr32,
ipv6_hdr(skb)->saddr.s6_addr32);
tcp_opt.rcv_tsecr -= tsoff;
}
if (!cookie_timestamp_decode(sock_net(sk), &tcp_opt))
goto out;
ret = NULL;
tcp: make sure treq->af_specific is initialized syzbot complained about a recent change in TCP stack, hitting a NULL pointer [1] tcp request sockets have an af_specific pointer, which was used before the blamed change only for SYNACK generation in non SYNCOOKIE mode. tcp requests sockets momentarily created when third packet coming from client in SYNCOOKIE mode were not using treq->af_specific. Make sure this field is populated, in the same way normal TCP requests sockets do in tcp_conn_request(). [1] TCP: request_sock_TCPv6: Possible SYN flooding on port 20002. Sending cookies. Check SNMP counters. general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] CPU: 1 PID: 3695 Comm: syz-executor864 Not tainted 5.18.0-rc3-syzkaller-00224-g5fd1fe4807f9 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:tcp_create_openreq_child+0xe16/0x16b0 net/ipv4/tcp_minisocks.c:534 Code: 48 c1 ea 03 80 3c 02 00 0f 85 e5 07 00 00 4c 8b b3 28 01 00 00 48 b8 00 00 00 00 00 fc ff df 49 8d 7e 08 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 c9 07 00 00 48 8b 3c 24 48 89 de 41 ff 56 08 48 RSP: 0018:ffffc90000de0588 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffff888076490330 RCX: 0000000000000100 RDX: 0000000000000001 RSI: ffffffff87d67ff0 RDI: 0000000000000008 RBP: ffff88806ee1c7f8 R08: 0000000000000000 R09: 0000000000000000 R10: ffffffff87d67f00 R11: 0000000000000000 R12: ffff88806ee1bfc0 R13: ffff88801b0e0368 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f517fe58700(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffcead76960 CR3: 000000006f97b000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <IRQ> tcp_v6_syn_recv_sock+0x199/0x23b0 net/ipv6/tcp_ipv6.c:1267 tcp_get_cookie_sock+0xc9/0x850 net/ipv4/syncookies.c:207 cookie_v6_check+0x15c3/0x2340 net/ipv6/syncookies.c:258 tcp_v6_cookie_check net/ipv6/tcp_ipv6.c:1131 [inline] tcp_v6_do_rcv+0x1148/0x13b0 net/ipv6/tcp_ipv6.c:1486 tcp_v6_rcv+0x3305/0x3840 net/ipv6/tcp_ipv6.c:1725 ip6_protocol_deliver_rcu+0x2e9/0x1900 net/ipv6/ip6_input.c:422 ip6_input_finish+0x14c/0x2c0 net/ipv6/ip6_input.c:464 NF_HOOK include/linux/netfilter.h:307 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] ip6_input+0x9c/0xd0 net/ipv6/ip6_input.c:473 dst_input include/net/dst.h:461 [inline] ip6_rcv_finish net/ipv6/ip6_input.c:76 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] ipv6_rcv+0x27f/0x3b0 net/ipv6/ip6_input.c:297 __netif_receive_skb_one_core+0x114/0x180 net/core/dev.c:5405 __netif_receive_skb+0x24/0x1b0 net/core/dev.c:5519 process_backlog+0x3a0/0x7c0 net/core/dev.c:5847 __napi_poll+0xb3/0x6e0 net/core/dev.c:6413 napi_poll net/core/dev.c:6480 [inline] net_rx_action+0x8ec/0xc60 net/core/dev.c:6567 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 invoke_softirq kernel/softirq.c:432 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:637 irq_exit_rcu+0x5/0x20 kernel/softirq.c:649 sysvec_apic_timer_interrupt+0x93/0xc0 arch/x86/kernel/apic/apic.c:1097 Fixes: 5b0b9e4c2c89 ("tcp: md5: incorrect tcp_header_len for incoming connections") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Francesco Ruggeri <fruggeri@arista.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-04-24 20:35:09 +00:00
req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops,
&tcp_request_sock_ipv6_ops, sk, skb);
if (!req)
goto out;
ireq = inet_rsk(req);
treq = tcp_rsk(req);
treq->tfo_listener = false;
if (security_inet_conn_request(sk, skb, req))
goto out_free;
req->mss = mss;
ireq->ir_rmt_port = th->source;
ireq->ir_num = ntohs(th->dest);
ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
refcount_inc(&skb->users);
ireq->pktopts = skb;
}
ireq->ir_iif = inet_request_bound_dev_if(sk, skb);
/* So that link locals have meaning */
if (!sk->sk_bound_dev_if &&
ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
ireq->ir_iif = tcp_v6_iif(skb);
ireq->ir_mark = inet_request_mark(sk, skb);
tcp: better retrans tracking for defer-accept For passive TCP connections using TCP_DEFER_ACCEPT facility, we incorrectly increment req->retrans each time timeout triggers while no SYNACK is sent. SYNACK are not sent for TCP_DEFER_ACCEPT that were established (for which we received the ACK from client). Only the last SYNACK is sent so that we can receive again an ACK from client, to move the req into accept queue. We plan to change this later to avoid the useless retransmit (and potential problem as this SYNACK could be lost) TCP_INFO later gives wrong information to user, claiming imaginary retransmits. Decouple req->retrans field into two independent fields : num_retrans : number of retransmit num_timeout : number of timeouts num_timeout is the counter that is incremented at each timeout, regardless of actual SYNACK being sent or not, and used to compute the exponential timeout. Introduce inet_rtx_syn_ack() helper to increment num_retrans only if ->rtx_syn_ack() succeeded. Use inet_rtx_syn_ack() from tcp_check_req() to increment num_retrans when we re-send a SYNACK in answer to a (retransmitted) SYN. Prior to this patch, we were not counting these retransmits. Change tcp_v[46]_rtx_synack() to increment TCP_MIB_RETRANSSEGS only if a synack packet was successfully queued. Reported-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Julian Anastasov <ja@ssi.bg> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Elliott Hughes <enh@google.com> Cc: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-27 23:16:46 +00:00
req->num_retrans = 0;
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->rcv_isn = ntohl(th->seq) - 1;
treq->snt_isn = cookie;
treq->ts_off = 0;
ipv4: ipv6: initialize treq->txhash in cookie_v[46]_check() KMSAN reported use of uninitialized memory in skb_set_hash_from_sk(), which originated from the TCP request socket created in cookie_v6_check(): ================================================================== BUG: KMSAN: use of uninitialized memory in tcp_transmit_skb+0xf77/0x3ec0 CPU: 1 PID: 2949 Comm: syz-execprog Not tainted 4.11.0-rc5+ #2931 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 TCP: request_sock_TCPv6: Possible SYN flooding on port 20028. Sending cookies. Check SNMP counters. Call Trace: <IRQ> __dump_stack lib/dump_stack.c:16 dump_stack+0x172/0x1c0 lib/dump_stack.c:52 kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:927 __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:469 skb_set_hash_from_sk ./include/net/sock.h:2011 tcp_transmit_skb+0xf77/0x3ec0 net/ipv4/tcp_output.c:983 tcp_send_ack+0x75b/0x830 net/ipv4/tcp_output.c:3493 tcp_delack_timer_handler+0x9a6/0xb90 net/ipv4/tcp_timer.c:284 tcp_delack_timer+0x1b0/0x310 net/ipv4/tcp_timer.c:309 call_timer_fn+0x240/0x520 kernel/time/timer.c:1268 expire_timers kernel/time/timer.c:1307 __run_timers+0xc13/0xf10 kernel/time/timer.c:1601 run_timer_softirq+0x36/0xa0 kernel/time/timer.c:1614 __do_softirq+0x485/0x942 kernel/softirq.c:284 invoke_softirq kernel/softirq.c:364 irq_exit+0x1fa/0x230 kernel/softirq.c:405 exiting_irq+0xe/0x10 ./arch/x86/include/asm/apic.h:657 smp_apic_timer_interrupt+0x5a/0x80 arch/x86/kernel/apic/apic.c:966 apic_timer_interrupt+0x86/0x90 arch/x86/entry/entry_64.S:489 RIP: 0010:native_restore_fl ./arch/x86/include/asm/irqflags.h:36 RIP: 0010:arch_local_irq_restore ./arch/x86/include/asm/irqflags.h:77 RIP: 0010:__msan_poison_alloca+0xed/0x120 mm/kmsan/kmsan_instr.c:440 RSP: 0018:ffff880024917cd8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff10 RAX: 0000000000000246 RBX: ffff8800224c0000 RCX: 0000000000000005 RDX: 0000000000000004 RSI: ffff880000000000 RDI: ffffea0000b6d770 RBP: ffff880024917d58 R08: 0000000000000dd8 R09: 0000000000000004 R10: 0000160000000000 R11: 0000000000000000 R12: ffffffff85abf810 R13: ffff880024917dd8 R14: 0000000000000010 R15: ffffffff81cabde4 </IRQ> poll_select_copy_remaining+0xac/0x6b0 fs/select.c:293 SYSC_select+0x4b4/0x4e0 fs/select.c:653 SyS_select+0x76/0xa0 fs/select.c:634 entry_SYSCALL_64_fastpath+0x13/0x94 arch/x86/entry/entry_64.S:204 RIP: 0033:0x4597e7 RSP: 002b:000000c420037ee0 EFLAGS: 00000246 ORIG_RAX: 0000000000000017 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00000000004597e7 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 000000c420037ef0 R08: 000000c420037ee0 R09: 0000000000000059 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000042dc20 R13: 00000000000000f3 R14: 0000000000000030 R15: 0000000000000003 chained origin: save_stack_trace+0x37/0x40 arch/x86/kernel/stacktrace.c:59 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:302 kmsan_save_stack mm/kmsan/kmsan.c:317 kmsan_internal_chain_origin+0x12a/0x1f0 mm/kmsan/kmsan.c:547 __msan_store_shadow_origin_4+0xac/0x110 mm/kmsan/kmsan_instr.c:259 tcp_create_openreq_child+0x709/0x1ae0 net/ipv4/tcp_minisocks.c:472 tcp_v6_syn_recv_sock+0x7eb/0x2a30 net/ipv6/tcp_ipv6.c:1103 tcp_get_cookie_sock+0x136/0x5f0 net/ipv4/syncookies.c:212 cookie_v6_check+0x17a9/0x1b50 net/ipv6/syncookies.c:245 tcp_v6_cookie_check net/ipv6/tcp_ipv6.c:989 tcp_v6_do_rcv+0xdd8/0x1c60 net/ipv6/tcp_ipv6.c:1298 tcp_v6_rcv+0x41a3/0x4f00 net/ipv6/tcp_ipv6.c:1487 ip6_input_finish+0x82f/0x1ee0 net/ipv6/ip6_input.c:279 NF_HOOK ./include/linux/netfilter.h:257 ip6_input+0x239/0x290 net/ipv6/ip6_input.c:322 dst_input ./include/net/dst.h:492 ip6_rcv_finish net/ipv6/ip6_input.c:69 NF_HOOK ./include/linux/netfilter.h:257 ipv6_rcv+0x1dbd/0x22e0 net/ipv6/ip6_input.c:203 __netif_receive_skb_core+0x2f6f/0x3a20 net/core/dev.c:4208 __netif_receive_skb net/core/dev.c:4246 process_backlog+0x667/0xba0 net/core/dev.c:4866 napi_poll net/core/dev.c:5268 net_rx_action+0xc95/0x1590 net/core/dev.c:5333 __do_softirq+0x485/0x942 kernel/softirq.c:284 origin: save_stack_trace+0x37/0x40 arch/x86/kernel/stacktrace.c:59 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:302 kmsan_internal_poison_shadow+0xb1/0x1a0 mm/kmsan/kmsan.c:198 kmsan_kmalloc+0x7f/0xe0 mm/kmsan/kmsan.c:337 kmem_cache_alloc+0x1c2/0x1e0 mm/slub.c:2766 reqsk_alloc ./include/net/request_sock.h:87 inet_reqsk_alloc+0xa4/0x5b0 net/ipv4/tcp_input.c:6200 cookie_v6_check+0x4f4/0x1b50 net/ipv6/syncookies.c:169 tcp_v6_cookie_check net/ipv6/tcp_ipv6.c:989 tcp_v6_do_rcv+0xdd8/0x1c60 net/ipv6/tcp_ipv6.c:1298 tcp_v6_rcv+0x41a3/0x4f00 net/ipv6/tcp_ipv6.c:1487 ip6_input_finish+0x82f/0x1ee0 net/ipv6/ip6_input.c:279 NF_HOOK ./include/linux/netfilter.h:257 ip6_input+0x239/0x290 net/ipv6/ip6_input.c:322 dst_input ./include/net/dst.h:492 ip6_rcv_finish net/ipv6/ip6_input.c:69 NF_HOOK ./include/linux/netfilter.h:257 ipv6_rcv+0x1dbd/0x22e0 net/ipv6/ip6_input.c:203 __netif_receive_skb_core+0x2f6f/0x3a20 net/core/dev.c:4208 __netif_receive_skb net/core/dev.c:4246 process_backlog+0x667/0xba0 net/core/dev.c:4866 napi_poll net/core/dev.c:5268 net_rx_action+0xc95/0x1590 net/core/dev.c:5333 __do_softirq+0x485/0x942 kernel/softirq.c:284 ================================================================== Similar error is reported for cookie_v4_check(). Fixes: 58d607d3e52f ("tcp: provide skb->hash to synack packets") Signed-off-by: Alexander Potapenko <glider@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-17 10:35:58 +00:00
treq->txhash = net_tx_rndhash();
if (IS_ENABLED(CONFIG_SMC))
ireq->smc_ok = 0;
/*
* We need to lookup the dst_entry to get the correct window size.
* This is taken from tcp_v6_syn_recv_sock. Somebody please enlighten
* me if there is a preferred way.
*/
{
struct in6_addr *final_p, final;
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
fl6.daddr = ireq->ir_v6_rmt_addr;
final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
fl6.saddr = ireq->ir_v6_loc_addr;
fl6.flowi6_oif = ireq->ir_iif;
fl6.flowi6_mark = ireq->ir_mark;
fl6.fl6_dport = ireq->ir_rmt_port;
fl6.fl6_sport = inet_sk(sk)->inet_sport;
fl6.flowi6_uid = sk->sk_uid;
security_req_classify_flow(req, flowi6_to_flowi_common(&fl6));
dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
if (IS_ERR(dst))
goto out_free;
}
req->rsk_window_clamp = tp->window_clamp ? :dst_metric(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(dst, RTAX_INITRWND));
ireq->rcv_wscale = rcv_wscale;
net: allow setting ecn via routing table This patch allows to set ECN on a per-route basis in case the sysctl tcp_ecn is not set to 1. In other words, when ECN is set for specific routes, it provides a tcp_ecn=1 behaviour for that route while the rest of the stack acts according to the global settings. One can use 'ip route change dev $dev $net features ecn' to toggle this. Having a more fine-grained per-route setting can be beneficial for various reasons, for example, 1) within data centers, or 2) local ISPs may deploy ECN support for their own video/streaming services [1], etc. There was a recent measurement study/paper [2] which scanned the Alexa's publicly available top million websites list from a vantage point in US, Europe and Asia: Half of the Alexa list will now happily use ECN (tcp_ecn=2, most likely blamed to commit 255cac91c3 ("tcp: extend ECN sysctl to allow server-side only ECN") ;)); the break in connectivity on-path was found is about 1 in 10,000 cases. Timeouts rather than receiving back RSTs were much more common in the negotiation phase (and mostly seen in the Alexa middle band, ranks around 50k-150k): from 12-thousand hosts on which there _may_ be ECN-linked connection failures, only 79 failed with RST when _not_ failing with RST when ECN is not requested. It's unclear though, how much equipment in the wild actually marks CE when buffers start to fill up. We thought about a fallback to non-ECN for retransmitted SYNs as another global option (which could perhaps one day be made default), but as Eric points out, there's much more work needed to detect broken middleboxes. Two examples Eric mentioned are buggy firewalls that accept only a single SYN per flow, and middleboxes that successfully let an ECN flow establish, but later mark CE for all packets (so cwnd converges to 1). [1] http://www.ietf.org/proceedings/89/slides/slides-89-tsvarea-1.pdf, p.15 [2] http://ecn.ethz.ch/ Joint work with Daniel Borkmann. Reference: http://thread.gmane.org/gmane.linux.network/335797 Suggested-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-03 16:35:03 +00:00
ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), dst);
ret = tcp_get_cookie_sock(sk, skb, req, dst, tsoff);
out:
return ret;
out_free:
reqsk_free(req);
return NULL;
}