2020-07-30 22:25:56 +03:00
// SPDX-License-Identifier: GPL-2.0
# include <linux/skbuff.h>
# include "protocol.h"
/* Syncookies do not work for JOIN requests.
*
* Unlike MP_CAPABLE , where the ACK cookie contains the needed MPTCP
* options to reconstruct the initial syn state , MP_JOIN does not contain
* the token to obtain the mptcp socket nor the server - generated nonce
* that was used in the cookie SYN / ACK response .
*
* Keep a small best effort state table to store the syn / synack data ,
* indexed by skb hash .
*
* A MP_JOIN SYN packet handled by syn cookies is only stored if the 32 bit
* token matches a known mptcp connection that can still accept more subflows .
*
* There is no timeout handling - - state is only re - constructed
* when the TCP ACK passed the cookie validation check .
*/
struct join_entry {
u32 token ;
u32 remote_nonce ;
u32 local_nonce ;
u8 join_id ;
u8 local_id ;
u8 backup ;
u8 valid ;
} ;
# define COOKIE_JOIN_SLOTS 1024
static struct join_entry join_entries [ COOKIE_JOIN_SLOTS ] __cacheline_aligned_in_smp ;
static spinlock_t join_entry_locks [ COOKIE_JOIN_SLOTS ] __cacheline_aligned_in_smp ;
static u32 mptcp_join_entry_hash ( struct sk_buff * skb , struct net * net )
{
mptcp: fix warning in __skb_flow_dissect() when do syn cookie for subflow join
I did stress test with wrk[1] and webfsd[2] with the assistance of
mptcp-tools[3]:
Server side:
./use_mptcp.sh webfsd -4 -R /tmp/ -p 8099
Client side:
./use_mptcp.sh wrk -c 200 -d 30 -t 4 http://192.168.174.129:8099/
and got the following warning message:
[ 55.552626] TCP: request_sock_subflow: Possible SYN flooding on port 8099. Sending cookies. Check SNMP counters.
[ 55.553024] ------------[ cut here ]------------
[ 55.553027] WARNING: CPU: 0 PID: 10 at net/core/flow_dissector.c:984 __skb_flow_dissect+0x280/0x1650
...
[ 55.553117] CPU: 0 PID: 10 Comm: ksoftirqd/0 Not tainted 5.12.0+ #18
[ 55.553121] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 02/27/2020
[ 55.553124] RIP: 0010:__skb_flow_dissect+0x280/0x1650
...
[ 55.553133] RSP: 0018:ffffb79580087770 EFLAGS: 00010246
[ 55.553137] RAX: 0000000000000000 RBX: ffffffff8ddb58e0 RCX: ffffb79580087888
[ 55.553139] RDX: ffffffff8ddb58e0 RSI: ffff8f7e4652b600 RDI: 0000000000000000
[ 55.553141] RBP: ffffb79580087858 R08: 0000000000000000 R09: 0000000000000008
[ 55.553143] R10: 000000008c622965 R11: 00000000d3313a5b R12: ffff8f7e4652b600
[ 55.553146] R13: ffff8f7e465c9062 R14: 0000000000000000 R15: ffffb79580087888
[ 55.553149] FS: 0000000000000000(0000) GS:ffff8f7f75e00000(0000) knlGS:0000000000000000
[ 55.553152] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 55.553154] CR2: 00007f73d1d19000 CR3: 0000000135e10004 CR4: 00000000003706f0
[ 55.553160] Call Trace:
[ 55.553166] ? __sha256_final+0x67/0xd0
[ 55.553173] ? sha256+0x7e/0xa0
[ 55.553177] __skb_get_hash+0x57/0x210
[ 55.553182] subflow_init_req_cookie_join_save+0xac/0xc0
[ 55.553189] subflow_check_req+0x474/0x550
[ 55.553195] ? ip_route_output_key_hash+0x67/0x90
[ 55.553200] ? xfrm_lookup_route+0x1d/0xa0
[ 55.553207] subflow_v4_route_req+0x8e/0xd0
[ 55.553212] tcp_conn_request+0x31e/0xab0
[ 55.553218] ? selinux_socket_sock_rcv_skb+0x116/0x210
[ 55.553224] ? tcp_rcv_state_process+0x179/0x6d0
[ 55.553229] tcp_rcv_state_process+0x179/0x6d0
[ 55.553235] tcp_v4_do_rcv+0xaf/0x220
[ 55.553239] tcp_v4_rcv+0xce4/0xd80
[ 55.553243] ? ip_route_input_rcu+0x246/0x260
[ 55.553248] ip_protocol_deliver_rcu+0x35/0x1b0
[ 55.553253] ip_local_deliver_finish+0x44/0x50
[ 55.553258] ip_local_deliver+0x6c/0x110
[ 55.553262] ? ip_rcv_finish_core.isra.19+0x5a/0x400
[ 55.553267] ip_rcv+0xd1/0xe0
...
After debugging, I found in __skb_flow_dissect(), skb->dev and skb->sk
are both NULL, then net is NULL, and trigger WARN_ON_ONCE(!net),
actually net is always NULL in this code path, as skb->dev is set to
NULL in tcp_v4_rcv(), and skb->sk is never set.
Code snippet in __skb_flow_dissect() that trigger warning:
975 if (skb) {
976 if (!net) {
977 if (skb->dev)
978 net = dev_net(skb->dev);
979 else if (skb->sk)
980 net = sock_net(skb->sk);
981 }
982 }
983
984 WARN_ON_ONCE(!net);
So, using seq and transport header derived hash.
[1] https://github.com/wg/wrk
[2] https://github.com/ourway/webfsd
[3] https://github.com/pabeni/mptcp-tools
Fixes: 9466a1ccebbe ("mptcp: enable JOIN requests even if cookies are in use")
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Jianguo Wu <wujianguo@chinatelecom.cn>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-10 03:20:46 +03:00
static u32 mptcp_join_hash_secret __read_mostly ;
struct tcphdr * th = tcp_hdr ( skb ) ;
u32 seq , i ;
net_get_random_once ( & mptcp_join_hash_secret ,
sizeof ( mptcp_join_hash_secret ) ) ;
if ( th - > syn )
seq = TCP_SKB_CB ( skb ) - > seq ;
else
seq = TCP_SKB_CB ( skb ) - > seq - 1 ;
i = jhash_3words ( seq , net_hash_mix ( net ) ,
( __force __u32 ) th - > source < < 16 | ( __force __u32 ) th - > dest ,
mptcp_join_hash_secret ) ;
2020-07-30 22:25:56 +03:00
return i % ARRAY_SIZE ( join_entries ) ;
}
static void mptcp_join_store_state ( struct join_entry * entry ,
const struct mptcp_subflow_request_sock * subflow_req )
{
entry - > token = subflow_req - > token ;
entry - > remote_nonce = subflow_req - > remote_nonce ;
entry - > local_nonce = subflow_req - > local_nonce ;
entry - > backup = subflow_req - > backup ;
entry - > join_id = subflow_req - > remote_id ;
entry - > local_id = subflow_req - > local_id ;
entry - > valid = 1 ;
}
void subflow_init_req_cookie_join_save ( const struct mptcp_subflow_request_sock * subflow_req ,
struct sk_buff * skb )
{
struct net * net = read_pnet ( & subflow_req - > sk . req . ireq_net ) ;
u32 i = mptcp_join_entry_hash ( skb , net ) ;
/* No use in waiting if other cpu is already using this slot --
* would overwrite the data that got stored .
*/
spin_lock_bh ( & join_entry_locks [ i ] ) ;
mptcp_join_store_state ( & join_entries [ i ] , subflow_req ) ;
spin_unlock_bh ( & join_entry_locks [ i ] ) ;
}
/* Called for a cookie-ack with MP_JOIN option present.
* Look up the saved state based on skb hash & check token matches msk
* in same netns .
*
* Caller will check msk can still accept another subflow . The hmac
* present in the cookie ACK mptcp option space will be checked later .
*/
bool mptcp_token_join_cookie_init_state ( struct mptcp_subflow_request_sock * subflow_req ,
struct sk_buff * skb )
{
struct net * net = read_pnet ( & subflow_req - > sk . req . ireq_net ) ;
u32 i = mptcp_join_entry_hash ( skb , net ) ;
struct mptcp_sock * msk ;
struct join_entry * e ;
e = & join_entries [ i ] ;
spin_lock_bh ( & join_entry_locks [ i ] ) ;
if ( e - > valid = = 0 ) {
spin_unlock_bh ( & join_entry_locks [ i ] ) ;
return false ;
}
e - > valid = 0 ;
2021-09-24 03:04:11 +03:00
msk = mptcp_token_get_sock ( net , e - > token ) ;
2020-07-30 22:25:56 +03:00
if ( ! msk ) {
spin_unlock_bh ( & join_entry_locks [ i ] ) ;
return false ;
}
subflow_req - > remote_nonce = e - > remote_nonce ;
subflow_req - > local_nonce = e - > local_nonce ;
subflow_req - > backup = e - > backup ;
subflow_req - > remote_id = e - > join_id ;
subflow_req - > token = e - > token ;
subflow_req - > msk = msk ;
spin_unlock_bh ( & join_entry_locks [ i ] ) ;
return true ;
}
void __init mptcp_join_cookie_init ( void )
{
int i ;
2020-08-01 17:39:59 +03:00
for ( i = 0 ; i < COOKIE_JOIN_SLOTS ; i + + )
2020-07-30 22:25:56 +03:00
spin_lock_init ( & join_entry_locks [ i ] ) ;
}