Commit b8fa4100 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'tcp_tsoffset' 



Andrey Vagin says:

====================
If a TCP socket will get live-migrated from one box to another the
timestamps (which are typically ON) will get screwed up -- the new
kernel will generate TS values that has nothing to do with what they
were on dump. The solution is to yet again fix the kernel and put a
"timestamp offset" on a socket.

A socket offset is added in places where externally visible tcp
timestamp option is parsed/initialized.

Connections in the SYN_RECV state are not supported, global
tcp_time_stamp is used for them, because repair mode doesn't support
this state. In a future it can be implemented by the similar way as for
TIME_WAIT sockets.

For time-wait sockets offset is inhereted by a proper tcp_sock.

A per-socket offset can be set only for sockets in repair mode.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents d0023f82 ee684b6f

include/linux/tcp.h

+3 −0
Original line number Diff line number Diff line
@@ -162,6 +162,8 @@ struct tcp_sock { 
	u32	rcv_tstamp;	/* timestamp of last received ACK (for keepalives) */

	u32	lsndtime;	/* timestamp of last sent data packet (for restart window) */



	u32	tsoffset;	/* timestamp offset */



	struct list_head tsq_node; /* anchor in tsq_tasklet.head list */

	unsigned long	tsq_flags;
@@ -353,6 +355,7 @@ struct tcp_timewait_sock { 
	u32			  tw_rcv_nxt;

	u32			  tw_snd_nxt;

	u32			  tw_rcv_wnd;

	u32			  tw_ts_offset;

	u32			  tw_ts_recent;

	long			  tw_ts_recent_stamp;

#ifdef CONFIG_TCP_MD5SIG

include/uapi/linux/tcp.h

+1 −0
Original line number Diff line number Diff line
@@ -111,6 +111,7 @@ enum { 
#define TCP_QUEUE_SEQ		21

#define TCP_REPAIR_OPTIONS	22

#define TCP_FASTOPEN		23	/* Enable FastOpen on listeners */

#define TCP_TIMESTAMP		24



struct tcp_repair_opt {

	__u32	opt_code;

net/ipv4/tcp.c

+11 −0
Original line number Diff line number Diff line
@@ -400,6 +400,8 @@ void tcp_init_sock(struct sock *sk) 
	tcp_enable_early_retrans(tp);

	icsk->icsk_ca_ops = &tcp_init_congestion_ops;



	tp->tsoffset = 0;



	sk->sk_state = TCP_CLOSE;



	sk->sk_write_space = sk_stream_write_space;
@@ -2712,6 +2714,12 @@ static int do_tcp_setsockopt(struct sock *sk, int level, 
		else

			err = -EINVAL;

		break;

	case TCP_TIMESTAMP:

		if (!tp->repair)

			err = -EPERM;

		else

			tp->tsoffset = val - tcp_time_stamp;

		break;

	default:

		err = -ENOPROTOOPT;

		break;
@@ -2960,6 +2968,9 @@ static int do_tcp_getsockopt(struct sock *sk, int level, 
	case TCP_USER_TIMEOUT:

		val = jiffies_to_msecs(icsk->icsk_user_timeout);

		break;

	case TCP_TIMESTAMP:

		val = tcp_time_stamp + tp->tsoffset;

		break;

	default:

		return -ENOPROTOOPT;

	}

net/ipv4/tcp_input.c

+7 −1
Original line number Diff line number Diff line
@@ -3860,7 +3860,7 @@ static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr 
		++ptr;

		tp->rx_opt.rcv_tsval = ntohl(*ptr);

		++ptr;

		tp->rx_opt.rcv_tsecr = ntohl(*ptr);

		tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset;

		return true;

	}

	return false;
@@ -3884,7 +3884,11 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb, 
		if (tcp_parse_aligned_timestamp(tp, th))

			return true;

	}



	tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL);

	if (tp->rx_opt.saw_tstamp)

		tp->rx_opt.rcv_tsecr -= tp->tsoffset;



	return true;

}
@@ -5665,6 +5669,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, 
	int saved_clamp = tp->rx_opt.mss_clamp;



	tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, &foc);

	if (tp->rx_opt.saw_tstamp)

		tp->rx_opt.rcv_tsecr -= tp->tsoffset;



	if (th->ack) {

		/* rfc793:

net/ipv4/tcp_ipv4.c

+7 −5
Original line number Diff line number Diff line
@@ -726,7 +726,7 @@ release_sk1: 
 */



static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,

			    u32 win, u32 ts, int oif,

			    u32 win, u32 tsval, u32 tsecr, int oif,

			    struct tcp_md5sig_key *key,

			    int reply_flags, u8 tos)

{
@@ -747,12 +747,12 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, 


	arg.iov[0].iov_base = (unsigned char *)&rep;

	arg.iov[0].iov_len  = sizeof(rep.th);

	if (ts) {

	if (tsecr) {

		rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |

				   (TCPOPT_TIMESTAMP << 8) |

				   TCPOLEN_TIMESTAMP);

		rep.opt[1] = htonl(tcp_time_stamp);

		rep.opt[2] = htonl(ts);

		rep.opt[1] = htonl(tsval);

		rep.opt[2] = htonl(tsecr);

		arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED;

	}
@@ -767,7 +767,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, 


#ifdef CONFIG_TCP_MD5SIG

	if (key) {

		int offset = (ts) ? 3 : 0;

		int offset = (tsecr) ? 3 : 0;



		rep.opt[offset++] = htonl((TCPOPT_NOP << 24) |

					  (TCPOPT_NOP << 16) |
@@ -802,6 +802,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) 


	tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,

			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,

			tcp_time_stamp + tcptw->tw_ts_offset,

			tcptw->tw_ts_recent,

			tw->tw_bound_dev_if,

			tcp_twsk_md5_key(tcptw),
@@ -821,6 +822,7 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, 
	tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?

			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,

			tcp_rsk(req)->rcv_nxt, req->rcv_wnd,

			tcp_time_stamp,

			req->ts_recent,

			0,

			tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,

CRA Git | Maintained and supported by SUSTech CRA and CCSE