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.
This patch adds one more tcp socket option TCP_TIMESTAMP, which is used
for getting and setting a current value of tcp_timestamp.
Cc: "David S. Miller" <da...@davemloft.net>
Cc: Alexey Kuznetsov <kuz...@ms2.inr.ac.ru>
Cc: James Morris <jmor...@namei.org>
Cc: Hideaki YOSHIFUJI <yoshf...@linux-ipv6.org>
Cc: Patrick McHardy <ka...@trash.net>
Cc: Eric Dumazet <eduma...@google.com>
Cc: Yuchung Cheng <ych...@google.com>
Cc: Neal Cardwell <ncardw...@google.com>
Cc: Pavel Emelyanov <xe...@parallels.com>
Cc: Dave Jones <da...@redhat.com>
Cc: Michael Kerrisk <mtk.manpa...@gmail.com>
Signed-off-by: Andrey Vagin <ava...@openvz.org>
---
include/linux/tcp.h | 2 ++
include/net/tcp.h | 2 +-
include/uapi/linux/tcp.h | 1 +
net/ipv4/tcp.c | 7 +++++++
4 files changed, 11 insertions(+), 1 deletion(-)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 4e1d228..5ebc67c 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -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;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3e242ba..25119c0 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -677,7 +677,7 @@ void tcp_send_window_probe(struct sock *sk);
*/
static inline u32 tcp_time_stamp(const struct tcp_sock *tp)
{
- return (__u32)jiffies;
+ return (__u32)(jiffies) + tp->tsoffset;
}
#define tcp_flag_byte(th) (((u_int8_t *)th)[13])
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index e962faa..6b1ead0 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -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;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 086ceda..23f93d4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2704,6 +2704,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
else
err = -EINVAL;
break;
+ case TCP_TIMESTAMP:
+ tp->tsoffset = 0;
+ tp->tsoffset = val - tcp_time_stamp(tp);
+ break;
default:
err = -ENOPROTOOPT;
break;
@@ -2952,6 +2956,9 @@ 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);
+ break;
default:
return -ENOPROTOOPT;
}
--
1.7.11.7
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
