summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/networking/timestamping.rst32
-rw-r--r--include/net/sock.h6
-rw-r--r--include/uapi/linux/net_tstamp.h3
-rw-r--r--net/core/sock.c9
-rw-r--r--net/ethtool/common.c1
5 files changed, 45 insertions, 6 deletions
diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst
index be4eb1242057..f17c01834a12 100644
--- a/Documentation/networking/timestamping.rst
+++ b/Documentation/networking/timestamping.rst
@@ -179,7 +179,8 @@ SOF_TIMESTAMPING_OPT_ID:
identifier and returns that along with the timestamp. The identifier
is derived from a per-socket u32 counter (that wraps). For datagram
sockets, the counter increments with each sent packet. For stream
- sockets, it increments with every byte.
+ sockets, it increments with every byte. For stream sockets, also set
+ SOF_TIMESTAMPING_OPT_ID_TCP, see the section below.
The counter starts at zero. It is initialized the first time that
the socket option is enabled. It is reset each time the option is
@@ -192,6 +193,35 @@ SOF_TIMESTAMPING_OPT_ID:
among all possibly concurrently outstanding timestamp requests for
that socket.
+SOF_TIMESTAMPING_OPT_ID_TCP:
+ Pass this modifier along with SOF_TIMESTAMPING_OPT_ID for new TCP
+ timestamping applications. SOF_TIMESTAMPING_OPT_ID defines how the
+ counter increments for stream sockets, but its starting point is
+ not entirely trivial. This option fixes that.
+
+ For stream sockets, if SOF_TIMESTAMPING_OPT_ID is set, this should
+ always be set too. On datagram sockets the option has no effect.
+
+ A reasonable expectation is that the counter is reset to zero with
+ the system call, so that a subsequent write() of N bytes generates
+ a timestamp with counter N-1. SOF_TIMESTAMPING_OPT_ID_TCP
+ implements this behavior under all conditions.
+
+ SOF_TIMESTAMPING_OPT_ID without modifier often reports the same,
+ especially when the socket option is set when no data is in
+ transmission. If data is being transmitted, it may be off by the
+ length of the output queue (SIOCOUTQ).
+
+ The difference is due to being based on snd_una versus write_seq.
+ snd_una is the offset in the stream acknowledged by the peer. This
+ depends on factors outside of process control, such as network RTT.
+ write_seq is the last byte written by the process. This offset is
+ not affected by external inputs.
+
+ The difference is subtle and unlikely to be noticed when configured
+ at initial socket creation, when no data is queued or sent. But
+ SOF_TIMESTAMPING_OPT_ID_TCP behavior is more robust regardless of
+ when the socket option is set.
SOF_TIMESTAMPING_OPT_CMSG:
Support recv() cmsg for all timestamped packets. Control messages
diff --git a/include/net/sock.h b/include/net/sock.h
index 6d207e7c4ad0..ecea3dcc2217 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -503,10 +503,10 @@ struct sock {
#if BITS_PER_LONG==32
seqlock_t sk_stamp_seq;
#endif
- u16 sk_tsflags;
- u8 sk_shutdown;
atomic_t sk_tskey;
atomic_t sk_zckey;
+ u32 sk_tsflags;
+ u8 sk_shutdown;
u8 sk_clockid;
u8 sk_txtime_deadline_mode : 1,
@@ -1899,7 +1899,7 @@ static inline void sock_replace_proto(struct sock *sk, struct proto *proto)
struct sockcm_cookie {
u64 transmit_time;
u32 mark;
- u16 tsflags;
+ u32 tsflags;
};
static inline void sockcm_init(struct sockcm_cookie *sockc,
diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index 55501e5e7ac8..a2c66b3d7f0f 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -31,8 +31,9 @@ enum {
SOF_TIMESTAMPING_OPT_PKTINFO = (1<<13),
SOF_TIMESTAMPING_OPT_TX_SWHW = (1<<14),
SOF_TIMESTAMPING_BIND_PHC = (1 << 15),
+ SOF_TIMESTAMPING_OPT_ID_TCP = (1 << 16),
- SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_BIND_PHC,
+ SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_ID_TCP,
SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) |
SOF_TIMESTAMPING_LAST
};
diff --git a/net/core/sock.c b/net/core/sock.c
index 4571914a4aa8..b0ab841e0aed 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -901,13 +901,20 @@ int sock_set_timestamping(struct sock *sk, int optname,
if (val & ~SOF_TIMESTAMPING_MASK)
return -EINVAL;
+ if (val & SOF_TIMESTAMPING_OPT_ID_TCP &&
+ !(val & SOF_TIMESTAMPING_OPT_ID))
+ return -EINVAL;
+
if (val & SOF_TIMESTAMPING_OPT_ID &&
!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
if (sk_is_tcp(sk)) {
if ((1 << sk->sk_state) &
(TCPF_CLOSE | TCPF_LISTEN))
return -EINVAL;
- atomic_set(&sk->sk_tskey, tcp_sk(sk)->snd_una);
+ if (val & SOF_TIMESTAMPING_OPT_ID_TCP)
+ atomic_set(&sk->sk_tskey, tcp_sk(sk)->write_seq);
+ else
+ atomic_set(&sk->sk_tskey, tcp_sk(sk)->snd_una);
} else {
atomic_set(&sk->sk_tskey, 0);
}
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 21cfe8557205..6f399afc2ff2 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -417,6 +417,7 @@ const char sof_timestamping_names[][ETH_GSTRING_LEN] = {
[const_ilog2(SOF_TIMESTAMPING_OPT_PKTINFO)] = "option-pktinfo",
[const_ilog2(SOF_TIMESTAMPING_OPT_TX_SWHW)] = "option-tx-swhw",
[const_ilog2(SOF_TIMESTAMPING_BIND_PHC)] = "bind-phc",
+ [const_ilog2(SOF_TIMESTAMPING_OPT_ID_TCP)] = "option-id-tcp",
};
static_assert(ARRAY_SIZE(sof_timestamping_names) == __SOF_TIMESTAMPING_CNT);