[PATCH v2 net-next 0/8] add TX timestamping via cmsg

[PATCH v2 net-next 0/8] add TX timestamping via cmsg

[Soheil Hassas Yeganeh]

From: Soheil Hassas Yeganeh <soheil@google.com>

This patch series aim at enabling TX timestamping via cmsg.

Currently, to occasionally sample TX timestamping on a socket,
applications need to call setsockopt twice: first for enabling
timestamps and then for disabling them. This is an unnecessary
overhead. With cmsg, in contrast, applications can sample TX
timestamps per sendmsg().

This patch series adds the code for processing SO_TIMESTAMPING
for cmsg's of the SOL_SOCKET level, and adds the glue code for
TCP, UDP, and RAW for both IPv4 and IPv6. This implementation
supports overriding timestamp generation flags (i.e.,
SOF_TIMESTAMPING_TX_*) but not timestamp reporting flags.
Applications must still enable timestamp reporting via
setsockopt to receive timestamps.

This series does not change existing timestamping behavior for
applications that are using socket options.

I will follow up with another patch to enable timestamping for
active TFO (client-side TCP Fast Open) and also setting packet
mark via cmsgs.

Thanks!

Changes in v2:
	- Replace u32 with __u32 in the documentation.

Soheil Hassas Yeganeh (7):
  tcp: accept SOF_TIMESTAMPING_OPT_ID for passive TFO
  tcp: use one bit in TCP_SKB_CB to mark ACK timestamps
  sock: accept SO_TIMESTAMPING flags in socket cmsg
  ipv4: process socket-level control messages in IPv4
  ipv6: process socket-level control messages in IPv6
  sock: enable timestamping using control messages
  sock: document timestamping via cmsg in Documentation

Willem de Bruijn (1):
  sock: break up sock_cmsg_snd into __sock_cmsg_snd and loop

 Documentation/networking/timestamping.txt | 48 ++++++++++++++++++++++++++++--
 drivers/net/tun.c                         |  3 +-
 include/net/ip.h                          |  3 +-
 include/net/ipv6.h                        |  6 ++--
 include/net/sock.h                        | 13 +++++---
 include/net/tcp.h                         |  3 +-
 include/net/transp_v6.h                   |  3 +-
 include/uapi/linux/net_tstamp.h           | 10 +++++++
 net/can/raw.c                             |  2 +-
 net/core/sock.c                           | 49 +++++++++++++++++++++++--------
 net/ipv4/ip_sockglue.c                    |  9 +++++-
 net/ipv4/ping.c                           |  7 +++--
 net/ipv4/raw.c                            | 13 ++++----
 net/ipv4/tcp.c                            | 22 ++++++++++----
 net/ipv4/tcp_input.c                      |  2 +-
 net/ipv4/udp.c                            | 10 +++----
 net/ipv6/datagram.c                       |  9 +++++-
 net/ipv6/icmp.c                           |  6 ++--
 net/ipv6/ip6_flowlabel.c                  |  3 +-
 net/ipv6/ip6_output.c                     | 15 ++++++----
 net/ipv6/ipv6_sockglue.c                  |  3 +-
 net/ipv6/ping.c                           |  3 +-
 net/ipv6/raw.c                            |  7 +++--
 net/ipv6/udp.c                            | 10 +++++--
 net/packet/af_packet.c                    | 30 +++++++++++++++----
 net/socket.c                              | 10 +++----
 26 files changed, 225 insertions(+), 74 deletions(-)

-- 
2.8.0.rc3.226.g39d4020

[PATCH v2 net-next 1/8] sock: break up sock_cmsg_snd into __sock_cmsg_snd and loop

[Soheil Hassas Yeganeh]

From: Willem de Bruijn <willemb@google.com>

To process cmsg's of the SOL_SOCKET level in addition to
cmsgs of another level, protocols can call sock_cmsg_send().
This causes a double walk on the cmsghdr list, one for SOL_SOCKET
and one for the other level.

Extract the inner demultiplex logic from the loop that walks the list,
to allow having this called directly from a walker in the protocol
specific code.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
---
 include/net/sock.h |  2 ++
 net/core/sock.c    | 33 ++++++++++++++++++++++-----------
 2 files changed, 24 insertions(+), 11 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 255d3e0..03772d4 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1420,6 +1420,8 @@ struct sockcm_cookie {
 	u32 mark;
 };
 
+int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
+		     struct sockcm_cookie *sockc);
 int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
 		   struct sockcm_cookie *sockc);
 
diff --git a/net/core/sock.c b/net/core/sock.c
index b67b9ae..66976f8 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1866,27 +1866,38 @@ struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
 }
 EXPORT_SYMBOL(sock_alloc_send_skb);
 
+int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
+		     struct sockcm_cookie *sockc)
+{
+	switch (cmsg->cmsg_type) {
+	case SO_MARK:
+		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+		if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
+			return -EINVAL;
+		sockc->mark = *(u32 *)CMSG_DATA(cmsg);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(__sock_cmsg_send);
+
 int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
 		   struct sockcm_cookie *sockc)
 {
 	struct cmsghdr *cmsg;
+	int ret;
 
 	for_each_cmsghdr(cmsg, msg) {
 		if (!CMSG_OK(msg, cmsg))
 			return -EINVAL;
 		if (cmsg->cmsg_level != SOL_SOCKET)
 			continue;
-		switch (cmsg->cmsg_type) {
-		case SO_MARK:
-			if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
-				return -EPERM;
-			if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
-				return -EINVAL;
-			sockc->mark = *(u32 *)CMSG_DATA(cmsg);
-			break;
-		default:
-			return -EINVAL;
-		}
+		ret = __sock_cmsg_send(sk, msg, cmsg, sockc);
+		if (ret)
+			return ret;
 	}
 	return 0;
 }
-- 
2.8.0.rc3.226.g39d4020

[PATCH v2 net-next 2/8] tcp: accept SOF_TIMESTAMPING_OPT_ID for passive TFO

[Soheil Hassas Yeganeh]

From: Soheil Hassas Yeganeh <soheil@google.com>

SOF_TIMESTAMPING_OPT_ID is set to get data-independent IDs
to associate timestamps with send calls. For TCP connections,
tp->snd_una is used as the starting point to calculate
relative IDs.

This socket option will fail if set before the handshake on a
passive TCP fast open connection with data in SYN or SYN/ACK,
since setsockopt requires the connection to be in the
ESTABLISHED state.

To address these, instead of limiting the option to the
ESTABLISHED state, accept the SOF_TIMESTAMPING_OPT_ID option as
long as the connection is not in LISTEN or CLOSE states.

Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
---
 net/core/sock.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 66976f8..0a64fe2 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -832,7 +832,8 @@ set_rcvbuf:
 		    !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
 			if (sk->sk_protocol == IPPROTO_TCP &&
 			    sk->sk_type == SOCK_STREAM) {
-				if (sk->sk_state != TCP_ESTABLISHED) {
+				if ((1 << sk->sk_state) &
+				    (TCPF_CLOSE | TCPF_LISTEN)) {
 					ret = -EINVAL;
 					break;
 				}
-- 
2.8.0.rc3.226.g39d4020

[PATCH v2 net-next 3/8] tcp: use one bit in TCP_SKB_CB to mark ACK timestamps

[Soheil Hassas Yeganeh]

From: Soheil Hassas Yeganeh <soheil@google.com>

Currently, to avoid a cache line miss for accessing skb_shinfo,
tcp_ack_tstamp skips socket that do not have
SOF_TIMESTAMPING_TX_ACK bit set in sk_tsflags. This is
implemented based on an implicit assumption that the
SOF_TIMESTAMPING_TX_ACK is set via socket options for the
duration that ACK timestamps are needed.

To implement per-write timestamps, this check should be
removed and replaced with a per-packet alternative that
quickly skips packets missing ACK timestamps marks without
a cache-line miss.

To enable per-packet marking without a cache line miss, use
one bit in TCP_SKB_CB to mark a whether a SKB might need a
ack tx timestamp or not. Further checks in tcp_ack_tstamp are not
modified and work as before.

Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
---
 include/net/tcp.h    | 3 ++-
 net/ipv4/tcp.c       | 2 ++
 net/ipv4/tcp_input.c | 2 +-
 3 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index b91370f..f3a80ec 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -754,7 +754,8 @@ struct tcp_skb_cb {
 				TCPCB_REPAIRED)
 
 	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
-	/* 1 byte hole */
+	__u8		txstamp_ack:1,	/* Record TX timestamp for ack? */
+			unused:7;
 	__u32		ack_seq;	/* Sequence number ACK'd	*/
 	union {
 		struct inet_skb_parm	h4;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 08b8b96..ce3c9eb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -432,10 +432,12 @@ static void tcp_tx_timestamp(struct sock *sk, struct sk_buff *skb)
 {
 	if (sk->sk_tsflags) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
+		struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
 
 		sock_tx_timestamp(sk, &shinfo->tx_flags);
 		if (shinfo->tx_flags & SKBTX_ANY_TSTAMP)
 			shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
+		tcb->txstamp_ack = !!(shinfo->tx_flags & SKBTX_ACK_TSTAMP);
 	}
 }
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e6e65f7..2d5fee4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3093,7 +3093,7 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
 	const struct skb_shared_info *shinfo;
 
 	/* Avoid cache line misses to get skb_shinfo() and shinfo->tx_flags */
-	if (likely(!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)))
+	if (likely(!TCP_SKB_CB(skb)->txstamp_ack))
 		return;
 
 	shinfo = skb_shinfo(skb);
-- 
2.8.0.rc3.226.g39d4020

[PATCH v2 net-next 4/8] sock: accept SO_TIMESTAMPING flags in socket cmsg

[Soheil Hassas Yeganeh]

From: Soheil Hassas Yeganeh <soheil@google.com>

Accept SO_TIMESTAMPING in control messages of the SOL_SOCKET level
as a basis to accept timestamping requests per write.

This implementation only accepts TX recording flags (i.e.,
SOF_TIMESTAMPING_TX_HARDWARE, SOF_TIMESTAMPING_TX_SOFTWARE,
SOF_TIMESTAMPING_TX_SCHED, and SOF_TIMESTAMPING_TX_ACK) in
control messages. Users need to set reporting flags (e.g.,
SOF_TIMESTAMPING_OPT_ID) per socket via socket options.

This commit adds a tsflags field in sockcm_cookie which is
set in __sock_cmsg_send. It only override the SOF_TIMESTAMPING_TX_*
bits in sockcm_cookie.tsflags allowing the control message
to override the recording behavior per write, yet maintaining
the value of other flags.

This patch implements validating the control message and setting
tsflags in struct sockcm_cookie. Next commits in this series will
actually implement timestamping per write for different protocols.

Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
---
 include/net/sock.h              |  1 +
 include/uapi/linux/net_tstamp.h | 10 ++++++++++
 net/core/sock.c                 | 13 +++++++++++++
 3 files changed, 24 insertions(+)

diff --git a/include/net/sock.h b/include/net/sock.h
index 03772d4..af012da 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1418,6 +1418,7 @@ void sk_send_sigurg(struct sock *sk);
 
 struct sockcm_cookie {
 	u32 mark;
+	u16 tsflags;
 };
 
 int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index 6d1abea..264e515 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -31,6 +31,16 @@ enum {
 				 SOF_TIMESTAMPING_LAST
 };
 
+/*
+ * SO_TIMESTAMPING flags are either for recording a packet timestamp or for
+ * reporting the timestamp to user space.
+ * Recording flags can be set both via socket options and control messages.
+ */
+#define SOF_TIMESTAMPING_TX_RECORD_MASK	(SOF_TIMESTAMPING_TX_HARDWARE | \
+					 SOF_TIMESTAMPING_TX_SOFTWARE | \
+					 SOF_TIMESTAMPING_TX_SCHED | \
+					 SOF_TIMESTAMPING_TX_ACK)
+
 /**
  * struct hwtstamp_config - %SIOCGHWTSTAMP and %SIOCSHWTSTAMP parameter
  *
diff --git a/net/core/sock.c b/net/core/sock.c
index 0a64fe2..315f5e5 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1870,6 +1870,8 @@ EXPORT_SYMBOL(sock_alloc_send_skb);
 int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
 		     struct sockcm_cookie *sockc)
 {
+	u32 tsflags;
+
 	switch (cmsg->cmsg_type) {
 	case SO_MARK:
 		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
@@ -1878,6 +1880,17 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
 			return -EINVAL;
 		sockc->mark = *(u32 *)CMSG_DATA(cmsg);
 		break;
+	case SO_TIMESTAMPING:
+		if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
+			return -EINVAL;
+
+		tsflags = *(u32 *)CMSG_DATA(cmsg);
+		if (tsflags & ~SOF_TIMESTAMPING_TX_RECORD_MASK)
+			return -EINVAL;
+
+		sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK;
+		sockc->tsflags |= tsflags;
+		break;
 	default:
 		return -EINVAL;
 	}
-- 
2.8.0.rc3.226.g39d4020

[PATCH v2 net-next 5/8] ipv4: process socket-level control messages in IPv4

[Soheil Hassas Yeganeh]

From: Soheil Hassas Yeganeh <soheil@google.com>

Process socket-level control messages by invoking
__sock_cmsg_send in ip_cmsg_send for control messages on
the SOL_SOCKET layer.

This makes sure whenever ip_cmsg_send is called in udp, icmp,
and raw, we also process socket-level control messages.

Note that this commit interprets new control messages that
were ignored before. As such, this commit does not change
the behavior of IPv4 control messages.

Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
---
 include/net/ip.h       | 3 ++-
 net/ipv4/ip_sockglue.c | 9 ++++++++-
 net/ipv4/ping.c        | 2 +-
 net/ipv4/raw.c         | 2 +-
 net/ipv4/udp.c         | 3 +--
 5 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index fad74d3..93725e5 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -56,6 +56,7 @@ static inline unsigned int ip_hdrlen(const struct sk_buff *skb)
 }
 
 struct ipcm_cookie {
+	struct sockcm_cookie	sockc;
 	__be32			addr;
 	int			oif;
 	struct ip_options_rcu	*opt;
@@ -550,7 +551,7 @@ int ip_options_rcv_srr(struct sk_buff *skb);
 
 void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
 void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int offset);
-int ip_cmsg_send(struct net *net, struct msghdr *msg,
+int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
 		 struct ipcm_cookie *ipc, bool allow_ipv6);
 int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
 		  unsigned int optlen);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 035ad64..1b7c077 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -219,11 +219,12 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(ip_cmsg_recv_offset);
 
-int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
+int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
 		 bool allow_ipv6)
 {
 	int err, val;
 	struct cmsghdr *cmsg;
+	struct net *net = sock_net(sk);
 
 	for_each_cmsghdr(cmsg, msg) {
 		if (!CMSG_OK(msg, cmsg))
@@ -244,6 +245,12 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
 			continue;
 		}
 #endif
+		if (cmsg->cmsg_level == SOL_SOCKET) {
+			if (__sock_cmsg_send(sk, msg, cmsg, &ipc->sockc))
+				return -EINVAL;
+			continue;
+		}
+
 		if (cmsg->cmsg_level != SOL_IP)
 			continue;
 		switch (cmsg->cmsg_type) {
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index cf9700b..670639b 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -747,7 +747,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	sock_tx_timestamp(sk, &ipc.tx_flags);
 
 	if (msg->msg_controllen) {
-		err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
+		err = ip_cmsg_send(sk, msg, &ipc, false);
 		if (unlikely(err)) {
 			kfree(ipc.opt);
 			return err;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 8d22de7..088ce66 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -548,7 +548,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc.oif = sk->sk_bound_dev_if;
 
 	if (msg->msg_controllen) {
-		err = ip_cmsg_send(net, msg, &ipc, false);
+		err = ip_cmsg_send(sk, msg, &ipc, false);
 		if (unlikely(err)) {
 			kfree(ipc.opt);
 			goto out;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 08eed5e..bccb4e1 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1034,8 +1034,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	sock_tx_timestamp(sk, &ipc.tx_flags);
 
 	if (msg->msg_controllen) {
-		err = ip_cmsg_send(sock_net(sk), msg, &ipc,
-				   sk->sk_family == AF_INET6);
+		err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6);
 		if (unlikely(err)) {
 			kfree(ipc.opt);
 			return err;
-- 
2.8.0.rc3.226.g39d4020

[PATCH v2 net-next 6/8] ipv6: process socket-level control messages in IPv6

[Soheil Hassas Yeganeh]

From: Soheil Hassas Yeganeh <soheil@google.com>

Process socket-level control messages by invoking
__sock_cmsg_send in ip6_datagram_send_ctl for control messages on
the SOL_SOCKET layer.

This makes sure whenever ip6_datagram_send_ctl is called for
udp and raw, we also process socket-level control messages.

This is a bit uglier than IPv4, since IPv6 does not have
something like ipcm_cookie. Perhaps we can later create
a control message cookie for IPv6?

Note that this commit interprets new control messages that
were ignored before. As such, this commit does not change
the behavior of IPv6 control messages.

Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
---
 include/net/transp_v6.h  | 3 ++-
 net/ipv6/datagram.c      | 9 ++++++++-
 net/ipv6/ip6_flowlabel.c | 3 ++-
 net/ipv6/ipv6_sockglue.c | 3 ++-
 net/ipv6/raw.c           | 6 +++++-
 net/ipv6/udp.c           | 5 ++++-
 6 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h
index b927413..2b1c345 100644
--- a/include/net/transp_v6.h
+++ b/include/net/transp_v6.h
@@ -42,7 +42,8 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 
 int ip6_datagram_send_ctl(struct net *net, struct sock *sk, struct msghdr *msg,
 			  struct flowi6 *fl6, struct ipv6_txoptions *opt,
-			  int *hlimit, int *tclass, int *dontfrag);
+			  int *hlimit, int *tclass, int *dontfrag,
+			  struct sockcm_cookie *sockc);
 
 void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
 			     __u16 srcp, __u16 destp, int bucket);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 4281621..a73d701 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -685,7 +685,8 @@ EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl);
 int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 			  struct msghdr *msg, struct flowi6 *fl6,
 			  struct ipv6_txoptions *opt,
-			  int *hlimit, int *tclass, int *dontfrag)
+			  int *hlimit, int *tclass, int *dontfrag,
+			  struct sockcm_cookie *sockc)
 {
 	struct in6_pktinfo *src_info;
 	struct cmsghdr *cmsg;
@@ -702,6 +703,12 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 			goto exit_f;
 		}
 
+		if (cmsg->cmsg_level == SOL_SOCKET) {
+			if (__sock_cmsg_send(sk, msg, cmsg, sockc))
+				return -EINVAL;
+			continue;
+		}
+
 		if (cmsg->cmsg_level != SOL_IPV6)
 			continue;
 
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index dc2db4f..35d3ddc 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -372,6 +372,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 	if (olen > 0) {
 		struct msghdr msg;
 		struct flowi6 flowi6;
+		struct sockcm_cookie sockc_junk;
 		int junk;
 
 		err = -ENOMEM;
@@ -390,7 +391,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 		memset(&flowi6, 0, sizeof(flowi6));
 
 		err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, fl->opt,
-					    &junk, &junk, &junk);
+					    &junk, &junk, &junk, &sockc_junk);
 		if (err)
 			goto done;
 		err = -EINVAL;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 4449ad1..a5557d2 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -471,6 +471,7 @@ sticky_done:
 		struct ipv6_txoptions *opt = NULL;
 		struct msghdr msg;
 		struct flowi6 fl6;
+		struct sockcm_cookie sockc_junk;
 		int junk;
 
 		memset(&fl6, 0, sizeof(fl6));
@@ -503,7 +504,7 @@ sticky_done:
 		msg.msg_control = (void *)(opt+1);
 
 		retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk,
-					     &junk, &junk);
+					     &junk, &junk, &sockc_junk);
 		if (retv)
 			goto done;
 update:
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index fa59dd7..f175ec0 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -745,6 +745,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	struct dst_entry *dst = NULL;
 	struct raw6_frag_vec rfv;
 	struct flowi6 fl6;
+	struct sockcm_cookie sockc;
 	int addr_len = msg->msg_namelen;
 	int hlimit = -1;
 	int tclass = -1;
@@ -821,13 +822,16 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (fl6.flowi6_oif == 0)
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 
+	sockc.tsflags = 0;
+
 	if (msg->msg_controllen) {
 		opt = &opt_space;
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
 		opt->tot_len = sizeof(struct ipv6_txoptions);
 
 		err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
-					    &hlimit, &tclass, &dontfrag);
+					    &hlimit, &tclass, &dontfrag,
+					    &sockc);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index fd25e44..8371a51 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1128,6 +1128,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	int connected = 0;
 	int is_udplite = IS_UDPLITE(sk);
 	int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
+	struct sockcm_cookie sockc;
 
 	/* destination address check */
 	if (sin6) {
@@ -1247,6 +1248,7 @@ do_udp_sendmsg:
 		fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
 
 	fl6.flowi6_mark = sk->sk_mark;
+	sockc.tsflags = 0;
 
 	if (msg->msg_controllen) {
 		opt = &opt_space;
@@ -1254,7 +1256,8 @@ do_udp_sendmsg:
 		opt->tot_len = sizeof(*opt);
 
 		err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
-					    &hlimit, &tclass, &dontfrag);
+					    &hlimit, &tclass, &dontfrag,
+					    &sockc);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
-- 
2.8.0.rc3.226.g39d4020

[PATCH v2 net-next 7/8] sock: enable timestamping using control messages

[Soheil Hassas Yeganeh]

From: Soheil Hassas Yeganeh <soheil@google.com>

Currently, SOL_TIMESTAMPING can only be enabled using setsockopt.
This is very costly when users want to sample writes to gather
tx timestamps.

Add support for enabling SO_TIMESTAMPING via control messages by
using tsflags added in `struct sockcm_cookie` (added in the previous
patches in this series) to set the tx_flags of the last skb created in
a sendmsg. With this patch, the timestamp recording bits in tx_flags
of the skbuff is overridden if SO_TIMESTAMPING is passed in a cmsg.

Please note that this is only effective for overriding the recording
timestamps flags. Users should enable timestamp reporting (e.g.,
SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_OPT_ID) using
socket options and then should ask for SOF_TIMESTAMPING_TX_*
using control messages per sendmsg to sample timestamps for each
write.

Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
---
 drivers/net/tun.c      |  3 ++-
 include/net/ipv6.h     |  6 ++++--
 include/net/sock.h     | 10 ++++++----
 net/can/raw.c          |  2 +-
 net/ipv4/ping.c        |  5 +++--
 net/ipv4/raw.c         | 11 ++++++-----
 net/ipv4/tcp.c         | 20 +++++++++++++++-----
 net/ipv4/udp.c         |  7 ++++---
 net/ipv6/icmp.c        |  6 ++++--
 net/ipv6/ip6_output.c  | 15 +++++++++------
 net/ipv6/ping.c        |  3 ++-
 net/ipv6/raw.c         |  5 ++---
 net/ipv6/udp.c         |  7 ++++---
 net/packet/af_packet.c | 30 +++++++++++++++++++++++++-----
 net/socket.c           | 10 +++++-----
 15 files changed, 92 insertions(+), 48 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index afdf950..6d2fcd0 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -860,7 +860,8 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto drop;
 
 	if (skb->sk && sk_fullsock(skb->sk)) {
-		sock_tx_timestamp(skb->sk, &skb_shinfo(skb)->tx_flags);
+		sock_tx_timestamp(skb->sk, skb->sk->sk_tsflags,
+				  &skb_shinfo(skb)->tx_flags);
 		sw_tx_timestamp(skb);
 	}
 
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index d0aeb97..55ee1eb 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -867,7 +867,8 @@ int ip6_append_data(struct sock *sk,
 				int odd, struct sk_buff *skb),
 		    void *from, int length, int transhdrlen, int hlimit,
 		    int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6,
-		    struct rt6_info *rt, unsigned int flags, int dontfrag);
+		    struct rt6_info *rt, unsigned int flags, int dontfrag,
+		    const struct sockcm_cookie *sockc);
 
 int ip6_push_pending_frames(struct sock *sk);
 
@@ -884,7 +885,8 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 			     void *from, int length, int transhdrlen,
 			     int hlimit, int tclass, struct ipv6_txoptions *opt,
 			     struct flowi6 *fl6, struct rt6_info *rt,
-			     unsigned int flags, int dontfrag);
+			     unsigned int flags, int dontfrag,
+			     const struct sockcm_cookie *sockc);
 
 static inline struct sk_buff *ip6_finish_skb(struct sock *sk)
 {
diff --git a/include/net/sock.h b/include/net/sock.h
index af012da..e91b87f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2057,19 +2057,21 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 		sk->sk_stamp = skb->tstamp;
 }
 
-void __sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags);
+void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags);
 
 /**
  * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped
  * @sk:		socket sending this packet
+ * @tsflags:	timestamping flags to use
  * @tx_flags:	completed with instructions for time stamping
  *
  * Note : callers should take care of initial *tx_flags value (usually 0)
  */
-static inline void sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags)
+static inline void sock_tx_timestamp(const struct sock *sk, __u16 tsflags,
+				     __u8 *tx_flags)
 {
-	if (unlikely(sk->sk_tsflags))
-		__sock_tx_timestamp(sk, tx_flags);
+	if (unlikely(tsflags))
+		__sock_tx_timestamp(tsflags, tx_flags);
 	if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS)))
 		*tx_flags |= SKBTX_WIFI_STATUS;
 }
diff --git a/net/can/raw.c b/net/can/raw.c
index 2e67b14..972c187 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -755,7 +755,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	if (err < 0)
 		goto free_skb;
 
-	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
+	sock_tx_timestamp(sk, sk->sk_tsflags, &skb_shinfo(skb)->tx_flags);
 
 	skb->dev = dev;
 	skb->sk  = sk;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 670639b..66ddcb6 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -737,6 +737,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		/* no remote port */
 	}
 
+	ipc.sockc.tsflags = sk->sk_tsflags;
 	ipc.addr = inet->inet_saddr;
 	ipc.opt = NULL;
 	ipc.oif = sk->sk_bound_dev_if;
@@ -744,8 +745,6 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc.ttl = 0;
 	ipc.tos = -1;
 
-	sock_tx_timestamp(sk, &ipc.tx_flags);
-
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sk, msg, &ipc, false);
 		if (unlikely(err)) {
@@ -768,6 +767,8 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		rcu_read_unlock();
 	}
 
+	sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
+
 	saddr = ipc.addr;
 	ipc.addr = faddr = daddr;
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 088ce66..438f50c 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -339,8 +339,8 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb)
 
 static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 			   struct msghdr *msg, size_t length,
-			   struct rtable **rtp,
-			   unsigned int flags)
+			   struct rtable **rtp, unsigned int flags,
+			   const struct sockcm_cookie *sockc)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct net *net = sock_net(sk);
@@ -379,7 +379,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 
 	skb->ip_summed = CHECKSUM_NONE;
 
-	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
+	sock_tx_timestamp(sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags);
 
 	skb->transport_header = skb->network_header;
 	err = -EFAULT;
@@ -540,6 +540,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		daddr = inet->inet_daddr;
 	}
 
+	ipc.sockc.tsflags = sk->sk_tsflags;
 	ipc.addr = inet->inet_saddr;
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;
@@ -638,10 +639,10 @@ back_from_confirm:
 
 	if (inet->hdrincl)
 		err = raw_send_hdrinc(sk, &fl4, msg, len,
-				      &rt, msg->msg_flags);
+				      &rt, msg->msg_flags, &ipc.sockc);
 
 	 else {
-		sock_tx_timestamp(sk, &ipc.tx_flags);
+		sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
 
 		if (!ipc.addr)
 			ipc.addr = fl4.daddr;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index ce3c9eb..4d73858 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -428,13 +428,13 @@ void tcp_init_sock(struct sock *sk)
 }
 EXPORT_SYMBOL(tcp_init_sock);
 
-static void tcp_tx_timestamp(struct sock *sk, struct sk_buff *skb)
+static void tcp_tx_timestamp(struct sock *sk, u16 tsflags, struct sk_buff *skb)
 {
-	if (sk->sk_tsflags) {
+	if (sk->sk_tsflags || tsflags) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 		struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
 
-		sock_tx_timestamp(sk, &shinfo->tx_flags);
+		sock_tx_timestamp(sk, tsflags, &shinfo->tx_flags);
 		if (shinfo->tx_flags & SKBTX_ANY_TSTAMP)
 			shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
 		tcb->txstamp_ack = !!(shinfo->tx_flags & SKBTX_ACK_TSTAMP);
@@ -959,7 +959,7 @@ new_segment:
 		offset += copy;
 		size -= copy;
 		if (!size) {
-			tcp_tx_timestamp(sk, skb);
+			tcp_tx_timestamp(sk, sk->sk_tsflags, skb);
 			goto out;
 		}
 
@@ -1079,6 +1079,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
+	struct sockcm_cookie sockc;
 	int flags, err, copied = 0;
 	int mss_now = 0, size_goal, copied_syn = 0;
 	bool sg;
@@ -1121,6 +1122,15 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 		/* 'common' sending to sendq */
 	}
 
+	sockc.tsflags = sk->sk_tsflags;
+	if (msg->msg_controllen) {
+		err = sock_cmsg_send(sk, msg, &sockc);
+		if (unlikely(err)) {
+			err = -EINVAL;
+			goto out_err;
+		}
+	}
+
 	/* This should be in poll */
 	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
@@ -1239,7 +1249,7 @@ new_segment:
 
 		copied += copy;
 		if (!msg_data_left(msg)) {
-			tcp_tx_timestamp(sk, skb);
+			tcp_tx_timestamp(sk, sockc.tsflags, skb);
 			goto out;
 		}
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index bccb4e1..45ff590 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1027,12 +1027,11 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		 */
 		connected = 1;
 	}
-	ipc.addr = inet->inet_saddr;
 
+	ipc.sockc.tsflags = sk->sk_tsflags;
+	ipc.addr = inet->inet_saddr;
 	ipc.oif = sk->sk_bound_dev_if;
 
-	sock_tx_timestamp(sk, &ipc.tx_flags);
-
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6);
 		if (unlikely(err)) {
@@ -1059,6 +1058,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	saddr = ipc.addr;
 	ipc.addr = faddr = daddr;
 
+	sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
+
 	if (ipc.opt && ipc.opt->opt.srr) {
 		if (!daddr)
 			return -EINVAL;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 0a37ddc..6b573eb 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -400,6 +400,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	struct icmp6hdr tmp_hdr;
 	struct flowi6 fl6;
 	struct icmpv6_msg msg;
+	struct sockcm_cookie sockc_unused = {0};
 	int iif = 0;
 	int addr_type = 0;
 	int len;
@@ -527,7 +528,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 			      len + sizeof(struct icmp6hdr),
 			      sizeof(struct icmp6hdr), hlimit,
 			      np->tclass, NULL, &fl6, (struct rt6_info *)dst,
-			      MSG_DONTWAIT, np->dontfrag);
+			      MSG_DONTWAIT, np->dontfrag, &sockc_unused);
 	if (err) {
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
@@ -566,6 +567,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	int hlimit;
 	u8 tclass;
 	u32 mark = IP6_REPLY_MARK(net, skb->mark);
+	struct sockcm_cookie sockc_unused = {0};
 
 	saddr = &ipv6_hdr(skb)->daddr;
 
@@ -617,7 +619,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr),
 				sizeof(struct icmp6hdr), hlimit, tclass, NULL, &fl6,
 				(struct rt6_info *)dst, MSG_DONTWAIT,
-				np->dontfrag);
+				np->dontfrag, &sockc_unused);
 
 	if (err) {
 		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 9428345..612f3d1 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1258,7 +1258,8 @@ static int __ip6_append_data(struct sock *sk,
 			     int getfrag(void *from, char *to, int offset,
 					 int len, int odd, struct sk_buff *skb),
 			     void *from, int length, int transhdrlen,
-			     unsigned int flags, int dontfrag)
+			     unsigned int flags, int dontfrag,
+			     const struct sockcm_cookie *sockc)
 {
 	struct sk_buff *skb, *skb_prev = NULL;
 	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
@@ -1329,7 +1330,7 @@ emsgsize:
 		csummode = CHECKSUM_PARTIAL;
 
 	if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) {
-		sock_tx_timestamp(sk, &tx_flags);
+		sock_tx_timestamp(sk, sockc->tsflags, &tx_flags);
 		if (tx_flags & SKBTX_ANY_SW_TSTAMP &&
 		    sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
 			tskey = sk->sk_tskey++;
@@ -1565,7 +1566,8 @@ int ip6_append_data(struct sock *sk,
 				int odd, struct sk_buff *skb),
 		    void *from, int length, int transhdrlen, int hlimit,
 		    int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6,
-		    struct rt6_info *rt, unsigned int flags, int dontfrag)
+		    struct rt6_info *rt, unsigned int flags, int dontfrag,
+		    const struct sockcm_cookie *sockc)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
@@ -1593,7 +1595,8 @@ int ip6_append_data(struct sock *sk,
 
 	return __ip6_append_data(sk, fl6, &sk->sk_write_queue, &inet->cork.base,
 				 &np->cork, sk_page_frag(sk), getfrag,
-				 from, length, transhdrlen, flags, dontfrag);
+				 from, length, transhdrlen, flags, dontfrag,
+				 sockc);
 }
 EXPORT_SYMBOL_GPL(ip6_append_data);
 
@@ -1752,7 +1755,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 			     int hlimit, int tclass,
 			     struct ipv6_txoptions *opt, struct flowi6 *fl6,
 			     struct rt6_info *rt, unsigned int flags,
-			     int dontfrag)
+			     int dontfrag, const struct sockcm_cookie *sockc)
 {
 	struct inet_cork_full cork;
 	struct inet6_cork v6_cork;
@@ -1779,7 +1782,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 	err = __ip6_append_data(sk, fl6, &queue, &cork.base, &v6_cork,
 				&current->task_frag, getfrag, from,
 				length + exthdrlen, transhdrlen + exthdrlen,
-				flags, dontfrag);
+				flags, dontfrag, sockc);
 	if (err) {
 		__ip6_flush_pending_frames(sk, &queue, &cork, &v6_cork);
 		return ERR_PTR(err);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index c382db7..da1cff7 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -62,6 +62,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	struct dst_entry *dst;
 	struct rt6_info *rt;
 	struct pingfakehdr pfh;
+	struct sockcm_cookie junk = {0};
 
 	pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
 
@@ -144,7 +145,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	err = ip6_append_data(sk, ping_getfrag, &pfh, len,
 			      0, hlimit,
 			      np->tclass, NULL, &fl6, rt,
-			      MSG_DONTWAIT, np->dontfrag);
+			      MSG_DONTWAIT, np->dontfrag, &junk);
 
 	if (err) {
 		ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev,
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index f175ec0..b07ce21 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -822,8 +822,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (fl6.flowi6_oif == 0)
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 
-	sockc.tsflags = 0;
-
+	sockc.tsflags = sk->sk_tsflags;
 	if (msg->msg_controllen) {
 		opt = &opt_space;
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
@@ -901,7 +900,7 @@ back_from_confirm:
 		lock_sock(sk);
 		err = ip6_append_data(sk, raw6_getfrag, &rfv,
 			len, 0, hlimit, tclass, opt, &fl6, (struct rt6_info *)dst,
-			msg->msg_flags, dontfrag);
+			msg->msg_flags, dontfrag, &sockc);
 
 		if (err)
 			ip6_flush_pending_frames(sk);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 8371a51..fef21c4 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1248,7 +1248,7 @@ do_udp_sendmsg:
 		fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
 
 	fl6.flowi6_mark = sk->sk_mark;
-	sockc.tsflags = 0;
+	sockc.tsflags = sk->sk_tsflags;
 
 	if (msg->msg_controllen) {
 		opt = &opt_space;
@@ -1324,7 +1324,7 @@ back_from_confirm:
 		skb = ip6_make_skb(sk, getfrag, msg, ulen,
 				   sizeof(struct udphdr), hlimit, tclass, opt,
 				   &fl6, (struct rt6_info *)dst,
-				   msg->msg_flags, dontfrag);
+				   msg->msg_flags, dontfrag, &sockc);
 		err = PTR_ERR(skb);
 		if (!IS_ERR_OR_NULL(skb))
 			err = udp_v6_send_skb(skb, &fl6);
@@ -1351,7 +1351,8 @@ do_append_data:
 	err = ip6_append_data(sk, getfrag, msg, ulen,
 		sizeof(struct udphdr), hlimit, tclass, opt, &fl6,
 		(struct rt6_info *)dst,
-		corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag);
+		corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag,
+		&sockc);
 	if (err)
 		udp_v6_flush_pending_frames(sk);
 	else if (!corkreq)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 1ecfa71..0007e23 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1837,6 +1837,7 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg,
 	DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name);
 	struct sk_buff *skb = NULL;
 	struct net_device *dev;
+	struct sockcm_cookie sockc;
 	__be16 proto = 0;
 	int err;
 	int extra_len = 0;
@@ -1925,12 +1926,21 @@ retry:
 		goto out_unlock;
 	}
 
+	sockc.tsflags = 0;
+	if (msg->msg_controllen) {
+		err = sock_cmsg_send(sk, msg, &sockc);
+		if (unlikely(err)) {
+			err = -EINVAL;
+			goto out_unlock;
+		}
+	}
+
 	skb->protocol = proto;
 	skb->dev = dev;
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
 
-	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
+	sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags);
 
 	if (unlikely(extra_len == 4))
 		skb->no_fcs = 1;
@@ -2486,7 +2496,8 @@ static int packet_snd_vnet_gso(struct sk_buff *skb,
 
 static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		void *frame, struct net_device *dev, void *data, int tp_len,
-		__be16 proto, unsigned char *addr, int hlen, int copylen)
+		__be16 proto, unsigned char *addr, int hlen, int copylen,
+		const struct sockcm_cookie *sockc)
 {
 	union tpacket_uhdr ph;
 	int to_write, offset, len, nr_frags, len_max;
@@ -2500,7 +2511,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb->dev = dev;
 	skb->priority = po->sk.sk_priority;
 	skb->mark = po->sk.sk_mark;
-	sock_tx_timestamp(&po->sk, &skb_shinfo(skb)->tx_flags);
+	sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags);
 	skb_shinfo(skb)->destructor_arg = ph.raw;
 
 	skb_reserve(skb, hlen);
@@ -2624,6 +2635,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	struct sk_buff *skb;
 	struct net_device *dev;
 	struct virtio_net_hdr *vnet_hdr = NULL;
+	struct sockcm_cookie sockc;
 	__be16 proto;
 	int err, reserve = 0;
 	void *ph;
@@ -2655,6 +2667,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
 	}
 
+	sockc.tsflags = 0;
+	if (msg->msg_controllen) {
+		err = sock_cmsg_send(&po->sk, msg, &sockc);
+		if (unlikely(err))
+			goto out;
+	}
+
 	err = -ENXIO;
 	if (unlikely(dev == NULL))
 		goto out;
@@ -2712,7 +2731,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 			goto out_status;
 		}
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, data, tp_len, proto,
-					  addr, hlen, copylen);
+					  addr, hlen, copylen, &sockc);
 		if (likely(tp_len >= 0) &&
 		    tp_len > dev->mtu + reserve &&
 		    !po->has_vnet_hdr &&
@@ -2851,6 +2870,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_unlock;
 
+	sockc.tsflags = 0;
 	sockc.mark = sk->sk_mark;
 	if (msg->msg_controllen) {
 		err = sock_cmsg_send(sk, msg, &sockc);
@@ -2908,7 +2928,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		goto out_free;
 	}
 
-	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
+	sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags);
 
 	if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) &&
 	    !packet_extra_vlan_len_allowed(dev, skb)) {
diff --git a/net/socket.c b/net/socket.c
index 5f77a8e..979d314 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -587,20 +587,20 @@ void sock_release(struct socket *sock)
 }
 EXPORT_SYMBOL(sock_release);
 
-void __sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags)
+void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags)
 {
 	u8 flags = *tx_flags;
 
-	if (sk->sk_tsflags & SOF_TIMESTAMPING_TX_HARDWARE)
+	if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE)
 		flags |= SKBTX_HW_TSTAMP;
 
-	if (sk->sk_tsflags & SOF_TIMESTAMPING_TX_SOFTWARE)
+	if (tsflags & SOF_TIMESTAMPING_TX_SOFTWARE)
 		flags |= SKBTX_SW_TSTAMP;
 
-	if (sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED)
+	if (tsflags & SOF_TIMESTAMPING_TX_SCHED)
 		flags |= SKBTX_SCHED_TSTAMP;
 
-	if (sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)
+	if (tsflags & SOF_TIMESTAMPING_TX_ACK)
 		flags |= SKBTX_ACK_TSTAMP;
 
 	*tx_flags = flags;
-- 
2.8.0.rc3.226.g39d4020

Re: [PATCH v2 net-next 2/8] tcp: accept SOF_TIMESTAMPING_OPT_ID for passive TFO

[Eric Dumazet]

On Fri, 2016-04-01 at 11:04 -0400, Soheil Hassas Yeganeh wrote:
> From: Soheil Hassas Yeganeh <soheil@google.com>
> 
> SOF_TIMESTAMPING_OPT_ID is set to get data-independent IDs
> to associate timestamps with send calls. For TCP connections,
> tp->snd_una is used as the starting point to calculate
> relative IDs.
> 
> This socket option will fail if set before the handshake on a
> passive TCP fast open connection with data in SYN or SYN/ACK,
> since setsockopt requires the connection to be in the
> ESTABLISHED state.
> 
> To address these, instead of limiting the option to the
> ESTABLISHED state, accept the SOF_TIMESTAMPING_OPT_ID option as
> long as the connection is not in LISTEN or CLOSE states.


Acked-by: Eric Dumazet <edumazet@google.com>

Re: [PATCH v2 net-next 3/8] tcp: use one bit in TCP_SKB_CB to mark ACK timestamps

[Eric Dumazet]

On Fri, 2016-04-01 at 11:04 -0400, Soheil Hassas Yeganeh wrote:
> From: Soheil Hassas Yeganeh <soheil@google.com>
> 
> Currently, to avoid a cache line miss for accessing skb_shinfo,
> tcp_ack_tstamp skips socket that do not have
> SOF_TIMESTAMPING_TX_ACK bit set in sk_tsflags. This is
> implemented based on an implicit assumption that the
> SOF_TIMESTAMPING_TX_ACK is set via socket options for the
> duration that ACK timestamps are needed.
> 
> To implement per-write timestamps, this check should be
> removed and replaced with a per-packet alternative that
> quickly skips packets missing ACK timestamps marks without
> a cache-line miss.
> 
> To enable per-packet marking without a cache line miss, use
> one bit in TCP_SKB_CB to mark a whether a SKB might need a
> ack tx timestamp or not. Further checks in tcp_ack_tstamp are not
> modified and work as before.

Acked-by: Eric Dumazet <edumazet@google.com>

Re: [PATCH v2 net-next 0/8] add TX timestamping via cmsg

[David Miller]

From: Soheil Hassas Yeganeh <soheil.kdev@gmail.com>
Date: Fri,  1 Apr 2016 11:04:32 -0400

> From: Soheil Hassas Yeganeh <soheil@google.com>
> 
> This patch series aim at enabling TX timestamping via cmsg.
> 
> Currently, to occasionally sample TX timestamping on a socket,
> applications need to call setsockopt twice: first for enabling
> timestamps and then for disabling them. This is an unnecessary
> overhead. With cmsg, in contrast, applications can sample TX
> timestamps per sendmsg().
> 
> This patch series adds the code for processing SO_TIMESTAMPING
> for cmsg's of the SOL_SOCKET level, and adds the glue code for
> TCP, UDP, and RAW for both IPv4 and IPv6. This implementation
> supports overriding timestamp generation flags (i.e.,
> SOF_TIMESTAMPING_TX_*) but not timestamp reporting flags.
> Applications must still enable timestamp reporting via
> setsockopt to receive timestamps.
> 
> This series does not change existing timestamping behavior for
> applications that are using socket options.
> 
> I will follow up with another patch to enable timestamping for
> active TFO (client-side TCP Fast Open) and also setting packet
> mark via cmsgs.
 ...
> Changes in v2:
> 	- Replace u32 with __u32 in the documentation.

Series applied, thanks.

Re: [PATCH v2 net-next 0/8] add TX timestamping via cmsg

[David Miller]

From: David Miller <davem@davemloft.net>
Date: Sat, 02 Apr 2016 21:19:42 -0400 (EDT)

> Series applied, thanks.

I had to revert, this breaks the build:

net/l2tp/l2tp_ip6.c: In function ‘l2tp_ip6_sendmsg’:
net/l2tp/l2tp_ip6.c:565:9: error: too few arguments to function ‘ip6_datagram_send_ctl’
   err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
         ^
In file included from net/l2tp/l2tp_ip6.c:33:0:
include/net/transp_v6.h:43:5: note: declared here
 int ip6_datagram_send_ctl(struct net *net, struct sock *sk, struct msghdr *msg,
     ^
net/l2tp/l2tp_ip6.c:625:8: error: too few arguments to function ‘ip6_append_data’
  err = ip6_append_data(sk, ip_generic_getfrag, msg,
        ^
In file included from include/net/inetpeer.h:15:0,
                 from include/net/route.h:28,
                 from include/net/ip.h:31,
                 from net/l2tp/l2tp_ip6.c:23:
include/net/ipv6.h:865:5: note: declared here
 int ip6_append_data(struct sock *sk,
     ^

Re: [PATCH v2 net-next 0/8] add TX timestamping via cmsg

[Soheil Hassas Yeganeh]

On Sat, Apr 2, 2016 at 9:27 PM, David Miller <davem@davemloft.net> wrote:
> From: David Miller <davem@davemloft.net>
> Date: Sat, 02 Apr 2016 21:19:42 -0400 (EDT)
>
>> Series applied, thanks.
>
> I had to revert, this breaks the build:
>
> net/l2tp/l2tp_ip6.c: In function ‘l2tp_ip6_sendmsg’:
> net/l2tp/l2tp_ip6.c:565:9: error: too few arguments to function ‘ip6_datagram_send_ctl’
>    err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
>          ^
> In file included from net/l2tp/l2tp_ip6.c:33:0:
> include/net/transp_v6.h:43:5: note: declared here
>  int ip6_datagram_send_ctl(struct net *net, struct sock *sk, struct msghdr *msg,
>      ^
> net/l2tp/l2tp_ip6.c:625:8: error: too few arguments to function ‘ip6_append_data’
>   err = ip6_append_data(sk, ip_generic_getfrag, msg,
>         ^
> In file included from include/net/inetpeer.h:15:0,
>                  from include/net/route.h:28,
>                  from include/net/ip.h:31,
>                  from net/l2tp/l2tp_ip6.c:23:
> include/net/ipv6.h:865:5: note: declared here
>  int ip6_append_data(struct sock *sk,
>      ^

I'm really sorry about this. CONFIG_L2TP was no enabled in my config.
I'll fix the patch, and will mail v3.

Thanks,
Soheil