sock: enable timestamping using control messages

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>
Signed-off-by: David S. Miller <davem@davemloft.net>
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 @@
 	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 @@
 			      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 @@
 	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 @@
 	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 9428345d..612f3d1 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1258,7 +1258,8 @@
 			     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 @@
 		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 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 @@
 
 	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 @@
 			     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 @@
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 		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 2a787af..b772a76 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1248,7 +1248,7 @@
 		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 @@
 		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 @@
 	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)