net_tstamp: add SCM_TS_OPT_ID to provide OPT_ID in control message

SOF_TIMESTAMPING_OPT_ID socket option flag gives a way to correlate TX
timestamps and packets sent via socket. Unfortunately, there is no way
to reliably predict socket timestamp ID value in case of error returned
by sendmsg. For UDP sockets it's impossible because of lockless
nature of UDP transmit, several threads may send packets in parallel. In
case of RAW sockets MSG_MORE option makes things complicated. More
details are in the conversation [1].
This patch adds new control message type to give user-space
software an opportunity to control the mapping between packets and
values by providing ID with each sendmsg for UDP sockets.
The documentation is also added in this patch.

[1] https://lore.kernel.org/netdev/CALCETrU0jB+kg0mhV6A8mrHfTE1D1pr1SD_B9Eaa9aDPfgHdtA@mail.gmail.com/

Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Link: https://patch.msgid.link/20241001125716.2832769-2-vadfed@meta.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 41 insertions, 11 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 039be95c40cf..846f494a17cf 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2899,6 +2899,8 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
 {
 	u32 tsflags;
 
+	BUILD_BUG_ON(SOF_TIMESTAMPING_LAST == (1 << 31));
+
 	switch (cmsg->cmsg_type) {
 	case SO_MARK:
 		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
@@ -2927,6 +2929,17 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
 			return -EINVAL;
 		sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg));
 		break;
+	case SCM_TS_OPT_ID:
+		if (sk_is_tcp(sk))
+			return -EINVAL;
+		tsflags = READ_ONCE(sk->sk_tsflags);
+		if (!(tsflags & SOF_TIMESTAMPING_OPT_ID))
+			return -EINVAL;
+		if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
+			return -EINVAL;
+		sockc->ts_opt_id = *(u32 *)CMSG_DATA(cmsg);
+		sockc->tsflags |= SOCKCM_FLAG_TS_OPT_ID;
+		break;
 	/* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */
 	case SCM_RIGHTS:
 	case SCM_CREDENTIALS:
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 49811c9281d4..0c7049f50369 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -973,7 +973,7 @@ static int __ip_append_data(struct sock *sk,
 	unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
 	int csummode = CHECKSUM_NONE;
 	struct rtable *rt = dst_rtable(cork->dst);
-	bool paged, hold_tskey, extra_uref = false;
+	bool paged, hold_tskey = false, extra_uref = false;
 	unsigned int wmem_alloc_delta = 0;
 	u32 tskey = 0;
 
@@ -1049,10 +1049,15 @@ static int __ip_append_data(struct sock *sk,
 
 	cork->length += length;
 
-	hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP &&
-		     READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID;
-	if (hold_tskey)
-		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+	if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
+	    READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) {
+		if (cork->flags & IPCORK_TS_OPT_ID) {
+			tskey = cork->ts_opt_id;
+		} else {
+			tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+			hold_tskey = true;
+		}
+	}
 
 	/* So, what's going on in the loop below?
 	 *
@@ -1327,6 +1332,10 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	cork->transmit_time = ipc->sockc.transmit_time;
 	cork->tx_flags = 0;
 	sock_tx_timestamp(sk, ipc->sockc.tsflags, &cork->tx_flags);
+	if (ipc->sockc.tsflags & SOCKCM_FLAG_TS_OPT_ID) {
+		cork->flags |= IPCORK_TS_OPT_ID;
+		cork->ts_opt_id = ipc->sockc.ts_opt_id;
+	}
 
 	return 0;
 }
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f26841f1490f..ff6bd8d85e9a 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1402,7 +1402,10 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 	cork->base.tx_flags = 0;
 	cork->base.mark = ipc6->sockc.mark;
 	sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags);
-
+	if (ipc6->sockc.tsflags & SOCKCM_FLAG_TS_OPT_ID) {
+		cork->base.flags |= IPCORK_TS_OPT_ID;
+		cork->base.ts_opt_id = ipc6->sockc.ts_opt_id;
+	}
 	cork->base.length = 0;
 	cork->base.transmit_time = ipc6->sockc.transmit_time;
 
@@ -1433,7 +1436,7 @@ static int __ip6_append_data(struct sock *sk,
 	bool zc = false;
 	u32 tskey = 0;
 	struct rt6_info *rt = dst_rt6_info(cork->dst);
-	bool paged, hold_tskey, extra_uref = false;
+	bool paged, hold_tskey = false, extra_uref = false;
 	struct ipv6_txoptions *opt = v6_cork->opt;
 	int csummode = CHECKSUM_NONE;
 	unsigned int maxnonfragsize, headersize;
@@ -1543,10 +1546,15 @@ emsgsize:
 			flags &= ~MSG_SPLICE_PAGES;
 	}
 
-	hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP &&
-		     READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID;
-	if (hold_tskey)
-		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+	if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
+	    READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) {
+		if (cork->flags & IPCORK_TS_OPT_ID) {
+			tskey = cork->ts_opt_id;
+		} else {
+			tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+			hold_tskey = true;
+		}
+	}
 
 	/*
 	 * Let's try using as much space as possible.