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/ (local)

Signed-off-by: Vadim Fedorenko <redacted>
---
 Documentation/networking/timestamping.rst | 13 +++++++++++++
 arch/alpha/include/uapi/asm/socket.h      |  2 ++
 arch/mips/include/uapi/asm/socket.h       |  2 ++
 arch/parisc/include/uapi/asm/socket.h     |  2 ++
 arch/sparc/include/uapi/asm/socket.h      |  2 ++
 include/net/inet_sock.h                   |  4 +++-
 include/net/sock.h                        |  2 ++
 include/uapi/asm-generic/socket.h         |  2 ++
 include/uapi/linux/net_tstamp.h           |  7 +++++++
 net/core/sock.c                           |  9 +++++++++
 net/ipv4/ip_output.c                      | 18 +++++++++++++-----
 net/ipv6/ip6_output.c                     | 18 +++++++++++++-----
 12 files changed, 70 insertions(+), 11 deletions(-)

diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index a2c66b3d7f0f..1c38536350e7 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h

@@ -38,6 +38,13 @@ enum {
 				 SOF_TIMESTAMPING_LAST
 };
 
+/*
+ * The highest bit of sk_tsflags is reserved for kernel-internal
+ * SOCKCM_FLAG_TS_OPT_ID. This check is to control that SOF_TIMESTAMPING*
+ * values do not reach this reserved area
+ */
+static_assert(SOF_TIMESTAMPING_LAST != (1 << 31));

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index eea443b7f65e..bd2f6a699470 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) & SOCKCM_FLAG_TS_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?
 	 *

@@ -1325,8 +1330,11 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	cork->mark = ipc->sockc.mark;
 	cork->priority = ipc->priority;
 	cork->transmit_time = ipc->sockc.transmit_time;
+	cork->ts_opt_id = ipc->sockc.ts_opt_id;
 	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;