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>

Documentation/networking/timestamping.rst

@@ -194,6 +194,20 @@ SOF_TIMESTAMPING_OPT_ID:
   among all possibly concurrently outstanding timestamp requests for
   that socket.
 
+  The process can optionally override the default generated ID, by
+  passing a specific ID with control message SCM_TS_OPT_ID (not
+  supported for TCP sockets)::
+
+    struct msghdr *msg;
+    ...
+    cmsg			 = CMSG_FIRSTHDR(msg);
+    cmsg->cmsg_level		 = SOL_SOCKET;
+    cmsg->cmsg_type		 = SCM_TS_OPT_ID;
+    cmsg->cmsg_len		 = CMSG_LEN(sizeof(__u32));
+    *((__u32 *) CMSG_DATA(cmsg)) = opt_id;
+    err = sendmsg(fd, msg, 0);
+
+
 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

arch/alpha/include/uapi/asm/socket.h

@@ -146,6 +146,8 @@
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
 #define SO_DEVMEM_DONTNEED	80
 
+#define SCM_TS_OPT_ID		81
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

arch/mips/include/uapi/asm/socket.h

@@ -157,6 +157,8 @@
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
 #define SO_DEVMEM_DONTNEED	80
 
+#define SCM_TS_OPT_ID		81
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

arch/parisc/include/uapi/asm/socket.h

@@ -138,6 +138,8 @@
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
 #define SO_DEVMEM_DONTNEED	80
 
+#define SCM_TS_OPT_ID		0x404C
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

arch/sparc/include/uapi/asm/socket.h

@@ -139,6 +139,8 @@
 #define SCM_DEVMEM_DMABUF        SO_DEVMEM_DMABUF
 #define SO_DEVMEM_DONTNEED       0x0059
 
+#define SCM_TS_OPT_ID            0x005a
+
 #if !defined(__KERNEL__)
 
 

include/net/inet_sock.h

@@ -174,6 +174,7 @@ struct inet_cork {
 	__s16			tos;
 	char			priority;
 	__u16			gso_size;
+	u32			ts_opt_id;
 	u64			transmit_time;
 	u32			mark;
 };
@@ -241,7 +242,8 @@ struct inet_sock {
 	struct inet_cork_full	cork;
 };
 
-#define IPCORK_OPT	1	/* ip-options has been held in ipcork.opt */
+#define IPCORK_OPT		1	/* ip-options has been held in ipcork.opt */
+#define IPCORK_TS_OPT_ID	2	/* ts_opt_id field is valid, overriding sk_tskey */
 
 enum {
 	INET_FLAGS_PKTINFO	= 0,

include/net/sock.h

@@ -954,6 +954,12 @@ enum sock_flags {
 };
 
 #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
+/*
+ * The highest bit of sk_tsflags is reserved for kernel-internal
+ * SOCKCM_FLAG_TS_OPT_ID. There is a check in core/sock.c to control that
+ * SOF_TIMESTAMPING* values do not reach this reserved area
+ */
+#define SOCKCM_FLAG_TS_OPT_ID	BIT(31)
 
 static inline void sock_copy_flags(struct sock *nsk, const struct sock *osk)
 {
@@ -1796,6 +1802,7 @@ struct sockcm_cookie {
 	u64 transmit_time;
 	u32 mark;
 	u32 tsflags;
+	u32 ts_opt_id;
 };
 
 static inline void sockcm_init(struct sockcm_cookie *sockc,

include/uapi/asm-generic/socket.h

@@ -141,6 +141,8 @@
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
 #define SO_DEVMEM_DONTNEED	80
 
+#define SCM_TS_OPT_ID		81
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))

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:

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;
 }

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 @@ static int __ip6_append_data(struct sock *sk,
 			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.