bpf: Add BPF_SOCK_OPS_TSTAMP_SCHED_CB callback

Support SCM_TSTAMP_SCHED case for bpf timestamping.

Add a new sock_ops callback, BPF_SOCK_OPS_TSTAMP_SCHED_CB. This
callback will occur at the same timestamping point as the user
space's SCM_TSTAMP_SCHED. The BPF program can use it to get the
same SCM_TSTAMP_SCHED timestamp without modifying the user-space
application.

A new SKBTX_BPF flag is added to mark skb_shinfo(skb)->tx_flags,
ensuring that the new BPF timestamping and the current user
space's SO_TIMESTAMPING do not interfere with each other.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250220072940.99994-7-kerneljasonxing@gmail.com

5 files changed, 37 insertions, 2 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index bb2b751d274a..52f6e033e704 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -489,10 +489,14 @@ enum {
 
 	/* generate software time stamp when entering packet scheduling */
 	SKBTX_SCHED_TSTAMP = 1 << 6,
+
+	/* used for bpf extension when a bpf program is loaded */
+	SKBTX_BPF = 1 << 7,
 };
 
 #define SKBTX_ANY_SW_TSTAMP	(SKBTX_SW_TSTAMP    | \
-				 SKBTX_SCHED_TSTAMP)
+				 SKBTX_SCHED_TSTAMP | \
+				 SKBTX_BPF)
 #define SKBTX_ANY_TSTAMP	(SKBTX_HW_TSTAMP | \
 				 SKBTX_HW_TSTAMP_USE_CYCLES | \
 				 SKBTX_ANY_SW_TSTAMP)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4e0632848440..bb62fe25b2d0 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7031,6 +7031,11 @@ enum {
 					 * by the kernel or the
 					 * earlier bpf-progs.
 					 */
+	BPF_SOCK_OPS_TSTAMP_SCHED_CB,	/* Called when skb is passing
+					 * through dev layer when
+					 * SK_BPF_CB_TX_TIMESTAMPING
+					 * feature is on.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
diff --git a/net/core/dev.c b/net/core/dev.c
index d5ab9a4b318e..436f2bdfb2d5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4501,7 +4501,8 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	skb_reset_mac_header(skb);
 	skb_assert_len(skb);
 
-	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP))
+	if (unlikely(skb_shinfo(skb)->tx_flags &
+		     (SKBTX_SCHED_TSTAMP | SKBTX_BPF)))
 		__skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED);
 
 	/* Disable soft irqs for various locks below. Also
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 341a3290e898..3206f7708974 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5556,6 +5556,23 @@ static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,
 	return false;
 }
 
+static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb,
+						  struct sock *sk,
+						  int tstype)
+{
+	int op;
+
+	switch (tstype) {
+	case SCM_TSTAMP_SCHED:
+		op = BPF_SOCK_OPS_TSTAMP_SCHED_CB;
+		break;
+	default:
+		return;
+	}
+
+	bpf_skops_tx_timestamping(sk, skb, op);
+}
+
 void __skb_tstamp_tx(struct sk_buff *orig_skb,
 		     const struct sk_buff *ack_skb,
 		     struct skb_shared_hwtstamps *hwtstamps,
@@ -5568,6 +5585,9 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 	if (!sk)
 		return;
 
+	if (skb_shinfo(orig_skb)->tx_flags & SKBTX_BPF)
+		skb_tstamp_tx_report_bpf_timestamping(orig_skb, sk, tstype);
+
 	if (!skb_tstamp_tx_report_so_timestamping(orig_skb, hwtstamps, tstype))
 		return;
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4e0632848440..bb62fe25b2d0 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7031,6 +7031,11 @@ enum {
 					 * by the kernel or the
 					 * earlier bpf-progs.
 					 */
+	BPF_SOCK_OPS_TSTAMP_SCHED_CB,	/* Called when skb is passing
+					 * through dev layer when
+					 * SK_BPF_CB_TX_TIMESTAMPING
+					 * feature is on.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect