Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Martin KaFai Lau says:

====================
pull-request: bpf-next 2025-02-20

We've added 19 non-merge commits during the last 8 day(s) which contain
a total of 35 files changed, 1126 insertions(+), 53 deletions(-).

The main changes are:

1) Add TCP_RTO_MAX_MS support to bpf_set/getsockopt, from Jason Xing

2) Add network TX timestamping support to BPF sock_ops, from Jason Xing

3) Add TX metadata Launch Time support, from Song Yoong Siang

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next:
  igc: Add launch time support to XDP ZC
  igc: Refactor empty frame insertion for launch time support
  net: stmmac: Add launch time support to XDP ZC
  selftests/bpf: Add launch time request to xdp_hw_metadata
  xsk: Add launch time hardware offload support to XDP Tx metadata
  selftests/bpf: Add simple bpf tests in the tx path for timestamping feature
  bpf: Support selective sampling for bpf timestamping
  bpf: Add BPF_SOCK_OPS_TSTAMP_SENDMSG_CB callback
  bpf: Add BPF_SOCK_OPS_TSTAMP_ACK_CB callback
  bpf: Add BPF_SOCK_OPS_TSTAMP_SND_HW_CB callback
  bpf: Add BPF_SOCK_OPS_TSTAMP_SND_SW_CB callback
  bpf: Add BPF_SOCK_OPS_TSTAMP_SCHED_CB callback
  net-timestamp: Prepare for isolating two modes of SO_TIMESTAMPING
  bpf: Disable unsafe helpers in TX timestamping callbacks
  bpf: Prevent unsafe access to the sock fields in the BPF timestamping callback
  bpf: Prepare the sock_ops ctx and call bpf prog for TX timestamping
  bpf: Add networking timestamping support to bpf_get/setsockopt()
  selftests/bpf: Add rto max for bpf_setsockopt test
  bpf: Support TCP_RTO_MAX_MS for bpf_setsockopt
====================

Link: https://patch.msgid.link/20250221022104.386462-1-martin.lau@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

9 files changed, 79 insertions, 5 deletions

diff --git a/include/linux/filter.h b/include/linux/filter.h
index a3ea46281595..d36d5d5180b1 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1508,6 +1508,7 @@ struct bpf_sock_ops_kern {
 	void	*skb_data_end;
 	u8	op;
 	u8	is_fullsock;
+	u8	is_locked_tcp_sock;
 	u8	remaining_opt_len;
 	u64	temp;			/* temp and everything after is not
 					 * initialized to 0 before calling
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index bb2b751d274a..0b4f1889500d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -470,7 +470,7 @@ struct skb_shared_hwtstamps {
 /* Definitions for tx_flags in struct skb_shared_info */
 enum {
 	/* generate hardware time stamp */
-	SKBTX_HW_TSTAMP = 1 << 0,
+	SKBTX_HW_TSTAMP_NOBPF = 1 << 0,
 
 	/* generate software time stamp when queueing packet to NIC */
 	SKBTX_SW_TSTAMP = 1 << 1,
@@ -489,10 +489,16 @@ 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_HW_TSTAMP		(SKBTX_HW_TSTAMP_NOBPF | SKBTX_BPF)
+
 #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)
@@ -4564,7 +4570,7 @@ void skb_tstamp_tx(struct sk_buff *orig_skb,
 static inline void skb_tx_timestamp(struct sk_buff *skb)
 {
 	skb_clone_tx_timestamp(skb);
-	if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP)
+	if (skb_shinfo(skb)->tx_flags & (SKBTX_SW_TSTAMP | SKBTX_BPF))
 		skb_tstamp_tx(skb, NULL);
 }
 
diff --git a/include/net/sock.h b/include/net/sock.h
index edbb870e3f86..efc031163c33 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -303,6 +303,7 @@ struct sk_filter;
   *	@sk_stamp: time stamp of last packet received
   *	@sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only
   *	@sk_tsflags: SO_TIMESTAMPING flags
+  *	@sk_bpf_cb_flags: used in bpf_setsockopt()
   *	@sk_use_task_frag: allow sk_page_frag() to use current->task_frag.
   *			   Sockets that can be used under memory reclaim should
   *			   set this to false.
@@ -525,6 +526,8 @@ struct sock {
 	u8			sk_txtime_deadline_mode : 1,
 				sk_txtime_report_errors : 1,
 				sk_txtime_unused : 6;
+#define SK_BPF_CB_FLAG_TEST(SK, FLAG) ((SK)->sk_bpf_cb_flags & (FLAG))
+	u8			sk_bpf_cb_flags;
 
 	void			*sk_user_data;
 #ifdef CONFIG_SECURITY
@@ -2909,6 +2912,13 @@ int sock_set_timestamping(struct sock *sk, int optname,
 			  struct so_timestamping timestamping);
 
 void sock_enable_timestamps(struct sock *sk);
+#if defined(CONFIG_CGROUP_BPF)
+void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op);
+#else
+static inline void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op)
+{
+}
+#endif
 void sock_no_linger(struct sock *sk);
 void sock_set_keepalive(struct sock *sk);
 void sock_set_priority(struct sock *sk, u32 priority);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index ced32b924a9c..9745c7f18170 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -978,10 +978,12 @@ struct tcp_skb_cb {
 
 	__u8		sacked;		/* State flags for SACK.	*/
 	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
-	__u8		txstamp_ack:1,	/* Record TX timestamp for ack? */
+#define TSTAMP_ACK_SK	0x1
+#define TSTAMP_ACK_BPF	0x2
+	__u8		txstamp_ack:2,	/* Record TX timestamp for ack? */
 			eor:1,		/* Is skb MSG_EOR marked? */
 			has_rxtstamp:1,	/* SKB has a RX timestamp	*/
-			unused:5;
+			unused:4;
 	__u32		ack_seq;	/* Sequence number ACK'd	*/
 	union {
 		struct {
@@ -2671,6 +2673,7 @@ static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
 	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
 	if (sk_fullsock(sk)) {
 		sock_ops.is_fullsock = 1;
+		sock_ops.is_locked_tcp_sock = 1;
 		sock_owned_by_me(sk);
 	}
 
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index bfe625b55d55..a58ae7589d12 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -110,11 +110,16 @@ struct xdp_sock {
  *     indicates position where checksumming should start.
  *     csum_offset indicates position where checksum should be stored.
  *
+ * void (*tmo_request_launch_time)(u64 launch_time, void *priv)
+ *     Called when AF_XDP frame requested launch time HW offload support.
+ *     launch_time indicates the PTP time at which the device can schedule the
+ *     packet for transmission.
  */
 struct xsk_tx_metadata_ops {
 	void	(*tmo_request_timestamp)(void *priv);
 	u64	(*tmo_fill_timestamp)(void *priv);
 	void	(*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv);
+	void	(*tmo_request_launch_time)(u64 launch_time, void *priv);
 };
 
 #ifdef CONFIG_XDP_SOCKETS
@@ -162,6 +167,11 @@ static inline void xsk_tx_metadata_request(const struct xsk_tx_metadata *meta,
 	if (!meta)
 		return;
 
+	if (ops->tmo_request_launch_time)
+		if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME)
+			ops->tmo_request_launch_time(meta->request.launch_time,
+						     priv);
+
 	if (ops->tmo_request_timestamp)
 		if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)
 			ops->tmo_request_timestamp(priv);
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 15086dcf51d8..513c8e9704f6 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -216,6 +216,7 @@ xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr)
 #define XDP_TXMD_FLAGS_VALID ( \
 		XDP_TXMD_FLAGS_TIMESTAMP | \
 		XDP_TXMD_FLAGS_CHECKSUM | \
+		XDP_TXMD_FLAGS_LAUNCH_TIME | \
 	0)
 
 static inline bool
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2acf9b336371..defa5bb881f4 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6913,6 +6913,12 @@ enum {
 	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x7F,
 };
 
+enum {
+	SK_BPF_CB_TX_TIMESTAMPING	= 1<<0,
+	SK_BPF_CB_MASK			= (SK_BPF_CB_TX_TIMESTAMPING - 1) |
+					   SK_BPF_CB_TX_TIMESTAMPING
+};
+
 /* List of known BPF sock_ops operators.
  * New entries can only be added at the end
  */
@@ -7025,6 +7031,29 @@ 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.
+					 */
+	BPF_SOCK_OPS_TSTAMP_SND_SW_CB,	/* Called when skb is about to send
+					 * to the nic when SK_BPF_CB_TX_TIMESTAMPING
+					 * feature is on.
+					 */
+	BPF_SOCK_OPS_TSTAMP_SND_HW_CB,	/* Called in hardware phase when
+					 * SK_BPF_CB_TX_TIMESTAMPING feature
+					 * is on.
+					 */
+	BPF_SOCK_OPS_TSTAMP_ACK_CB,	/* Called when all the skbs in the
+					 * same sendmsg call are acked
+					 * when SK_BPF_CB_TX_TIMESTAMPING
+					 * feature is on.
+					 */
+	BPF_SOCK_OPS_TSTAMP_SENDMSG_CB,	/* Called when every sendmsg syscall
+					 * is triggered. It's used to correlate
+					 * sendmsg timestamp with corresponding
+					 * tskey.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
@@ -7091,6 +7120,7 @@ enum {
 	TCP_BPF_SYN_IP		= 1006, /* Copy the IP[46] and TCP header */
 	TCP_BPF_SYN_MAC         = 1007, /* Copy the MAC, IP[46], and TCP header */
 	TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
+	SK_BPF_CB_FLAGS		= 1009, /* Get or set sock ops flags in socket */
 };
 
 enum {
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index 42ec5ddaab8d..42869770776e 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -127,6 +127,12 @@ struct xdp_options {
  */
 #define XDP_TXMD_FLAGS_CHECKSUM			(1 << 1)
 
+/* Request launch time hardware offload. The device will schedule the packet for
+ * transmission at a pre-determined time called launch time. The value of
+ * launch time is communicated via launch_time field of struct xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_LAUNCH_TIME		(1 << 2)
+
 /* AF_XDP offloads request. 'request' union member is consumed by the driver
  * when the packet is being transmitted. 'completion' union member is
  * filled by the driver when the transmit completion arrives.
@@ -142,6 +148,10 @@ struct xsk_tx_metadata {
 			__u16 csum_start;
 			/* Offset from csum_start where checksum should be stored. */
 			__u16 csum_offset;
+
+			/* XDP_TXMD_FLAGS_LAUNCH_TIME */
+			/* Launch time in nanosecond against the PTP HW Clock */
+			__u64 launch_time;
 		} request;
 
 		struct {
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 4e82f3871473..7600bf62dbdf 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -59,10 +59,13 @@ enum netdev_xdp_rx_metadata {
  *   by the driver.
  * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the
  *   driver.
+ * @NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO: Launch time HW offload is supported
+ *   by the driver.
  */
 enum netdev_xsk_flags {
 	NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1,
 	NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
+	NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO = 4,
 };
 
 enum netdev_queue_type {