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>

Documentation/netlink/specs/netdev.yaml

@@ -70,6 +70,10 @@ definitions:
         name: tx-checksum
         doc:
           L3 checksum HW offload is supported by the driver.
+      -
+        name: tx-launch-time-fifo
+        doc:
+          Launch time HW offload is supported by the driver.
   -
     name: queue-type
     type: enum

Documentation/networking/xsk-tx-metadata.rst

@@ -50,6 +50,10 @@ The flags field enables the particular offload:
   checksum. ``csum_start`` specifies byte offset of where the checksumming
   should start and ``csum_offset`` specifies byte offset where the
   device should store the computed checksum.
+- ``XDP_TXMD_FLAGS_LAUNCH_TIME``: requests the device to schedule the
+  packet for transmission at a pre-determined time called launch time. The
+  value of launch time is indicated by ``launch_time`` field of
+  ``union xsk_tx_metadata``.
 
 Besides the flags above, in order to trigger the offloads, the first
 packet's ``struct xdp_desc`` descriptor should set ``XDP_TX_METADATA``
@@ -65,6 +69,63 @@ In this case, when running in ``XDK_COPY`` mode, the TX checksum
 is calculated on the CPU. Do not enable this option in production because
 it will negatively affect performance.
 
+Launch Time
+===========
+
+The value of the requested launch time should be based on the device's PTP
+Hardware Clock (PHC) to ensure accuracy. AF_XDP takes a different data path
+compared to the ETF queuing discipline, which organizes packets and delays
+their transmission. Instead, AF_XDP immediately hands off the packets to
+the device driver without rearranging their order or holding them prior to
+transmission. Since the driver maintains FIFO behavior and does not perform
+packet reordering, a packet with a launch time request will block other
+packets in the same Tx Queue until it is sent. Therefore, it is recommended
+to allocate separate queue for scheduling traffic that is intended for
+future transmission.
+
+In scenarios where the launch time offload feature is disabled, the device
+driver is expected to disregard the launch time request. For correct
+interpretation and meaningful operation, the launch time should never be
+set to a value larger than the farthest programmable time in the future
+(the horizon). Different devices have different hardware limitations on the
+launch time offload feature.
+
+stmmac driver
+-------------
+
+For stmmac, TSO and launch time (TBS) features are mutually exclusive for
+each individual Tx Queue. By default, the driver configures Tx Queue 0 to
+support TSO and the rest of the Tx Queues to support TBS. The launch time
+hardware offload feature can be enabled or disabled by using the tc-etf
+command to call the driver's ndo_setup_tc() callback.
+
+The value of the launch time that is programmed in the Enhanced Normal
+Transmit Descriptors is a 32-bit value, where the most significant 8 bits
+represent the time in seconds and the remaining 24 bits represent the time
+in 256 ns increments. The programmed launch time is compared against the
+PTP time (bits[39:8]) and rolls over after 256 seconds. Therefore, the
+horizon of the launch time for dwmac4 and dwxlgmac2 is 128 seconds in the
+future.
+
+igc driver
+----------
+
+For igc, all four Tx Queues support the launch time feature. The launch
+time hardware offload feature can be enabled or disabled by using the
+tc-etf command to call the driver's ndo_setup_tc() callback. When entering
+TSN mode, the igc driver will reset the device and create a default Qbv
+schedule with a 1-second cycle time, with all Tx Queues open at all times.
+
+The value of the launch time that is programmed in the Advanced Transmit
+Context Descriptor is a relative offset to the starting time of the Qbv
+transmission window of the queue. The Frst flag of the descriptor can be
+set to schedule the packet for the next Qbv cycle. Therefore, the horizon
+of the launch time for i225 and i226 is the ending time of the next cycle
+of the Qbv transmission window of the queue. For example, when the Qbv
+cycle time is set to 1 second, the horizon of the launch time ranges
+from 1 second to 2 seconds, depending on where the Qbv cycle is currently
+running.
+
 Querying Device Capabilities
 ============================
 
@@ -74,6 +135,7 @@ Refer to ``xsk-flags`` features bitmask in
 
 - ``tx-timestamp``: device supports ``XDP_TXMD_FLAGS_TIMESTAMP``
 - ``tx-checksum``: device supports ``XDP_TXMD_FLAGS_CHECKSUM``
+- ``tx-launch-time-fifo``: device supports ``XDP_TXMD_FLAGS_LAUNCH_TIME``
 
 See ``tools/net/ynl/samples/netdev.c`` on how to query this information.
 

drivers/net/ethernet/intel/igc/igc.h

@@ -579,6 +579,7 @@ struct igc_metadata_request {
 	struct xsk_tx_metadata *meta;
 	struct igc_ring *tx_ring;
 	u32 cmd_type;
+	u16 used_desc;
 };
 
 struct igc_q_vector {

drivers/net/ethernet/intel/igc/igc_main.c

@@ -1092,7 +1092,8 @@ static int igc_init_empty_frame(struct igc_ring *ring,
 
 	dma = dma_map_single(ring->dev, skb->data, size, DMA_TO_DEVICE);
 	if (dma_mapping_error(ring->dev, dma)) {
-		netdev_err_once(ring->netdev, "Failed to map DMA for TX\n");
+		net_err_ratelimited("%s: DMA mapping error for empty frame\n",
+				    netdev_name(ring->netdev));
 		return -ENOMEM;
 	}
 
@@ -1108,20 +1109,12 @@ static int igc_init_empty_frame(struct igc_ring *ring,
 	return 0;
 }
 
-static int igc_init_tx_empty_descriptor(struct igc_ring *ring,
-					struct sk_buff *skb,
-					struct igc_tx_buffer *first)
+static void igc_init_tx_empty_descriptor(struct igc_ring *ring,
+					 struct sk_buff *skb,
+					 struct igc_tx_buffer *first)
 {
 	union igc_adv_tx_desc *desc;
 	u32 cmd_type, olinfo_status;
-	int err;
-
-	if (!igc_desc_unused(ring))
-		return -EBUSY;
-
-	err = igc_init_empty_frame(ring, first, skb);
-	if (err)
-		return err;
 
 	cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT |
 		   IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD |
@@ -1140,8 +1133,6 @@ static int igc_init_tx_empty_descriptor(struct igc_ring *ring,
 	ring->next_to_use++;
 	if (ring->next_to_use == ring->count)
 		ring->next_to_use = 0;
-
-	return 0;
 }
 
 #define IGC_EMPTY_FRAME_SIZE 60
@@ -1567,6 +1558,40 @@ static bool igc_request_tx_tstamp(struct igc_adapter *adapter, struct sk_buff *s
 	return false;
 }
 
+static int igc_insert_empty_frame(struct igc_ring *tx_ring)
+{
+	struct igc_tx_buffer *empty_info;
+	struct sk_buff *empty_skb;
+	void *data;
+	int ret;
+
+	empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
+	empty_skb = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC);
+	if (unlikely(!empty_skb)) {
+		net_err_ratelimited("%s: skb alloc error for empty frame\n",
+				    netdev_name(tx_ring->netdev));
+		return -ENOMEM;
+	}
+
+	data = skb_put(empty_skb, IGC_EMPTY_FRAME_SIZE);
+	memset(data, 0, IGC_EMPTY_FRAME_SIZE);
+
+	/* Prepare DMA mapping and Tx buffer information */
+	ret = igc_init_empty_frame(tx_ring, empty_info, empty_skb);
+	if (unlikely(ret)) {
+		dev_kfree_skb_any(empty_skb);
+		return ret;
+	}
+
+	/* Prepare advanced context descriptor for empty packet */
+	igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0);
+
+	/* Prepare advanced data descriptor for empty packet */
+	igc_init_tx_empty_descriptor(tx_ring, empty_skb, empty_info);
+
+	return 0;
+}
+
 static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 				       struct igc_ring *tx_ring)
 {
@@ -1586,6 +1611,7 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 	 *	+ 1 desc for skb_headlen/IGC_MAX_DATA_PER_TXD,
 	 *	+ 2 desc gap to keep tail from touching head,
 	 *	+ 1 desc for context descriptor,
+	 *	+ 2 desc for inserting an empty packet for launch time,
 	 * otherwise try next time
 	 */
 	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
@@ -1605,24 +1631,16 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 	launch_time = igc_tx_launchtime(tx_ring, txtime, &first_flag, &insert_empty);
 
 	if (insert_empty) {
-		struct igc_tx_buffer *empty_info;
-		struct sk_buff *empty;
-		void *data;
-
-		empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
-		empty = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC);
-		if (!empty)
-			goto done;
-
-		data = skb_put(empty, IGC_EMPTY_FRAME_SIZE);
-		memset(data, 0, IGC_EMPTY_FRAME_SIZE);
-
-		igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0);
-
-		if (igc_init_tx_empty_descriptor(tx_ring,
-						 empty,
-						 empty_info) < 0)
-			dev_kfree_skb_any(empty);
+		/* Reset the launch time if the required empty frame fails to
+		 * be inserted. However, this packet is not dropped, so it
+		 * "dirties" the current Qbv cycle. This ensures that the
+		 * upcoming packet, which is scheduled in the next Qbv cycle,
+		 * does not require an empty frame. This way, the launch time
+		 * continues to function correctly despite the current failure
+		 * to insert the empty frame.
+		 */
+		if (igc_insert_empty_frame(tx_ring))
+			launch_time = 0;
 	}
 
 done:
@@ -2953,9 +2971,48 @@ static u64 igc_xsk_fill_timestamp(void *_priv)
 	return *(u64 *)_priv;
 }
 
+static void igc_xsk_request_launch_time(u64 launch_time, void *_priv)
+{
+	struct igc_metadata_request *meta_req = _priv;
+	struct igc_ring *tx_ring = meta_req->tx_ring;
+	__le32 launch_time_offset;
+	bool insert_empty = false;
+	bool first_flag = false;
+	u16 used_desc = 0;
+
+	if (!tx_ring->launchtime_enable)
+		return;
+
+	launch_time_offset = igc_tx_launchtime(tx_ring,
+					       ns_to_ktime(launch_time),
+					       &first_flag, &insert_empty);
+	if (insert_empty) {
+		/* Disregard the launch time request if the required empty frame
+		 * fails to be inserted.
+		 */
+		if (igc_insert_empty_frame(tx_ring))
+			return;
+
+		meta_req->tx_buffer =
+			&tx_ring->tx_buffer_info[tx_ring->next_to_use];
+		/* Inserting an empty packet requires two descriptors:
+		 * one data descriptor and one context descriptor.
+		 */
+		used_desc += 2;
+	}
+
+	/* Use one context descriptor to specify launch time and first flag. */
+	igc_tx_ctxtdesc(tx_ring, launch_time_offset, first_flag, 0, 0, 0);
+	used_desc += 1;
+
+	/* Update the number of used descriptors in this request */
+	meta_req->used_desc += used_desc;
+}
+
 const struct xsk_tx_metadata_ops igc_xsk_tx_metadata_ops = {
 	.tmo_request_timestamp		= igc_xsk_request_timestamp,
 	.tmo_fill_timestamp		= igc_xsk_fill_timestamp,
+	.tmo_request_launch_time	= igc_xsk_request_launch_time,
 };
 
 static void igc_xdp_xmit_zc(struct igc_ring *ring)
@@ -2978,7 +3035,13 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 	ntu = ring->next_to_use;
 	budget = igc_desc_unused(ring);
 
-	while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) {
+	/* Packets with launch time require one data descriptor and one context
+	 * descriptor. When the launch time falls into the next Qbv cycle, we
+	 * may need to insert an empty packet, which requires two more
+	 * descriptors. Therefore, to be safe, we always ensure we have at least
+	 * 4 descriptors available.
+	 */
+	while (xsk_tx_peek_desc(pool, &xdp_desc) && budget >= 4) {
 		struct igc_metadata_request meta_req;
 		struct xsk_tx_metadata *meta = NULL;
 		struct igc_tx_buffer *bi;
@@ -2999,9 +3062,19 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 		meta_req.tx_ring = ring;
 		meta_req.tx_buffer = bi;
 		meta_req.meta = meta;
+		meta_req.used_desc = 0;
 		xsk_tx_metadata_request(meta, &igc_xsk_tx_metadata_ops,
 					&meta_req);
 
+		/* xsk_tx_metadata_request() may have updated next_to_use */
+		ntu = ring->next_to_use;
+
+		/* xsk_tx_metadata_request() may have updated Tx buffer info */
+		bi = meta_req.tx_buffer;
+
+		/* xsk_tx_metadata_request() may use a few descriptors */
+		budget -= meta_req.used_desc;
+
 		tx_desc = IGC_TX_DESC(ring, ntu);
 		tx_desc->read.cmd_type_len = cpu_to_le32(meta_req.cmd_type);
 		tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
@@ -3019,9 +3092,11 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 		ntu++;
 		if (ntu == ring->count)
 			ntu = 0;
+
+		ring->next_to_use = ntu;
+		budget--;
 	}
 
-	ring->next_to_use = ntu;
 	if (tx_desc) {
 		igc_flush_tx_descriptors(ring);
 		xsk_tx_release(pool);

drivers/net/ethernet/stmicro/stmmac/stmmac.h

@@ -106,6 +106,8 @@ struct stmmac_metadata_request {
 	struct stmmac_priv *priv;
 	struct dma_desc *tx_desc;
 	bool *set_ic;
+	struct dma_edesc *edesc;
+	int tbs;
 };
 
 struct stmmac_xsk_tx_complete {

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c

@@ -2486,9 +2486,20 @@ static u64 stmmac_xsk_fill_timestamp(void *_priv)
 	return 0;
 }
 
+static void stmmac_xsk_request_launch_time(u64 launch_time, void *_priv)
+{
+	struct timespec64 ts = ns_to_timespec64(launch_time);
+	struct stmmac_metadata_request *meta_req = _priv;
+
+	if (meta_req->tbs & STMMAC_TBS_EN)
+		stmmac_set_desc_tbs(meta_req->priv, meta_req->edesc, ts.tv_sec,
+				    ts.tv_nsec);
+}
+
 static const struct xsk_tx_metadata_ops stmmac_xsk_tx_metadata_ops = {
 	.tmo_request_timestamp		= stmmac_xsk_request_timestamp,
 	.tmo_fill_timestamp		= stmmac_xsk_fill_timestamp,
+	.tmo_request_launch_time	= stmmac_xsk_request_launch_time,
 };
 
 static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
@@ -2572,6 +2583,8 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 		meta_req.priv = priv;
 		meta_req.tx_desc = tx_desc;
 		meta_req.set_ic = &set_ic;
+		meta_req.tbs = tx_q->tbs;
+		meta_req.edesc = &tx_q->dma_entx[entry];
 		xsk_tx_metadata_request(meta, &stmmac_xsk_tx_metadata_ops,
 					&meta_req);
 		if (set_ic) {

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

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);
 }
 

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);

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);
 	}
 

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);

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

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 {

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 {

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 {

kernel/bpf/btf.c

@@ -8524,6 +8524,7 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type)
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
 	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
+	case BPF_PROG_TYPE_SOCK_OPS:
 		return BTF_KFUNC_HOOK_CGROUP;
 	case BPF_PROG_TYPE_SCHED_ACT:
 		return BTF_KFUNC_HOOK_SCHED_ACT;

net/core/dev.c

@@ -4572,7 +4572,8 @@ 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

net/core/filter.c

@@ -5222,6 +5222,25 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
+static int sk_bpf_set_get_cb_flags(struct sock *sk, char *optval, bool getopt)
+{
+	u32 sk_bpf_cb_flags;
+
+	if (getopt) {
+		*(u32 *)optval = sk->sk_bpf_cb_flags;
+		return 0;
+	}
+
+	sk_bpf_cb_flags = *(u32 *)optval;
+
+	if (sk_bpf_cb_flags & ~SK_BPF_CB_MASK)
+		return -EINVAL;
+
+	sk->sk_bpf_cb_flags = sk_bpf_cb_flags;
+
+	return 0;
+}
+
 static int sol_socket_sockopt(struct sock *sk, int optname,
 			      char *optval, int *optlen,
 			      bool getopt)
@@ -5238,6 +5257,7 @@ static int sol_socket_sockopt(struct sock *sk, int optname,
 	case SO_MAX_PACING_RATE:
 	case SO_BINDTOIFINDEX:
 	case SO_TXREHASH:
+	case SK_BPF_CB_FLAGS:
 		if (*optlen != sizeof(int))
 			return -EINVAL;
 		break;
@@ -5247,6 +5267,9 @@ static int sol_socket_sockopt(struct sock *sk, int optname,
 		return -EINVAL;
 	}
 
+	if (optname == SK_BPF_CB_FLAGS)
+		return sk_bpf_set_get_cb_flags(sk, optval, getopt);
+
 	if (getopt) {
 		if (optname == SO_BINDTODEVICE)
 			return -EINVAL;
@@ -5382,6 +5405,7 @@ static int sol_tcp_sockopt(struct sock *sk, int optname,
 	case TCP_USER_TIMEOUT:
 	case TCP_NOTSENT_LOWAT:
 	case TCP_SAVE_SYN:
+	case TCP_RTO_MAX_MS:
 		if (*optlen != sizeof(int))
 			return -EINVAL;
 		break;
@@ -5500,6 +5524,11 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 	return -EINVAL;
 }
 
+static bool is_locked_tcp_sock_ops(struct bpf_sock_ops_kern *bpf_sock)
+{
+	return bpf_sock->op <= BPF_SOCK_OPS_WRITE_HDR_OPT_CB;
+}
+
 static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 			   char *optval, int optlen)
 {
@@ -5650,6 +5679,9 @@ static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = {
 BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 	   int, level, int, optname, char *, optval, int, optlen)
 {
+	if (!is_locked_tcp_sock_ops(bpf_sock))
+		return -EOPNOTSUPP;
+
 	return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen);
 }
 
@@ -5735,6 +5767,9 @@ static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock,
 BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 	   int, level, int, optname, char *, optval, int, optlen)
 {
+	if (!is_locked_tcp_sock_ops(bpf_sock))
+		return -EOPNOTSUPP;
+
 	if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP &&
 	    optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_MAC) {
 		int ret, copy_len = 0;
@@ -5777,6 +5812,9 @@ BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock,
 	struct sock *sk = bpf_sock->sk;
 	int val = argval & BPF_SOCK_OPS_ALL_CB_FLAGS;
 
+	if (!is_locked_tcp_sock_ops(bpf_sock))
+		return -EOPNOTSUPP;
+
 	if (!IS_ENABLED(CONFIG_INET) || !sk_fullsock(sk))
 		return -EINVAL;
 
@@ -7586,6 +7624,9 @@ BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock,
 	u8 search_kind, search_len, copy_len, magic_len;
 	int ret;
 
+	if (!is_locked_tcp_sock_ops(bpf_sock))
+		return -EOPNOTSUPP;
+
 	/* 2 byte is the minimal option len except TCPOPT_NOP and
 	 * TCPOPT_EOL which are useless for the bpf prog to learn
 	 * and this helper disallow loading them also.
@@ -10358,10 +10399,10 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 		}							      \
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
 						struct bpf_sock_ops_kern,     \
-						is_fullsock),		      \
+						is_locked_tcp_sock),	      \
 				      fullsock_reg, si->src_reg,	      \
 				      offsetof(struct bpf_sock_ops_kern,      \
-					       is_fullsock));		      \
+					       is_locked_tcp_sock));	      \
 		*insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp);	      \
 		if (si->dst_reg == si->src_reg)				      \
 			*insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg,	      \
@@ -10446,10 +10487,10 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 					       temp));			      \
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
 						struct bpf_sock_ops_kern,     \
-						is_fullsock),		      \
+						is_locked_tcp_sock),	      \
 				      reg, si->dst_reg,			      \
 				      offsetof(struct bpf_sock_ops_kern,      \
-					       is_fullsock));		      \
+					       is_locked_tcp_sock));	      \
 		*insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2);		      \
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
 						struct bpf_sock_ops_kern, sk),\
@@ -12062,6 +12103,25 @@ __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk,
 #endif
 }
 
+__bpf_kfunc int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops,
+					      u64 flags)
+{
+	struct sk_buff *skb;
+
+	if (skops->op != BPF_SOCK_OPS_TSTAMP_SENDMSG_CB)
+		return -EOPNOTSUPP;
+
+	if (flags)
+		return -EINVAL;
+
+	skb = skops->skb;
+	skb_shinfo(skb)->tx_flags |= SKBTX_BPF;
+	TCP_SKB_CB(skb)->txstamp_ack |= TSTAMP_ACK_BPF;
+	skb_shinfo(skb)->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
+
+	return 0;
+}
+
 __bpf_kfunc_end_defs();
 
 int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
@@ -12095,6 +12155,10 @@ BTF_KFUNCS_START(bpf_kfunc_check_set_tcp_reqsk)
 BTF_ID_FLAGS(func, bpf_sk_assign_tcp_reqsk, KF_TRUSTED_ARGS)
 BTF_KFUNCS_END(bpf_kfunc_check_set_tcp_reqsk)
 
+BTF_KFUNCS_START(bpf_kfunc_check_set_sock_ops)
+BTF_ID_FLAGS(func, bpf_sock_ops_enable_tx_tstamp, KF_TRUSTED_ARGS)
+BTF_KFUNCS_END(bpf_kfunc_check_set_sock_ops)
+
 static const struct btf_kfunc_id_set bpf_kfunc_set_skb = {
 	.owner = THIS_MODULE,
 	.set = &bpf_kfunc_check_set_skb,
@@ -12115,6 +12179,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_tcp_reqsk = {
 	.set = &bpf_kfunc_check_set_tcp_reqsk,
 };
 
+static const struct btf_kfunc_id_set bpf_kfunc_set_sock_ops = {
+	.owner = THIS_MODULE,
+	.set = &bpf_kfunc_check_set_sock_ops,
+};
+
 static int __init bpf_kfunc_init(void)
 {
 	int ret;
@@ -12133,7 +12202,8 @@ static int __init bpf_kfunc_init(void)
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
 					       &bpf_kfunc_set_sock_addr);
-	return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk);
+	return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCK_OPS, &bpf_kfunc_set_sock_ops);
 }
 late_initcall(bpf_kfunc_init);
 

net/core/netdev-genl.c

@@ -53,6 +53,8 @@ XDP_METADATA_KFUNC_xxx
 			xsk_features |= NETDEV_XSK_FLAGS_TX_TIMESTAMP;
 		if (netdev->xsk_tx_metadata_ops->tmo_request_checksum)
 			xsk_features |= NETDEV_XSK_FLAGS_TX_CHECKSUM;
+		if (netdev->xsk_tx_metadata_ops->tmo_request_launch_time)
+			xsk_features |= NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO;
 	}
 
 	if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) ||

net/core/skbuff.c

@@ -5449,6 +5449,52 @@ err:
 }
 EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
 
+static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,
+						 struct skb_shared_hwtstamps *hwtstamps,
+						 int tstype)
+{
+	switch (tstype) {
+	case SCM_TSTAMP_SCHED:
+		return skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP;
+	case SCM_TSTAMP_SND:
+		return skb_shinfo(skb)->tx_flags & (hwtstamps ? SKBTX_HW_TSTAMP_NOBPF :
+						    SKBTX_SW_TSTAMP);
+	case SCM_TSTAMP_ACK:
+		return TCP_SKB_CB(skb)->txstamp_ack & TSTAMP_ACK_SK;
+	}
+
+	return false;
+}
+
+static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb,
+						  struct skb_shared_hwtstamps *hwtstamps,
+						  struct sock *sk,
+						  int tstype)
+{
+	int op;
+
+	switch (tstype) {
+	case SCM_TSTAMP_SCHED:
+		op = BPF_SOCK_OPS_TSTAMP_SCHED_CB;
+		break;
+	case SCM_TSTAMP_SND:
+		if (hwtstamps) {
+			op = BPF_SOCK_OPS_TSTAMP_SND_HW_CB;
+			*skb_hwtstamps(skb) = *hwtstamps;
+		} else {
+			op = BPF_SOCK_OPS_TSTAMP_SND_SW_CB;
+		}
+		break;
+	case SCM_TSTAMP_ACK:
+		op = BPF_SOCK_OPS_TSTAMP_ACK_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,
@@ -5461,6 +5507,13 @@ 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, hwtstamps,
+						      sk, tstype);
+
+	if (!skb_tstamp_tx_report_so_timestamping(orig_skb, hwtstamps, tstype))
+		return;
+
 	tsflags = READ_ONCE(sk->sk_tsflags);
 	if (!hwtstamps && !(tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) &&
 	    skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS)