xsk: TX metadata Launch Time support

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_main.c

@@ -1566,6 +1566,26 @@ static bool igc_request_tx_tstamp(struct igc_adapter *adapter, struct sk_buff *s
 	return false;
 }
 
+static void igc_insert_empty_packet(struct igc_ring *tx_ring)
+{
+	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)
+		return;
+
+	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);
+}
+
 static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 				       struct igc_ring *tx_ring)
 {
@@ -1603,26 +1623,8 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 	skb->tstamp = ktime_set(0, 0);
 	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);
-	}
+	if (insert_empty)
+		igc_insert_empty_packet(tx_ring);
 
 done:
 	/* record the location of the first descriptor for this packet */
@@ -2949,9 +2951,33 @@ 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;
+
+	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) {
+		igc_insert_empty_packet(tx_ring);
+		meta_req->tx_buffer =
+			&tx_ring->tx_buffer_info[tx_ring->next_to_use];
+	}
+
+	igc_tx_ctxtdesc(tx_ring, launch_time_offset, first_flag, 0, 0, 0);
+}
+
 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)
@@ -2974,7 +3000,13 @@ 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;
@@ -2998,6 +3030,12 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 		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;
+
 		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);
@@ -3015,9 +3053,11 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 		ntu++;
 		if (ntu == ring->count)
 			ntu = 0;
+
+		ring->next_to_use = ntu;
+		budget = igc_desc_unused(ring);
 	}
 
-	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

@@ -2514,9 +2514,20 @@ static u64 stmmac_xsk_fill_timestamp(void *_priv)
 	return 0;
 }
 
+static void stmmac_xsk_request_launch_time(u64 launch_time, void *_priv)
+{
+	struct stmmac_metadata_request *meta_req = _priv;
+	struct timespec64 ts = ns_to_timespec64(launch_time);
+
+	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)
@@ -2600,6 +2611,8 @@ 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/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

@@ -199,6 +199,7 @@ static inline void *xsk_buff_raw_get_data(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/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_LAUNCH_TIME: 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_LAUNCH_TIME = 4,
 };
 
 enum netdev_queue_type {

net/core/netdev-genl.c

@@ -52,6 +52,8 @@ 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_LAUNCH_TIME;
 	}
 
 	if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) ||

net/xdp/xsk.c

@@ -742,6 +742,9 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 						goto free_err;
 				}
 			}
+
+			if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME)
+				skb->skb_mstamp_ns = meta->request.launch_time;
 		}
 	}
 

tools/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 {

tools/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_LAUNCH_TIME: 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_LAUNCH_TIME = 4,
 };
 
 enum netdev_queue_type {