net: stmmac: Add Tx HWTS support to XDP ZC

This patch enables transmit hardware timestamp support to XDP zero copy
via XDP Tx metadata framework.

This patchset is tested with tools/testing/selftests/bpf/xdp_hw_metadata
on Intel Tiger Lake platform. Below are the test steps and results.

Command on DUT:
sudo ./xdp_hw_metadata <interface name>
sudo hwstamp_ctl -i <interface name> -t 1 -r 1

Command on Link Partner:
echo -n xdp | nc -u -q1 <destination IPv4 addr> 9091

Result:
xsk_ring_cons__peek: 1
0x55bbbf08b6d0: rx_desc[2]->addr=8c100 addr=8c100 comp_addr=8c100 EoP
No rx_hash err=-95
rx_timestamp:  1677762688429141540 (sec:1677762688.4291)
HW RX-time:   1677762688429141540 (sec:1677762688.4291) delta to User RX-time sec:0.0003 (250.665 usec)
XDP RX-time:   1677762688429375597 (sec:1677762688.4294) delta to User RX-time sec:0.0000 (16.608 usec)
0x55bbbf08b6d0: ping-pong with csum=561c (want f488) csum_start=34 csum_offset=6
0x55bbbf08b6d0: complete tx idx=2 addr=2008
tx_timestamp:  1677762688431127273 (sec:1677762688.4311)
HW TX-complete-time:   1677762688431127273 (sec:1677762688.4311) delta to User TX-complete-time sec:0.0083 (8331.655 usec)
XDP RX-time:   1677762688429375597 (sec:1677762688.4294) delta to User TX-complete-time sec:0.0101 (10083.331 usec)
HW RX-time:   1677762688429141540 (sec:1677762688.4291) delta to HW TX-complete-time sec:0.0020 (1985.733 usec)
0x55bbbf08b6d0: complete rx idx=130 addr=8c100
Signed-off-by: Song Yoong Siang <yoong.siang.song@intel.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20231127190319.1190813-6-sdf@google.comSigned-off-by: Alexei Starovoitov <ast@kernel.org>

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

@@ -51,6 +51,7 @@ struct stmmac_tx_info {
 	bool last_segment;
 	bool is_jumbo;
 	enum stmmac_txbuf_type buf_type;
+	struct xsk_tx_metadata_compl xsk_meta;
 };
 
 #define STMMAC_TBS_AVAIL	BIT(0)
@@ -100,6 +101,17 @@ struct stmmac_xdp_buff {
 	struct dma_desc *ndesc;
 };
 
+struct stmmac_metadata_request {
+	struct stmmac_priv *priv;
+	struct dma_desc *tx_desc;
+	bool *set_ic;
+};
+
+struct stmmac_xsk_tx_complete {
+	struct stmmac_priv *priv;
+	struct dma_desc *desc;
+};
+
 struct stmmac_rx_queue {
 	u32 rx_count_frames;
 	u32 queue_index;

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

@@ -2430,6 +2430,46 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
 	}
 }
 
+static void stmmac_xsk_request_timestamp(void *_priv)
+{
+	struct stmmac_metadata_request *meta_req = _priv;
+
+	stmmac_enable_tx_timestamp(meta_req->priv, meta_req->tx_desc);
+	*meta_req->set_ic = true;
+}
+
+static u64 stmmac_xsk_fill_timestamp(void *_priv)
+{
+	struct stmmac_xsk_tx_complete *tx_compl = _priv;
+	struct stmmac_priv *priv = tx_compl->priv;
+	struct dma_desc *desc = tx_compl->desc;
+	bool found = false;
+	u64 ns = 0;
+
+	if (!priv->hwts_tx_en)
+		return 0;
+
+	/* check tx tstamp status */
+	if (stmmac_get_tx_timestamp_status(priv, desc)) {
+		stmmac_get_timestamp(priv, desc, priv->adv_ts, &ns);
+		found = true;
+	} else if (!stmmac_get_mac_tx_timestamp(priv, priv->hw, &ns)) {
+		found = true;
+	}
+
+	if (found) {
+		ns -= priv->plat->cdc_error_adj;
+		return ns_to_ktime(ns);
+	}
+
+	return 0;
+}
+
+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,
+};
+
 static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 {
 	struct netdev_queue *nq = netdev_get_tx_queue(priv->dev, queue);
@@ -2449,6 +2489,8 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 	budget = min(budget, stmmac_tx_avail(priv, queue));
 
 	while (budget-- > 0) {
+		struct stmmac_metadata_request meta_req;
+		struct xsk_tx_metadata *meta = NULL;
 		dma_addr_t dma_addr;
 		bool set_ic;
 
@@ -2472,6 +2514,7 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 			tx_desc = tx_q->dma_tx + entry;
 
 		dma_addr = xsk_buff_raw_get_dma(pool, xdp_desc.addr);
+		meta = xsk_buff_get_metadata(pool, xdp_desc.addr);
 		xsk_buff_raw_dma_sync_for_device(pool, dma_addr, xdp_desc.len);
 
 		tx_q->tx_skbuff_dma[entry].buf_type = STMMAC_TXBUF_T_XSK_TX;
@@ -2499,6 +2542,11 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 		else
 			set_ic = false;
 
+		meta_req.priv = priv;
+		meta_req.tx_desc = tx_desc;
+		meta_req.set_ic = &set_ic;
+		xsk_tx_metadata_request(meta, &stmmac_xsk_tx_metadata_ops,
+					&meta_req);
 		if (set_ic) {
 			tx_q->tx_count_frames = 0;
 			stmmac_set_tx_ic(priv, tx_desc);
@@ -2511,6 +2559,9 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 
 		stmmac_enable_dma_transmission(priv, priv->ioaddr);
 
+		xsk_tx_metadata_to_compl(meta,
+					 &tx_q->tx_skbuff_dma[entry].xsk_meta);
+
 		tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, priv->dma_conf.dma_tx_size);
 		entry = tx_q->cur_tx;
 	}
@@ -2620,8 +2671,18 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue,
 			} else {
 				tx_packets++;
 			}
-			if (skb)
+			if (skb) {
 				stmmac_get_tx_hwtstamp(priv, p, skb);
+			} else {
+				struct stmmac_xsk_tx_complete tx_compl = {
+					.priv = priv,
+					.desc = p,
+				};
+
+				xsk_tx_metadata_complete(&tx_q->tx_skbuff_dma[entry].xsk_meta,
+							 &stmmac_xsk_tx_metadata_ops,
+							 &tx_compl);
+			}
 		}
 
 		if (likely(tx_q->tx_skbuff_dma[entry].buf &&
@@ -7464,6 +7525,7 @@ int stmmac_dvr_probe(struct device *device,
 	ndev->netdev_ops = &stmmac_netdev_ops;
 
 	ndev->xdp_metadata_ops = &stmmac_xdp_metadata_ops;
+	ndev->xsk_tx_metadata_ops = &stmmac_xsk_tx_metadata_ops;
 
 	ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 			    NETIF_F_RXCSUM;