Merge branch 'xdp-rx-hwts-metadata-for-stmmac-driver'

Song Yoong Siang says:

====================
XDP Rx HWTS metadata for stmmac driver

Implemented XDP receive hardware timestamp metadata for stmmac driver.

This patchset is tested with tools/testing/selftests/bpf/xdp_hw_metadata.
Below are the test steps and results.

Command on DUT:
	sudo ./xdp_hw_metadata <interface name>

Command on Link Partner:
	echo -n xdp | nc -u -q1 <destination IPv4 addr> 9091
	echo -n skb | nc -u -q1 <destination IPv4 addr> 9092

Result for port 9091:
	poll: 1 (0) skip=1 fail=0 redir=1
	xsk_ring_cons__peek: 1
	0x55f69f65f6d0: rx_desc[0]->addr=100000000008000 addr=8100 comp_addr=8000
	rx_timestamp: 1677762069053692631
	No rx_hash err=-95
	0x55f69f65f6d0: complete idx=8 addr=8000

Result for port 9092:
	poll: 1 (0) skip=2 fail=0 redir=1
	found skb hwtstamp = 1677762071.937207680
====================

Link: https://lore.kernel.org/r/20230415064503.3225835-1-yoong.siang.song@intel.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

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

@@ -92,6 +92,13 @@ struct stmmac_rx_buffer {
 	dma_addr_t sec_addr;
 };
 
+struct stmmac_xdp_buff {
+	struct xdp_buff xdp;
+	struct stmmac_priv *priv;
+	struct dma_desc *desc;
+	struct dma_desc *ndesc;
+};
+
 struct stmmac_rx_queue {
 	u32 rx_count_frames;
 	u32 queue_index;

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

@@ -1614,6 +1614,12 @@ static int stmmac_alloc_rx_buffers_zc(struct stmmac_priv *priv,
 	struct stmmac_rx_queue *rx_q = &dma_conf->rx_queue[queue];
 	int i;
 
+	/* struct stmmac_xdp_buff is using cb field (maximum size of 24 bytes)
+	 * in struct xdp_buff_xsk to stash driver specific information. Thus,
+	 * use this macro to make sure no size violations.
+	 */
+	XSK_CHECK_PRIV_TYPE(struct stmmac_xdp_buff);
+
 	for (i = 0; i < dma_conf->dma_rx_size; i++) {
 		struct stmmac_rx_buffer *buf;
 		dma_addr_t dma_addr;
@@ -4998,6 +5004,16 @@ static bool stmmac_rx_refill_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 	return ret;
 }
 
+static struct stmmac_xdp_buff *xsk_buff_to_stmmac_ctx(struct xdp_buff *xdp)
+{
+	/* In XDP zero copy data path, xdp field in struct xdp_buff_xsk is used
+	 * to represent incoming packet, whereas cb field in the same structure
+	 * is used to store driver specific info. Thus, struct stmmac_xdp_buff
+	 * is laid on top of xdp and cb fields of struct xdp_buff_xsk.
+	 */
+	return (struct stmmac_xdp_buff *)xdp;
+}
+
 static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue)
 {
 	struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[queue];
@@ -5027,6 +5043,7 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue)
 	}
 	while (count < limit) {
 		struct stmmac_rx_buffer *buf;
+		struct stmmac_xdp_buff *ctx;
 		unsigned int buf1_len = 0;
 		struct dma_desc *np, *p;
 		int entry;
@@ -5112,6 +5129,11 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue)
 			goto read_again;
 		}
 
+		ctx = xsk_buff_to_stmmac_ctx(buf->xdp);
+		ctx->priv = priv;
+		ctx->desc = p;
+		ctx->ndesc = np;
+
 		/* XDP ZC Frame only support primary buffers for now */
 		buf1_len = stmmac_rx_buf1_len(priv, p, status, len);
 		len += buf1_len;
@@ -5190,7 +5212,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 	enum dma_data_direction dma_dir;
 	unsigned int desc_size;
 	struct sk_buff *skb = NULL;
-	struct xdp_buff xdp;
+	struct stmmac_xdp_buff ctx;
 	int xdp_status = 0;
 	int buf_sz;
 
@@ -5311,17 +5333,22 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			dma_sync_single_for_cpu(priv->device, buf->addr,
 						buf1_len, dma_dir);
 
-			xdp_init_buff(&xdp, buf_sz, &rx_q->xdp_rxq);
-			xdp_prepare_buff(&xdp, page_address(buf->page),
-					 buf->page_offset, buf1_len, false);
+			xdp_init_buff(&ctx.xdp, buf_sz, &rx_q->xdp_rxq);
+			xdp_prepare_buff(&ctx.xdp, page_address(buf->page),
+					 buf->page_offset, buf1_len, true);
 
-			pre_len = xdp.data_end - xdp.data_hard_start -
+			pre_len = ctx.xdp.data_end - ctx.xdp.data_hard_start -
 				  buf->page_offset;
-			skb = stmmac_xdp_run_prog(priv, &xdp);
+
+			ctx.priv = priv;
+			ctx.desc = p;
+			ctx.ndesc = np;
+
+			skb = stmmac_xdp_run_prog(priv, &ctx.xdp);
 			/* Due xdp_adjust_tail: DMA sync for_device
 			 * cover max len CPU touch
 			 */
-			sync_len = xdp.data_end - xdp.data_hard_start -
+			sync_len = ctx.xdp.data_end - ctx.xdp.data_hard_start -
 				   buf->page_offset;
 			sync_len = max(sync_len, pre_len);
 
@@ -5331,7 +5358,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 
 				if (xdp_res & STMMAC_XDP_CONSUMED) {
 					page_pool_put_page(rx_q->page_pool,
-							   virt_to_head_page(xdp.data),
+							   virt_to_head_page(ctx.xdp.data),
 							   sync_len, true);
 					buf->page = NULL;
 					priv->dev->stats.rx_dropped++;
@@ -5359,7 +5386,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 
 		if (!skb) {
 			/* XDP program may expand or reduce tail */
-			buf1_len = xdp.data_end - xdp.data;
+			buf1_len = ctx.xdp.data_end - ctx.xdp.data;
 
 			skb = napi_alloc_skb(&ch->rx_napi, buf1_len);
 			if (!skb) {
@@ -5369,7 +5396,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			}
 
 			/* XDP program may adjust header */
-			skb_copy_to_linear_data(skb, xdp.data, buf1_len);
+			skb_copy_to_linear_data(skb, ctx.xdp.data, buf1_len);
 			skb_put(skb, buf1_len);
 
 			/* Data payload copied into SKB, page ready for recycle */
@@ -7060,6 +7087,37 @@ void stmmac_fpe_handshake(struct stmmac_priv *priv, bool enable)
 	}
 }
 
+static int stmmac_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp)
+{
+	const struct stmmac_xdp_buff *ctx = (void *)_ctx;
+	struct dma_desc *desc_contains_ts = ctx->desc;
+	struct stmmac_priv *priv = ctx->priv;
+	struct dma_desc *ndesc = ctx->ndesc;
+	struct dma_desc *desc = ctx->desc;
+	u64 ns = 0;
+
+	if (!priv->hwts_rx_en)
+		return -ENODATA;
+
+	/* For GMAC4, the valid timestamp is from CTX next desc. */
+	if (priv->plat->has_gmac4 || priv->plat->has_xgmac)
+		desc_contains_ts = ndesc;
+
+	/* Check if timestamp is available */
+	if (stmmac_get_rx_timestamp_status(priv, desc, ndesc, priv->adv_ts)) {
+		stmmac_get_timestamp(priv, desc_contains_ts, priv->adv_ts, &ns);
+		ns -= priv->plat->cdc_error_adj;
+		*timestamp = ns_to_ktime(ns);
+		return 0;
+	}
+
+	return -ENODATA;
+}
+
+static const struct xdp_metadata_ops stmmac_xdp_metadata_ops = {
+	.xmo_rx_timestamp		= stmmac_xdp_rx_timestamp,
+};
+
 /**
  * stmmac_dvr_probe
  * @device: device pointer
@@ -7167,6 +7225,8 @@ int stmmac_dvr_probe(struct device *device,
 
 	ndev->netdev_ops = &stmmac_netdev_ops;
 
+	ndev->xdp_metadata_ops = &stmmac_xdp_metadata_ops;
+
 	ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 			    NETIF_F_RXCSUM;
 	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |