ice: xsk: Tx multi-buffer support

Most of this patch is about actually supporting XDP_TX action. Pure Tx
ZC support is only about looking at XDP_PKT_CONTD presence at options
field and based on that generating EOP bit on Tx HW descriptor. This is
that simple due to the implementation on
xsk_tx_peek_release_desc_batch() where we are making sure that last
produced descriptor is an EOP one.

Overwrite xdp_zc_max_segs with a value that defines max scatter-gatter
count on Tx side that HW can handle.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-16-maciej.fijalkowski@intel.comSigned-off-by: Alexei Starovoitov <ast@kernel.org>

drivers/net/ethernet/intel/ice/ice_main.c

@@ -3392,6 +3392,7 @@ static void ice_set_ops(struct ice_vsi *vsi)
 	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
 			       NETDEV_XDP_ACT_XSK_ZEROCOPY |
 			       NETDEV_XDP_ACT_RX_SG;
+	netdev->xdp_zc_max_segs = ICE_MAX_BUF_TXD;
 }
 
 /**

drivers/net/ethernet/intel/ice/ice_xsk.c

@@ -613,7 +613,7 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
  * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ
  * @xdp_ring: XDP Tx ring
  */
-static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
+static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
 {
 	u16 ntc = xdp_ring->next_to_clean;
 	struct ice_tx_desc *tx_desc;
@@ -635,7 +635,7 @@ static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
 	}
 
 	if (!completed_frames)
-		return;
+		return 0;
 
 	if (likely(!xdp_ring->xdp_tx_active)) {
 		xsk_frames = completed_frames;
@@ -665,6 +665,8 @@ static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
 		xdp_ring->next_to_clean -= cnt;
 	if (xsk_frames)
 		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
+
+	return completed_frames;
 }
 
 /**
@@ -682,37 +684,72 @@ static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
 static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
 			      struct ice_tx_ring *xdp_ring)
 {
+	struct skb_shared_info *sinfo = NULL;
 	u32 size = xdp->data_end - xdp->data;
 	u32 ntu = xdp_ring->next_to_use;
 	struct ice_tx_desc *tx_desc;
 	struct ice_tx_buf *tx_buf;
-	dma_addr_t dma;
+	struct xdp_buff *head;
+	u32 nr_frags = 0;
+	u32 free_space;
+	u32 frag = 0;
 
-	if (ICE_DESC_UNUSED(xdp_ring) < ICE_RING_QUARTER(xdp_ring)) {
-		ice_clean_xdp_irq_zc(xdp_ring);
-		if (!ICE_DESC_UNUSED(xdp_ring)) {
-			xdp_ring->ring_stats->tx_stats.tx_busy++;
-			return ICE_XDP_CONSUMED;
-		}
-	}
+	free_space = ICE_DESC_UNUSED(xdp_ring);
+	if (free_space < ICE_RING_QUARTER(xdp_ring))
+		free_space += ice_clean_xdp_irq_zc(xdp_ring);
 
-	dma = xsk_buff_xdp_get_dma(xdp);
-	xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size);
+	if (unlikely(!free_space))
+		goto busy;
+
+	if (unlikely(xdp_buff_has_frags(xdp))) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		nr_frags = sinfo->nr_frags;
+		if (free_space < nr_frags + 1)
+			goto busy;
+	}
 
-	tx_buf = &xdp_ring->tx_buf[ntu];
-	tx_buf->xdp = xdp;
-	tx_buf->type = ICE_TX_BUF_XSK_TX;
 	tx_desc = ICE_TX_DESC(xdp_ring, ntu);
-	tx_desc->buf_addr = cpu_to_le64(dma);
-	tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP,
-						      0, size, 0);
-	xdp_ring->xdp_tx_active++;
+	tx_buf = &xdp_ring->tx_buf[ntu];
+	head = xdp;
+
+	for (;;) {
+		dma_addr_t dma;
+
+		dma = xsk_buff_xdp_get_dma(xdp);
+		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size);
+
+		tx_buf->xdp = xdp;
+		tx_buf->type = ICE_TX_BUF_XSK_TX;
+		tx_desc->buf_addr = cpu_to_le64(dma);
+		tx_desc->cmd_type_offset_bsz = ice_build_ctob(0, 0, size, 0);
+		/* account for each xdp_buff from xsk_buff_pool */
+		xdp_ring->xdp_tx_active++;
+
+		if (++ntu == xdp_ring->count)
+			ntu = 0;
+
+		if (frag == nr_frags)
+			break;
+
+		tx_desc = ICE_TX_DESC(xdp_ring, ntu);
+		tx_buf = &xdp_ring->tx_buf[ntu];
+
+		xdp = xsk_buff_get_frag(head);
+		size = skb_frag_size(&sinfo->frags[frag]);
+		frag++;
+	}
 
-	if (++ntu == xdp_ring->count)
-		ntu = 0;
 	xdp_ring->next_to_use = ntu;
+	/* update last descriptor from a frame with EOP */
+	tx_desc->cmd_type_offset_bsz |=
+		cpu_to_le64(ICE_TX_DESC_CMD_EOP << ICE_TXD_QW1_CMD_S);
 
 	return ICE_XDP_TX;
+
+busy:
+	xdp_ring->ring_stats->tx_stats.tx_busy++;
+
+	return ICE_XDP_CONSUMED;
 }
 
 /**
@@ -960,7 +997,7 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
 
 	tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++);
 	tx_desc->buf_addr = cpu_to_le64(dma);
-	tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP,
+	tx_desc->cmd_type_offset_bsz = ice_build_ctob(xsk_is_eop_desc(desc),
 						      0, desc->len, 0);
 
 	*total_bytes += desc->len;
@@ -987,7 +1024,7 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
 
 		tx_desc = ICE_TX_DESC(xdp_ring, ntu++);
 		tx_desc->buf_addr = cpu_to_le64(dma);
-		tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP,
+		tx_desc->cmd_type_offset_bsz = ice_build_ctob(xsk_is_eop_desc(&descs[i]),
 							      0, descs[i].len, 0);
 
 		*total_bytes += descs[i].len;