ice: Add support for XDP multi-buffer on Tx side

Similarly as for Rx side in previous patch, logic on XDP Tx in ice
driver needs to be adjusted for multi-buffer support. Specifically, the
way how HW Tx descriptors are produced and cleaned.

Currently, XDP_TX works on strict ring boundaries, meaning it sets RS
bit (on producer side) / looks up DD bit (on consumer/cleaning side)
every quarter of the ring. It means that if for example multi buffer
frame would span across the ring quarter boundary (say that frame
consists of 4 frames and we start from 62 descriptor where ring is sized
to 256 entries), RS bit would be produced in the middle of multi buffer
frame, which would be a broken behavior as it needs to be set on the
last descriptor of the frame.

To make it work, set RS bit at the last descriptor from the batch of
frames that XDP_TX action was used on and make the first entry remember
the index of last descriptor with RS bit set. This way, cleaning side
can take the index of descriptor with RS bit, look up DD bit's presence
and clean from first entry to last.

In order to clean up the code base introduce the common ice_set_rs_bit()
which will return index of descriptor that got RS bit produced on so
that standard driver can store this within proper ice_tx_buf and ZC
driver can simply ignore return value.

Co-developed-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com>
Signed-off-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Link: https://lore.kernel.org/bpf/20230131204506.219292-12-maciej.fijalkowski@intel.com

1 files changed, 158 insertions, 72 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 25f04266c668..3dcc40b96b58 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -221,111 +221,190 @@ ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag)
 }
 
 /**
+ * ice_clean_xdp_tx_buf - Free and unmap XDP Tx buffer
+ * @xdp_ring: XDP Tx ring
+ * @tx_buf: Tx buffer to clean
+ */
+static void
+ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf)
+{
+	dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma),
+			 dma_unmap_len(tx_buf, len), DMA_TO_DEVICE);
+	dma_unmap_len_set(tx_buf, len, 0);
+	xdp_ring->xdp_tx_active--;
+	page_frag_free(tx_buf->raw_buf);
+	tx_buf->raw_buf = NULL;
+}
+
+/**
  * ice_clean_xdp_irq - Reclaim resources after transmit completes on XDP ring
  * @xdp_ring: XDP ring to clean
  */
-static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring)
+static u32 ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring)
 {
-	unsigned int total_bytes = 0, total_pkts = 0;
-	u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
-	u16 ntc = xdp_ring->next_to_clean;
-	struct ice_tx_desc *next_dd_desc;
-	u16 next_dd = xdp_ring->next_dd;
-	struct ice_tx_buf *tx_buf;
-	int i;
+	int total_bytes = 0, total_pkts = 0;
+	u32 ntc = xdp_ring->next_to_clean;
+	struct ice_tx_desc *tx_desc;
+	u32 cnt = xdp_ring->count;
+	u32 ready_frames = 0;
+	u32 frags;
+	u32 idx;
+	u32 ret;
+
+	idx = xdp_ring->tx_buf[ntc].rs_idx;
+	tx_desc = ICE_TX_DESC(xdp_ring, idx);
+	if (tx_desc->cmd_type_offset_bsz &
+	    cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)) {
+		if (idx >= ntc)
+			ready_frames = idx - ntc + 1;
+		else
+			ready_frames = idx + cnt - ntc + 1;
+	}
 
-	next_dd_desc = ICE_TX_DESC(xdp_ring, next_dd);
-	if (!(next_dd_desc->cmd_type_offset_bsz &
-	    cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)))
-		return;
+	if (!ready_frames)
+		return 0;
+	ret = ready_frames;
 
-	for (i = 0; i < tx_thresh; i++) {
-		tx_buf = &xdp_ring->tx_buf[ntc];
+	while (ready_frames) {
+		struct ice_tx_buf *tx_buf = &xdp_ring->tx_buf[ntc];
 
+		/* bytecount holds size of head + frags */
 		total_bytes += tx_buf->bytecount;
-		/* normally tx_buf->gso_segs was taken but at this point
-		 * it's always 1 for us
-		 */
+		frags = tx_buf->nr_frags;
 		total_pkts++;
+		/* count head + frags */
+		ready_frames -= frags + 1;
 
-		page_frag_free(tx_buf->raw_buf);
-		dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma),
-				 dma_unmap_len(tx_buf, len), DMA_TO_DEVICE);
-		dma_unmap_len_set(tx_buf, len, 0);
-		tx_buf->raw_buf = NULL;
-
+		ice_clean_xdp_tx_buf(xdp_ring, tx_buf);
 		ntc++;
-		if (ntc >= xdp_ring->count)
+		if (ntc == cnt)
 			ntc = 0;
+
+		for (int i = 0; i < frags; i++) {
+			tx_buf = &xdp_ring->tx_buf[ntc];
+
+			ice_clean_xdp_tx_buf(xdp_ring, tx_buf);
+			ntc++;
+			if (ntc == cnt)
+				ntc = 0;
+		}
 	}
 
-	next_dd_desc->cmd_type_offset_bsz = 0;
-	xdp_ring->next_dd = xdp_ring->next_dd + tx_thresh;
-	if (xdp_ring->next_dd > xdp_ring->count)
-		xdp_ring->next_dd = tx_thresh - 1;
+	tx_desc->cmd_type_offset_bsz = 0;
 	xdp_ring->next_to_clean = ntc;
 	ice_update_tx_ring_stats(xdp_ring, total_pkts, total_bytes);
+
+	return ret;
 }
 
 /**
- * ice_xmit_xdp_ring - submit single packet to XDP ring for transmission
- * @data: packet data pointer
- * @size: packet data size
+ * __ice_xmit_xdp_ring - submit frame to XDP ring for transmission
+ * @xdp: XDP buffer to be placed onto Tx descriptors
  * @xdp_ring: XDP ring for transmission
  */
-int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring)
+int __ice_xmit_xdp_ring(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring)
 {
-	u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
-	u16 i = xdp_ring->next_to_use;
+	struct skb_shared_info *sinfo = NULL;
+	u32 size = xdp->data_end - xdp->data;
+	struct device *dev = xdp_ring->dev;
+	u32 ntu = xdp_ring->next_to_use;
 	struct ice_tx_desc *tx_desc;
+	struct ice_tx_buf *tx_head;
 	struct ice_tx_buf *tx_buf;
-	dma_addr_t dma;
+	u32 cnt = xdp_ring->count;
+	void *data = xdp->data;
+	u32 nr_frags = 0;
+	u32 free_space;
+	u32 frag = 0;
+
+	free_space = ICE_DESC_UNUSED(xdp_ring);
+
+	if (ICE_DESC_UNUSED(xdp_ring) < ICE_RING_QUARTER(xdp_ring))
+		free_space += ice_clean_xdp_irq(xdp_ring);
+
+	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) {
+			xdp_ring->ring_stats->tx_stats.tx_busy++;
+			return ICE_XDP_CONSUMED;
+		}
+	}
 
-	if (ICE_DESC_UNUSED(xdp_ring) < tx_thresh)
-		ice_clean_xdp_irq(xdp_ring);
+	tx_desc = ICE_TX_DESC(xdp_ring, ntu);
+	tx_head = &xdp_ring->tx_buf[ntu];
+	tx_buf = tx_head;
 
-	if (!unlikely(ICE_DESC_UNUSED(xdp_ring))) {
-		xdp_ring->ring_stats->tx_stats.tx_busy++;
-		return ICE_XDP_CONSUMED;
-	}
+	for (;;) {
+		dma_addr_t dma;
 
-	dma = dma_map_single(xdp_ring->dev, data, size, DMA_TO_DEVICE);
-	if (dma_mapping_error(xdp_ring->dev, dma))
-		return ICE_XDP_CONSUMED;
+		dma = dma_map_single(dev, data, size, DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, dma))
+			goto dma_unmap;
 
-	tx_buf = &xdp_ring->tx_buf[i];
-	tx_buf->bytecount = size;
-	tx_buf->gso_segs = 1;
-	tx_buf->raw_buf = data;
+		/* record length, and DMA address */
+		dma_unmap_len_set(tx_buf, len, size);
+		dma_unmap_addr_set(tx_buf, dma, dma);
 
-	/* record length, and DMA address */
-	dma_unmap_len_set(tx_buf, len, size);
-	dma_unmap_addr_set(tx_buf, dma, dma);
+		tx_desc->buf_addr = cpu_to_le64(dma);
+		tx_desc->cmd_type_offset_bsz = ice_build_ctob(0, 0, size, 0);
+		tx_buf->raw_buf = data;
 
-	tx_desc = ICE_TX_DESC(xdp_ring, i);
-	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);
+		ntu++;
+		if (ntu == cnt)
+			ntu = 0;
 
-	xdp_ring->xdp_tx_active++;
-	i++;
-	if (i == xdp_ring->count) {
-		i = 0;
-		tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs);
-		tx_desc->cmd_type_offset_bsz |=
-			cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S);
-		xdp_ring->next_rs = tx_thresh - 1;
-	}
-	xdp_ring->next_to_use = i;
+		if (frag == nr_frags)
+			break;
+
+		tx_desc = ICE_TX_DESC(xdp_ring, ntu);
+		tx_buf = &xdp_ring->tx_buf[ntu];
 
-	if (i > xdp_ring->next_rs) {
-		tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs);
-		tx_desc->cmd_type_offset_bsz |=
-			cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S);
-		xdp_ring->next_rs += tx_thresh;
+		data = skb_frag_address(&sinfo->frags[frag]);
+		size = skb_frag_size(&sinfo->frags[frag]);
+		frag++;
 	}
 
+	/* store info about bytecount and frag count in first desc */
+	tx_head->bytecount = xdp_get_buff_len(xdp);
+	tx_head->nr_frags = nr_frags;
+
+	/* 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);
+
+	xdp_ring->xdp_tx_active++;
+	xdp_ring->next_to_use = ntu;
+
 	return ICE_XDP_TX;
+
+dma_unmap:
+	for (;;) {
+		tx_buf = &xdp_ring->tx_buf[ntu];
+		dma_unmap_page(dev, dma_unmap_addr(tx_buf, dma),
+			       dma_unmap_len(tx_buf, len), DMA_TO_DEVICE);
+		dma_unmap_len_set(tx_buf, len, 0);
+		if (tx_buf == tx_head)
+			break;
+
+		if (!ntu)
+			ntu += cnt;
+		ntu--;
+	}
+	return ICE_XDP_CONSUMED;
+}
+
+/**
+ * ice_xmit_xdp_ring - submit frame to XDP ring for transmission
+ * @xdpf: XDP frame that will be converted to XDP buff
+ * @xdp_ring: XDP ring for transmission
+ */
+int ice_xmit_xdp_ring(struct xdp_frame *xdpf, struct ice_tx_ring *xdp_ring)
+{
+	struct xdp_buff xdp;
+
+	xdp_convert_frame_to_buff(xdpf, &xdp);
+	return __ice_xmit_xdp_ring(&xdp, xdp_ring);
 }
 
 /**
@@ -342,7 +421,7 @@ int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring)
 	if (unlikely(!xdpf))
 		return ICE_XDP_CONSUMED;
 
-	return ice_xmit_xdp_ring(xdpf->data, xdpf->len, xdp_ring);
+	return ice_xmit_xdp_ring(xdpf, xdp_ring);
 }
 
 /**
@@ -354,14 +433,21 @@ int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring)
  * should be called when a batch of packets has been processed in the
  * napi loop.
  */
-void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res)
+void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res,
+			 u32 first_idx)
 {
+	struct ice_tx_buf *tx_buf = &xdp_ring->tx_buf[first_idx];
+
 	if (xdp_res & ICE_XDP_REDIR)
 		xdp_do_flush_map();
 
 	if (xdp_res & ICE_XDP_TX) {
 		if (static_branch_unlikely(&ice_xdp_locking_key))
 			spin_lock(&xdp_ring->tx_lock);
+		/* store index of descriptor with RS bit set in the first
+		 * ice_tx_buf of given NAPI batch
+		 */
+		tx_buf->rs_idx = ice_set_rs_bit(xdp_ring);
 		ice_xdp_ring_update_tail(xdp_ring);
 		if (static_branch_unlikely(&ice_xdp_locking_key))
 			spin_unlock(&xdp_ring->tx_lock);