ice: xsk: Improve AF_XDP ZC Tx and use batching API

Apply the logic that was done for regular XDP from commit 9610bd988df9
("ice: optimize XDP_TX workloads") to the ZC side of the driver. On top
of that, introduce batching to Tx that is inspired by i40e's
implementation with adjustments to the cleaning logic - take into the
account NAPI budget in ice_clean_xdp_irq_zc().

Separating the stats structs onto separate cache lines seemed to improve
the performance.

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/20220125160446.78976-8-maciej.fijalkowski@intel.com

1 files changed, 167 insertions, 89 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index b12079a7ef8a..8b6acb4afb7f 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -679,134 +679,212 @@ construct_skb:
 }
 
 /**
- * ice_xmit_zc - Completes AF_XDP entries, and cleans XDP entries
+ * ice_clean_xdp_tx_buf - Free and unmap XDP Tx buffer
  * @xdp_ring: XDP Tx ring
- * @budget: max number of frames to xmit
+ * @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)
+{
+	xdp_return_frame((struct xdp_frame *)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);
+}
+
+/**
+ * ice_clean_xdp_irq_zc - Reclaim resources after transmit completes on XDP ring
+ * @xdp_ring: XDP ring to clean
+ * @napi_budget: amount of descriptors that NAPI allows us to clean
  *
- * Returns true if cleanup/transmission is done.
+ * Returns count of cleaned descriptors
  */
-static bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, int budget)
+static u16 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring, int napi_budget)
 {
-	struct ice_tx_desc *tx_desc = NULL;
-	bool work_done = true;
-	struct xdp_desc desc;
-	dma_addr_t dma;
+	u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
+	int budget = napi_budget / tx_thresh;
+	u16 ntc = xdp_ring->next_to_clean;
+	u16 next_dd = xdp_ring->next_dd;
+	u16 cleared_dds = 0;
 
-	while (likely(budget-- > 0)) {
+	do {
+		struct ice_tx_desc *next_dd_desc;
+		u16 desc_cnt = xdp_ring->count;
 		struct ice_tx_buf *tx_buf;
+		u32 xsk_frames;
+		u16 i;
 
-		if (unlikely(!ICE_DESC_UNUSED(xdp_ring))) {
-			xdp_ring->tx_stats.tx_busy++;
-			work_done = false;
-			break;
-		}
-
-		tx_buf = &xdp_ring->tx_buf[xdp_ring->next_to_use];
-
-		if (!xsk_tx_peek_desc(xdp_ring->xsk_pool, &desc))
+		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)))
 			break;
 
-		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc.addr);
-		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma,
-						 desc.len);
+		cleared_dds++;
+		xsk_frames = 0;
 
-		tx_buf->bytecount = desc.len;
+		for (i = 0; i < tx_thresh; i++) {
+			tx_buf = &xdp_ring->tx_buf[ntc];
 
-		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_TXD_LAST_DESC_CMD, 0, desc.len, 0);
+			if (tx_buf->raw_buf) {
+				ice_clean_xdp_tx_buf(xdp_ring, tx_buf);
+				tx_buf->raw_buf = NULL;
+			} else {
+				xsk_frames++;
+			}
 
-		xdp_ring->next_to_use++;
-		if (xdp_ring->next_to_use == xdp_ring->count)
-			xdp_ring->next_to_use = 0;
-	}
+			ntc++;
+			if (ntc >= xdp_ring->count)
+				ntc = 0;
+		}
+		if (xsk_frames)
+			xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
+		next_dd_desc->cmd_type_offset_bsz = 0;
+		next_dd = next_dd + tx_thresh;
+		if (next_dd >= desc_cnt)
+			next_dd = tx_thresh - 1;
+	} while (budget--);
 
-	if (tx_desc) {
-		ice_xdp_ring_update_tail(xdp_ring);
-		xsk_tx_release(xdp_ring->xsk_pool);
-	}
+	xdp_ring->next_to_clean = ntc;
+	xdp_ring->next_dd = next_dd;
 
-	return budget > 0 && work_done;
+	return cleared_dds * tx_thresh;
 }
 
 /**
- * ice_clean_xdp_tx_buf - Free and unmap XDP Tx buffer
- * @xdp_ring: XDP Tx ring
- * @tx_buf: Tx buffer to clean
+ * ice_xmit_pkt - produce a single HW Tx descriptor out of AF_XDP descriptor
+ * @xdp_ring: XDP ring to produce the HW Tx descriptor on
+ * @desc: AF_XDP descriptor to pull the DMA address and length from
+ * @total_bytes: bytes accumulator that will be used for stats update
  */
-static void
-ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf)
+static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
+			 unsigned int *total_bytes)
 {
-	xdp_return_frame((struct xdp_frame *)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);
+	struct ice_tx_desc *tx_desc;
+	dma_addr_t dma;
+
+	dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr);
+	xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len);
+
+	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,
+						      0, desc->len, 0);
+
+	*total_bytes += desc->len;
 }
 
 /**
- * ice_clean_tx_irq_zc - Completes AF_XDP entries, and cleans XDP entries
- * @xdp_ring: XDP Tx ring
- * @budget: NAPI budget
- *
- * Returns true if cleanup/tranmission is done.
+ * ice_xmit_pkt_batch - produce a batch of HW Tx descriptors out of AF_XDP descriptors
+ * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from
+ * @total_bytes: bytes accumulator that will be used for stats update
  */
-bool ice_clean_tx_irq_zc(struct ice_tx_ring *xdp_ring, int budget)
+static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
+			       unsigned int *total_bytes)
 {
-	int total_packets = 0, total_bytes = 0;
-	s16 ntc = xdp_ring->next_to_clean;
+	u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
+	u16 ntu = xdp_ring->next_to_use;
 	struct ice_tx_desc *tx_desc;
-	struct ice_tx_buf *tx_buf;
-	u32 xsk_frames = 0;
-	bool xmit_done;
+	u32 i;
 
-	tx_desc = ICE_TX_DESC(xdp_ring, ntc);
-	tx_buf = &xdp_ring->tx_buf[ntc];
-	ntc -= xdp_ring->count;
+	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+		dma_addr_t dma;
 
-	do {
-		if (!(tx_desc->cmd_type_offset_bsz &
-		      cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)))
-			break;
+		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, descs[i].addr);
+		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, descs[i].len);
 
-		total_bytes += tx_buf->bytecount;
-		total_packets++;
+		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, descs[i].len, 0);
 
-		if (tx_buf->raw_buf) {
-			ice_clean_xdp_tx_buf(xdp_ring, tx_buf);
-			tx_buf->raw_buf = NULL;
-		} else {
-			xsk_frames++;
-		}
+		*total_bytes += descs[i].len;
+	}
 
-		tx_desc->cmd_type_offset_bsz = 0;
-		tx_buf++;
-		tx_desc++;
-		ntc++;
+	xdp_ring->next_to_use = ntu;
 
-		if (unlikely(!ntc)) {
-			ntc -= xdp_ring->count;
-			tx_buf = xdp_ring->tx_buf;
-			tx_desc = ICE_TX_DESC(xdp_ring, 0);
-		}
+	if (xdp_ring->next_to_use > 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;
+	}
+}
 
-		prefetch(tx_desc);
+/**
+ * ice_fill_tx_hw_ring - produce the number of Tx descriptors onto ring
+ * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from
+ * @nb_pkts: count of packets to be send
+ * @total_bytes: bytes accumulator that will be used for stats update
+ */
+static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
+				u32 nb_pkts, unsigned int *total_bytes)
+{
+	u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
+	u32 batched, leftover, i;
+
+	batched = ALIGN_DOWN(nb_pkts, PKTS_PER_BATCH);
+	leftover = nb_pkts & (PKTS_PER_BATCH - 1);
+	for (i = 0; i < batched; i += PKTS_PER_BATCH)
+		ice_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes);
+	for (; i < batched + leftover; i++)
+		ice_xmit_pkt(xdp_ring, &descs[i], total_bytes);
+
+	if (xdp_ring->next_to_use > xdp_ring->next_rs) {
+		struct ice_tx_desc *tx_desc;
+
+		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;
+	}
+}
 
-	} while (likely(--budget));
+/**
+ * ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring
+ * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @budget: number of free descriptors on HW Tx ring that can be used
+ * @napi_budget: amount of descriptors that NAPI allows us to clean
+ *
+ * Returns true if there is no more work that needs to be done, false otherwise
+ */
+bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, u32 budget, int napi_budget)
+{
+	struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs;
+	u16 tx_thresh = ICE_RING_QUARTER(xdp_ring);
+	u32 nb_pkts, nb_processed = 0;
+	unsigned int total_bytes = 0;
+
+	if (budget < tx_thresh)
+		budget += ice_clean_xdp_irq_zc(xdp_ring, napi_budget);
+
+	nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget);
+	if (!nb_pkts)
+		return true;
+
+	if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) {
+		struct ice_tx_desc *tx_desc;
+
+		nb_processed = xdp_ring->count - xdp_ring->next_to_use;
+		ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes);
+		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 = 0;
+	}
 
-	ntc += xdp_ring->count;
-	xdp_ring->next_to_clean = ntc;
+	ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed,
+			    &total_bytes);
 
-	if (xsk_frames)
-		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
+	ice_xdp_ring_update_tail(xdp_ring);
+	ice_update_tx_ring_stats(xdp_ring, nb_pkts, total_bytes);
 
 	if (xsk_uses_need_wakeup(xdp_ring->xsk_pool))
 		xsk_set_tx_need_wakeup(xdp_ring->xsk_pool);
 
-	ice_update_tx_ring_stats(xdp_ring, total_packets, total_bytes);
-	xmit_done = ice_xmit_zc(xdp_ring, ICE_DFLT_IRQ_WORK);
-
-	return budget > 0 && xmit_done;
+	return nb_pkts < budget;
 }
 
 /**