1 files changed, 393 insertions, 174 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index bb9a80847298..056c904b83cc 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -12,6 +12,11 @@
 #include "ice_txrx_lib.h"
 #include "ice_lib.h"
 
+static struct xdp_buff **ice_xdp_buf(struct ice_rx_ring *rx_ring, u32 idx)
+{
+	return &rx_ring->xdp_buf[idx];
+}
+
 /**
  * ice_qp_reset_stats - Resets all stats for rings of given index
  * @vsi: VSI that contains rings of interest
@@ -36,8 +41,10 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx)
 static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx)
 {
 	ice_clean_tx_ring(vsi->tx_rings[q_idx]);
-	if (ice_is_xdp_ena_vsi(vsi))
+	if (ice_is_xdp_ena_vsi(vsi)) {
+		synchronize_rcu();
 		ice_clean_tx_ring(vsi->xdp_rings[q_idx]);
+	}
 	ice_clean_rx_ring(vsi->rx_rings[q_idx]);
 }
 
@@ -185,6 +192,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 	err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true);
 	if (err)
 		return err;
+	ice_clean_rx_ring(rx_ring);
 
 	ice_qvec_toggle_napi(vsi, q_vector, false);
 	ice_qp_clean_rings(vsi, q_idx);
@@ -236,7 +244,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
 		if (err)
 			goto free_buf;
 		ice_set_ring_xdp(xdp_ring);
-		xdp_ring->xsk_pool = ice_tx_xsk_pool(xdp_ring);
+		ice_tx_xsk_pool(vsi, q_idx);
 	}
 
 	err = ice_vsi_cfg_rxq(rx_ring);
@@ -310,6 +318,62 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 }
 
 /**
+ * ice_realloc_rx_xdp_bufs - reallocate for either XSK or normal buffer
+ * @rx_ring: Rx ring
+ * @pool_present: is pool for XSK present
+ *
+ * Try allocating memory and return ENOMEM, if failed to allocate.
+ * If allocation was successful, substitute buffer with allocated one.
+ * Returns 0 on success, negative on failure
+ */
+static int
+ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present)
+{
+	size_t elem_size = pool_present ? sizeof(*rx_ring->xdp_buf) :
+					  sizeof(*rx_ring->rx_buf);
+	void *sw_ring = kcalloc(rx_ring->count, elem_size, GFP_KERNEL);
+
+	if (!sw_ring)
+		return -ENOMEM;
+
+	if (pool_present) {
+		kfree(rx_ring->rx_buf);
+		rx_ring->rx_buf = NULL;
+		rx_ring->xdp_buf = sw_ring;
+	} else {
+		kfree(rx_ring->xdp_buf);
+		rx_ring->xdp_buf = NULL;
+		rx_ring->rx_buf = sw_ring;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_realloc_zc_buf - reallocate XDP ZC queue pairs
+ * @vsi: Current VSI
+ * @zc: is zero copy set
+ *
+ * Reallocate buffer for rx_rings that might be used by XSK.
+ * XDP requires more memory, than rx_buf provides.
+ * Returns 0 on success, negative on failure
+ */
+int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc)
+{
+	struct ice_rx_ring *rx_ring;
+	unsigned long q;
+
+	for_each_set_bit(q, vsi->af_xdp_zc_qps,
+			 max_t(int, vsi->alloc_txq, vsi->alloc_rxq)) {
+		rx_ring = vsi->rx_rings[q];
+		if (ice_realloc_rx_xdp_bufs(rx_ring, zc))
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/**
  * ice_xsk_pool_setup - enable/disable a buffer pool region depending on its state
  * @vsi: Current VSI
  * @pool: buffer pool to enable/associate to a ring, NULL to disable
@@ -322,14 +386,26 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 	bool if_running, pool_present = !!pool;
 	int ret = 0, pool_failure = 0;
 
+	if (qid >= vsi->num_rxq || qid >= vsi->num_txq) {
+		netdev_err(vsi->netdev, "Please use queue id in scope of combined queues count\n");
+		pool_failure = -EINVAL;
+		goto failure;
+	}
+
 	if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi);
 
 	if (if_running) {
+		struct ice_rx_ring *rx_ring = vsi->rx_rings[qid];
+
 		ret = ice_qp_dis(vsi, qid);
 		if (ret) {
 			netdev_err(vsi->netdev, "ice_qp_dis error = %d\n", ret);
 			goto xsk_pool_if_up;
 		}
+
+		ret = ice_realloc_rx_xdp_bufs(rx_ring, pool_present);
+		if (ret)
+			goto xsk_pool_if_up;
 	}
 
 	pool_failure = pool_present ? ice_xsk_pool_enable(vsi, pool, qid) :
@@ -339,11 +415,12 @@ xsk_pool_if_up:
 	if (if_running) {
 		ret = ice_qp_ena(vsi, qid);
 		if (!ret && pool_present)
-			napi_schedule(&vsi->xdp_rings[qid]->q_vector->napi);
+			napi_schedule(&vsi->rx_rings[qid]->xdp_ring->q_vector->napi);
 		else if (ret)
 			netdev_err(vsi->netdev, "ice_qp_ena error = %d\n", ret);
 	}
 
+failure:
 	if (pool_failure) {
 		netdev_err(vsi->netdev, "Could not %sable buffer pool, error = %d\n",
 			   pool_present ? "en" : "dis", pool_failure);
@@ -354,33 +431,28 @@ xsk_pool_if_up:
 }
 
 /**
- * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
- * @rx_ring: Rx ring
+ * ice_fill_rx_descs - pick buffers from XSK buffer pool and use it
+ * @pool: XSK Buffer pool to pull the buffers from
+ * @xdp: SW ring of xdp_buff that will hold the buffers
+ * @rx_desc: Pointer to Rx descriptors that will be filled
  * @count: The number of buffers to allocate
  *
  * This function allocates a number of Rx buffers from the fill ring
  * or the internal recycle mechanism and places them on the Rx ring.
  *
- * Returns true if all allocations were successful, false if any fail.
+ * Note that ring wrap should be handled by caller of this function.
+ *
+ * Returns the amount of allocated Rx descriptors
  */
-bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
+			     union ice_32b_rx_flex_desc *rx_desc, u16 count)
 {
-	union ice_32b_rx_flex_desc *rx_desc;
-	u16 ntu = rx_ring->next_to_use;
-	struct xdp_buff **xdp;
-	u32 nb_buffs, i;
 	dma_addr_t dma;
+	u16 buffs;
+	int i;
 
-	rx_desc = ICE_RX_DESC(rx_ring, ntu);
-	xdp = &rx_ring->xdp_buf[ntu];
-
-	nb_buffs = min_t(u16, count, rx_ring->count - ntu);
-	nb_buffs = xsk_buff_alloc_batch(rx_ring->xsk_pool, xdp, nb_buffs);
-	if (!nb_buffs)
-		return false;
-
-	i = nb_buffs;
-	while (i--) {
+	buffs = xsk_buff_alloc_batch(pool, xdp, count);
+	for (i = 0; i < buffs; i++) {
 		dma = xsk_buff_xdp_get_dma(*xdp);
 		rx_desc->read.pkt_addr = cpu_to_le64(dma);
 		rx_desc->wb.status_error0 = 0;
@@ -389,18 +461,81 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 		xdp++;
 	}
 
-	ntu += nb_buffs;
-	if (ntu == rx_ring->count) {
+	return buffs;
+}
+
+/**
+ * __ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
+ * @rx_ring: Rx ring
+ * @count: The number of buffers to allocate
+ *
+ * Place the @count of descriptors onto Rx ring. Handle the ring wrap
+ * for case where space from next_to_use up to the end of ring is less
+ * than @count. Finally do a tail bump.
+ *
+ * Returns true if all allocations were successful, false if any fail.
+ */
+static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+{
+	u32 nb_buffs_extra = 0, nb_buffs = 0;
+	union ice_32b_rx_flex_desc *rx_desc;
+	u16 ntu = rx_ring->next_to_use;
+	u16 total_count = count;
+	struct xdp_buff **xdp;
+
+	rx_desc = ICE_RX_DESC(rx_ring, ntu);
+	xdp = ice_xdp_buf(rx_ring, ntu);
+
+	if (ntu + count >= rx_ring->count) {
+		nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp,
+						   rx_desc,
+						   rx_ring->count - ntu);
+		if (nb_buffs_extra != rx_ring->count - ntu) {
+			ntu += nb_buffs_extra;
+			goto exit;
+		}
 		rx_desc = ICE_RX_DESC(rx_ring, 0);
-		xdp = rx_ring->xdp_buf;
+		xdp = ice_xdp_buf(rx_ring, 0);
 		ntu = 0;
+		count -= nb_buffs_extra;
+		ice_release_rx_desc(rx_ring, 0);
 	}
 
-	/* clear the status bits for the next_to_use descriptor */
-	rx_desc->wb.status_error0 = 0;
-	ice_release_rx_desc(rx_ring, ntu);
+	nb_buffs = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, count);
+
+	ntu += nb_buffs;
+	if (ntu == rx_ring->count)
+		ntu = 0;
 
-	return count == nb_buffs;
+exit:
+	if (rx_ring->next_to_use != ntu)
+		ice_release_rx_desc(rx_ring, ntu);
+
+	return total_count == (nb_buffs_extra + nb_buffs);
+}
+
+/**
+ * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
+ * @rx_ring: Rx ring
+ * @count: The number of buffers to allocate
+ *
+ * Wrapper for internal allocation routine; figure out how many tail
+ * bumps should take place based on the given threshold
+ *
+ * Returns true if all calls to internal alloc routine succeeded
+ */
+bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+{
+	u16 rx_thresh = ICE_RING_QUARTER(rx_ring);
+	u16 leftover, i, tail_bumps;
+
+	tail_bumps = count / rx_thresh;
+	leftover = count - (tail_bumps * rx_thresh);
+
+	for (i = 0; i < tail_bumps; i++)
+		if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh))
+			return false;
+	return __ice_alloc_rx_bufs_zc(rx_ring, leftover);
 }
 
 /**
@@ -419,33 +554,35 @@ static void ice_bump_ntc(struct ice_rx_ring *rx_ring)
 /**
  * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer
  * @rx_ring: Rx ring
- * @xdp_arr: Pointer to the SW ring of xdp_buff pointers
+ * @xdp: Pointer to XDP buffer
  *
  * This function allocates a new skb from a zero-copy Rx buffer.
  *
  * Returns the skb on success, NULL on failure.
  */
 static struct sk_buff *
-ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff **xdp_arr)
+ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 {
-	struct xdp_buff *xdp = *xdp_arr;
+	unsigned int totalsize = xdp->data_end - xdp->data_meta;
 	unsigned int metasize = xdp->data - xdp->data_meta;
-	unsigned int datasize = xdp->data_end - xdp->data;
-	unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start;
 	struct sk_buff *skb;
 
-	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, datasize_hard,
+	net_prefetch(xdp->data_meta);
+
+	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize,
 			       GFP_ATOMIC | __GFP_NOWARN);
 	if (unlikely(!skb))
 		return NULL;
 
-	skb_reserve(skb, xdp->data - xdp->data_hard_start);
-	memcpy(__skb_put(skb, datasize), xdp->data, datasize);
-	if (metasize)
+	memcpy(__skb_put(skb, totalsize), xdp->data_meta,
+	       ALIGN(totalsize, sizeof(long)));
+
+	if (metasize) {
 		skb_metadata_set(skb, metasize);
+		__skb_pull(skb, metasize);
+	}
 
 	xsk_buff_free(xdp);
-	*xdp_arr = NULL;
 	return skb;
 }
 
@@ -469,9 +606,13 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 
 	if (likely(act == XDP_REDIRECT)) {
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		if (err)
-			goto out_failure;
-		return ICE_XDP_REDIR;
+		if (!err)
+			return ICE_XDP_REDIR;
+		if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
+			result = ICE_XDP_EXIT;
+		else
+			result = ICE_XDP_CONSUMED;
+		goto out_failure;
 	}
 
 	switch (act) {
@@ -482,15 +623,16 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 		if (result == ICE_XDP_CONSUMED)
 			goto out_failure;
 		break;
+	case XDP_DROP:
+		result = ICE_XDP_CONSUMED;
+		break;
 	default:
-		bpf_warn_invalid_xdp_action(act);
+		bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
 		fallthrough;
 	case XDP_ABORTED:
+		result = ICE_XDP_CONSUMED;
 out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
-		fallthrough;
-	case XDP_DROP:
-		result = ICE_XDP_CONSUMED;
 		break;
 	}
 
@@ -507,11 +649,11 @@ out_failure:
 int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
-	u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
 	struct ice_tx_ring *xdp_ring;
 	unsigned int xdp_xmit = 0;
 	struct bpf_prog *xdp_prog;
 	bool failure = false;
+	int entries_to_alloc;
 
 	/* ZC patch is enabled only when XDP program is set,
 	 * so here it can not be NULL
@@ -522,7 +664,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		union ice_32b_rx_flex_desc *rx_desc;
 		unsigned int size, xdp_res = 0;
-		struct xdp_buff **xdp;
+		struct xdp_buff *xdp;
 		struct sk_buff *skb;
 		u16 stat_err_bits;
 		u16 vlan_tag = 0;
@@ -531,7 +673,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean);
 
 		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S);
-		if (!ice_test_staterr(rx_desc, stat_err_bits))
+		if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits))
 			break;
 
 		/* This memory barrier is needed to keep us from reading
@@ -540,31 +682,43 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
-		size = le16_to_cpu(rx_desc->wb.pkt_len) &
-				   ICE_RX_FLX_DESC_PKT_LEN_M;
-		if (!size)
+		if (unlikely(rx_ring->next_to_clean == rx_ring->next_to_use))
 			break;
 
-		xdp = &rx_ring->xdp_buf[rx_ring->next_to_clean];
-		xsk_buff_set_size(*xdp, size);
-		xsk_buff_dma_sync_for_cpu(*xdp, rx_ring->xsk_pool);
+		xdp = *ice_xdp_buf(rx_ring, rx_ring->next_to_clean);
 
-		xdp_res = ice_run_xdp_zc(rx_ring, *xdp, xdp_prog, xdp_ring);
-		if (xdp_res) {
-			if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))
-				xdp_xmit |= xdp_res;
-			else
-				xsk_buff_free(*xdp);
+		size = le16_to_cpu(rx_desc->wb.pkt_len) &
+				   ICE_RX_FLX_DESC_PKT_LEN_M;
+		if (!size) {
+			xdp->data = NULL;
+			xdp->data_end = NULL;
+			xdp->data_hard_start = NULL;
+			xdp->data_meta = NULL;
+			goto construct_skb;
+		}
 
-			*xdp = NULL;
-			total_rx_bytes += size;
-			total_rx_packets++;
-			cleaned_count++;
+		xsk_buff_set_size(xdp, size);
+		xsk_buff_dma_sync_for_cpu(xdp, rx_ring->xsk_pool);
 
-			ice_bump_ntc(rx_ring);
-			continue;
+		xdp_res = ice_run_xdp_zc(rx_ring, xdp, xdp_prog, xdp_ring);
+		if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) {
+			xdp_xmit |= xdp_res;
+		} else if (xdp_res == ICE_XDP_EXIT) {
+			failure = true;
+			break;
+		} else if (xdp_res == ICE_XDP_CONSUMED) {
+			xsk_buff_free(xdp);
+		} else if (xdp_res == ICE_XDP_PASS) {
+			goto construct_skb;
 		}
 
+		total_rx_bytes += size;
+		total_rx_packets++;
+
+		ice_bump_ntc(rx_ring);
+		continue;
+
+construct_skb:
 		/* XDP_PASS path */
 		skb = ice_construct_skb_zc(rx_ring, xdp);
 		if (!skb) {
@@ -572,7 +726,6 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 			break;
 		}
 
-		cleaned_count++;
 		ice_bump_ntc(rx_ring);
 
 		if (eth_skb_pad(skb)) {
@@ -583,9 +736,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		total_rx_bytes += skb->len;
 		total_rx_packets++;
 
-		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_L2TAG1P_S);
-		if (ice_test_staterr(rx_desc, stat_err_bits))
-			vlan_tag = le16_to_cpu(rx_desc->wb.l2tag1);
+		vlan_tag = ice_get_vlan_tag_from_rx_desc(rx_desc);
 
 		rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
 				       ICE_RX_FLEX_DESC_PTYPE_M;
@@ -594,8 +745,9 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		ice_receive_skb(rx_ring, skb, vlan_tag);
 	}
 
-	if (cleaned_count >= ICE_RX_BUF_WRITE)
-		failure = !ice_alloc_rx_bufs_zc(rx_ring, cleaned_count);
+	entries_to_alloc = ICE_DESC_UNUSED(rx_ring);
+	if (entries_to_alloc > ICE_RING_QUARTER(rx_ring))
+		failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc);
 
 	ice_finalize_xdp_rx(xdp_ring, xdp_xmit);
 	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
@@ -613,58 +765,6 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 }
 
 /**
- * ice_xmit_zc - Completes AF_XDP entries, and cleans XDP entries
- * @xdp_ring: XDP Tx ring
- * @budget: max number of frames to xmit
- *
- * Returns true if cleanup/transmission is done.
- */
-static bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, int budget)
-{
-	struct ice_tx_desc *tx_desc = NULL;
-	bool work_done = true;
-	struct xdp_desc desc;
-	dma_addr_t dma;
-
-	while (likely(budget-- > 0)) {
-		struct ice_tx_buf *tx_buf;
-
-		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))
-			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);
-
-		tx_buf->bytecount = 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_TXD_LAST_DESC_CMD, 0, desc.len, 0);
-
-		xdp_ring->next_to_use++;
-		if (xdp_ring->next_to_use == xdp_ring->count)
-			xdp_ring->next_to_use = 0;
-	}
-
-	if (tx_desc) {
-		ice_xdp_ring_update_tail(xdp_ring);
-		xsk_tx_release(xdp_ring->xsk_pool);
-	}
-
-	return budget > 0 && work_done;
-}
-
-/**
  * ice_clean_xdp_tx_buf - Free and unmap XDP Tx buffer
  * @xdp_ring: XDP Tx ring
  * @tx_buf: Tx buffer to clean
@@ -673,38 +773,45 @@ 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);
+	xdp_ring->xdp_tx_active--;
 	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_tx_irq_zc - Completes AF_XDP entries, and cleans XDP entries
+ * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ
  * @xdp_ring: XDP Tx ring
- * @budget: NAPI budget
- *
- * Returns true if cleanup/tranmission is done.
  */
-bool ice_clean_tx_irq_zc(struct ice_tx_ring *xdp_ring, int budget)
+static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
 {
-	int total_packets = 0, total_bytes = 0;
-	s16 ntc = xdp_ring->next_to_clean;
+	u16 ntc = xdp_ring->next_to_clean;
 	struct ice_tx_desc *tx_desc;
+	u16 cnt = xdp_ring->count;
 	struct ice_tx_buf *tx_buf;
-	u32 xsk_frames = 0;
-	bool xmit_done;
+	u16 xsk_frames = 0;
+	u16 last_rs;
+	int i;
 
-	tx_desc = ICE_TX_DESC(xdp_ring, ntc);
-	tx_buf = &xdp_ring->tx_buf[ntc];
-	ntc -= xdp_ring->count;
+	last_rs = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : cnt - 1;
+	tx_desc = ICE_TX_DESC(xdp_ring, last_rs);
+	if ((tx_desc->cmd_type_offset_bsz &
+	    cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) {
+		if (last_rs >= ntc)
+			xsk_frames = last_rs - ntc + 1;
+		else
+			xsk_frames = last_rs + cnt - ntc + 1;
+	}
 
-	do {
-		if (!(tx_desc->cmd_type_offset_bsz &
-		      cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)))
-			break;
+	if (!xsk_frames)
+		return;
 
-		total_bytes += tx_buf->bytecount;
-		total_packets++;
+	if (likely(!xdp_ring->xdp_tx_active))
+		goto skip;
+
+	ntc = xdp_ring->next_to_clean;
+	for (i = 0; i < xsk_frames; i++) {
+		tx_buf = &xdp_ring->tx_buf[ntc];
 
 		if (tx_buf->raw_buf) {
 			ice_clean_xdp_tx_buf(xdp_ring, tx_buf);
@@ -713,34 +820,145 @@ bool ice_clean_tx_irq_zc(struct ice_tx_ring *xdp_ring, int budget)
 			xsk_frames++;
 		}
 
-		tx_desc->cmd_type_offset_bsz = 0;
-		tx_buf++;
-		tx_desc++;
 		ntc++;
+		if (ntc >= xdp_ring->count)
+			ntc = 0;
+	}
+skip:
+	tx_desc->cmd_type_offset_bsz = 0;
+	xdp_ring->next_to_clean += xsk_frames;
+	if (xdp_ring->next_to_clean >= cnt)
+		xdp_ring->next_to_clean -= cnt;
+	if (xsk_frames)
+		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
+}
 
-		if (unlikely(!ntc)) {
-			ntc -= xdp_ring->count;
-			tx_buf = xdp_ring->tx_buf;
-			tx_desc = ICE_TX_DESC(xdp_ring, 0);
-		}
+/**
+ * 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_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
+			 unsigned int *total_bytes)
+{
+	struct ice_tx_desc *tx_desc;
+	dma_addr_t dma;
 
-		prefetch(tx_desc);
+	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);
 
-	} while (likely(--budget));
+	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);
 
-	ntc += xdp_ring->count;
-	xdp_ring->next_to_clean = ntc;
+	*total_bytes += desc->len;
+}
 
-	if (xsk_frames)
-		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
+/**
+ * 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
+ */
+static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
+			       unsigned int *total_bytes)
+{
+	u16 ntu = xdp_ring->next_to_use;
+	struct ice_tx_desc *tx_desc;
+	u32 i;
+
+	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+		dma_addr_t dma;
+
+		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);
+
+		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);
+
+		*total_bytes += descs[i].len;
+	}
+
+	xdp_ring->next_to_use = ntu;
+}
+
+/**
+ * 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)
+{
+	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);
+}
+
+/**
+ * ice_set_rs_bit - set RS bit on last produced descriptor (one behind current NTU)
+ * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ */
+static void ice_set_rs_bit(struct ice_tx_ring *xdp_ring)
+{
+	u16 ntu = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : xdp_ring->count - 1;
+	struct ice_tx_desc *tx_desc;
+
+	tx_desc = ICE_TX_DESC(xdp_ring, ntu);
+	tx_desc->cmd_type_offset_bsz |=
+		cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S);
+}
+
+/**
+ * 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
+ *
+ * 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)
+{
+	struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs;
+	u32 nb_pkts, nb_processed = 0;
+	unsigned int total_bytes = 0;
+	int budget;
+
+	ice_clean_xdp_irq_zc(xdp_ring);
+
+	budget = ICE_DESC_UNUSED(xdp_ring);
+	budget = min_t(u16, budget, ICE_RING_QUARTER(xdp_ring));
+
+	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) {
+		nb_processed = xdp_ring->count - xdp_ring->next_to_use;
+		ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes);
+		xdp_ring->next_to_use = 0;
+	}
+
+	ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed,
+			    &total_bytes);
+
+	ice_set_rs_bit(xdp_ring);
+	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;
 }
 
 /**
@@ -760,19 +978,19 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_tx_ring *ring;
 
-	if (test_bit(ICE_DOWN, vsi->state))
+	if (test_bit(ICE_VSI_DOWN, vsi->state))
 		return -ENETDOWN;
 
 	if (!ice_is_xdp_ena_vsi(vsi))
-		return -ENXIO;
+		return -EINVAL;
 
-	if (queue_id >= vsi->num_txq)
-		return -ENXIO;
+	if (queue_id >= vsi->num_txq || queue_id >= vsi->num_rxq)
+		return -EINVAL;
 
-	if (!vsi->xdp_rings[queue_id]->xsk_pool)
-		return -ENXIO;
+	ring = vsi->rx_rings[queue_id]->xdp_ring;
 
-	ring = vsi->xdp_rings[queue_id];
+	if (!ring->xsk_pool)
+		return -EINVAL;
 
 	/* The idea here is that if NAPI is running, mark a miss, so
 	 * it will run again. If not, trigger an interrupt and
@@ -811,15 +1029,16 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi)
  */
 void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring)
 {
-	u16 i;
-
-	for (i = 0; i < rx_ring->count; i++) {
-		struct xdp_buff **xdp = &rx_ring->xdp_buf[i];
+	u16 ntc = rx_ring->next_to_clean;
+	u16 ntu = rx_ring->next_to_use;
 
-		if (!xdp)
-			continue;
+	while (ntc != ntu) {
+		struct xdp_buff *xdp = *ice_xdp_buf(rx_ring, ntc);
 
-		*xdp = NULL;
+		xsk_buff_free(xdp);
+		ntc++;
+		if (ntc >= rx_ring->count)
+			ntc = 0;
 	}
 }