diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
index 3cf493a51b8d0..e761f12d8901d 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (C) 2023 Intel Corporation */
 
+#include <net/libeth/tx.h>
+
 #include "idpf.h"
 
 /**
@@ -176,6 +178,58 @@ static int idpf_tx_singleq_csum(struct sk_buff *skb,
 	return 1;
 }
 
+/**
+ * idpf_tx_singleq_dma_map_error - handle TX DMA map errors
+ * @txq: queue to send buffer on
+ * @skb: send buffer
+ * @first: original first buffer info buffer for packet
+ * @idx: starting point on ring to unwind
+ */
+static void idpf_tx_singleq_dma_map_error(struct idpf_tx_queue *txq,
+					  struct sk_buff *skb,
+					  struct idpf_tx_buf *first, u16 idx)
+{
+	struct libeth_sq_napi_stats ss = { };
+	struct libeth_cq_pp cp = {
+		.dev	= txq->dev,
+		.ss	= &ss,
+	};
+
+	u64_stats_update_begin(&txq->stats_sync);
+	u64_stats_inc(&txq->q_stats.dma_map_errs);
+	u64_stats_update_end(&txq->stats_sync);
+
+	/* clear dma mappings for failed tx_buf map */
+	for (;;) {
+		struct idpf_tx_buf *tx_buf;
+
+		tx_buf = &txq->tx_buf[idx];
+		libeth_tx_complete(tx_buf, &cp);
+		if (tx_buf == first)
+			break;
+		if (idx == 0)
+			idx = txq->desc_count;
+		idx--;
+	}
+
+	if (skb_is_gso(skb)) {
+		union idpf_tx_flex_desc *tx_desc;
+
+		/* If we failed a DMA mapping for a TSO packet, we will have
+		 * used one additional descriptor for a context
+		 * descriptor. Reset that here.
+		 */
+		tx_desc = &txq->flex_tx[idx];
+		memset(tx_desc, 0, sizeof(*tx_desc));
+		if (idx == 0)
+			idx = txq->desc_count;
+		idx--;
+	}
+
+	/* Update tail in case netdev_xmit_more was previously true */
+	idpf_tx_buf_hw_update(txq, idx, false);
+}
+
 /**
  * idpf_tx_singleq_map - Build the Tx base descriptor
  * @tx_q: queue to send buffer on
@@ -216,12 +270,14 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 	for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
 		unsigned int max_data = IDPF_TX_MAX_DESC_DATA_ALIGNED;
 
-		if (dma_mapping_error(tx_q->dev, dma))
-			return idpf_tx_dma_map_error(tx_q, skb, first, i);
+		if (unlikely(dma_mapping_error(tx_q->dev, dma)))
+			return idpf_tx_singleq_dma_map_error(tx_q, skb,
+							     first, i);
 
 		/* record length, and DMA address */
 		dma_unmap_len_set(tx_buf, len, size);
 		dma_unmap_addr_set(tx_buf, dma, dma);
+		tx_buf->type = LIBETH_SQE_FRAG;
 
 		/* align size to end of page */
 		max_data += -dma & (IDPF_TX_MAX_READ_REQ_SIZE - 1);
@@ -235,14 +291,17 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 								  offsets,
 								  max_data,
 								  td_tag);
-			tx_desc++;
-			i++;
-
-			if (i == tx_q->desc_count) {
+			if (unlikely(++i == tx_q->desc_count)) {
+				tx_buf = &tx_q->tx_buf[0];
 				tx_desc = &tx_q->base_tx[0];
 				i = 0;
+			} else {
+				tx_buf++;
+				tx_desc++;
 			}
 
+			tx_buf->type = LIBETH_SQE_EMPTY;
+
 			dma += max_data;
 			size -= max_data;
 
@@ -255,12 +314,14 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 
 		tx_desc->qw1 = idpf_tx_singleq_build_ctob(td_cmd, offsets,
 							  size, td_tag);
-		tx_desc++;
-		i++;
 
-		if (i == tx_q->desc_count) {
+		if (unlikely(++i == tx_q->desc_count)) {
+			tx_buf = &tx_q->tx_buf[0];
 			tx_desc = &tx_q->base_tx[0];
 			i = 0;
+		} else {
+			tx_buf++;
+			tx_desc++;
 		}
 
 		size = skb_frag_size(frag);
@@ -268,8 +329,6 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 
 		dma = skb_frag_dma_map(tx_q->dev, frag, 0, size,
 				       DMA_TO_DEVICE);
-
-		tx_buf = &tx_q->tx_buf[i];
 	}
 
 	skb_tx_timestamp(first->skb);
@@ -280,13 +339,13 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 	tx_desc->qw1 = idpf_tx_singleq_build_ctob(td_cmd, offsets,
 						  size, td_tag);
 
-	IDPF_SINGLEQ_BUMP_RING_IDX(tx_q, i);
+	first->type = LIBETH_SQE_SKB;
+	first->rs_idx = i;
 
-	/* set next_to_watch value indicating a packet is present */
-	first->next_to_watch = tx_desc;
+	IDPF_SINGLEQ_BUMP_RING_IDX(tx_q, i);
 
 	nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
-	netdev_tx_sent_queue(nq, first->bytecount);
+	netdev_tx_sent_queue(nq, first->bytes);
 
 	idpf_tx_buf_hw_update(tx_q, i, netdev_xmit_more());
 }
@@ -304,8 +363,7 @@ idpf_tx_singleq_get_ctx_desc(struct idpf_tx_queue *txq)
 	struct idpf_base_tx_ctx_desc *ctx_desc;
 	int ntu = txq->next_to_use;
 
-	memset(&txq->tx_buf[ntu], 0, sizeof(struct idpf_tx_buf));
-	txq->tx_buf[ntu].ctx_entry = true;
+	txq->tx_buf[ntu].type = LIBETH_SQE_CTX;
 
 	ctx_desc = &txq->base_ctx[ntu];
 
@@ -356,11 +414,11 @@ netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 {
 	struct idpf_tx_offload_params offload = { };
 	struct idpf_tx_buf *first;
+	u32 count, buf_count = 1;
 	int csum, tso, needed;
-	unsigned int count;
 	__be16 protocol;
 
-	count = idpf_tx_desc_count_required(tx_q, skb);
+	count = idpf_tx_res_count_required(tx_q, skb, &buf_count);
 	if (unlikely(!count))
 		return idpf_tx_drop_skb(tx_q, skb);
 
@@ -399,11 +457,11 @@ netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 	first->skb = skb;
 
 	if (tso) {
-		first->gso_segs = offload.tso_segs;
-		first->bytecount = skb->len + ((first->gso_segs - 1) * offload.tso_hdr_len);
+		first->packets = offload.tso_segs;
+		first->bytes = skb->len + ((first->packets - 1) * offload.tso_hdr_len);
 	} else {
-		first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN);
-		first->gso_segs = 1;
+		first->bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
+		first->packets = 1;
 	}
 	idpf_tx_singleq_map(tx_q, first, &offload);
 
@@ -423,10 +481,15 @@ netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget,
 				  int *cleaned)
 {
-	unsigned int total_bytes = 0, total_pkts = 0;
+	struct libeth_sq_napi_stats ss = { };
 	struct idpf_base_tx_desc *tx_desc;
 	u32 budget = tx_q->clean_budget;
 	s16 ntc = tx_q->next_to_clean;
+	struct libeth_cq_pp cp = {
+		.dev	= tx_q->dev,
+		.ss	= &ss,
+		.napi	= napi_budget,
+	};
 	struct idpf_netdev_priv *np;
 	struct idpf_tx_buf *tx_buf;
 	struct netdev_queue *nq;
@@ -444,47 +507,26 @@ static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget,
 		 * such. We can skip this descriptor since there is no buffer
 		 * to clean.
 		 */
-		if (tx_buf->ctx_entry) {
-			/* Clear this flag here to avoid stale flag values when
-			 * this buffer is used for actual data in the future.
-			 * There are cases where the tx_buf struct / the flags
-			 * field will not be cleared before being reused.
-			 */
-			tx_buf->ctx_entry = false;
+		if (unlikely(tx_buf->type <= LIBETH_SQE_CTX)) {
+			tx_buf->type = LIBETH_SQE_EMPTY;
 			goto fetch_next_txq_desc;
 		}
 
-		/* if next_to_watch is not set then no work pending */
-		eop_desc = (struct idpf_base_tx_desc *)tx_buf->next_to_watch;
-		if (!eop_desc)
+		if (unlikely(tx_buf->type != LIBETH_SQE_SKB))
 			break;
 
-		/* prevent any other reads prior to eop_desc */
+		/* prevent any other reads prior to type */
 		smp_rmb();
 
+		eop_desc = &tx_q->base_tx[tx_buf->rs_idx];
+
 		/* if the descriptor isn't done, no work yet to do */
 		if (!(eop_desc->qw1 &
 		      cpu_to_le64(IDPF_TX_DESC_DTYPE_DESC_DONE)))
 			break;
 
-		/* clear next_to_watch to prevent false hangs */
-		tx_buf->next_to_watch = NULL;
-
 		/* update the statistics for this packet */
-		total_bytes += tx_buf->bytecount;
-		total_pkts += tx_buf->gso_segs;
-
-		napi_consume_skb(tx_buf->skb, napi_budget);
-
-		/* unmap skb header data */
-		dma_unmap_single(tx_q->dev,
-				 dma_unmap_addr(tx_buf, dma),
-				 dma_unmap_len(tx_buf, len),
-				 DMA_TO_DEVICE);
-
-		/* clear tx_buf data */
-		tx_buf->skb = NULL;
-		dma_unmap_len_set(tx_buf, len, 0);
+		libeth_tx_complete(tx_buf, &cp);
 
 		/* unmap remaining buffers */
 		while (tx_desc != eop_desc) {
@@ -498,13 +540,7 @@ static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget,
 			}
 
 			/* unmap any remaining paged data */
-			if (dma_unmap_len(tx_buf, len)) {
-				dma_unmap_page(tx_q->dev,
-					       dma_unmap_addr(tx_buf, dma),
-					       dma_unmap_len(tx_buf, len),
-					       DMA_TO_DEVICE);
-				dma_unmap_len_set(tx_buf, len, 0);
-			}
+			libeth_tx_complete(tx_buf, &cp);
 		}
 
 		/* update budget only if we did something */
@@ -524,11 +560,11 @@ static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget,
 	ntc += tx_q->desc_count;
 	tx_q->next_to_clean = ntc;
 
-	*cleaned += total_pkts;
+	*cleaned += ss.packets;
 
 	u64_stats_update_begin(&tx_q->stats_sync);
-	u64_stats_add(&tx_q->q_stats.packets, total_pkts);
-	u64_stats_add(&tx_q->q_stats.bytes, total_bytes);
+	u64_stats_add(&tx_q->q_stats.packets, ss.packets);
+	u64_stats_add(&tx_q->q_stats.bytes, ss.bytes);
 	u64_stats_update_end(&tx_q->stats_sync);
 
 	np = netdev_priv(tx_q->netdev);
@@ -536,7 +572,7 @@ static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget,
 
 	dont_wake = np->state != __IDPF_VPORT_UP ||
 		    !netif_carrier_ok(tx_q->netdev);
-	__netif_txq_completed_wake(nq, total_pkts, total_bytes,
+	__netif_txq_completed_wake(nq, ss.packets, ss.bytes,
 				   IDPF_DESC_UNUSED(tx_q), IDPF_TX_WAKE_THRESH,
 				   dont_wake);
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index e163e54d1c31e..24b255145f57c 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -1,42 +1,17 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (C) 2023 Intel Corporation */
 
+#include <net/libeth/tx.h>
+
 #include "idpf.h"
 #include "idpf_virtchnl.h"
 
+#define idpf_tx_buf_next(buf)		(*(u32 *)&(buf)->priv)
+LIBETH_SQE_CHECK_PRIV(u32);
+
 static bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
 			       unsigned int count);
 
-/**
- * idpf_buf_lifo_push - push a buffer pointer onto stack
- * @stack: pointer to stack struct
- * @buf: pointer to buf to push
- *
- * Returns 0 on success, negative on failure
- **/
-static int idpf_buf_lifo_push(struct idpf_buf_lifo *stack,
-			      struct idpf_tx_stash *buf)
-{
-	if (unlikely(stack->top == stack->size))
-		return -ENOSPC;
-
-	stack->bufs[stack->top++] = buf;
-
-	return 0;
-}
-
-/**
- * idpf_buf_lifo_pop - pop a buffer pointer from stack
- * @stack: pointer to stack struct
- **/
-static struct idpf_tx_stash *idpf_buf_lifo_pop(struct idpf_buf_lifo *stack)
-{
-	if (unlikely(!stack->top))
-		return NULL;
-
-	return stack->bufs[--stack->top];
-}
-
 /**
  * idpf_tx_timeout - Respond to a Tx Hang
  * @netdev: network interface device structure
@@ -58,66 +33,29 @@ void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	}
 }
 
-/**
- * idpf_tx_buf_rel - Release a Tx buffer
- * @tx_q: the queue that owns the buffer
- * @tx_buf: the buffer to free
- */
-static void idpf_tx_buf_rel(struct idpf_tx_queue *tx_q,
-			    struct idpf_tx_buf *tx_buf)
-{
-	if (tx_buf->skb) {
-		if (dma_unmap_len(tx_buf, len))
-			dma_unmap_single(tx_q->dev,
-					 dma_unmap_addr(tx_buf, dma),
-					 dma_unmap_len(tx_buf, len),
-					 DMA_TO_DEVICE);
-		dev_kfree_skb_any(tx_buf->skb);
-	} else if (dma_unmap_len(tx_buf, len)) {
-		dma_unmap_page(tx_q->dev,
-			       dma_unmap_addr(tx_buf, dma),
-			       dma_unmap_len(tx_buf, len),
-			       DMA_TO_DEVICE);
-	}
-
-	tx_buf->next_to_watch = NULL;
-	tx_buf->skb = NULL;
-	tx_buf->compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG;
-	dma_unmap_len_set(tx_buf, len, 0);
-}
-
 /**
  * idpf_tx_buf_rel_all - Free any empty Tx buffers
  * @txq: queue to be cleaned
  */
 static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq)
 {
-	struct idpf_buf_lifo *buf_stack;
-	u16 i;
+	struct libeth_sq_napi_stats ss = { };
+	struct libeth_cq_pp cp = {
+		.dev	= txq->dev,
+		.ss	= &ss,
+	};
+	u32 i;
 
 	/* Buffers already cleared, nothing to do */
 	if (!txq->tx_buf)
 		return;
 
 	/* Free all the Tx buffer sk_buffs */
-	for (i = 0; i < txq->desc_count; i++)
-		idpf_tx_buf_rel(txq, &txq->tx_buf[i]);
+	for (i = 0; i < txq->buf_pool_size; i++)
+		libeth_tx_complete(&txq->tx_buf[i], &cp);
 
 	kfree(txq->tx_buf);
 	txq->tx_buf = NULL;
-
-	if (!idpf_queue_has(FLOW_SCH_EN, txq))
-		return;
-
-	buf_stack = &txq->stash->buf_stack;
-	if (!buf_stack->bufs)
-		return;
-
-	for (i = 0; i < buf_stack->size; i++)
-		kfree(buf_stack->bufs[i]);
-
-	kfree(buf_stack->bufs);
-	buf_stack->bufs = NULL;
 }
 
 /**
@@ -129,10 +67,14 @@ static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq)
 static void idpf_tx_desc_rel(struct idpf_tx_queue *txq)
 {
 	idpf_tx_buf_rel_all(txq);
+	netdev_tx_reset_subqueue(txq->netdev, txq->idx);
 
 	if (!txq->desc_ring)
 		return;
 
+	if (txq->refillq)
+		kfree(txq->refillq->ring);
+
 	dmam_free_coherent(txq->dev, txq->size, txq->desc_ring, txq->dma);
 	txq->desc_ring = NULL;
 	txq->next_to_use = 0;
@@ -189,45 +131,18 @@ static void idpf_tx_desc_rel_all(struct idpf_vport *vport)
  */
 static int idpf_tx_buf_alloc_all(struct idpf_tx_queue *tx_q)
 {
-	struct idpf_buf_lifo *buf_stack;
-	int buf_size;
-	int i;
-
 	/* Allocate book keeping buffers only. Buffers to be supplied to HW
 	 * are allocated by kernel network stack and received as part of skb
 	 */
-	buf_size = sizeof(struct idpf_tx_buf) * tx_q->desc_count;
-	tx_q->tx_buf = kzalloc(buf_size, GFP_KERNEL);
+	if (idpf_queue_has(FLOW_SCH_EN, tx_q))
+		tx_q->buf_pool_size = U16_MAX;
+	else
+		tx_q->buf_pool_size = tx_q->desc_count;
+	tx_q->tx_buf = kcalloc(tx_q->buf_pool_size, sizeof(*tx_q->tx_buf),
+			       GFP_KERNEL);
 	if (!tx_q->tx_buf)
 		return -ENOMEM;
 
-	/* Initialize tx_bufs with invalid completion tags */
-	for (i = 0; i < tx_q->desc_count; i++)
-		tx_q->tx_buf[i].compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG;
-
-	if (!idpf_queue_has(FLOW_SCH_EN, tx_q))
-		return 0;
-
-	buf_stack = &tx_q->stash->buf_stack;
-
-	/* Initialize tx buf stack for out-of-order completions if
-	 * flow scheduling offload is enabled
-	 */
-	buf_stack->bufs = kcalloc(tx_q->desc_count, sizeof(*buf_stack->bufs),
-				  GFP_KERNEL);
-	if (!buf_stack->bufs)
-		return -ENOMEM;
-
-	buf_stack->size = tx_q->desc_count;
-	buf_stack->top = tx_q->desc_count;
-
-	for (i = 0; i < tx_q->desc_count; i++) {
-		buf_stack->bufs[i] = kzalloc(sizeof(*buf_stack->bufs[i]),
-					     GFP_KERNEL);
-		if (!buf_stack->bufs[i])
-			return -ENOMEM;
-	}
-
 	return 0;
 }
 
@@ -242,7 +157,9 @@ static int idpf_tx_desc_alloc(const struct idpf_vport *vport,
 			      struct idpf_tx_queue *tx_q)
 {
 	struct device *dev = tx_q->dev;
+	struct idpf_sw_queue *refillq;
 	int err;
+	unsigned int i = 0;
 
 	err = idpf_tx_buf_alloc_all(tx_q);
 	if (err)
@@ -265,6 +182,31 @@ static int idpf_tx_desc_alloc(const struct idpf_vport *vport,
 	tx_q->next_to_clean = 0;
 	idpf_queue_set(GEN_CHK, tx_q);
 
+	if (!idpf_queue_has(FLOW_SCH_EN, tx_q))
+		return 0;
+
+	refillq = tx_q->refillq;
+	refillq->desc_count = tx_q->buf_pool_size;
+	refillq->ring = kcalloc(refillq->desc_count, sizeof(u32),
+				GFP_KERNEL);
+	if (!refillq->ring) {
+		err = -ENOMEM;
+		goto err_alloc;
+	}
+
+	for (i = 0; i < refillq->desc_count; i++)
+		refillq->ring[i] =
+			FIELD_PREP(IDPF_RFL_BI_BUFID_M, i) |
+			FIELD_PREP(IDPF_RFL_BI_GEN_M,
+				   idpf_queue_has(GEN_CHK, refillq));
+
+	/* Go ahead and flip the GEN bit since this counts as filling
+	 * up the ring, i.e. we already ring wrapped.
+	 */
+	idpf_queue_change(GEN_CHK, refillq);
+
+	tx_q->last_re = tx_q->desc_count - IDPF_TX_SPLITQ_RE_MIN_GAP;
+
 	return 0;
 
 err_alloc:
@@ -315,8 +257,6 @@ static int idpf_tx_desc_alloc_all(struct idpf_vport *vport)
 	for (i = 0; i < vport->num_txq_grp; i++) {
 		for (j = 0; j < vport->txq_grps[i].num_txq; j++) {
 			struct idpf_tx_queue *txq = vport->txq_grps[i].txqs[j];
-			u8 gen_bits = 0;
-			u16 bufidx_mask;
 
 			err = idpf_tx_desc_alloc(vport, txq);
 			if (err) {
@@ -325,34 +265,6 @@ static int idpf_tx_desc_alloc_all(struct idpf_vport *vport)
 					i);
 				goto err_out;
 			}
-
-			if (!idpf_is_queue_model_split(vport->txq_model))
-				continue;
-
-			txq->compl_tag_cur_gen = 0;
-
-			/* Determine the number of bits in the bufid
-			 * mask and add one to get the start of the
-			 * generation bits
-			 */
-			bufidx_mask = txq->desc_count - 1;
-			while (bufidx_mask >> 1) {
-				txq->compl_tag_gen_s++;
-				bufidx_mask = bufidx_mask >> 1;
-			}
-			txq->compl_tag_gen_s++;
-
-			gen_bits = IDPF_TX_SPLITQ_COMPL_TAG_WIDTH -
-							txq->compl_tag_gen_s;
-			txq->compl_tag_gen_max = GETMAXVAL(gen_bits);
-
-			/* Set bufid mask based on location of first
-			 * gen bit; it cannot simply be the descriptor
-			 * ring size-1 since we can have size values
-			 * where not all of those bits are set.
-			 */
-			txq->compl_tag_bufid_m =
-				GETMAXVAL(txq->compl_tag_gen_s);
 		}
 
 		if (!idpf_is_queue_model_split(vport->txq_model))
@@ -586,18 +498,18 @@ static int idpf_rx_hdr_buf_alloc_all(struct idpf_buf_queue *bufq)
 }
 
 /**
- * idpf_rx_post_buf_refill - Post buffer id to refill queue
+ * idpf_post_buf_refill - Post buffer id to refill queue
  * @refillq: refill queue to post to
  * @buf_id: buffer id to post
  */
-static void idpf_rx_post_buf_refill(struct idpf_sw_queue *refillq, u16 buf_id)
+static void idpf_post_buf_refill(struct idpf_sw_queue *refillq, u16 buf_id)
 {
 	u32 nta = refillq->next_to_use;
 
 	/* store the buffer ID and the SW maintained GEN bit to the refillq */
 	refillq->ring[nta] =
-		FIELD_PREP(IDPF_RX_BI_BUFID_M, buf_id) |
-		FIELD_PREP(IDPF_RX_BI_GEN_M,
+		FIELD_PREP(IDPF_RFL_BI_BUFID_M, buf_id) |
+		FIELD_PREP(IDPF_RFL_BI_GEN_M,
 			   idpf_queue_has(GEN_CHK, refillq));
 
 	if (unlikely(++nta == refillq->desc_count)) {
@@ -977,6 +889,11 @@ static void idpf_txq_group_rel(struct idpf_vport *vport)
 		struct idpf_txq_group *txq_grp = &vport->txq_grps[i];
 
 		for (j = 0; j < txq_grp->num_txq; j++) {
+			if (flow_sch_en) {
+				kfree(txq_grp->txqs[j]->refillq);
+				txq_grp->txqs[j]->refillq = NULL;
+			}
+
 			kfree(txq_grp->txqs[j]);
 			txq_grp->txqs[j] = NULL;
 		}
@@ -986,9 +903,6 @@ static void idpf_txq_group_rel(struct idpf_vport *vport)
 
 		kfree(txq_grp->complq);
 		txq_grp->complq = NULL;
-
-		if (flow_sch_en)
-			kfree(txq_grp->stashes);
 	}
 	kfree(vport->txq_grps);
 	vport->txq_grps = NULL;
@@ -1347,7 +1261,6 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
 	for (i = 0; i < vport->num_txq_grp; i++) {
 		struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
 		struct idpf_adapter *adapter = vport->adapter;
-		struct idpf_txq_stash *stashes;
 		int j;
 
 		tx_qgrp->vport = vport;
@@ -1360,15 +1273,6 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
 				goto err_alloc;
 		}
 
-		if (split && flow_sch_en) {
-			stashes = kcalloc(num_txq, sizeof(*stashes),
-					  GFP_KERNEL);
-			if (!stashes)
-				goto err_alloc;
-
-			tx_qgrp->stashes = stashes;
-		}
-
 		for (j = 0; j < tx_qgrp->num_txq; j++) {
 			struct idpf_tx_queue *q = tx_qgrp->txqs[j];
 
@@ -1388,12 +1292,14 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
 			if (!flow_sch_en)
 				continue;
 
-			if (split) {
-				q->stash = &stashes[j];
-				hash_init(q->stash->sched_buf_hash);
-			}
-
 			idpf_queue_set(FLOW_SCH_EN, q);
+
+			q->refillq = kzalloc(sizeof(*q->refillq), GFP_KERNEL);
+			if (!q->refillq)
+				goto err_alloc;
+
+			idpf_queue_set(GEN_CHK, q->refillq);
+			idpf_queue_set(RFL_GEN_CHK, q->refillq);
 		}
 
 		if (!split)
@@ -1651,125 +1557,10 @@ static void idpf_tx_handle_sw_marker(struct idpf_tx_queue *tx_q)
 	wake_up(&vport->sw_marker_wq);
 }
 
-/**
- * idpf_tx_splitq_clean_hdr - Clean TX buffer resources for header portion of
- * packet
- * @tx_q: tx queue to clean buffer from
- * @tx_buf: buffer to be cleaned
- * @cleaned: pointer to stats struct to track cleaned packets/bytes
- * @napi_budget: Used to determine if we are in netpoll
- */
-static void idpf_tx_splitq_clean_hdr(struct idpf_tx_queue *tx_q,
-				     struct idpf_tx_buf *tx_buf,
-				     struct idpf_cleaned_stats *cleaned,
-				     int napi_budget)
-{
-	napi_consume_skb(tx_buf->skb, napi_budget);
-
-	if (dma_unmap_len(tx_buf, len)) {
-		dma_unmap_single(tx_q->dev,
-				 dma_unmap_addr(tx_buf, dma),
-				 dma_unmap_len(tx_buf, len),
-				 DMA_TO_DEVICE);
-
-		dma_unmap_len_set(tx_buf, len, 0);
-	}
-
-	/* clear tx_buf data */
-	tx_buf->skb = NULL;
-
-	cleaned->bytes += tx_buf->bytecount;
-	cleaned->packets += tx_buf->gso_segs;
-}
-
-/**
- * idpf_tx_clean_stashed_bufs - clean bufs that were stored for
- * out of order completions
- * @txq: queue to clean
- * @compl_tag: completion tag of packet to clean (from completion descriptor)
- * @cleaned: pointer to stats struct to track cleaned packets/bytes
- * @budget: Used to determine if we are in netpoll
- */
-static void idpf_tx_clean_stashed_bufs(struct idpf_tx_queue *txq,
-				       u16 compl_tag,
-				       struct idpf_cleaned_stats *cleaned,
-				       int budget)
-{
-	struct idpf_tx_stash *stash;
-	struct hlist_node *tmp_buf;
-
-	/* Buffer completion */
-	hash_for_each_possible_safe(txq->stash->sched_buf_hash, stash, tmp_buf,
-				    hlist, compl_tag) {
-		if (unlikely(stash->buf.compl_tag != (int)compl_tag))
-			continue;
-
-		if (stash->buf.skb) {
-			idpf_tx_splitq_clean_hdr(txq, &stash->buf, cleaned,
-						 budget);
-		} else if (dma_unmap_len(&stash->buf, len)) {
-			dma_unmap_page(txq->dev,
-				       dma_unmap_addr(&stash->buf, dma),
-				       dma_unmap_len(&stash->buf, len),
-				       DMA_TO_DEVICE);
-			dma_unmap_len_set(&stash->buf, len, 0);
-		}
-
-		/* Push shadow buf back onto stack */
-		idpf_buf_lifo_push(&txq->stash->buf_stack, stash);
-
-		hash_del(&stash->hlist);
-	}
-}
-
-/**
- * idpf_stash_flow_sch_buffers - store buffer parameters info to be freed at a
- * later time (only relevant for flow scheduling mode)
- * @txq: Tx queue to clean
- * @tx_buf: buffer to store
- */
-static int idpf_stash_flow_sch_buffers(struct idpf_tx_queue *txq,
-				       struct idpf_tx_buf *tx_buf)
-{
-	struct idpf_tx_stash *stash;
-
-	if (unlikely(!dma_unmap_addr(tx_buf, dma) &&
-		     !dma_unmap_len(tx_buf, len)))
-		return 0;
-
-	stash = idpf_buf_lifo_pop(&txq->stash->buf_stack);
-	if (unlikely(!stash)) {
-		net_err_ratelimited("%s: No out-of-order TX buffers left!\n",
-				    netdev_name(txq->netdev));
-
-		return -ENOMEM;
-	}
-
-	/* Store buffer params in shadow buffer */
-	stash->buf.skb = tx_buf->skb;
-	stash->buf.bytecount = tx_buf->bytecount;
-	stash->buf.gso_segs = tx_buf->gso_segs;
-	dma_unmap_addr_set(&stash->buf, dma, dma_unmap_addr(tx_buf, dma));
-	dma_unmap_len_set(&stash->buf, len, dma_unmap_len(tx_buf, len));
-	stash->buf.compl_tag = tx_buf->compl_tag;
-
-	/* Add buffer to buf_hash table to be freed later */
-	hash_add(txq->stash->sched_buf_hash, &stash->hlist,
-		 stash->buf.compl_tag);
-
-	memset(tx_buf, 0, sizeof(struct idpf_tx_buf));
-
-	/* Reinitialize buf_id portion of tag */
-	tx_buf->compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG;
-
-	return 0;
-}
-
 #define idpf_tx_splitq_clean_bump_ntc(txq, ntc, desc, buf)	\
 do {								\
-	(ntc)++;						\
-	if (unlikely(!(ntc))) {					\
-		ntc -= (txq)->desc_count;			\
+	if (unlikely(++(ntc) == (txq)->desc_count)) {		\
+		ntc = 0;					\
 		buf = (txq)->tx_buf;				\
 		desc = &(txq)->flex_tx[0];			\
 	} else {						\
@@ -1796,156 +1587,95 @@ do {								\
  */
 static void idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 				 int napi_budget,
-				 struct idpf_cleaned_stats *cleaned,
+				 struct libeth_sq_napi_stats *cleaned,
 				 bool descs_only)
 {
 	union idpf_tx_flex_desc *next_pending_desc = NULL;
 	union idpf_tx_flex_desc *tx_desc;
-	s16 ntc = tx_q->next_to_clean;
+	u32 ntc = tx_q->next_to_clean;
+	struct libeth_cq_pp cp = {
+		.dev	= tx_q->dev,
+		.ss	= cleaned,
+		.napi	= napi_budget,
+	};
 	struct idpf_tx_buf *tx_buf;
 
+	if (descs_only) {
+		/* Bump ring index to mark as cleaned. */
+		tx_q->next_to_clean = end;
+		return;
+	}
+
 	tx_desc = &tx_q->flex_tx[ntc];
 	next_pending_desc = &tx_q->flex_tx[end];
 	tx_buf = &tx_q->tx_buf[ntc];
-	ntc -= tx_q->desc_count;
 
 	while (tx_desc != next_pending_desc) {
-		union idpf_tx_flex_desc *eop_desc;
+		u32 eop_idx;
 
 		/* If this entry in the ring was used as a context descriptor,
-		 * it's corresponding entry in the buffer ring will have an
-		 * invalid completion tag since no buffer was used.  We can
-		 * skip this descriptor since there is no buffer to clean.
+		 * it's corresponding entry in the buffer ring is reserved. We
+		 * can skip this descriptor since there is no buffer to clean.
 		 */
-		if (unlikely(tx_buf->compl_tag == IDPF_SPLITQ_TX_INVAL_COMPL_TAG))
+		if (tx_buf->type <= LIBETH_SQE_CTX)
 			goto fetch_next_txq_desc;
 
-		eop_desc = (union idpf_tx_flex_desc *)tx_buf->next_to_watch;
-
-		/* clear next_to_watch to prevent false hangs */
-		tx_buf->next_to_watch = NULL;
+		if (unlikely(tx_buf->type != LIBETH_SQE_SKB))
+			break;
 
-		if (descs_only) {
-			if (idpf_stash_flow_sch_buffers(tx_q, tx_buf))
-				goto tx_splitq_clean_out;
+		eop_idx = tx_buf->rs_idx;
+		libeth_tx_complete(tx_buf, &cp);
 
-			while (tx_desc != eop_desc) {
-				idpf_tx_splitq_clean_bump_ntc(tx_q, ntc,
-							      tx_desc, tx_buf);
+		/* unmap remaining buffers */
+		while (ntc != eop_idx) {
+			idpf_tx_splitq_clean_bump_ntc(tx_q, ntc,
+						      tx_desc, tx_buf);
 
-				if (dma_unmap_len(tx_buf, len)) {
-					if (idpf_stash_flow_sch_buffers(tx_q,
-									tx_buf))
-						goto tx_splitq_clean_out;
-				}
-			}
-		} else {
-			idpf_tx_splitq_clean_hdr(tx_q, tx_buf, cleaned,
-						 napi_budget);
-
-			/* unmap remaining buffers */
-			while (tx_desc != eop_desc) {
-				idpf_tx_splitq_clean_bump_ntc(tx_q, ntc,
-							      tx_desc, tx_buf);
-
-				/* unmap any remaining paged data */
-				if (dma_unmap_len(tx_buf, len)) {
-					dma_unmap_page(tx_q->dev,
-						       dma_unmap_addr(tx_buf, dma),
-						       dma_unmap_len(tx_buf, len),
-						       DMA_TO_DEVICE);
-					dma_unmap_len_set(tx_buf, len, 0);
-				}
-			}
+			/* unmap any remaining paged data */
+			libeth_tx_complete(tx_buf, &cp);
 		}
 
 fetch_next_txq_desc:
 		idpf_tx_splitq_clean_bump_ntc(tx_q, ntc, tx_desc, tx_buf);
 	}
 
-tx_splitq_clean_out:
-	ntc += tx_q->desc_count;
 	tx_q->next_to_clean = ntc;
 }
 
-#define idpf_tx_clean_buf_ring_bump_ntc(txq, ntc, buf)	\
-do {							\
-	(buf)++;					\
-	(ntc)++;					\
-	if (unlikely((ntc) == (txq)->desc_count)) {	\
-		buf = (txq)->tx_buf;			\
-		ntc = 0;				\
-	}						\
-} while (0)
-
 /**
- * idpf_tx_clean_buf_ring - clean flow scheduling TX queue buffers
+ * idpf_tx_clean_bufs - clean flow scheduling TX queue buffers
  * @txq: queue to clean
- * @compl_tag: completion tag of packet to clean (from completion descriptor)
+ * @buf_id: packet's starting buffer ID, from completion descriptor
  * @cleaned: pointer to stats struct to track cleaned packets/bytes
  * @budget: Used to determine if we are in netpoll
  *
- * Cleans all buffers associated with the input completion tag either from the
- * TX buffer ring or from the hash table if the buffers were previously
- * stashed. Returns the byte/segment count for the cleaned packet associated
- * this completion tag.
+ * Clean all buffers associated with the packet starting at buf_id. Returns the
+ * byte/segment count for the cleaned packet.
  */
-static bool idpf_tx_clean_buf_ring(struct idpf_tx_queue *txq, u16 compl_tag,
-				   struct idpf_cleaned_stats *cleaned,
-				   int budget)
+static void idpf_tx_clean_bufs(struct idpf_tx_queue *txq, u32 buf_id,
+			       struct libeth_sq_napi_stats *cleaned,
+			       int budget)
 {
-	u16 idx = compl_tag & txq->compl_tag_bufid_m;
 	struct idpf_tx_buf *tx_buf = NULL;
-	u16 ntc = txq->next_to_clean;
-	u16 num_descs_cleaned = 0;
-	u16 orig_idx = idx;
-
-	tx_buf = &txq->tx_buf[idx];
-
-	while (tx_buf->compl_tag == (int)compl_tag) {
-		if (tx_buf->skb) {
-			idpf_tx_splitq_clean_hdr(txq, tx_buf, cleaned, budget);
-		} else if (dma_unmap_len(tx_buf, len)) {
-			dma_unmap_page(txq->dev,
-				       dma_unmap_addr(tx_buf, dma),
-				       dma_unmap_len(tx_buf, len),
-				       DMA_TO_DEVICE);
-			dma_unmap_len_set(tx_buf, len, 0);
-		}
-
-		memset(tx_buf, 0, sizeof(struct idpf_tx_buf));
-		tx_buf->compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG;
+	struct libeth_cq_pp cp = {
+		.dev	= txq->dev,
+		.ss	= cleaned,
+		.napi	= budget,
+	};
 
-		num_descs_cleaned++;
-		idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf);
+	tx_buf = &txq->tx_buf[buf_id];
+	if (tx_buf->type == LIBETH_SQE_SKB) {
+		libeth_tx_complete(tx_buf, &cp);
+		idpf_post_buf_refill(txq->refillq, buf_id);
 	}
 
-	/* If we didn't clean anything on the ring for this completion, there's
-	 * nothing more to do.
-	 */
-	if (unlikely(!num_descs_cleaned))
-		return false;
+	while (idpf_tx_buf_next(tx_buf) != IDPF_TXBUF_NULL) {
+		buf_id = idpf_tx_buf_next(tx_buf);
 
-	/* Otherwise, if we did clean a packet on the ring directly, it's safe
-	 * to assume that the descriptors starting from the original
-	 * next_to_clean up until the previously cleaned packet can be reused.
-	 * Therefore, we will go back in the ring and stash any buffers still
-	 * in the ring into the hash table to be cleaned later.
-	 */
-	tx_buf = &txq->tx_buf[ntc];
-	while (tx_buf != &txq->tx_buf[orig_idx]) {
-		idpf_stash_flow_sch_buffers(txq, tx_buf);
-		idpf_tx_clean_buf_ring_bump_ntc(txq, ntc, tx_buf);
+		tx_buf = &txq->tx_buf[buf_id];
+		libeth_tx_complete(tx_buf, &cp);
+		idpf_post_buf_refill(txq->refillq, buf_id);
 	}
-
-	/* Finally, update next_to_clean to reflect the work that was just done
-	 * on the ring, if any. If the packet was only cleaned from the hash
-	 * table, the ring will not be impacted, therefore we should not touch
-	 * next_to_clean. The updated idx is used here
-	 */
-	txq->next_to_clean = idx;
-
-	return true;
 }
 
 /**
@@ -1961,24 +1691,20 @@ static bool idpf_tx_clean_buf_ring(struct idpf_tx_queue *txq, u16 compl_tag,
  */
 static void idpf_tx_handle_rs_completion(struct idpf_tx_queue *txq,
 					 struct idpf_splitq_tx_compl_desc *desc,
-					 struct idpf_cleaned_stats *cleaned,
+					 struct libeth_sq_napi_stats *cleaned,
 					 int budget)
 {
-	u16 compl_tag;
+	/* RS completion contains queue head for queue based scheduling or
+	 * completion tag for flow based scheduling.
+	 */
+	u16 rs_compl_val = le16_to_cpu(desc->q_head_compl_tag.q_head);
 
 	if (!idpf_queue_has(FLOW_SCH_EN, txq)) {
-		u16 head = le16_to_cpu(desc->q_head_compl_tag.q_head);
-
-		return idpf_tx_splitq_clean(txq, head, budget, cleaned, false);
+		idpf_tx_splitq_clean(txq, rs_compl_val, budget, cleaned, false);
+		return;
 	}
 
-	compl_tag = le16_to_cpu(desc->q_head_compl_tag.compl_tag);
-
-	/* If we didn't clean anything on the ring, this packet must be
-	 * in the hash table. Go clean it there.
-	 */
-	if (!idpf_tx_clean_buf_ring(txq, compl_tag, cleaned, budget))
-		idpf_tx_clean_stashed_bufs(txq, compl_tag, cleaned, budget);
+	idpf_tx_clean_bufs(txq, rs_compl_val, cleaned, budget);
 }
 
 /**
@@ -2004,7 +1730,7 @@ static bool idpf_tx_clean_complq(struct idpf_compl_queue *complq, int budget,
 	ntc -= complq->desc_count;
 
 	do {
-		struct idpf_cleaned_stats cleaned_stats = { };
+		struct libeth_sq_napi_stats cleaned_stats = { };
 		struct idpf_tx_queue *tx_q;
 		int rel_tx_qid;
 		u16 hw_head;
@@ -2095,8 +1821,7 @@ static bool idpf_tx_clean_complq(struct idpf_compl_queue *complq, int budget,
 		/* Update BQL */
 		nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
 
-		dont_wake = !complq_ok || IDPF_TX_BUF_RSV_LOW(tx_q) ||
-			    np->state != __IDPF_VPORT_UP ||
+		dont_wake = !complq_ok || np->state != __IDPF_VPORT_UP ||
 			    !netif_carrier_ok(tx_q->netdev);
 		/* Check if the TXQ needs to and can be restarted */
 		__netif_txq_completed_wake(nq, tx_q->cleaned_pkts, tx_q->cleaned_bytes,
@@ -2153,15 +1878,21 @@ void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc,
 	desc->flow.qw1.compl_tag = cpu_to_le16(params->compl_tag);
 }
 
-/* Global conditions to tell whether the txq (and related resources)
- * has room to allow the use of "size" descriptors.
+/**
+ * idpf_tx_splitq_has_room - check if enough Tx splitq resources are available
+ * @tx_q: the queue to be checked
+ * @descs_needed: number of descriptors required for this packet
+ * @bufs_needed: number of Tx buffers required for this packet
+ *
+ * Return: 0 if no room available, 1 otherwise
  */
-static int idpf_txq_has_room(struct idpf_tx_queue *tx_q, u32 size)
+static int idpf_txq_has_room(struct idpf_tx_queue *tx_q, u32 descs_needed,
+			     u32 bufs_needed)
 {
-	if (IDPF_DESC_UNUSED(tx_q) < size ||
+	if (IDPF_DESC_UNUSED(tx_q) < descs_needed ||
 	    IDPF_TX_COMPLQ_PENDING(tx_q->txq_grp) >
 		IDPF_TX_COMPLQ_OVERFLOW_THRESH(tx_q->txq_grp->complq) ||
-	    IDPF_TX_BUF_RSV_LOW(tx_q))
+	    idpf_tx_splitq_get_free_bufs(tx_q->refillq) < bufs_needed)
 		return 0;
 	return 1;
 }
@@ -2170,14 +1901,21 @@ static int idpf_txq_has_room(struct idpf_tx_queue *tx_q, u32 size)
  * idpf_tx_maybe_stop_splitq - 1st level check for Tx splitq stop conditions
  * @tx_q: the queue to be checked
  * @descs_needed: number of descriptors required for this packet
+ * @bufs_needed: number of buffers needed for this packet
  *
- * Returns 0 if stop is not needed
+ * Return: 0 if stop is not needed
  */
 static int idpf_tx_maybe_stop_splitq(struct idpf_tx_queue *tx_q,
-				     unsigned int descs_needed)
+				     u32 descs_needed,
+				     u32 bufs_needed)
 {
+	/* Since we have multiple resources to check for splitq, our
+	 * start,stop_thrs becomes a boolean check instead of a count
+	 * threshold.
+	 */
 	if (netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
-				      idpf_txq_has_room(tx_q, descs_needed),
+				      idpf_txq_has_room(tx_q, descs_needed,
+							bufs_needed),
 				      1, 1))
 		return 0;
 
@@ -2219,14 +1957,16 @@ void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
 }
 
 /**
- * idpf_tx_desc_count_required - calculate number of Tx descriptors needed
+ * idpf_tx_res_count_required - get number of Tx resources needed for this pkt
  * @txq: queue to send buffer on
  * @skb: send buffer
+ * @bufs_needed: (output) number of buffers needed for this skb.
  *
- * Returns number of data descriptors needed for this skb.
+ * Return: number of data descriptors and buffers needed for this skb.
  */
-unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
-					 struct sk_buff *skb)
+unsigned int idpf_tx_res_count_required(struct idpf_tx_queue *txq,
+					struct sk_buff *skb,
+					u32 *bufs_needed)
 {
 	const struct skb_shared_info *shinfo;
 	unsigned int count = 0, i;
@@ -2237,6 +1977,7 @@ unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
 		return count;
 
 	shinfo = skb_shinfo(skb);
+	*bufs_needed += shinfo->nr_frags;
 	for (i = 0; i < shinfo->nr_frags; i++) {
 		unsigned int size;
 
@@ -2266,65 +2007,89 @@ unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
 }
 
 /**
- * idpf_tx_dma_map_error - handle TX DMA map errors
- * @txq: queue to send buffer on
- * @skb: send buffer
- * @first: original first buffer info buffer for packet
- * @idx: starting point on ring to unwind
+ * idpf_tx_splitq_bump_ntu - adjust NTU and generation
+ * @txq: the tx ring to wrap
+ * @ntu: ring index to bump
  */
-void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
-			   struct idpf_tx_buf *first, u16 idx)
+static unsigned int idpf_tx_splitq_bump_ntu(struct idpf_tx_queue *txq, u16 ntu)
 {
-	u64_stats_update_begin(&txq->stats_sync);
-	u64_stats_inc(&txq->q_stats.dma_map_errs);
-	u64_stats_update_end(&txq->stats_sync);
+	ntu++;
 
-	/* clear dma mappings for failed tx_buf map */
-	for (;;) {
-		struct idpf_tx_buf *tx_buf;
+	if (ntu == txq->desc_count)
+		ntu = 0;
 
-		tx_buf = &txq->tx_buf[idx];
-		idpf_tx_buf_rel(txq, tx_buf);
-		if (tx_buf == first)
-			break;
-		if (idx == 0)
-			idx = txq->desc_count;
-		idx--;
-	}
+	return ntu;
+}
 
-	if (skb_is_gso(skb)) {
-		union idpf_tx_flex_desc *tx_desc;
+/**
+ * idpf_tx_get_free_buf_id - get a free buffer ID from the refill queue
+ * @refillq: refill queue to get buffer ID from
+ * @buf_id: return buffer ID
+ *
+ * Return: true if a buffer ID was found, false if not
+ */
+static bool idpf_tx_get_free_buf_id(struct idpf_sw_queue *refillq,
+				    u32 *buf_id)
+{
+	u32 ntc = refillq->next_to_clean;
+	u32 refill_desc;
 
-		/* If we failed a DMA mapping for a TSO packet, we will have
-		 * used one additional descriptor for a context
-		 * descriptor. Reset that here.
-		 */
-		tx_desc = &txq->flex_tx[idx];
-		memset(tx_desc, 0, sizeof(struct idpf_flex_tx_ctx_desc));
-		if (idx == 0)
-			idx = txq->desc_count;
-		idx--;
+	refill_desc = refillq->ring[ntc];
+
+	if (unlikely(idpf_queue_has(RFL_GEN_CHK, refillq) !=
+		     !!(refill_desc & IDPF_RFL_BI_GEN_M)))
+		return false;
+
+	*buf_id = FIELD_GET(IDPF_RFL_BI_BUFID_M, refill_desc);
+
+	if (unlikely(++ntc == refillq->desc_count)) {
+		idpf_queue_change(RFL_GEN_CHK, refillq);
+		ntc = 0;
 	}
 
-	/* Update tail in case netdev_xmit_more was previously true */
-	idpf_tx_buf_hw_update(txq, idx, false);
+	refillq->next_to_clean = ntc;
+
+	return true;
 }
 
 /**
- * idpf_tx_splitq_bump_ntu - adjust NTU and generation
- * @txq: the tx ring to wrap
- * @ntu: ring index to bump
+ * idpf_tx_splitq_pkt_err_unmap - Unmap buffers and bump tail in case of error
+ * @txq: Tx queue to unwind
+ * @params: pointer to splitq params struct
+ * @first: starting buffer for packet to unmap
  */
-static unsigned int idpf_tx_splitq_bump_ntu(struct idpf_tx_queue *txq, u16 ntu)
+static void idpf_tx_splitq_pkt_err_unmap(struct idpf_tx_queue *txq,
+					 struct idpf_tx_splitq_params *params,
+					 struct idpf_tx_buf *first)
 {
-	ntu++;
+	struct idpf_sw_queue *refillq = txq->refillq;
+	struct libeth_sq_napi_stats ss = { };
+	struct idpf_tx_buf *tx_buf = first;
+	struct libeth_cq_pp cp = {
+		.dev    = txq->dev,
+		.ss     = &ss,
+	};
 
-	if (ntu == txq->desc_count) {
-		ntu = 0;
-		txq->compl_tag_cur_gen = IDPF_TX_ADJ_COMPL_TAG_GEN(txq);
+	u64_stats_update_begin(&txq->stats_sync);
+	u64_stats_inc(&txq->q_stats.dma_map_errs);
+	u64_stats_update_end(&txq->stats_sync);
+
+	libeth_tx_complete(tx_buf, &cp);
+	while (idpf_tx_buf_next(tx_buf) != IDPF_TXBUF_NULL) {
+		tx_buf = &txq->tx_buf[idpf_tx_buf_next(tx_buf)];
+		libeth_tx_complete(tx_buf, &cp);
 	}
 
-	return ntu;
+	/* Update tail in case netdev_xmit_more was previously true. */
+	idpf_tx_buf_hw_update(txq, params->prev_ntu, false);
+
+	if (!refillq)
+		return;
+
+	/* Restore refillq state to avoid leaking tags. */
+	if (params->prev_refill_gen != idpf_queue_has(RFL_GEN_CHK, refillq))
+		idpf_queue_change(RFL_GEN_CHK, refillq);
+	refillq->next_to_clean = params->prev_refill_ntc;
 }
 
 /**
@@ -2348,6 +2113,7 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 	struct netdev_queue *nq;
 	struct sk_buff *skb;
 	skb_frag_t *frag;
+	u32 next_buf_id;
 	u16 td_cmd = 0;
 	dma_addr_t dma;
 
@@ -2363,17 +2129,19 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 	dma = dma_map_single(tx_q->dev, skb->data, size, DMA_TO_DEVICE);
 
 	tx_buf = first;
-
-	params->compl_tag =
-		(tx_q->compl_tag_cur_gen << tx_q->compl_tag_gen_s) | i;
+	first->nr_frags = 0;
 
 	for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
 		unsigned int max_data = IDPF_TX_MAX_DESC_DATA_ALIGNED;
 
-		if (dma_mapping_error(tx_q->dev, dma))
-			return idpf_tx_dma_map_error(tx_q, skb, first, i);
+		if (unlikely(dma_mapping_error(tx_q->dev, dma))) {
+			idpf_tx_buf_next(tx_buf) = IDPF_TXBUF_NULL;
+			return idpf_tx_splitq_pkt_err_unmap(tx_q, params,
+							    first);
+		}
 
-		tx_buf->compl_tag = params->compl_tag;
+		first->nr_frags++;
+		tx_buf->type = LIBETH_SQE_FRAG;
 
 		/* record length, and DMA address */
 		dma_unmap_len_set(tx_buf, len, size);
@@ -2427,29 +2195,13 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 			idpf_tx_splitq_build_desc(tx_desc, params, td_cmd,
 						  max_data);
 
-			tx_desc++;
-			i++;
-
-			if (i == tx_q->desc_count) {
+			if (unlikely(++i == tx_q->desc_count)) {
 				tx_desc = &tx_q->flex_tx[0];
 				i = 0;
-				tx_q->compl_tag_cur_gen =
-					IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q);
+			} else {
+				tx_desc++;
 			}
 
-			/* Since this packet has a buffer that is going to span
-			 * multiple descriptors, it's going to leave holes in
-			 * to the TX buffer ring. To ensure these holes do not
-			 * cause issues in the cleaning routines, we will clear
-			 * them of any stale data and assign them the same
-			 * completion tag as the current packet. Then when the
-			 * packet is being cleaned, the cleaning routines will
-			 * simply pass over these holes and finish cleaning the
-			 * rest of the packet.
-			 */
-			memset(&tx_q->tx_buf[i], 0, sizeof(struct idpf_tx_buf));
-			tx_q->tx_buf[i].compl_tag = params->compl_tag;
-
 			/* Adjust the DMA offset and the remaining size of the
 			 * fragment.  On the first iteration of this loop,
 			 * max_data will be >= 12K and <= 16K-1.  On any
@@ -2472,40 +2224,51 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 			break;
 
 		idpf_tx_splitq_build_desc(tx_desc, params, td_cmd, size);
-		tx_desc++;
-		i++;
 
-		if (i == tx_q->desc_count) {
+		if (unlikely(++i == tx_q->desc_count)) {
 			tx_desc = &tx_q->flex_tx[0];
 			i = 0;
-			tx_q->compl_tag_cur_gen = IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q);
+		} else {
+			tx_desc++;
+		}
+
+		if (idpf_queue_has(FLOW_SCH_EN, tx_q)) {
+			if (unlikely(!idpf_tx_get_free_buf_id(tx_q->refillq,
+							      &next_buf_id))) {
+				idpf_tx_buf_next(tx_buf) = IDPF_TXBUF_NULL;
+				return idpf_tx_splitq_pkt_err_unmap(tx_q, params,
+								    first);
+			}
+		} else {
+			next_buf_id = i;
 		}
+		idpf_tx_buf_next(tx_buf) = next_buf_id;
+		tx_buf = &tx_q->tx_buf[next_buf_id];
 
 		size = skb_frag_size(frag);
 		data_len -= size;
 
 		dma = skb_frag_dma_map(tx_q->dev, frag, 0, size,
 				       DMA_TO_DEVICE);
-
-		tx_buf = &tx_q->tx_buf[i];
 	}
 
 	/* record SW timestamp if HW timestamp is not available */
 	skb_tx_timestamp(skb);
 
+	first->type = LIBETH_SQE_SKB;
+
 	/* write last descriptor with RS and EOP bits */
+	first->rs_idx = i;
+	idpf_tx_buf_next(tx_buf) = IDPF_TXBUF_NULL;
 	td_cmd |= params->eop_cmd;
 	idpf_tx_splitq_build_desc(tx_desc, params, td_cmd, size);
 	i = idpf_tx_splitq_bump_ntu(tx_q, i);
 
-	/* set next_to_watch value indicating a packet is present */
-	first->next_to_watch = tx_desc;
-
 	tx_q->txq_grp->num_completions_pending++;
 
 	/* record bytecount for BQL */
 	nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
-	netdev_tx_sent_queue(nq, first->bytecount);
+	netdev_tx_sent_queue(nq, first->bytes);
 
 	idpf_tx_buf_hw_update(tx_q, i, netdev_xmit_more());
 }
@@ -2705,9 +2468,6 @@ idpf_tx_splitq_get_ctx_desc(struct idpf_tx_queue *txq)
 	struct idpf_flex_tx_ctx_desc *desc;
 	int i = txq->next_to_use;
 
-	memset(&txq->tx_buf[i], 0, sizeof(struct idpf_tx_buf));
-	txq->tx_buf[i].compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG;
-
 	/* grab the next descriptor */
 	desc = &txq->flex_ctx[i];
 	txq->next_to_use = idpf_tx_splitq_bump_ntu(txq, i);
@@ -2733,6 +2493,21 @@ netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_queue *tx_q, struct sk_buff *skb)
 	return NETDEV_TX_OK;
 }
 
+/**
+ * idpf_tx_splitq_need_re - check whether RE bit needs to be set
+ * @tx_q: pointer to Tx queue
+ *
+ * Return: true if RE bit needs to be set, false otherwise
+ */
+static bool idpf_tx_splitq_need_re(struct idpf_tx_queue *tx_q)
+{
+	int gap = tx_q->next_to_use - tx_q->last_re;
+
+	gap += (gap < 0) ? tx_q->desc_count : 0;
+
+	return gap >= IDPF_TX_SPLITQ_RE_MIN_GAP;
+}
+
 /**
  * idpf_tx_splitq_frame - Sends buffer on Tx ring using flex descriptors
  * @skb: send buffer
@@ -2743,12 +2518,15 @@ netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_queue *tx_q, struct sk_buff *skb)
 static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 					struct idpf_tx_queue *tx_q)
 {
-	struct idpf_tx_splitq_params tx_params = { };
+	struct idpf_tx_splitq_params tx_params = {
+		.prev_ntu = tx_q->next_to_use,
+	};
 	struct idpf_tx_buf *first;
-	unsigned int count;
+	u32 count, buf_count = 1;
 	int tso;
+	u32 buf_id;
 
-	count = idpf_tx_desc_count_required(tx_q, skb);
+	count = idpf_tx_res_count_required(tx_q, skb, &buf_count);
 	if (unlikely(!count))
 		return idpf_tx_drop_skb(tx_q, skb);
 
@@ -2758,7 +2536,7 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 
 	/* Check for splitq specific TX resources */
 	count += (IDPF_TX_DESCS_PER_CACHE_LINE + tso);
-	if (idpf_tx_maybe_stop_splitq(tx_q, count)) {
+	if (idpf_tx_maybe_stop_splitq(tx_q, count, buf_count)) {
 		idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false);
 
 		return NETDEV_TX_BUSY;
@@ -2785,36 +2563,47 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 		u64_stats_update_end(&tx_q->stats_sync);
 	}
 
-	/* record the location of the first descriptor for this packet */
-	first = &tx_q->tx_buf[tx_q->next_to_use];
-	first->skb = skb;
+	if (idpf_queue_has(FLOW_SCH_EN, tx_q)) {
+		struct idpf_sw_queue *refillq = tx_q->refillq;
 
-	if (tso) {
-		first->gso_segs = tx_params.offload.tso_segs;
-		first->bytecount = skb->len +
-			((first->gso_segs - 1) * tx_params.offload.tso_hdr_len);
-	} else {
-		first->gso_segs = 1;
-		first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN);
-	}
+		/* Save refillq state in case of a packet rollback.  Otherwise,
+		 * the tags will be leaked since they will be popped from the
+		 * refillq but never reposted during cleaning.
+		 */
+		tx_params.prev_refill_gen =
+			idpf_queue_has(RFL_GEN_CHK, refillq);
+		tx_params.prev_refill_ntc = refillq->next_to_clean;
+
+		if (unlikely(!idpf_tx_get_free_buf_id(tx_q->refillq,
+						      &buf_id))) {
+			if (tx_params.prev_refill_gen !=
+			    idpf_queue_has(RFL_GEN_CHK, refillq))
+				idpf_queue_change(RFL_GEN_CHK, refillq);
+			refillq->next_to_clean = tx_params.prev_refill_ntc;
+
+			tx_q->next_to_use = tx_params.prev_ntu;
+			return idpf_tx_drop_skb(tx_q, skb);
+		}
+		tx_params.compl_tag = buf_id;
 
-	if (idpf_queue_has(FLOW_SCH_EN, tx_q)) {
 		tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE;
 		tx_params.eop_cmd = IDPF_TXD_FLEX_FLOW_CMD_EOP;
-		/* Set the RE bit to catch any packets that may have not been
-		 * stashed during RS completion cleaning. MIN_GAP is set to
-		 * MIN_RING size to ensure it will be set at least once each
-		 * time around the ring.
+		/* Set the RE bit to periodically "clean" the descriptor ring.
+		 * MIN_GAP is set to MIN_RING size to ensure it will be set at
+		 * least once each time around the ring.
 		 */
-		if (!(tx_q->next_to_use % IDPF_TX_SPLITQ_RE_MIN_GAP)) {
+		if (idpf_tx_splitq_need_re(tx_q)) {
 			tx_params.eop_cmd |= IDPF_TXD_FLEX_FLOW_CMD_RE;
 			tx_q->txq_grp->num_completions_pending++;
+			tx_q->last_re = tx_q->next_to_use;
 		}
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL)
 			tx_params.offload.td_cmd |= IDPF_TXD_FLEX_FLOW_CMD_CS_EN;
 
 	} else {
+		buf_id = tx_q->next_to_use;
+
 		tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_L2TAG1_L2TAG2;
 		tx_params.eop_cmd = IDPF_TXD_LAST_DESC_CMD;
 
@@ -2822,6 +2611,18 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 			tx_params.offload.td_cmd |= IDPF_TX_FLEX_DESC_CMD_CS_EN;
 	}
 
+	first = &tx_q->tx_buf[buf_id];
+	first->skb = skb;
+
+	if (tso) {
+		first->packets = tx_params.offload.tso_segs;
+		first->bytes = skb->len +
+			((first->packets - 1) * tx_params.offload.tso_hdr_len);
+	} else {
+		first->packets = 1;
+		first->bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
+	}
+
 	idpf_tx_splitq_map(tx_q, &tx_params, first);
 
 	return NETDEV_TX_OK;
@@ -3375,7 +3176,7 @@ static int idpf_rx_splitq_clean(struct idpf_rx_queue *rxq, int budget)
 		if (!skb)
 			break;
 
-		idpf_rx_post_buf_refill(refillq, buf_id);
+		idpf_post_buf_refill(refillq, buf_id);
 
 		IDPF_RX_BUMP_NTC(rxq, ntc);
 		/* skip if it is non EOP desc */
@@ -3473,10 +3274,10 @@ static void idpf_rx_clean_refillq(struct idpf_buf_queue *bufq,
 		bool failure;
 
 		if (idpf_queue_has(RFL_GEN_CHK, refillq) !=
-		    !!(refill_desc & IDPF_RX_BI_GEN_M))
+		    !!(refill_desc & IDPF_RFL_BI_GEN_M))
 			break;
 
-		buf_id = FIELD_GET(IDPF_RX_BI_BUFID_M, refill_desc);
+		buf_id = FIELD_GET(IDPF_RFL_BI_BUFID_M, refill_desc);
 		failure = idpf_rx_update_bufq_desc(bufq, buf_id, buf_desc);
 		if (failure)
 			break;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index f119f240d21cd..1011e25e9f925 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -113,8 +113,8 @@ do {								\
  */
 #define IDPF_TX_SPLITQ_RE_MIN_GAP	64
 
-#define IDPF_RX_BI_GEN_M		BIT(16)
-#define IDPF_RX_BI_BUFID_M		GENMASK(15, 0)
+#define IDPF_RFL_BI_GEN_M		BIT(16)
+#define IDPF_RFL_BI_BUFID_M		GENMASK(15, 0)
 
 #define IDPF_RXD_EOF_SPLITQ		VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_EOF_M
 #define IDPF_RXD_EOF_SINGLEQ		VIRTCHNL2_RX_BASE_DESC_STATUS_EOF_M
@@ -123,25 +123,16 @@ do {								\
 	((((txq)->next_to_clean > (txq)->next_to_use) ? 0 : (txq)->desc_count) + \
 	(txq)->next_to_clean - (txq)->next_to_use - 1)
 
-#define IDPF_TX_BUF_RSV_UNUSED(txq)	((txq)->stash->buf_stack.top)
-#define IDPF_TX_BUF_RSV_LOW(txq)	(IDPF_TX_BUF_RSV_UNUSED(txq) < \
-					 (txq)->desc_count >> 2)
-
 #define IDPF_TX_COMPLQ_OVERFLOW_THRESH(txcq)	((txcq)->desc_count >> 1)
 /* Determine the absolute number of completions pending, i.e. the number of
  * completions that are expected to arrive on the TX completion queue.
  */
 #define IDPF_TX_COMPLQ_PENDING(txq)	\
 	(((txq)->num_completions_pending >= (txq)->complq->num_completions ? \
-	0 : U64_MAX) + \
+	0 : U32_MAX) + \
 	(txq)->num_completions_pending - (txq)->complq->num_completions)
 
-#define IDPF_TX_SPLITQ_COMPL_TAG_WIDTH	16
-#define IDPF_SPLITQ_TX_INVAL_COMPL_TAG	-1
-/* Adjust the generation for the completion tag and wrap if necessary */
-#define IDPF_TX_ADJ_COMPL_TAG_GEN(txq) \
-	((++(txq)->compl_tag_cur_gen) >= (txq)->compl_tag_gen_max ? \
-	0 : (txq)->compl_tag_cur_gen)
+#define IDPF_TXBUF_NULL			U32_MAX
 
 #define IDPF_TXD_LAST_DESC_CMD (IDPF_TX_DESC_CMD_EOP | IDPF_TX_DESC_CMD_RS)
 
@@ -155,59 +146,7 @@ union idpf_tx_flex_desc {
 	struct idpf_flex_tx_sched_desc flow; /* flow based scheduling */
 };
 
-/**
- * struct idpf_tx_buf
- * @next_to_watch: Next descriptor to clean
- * @skb: Pointer to the skb
- * @dma: DMA address
- * @len: DMA length
- * @bytecount: Number of bytes
- * @gso_segs: Number of GSO segments
- * @compl_tag: Splitq only, unique identifier for a buffer. Used to compare
- *	       with completion tag returned in buffer completion event.
- *	       Because the completion tag is expected to be the same in all
- *	       data descriptors for a given packet, and a single packet can
- *	       span multiple buffers, we need this field to track all
- *	       buffers associated with this completion tag independently of
- *	       the buf_id. The tag consists of a N bit buf_id and M upper
- *	       order "generation bits". See compl_tag_bufid_m and
- *	       compl_tag_gen_s in struct idpf_queue. We'll use a value of -1
- *	       to indicate the tag is not valid.
- * @ctx_entry: Singleq only. Used to indicate the corresponding entry
- *	       in the descriptor ring was used for a context descriptor and
- *	       this buffer entry should be skipped.
- */
-struct idpf_tx_buf {
-	void *next_to_watch;
-	struct sk_buff *skb;
-	DEFINE_DMA_UNMAP_ADDR(dma);
-	DEFINE_DMA_UNMAP_LEN(len);
-	unsigned int bytecount;
-	unsigned short gso_segs;
-
-	union {
-		int compl_tag;
-
-		bool ctx_entry;
-	};
-};
-
-struct idpf_tx_stash {
-	struct hlist_node hlist;
-	struct idpf_tx_buf buf;
-};
-
-/**
- * struct idpf_buf_lifo - LIFO for managing OOO completions
- * @top: Used to know how many buffers are left
- * @size: Total size of LIFO
- * @bufs: Backing array
- */
-struct idpf_buf_lifo {
-	u16 top;
-	u16 size;
-	struct idpf_tx_stash **bufs;
-};
+#define idpf_tx_buf libeth_sqe
 
 /**
  * struct idpf_tx_offload_params - Offload parameters for a given packet
@@ -241,6 +180,9 @@ struct idpf_tx_offload_params {
  * @compl_tag: Associated tag for completion
  * @td_tag: Descriptor tunneling tag
  * @offload: Offload parameters
+ * @prev_ntu: stored TxQ next_to_use in case of rollback
+ * @prev_refill_ntc: stored refillq next_to_clean in case of packet rollback
+ * @prev_refill_gen: stored refillq generation bit in case of packet rollback
  */
 struct idpf_tx_splitq_params {
 	enum idpf_tx_desc_dtype_value dtype;
@@ -251,6 +193,10 @@ struct idpf_tx_splitq_params {
 	};
 
 	struct idpf_tx_offload_params offload;
+
+	u16 prev_ntu;
+	u16 prev_refill_ntc;
+	bool prev_refill_gen;
 };
 
 enum idpf_tx_ctx_desc_eipt_offload {
@@ -589,11 +535,6 @@ struct idpf_tx_queue_stats {
 	u64_stats_t dma_map_errs;
 };
 
-struct idpf_cleaned_stats {
-	u32 packets;
-	u32 bytes;
-};
-
 #define IDPF_ITR_DYNAMIC	1
 #define IDPF_ITR_MAX		0x1FE0
 #define IDPF_ITR_20K		0x0032
@@ -610,17 +551,6 @@ struct idpf_cleaned_stats {
 #define IDPF_ITR_IDX_SPACING(spacing, dflt)	(spacing ? spacing : dflt)
 #define IDPF_DIM_DEFAULT_PROFILE_IX		1
 
-/**
- * struct idpf_txq_stash - Tx buffer stash for Flow-based scheduling mode
- * @buf_stack: Stack of empty buffers to store buffer info for out of order
- *	       buffer completions. See struct idpf_buf_lifo
- * @sched_buf_hash: Hash table to store buffers
- */
-struct idpf_txq_stash {
-	struct idpf_buf_lifo buf_stack;
-	DECLARE_HASHTABLE(sched_buf_hash, 12);
-} ____cacheline_aligned;
-
 /**
  * struct idpf_rx_queue - software structure representing a receive queue
  * @rx: universal receive descriptor array
@@ -718,6 +648,8 @@ struct idpf_rx_queue {
  * @desc_count: Number of descriptors
  * @next_to_use: Next descriptor to use
  * @next_to_clean: Next descriptor to clean
+ * @last_re: last descriptor index that RE bit was set
+ * @tx_max_bufs: Max buffers that can be transmitted with scatter-gather
  * @netdev: &net_device corresponding to this queue
  * @cleaned_bytes: Splitq only, TXQ only: When a TX completion is received on
  *		   the TX completion queue, it can be for any TXQ associated
@@ -729,9 +661,8 @@ struct idpf_rx_queue {
  *		   only once at the end of the cleaning routine.
  * @clean_budget: singleq only, queue cleaning budget
  * @cleaned_pkts: Number of packets cleaned for the above said case
- * @tx_max_bufs: Max buffers that can be transmitted with scatter-gather
  * @tx_min_pkt_len: Min supported packet length
- * @compl_tag_bufid_m: Completion tag buffer id mask
+ * @refillq: Pointer to refill queue
  * @compl_tag_gen_s: Completion tag generation bit
  *	The format of the completion tag will change based on the TXQ
  *	descriptor ring size so that we can maintain roughly the same level
@@ -752,15 +683,13 @@ struct idpf_rx_queue {
  *	--------------------------------
  *
  *	This gives us 8*8160 = 65280 possible unique values.
- * @compl_tag_cur_gen: Used to keep track of current completion tag generation
- * @compl_tag_gen_max: To determine when compl_tag_cur_gen should be reset
- * @stash: Tx buffer stash for Flow-based scheduling mode
  * @stats_sync: See struct u64_stats_sync
  * @q_stats: See union idpf_tx_queue_stats
  * @q_id: Queue id
  * @size: Length of descriptor ring in bytes
  * @dma: Physical address of ring
  * @q_vector: Backreference to associated vector
+ * @buf_pool_size: Total number of idpf_tx_buf
  */
 struct idpf_tx_queue {
 	union {
@@ -771,7 +700,7 @@ struct idpf_tx_queue {
 
 		void *desc_ring;
 	};
-	struct idpf_tx_buf *tx_buf;
+	struct libeth_sqe *tx_buf;
 	struct idpf_txq_group *txq_grp;
 	struct device *dev;
 	void __iomem *tail;
@@ -781,6 +710,8 @@ struct idpf_tx_queue {
 	u16 desc_count;
 	u16 next_to_use;
 	u16 next_to_clean;
+	u16 last_re;
+	u16 tx_max_bufs;
 
 	struct net_device *netdev;
 
@@ -790,16 +721,8 @@ struct idpf_tx_queue {
 	};
 	u16 cleaned_pkts;
 
-	u16 tx_max_bufs;
 	u16 tx_min_pkt_len;
-
-	u16 compl_tag_bufid_m;
-	u16 compl_tag_gen_s;
-
-	u16 compl_tag_cur_gen;
-	u16 compl_tag_gen_max;
-
-	struct idpf_txq_stash *stash;
+	struct idpf_sw_queue *refillq;
 
 	struct u64_stats_sync stats_sync;
 	struct idpf_tx_queue_stats q_stats;
@@ -810,6 +733,7 @@ struct idpf_tx_queue {
 	dma_addr_t dma;
 
 	struct idpf_q_vector *q_vector;
+	u32 buf_pool_size;
 } ____cacheline_aligned;
 
 /**
@@ -893,7 +817,7 @@ struct idpf_compl_queue {
 
 	struct net_device *netdev;
 	u32 clean_budget;
-	u32 num_completions;
+	aligned_u64 num_completions;
 
 	/* Slowpath */
 	u32 q_id;
@@ -995,7 +919,6 @@ struct idpf_rxq_group {
  * @vport: Vport back pointer
  * @num_txq: Number of TX queues associated
  * @txqs: Array of TX queue pointers
- * @stashes: array of OOO stashes for the queues
  * @complq: Associated completion queue pointer, split queue only
  * @num_completions_pending: Total number of completions pending for the
  *			     completion queue, acculumated for all TX queues
@@ -1010,11 +933,10 @@ struct idpf_txq_group {
 
 	u16 num_txq;
 	struct idpf_tx_queue *txqs[IDPF_LARGE_MAX_Q];
-	struct idpf_txq_stash *stashes;
 
 	struct idpf_compl_queue *complq;
 
-	u32 num_completions_pending;
+	aligned_u64 num_completions_pending;
 };
 
 /**
@@ -1143,6 +1065,17 @@ static inline void idpf_vport_intr_set_wb_on_itr(struct idpf_q_vector *q_vector)
 	       reg->dyn_ctl);
 }
 
+/**
+ * idpf_tx_splitq_get_free_bufs - get number of free buf_ids in refillq
+ * @refillq: pointer to refillq containing buf_ids
+ */
+static inline u32 idpf_tx_splitq_get_free_bufs(struct idpf_sw_queue *refillq)
+{
+	return (refillq->next_to_use > refillq->next_to_clean ?
+		0 : refillq->desc_count) +
+	       refillq->next_to_use - refillq->next_to_clean - 1;
+}
+
 int idpf_vport_singleq_napi_poll(struct napi_struct *napi, int budget);
 void idpf_vport_init_num_qs(struct idpf_vport *vport,
 			    struct virtchnl2_create_vport *vport_msg);
@@ -1173,10 +1106,8 @@ void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
 			   bool xmit_more);
 unsigned int idpf_size_to_txd_count(unsigned int size);
 netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_queue *tx_q, struct sk_buff *skb);
-void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
-			   struct idpf_tx_buf *first, u16 ring_idx);
-unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
-					 struct sk_buff *skb);
+unsigned int idpf_tx_res_count_required(struct idpf_tx_queue *txq,
+					struct sk_buff *skb, u32 *buf_count);
 void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue);
 netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 				  struct idpf_tx_queue *tx_q);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cef072e7cfbbc..de45924a74c49 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3699,6 +3699,17 @@ static inline void netdev_tx_reset_queue(struct netdev_queue *q)
 #endif
 }
 
+/**
+ * netdev_tx_reset_subqueue - reset the BQL stats and state of a netdev queue
+ * @dev: network device
+ * @qid: stack index of the queue to reset
+ */
+static inline void netdev_tx_reset_subqueue(const struct net_device *dev,
+					    u32 qid)
+{
+	netdev_tx_reset_queue(netdev_get_tx_queue(dev, qid));
+}
+
 /**
  * 	netdev_reset_queue - reset the packets and bytes count of a network device
  * 	@dev_queue: network device
@@ -3708,7 +3719,7 @@ static inline void netdev_tx_reset_queue(struct netdev_queue *q)
  */
 static inline void netdev_reset_queue(struct net_device *dev_queue)
 {
-	netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0));
+	netdev_tx_reset_subqueue(dev_queue, 0);
 }
 
 /**
diff --git a/include/net/libeth/tx.h b/include/net/libeth/tx.h
new file mode 100644
index 0000000000000..35614f9523f60
--- /dev/null
+++ b/include/net/libeth/tx.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2024 Intel Corporation */
+
+#ifndef __LIBETH_TX_H
+#define __LIBETH_TX_H
+
+#include <linux/skbuff.h>
+
+#include <net/libeth/types.h>
+
+/* Tx buffer completion */
+
+/**
+ * enum libeth_sqe_type - type of &libeth_sqe to act on Tx completion
+ * @LIBETH_SQE_EMPTY: unused/empty, no action required
+ * @LIBETH_SQE_CTX: context descriptor with empty SQE, no action required
+ * @LIBETH_SQE_SLAB: kmalloc-allocated buffer, unmap and kfree()
+ * @LIBETH_SQE_FRAG: mapped skb frag, only unmap DMA
+ * @LIBETH_SQE_SKB: &sk_buff, unmap and napi_consume_skb(), update stats
+ */
+enum libeth_sqe_type {
+	LIBETH_SQE_EMPTY		= 0U,
+	LIBETH_SQE_CTX,
+	LIBETH_SQE_SLAB,
+	LIBETH_SQE_FRAG,
+	LIBETH_SQE_SKB,
+};
+
+/**
+ * struct libeth_sqe - represents a Send Queue Element / Tx buffer
+ * @type: type of the buffer, see the enum above
+ * @rs_idx: index of the last buffer from the batch this one was sent in
+ * @raw: slab buffer to free via kfree()
+ * @skb: &sk_buff to consume
+ * @dma: DMA address to unmap
+ * @len: length of the mapped region to unmap
+ * @nr_frags: number of frags in the frame this buffer belongs to
+ * @packets: number of physical packets sent for this frame
+ * @bytes: number of physical bytes sent for this frame
+ * @priv: driver-private scratchpad
+ */
+struct libeth_sqe {
+	enum libeth_sqe_type		type:32;
+	u32				rs_idx;
+
+	union {
+		void				*raw;
+		struct sk_buff			*skb;
+	};
+
+	DEFINE_DMA_UNMAP_ADDR(dma);
+	DEFINE_DMA_UNMAP_LEN(len);
+
+	u32				nr_frags;
+	u32				packets;
+	u32				bytes;
+
+	unsigned long			priv;
+} __aligned_largest;
+
+/**
+ * LIBETH_SQE_CHECK_PRIV - check the driver's private SQE data
+ * @p: type or name of the object the driver wants to fit into &libeth_sqe
+ *
+ * Make sure the driver's private data fits into libeth_sqe::priv. To be used
+ * right after its declaration.
+ */
+#define LIBETH_SQE_CHECK_PRIV(p)					  \
+	static_assert(sizeof(p) <= sizeof_field(struct libeth_sqe, priv))
+
+/**
+ * struct libeth_cq_pp - completion queue poll params
+ * @dev: &device to perform DMA unmapping
+ * @ss: onstack NAPI stats to fill
+ * @napi: whether it's called from the NAPI context
+ *
+ * libeth uses this structure to access objects needed for performing full
+ * Tx complete operation without passing lots of arguments and change the
+ * prototypes each time a new one is added.
+ */
+struct libeth_cq_pp {
+	struct device			*dev;
+	struct libeth_sq_napi_stats	*ss;
+
+	bool				napi;
+};
+
+/**
+ * libeth_tx_complete - perform Tx completion for one SQE
+ * @sqe: SQE to complete
+ * @cp: poll params
+ *
+ * Do Tx complete for all the types of buffers, incl. freeing, unmapping,
+ * updating the stats etc.
+ */
+static inline void libeth_tx_complete(struct libeth_sqe *sqe,
+				      const struct libeth_cq_pp *cp)
+{
+	switch (sqe->type) {
+	case LIBETH_SQE_EMPTY:
+		return;
+	case LIBETH_SQE_SKB:
+	case LIBETH_SQE_FRAG:
+	case LIBETH_SQE_SLAB:
+		dma_unmap_page(cp->dev, dma_unmap_addr(sqe, dma),
+			       dma_unmap_len(sqe, len), DMA_TO_DEVICE);
+		break;
+	default:
+		break;
+	}
+
+	switch (sqe->type) {
+	case LIBETH_SQE_SKB:
+		cp->ss->packets += sqe->packets;
+		cp->ss->bytes += sqe->bytes;
+
+		napi_consume_skb(sqe->skb, cp->napi);
+		break;
+	case LIBETH_SQE_SLAB:
+		kfree(sqe->raw);
+		break;
+	default:
+		break;
+	}
+
+	sqe->type = LIBETH_SQE_EMPTY;
+}
+
+#endif /* __LIBETH_TX_H */
diff --git a/include/net/libeth/types.h b/include/net/libeth/types.h
new file mode 100644
index 0000000000000..603825e451339
--- /dev/null
+++ b/include/net/libeth/types.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2024 Intel Corporation */
+
+#ifndef __LIBETH_TYPES_H
+#define __LIBETH_TYPES_H
+
+#include <linux/types.h>
+
+/**
+ * struct libeth_sq_napi_stats - "hot" counters to update in Tx completion loop
+ * @packets: completed frames counter
+ * @bytes: sum of bytes of completed frames above
+ * @raw: alias to access all the fields as an array
+ */
+struct libeth_sq_napi_stats {
+	union {
+		struct {
+							u32 packets;
+							u32 bytes;
+		};
+		DECLARE_FLEX_ARRAY(u32, raw);
+	};
+};
+
+#endif /* __LIBETH_TYPES_H */