Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue

Tony Nguyen says:

====================
Intel Wired LAN Driver Updates 2025-10-29 (ice, i40e, idpf, ixgbe, igbvf)

For ice:
Michal converts driver to utilize Page Pool and libeth APIs. Conversion
is based on similar changes done for iavf in order to simplify buffer
management, improve maintainability, and increase code reuse across
Intel Ethernet drivers.

Additional details:
https://lore.kernel.org/20250925092253.1306476-1-michal.kubiak@intel.com

Alexander adds support for header split, configurable via ethtool.

Grzegorz allows for use of 100Mbps on E825C SGMII devices.

For i40e:
Jay Vosburgh avoids sending link state changes to VF if it is already in
the requested state.

For idpf:
Sreedevi removes duplicated defines.

For ixgbe:
Alok Tiwari fixes some typos.

For igbvf:
Alok Tiwari fixes output of VLAN warning message.

* '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue:
  igbvf: fix misplaced newline in VLAN add warning message
  ixgbe: fix typos in ixgbe driver comments
  idpf: remove duplicate defines in IDPF_CAP_RSS
  i40e: avoid redundant VF link state updates
  ice: Allow 100M speed for E825C SGMII device
  ice: implement configurable header split for regular Rx
  ice: switch to Page Pool
  ice: drop page splitting and recycling
  ice: remove legacy Rx and construct SKB
====================

Link: https://patch.msgid.link/20251029231218.1277233-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 136 insertions, 574 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 73f08d02f9c7..ad76768a4232 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -7,6 +7,8 @@
 #include <linux/netdevice.h>
 #include <linux/prefetch.h>
 #include <linux/bpf_trace.h>
+#include <linux/net/intel/libie/rx.h>
+#include <net/libeth/xdp.h>
 #include <net/dsfield.h>
 #include <net/mpls.h>
 #include <net/xdp.h>
@@ -111,7 +113,7 @@ ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc,
 static void
 ice_unmap_and_free_tx_buf(struct ice_tx_ring *ring, struct ice_tx_buf *tx_buf)
 {
-	if (dma_unmap_len(tx_buf, len))
+	if (tx_buf->type != ICE_TX_BUF_XDP_TX && dma_unmap_len(tx_buf, len))
 		dma_unmap_page(ring->dev,
 			       dma_unmap_addr(tx_buf, dma),
 			       dma_unmap_len(tx_buf, len),
@@ -125,7 +127,7 @@ ice_unmap_and_free_tx_buf(struct ice_tx_ring *ring, struct ice_tx_buf *tx_buf)
 		dev_kfree_skb_any(tx_buf->skb);
 		break;
 	case ICE_TX_BUF_XDP_TX:
-		page_frag_free(tx_buf->raw_buf);
+		libeth_xdp_return_va(tx_buf->raw_buf, false);
 		break;
 	case ICE_TX_BUF_XDP_XMIT:
 		xdp_return_frame(tx_buf->xdpf);
@@ -506,61 +508,67 @@ err:
 	return -ENOMEM;
 }
 
+void ice_rxq_pp_destroy(struct ice_rx_ring *rq)
+{
+	struct libeth_fq fq = {
+		.fqes	= rq->rx_fqes,
+		.pp	= rq->pp,
+	};
+
+	libeth_rx_fq_destroy(&fq);
+	rq->rx_fqes = NULL;
+	rq->pp = NULL;
+
+	if (!rq->hdr_pp)
+		return;
+
+	fq.fqes = rq->hdr_fqes;
+	fq.pp = rq->hdr_pp;
+
+	libeth_rx_fq_destroy(&fq);
+	rq->hdr_fqes = NULL;
+	rq->hdr_pp = NULL;
+}
+
 /**
  * ice_clean_rx_ring - Free Rx buffers
  * @rx_ring: ring to be cleaned
  */
 void ice_clean_rx_ring(struct ice_rx_ring *rx_ring)
 {
-	struct xdp_buff *xdp = &rx_ring->xdp;
-	struct device *dev = rx_ring->dev;
 	u32 size;
-	u16 i;
-
-	/* ring already cleared, nothing to do */
-	if (!rx_ring->rx_buf)
-		return;
 
 	if (rx_ring->xsk_pool) {
 		ice_xsk_clean_rx_ring(rx_ring);
 		goto rx_skip_free;
 	}
 
-	if (xdp->data) {
-		xdp_return_buff(xdp);
-		xdp->data = NULL;
-	}
+	/* ring already cleared, nothing to do */
+	if (!rx_ring->rx_fqes)
+		return;
+
+	libeth_xdp_return_stash(&rx_ring->xdp);
 
 	/* Free all the Rx ring sk_buffs */
-	for (i = 0; i < rx_ring->count; i++) {
-		struct ice_rx_buf *rx_buf = &rx_ring->rx_buf[i];
+	for (u32 i = rx_ring->next_to_clean; i != rx_ring->next_to_use; ) {
+		libeth_rx_recycle_slow(rx_ring->rx_fqes[i].netmem);
 
-		if (!rx_buf->page)
-			continue;
+		if (rx_ring->hdr_pp)
+			libeth_rx_recycle_slow(rx_ring->hdr_fqes[i].netmem);
 
-		/* Invalidate cache lines that may have been written to by
-		 * device so that we avoid corrupting memory.
-		 */
-		dma_sync_single_range_for_cpu(dev, rx_buf->dma,
-					      rx_buf->page_offset,
-					      rx_ring->rx_buf_len,
-					      DMA_FROM_DEVICE);
-
-		/* free resources associated with mapping */
-		dma_unmap_page_attrs(dev, rx_buf->dma, ice_rx_pg_size(rx_ring),
-				     DMA_FROM_DEVICE, ICE_RX_DMA_ATTR);
-		__page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias);
-
-		rx_buf->page = NULL;
-		rx_buf->page_offset = 0;
+		if (unlikely(++i == rx_ring->count))
+			i = 0;
 	}
 
-rx_skip_free:
-	if (rx_ring->xsk_pool)
-		memset(rx_ring->xdp_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->xdp_buf)));
-	else
-		memset(rx_ring->rx_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->rx_buf)));
+	if (rx_ring->vsi->type == ICE_VSI_PF &&
+	    xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) {
+		xdp_rxq_info_detach_mem_model(&rx_ring->xdp_rxq);
+		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
+	}
 
+	ice_rxq_pp_destroy(rx_ring);
+
+rx_skip_free:
 	/* Zero out the descriptor ring */
 	size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
 		     PAGE_SIZE);
@@ -568,7 +576,6 @@ rx_skip_free:
 
 	rx_ring->next_to_alloc = 0;
 	rx_ring->next_to_clean = 0;
-	rx_ring->first_desc = 0;
 	rx_ring->next_to_use = 0;
 }
 
@@ -580,26 +587,20 @@ rx_skip_free:
  */
 void ice_free_rx_ring(struct ice_rx_ring *rx_ring)
 {
+	struct device *dev = ice_pf_to_dev(rx_ring->vsi->back);
 	u32 size;
 
 	ice_clean_rx_ring(rx_ring);
-	if (rx_ring->vsi->type == ICE_VSI_PF)
-		if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
-			xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
 	WRITE_ONCE(rx_ring->xdp_prog, NULL);
 	if (rx_ring->xsk_pool) {
 		kfree(rx_ring->xdp_buf);
 		rx_ring->xdp_buf = NULL;
-	} else {
-		kfree(rx_ring->rx_buf);
-		rx_ring->rx_buf = NULL;
 	}
 
 	if (rx_ring->desc) {
 		size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
 			     PAGE_SIZE);
-		dmam_free_coherent(rx_ring->dev, size,
-				   rx_ring->desc, rx_ring->dma);
+		dmam_free_coherent(dev, size, rx_ring->desc, rx_ring->dma);
 		rx_ring->desc = NULL;
 	}
 }
@@ -612,19 +613,9 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring)
  */
 int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
 {
-	struct device *dev = rx_ring->dev;
+	struct device *dev = ice_pf_to_dev(rx_ring->vsi->back);
 	u32 size;
 
-	if (!dev)
-		return -ENOMEM;
-
-	/* warn if we are about to overwrite the pointer */
-	WARN_ON(rx_ring->rx_buf);
-	rx_ring->rx_buf =
-		kcalloc(rx_ring->count, sizeof(*rx_ring->rx_buf), GFP_KERNEL);
-	if (!rx_ring->rx_buf)
-		return -ENOMEM;
-
 	/* round up to nearest page */
 	size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
 		     PAGE_SIZE);
@@ -633,22 +624,16 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
 	if (!rx_ring->desc) {
 		dev_err(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n",
 			size);
-		goto err;
+		return -ENOMEM;
 	}
 
 	rx_ring->next_to_use = 0;
 	rx_ring->next_to_clean = 0;
-	rx_ring->first_desc = 0;
 
 	if (ice_is_xdp_ena_vsi(rx_ring->vsi))
 		WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog);
 
 	return 0;
-
-err:
-	kfree(rx_ring->rx_buf);
-	rx_ring->rx_buf = NULL;
-	return -ENOMEM;
 }
 
 /**
@@ -662,7 +647,7 @@ err:
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
 static u32
-ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
+ice_run_xdp(struct ice_rx_ring *rx_ring, struct libeth_xdp_buff *xdp,
 	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
 	    union ice_32b_rx_flex_desc *eop_desc)
 {
@@ -672,23 +657,23 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	if (!xdp_prog)
 		goto exit;
 
-	ice_xdp_meta_set_desc(xdp, eop_desc);
+	xdp->desc = eop_desc;
 
-	act = bpf_prog_run_xdp(xdp_prog, xdp);
+	act = bpf_prog_run_xdp(xdp_prog, &xdp->base);
 	switch (act) {
 	case XDP_PASS:
 		break;
 	case XDP_TX:
 		if (static_branch_unlikely(&ice_xdp_locking_key))
 			spin_lock(&xdp_ring->tx_lock);
-		ret = __ice_xmit_xdp_ring(xdp, xdp_ring, false);
+		ret = __ice_xmit_xdp_ring(&xdp->base, xdp_ring, false);
 		if (static_branch_unlikely(&ice_xdp_locking_key))
 			spin_unlock(&xdp_ring->tx_lock);
 		if (ret == ICE_XDP_CONSUMED)
 			goto out_failure;
 		break;
 	case XDP_REDIRECT:
-		if (xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog))
+		if (xdp_do_redirect(rx_ring->netdev, &xdp->base, xdp_prog))
 			goto out_failure;
 		ret = ICE_XDP_REDIR;
 		break;
@@ -700,8 +685,10 @@ out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough;
 	case XDP_DROP:
+		libeth_xdp_return_buff(xdp);
 		ret = ICE_XDP_CONSUMED;
 	}
+
 exit:
 	return ret;
 }
@@ -790,53 +777,6 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 }
 
 /**
- * ice_alloc_mapped_page - recycle or make a new page
- * @rx_ring: ring to use
- * @bi: rx_buf struct to modify
- *
- * Returns true if the page was successfully allocated or
- * reused.
- */
-static bool
-ice_alloc_mapped_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *bi)
-{
-	struct page *page = bi->page;
-	dma_addr_t dma;
-
-	/* since we are recycling buffers we should seldom need to alloc */
-	if (likely(page))
-		return true;
-
-	/* alloc new page for storage */
-	page = dev_alloc_pages(ice_rx_pg_order(rx_ring));
-	if (unlikely(!page)) {
-		rx_ring->ring_stats->rx_stats.alloc_page_failed++;
-		return false;
-	}
-
-	/* map page for use */
-	dma = dma_map_page_attrs(rx_ring->dev, page, 0, ice_rx_pg_size(rx_ring),
-				 DMA_FROM_DEVICE, ICE_RX_DMA_ATTR);
-
-	/* if mapping failed free memory back to system since
-	 * there isn't much point in holding memory we can't use
-	 */
-	if (dma_mapping_error(rx_ring->dev, dma)) {
-		__free_pages(page, ice_rx_pg_order(rx_ring));
-		rx_ring->ring_stats->rx_stats.alloc_page_failed++;
-		return false;
-	}
-
-	bi->dma = dma;
-	bi->page = page;
-	bi->page_offset = rx_ring->rx_offset;
-	page_ref_add(page, USHRT_MAX - 1);
-	bi->pagecnt_bias = USHRT_MAX;
-
-	return true;
-}
-
-/**
  * ice_init_ctrl_rx_descs - Initialize Rx descriptors for control vsi.
  * @rx_ring: ring to init descriptors on
  * @count: number of descriptors to initialize
@@ -882,9 +822,20 @@ void ice_init_ctrl_rx_descs(struct ice_rx_ring *rx_ring, u32 count)
  */
 bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, unsigned int cleaned_count)
 {
+	const struct libeth_fq_fp hdr_fq = {
+		.pp		= rx_ring->hdr_pp,
+		.fqes		= rx_ring->hdr_fqes,
+		.truesize	= rx_ring->hdr_truesize,
+		.count		= rx_ring->count,
+	};
+	const struct libeth_fq_fp fq = {
+		.pp		= rx_ring->pp,
+		.fqes		= rx_ring->rx_fqes,
+		.truesize	= rx_ring->truesize,
+		.count		= rx_ring->count,
+	};
 	union ice_32b_rx_flex_desc *rx_desc;
 	u16 ntu = rx_ring->next_to_use;
-	struct ice_rx_buf *bi;
 
 	/* do nothing if no valid netdev defined */
 	if (!rx_ring->netdev || !cleaned_count)
@@ -892,30 +843,39 @@ bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, unsigned int cleaned_count)
 
 	/* get the Rx descriptor and buffer based on next_to_use */
 	rx_desc = ICE_RX_DESC(rx_ring, ntu);
-	bi = &rx_ring->rx_buf[ntu];
 
 	do {
-		/* if we fail here, we have work remaining */
-		if (!ice_alloc_mapped_page(rx_ring, bi))
-			break;
+		dma_addr_t addr;
 
-		/* sync the buffer for use by the device */
-		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
-						 bi->page_offset,
-						 rx_ring->rx_buf_len,
-						 DMA_FROM_DEVICE);
+		addr = libeth_rx_alloc(&fq, ntu);
+		if (addr == DMA_MAPPING_ERROR) {
+			rx_ring->ring_stats->rx_stats.alloc_page_failed++;
+			break;
+		}
 
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
-		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);
+		rx_desc->read.pkt_addr = cpu_to_le64(addr);
+
+		if (!hdr_fq.pp)
+			goto next;
+
+		addr = libeth_rx_alloc(&hdr_fq, ntu);
+		if (addr == DMA_MAPPING_ERROR) {
+			rx_ring->ring_stats->rx_stats.alloc_page_failed++;
+
+			libeth_rx_recycle_slow(fq.fqes[ntu].netmem);
+			break;
+		}
+
+		rx_desc->read.hdr_addr = cpu_to_le64(addr);
 
+next:
 		rx_desc++;
-		bi++;
 		ntu++;
 		if (unlikely(ntu == rx_ring->count)) {
 			rx_desc = ICE_RX_DESC(rx_ring, 0);
-			bi = rx_ring->rx_buf;
 			ntu = 0;
 		}
 
@@ -932,402 +892,6 @@ bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, unsigned int cleaned_count)
 }
 
 /**
- * ice_rx_buf_adjust_pg_offset - Prepare Rx buffer for reuse
- * @rx_buf: Rx buffer to adjust
- * @size: Size of adjustment
- *
- * Update the offset within page so that Rx buf will be ready to be reused.
- * For systems with PAGE_SIZE < 8192 this function will flip the page offset
- * so the second half of page assigned to Rx buffer will be used, otherwise
- * the offset is moved by "size" bytes
- */
-static void
-ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size)
-{
-#if (PAGE_SIZE < 8192)
-	/* flip page offset to other buffer */
-	rx_buf->page_offset ^= size;
-#else
-	/* move offset up to the next cache line */
-	rx_buf->page_offset += size;
-#endif
-}
-
-/**
- * ice_can_reuse_rx_page - Determine if page can be reused for another Rx
- * @rx_buf: buffer containing the page
- *
- * If page is reusable, we have a green light for calling ice_reuse_rx_page,
- * which will assign the current buffer to the buffer that next_to_alloc is
- * pointing to; otherwise, the DMA mapping needs to be destroyed and
- * page freed
- */
-static bool
-ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf)
-{
-	unsigned int pagecnt_bias = rx_buf->pagecnt_bias;
-	struct page *page = rx_buf->page;
-
-	/* avoid re-using remote and pfmemalloc pages */
-	if (!dev_page_is_reusable(page))
-		return false;
-
-	/* if we are only owner of page we can reuse it */
-	if (unlikely(rx_buf->pgcnt - pagecnt_bias > 1))
-		return false;
-#if (PAGE_SIZE >= 8192)
-#define ICE_LAST_OFFSET \
-	(SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_3072)
-	if (rx_buf->page_offset > ICE_LAST_OFFSET)
-		return false;
-#endif /* PAGE_SIZE >= 8192) */
-
-	/* If we have drained the page fragment pool we need to update
-	 * the pagecnt_bias and page count so that we fully restock the
-	 * number of references the driver holds.
-	 */
-	if (unlikely(pagecnt_bias == 1)) {
-		page_ref_add(page, USHRT_MAX - 1);
-		rx_buf->pagecnt_bias = USHRT_MAX;
-	}
-
-	return true;
-}
-
-/**
- * ice_add_xdp_frag - Add contents of Rx buffer to xdp buf as a frag
- * @rx_ring: Rx descriptor ring to transact packets on
- * @xdp: xdp buff to place the data into
- * @rx_buf: buffer containing page to add
- * @size: packet length from rx_desc
- *
- * This function will add the data contained in rx_buf->page to the xdp buf.
- * It will just attach the page as a frag.
- */
-static int
-ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
-		 struct ice_rx_buf *rx_buf, const unsigned int size)
-{
-	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
-
-	if (!size)
-		return 0;
-
-	if (!xdp_buff_has_frags(xdp)) {
-		sinfo->nr_frags = 0;
-		sinfo->xdp_frags_size = 0;
-		xdp_buff_set_frags_flag(xdp);
-	}
-
-	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS))
-		return -ENOMEM;
-
-	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page,
-				   rx_buf->page_offset, size);
-	sinfo->xdp_frags_size += size;
-
-	if (page_is_pfmemalloc(rx_buf->page))
-		xdp_buff_set_frag_pfmemalloc(xdp);
-
-	return 0;
-}
-
-/**
- * ice_reuse_rx_page - page flip buffer and store it back on the ring
- * @rx_ring: Rx descriptor ring to store buffers on
- * @old_buf: donor buffer to have page reused
- *
- * Synchronizes page for reuse by the adapter
- */
-static void
-ice_reuse_rx_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *old_buf)
-{
-	u16 nta = rx_ring->next_to_alloc;
-	struct ice_rx_buf *new_buf;
-
-	new_buf = &rx_ring->rx_buf[nta];
-
-	/* update, and store next to alloc */
-	nta++;
-	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
-
-	/* Transfer page from old buffer to new buffer.
-	 * Move each member individually to avoid possible store
-	 * forwarding stalls and unnecessary copy of skb.
-	 */
-	new_buf->dma = old_buf->dma;
-	new_buf->page = old_buf->page;
-	new_buf->page_offset = old_buf->page_offset;
-	new_buf->pagecnt_bias = old_buf->pagecnt_bias;
-}
-
-/**
- * ice_get_rx_buf - Fetch Rx buffer and synchronize data for use
- * @rx_ring: Rx descriptor ring to transact packets on
- * @size: size of buffer to add to skb
- * @ntc: index of next to clean element
- *
- * This function will pull an Rx buffer from the ring and synchronize it
- * for use by the CPU.
- */
-static struct ice_rx_buf *
-ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
-	       const unsigned int ntc)
-{
-	struct ice_rx_buf *rx_buf;
-
-	rx_buf = &rx_ring->rx_buf[ntc];
-	prefetchw(rx_buf->page);
-
-	if (!size)
-		return rx_buf;
-	/* we are reusing so sync this buffer for CPU use */
-	dma_sync_single_range_for_cpu(rx_ring->dev, rx_buf->dma,
-				      rx_buf->page_offset, size,
-				      DMA_FROM_DEVICE);
-
-	/* We have pulled a buffer for use, so decrement pagecnt_bias */
-	rx_buf->pagecnt_bias--;
-
-	return rx_buf;
-}
-
-/**
- * ice_get_pgcnts - grab page_count() for gathered fragments
- * @rx_ring: Rx descriptor ring to store the page counts on
- * @ntc: the next to clean element (not included in this frame!)
- *
- * This function is intended to be called right before running XDP
- * program so that the page recycling mechanism will be able to take
- * a correct decision regarding underlying pages; this is done in such
- * way as XDP program can change the refcount of page
- */
-static void ice_get_pgcnts(struct ice_rx_ring *rx_ring, unsigned int ntc)
-{
-	u32 idx = rx_ring->first_desc;
-	struct ice_rx_buf *rx_buf;
-	u32 cnt = rx_ring->count;
-
-	while (idx != ntc) {
-		rx_buf = &rx_ring->rx_buf[idx];
-		rx_buf->pgcnt = page_count(rx_buf->page);
-
-		if (++idx == cnt)
-			idx = 0;
-	}
-}
-
-/**
- * ice_build_skb - Build skb around an existing buffer
- * @rx_ring: Rx descriptor ring to transact packets on
- * @xdp: xdp_buff pointing to the data
- *
- * This function builds an skb around an existing XDP buffer, taking care
- * to set up the skb correctly and avoid any memcpy overhead. Driver has
- * already combined frags (if any) to skb_shared_info.
- */
-static struct sk_buff *
-ice_build_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
-{
-	u8 metasize = xdp->data - xdp->data_meta;
-	struct skb_shared_info *sinfo = NULL;
-	unsigned int nr_frags;
-	struct sk_buff *skb;
-
-	if (unlikely(xdp_buff_has_frags(xdp))) {
-		sinfo = xdp_get_shared_info_from_buff(xdp);
-		nr_frags = sinfo->nr_frags;
-	}
-
-	/* Prefetch first cache line of first page. If xdp->data_meta
-	 * is unused, this points exactly as xdp->data, otherwise we
-	 * likely have a consumer accessing first few bytes of meta
-	 * data, and then actual data.
-	 */
-	net_prefetch(xdp->data_meta);
-	/* build an skb around the page buffer */
-	skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz);
-	if (unlikely(!skb))
-		return NULL;
-
-	/* must to record Rx queue, otherwise OS features such as
-	 * symmetric queue won't work
-	 */
-	skb_record_rx_queue(skb, rx_ring->q_index);
-
-	/* update pointers within the skb to store the data */
-	skb_reserve(skb, xdp->data - xdp->data_hard_start);
-	__skb_put(skb, xdp->data_end - xdp->data);
-	if (metasize)
-		skb_metadata_set(skb, metasize);
-
-	if (unlikely(xdp_buff_has_frags(xdp)))
-		xdp_update_skb_frags_info(skb, nr_frags, sinfo->xdp_frags_size,
-					  nr_frags * xdp->frame_sz,
-					  xdp_buff_get_skb_flags(xdp));
-
-	return skb;
-}
-
-/**
- * ice_construct_skb - Allocate skb and populate it
- * @rx_ring: Rx descriptor ring to transact packets on
- * @xdp: xdp_buff pointing to the data
- *
- * This function allocates an skb. It then populates it with the page
- * data from the current receive descriptor, taking care to set up the
- * skb correctly.
- */
-static struct sk_buff *
-ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
-{
-	unsigned int size = xdp->data_end - xdp->data;
-	struct skb_shared_info *sinfo = NULL;
-	struct ice_rx_buf *rx_buf;
-	unsigned int nr_frags = 0;
-	unsigned int headlen;
-	struct sk_buff *skb;
-
-	/* prefetch first cache line of first page */
-	net_prefetch(xdp->data);
-
-	if (unlikely(xdp_buff_has_frags(xdp))) {
-		sinfo = xdp_get_shared_info_from_buff(xdp);
-		nr_frags = sinfo->nr_frags;
-	}
-
-	/* allocate a skb to store the frags */
-	skb = napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE);
-	if (unlikely(!skb))
-		return NULL;
-
-	rx_buf = &rx_ring->rx_buf[rx_ring->first_desc];
-	skb_record_rx_queue(skb, rx_ring->q_index);
-	/* Determine available headroom for copy */
-	headlen = size;
-	if (headlen > ICE_RX_HDR_SIZE)
-		headlen = eth_get_headlen(skb->dev, xdp->data, ICE_RX_HDR_SIZE);
-
-	/* align pull length to size of long to optimize memcpy performance */
-	memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen,
-							 sizeof(long)));
-
-	/* if we exhaust the linear part then add what is left as a frag */
-	size -= headlen;
-	if (size) {
-		/* besides adding here a partial frag, we are going to add
-		 * frags from xdp_buff, make sure there is enough space for
-		 * them
-		 */
-		if (unlikely(nr_frags >= MAX_SKB_FRAGS - 1)) {
-			dev_kfree_skb(skb);
-			return NULL;
-		}
-		skb_add_rx_frag(skb, 0, rx_buf->page,
-				rx_buf->page_offset + headlen, size,
-				xdp->frame_sz);
-	} else {
-		/* buffer is unused, restore biased page count in Rx buffer;
-		 * data was copied onto skb's linear part so there's no
-		 * need for adjusting page offset and we can reuse this buffer
-		 * as-is
-		 */
-		rx_buf->pagecnt_bias++;
-	}
-
-	if (unlikely(xdp_buff_has_frags(xdp))) {
-		struct skb_shared_info *skinfo = skb_shinfo(skb);
-
-		memcpy(&skinfo->frags[skinfo->nr_frags], &sinfo->frags[0],
-		       sizeof(skb_frag_t) * nr_frags);
-
-		xdp_update_skb_frags_info(skb, skinfo->nr_frags + nr_frags,
-					  sinfo->xdp_frags_size,
-					  nr_frags * xdp->frame_sz,
-					  xdp_buff_get_skb_flags(xdp));
-	}
-
-	return skb;
-}
-
-/**
- * ice_put_rx_buf - Clean up used buffer and either recycle or free
- * @rx_ring: Rx descriptor ring to transact packets on
- * @rx_buf: Rx buffer to pull data from
- *
- * This function will clean up the contents of the rx_buf. It will either
- * recycle the buffer or unmap it and free the associated resources.
- */
-static void
-ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf)
-{
-	if (!rx_buf)
-		return;
-
-	if (ice_can_reuse_rx_page(rx_buf)) {
-		/* hand second half of page back to the ring */
-		ice_reuse_rx_page(rx_ring, rx_buf);
-	} else {
-		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page_attrs(rx_ring->dev, rx_buf->dma,
-				     ice_rx_pg_size(rx_ring), DMA_FROM_DEVICE,
-				     ICE_RX_DMA_ATTR);
-		__page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias);
-	}
-
-	/* clear contents of buffer_info */
-	rx_buf->page = NULL;
-}
-
-/**
- * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all buffers in frame
- * @rx_ring: Rx ring with all the auxiliary data
- * @xdp: XDP buffer carrying linear + frags part
- * @ntc: the next to clean element (not included in this frame!)
- * @verdict: return code from XDP program execution
- *
- * Called after XDP program is completed, or on error with verdict set to
- * ICE_XDP_CONSUMED.
- *
- * Walk through buffers from first_desc to the end of the frame, releasing
- * buffers and satisfying internal page recycle mechanism. The action depends
- * on verdict from XDP program.
- */
-static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
-			    u32 ntc, u32 verdict)
-{
-	u32 idx = rx_ring->first_desc;
-	u32 cnt = rx_ring->count;
-	struct ice_rx_buf *buf;
-	u32 xdp_frags = 0;
-	int i = 0;
-
-	if (unlikely(xdp_buff_has_frags(xdp)))
-		xdp_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags;
-
-	while (idx != ntc) {
-		buf = &rx_ring->rx_buf[idx];
-		if (++idx == cnt)
-			idx = 0;
-
-		/* An XDP program could release fragments from the end of the
-		 * buffer. For these, we need to keep the pagecnt_bias as-is.
-		 * To do this, only adjust pagecnt_bias for fragments up to
-		 * the total remaining after the XDP program has run.
-		 */
-		if (verdict != ICE_XDP_CONSUMED)
-			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
-		else if (i++ <= xdp_frags)
-			buf->pagecnt_bias++;
-
-		ice_put_rx_buf(rx_ring, buf);
-	}
-
-	xdp->data = NULL;
-	rx_ring->first_desc = ntc;
-}
-
-/**
  * ice_clean_ctrl_rx_irq - Clean descriptors from flow director Rx ring
  * @rx_ring: Rx descriptor ring for ctrl_vsi to transact packets on
  *
@@ -1361,9 +925,8 @@ void ice_clean_ctrl_rx_irq(struct ice_rx_ring *rx_ring)
 		total_rx_pkts++;
 	}
 
-	rx_ring->first_desc = ntc;
 	rx_ring->next_to_clean = ntc;
-	ice_init_ctrl_rx_descs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring));
+	ice_init_ctrl_rx_descs(rx_ring, ICE_DESC_UNUSED(rx_ring));
 }
 
 /**
@@ -1381,16 +944,17 @@ void ice_clean_ctrl_rx_irq(struct ice_rx_ring *rx_ring)
 static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
-	unsigned int offset = rx_ring->rx_offset;
-	struct xdp_buff *xdp = &rx_ring->xdp;
 	struct ice_tx_ring *xdp_ring = NULL;
 	struct bpf_prog *xdp_prog = NULL;
 	u32 ntc = rx_ring->next_to_clean;
+	LIBETH_XDP_ONSTACK_BUFF(xdp);
 	u32 cached_ntu, xdp_verdict;
 	u32 cnt = rx_ring->count;
 	u32 xdp_xmit = 0;
 	bool failure;
 
+	libeth_xdp_init_buff(xdp, &rx_ring->xdp, &rx_ring->xdp_rxq);
+
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	if (xdp_prog) {
 		xdp_ring = rx_ring->xdp_ring;
@@ -1400,19 +964,21 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 	/* start the loop to process Rx packets bounded by 'budget' */
 	while (likely(total_rx_pkts < (unsigned int)budget)) {
 		union ice_32b_rx_flex_desc *rx_desc;
-		struct ice_rx_buf *rx_buf;
+		struct libeth_fqe *rx_buf;
 		struct sk_buff *skb;
 		unsigned int size;
 		u16 stat_err_bits;
 		u16 vlan_tci;
+		bool rxe;
 
 		/* get the Rx desc from Rx ring based on 'next_to_clean' */
 		rx_desc = ICE_RX_DESC(rx_ring, ntc);
 
-		/* status_error_len will always be zero for unused descriptors
-		 * because it's cleared in cleanup, and overlaps with hdr_addr
-		 * which is always zero because packet split isn't used, if the
-		 * hardware wrote DD then it will be non-zero
+		/*
+		 * The DD bit will always be zero for unused descriptors
+		 * because it's cleared in cleanup or when setting the DMA
+		 * address of the header buffer, which never uses the DD bit.
+		 * If the hardware wrote the descriptor, it will be non-zero.
 		 */
 		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S);
 		if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits))
@@ -1426,71 +992,65 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 
 		ice_trace(clean_rx_irq, rx_ring, rx_desc);
 
+		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_HBO_S) |
+				BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S);
+		rxe = ice_test_staterr(rx_desc->wb.status_error0,
+				       stat_err_bits);
+
+		if (!rx_ring->hdr_pp)
+			goto payload;
+
+		size = le16_get_bits(rx_desc->wb.hdr_len_sph_flex_flags1,
+				     ICE_RX_FLEX_DESC_HDR_LEN_M);
+		if (unlikely(rxe))
+			size = 0;
+
+		rx_buf = &rx_ring->hdr_fqes[ntc];
+		libeth_xdp_process_buff(xdp, rx_buf, size);
+		rx_buf->netmem = 0;
+
+payload:
 		size = le16_to_cpu(rx_desc->wb.pkt_len) &
 			ICE_RX_FLX_DESC_PKT_LEN_M;
+		if (unlikely(rxe))
+			size = 0;
 
 		/* retrieve a buffer from the ring */
-		rx_buf = ice_get_rx_buf(rx_ring, size, ntc);
+		rx_buf = &rx_ring->rx_fqes[ntc];
+		libeth_xdp_process_buff(xdp, rx_buf, size);
 
-		/* Increment ntc before calls to ice_put_rx_mbuf() */
 		if (++ntc == cnt)
 			ntc = 0;
 
-		if (!xdp->data) {
-			void *hard_start;
-
-			hard_start = page_address(rx_buf->page) + rx_buf->page_offset -
-				     offset;
-			xdp_prepare_buff(xdp, hard_start, offset, size, !!offset);
-			xdp_buff_clear_frags_flag(xdp);
-		} else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) {
-			ice_put_rx_mbuf(rx_ring, xdp, ntc, ICE_XDP_CONSUMED);
-			break;
-		}
-
 		/* skip if it is NOP desc */
-		if (ice_is_non_eop(rx_ring, rx_desc))
+		if (ice_is_non_eop(rx_ring, rx_desc) || unlikely(!xdp->data))
 			continue;
 
-		ice_get_pgcnts(rx_ring, ntc);
 		xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc);
 		if (xdp_verdict == ICE_XDP_PASS)
 			goto construct_skb;
-		total_rx_bytes += xdp_get_buff_len(xdp);
-		total_rx_pkts++;
 
-		ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict);
-		xdp_xmit |= xdp_verdict & (ICE_XDP_TX | ICE_XDP_REDIR);
+		if (xdp_verdict & (ICE_XDP_TX | ICE_XDP_REDIR))
+			xdp_xmit |= xdp_verdict;
+		total_rx_bytes += xdp_get_buff_len(&xdp->base);
+		total_rx_pkts++;
 
+		xdp->data = NULL;
 		continue;
+
 construct_skb:
-		if (likely(ice_ring_uses_build_skb(rx_ring)))
-			skb = ice_build_skb(rx_ring, xdp);
-		else
-			skb = ice_construct_skb(rx_ring, xdp);
+		skb = xdp_build_skb_from_buff(&xdp->base);
+		xdp->data = NULL;
+
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
+			libeth_xdp_return_buff_slow(xdp);
 			rx_ring->ring_stats->rx_stats.alloc_buf_failed++;
-			xdp_verdict = ICE_XDP_CONSUMED;
-		}
-		ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict);
-
-		if (!skb)
-			break;
-
-		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S);
-		if (unlikely(ice_test_staterr(rx_desc->wb.status_error0,
-					      stat_err_bits))) {
-			dev_kfree_skb_any(skb);
 			continue;
 		}
 
 		vlan_tci = ice_get_vlan_tci(rx_desc);
 
-		/* pad the skb if needed, to make a valid ethernet frame */
-		if (eth_skb_pad(skb))
-			continue;
-
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
 
@@ -1507,11 +1067,13 @@ construct_skb:
 
 	rx_ring->next_to_clean = ntc;
 	/* return up to cleaned_count buffers to hardware */
-	failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring));
+	failure = ice_alloc_rx_bufs(rx_ring, ICE_DESC_UNUSED(rx_ring));
 
 	if (xdp_xmit)
 		ice_finalize_xdp_rx(xdp_ring, xdp_xmit, cached_ntu);
 
+	libeth_xdp_save_buff(&rx_ring->xdp, xdp);
+
 	if (rx_ring->ring_stats)
 		ice_update_rx_ring_stats(rx_ring, total_rx_pkts,
 					 total_rx_bytes);