1 files changed, 487 insertions, 625 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 086f0b3ab68d..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>
@@ -20,7 +22,6 @@
 
 #define ICE_RX_HDR_SIZE		256
 
-#define FDIR_DESC_RXDID 0x40
 #define ICE_FDIR_CLEAN_DELAY 10
 
 /**
@@ -85,7 +86,7 @@ ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc,
 	td_cmd = ICE_TXD_LAST_DESC_CMD | ICE_TX_DESC_CMD_DUMMY |
 		 ICE_TX_DESC_CMD_RE;
 
-	tx_buf->tx_flags = ICE_TX_FLAGS_DUMMY_PKT;
+	tx_buf->type = ICE_TX_BUF_DUMMY;
 	tx_buf->raw_buf = raw_packet;
 
 	tx_desc->cmd_type_offset_bsz =
@@ -112,27 +113,29 @@ 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 (tx_buf->skb) {
-		if (tx_buf->tx_flags & ICE_TX_FLAGS_DUMMY_PKT)
-			devm_kfree(ring->dev, tx_buf->raw_buf);
-		else if (ice_ring_is_xdp(ring))
-			page_frag_free(tx_buf->raw_buf);
-		else
-			dev_kfree_skb_any(tx_buf->skb);
-		if (dma_unmap_len(tx_buf, len))
-			dma_unmap_single(ring->dev,
-					 dma_unmap_addr(tx_buf, dma),
-					 dma_unmap_len(tx_buf, len),
-					 DMA_TO_DEVICE);
-	} else 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),
 			       DMA_TO_DEVICE);
+
+	switch (tx_buf->type) {
+	case ICE_TX_BUF_DUMMY:
+		devm_kfree(ring->dev, tx_buf->raw_buf);
+		break;
+	case ICE_TX_BUF_SKB:
+		dev_kfree_skb_any(tx_buf->skb);
+		break;
+	case ICE_TX_BUF_XDP_TX:
+		libeth_xdp_return_va(tx_buf->raw_buf, false);
+		break;
+	case ICE_TX_BUF_XDP_XMIT:
+		xdp_return_frame(tx_buf->xdpf);
+		break;
 	}
 
 	tx_buf->next_to_watch = NULL;
-	tx_buf->skb = NULL;
+	tx_buf->type = ICE_TX_BUF_EMPTY;
 	dma_unmap_len_set(tx_buf, len, 0);
 	/* tx_buf must be completely set up in the transmit path */
 }
@@ -143,6 +146,56 @@ static struct netdev_queue *txring_txq(const struct ice_tx_ring *ring)
 }
 
 /**
+ * ice_clean_tstamp_ring - clean time stamp ring
+ * @tx_ring: Tx ring to clean the Time Stamp ring for
+ */
+static void ice_clean_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	struct ice_tstamp_ring *tstamp_ring = tx_ring->tstamp_ring;
+	u32 size;
+
+	if (!tstamp_ring->desc)
+		return;
+
+	size = ALIGN(tstamp_ring->count * sizeof(struct ice_ts_desc),
+		     PAGE_SIZE);
+	memset(tstamp_ring->desc, 0, size);
+	tstamp_ring->next_to_use = 0;
+}
+
+/**
+ * ice_free_tstamp_ring - free time stamp resources per queue
+ * @tx_ring: Tx ring to free the Time Stamp ring for
+ */
+void ice_free_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	struct ice_tstamp_ring *tstamp_ring = tx_ring->tstamp_ring;
+	u32 size;
+
+	if (!tstamp_ring->desc)
+		return;
+
+	ice_clean_tstamp_ring(tx_ring);
+	size = ALIGN(tstamp_ring->count * sizeof(struct ice_ts_desc),
+		     PAGE_SIZE);
+	dmam_free_coherent(tx_ring->dev, size, tstamp_ring->desc,
+			   tstamp_ring->dma);
+	tstamp_ring->desc = NULL;
+}
+
+/**
+ * ice_free_tx_tstamp_ring - free time stamp resources per Tx ring
+ * @tx_ring: Tx ring to free the Time Stamp ring for
+ */
+void ice_free_tx_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	ice_free_tstamp_ring(tx_ring);
+	kfree_rcu(tx_ring->tstamp_ring, rcu);
+	tx_ring->tstamp_ring = NULL;
+	tx_ring->flags &= ~ICE_TX_FLAGS_TXTIME;
+}
+
+/**
  * ice_clean_tx_ring - Free any empty Tx buffers
  * @tx_ring: ring to be cleaned
  */
@@ -174,14 +227,15 @@ tx_skip_free:
 
 	tx_ring->next_to_use = 0;
 	tx_ring->next_to_clean = 0;
-	tx_ring->next_dd = ICE_RING_QUARTER(tx_ring) - 1;
-	tx_ring->next_rs = ICE_RING_QUARTER(tx_ring) - 1;
 
 	if (!tx_ring->netdev)
 		return;
 
 	/* cleanup Tx queue statistics */
 	netdev_tx_reset_queue(txring_txq(tx_ring));
+
+	if (ice_is_txtime_cfg(tx_ring))
+		ice_free_tx_tstamp_ring(tx_ring);
 }
 
 /**
@@ -267,7 +321,7 @@ static bool ice_clean_tx_irq(struct ice_tx_ring *tx_ring, int napi_budget)
 				 DMA_TO_DEVICE);
 
 		/* clear tx_buf data */
-		tx_buf->skb = NULL;
+		tx_buf->type = ICE_TX_BUF_EMPTY;
 		dma_unmap_len_set(tx_buf, len, 0);
 
 		/* unmap remaining buffers */
@@ -333,6 +387,84 @@ static bool ice_clean_tx_irq(struct ice_tx_ring *tx_ring, int napi_budget)
 }
 
 /**
+ * ice_alloc_tstamp_ring - allocate the Time Stamp ring
+ * @tx_ring: Tx ring to allocate the Time Stamp ring for
+ *
+ * Return: 0 on success, negative on error
+ */
+static int ice_alloc_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	struct ice_tstamp_ring *tstamp_ring;
+
+	/* allocate with kzalloc(), free with kfree_rcu() */
+	tstamp_ring = kzalloc(sizeof(*tstamp_ring), GFP_KERNEL);
+	if (!tstamp_ring)
+		return -ENOMEM;
+
+	tstamp_ring->tx_ring = tx_ring;
+	tx_ring->tstamp_ring = tstamp_ring;
+	tstamp_ring->desc = NULL;
+	tstamp_ring->count = ice_calc_ts_ring_count(tx_ring);
+	tx_ring->flags |= ICE_TX_FLAGS_TXTIME;
+	return 0;
+}
+
+/**
+ * ice_setup_tstamp_ring - allocate the Time Stamp ring
+ * @tx_ring: Tx ring to set up the Time Stamp ring for
+ *
+ * Return: 0 on success, negative on error
+ */
+static int ice_setup_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	struct ice_tstamp_ring *tstamp_ring = tx_ring->tstamp_ring;
+	struct device *dev = tx_ring->dev;
+	u32 size;
+
+	/* round up to nearest page */
+	size = ALIGN(tstamp_ring->count * sizeof(struct ice_ts_desc),
+		     PAGE_SIZE);
+	tstamp_ring->desc = dmam_alloc_coherent(dev, size, &tstamp_ring->dma,
+						GFP_KERNEL);
+	if (!tstamp_ring->desc) {
+		dev_err(dev, "Unable to allocate memory for Time stamp Ring, size=%d\n",
+			size);
+		return -ENOMEM;
+	}
+
+	tstamp_ring->next_to_use = 0;
+	return 0;
+}
+
+/**
+ * ice_alloc_setup_tstamp_ring - Allocate and setup the Time Stamp ring
+ * @tx_ring: Tx ring to allocate and setup the Time Stamp ring for
+ *
+ * Return: 0 on success, negative on error
+ */
+int ice_alloc_setup_tstamp_ring(struct ice_tx_ring *tx_ring)
+{
+	struct device *dev = tx_ring->dev;
+	int err;
+
+	err = ice_alloc_tstamp_ring(tx_ring);
+	if (err) {
+		dev_err(dev, "Unable to allocate Time stamp ring for Tx ring %d\n",
+			tx_ring->q_index);
+		return err;
+	}
+
+	err = ice_setup_tstamp_ring(tx_ring);
+	if (err) {
+		dev_err(dev, "Unable to setup Time stamp ring for Tx ring %d\n",
+			tx_ring->q_index);
+		ice_free_tx_tstamp_ring(tx_ring);
+		return err;
+	}
+	return 0;
+}
+
+/**
  * ice_setup_tx_ring - Allocate the Tx descriptors
  * @tx_ring: the Tx ring to set up
  *
@@ -376,60 +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 device *dev = rx_ring->dev;
 	u32 size;
-	u16 i;
-
-	/* ring already cleared, nothing to do */
-	if (!rx_ring->rx_buf)
-		return;
-
-	if (rx_ring->skb) {
-		dev_kfree_skb(rx_ring->skb);
-		rx_ring->skb = NULL;
-	}
 
 	if (rx_ring->xsk_pool) {
 		ice_xsk_clean_rx_ring(rx_ring);
 		goto rx_skip_free;
 	}
 
+	/* 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);
@@ -448,26 +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);
-	rx_ring->xdp_prog = NULL;
+	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;
 	}
 }
@@ -480,19 +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);
@@ -501,7 +624,7 @@ 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;
@@ -510,33 +633,7 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
 	if (ice_is_xdp_ena_vsi(rx_ring->vsi))
 		WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog);
 
-	if (rx_ring->vsi->type == ICE_VSI_PF &&
-	    !xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
-		if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
-				     rx_ring->q_index, rx_ring->q_vector->napi.napi_id))
-			goto err;
 	return 0;
-
-err:
-	kfree(rx_ring->rx_buf);
-	rx_ring->rx_buf = NULL;
-	return -ENOMEM;
-}
-
-static unsigned int
-ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, unsigned int __maybe_unused size)
-{
-	unsigned int truesize;
-
-#if (PAGE_SIZE < 8192)
-	truesize = ice_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */
-#else
-	truesize = rx_ring->rx_offset ?
-		SKB_DATA_ALIGN(rx_ring->rx_offset + size) +
-		SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
-		SKB_DATA_ALIGN(size);
-#endif
-	return truesize;
 }
 
 /**
@@ -545,34 +642,41 @@ ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, unsigned int __maybe_unused s
  * @xdp: xdp_buff used as input to the XDP program
  * @xdp_prog: XDP program to run
  * @xdp_ring: ring to be used for XDP_TX action
+ * @eop_desc: Last descriptor in packet to read metadata from
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
-static int
-ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
-	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring)
+static u32
+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)
 {
-	int err;
+	unsigned int ret = ICE_XDP_PASS;
 	u32 act;
 
-	act = bpf_prog_run_xdp(xdp_prog, xdp);
+	if (!xdp_prog)
+		goto exit;
+
+	xdp->desc = eop_desc;
+
+	act = bpf_prog_run_xdp(xdp_prog, &xdp->base);
 	switch (act) {
 	case XDP_PASS:
-		return ICE_XDP_PASS;
+		break;
 	case XDP_TX:
 		if (static_branch_unlikely(&ice_xdp_locking_key))
 			spin_lock(&xdp_ring->tx_lock);
-		err = ice_xmit_xdp_ring(xdp->data, xdp->data_end - xdp->data, xdp_ring);
+		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 (err == ICE_XDP_CONSUMED)
+		if (ret == ICE_XDP_CONSUMED)
 			goto out_failure;
-		return err;
+		break;
 	case XDP_REDIRECT:
-		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		if (err)
+		if (xdp_do_redirect(rx_ring->netdev, &xdp->base, xdp_prog))
 			goto out_failure;
-		return ICE_XDP_REDIR;
+		ret = ICE_XDP_REDIR;
+		break;
 	default:
 		bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
 		fallthrough;
@@ -581,8 +685,31 @@ out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough;
 	case XDP_DROP:
-		return ICE_XDP_CONSUMED;
+		libeth_xdp_return_buff(xdp);
+		ret = ICE_XDP_CONSUMED;
 	}
+
+exit:
+	return ret;
+}
+
+/**
+ * ice_xmit_xdp_ring - submit frame to XDP ring for transmission
+ * @xdpf: XDP frame that will be converted to XDP buff
+ * @xdp_ring: XDP ring for transmission
+ */
+static int ice_xmit_xdp_ring(const struct xdp_frame *xdpf,
+			     struct ice_tx_ring *xdp_ring)
+{
+	struct xdp_buff xdp;
+
+	xdp.data_hard_start = (void *)xdpf;
+	xdp.data = xdpf->data;
+	xdp.data_end = xdp.data + xdpf->len;
+	xdp.frame_sz = xdpf->frame_sz;
+	xdp.flags = xdpf->flags;
+
+	return __ice_xmit_xdp_ring(&xdp, xdp_ring, true);
 }
 
 /**
@@ -605,6 +732,7 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	unsigned int queue_index = smp_processor_id();
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_tx_ring *xdp_ring;
+	struct ice_tx_buf *tx_buf;
 	int nxmit = 0, i;
 
 	if (test_bit(ICE_VSI_DOWN, vsi->state))
@@ -627,16 +755,18 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		xdp_ring = vsi->xdp_rings[queue_index];
 	}
 
+	tx_buf = &xdp_ring->tx_buf[xdp_ring->next_to_use];
 	for (i = 0; i < n; i++) {
-		struct xdp_frame *xdpf = frames[i];
+		const struct xdp_frame *xdpf = frames[i];
 		int err;
 
-		err = ice_xmit_xdp_ring(xdpf->data, xdpf->len, xdp_ring);
+		err = ice_xmit_xdp_ring(xdpf, xdp_ring);
 		if (err != ICE_XDP_TX)
 			break;
 		nxmit++;
 	}
 
+	tx_buf->rs_idx = ice_set_rs_bit(xdp_ring);
 	if (unlikely(flags & XDP_XMIT_FLUSH))
 		ice_xdp_ring_update_tail(xdp_ring);
 
@@ -647,50 +777,34 @@ 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.
+ * ice_init_ctrl_rx_descs - Initialize Rx descriptors for control vsi.
+ * @rx_ring: ring to init descriptors on
+ * @count: number of descriptors to initialize
  */
-static bool
-ice_alloc_mapped_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *bi)
+void ice_init_ctrl_rx_descs(struct ice_rx_ring *rx_ring, u32 count)
 {
-	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;
+	union ice_32b_rx_flex_desc *rx_desc;
+	u32 ntu = rx_ring->next_to_use;
 
-	/* 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;
-	}
+	if (!count)
+		return;
 
-	/* 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);
+	rx_desc = ICE_RX_DESC(rx_ring, ntu);
 
-	/* 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;
-	}
+	do {
+		rx_desc++;
+		ntu++;
+		if (unlikely(ntu == rx_ring->count)) {
+			rx_desc = ICE_RX_DESC(rx_ring, 0);
+			ntu = 0;
+		}
 
-	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;
+		rx_desc->wb.status_error0 = 0;
+		count--;
+	} while (count);
 
-	return true;
+	if (rx_ring->next_to_use != ntu)
+		ice_release_rx_desc(rx_ring, ntu);
 }
 
 /**
@@ -706,43 +820,62 @@ ice_alloc_mapped_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *bi)
  * buffers. Then bump tail at most one time. Grouping like this lets us avoid
  * multiple tail writes per call.
  */
-bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, u16 cleaned_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 && rx_ring->vsi->type != ICE_VSI_CTRL) ||
-	    !cleaned_count)
+	if (!rx_ring->netdev || !cleaned_count)
 		return false;
 
 	/* 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;
 		}
 
@@ -759,341 +892,41 @@ bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, u16 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
- * @rx_buf_pgcnt: rx_buf page refcount pre xdp_do_redirect() call
- *
- * 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, int rx_buf_pgcnt)
-{
-	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 (PAGE_SIZE < 8192)
-	/* if we are only owner of page we can reuse it */
-	if (unlikely((rx_buf_pgcnt - pagecnt_bias) > 1))
-		return false;
-#else
-#define ICE_LAST_OFFSET \
-	(SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_2048)
-	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_rx_frag - Add contents of Rx buffer to sk_buff as a frag
- * @rx_ring: Rx descriptor ring to transact packets on
- * @rx_buf: buffer containing page to add
- * @skb: sk_buff to place the data into
- * @size: packet length from rx_desc
- *
- * This function will add the data contained in rx_buf->page to the skb.
- * It will just attach the page as a frag to the skb.
- * The function will then update the page offset.
- */
-static void
-ice_add_rx_frag(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf,
-		struct sk_buff *skb, unsigned int size)
-{
-#if (PAGE_SIZE >= 8192)
-	unsigned int truesize = SKB_DATA_ALIGN(size + rx_ring->rx_offset);
-#else
-	unsigned int truesize = ice_rx_pg_size(rx_ring) / 2;
-#endif
-
-	if (!size)
-		return;
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buf->page,
-			rx_buf->page_offset, size, truesize);
-
-	/* page is being used so we must update the page offset */
-	ice_rx_buf_adjust_pg_offset(rx_buf, truesize);
-}
-
-/**
- * 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
- * @rx_buf_pgcnt: rx_buf page refcount
+ * ice_clean_ctrl_rx_irq - Clean descriptors from flow director Rx ring
+ * @rx_ring: Rx descriptor ring for ctrl_vsi to transact packets on
  *
- * This function will pull an Rx buffer from the ring and synchronize it
- * for use by the CPU.
+ * This function cleans Rx descriptors from the ctrl_vsi Rx ring used
+ * to set flow director rules on VFs.
  */
-static struct ice_rx_buf *
-ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
-	       int *rx_buf_pgcnt)
+void ice_clean_ctrl_rx_irq(struct ice_rx_ring *rx_ring)
 {
-	struct ice_rx_buf *rx_buf;
-
-	rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean];
-	*rx_buf_pgcnt =
-#if (PAGE_SIZE < 8192)
-		page_count(rx_buf->page);
-#else
-		0;
-#endif
-	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;
-}
+	u32 ntc = rx_ring->next_to_clean;
+	unsigned int total_rx_pkts = 0;
+	u32 cnt = rx_ring->count;
 
-/**
- * ice_build_skb - Build skb around an existing buffer
- * @rx_ring: Rx descriptor ring to transact packets on
- * @rx_buf: Rx buffer to pull data from
- * @xdp: xdp_buff pointing to the data
- *
- * This function builds an skb around an existing Rx buffer, taking care
- * to set up the skb correctly and avoid any memcpy overhead.
- */
-static struct sk_buff *
-ice_build_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf,
-	      struct xdp_buff *xdp)
-{
-	u8 metasize = xdp->data - xdp->data_meta;
-#if (PAGE_SIZE < 8192)
-	unsigned int truesize = ice_rx_pg_size(rx_ring) / 2;
-#else
-	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
-				SKB_DATA_ALIGN(xdp->data_end -
-					       xdp->data_hard_start);
-#endif
-	struct sk_buff *skb;
-
-	/* 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, truesize);
-	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);
+	while (likely(total_rx_pkts < ICE_DFLT_IRQ_WORK)) {
+		struct ice_vsi *ctrl_vsi = rx_ring->vsi;
+		union ice_32b_rx_flex_desc *rx_desc;
+		u16 stat_err_bits;
 
-	/* buffer is used by skb, update page_offset */
-	ice_rx_buf_adjust_pg_offset(rx_buf, truesize);
+		rx_desc = ICE_RX_DESC(rx_ring, ntc);
 
-	return skb;
-}
+		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S);
+		if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits))
+			break;
 
-/**
- * ice_construct_skb - Allocate skb and populate it
- * @rx_ring: Rx descriptor ring to transact packets on
- * @rx_buf: Rx buffer to pull data from
- * @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 ice_rx_buf *rx_buf,
-		  struct xdp_buff *xdp)
-{
-	unsigned int metasize = xdp->data - xdp->data_meta;
-	unsigned int size = xdp->data_end - xdp->data;
-	unsigned int headlen;
-	struct sk_buff *skb;
+		dma_rmb();
 
-	/* prefetch first cache line of first page */
-	net_prefetch(xdp->data_meta);
-
-	/* allocate a skb to store the frags */
-	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
-			       ICE_RX_HDR_SIZE + metasize,
-			       GFP_ATOMIC | __GFP_NOWARN);
-	if (unlikely(!skb))
-		return NULL;
-
-	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 + metasize), xdp->data_meta,
-	       ALIGN(headlen + metasize, sizeof(long)));
-
-	if (metasize) {
-		skb_metadata_set(skb, metasize);
-		__skb_pull(skb, metasize);
-	}
+		if (ctrl_vsi->vf)
+			ice_vc_fdir_irq_handler(ctrl_vsi, rx_desc);
 
-	/* if we exhaust the linear part then add what is left as a frag */
-	size -= headlen;
-	if (size) {
-#if (PAGE_SIZE >= 8192)
-		unsigned int truesize = SKB_DATA_ALIGN(size);
-#else
-		unsigned int truesize = ice_rx_pg_size(rx_ring) / 2;
-#endif
-		skb_add_rx_frag(skb, 0, rx_buf->page,
-				rx_buf->page_offset + headlen, size, truesize);
-		/* buffer is used by skb, update page_offset */
-		ice_rx_buf_adjust_pg_offset(rx_buf, truesize);
-	} else {
-		/* buffer is unused, reset bias back to rx_buf; 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 (++ntc == cnt)
+			ntc = 0;
+		total_rx_pkts++;
 	}
 
-	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
- * @rx_buf_pgcnt: Rx buffer page count pre xdp_do_redirect()
- *
- * This function will update next_to_clean and then 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,
-	       int rx_buf_pgcnt)
-{
-	u16 ntc = rx_ring->next_to_clean + 1;
-
-	/* fetch, update, and store next to clean */
-	ntc = (ntc < rx_ring->count) ? ntc : 0;
 	rx_ring->next_to_clean = ntc;
-
-	if (!rx_buf)
-		return;
-
-	if (ice_can_reuse_rx_page(rx_buf, rx_buf_pgcnt)) {
-		/* 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_is_non_eop - process handling of non-EOP buffers
- * @rx_ring: Rx ring being processed
- * @rx_desc: Rx descriptor for current buffer
- *
- * If the buffer is an EOP buffer, this function exits returning false,
- * otherwise return true indicating that this is in fact a non-EOP buffer.
- */
-static bool
-ice_is_non_eop(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc)
-{
-	/* if we are the last buffer then there is nothing else to do */
-#define ICE_RXD_EOF BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S)
-	if (likely(ice_test_staterr(rx_desc->wb.status_error0, ICE_RXD_EOF)))
-		return false;
-
-	rx_ring->ring_stats->rx_stats.non_eop_descs++;
-
-	return true;
+	ice_init_ctrl_rx_descs(rx_ring, ICE_DESC_UNUSED(rx_ring));
 }
 
 /**
@@ -1108,46 +941,44 @@ ice_is_non_eop(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc)
  *
  * Returns amount of work completed
  */
-int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
+static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 {
-	unsigned int total_rx_bytes = 0, total_rx_pkts = 0, frame_sz = 0;
-	u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
-	unsigned int offset = rx_ring->rx_offset;
+	unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
 	struct ice_tx_ring *xdp_ring = NULL;
-	unsigned int xdp_res, xdp_xmit = 0;
-	struct sk_buff *skb = rx_ring->skb;
 	struct bpf_prog *xdp_prog = NULL;
-	struct xdp_buff xdp;
+	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;
 
-	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
-#if (PAGE_SIZE < 8192)
-	frame_sz = ice_rx_frame_truesize(rx_ring, 0);
-#endif
-	xdp_init_buff(&xdp, frame_sz, &rx_ring->xdp_rxq);
+	libeth_xdp_init_buff(xdp, &rx_ring->xdp, &rx_ring->xdp_rxq);
 
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
-	if (xdp_prog)
+	if (xdp_prog) {
 		xdp_ring = rx_ring->xdp_ring;
+		cached_ntu = xdp_ring->next_to_use;
+	}
 
 	/* 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;
-		unsigned char *hard_start;
+		struct libeth_fqe *rx_buf;
+		struct sk_buff *skb;
 		unsigned int size;
 		u16 stat_err_bits;
-		int rx_buf_pgcnt;
-		u16 vlan_tag = 0;
-		u16 rx_ptype;
+		u16 vlan_tci;
+		bool rxe;
 
 		/* get the Rx desc from Rx ring based on 'next_to_clean' */
-		rx_desc = ICE_RX_DESC(rx_ring, rx_ring->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))
@@ -1160,120 +991,88 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		dma_rmb();
 
 		ice_trace(clean_rx_irq, rx_ring, rx_desc);
-		if (rx_desc->wb.rxdid == FDIR_DESC_RXDID || !rx_ring->netdev) {
-			struct ice_vsi *ctrl_vsi = rx_ring->vsi;
-
-			if (rx_desc->wb.rxdid == FDIR_DESC_RXDID &&
-			    ctrl_vsi->vf)
-				ice_vc_fdir_irq_handler(ctrl_vsi, rx_desc);
-			ice_put_rx_buf(rx_ring, NULL, 0);
-			cleaned_count++;
-			continue;
-		}
 
+		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, &rx_buf_pgcnt);
+		rx_buf = &rx_ring->rx_fqes[ntc];
+		libeth_xdp_process_buff(xdp, rx_buf, size);
 
-		if (!size) {
-			xdp.data = NULL;
-			xdp.data_end = NULL;
-			xdp.data_hard_start = NULL;
-			xdp.data_meta = NULL;
-			goto construct_skb;
-		}
+		if (++ntc == cnt)
+			ntc = 0;
 
-		hard_start = page_address(rx_buf->page) + rx_buf->page_offset -
-			     offset;
-		xdp_prepare_buff(&xdp, hard_start, offset, size, true);
-#if (PAGE_SIZE > 4096)
-		/* At larger PAGE_SIZE, frame_sz depend on len size */
-		xdp.frame_sz = ice_rx_frame_truesize(rx_ring, size);
-#endif
+		/* skip if it is NOP desc */
+		if (ice_is_non_eop(rx_ring, rx_desc) || unlikely(!xdp->data))
+			continue;
 
-		if (!xdp_prog)
+		xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc);
+		if (xdp_verdict == ICE_XDP_PASS)
 			goto construct_skb;
 
-		xdp_res = ice_run_xdp(rx_ring, &xdp, xdp_prog, xdp_ring);
-		if (!xdp_res)
-			goto construct_skb;
-		if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) {
-			xdp_xmit |= xdp_res;
-			ice_rx_buf_adjust_pg_offset(rx_buf, xdp.frame_sz);
-		} else {
-			rx_buf->pagecnt_bias++;
-		}
-		total_rx_bytes += size;
+		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++;
 
-		cleaned_count++;
-		ice_put_rx_buf(rx_ring, rx_buf, rx_buf_pgcnt);
+		xdp->data = NULL;
 		continue;
+
 construct_skb:
-		if (skb) {
-			ice_add_rx_frag(rx_ring, rx_buf, skb, size);
-		} else if (likely(xdp.data)) {
-			if (ice_ring_uses_build_skb(rx_ring))
-				skb = ice_build_skb(rx_ring, rx_buf, &xdp);
-			else
-				skb = ice_construct_skb(rx_ring, rx_buf, &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++;
-			if (rx_buf)
-				rx_buf->pagecnt_bias++;
-			break;
-		}
-
-		ice_put_rx_buf(rx_ring, rx_buf, rx_buf_pgcnt);
-		cleaned_count++;
-
-		/* skip if it is NOP desc */
-		if (ice_is_non_eop(rx_ring, rx_desc))
-			continue;
-
-		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_tag = ice_get_vlan_tag_from_rx_desc(rx_desc);
-
-		/* pad the skb if needed, to make a valid ethernet frame */
-		if (eth_skb_pad(skb)) {
-			skb = NULL;
-			continue;
-		}
+		vlan_tci = ice_get_vlan_tci(rx_desc);
 
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
 
 		/* populate checksum, VLAN, and protocol */
-		rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
-			ICE_RX_FLEX_DESC_PTYPE_M;
-
-		ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
+		ice_process_skb_fields(rx_ring, rx_desc, skb);
 
 		ice_trace(clean_rx_irq_indicate, rx_ring, rx_desc, skb);
 		/* send completed skb up the stack */
-		ice_receive_skb(rx_ring, skb, vlan_tag);
-		skb = NULL;
+		ice_receive_skb(rx_ring, skb, vlan_tci);
 
 		/* update budget accounting */
 		total_rx_pkts++;
 	}
 
+	rx_ring->next_to_clean = ntc;
 	/* return up to cleaned_count buffers to hardware */
-	failure = ice_alloc_rx_bufs(rx_ring, cleaned_count);
+	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);
 
-	if (xdp_prog)
-		ice_finalize_xdp_rx(xdp_ring, xdp_xmit);
-	rx_ring->skb = skb;
+	libeth_xdp_save_buff(&rx_ring->xdp, xdp);
 
 	if (rx_ring->ring_stats)
 		ice_update_rx_ring_stats(rx_ring, total_rx_pkts,
@@ -1346,14 +1145,14 @@ static void ice_net_dim(struct ice_q_vector *q_vector)
 		struct dim_sample dim_sample;
 
 		__ice_update_sample(q_vector, tx, &dim_sample, true);
-		net_dim(&tx->dim, dim_sample);
+		net_dim(&tx->dim, &dim_sample);
 	}
 
 	if (ITR_IS_DYNAMIC(rx)) {
 		struct dim_sample dim_sample;
 
 		__ice_update_sample(q_vector, rx, &dim_sample, false);
-		net_dim(&rx->dim, dim_sample);
+		net_dim(&rx->dim, &dim_sample);
 	}
 }
 
@@ -1446,9 +1245,9 @@ static void ice_set_wb_on_itr(struct ice_q_vector *q_vector)
 	 * be static in non-adaptive mode (user configured)
 	 */
 	wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx),
-	     ((ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S) &
-	      GLINT_DYN_CTL_ITR_INDX_M) | GLINT_DYN_CTL_INTENA_MSK_M |
-	     GLINT_DYN_CTL_WB_ON_ITR_M);
+	     FIELD_PREP(GLINT_DYN_CTL_ITR_INDX_M, ICE_ITR_NONE) |
+	     FIELD_PREP(GLINT_DYN_CTL_INTENA_MSK_M, 1) |
+	     FIELD_PREP(GLINT_DYN_CTL_WB_ON_ITR_M, 1));
 
 	q_vector->wb_on_itr = true;
 }
@@ -1476,10 +1275,11 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
 	ice_for_each_tx_ring(tx_ring, q_vector->tx) {
+		struct xsk_buff_pool *xsk_pool = READ_ONCE(tx_ring->xsk_pool);
 		bool wd;
 
-		if (tx_ring->xsk_pool)
-			wd = ice_xmit_zc(tx_ring);
+		if (xsk_pool)
+			wd = ice_xmit_zc(tx_ring, xsk_pool);
 		else if (ice_ring_is_xdp(tx_ring))
 			wd = true;
 		else
@@ -1505,6 +1305,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 		budget_per_ring = budget;
 
 	ice_for_each_rx_ring(rx_ring, q_vector->rx) {
+		struct xsk_buff_pool *xsk_pool = READ_ONCE(rx_ring->xsk_pool);
 		int cleaned;
 
 		/* A dedicated path for zero-copy allows making a single
@@ -1512,7 +1313,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 		 * ice_clean_rx_irq function and makes the codebase cleaner.
 		 */
 		cleaned = rx_ring->xsk_pool ?
-			  ice_clean_rx_irq_zc(rx_ring, budget_per_ring) :
+			  ice_clean_rx_irq_zc(rx_ring, xsk_pool, budget_per_ring) :
 			  ice_clean_rx_irq(rx_ring, budget_per_ring);
 		work_done += cleaned;
 		/* if we clean as many as budgeted, we must not be done */
@@ -1616,8 +1417,7 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first,
 
 	if (first->tx_flags & ICE_TX_FLAGS_HW_VLAN) {
 		td_cmd |= (u64)ICE_TX_DESC_CMD_IL2TAG1;
-		td_tag = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >>
-			  ICE_TX_FLAGS_VLAN_S;
+		td_tag = first->vid;
 	}
 
 	dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE);
@@ -1682,6 +1482,7 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first,
 				       DMA_TO_DEVICE);
 
 		tx_buf = &tx_ring->tx_buf[i];
+		tx_buf->type = ICE_TX_BUF_FRAG;
 	}
 
 	/* record SW timestamp if HW timestamp is not available */
@@ -1714,10 +1515,46 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first,
 	/* notify HW of packet */
 	kick = __netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount,
 				      netdev_xmit_more());
-	if (kick)
-		/* notify HW of packet */
-		writel(i, tx_ring->tail);
+	if (!kick)
+		return;
 
+	if (ice_is_txtime_cfg(tx_ring)) {
+		struct ice_tstamp_ring *tstamp_ring = tx_ring->tstamp_ring;
+		u32 tstamp_count = tstamp_ring->count;
+		u32 j = tstamp_ring->next_to_use;
+		struct ice_ts_desc *ts_desc;
+		struct timespec64 ts;
+		u32 tstamp;
+
+		ts = ktime_to_timespec64(first->skb->tstamp);
+		tstamp = ts.tv_nsec >> ICE_TXTIME_CTX_RESOLUTION_128NS;
+
+		ts_desc = ICE_TS_DESC(tstamp_ring, j);
+		ts_desc->tx_desc_idx_tstamp = ice_build_tstamp_desc(i, tstamp);
+
+		j++;
+		if (j == tstamp_count) {
+			u32 fetch = tstamp_count - tx_ring->count;
+
+			j = 0;
+
+			/* To prevent an MDD, when wrapping the tstamp ring
+			 * create additional TS descriptors equal to the number
+			 * of the fetch TS descriptors value. HW will merge the
+			 * TS descriptors with the same timestamp value into a
+			 * single descriptor.
+			 */
+			for (; j < fetch; j++) {
+				ts_desc = ICE_TS_DESC(tstamp_ring, j);
+				ts_desc->tx_desc_idx_tstamp =
+				       ice_build_tstamp_desc(i, tstamp);
+			}
+		}
+		tstamp_ring->next_to_use = j;
+		writel_relaxed(j, tstamp_ring->tail);
+	} else {
+		writel_relaxed(i, tx_ring->tail);
+	}
 	return;
 
 dma_error:
@@ -1745,6 +1582,7 @@ dma_error:
 static
 int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 {
+	const struct ice_tx_ring *tx_ring = off->tx_ring;
 	u32 l4_len = 0, l3_len = 0, l2_len = 0;
 	struct sk_buff *skb = first->skb;
 	union {
@@ -1894,6 +1732,30 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 	l3_len = l4.hdr - ip.hdr;
 	offset |= (l3_len / 4) << ICE_TX_DESC_LEN_IPLEN_S;
 
+	if ((tx_ring->netdev->features & NETIF_F_HW_CSUM) &&
+	    !(first->tx_flags & ICE_TX_FLAGS_TSO) &&
+	    !skb_csum_is_sctp(skb)) {
+		/* Set GCS */
+		u16 csum_start = (skb->csum_start - skb->mac_header) / 2;
+		u16 csum_offset = skb->csum_offset / 2;
+		u16 gcs_params;
+
+		gcs_params = FIELD_PREP(ICE_TX_GCS_DESC_START_M, csum_start) |
+			     FIELD_PREP(ICE_TX_GCS_DESC_OFFSET_M, csum_offset) |
+			     FIELD_PREP(ICE_TX_GCS_DESC_TYPE_M,
+					ICE_TX_GCS_DESC_CSUM_PSH);
+
+		/* Unlike legacy HW checksums, GCS requires a context
+		 * descriptor.
+		 */
+		off->cd_qw1 |= ICE_TX_DESC_DTYPE_CTX;
+		off->cd_gcs_params = gcs_params;
+		/* Fill out CSO info in data descriptors */
+		off->td_offset |= offset;
+		off->td_cmd |= cmd;
+		return 1;
+	}
+
 	/* Enable L4 checksum offloads */
 	switch (l4_proto) {
 	case IPPROTO_TCP:
@@ -1949,7 +1811,7 @@ ice_tx_prepare_vlan_flags(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first)
 	 * VLAN offloads exclusively so we only care about the VLAN ID here
 	 */
 	if (skb_vlan_tag_present(skb)) {
-		first->tx_flags |= skb_vlan_tag_get(skb) << ICE_TX_FLAGS_VLAN_S;
+		first->vid = skb_vlan_tag_get(skb);
 		if (tx_ring->flags & ICE_TX_FLAGS_RING_VLAN_L2TAG2)
 			first->tx_flags |= ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN;
 		else
@@ -1996,7 +1858,6 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 	if (err < 0)
 		return err;
 
-	/* cppcheck-suppress unreadVariable */
 	protocol = vlan_get_protocol(skb);
 
 	if (eth_p_mpls(protocol))
@@ -2033,8 +1894,6 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 		}
 
 		/* reset pointers to inner headers */
-
-		/* cppcheck-suppress unreadVariable */
 		ip.hdr = skb_inner_network_header(skb);
 		l4.hdr = skb_inner_transport_header(skb);
 
@@ -2261,9 +2120,6 @@ ice_tstamp(struct ice_tx_ring *tx_ring, struct sk_buff *skb,
 	if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
 		return;
 
-	if (!tx_ring->ptp_tx)
-		return;
-
 	/* Tx timestamps cannot be sampled when doing TSO */
 	if (first->tx_flags & ICE_TX_FLAGS_TSO)
 		return;
@@ -2300,6 +2156,9 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 
 	ice_trace(xmit_frame_ring, tx_ring, skb);
 
+	if (unlikely(ipv6_hopopt_jumbo_remove(skb)))
+		goto out_drop;
+
 	count = ice_xmit_desc_count(skb);
 	if (ice_chk_linearize(skb, count)) {
 		if (__skb_linearize(skb))
@@ -2328,6 +2187,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 	/* record the location of the first descriptor for this packet */
 	first = &tx_ring->tx_buf[tx_ring->next_to_use];
 	first->skb = skb;
+	first->type = ICE_TX_BUF_SKB;
 	first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN);
 	first->gso_segs = 1;
 	first->tx_flags = 0;
@@ -2338,8 +2198,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 		offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
 					(ICE_TX_CTX_DESC_IL2TAG2 <<
 					ICE_TXD_CTX_QW1_CMD_S));
-		offload.cd_l2tag2 = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >>
-			ICE_TX_FLAGS_VLAN_S;
+		offload.cd_l2tag2 = first->vid;
 	}
 
 	/* set up TSO offload */
@@ -2354,17 +2213,20 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 
 	/* allow CONTROL frames egress from main VSI if FW LLDP disabled */
 	eth = (struct ethhdr *)skb_mac_header(skb);
-	if (unlikely((skb->priority == TC_PRIO_CONTROL ||
-		      eth->h_proto == htons(ETH_P_LLDP)) &&
-		     vsi->type == ICE_VSI_PF &&
-		     vsi->port_info->qos_cfg.is_sw_lldp))
+
+	if ((ice_is_switchdev_running(vsi->back) ||
+	     ice_lag_is_switchdev_running(vsi->back)) &&
+	    vsi->type != ICE_VSI_SF)
+		ice_eswitch_set_target_vsi(skb, &offload);
+	else if (unlikely((skb->priority == TC_PRIO_CONTROL ||
+			   eth->h_proto == htons(ETH_P_LLDP)) &&
+			   vsi->type == ICE_VSI_PF &&
+			   vsi->port_info->qos_cfg.is_sw_lldp))
 		offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
 					ICE_TX_CTX_DESC_SWTCH_UPLINK <<
 					ICE_TXD_CTX_QW1_CMD_S);
 
 	ice_tstamp(tx_ring, skb, first, &offload);
-	if (ice_is_switchdev_running(vsi->back))
-		ice_eswitch_set_target_vsi(skb, &offload);
 
 	if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) {
 		struct ice_tx_ctx_desc *cdesc;
@@ -2378,7 +2240,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 		/* setup context descriptor */
 		cdesc->tunneling_params = cpu_to_le32(offload.cd_tunnel_params);
 		cdesc->l2tag2 = cpu_to_le16(offload.cd_l2tag2);
-		cdesc->rsvd = cpu_to_le16(0);
+		cdesc->gcs = cpu_to_le16(offload.cd_gcs_params);
 		cdesc->qw1 = cpu_to_le64(offload.cd_qw1);
 	}
 
@@ -2500,11 +2362,11 @@ void ice_clean_ctrl_tx_irq(struct ice_tx_ring *tx_ring)
 					 dma_unmap_addr(tx_buf, dma),
 					 dma_unmap_len(tx_buf, len),
 					 DMA_TO_DEVICE);
-		if (tx_buf->tx_flags & ICE_TX_FLAGS_DUMMY_PKT)
+		if (tx_buf->type == ICE_TX_BUF_DUMMY)
 			devm_kfree(tx_ring->dev, tx_buf->raw_buf);
 
 		/* clear next_to_watch to prevent false hangs */
-		tx_buf->raw_buf = NULL;
+		tx_buf->type = ICE_TX_BUF_EMPTY;
 		tx_buf->tx_flags = 0;
 		tx_buf->next_to_watch = NULL;
 		dma_unmap_len_set(tx_buf, len, 0);