Merge branch 'bnxt-xdp-multi-buffer'

Michael Chan says:

====================
bnxt: Support XDP multi buffer

This series adds XDP multi buffer support, allowing MTU to go beyond
the page size limit.

v4: Rebase with latest net-next
v3: Simplify page mode buffer size calculation
    Check to make sure XDP program supports multipage packets
v2: Fix uninitialized variable warnings in patch 1 and 10.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 416 insertions, 113 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 874fad0a5cf8..0489c1c2e7dd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -56,6 +56,7 @@
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 #include <net/page_pool.h>
+#include <linux/align.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -738,7 +739,6 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
 		page_pool_recycle_direct(rxr->page_pool, page);
 		return NULL;
 	}
-	*mapping += bp->rx_dma_offset;
 	return page;
 }
 
@@ -780,6 +780,7 @@ int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		if (!page)
 			return -ENOMEM;
 
+		mapping += bp->rx_dma_offset;
 		rx_buf->data = page;
 		rx_buf->data_ptr = page_address(page) + bp->rx_offset;
 	} else {
@@ -840,33 +841,41 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp,
 	u16 sw_prod = rxr->rx_sw_agg_prod;
 	unsigned int offset = 0;
 
-	if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) {
-		page = rxr->rx_page;
-		if (!page) {
+	if (BNXT_RX_PAGE_MODE(bp)) {
+		page = __bnxt_alloc_rx_page(bp, &mapping, rxr, gfp);
+
+		if (!page)
+			return -ENOMEM;
+
+	} else {
+		if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) {
+			page = rxr->rx_page;
+			if (!page) {
+				page = alloc_page(gfp);
+				if (!page)
+					return -ENOMEM;
+				rxr->rx_page = page;
+				rxr->rx_page_offset = 0;
+			}
+			offset = rxr->rx_page_offset;
+			rxr->rx_page_offset += BNXT_RX_PAGE_SIZE;
+			if (rxr->rx_page_offset == PAGE_SIZE)
+				rxr->rx_page = NULL;
+			else
+				get_page(page);
+		} else {
 			page = alloc_page(gfp);
 			if (!page)
 				return -ENOMEM;
-			rxr->rx_page = page;
-			rxr->rx_page_offset = 0;
 		}
-		offset = rxr->rx_page_offset;
-		rxr->rx_page_offset += BNXT_RX_PAGE_SIZE;
-		if (rxr->rx_page_offset == PAGE_SIZE)
-			rxr->rx_page = NULL;
-		else
-			get_page(page);
-	} else {
-		page = alloc_page(gfp);
-		if (!page)
-			return -ENOMEM;
-	}
 
-	mapping = dma_map_page_attrs(&pdev->dev, page, offset,
-				     BNXT_RX_PAGE_SIZE, DMA_FROM_DEVICE,
-				     DMA_ATTR_WEAK_ORDERING);
-	if (dma_mapping_error(&pdev->dev, mapping)) {
-		__free_page(page);
-		return -EIO;
+		mapping = dma_map_page_attrs(&pdev->dev, page, offset,
+					     BNXT_RX_PAGE_SIZE, DMA_FROM_DEVICE,
+					     DMA_ATTR_WEAK_ORDERING);
+		if (dma_mapping_error(&pdev->dev, mapping)) {
+			__free_page(page);
+			return -EIO;
+		}
 	}
 
 	if (unlikely(test_bit(sw_prod, rxr->rx_agg_bmap)))
@@ -962,6 +971,39 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
 	rxr->rx_sw_agg_prod = sw_prod;
 }
 
+static struct sk_buff *bnxt_rx_multi_page_skb(struct bnxt *bp,
+					      struct bnxt_rx_ring_info *rxr,
+					      u16 cons, void *data, u8 *data_ptr,
+					      dma_addr_t dma_addr,
+					      unsigned int offset_and_len)
+{
+	unsigned int len = offset_and_len & 0xffff;
+	struct page *page = data;
+	u16 prod = rxr->rx_prod;
+	struct sk_buff *skb;
+	int err;
+
+	err = bnxt_alloc_rx_data(bp, rxr, prod, GFP_ATOMIC);
+	if (unlikely(err)) {
+		bnxt_reuse_rx_data(rxr, cons, data);
+		return NULL;
+	}
+	dma_addr -= bp->rx_dma_offset;
+	dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir,
+			     DMA_ATTR_WEAK_ORDERING);
+	skb = build_skb(page_address(page), BNXT_PAGE_MODE_BUF_SIZE +
+					    bp->rx_dma_offset);
+	if (!skb) {
+		__free_page(page);
+		return NULL;
+	}
+	skb_mark_for_recycle(skb);
+	skb_reserve(skb, bp->rx_dma_offset);
+	__skb_put(skb, len);
+
+	return skb;
+}
+
 static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp,
 					struct bnxt_rx_ring_info *rxr,
 					u16 cons, void *data, u8 *data_ptr,
@@ -984,7 +1026,6 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp,
 	dma_addr -= bp->rx_dma_offset;
 	dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir,
 			     DMA_ATTR_WEAK_ORDERING);
-	page_pool_release_page(rxr->page_pool, page);
 
 	if (unlikely(!payload))
 		payload = eth_get_headlen(bp->dev, data_ptr, len);
@@ -995,6 +1036,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp,
 		return NULL;
 	}
 
+	skb_mark_for_recycle(skb);
 	off = (void *)data_ptr - page_address(page);
 	skb_add_rx_frag(skb, 0, page, off, len, PAGE_SIZE);
 	memcpy(skb->data - NET_IP_ALIGN, data_ptr - NET_IP_ALIGN,
@@ -1038,22 +1080,24 @@ static struct sk_buff *bnxt_rx_skb(struct bnxt *bp,
 	return skb;
 }
 
-static struct sk_buff *bnxt_rx_pages(struct bnxt *bp,
-				     struct bnxt_cp_ring_info *cpr,
-				     struct sk_buff *skb, u16 idx,
-				     u32 agg_bufs, bool tpa)
+static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
+			       struct bnxt_cp_ring_info *cpr,
+			       struct skb_shared_info *shinfo,
+			       u16 idx, u32 agg_bufs, bool tpa,
+			       struct xdp_buff *xdp)
 {
 	struct bnxt_napi *bnapi = cpr->bnapi;
 	struct pci_dev *pdev = bp->pdev;
 	struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
 	u16 prod = rxr->rx_agg_prod;
+	u32 i, total_frag_len = 0;
 	bool p5_tpa = false;
-	u32 i;
 
 	if ((bp->flags & BNXT_FLAG_CHIP_P5) && tpa)
 		p5_tpa = true;
 
 	for (i = 0; i < agg_bufs; i++) {
+		skb_frag_t *frag = &shinfo->frags[i];
 		u16 cons, frag_len;
 		struct rx_agg_cmp *agg;
 		struct bnxt_sw_rx_agg_bd *cons_rx_buf;
@@ -1069,8 +1113,10 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp,
 			    RX_AGG_CMP_LEN) >> RX_AGG_CMP_LEN_SHIFT;
 
 		cons_rx_buf = &rxr->rx_agg_ring[cons];
-		skb_fill_page_desc(skb, i, cons_rx_buf->page,
-				   cons_rx_buf->offset, frag_len);
+		skb_frag_off_set(frag, cons_rx_buf->offset);
+		skb_frag_size_set(frag, frag_len);
+		__skb_frag_set_page(frag, cons_rx_buf->page);
+		shinfo->nr_frags = i + 1;
 		__clear_bit(cons, rxr->rx_agg_bmap);
 
 		/* It is possible for bnxt_alloc_rx_page() to allocate
@@ -1081,16 +1127,14 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp,
 		page = cons_rx_buf->page;
 		cons_rx_buf->page = NULL;
 
+		if (xdp && page_is_pfmemalloc(page))
+			xdp_buff_set_frag_pfmemalloc(xdp);
+
 		if (bnxt_alloc_rx_page(bp, rxr, prod, GFP_ATOMIC) != 0) {
-			struct skb_shared_info *shinfo;
 			unsigned int nr_frags;
 
-			shinfo = skb_shinfo(skb);
 			nr_frags = --shinfo->nr_frags;
 			__skb_frag_set_page(&shinfo->frags[nr_frags], NULL);
-
-			dev_kfree_skb(skb);
-
 			cons_rx_buf->page = page;
 
 			/* Update prod since possibly some pages have been
@@ -1098,23 +1142,62 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp,
 			 */
 			rxr->rx_agg_prod = prod;
 			bnxt_reuse_rx_agg_bufs(cpr, idx, i, agg_bufs - i, tpa);
-			return NULL;
+			return 0;
 		}
 
 		dma_unmap_page_attrs(&pdev->dev, mapping, BNXT_RX_PAGE_SIZE,
-				     DMA_FROM_DEVICE,
+				     bp->rx_dir,
 				     DMA_ATTR_WEAK_ORDERING);
 
-		skb->data_len += frag_len;
-		skb->len += frag_len;
-		skb->truesize += PAGE_SIZE;
-
+		total_frag_len += frag_len;
 		prod = NEXT_RX_AGG(prod);
 	}
 	rxr->rx_agg_prod = prod;
+	return total_frag_len;
+}
+
+static struct sk_buff *bnxt_rx_agg_pages_skb(struct bnxt *bp,
+					     struct bnxt_cp_ring_info *cpr,
+					     struct sk_buff *skb, u16 idx,
+					     u32 agg_bufs, bool tpa)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+	u32 total_frag_len = 0;
+
+	total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo, idx,
+					     agg_bufs, tpa, NULL);
+	if (!total_frag_len) {
+		dev_kfree_skb(skb);
+		return NULL;
+	}
+
+	skb->data_len += total_frag_len;
+	skb->len += total_frag_len;
+	skb->truesize += PAGE_SIZE * agg_bufs;
 	return skb;
 }
 
+static u32 bnxt_rx_agg_pages_xdp(struct bnxt *bp,
+				 struct bnxt_cp_ring_info *cpr,
+				 struct xdp_buff *xdp, u16 idx,
+				 u32 agg_bufs, bool tpa)
+{
+	struct skb_shared_info *shinfo = xdp_get_shared_info_from_buff(xdp);
+	u32 total_frag_len = 0;
+
+	if (!xdp_buff_has_frags(xdp))
+		shinfo->nr_frags = 0;
+
+	total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo,
+					     idx, agg_bufs, tpa, xdp);
+	if (total_frag_len) {
+		xdp_buff_set_frags_flag(xdp);
+		shinfo->nr_frags = agg_bufs;
+		shinfo->xdp_frags_size = total_frag_len;
+	}
+	return total_frag_len;
+}
+
 static int bnxt_agg_bufs_valid(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			       u8 agg_bufs, u32 *raw_cons)
 {
@@ -1644,7 +1727,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 	}
 
 	if (agg_bufs) {
-		skb = bnxt_rx_pages(bp, cpr, skb, idx, agg_bufs, true);
+		skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, idx, agg_bufs, true);
 		if (!skb) {
 			/* Page reuse already handled by bnxt_rx_pages(). */
 			cpr->sw_stats.rx.rx_oom_discards += 1;
@@ -1729,8 +1812,10 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	struct bnxt_sw_rx_bd *rx_buf;
 	unsigned int len;
 	u8 *data_ptr, agg_bufs, cmp_type;
+	bool xdp_active = false;
 	dma_addr_t dma_addr;
 	struct sk_buff *skb;
+	struct xdp_buff xdp;
 	u32 flags, misc;
 	void *data;
 	int rc = 0;
@@ -1839,18 +1924,39 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	len = flags >> RX_CMP_LEN_SHIFT;
 	dma_addr = rx_buf->mapping;
 
-	if (bnxt_rx_xdp(bp, rxr, cons, data, &data_ptr, &len, event)) {
-		rc = 1;
-		goto next_rx;
+	if (bnxt_xdp_attached(bp, rxr)) {
+		bnxt_xdp_buff_init(bp, rxr, cons, &data_ptr, &len, &xdp);
+		if (agg_bufs) {
+			u32 frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp,
+							     cp_cons, agg_bufs,
+							     false);
+			if (!frag_len) {
+				cpr->sw_stats.rx.rx_oom_discards += 1;
+				rc = -ENOMEM;
+				goto next_rx;
+			}
+		}
+		xdp_active = true;
+	}
+
+	if (xdp_active) {
+		if (bnxt_rx_xdp(bp, rxr, cons, xdp, data, &len, event)) {
+			rc = 1;
+			goto next_rx;
+		}
 	}
 
 	if (len <= bp->rx_copy_thresh) {
 		skb = bnxt_copy_skb(bnapi, data_ptr, len, dma_addr);
 		bnxt_reuse_rx_data(rxr, cons, data);
 		if (!skb) {
-			if (agg_bufs)
-				bnxt_reuse_rx_agg_bufs(cpr, cp_cons, 0,
-						       agg_bufs, false);
+			if (agg_bufs) {
+				if (!xdp_active)
+					bnxt_reuse_rx_agg_bufs(cpr, cp_cons, 0,
+							       agg_bufs, false);
+				else
+					bnxt_xdp_buff_frags_free(rxr, &xdp);
+			}
 			cpr->sw_stats.rx.rx_oom_discards += 1;
 			rc = -ENOMEM;
 			goto next_rx;
@@ -1872,11 +1978,22 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	}
 
 	if (agg_bufs) {
-		skb = bnxt_rx_pages(bp, cpr, skb, cp_cons, agg_bufs, false);
-		if (!skb) {
-			cpr->sw_stats.rx.rx_oom_discards += 1;
-			rc = -ENOMEM;
-			goto next_rx;
+		if (!xdp_active) {
+			skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, cp_cons, agg_bufs, false);
+			if (!skb) {
+				cpr->sw_stats.rx.rx_oom_discards += 1;
+				rc = -ENOMEM;
+				goto next_rx;
+			}
+		} else {
+			skb = bnxt_xdp_build_skb(bp, skb, agg_bufs, rxr->page_pool, &xdp, rxcmp1);
+			if (!skb) {
+				/* we should be able to free the old skb here */
+				bnxt_xdp_buff_frags_free(rxr, &xdp);
+				cpr->sw_stats.rx.rx_oom_discards += 1;
+				rc = -ENOMEM;
+				goto next_rx;
+			}
 		}
 	}
 
@@ -2492,10 +2609,13 @@ static void __bnxt_poll_work_done(struct bnxt *bp, struct bnxt_napi *bnapi)
 	if ((bnapi->events & BNXT_RX_EVENT) && !(bnapi->in_reset)) {
 		struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
 
-		if (bnapi->events & BNXT_AGG_EVENT)
-			bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod);
 		bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
 	}
+	if (bnapi->events & BNXT_AGG_EVENT) {
+		struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
+
+		bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod);
+	}
 	bnapi->events = 0;
 }
 
@@ -2872,14 +2992,23 @@ skip_rx_buf_free:
 		if (!page)
 			continue;
 
-		dma_unmap_page_attrs(&pdev->dev, rx_agg_buf->mapping,
-				     BNXT_RX_PAGE_SIZE, DMA_FROM_DEVICE,
-				     DMA_ATTR_WEAK_ORDERING);
+		if (BNXT_RX_PAGE_MODE(bp)) {
+			dma_unmap_page_attrs(&pdev->dev, rx_agg_buf->mapping,
+					     BNXT_RX_PAGE_SIZE, bp->rx_dir,
+					     DMA_ATTR_WEAK_ORDERING);
+			rx_agg_buf->page = NULL;
+			__clear_bit(i, rxr->rx_agg_bmap);
 
-		rx_agg_buf->page = NULL;
-		__clear_bit(i, rxr->rx_agg_bmap);
+			page_pool_recycle_direct(rxr->page_pool, page);
+		} else {
+			dma_unmap_page_attrs(&pdev->dev, rx_agg_buf->mapping,
+					     BNXT_RX_PAGE_SIZE, DMA_FROM_DEVICE,
+					     DMA_ATTR_WEAK_ORDERING);
+			rx_agg_buf->page = NULL;
+			__clear_bit(i, rxr->rx_agg_bmap);
 
-		__free_page(page);
+			__free_page(page);
+		}
 	}
 
 skip_rx_agg_free:
@@ -3793,7 +3922,7 @@ void bnxt_set_ring_params(struct bnxt *bp)
 	/* 8 for CRC and VLAN */
 	rx_size = SKB_DATA_ALIGN(bp->dev->mtu + ETH_HLEN + NET_IP_ALIGN + 8);
 
-	rx_space = rx_size + NET_SKB_PAD +
+	rx_space = rx_size + ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8) +
 		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	bp->rx_copy_thresh = BNXT_RX_COPY_THRESH;
@@ -3834,9 +3963,15 @@ void bnxt_set_ring_params(struct bnxt *bp)
 		}
 		bp->rx_agg_ring_size = agg_ring_size;
 		bp->rx_agg_ring_mask = (bp->rx_agg_nr_pages * RX_DESC_CNT) - 1;
-		rx_size = SKB_DATA_ALIGN(BNXT_RX_COPY_THRESH + NET_IP_ALIGN);
-		rx_space = rx_size + NET_SKB_PAD +
-			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+		if (BNXT_RX_PAGE_MODE(bp)) {
+			rx_space = BNXT_PAGE_MODE_BUF_SIZE;
+			rx_size = BNXT_MAX_PAGE_MODE_MTU;
+		} else {
+			rx_size = SKB_DATA_ALIGN(BNXT_RX_COPY_THRESH + NET_IP_ALIGN);
+			rx_space = rx_size + NET_SKB_PAD +
+				SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+		}
 	}
 
 	bp->rx_buf_use_size = rx_size;
@@ -3877,14 +4012,21 @@ void bnxt_set_ring_params(struct bnxt *bp)
 int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode)
 {
 	if (page_mode) {
-		if (bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU)
-			return -EOPNOTSUPP;
-		bp->dev->max_mtu =
-			min_t(u16, bp->max_mtu, BNXT_MAX_PAGE_MODE_MTU);
 		bp->flags &= ~BNXT_FLAG_AGG_RINGS;
-		bp->flags |= BNXT_FLAG_NO_AGG_RINGS | BNXT_FLAG_RX_PAGE_MODE;
+		bp->flags |= BNXT_FLAG_RX_PAGE_MODE;
+
+		if (bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU) {
+			bp->flags |= BNXT_FLAG_JUMBO;
+			bp->rx_skb_func = bnxt_rx_multi_page_skb;
+			bp->dev->max_mtu =
+				min_t(u16, bp->max_mtu, BNXT_MAX_MTU);
+		} else {
+			bp->flags |= BNXT_FLAG_NO_AGG_RINGS;
+			bp->rx_skb_func = bnxt_rx_page_skb;
+			bp->dev->max_mtu =
+				min_t(u16, bp->max_mtu, BNXT_MAX_PAGE_MODE_MTU);
+		}
 		bp->rx_dir = DMA_BIDIRECTIONAL;
-		bp->rx_skb_func = bnxt_rx_page_skb;
 		/* Disable LRO or GRO_HW */
 		netdev_update_features(bp->dev);
 	} else {
@@ -5226,12 +5368,15 @@ static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, u16 vnic_id)
 	if (rc)
 		return rc;
 
-	req->flags = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT |
-				 VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4 |
-				 VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6);
-	req->enables =
-		cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID |
-			    VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID);
+	req->flags = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT);
+	req->enables = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID);
+
+	if (BNXT_RX_PAGE_MODE(bp) && !BNXT_RX_JUMBO_MODE(bp)) {
+		req->flags |= cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4 |
+					  VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6);
+		req->enables |=
+			cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID);
+	}
 	/* thresholds not implemented in firmware yet */
 	req->jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh);
 	req->hds_threshold = cpu_to_le16(bp->rx_copy_thresh);
@@ -11031,6 +11176,9 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev,
 	if (bp->flags & BNXT_FLAG_NO_AGG_RINGS)
 		features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW);
 
+	if (!(bp->flags & BNXT_FLAG_TPA))
+		features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW);
+
 	if (!(features & NETIF_F_GRO))
 		features &= ~NETIF_F_GRO_HW;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 98453a78cbd0..a498ee297946 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -591,10 +591,12 @@ struct nqe_cn {
 #define BNXT_RX_PAGE_SIZE (1 << BNXT_RX_PAGE_SHIFT)
 
 #define BNXT_MAX_MTU		9500
-#define BNXT_MAX_PAGE_MODE_MTU	\
+#define BNXT_PAGE_MODE_BUF_SIZE \
 	((unsigned int)PAGE_SIZE - VLAN_ETH_HLEN - NET_IP_ALIGN -	\
-	 XDP_PACKET_HEADROOM - \
-	 SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info)))
+	 XDP_PACKET_HEADROOM)
+#define BNXT_MAX_PAGE_MODE_MTU	\
+	BNXT_PAGE_MODE_BUF_SIZE - \
+	SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info))
 
 #define BNXT_MIN_PKT_SIZE	52
 
@@ -699,13 +701,12 @@ struct bnxt_sw_tx_bd {
 	};
 	DEFINE_DMA_UNMAP_ADDR(mapping);
 	DEFINE_DMA_UNMAP_LEN(len);
+	struct page		*page;
 	u8			is_gso;
 	u8			is_push;
 	u8			action;
-	union {
-		unsigned short		nr_frags;
-		u16			rx_prod;
-	};
+	unsigned short		nr_frags;
+	u16			rx_prod;
 };
 
 struct bnxt_sw_rx_bd {
@@ -1817,6 +1818,7 @@ struct bnxt {
 #define BNXT_SUPPORTS_TPA(bp)	(!BNXT_CHIP_TYPE_NITRO_A0(bp) &&	\
 				 (!((bp)->flags & BNXT_FLAG_CHIP_P5) ||	\
 				  (bp)->max_tpa_v2) && !is_kdump_kernel())
+#define BNXT_RX_JUMBO_MODE(bp)	((bp)->flags & BNXT_FLAG_JUMBO)
 
 #define BNXT_CHIP_SR2(bp)			\
 	((bp)->chip_num == CHIP_NUM_58818)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 22e965e18fbc..b3a48d6675fe 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -3491,7 +3491,7 @@ static int bnxt_run_loopback(struct bnxt *bp)
 		dev_kfree_skb(skb);
 		return -EIO;
 	}
-	bnxt_xmit_bd(bp, txr, map, pkt_size);
+	bnxt_xmit_bd(bp, txr, map, pkt_size, NULL);
 
 	/* Sync BD data before updating doorbell */
 	wmb();
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 03b1d6c04504..f02fe906dedb 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -24,36 +24,91 @@ DEFINE_STATIC_KEY_FALSE(bnxt_xdp_locking_key);
 
 struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
 				   struct bnxt_tx_ring_info *txr,
-				   dma_addr_t mapping, u32 len)
+				   dma_addr_t mapping, u32 len,
+				   struct xdp_buff *xdp)
 {
-	struct bnxt_sw_tx_bd *tx_buf;
+	struct skb_shared_info *sinfo;
+	struct bnxt_sw_tx_bd *tx_buf, *first_buf;
 	struct tx_bd *txbd;
+	int num_frags = 0;
 	u32 flags;
 	u16 prod;
+	int i;
+
+	if (xdp && xdp_buff_has_frags(xdp)) {
+		sinfo = xdp_get_shared_info_from_buff(xdp);
+		num_frags = sinfo->nr_frags;
+	}
 
+	/* fill up the first buffer */
 	prod = txr->tx_prod;
 	tx_buf = &txr->tx_buf_ring[prod];
+	first_buf = tx_buf;
+	tx_buf->nr_frags = num_frags;
+	if (xdp)
+		tx_buf->page = virt_to_head_page(xdp->data);
 
 	txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
-	flags = (len << TX_BD_LEN_SHIFT) | (1 << TX_BD_FLAGS_BD_CNT_SHIFT) |
-		TX_BD_FLAGS_PACKET_END | bnxt_lhint_arr[len >> 9];
+	flags = ((len) << TX_BD_LEN_SHIFT) | ((num_frags + 1) << TX_BD_FLAGS_BD_CNT_SHIFT);
 	txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
 	txbd->tx_bd_opaque = prod;
 	txbd->tx_bd_haddr = cpu_to_le64(mapping);
 
+	/* now let us fill up the frags into the next buffers */
+	for (i = 0; i < num_frags ; i++) {
+		skb_frag_t *frag = &sinfo->frags[i];
+		struct bnxt_sw_tx_bd *frag_tx_buf;
+		struct pci_dev *pdev = bp->pdev;
+		dma_addr_t frag_mapping;
+		int frag_len;
+
+		prod = NEXT_TX(prod);
+		txr->tx_prod = prod;
+
+		/* first fill up the first buffer */
+		frag_tx_buf = &txr->tx_buf_ring[prod];
+		frag_tx_buf->page = skb_frag_page(frag);
+
+		txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
+
+		frag_len = skb_frag_size(frag);
+		frag_mapping = skb_frag_dma_map(&pdev->dev, frag, 0,
+						frag_len, DMA_TO_DEVICE);
+
+		if (unlikely(dma_mapping_error(&pdev->dev, frag_mapping)))
+			return NULL;
+
+		dma_unmap_addr_set(frag_tx_buf, mapping, frag_mapping);
+
+		flags = frag_len << TX_BD_LEN_SHIFT;
+		txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
+		txbd->tx_bd_opaque = prod;
+		txbd->tx_bd_haddr = cpu_to_le64(frag_mapping);
+
+		len = frag_len;
+	}
+
+	flags &= ~TX_BD_LEN;
+	txbd->tx_bd_len_flags_type = cpu_to_le32(((len) << TX_BD_LEN_SHIFT) | flags |
+			TX_BD_FLAGS_PACKET_END);
+	/* Sync TX BD */
+	wmb();
 	prod = NEXT_TX(prod);
 	txr->tx_prod = prod;
-	return tx_buf;
+
+	return first_buf;
 }
 
 static void __bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
-			    dma_addr_t mapping, u32 len, u16 rx_prod)
+			    dma_addr_t mapping, u32 len, u16 rx_prod,
+			    struct xdp_buff *xdp)
 {
 	struct bnxt_sw_tx_bd *tx_buf;
 
-	tx_buf = bnxt_xmit_bd(bp, txr, mapping, len);
+	tx_buf = bnxt_xmit_bd(bp, txr, mapping, len, xdp);
 	tx_buf->rx_prod = rx_prod;
 	tx_buf->action = XDP_TX;
+
 }
 
 static void __bnxt_xmit_xdp_redirect(struct bnxt *bp,
@@ -63,7 +118,7 @@ static void __bnxt_xmit_xdp_redirect(struct bnxt *bp,
 {
 	struct bnxt_sw_tx_bd *tx_buf;
 
-	tx_buf = bnxt_xmit_bd(bp, txr, mapping, len);
+	tx_buf = bnxt_xmit_bd(bp, txr, mapping, len, NULL);
 	tx_buf->action = XDP_REDIRECT;
 	tx_buf->xdpf = xdpf;
 	dma_unmap_addr_set(tx_buf, mapping, mapping);
@@ -78,7 +133,7 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 	struct bnxt_sw_tx_bd *tx_buf;
 	u16 tx_cons = txr->tx_cons;
 	u16 last_tx_cons = tx_cons;
-	int i;
+	int i, j, frags;
 
 	for (i = 0; i < nr_pkts; i++) {
 		tx_buf = &txr->tx_buf_ring[tx_cons];
@@ -96,6 +151,13 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 		} else if (tx_buf->action == XDP_TX) {
 			rx_doorbell_needed = true;
 			last_tx_cons = tx_cons;
+
+			frags = tx_buf->nr_frags;
+			for (j = 0; j < frags; j++) {
+				tx_cons = NEXT_TX(tx_cons);
+				tx_buf = &txr->tx_buf_ring[tx_cons];
+				page_pool_recycle_direct(rxr->page_pool, tx_buf->page);
+			}
 		}
 		tx_cons = NEXT_TX(tx_cons);
 	}
@@ -103,7 +165,52 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 	if (rx_doorbell_needed) {
 		tx_buf = &txr->tx_buf_ring[last_tx_cons];
 		bnxt_db_write(bp, &rxr->rx_db, tx_buf->rx_prod);
+
+	}
+}
+
+bool bnxt_xdp_attached(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
+{
+	struct bpf_prog *xdp_prog = READ_ONCE(rxr->xdp_prog);
+
+	return !!xdp_prog;
+}
+
+void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
+			u16 cons, u8 **data_ptr, unsigned int *len,
+			struct xdp_buff *xdp)
+{
+	struct bnxt_sw_rx_bd *rx_buf;
+	struct pci_dev *pdev;
+	dma_addr_t mapping;
+	u32 offset;
+
+	pdev = bp->pdev;
+	rx_buf = &rxr->rx_buf_ring[cons];
+	offset = bp->rx_offset;
+
+	mapping = rx_buf->mapping - bp->rx_dma_offset;
+	dma_sync_single_for_cpu(&pdev->dev, mapping + offset, *len, bp->rx_dir);
+
+	xdp_init_buff(xdp, BNXT_PAGE_MODE_BUF_SIZE + offset, &rxr->xdp_rxq);
+	xdp_prepare_buff(xdp, *data_ptr - offset, offset, *len, false);
+}
+
+void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
+			      struct xdp_buff *xdp)
+{
+	struct skb_shared_info *shinfo;
+	int i;
+
+	if (!xdp || !xdp_buff_has_frags(xdp))
+		return;
+	shinfo = xdp_get_shared_info_from_buff(xdp);
+	for (i = 0; i < shinfo->nr_frags; i++) {
+		struct page *page = skb_frag_page(&shinfo->frags[i]);
+
+		page_pool_recycle_direct(rxr->page_pool, page);
 	}
+	shinfo->nr_frags = 0;
 }
 
 /* returns the following:
@@ -111,14 +218,14 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
  * false   - packet should be passed to the stack.
  */
 bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
-		 struct page *page, u8 **data_ptr, unsigned int *len, u8 *event)
+		 struct xdp_buff xdp, struct page *page, unsigned int *len, u8 *event)
 {
 	struct bpf_prog *xdp_prog = READ_ONCE(rxr->xdp_prog);
 	struct bnxt_tx_ring_info *txr;
 	struct bnxt_sw_rx_bd *rx_buf;
 	struct pci_dev *pdev;
-	struct xdp_buff xdp;
 	dma_addr_t mapping;
+	u32 tx_needed = 1;
 	void *orig_data;
 	u32 tx_avail;
 	u32 offset;
@@ -128,16 +235,10 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		return false;
 
 	pdev = bp->pdev;
-	rx_buf = &rxr->rx_buf_ring[cons];
 	offset = bp->rx_offset;
 
-	mapping = rx_buf->mapping - bp->rx_dma_offset;
-	dma_sync_single_for_cpu(&pdev->dev, mapping + offset, *len, bp->rx_dir);
-
 	txr = rxr->bnapi->tx_ring;
 	/* BNXT_RX_PAGE_MODE(bp) when XDP enabled */
-	xdp_init_buff(&xdp, PAGE_SIZE, &rxr->xdp_rxq);
-	xdp_prepare_buff(&xdp, *data_ptr - offset, offset, *len, false);
 	orig_data = xdp.data;
 
 	act = bpf_prog_run_xdp(xdp_prog, &xdp);
@@ -150,26 +251,38 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		*event &= ~BNXT_RX_EVENT;
 
 	*len = xdp.data_end - xdp.data;
-	if (orig_data != xdp.data) {
+	if (orig_data != xdp.data)
 		offset = xdp.data - xdp.data_hard_start;
-		*data_ptr = xdp.data_hard_start + offset;
-	}
+
 	switch (act) {
 	case XDP_PASS:
 		return false;
 
 	case XDP_TX:
-		if (tx_avail < 1) {
+		rx_buf = &rxr->rx_buf_ring[cons];
+		mapping = rx_buf->mapping - bp->rx_dma_offset;
+		*event = 0;
+
+		if (unlikely(xdp_buff_has_frags(&xdp))) {
+			struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(&xdp);
+
+			tx_needed += sinfo->nr_frags;
+			*event = BNXT_AGG_EVENT;
+		}
+
+		if (tx_avail < tx_needed) {
 			trace_xdp_exception(bp->dev, xdp_prog, act);
+			bnxt_xdp_buff_frags_free(rxr, &xdp);
 			bnxt_reuse_rx_data(rxr, cons, page);
 			return true;
 		}
 
-		*event = BNXT_TX_EVENT;
 		dma_sync_single_for_device(&pdev->dev, mapping + offset, *len,
 					   bp->rx_dir);
+
+		*event |= BNXT_TX_EVENT;
 		__bnxt_xmit_xdp(bp, txr, mapping + offset, *len,
-				NEXT_RX(rxr->rx_prod));
+				NEXT_RX(rxr->rx_prod), &xdp);
 		bnxt_reuse_rx_data(rxr, cons, page);
 		return true;
 	case XDP_REDIRECT:
@@ -177,6 +290,8 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		 * redirect is coming from a frame received by the
 		 * bnxt_en driver.
 		 */
+		rx_buf = &rxr->rx_buf_ring[cons];
+		mapping = rx_buf->mapping - bp->rx_dma_offset;
 		dma_unmap_page_attrs(&pdev->dev, mapping,
 				     PAGE_SIZE, bp->rx_dir,
 				     DMA_ATTR_WEAK_ORDERING);
@@ -184,6 +299,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		/* if we are unable to allocate a new buffer, abort and reuse */
 		if (bnxt_alloc_rx_data(bp, rxr, rxr->rx_prod, GFP_ATOMIC)) {
 			trace_xdp_exception(bp->dev, xdp_prog, act);
+			bnxt_xdp_buff_frags_free(rxr, &xdp);
 			bnxt_reuse_rx_data(rxr, cons, page);
 			return true;
 		}
@@ -203,6 +319,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		trace_xdp_exception(bp->dev, xdp_prog, act);
 		fallthrough;
 	case XDP_DROP:
+		bnxt_xdp_buff_frags_free(rxr, &xdp);
 		bnxt_reuse_rx_data(rxr, cons, page);
 		break;
 	}
@@ -270,8 +387,9 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 	int tx_xdp = 0, rc, tc;
 	struct bpf_prog *old;
 
-	if (prog && bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU) {
-		netdev_warn(dev, "MTU %d larger than largest XDP supported MTU %d.\n",
+	if (prog && !prog->aux->xdp_has_frags &&
+	    bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU) {
+		netdev_warn(dev, "MTU %d larger than %d without XDP frag support.\n",
 			    bp->dev->mtu, BNXT_MAX_PAGE_MODE_MTU);
 		return -EOPNOTSUPP;
 	}
@@ -337,3 +455,26 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 	return rc;
 }
+
+struct sk_buff *
+bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb, u8 num_frags,
+		   struct page_pool *pool, struct xdp_buff *xdp,
+		   struct rx_cmp_ext *rxcmp1)
+{
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+
+	if (!skb)
+		return NULL;
+	skb_checksum_none_assert(skb);
+	if (RX_CMP_L4_CS_OK(rxcmp1)) {
+		if (bp->dev->features & NETIF_F_RXCSUM) {
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+			skb->csum_level = RX_CMP_ENCAP(rxcmp1);
+		}
+	}
+	xdp_update_skb_shared_info(skb, num_frags,
+				   sinfo->xdp_frags_size,
+				   PAGE_SIZE * sinfo->nr_frags,
+				   xdp_buff_is_frag_pfmemalloc(xdp));
+	return skb;
+}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index 067bb5e821f5..505911ae095d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -14,13 +14,25 @@ DECLARE_STATIC_KEY_FALSE(bnxt_xdp_locking_key);
 
 struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
 				   struct bnxt_tx_ring_info *txr,
-				   dma_addr_t mapping, u32 len);
+				   dma_addr_t mapping, u32 len,
+				   struct xdp_buff *xdp);
 void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts);
 bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
-		 struct page *page, u8 **data_ptr, unsigned int *len,
+		 struct xdp_buff xdp, struct page *page, unsigned int *len,
 		 u8 *event);
 int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp);
 int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
 		  struct xdp_frame **frames, u32 flags);
 
+bool bnxt_xdp_attached(struct bnxt *bp, struct bnxt_rx_ring_info *rxr);
+
+void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
+			u16 cons, u8 **data_ptr, unsigned int *len,
+			struct xdp_buff *xdp);
+void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
+			      struct xdp_buff *xdp);
+struct sk_buff *bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb,
+				   u8 num_frags, struct page_pool *pool,
+				   struct xdp_buff *xdp,
+				   struct rx_cmp_ext *rxcmp1);
 #endif