bnxt: adding bnxt_xdp_build_skb to build skb from multibuffer xdp_buff

Since we have an xdp_buff with frags there needs to be a way to
convert that into a valid sk_buff in the event that XDP_PASS is
the resulting operation.  This adds a new rx_skb_func when the
netdev has an MTU that prevents the packets from sitting in a
single page.

This also make sure that GRO/LRO stay disabled even when using
the aggregation ring for large buffers.

v3: Use BNXT_PAGE_MODE_BUF_SIZE for build_skb

Signed-off-by: Andy Gospodarek <gospo@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 85 insertions, 7 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index f89a45042f38..f96f41c7927e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -971,6 +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,
@@ -993,7 +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);
@@ -1004,6 +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,
@@ -1949,6 +1982,14 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 				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 */
+				cpr->sw_stats.rx.rx_oom_discards += 1;
+				rc = -ENOMEM;
+				goto next_rx;
+			}
 		}
 	}
 
@@ -3964,14 +4005,21 @@ 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 {
@@ -11121,6 +11169,9 @@ 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_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index a3924e6030fe..5183357ca11c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -361,3 +361,26 @@ 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 97e7905dbb20..27290f649be3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -28,4 +28,8 @@ 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);
+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