net/mlx4_en: add support for fast rx drop bpf program

Add support for the BPF_PROG_TYPE_XDP hook in mlx4 driver.

In tc/socket bpf programs, helpers linearize skb fragments as needed
when the program touches the packet data. However, in the pursuit of
speed, XDP programs will not be allowed to use these slower functions,
especially if it involves allocating an skb.

Therefore, disallow MTU settings that would produce a multi-fragment
packet that XDP programs would fail to access. Future enhancements could
be done to increase the allowable MTU.

The xdp program is present as a per-ring data structure, but as of yet
it is not possible to set at that granularity through any ndo.

Signed-off-by: Brenden Blanco <bblanco@plumgrid.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 36 insertions, 4 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index c1b3a9c8cf3b..67295458ebed 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -32,6 +32,7 @@
  */
 
 #include <net/busy_poll.h>
+#include <linux/bpf.h>
 #include <linux/mlx4/cq.h>
 #include <linux/slab.h>
 #include <linux/mlx4/qp.h>
@@ -509,6 +510,8 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_en_rx_ring *ring = *pring;
 
+	if (ring->xdp_prog)
+		bpf_prog_put(ring->xdp_prog);
 	mlx4_free_hwq_res(mdev->dev, &ring->wqres, size * stride + TXBB_SIZE);
 	vfree(ring->rx_info);
 	ring->rx_info = NULL;
@@ -743,6 +746,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	struct mlx4_en_rx_ring *ring = priv->rx_ring[cq->ring];
 	struct mlx4_en_rx_alloc *frags;
 	struct mlx4_en_rx_desc *rx_desc;
+	struct bpf_prog *xdp_prog;
 	struct sk_buff *skb;
 	int index;
 	int nr;
@@ -759,6 +763,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	if (budget <= 0)
 		return polled;
 
+	xdp_prog = READ_ONCE(ring->xdp_prog);
+
 	/* We assume a 1:1 mapping between CQEs and Rx descriptors, so Rx
 	 * descriptor offset can be deduced from the CQE index instead of
 	 * reading 'cqe->index' */
@@ -835,6 +841,35 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
 			(cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
 
+		/* A bpf program gets first chance to drop the packet. It may
+		 * read bytes but not past the end of the frag.
+		 */
+		if (xdp_prog) {
+			struct xdp_buff xdp;
+			dma_addr_t dma;
+			u32 act;
+
+			dma = be64_to_cpu(rx_desc->data[0].addr);
+			dma_sync_single_for_cpu(priv->ddev, dma,
+						priv->frag_info[0].frag_size,
+						DMA_FROM_DEVICE);
+
+			xdp.data = page_address(frags[0].page) +
+							frags[0].page_offset;
+			xdp.data_end = xdp.data + length;
+
+			act = bpf_prog_run_xdp(xdp_prog, &xdp);
+			switch (act) {
+			case XDP_PASS:
+				break;
+			default:
+				bpf_warn_invalid_xdp_action(act);
+			case XDP_ABORTED:
+			case XDP_DROP:
+				goto next;
+			}
+		}
+
 		if (likely(dev->features & NETIF_F_RXCSUM)) {
 			if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
 						      MLX4_CQE_STATUS_UDP)) {
@@ -1062,10 +1097,7 @@ static const int frag_sizes[] = {
 void mlx4_en_calc_rx_buf(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
-	/* VLAN_HLEN is added twice,to support skb vlan tagged with multiple
-	 * headers. (For example: ETH_P_8021Q and ETH_P_8021AD).
-	 */
-	int eff_mtu = dev->mtu + ETH_HLEN + (2 * VLAN_HLEN);
+	int eff_mtu = MLX4_EN_EFF_MTU(dev->mtu);
 	int buf_size = 0;
 	int i = 0;