Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 46 insertions, 13 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 91b1b0938931..5b499c7a698f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -42,10 +42,11 @@
 #include "en_rep.h"
 #include "ipoib/ipoib.h"
 #include "en_accel/ipsec_rxtx.h"
+#include "lib/clock.h"
 
-static inline bool mlx5e_rx_hw_stamp(struct mlx5e_tstamp *tstamp)
+static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
 {
-	return tstamp->hwtstamp_config.rx_filter == HWTSTAMP_FILTER_ALL;
+	return config->rx_filter == HWTSTAMP_FILTER_ALL;
 }
 
 static inline void mlx5e_read_cqe_slot(struct mlx5e_cq *cq, u32 cqcc,
@@ -560,7 +561,6 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
 	u8 tcp_ack = (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) ||
 		(l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA);
 
-	skb->mac_len = ETH_HLEN;
 	proto = __vlan_get_protocol(skb, eth->h_proto, &network_depth);
 
 	tot_len = cqe_bcnt - network_depth;
@@ -607,10 +607,11 @@ static inline void mlx5e_skb_set_hash(struct mlx5_cqe64 *cqe,
 	skb_set_hash(skb, be32_to_cpu(cqe->rss_hash_result), ht);
 }
 
-static inline bool is_first_ethertype_ip(struct sk_buff *skb)
+static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth)
 {
 	__be16 ethertype = ((struct ethhdr *)skb->data)->h_proto;
 
+	ethertype = __vlan_get_protocol(skb, ethertype, network_depth);
 	return (ethertype == htons(ETH_P_IP) || ethertype == htons(ETH_P_IPV6));
 }
 
@@ -620,6 +621,8 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 				     struct sk_buff *skb,
 				     bool   lro)
 {
+	int network_depth = 0;
+
 	if (unlikely(!(netdev->features & NETIF_F_RXCSUM)))
 		goto csum_none;
 
@@ -629,9 +632,17 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		return;
 	}
 
-	if (is_first_ethertype_ip(skb)) {
+	if (is_last_ethertype_ip(skb, &network_depth)) {
 		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
+		if (network_depth > ETH_HLEN)
+			/* CQE csum is calculated from the IP header and does
+			 * not cover VLAN headers (if present). This will add
+			 * the checksum manually.
+			 */
+			skb->csum = csum_partial(skb->data + ETH_HLEN,
+						 network_depth - ETH_HLEN,
+						 skb->csum);
 		rq->stats.csum_complete++;
 		return;
 	}
@@ -659,9 +670,9 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 				      struct sk_buff *skb)
 {
 	struct net_device *netdev = rq->netdev;
-	struct mlx5e_tstamp *tstamp = rq->tstamp;
 	int lro_num_seg;
 
+	skb->mac_len = ETH_HLEN;
 	lro_num_seg = be32_to_cpu(cqe->srqn) >> 24;
 	if (lro_num_seg > 1) {
 		mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
@@ -674,17 +685,20 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 		rq->stats.lro_bytes += cqe_bcnt;
 	}
 
-	if (unlikely(mlx5e_rx_hw_stamp(tstamp)))
-		mlx5e_fill_hwstamp(tstamp, get_cqe_ts(cqe), skb_hwtstamps(skb));
+	if (unlikely(mlx5e_rx_hw_stamp(rq->tstamp)))
+		skb_hwtstamps(skb)->hwtstamp =
+				mlx5_timecounter_cyc2time(rq->clock, get_cqe_ts(cqe));
 
 	skb_record_rx_queue(skb, rq->ix);
 
 	if (likely(netdev->features & NETIF_F_RXHASH))
 		mlx5e_skb_set_hash(cqe, skb);
 
-	if (cqe_has_vlan(cqe))
+	if (cqe_has_vlan(cqe)) {
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
 				       be16_to_cpu(cqe->vlan_info));
+		rq->stats.removed_vlan_packets++;
+	}
 
 	skb->mark = be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK;
 
@@ -795,6 +809,7 @@ static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq,
 		return false;
 
 	xdp.data = va + *rx_headroom;
+	xdp_set_data_meta_invalid(&xdp);
 	xdp.data_end = xdp.data + *len;
 	xdp.data_hard_start = va;
 
@@ -1160,12 +1175,25 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 					 u32 cqe_bcnt,
 					 struct sk_buff *skb)
 {
-	struct net_device *netdev = rq->netdev;
-	struct mlx5e_tstamp *tstamp = rq->tstamp;
+	struct net_device *netdev;
 	char *pseudo_header;
+	u32 qpn;
 	u8 *dgid;
 	u8 g;
 
+	qpn = be32_to_cpu(cqe->sop_drop_qpn) & 0xffffff;
+	netdev = mlx5i_pkey_get_netdev(rq->netdev, qpn);
+
+	/* No mapping present, cannot process SKB. This might happen if a child
+	 * interface is going down while having unprocessed CQEs on parent RQ
+	 */
+	if (unlikely(!netdev)) {
+		/* TODO: add drop counters support */
+		skb->dev = NULL;
+		pr_warn_once("Unable to map QPN %u to dev - dropping skb\n", qpn);
+		return;
+	}
+
 	g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3;
 	dgid = skb->data + MLX5_IB_GRH_DGID_OFFSET;
 	if ((!g) || dgid[0] != 0xff)
@@ -1186,8 +1214,9 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 	skb->ip_summed = CHECKSUM_COMPLETE;
 	skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
 
-	if (unlikely(mlx5e_rx_hw_stamp(tstamp)))
-		mlx5e_fill_hwstamp(tstamp, get_cqe_ts(cqe), skb_hwtstamps(skb));
+	if (unlikely(mlx5e_rx_hw_stamp(rq->tstamp)))
+		skb_hwtstamps(skb)->hwtstamp =
+				mlx5_timecounter_cyc2time(rq->clock, get_cqe_ts(cqe));
 
 	skb_record_rx_queue(skb, rq->ix);
 
@@ -1227,6 +1256,10 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 		goto wq_free_wqe;
 
 	mlx5i_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	if (unlikely(!skb->dev)) {
+		dev_kfree_skb_any(skb);
+		goto wq_free_wqe;
+	}
 	napi_gro_receive(rq->cq.napi, skb);
 
 wq_free_wqe: