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

Pull networking updates from David Miller:
 "Highlights:

   1) Support more Realtek wireless chips, from Jes Sorenson.

   2) New BPF types for per-cpu hash and arrap maps, from Alexei
      Starovoitov.

   3) Make several TCP sysctls per-namespace, from Nikolay Borisov.

   4) Allow the use of SO_REUSEPORT in order to do per-thread processing
   of incoming TCP/UDP connections.  The muxing can be done using a
   BPF program which hashes the incoming packet.  From Craig Gallek.

   5) Add a multiplexer for TCP streams, to provide a messaged based
      interface.  BPF programs can be used to determine the message
      boundaries.  From Tom Herbert.

   6) Add 802.1AE MACSEC support, from Sabrina Dubroca.

   7) Avoid factorial complexity when taking down an inetdev interface
      with lots of configured addresses.  We were doing things like
      traversing the entire address less for each address removed, and
      flushing the entire netfilter conntrack table for every address as
      well.

   8) Add and use SKB bulk free infrastructure, from Jesper Brouer.

   9) Allow offloading u32 classifiers to hardware, and implement for
      ixgbe, from John Fastabend.

  10) Allow configuring IRQ coalescing parameters on a per-queue basis,
      from Kan Liang.

  11) Extend ethtool so that larger link mode masks can be supported.
      From David Decotigny.

  12) Introduce devlink, which can be used to configure port link types
      (ethernet vs Infiniband, etc.), port splitting, and switch device
      level attributes as a whole.  From Jiri Pirko.

  13) Hardware offload support for flower classifiers, from Amir Vadai.

  14) Add "Local Checksum Offload".  Basically, for a tunneled packet
      the checksum of the outer header is 'constant' (because with the
      checksum field filled into the inner protocol header, the payload
      of the outer frame checksums to 'zero'), and we can take advantage
      of that in various ways.  From Edward Cree"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits)
  bonding: fix bond_get_stats()
  net: bcmgenet: fix dma api length mismatch
  net/mlx4_core: Fix backward compatibility on VFs
  phy: mdio-thunder: Fix some Kconfig typos
  lan78xx: add ndo_get_stats64
  lan78xx: handle statistics counter rollover
  RDS: TCP: Remove unused constant
  RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket
  net: smc911x: convert pxa dma to dmaengine
  team: remove duplicate set of flag IFF_MULTICAST
  bonding: remove duplicate set of flag IFF_MULTICAST
  net: fix a comment typo
  ethernet: micrel: fix some error codes
  ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it
  bpf, dst: add and use dst_tclassid helper
  bpf: make skb->tc_classid also readable
  net: mvneta: bm: clarify dependencies
  cls_bpf: reset class and reuse major in da
  ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c
  ldmvsw: Add ldmvsw.c driver code
  ...

1 files changed, 97 insertions, 4 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5440b7b705eb..be693b34662f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -51,6 +51,7 @@
 #include <linux/neighbour.h>
 #include <uapi/linux/netdevice.h>
 #include <uapi/linux/if_bonding.h>
+#include <uapi/linux/pkt_cls.h>
 
 struct netpoll_info;
 struct device;
@@ -267,6 +268,7 @@ struct header_ops {
         void    (*cache_update)(struct hh_cache *hh,
                                 const struct net_device *dev,
                                 const unsigned char *haddr);
+        bool    (*validate)(const char *ll_header, unsigned int len);
 };
 
 /* These flag bits are private to the generic network queueing
@@ -778,6 +780,27 @@ static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a,
 typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
                                        struct sk_buff *skb);
 
+/* These structures hold the attributes of qdisc and classifiers
+ * that are being passed to the netdevice through the setup_tc op.
+ */
+enum {
+        TC_SETUP_MQPRIO,
+        TC_SETUP_CLSU32,
+        TC_SETUP_CLSFLOWER,
+};
+
+struct tc_cls_u32_offload;
+
+struct tc_to_netdev {
+        unsigned int type;
+        union {
+                u8 tc;
+                struct tc_cls_u32_offload *cls_u32;
+                struct tc_cls_flower_offload *cls_flower;
+        };
+};
+
+
 /*
  * This structure defines the management hooks for network devices.
  * The following hooks can be defined; unless noted otherwise, they are
@@ -1073,6 +1096,12 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *      This function is used to get egress tunnel information for given skb.
  *      This is useful for retrieving outer tunnel header parameters while
  *      sampling packet.
+ * void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom);
+ *      This function is used to specify the headroom that the skb must
+ *      consider when allocation skb during packet reception. Setting
+ *      appropriate rx headroom value allows avoiding skb head copy on
+ *      forward. Setting a negative value reset the rx headroom to the
+ *      default value.
  *
  */
 struct net_device_ops {
@@ -1150,7 +1179,10 @@ struct net_device_ops {
         int                     (*ndo_set_vf_rss_query_en)(
                                                    struct net_device *dev,
                                                    int vf, bool setting);
-        int                     (*ndo_setup_tc)(struct net_device *dev, u8 tc);
+        int                     (*ndo_setup_tc)(struct net_device *dev,
+                                                u32 handle,
+                                                __be16 protocol,
+                                                struct tc_to_netdev *tc);
 #if IS_ENABLED(CONFIG_FCOE)
         int                     (*ndo_fcoe_enable)(struct net_device *dev);
         int                     (*ndo_fcoe_disable)(struct net_device *dev);
@@ -1255,6 +1287,8 @@ struct net_device_ops {
                                                          bool proto_down);
         int                     (*ndo_fill_metadata_dst)(struct net_device *dev,
                                                        struct sk_buff *skb);
+        void                    (*ndo_set_rx_headroom)(struct net_device *dev,
+                                                       int needed_headroom);
 };
 
 /**
@@ -1291,6 +1325,10 @@ struct net_device_ops {
  * @IFF_OPENVSWITCH: device is a Open vSwitch master
  * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device
  * @IFF_TEAM: device is a team device
+ * @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured
+ * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external
+ *      entity (i.e. the master device for bridged veth)
+ * @IFF_MACSEC: device is a MACsec device
  */
 enum netdev_priv_flags {
         IFF_802_1Q_VLAN                 = 1<<0,
@@ -1318,6 +1356,9 @@ enum netdev_priv_flags {
         IFF_OPENVSWITCH                 = 1<<22,
         IFF_L3MDEV_SLAVE                = 1<<23,
         IFF_TEAM                        = 1<<24,
+        IFF_RXFH_CONFIGURED             = 1<<25,
+        IFF_PHONY_HEADROOM              = 1<<26,
+        IFF_MACSEC                      = 1<<27,
 };
 
 #define IFF_802_1Q_VLAN                 IFF_802_1Q_VLAN
@@ -1345,6 +1386,8 @@ enum netdev_priv_flags {
 #define IFF_OPENVSWITCH                 IFF_OPENVSWITCH
 #define IFF_L3MDEV_SLAVE                IFF_L3MDEV_SLAVE
 #define IFF_TEAM                        IFF_TEAM
+#define IFF_RXFH_CONFIGURED             IFF_RXFH_CONFIGURED
+#define IFF_MACSEC                      IFF_MACSEC
 
 /**
  *      struct net_device - The DEVICE structure.
@@ -1397,6 +1440,8 @@ enum netdev_priv_flags {
  *                      do not use this in drivers
  *      @tx_dropped:    Dropped packets by core network,
  *                      do not use this in drivers
+ *      @rx_nohandler:  nohandler dropped packets by core network on
+ *                      inactive devices, do not use this in drivers
  *
  *      @wireless_handlers:     List of functions to handle Wireless Extensions,
  *                              instead of ioctl,
@@ -1420,8 +1465,7 @@ enum netdev_priv_flags {
  *      @dma:           DMA channel
  *      @mtu:           Interface MTU value
  *      @type:          Interface hardware type
- *      @hard_header_len: Hardware header length, which means that this is the
- *                        minimum size of a packet.
+ *      @hard_header_len: Maximum hardware header length.
  *
  *      @needed_headroom: Extra headroom the hardware may need, but not in all
  *                        cases can this be guaranteed
@@ -1611,6 +1655,7 @@ struct net_device {
 
         atomic_long_t           rx_dropped;
         atomic_long_t           tx_dropped;
+        atomic_long_t           rx_nohandler;
 
 #ifdef CONFIG_WIRELESS_EXT
         const struct iw_handler_def *   wireless_handlers;
@@ -1908,6 +1953,26 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
                                     struct sk_buff *skb,
                                     void *accel_priv);
 
+/* returns the headroom that the master device needs to take in account
+ * when forwarding to this dev
+ */
+static inline unsigned netdev_get_fwd_headroom(struct net_device *dev)
+{
+        return dev->priv_flags & IFF_PHONY_HEADROOM ? 0 : dev->needed_headroom;
+}
+
+static inline void netdev_set_rx_headroom(struct net_device *dev, int new_hr)
+{
+        if (dev->netdev_ops->ndo_set_rx_headroom)
+                dev->netdev_ops->ndo_set_rx_headroom(dev, new_hr);
+}
+
+/* set the device rx headroom to the dev's default */
+static inline void netdev_reset_rx_headroom(struct net_device *dev)
+{
+        netdev_set_rx_headroom(dev, -1);
+}
+
 /*
  * Net namespace inlines
  */
@@ -2627,6 +2692,24 @@ static inline int dev_parse_header(const struct sk_buff *skb,
         return dev->header_ops->parse(skb, haddr);
 }
 
+/* ll_header must have at least hard_header_len allocated */
+static inline bool dev_validate_header(const struct net_device *dev,
+                                       char *ll_header, int len)
+{
+        if (likely(len >= dev->hard_header_len))
+                return true;
+
+        if (capable(CAP_SYS_RAWIO)) {
+                memset(ll_header + len, 0, dev->hard_header_len - len);
+                return true;
+        }
+
+        if (dev->header_ops && dev->header_ops->validate)
+                return dev->header_ops->validate(ll_header, len);
+
+        return false;
+}
+
 typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
 int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
 static inline int unregister_gifconf(unsigned int family)
@@ -3741,7 +3824,7 @@ void netdev_lower_state_changed(struct net_device *lower_dev,
 
 /* RSS keys are 40 or 52 bytes long */
 #define NETDEV_RSS_KEY_LEN 52
-extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN];
+extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly;
 void netdev_rss_key_fill(void *buffer, size_t len);
 
 int dev_get_nest_level(struct net_device *dev,
@@ -3965,6 +4048,11 @@ static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol,
         skb->mac_len = mac_len;
 }
 
+static inline bool netif_is_macsec(const struct net_device *dev)
+{
+        return dev->priv_flags & IFF_MACSEC;
+}
+
 static inline bool netif_is_macvlan(const struct net_device *dev)
 {
         return dev->priv_flags & IFF_MACVLAN;
@@ -4045,6 +4133,11 @@ static inline bool netif_is_lag_port(const struct net_device *dev)
         return netif_is_bond_slave(dev) || netif_is_team_port(dev);
 }
 
+static inline bool netif_is_rxfh_configured(const struct net_device *dev)
+{
+        return dev->priv_flags & IFF_RXFH_CONFIGURED;
+}
+
 /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */
 static inline void netif_keep_dst(struct net_device *dev)
 {