1 files changed, 73 insertions, 69 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 278738873703..bcbde799ec69 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -261,7 +261,6 @@ struct header_ops {
                            unsigned short type, const void *daddr,
                            const void *saddr, unsigned int len);
         int     (*parse)(const struct sk_buff *skb, unsigned char *haddr);
-        int     (*rebuild)(struct sk_buff *skb);
         int     (*cache)(const struct neighbour *neigh, struct hh_cache *hh, __be16 type);
         void    (*cache_update)(struct hh_cache *hh,
                                 const struct net_device *dev,
@@ -588,6 +587,7 @@ struct netdev_queue {
 #ifdef CONFIG_BQL
         struct dql              dql;
 #endif
+        unsigned long           tx_maxrate;
 } ____cacheline_aligned_in_smp;
 
 static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
@@ -795,7 +795,10 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  * netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb,
  *                               struct net_device *dev);
  *      Called when a packet needs to be transmitted.
- *      Must return NETDEV_TX_OK , NETDEV_TX_BUSY.
+ *      Returns NETDEV_TX_OK.  Can return NETDEV_TX_BUSY, but you should stop
+ *      the queue before that can happen; it's for obsolete devices and weird
+ *      corner cases, but the stack really does a non-trivial amount
+ *      of useless work if you return NETDEV_TX_BUSY.
  *        (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)
  *      Required can not be NULL.
  *
@@ -875,6 +878,11 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  * int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state);
  * int (*ndo_set_vf_port)(struct net_device *dev, int vf,
  *                        struct nlattr *port[]);
+ *
+ *      Enable or disable the VF ability to query its RSS Redirection Table and
+ *      Hash Key. This is needed since on some devices VF share this information
+ *      with PF and querying it may adduce a theoretical security risk.
+ * int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting);
  * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb);
  * int (*ndo_setup_tc)(struct net_device *dev, u8 tc)
  *      Called to setup 'tc' number of traffic classes in the net device. This
@@ -1026,15 +1034,12 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *      be otherwise expressed by feature flags. The check is called with
  *      the set of features that the stack has calculated and it returns
  *      those the driver believes to be appropriate.
- *
- * int (*ndo_switch_parent_id_get)(struct net_device *dev,
- *                                 struct netdev_phys_item_id *psid);
- *      Called to get an ID of the switch chip this port is part of.
- *      If driver implements this, it indicates that it represents a port
- *      of a switch chip.
- * int (*ndo_switch_port_stp_update)(struct net_device *dev, u8 state);
- *      Called to notify switch device port of bridge port STP
- *      state change.
+ * int (*ndo_set_tx_maxrate)(struct net_device *dev,
+ *                           int queue_index, u32 maxrate);
+ *      Called when a user wants to set a max-rate limitation of specific
+ *      TX queue.
+ * int (*ndo_get_iflink)(const struct net_device *dev);
+ *      Called to get the iflink value of this device.
  */
 struct net_device_ops {
         int                     (*ndo_init)(struct net_device *dev);
@@ -1099,6 +1104,9 @@ struct net_device_ops {
                                                    struct nlattr *port[]);
         int                     (*ndo_get_vf_port)(struct net_device *dev,
                                                    int vf, struct sk_buff *skb);
+        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);
 #if IS_ENABLED(CONFIG_FCOE)
         int                     (*ndo_fcoe_enable)(struct net_device *dev);
@@ -1172,6 +1180,8 @@ struct net_device_ops {
                                                       bool new_carrier);
         int                     (*ndo_get_phys_port_id)(struct net_device *dev,
                                                         struct netdev_phys_item_id *ppid);
+        int                     (*ndo_get_phys_port_name)(struct net_device *dev,
+                                                          char *name, size_t len);
         void                    (*ndo_add_vxlan_port)(struct  net_device *dev,
                                                       sa_family_t sa_family,
                                                       __be16 port);
@@ -1191,12 +1201,10 @@ struct net_device_ops {
         netdev_features_t       (*ndo_features_check) (struct sk_buff *skb,
                                                        struct net_device *dev,
                                                        netdev_features_t features);
-#ifdef CONFIG_NET_SWITCHDEV
-        int                     (*ndo_switch_parent_id_get)(struct net_device *dev,
-                                                            struct netdev_phys_item_id *psid);
-        int                     (*ndo_switch_port_stp_update)(struct net_device *dev,
-                                                              u8 state);
-#endif
+        int                     (*ndo_set_tx_maxrate)(struct net_device *dev,
+                                                      int queue_index,
+                                                      u32 maxrate);
+        int                     (*ndo_get_iflink)(const struct net_device *dev);
 };
 
 /**
@@ -1305,6 +1313,8 @@ enum netdev_priv_flags {
  *      @base_addr:     Device I/O address
  *      @irq:           Device IRQ number
  *
+ *      @carrier_changes:       Stats to monitor carrier on<->off transitions
+ *
  *      @state:         Generic network queuing layer state, see netdev_state_t
  *      @dev_list:      The global list of network devices
  *      @napi_list:     List entry, that is used for polling napi devices
@@ -1328,7 +1338,7 @@ enum netdev_priv_flags {
  *      @mpls_features: Mask of features inheritable by MPLS
  *
  *      @ifindex:       interface index
- *      @iflink:        unique device identifier
+ *      @group:         The group, that the device belongs to
  *
  *      @stats:         Statistics struct, which was left as a legacy, use
  *                      rtnl_link_stats64 instead
@@ -1338,8 +1348,6 @@ enum netdev_priv_flags {
  *      @tx_dropped:    Dropped packets by core network,
  *                      do not use this in drivers
  *
- *      @carrier_changes:       Stats to monitor carrier on<->off transitions
- *
  *      @wireless_handlers:     List of functions to handle Wireless Extensions,
  *                              instead of ioctl,
  *                              see <net/iw_handler.h> for details.
@@ -1348,8 +1356,7 @@ enum netdev_priv_flags {
  *      @netdev_ops:    Includes several pointers to callbacks,
  *                      if one wants to override the ndo_*() functions
  *      @ethtool_ops:   Management operations
- *      @fwd_ops:       Management operations
- *      @header_ops:    Includes callbacks for creating,parsing,rebuilding,etc
+ *      @header_ops:    Includes callbacks for creating,parsing,caching,etc
  *                      of Layer 2 headers.
  *
  *      @flags:         Interface flags (a la BSD)
@@ -1383,14 +1390,14 @@ enum netdev_priv_flags {
  *      @dev_port:              Used to differentiate devices that share
  *                              the same function
  *      @addr_list_lock:        XXX: need comments on this one
- *      @uc:                    unicast mac addresses
- *      @mc:                    multicast mac addresses
- *      @dev_addrs:             list of device hw addresses
- *      @queues_kset:           Group of all Kobjects in the Tx and RX queues
  *      @uc_promisc:            Counter, that indicates, that promiscuous mode
  *                              has been enabled due to the need to listen to
  *                              additional unicast addresses in a device that
  *                              does not implement ndo_set_rx_mode()
+ *      @uc:                    unicast mac addresses
+ *      @mc:                    multicast mac addresses
+ *      @dev_addrs:             list of device hw addresses
+ *      @queues_kset:           Group of all Kobjects in the Tx and RX queues
  *      @promiscuity:           Number of times, the NIC is told to work in
  *                              Promiscuous mode, if it becomes 0 the NIC will
  *                              exit from working in Promiscuous mode
@@ -1420,6 +1427,12 @@ enum netdev_priv_flags {
  *      @ingress_queue:         XXX: need comments on this one
  *      @broadcast:             hw bcast address
  *
+ *      @rx_cpu_rmap:   CPU reverse-mapping for RX completion interrupts,
+ *                      indexed by RX queue number. Assigned by driver.
+ *                      This must only be set if the ndo_rx_flow_steer
+ *                      operation is defined
+ *      @index_hlist:           Device index hash chain
+ *
  *      @_tx:                   Array of TX queues
  *      @num_tx_queues:         Number of TX queues allocated at alloc_netdev_mq() time
  *      @real_num_tx_queues:    Number of TX queues currently active in device
@@ -1429,11 +1442,6 @@ enum netdev_priv_flags {
  *
  *      @xps_maps:      XXX: need comments on this one
  *
- *      @rx_cpu_rmap:   CPU reverse-mapping for RX completion interrupts,
- *                      indexed by RX queue number. Assigned by driver.
- *                      This must only be set if the ndo_rx_flow_steer
- *                      operation is defined
- *
  *      @trans_start:           Time (in jiffies) of last Tx
  *      @watchdog_timeo:        Represents the timeout that is used by
  *                              the watchdog ( see dev_watchdog() )
@@ -1441,7 +1449,6 @@ enum netdev_priv_flags {
  *
  *      @pcpu_refcnt:           Number of references to this device
  *      @todo_list:             Delayed register/unregister
- *      @index_hlist:           Device index hash chain
  *      @link_watch_list:       XXX: need comments on this one
  *
  *      @reg_state:             Register/unregister state machine
@@ -1489,7 +1496,6 @@ enum netdev_priv_flags {
  *
  *      @qdisc_tx_busylock:     XXX: need comments on this one
  *
- *      @group:         The group, that the device belongs to
  *      @pm_qos_req:    Power Management QoS object
  *
  *      FIXME: cleanup struct net_device such that network protocol info
@@ -1509,6 +1515,8 @@ struct net_device {
         unsigned long           base_addr;
         int                     irq;
 
+        atomic_t                carrier_changes;
+
         /*
          *      Some hardware also needs these fields (state,dev_list,
          *      napi_list,unreg_list,close_list) but they are not
@@ -1542,22 +1550,22 @@ struct net_device {
         netdev_features_t       mpls_features;
 
         int                     ifindex;
-        int                     iflink;
+        int                     group;
 
         struct net_device_stats stats;
 
         atomic_long_t           rx_dropped;
         atomic_long_t           tx_dropped;
 
-        atomic_t                carrier_changes;
-
 #ifdef CONFIG_WIRELESS_EXT
         const struct iw_handler_def *   wireless_handlers;
         struct iw_public_data * wireless_data;
 #endif
         const struct net_device_ops *netdev_ops;
         const struct ethtool_ops *ethtool_ops;
-        const struct forwarding_accel_ops *fwd_ops;
+#ifdef CONFIG_NET_SWITCHDEV
+        const struct swdev_ops *swdev_ops;
+#endif
 
         const struct header_ops *header_ops;
 
@@ -1588,6 +1596,8 @@ struct net_device {
         unsigned short          dev_id;
         unsigned short          dev_port;
         spinlock_t              addr_list_lock;
+        unsigned char           name_assign_type;
+        bool                    uc_promisc;
         struct netdev_hw_addr_list      uc;
         struct netdev_hw_addr_list      mc;
         struct netdev_hw_addr_list      dev_addrs;
@@ -1595,10 +1605,6 @@ struct net_device {
 #ifdef CONFIG_SYSFS
         struct kset             *queues_kset;
 #endif
-
-        unsigned char           name_assign_type;
-
-        bool                    uc_promisc;
         unsigned int            promiscuity;
         unsigned int            allmulti;
 
@@ -1645,7 +1651,10 @@ struct net_device {
 
         struct netdev_queue __rcu *ingress_queue;
         unsigned char           broadcast[MAX_ADDR_LEN];
-
+#ifdef CONFIG_RFS_ACCEL
+        struct cpu_rmap         *rx_cpu_rmap;
+#endif
+        struct hlist_node       index_hlist;
 
 /*
  * Cache lines mostly used on transmit path
@@ -1656,13 +1665,11 @@ struct net_device {
         struct Qdisc            *qdisc;
         unsigned long           tx_queue_len;
         spinlock_t              tx_global_lock;
+        int                     watchdog_timeo;
 
 #ifdef CONFIG_XPS
         struct xps_dev_maps __rcu *xps_maps;
 #endif
-#ifdef CONFIG_RFS_ACCEL
-        struct cpu_rmap         *rx_cpu_rmap;
-#endif
 
         /* These may be needed for future network-power-down code. */
 
@@ -1672,13 +1679,11 @@ struct net_device {
          */
         unsigned long           trans_start;
 
-        int                     watchdog_timeo;
         struct timer_list       watchdog_timer;
 
         int __percpu            *pcpu_refcnt;
         struct list_head        todo_list;
 
-        struct hlist_node       index_hlist;
         struct list_head        link_watch_list;
 
         enum { NETREG_UNINITIALIZED=0,
@@ -1702,9 +1707,7 @@ struct net_device {
         struct netpoll_info __rcu       *npinfo;
 #endif
 
-#ifdef CONFIG_NET_NS
-        struct net              *nd_net;
-#endif
+        possible_net_t                  nd_net;
 
         /* mid-layer private */
         union {
@@ -1745,8 +1748,6 @@ struct net_device {
 #endif
         struct phy_device *phydev;
         struct lock_class_key *qdisc_tx_busylock;
-        int group;
-        struct pm_qos_request   pm_qos_req;
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
@@ -1844,10 +1845,7 @@ struct net *dev_net(const struct net_device *dev)
 static inline
 void dev_net_set(struct net_device *dev, struct net *net)
 {
-#ifdef CONFIG_NET_NS
-        release_net(dev->nd_net);
-        dev->nd_net = hold_net(net);
-#endif
+        write_pnet(&dev->nd_net, net);
 }
 
 static inline bool netdev_uses_dsa(struct net_device *dev)
@@ -2159,6 +2157,7 @@ void __dev_remove_pack(struct packet_type *pt);
 void dev_add_offload(struct packet_offload *po);
 void dev_remove_offload(struct packet_offload *po);
 
+int dev_get_iflink(const struct net_device *dev);
 struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,
                                       unsigned short mask);
 struct net_device *dev_get_by_name(struct net *net, const char *name);
@@ -2167,9 +2166,14 @@ struct net_device *__dev_get_by_name(struct net *net, const char *name);
 int dev_alloc_name(struct net_device *dev, const char *name);
 int dev_open(struct net_device *dev);
 int dev_close(struct net_device *dev);
+int dev_close_many(struct list_head *head, bool unlink);
 void dev_disable_lro(struct net_device *dev);
-int dev_loopback_xmit(struct sk_buff *newskb);
-int dev_queue_xmit(struct sk_buff *skb);
+int dev_loopback_xmit(struct sock *sk, struct sk_buff *newskb);
+int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb);
+static inline int dev_queue_xmit(struct sk_buff *skb)
+{
+        return dev_queue_xmit_sk(skb->sk, skb);
+}
 int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv);
 int register_netdevice(struct net_device *dev);
 void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
@@ -2409,15 +2413,6 @@ static inline int dev_parse_header(const struct sk_buff *skb,
         return dev->header_ops->parse(skb, haddr);
 }
 
-static inline int dev_rebuild_header(struct sk_buff *skb)
-{
-        const struct net_device *dev = skb->dev;
-
-        if (!dev->header_ops || !dev->header_ops->rebuild)
-                return 0;
-        return dev->header_ops->rebuild(skb);
-}
-
 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)
@@ -2939,7 +2934,11 @@ static inline void dev_consume_skb_any(struct sk_buff *skb)
 
 int netif_rx(struct sk_buff *skb);
 int netif_rx_ni(struct sk_buff *skb);
-int netif_receive_skb(struct sk_buff *skb);
+int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb);
+static inline int netif_receive_skb(struct sk_buff *skb)
+{
+        return netif_receive_skb_sk(skb->sk, skb);
+}
 gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
 void napi_gro_flush(struct napi_struct *napi, bool flush_old);
 struct sk_buff *napi_get_frags(struct napi_struct *napi);
@@ -2975,6 +2974,8 @@ int dev_set_mac_address(struct net_device *, struct sockaddr *);
 int dev_change_carrier(struct net_device *, bool new_carrier);
 int dev_get_phys_port_id(struct net_device *dev,
                          struct netdev_phys_item_id *ppid);
+int dev_get_phys_port_name(struct net_device *dev,
+                           char *name, size_t len);
 struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev);
 struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
                                     struct netdev_queue *txq, int *ret);
@@ -3679,6 +3680,9 @@ void netdev_change_features(struct net_device *dev);
 void netif_stacked_transfer_operstate(const struct net_device *rootdev,
                                         struct net_device *dev);
 
+netdev_features_t passthru_features_check(struct sk_buff *skb,
+                                          struct net_device *dev,
+                                          netdev_features_t features);
 netdev_features_t netif_skb_features(struct sk_buff *skb);
 
 static inline bool net_gso_ok(netdev_features_t features, int gso_type)
@@ -3709,7 +3713,7 @@ static inline bool skb_gso_ok(struct sk_buff *skb, netdev_features_t features)
                (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST));
 }
 
-static inline bool netif_needs_gso(struct net_device *dev, struct sk_buff *skb,
+static inline bool netif_needs_gso(struct sk_buff *skb,
                                    netdev_features_t features)
 {
         return skb_is_gso(skb) && (!skb_gso_ok(skb, features) ||