diff options
Diffstat (limited to 'kernel/include/linux/netdevice.h')
| -rw-r--r-- | kernel/include/linux/netdevice.h | 269 |
1 files changed, 184 insertions, 85 deletions
diff --git a/kernel/include/linux/netdevice.h b/kernel/include/linux/netdevice.h index 7a289e802..c0e12f7f0 100644 --- a/kernel/include/linux/netdevice.h +++ b/kernel/include/linux/netdevice.h @@ -507,6 +507,7 @@ static inline void napi_enable(struct napi_struct *n) BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); smp_mb__before_atomic(); clear_bit(NAPI_STATE_SCHED, &n->state); + clear_bit(NAPI_STATE_NPSVC, &n->state); } #ifdef CONFIG_SMP @@ -717,8 +718,8 @@ struct xps_map { u16 queues[0]; }; #define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + ((_num) * sizeof(u16))) -#define XPS_MIN_MAP_ALLOC ((L1_CACHE_BYTES - sizeof(struct xps_map)) \ - / sizeof(u16)) +#define XPS_MIN_MAP_ALLOC ((L1_CACHE_ALIGN(offsetof(struct xps_map, queues[1])) \ + - sizeof(struct xps_map)) / sizeof(u16)) /* * This structure holds all XPS maps for device. Maps are indexed by CPU. @@ -766,6 +767,13 @@ struct netdev_phys_item_id { unsigned char id_len; }; +static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, + struct netdev_phys_item_id *b) +{ + return a->id_len == b->id_len && + memcmp(a->id, b->id, a->id_len) == 0; +} + typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); @@ -873,6 +881,7 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, * int max_tx_rate); * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); + * int (*ndo_set_vf_trust)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_config)(struct net_device *dev, * int vf, struct ifla_vf_info *ivf); * int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state); @@ -1041,6 +1050,16 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * TX queue. * int (*ndo_get_iflink)(const struct net_device *dev); * Called to get the iflink value of this device. + * void (*ndo_change_proto_down)(struct net_device *dev, + * bool proto_down); + * This function is used to pass protocol port error state information + * to the switch driver. The switch driver can react to the proto_down + * by doing a phys down on the associated switch port. + * int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); + * This function is used to get egress tunnel information for given skb. + * This is useful for retrieving outer tunnel header parameters while + * sampling packet. + * */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1095,11 +1114,17 @@ struct net_device_ops { int max_tx_rate); int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); + int (*ndo_set_vf_trust)(struct net_device *dev, + int vf, bool setting); int (*ndo_get_vf_config)(struct net_device *dev, int vf, struct ifla_vf_info *ivf); int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state); + int (*ndo_get_vf_stats)(struct net_device *dev, + int vf, + struct ifla_vf_stats + *vf_stats); int (*ndo_set_vf_port)(struct net_device *dev, int vf, struct nlattr *port[]); @@ -1207,6 +1232,10 @@ struct net_device_ops { int queue_index, u32 maxrate); int (*ndo_get_iflink)(const struct net_device *dev); + int (*ndo_change_proto_down)(struct net_device *dev, + bool proto_down); + int (*ndo_fill_metadata_dst)(struct net_device *dev, + struct sk_buff *skb); }; /** @@ -1221,13 +1250,8 @@ struct net_device_ops { * * @IFF_802_1Q_VLAN: 802.1Q VLAN device * @IFF_EBRIDGE: Ethernet bridging device - * @IFF_SLAVE_INACTIVE: bonding slave not the curr. active - * @IFF_MASTER_8023AD: bonding master, 802.3ad - * @IFF_MASTER_ALB: bonding master, balance-alb * @IFF_BONDING: bonding master or slave - * @IFF_SLAVE_NEEDARP: need ARPs for validation * @IFF_ISATAP: ISATAP interface (RFC4214) - * @IFF_MASTER_ARPMON: bonding master, ARP mon in use * @IFF_WAN_HDLC: WAN HDLC device * @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to * release skb->dst @@ -1243,44 +1267,42 @@ struct net_device_ops { * @IFF_LIVE_ADDR_CHANGE: device supports hardware address * change when it's running * @IFF_MACVLAN: Macvlan device + * @IFF_L3MDEV_MASTER: device is an L3 master device + * @IFF_NO_QUEUE: device can run without qdisc attached + * @IFF_OPENVSWITCH: device is a Open vSwitch master + * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, IFF_EBRIDGE = 1<<1, - IFF_SLAVE_INACTIVE = 1<<2, - IFF_MASTER_8023AD = 1<<3, - IFF_MASTER_ALB = 1<<4, - IFF_BONDING = 1<<5, - IFF_SLAVE_NEEDARP = 1<<6, - IFF_ISATAP = 1<<7, - IFF_MASTER_ARPMON = 1<<8, - IFF_WAN_HDLC = 1<<9, - IFF_XMIT_DST_RELEASE = 1<<10, - IFF_DONT_BRIDGE = 1<<11, - IFF_DISABLE_NETPOLL = 1<<12, - IFF_MACVLAN_PORT = 1<<13, - IFF_BRIDGE_PORT = 1<<14, - IFF_OVS_DATAPATH = 1<<15, - IFF_TX_SKB_SHARING = 1<<16, - IFF_UNICAST_FLT = 1<<17, - IFF_TEAM_PORT = 1<<18, - IFF_SUPP_NOFCS = 1<<19, - IFF_LIVE_ADDR_CHANGE = 1<<20, - IFF_MACVLAN = 1<<21, - IFF_XMIT_DST_RELEASE_PERM = 1<<22, - IFF_IPVLAN_MASTER = 1<<23, - IFF_IPVLAN_SLAVE = 1<<24, + IFF_BONDING = 1<<2, + IFF_ISATAP = 1<<3, + IFF_WAN_HDLC = 1<<4, + IFF_XMIT_DST_RELEASE = 1<<5, + IFF_DONT_BRIDGE = 1<<6, + IFF_DISABLE_NETPOLL = 1<<7, + IFF_MACVLAN_PORT = 1<<8, + IFF_BRIDGE_PORT = 1<<9, + IFF_OVS_DATAPATH = 1<<10, + IFF_TX_SKB_SHARING = 1<<11, + IFF_UNICAST_FLT = 1<<12, + IFF_TEAM_PORT = 1<<13, + IFF_SUPP_NOFCS = 1<<14, + IFF_LIVE_ADDR_CHANGE = 1<<15, + IFF_MACVLAN = 1<<16, + IFF_XMIT_DST_RELEASE_PERM = 1<<17, + IFF_IPVLAN_MASTER = 1<<18, + IFF_IPVLAN_SLAVE = 1<<19, + IFF_L3MDEV_MASTER = 1<<20, + IFF_NO_QUEUE = 1<<21, + IFF_OPENVSWITCH = 1<<22, + IFF_L3MDEV_SLAVE = 1<<23, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN #define IFF_EBRIDGE IFF_EBRIDGE -#define IFF_SLAVE_INACTIVE IFF_SLAVE_INACTIVE -#define IFF_MASTER_8023AD IFF_MASTER_8023AD -#define IFF_MASTER_ALB IFF_MASTER_ALB #define IFF_BONDING IFF_BONDING -#define IFF_SLAVE_NEEDARP IFF_SLAVE_NEEDARP #define IFF_ISATAP IFF_ISATAP -#define IFF_MASTER_ARPMON IFF_MASTER_ARPMON #define IFF_WAN_HDLC IFF_WAN_HDLC #define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE #define IFF_DONT_BRIDGE IFF_DONT_BRIDGE @@ -1297,6 +1319,10 @@ enum netdev_priv_flags { #define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM #define IFF_IPVLAN_MASTER IFF_IPVLAN_MASTER #define IFF_IPVLAN_SLAVE IFF_IPVLAN_SLAVE +#define IFF_L3MDEV_MASTER IFF_L3MDEV_MASTER +#define IFF_NO_QUEUE IFF_NO_QUEUE +#define IFF_OPENVSWITCH IFF_OPENVSWITCH +#define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE /** * struct net_device - The DEVICE structure. @@ -1372,7 +1398,8 @@ enum netdev_priv_flags { * @dma: DMA channel * @mtu: Interface MTU value * @type: Interface hardware type - * @hard_header_len: Hardware header length + * @hard_header_len: Hardware header length, which means that this is the + * minimum size of a packet. * * @needed_headroom: Extra headroom the hardware may need, but not in all * cases can this be guaranteed @@ -1444,6 +1471,8 @@ enum netdev_priv_flags { * * @xps_maps: XXX: need comments on this one * + * @offload_fwd_mark: Offload device fwding mark + * * @trans_start: Time (in jiffies) of last Tx * @watchdog_timeo: Represents the timeout that is used by * the watchdog ( see dev_watchdog() ) @@ -1498,6 +1527,10 @@ enum netdev_priv_flags { * * @qdisc_tx_busylock: XXX: need comments on this one * + * @proto_down: protocol port state information can be sent to the + * switch driver and used to set the phys state of the + * switch port. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -1564,7 +1597,10 @@ struct net_device { const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; #ifdef CONFIG_NET_SWITCHDEV - const struct swdev_ops *swdev_ops; + const struct switchdev_ops *switchdev_ops; +#endif +#ifdef CONFIG_NET_L3_MASTER_DEV + const struct l3mdev_ops *l3mdev_ops; #endif const struct header_ops *header_ops; @@ -1652,7 +1688,14 @@ struct net_device { rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; +#ifdef CONFIG_NET_CLS_ACT + struct tcf_proto __rcu *ingress_cl_list; +#endif struct netdev_queue __rcu *ingress_queue; +#ifdef CONFIG_NETFILTER_INGRESS + struct list_head nf_hooks_ingress; +#endif + unsigned char broadcast[MAX_ADDR_LEN]; #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rx_cpu_rmap; @@ -1674,6 +1717,10 @@ struct net_device { struct xps_dev_maps __rcu *xps_maps; #endif +#ifdef CONFIG_NET_SWITCHDEV + u32 offload_fwd_mark; +#endif + /* These may be needed for future network-power-down code. */ /* @@ -1751,6 +1798,7 @@ struct net_device { #endif struct phy_device *phydev; struct lock_class_key *qdisc_tx_busylock; + bool proto_down; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -1990,6 +2038,7 @@ struct offload_callbacks { struct packet_offload { __be16 type; /* This is really htons(ether_type). */ + u16 priority; struct offload_callbacks callbacks; struct list_head list; }; @@ -2020,20 +2069,23 @@ struct pcpu_sw_netstats { struct u64_stats_sync syncp; }; -#define netdev_alloc_pcpu_stats(type) \ -({ \ - typeof(type) __percpu *pcpu_stats = alloc_percpu(type); \ - if (pcpu_stats) { \ - int __cpu; \ - for_each_possible_cpu(__cpu) { \ - typeof(type) *stat; \ - stat = per_cpu_ptr(pcpu_stats, __cpu); \ - u64_stats_init(&stat->syncp); \ - } \ - } \ - pcpu_stats; \ +#define __netdev_alloc_pcpu_stats(type, gfp) \ +({ \ + typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ + if (pcpu_stats) { \ + int __cpu; \ + for_each_possible_cpu(__cpu) { \ + typeof(type) *stat; \ + stat = per_cpu_ptr(pcpu_stats, __cpu); \ + u64_stats_init(&stat->syncp); \ + } \ + } \ + pcpu_stats; \ }) +#define netdev_alloc_pcpu_stats(type) \ + __netdev_alloc_pcpu_stats(type, GFP_KERNEL) + #include <linux/notifier.h> /* netdevice notifier chain. Please remember to update the rtnetlink @@ -2068,6 +2120,7 @@ struct pcpu_sw_netstats { #define NETDEV_PRECHANGEMTU 0x0017 /* notify before mtu change happened */ #define NETDEV_CHANGEINFODATA 0x0018 #define NETDEV_BONDING_INFO 0x0019 +#define NETDEV_PRECHANGEUPPER 0x001A int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); @@ -2081,6 +2134,13 @@ struct netdev_notifier_change_info { unsigned int flags_changed; }; +struct netdev_notifier_changeupper_info { + struct netdev_notifier_info info; /* must be first */ + struct net_device *upper_dev; /* new upper dev */ + bool master; /* is upper dev master */ + bool linking; /* is the nofication for link or unlink */ +}; + static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { @@ -2161,6 +2221,7 @@ 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); +int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb); 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); @@ -2171,12 +2232,8 @@ 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 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_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); +int dev_queue_xmit(struct sk_buff *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); @@ -2192,11 +2249,20 @@ void netdev_freemem(struct net_device *dev); void synchronize_net(void); int init_dummy_netdev(struct net_device *dev); +#ifdef CONFIG_PREEMPT_RT_FULL +static inline int dev_recursion_level(void) +{ + return current->xmit_recursion; +} + +#else + DECLARE_PER_CPU(int, xmit_recursion); static inline int dev_recursion_level(void) { return this_cpu_read(xmit_recursion); } +#endif struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); @@ -2265,8 +2331,7 @@ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb); static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb) { - return (NAPI_GRO_CB(skb)->gro_remcsum_start - skb_headroom(skb) == - skb_gro_offset(skb)); + return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb)); } static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, @@ -2362,37 +2427,58 @@ static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) grc->delta = 0; } -static inline void skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, - int start, int offset, - struct gro_remcsum *grc, - bool nopartial) +static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, + unsigned int off, size_t hdrlen, + int start, int offset, + struct gro_remcsum *grc, + bool nopartial) { __wsum delta; + size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); if (!nopartial) { - NAPI_GRO_CB(skb)->gro_remcsum_start = - ((unsigned char *)ptr + start) - skb->head; - return; + NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start; + return ptr; + } + + ptr = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, off + plen)) { + ptr = skb_gro_header_slow(skb, off + plen, off); + if (!ptr) + return NULL; } - delta = remcsum_adjust(ptr, NAPI_GRO_CB(skb)->csum, start, offset); + delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum, + start, offset); /* Adjust skb->csum since we changed the packet */ NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); - grc->offset = (ptr + offset) - (void *)skb->head; + grc->offset = off + hdrlen + offset; grc->delta = delta; + + return ptr; } static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, struct gro_remcsum *grc) { + void *ptr; + size_t plen = grc->offset + sizeof(u16); + if (!grc->delta) return; - remcsum_unadjust((__sum16 *)(skb->head + grc->offset), grc->delta); + ptr = skb_gro_header_fast(skb, grc->offset); + if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) { + ptr = skb_gro_header_slow(skb, plen, grc->offset); + if (!ptr) + return; + } + + remcsum_unadjust((__sum16 *)ptr, grc->delta); } static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, @@ -2553,10 +2639,6 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev) static inline void netif_tx_stop_queue(struct netdev_queue *dev_queue) { - if (WARN_ON(!dev_queue)) { - pr_info("netif_stop_queue() cannot be called before register_netdev()\n"); - return; - } set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } @@ -2572,15 +2654,7 @@ static inline void netif_stop_queue(struct net_device *dev) netif_tx_stop_queue(netdev_get_tx_queue(dev, 0)); } -static inline void netif_tx_stop_all_queues(struct net_device *dev) -{ - unsigned int i; - - for (i = 0; i < dev->num_tx_queues; i++) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - netif_tx_stop_queue(txq); - } -} +void netif_tx_stop_all_queues(struct net_device *dev); static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue) { @@ -2841,6 +2915,9 @@ static inline int netif_set_xps_queue(struct net_device *dev, } #endif +u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, + unsigned int num_tx_queues); + /* * Returns a Tx hash for the given packet when dev->real_num_tx_queues is used * as a distribution range limit for the returned value. @@ -2938,11 +3015,7 @@ 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_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); -} +int netif_receive_skb(struct sk_buff *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); @@ -2980,6 +3053,7 @@ 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); +int dev_change_proto_down(struct net_device *dev, bool proto_down); 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); @@ -3779,6 +3853,31 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } +static inline bool netif_is_l3_master(const struct net_device *dev) +{ + return dev->priv_flags & IFF_L3MDEV_MASTER; +} + +static inline bool netif_is_l3_slave(const struct net_device *dev) +{ + return dev->priv_flags & IFF_L3MDEV_SLAVE; +} + +static inline bool netif_is_bridge_master(const struct net_device *dev) +{ + return dev->priv_flags & IFF_EBRIDGE; +} + +static inline bool netif_is_bridge_port(const struct net_device *dev) +{ + return dev->priv_flags & IFF_BRIDGE_PORT; +} + +static inline bool netif_is_ovs_master(const struct net_device *dev) +{ + return dev->priv_flags & IFF_OPENVSWITCH; +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { |