--- zzzz-none-000/linux-3.10.107/include/linux/netdevice.h 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/include/linux/netdevice.h 2021-02-04 17:41:59.000000000 +0000 @@ -25,11 +25,11 @@ #ifndef _LINUX_NETDEVICE_H #define _LINUX_NETDEVICE_H -#include #include #include #include #include +#include #include #include @@ -50,25 +50,26 @@ #include #include #include +#include + +#ifdef CONFIG_AVM_PA +/* Cannot include avm_pa.h */ +struct avm_pa_dev_info; +/* transitional define to allow older avm_pa tags, to be removed */ +#define NETDEVICE_H_NO_AVM_PA_H 1 +#endif struct netpoll_info; struct device; struct phy_device; /* 802.11 specific */ struct wireless_dev; - /* source back-compat hooks */ -#define SET_ETHTOOL_OPS(netdev,ops) \ - ( (netdev)->ethtool_ops = (ops) ) - -extern void netdev_set_default_ethtool_ops(struct net_device *dev, - const struct ethtool_ops *ops); - -/* hardware address assignment types */ -#define NET_ADDR_PERM 0 /* address is permanent (default) */ -#define NET_ADDR_RANDOM 1 /* address is generated randomly */ -#define NET_ADDR_STOLEN 2 /* address is stolen from other device */ -#define NET_ADDR_SET 3 /* address is set using - * dev_set_mac_address() */ +/* 802.15.4 specific */ +struct wpan_dev; +struct mpls_dev; + +void netdev_set_default_ethtool_ops(struct net_device *dev, + const struct ethtool_ops *ops); /* Backlog congestion levels */ #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ @@ -139,7 +140,7 @@ */ #if defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25) -# if defined(CONFIG_MAC80211_MESH) +# if 1 || defined(CONFIG_MAC80211_MESH) # define LL_MAX_HEADER 128 # else # define LL_MAX_HEADER 96 @@ -186,7 +187,6 @@ unsigned long tx_compressed; }; - #include #include @@ -267,11 +267,11 @@ 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, const unsigned char *haddr); + bool (*validate)(const char *ll_header, unsigned int len); }; /* These flag bits are private to the generic network queueing @@ -287,7 +287,6 @@ __LINK_STATE_DORMANT, }; - /* * This structure holds at boot time configured netdevice settings. They * are then used in the device probing. @@ -298,7 +297,7 @@ }; #define NETDEV_BOOT_SETUP_MAX 8 -extern int __init netdev_boot_setup(char *str); +int __init netdev_boot_setup(char *str); /* * Structure for NAPI scheduling similar to tasklet but with weighting @@ -323,13 +322,17 @@ struct net_device *dev; struct sk_buff *gro_list; struct sk_buff *skb; + struct hrtimer timer; struct list_head dev_list; + struct hlist_node napi_hash_node; + unsigned int napi_id; }; enum { NAPI_STATE_SCHED, /* Poll is scheduled */ NAPI_STATE_DISABLE, /* Disable pending */ NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ + NAPI_STATE_HASHED, /* In NAPI hash */ }; enum gro_result { @@ -391,7 +394,8 @@ typedef enum rx_handler_result rx_handler_result_t; typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb); -extern void __napi_schedule(struct napi_struct *n); +void __napi_schedule(struct napi_struct *n); +void __napi_schedule_irqoff(struct napi_struct *n); static inline bool napi_disable_pending(struct napi_struct *n) { @@ -426,6 +430,18 @@ __napi_schedule(n); } +/** + * napi_schedule_irqoff - schedule NAPI poll + * @n: napi context + * + * Variant of napi_schedule(), assuming hard irqs are masked. + */ +static inline void napi_schedule_irqoff(struct napi_struct *n) +{ + if (napi_schedule_prep(n)) + __napi_schedule_irqoff(n); +} + /* Try to reschedule poll. Called by dev->poll() after napi_complete(). */ static inline bool napi_reschedule(struct napi_struct *napi) { @@ -436,14 +452,45 @@ return false; } +void __napi_complete(struct napi_struct *n); +void napi_complete_done(struct napi_struct *n, int work_done); /** * napi_complete - NAPI processing complete * @n: napi context * * Mark NAPI processing as complete. + * Consider using napi_complete_done() instead. + */ +static inline void napi_complete(struct napi_struct *n) +{ + return napi_complete_done(n, 0); +} + +/** + * napi_by_id - lookup a NAPI by napi_id + * @napi_id: hashed napi_id + * + * lookup @napi_id in napi_hash table + * must be called under rcu_read_lock() + */ +struct napi_struct *napi_by_id(unsigned int napi_id); + +/** + * napi_hash_add - add a NAPI to global hashtable + * @napi: napi context + * + * generate a new napi_id and store a @napi under it in napi_hash + */ +void napi_hash_add(struct napi_struct *napi); + +/** + * napi_hash_del - remove a NAPI from global table + * @napi: napi context + * + * Warning: caller must observe rcu grace period + * before freeing memory containing @napi */ -extern void __napi_complete(struct napi_struct *n); -extern void napi_complete(struct napi_struct *n); +void napi_hash_del(struct napi_struct *napi); /** * napi_disable - prevent NAPI from scheduling @@ -452,13 +499,7 @@ * Stop NAPI from being scheduled on this context. * Waits till any outstanding processing completes. */ -static inline void napi_disable(struct napi_struct *n) -{ - set_bit(NAPI_STATE_DISABLE, &n->state); - while (test_and_set_bit(NAPI_STATE_SCHED, &n->state)) - msleep(1); - clear_bit(NAPI_STATE_DISABLE, &n->state); -} +void napi_disable(struct napi_struct *n); /** * napi_enable - enable NAPI scheduling @@ -470,11 +511,11 @@ static inline void napi_enable(struct napi_struct *n) { BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); - smp_mb__before_clear_bit(); + smp_mb__before_atomic(); clear_bit(NAPI_STATE_SCHED, &n->state); + clear_bit(NAPI_STATE_NPSVC, &n->state); } -#ifdef CONFIG_SMP /** * napi_synchronize - wait until NAPI is not running * @n: napi context @@ -485,22 +526,29 @@ */ static inline void napi_synchronize(const struct napi_struct *n) { - while (test_bit(NAPI_STATE_SCHED, &n->state)) - msleep(1); + if (IS_ENABLED(CONFIG_SMP)) + while (test_bit(NAPI_STATE_SCHED, &n->state)) + msleep(1); + else + barrier(); } -#else -# define napi_synchronize(n) barrier() -#endif enum netdev_queue_state_t { __QUEUE_STATE_DRV_XOFF, __QUEUE_STATE_STACK_XOFF, __QUEUE_STATE_FROZEN, -#define QUEUE_STATE_ANY_XOFF ((1 << __QUEUE_STATE_DRV_XOFF) | \ - (1 << __QUEUE_STATE_STACK_XOFF)) -#define QUEUE_STATE_ANY_XOFF_OR_FROZEN (QUEUE_STATE_ANY_XOFF | \ - (1 << __QUEUE_STATE_FROZEN)) }; + +#define QUEUE_STATE_DRV_XOFF (1 << __QUEUE_STATE_DRV_XOFF) +#define QUEUE_STATE_STACK_XOFF (1 << __QUEUE_STATE_STACK_XOFF) +#define QUEUE_STATE_FROZEN (1 << __QUEUE_STATE_FROZEN) + +#define QUEUE_STATE_ANY_XOFF (QUEUE_STATE_DRV_XOFF | QUEUE_STATE_STACK_XOFF) +#define QUEUE_STATE_ANY_XOFF_OR_FROZEN (QUEUE_STATE_ANY_XOFF | \ + QUEUE_STATE_FROZEN) +#define QUEUE_STATE_DRV_XOFF_OR_FROZEN (QUEUE_STATE_DRV_XOFF | \ + QUEUE_STATE_FROZEN) + /* * __QUEUE_STATE_DRV_XOFF is used by drivers to stop the transmit queue. The * netif_tx_* functions below are used to manipulate this flag. The @@ -516,7 +564,7 @@ * read mostly part */ struct net_device *dev; - struct Qdisc *qdisc; + struct Qdisc __rcu *qdisc; struct Qdisc *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; @@ -545,6 +593,7 @@ #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) @@ -601,52 +650,66 @@ /* * The rps_sock_flow_table contains mappings of flows to the last CPU * on which they were processed by the application (set in recvmsg). + * Each entry is a 32bit value. Upper part is the high order bits + * of flow hash, lower part is cpu number. + * rps_cpu_mask is used to partition the space, depending on number of + * possible cpus : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1 + * For example, if 64 cpus are possible, rps_cpu_mask = 0x3f, + * meaning we use 32-6=26 bits for the hash. */ struct rps_sock_flow_table { - unsigned int mask; - u16 ents[0]; + u32 mask; + + u32 ents[0] ____cacheline_aligned_in_smp; }; -#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_sock_flow_table) + \ - ((_num) * sizeof(u16))) +#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) #define RPS_NO_CPU 0xffff +extern u32 rps_cpu_mask; +extern struct rps_sock_flow_table __rcu *rps_sock_flow_table; + static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, u32 hash) { if (table && hash) { - unsigned int cpu, index = hash & table->mask; + unsigned int index = hash & table->mask; + u32 val = hash & ~rps_cpu_mask; /* We only give a hint, preemption can change cpu under us */ - cpu = raw_smp_processor_id(); + val |= raw_smp_processor_id(); - if (table->ents[index] != cpu) - table->ents[index] = cpu; + if (table->ents[index] != val) + table->ents[index] = val; } } -static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table, - u32 hash) -{ - if (table && hash) - table->ents[hash & table->mask] = RPS_NO_CPU; -} - -extern struct rps_sock_flow_table __rcu *rps_sock_flow_table; - #ifdef CONFIG_RFS_ACCEL -extern bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, - u32 flow_id, u16 filter_id); +bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, + u16 filter_id); #endif +#endif /* CONFIG_RPS */ /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { +#ifdef CONFIG_RPS struct rps_map __rcu *rps_map; struct rps_dev_flow_table __rcu *rps_flow_table; +#endif struct kobject kobj; struct net_device *dev; } ____cacheline_aligned_in_smp; -#endif /* CONFIG_RPS */ + +/* + * RX queue sysfs structures and functions. + */ +struct rx_queue_attribute { + struct attribute attr; + ssize_t (*show)(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, char *buf); + ssize_t (*store)(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, const char *buf, size_t len); +}; #ifdef CONFIG_XPS /* @@ -660,8 +723,8 @@ 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. @@ -699,6 +762,37 @@ }; #endif +#define MAX_PHYS_ITEM_ID_LEN 32 + +/* This structure holds a unique identifier to identify some + * physical item (port for example) used by a netdevice. + */ +struct netdev_phys_item_id { + unsigned char id[MAX_PHYS_ITEM_ID_LEN]; + 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); + +#ifdef CONFIG_RFS_ACCEL +typedef int (*set_rfs_filter_callback_t)(struct net_device *dev, + __be32 src, + __be32 dst, + __be16 sport, + __be16 dport, + u8 proto, + u16 rxq_index, + u32 action); +#endif + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -725,11 +819,15 @@ * 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. * - * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb); + * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, + * void *accel_priv, select_queue_fallback_t fallback); * Called to decide which queue to when device supports multiple * transmit queues. * @@ -783,11 +881,11 @@ * 3. Update dev->stats asynchronously and atomically, and define * neither operation. * - * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16t vid); + * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid); * If device support VLAN filtering this function is called when a * VLAN id is registered. * - * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid); + * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid); * If device support VLAN filtering this function is called when a * VLAN id is unregistered. * @@ -796,12 +894,20 @@ * SR-IOV management functions. * int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac); * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, u8 qos); - * int (*ndo_set_vf_tx_rate)(struct net_device *dev, int vf, int rate); + * 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); * 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 @@ -858,6 +964,15 @@ * Set hardware filter for RFS. rxq_index is the target queue index; * flow_id is a flow ID to be passed to rps_may_expire_flow() later. * Return the filter ID on success, or a negative error code. + * int (*ndo_register_rfs_filter(struct net_device *dev, + * set_rfs_filter_callback_t set_filter); + * Register callback to handle commands for low layer RFS filter engine. + * Return 0 on success, or a negative error code. + * + * Get Default VLAN tag + * int (*ndo_get_default_vlan_tag)(struct net_device *net); + * This api can be called by other modules to get + * the default vlan tag * * Slave management functions (for bridge, bonding, etc). * int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev); @@ -880,20 +995,25 @@ * * int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, - * const unsigned char *addr, u16 flags) + * const unsigned char *addr, u16 vid, u16 flags) * Adds an FDB entry to dev for addr. * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, - * const unsigned char *addr) + * const unsigned char *addr, u16 vid) * Deletes the FDB entry from dev coresponding to addr. * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, - * struct net_device *dev, int idx) + * struct net_device *dev, struct net_device *filter_dev, + * int idx) * Used to add FDB entries to dump requests. Implementers should add * entries to skb and update idx with the number of entries. * - * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh) + * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, + * u16 flags) * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, - * struct net_device *dev, u32 filter_mask) + * struct net_device *dev, u32 filter_mask, + * int nlflags) + * int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh, + * u16 flags); * * int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); * Called to change device carrier. Soft-devices (like dummy, team, etc) @@ -902,6 +1022,69 @@ * that determine carrier state from physical hardware properties (eg * network cables) or protocol-dependent mechanisms (eg * USB_CDC_NOTIFY_NETWORK_CONNECTION) should NOT implement this function. + * + * int (*ndo_get_phys_port_id)(struct net_device *dev, + * struct netdev_phys_item_id *ppid); + * Called to get ID of physical port of this device. If driver does + * not implement this, it is assumed that the hw is not able to have + * multiple net devices on single physical port. + * + * void (*ndo_add_vxlan_port)(struct net_device *dev, + * sa_family_t sa_family, __be16 port); + * Called by vxlan to notiy a driver about the UDP port and socket + * address family that vxlan is listnening to. It is called only when + * a new port starts listening. The operation is protected by the + * vxlan_net->sock_lock. + * + * void (*ndo_del_vxlan_port)(struct net_device *dev, + * sa_family_t sa_family, __be16 port); + * Called by vxlan to notify the driver about a UDP port and socket + * address family that vxlan is not listening to anymore. The operation + * is protected by the vxlan_net->sock_lock. + * + * void* (*ndo_dfwd_add_station)(struct net_device *pdev, + * struct net_device *dev) + * Called by upper layer devices to accelerate switching or other + * station functionality into hardware. 'pdev is the lowerdev + * to use for the offload and 'dev' is the net device that will + * back the offload. Returns a pointer to the private structure + * the upper layer will maintain. + * void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv) + * Called by upper layer device to delete the station created + * by 'ndo_dfwd_add_station'. 'pdev' is the net device backing + * the station and priv is the structure returned by the add + * operation. + * netdev_tx_t (*ndo_dfwd_start_xmit)(struct sk_buff *skb, + * struct net_device *dev, + * void *priv); + * Callback to use for xmit over the accelerated station. This + * is used in place of ndo_start_xmit on accelerated net + * devices. + * netdev_features_t (*ndo_features_check) (struct sk_buff *skb, + * struct net_device *dev + * netdev_features_t features); + * Called by core transmit path to determine if device is capable of + * performing offload operations on a given packet. This is to give + * the device an opportunity to implement any restrictions that cannot + * 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_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. + * 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); @@ -911,7 +1094,9 @@ netdev_tx_t (*ndo_start_xmit) (struct sk_buff *skb, struct net_device *dev); u16 (*ndo_select_queue)(struct net_device *dev, - struct sk_buff *skb); + struct sk_buff *skb, + void *accel_priv, + select_queue_fallback_t fallback); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); @@ -939,26 +1124,40 @@ #ifdef CONFIG_NET_POLL_CONTROLLER void (*ndo_poll_controller)(struct net_device *dev); int (*ndo_netpoll_setup)(struct net_device *dev, - struct netpoll_info *info, - gfp_t gfp); + struct netpoll_info *info); void (*ndo_netpoll_cleanup)(struct net_device *dev); #endif +#ifdef CONFIG_NET_RX_BUSY_POLL + int (*ndo_busy_poll)(struct napi_struct *dev); +#endif int (*ndo_set_vf_mac)(struct net_device *dev, int queue, u8 *mac); int (*ndo_set_vf_vlan)(struct net_device *dev, int queue, u16 vlan, u8 qos); - int (*ndo_set_vf_tx_rate)(struct net_device *dev, - int vf, int rate); + 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); + 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[]); 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); @@ -989,6 +1188,9 @@ const struct sk_buff *skb, u16 rxq_index, u32 flow_id); + int (*ndo_register_rfs_filter)(struct net_device *dev, + set_rfs_filter_callback_t set_filter); + int (*ndo_get_default_vlan_tag)(struct net_device *net); #endif int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev); @@ -1005,64 +1207,389 @@ struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, + u16 vid, u16 flags); int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr); + const unsigned char *addr, + u16 vid); int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, + struct net_device *filter_dev, int idx); int (*ndo_bridge_setlink)(struct net_device *dev, - struct nlmsghdr *nlh); + struct nlmsghdr *nlh, + u16 flags); int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, - u32 filter_mask); + u32 filter_mask, + int nlflags); int (*ndo_bridge_dellink)(struct net_device *dev, - struct nlmsghdr *nlh); + struct nlmsghdr *nlh, + u16 flags); int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); -}; - -/* - * The DEVICE structure. - * Actually, this whole structure is a big mistake. It mixes I/O - * data with strictly "high-level" data, and it has to know about - * almost every data structure used in the INET module. + 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); + void (*ndo_del_vxlan_port)(struct net_device *dev, + sa_family_t sa_family, + __be16 port); + + void* (*ndo_dfwd_add_station)(struct net_device *pdev, + struct net_device *dev); + void (*ndo_dfwd_del_station)(struct net_device *pdev, + void *priv); + + netdev_tx_t (*ndo_dfwd_start_xmit) (struct sk_buff *skb, + struct net_device *dev, + void *priv); + int (*ndo_get_lock_subclass)(struct net_device *dev); + netdev_features_t (*ndo_features_check) (struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features); + int (*ndo_set_tx_maxrate)(struct net_device *dev, + 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); +}; + +/** + * enum net_device_priv_flags - &struct net_device priv_flags + * + * These are the &struct net_device, they are only set internally + * by drivers and used in the kernel. These flags are invisible to + * userspace, this means that the order of these flags can change + * during any kernel release. + * + * You should have a pretty good reason to be extending these flags. + * + * @IFF_802_1Q_VLAN: 802.1Q VLAN device + * @IFF_EBRIDGE: Ethernet bridging device + * @IFF_BONDING: bonding master or slave + * @IFF_ISATAP: ISATAP interface (RFC4214) + * @IFF_WAN_HDLC: WAN HDLC device + * @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to + * release skb->dst + * @IFF_DONT_BRIDGE: disallow bridging this ether dev + * @IFF_DISABLE_NETPOLL: disable netpoll at run-time + * @IFF_MACVLAN_PORT: device used as macvlan port + * @IFF_BRIDGE_PORT: device used as bridge port + * @IFF_OVS_DATAPATH: device used as Open vSwitch datapath port + * @IFF_TX_SKB_SHARING: The interface supports sharing skbs on transmit + * @IFF_UNICAST_FLT: Supports unicast filtering + * @IFF_TEAM_PORT: device used as team port + * @IFF_SUPP_NOFCS: device supports sending custom FCS + * @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_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, + IFF_NO_IP_ALIGN = 1<<24, + IFF_TUN_TAP = 1<<25, + IFF_PPP_L2TPV2 = 1<<26, + IFF_PPP_L2TPV3 = 1<<27, + IFF_PPP_PPTP = 1<<28, + IFF_GRE_V4_TAP = 1<<29, + IFF_GRE_V6_TAP = 1<<30, +}; + +#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN +#define IFF_EBRIDGE IFF_EBRIDGE +#define IFF_BONDING IFF_BONDING +#define IFF_ISATAP IFF_ISATAP +#define IFF_WAN_HDLC IFF_WAN_HDLC +#define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE +#define IFF_DONT_BRIDGE IFF_DONT_BRIDGE +#define IFF_DISABLE_NETPOLL IFF_DISABLE_NETPOLL +#define IFF_MACVLAN_PORT IFF_MACVLAN_PORT +#define IFF_BRIDGE_PORT IFF_BRIDGE_PORT +#define IFF_OVS_DATAPATH IFF_OVS_DATAPATH +#define IFF_TX_SKB_SHARING IFF_TX_SKB_SHARING +#define IFF_UNICAST_FLT IFF_UNICAST_FLT +#define IFF_TEAM_PORT IFF_TEAM_PORT +#define IFF_SUPP_NOFCS IFF_SUPP_NOFCS +#define IFF_LIVE_ADDR_CHANGE IFF_LIVE_ADDR_CHANGE +#define IFF_MACVLAN IFF_MACVLAN +#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 +#define IFF_NO_IP_ALIGN IFF_NO_IP_ALIGN +#define IFF_TUN_TAP IFF_TUN_TAP + +/** + * struct net_device - The DEVICE structure. + * Actually, this whole structure is a big mistake. It mixes I/O + * data with strictly "high-level" data, and it has to know about + * almost every data structure used in the INET module. + * + * @name: This is the first field of the "visible" part of this structure + * (i.e. as seen by users in the "Space.c" file). It is the name + * of the interface. + * + * @name_hlist: Device name hash chain, please keep it close to name[] + * @ifalias: SNMP alias + * @mem_end: Shared memory end + * @mem_start: Shared memory start + * @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 + * @unreg_list: List entry, that is used, when we are unregistering the + * device, see the function unregister_netdev + * @close_list: List entry, that is used, when we are closing the device + * + * @adj_list: Directly linked devices, like slaves for bonding + * @all_adj_list: All linked devices, *including* neighbours + * @features: Currently active device features + * @hw_features: User-changeable features + * + * @wanted_features: User-requested features + * @vlan_features: Mask of features inheritable by VLAN devices + * + * @hw_enc_features: Mask of features inherited by encapsulating devices + * This field indicates what encapsulation + * offloads the hardware is capable of doing, + * and drivers will need to set them appropriately. + * + * @mpls_features: Mask of features inheritable by MPLS + * + * @ifindex: interface index + * @group: The group, that the device belongs to + * + * @stats: Statistics struct, which was left as a legacy, use + * rtnl_link_stats64 instead + * + * @rx_dropped: Dropped packets by core network, + * do not use this in drivers + * @tx_dropped: Dropped packets by core network, + * do not use this in drivers + * + * @wireless_handlers: List of functions to handle Wireless Extensions, + * instead of ioctl, + * see for details. + * @wireless_data: Instance data managed by the core of wireless extensions + * + * @netdev_ops: Includes several pointers to callbacks, + * if one wants to override the ndo_*() functions + * @ethtool_ops: Management operations + * @header_ops: Includes callbacks for creating,parsing,caching,etc + * of Layer 2 headers. + * + * @flags: Interface flags (a la BSD) + * @priv_flags: Like 'flags' but invisible to userspace, + * see if.h for the definitions + * @gflags: Global flags ( kept as legacy ) + * @padded: How much padding added by alloc_netdev() + * @operstate: RFC2863 operstate + * @link_mode: Mapping policy to operstate + * @if_port: Selectable AUI, TP, ... + * @dma: DMA channel + * @mtu: Interface MTU value + * @type: Interface hardware type + * @hard_header_len: Maximum hardware header length. + * @min_header_len: Minimum hardware header length + * + * @needed_headroom: Extra headroom the hardware may need, but not in all + * cases can this be guaranteed + * @needed_tailroom: Extra tailroom the hardware may need, but not in all + * cases can this be guaranteed. Some cases also use + * LL_MAX_HEADER instead to allocate the skb + * + * interface address info: + * + * @perm_addr: Permanent hw address + * @addr_assign_type: Hw address assignment type + * @addr_len: Hardware address length + * @neigh_priv_len; Used in neigh_alloc(), + * initialized only in atm/clip.c + * @dev_id: Used to differentiate devices that share + * the same link layer address + * @dev_port: Used to differentiate devices that share + * the same function + * @addr_list_lock: XXX: need comments on this one + * @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 + * @allmulti: Counter, enables or disables allmulticast mode + * + * @vlan_info: VLAN info + * @dsa_ptr: dsa specific data + * @tipc_ptr: TIPC specific data + * @atalk_ptr: AppleTalk link + * @ip_ptr: IPv4 specific data + * @dn_ptr: DECnet specific data + * @ip6_ptr: IPv6 specific data + * @ax25_ptr: AX.25 specific data + * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering + * + * @last_rx: Time of last Rx + * @dev_addr: Hw address (before bcast, + * because most packets are unicast) + * + * @_rx: Array of RX queues + * @num_rx_queues: Number of RX queues + * allocated at register_netdev() time + * @real_num_rx_queues: Number of RX queues currently active in device + * + * @rx_handler: handler for received packets + * @rx_handler_data: XXX: need comments on this one + * @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 + * @qdisc: Root qdisc from userspace point of view + * @tx_queue_len: Max frames per queue allowed + * @tx_global_lock: XXX: need comments on this one + * + * @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() ) + * @watchdog_timer: List of timers + * + * @pcpu_refcnt: Number of references to this device + * @todo_list: Delayed register/unregister + * @link_watch_list: XXX: need comments on this one + * + * @reg_state: Register/unregister state machine + * @dismantle: Device is going to be freed + * @rtnl_link_state: This enum represents the phases of creating + * a new link + * + * @destructor: Called from unregister, + * can be used to call free_netdev + * @npinfo: XXX: need comments on this one + * @nd_net: Network namespace this network device is inside + * + * @ml_priv: Mid-layer private + * @lstats: Loopback statistics + * @tstats: Tunnel statistics + * @dstats: Dummy statistics + * @vstats: Virtual ethernet statistics + * + * @garp_port: GARP + * @mrp_port: MRP + * + * @dev: Class/net/name entry + * @sysfs_groups: Space for optional device, statistics and wireless + * sysfs groups + * + * @sysfs_rx_queue_group: Space for optional per-rx queue attributes + * @rtnl_link_ops: Rtnl_link_ops + * + * @gso_max_size: Maximum size of generic segmentation offload + * @gso_max_segs: Maximum number of segments that can be passed to the + * NIC for GSO + * @gso_min_segs: Minimum number of segments that can be passed to the + * NIC for GSO + * + * @dcbnl_ops: Data Center Bridging netlink ops + * @num_tc: Number of traffic classes in the net device + * @tc_to_txq: XXX: need comments on this one + * @prio_tc_map XXX: need comments on this one + * + * @fcoe_ddp_xid: Max exchange id for FCoE LRO by ddp + * + * @priomap: XXX: need comments on this one + * @phydev: Physical device may attach itself + * for hardware timestamping + * + * @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. */ struct net_device { - - /* - * This is the first field of the "visible" part of this structure - * (i.e. as seen by users in the "Space.c" file). It is the name - * of the interface. - */ char name[IFNAMSIZ]; - - /* device name hash chain, please keep it close to name[] */ struct hlist_node name_hlist; - - /* snmp alias */ char *ifalias; - /* * I/O specific fields * FIXME: Merge these and struct ifmap into one */ - unsigned long mem_end; /* shared mem end */ - unsigned long mem_start; /* shared mem start */ - unsigned long base_addr; /* device I/O address */ - unsigned int irq; /* device IRQ number */ + unsigned long mem_end; + unsigned long mem_start; + unsigned long base_addr; + int irq; + + atomic_t carrier_changes; /* - * Some hardware also needs these fields, but they are not + * Some hardware also needs these fields (state,dev_list, + * napi_list,unreg_list,close_list) but they are not * part of the usual set specified in Space.c. */ @@ -1071,168 +1598,174 @@ struct list_head dev_list; struct list_head napi_list; struct list_head unreg_list; - struct list_head upper_dev_list; /* List of upper devices */ + struct list_head close_list; + struct list_head ptype_all; + struct list_head ptype_specific; + + struct { + struct list_head upper; + struct list_head lower; + } adj_list; + + struct { + struct list_head upper; + struct list_head lower; + } all_adj_list; - - /* currently active device features */ netdev_features_t features; - /* user-changeable features */ netdev_features_t hw_features; - /* user-requested features */ netdev_features_t wanted_features; - /* mask of features inheritable by VLAN devices */ netdev_features_t vlan_features; - /* mask of features inherited by encapsulating devices - * This field indicates what encapsulation offloads - * the hardware is capable of doing, and drivers will - * need to set them appropriately. - */ netdev_features_t hw_enc_features; + netdev_features_t mpls_features; - /* Interface index. Unique device identifier */ int ifindex; - int iflink; + int group; struct net_device_stats stats; - atomic_long_t rx_dropped; /* dropped packets by core network - * Do not use this in drivers. - */ + + atomic_long_t rx_dropped; + atomic_long_t tx_dropped; #ifdef CONFIG_WIRELESS_EXT - /* List of functions to handle Wireless Extensions (instead of ioctl). - * See for details. Jean II */ const struct iw_handler_def * wireless_handlers; - /* Instance data managed by the core of Wireless Extensions. */ struct iw_public_data * wireless_data; #endif - /* Management operations */ const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; +#ifdef CONFIG_NET_SWITCHDEV + const struct switchdev_ops *switchdev_ops; +#endif +#ifdef CONFIG_NET_L3_MASTER_DEV + const struct l3mdev_ops *l3mdev_ops; +#endif + +#ifdef CONFIG_ETHERNET_PACKET_MANGLE + void (*eth_mangle_rx)(struct net_device *dev, struct sk_buff *skb); + struct sk_buff *(*eth_mangle_tx)(struct net_device *dev, struct sk_buff *skb); +#endif - /* Hardware header description */ const struct header_ops *header_ops; - unsigned int flags; /* interface flags (a la BSD) */ - unsigned int priv_flags; /* Like 'flags' but invisible to userspace. - * See if.h for definitions. */ + unsigned int flags; + unsigned int priv_flags; + unsigned short gflags; - unsigned short padded; /* How much padding added by alloc_netdev() */ + unsigned short padded; - unsigned char operstate; /* RFC2863 operstate */ - unsigned char link_mode; /* mapping policy to operstate */ + unsigned char operstate; + unsigned char link_mode; - unsigned char if_port; /* Selectable AUI, TP,..*/ - unsigned char dma; /* DMA channel */ + unsigned char if_port; + unsigned char dma; - unsigned int mtu; /* interface MTU value */ - unsigned short type; /* interface hardware type */ - unsigned short hard_header_len; /* hardware hdr length */ + unsigned int mtu; + unsigned short type; + unsigned short hard_header_len; + unsigned short min_header_len; - /* extra head- and tailroom the hardware may need, but not in all cases - * can this be guaranteed, especially tailroom. Some cases also use - * LL_MAX_HEADER instead to allocate the skb. - */ unsigned short needed_headroom; unsigned short needed_tailroom; /* Interface address info. */ - unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */ - unsigned char addr_assign_type; /* hw address assignment type */ - unsigned char addr_len; /* hardware address length */ - unsigned char neigh_priv_len; - unsigned short dev_id; /* for shared network cards */ - + unsigned char perm_addr[MAX_ADDR_LEN]; + unsigned char addr_assign_type; + unsigned char addr_len; + unsigned short neigh_priv_len; + unsigned short dev_id; + unsigned short dev_port; spinlock_t addr_list_lock; - struct netdev_hw_addr_list uc; /* Unicast mac addresses */ - struct netdev_hw_addr_list mc; /* Multicast mac addresses */ - struct netdev_hw_addr_list dev_addrs; /* list of device - * hw addresses - */ + 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; + + unsigned char local_addr_mask[MAX_ADDR_LEN]; + #ifdef CONFIG_SYSFS struct kset *queues_kset; #endif - - bool uc_promisc; unsigned int promiscuity; unsigned int allmulti; - /* Protocol specific pointers */ #if IS_ENABLED(CONFIG_VLAN_8021Q) - struct vlan_info __rcu *vlan_info; /* VLAN info */ + struct vlan_info __rcu *vlan_info; #endif #if IS_ENABLED(CONFIG_NET_DSA) - struct dsa_switch_tree *dsa_ptr; /* dsa specific data */ + struct dsa_switch_tree *dsa_ptr; +#endif +#if IS_ENABLED(CONFIG_TIPC) + struct tipc_bearer __rcu *tipc_ptr; +#endif + void *atalk_ptr; + struct in_device __rcu *ip_ptr; + struct dn_dev __rcu *dn_ptr; + struct inet6_dev __rcu *ip6_ptr; + void *ax25_ptr; + struct wireless_dev *ieee80211_ptr; + struct wpan_dev *ieee802154_ptr; +#if IS_ENABLED(CONFIG_MPLS_ROUTING) + struct mpls_dev __rcu *mpls_ptr; +#endif + +#ifdef CONFIG_ETHERNET_PACKET_MANGLE + void *phy_ptr; /* PHY device specific data */ #endif - void *atalk_ptr; /* AppleTalk link */ - struct in_device __rcu *ip_ptr; /* IPv4 specific data */ - struct dn_dev __rcu *dn_ptr; /* DECnet specific data */ - struct inet6_dev __rcu *ip6_ptr; /* IPv6 specific data */ - void *ax25_ptr; /* AX.25 specific data */ - struct wireless_dev *ieee80211_ptr; /* IEEE 802.11 specific data, - assign before registering */ /* * Cache lines mostly used on receive path (including eth_type_trans()) */ - unsigned long last_rx; /* Time of last Rx - * This should not be set in - * drivers, unless really needed, - * because network stack (bonding) - * use it if/when necessary, to - * avoid dirtying this cache line. - */ + unsigned long last_rx; /* Interface address info used in eth_type_trans() */ - unsigned char *dev_addr; /* hw address, (before bcast - because most packets are - unicast) */ - + unsigned char *dev_addr; -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS struct netdev_rx_queue *_rx; - /* Number of RX queues allocated at register_netdev() time */ unsigned int num_rx_queues; - - /* Number of RX queues currently active in device */ unsigned int real_num_rx_queues; #endif + unsigned long gro_flush_timeout; 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; - unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */ +#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; +#endif + struct hlist_node index_hlist; /* * Cache lines mostly used on transmit path */ struct netdev_queue *_tx ____cacheline_aligned_in_smp; - - /* Number of TX queues allocated at alloc_netdev_mq() time */ unsigned int num_tx_queues; - - /* Number of TX queues currently active in device */ unsigned int real_num_tx_queues; - - /* root qdisc from userspace point of view */ struct Qdisc *qdisc; - - unsigned long tx_queue_len; /* Max frames per queue allowed */ + 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 - /* 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. */ - struct cpu_rmap *rx_cpu_rmap; + +#ifdef CONFIG_NET_SWITCHDEV + u32 offload_fwd_mark; #endif /* These may be needed for future network-power-down code. */ @@ -1241,22 +1774,15 @@ * trans_start here is expensive for high speed devices on SMP, * please use netdev_queue->trans_start instead. */ - unsigned long trans_start; /* Time (in jiffies) of last Tx */ + unsigned long trans_start; - int watchdog_timeo; /* used by dev_watchdog() */ struct timer_list watchdog_timer; - /* Number of references to this device */ int __percpu *pcpu_refcnt; - - /* delayed register/unregister */ struct list_head todo_list; - /* device index hash chain */ - struct hlist_node index_hlist; struct list_head link_watch_list; - /* register/unregister state machine */ enum { NETREG_UNINITIALIZED=0, NETREG_REGISTERED, /* completed register_netdevice */ NETREG_UNREGISTERING, /* called unregister_netdevice */ @@ -1265,44 +1791,42 @@ NETREG_DUMMY, /* dummy device for NAPI poll */ } reg_state:8; - bool dismantle; /* device is going do be freed */ + bool dismantle; enum { RTNL_LINK_INITIALIZED, RTNL_LINK_INITIALIZING, } rtnl_link_state:16; - /* Called from unregister, can be used to call free_netdev */ void (*destructor)(struct net_device *dev); #ifdef CONFIG_NETPOLL struct netpoll_info __rcu *npinfo; #endif -#ifdef CONFIG_NET_NS - /* Network namespace this network device is inside */ - struct net *nd_net; -#endif + possible_net_t nd_net; /* mid-layer private */ union { - void *ml_priv; - struct pcpu_lstats __percpu *lstats; /* loopback stats */ - struct pcpu_tstats __percpu *tstats; /* tunnel stats */ - struct pcpu_dstats __percpu *dstats; /* dummy stats */ - struct pcpu_vstats __percpu *vstats; /* veth stats */ + void *ml_priv; + struct pcpu_lstats __percpu *lstats; + struct pcpu_sw_netstats __percpu *tstats; + struct pcpu_dstats __percpu *dstats; + struct pcpu_vstats __percpu *vstats; }; - /* GARP */ + +#ifdef CONFIG_AVM_PA + u8 avm_pa[32]; +#define AVM_PA_DEVINFO(dev) ((struct avm_pa_dev_info *) (dev)->avm_pa) +#endif + struct garp_port __rcu *garp_port; - /* MRP */ struct mrp_port __rcu *mrp_port; - /* class/net/name entry */ - struct device dev; - /* space for optional device, statistics, and wireless sysfs groups */ + struct device dev; const struct attribute_group *sysfs_groups[4]; + const struct attribute_group *sysfs_rx_queue_group; - /* rtnetlink link ops */ const struct rtnl_link_ops *rtnl_link_ops; /* for setting kernel sock attribute on TCP connection setup */ @@ -1310,9 +1834,8 @@ unsigned int gso_max_size; #define GSO_MAX_SEGS 65535 u16 gso_max_segs; - + u16 gso_min_segs; #ifdef CONFIG_DCB - /* Data Center Bridging netlink ops */ const struct dcbnl_rtnl_ops *dcbnl_ops; #endif u8 num_tc; @@ -1320,21 +1843,14 @@ u8 prio_tc_map[TC_BITMASK + 1]; #if IS_ENABLED(CONFIG_FCOE) - /* max exchange id for FCoE LRO by ddp */ unsigned int fcoe_ddp_xid; #endif -#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map __rcu *priomap; #endif - /* phy device may attach itself for hardware timestamping */ struct phy_device *phydev; - struct lock_class_key *qdisc_tx_busylock; - - /* group the device belongs to */ - int group; - - struct pm_qos_request pm_qos_req; + bool proto_down; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -1398,6 +1914,12 @@ return &dev->_tx[index]; } +static inline struct netdev_queue *skb_get_tx_queue(const struct net_device *dev, + const struct sk_buff *skb) +{ + return netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); +} + static inline void netdev_for_each_tx_queue(struct net_device *dev, void (*f)(struct net_device *, struct netdev_queue *, @@ -1410,9 +1932,9 @@ f(dev, &dev->_tx[i], arg); } -extern struct netdev_queue *netdev_pick_tx(struct net_device *dev, - struct sk_buff *skb); -extern u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb); +struct netdev_queue *netdev_pick_tx(struct net_device *dev, + struct sk_buff *skb, + void *accel_priv); /* * Net namespace inlines @@ -1426,30 +1948,16 @@ 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 -} - -static inline bool netdev_uses_dsa_tags(struct net_device *dev) -{ -#ifdef CONFIG_NET_DSA_TAG_DSA - if (dev->dsa_ptr != NULL) - return dsa_uses_dsa_tags(dev->dsa_ptr); -#endif - - return 0; + write_pnet(&dev->nd_net, net); } -static inline bool netdev_uses_trailer_tags(struct net_device *dev) +static inline bool netdev_uses_dsa(struct net_device *dev) { -#ifdef CONFIG_NET_DSA_TAG_TRAILER +#if IS_ENABLED(CONFIG_NET_DSA) if (dev->dsa_ptr != NULL) - return dsa_uses_trailer_tags(dev->dsa_ptr); + return dsa_uses_tagged_protocol(dev->dsa_ptr); #endif - - return 0; + return false; } /** @@ -1469,7 +1977,7 @@ #define SET_NETDEV_DEV(net, pdev) ((net)->dev.parent = (pdev)) /* Set the sysfs device type for the network logical device to allow - * fin grained indentification of different network device types. For + * fine-grained identification of different network device types. For * example Ethernet, Wirelss LAN, Bluetooth, WiMAX etc. */ #define SET_NETDEV_DEVTYPE(net, devtype) ((net)->dev.type = (devtype)) @@ -1511,24 +2019,50 @@ int data_offset; /* This is non-zero if the packet cannot be merged with the new skb. */ - int flush; + u16 flush; + + /* Save the IP ID here and check when we get to the transport layer */ + u16 flush_id; /* Number of segments aggregated. */ u16 count; + /* Start offset for remote checksum offload */ + u16 gro_remcsum_start; + + /* jiffies when first packet was created/queued */ + unsigned long age; + + /* Used in ipv6_gro_receive() and foo-over-udp */ + u16 proto; + /* This is non-zero if the packet may be of the same flow. */ - u8 same_flow; + u8 same_flow:1; + + /* Used in tunnel GRO receive */ + u8 encap_mark:1; + + /* GRO checksum is valid */ + u8 csum_valid:1; + + /* Number of checksums via CHECKSUM_UNNECESSARY */ + u8 csum_cnt:3; /* Free the skb? */ - u8 free; + u8 free:2; #define NAPI_GRO_FREE 1 #define NAPI_GRO_FREE_STOLEN_HEAD 2 - /* jiffies when first packet was created/queued */ - unsigned long age; + /* Used in foo-over-udp, set in udp[46]_gro_receive */ + u8 is_ipv6:1; + + /* Number of gro_receive callbacks this packet already went through */ + u8 recursion_counter:4; + + /* 3 bit hole */ - /* Used in ipv6_gro_receive() */ - int proto; + /* used to support CHECKSUM_COMPLETE for tunneling protocols */ + __wsum csum; /* used in skb_gro_receive() slow path */ struct sk_buff *last; @@ -1536,6 +2070,25 @@ #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) +#define GRO_RECURSION_LIMIT 15 +static inline int gro_recursion_inc_test(struct sk_buff *skb) +{ + return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; +} + +typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *); +static inline struct sk_buff **call_gro_receive(gro_receive_t cb, + struct sk_buff **head, + struct sk_buff *skb) +{ + if (unlikely(gro_recursion_inc_test(skb))) { + NAPI_GRO_CB(skb)->flush |= 1; + return NULL; + } + + return cb(head, skb); +} + struct packet_type { __be16 type; /* This is really htons(ether_type). */ struct net_device *dev; /* NULL is wildcarded here */ @@ -1546,24 +2099,89 @@ bool (*id_match)(struct packet_type *ptype, struct sock *sk); void *af_packet_priv; + +#ifdef CONFIG_AVM_PA + u8 avm_pa[32]; +#define AVM_PA_PTYPE_DEVINFO(ptype) ((struct avm_pa_dev_info *) (ptype)->avm_pa) +#endif + struct list_head list; }; struct offload_callbacks { struct sk_buff *(*gso_segment)(struct sk_buff *skb, netdev_features_t features); - int (*gso_send_check)(struct sk_buff *skb); struct sk_buff **(*gro_receive)(struct sk_buff **head, - struct sk_buff *skb); - int (*gro_complete)(struct sk_buff *skb); + struct sk_buff *skb); + int (*gro_complete)(struct sk_buff *skb, int nhoff); }; struct packet_offload { __be16 type; /* This is really htons(ether_type). */ + u16 priority; struct offload_callbacks callbacks; struct list_head list; }; +struct udp_offload; + +struct udp_offload_callbacks { + struct sk_buff **(*gro_receive)(struct sk_buff **head, + struct sk_buff *skb, + struct udp_offload *uoff); + int (*gro_complete)(struct sk_buff *skb, + int nhoff, + struct udp_offload *uoff); +}; + +struct udp_offload { + __be16 port; + u8 ipproto; + struct udp_offload_callbacks callbacks; +}; + +typedef struct sk_buff **(*gro_receive_udp_t)(struct sk_buff **, + struct sk_buff *, + struct udp_offload *); +static inline struct sk_buff **call_gro_receive_udp(gro_receive_udp_t cb, + struct sk_buff **head, + struct sk_buff *skb, + struct udp_offload *uoff) +{ + if (unlikely(gro_recursion_inc_test(skb))) { + NAPI_GRO_CB(skb)->flush |= 1; + return NULL; + } + + return cb(head, skb, uoff); +} + +/* often modified stats are per cpu, other are shared (netdev->stats) */ +struct pcpu_sw_netstats { + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + struct u64_stats_sync syncp; +}; + +#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 /* netdevice notifier chain. Please remember to update the rtnetlink @@ -1579,7 +2197,7 @@ #define NETDEV_CHANGE 0x0004 /* Notify device state change */ #define NETDEV_REGISTER 0x0005 #define NETDEV_UNREGISTER 0x0006 -#define NETDEV_CHANGEMTU 0x0007 +#define NETDEV_CHANGEMTU 0x0007 /* notify after mtu change happened */ #define NETDEV_CHANGEADDR 0x0008 #define NETDEV_GOING_DOWN 0x0009 #define NETDEV_CHANGENAME 0x000A @@ -1593,16 +2211,49 @@ #define NETDEV_RELEASE 0x0012 #define NETDEV_NOTIFY_PEERS 0x0013 #define NETDEV_JOIN 0x0014 +#define NETDEV_CHANGEUPPER 0x0015 +#define NETDEV_RESEND_IGMP 0x0016 +#define NETDEV_PRECHANGEMTU 0x0017 /* notify before mtu change happened */ +#define NETDEV_CHANGEINFODATA 0x0018 +#define NETDEV_BONDING_INFO 0x0019 +#define NETDEV_PRECHANGEUPPER 0x001A +#define NETDEV_BR_JOIN 0x001B +#define NETDEV_BR_LEAVE 0x001C -extern int register_netdevice_notifier(struct notifier_block *nb); -extern int unregister_netdevice_notifier(struct notifier_block *nb); -extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev); +int register_netdevice_notifier(struct notifier_block *nb); +int unregister_netdevice_notifier(struct notifier_block *nb); +struct netdev_notifier_info { + struct net_device *dev; +}; -extern rwlock_t dev_base_lock; /* Device list lock */ +struct netdev_notifier_change_info { + struct netdev_notifier_info info; /* must be first */ + 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 */ +}; -extern seqcount_t devnet_rename_seq; /* Device rename seq */ +static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, + struct net_device *dev) +{ + info->dev = dev; +} +static inline struct net_device * +netdev_notifier_info_to_dev(const struct netdev_notifier_info *info) +{ + return info->dev; +} + +int call_netdevice_notifiers(unsigned long val, struct net_device *dev); + +extern rwlock_t dev_base_lock; /* Device list lock */ #define for_each_netdev(net, d) \ list_for_each_entry(d, &(net)->dev_base_head, dev_list) @@ -1618,7 +2269,7 @@ list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_in_bond_rcu(bond, slave) \ for_each_netdev_rcu(&init_net, slave) \ - if (netdev_master_upper_dev_get_rcu(slave) == bond) + if (netdev_master_upper_dev_get_rcu(slave) == (bond)) #define net_device_entry(lh) list_entry(lh, struct net_device, dev_list) static inline struct net_device *next_net_device(struct net_device *dev) @@ -1654,54 +2305,59 @@ return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } -extern int netdev_boot_setup_check(struct net_device *dev); -extern unsigned long netdev_boot_base(const char *prefix, int unit); -extern struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, - const char *hwaddr); -extern struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type); -extern struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type); -extern void dev_add_pack(struct packet_type *pt); -extern void dev_remove_pack(struct packet_type *pt); -extern void __dev_remove_pack(struct packet_type *pt); -extern void dev_add_offload(struct packet_offload *po); -extern void dev_remove_offload(struct packet_offload *po); -extern void __dev_remove_offload(struct packet_offload *po); - -extern struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short flags, - unsigned short mask); -extern struct net_device *dev_get_by_name(struct net *net, const char *name); -extern struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); -extern struct net_device *__dev_get_by_name(struct net *net, const char *name); -extern int dev_alloc_name(struct net_device *dev, const char *name); -extern int dev_open(struct net_device *dev); -extern int dev_close(struct net_device *dev); -extern void dev_disable_lro(struct net_device *dev); -extern int dev_loopback_xmit(struct sk_buff *newskb); -extern int dev_queue_xmit(struct sk_buff *skb); -extern int register_netdevice(struct net_device *dev); -extern void unregister_netdevice_queue(struct net_device *dev, - struct list_head *head); -extern void unregister_netdevice_many(struct list_head *head); +int netdev_boot_setup_check(struct net_device *dev); +unsigned long netdev_boot_base(const char *prefix, int unit); +struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, + const char *hwaddr); +struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type); +struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type); +void dev_add_pack(struct packet_type *pt); +void dev_remove_pack(struct packet_type *pt); +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); +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); +struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); +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 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); +void unregister_netdevice_many(struct list_head *head); static inline void unregister_netdevice(struct net_device *dev) { unregister_netdevice_queue(dev, NULL); } -extern int netdev_refcnt_read(const struct net_device *dev); -extern void free_netdev(struct net_device *dev); -extern void synchronize_net(void); -extern int init_dummy_netdev(struct net_device *dev); - -extern struct net_device *dev_get_by_index(struct net *net, int ifindex); -extern struct net_device *__dev_get_by_index(struct net *net, int ifindex); -extern struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); -extern int netdev_get_name(struct net *net, char *name, int ifindex); -extern int dev_restart(struct net_device *dev); -#ifdef CONFIG_NETPOLL_TRAP -extern int netpoll_trap(void); -#endif -extern int skb_gro_receive(struct sk_buff **head, - struct sk_buff *skb); +int netdev_refcnt_read(const struct net_device *dev); +void free_netdev(struct net_device *dev); +void netdev_freemem(struct net_device *dev); +void synchronize_net(void); +int init_dummy_netdev(struct net_device *dev); + +DECLARE_PER_CPU(int, xmit_recursion); +static inline int dev_recursion_level(void) +{ + return this_cpu_read(xmit_recursion); +} + +struct net_device *dev_get_by_index(struct net *net, int ifindex); +struct net_device *__dev_get_by_index(struct net *net, int ifindex); +struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); +int netdev_get_name(struct net *net, char *name, int ifindex); +int dev_restart(struct net_device *dev); +int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb); static inline unsigned int skb_gro_offset(const struct sk_buff *skb) { @@ -1745,17 +2401,179 @@ return skb->data + offset; } -static inline void *skb_gro_mac_header(struct sk_buff *skb) -{ - return NAPI_GRO_CB(skb)->frag0 ?: skb_mac_header(skb); -} - static inline void *skb_gro_network_header(struct sk_buff *skb) { return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) + skb_network_offset(skb); } +static inline void skb_gro_postpull_rcsum(struct sk_buff *skb, + const void *start, unsigned int len) +{ + if (NAPI_GRO_CB(skb)->csum_valid) + NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum, + csum_partial(start, len, 0)); +} + +/* GRO checksum functions. These are logical equivalents of the normal + * checksum functions (in skbuff.h) except that they operate on the GRO + * offsets and fields in sk_buff. + */ + +__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_gro_offset(skb)); +} + +static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, + bool zero_okay, + __sum16 check) +{ + return ((skb->ip_summed != CHECKSUM_PARTIAL || + skb_checksum_start_offset(skb) < + skb_gro_offset(skb)) && + !skb_at_gro_remcsum_start(skb) && + NAPI_GRO_CB(skb)->csum_cnt == 0 && + (!zero_okay || check)); +} + +static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb, + __wsum psum) +{ + if (NAPI_GRO_CB(skb)->csum_valid && + !csum_fold(csum_add(psum, NAPI_GRO_CB(skb)->csum))) + return 0; + + NAPI_GRO_CB(skb)->csum = psum; + + return __skb_gro_checksum_complete(skb); +} + +static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb) +{ + if (NAPI_GRO_CB(skb)->csum_cnt > 0) { + /* Consume a checksum from CHECKSUM_UNNECESSARY */ + NAPI_GRO_CB(skb)->csum_cnt--; + } else { + /* Update skb for CHECKSUM_UNNECESSARY and csum_level when we + * verified a new top level checksum or an encapsulated one + * during GRO. This saves work if we fallback to normal path. + */ + __skb_incr_checksum_unnecessary(skb); + } +} + +#define __skb_gro_checksum_validate(skb, proto, zero_okay, check, \ + compute_pseudo) \ +({ \ + __sum16 __ret = 0; \ + if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \ + __ret = __skb_gro_checksum_validate_complete(skb, \ + compute_pseudo(skb, proto)); \ + if (__ret) \ + __skb_mark_checksum_bad(skb); \ + else \ + skb_gro_incr_csum_unnecessary(skb); \ + __ret; \ +}) + +#define skb_gro_checksum_validate(skb, proto, compute_pseudo) \ + __skb_gro_checksum_validate(skb, proto, false, 0, compute_pseudo) + +#define skb_gro_checksum_validate_zero_check(skb, proto, check, \ + compute_pseudo) \ + __skb_gro_checksum_validate(skb, proto, true, check, compute_pseudo) + +#define skb_gro_checksum_simple_validate(skb) \ + __skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo) + +static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb) +{ + return (NAPI_GRO_CB(skb)->csum_cnt == 0 && + !NAPI_GRO_CB(skb)->csum_valid); +} + +static inline void __skb_gro_checksum_convert(struct sk_buff *skb, + __sum16 check, __wsum pseudo) +{ + NAPI_GRO_CB(skb)->csum = ~pseudo; + NAPI_GRO_CB(skb)->csum_valid = 1; +} + +#define skb_gro_checksum_try_convert(skb, proto, check, compute_pseudo) \ +do { \ + if (__skb_gro_checksum_convert_check(skb)) \ + __skb_gro_checksum_convert(skb, check, \ + compute_pseudo(skb, proto)); \ +} while (0) + +struct gro_remcsum { + int offset; + __wsum delta; +}; + +static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) +{ + grc->offset = 0; + grc->delta = 0; +} + +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 = 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 + 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 = 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; + + 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, unsigned short type, const void *daddr, const void *saddr, @@ -1777,30 +2595,52 @@ return dev->header_ops->parse(skb, haddr); } -static inline int dev_rebuild_header(struct sk_buff *skb) +/* 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) { - const struct net_device *dev = skb->dev; + if (likely(len >= dev->hard_header_len)) + return true; + if (len < dev->min_header_len) + return false; - if (!dev->header_ops || !dev->header_ops->rebuild) - return 0; - return dev->header_ops->rebuild(skb); + 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); -extern int register_gifconf(unsigned int family, gifconf_func_t * gifconf); +int register_gifconf(unsigned int family, gifconf_func_t *gifconf); static inline int unregister_gifconf(unsigned int family) { return register_gifconf(family, NULL); } +#ifdef CONFIG_NET_FLOW_LIMIT +#define FLOW_LIMIT_HISTORY (1 << 7) /* must be ^2 and !overflow buckets */ +struct sd_flow_limit { + u64 count; + unsigned int num_buckets; + unsigned int history_head; + u16 history[FLOW_LIMIT_HISTORY]; + u8 buckets[]; +}; + +extern int netdev_flow_limit_table_len; +#endif /* CONFIG_NET_FLOW_LIMIT */ + /* * Incoming packets are placed on per-cpu queues */ struct softnet_data { - struct Qdisc *output_queue; - struct Qdisc **output_queue_tailp; struct list_head poll_list; - struct sk_buff *completion_queue; + struct napi_struct *current_napi; struct sk_buff_head process_queue; /* stats */ @@ -1808,10 +2648,17 @@ unsigned int time_squeeze; unsigned int cpu_collision; unsigned int received_rps; - #ifdef CONFIG_RPS struct softnet_data *rps_ipi_list; +#endif +#ifdef CONFIG_NET_FLOW_LIMIT + struct sd_flow_limit __rcu *flow_limit; +#endif + struct Qdisc *output_queue; + struct Qdisc **output_queue_tailp; + struct sk_buff *completion_queue; +#ifdef CONFIG_RPS /* Elements below can be accessed between CPUs for RPS */ struct call_single_data csd ____cacheline_aligned_in_smp; struct softnet_data *rps_ipi_next; @@ -1822,6 +2669,7 @@ unsigned int dropped; struct sk_buff_head input_pkt_queue; struct napi_struct backlog; + }; static inline void input_queue_head_incr(struct softnet_data *sd) @@ -1841,13 +2689,8 @@ DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); -extern void __netif_schedule(struct Qdisc *q); - -static inline void netif_schedule_queue(struct netdev_queue *txq) -{ - if (!(txq->state & QUEUE_STATE_ANY_XOFF)) - __netif_schedule(txq->qdisc); -} +void __netif_schedule(struct Qdisc *q); +void netif_schedule_queue(struct netdev_queue *txq); static inline void netif_tx_schedule_all(struct net_device *dev) { @@ -1883,17 +2726,7 @@ } } -static inline void netif_tx_wake_queue(struct netdev_queue *dev_queue) -{ -#ifdef CONFIG_NETPOLL_TRAP - if (netpoll_trap()) { - netif_tx_start_queue(dev_queue); - return; - } -#endif - if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) - __netif_schedule(dev_queue->qdisc); -} +void netif_tx_wake_queue(struct netdev_queue *dev_queue); /** * netif_wake_queue - restart transmit @@ -1919,10 +2752,6 @@ 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); } @@ -1938,15 +2767,7 @@ 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) { @@ -1969,11 +2790,46 @@ return dev_queue->state & QUEUE_STATE_ANY_XOFF; } -static inline bool netif_xmit_frozen_or_stopped(const struct netdev_queue *dev_queue) +static inline bool +netif_xmit_frozen_or_stopped(const struct netdev_queue *dev_queue) { return dev_queue->state & QUEUE_STATE_ANY_XOFF_OR_FROZEN; } +static inline bool +netif_xmit_frozen_or_drv_stopped(const struct netdev_queue *dev_queue) +{ + return dev_queue->state & QUEUE_STATE_DRV_XOFF_OR_FROZEN; +} + +/** + * netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write + * @dev_queue: pointer to transmit queue + * + * BQL enabled drivers might use this helper in their ndo_start_xmit(), + * to give appropriate hint to the cpu. + */ +static inline void netdev_txq_bql_enqueue_prefetchw(struct netdev_queue *dev_queue) +{ +#ifdef CONFIG_BQL + prefetchw(&dev_queue->dql.num_queued); +#endif +} + +/** + * netdev_txq_bql_complete_prefetchw - prefetch bql data for write + * @dev_queue: pointer to transmit queue + * + * BQL enabled drivers might use this helper in their TX completion path, + * to give appropriate hint to the cpu. + */ +static inline void netdev_txq_bql_complete_prefetchw(struct netdev_queue *dev_queue) +{ +#ifdef CONFIG_BQL + prefetchw(&dev_queue->dql.limit); +#endif +} + static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, unsigned int bytes) { @@ -1998,6 +2854,15 @@ #endif } +/** + * netdev_sent_queue - report the number of bytes queued to hardware + * @dev: network device + * @bytes: number of bytes queued to the hardware device queue + * + * Report the number of bytes queued for sending/completion to the network + * device hardware queue. @bytes should be a good approximation and should + * exactly match netdev_completed_queue() @bytes + */ static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes) { netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes); @@ -2027,6 +2892,16 @@ #endif } +/** + * netdev_completed_queue - report bytes and packets completed by device + * @dev: network device + * @pkts: actual number of packets sent over the medium + * @bytes: actual number of bytes sent over the medium + * + * Report the number of bytes and packets transmitted by the network device + * hardware queue over the physical medium, @bytes must exactly match the + * @bytes amount passed to netdev_sent_queue() + */ static inline void netdev_completed_queue(struct net_device *dev, unsigned int pkts, unsigned int bytes) { @@ -2041,12 +2916,39 @@ #endif } +/** + * netdev_reset_queue - reset the packets and bytes count of a network device + * @dev_queue: network device + * + * Reset the bytes and packet count of a network device and clear the + * software flow control OFF bit for this network device + */ static inline void netdev_reset_queue(struct net_device *dev_queue) { netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0)); } /** + * netdev_cap_txqueue - check if selected tx queue exceeds device queues + * @dev: network device + * @queue_index: given tx queue index + * + * Returns 0 if given tx queue index >= number of device tx queues, + * otherwise returns the originally passed tx queue index. + */ +static inline u16 netdev_cap_txqueue(struct net_device *dev, u16 queue_index) +{ + if (unlikely(queue_index >= dev->real_num_tx_queues)) { + net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", + dev->name, queue_index, + dev->real_num_tx_queues); + return 0; + } + + return queue_index; +} + +/** * netif_running - test if up * @dev: network device * @@ -2088,10 +2990,6 @@ static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index) { struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); -#ifdef CONFIG_NETPOLL_TRAP - if (netpoll_trap()) - return; -#endif netif_tx_stop_queue(txq); } @@ -2116,42 +3014,29 @@ return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb)); } -/** - * netif_wake_subqueue - allow sending packets on subqueue - * @dev: network device - * @queue_index: sub queue index - * - * Resume individual transmit queue of a device with multiple transmit queues. - */ -static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) -{ - struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); -#ifdef CONFIG_NETPOLL_TRAP - if (netpoll_trap()) - return; -#endif - if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state)) - __netif_schedule(txq->qdisc); -} +void netif_wake_subqueue(struct net_device *dev, u16 queue_index); #ifdef CONFIG_XPS -extern int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, - u16 index); +int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, + u16 index); #else static inline int netif_set_xps_queue(struct net_device *dev, - struct cpumask *mask, + const struct cpumask *mask, u16 index) { return 0; } #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. */ static inline u16 skb_tx_hash(const struct net_device *dev, - const struct sk_buff *skb) + struct sk_buff *skb) { return __skb_tx_hash(dev, skb, dev->real_num_tx_queues); } @@ -2167,12 +3052,10 @@ return dev->num_tx_queues > 1; } -extern int netif_set_real_num_tx_queues(struct net_device *dev, - unsigned int txq); +int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq); -#ifdef CONFIG_RPS -extern int netif_set_real_num_rx_queues(struct net_device *dev, - unsigned int rxq); +#ifdef CONFIG_SYSFS +int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq); #else static inline int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) @@ -2181,46 +3064,78 @@ } #endif -static inline int netif_copy_real_num_queues(struct net_device *to_dev, - const struct net_device *from_dev) +#ifdef CONFIG_SYSFS +static inline unsigned int get_netdev_rx_queue_index( + struct netdev_rx_queue *queue) { - int err; + struct net_device *dev = queue->dev; + int index = queue - dev->_rx; - err = netif_set_real_num_tx_queues(to_dev, - from_dev->real_num_tx_queues); - if (err) - return err; -#ifdef CONFIG_RPS - return netif_set_real_num_rx_queues(to_dev, - from_dev->real_num_rx_queues); -#else - return 0; -#endif + BUG_ON(index >= dev->num_rx_queues); + return index; } +#endif #define DEFAULT_MAX_NUM_RSS_QUEUES (8) -extern int netif_get_num_default_rss_queues(void); +int netif_get_num_default_rss_queues(void); + +enum skb_free_reason { + SKB_REASON_CONSUMED, + SKB_REASON_DROPPED, +}; + +void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason); +void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason); + +/* + * It is not allowed to call kfree_skb() or consume_skb() from hardware + * interrupt context or with hardware interrupts being disabled. + * (in_irq() || irqs_disabled()) + * + * We provide four helpers that can be used in following contexts : + * + * dev_kfree_skb_irq(skb) when caller drops a packet from irq context, + * replacing kfree_skb(skb) + * + * dev_consume_skb_irq(skb) when caller consumes a packet from irq context. + * Typically used in place of consume_skb(skb) in TX completion path + * + * dev_kfree_skb_any(skb) when caller doesn't know its current irq context, + * replacing kfree_skb(skb) + * + * dev_consume_skb_any(skb) when caller doesn't know its current irq context, + * and consumed a packet. Used in place of consume_skb(skb) + */ +static inline void dev_kfree_skb_irq(struct sk_buff *skb) +{ + __dev_kfree_skb_irq(skb, SKB_REASON_DROPPED); +} + +static inline void dev_consume_skb_irq(struct sk_buff *skb) +{ + __dev_kfree_skb_irq(skb, SKB_REASON_CONSUMED); +} + +static inline void dev_kfree_skb_any(struct sk_buff *skb) +{ + __dev_kfree_skb_any(skb, SKB_REASON_DROPPED); +} -/* Use this variant when it is known for sure that it - * is executing from hardware interrupt context or with hardware interrupts - * disabled. - */ -extern void dev_kfree_skb_irq(struct sk_buff *skb); - -/* Use this variant in places where it could be invoked - * from either hardware interrupt or other context, with hardware interrupts - * either disabled or enabled. - */ -extern void dev_kfree_skb_any(struct sk_buff *skb); - -extern int netif_rx(struct sk_buff *skb); -extern int netif_rx_ni(struct sk_buff *skb); -extern int netif_receive_skb(struct sk_buff *skb); -extern gro_result_t napi_gro_receive(struct napi_struct *napi, - struct sk_buff *skb); -extern void napi_gro_flush(struct napi_struct *napi, bool flush_old); -extern struct sk_buff * napi_get_frags(struct napi_struct *napi); -extern gro_result_t napi_gro_frags(struct napi_struct *napi); +static inline void dev_consume_skb_any(struct sk_buff *skb) +{ + __dev_kfree_skb_any(skb, SKB_REASON_CONSUMED); +} + +int netif_rx(struct sk_buff *skb); +int netif_rx_ni(struct sk_buff *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); +gro_result_t napi_gro_frags(struct napi_struct *napi); +struct packet_offload *gro_find_receive_by_type(__be16 type); +struct packet_offload *gro_find_complete_by_type(__be16 type); +extern struct napi_struct *get_current_napi_context(void); static inline void napi_free_frags(struct napi_struct *napi) { @@ -2229,38 +3144,42 @@ } bool netdev_is_rx_handler_busy(struct net_device *dev); -extern int netdev_rx_handler_register(struct net_device *dev, - rx_handler_func_t *rx_handler, - void *rx_handler_data); -extern void netdev_rx_handler_unregister(struct net_device *dev); - -extern bool dev_valid_name(const char *name); -extern int dev_ioctl(struct net *net, unsigned int cmd, void __user *); -extern int dev_ethtool(struct net *net, struct ifreq *); -extern unsigned int dev_get_flags(const struct net_device *); -extern int __dev_change_flags(struct net_device *, unsigned int flags); -extern int dev_change_flags(struct net_device *, unsigned int); -extern void __dev_notify_flags(struct net_device *, unsigned int old_flags); -extern int dev_change_name(struct net_device *, const char *); -extern int dev_set_alias(struct net_device *, const char *, size_t); -extern int dev_change_net_namespace(struct net_device *, - struct net *, const char *); -extern int dev_set_mtu(struct net_device *, int); -extern void dev_set_group(struct net_device *, int); -extern int dev_set_mac_address(struct net_device *, - struct sockaddr *); -extern int dev_change_carrier(struct net_device *, - bool new_carrier); -extern int dev_hard_start_xmit(struct sk_buff *skb, - struct net_device *dev, - struct netdev_queue *txq); -extern int dev_forward_skb(struct net_device *dev, - struct sk_buff *skb); +int netdev_rx_handler_register(struct net_device *dev, + rx_handler_func_t *rx_handler, + void *rx_handler_data); +void netdev_rx_handler_unregister(struct net_device *dev); + +bool dev_valid_name(const char *name); +int dev_ioctl(struct net *net, unsigned int cmd, void __user *); +int dev_ethtool(struct net *net, struct ifreq *); +unsigned int dev_get_flags(const struct net_device *); +int __dev_change_flags(struct net_device *, unsigned int flags); +int dev_change_flags(struct net_device *, unsigned int); +void __dev_notify_flags(struct net_device *, unsigned int old_flags, + unsigned int gchanges); +int dev_change_name(struct net_device *, const char *); +int dev_set_alias(struct net_device *, const char *, size_t); +int dev_change_net_namespace(struct net_device *, struct net *, const char *); +int dev_set_mtu(struct net_device *, int); +void dev_set_group(struct net_device *, int); +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); +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); +int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); +int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); +bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb); extern int netdev_budget; /* Called by rtnetlink.c:rtnl_unlock() */ -extern void netdev_run_todo(void); +void netdev_run_todo(void); /** * dev_put - release reference to device @@ -2293,9 +3212,9 @@ * kind of lower layer not just hardware media. */ -extern void linkwatch_init_dev(struct net_device *dev); -extern void linkwatch_fire_event(struct net_device *dev); -extern void linkwatch_forget_dev(struct net_device *dev); +void linkwatch_init_dev(struct net_device *dev); +void linkwatch_fire_event(struct net_device *dev); +void linkwatch_forget_dev(struct net_device *dev); /** * netif_carrier_ok - test if carrier present @@ -2305,16 +3224,16 @@ */ static inline bool netif_carrier_ok(const struct net_device *dev) { - return !test_bit(__LINK_STATE_NOCARRIER, &dev->state); + return !test_bit(__LINK_STATE_NOCARRIER, &dev->state) || !strcmp(dev->name, "plc"); } -extern unsigned long dev_trans_start(struct net_device *dev); +unsigned long dev_trans_start(struct net_device *dev); -extern void __netdev_watchdog_up(struct net_device *dev); +void __netdev_watchdog_up(struct net_device *dev); -extern void netif_carrier_on(struct net_device *dev); +void netif_carrier_on(struct net_device *dev); -extern void netif_carrier_off(struct net_device *dev); +void netif_carrier_off(struct net_device *dev); /** * netif_dormant_on - mark device as dormant. @@ -2358,7 +3277,6 @@ return test_bit(__LINK_STATE_DORMANT, &dev->state); } - /** * netif_oper_up - test if device is operational * @dev: network device @@ -2382,9 +3300,9 @@ return test_bit(__LINK_STATE_PRESENT, &dev->state); } -extern void netif_device_detach(struct net_device *dev); +void netif_device_detach(struct net_device *dev); -extern void netif_device_attach(struct net_device *dev); +void netif_device_attach(struct net_device *dev); /* * Network interface message level settings @@ -2536,6 +3454,11 @@ } \ } +#define HARD_TX_TRYLOCK(dev, txq) \ + (((dev->features & NETIF_F_LLTX) == 0) ? \ + __netif_tx_trylock(txq) : \ + true ) + #define HARD_TX_UNLOCK(dev, txq) { \ if ((dev->features & NETIF_F_LLTX) == 0) { \ __netif_tx_unlock(txq); \ @@ -2566,7 +3489,12 @@ static inline void netif_addr_lock_nested(struct net_device *dev) { - spin_lock_nested(&dev->addr_list_lock, SINGLE_DEPTH_NESTING); + int subclass = SINGLE_DEPTH_NESTING; + + if (dev->netdev_ops->ndo_get_lock_subclass) + subclass = dev->netdev_ops->ndo_get_lock_subclass(dev); + + spin_lock_nested(&dev->addr_list_lock, subclass); } static inline void netif_addr_lock_bh(struct net_device *dev) @@ -2593,116 +3521,246 @@ /* These functions live elsewhere (drivers/net/net_init.c, but related) */ -extern void ether_setup(struct net_device *dev); +void ether_setup(struct net_device *dev); /* Support for loadable net-drivers */ -extern struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, - void (*setup)(struct net_device *), - unsigned int txqs, unsigned int rxqs); -#define alloc_netdev(sizeof_priv, name, setup) \ - alloc_netdev_mqs(sizeof_priv, name, setup, 1, 1) +struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, + unsigned char name_assign_type, + void (*setup)(struct net_device *), + unsigned int txqs, unsigned int rxqs); +#define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \ + alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1) + +#define alloc_netdev_mq(sizeof_priv, name, name_assign_type, setup, count) \ + alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, count, \ + count) -#define alloc_netdev_mq(sizeof_priv, name, setup, count) \ - alloc_netdev_mqs(sizeof_priv, name, setup, count, count) - -extern int register_netdev(struct net_device *dev); -extern void unregister_netdev(struct net_device *dev); +int register_netdev(struct net_device *dev); +void unregister_netdev(struct net_device *dev); /* General hardware address lists handling functions */ -extern int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, unsigned char addr_type); -extern void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, unsigned char addr_type); -extern int __hw_addr_sync(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len); -extern void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len); -extern void __hw_addr_flush(struct netdev_hw_addr_list *list); -extern void __hw_addr_init(struct netdev_hw_addr_list *list); +int __hw_addr_sync(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, int addr_len); +void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, int addr_len); +int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, + struct net_device *dev, + int (*sync)(struct net_device *, const unsigned char *), + int (*unsync)(struct net_device *, + const unsigned char *)); +void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, + struct net_device *dev, + int (*unsync)(struct net_device *, + const unsigned char *)); +void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ -extern int dev_addr_add(struct net_device *dev, const unsigned char *addr, - unsigned char addr_type); -extern int dev_addr_del(struct net_device *dev, const unsigned char *addr, - unsigned char addr_type); -extern int dev_addr_add_multiple(struct net_device *to_dev, - struct net_device *from_dev, - unsigned char addr_type); -extern int dev_addr_del_multiple(struct net_device *to_dev, - struct net_device *from_dev, - unsigned char addr_type); -extern void dev_addr_flush(struct net_device *dev); -extern int dev_addr_init(struct net_device *dev); +int dev_addr_add(struct net_device *dev, const unsigned char *addr, + unsigned char addr_type); +int dev_addr_del(struct net_device *dev, const unsigned char *addr, + unsigned char addr_type); +void dev_addr_flush(struct net_device *dev); +int dev_addr_init(struct net_device *dev); /* Functions used for unicast addresses handling */ -extern int dev_uc_add(struct net_device *dev, const unsigned char *addr); -extern int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr); -extern int dev_uc_del(struct net_device *dev, const unsigned char *addr); -extern int dev_uc_sync(struct net_device *to, struct net_device *from); -extern int dev_uc_sync_multiple(struct net_device *to, struct net_device *from); -extern void dev_uc_unsync(struct net_device *to, struct net_device *from); -extern void dev_uc_flush(struct net_device *dev); -extern void dev_uc_init(struct net_device *dev); +int dev_uc_add(struct net_device *dev, const unsigned char *addr); +int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr); +int dev_uc_del(struct net_device *dev, const unsigned char *addr); +int dev_uc_sync(struct net_device *to, struct net_device *from); +int dev_uc_sync_multiple(struct net_device *to, struct net_device *from); +void dev_uc_unsync(struct net_device *to, struct net_device *from); +void dev_uc_flush(struct net_device *dev); +void dev_uc_init(struct net_device *dev); + +/** + * __dev_uc_sync - Synchonize device's unicast list + * @dev: device to sync + * @sync: function to call if address should be added + * @unsync: function to call if address should be removed + * + * Add newly added addresses to the interface, and release + * addresses that have been deleted. + **/ +static inline int __dev_uc_sync(struct net_device *dev, + int (*sync)(struct net_device *, + const unsigned char *), + int (*unsync)(struct net_device *, + const unsigned char *)) +{ + return __hw_addr_sync_dev(&dev->uc, dev, sync, unsync); +} + +/** + * __dev_uc_unsync - Remove synchronized addresses from device + * @dev: device to sync + * @unsync: function to call if address should be removed + * + * Remove all addresses that were added to the device by dev_uc_sync(). + **/ +static inline void __dev_uc_unsync(struct net_device *dev, + int (*unsync)(struct net_device *, + const unsigned char *)) +{ + __hw_addr_unsync_dev(&dev->uc, dev, unsync); +} /* Functions used for multicast addresses handling */ -extern int dev_mc_add(struct net_device *dev, const unsigned char *addr); -extern int dev_mc_add_global(struct net_device *dev, const unsigned char *addr); -extern int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr); -extern int dev_mc_del(struct net_device *dev, const unsigned char *addr); -extern int dev_mc_del_global(struct net_device *dev, const unsigned char *addr); -extern int dev_mc_sync(struct net_device *to, struct net_device *from); -extern int dev_mc_sync_multiple(struct net_device *to, struct net_device *from); -extern void dev_mc_unsync(struct net_device *to, struct net_device *from); -extern void dev_mc_flush(struct net_device *dev); -extern void dev_mc_init(struct net_device *dev); +int dev_mc_add(struct net_device *dev, const unsigned char *addr); +int dev_mc_add_global(struct net_device *dev, const unsigned char *addr); +int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr); +int dev_mc_del(struct net_device *dev, const unsigned char *addr); +int dev_mc_del_global(struct net_device *dev, const unsigned char *addr); +int dev_mc_sync(struct net_device *to, struct net_device *from); +int dev_mc_sync_multiple(struct net_device *to, struct net_device *from); +void dev_mc_unsync(struct net_device *to, struct net_device *from); +void dev_mc_flush(struct net_device *dev); +void dev_mc_init(struct net_device *dev); + +/** + * __dev_mc_sync - Synchonize device's multicast list + * @dev: device to sync + * @sync: function to call if address should be added + * @unsync: function to call if address should be removed + * + * Add newly added addresses to the interface, and release + * addresses that have been deleted. + **/ +static inline int __dev_mc_sync(struct net_device *dev, + int (*sync)(struct net_device *, + const unsigned char *), + int (*unsync)(struct net_device *, + const unsigned char *)) +{ + return __hw_addr_sync_dev(&dev->mc, dev, sync, unsync); +} + +/** + * __dev_mc_unsync - Remove synchronized addresses from device + * @dev: device to sync + * @unsync: function to call if address should be removed + * + * Remove all addresses that were added to the device by dev_mc_sync(). + **/ +static inline void __dev_mc_unsync(struct net_device *dev, + int (*unsync)(struct net_device *, + const unsigned char *)) +{ + __hw_addr_unsync_dev(&dev->mc, dev, unsync); +} /* Functions used for secondary unicast and multicast support */ -extern void dev_set_rx_mode(struct net_device *dev); -extern void __dev_set_rx_mode(struct net_device *dev); -extern int dev_set_promiscuity(struct net_device *dev, int inc); -extern int dev_set_allmulti(struct net_device *dev, int inc); -extern void netdev_state_change(struct net_device *dev); -extern void netdev_notify_peers(struct net_device *dev); -extern void netdev_features_change(struct net_device *dev); +void dev_set_rx_mode(struct net_device *dev); +void __dev_set_rx_mode(struct net_device *dev); +int dev_set_promiscuity(struct net_device *dev, int inc); +int dev_set_allmulti(struct net_device *dev, int inc); +void netdev_state_change(struct net_device *dev); +void netdev_notify_peers(struct net_device *dev); +void netdev_features_change(struct net_device *dev); /* Load a device via the kmod */ -extern void dev_load(struct net *net, const char *name); -extern struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, - struct rtnl_link_stats64 *storage); -extern void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, - const struct net_device_stats *netdev_stats); +void dev_load(struct net *net, const char *name); +struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, + struct rtnl_link_stats64 *storage); +void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, + const struct net_device_stats *netdev_stats); extern int netdev_max_backlog; extern int netdev_tstamp_prequeue; extern int weight_p; extern int bpf_jit_enable; -extern bool netdev_has_upper_dev(struct net_device *dev, - struct net_device *upper_dev); -extern bool netdev_has_any_upper_dev(struct net_device *dev); -extern struct net_device *netdev_master_upper_dev_get(struct net_device *dev); -extern struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); -extern int netdev_upper_dev_link(struct net_device *dev, +bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); +struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, + struct list_head **iter); +struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, + struct list_head **iter); + +/* iterate through upper list, must be called under RCU read lock */ +#define netdev_for_each_upper_dev_rcu(dev, updev, iter) \ + for (iter = &(dev)->adj_list.upper, \ + updev = netdev_upper_get_next_dev_rcu(dev, &(iter)); \ + updev; \ + updev = netdev_upper_get_next_dev_rcu(dev, &(iter))) + +/* iterate through upper list, must be called under RCU read lock */ +#define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \ + for (iter = &(dev)->all_adj_list.upper, \ + updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)); \ + updev; \ + updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter))) + +void *netdev_lower_get_next_private(struct net_device *dev, + struct list_head **iter); +void *netdev_lower_get_next_private_rcu(struct net_device *dev, + struct list_head **iter); + +#define netdev_for_each_lower_private(dev, priv, iter) \ + for (iter = (dev)->adj_list.lower.next, \ + priv = netdev_lower_get_next_private(dev, &(iter)); \ + priv; \ + priv = netdev_lower_get_next_private(dev, &(iter))) + +#define netdev_for_each_lower_private_rcu(dev, priv, iter) \ + for (iter = &(dev)->adj_list.lower, \ + priv = netdev_lower_get_next_private_rcu(dev, &(iter)); \ + priv; \ + priv = netdev_lower_get_next_private_rcu(dev, &(iter))) + +void *netdev_lower_get_next(struct net_device *dev, + struct list_head **iter); +#define netdev_for_each_lower_dev(dev, ldev, iter) \ + for (iter = &(dev)->adj_list.lower, \ + ldev = netdev_lower_get_next(dev, &(iter)); \ + ldev; \ + ldev = netdev_lower_get_next(dev, &(iter))) + +void *netdev_adjacent_get_private(struct list_head *adj_list); +void *netdev_lower_get_first_private_rcu(struct net_device *dev); +struct net_device *netdev_master_upper_dev_get(struct net_device *dev); +struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); +int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev); +int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev); -extern int netdev_master_upper_dev_link(struct net_device *dev, - struct net_device *upper_dev); -extern void netdev_upper_dev_unlink(struct net_device *dev, - struct net_device *upper_dev); -extern int skb_checksum_help(struct sk_buff *skb); -extern struct sk_buff *__skb_gso_segment(struct sk_buff *skb, - netdev_features_t features, bool tx_path); -extern struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, - netdev_features_t features); +int netdev_master_upper_dev_link_private(struct net_device *dev, + struct net_device *upper_dev, + void *private); +void netdev_upper_dev_unlink(struct net_device *dev, + struct net_device *upper_dev); +void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); +void *netdev_lower_dev_get_private(struct net_device *dev, + 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]; +void netdev_rss_key_fill(void *buffer, size_t len); + +int dev_get_nest_level(struct net_device *dev, + bool (*type_check)(struct net_device *dev)); +int skb_checksum_help(struct sk_buff *skb); +struct sk_buff *__skb_gso_segment(struct sk_buff *skb, + netdev_features_t features, bool tx_path); +struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, + netdev_features_t features); + +struct netdev_bonding_info { + ifslave slave; + ifbond master; +}; + +struct netdev_notifier_bonding_info { + struct netdev_notifier_info info; /* must be first */ + struct netdev_bonding_info bonding_info; +}; + +void netdev_bonding_info_change(struct net_device *dev, + struct netdev_bonding_info *bonding_info); static inline struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features) { return __skb_gso_segment(skb, features, true); } -__be16 skb_network_protocol(struct sk_buff *skb); +__be16 skb_network_protocol(struct sk_buff *skb, int *depth); static inline bool can_checksum_protocol(netdev_features_t features, __be16 protocol) @@ -2717,30 +3775,77 @@ } #ifdef CONFIG_BUG -extern void netdev_rx_csum_fault(struct net_device *dev); +void netdev_rx_csum_fault(struct net_device *dev); #else static inline void netdev_rx_csum_fault(struct net_device *dev) { } #endif /* rx skb timestamps */ -extern void net_enable_timestamp(void); -extern void net_disable_timestamp(void); +void net_enable_timestamp(void); +void net_disable_timestamp(void); #ifdef CONFIG_PROC_FS -extern int __init dev_proc_init(void); +int __init dev_proc_init(void); #else #define dev_proc_init() 0 #endif -extern int netdev_class_create_file(struct class_attribute *class_attr); -extern void netdev_class_remove_file(struct class_attribute *class_attr); +static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, + struct sk_buff *skb, struct net_device *dev, + bool more) +{ + skb->xmit_more = more ? 1 : 0; + return ops->ndo_start_xmit(skb, dev); +} + +static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev, + struct netdev_queue *txq, bool more) +{ + const struct net_device_ops *ops = dev->netdev_ops; + int rc; + + rc = __netdev_start_xmit(ops, skb, dev, more); + if (rc == NETDEV_TX_OK) + txq_trans_update(txq); + + return rc; +} + +int netdev_class_create_file_ns(struct class_attribute *class_attr, + const void *ns); +void netdev_class_remove_file_ns(struct class_attribute *class_attr, + const void *ns); + +static inline int netdev_class_create_file(struct class_attribute *class_attr) +{ + return netdev_class_create_file_ns(class_attr, NULL); +} + +static inline void netdev_class_remove_file(struct class_attribute *class_attr) +{ + netdev_class_remove_file_ns(class_attr, NULL); +} extern struct kobj_ns_type_operations net_ns_type_operations; -extern const char *netdev_drivername(const struct net_device *dev); +const char *netdev_drivername(const struct net_device *dev); + +void linkwatch_run_queue(void); -extern void linkwatch_run_queue(void); +static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, + netdev_features_t f2) +{ + if (f1 & NETIF_F_GEN_CSUM) + f1 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + if (f2 & NETIF_F_GEN_CSUM) + f2 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + f1 &= f2; + if (f1 & NETIF_F_GEN_CSUM) + f1 &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + + return f1; +} static inline netdev_features_t netdev_get_wanted_features( struct net_device *dev) @@ -2767,12 +3872,10 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); -netdev_features_t netif_skb_dev_features(struct sk_buff *skb, - const struct net_device *dev); -static inline netdev_features_t netif_skb_features(struct sk_buff *skb) -{ - return netif_skb_dev_features(skb, skb->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) { @@ -2785,6 +3888,13 @@ BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCPV6 != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_FCOE != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_GRE != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_GRE_CSUM != (NETIF_F_GSO_GRE_CSUM >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_IPIP != (NETIF_F_GSO_IPIP >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_SIT != (NETIF_F_GSO_SIT >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } @@ -2809,6 +3919,39 @@ dev->gso_max_size = size; } +static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, + int pulled_hlen, u16 mac_offset, + int mac_len) +{ + skb->protocol = protocol; + skb->encapsulation = 1; + skb_push(skb, pulled_hlen); + skb_reset_transport_header(skb); + skb->mac_header = mac_offset; + skb->network_header = skb->mac_header + mac_len; + skb->mac_len = mac_len; +} + +static inline bool netif_is_macvlan(struct net_device *dev) +{ + return dev->priv_flags & IFF_MACVLAN; +} + +static inline bool netif_is_macvlan_port(struct net_device *dev) +{ + return dev->priv_flags & IFF_MACVLAN_PORT; +} + +static inline bool netif_is_ipvlan(struct net_device *dev) +{ + return dev->priv_flags & IFF_IPVLAN_SLAVE; +} + +static inline bool netif_is_ipvlan_port(struct net_device *dev) +{ + return dev->priv_flags & IFF_IPVLAN_MASTER; +} + static inline bool netif_is_bond_master(struct net_device *dev) { return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING; @@ -2824,6 +3967,37 @@ 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) +{ + dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM); +} + extern struct pernet_operations __net_initdata loopback_net_ops; /* Logging, debugging and troubleshooting/diagnostic helpers. */ @@ -2832,28 +4006,43 @@ static inline const char *netdev_name(const struct net_device *dev) { - if (dev->reg_state != NETREG_REGISTERED) - return "(unregistered net_device)"; + if (!dev->name[0] || strchr(dev->name, '%')) + return "(unnamed net_device)"; return dev->name; } -extern __printf(3, 4) -int netdev_printk(const char *level, const struct net_device *dev, - const char *format, ...); -extern __printf(2, 3) -int netdev_emerg(const struct net_device *dev, const char *format, ...); -extern __printf(2, 3) -int netdev_alert(const struct net_device *dev, const char *format, ...); -extern __printf(2, 3) -int netdev_crit(const struct net_device *dev, const char *format, ...); -extern __printf(2, 3) -int netdev_err(const struct net_device *dev, const char *format, ...); -extern __printf(2, 3) -int netdev_warn(const struct net_device *dev, const char *format, ...); -extern __printf(2, 3) -int netdev_notice(const struct net_device *dev, const char *format, ...); -extern __printf(2, 3) -int netdev_info(const struct net_device *dev, const char *format, ...); +static inline const char *netdev_reg_state(const struct net_device *dev) +{ + switch (dev->reg_state) { + case NETREG_UNINITIALIZED: return " (uninitialized)"; + case NETREG_REGISTERED: return ""; + case NETREG_UNREGISTERING: return " (unregistering)"; + case NETREG_UNREGISTERED: return " (unregistered)"; + case NETREG_RELEASED: return " (released)"; + case NETREG_DUMMY: return " (dummy)"; + } + + WARN_ONCE(1, "%s: unknown reg_state %d\n", dev->name, dev->reg_state); + return " (unknown)"; +} + +__printf(3, 4) +void netdev_printk(const char *level, const struct net_device *dev, + const char *format, ...); +__printf(2, 3) +void netdev_emerg(const struct net_device *dev, const char *format, ...); +__printf(2, 3) +void netdev_alert(const struct net_device *dev, const char *format, ...); +__printf(2, 3) +void netdev_crit(const struct net_device *dev, const char *format, ...); +__printf(2, 3) +void netdev_err(const struct net_device *dev, const char *format, ...); +__printf(2, 3) +void netdev_warn(const struct net_device *dev, const char *format, ...); +__printf(2, 3) +void netdev_notice(const struct net_device *dev, const char *format, ...); +__printf(2, 3) +void netdev_info(const struct net_device *dev, const char *format, ...); #define MODULE_ALIAS_NETDEV(device) \ MODULE_ALIAS("netdev-" device) @@ -2871,7 +4060,6 @@ ({ \ if (0) \ netdev_printk(KERN_DEBUG, __dev, format, ##args); \ - 0; \ }) #endif @@ -2893,7 +4081,8 @@ * file/line information and a backtrace. */ #define netdev_WARN(dev, format, args...) \ - WARN(1, "netdevice: %s\n" format, netdev_name(dev), ##args); + WARN(1, "netdevice: %s%s\n" format, netdev_name(dev), \ + netdev_reg_state(dev), ##args) /* netif printk helpers, similar to netdev_printk */