/* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the Interfaces handler. * * Version: @(#)dev.h 1.0.10 08/12/93 * * Authors: Ross Biro * Fred N. van Kempen, * Corey Minyard * Donald J. Becker, * Alan Cox, * Bjorn Ekwall. * Pekka Riikonen * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * * Moved to /usr/include/linux for NET3 */ #ifndef _LINUX_NETDEVICE_H #define _LINUX_NETDEVICE_H #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #ifdef CONFIG_DCB #include #endif #include #include #include #include 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) ) 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() */ /* Backlog congestion levels */ #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ #define NET_RX_DROP 1 /* packet dropped */ /* * Transmit return codes: transmit return codes originate from three different * namespaces: * * - qdisc return codes * - driver transmit return codes * - errno values * * Drivers are allowed to return any one of those in their hard_start_xmit() * function. Real network devices commonly used with qdiscs should only return * the driver transmit return codes though - when qdiscs are used, the actual * transmission happens asynchronously, so the value is not propagated to * higher layers. Virtual network devices transmit synchronously, in this case * the driver transmit return codes are consumed by dev_queue_xmit(), all * others are propagated to higher layers. */ /* qdisc ->enqueue() return codes. */ #define NET_XMIT_SUCCESS 0x00 #define NET_XMIT_DROP 0x01 /* skb dropped */ #define NET_XMIT_CN 0x02 /* congestion notification */ #define NET_XMIT_POLICED 0x03 /* skb is shot by police */ #define NET_XMIT_MASK 0x0f /* qdisc flags in net/sch_generic.h */ /* NET_XMIT_CN is special. It does not guarantee that this packet is lost. It * indicates that the device will soon be dropping packets, or already drops * some packets of the same priority; prompting us to send less aggressively. */ #define net_xmit_eval(e) ((e) == NET_XMIT_CN ? 0 : (e)) #define net_xmit_errno(e) ((e) != NET_XMIT_CN ? -ENOBUFS : 0) /* Driver transmit return codes */ #define NETDEV_TX_MASK 0xf0 enum netdev_tx { __NETDEV_TX_MIN = INT_MIN, /* make sure enum is signed */ NETDEV_TX_OK = 0x00, /* driver took care of packet */ NETDEV_TX_BUSY = 0x10, /* driver tx path was busy*/ NETDEV_TX_LOCKED = 0x20, /* driver tx lock was already taken */ }; typedef enum netdev_tx netdev_tx_t; /* * Current order: NETDEV_TX_MASK > NET_XMIT_MASK >= 0 is significant; * hard_start_xmit() return < NET_XMIT_MASK means skb was consumed. */ static inline bool dev_xmit_complete(int rc) { /* * Positive cases with an skb consumed by a driver: * - successful transmission (rc == NETDEV_TX_OK) * - error while transmitting (rc < 0) * - error while queueing to a different device (rc & NET_XMIT_MASK) */ if (likely(rc < NET_XMIT_MASK)) return true; return false; } /* * Compute the worst case header length according to the protocols * used. */ #if defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25) # if defined(CONFIG_MAC80211_MESH) # define LL_MAX_HEADER 128 # else # define LL_MAX_HEADER 96 # endif #else # define LL_MAX_HEADER 32 #endif #if !IS_ENABLED(CONFIG_NET_IPIP) && !IS_ENABLED(CONFIG_NET_IPGRE) && \ !IS_ENABLED(CONFIG_IPV6_SIT) && !IS_ENABLED(CONFIG_IPV6_TUNNEL) #define MAX_HEADER LL_MAX_HEADER #else #define MAX_HEADER (LL_MAX_HEADER + 48) #endif /* * Old network device statistics. Fields are native words * (unsigned long) so they can be read and written atomically. */ struct net_device_stats { unsigned long rx_packets; unsigned long tx_packets; unsigned long rx_bytes; unsigned long tx_bytes; unsigned long rx_errors; unsigned long tx_errors; unsigned long rx_dropped; unsigned long tx_dropped; unsigned long multicast; unsigned long collisions; unsigned long rx_length_errors; unsigned long rx_over_errors; unsigned long rx_crc_errors; unsigned long rx_frame_errors; unsigned long rx_fifo_errors; unsigned long rx_missed_errors; unsigned long tx_aborted_errors; unsigned long tx_carrier_errors; unsigned long tx_fifo_errors; unsigned long tx_heartbeat_errors; unsigned long tx_window_errors; unsigned long rx_compressed; unsigned long tx_compressed; }; #include #include #ifdef CONFIG_RPS #include extern struct static_key rps_needed; #endif struct neighbour; struct neigh_parms; struct sk_buff; struct netdev_hw_addr { struct list_head list; unsigned char addr[MAX_ADDR_LEN]; unsigned char type; #define NETDEV_HW_ADDR_T_LAN 1 #define NETDEV_HW_ADDR_T_SAN 2 #define NETDEV_HW_ADDR_T_SLAVE 3 #define NETDEV_HW_ADDR_T_UNICAST 4 #define NETDEV_HW_ADDR_T_MULTICAST 5 bool global_use; int sync_cnt; int refcount; int synced; struct rcu_head rcu_head; }; struct netdev_hw_addr_list { struct list_head list; int count; }; #define netdev_hw_addr_list_count(l) ((l)->count) #define netdev_hw_addr_list_empty(l) (netdev_hw_addr_list_count(l) == 0) #define netdev_hw_addr_list_for_each(ha, l) \ list_for_each_entry(ha, &(l)->list, list) #define netdev_uc_count(dev) netdev_hw_addr_list_count(&(dev)->uc) #define netdev_uc_empty(dev) netdev_hw_addr_list_empty(&(dev)->uc) #define netdev_for_each_uc_addr(ha, dev) \ netdev_hw_addr_list_for_each(ha, &(dev)->uc) #define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc) #define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc) #define netdev_for_each_mc_addr(ha, dev) \ netdev_hw_addr_list_for_each(ha, &(dev)->mc) struct hh_cache { u16 hh_len; u16 __pad; seqlock_t hh_lock; /* cached hardware header; allow for machine alignment needs. */ #define HH_DATA_MOD 16 #define HH_DATA_OFF(__len) \ (HH_DATA_MOD - (((__len - 1) & (HH_DATA_MOD - 1)) + 1)) #define HH_DATA_ALIGN(__len) \ (((__len)+(HH_DATA_MOD-1))&~(HH_DATA_MOD - 1)) unsigned long hh_data[HH_DATA_ALIGN(LL_MAX_HEADER) / sizeof(long)]; }; /* Reserve HH_DATA_MOD byte aligned hard_header_len, but at least that much. * Alternative is: * dev->hard_header_len ? (dev->hard_header_len + * (HH_DATA_MOD - 1)) & ~(HH_DATA_MOD - 1) : 0 * * We could use other alignment values, but we must maintain the * relationship HH alignment <= LL alignment. */ #define LL_RESERVED_SPACE(dev) \ ((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ ((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) struct header_ops { int (*create) (struct sk_buff *skb, struct net_device *dev, 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); }; /* These flag bits are private to the generic network queueing * layer, they may not be explicitly referenced by any other * code. */ enum netdev_state_t { __LINK_STATE_START, __LINK_STATE_PRESENT, __LINK_STATE_NOCARRIER, __LINK_STATE_LINKWATCH_PENDING, __LINK_STATE_DORMANT, }; /* * This structure holds at boot time configured netdevice settings. They * are then used in the device probing. */ struct netdev_boot_setup { char name[IFNAMSIZ]; struct ifmap map; }; #define NETDEV_BOOT_SETUP_MAX 8 int __init netdev_boot_setup(char *str); /* * Structure for NAPI scheduling similar to tasklet but with weighting */ struct napi_struct { /* The poll_list must only be managed by the entity which * changes the state of the NAPI_STATE_SCHED bit. This means * whoever atomically sets that bit can add this napi_struct * to the per-cpu poll_list, and whoever clears that bit * can remove from the list right before clearing the bit. */ struct list_head poll_list; unsigned long state; int weight; unsigned int gro_count; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL spinlock_t poll_lock; int poll_owner; #endif struct net_device *dev; struct sk_buff *gro_list; struct sk_buff *skb; 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 { GRO_MERGED, GRO_MERGED_FREE, GRO_HELD, GRO_NORMAL, GRO_DROP, }; typedef enum gro_result gro_result_t; /* * enum rx_handler_result - Possible return values for rx_handlers. * @RX_HANDLER_CONSUMED: skb was consumed by rx_handler, do not process it * further. * @RX_HANDLER_ANOTHER: Do another round in receive path. This is indicated in * case skb->dev was changed by rx_handler. * @RX_HANDLER_EXACT: Force exact delivery, no wildcard. * @RX_HANDLER_PASS: Do nothing, passe the skb as if no rx_handler was called. * * rx_handlers are functions called from inside __netif_receive_skb(), to do * special processing of the skb, prior to delivery to protocol handlers. * * Currently, a net_device can only have a single rx_handler registered. Trying * to register a second rx_handler will return -EBUSY. * * To register a rx_handler on a net_device, use netdev_rx_handler_register(). * To unregister a rx_handler on a net_device, use * netdev_rx_handler_unregister(). * * Upon return, rx_handler is expected to tell __netif_receive_skb() what to * do with the skb. * * If the rx_handler consumed to skb in some way, it should return * RX_HANDLER_CONSUMED. This is appropriate when the rx_handler arranged for * the skb to be delivered in some other ways. * * If the rx_handler changed skb->dev, to divert the skb to another * net_device, it should return RX_HANDLER_ANOTHER. The rx_handler for the * new device will be called if it exists. * * If the rx_handler consider the skb should be ignored, it should return * RX_HANDLER_EXACT. The skb will only be delivered to protocol handlers that * are registered on exact device (ptype->dev == skb->dev). * * If the rx_handler didn't changed skb->dev, but want the skb to be normally * delivered, it should return RX_HANDLER_PASS. * * A device without a registered rx_handler will behave as if rx_handler * returned RX_HANDLER_PASS. */ enum rx_handler_result { RX_HANDLER_CONSUMED, RX_HANDLER_ANOTHER, RX_HANDLER_EXACT, RX_HANDLER_PASS, }; typedef enum rx_handler_result rx_handler_result_t; typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb); void __napi_schedule(struct napi_struct *n); static inline bool napi_disable_pending(struct napi_struct *n) { return test_bit(NAPI_STATE_DISABLE, &n->state); } /** * napi_schedule_prep - check if napi can be scheduled * @n: napi context * * Test if NAPI routine is already running, and if not mark * it as running. This is used as a condition variable * insure only one NAPI poll instance runs. We also make * sure there is no pending NAPI disable. */ static inline bool napi_schedule_prep(struct napi_struct *n) { return !napi_disable_pending(n) && !test_and_set_bit(NAPI_STATE_SCHED, &n->state); } /** * napi_schedule - schedule NAPI poll * @n: napi context * * Schedule NAPI poll routine to be called if it is not already * running. */ static inline void napi_schedule(struct napi_struct *n) { if (napi_schedule_prep(n)) __napi_schedule(n); } /* Try to reschedule poll. Called by dev->poll() after napi_complete(). */ static inline bool napi_reschedule(struct napi_struct *napi) { if (napi_schedule_prep(napi)) { __napi_schedule(napi); return true; } return false; } /** * napi_complete - NAPI processing complete * @n: napi context * * Mark NAPI processing as complete. */ void __napi_complete(struct napi_struct *n); void napi_complete(struct napi_struct *n); /** * 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 */ void napi_hash_del(struct napi_struct *napi); /** * napi_disable - prevent NAPI from scheduling * @n: napi context * * Stop NAPI from being scheduled on this context. * Waits till any outstanding processing completes. */ static inline void napi_disable(struct napi_struct *n) { might_sleep(); 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); } /** * napi_enable - enable NAPI scheduling * @n: napi context * * Resume NAPI from being scheduled on this context. * Must be paired with napi_disable. */ static inline void napi_enable(struct napi_struct *n) { BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); smp_mb__before_clear_bit(); clear_bit(NAPI_STATE_SCHED, &n->state); } #ifdef CONFIG_SMP /** * napi_synchronize - wait until NAPI is not running * @n: napi context * * Wait until NAPI is done being scheduled on this context. * Waits till any outstanding processing completes but * does not disable future activations. */ static inline void napi_synchronize(const struct napi_struct *n) { while (test_bit(NAPI_STATE_SCHED, &n->state)) msleep(1); } #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)) }; /* * __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 * __QUEUE_STATE_STACK_XOFF flag is used by the stack to stop the transmit * queue independently. The netif_xmit_*stopped functions below are called * to check if the queue has been stopped by the driver or stack (either * of the XOFF bits are set in the state). Drivers should not need to call * netif_xmit*stopped functions, they should only be using netif_tx_*. */ struct netdev_queue { /* * read mostly part */ struct net_device *dev; struct Qdisc *qdisc; struct Qdisc *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; #endif #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) int numa_node; #endif /* * write mostly part */ spinlock_t _xmit_lock ____cacheline_aligned_in_smp; int xmit_lock_owner; /* * please use this field instead of dev->trans_start */ unsigned long trans_start; /* * Number of TX timeouts for this queue * (/sys/class/net/DEV/Q/trans_timeout) */ unsigned long trans_timeout; unsigned long state; #ifdef CONFIG_BQL struct dql dql; #endif } ____cacheline_aligned_in_smp; static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) { #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) return q->numa_node; #else return NUMA_NO_NODE; #endif } static inline void netdev_queue_numa_node_write(struct netdev_queue *q, int node) { #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) q->numa_node = node; #endif } #ifdef CONFIG_RPS /* * This structure holds an RPS map which can be of variable length. The * map is an array of CPUs. */ struct rps_map { unsigned int len; struct rcu_head rcu; u16 cpus[0]; }; #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16))) /* * The rps_dev_flow structure contains the mapping of a flow to a CPU, the * tail pointer for that CPU's input queue at the time of last enqueue, and * a hardware filter index. */ struct rps_dev_flow { u16 cpu; u16 filter; unsigned int last_qtail; }; #define RPS_NO_FILTER 0xffff /* * The rps_dev_flow_table structure contains a table of flow mappings. */ struct rps_dev_flow_table { unsigned int mask; struct rcu_head rcu; struct rps_dev_flow flows[0]; }; #define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ ((_num) * sizeof(struct rps_dev_flow))) /* * The rps_sock_flow_table contains mappings of flows to the last CPU * on which they were processed by the application (set in recvmsg). */ struct rps_sock_flow_table { unsigned int mask; u16 ents[0]; }; #define RPS_SOCK_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_sock_flow_table) + \ ((_num) * sizeof(u16))) #define RPS_NO_CPU 0xffff 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; /* We only give a hint, preemption can change cpu under us */ cpu = raw_smp_processor_id(); if (table->ents[index] != cpu) table->ents[index] = cpu; } } 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 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; /* * 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 /* * This structure holds an XPS map which can be of variable length. The * map is an array of queues. */ struct xps_map { unsigned int len; unsigned int alloc_len; struct rcu_head rcu; 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)) /* * This structure holds all XPS maps for device. Maps are indexed by CPU. */ struct xps_dev_maps { struct rcu_head rcu; struct xps_map __rcu *cpu_map[0]; }; #define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) + \ (nr_cpu_ids * sizeof(struct xps_map *))) #endif /* CONFIG_XPS */ #define TC_MAX_QUEUE 16 #define TC_BITMASK 15 /* HW offloaded queuing disciplines txq count and offset maps */ struct netdev_tc_txq { u16 count; u16 offset; }; #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) /* * This structure is to hold information about the device * configured to run FCoE protocol stack. */ struct netdev_fcoe_hbainfo { char manufacturer[64]; char serial_number[64]; char hardware_version[64]; char driver_version[64]; char optionrom_version[64]; char firmware_version[64]; char model[256]; char model_description[256]; }; #endif #define MAX_PHYS_PORT_ID_LEN 32 /* This structure holds a unique identifier to identify the * physical port used by a netdevice. */ struct netdev_phys_port_id { unsigned char id[MAX_PHYS_PORT_ID_LEN]; unsigned char id_len; }; /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are * optional and can be filled with a null pointer. * * int (*ndo_init)(struct net_device *dev); * This function is called once when network device is registered. * The network device can use this to any late stage initializaton * or semantic validattion. It can fail with an error code which will * be propogated back to register_netdev * * void (*ndo_uninit)(struct net_device *dev); * This function is called when device is unregistered or when registration * fails. It is not called if init fails. * * int (*ndo_open)(struct net_device *dev); * This function is called when network device transistions to the up * state. * * int (*ndo_stop)(struct net_device *dev); * This function is called when network device transistions to the down * state. * * 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. * (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, * void *accel_priv); * Called to decide which queue to when device supports multiple * transmit queues. * * void (*ndo_change_rx_flags)(struct net_device *dev, int flags); * This function is called to allow device receiver to make * changes to configuration when multicast or promiscious is enabled. * * void (*ndo_set_rx_mode)(struct net_device *dev); * This function is called device changes address list filtering. * If driver handles unicast address filtering, it should set * IFF_UNICAST_FLT to its priv_flags. * * int (*ndo_set_mac_address)(struct net_device *dev, void *addr); * This function is called when the Media Access Control address * needs to be changed. If this interface is not defined, the * mac address can not be changed. * * int (*ndo_validate_addr)(struct net_device *dev); * Test if Media Access Control address is valid for the device. * * int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); * Called when a user request an ioctl which can't be handled by * the generic interface code. If not defined ioctl's return * not supported error code. * * int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); * Used to set network devices bus interface parameters. This interface * is retained for legacy reason, new devices should use the bus * interface (PCI) for low level management. * * int (*ndo_change_mtu)(struct net_device *dev, int new_mtu); * Called when a user wants to change the Maximum Transfer Unit * of a device. If not defined, any request to change MTU will * will return an error. * * void (*ndo_tx_timeout)(struct net_device *dev); * Callback uses when the transmitter has not made any progress * for dev->watchdog ticks. * * struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev, * struct rtnl_link_stats64 *storage); * struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); * Called when a user wants to get the network device usage * statistics. Drivers must do one of the following: * 1. Define @ndo_get_stats64 to fill in a zero-initialised * rtnl_link_stats64 structure passed by the caller. * 2. Define @ndo_get_stats to update a net_device_stats structure * (which should normally be dev->stats) and return a pointer to * it. The structure may be changed asynchronously only if each * field is written atomically. * 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); * 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); * If device support VLAN filtering this function is called when a * VLAN id is unregistered. * * void (*ndo_poll_controller)(struct net_device *dev); * * 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_spoofchk)(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[]); * 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 * is always called from the stack with the rtnl lock held and netif tx * queues stopped. This allows the netdevice to perform queue management * safely. * * Fiber Channel over Ethernet (FCoE) offload functions. * int (*ndo_fcoe_enable)(struct net_device *dev); * Called when the FCoE protocol stack wants to start using LLD for FCoE * so the underlying device can perform whatever needed configuration or * initialization to support acceleration of FCoE traffic. * * int (*ndo_fcoe_disable)(struct net_device *dev); * Called when the FCoE protocol stack wants to stop using LLD for FCoE * so the underlying device can perform whatever needed clean-ups to * stop supporting acceleration of FCoE traffic. * * int (*ndo_fcoe_ddp_setup)(struct net_device *dev, u16 xid, * struct scatterlist *sgl, unsigned int sgc); * Called when the FCoE Initiator wants to initialize an I/O that * is a possible candidate for Direct Data Placement (DDP). The LLD can * perform necessary setup and returns 1 to indicate the device is set up * successfully to perform DDP on this I/O, otherwise this returns 0. * * int (*ndo_fcoe_ddp_done)(struct net_device *dev, u16 xid); * Called when the FCoE Initiator/Target is done with the DDPed I/O as * indicated by the FC exchange id 'xid', so the underlying device can * clean up and reuse resources for later DDP requests. * * int (*ndo_fcoe_ddp_target)(struct net_device *dev, u16 xid, * struct scatterlist *sgl, unsigned int sgc); * Called when the FCoE Target wants to initialize an I/O that * is a possible candidate for Direct Data Placement (DDP). The LLD can * perform necessary setup and returns 1 to indicate the device is set up * successfully to perform DDP on this I/O, otherwise this returns 0. * * int (*ndo_fcoe_get_hbainfo)(struct net_device *dev, * struct netdev_fcoe_hbainfo *hbainfo); * Called when the FCoE Protocol stack wants information on the underlying * device. This information is utilized by the FCoE protocol stack to * register attributes with Fiber Channel management service as per the * FC-GS Fabric Device Management Information(FDMI) specification. * * int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type); * Called when the underlying device wants to override default World Wide * Name (WWN) generation mechanism in FCoE protocol stack to pass its own * World Wide Port Name (WWPN) or World Wide Node Name (WWNN) to the FCoE * protocol stack to use. * * RFS acceleration. * int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb, * u16 rxq_index, u32 flow_id); * 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. * * Slave management functions (for bridge, bonding, etc). * int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev); * Called to make another netdev an underling. * * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); * Called to release previously enslaved netdev. * * Feature/offload setting functions. * netdev_features_t (*ndo_fix_features)(struct net_device *dev, * netdev_features_t features); * Adjusts the requested feature flags according to device-specific * constraints, and returns the resulting flags. Must not modify * the device state. * * int (*ndo_set_features)(struct net_device *dev, netdev_features_t features); * Called to update device configuration to new features. Passed * feature set might be less than what was returned by ndo_fix_features()). * Must return >0 or -errno if it changed dev->features itself. * * int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, * const unsigned char *addr, 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) * 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) * 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_getlink)(struct sk_buff *skb, u32 pid, u32 seq, * struct net_device *dev, u32 filter_mask) * * int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); * Called to change device carrier. Soft-devices (like dummy, team, etc) * which do not represent real hardware may define this to allow their * userspace components to manage their virtual carrier state. Devices * 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_port_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. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); void (*ndo_uninit)(struct net_device *dev); int (*ndo_open)(struct net_device *dev); int (*ndo_stop)(struct net_device *dev); 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, void *accel_priv); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); int (*ndo_set_mac_address)(struct net_device *dev, void *addr); int (*ndo_validate_addr)(struct net_device *dev); int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); int (*ndo_change_mtu)(struct net_device *dev, int new_mtu); int (*ndo_neigh_setup)(struct net_device *dev, struct neigh_parms *); void (*ndo_tx_timeout) (struct net_device *dev); struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev, struct rtnl_link_stats64 *storage); struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid); int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid); #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); 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_spoofchk)(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[]); 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); #if IS_ENABLED(CONFIG_FCOE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); int (*ndo_fcoe_ddp_setup)(struct net_device *dev, u16 xid, struct scatterlist *sgl, unsigned int sgc); int (*ndo_fcoe_ddp_done)(struct net_device *dev, u16 xid); int (*ndo_fcoe_ddp_target)(struct net_device *dev, u16 xid, struct scatterlist *sgl, unsigned int sgc); int (*ndo_fcoe_get_hbainfo)(struct net_device *dev, struct netdev_fcoe_hbainfo *hbainfo); #endif #if IS_ENABLED(CONFIG_LIBFCOE) #define NETDEV_FCOE_WWNN 0 #define NETDEV_FCOE_WWPN 1 int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type); #endif #ifdef CONFIG_RFS_ACCEL int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb, u16 rxq_index, u32 flow_id); #endif int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev); int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); netdev_features_t (*ndo_fix_features)(struct net_device *dev, netdev_features_t features); int (*ndo_set_features)(struct net_device *dev, netdev_features_t features); int (*ndo_neigh_construct)(struct neighbour *n); void (*ndo_neigh_destroy)(struct neighbour *n); int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 flags); int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr); int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, int idx); int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh); int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask); int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh); int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); int (*ndo_get_phys_port_id)(struct net_device *dev, struct netdev_phys_port_id *ppid); 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); }; /* * 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. * * 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 */ int irq; /* device IRQ number */ /* * Some hardware also needs these fields, but they are not * part of the usual set specified in Space.c. */ unsigned long state; struct list_head dev_list; struct list_head napi_list; struct list_head unreg_list; struct list_head close_list; /* directly linked devices, like slaves for bonding */ struct { struct list_head upper; struct list_head lower; } adj_list; /* all linked devices, *including* neighbours */ 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; /* mask of fetures inheritable by MPLS */ netdev_features_t mpls_features; /* Interface index. Unique device identifier */ int ifindex; int iflink; struct net_device_stats stats; atomic_long_t rx_dropped; /* dropped packets by core network * Do not use this in drivers. */ #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; const struct forwarding_accel_ops *fwd_ops; /* 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 short gflags; unsigned short padded; /* How much padding added by alloc_netdev() */ unsigned char operstate; /* RFC2863 operstate */ unsigned char link_mode; /* mapping policy to operstate */ unsigned char if_port; /* Selectable AUI, TP,..*/ unsigned char dma; /* DMA channel */ unsigned int mtu; /* interface MTU value */ unsigned short type; /* interface hardware type */ unsigned short hard_header_len; /* hardware hdr length */ /* 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 short neigh_priv_len; unsigned short dev_id; /* Used to differentiate devices * that share the same link * layer address */ 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 */ #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 */ #endif #if IS_ENABLED(CONFIG_NET_DSA) struct dsa_switch_tree *dsa_ptr; /* dsa specific data */ #endif #if IS_ENABLED(CONFIG_TIPC) struct tipc_bearer __rcu *tipc_ptr; /* TIPC 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. */ /* Interface address info used in eth_type_trans() */ unsigned char *dev_addr; /* hw address, (before bcast because most packets are unicast) */ #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 rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; struct netdev_queue __rcu *ingress_queue; unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */ /* * 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 */ spinlock_t tx_global_lock; #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; #endif /* These may be needed for future network-power-down code. */ /* * 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 */ 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 */ NETREG_UNREGISTERED, /* completed unregister todo */ NETREG_RELEASED, /* called free_netdev */ NETREG_DUMMY, /* dummy device for NAPI poll */ } reg_state:8; bool dismantle; /* device is going do be freed */ 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 /* mid-layer private */ union { void *ml_priv; struct pcpu_lstats __percpu *lstats; /* loopback stats */ struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; /* dummy stats */ struct pcpu_vstats __percpu *vstats; /* veth stats */ }; /* GARP */ 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 */ const struct attribute_group *sysfs_groups[4]; /* space for optional per-rx queue attributes */ 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 */ #define GSO_MAX_SIZE 65536 unsigned int gso_max_size; #define GSO_MAX_SEGS 65535 u16 gso_max_segs; #ifdef CONFIG_DCB /* Data Center Bridging netlink ops */ const struct dcbnl_rtnl_ops *dcbnl_ops; #endif u8 num_tc; struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; 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_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; }; #define to_net_dev(d) container_of(d, struct net_device, dev) #define NETDEV_ALIGN 32 static inline int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio) { return dev->prio_tc_map[prio & TC_BITMASK]; } static inline int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc) { if (tc >= dev->num_tc) return -EINVAL; dev->prio_tc_map[prio & TC_BITMASK] = tc & TC_BITMASK; return 0; } static inline void netdev_reset_tc(struct net_device *dev) { dev->num_tc = 0; memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); } static inline int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset) { if (tc >= dev->num_tc) return -EINVAL; dev->tc_to_txq[tc].count = count; dev->tc_to_txq[tc].offset = offset; return 0; } static inline int netdev_set_num_tc(struct net_device *dev, u8 num_tc) { if (num_tc > TC_MAX_QUEUE) return -EINVAL; dev->num_tc = num_tc; return 0; } static inline int netdev_get_num_tc(struct net_device *dev) { return dev->num_tc; } static inline struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev, unsigned int index) { return &dev->_tx[index]; } static inline void netdev_for_each_tx_queue(struct net_device *dev, void (*f)(struct net_device *, struct netdev_queue *, void *), void *arg) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) f(dev, &dev->_tx[i], arg); } struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, void *accel_priv); u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb); /* * Net namespace inlines */ static inline struct net *dev_net(const struct net_device *dev) { return read_pnet(&dev->nd_net); } 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; } static inline bool netdev_uses_trailer_tags(struct net_device *dev) { #ifdef CONFIG_NET_DSA_TAG_TRAILER if (dev->dsa_ptr != NULL) return dsa_uses_trailer_tags(dev->dsa_ptr); #endif return 0; } /** * netdev_priv - access network device private data * @dev: network device * * Get network device private data */ static inline void *netdev_priv(const struct net_device *dev) { return (char *)dev + ALIGN(sizeof(struct net_device), NETDEV_ALIGN); } /* Set the sysfs physical device reference for the network logical device * if set prior to registration will cause a symlink during initialization. */ #define SET_NETDEV_DEV(net, pdev) ((net)->dev.parent = (pdev)) /* Set the sysfs device type for the network logical device to allow * 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)) /* Default NAPI poll() weight * Device drivers are strongly advised to not use bigger value */ #define NAPI_POLL_WEIGHT 64 /** * netif_napi_add - initialize a napi context * @dev: network device * @napi: napi context * @poll: polling function * @weight: default weight * * netif_napi_add() must be used to initialize a napi context prior to calling * *any* of the other napi related functions. */ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight); /** * netif_napi_del - remove a napi context * @napi: napi context * * netif_napi_del() removes a napi context from the network device napi list */ void netif_napi_del(struct napi_struct *napi); struct napi_gro_cb { /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ void *frag0; /* Length of frag0. */ unsigned int frag0_len; /* This indicates where we are processing relative to skb->data. */ int data_offset; /* This is non-zero if the packet cannot be merged with the new skb. */ 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; /* This is non-zero if the packet may be of the same flow. */ u8 same_flow; /* Free the skb? */ u8 free; #define NAPI_GRO_FREE 1 #define NAPI_GRO_FREE_STOLEN_HEAD 2 /* jiffies when first packet was created/queued */ unsigned long age; /* Used in ipv6_gro_receive() */ u16 proto; /* Used in udp_gro_receive */ u16 udp_mark; /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; /* used in skb_gro_receive() slow path */ struct sk_buff *last; }; #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) struct packet_type { __be16 type; /* This is really htons(ether_type). */ struct net_device *dev; /* NULL is wildcarded here */ int (*func) (struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); bool (*id_match)(struct packet_type *ptype, struct sock *sk); void *af_packet_priv; 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, int nhoff); }; struct packet_offload { __be16 type; /* This is really htons(ether_type). */ struct offload_callbacks callbacks; struct list_head list; }; struct udp_offload { __be16 port; struct offload_callbacks callbacks; }; /* 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; }; #include /* netdevice notifier chain. Please remember to update the rtnetlink * notification exclusion list in rtnetlink_event() when adding new * types. */ #define NETDEV_UP 0x0001 /* For now you can't veto a device up/down */ #define NETDEV_DOWN 0x0002 #define NETDEV_REBOOT 0x0003 /* Tell a protocol stack a network interface detected a hardware crash and restarted - we can use this eg to kick tcp sessions once done */ #define NETDEV_CHANGE 0x0004 /* Notify device state change */ #define NETDEV_REGISTER 0x0005 #define NETDEV_UNREGISTER 0x0006 #define NETDEV_CHANGEMTU 0x0007 /* notify after mtu change happened */ #define NETDEV_CHANGEADDR 0x0008 #define NETDEV_GOING_DOWN 0x0009 #define NETDEV_CHANGENAME 0x000A #define NETDEV_FEAT_CHANGE 0x000B #define NETDEV_BONDING_FAILOVER 0x000C #define NETDEV_PRE_UP 0x000D #define NETDEV_PRE_TYPE_CHANGE 0x000E #define NETDEV_POST_TYPE_CHANGE 0x000F #define NETDEV_POST_INIT 0x0010 #define NETDEV_UNREGISTER_FINAL 0x0011 #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 */ int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); struct netdev_notifier_info { struct net_device *dev; }; struct netdev_notifier_change_info { struct netdev_notifier_info info; /* must be first */ unsigned int flags_changed; }; 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) #define for_each_netdev_reverse(net, d) \ list_for_each_entry_reverse(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_rcu(net, d) \ list_for_each_entry_rcu(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_safe(net, d, n) \ list_for_each_entry_safe(d, n, &(net)->dev_base_head, dev_list) #define for_each_netdev_continue(net, d) \ list_for_each_entry_continue(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_continue_rcu(net, d) \ 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) #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) { struct list_head *lh; struct net *net; net = dev_net(dev); lh = dev->dev_list.next; return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } static inline struct net_device *next_net_device_rcu(struct net_device *dev) { struct list_head *lh; struct net *net; net = dev_net(dev); lh = rcu_dereference(list_next_rcu(&dev->dev_list)); return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } static inline struct net_device *first_net_device(struct net *net) { return list_empty(&net->dev_base_head) ? NULL : net_device_entry(net->dev_base_head.next); } static inline struct net_device *first_net_device_rcu(struct net *net) { struct list_head *lh = rcu_dereference(list_next_rcu(&net->dev_base_head)); return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } 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); struct net_device *dev_get_by_flags_rcu(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); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct sk_buff *newskb); int dev_queue_xmit(struct sk_buff *skb); int dev_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); } 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); 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); #ifdef CONFIG_NETPOLL_TRAP int netpoll_trap(void); #endif int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb); static inline unsigned int skb_gro_offset(const struct sk_buff *skb) { return NAPI_GRO_CB(skb)->data_offset; } static inline unsigned int skb_gro_len(const struct sk_buff *skb) { return skb->len - NAPI_GRO_CB(skb)->data_offset; } static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len) { NAPI_GRO_CB(skb)->data_offset += len; } static inline void *skb_gro_header_fast(struct sk_buff *skb, unsigned int offset) { return NAPI_GRO_CB(skb)->frag0 + offset; } static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen) { return NAPI_GRO_CB(skb)->frag0_len < hlen; } static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, unsigned int offset) { if (!pskb_may_pull(skb, hlen)) return NULL; NAPI_GRO_CB(skb)->frag0 = NULL; NAPI_GRO_CB(skb)->frag0_len = 0; 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 (skb->ip_summed == CHECKSUM_COMPLETE) NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum, csum_partial(start, len, 0)); } static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { if (!dev->header_ops || !dev->header_ops->create) return 0; return dev->header_ops->create(skb, dev, type, daddr, saddr, len); } static inline int dev_parse_header(const struct sk_buff *skb, unsigned char *haddr) { const struct net_device *dev = skb->dev; if (!dev->header_ops || !dev->header_ops->parse) return 0; return dev->header_ops->parse(skb, haddr); } static inline int dev_rebuild_header(struct sk_buff *skb) { const struct net_device *dev = skb->dev; if (!dev->header_ops || !dev->header_ops->rebuild) return 0; return dev->header_ops->rebuild(skb); } typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len); int register_gifconf(unsigned int family, gifconf_func_t *gifconf); static inline int unregister_gifconf(unsigned int family) { 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 sk_buff_head process_queue; /* stats */ unsigned int processed; unsigned int time_squeeze; unsigned int cpu_collision; unsigned int received_rps; #ifdef CONFIG_RPS struct softnet_data *rps_ipi_list; /* Elements below can be accessed between CPUs for RPS */ struct call_single_data csd ____cacheline_aligned_in_smp; struct softnet_data *rps_ipi_next; unsigned int cpu; unsigned int input_queue_head; unsigned int input_queue_tail; #endif unsigned int dropped; struct sk_buff_head input_pkt_queue; struct napi_struct backlog; #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit __rcu *flow_limit; #endif }; static inline void input_queue_head_incr(struct softnet_data *sd) { #ifdef CONFIG_RPS sd->input_queue_head++; #endif } static inline void input_queue_tail_incr_save(struct softnet_data *sd, unsigned int *qtail) { #ifdef CONFIG_RPS *qtail = ++sd->input_queue_tail; #endif } DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); 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); } static inline void netif_tx_schedule_all(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) netif_schedule_queue(netdev_get_tx_queue(dev, i)); } static inline void netif_tx_start_queue(struct netdev_queue *dev_queue) { clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } /** * netif_start_queue - allow transmit * @dev: network device * * Allow upper layers to call the device hard_start_xmit routine. */ static inline void netif_start_queue(struct net_device *dev) { netif_tx_start_queue(netdev_get_tx_queue(dev, 0)); } static inline void netif