blob: f06fbee8638e84d42a4b8cb98bd2f2dcc33a0374 [file] [log] [blame]
/* SPDX-License-Identifier: GPL-2.0-or-later */
* 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, <waltje@uWalt.NL.Mugnet.ORG>
* Corey Minyard <wf-rch!>
* Donald J. Becker, <>
* Alan Cox, <>
* Bjorn Ekwall. <>
* Pekka Riikonen <>
* Moved to /usr/include/linux for NET3
#include <linux/timer.h>
#include <linux/bug.h>
#include <linux/delay.h>
#include <linux/atomic.h>
#include <linux/prefetch.h>
#include <asm/cache.h>
#include <asm/byteorder.h>
#include <linux/percpu.h>
#include <linux/rculist.h>
#include <linux/workqueue.h>
#include <linux/dynamic_queue_limits.h>
#include <net/net_namespace.h>
#include <net/dcbnl.h>
#include <net/netprio_cgroup.h>
#include <net/xdp.h>
#include <linux/netdev_features.h>
#include <linux/neighbour.h>
#include <uapi/linux/netdevice.h>
#include <uapi/linux/if_bonding.h>
#include <uapi/linux/pkt_cls.h>
#include <linux/hashtable.h>
struct netpoll_info;
struct device;
struct ethtool_ops;
struct phy_device;
struct dsa_port;
struct ip_tunnel_parm;
struct macsec_context;
struct macsec_ops;
struct sfp_bus;
/* 802.11 specific */
struct wireless_dev;
/* 802.15.4 specific */
struct wpan_dev;
struct mpls_dev;
/* UDP Tunnel offloads */
struct udp_tunnel_info;
struct udp_tunnel_nic_info;
struct udp_tunnel_nic;
struct bpf_prog;
struct xdp_buff;
void synchronize_net(void);
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 */
#define NET_RX_DROP 1 /* packet dropped */
#define MAX_NEST_DEV 8
* 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(), and 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_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*/
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_HYPERV_NET)
# define LL_MAX_HEADER 128
# if defined(CONFIG_MAC80211_MESH)
# define LL_MAX_HEADER 128
# else
# define LL_MAX_HEADER 96
# endif
# define LL_MAX_HEADER 32
* 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 <linux/cache.h>
#include <linux/skbuff.h>
#include <linux/static_key.h>
extern struct static_key_false rps_needed;
extern struct static_key_false rfs_needed;
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;
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 {
unsigned int hh_len;
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 (*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);
__be16 (*parse_protocol)(const struct sk_buff *skb);
/* 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 {
* This structure holds boot-time configured netdevice settings. They
* are then used in the device probing.
struct netdev_boot_setup {
char name[IFNAMSIZ];
struct ifmap map;
int __init netdev_boot_setup(char *str);
struct gro_list {
struct list_head list;
int count;
* size of gro hash buckets, must less than bit number of
* napi_struct::gro_bitmask
* 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;
int defer_hard_irqs_count;
unsigned long gro_bitmask;
int (*poll)(struct napi_struct *, int);
int poll_owner;
struct net_device *dev;
struct gro_list gro_hash[GRO_HASH_BUCKETS];
struct sk_buff *skb;
struct list_head rx_list; /* Pending GRO_NORMAL skbs */
int rx_count; /* length of rx_list */
struct hrtimer timer;
struct list_head dev_list;
struct hlist_node napi_hash_node;
unsigned int napi_id;
struct task_struct *thread;
enum {
NAPI_STATE_SCHED, /* Poll is scheduled */
NAPI_STATE_MISSED, /* reschedule a napi */
NAPI_STATE_DISABLE, /* Disable pending */
NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */
NAPI_STATE_LISTED, /* NAPI added to system lists */
NAPI_STATE_NO_BUSY_POLL, /* Do not add in napi_hash, no busy polling */
NAPI_STATE_IN_BUSY_POLL, /* sk_busy_loop() owns this NAPI */
NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/
NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/
enum {
enum gro_result {
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, pass 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 the 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 way.
* 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 decides 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 change skb->dev, but wants 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 {
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);
void __napi_schedule_irqoff(struct napi_struct *n);
static inline bool napi_disable_pending(struct napi_struct *n)
return test_bit(NAPI_STATE_DISABLE, &n->state);
static inline bool napi_prefer_busy_poll(struct napi_struct *n)
return test_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state);
bool napi_schedule_prep(struct napi_struct *n);
* 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_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))
/* 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)) {
return true;
return false;
bool 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.
* Return false if device should avoid rearming interrupts.
static inline bool napi_complete(struct napi_struct *n)
return napi_complete_done(n, 0);
int dev_set_threaded(struct net_device *dev, bool threaded);
* napi_disable - prevent NAPI from scheduling
* @n: NAPI context
* Stop NAPI from being scheduled on this context.
* Waits till any outstanding processing completes.
void napi_disable(struct napi_struct *n);
void napi_enable(struct napi_struct *n);
* 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))
* napi_if_scheduled_mark_missed - if napi is running, set the
* @n: NAPI context
* If napi is running, set the NAPIF_STATE_MISSED, and return true if
* NAPI is scheduled.
static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n)
unsigned long val, new;
do {
val = READ_ONCE(n->state);
return true;
if (!(val & NAPIF_STATE_SCHED))
return false;
} while (cmpxchg(&n->state, val, new) != val);
return true;
enum netdev_queue_state_t {
* __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 __rcu *qdisc;
struct Qdisc *qdisc_sleeping;
struct kobject kobj;
#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
int numa_node;
unsigned long tx_maxrate;
* Number of TX timeouts for this queue
* (/sys/class/net/DEV/Q/trans_timeout)
unsigned long trans_timeout;
/* Subordinate device that the queue has been assigned to */
struct net_device *sb_dev;
struct xsk_buff_pool *pool;
* write-mostly part
spinlock_t _xmit_lock ____cacheline_aligned_in_smp;
int xmit_lock_owner;
* Time (in jiffies) of last Tx
unsigned long trans_start;
unsigned long state;
struct dql dql;
} ____cacheline_aligned_in_smp;
extern int sysctl_fb_tunnels_only_for_init_net;
extern int sysctl_devconf_inherit_init_net;
* sysctl_fb_tunnels_only_for_init_net == 0 : For all netns
* == 1 : For initns only
* == 2 : For none.
static inline bool net_has_fallback_tunnels(const struct net *net)
!sysctl_fb_tunnels_only_for_init_net ||
(net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1);
static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
return q->numa_node;
return NUMA_NO_NODE;
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;
* 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[];
#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[];
#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).
* 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 {
u32 mask;
u32 ents[] ____cacheline_aligned_in_smp;
#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 index = hash & table->mask;
u32 val = hash & ~rps_cpu_mask;
/* We only give a hint, preemption can change CPU under us */
val |= raw_smp_processor_id();
if (table->ents[index] != val)
table->ents[index] = val;
bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id,
u16 filter_id);
#endif /* CONFIG_RPS */
/* This structure contains an instance of an RX queue. */
struct netdev_rx_queue {
struct rps_map __rcu *rps_map;
struct rps_dev_flow_table __rcu *rps_flow_table;
struct kobject kobj;
struct net_device *dev;
struct xdp_rxq_info xdp_rxq;
struct xsk_buff_pool *pool;
} ____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, char *buf);
ssize_t (*store)(struct netdev_rx_queue *queue,
const char *buf, size_t len);
* 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[];
#define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + ((_num) * 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.
struct xps_dev_maps {
struct rcu_head rcu;
struct xps_map __rcu *attr_map[]; /* Either CPUs map or RXQs map */
#define XPS_CPU_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \
(nr_cpu_ids * (_tcs) * sizeof(struct xps_map *)))
#define XPS_RXQ_DEV_MAPS_SIZE(_tcs, _rxqs) (sizeof(struct xps_dev_maps) +\
(_rxqs * (_tcs) * 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];
/* 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,
struct net_device *sb_dev);
enum tc_setup_type {
/* These structures hold the attributes of bpf state that are being passed
* to the netdevice through the bpf op.
enum bpf_netdev_command {
/* Set or clear a bpf program used in the earliest stages of packet
* rx. The prog will have been loaded as BPF_PROG_TYPE_XDP. The callee
* is responsible for calling bpf_prog_put on any old progs that are
* stored. In case of error, the callee need not release the new prog
* reference, but on success it takes ownership and must bpf_prog_put
* when it is no longer used.
/* BPF program for offload callbacks, invoked at program load time. */
struct bpf_prog_offload_ops;
struct netlink_ext_ack;
struct xdp_umem;
struct xdp_dev_bulk_queue;
struct bpf_xdp_link;
enum bpf_xdp_mode {
struct bpf_xdp_entity {
struct bpf_prog *prog;
struct bpf_xdp_link *link;
struct netdev_bpf {
enum bpf_netdev_command command;
union {
struct {
u32 flags;
struct bpf_prog *prog;
struct netlink_ext_ack *extack;
struct {
struct bpf_offloaded_map *offmap;
struct {
struct xsk_buff_pool *pool;
u16 queue_id;
} xsk;
/* Flags for ndo_xsk_wakeup. */
#define XDP_WAKEUP_RX (1 << 0)
#define XDP_WAKEUP_TX (1 << 1)
struct xfrmdev_ops {
int (*xdo_dev_state_add) (struct xfrm_state *x);
void (*xdo_dev_state_delete) (struct xfrm_state *x);
void (*xdo_dev_state_free) (struct xfrm_state *x);
bool (*xdo_dev_offload_ok) (struct sk_buff *skb,
struct xfrm_state *x);
void (*xdo_dev_state_advance_esn) (struct xfrm_state *x);
struct dev_ifalias {
struct rcu_head rcuhead;
char ifalias[];
struct devlink;
struct tlsdev_ops;
struct netdev_name_node {
struct hlist_node hlist;
struct list_head list;
struct net_device *dev;
const char *name;
int netdev_name_node_alt_create(struct net_device *dev, const char *name);
int netdev_name_node_alt_destroy(struct net_device *dev, const char *name);
struct netdev_net_notifier {
struct list_head list;
struct notifier_block *nb;
* 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 a network device is registered.
* The network device can use this for any late stage initialization
* or semantic validation. It can fail with an error code which will
* be propagated 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 a network device transitions to the up
* state.
* int (*ndo_stop)(struct net_device *dev);
* This function is called when a network device transitions 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.
* 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.
* Required; cannot be NULL.
* 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.
* u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
* struct net_device *sb_dev);
* Called to decide which queue to use 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 promiscuous 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 in 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 requests an ioctl which can't be handled by
* the generic interface code. If not defined ioctls 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 reasons; 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.
* void (*ndo_tx_timeout)(struct net_device *dev, unsigned int txqueue);
* Callback used when the transmitter has not made any progress
* for dev->watchdog ticks.
* void (*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.
* bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id)
* Return true if this device supports offload stats of this attr_id.
* int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev,
* void *attr_data)
* Get statistics for offload operations by attr_id. Write it into the
* attr_data pointer.
* int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid);
* If device supports VLAN filtering this function is called when a
* VLAN id is registered.
* int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid);
* If device supports 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, __be16 proto);
* 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 introduce 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, enum tc_setup_type type,
* void *type_data);
* Called to setup any 'tc' scheduler, classifier or action on @dev.
* 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.
* struct net_device *(*ndo_get_xmit_slave)(struct net_device *dev,
* struct sk_buff *skb,
* bool all_slaves);
* Get the xmit slave of master device. If all_slaves is true, function
* assume all the slaves can transmit.
* 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 vid, u16 flags,
* struct netlink_ext_ack *extack);
* 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, 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, 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,
* u16 flags, struct netlink_ext_ack *extack)
* int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq,
* 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)
* 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_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.
* int (*ndo_get_port_parent_id)(struct net_device *dev,
* struct netdev_phys_item_id *ppid)
* Called to get the parent ID of the physical port of this device.
* 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.
* 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.
* void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom);
* This function is used to specify the headroom that the skb must
* consider when allocation skb during packet reception. Setting
* appropriate rx headroom value allows avoiding skb head copy on
* forward. Setting a negative value resets the rx headroom to the
* default value.
* int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf);
* This function is used to set or query state related to XDP on the
* netdevice and manage BPF offload. See definition of
* enum bpf_netdev_command for details.
* int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp,
* u32 flags);
* This function is used to submit @n XDP packets for transmit on a
* netdevice. Returns number of frames successfully transmitted, frames
* that got dropped are freed/returned via xdp_return_frame().
* Returns negative number, means general error invoking ndo, meaning
* no frames were xmit'ed and core-caller will free all frames.
* int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags);
* This function is used to wake up the softirq, ksoftirqd or kthread
* responsible for sending and/or receiving packets on a specific
* queue id bound to an AF_XDP socket. The flags field specifies if
* only RX, only Tx, or both should be woken up using the flags
* struct devlink_port *(*ndo_get_devlink_port)(struct net_device *dev);
* Get devlink port instance associated with a given netdev.
* Called with a reference on the netdevice and devlink locks only,
* rtnl_lock is not held.
* int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p,
* int cmd);
* Add, change, delete or get information on an IPv4 tunnel.
* struct net_device *(*ndo_get_peer_dev)(struct net_device *dev);
* If a device is paired with a peer device, return the peer instance.
* The caller must be under RCU read context.
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);
netdev_features_t (*ndo_features_check)(struct sk_buff *skb,
struct net_device *dev,
netdev_features_t features);
u16 (*ndo_select_queue)(struct net_device *dev,
struct sk_buff *skb,
struct net_device *sb_dev);
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,
unsigned int txqueue);
void (*ndo_get_stats64)(struct net_device *dev,
struct rtnl_link_stats64 *storage);
bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id);
int (*ndo_get_offload_stats)(int attr_id,
const struct net_device *dev,
void *attr_data);
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);
void (*ndo_poll_controller)(struct net_device *dev);
int (*ndo_netpoll_setup)(struct net_device *dev,
struct netpoll_info *info);
void (*ndo_netpoll_cleanup)(struct net_device *dev);
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, __be16 proto);
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
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_get_vf_guid)(struct net_device *dev,
int vf,
struct ifla_vf_guid *node_guid,
struct ifla_vf_guid *port_guid);
int (*ndo_set_vf_guid)(struct net_device *dev,
int vf, u64 guid,
int guid_type);
int (*ndo_set_vf_rss_query_en)(
struct net_device *dev,
int vf, bool setting);
int (*ndo_setup_tc)(struct net_device *dev,
enum tc_setup_type type,
void *type_data);
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);
int (*ndo_fcoe_get_wwn)(struct net_device *dev,
u64 *wwn, int type);
int (*ndo_rx_flow_steer)(struct net_device *dev,
const struct sk_buff *skb,
u16 rxq_index,
u32 flow_id);
int (*ndo_add_slave)(struct net_device *dev,
struct net_device *slave_dev,
struct netlink_ext_ack *extack);
int (*ndo_del_slave)(struct net_device *dev,
struct net_device *slave_dev);
struct net_device* (*ndo_get_xmit_slave)(struct net_device *dev,
struct sk_buff *skb,
bool all_slaves);
struct net_device* (*ndo_sk_get_lower_dev)(struct net_device *dev,
struct sock *sk);
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 net_device *dev,
struct neighbour *n);
void (*ndo_neigh_destroy)(struct net_device *dev,
struct neighbour *n);
int (*ndo_fdb_add)(struct ndmsg *ndm,
struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr,
u16 vid,
u16 flags,
struct netlink_ext_ack *extack);
int (*ndo_fdb_del)(struct ndmsg *ndm,
struct nlattr *tb[],
struct net_device *dev,
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_fdb_get)(struct sk_buff *skb,
struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr,
u16 vid, u32 portid, u32 seq,
struct netlink_ext_ack *extack);
int (*ndo_bridge_setlink)(struct net_device *dev,
struct nlmsghdr *nlh,
u16 flags,
struct netlink_ext_ack *extack);
int (*ndo_bridge_getlink)(struct sk_buff *skb,
u32 pid, u32 seq,
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);
int (*ndo_get_phys_port_id)(struct net_device *dev,
struct netdev_phys_item_id *ppid);
int (*ndo_get_port_parent_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_dfwd_add_station)(struct net_device *pdev,
struct net_device *dev);
void (*ndo_dfwd_del_station)(struct net_device *pdev,
void *priv);
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);
void (*ndo_set_rx_headroom)(struct net_device *dev,
int needed_headroom);
int (*ndo_bpf)(struct net_device *dev,
struct netdev_bpf *bpf);
int (*ndo_xdp_xmit)(struct net_device *dev, int n,
struct xdp_frame **xdp,
u32 flags);
int (*ndo_xsk_wakeup)(struct net_device *dev,
u32 queue_id, u32 flags);
struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev);
int (*ndo_tunnel_ctl)(struct net_device *dev,
struct ip_tunnel_parm *p, int cmd);
struct net_device * (*ndo_get_peer_dev)(struct net_device *dev);
* enum netdev_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_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
* underlying stacked devices
* @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
* @IFF_TEAM: device is a team device
* @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured
* @IFF_PHONY_HEADROOM: the headroom value is controlled by an external
* entity (i.e. the master device for bridged veth)
* @IFF_MACSEC: device is a MACsec device
* @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook
* @IFF_FAILOVER: device is a failover master device
* @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device
* @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device
* @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running
enum netdev_priv_flags {
IFF_802_1Q_VLAN = 1<<0,
IFF_ISATAP = 1<<3,
IFF_WAN_HDLC = 1<<4,
IFF_TEAM_PORT = 1<<13,
IFF_MACVLAN = 1<<16,
IFF_NO_QUEUE = 1<<19,
IFF_TEAM = 1<<22,
IFF_MACSEC = 1<<25,
#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN
/* Specifies the type of the struct net_device::ml_priv pointer */
enum netdev_ml_priv_type {
* 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_node: Name hashlist node
* @ifalias: SNMP alias
* @mem_end: Shared memory end
* @mem_start: Shared memory start
* @base_addr: Device I/O address
* @irq: Device IRQ number
* @state: Generic network queuing layer state, see netdev_state_t
* @dev_list: The global list of network devices
* @napi_list: List entry used for polling NAPI devices
* @unreg_list: List entry when we are unregistering the
* device; see the function unregister_netdev
* @close_list: List entry used when we are closing the device
* @ptype_all: Device-specific packet handlers for all protocols
* @ptype_specific: Device-specific, protocol-specific packet handlers
* @adj_list: Directly linked devices, like slaves for bonding
* @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
* @gso_partial_features: value(s) from NETIF_F_GSO\*
* @ifindex: interface index
* @group: The group 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
* @rx_nohandler: nohandler dropped packets by core network on
* inactive devices, do not use this in drivers
* @carrier_up_count: Number of times the carrier has been up
* @carrier_down_count: Number of times the carrier has been down
* @wireless_handlers: List of functions to handle Wireless Extensions,
* instead of ioctl,
* see <net/iw_handler.h> 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
* @l3mdev_ops: Layer 3 master device operations
* @ndisc_ops: Includes callbacks for different IPv6 neighbour
* discovery handling. Necessary for e.g. 6LoWPAN.
* @xfrmdev_ops: Transformation offload operations
* @tlsdev_ops: Transport Layer Security offload 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
* @min_mtu: Interface Minimum MTU value
* @max_mtu: Interface Maximum 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
* @upper_level: Maximum depth level of upper devices.
* @lower_level: Maximum depth level of lower devices.
* @neigh_priv_len: Used in neigh_alloc()
* @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
* @name_assign_type: network interface name assignment type
* @uc_promisc: Counter that indicates 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 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
* @ieee802154_ptr: IEEE 802.15.4 low-rate Wireless Personal Area Network
* device struct
* @mpls_ptr: mpls_dev struct pointer
* @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
* @xdp_prog: XDP sockets filter program pointer
* @gro_flush_timeout: timeout for GRO layer in NAPI
* @napi_defer_hard_irqs: If not zero, provides a counter that would
* allow to avoid NIC hard IRQ, on busy queues.
* @rx_handler: handler for received packets
* @rx_handler_data: XXX: need comments on this one
* @miniq_ingress: ingress/clsact qdisc specific data for
* ingress processing
* @ingress_queue: XXX: need comments on this one
* @nf_hooks_ingress: netfilter hooks executed for ingress packets
* @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
* @xdp_bulkq: XDP device bulk queue
* @xps_cpus_map: all CPUs map for XPS device
* @xps_rxqs_map: all RXQs map for XPS device
* @xps_maps: XXX: need comments on this one
* @miniq_egress: clsact qdisc specific data for
* egress processing
* @qdisc_hash: qdisc hash table
* @watchdog_timeo: Represents the timeout that is used by
* the watchdog (see dev_watchdog())
* @watchdog_timer: List of timers
* @proto_down_reason: reason a netdev interface is held down
* @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
* @needs_free_netdev: Should unregister perform free_netdev?
* @priv_destructor: Called from unregister
* @npinfo: XXX: need comments on this one
* @nd_net: Network namespace this network device is inside
* @ml_priv: Mid-layer private
* @ml_priv_type: Mid-layer private type
* @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
* @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
* @sfp_bus: attached &struct sfp_bus structure.
* @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock
* @qdisc_running_key: lockdep class annotating Qdisc->running seqcount
* @proto_down: protocol port state information can be sent to the
* switch driver and used to set the phys state of the
* switch port.
* @wol_enabled: Wake-on-LAN is enabled
* @threaded: napi threaded mode is enabled
* @net_notifier_list: List of per-net netdev notifier block
* that follow this device when it is moved
* to another network namespace.
* @macsec_ops: MACsec offloading ops
* @udp_tunnel_nic_info: static structure describing the UDP tunnel
* offload capabilities of the device
* @udp_tunnel_nic: UDP tunnel offload state
* @xdp_state: stores info on attached XDP BPF programs
* @nested_level: Used as as a parameter of spin_lock_nested() of
* dev->addr_list_lock.
* @unlink_list: As netif_addr_lock() can be called recursively,
* keep a list of interfaces to be deleted.
* FIXME: cleanup struct net_device such that network protocol info
* moves out.
struct net_device {
char name[IFNAMSIZ];
struct netdev_name_node *name_node;
struct dev_ifalias __rcu *ifalias;
* I/O specific fields
* FIXME: Merge these and struct ifmap into one
unsigned long mem_end;
unsigned long mem_start;
unsigned long base_addr;
* 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.
unsigned long state;
struct list_head dev_list;
struct list_head napi_list;
struct list_head unreg_list;
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;
/* Read-mostly cache-line for fast-path access */
unsigned int flags;
unsigned int priv_flags;
const struct net_device_ops *netdev_ops;
int ifindex;
unsigned short gflags;
unsigned short hard_header_len;
/* Note : dev->mtu is often read without holding a lock.
* Writers usually hold RTNL.
* It is recommended to use READ_ONCE() to annotate the reads,
* and to use WRITE_ONCE() to annotate the writes.
unsigned int mtu;
unsigned short needed_headroom;
unsigned short needed_tailroom;
netdev_features_t features;
netdev_features_t hw_features;
netdev_features_t wanted_features;
netdev_features_t vlan_features;
netdev_features_t hw_enc_features;
netdev_features_t mpls_features;
netdev_features_t gso_partial_features;
unsigned int min_mtu;
unsigned int max_mtu;
unsigned short type;
unsigned char min_header_len;
unsigned char name_assign_type;
int group;
struct net_device_stats stats; /* not used by modern drivers */
atomic_long_t rx_dropped;
atomic_long_t tx_dropped;
atomic_long_t rx_nohandler;
/* Stats to monitor link on/off, flapping */
atomic_t carrier_up_count;
atomic_t carrier_down_count;
const struct iw_handler_def *wireless_handlers;
struct iw_public_data *wireless_data;
const struct ethtool_ops *ethtool_ops;
const struct l3mdev_ops *l3mdev_ops;
const struct ndisc_ops *ndisc_ops;
const struct xfrmdev_ops *xfrmdev_ops;
const struct tlsdev_ops *tlsdev_ops;
const struct header_ops *header_ops;
unsigned char operstate;
unsigned char link_mode;
unsigned char if_port;
unsigned char dma;
/* Interface address info. */
unsigned char perm_addr[MAX_ADDR_LEN];
unsigned char addr_assign_type;
unsigned char addr_len;
unsigned char upper_level;
unsigned char lower_level;
unsigned short neigh_priv_len;
unsigned short dev_id;
unsigned short dev_port;
unsigned short padded;
spinlock_t addr_list_lock;
int irq;
struct netdev_hw_addr_list uc;
struct netdev_hw_addr_list mc;
struct netdev_hw_addr_list dev_addrs;
struct kset *queues_kset;
struct list_head unlink_list;
unsigned int promiscuity;
unsigned int allmulti;
bool uc_promisc;
unsigned char nested_level;
/* Protocol-specific pointers */
struct vlan_info __rcu *vlan_info;
struct dsa_port *dsa_ptr;
struct tipc_bearer __rcu *tipc_ptr;
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;
struct mpls_dev __rcu *mpls_ptr;
* Cache lines mostly used on receive path (including eth_type_trans())
/* Interface address info used in eth_type_trans() */
unsigned char *dev_addr;
struct netdev_rx_queue *_rx;
unsigned int num_rx_queues;
unsigned int real_num_rx_queues;
struct bpf_prog __rcu *xdp_prog;
unsigned long gro_flush_timeout;
int napi_defer_hard_irqs;
rx_handler_func_t __rcu *rx_handler;
void __rcu *rx_handler_data;
struct mini_Qdisc __rcu *miniq_ingress;
struct netdev_queue __rcu *ingress_queue;
struct nf_hook_entries __rcu *nf_hooks_ingress;
unsigned char broadcast[MAX_ADDR_LEN];
struct cpu_rmap *rx_cpu_rmap;
struct hlist_node index_hlist;
* Cache lines mostly used on transmit path
struct netdev_queue *_tx ____cacheline_aligned_in_smp;
unsigned int num_tx_queues;
unsigned int real_num_tx_queues;
struct Qdisc *qdisc;
unsigned int tx_queue_len;
spinlock_t tx_global_lock;
struct xdp_dev_bulk_queue __percpu *xdp_bulkq;
struct xps_dev_maps __rcu *xps_cpus_map;
struct xps_dev_maps __rcu *xps_rxqs_map;
struct mini_Qdisc __rcu *miniq_egress;
DECLARE_HASHTABLE (qdisc_hash, 4);
/* These may be needed for future network-power-down code. */
struct timer_list watchdog_timer;
int watchdog_timeo;
u32 proto_down_reason;
struct list_head todo_list;
int __percpu *pcpu_refcnt;
struct list_head link_watch_list;
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;
enum {
} rtnl_link_state:16;
bool needs_free_netdev;
void (*priv_destructor)(struct net_device *dev);
struct netpoll_info __rcu *npinfo;
possible_net_t nd_net;
/* mid-layer private */
void *ml_priv;
enum netdev_ml_priv_type ml_priv_type;
union {
struct pcpu_lstats __percpu *lstats;
struct pcpu_sw_netstats __percpu *tstats;
struct pcpu_dstats __percpu *dstats;
struct garp_port __rcu *garp_port;
struct mrp_port __rcu *mrp_port;
struct device dev;
const struct attribute_group *sysfs_groups[4];
const struct attribute_group *sysfs_rx_queue_group;
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;
const struct dcbnl_rtnl_ops *dcbnl_ops;
s16 num_tc;
struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE];
u8 prio_tc_map[TC_BITMASK + 1];
unsigned int fcoe_ddp_xid;
struct netprio_map __rcu *priomap;
struct phy_device *phydev;
struct sfp_bus *sfp_bus;
struct lock_class_key *qdisc_tx_busylock;
struct lock_class_key *qdisc_running_key;
bool proto_down;
unsigned wol_enabled:1;
unsigned threaded:1;
struct list_head net_notifier_list;
/* MACsec management functions */
const struct macsec_ops *macsec_ops;
const struct udp_tunnel_nic_info *udp_tunnel_nic_info;
struct udp_tunnel_nic *udp_tunnel_nic;
/* protected by rtnl_lock */
struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE];
#define to_net_dev(d) container_of(d, struct net_device, dev)
static inline bool netif_elide_gro(const struct net_device *dev)
if (!(dev->features & NETIF_F_GRO) || dev->xdp_prog)
return true;
return false;
#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;
int netdev_txq_to_tc(struct net_device *dev, unsigned int txq);
void netdev_reset_tc(struct net_device *dev);
int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset);
int netdev_set_num_tc(struct net_device *dev, u8 num_tc);
static inline
int netdev_get_num_tc(struct net_device *dev)
return dev->num_tc;
static inline void net_prefetch(void *p)
#if L1_CACHE_BYTES < 128
prefetch((u8 *)p + L1_CACHE_BYTES);
static inline void net_prefetchw(void *p)
#if L1_CACHE_BYTES < 128
prefetchw((u8 *)p + L1_CACHE_BYTES);
void netdev_unbind_sb_channel(struct net_device *dev,
struct net_device *sb_dev);
int netdev_bind_sb_channel_queue(struct net_device *dev,
struct net_device *sb_dev,
u8 tc, u16 count, u16 offset);
int netdev_set_sb_channel(struct net_device *dev, u16 channel);
static inline int netdev_get_sb_channel(struct net_device *dev)
return max_t(int, -dev->num_tc, 0);
static inline
struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev,
unsigned int index)
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 *,
void *),
void *arg)
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++)
f(dev, &dev->_tx[i], arg);
#define netdev_lockdep_set_classes(dev) \
{ \
static struct lock_class_key qdisc_tx_busylock_key; \
static struct lock_class_key qdisc_running_key; \
static struct lock_class_key qdisc_xmit_lock_key; \
static struct lock_class_key dev_addr_list_lock_key; \
unsigned int i; \
(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \
(dev)->qdisc_running_key = &qdisc_running_key; \
lockdep_set_class(&(dev)->addr_list_lock, \
&dev_addr_list_lock_key); \
for (i = 0; i < (dev)->num_tx_queues; i++) \
lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \
&qdisc_xmit_lock_key); \
u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev);
struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
struct sk_buff *skb,
struct net_device *sb_dev);
/* returns the headroom that the master device needs to take in account
* when forwarding to this dev
static inline unsigned netdev_get_fwd_headroom(struct net_device *dev)
return dev->priv_flags & IFF_PHONY_HEADROOM ? 0 : dev->needed_headroom;
static inline void netdev_set_rx_headroom(struct net_device *dev, int new_hr)
if (dev->netdev_ops->ndo_set_rx_headroom)
dev->netdev_ops->ndo_set_rx_headroom(dev, new_hr);
/* set the device rx headroom to the dev's default */
static inline void netdev_reset_rx_headroom(struct net_device *dev)
netdev_set_rx_headroom(dev, -1);
static inline void *netdev_get_ml_priv(struct net_device *dev,
enum netdev_ml_priv_type type)
if (dev->ml_priv_type != type)
return NULL;
return dev->ml_priv;
static inline void netdev_set_ml_priv(struct net_device *dev,
void *ml_priv,
enum netdev_ml_priv_type type)
WARN(dev->ml_priv_type && dev->ml_priv_type != type,
"Overwriting already set ml_priv_type (%u) with different ml_priv_type (%u)!\n",
dev->ml_priv_type, type);
WARN(!dev->ml_priv_type && dev->ml_priv,
"Overwriting already set ml_priv and ml_priv_type is ML_PRIV_NONE!\n");
dev->ml_priv = ml_priv;
dev->ml_priv_type = type;
* 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)
write_pnet(&dev->nd_net, net);
* 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, Wireless 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
* 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_tx_napi_add - initialize a NAPI context
* @dev: network device
* @napi: NAPI context
* @poll: polling function
* @weight: default weight
* This variant of netif_napi_add() should be used from drivers using NAPI
* to exclusively poll a TX queue.
* This will avoid we add it into napi_hash[], thus polluting this hash table.
static inline void netif_tx_napi_add(struct net_device *dev,
struct napi_struct *napi,
int (*poll)(struct napi_struct *, int),
int weight)
set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state);
netif_napi_add(dev, napi, poll, weight);
* __netif_napi_del - remove a NAPI context
* @napi: NAPI context
* Warning: caller must observe RCU grace period before freeing memory
* containing @napi. Drivers might want to call this helper to combine
* all the needed RCU grace periods into a single one.
void __netif_napi_del(struct napi_struct *napi);
* netif_napi_del - remove a NAPI context
* @napi: NAPI context
* netif_napi_del() removes a NAPI context from the network device NAPI list
static inline 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;
/* 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: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:2;
#define NAPI_GRO_FREE 1
/* Used in foo-over-udp, set in udp[46]_gro_receive */
u8 is_ipv6:1;
/* Used in GRE, set in fou/gue_gro_receive */
u8 is_fou:1;
/* Used to determine if flush_id can be ignored */
u8 is_atomic:1;
/* Number of gro_receive callbacks this packet already went through */
u8 recursion_counter:4;
/* GRO is done by frag_list pointer chaining. */
u8 is_flist:1;
/* 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)
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 list_head *, struct sk_buff *);
static inline struct sk_buff *call_gro_receive(gro_receive_t cb,
struct list_head *head,
struct sk_buff *skb)
if (unlikely(gro_recursion_inc_test(skb))) {
NAPI_GRO_CB(skb)->flush |= 1;
return NULL;
return cb(head, skb);
typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *,
struct sk_buff *);
static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb,
struct sock *sk,
struct list_head *head,
struct sk_buff *skb)
if (unlikely(gro_recursion_inc_test(skb))) {
NAPI_GRO_CB(skb)->flush |= 1;
return NULL;
return cb(sk, head, skb);
struct packet_type {
__be16 type; /* This is really htons(ether_type). */
bool ignore_outgoing;
struct net_device *dev; /* NULL is wildcarded here */
int (*func) (struct sk_buff *,
struct net_device *,
struct packet_type *,
struct net_device *);
void (*list_func) (struct list_head *,
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);
struct sk_buff *(*gro_receive)(struct list_head *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). */
u16 priority;
struct offload_callbacks callbacks;
struct list_head list;
/* 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;
} __aligned(4 * sizeof(u64));
struct pcpu_lstats {
u64_stats_t packets;
u64_stats_t bytes;
struct u64_stats_sync syncp;
} __aligned(2 * sizeof(u64));
void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes);
static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int len)
struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
tstats->rx_bytes += len;
static inline void dev_sw_netstats_tx_add(struct net_device *dev,
unsigned int packets,
unsigned int len)
struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
tstats->tx_bytes += len;
tstats->tx_packets += packets;
static inline void dev_lstats_add(struct net_device *dev, unsigned int len)
struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats);
u64_stats_add(&lstats->bytes, len);
#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)
#define devm_netdev_alloc_pcpu_stats(dev, type) \
({ \
typeof(type) __percpu *pcpu_stats = devm_alloc_percpu(dev, type);\
if (pcpu_stats) { \
int __cpu; \
for_each_possible_cpu(__cpu) { \
typeof(type) *stat; \
stat = per_cpu_ptr(pcpu_stats, __cpu); \
u64_stats_init(&stat->syncp); \
} \
} \
pcpu_stats; \
enum netdev_lag_tx_type {
enum netdev_lag_hash {
struct netdev_lag_upper_info {
enum netdev_lag_tx_type tx_type;
enum netdev_lag_hash hash_type;
struct netdev_lag_lower_state_info {
u8 link_up : 1,
tx_enabled : 1;
#include <linux/notifier.h>
/* netdevice notifier chain. Please remember to update netdev_cmd_to_name()
* and the rtnetlink notification exclusion list in rtnetlink_event() when
* adding new types.
enum netdev_cmd {
NETDEV_UP = 1, /* For now you can't veto a device up/down */
NETDEV_REBOOT, /* Tell a protocol stack a network interface
detected a hardware crash and restarted
- we can use this eg to kick tcp sessions
once done */
NETDEV_CHANGE, /* Notify device state change */
NETDEV_CHANGEMTU, /* notify after mtu change happened */
NETDEV_CHANGEADDR, /* notify after the address change */
NETDEV_PRE_CHANGEADDR, /* notify before the address change */
NETDEV_PRECHANGEMTU, /* notify before mtu change happened */
const char *netdev_cmd_to_name(enum netdev_cmd cmd);
int register_netdevice_notifier(struct notifier_block *nb);
int unregister_netdevice_notifier(struct notifier_block *nb);
int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb);
int unregister_netdevice_notifier_net(struct net *net,
struct notifier_block *nb);
int register_netdevice_notifier_dev_net(struct net_device *dev,
struct notifier_block *nb,
struct netdev_net_notifier *nn);
int unregister_netdevice_notifier_dev_net(struct net_device *dev,
struct notifier_block *nb,
struct netdev_net_notifier *nn);
struct netdev_notifier_info {
struct net_device *dev;
struct netlink_ext_ack *extack;
struct netdev_notifier_info_ext {
struct netdev_notifier_info info; /* must be first */
union {
u32 mtu;
} ext;
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 notification for link or unlink */
void *upper_info; /* upper dev info */
struct netdev_notifier_changelowerstate_info {
struct netdev_notifier_info info; /* must be first */
void *lower_state_info; /* is lower dev state */
struct netdev_notifier_pre_changeaddr_info {
struct netdev_notifier_info info; /* must be first */
const unsigned char *dev_addr;
static inline void netdev_notifier_info_init(struct netdev_notifier_info *info,
struct net_device *dev)
info->dev = dev;
info->extack = NULL;
static inline struct net_device *
netdev_notifier_info_to_dev(const struct netdev_notifier_info *info)
return info->dev;
static inline struct netlink_ext_ack *
netdev_notifier_info_to_extack(const struct netdev_notifier_info *info)
return info->extack;
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_reverse(net, d) \
list_for_each_entry_continue_reverse(d, &(net)->dev_base_head, \
#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->;
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 :
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);
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, struct netlink_ext_ack *extack);
void dev_close(struct net_device *dev);
void 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);
u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev);
u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev);
int dev_queue_xmit(struct sk_buff *skb);
int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
int ret;
ret = __dev_direct_xmit(skb, queue_id);
if (!dev_xmit_complete(ret))
return ret;
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);
int init_dummy_netdev(struct net_device *dev);
struct net_device *netdev_get_xmit_slave(struct net_device *dev,
struct sk_buff *skb,
bool all_slaves);
struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev,
struct sock *sk);
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);
struct net_device *dev_get_by_napi_id(unsigned int napi_id);
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 *p, struct sk_buff *skb);
int skb_gro_receive_list(struct sk_buff *p, 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_frag0_invalidate(struct sk_buff *skb)
NAPI_GRO_CB(skb)->frag0 = NULL;
NAPI_GRO_CB(skb)->frag0_len = 0;
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;
return skb->data + offset;
static inline void *skb_gro_network_header(struct sk_buff *skb)
return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) +
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 */
} 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.