Current File : //usr/src/kernels/3.10.0-1160.80.1.el7.centos.plus.x86_64/include/linux/netdevice.h
/*
* 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!minyard@relay.EU.net>
* Donald J. Becker, <becker@cesdis.gsfc.nasa.gov>
* Alan Cox, <alan@lxorguk.ukuu.org.uk>
* Bjorn Ekwall. <bj0rn@blox.se>
* Pekka Riikonen <priikone@poseidon.pspt.fi>
*
* 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 <linux/pm_qos.h>
#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/dmaengine.h>
#include <linux/workqueue.h>
#include <linux/dynamic_queue_limits.h>
#include <linux/ethtool.h>
#include <net/net_namespace.h>
#include <net/dsa.h>
#ifdef CONFIG_DCB
#include <net/dcbnl.h>
#endif
#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>
#include <linux/rh_kabi.h>
struct netpoll_info;
struct device;
struct phy_device;
/* 802.11 specific */
struct wireless_dev;
/* 802.15.4 specific */
struct wpan_dev;
/* UDP Tunnel offloads */
struct udp_tunnel_info;
struct bpf_prog;
struct xdp_buff;
struct netdev_xdp;
#define netdev_bpf netdev_xdp
struct net_device_extended;
/* 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_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 <linux/cache.h>
#include <linux/skbuff.h>
#ifdef CONFIG_RPS
#include <linux/static_key.h>
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
RH_KABI_DEPRECATE(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;
RH_KABI_EXTEND(size_t size)
RH_KABI_EXTEND(struct hrtimer timer)
};
#define NAPI_STRUCT_HAS(napi, member) \
({ const struct napi_struct *__n = napi; \
(test_bit(NAPI_STATE_EXT, &__n->state) && \
(offsetof(struct napi_struct, member) < __n->size)); })
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 */
NAPI_STATE_EXT, /* Extended napi_struct */
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_MISSED, /* reschedule a napi */
};
enum {
NAPIF_STATE_SCHED = BIT(NAPI_STATE_SCHED),
NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED),
NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE),
NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC),
NAPIF_STATE_HASHED = BIT(NAPI_STATE_HASHED),
NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
};
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);
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);
}
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(n);
}
/**
* napi_schedule_irqoff - schedule NAPI poll
* @n: napi context
*
* Variant of napi_schedule(), assuming hard irqs are masked.
*/
static inline void napi_schedule_irqoff(struct napi_struct *n)
{
if (napi_schedule_prep(n))
__napi_schedule_irqoff(n);
}
/* Try to reschedule poll. Called by dev->poll() after napi_complete(). */
static inline bool napi_reschedule(struct napi_struct *napi)
{
if (napi_schedule_prep(napi)) {
__napi_schedule(napi);
return true;
}
return false;
}
RH_KABI_REPLACE_UNSAFE(void __napi_complete(struct napi_struct *n),
bool __napi_complete(struct napi_struct *n))
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);
}
/* RHEL has napi_complete in KABI so we need to keep it for binary
* modules. Newly compiled modules will use inlined function. */
void napi_complete(struct napi_struct *n);
#define napi_complete _napi_complete
/**
* 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
* Used for busy polling (CONFIG_NET_RX_BUSY_POLL)
* Note: This is normally automatically done from netif_napi_add(),
* so might disappear in a future linux version.
*/
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, if
* this function returns true.
* Note: core networking stack automatically calls it
* from netif_napi_del()
* Drivers might want to call this helper to combine all
* the needed rcu grace periods into a single one.
*/
bool 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.
*/
void napi_disable(struct napi_struct *n);
/**
* 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);
clear_bit(NAPI_STATE_NPSVC, &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
/**
* napi_if_scheduled_mark_missed - if napi is running, set the
* NAPIF_STATE_MISSED
* @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);
if (val & NAPIF_STATE_DISABLE)
return true;
if (!(val & NAPIF_STATE_SCHED))
return false;
new = val | NAPIF_STATE_MISSED;
} while (cmpxchg(&n->state, val, new) != val);
return true;
}
enum netdev_queue_state_t {
__QUEUE_STATE_DRV_XOFF,
__QUEUE_STATE_STACK_XOFF,
__QUEUE_STATE_FROZEN,
};
#define QUEUE_STATE_DRV_XOFF (1 << __QUEUE_STATE_DRV_XOFF)
#define QUEUE_STATE_STACK_XOFF (1 << __QUEUE_STATE_STACK_XOFF)
#define QUEUE_STATE_FROZEN (1 << __QUEUE_STATE_FROZEN)
#define QUEUE_STATE_ANY_XOFF (QUEUE_STATE_DRV_XOFF | QUEUE_STATE_STACK_XOFF)
#define QUEUE_STATE_ANY_XOFF_OR_FROZEN (QUEUE_STATE_ANY_XOFF | \
QUEUE_STATE_FROZEN)
#define QUEUE_STATE_DRV_XOFF_OR_FROZEN (QUEUE_STATE_DRV_XOFF | \
QUEUE_STATE_FROZEN)
/*
* __QUEUE_STATE_DRV_XOFF is used by drivers to stop the transmit queue. The
* netif_tx_* functions below are used to manipulate this flag. The
* __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;
#ifdef CONFIG_SYSFS
struct kobject kobj;
#endif
#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
int numa_node;
#endif
/* There is a hole that can be used for additional struct members
* without kABI breakage.
* There are 36 bytes available on all supported platforms.
*/
/*
* 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;
/*
* Number of TX timeouts for this queue
* (/sys/class/net/DEV/Q/trans_timeout)
*/
unsigned long trans_timeout;
unsigned long state;
/* There is a hole that can be used for additional struct members
* without kABI breakage.
* There are 32 bytes available on all supported platforms.
*/
RH_KABI_FILL_HOLE(unsigned long tx_maxrate) /* 8 bytes */
/* 24 bytes remaining */
#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
/* 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;
} ____cacheline_aligned_in_smp;
#endif /* CONFIG_RPS */
#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(_tcs) (sizeof(struct xps_dev_maps) + \
(nr_cpu_ids * (_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];
};
#endif
#define MAX_PHYS_PORT_ID_LEN 32
#define MAX_PHYS_ITEM_ID_LEN MAX_PHYS_PORT_ID_LEN
/* This structure holds a unique identifier to identify some
* physical item (port for example) used by a netdevice.
*/
struct netdev_phys_port_id {
unsigned char id[MAX_PHYS_ITEM_ID_LEN];
unsigned char id_len;
};
#define netdev_phys_item_id netdev_phys_port_id
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);
enum tc_setup_type {
TC_SETUP_QDISC_MQPRIO,
TC_SETUP_CLSU32,
TC_SETUP_CLSFLOWER,
TC_SETUP_CLSMATCHALL,
TC_SETUP_CLSBPF,
TC_SETUP_BLOCK,
TC_SETUP_QDISC_CBS,
TC_SETUP_QDISC_RED,
TC_SETUP_QDISC_PRIO,
};
/* Forward declaration of tc_to_netdev structure used by __rh_call_ndo_setup_tc
* wrapper for out-of-tree drivers compiled against RHEL7.4.
*/
struct tc_to_netdev_rh74;
struct tc_cls_u32_offload;
struct tc_to_netdev {
unsigned int type;
union {
u8 tc;
struct tc_cls_u32_offload *cls_u32;
struct tc_cls_flower_offload *cls_flower;
struct tc_cls_matchall_offload *cls_mall;
struct tc_cls_bpf_offload *cls_bpf;
};
bool egress_dev;
};
/* This structure defines the management hooks for network devices.
* It is an extension of net_device_ops. Drivers that want to use any of the
* fields defined here must initialize net_device_ops->ndo_size to
* sizeof(struct net_device_ops).
*
* 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.
* 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 reset the rx headroom to the
* default value.
* 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.
* 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.
* void (*ndo_udp_tunnel_add)(struct net_device *dev,
* struct udp_tunnel_info *ti);
* Called by UDP tunnel to notify a driver about the UDP port and socket
* address family that a UDP tunnel is listnening to. It is called only
* when a new port starts listening. The operation is protected by the
* RTNL.
*
* void (*ndo_udp_tunnel_del)(struct net_device *dev,
* struct udp_tunnel_info *ti);
* Called by UDP tunnel to notify the driver about a UDP port and socket
* address family that the UDP tunnel is not listening to anymore. The
* operation is protected by the RTNL.
*
* int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan,
* u8 qos, __be16 proto);
*
* 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_change_mtu)(struct net_device *dev, int new_mtu);
* Called when a user wants to change the Maximum Transfer Unit
* of a device.
* RHEL: This is an entry point for network device drivers that
* use central MTU range checking provided by network core.
*
* 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.
* RHEL: Note that this callback is not part of kABI and its prototype
* and semantic can be changed across releases.
* int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp);
* This function is used to set or query state related to XDP on the
* netdevice. See definition of enum xdp_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.
* void (*ndo_xdp_flush)(struct net_device *dev);
* This function is used to inform the driver to flush a paticular
* xpd tx queue. Must be called on same CPU as xdp_xmit.
*/
struct net_device_ops_extended {
int (*ndo_set_vf_trust)(struct net_device *dev,
int vf, bool setting);
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);
void (*ndo_set_rx_headroom)(struct net_device *dev,
int needed_headroom);
int (*ndo_set_vf_guid)(struct net_device *dev,
int vf, u64 guid,
int guid_type);
int (*ndo_fdb_dump_rh73)(struct sk_buff *skb,
struct netlink_callback *cb,
struct net_device *dev,
struct net_device *filter_dev,
int idx);
int (*ndo_get_phys_port_name)(struct net_device *dev,
char *name, size_t len);
int (*ndo_change_proto_down)(struct net_device *dev,
bool proto_down);
void (*ndo_udp_tunnel_add)(struct net_device *dev,
struct udp_tunnel_info *ti);
void (*ndo_udp_tunnel_del)(struct net_device *dev,
struct udp_tunnel_info *ti);
int (*ndo_neigh_construct)(struct net_device *dev,
struct neighbour *n);
void (*ndo_neigh_destroy)(struct net_device *dev,
struct neighbour *n);
int (*ndo_set_vf_vlan)(struct net_device *dev,
int vf, u16 vlan, u8 qos,
__be16 proto);
int (*ndo_fdb_dump)(struct sk_buff *skb,
struct netlink_callback *cb,
struct net_device *dev,
struct net_device *filter_dev,
int *idx);
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);
int (*ndo_change_mtu)(struct net_device *dev,
int new_mtu);
/*
* RHEL: Note that this callback is not part of kABI and its prototype
* and semantic can be changed across releases.
*/
int (*ndo_setup_tc_rh)(struct net_device *dev,
enum tc_setup_type type,
void *type_data);
int (*ndo_xdp)(struct net_device *dev,
struct netdev_xdp *xdp);
int (*ndo_xdp_xmit)(struct net_device *dev, int n,
struct xdp_frame **xdp,
u32 flags);
void (*ndo_xdp_flush)(struct net_device *dev);
int (*ndo_bpf)(struct net_device *dev,
struct netdev_bpf *bpf);
int (*ndo_xsk_async_xmit)(struct net_device *dev,
u32 queue_id);
};
/* These structures hold the attributes of xdp state that are being passed
* to the netdevice through the xdp op.
*/
enum xdp_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.
*/
XDP_SETUP_PROG,
XDP_QUERY_PROG,
XDP_QUERY_XSK_UMEM,
XDP_SETUP_XSK_UMEM,
};
struct xdp_umem;
struct netdev_xdp {
enum xdp_netdev_command command;
union {
/* XDP_SETUP_PROG */
struct bpf_prog *prog;
/* XDP_QUERY_PROG */
struct {
u32 prog_id;
};
/* XDP_SETUP_XSK_UMEM */
struct {
struct xdp_umem *umem;
u16 queue_id;
} xsk;
};
};
/*
* 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, select_queue_fallback_t fallback);
* 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.
*
* 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.
*
* 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_rate)(struct net_device *dev, int vf, int min_tx_rate,
* int max_tx_rate);
* int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting);
* int (*ndo_set_vf_trust)(struct net_device *dev, int vf, bool setting);
* int (*ndo_get_vf_config)(struct net_device *dev,
* int vf, struct ifla_vf_info *ivf);
* int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state);
* int (*ndo_set_vf_port)(struct net_device *dev, int vf,
* struct nlattr *port[]);
*
* Enable or disable the VF ability to query its RSS Redirection Table and
* Hash Key. This is needed since on some devices VF share this information
* with PF and querying it may adduce a theoretical security risk.
* int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting);
* int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb);
* int (*ndo_setup_tc)(struct net_device *dev, u8 tc)
* Called to setup 'tc' number of traffic classes in the net device. This
* 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 vid, u16 flags)
* Adds an FDB entry to dev for addr.
* int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[],
* struct net_device *dev,
* const unsigned char *addr, u16 vid)
* Deletes the FDB entry from dev coresponding to addr.
* int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh,
* u16 flags)
* int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq,
* struct net_device *dev, u32 filter_mask,
* 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.
*
* 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_add_geneve_port)(struct net_device *dev,
* sa_family_t sa_family, __be16 port);
* Called by geneve to notify a driver about the UDP port and socket
* address family that geneve is listnening to. It is called only when
* a new port starts listening. The operation is protected by the
* geneve_net->sock_lock.
*
* void (*ndo_del_geneve_port)(struct net_device *dev,
* sa_family_t sa_family, __be16 port);
* Called by geneve to notify the driver about a UDP port and socket
* address family that geneve is not listening to anymore. The operation
* is protected by the geneve_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.
*
* int (*ndo_get_iflink)(const struct net_device *dev);
* Called to get the iflink value of this device.
*
* netdev_features_t (*ndo_features_check) (struct sk_buff *skb,
* struct net_device *dev
* netdev_features_t features);
* Called by core transmit path to determine if device is capable of
* performing offload operations on a given packet. This is to give
* the device an opportunity to implement any restrictions that cannot
* be otherwise expressed by feature flags. The check is called with
* the set of features that the stack has calculated and it returns
* those the driver believes to be appropriate.
* int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb);
* This function is used to get egress tunnel information for given skb.
* This is useful for retrieving outer tunnel header parameters while
* sampling packet.
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
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);
RH_KABI_REPLACE(u16 (*ndo_select_queue)(struct net_device *dev,
struct sk_buff *skb),
u16 (*ndo_select_queue)(struct net_device *dev,
struct sk_buff *skb,
void *accel_priv,
select_queue_fallback_t fallback))
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);
RH_KABI_RENAME(int (*ndo_change_mtu),
int (*ndo_change_mtu_rh74))(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);
RH_KABI_REPLACE(
struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev,
struct rtnl_link_stats64 *storage),
void (*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);
RH_KABI_RENAME(int (*ndo_set_vf_vlan),
int (*ndo_set_vf_vlan_rh73))(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);
RH_KABI_RENAME(int (*ndo_setup_tc),
int (*ndo_setup_tc_rh72))(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);
RH_KABI_RENAME(int (*ndo_neigh_construct),
int (*ndo_neigh_construct_rh73))(struct neighbour *n);
RH_KABI_RENAME(void (*ndo_neigh_destroy),
void (*ndo_neigh_destroy_rh73))(struct neighbour *n);
RH_KABI_RENAME(int (*ndo_fdb_add),
int (*ndo_fdb_add_rh72))(struct ndmsg *ndm,
struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr,
u16 flags);
RH_KABI_REPLACE(int (*ndo_fdb_del)(struct ndmsg *ndm,
struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr),
int (*ndo_fdb_del)(struct ndmsg *ndm,
struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr,
u16 vid))
RH_KABI_RENAME(int (*ndo_fdb_dump),
int (*ndo_fdb_dump_rh72))(struct sk_buff *skb,
struct netlink_callback *cb,
struct net_device *dev,
int idx);
RH_KABI_REPLACE(int (*ndo_bridge_setlink)(struct net_device *dev,
struct nlmsghdr *nlh),
int (*ndo_bridge_setlink)(struct net_device *dev,
struct nlmsghdr *nlh,
u16 flags))
RH_KABI_REPLACE(int (*ndo_bridge_getlink)(struct sk_buff *skb,
u32 pid, u32 seq,
struct net_device *dev,
u32 filter_mask),
int (*ndo_bridge_getlink)(struct sk_buff *skb,
u32 pid, u32 seq,
struct net_device *dev,
u32 filter_mask,
int nlflags))
RH_KABI_REPLACE(int (*ndo_bridge_dellink)(struct net_device *dev,
struct nlmsghdr *nlh),
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);
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);
/* RHEL SPECIFIC
*
* The following padding has been inserted before ABI freeze to
* allow extending the structure while preserve ABI. Feel free
* to replace reserved slots with required structure field
* additions of your backport.
*/
RH_KABI_USE_P(1, int (*ndo_get_iflink)(const struct net_device *dev))
RH_KABI_USE_P(2, netdev_features_t
(*ndo_features_check)(struct sk_buff *skb,
struct net_device *dev,
netdev_features_t features))
RH_KABI_USE_P(3, int (*ndo_set_vf_rate)(struct net_device *dev,
int vf, int min_tx_rate,
int max_tx_rate))
RH_KABI_USE_P(4, int (*ndo_get_vf_stats)(struct net_device *dev,
int vf,
struct ifla_vf_stats
*vf_stats))
RH_KABI_USE_P(5, int (*ndo_set_vf_rss_query_en)(struct net_device *dev,
int vf, bool setting))
RH_KABI_USE_P(6, int (*ndo_fdb_add)(struct ndmsg *ndm,
struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr,
u16 vid,
u16 flags))
RH_KABI_USE_P(7,int (*ndo_setup_tc_rh74)(struct net_device *dev,
u32 handle,
__be16 protocol,
struct tc_to_netdev_rh74 *tc))
RH_KABI_USE_P(8, int (*ndo_fill_metadata_dst)(struct net_device *dev,
struct sk_buff *skb))
RH_KABI_USE_P(9, void (*ndo_add_geneve_port)(struct net_device *dev,
sa_family_t sa_family,
__be16 port))
RH_KABI_USE_P(10, void (*ndo_del_geneve_port)(struct net_device *dev,
sa_family_t sa_family,
__be16 port))
RH_KABI_RESERVE_P(11)
RH_KABI_RESERVE_P(12)
RH_KABI_RESERVE_P(13)
RH_KABI_RESERVE_P(14)
RH_KABI_RESERVE_P(15)
RH_KABI_USE_P(16, size_t ndo_size)
/* RHEL: put all new non-performance critical ndo's into
* net_device_ops_extended. The reserved slots above can be used
* only for performance critical operations.
* Drivers may access the extended fields directly from
* net_device_ops, if they allocated the net_device_ops structure
* themselves (usually statically). The kernel core and drivers
* using others' net_device_ops must access the extended fields
* using the get_ndo_ext macro.
*/
RH_KABI_EXTEND(struct net_device_ops_extended extended)
};
#define get_ndo_ext(ops, field) ({ \
const struct net_device_ops *__ops = (ops); \
size_t __off = offsetof(struct net_device_ops, extended.field); \
__ops->ndo_size > __off ? __ops->extended.field : NULL; \
})
/**
* enum net_device_priv_flags - &struct net_device priv_flags
*
* These are the &struct net_device, they are only set internally
* by drivers and used in the kernel. These flags are invisible to
* userspace, this means that the order of these flags can change
* during any kernel release.
*
* You should have a pretty good reason to be extending these flags.
*
* @IFF_802_1Q_VLAN: 802.1Q VLAN device
* @IFF_EBRIDGE: Ethernet bridging device
* @IFF_SLAVE_INACTIVE: bonding slave not the curr. active
* @IFF_MASTER_8023AD: bonding master, 802.3ad
* @IFF_MASTER_ALB: bonding master, balance-alb
* @IFF_BONDING: bonding master or slave
* @IFF_SLAVE_NEEDARP: need ARPs for validation
* @IFF_ISATAP: ISATAP interface (RFC4214)
* @IFF_MASTER_ARPMON: bonding master, ARP mon in use
* @IFF_WAN_HDLC: WAN HDLC device
* @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to
* release skb->dst
* @IFF_DONT_BRIDGE: disallow bridging this ether dev
* @IFF_DISABLE_NETPOLL: disable netpoll at run-time
* @IFF_MACVLAN_PORT: device used as macvlan port
* @IFF_BRIDGE_PORT: device used as bridge port
* @IFF_OVS_DATAPATH: device used as Open vSwitch datapath port
* @IFF_TX_SKB_SHARING: The interface supports sharing skbs on transmit
* @IFF_UNICAST_FLT: Supports unicast filtering
* @IFF_TEAM_PORT: device used as team port
* @IFF_SUPP_NOFCS: device supports sending custom FCS
* @IFF_LIVE_ADDR_CHANGE: device supports hardware address
* change when it's running
* @IFF_MACVLAN: Macvlan device
* @IFF_NO_QUEUE: device can run without qdisc attached
* @IFF_OPENVSWITCH: device is a Open vSwitch master
* @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_FAILOVER: device is a failover master device
* @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device
*/
enum netdev_priv_flags {
IFF_802_1Q_VLAN = 1<<0,
IFF_EBRIDGE = 1<<1,
IFF_SLAVE_INACTIVE = 1<<2,
IFF_MASTER_8023AD = 1<<3,
IFF_MASTER_ALB = 1<<4,
IFF_BONDING = 1<<5,
IFF_SLAVE_NEEDARP = 1<<6,
IFF_ISATAP = 1<<7,
IFF_MASTER_ARPMON = 1<<8,
IFF_WAN_HDLC = 1<<9,
IFF_XMIT_DST_RELEASE = 1<<10,
IFF_DONT_BRIDGE = 1<<11,
IFF_DISABLE_NETPOLL = 1<<12,
IFF_MACVLAN_PORT = 1<<13,
IFF_BRIDGE_PORT = 1<<14,
IFF_OVS_DATAPATH = 1<<15,
IFF_TX_SKB_SHARING = 1<<16,
IFF_UNICAST_FLT = 1<<17,
IFF_TEAM_PORT = 1<<18,
IFF_SUPP_NOFCS = 1<<19,
IFF_LIVE_ADDR_CHANGE = 1<<20,
IFF_MACVLAN = 1<<21,
IFF_XMIT_DST_RELEASE_PERM = 1<<22,
IFF_OPENVSWITCH = 1<<23,
IFF_TEAM = 1<<24,
IFF_RXFH_CONFIGURED = 1<<25,
IFF_NO_QUEUE = 1<<26,
IFF_PHONY_HEADROOM = 1<<27,
IFF_MACSEC = 1<<28,
IFF_FAILOVER = 1<<27,
IFF_FAILOVER_SLAVE = 1<<28,
};
#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN
#define IFF_EBRIDGE IFF_EBRIDGE
#define IFF_SLAVE_INACTIVE IFF_SLAVE_INACTIVE
#define IFF_MASTER_8023AD IFF_MASTER_8023AD
#define IFF_MASTER_ALB IFF_MASTER_ALB
#define IFF_BONDING IFF_BONDING
#define IFF_SLAVE_NEEDARP IFF_SLAVE_NEEDARP
#define IFF_ISATAP IFF_ISATAP
#define IFF_MASTER_ARPMON IFF_MASTER_ARPMON
#define IFF_WAN_HDLC IFF_WAN_HDLC
#define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE
#define IFF_DONT_BRIDGE IFF_DONT_BRIDGE
#define IFF_DISABLE_NETPOLL IFF_DISABLE_NETPOLL
#define IFF_MACVLAN_PORT IFF_MACVLAN_PORT
#define IFF_BRIDGE_PORT IFF_BRIDGE_PORT
#define IFF_OVS_DATAPATH IFF_OVS_DATAPATH
#define IFF_TX_SKB_SHARING IFF_TX_SKB_SHARING
#define IFF_UNICAST_FLT IFF_UNICAST_FLT
#define IFF_TEAM_PORT IFF_TEAM_PORT
#define IFF_SUPP_NOFCS IFF_SUPP_NOFCS
#define IFF_LIVE_ADDR_CHANGE IFF_LIVE_ADDR_CHANGE
#define IFF_MACVLAN IFF_MACVLAN
#define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM
#define IFF_NO_QUEUE IFF_NO_QUEUE
#define IFF_OPENVSWITCH IFF_OPENVSWITCH
#define IFF_TEAM IFF_TEAM
#define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED
#define IFF_MACSEC IFF_MACSEC
#define IFF_FAILOVER IFF_FAILOVER
#define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE
/*
* 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.
*
* @proto_down: protocol port state information can be sent to the
* switch driver and used to set the phys state of the
* switch port.
*
* FIXME: cleanup struct net_device such that network protocol info
* moves out.
*/
struct net_device {
/*
* This is the first field of the "visible" part of this structure
* (i.e. as seen by users in the "Space.c" file). It is the name
* of the interface.
*/
char name[IFNAMSIZ];
/* device name hash chain, please keep it close to name[] */
struct hlist_node name_hlist;
/* snmp alias */
char *ifalias;
/*
* I/O specific fields
* FIXME: Merge these and struct ifmap into one
*/
unsigned long mem_end; /* shared mem end */
unsigned long mem_start; /* shared mem start */
unsigned long base_addr; /* device I/O address */
unsigned int irq; /* device IRQ number */
/*
* 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 upper_dev_list; /* List of upper devices */
/* 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 <net/iw_handler.h> 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;
/* 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 */
/* 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; /* 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; /* for shared network cards */
RH_KABI_FILL_HOLE(unsigned short dev_port) /* Used to differentiate
* devices that share the same
* function
*/
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;
RH_KABI_FILL_HOLE(bool proto_down)
/* RH_KABI: 2 bytes hole remain here */
unsigned int promiscuity;
unsigned int allmulti;
/* Stats to monitor carrier on<->off transitions */
RH_KABI_FILL_HOLE(atomic_t carrier_changes)
/* 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
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())
*/
RH_KABI_DEPRECATE(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_RPS
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 */
#ifdef CONFIG_NET_CLS_ACT
RH_KABI_FILL_HOLE(struct mini_Qdisc __rcu *miniq_ingress)
#endif
/* Hole: 16 bytes remain */
/*
* 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. */
RH_KABI_DEPRECATE(unsigned long, trans_start)
int watchdog_timeo; /* used by dev_watchdog() */
struct timer_list watchdog_timer;
/* Number of references to this device */
int __percpu *pcpu_refcnt;
/* delayed register/unregister */
struct list_head todo_list;
/* device index hash chain */
struct hlist_node index_hlist;
struct list_head link_watch_list;
/* register/unregister state machine */
enum { NETREG_UNINITIALIZED=0,
NETREG_REGISTERED, /* completed register_netdevice */
NETREG_UNREGISTERING, /* called unregister_netdevice */
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
/* Network namespace this network device is inside */
possible_net_t nd_net;
/* mid-layer private */
union {
void *ml_priv;
struct pcpu_lstats __percpu *lstats; /* loopback stats */
RH_KABI_REPLACE(struct pcpu_tstats __percpu *tstats, 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];
/* 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_NETPRIO_CGROUP)
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;
/* RHEL: e1000e was the only in-tree driver that used this */
RH_KABI_DEPRECATE(struct pm_qos_request, pm_qos_req)
/* RHEL SPECIFIC
*
* The following padding has been inserted before ABI freeze to
* allow extending the structure while preserve ABI. Feel free
* to replace reserved slots with required structure field
* additions of your backport.
*/
RH_KABI_USE_P(1, unsigned long gro_flush_timeout)
RH_KABI_USE_P(2, atomic_long_t rx_nohandler) /* inactive slave drops */
#ifndef __GENKSYMS__
struct list_head lower_dev_list;
/* directly linked devices, like slaves for bonding */
struct {
struct list_head upper;
struct list_head lower;
} adj_list;
/*
* RHEL ONLY: upstream has a matching all_adj_list that replaces
* upper_dev_list and lower_dev_list directly, but making that
* replacement would be a kabi nightmare, even more than we've
* already got right here.
*/
#else
/*
* struct list_head contains two pointers, no easy way to make use of
* two reserved pointers in a single RH_KABI_* macro, so we're going
* old school and using __GENKSYMS wrappers directly here.
*/
RH_KABI_USE_P(3, lower_dev_list.prev)
RH_KABI_USE_P(4, lower_dev_list.next)
RH_KABI_USE_P(5, adj_list.upper.prev)
RH_KABI_USE_P(6, adj_list.upper.next)
RH_KABI_USE_P(7, adj_list.lower.prev)
RH_KABI_USE_P(8, adj_list.lower.next)
#endif
RH_KABI_USE_P(9, const struct forwarding_accel_ops *fwd_ops)
RH_KABI_USE_P(10, const struct dcbnl_rtnl_ops_ext *dcbnl_ops_ext)
RH_KABI_USE_P(11, struct wpan_dev *ieee802154_ptr)
#ifndef __GENKSYMS__
/*
* We can't use the RH_KABI_* helpers cleanly here, since
* list_head requires two reserved fields.
* Mark them as used anyway.
*/
struct list_head close_list;
#else
RH_KABI_USE_P(12, close_list.prev)
RH_KABI_USE_P(13, close_list.next)
#endif
RH_KABI_USE_P(14, const struct switchdev_ops *switchdev_ops)
RH_KABI_USE_P(15, netdev_features_t gso_partial_features)
RH_KABI_USE_P(16, struct net_device_extended *extended)
};
/* RHEL specific: Extension of struct net_device. Place new fields at the
* end of this struct. Be careful, we're not guarded by the automatic kABI
* checks, yet any changes here are kABI protected.
* This means only appends to this structure are allowed. Changes are
* generally disallowed with the exception of field renames (but not type
* changes nor any shuffling!).
*
* @ndisc_ops: Includes callbacks for different IPv6 neighbour
* discovery handling. Necessary for e.g. 6LoWPAN.
*
* @min_mtu: Interface Minimum MTU value
* @max_mtu: Interface Maximum MTU value
* RHEL note: These bounds are only checked when the old
* .ndo_change_mtu_rh74 handler is *not* provided.
* See dev_set_mtu() in net/core/dev.c
* @needs_free_netdev: Should unregister perform free_netdev?
* @priv_destructor: Called from unregister
*/
struct net_device_extended {
#if IS_ENABLED(CONFIG_IPV6)
const struct ndisc_ops *ndisc_ops;
#endif
unsigned int min_mtu;
unsigned int max_mtu;
struct list_head ptype_all;
struct list_head ptype_specific;
bool needs_free_netdev;
void (*priv_destructor)(struct net_device *dev);
#ifdef CONFIG_NET_CLS_ACT
struct mini_Qdisc __rcu *miniq_egress;
#endif
#ifdef CONFIG_NET_SCHED
DECLARE_HASHTABLE (qdisc_hash, 4);
#endif
};
#define to_net_dev(d) container_of(d, struct net_device, dev)
#define NETDEV_ALIGN 32
static inline
bool __rh_has_ndo_setup_tc(const struct net_device *dev)
{
const struct net_device_ops *ops = dev->netdev_ops;
return (get_ndo_ext(ops, ndo_setup_tc_rh) ||
ops->ndo_setup_tc_rh74 ||
ops->ndo_setup_tc_rh72) ? true : false;
}
int __rh_call_ndo_setup_tc(struct net_device *dev, u32 handle,
enum tc_setup_type type, void *type_data);
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
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_xmit_lock_key; \
static struct lock_class_key dev_addr_list_lock_key; \
unsigned int i; \
\
(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_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); \
}
struct netdev_queue *netdev_pick_tx(struct net_device *dev,
struct sk_buff *skb,
void *accel_priv);
/* 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 (get_ndo_ext(dev->netdev_ops, ndo_set_rx_headroom))
get_ndo_ext(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);
}
/*
* 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);
}
static inline bool netdev_uses_dsa(struct net_device *dev)
{
#ifdef CONFIG_NET_DSA
return dev->dsa_ptr != NULL;
#else
return false;
#endif
}
/**
* 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
* fin grained indentification 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
void __netif_napi_add(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int), int weight,
size_t size);
/**
* 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.
*/
static inline void _netif_napi_add(struct net_device *dev,
struct napi_struct *napi,
int (*poll)(struct napi_struct *, int),
int weight)
{
__netif_napi_add(dev, napi, poll, weight, sizeof(struct napi_struct));
}
/* RHEL has netif_napi_add in KABI so we need to keep it for binary
* modules. Another reason is that older binary modules uses non-extended
* napi_struct. Newly compiled modules will use inlined function that uses
* current (extended) napi_struct. */
void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int), int weight);
#define netif_napi_add _netif_napi_add
/**
* 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
*
* 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;
/* 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;
/* 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;
/* Used in foo-over-udp, set in udp[46]_gro_receive */
u8 is_ipv6:1;
/* Free the skb? */
u8 free:2;
#define NAPI_GRO_FREE 1
#define NAPI_GRO_FREE_STOLEN_HEAD 2
/* This is non-zero if the packet may be of the same flow. */
u8 same_flow:1;
/* Number of gro_receive callbacks this packet already went through */
u8 recursion_counter:4;
/* Used to determine if flush_id can be ignored */
u8 is_atomic:1;
/* 2 bit hole */
/* 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)
#define GRO_RECURSION_LIMIT 15
static inline int gro_recursion_inc_test(struct sk_buff *skb)
{
return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT;
}
typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *);
static inline struct sk_buff **call_gro_receive(gro_receive_t cb,
struct sk_buff **head,
struct sk_buff *skb)
{
if (gro_recursion_inc_test(skb)) {
NAPI_GRO_CB(skb)->flush |= 1;
return NULL;
}
return cb(head, skb);
}
struct packet_type {
__be16 type; /* This is really htons(ether_type). */
struct net_device *dev; /* NULL is wildcarded here */
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;
RH_KABI_RESERVE(1)
RH_KABI_RESERVE(2)
RH_KABI_RESERVE(3)
RH_KABI_RESERVE(4)
};
struct offload_callbacks {
struct sk_buff *(*gso_segment)(struct sk_buff *skb,
netdev_features_t features);
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). */
u16 priority;
struct offload_callbacks callbacks;
struct list_head list;
};
struct dsa_device_ops {
netdev_tx_t (*xmit)(struct sk_buff *skb, struct net_device *dev);
int (*rcv)(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev);
};
/* often modified stats are per cpu, other are shared (netdev->stats) */
struct pcpu_sw_netstats {
u64 rx_packets;
u64 rx_bytes;
u64 tx_packets;
u64 tx_bytes;
struct u64_stats_sync syncp;
};
#define __netdev_alloc_pcpu_stats(type, gfp) \
({ \
typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\
if (pcpu_stats) { \
int __cpu; \
for_each_possible_cpu(__cpu) { \
typeof(type) *stat; \
stat = per_cpu_ptr(pcpu_stats, __cpu); \
u64_stats_init(&stat->syncp); \
} \
} \
pcpu_stats; \
})
#define netdev_alloc_pcpu_stats(type) \
__netdev_alloc_pcpu_stats(type, GFP_KERNEL)
enum netdev_lag_tx_type {
NETDEV_LAG_TX_TYPE_UNKNOWN,
NETDEV_LAG_TX_TYPE_RANDOM,
NETDEV_LAG_TX_TYPE_BROADCAST,
NETDEV_LAG_TX_TYPE_ROUNDROBIN,
NETDEV_LAG_TX_TYPE_ACTIVEBACKUP,
NETDEV_LAG_TX_TYPE_HASH,
};
enum netdev_lag_hash {
NETDEV_LAG_HASH_NONE,
NETDEV_LAG_HASH_L2,
NETDEV_LAG_HASH_L34,
NETDEV_LAG_HASH_L23,
NETDEV_LAG_HASH_E23,
NETDEV_LAG_HASH_E34,
NETDEV_LAG_HASH_UNKNOWN,
};
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_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_REGISTER,
NETDEV_UNREGISTER,
NETDEV_CHANGEMTU, /* notify after mtu change happened */
NETDEV_CHANGEADDR,
NETDEV_GOING_DOWN,
NETDEV_CHANGENAME,
NETDEV_FEAT_CHANGE,
NETDEV_BONDING_FAILOVER,
NETDEV_PRE_UP,
NETDEV_PRE_TYPE_CHANGE,
NETDEV_POST_TYPE_CHANGE,
NETDEV_POST_INIT,
NETDEV_UNREGISTER_FINAL,
NETDEV_RELEASE,
NETDEV_NOTIFY_PEERS,
NETDEV_JOIN,
NETDEV_CHANGEUPPER,
NETDEV_RESEND_IGMP,
NETDEV_PRECHANGEMTU, /* notify before mtu change happened */
NETDEV_CHANGEINFODATA,
NETDEV_BONDING_INFO,
NETDEV_PRECHANGEUPPER,
NETDEV_CHANGELOWERSTATE,
NETDEV_OFFLOAD_PUSH_VXLAN,
NETDEV_OFFLOAD_PUSH_GENEVE,
NETDEV_UDP_TUNNEL_PUSH_INFO,
NETDEV_CHANGE_TX_QUEUE_LEN,
NETDEV_UDP_TUNNEL_DROP_INFO,
/* RHEL: New values need to be placed at the end to avoid
* re-numbering of existing ones.
*/
};
const char *netdev_cmd_to_name(enum netdev_cmd cmd);
/* (Un)registration functions for the notifiers that takes
* 'struct net_device *' as parameter
*/
int register_netdevice_notifier(struct notifier_block *nb);
int unregister_netdevice_notifier(struct notifier_block *nb);
/* (Un)registration functions for the notifiers that takes
* 'struct netdev_notifier_info *' as parameter
*/
int register_netdevice_notifier_rh(struct notifier_block *nb);
int unregister_netdevice_notifier_rh(struct notifier_block *nb);
struct netdev_notifier_info {
struct net_device *dev;
};
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 nofication 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 */
};
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_info(unsigned long val, struct net_device *dev,
struct netdev_notifier_info *info);
int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
extern rwlock_t dev_base_lock; /* Device list lock */
extern seqcount_t devnet_rename_seq; /* Device rename seq */
#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);
void __dev_remove_offload(struct packet_offload *po);
int dev_get_iflink(const struct net_device *dev);
int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb);
struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,
unsigned short mask);
struct net_device *dev_get_by_name(struct net *net, const char *name);
struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);
struct net_device *__dev_get_by_name(struct net *net, const char *name);
int dev_alloc_name(struct net_device *dev, const char *name);
int dev_open(struct net_device *dev);
int dev_close(struct net_device *dev);
void dev_disable_lro(struct net_device *dev);
int dev_loopback_xmit(struct sock *sk, struct sk_buff *newskb);
int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb);
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);
DECLARE_PER_CPU(int, xmit_recursion);
static inline int dev_recursion_level(void)
{
return this_cpu_read(xmit_recursion);
}
struct net_device *dev_get_by_index(struct net *net, int ifindex);
struct net_device *__dev_get_by_index(struct net *net, int ifindex);
struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
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);
#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_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;
skb_gro_frag0_invalidate(skb);
return skb->data + offset;
}
static inline void *skb_gro_network_header(struct sk_buff *skb)
{
return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) +
skb_network_offset(skb);
}
static inline void skb_gro_postpull_rcsum(struct sk_buff *skb,
const void *start, unsigned int len)
{
if (NAPI_GRO_CB(skb)->csum_valid)
NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum,
csum_partial(start, len, 0));
}
/* GRO checksum functions. These are logical equivalents of the normal
* checksum functions (in skbuff.h) except that they operate on the GRO
* offsets and fields in sk_buff.
*/
__sum16 __skb_gro_checksum_complete(struct sk_buff *skb);
static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb)
{
return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb));
}
static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb,
bool zero_okay,
__sum16 check)
{
return ((skb->ip_summed != CHECKSUM_PARTIAL ||
skb_checksum_start_offset(skb) <
skb_gro_offset(skb)) &&
!skb_at_gro_remcsum_start(skb) &&
NAPI_GRO_CB(skb)->csum_cnt == 0 &&
(!zero_okay || check));
}
static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb,
__wsum psum)
{
if (NAPI_GRO_CB(skb)->csum_valid &&
!csum_fold(csum_add(psum, NAPI_GRO_CB(skb)->csum)))
return 0;
NAPI_GRO_CB(skb)->csum = psum;
return __skb_gro_checksum_complete(skb);
}
static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb)
{
if (NAPI_GRO_CB(skb)->csum_cnt > 0) {
/* Consume a checksum from CHECKSUM_UNNECESSARY */
NAPI_GRO_CB(skb)->csum_cnt--;
} else {
/* Update skb for CHECKSUM_UNNECESSARY and csum_level when we
* verified a new top level checksum or an encapsulated one
* during GRO. This saves work if we fallback to normal path.
*/
__skb_incr_checksum_unnecessary(skb);
}
}
#define __skb_gro_checksum_validate(skb, proto, zero_okay, check, \
compute_pseudo) \
({ \
__sum16 __ret = 0; \
if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \
__ret = __skb_gro_checksum_validate_complete(skb, \
compute_pseudo(skb, proto)); \
if (!__ret) \
skb_gro_incr_csum_unnecessary(skb); \
__ret; \
})
#define skb_gro_checksum_validate(skb, proto, compute_pseudo) \
__skb_gro_checksum_validate(skb, proto, false, 0, compute_pseudo)
#define skb_gro_checksum_validate_zero_check(skb, proto, check, \
compute_pseudo) \
__skb_gro_checksum_validate(skb, proto, true, check, compute_pseudo)
#define skb_gro_checksum_simple_validate(skb) \
__skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo)
static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb)
{
return (NAPI_GRO_CB(skb)->csum_cnt == 0 &&
!NAPI_GRO_CB(skb)->csum_valid);
}
static inline void __skb_gro_checksum_convert(struct sk_buff *skb,
__sum16 check, __wsum pseudo)
{
NAPI_GRO_CB(skb)->csum = ~pseudo;
NAPI_GRO_CB(skb)->csum_valid = 1;
}
#define skb_gro_checksum_try_convert(skb, proto, check, compute_pseudo) \
do { \
if (__skb_gro_checksum_convert_check(skb)) \
__skb_gro_checksum_convert(skb, check, \
compute_pseudo(skb, proto)); \
} while (0)
struct gro_remcsum {
int offset;
__wsum delta;
};
static inline void skb_gro_remcsum_init(struct gro_remcsum *grc)
{
grc->delta = 0;
}
static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr,
unsigned int off, size_t hdrlen,
int start, int offset,
struct gro_remcsum *grc,
bool nopartial)
{
__wsum delta;
size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start);
BUG_ON(!NAPI_GRO_CB(skb)->csum_valid);
if (!nopartial) {
NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start;
return ptr;
}
ptr = skb_gro_header_fast(skb, off);
if (skb_gro_header_hard(skb, off + plen)) {
ptr = skb_gro_header_slow(skb, off + plen, off);
if (!ptr)
return NULL;
}
delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum,
start, offset);
/* Adjust skb->csum since we changed the packet */
NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta);
grc->offset = off + hdrlen + offset;
grc->delta = delta;
return ptr;
}
static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb,
struct gro_remcsum *grc)
{
void *ptr;
size_t plen = grc->offset + sizeof(u16);
if (!grc->delta)
return;
ptr = skb_gro_header_fast(skb, grc->offset);
if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) {
ptr = skb_gro_header_slow(skb, plen, grc->offset);
if (!ptr)
return;
}
remcsum_unadjust((__sum16 *)ptr, grc->delta);
}
static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
unsigned short type,
const void *daddr, const void *saddr,
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);
}
/*
* 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;
};
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);
void netif_schedule_queue(struct netdev_queue *txq);
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_tx_start_all_queues(struct net_device *dev)
{
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
netif_tx_start_queue(txq);
}
}
void netif_tx_wake_queue(struct netdev_queue *dev_queue);
/**
* netif_wake_queue - restart transmit
* @dev: network device
*
* Allow upper layers to call the device hard_start_xmit routine.
* Used for flow control when transmit resources are available.
*/
static inline void netif_wake_queue(struct net_device *dev)
{
netif_tx_wake_queue(netdev_get_tx_queue(dev, 0));
}
static inline void netif_tx_wake_all_queues(struct net_device *dev)
{
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
netif_tx_wake_queue(txq);
}
}
static inline void netif_tx_stop_queue(struct netdev_queue *dev_queue)
{
if (WARN_ON(!dev_queue)) {
pr_info("netif_stop_queue() cannot be called before register_netdev()\n");
return;
}
set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
}
/**
* netif_stop_queue - stop transmitted packets
* @dev: network device
*
* Stop upper layers calling the device hard_start_xmit routine.
* Used for flow control when transmit resources are unavailable.
*/
static inline void netif_stop_queue(struct net_device *dev)
{
netif_tx_stop_queue(netdev_get_tx_queue(dev, 0));
}
static inline void netif_tx_stop_all_queues(struct net_device *dev)
{
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
netif_tx_stop_queue(txq);
}
}
static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue)
{
return test_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
}
/**
* netif_queue_stopped - test if transmit queue is flowblocked
* @dev: network device
*
* Test if transmit queue on device is currently unable to send.
*/
static inline bool netif_queue_stopped(const struct net_device *dev)
{
return netif_tx_queue_stopped(netdev_get_tx_queue(dev, 0));
}
static inline bool netif_xmit_stopped(const struct netdev_queue *dev_queue)
{
return dev_queue->state & QUEUE_STATE_ANY_XOFF;
}
static inline bool
netif_xmit_frozen_or_stopped(const struct netdev_queue *dev_queue)
{
return dev_queue->state & QUEUE_STATE_ANY_XOFF_OR_FROZEN;
}
static inline bool
netif_xmit_frozen_or_drv_stopped(const struct netdev_queue *dev_queue)
{
return dev_queue->state & QUEUE_STATE_DRV_XOFF_OR_FROZEN;
}
/**
* netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write
* @dev_queue: pointer to transmit queue
*
* BQL enabled drivers might use this helper in their ndo_start_xmit(),
* to give appropriate hint to the cpu.
*/
static inline void netdev_txq_bql_enqueue_prefetchw(struct netdev_queue *dev_queue)
{
#ifdef CONFIG_BQL
prefetchw(&dev_queue->dql.num_queued);
#endif
}
/**
* netdev_txq_bql_complete_prefetchw - prefetch bql data for write
* @dev_queue: pointer to transmit queue
*
* BQL enabled drivers might use this helper in their TX completion path,
* to give appropriate hint to the cpu.
*/
static inline void netdev_txq_bql_complete_prefetchw(struct netdev_queue *dev_queue)
{
#ifdef CONFIG_BQL
prefetchw(&dev_queue->dql.limit);
#endif
}
static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
unsigned int bytes)
{
#ifdef CONFIG_BQL
dql_queued(&dev_queue->dql, bytes);
if (likely(dql_avail(&dev_queue->dql) >= 0))
return;
set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
/*
* The XOFF flag must be set before checking the dql_avail below,
* because in netdev_tx_completed_queue we update the dql_completed
* before checking the XOFF flag.
*/
smp_mb();
/* check again in case another CPU has just made room avail */
if (unlikely(dql_avail(&dev_queue->dql) >= 0))
clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
#endif
}
/* Variant of netdev_tx_sent_queue() for drivers that are aware
* that they should not test BQL status themselves.
* We do want to change __QUEUE_STATE_STACK_XOFF only for the last
* skb of a batch.
* Returns true if the doorbell must be used to kick the NIC.
*/
static inline bool __netdev_tx_sent_queue(struct netdev_queue *dev_queue,
unsigned int bytes,
bool xmit_more)
{
if (xmit_more) {
#ifdef CONFIG_BQL
dql_queued(&dev_queue->dql, bytes);
#endif
return netif_tx_queue_stopped(dev_queue);
}
netdev_tx_sent_queue(dev_queue, bytes);
return true;
}
/**
* netdev_sent_queue - report the number of bytes queued to hardware
* @dev: network device
* @bytes: number of bytes queued to the hardware device queue
*
* Report the number of bytes queued for sending/completion to the network
* device hardware queue. @bytes should be a good approximation and should
* exactly match netdev_completed_queue() @bytes
*/
static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes)
{
netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes);
}
static inline bool __netdev_sent_queue(struct net_device *dev,
unsigned int bytes,
bool xmit_more)
{
return __netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes,
xmit_more);
}
static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue,
unsigned int pkts, unsigned int bytes)
{
#ifdef CONFIG_BQL
if (unlikely(!bytes))
return;
dql_completed(&dev_queue->dql, bytes);
/*
* Without the memory barrier there is a small possiblity that
* netdev_tx_sent_queue will miss the update and cause the queue to
* be stopped forever
*/
smp_mb();
if (dql_avail(&dev_queue->dql) < 0)
return;
if (test_and_clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state))
netif_schedule_queue(dev_queue);
#endif
}
/**
* netdev_completed_queue - report bytes and packets completed by device
* @dev: network device
* @pkts: actual number of packets sent over the medium
* @bytes: actual number of bytes sent over the medium
*
* Report the number of bytes and packets transmitted by the network device
* hardware queue over the physical medium, @bytes must exactly match the
* @bytes amount passed to netdev_sent_queue()
*/
static inline void netdev_completed_queue(struct net_device *dev,
unsigned int pkts, unsigned int bytes)
{
netdev_tx_completed_queue(netdev_get_tx_queue(dev, 0), pkts, bytes);
}
static inline void netdev_tx_reset_queue(struct netdev_queue *q)
{
#ifdef CONFIG_BQL
clear_bit(__QUEUE_STATE_STACK_XOFF, &q->state);
dql_reset(&q->dql);
#endif
}
/**
* netdev_reset_queue - reset the packets and bytes count of a network device
* @dev_queue: network device
*
* Reset the bytes and packet count of a network device and clear the
* software flow control OFF bit for this network device
*/
static inline void netdev_reset_queue(struct net_device *dev_queue)
{
netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0));
}
/**
* netdev_cap_txqueue - check if selected tx queue exceeds device queues
* @dev: network device
* @queue_index: given tx queue index
*
* Returns 0 if given tx queue index >= number of device tx queues,
* otherwise returns the originally passed tx queue index.
*/
static inline u16 netdev_cap_txqueue(struct net_device *dev, u16 queue_index)
{
if (unlikely(queue_index >= dev->real_num_tx_queues)) {
net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
dev->name, queue_index,
dev->real_num_tx_queues);
return 0;
}
return queue_index;
}
/**
* netif_running - test if up
* @dev: network device
*
* Test if the device has been brought up.
*/
static inline bool netif_running(const struct net_device *dev)
{
return test_bit(__LINK_STATE_START, &dev->state);
}
/*
* Routines to manage the subqueues on a device. We only need start
* stop, and a check if it's stopped. All other device management is
* done at the overall netdevice level.
* Also test the device if we're multiqueue.
*/
/**
* netif_start_subqueue - allow sending packets on subqueue
* @dev: network device
* @queue_index: sub queue index
*
* Start individual transmit queue of a device with multiple transmit queues.
*/
static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index)
{
struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
netif_tx_start_queue(txq);
}
/**
* netif_stop_subqueue - stop sending packets on subqueue
* @dev: network device
* @queue_index: sub queue index
*
* Stop individual transmit queue of a device with multiple transmit queues.
*/
static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index)
{
struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
netif_tx_stop_queue(txq);
}
/**
* netif_subqueue_stopped - test status of subqueue
* @dev: network device
* @queue_index: sub queue index
*
* Check individual transmit queue of a device with multiple transmit queues.
*/
static inline bool __netif_subqueue_stopped(const struct net_device *dev,
u16 queue_index)
{
struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
return netif_tx_queue_stopped(txq);
}
static inline bool netif_subqueue_stopped(const struct net_device *dev,
struct sk_buff *skb)
{
return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb));
}
void netif_wake_subqueue(struct net_device *dev, u16 queue_index);
#ifdef CONFIG_XPS
int netif_set_xps_queue(struct net_device *dev,
const struct cpumask *mask,
u16 index);
#else
static inline int netif_set_xps_queue(struct net_device *dev,
const struct cpumask *mask,
u16 index)
{
return 0;
}
#endif
u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
unsigned int num_tx_queues);
/*
* Returns a Tx hash for the given packet when dev->real_num_tx_queues is used
* as a distribution range limit for the returned value.
*/
static inline u16 skb_tx_hash(const struct net_device *dev,
struct sk_buff *skb)
{
return __skb_tx_hash(dev, skb, dev->real_num_tx_queues);
}
/**
* netif_is_multiqueue - test if device has multiple transmit queues
* @dev: network device
*
* Check if device has multiple transmit queues
*/
static inline bool netif_is_multiqueue(const struct net_device *dev)
{
return dev->num_tx_queues > 1;
}
int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq);
#ifdef CONFIG_RPS
int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq);
#else
static inline int netif_set_real_num_rx_queues(struct net_device *dev,
unsigned int rxq)
{
return 0;
}
#endif
static inline int netif_copy_real_num_queues(struct net_device *to_dev,
const struct net_device *from_dev)
{
int err;
err = netif_set_real_num_tx_queues(to_dev,
from_dev->real_num_tx_queues);
if (err)
return err;
#ifdef CONFIG_RPS
return netif_set_real_num_rx_queues(to_dev,
from_dev->real_num_rx_queues);
#else
return 0;
#endif
}
#define DEFAULT_MAX_NUM_RSS_QUEUES (8)
int netif_get_num_default_rss_queues(void);
enum skb_free_reason {
SKB_REASON_CONSUMED,
SKB_REASON_DROPPED,
};
void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason);
void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason);
/*
* It is not allowed to call kfree_skb() or consume_skb() from hardware
* interrupt context or with hardware interrupts being disabled.
* (in_irq() || irqs_disabled())
*
* We provide four helpers that can be used in following contexts :
*
* dev_kfree_skb_irq(skb) when caller drops a packet from irq context,
* replacing kfree_skb(skb)
*
* dev_consume_skb_irq(skb) when caller consumes a packet from irq context.
* Typically used in place of consume_skb(skb) in TX completion path
*
* dev_kfree_skb_any(skb) when caller doesn't know its current irq context,
* replacing kfree_skb(skb)
*
* dev_consume_skb_any(skb) when caller doesn't know its current irq context,
* and consumed a packet. Used in place of consume_skb(skb)
*/
static inline void _dev_kfree_skb_irq(struct sk_buff *skb)
{
__dev_kfree_skb_irq(skb, SKB_REASON_DROPPED);
}
/* RHEL has dev_kfree_skb_irq in KABI so we need to keep it for binary
* modules but we need to ensure that compiled modules use new inlined
* function. */
void dev_kfree_skb_irq(struct sk_buff *skb);
#define dev_kfree_skb_irq _dev_kfree_skb_irq
static inline void dev_consume_skb_irq(struct sk_buff *skb)
{
__dev_kfree_skb_irq(skb, SKB_REASON_CONSUMED);
}
static inline void _dev_kfree_skb_any(struct sk_buff *skb)
{
__dev_kfree_skb_any(skb, SKB_REASON_DROPPED);
}
/* RHEL has dev_kfree_skb_any in KABI etc. (see above) */
void dev_kfree_skb_any(struct sk_buff *skb);
#define dev_kfree_skb_any _dev_kfree_skb_any
static inline void dev_consume_skb_any(struct sk_buff *skb)
{
__dev_kfree_skb_any(skb, SKB_REASON_CONSUMED);
}
int netif_rx(struct sk_buff *skb);
int netif_rx_ni(struct sk_buff *skb);
int netif_receive_skb(struct sk_buff *skb);
gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
void napi_gro_flush(struct napi_struct *napi, bool flush_old);
struct sk_buff *napi_get_frags(struct napi_struct *napi);
gro_result_t napi_gro_frags(struct napi_struct *napi);
struct packet_offload *gro_find_receive_by_type(__be16 type);
struct packet_offload *gro_find_complete_by_type(__be16 type);
static inline void napi_free_frags(struct napi_struct *napi)
{
kfree_skb(napi->skb);
napi->skb = NULL;
}
bool netdev_is_rx_handler_busy(struct net_device *dev);
int netdev_rx_handler_register(struct net_device *dev,
rx_handler_func_t *rx_handler,
void *rx_handler_data);
void netdev_rx_handler_unregister(struct net_device *dev);
bool dev_valid_name(const char *name);
int dev_ioctl(struct net *net, unsigned int cmd, void __user *);
int dev_ethtool(struct net *net, struct ifreq *);
unsigned int dev_get_flags(const struct net_device *);
int __dev_change_flags(struct net_device *, unsigned int flags);
int dev_change_flags(struct net_device *, unsigned int);
void __dev_notify_flags(struct net_device *, unsigned int old_flags,
unsigned int gchanges);
int dev_change_name(struct net_device *, const char *);
int dev_set_alias(struct net_device *, const char *, size_t);
int dev_change_net_namespace(struct net_device *, struct net *, const char *);
int __dev_set_mtu(struct net_device *, int);
int dev_set_mtu(struct net_device *, int);
void dev_set_group(struct net_device *, int);
int dev_set_mac_address(struct net_device *, struct sockaddr *);
int dev_change_carrier(struct net_device *, bool new_carrier);
int dev_get_phys_port_id(struct net_device *dev,
struct netdev_phys_item_id *ppid);
int dev_get_phys_port_name(struct net_device *dev,
char *name, size_t len);
int dev_change_proto_down(struct net_device *dev, bool proto_down);
int dev_change_xdp_fd(struct net_device *dev, int fd);
struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev);
struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, int *ret);
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb);
extern int netdev_budget;
/* Called by rtnetlink.c:rtnl_unlock() */
void netdev_run_todo(void);
/**
* dev_put - release reference to device
* @dev: network device
*
* Release reference to device to allow it to be freed.
*/
static inline void dev_put(struct net_device *dev)
{
this_cpu_dec(*dev->pcpu_refcnt);
}
/**
* dev_hold - get reference to device
* @dev: network device
*
* Hold reference to device to keep it from being freed.
*/
static inline void dev_hold(struct net_device *dev)
{
this_cpu_inc(*dev->pcpu_refcnt);
}
/* Carrier loss detection, dial on demand. The functions netif_carrier_on
* and _off may be called from IRQ context, but it is caller
* who is responsible for serialization of these calls.
*
* The name carrier is inappropriate, these functions should really be
* called netif_lowerlayer_*() because they represent the state of any
* kind of lower layer not just hardware media.
*/
void linkwatch_init_dev(struct net_device *dev);
void linkwatch_fire_event(struct net_device *dev);
void linkwatch_forget_dev(struct net_device *dev);
/**
* netif_carrier_ok - test if carrier present
* @dev: network device
*
* Check if carrier is present on device
*/
static inline bool netif_carrier_ok(const struct net_device *dev)
{
return !test_bit(__LINK_STATE_NOCARRIER, &dev->state);
}
unsigned long dev_trans_start(struct net_device *dev);
void __netdev_watchdog_up(struct net_device *dev);
void netif_carrier_on(struct net_device *dev);
void netif_carrier_off(struct net_device *dev);
/**
* netif_dormant_on - mark device as dormant.
* @dev: network device
*
* Mark device as dormant (as per RFC2863).
*
* The dormant state indicates that the relevant interface is not
* actually in a condition to pass packets (i.e., it is not 'up') but is
* in a "pending" state, waiting for some external event. For "on-
* demand" interfaces, this new state identifies the situation where the
* interface is waiting for events to place it in the up state.
*
*/
static inline void netif_dormant_on(struct net_device *dev)
{
if (!test_and_set_bit(__LINK_STATE_DORMANT, &dev->state))
linkwatch_fire_event(dev);
}
/**
* netif_dormant_off - set device as not dormant.
* @dev: network device
*
* Device is not in dormant state.
*/
static inline void netif_dormant_off(struct net_device *dev)
{
if (test_and_clear_bit(__LINK_STATE_DORMANT, &dev->state))
linkwatch_fire_event(dev);
}
/**
* netif_dormant - test if carrier present
* @dev: network device
*
* Check if carrier is present on device
*/
static inline bool netif_dormant(const struct net_device *dev)
{
return test_bit(__LINK_STATE_DORMANT, &dev->state);
}
/**
* netif_oper_up - test if device is operational
* @dev: network device
*
* Check if carrier is operational
*/
static inline bool netif_oper_up(const struct net_device *dev)
{
return (dev->operstate == IF_OPER_UP ||
dev->operstate == IF_OPER_UNKNOWN /* backward compat */);
}
/**
* netif_device_present - is device available or removed
* @dev: network device
*
* Check if device has not been removed from system.
*/
static inline bool netif_device_present(struct net_device *dev)
{
return test_bit(__LINK_STATE_PRESENT, &dev->state);
}
void netif_device_detach(struct net_device *dev);
void netif_device_attach(struct net_device *dev);
/*
* Network interface message level settings
*/
enum {
NETIF_MSG_DRV = 0x0001,
NETIF_MSG_PROBE = 0x0002,
NETIF_MSG_LINK = 0x0004,
NETIF_MSG_TIMER = 0x0008,
NETIF_MSG_IFDOWN = 0x0010,
NETIF_MSG_IFUP = 0x0020,
NETIF_MSG_RX_ERR = 0x0040,
NETIF_MSG_TX_ERR = 0x0080,
NETIF_MSG_TX_QUEUED = 0x0100,
NETIF_MSG_INTR = 0x0200,
NETIF_MSG_TX_DONE = 0x0400,
NETIF_MSG_RX_STATUS = 0x0800,
NETIF_MSG_PKTDATA = 0x1000,
NETIF_MSG_HW = 0x2000,
NETIF_MSG_WOL = 0x4000,
};
#define netif_msg_drv(p) ((p)->msg_enable & NETIF_MSG_DRV)
#define netif_msg_probe(p) ((p)->msg_enable & NETIF_MSG_PROBE)
#define netif_msg_link(p) ((p)->msg_enable & NETIF_MSG_LINK)
#define netif_msg_timer(p) ((p)->msg_enable & NETIF_MSG_TIMER)
#define netif_msg_ifdown(p) ((p)->msg_enable & NETIF_MSG_IFDOWN)
#define netif_msg_ifup(p) ((p)->msg_enable & NETIF_MSG_IFUP)
#define netif_msg_rx_err(p) ((p)->msg_enable & NETIF_MSG_RX_ERR)
#define netif_msg_tx_err(p) ((p)->msg_enable & NETIF_MSG_TX_ERR)
#define netif_msg_tx_queued(p) ((p)->msg_enable & NETIF_MSG_TX_QUEUED)
#define netif_msg_intr(p) ((p)->msg_enable & NETIF_MSG_INTR)
#define netif_msg_tx_done(p) ((p)->msg_enable & NETIF_MSG_TX_DONE)
#define netif_msg_rx_status(p) ((p)->msg_enable & NETIF_MSG_RX_STATUS)
#define netif_msg_pktdata(p) ((p)->msg_enable & NETIF_MSG_PKTDATA)
#define netif_msg_hw(p) ((p)->msg_enable & NETIF_MSG_HW)
#define netif_msg_wol(p) ((p)->msg_enable & NETIF_MSG_WOL)
static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits)
{
/* use default */
if (debug_value < 0 || debug_value >= (sizeof(u32) * 8))
return default_msg_enable_bits;
if (debug_value == 0) /* no output */
return 0;
/* set low N bits */
return (1 << debug_value) - 1;
}
static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
{
spin_lock(&txq->_xmit_lock);
txq->xmit_lock_owner = cpu;
}
static inline void __netif_tx_lock_bh(struct netdev_queue *txq)
{
spin_lock_bh(&txq->_xmit_lock);
txq->xmit_lock_owner = smp_processor_id();
}
static inline bool __netif_tx_trylock(struct netdev_queue *txq)
{
bool ok = spin_trylock(&txq->_xmit_lock);
if (likely(ok))
txq->xmit_lock_owner = smp_processor_id();
return ok;
}
static inline void __netif_tx_unlock(struct netdev_queue *txq)
{
txq->xmit_lock_owner = -1;
spin_unlock(&txq->_xmit_lock);
}
static inline void __netif_tx_unlock_bh(struct netdev_queue *txq)
{
txq->xmit_lock_owner = -1;
spin_unlock_bh(&txq->_xmit_lock);
}
static inline void txq_trans_update(struct netdev_queue *txq)
{
if (txq->xmit_lock_owner != -1)
txq->trans_start = jiffies;
}
/* legacy drivers only, netdev_start_xmit() sets txq->trans_start */
static inline void netif_trans_update(struct net_device *dev)
{
struct netdev_queue *txq = netdev_get_tx_queue(dev, 0);
if (txq->trans_start != jiffies)
txq->trans_start = jiffies;
/* RHEL - update deprecated trans_start for old binary modules */
dev->rh_reserved_trans_start = jiffies;
}
/**
* netif_tx_lock - grab network device transmit lock
* @dev: network device
*
* Get network device transmit lock
*/
static inline void netif_tx_lock(struct net_device *dev)
{
unsigned int i;
int cpu;
spin_lock(&dev->tx_global_lock);
cpu = smp_processor_id();
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
/* We are the only thread of execution doing a
* freeze, but we have to grab the _xmit_lock in
* order to synchronize with threads which are in
* the ->hard_start_xmit() handler and already
* checked the frozen bit.
*/
__netif_tx_lock(txq, cpu);
set_bit(__QUEUE_STATE_FROZEN, &txq->state);
__netif_tx_unlock(txq);
}
}
static inline void netif_tx_lock_bh(struct net_device *dev)
{
local_bh_disable();
netif_tx_lock(dev);
}
static inline void netif_tx_unlock(struct net_device *dev)
{
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
/* No need to grab the _xmit_lock here. If the
* queue is not stopped for another reason, we
* force a schedule.
*/
clear_bit(__QUEUE_STATE_FROZEN, &txq->state);
netif_schedule_queue(txq);
}
spin_unlock(&dev->tx_global_lock);
}
static inline void netif_tx_unlock_bh(struct net_device *dev)
{
netif_tx_unlock(dev);
local_bh_enable();
}
#define HARD_TX_LOCK(dev, txq, cpu) { \
if ((dev->features & NETIF_F_LLTX) == 0) { \
__netif_tx_lock(txq, cpu); \
} \
}
#define HARD_TX_UNLOCK(dev, txq) { \
if ((dev->features & NETIF_F_LLTX) == 0) { \
__netif_tx_unlock(txq); \
} \
}
static inline void netif_tx_disable(struct net_device *dev)
{
unsigned int i;
int cpu;
local_bh_disable();
cpu = smp_processor_id();
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
__netif_tx_lock(txq, cpu);
netif_tx_stop_queue(txq);
__netif_tx_unlock(txq);
}
local_bh_enable();
}
static inline void netif_addr_lock(struct net_device *dev)
{
spin_lock(&dev->addr_list_lock);
}
static inline void netif_addr_lock_nested(struct net_device *dev)
{
spin_lock_nested(&dev->addr_list_lock, SINGLE_DEPTH_NESTING);
}
static inline void netif_addr_lock_bh(struct net_device *dev)
{
spin_lock_bh(&dev->addr_list_lock);
}
static inline void netif_addr_unlock(struct net_device *dev)
{
spin_unlock(&dev->addr_list_lock);
}
static inline void netif_addr_unlock_bh(struct net_device *dev)
{
spin_unlock_bh(&dev->addr_list_lock);
}
/*
* dev_addrs walker. Should be used only for read access. Call with
* rcu_read_lock held.
*/
#define for_each_dev_addr(dev, ha) \
list_for_each_entry_rcu(ha, &dev->dev_addrs.list, list)
/* These functions live elsewhere (drivers/net/net_init.c, but related) */
/*
* RHEL 7.5+: The network core checks MTU value requested by an user
* against minimum and maximum stored in .min_mtu and .max_mtu fields when
* both .extended.ndo_change_mtu() as well as .ndo_change_mtu_rh74() are
* not implemented by a driver. Default values for .{min,max}_mtu are
* initialized by ether_setup() but because this function is on kABI
* white-list we have to preserve its semantic so this initialization
* cannot be placed there. Instead of this we have to create separate
* ether_setup_rh() that additionally initializes .{min,max}_mtu.
* Macro ether_setup ensures that old ether_setup (preserved for existing
* binary modules) is not used by inbox drivers & o-o-box drivers compiled
* against RHEL-7.5 and above.
*/
void ether_setup_rh(struct net_device *dev);
#define ether_setup ether_setup_rh
/* Support for loadable net-drivers */
struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
void (*setup)(struct net_device *),
unsigned int txqs, unsigned int rxqs);
int dev_get_valid_name(struct net *net, struct net_device *dev,
const char *name);
#define alloc_netdev(sizeof_priv, name, setup) \
alloc_netdev_mqs(sizeof_priv, name, setup, 1, 1)
#define alloc_netdev_mq(sizeof_priv, name, setup, count) \
alloc_netdev_mqs(sizeof_priv, name, setup, count, count)
int register_netdev(struct net_device *dev);
void unregister_netdev(struct net_device *dev);
/* General hardware address lists handling functions */
int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
struct netdev_hw_addr_list *from_list, int addr_len);
void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
struct netdev_hw_addr_list *from_list, int addr_len);
int __hw_addr_sync_dev(struct netdev_hw_addr_list *list,
struct net_device *dev,
int (*sync)(struct net_device *, const unsigned char *),
int (*unsync)(struct net_device *,
const unsigned char *));
void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list,
struct net_device *dev,
int (*unsync)(struct net_device *,
const unsigned char *));
void __hw_addr_init(struct netdev_hw_addr_list *list);
/* Functions used for device addresses handling */
int dev_addr_add(struct net_device *dev, const unsigned char *addr,
unsigned char addr_type);
int dev_addr_del(struct net_device *dev, const unsigned char *addr,
unsigned char addr_type);
void dev_addr_flush(struct net_device *dev);
int dev_addr_init(struct net_device *dev);
/* Functions used for unicast addresses handling */
int dev_uc_add(struct net_device *dev, const unsigned char *addr);
int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr);
int dev_uc_del(struct net_device *dev, const unsigned char *addr);
int dev_uc_sync(struct net_device *to, struct net_device *from);
int dev_uc_sync_multiple(struct net_device *to, struct net_device *from);
void dev_uc_unsync(struct net_device *to, struct net_device *from);
void dev_uc_flush(struct net_device *dev);
void dev_uc_init(struct net_device *dev);
/**
* __dev_uc_sync - Synchonize device's unicast list
* @dev: device to sync
* @sync: function to call if address should be added
* @unsync: function to call if address should be removed
*
* Add newly added addresses to the interface, and release
* addresses that have been deleted.
**/
static inline int __dev_uc_sync(struct net_device *dev,
int (*sync)(struct net_device *,
const unsigned char *),
int (*unsync)(struct net_device *,
const unsigned char *))
{
return __hw_addr_sync_dev(&dev->uc, dev, sync, unsync);
}
/**
* __dev_uc_unsync - Remove synchonized addresses from device
* @dev: device to sync
* @unsync: function to call if address should be removed
*
* Remove all addresses that were added to the device by dev_uc_sync().
**/
static inline void __dev_uc_unsync(struct net_device *dev,
int (*unsync)(struct net_device *,
const unsigned char *))
{
__hw_addr_unsync_dev(&dev->uc, dev, unsync);
}
/* Functions used for multicast addresses handling */
int dev_mc_add(struct net_device *dev, const unsigned char *addr);
int dev_mc_add_global(struct net_device *dev, const unsigned char *addr);
int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr);
int dev_mc_del(struct net_device *dev, const unsigned char *addr);
int dev_mc_del_global(struct net_device *dev, const unsigned char *addr);
int dev_mc_sync(struct net_device *to, struct net_device *from);
int dev_mc_sync_multiple(struct net_device *to, struct net_device *from);
void dev_mc_unsync(struct net_device *to, struct net_device *from);
void dev_mc_flush(struct net_device *dev);
void dev_mc_init(struct net_device *dev);
/**
* __dev_mc_sync - Synchonize device's multicast list
* @dev: device to sync
* @sync: function to call if address should be added
* @unsync: function to call if address should be removed
*
* Add newly added addresses to the interface, and release
* addresses that have been deleted.
**/
static inline int __dev_mc_sync(struct net_device *dev,
int (*sync)(struct net_device *,
const unsigned char *),
int (*unsync)(struct net_device *,
const unsigned char *))
{
return __hw_addr_sync_dev(&dev->mc, dev, sync, unsync);
}
/**
* __dev_mc_unsync - Remove synchonized addresses from device
* @dev: device to sync
* @unsync: function to call if address should be removed
*
* Remove all addresses that were added to the device by dev_mc_sync().
**/
static inline void __dev_mc_unsync(struct net_device *dev,
int (*unsync)(struct net_device *,
const unsigned char *))
{
__hw_addr_unsync_dev(&dev->mc, dev, unsync);
}
/* Functions used for secondary unicast and multicast support */
void dev_set_rx_mode(struct net_device *dev);
void __dev_set_rx_mode(struct net_device *dev);
int dev_set_promiscuity(struct net_device *dev, int inc);
int dev_set_allmulti(struct net_device *dev, int inc);
void netdev_state_change(struct net_device *dev);
void netdev_notify_peers(struct net_device *dev);
void netdev_features_change(struct net_device *dev);
/* Load a device via the kmod */
void dev_load(struct net *net, const char *name);
struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
struct rtnl_link_stats64 *storage);
void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
const struct net_device_stats *netdev_stats);
extern int netdev_max_backlog;
extern int netdev_tstamp_prequeue;
extern int weight_p;
extern int dev_weight_rx_bias;
extern int dev_weight_tx_bias;
extern int dev_rx_weight;
extern int dev_tx_weight;
extern int bpf_jit_enable;
bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev);
bool netdev_has_any_upper_dev(struct net_device *dev);
struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
struct list_head **iter);
struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
struct list_head **iter);
/* iterate through upper list, must be called under RCU read lock */
#define netdev_for_each_upper_dev_rcu(dev, updev, iter) \
for (iter = &(dev)->adj_list.upper, \
updev = netdev_upper_get_next_dev_rcu(dev, &(iter)); \
updev; \
updev = netdev_upper_get_next_dev_rcu(dev, &(iter)))
/* iterate through upper list, must be called under RCU read lock */
#define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \
for (iter = &(dev)->upper_dev_list, \
updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)); \
updev; \
updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)))
int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *upper_dev,
void *data),
void *data);
bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
struct net_device *upper_dev);
bool netdev_has_any_upper_dev(struct net_device *dev);
void *netdev_lower_get_next_private(struct net_device *dev,
struct list_head **iter);
void *netdev_lower_get_next_private_rcu(struct net_device *dev,
struct list_head **iter);
#define netdev_for_each_lower_private(dev, priv, iter) \
for (iter = (dev)->adj_list.lower.next, \
priv = netdev_lower_get_next_private(dev, &(iter)); \
priv; \
priv = netdev_lower_get_next_private(dev, &(iter)))
#define netdev_for_each_lower_private_rcu(dev, priv, iter) \
for (iter = &(dev)->adj_list.lower, \
priv = netdev_lower_get_next_private_rcu(dev, &(iter)); \
priv; \
priv = netdev_lower_get_next_private_rcu(dev, &(iter)))
void *netdev_lower_get_next(struct net_device *dev,
struct list_head **iter);
#define netdev_for_each_lower_dev(dev, ldev, iter) \
for (iter = &(dev)->adj_list.lower, \
ldev = netdev_lower_get_next(dev, &(iter)); \
ldev; \
ldev = netdev_lower_get_next(dev, &(iter)))
struct net_device *netdev_all_lower_get_next(struct net_device *dev,
struct list_head **iter);
struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
struct list_head **iter);
#define netdev_for_each_all_lower_dev(dev, ldev, iter) \
for (iter = (dev)->lower_dev_list.next, \
ldev = netdev_all_lower_get_next(dev, &(iter)); \
ldev; \
ldev = netdev_all_lower_get_next(dev, &(iter)))
#define netdev_for_each_all_lower_dev_rcu(dev, ldev, iter) \
for (iter = &(dev)->lower_dev_list, \
ldev = netdev_all_lower_get_next_rcu(dev, &(iter)); \
ldev; \
ldev = netdev_all_lower_get_next_rcu(dev, &(iter)))
int netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *lower_dev,
void *data),
void *data);
int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *lower_dev,
void *data),
void *data);
void *netdev_adjacent_get_private(struct list_head *adj_list);
void *netdev_lower_get_first_private_rcu(struct net_device *dev);
struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev);
int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev);
int netdev_master_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev);
int netdev_master_upper_dev_link_rh(struct net_device *dev,
struct net_device *upper_dev,
void *upper_priv, void *upper_info);
#define netdev_master_upper_dev_link netdev_master_upper_dev_link_rh
void netdev_upper_dev_unlink(struct net_device *dev,
struct net_device *upper_dev);
void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
void *netdev_lower_dev_get_private_rcu(struct net_device *dev,
struct net_device *lower_dev);
void *netdev_lower_dev_get_private(struct net_device *dev,
struct net_device *lower_dev);
void netdev_lower_state_changed(struct net_device *lower_dev,
void *lower_state_info);
int netdev_default_l2upper_neigh_construct(struct net_device *dev,
struct neighbour *n);
void netdev_default_l2upper_neigh_destroy(struct net_device *dev,
struct neighbour *n);
/* RSS keys are 40 or 52 bytes long */
#define NETDEV_RSS_KEY_LEN 52
extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly;
void netdev_rss_key_fill(void *buffer, size_t len);
int dev_get_nest_level(struct net_device *dev,
bool (*type_check)(const struct net_device *dev));
int skb_checksum_help(struct sk_buff *skb);
int skb_crc32c_csum_help(struct sk_buff *skb);
int skb_csum_hwoffload_help(struct sk_buff *skb,
const netdev_features_t features);
struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
netdev_features_t features, bool tx_path);
struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
netdev_features_t features);
struct netdev_bonding_info {
ifslave slave;
ifbond master;
};
struct netdev_notifier_bonding_info {
struct netdev_notifier_info info; /* must be first */
struct netdev_bonding_info bonding_info;
};
void netdev_bonding_info_change(struct net_device *dev,
struct netdev_bonding_info *bonding_info);
static inline
struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features)
{
return __skb_gso_segment(skb, features, true);
}
__be16 skb_network_protocol(struct sk_buff *skb, int *depth);
static inline bool can_checksum_protocol(netdev_features_t features,
__be16 protocol)
{
if (protocol == htons(ETH_P_FCOE))
return !!(features & NETIF_F_FCOE_CRC);
/* Assume this is an IP checksum (not SCTP CRC) */
if (features & NETIF_F_HW_CSUM) {
/* Can checksum everything */
return true;
}
switch (protocol) {
case htons(ETH_P_IP):
return !!(features & NETIF_F_IP_CSUM);
case htons(ETH_P_IPV6):
return !!(features & NETIF_F_IPV6_CSUM);
default:
return false;
}
}
#ifdef CONFIG_BUG
void netdev_rx_csum_fault(struct net_device *dev);
#else
static inline void netdev_rx_csum_fault(struct net_device *dev)
{
}
#endif
/* rx skb timestamps */
void net_enable_timestamp(void);
void net_disable_timestamp(void);
#ifdef CONFIG_PROC_FS
int __init dev_proc_init(void);
#else
#define dev_proc_init() 0
#endif
static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
struct sk_buff *skb, struct net_device *dev,
bool more)
{
skb->xmit_more = more ? 1 : 0;
return ops->ndo_start_xmit(skb, dev);
}
static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, bool more)
{
const struct net_device_ops *ops = dev->netdev_ops;
int rc;
rc = __netdev_start_xmit(ops, skb, dev, more);
if (rc == NETDEV_TX_OK)
txq_trans_update(txq);
return rc;
}
extern int netdev_class_create_file_ns(struct class_attribute *class_attr,
const void *ns);
extern void netdev_class_remove_file_ns(struct class_attribute *class_attr,
const void *ns);
static inline int netdev_class_create_file(struct class_attribute *class_attr)
{
return netdev_class_create_file_ns(class_attr, NULL);
}
static inline void netdev_class_remove_file(struct class_attribute *class_attr)
{
netdev_class_remove_file_ns(class_attr, NULL);
}
extern struct kobj_ns_type_operations net_ns_type_operations;
const char *netdev_drivername(const struct net_device *dev);
void linkwatch_run_queue(void);
static inline netdev_features_t netdev_intersect_features(netdev_features_t f1,
netdev_features_t f2)
{
if ((f1 ^ f2) & NETIF_F_HW_CSUM) {
if (f1 & NETIF_F_HW_CSUM)
f1 |= (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
else
f2 |= (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
}
return f1 & f2;
}
static inline netdev_features_t netdev_get_wanted_features(
struct net_device *dev)
{
return (dev->features & ~dev->hw_features) | dev->wanted_features;
}
netdev_features_t netdev_increment_features(netdev_features_t all,
netdev_features_t one, netdev_features_t mask);
/* Allow TSO being used on stacked device :
* Performing the GSO segmentation before last device
* is a performance improvement.
*/
static inline netdev_features_t netdev_add_tso_features(netdev_features_t features,
netdev_features_t mask)
{
return netdev_increment_features(features, NETIF_F_ALL_TSO, mask);
}
int __netdev_update_features(struct net_device *dev);
void netdev_update_features(struct net_device *dev);
void netdev_change_features(struct net_device *dev);
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
struct net_device *dev);
netdev_features_t passthru_features_check(struct sk_buff *skb,
struct net_device *dev,
netdev_features_t features);
netdev_features_t netif_skb_features(struct sk_buff *skb);
static inline bool net_gso_ok(netdev_features_t features, int gso_type)
{
netdev_features_t feature = gso_type & SKB_GSO1_MASK;
feature <<= NETIF_F_GSO_SHIFT;
if (gso_type & SKB_GSO2_MASK) {
netdev_features_t f = gso_type & SKB_GSO2_MASK;
f <<= NETIF_F_GSO2_SHIFT;
feature |= f;
}
/* check flags correspondence */
BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_UFO >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_DODGY != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_TCPV6 != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_FCOE != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_GRE != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_IPIP != (NETIF_F_GSO_IPIP >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_SIT != (NETIF_F_GSO_SIT >> NETIF_F_GSO_SHIFT));
BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT));
/* GSO2 flags, see netdev_features.h */
BUILD_BUG_ON(SKB_GSO_GRE_CSUM != (NETIF_F_GSO_GRE_CSUM >> NETIF_F_GSO2_SHIFT));
BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO2_SHIFT));
BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO2_SHIFT));
BUILD_BUG_ON(SKB_GSO_SCTP != (NETIF_F_GSO_SCTP >> NETIF_F_GSO2_SHIFT));
BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO2_SHIFT));
return (features & feature) == feature;
}
static inline bool skb_gso_ok(struct sk_buff *skb, netdev_features_t features)
{
return net_gso_ok(features, skb_shinfo(skb)->gso_type) &&
(!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST));
}
static inline bool netif_needs_gso(struct sk_buff *skb,
netdev_features_t features)
{
return skb_is_gso(skb) && (!skb_gso_ok(skb, features) ||
unlikely((skb->ip_summed != CHECKSUM_PARTIAL) &&
(skb->ip_summed != CHECKSUM_UNNECESSARY)));
}
static inline void netif_set_gso_max_size(struct net_device *dev,
unsigned int size)
{
dev->gso_max_size = size;
}
static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol,
int pulled_hlen, u16 mac_offset,
int mac_len)
{
skb->protocol = protocol;
skb->encapsulation = 1;
skb_push(skb, pulled_hlen);
skb_reset_transport_header(skb);
skb->mac_header = mac_offset;
skb->network_header = skb->mac_header + mac_len;
skb->mac_len = mac_len;
}
static inline bool netif_is_macvlan(const struct net_device *dev)
{
return dev->priv_flags & IFF_MACVLAN;
}
static inline bool netif_is_macsec(const struct net_device *dev)
{
return dev->priv_flags & IFF_MACSEC;
}
static inline bool netif_is_macvlan_port(const struct net_device *dev)
{
return dev->priv_flags & IFF_MACVLAN_PORT;
}
static inline bool netif_is_bond_master(const struct net_device *dev)
{
return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING;
}
static inline bool netif_is_bond_slave(const struct net_device *dev)
{
return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING;
}
static inline bool netif_is_bridge_port(const struct net_device *dev)
{
return dev->priv_flags & IFF_BRIDGE_PORT;
}
static inline bool netif_supports_nofcs(struct net_device *dev)
{
return dev->priv_flags & IFF_SUPP_NOFCS;
}
static inline bool netif_is_bridge_master(const struct net_device *dev)
{
return dev->priv_flags & IFF_EBRIDGE;
}
static inline bool netif_is_ovs_master(const struct net_device *dev)
{
return dev->priv_flags & IFF_OPENVSWITCH;
}
static inline bool netif_is_ovs_port(const struct net_device *dev)
{
return dev->priv_flags & IFF_OVS_DATAPATH;
}
static inline bool netif_is_rxfh_configured(const struct net_device *dev)
{
return dev->priv_flags & IFF_RXFH_CONFIGURED;
}
static inline bool netif_is_team_master(const struct net_device *dev)
{
return dev->priv_flags & IFF_TEAM;
}
static inline bool netif_is_team_port(const struct net_device *dev)
{
return dev->priv_flags & IFF_TEAM_PORT;
}
static inline bool netif_is_lag_master(const struct net_device *dev)
{
return netif_is_bond_master(dev) || netif_is_team_master(dev);
}
static inline bool netif_is_lag_port(const struct net_device *dev)
{
return netif_is_bond_slave(dev) || netif_is_team_port(dev);
}
static inline bool netif_is_failover(const struct net_device *dev)
{
return dev->priv_flags & IFF_FAILOVER;
}
static inline bool netif_is_failover_slave(const struct net_device *dev)
{
return dev->priv_flags & IFF_FAILOVER_SLAVE;
}
/* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */
static inline void netif_keep_dst(struct net_device *dev)
{
dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM);
}
/* return true if dev can't cope with mtu frames that need vlan tag insertion */
static inline bool netif_reduces_vlan_mtu(struct net_device *dev)
{
/* TODO: reserve and use an additional IFF bit, if we get more users */
return dev->priv_flags & IFF_MACSEC;
}
extern struct pernet_operations __net_initdata loopback_net_ops;
/* Logging, debugging and troubleshooting/diagnostic helpers. */
/* netdev_printk helpers, similar to dev_printk */
static inline const char *netdev_name(const struct net_device *dev)
{
if (dev->reg_state != NETREG_REGISTERED)
return "(unregistered net_device)";
return dev->name;
}
static inline const char *netdev_reg_state(const struct net_device *dev)
{
switch (dev->reg_state) {
case NETREG_UNINITIALIZED: return " (uninitialized)";
case NETREG_REGISTERED: return "";
case NETREG_UNREGISTERING: return " (unregistering)";
case NETREG_UNREGISTERED: return " (unregistered)";
case NETREG_RELEASED: return " (released)";
case NETREG_DUMMY: return " (dummy)";
}
WARN_ONCE(1, "%s: unknown reg_state %d\n", dev->name, dev->reg_state);
return " (unknown)";
}
__printf(3, 4)
int netdev_printk(const char *level, const struct net_device *dev,
const char *format, ...);
__printf(2, 3)
int netdev_emerg(const struct net_device *dev, const char *format, ...);
__printf(2, 3)
int netdev_alert(const struct net_device *dev, const char *format, ...);
__printf(2, 3)
int netdev_crit(const struct net_device *dev, const char *format, ...);
__printf(2, 3)
int netdev_err(const struct net_device *dev, const char *format, ...);
__printf(2, 3)
int netdev_warn(const struct net_device *dev, const char *format, ...);
__printf(2, 3)
int netdev_notice(const struct net_device *dev, const char *format, ...);
__printf(2, 3)
int netdev_info(const struct net_device *dev, const char *format, ...);
#define netdev_level_once(level, dev, fmt, ...) \
do { \
static bool __print_once __read_mostly; \
\
if (!__print_once) { \
__print_once = true; \
netdev_printk(level, dev, fmt, ##__VA_ARGS__); \
} \
} while (0)
#define netdev_emerg_once(dev, fmt, ...) \
netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__)
#define netdev_alert_once(dev, fmt, ...) \
netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__)
#define netdev_crit_once(dev, fmt, ...) \
netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__)
#define netdev_err_once(dev, fmt, ...) \
netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__)
#define netdev_warn_once(dev, fmt, ...) \
netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__)
#define netdev_notice_once(dev, fmt, ...) \
netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__)
#define netdev_info_once(dev, fmt, ...) \
netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__)
#define MODULE_ALIAS_NETDEV(device) \
MODULE_ALIAS("netdev-" device)
#if defined(CONFIG_DYNAMIC_DEBUG)
#define netdev_dbg(__dev, format, args...) \
do { \
dynamic_netdev_dbg(__dev, format, ##args); \
} while (0)
#elif defined(DEBUG)
#define netdev_dbg(__dev, format, args...) \
netdev_printk(KERN_DEBUG, __dev, format, ##args)
#else
#define netdev_dbg(__dev, format, args...) \
({ \
if (0) \
netdev_printk(KERN_DEBUG, __dev, format, ##args); \
0; \
})
#endif
#if defined(VERBOSE_DEBUG)
#define netdev_vdbg netdev_dbg
#else
#define netdev_vdbg(dev, format, args...) \
({ \
if (0) \
netdev_printk(KERN_DEBUG, dev, format, ##args); \
0; \
})
#endif
/*
* netdev_WARN() acts like dev_printk(), but with the key difference
* of using a WARN/WARN_ON to get the message out, including the
* file/line information and a backtrace.
*/
#define netdev_WARN(dev, format, args...) \
WARN(1, "netdevice: %s%s: " format, netdev_name(dev), \
netdev_reg_state(dev), ##args)
#define netdev_WARN_ONCE(dev, format, args...) \
WARN_ONCE(1, "netdevice: %s%s: " format, netdev_name(dev), \
netdev_reg_state(dev), ##args)
/* netif printk helpers, similar to netdev_printk */
#define netif_printk(priv, type, level, dev, fmt, args...) \
do { \
if (netif_msg_##type(priv)) \
netdev_printk(level, (dev), fmt, ##args); \
} while (0)
#define netif_level(level, priv, type, dev, fmt, args...) \
do { \
if (netif_msg_##type(priv)) \
netdev_##level(dev, fmt, ##args); \
} while (0)
#define netif_emerg(priv, type, dev, fmt, args...) \
netif_level(emerg, priv, type, dev, fmt, ##args)
#define netif_alert(priv, type, dev, fmt, args...) \
netif_level(alert, priv, type, dev, fmt, ##args)
#define netif_crit(priv, type, dev, fmt, args...) \
netif_level(crit, priv, type, dev, fmt, ##args)
#define netif_err(priv, type, dev, fmt, args...) \
netif_level(err, priv, type, dev, fmt, ##args)
#define netif_warn(priv, type, dev, fmt, args...) \
netif_level(warn, priv, type, dev, fmt, ##args)
#define netif_notice(priv, type, dev, fmt, args...) \
netif_level(notice, priv, type, dev, fmt, ##args)
#define netif_info(priv, type, dev, fmt, args...) \
netif_level(info, priv, type, dev, fmt, ##args)
#if defined(CONFIG_DYNAMIC_DEBUG)
#define netif_dbg(priv, type, netdev, format, args...) \
do { \
if (netif_msg_##type(priv)) \
dynamic_netdev_dbg(netdev, format, ##args); \
} while (0)
#elif defined(DEBUG)
#define netif_dbg(priv, type, dev, format, args...) \
netif_printk(priv, type, KERN_DEBUG, dev, format, ##args)
#else
#define netif_dbg(priv, type, dev, format, args...) \
({ \
if (0) \
netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
0; \
})
#endif
/* if @cond then downgrade to debug, else print at @level */
#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...) \
do { \
if (cond) \
netif_dbg(priv, type, netdev, fmt, ##args); \
else \
netif_ ## level(priv, type, netdev, fmt, ##args); \
} while (0)
#if defined(VERBOSE_DEBUG)
#define netif_vdbg netif_dbg
#else
#define netif_vdbg(priv, type, dev, format, args...) \
({ \
if (0) \
netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
0; \
})
#endif
/*
* The list of packet types we will receive (as opposed to discard)
* and the routines to invoke.
*
* Why 16. Because with 16 the only overlap we get on a hash of the
* low nibble of the protocol value is RARP/SNAP/X.25.
*
* NOTE: That is no longer true with the addition of VLAN tags. Not
* sure which should go first, but I bet it won't make much
* difference if we are running VLANs. The good news is that
* this protocol won't be in the list unless compiled in, so
* the average user (w/out VLANs) will not be adversely affected.
* --BLG
*
* 0800 IP
* 8100 802.1Q VLAN
* 0001 802.3
* 0002 AX.25
* 0004 802.2
* 8035 RARP
* 0005 SNAP
* 0805 X.25
* 0806 ARP
* 8137 IPX
* 0009 Localtalk
* 86DD IPv6
*/
#define PTYPE_HASH_SIZE (16)
#define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1)
#endif /* _LINUX_NETDEVICE_H */
Mini Shell