Release 4.12 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/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>
#ifdef CONFIG_DCB
#include <net/dcbnl.h>
#endif
#include <net/netprio_cgroup.h>
#include <linux/netdev_features.h>
#include <linux/neighbour.h>
#include <uapi/linux/netdevice.h>
#include <uapi/linux/if_bonding.h>
#include <uapi/linux/pkt_cls.h>
#include <linux/hashtable.h>
struct netpoll_info;
struct device;
struct phy_device;
struct dsa_switch_tree;
/* 802.11 specific */
struct wireless_dev;
/* 802.15.4 specific */
struct wpan_dev;
struct mpls_dev;
/* UDP Tunnel offloads */
struct udp_tunnel_info;
struct bpf_prog;
void netdev_set_default_ethtool_ops(struct net_device *dev,
const struct ethtool_ops *ops);
/* Backlog congestion levels */
#define NET_RX_SUCCESS 0
/* keep 'em coming, baby */
#define NET_RX_DROP 1
/* packet dropped */
/*
* Transmit return codes: transmit return codes originate from three different
* namespaces:
*
* - qdisc return codes
* - driver transmit return codes
* - errno values
*
* Drivers are allowed to return any one of those in their hard_start_xmit()
* function. Real network devices commonly used with qdiscs should only return
* the driver transmit return codes though - when qdiscs are used, the actual
* transmission happens asynchronously, so the value is not propagated to
* higher layers. Virtual network devices transmit synchronously; in this case
* the driver transmit return codes are consumed by dev_queue_xmit(), and all
* others are propagated to higher layers.
*/
/* qdisc ->enqueue() return codes. */
#define NET_XMIT_SUCCESS 0x00
#define NET_XMIT_DROP 0x01
/* skb dropped */
#define NET_XMIT_CN 0x02
/* congestion notification */
#define NET_XMIT_MASK 0x0f
/* qdisc flags in net/sch_generic.h */
/* NET_XMIT_CN is special. It does not guarantee that this packet is lost. It
* indicates that the device will soon be dropping packets, or already drops
* some packets of the same priority; prompting us to send less aggressively. */
#define net_xmit_eval(e) ((e) == NET_XMIT_CN ? 0 : (e))
#define net_xmit_errno(e) ((e) != NET_XMIT_CN ? -ENOBUFS : 0)
/* Driver transmit return codes */
#define NETDEV_TX_MASK 0xf0
enum netdev_tx {
__NETDEV_TX_MIN = INT_MIN, /* make sure enum is signed */
NETDEV_TX_OK = 0x00, /* driver took care of packet */
NETDEV_TX_BUSY = 0x10, /* driver tx path was busy*/
};
typedef enum netdev_tx netdev_tx_t;
/*
* Current order: NETDEV_TX_MASK > NET_XMIT_MASK >= 0 is significant;
* hard_start_xmit() return < NET_XMIT_MASK means skb was consumed.
*/
static inline bool dev_xmit_complete(int rc)
{
/*
* Positive cases with an skb consumed by a driver:
* - successful transmission (rc == NETDEV_TX_OK)
* - error while transmitting (rc < 0)
* - error while queueing to a different device (rc & NET_XMIT_MASK)
*/
if (likely(rc < NET_XMIT_MASK))
return true;
return false;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Jarek Poplawski | 26 | 100.00% | 1 | 100.00% |
| Total | 26 | 100.00% | 1 | 100.00% |
/*
* Compute the worst-case header length according to the protocols
* used.
*/
#if defined(CONFIG_HYPERV_NET)
# define LL_MAX_HEADER 128
#elif 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;
extern struct static_key rfs_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 {
unsigned int hh_len;
seqlock_t hh_lock;
/* cached hardware header; allow for machine alignment needs. */
#define HH_DATA_MOD 16
#define HH_DATA_OFF(__len) \
(HH_DATA_MOD - (((__len - 1) & (HH_DATA_MOD - 1)) + 1))
#define HH_DATA_ALIGN(__len) \
(((__len)+(HH_DATA_MOD-1))&~(HH_DATA_MOD - 1))
unsigned long hh_data[HH_DATA_ALIGN(LL_MAX_HEADER) / sizeof(long)];
};
/* Reserve HH_DATA_MOD byte-aligned hard_header_len, but at least that much.
* Alternative is:
* dev->hard_header_len ? (dev->hard_header_len +
* (HH_DATA_MOD - 1)) & ~(HH_DATA_MOD - 1) : 0
*
* We could use other alignment values, but we must maintain the
* relationship HH alignment <= LL alignment.
*/
#define LL_RESERVED_SPACE(dev) \
((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
#define LL_RESERVED_SPACE_EXTRA(dev,extra) \
((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
struct header_ops {
int (*create) (struct sk_buff *skb, struct net_device *dev,
unsigned short type, const void *daddr,
const void *saddr, unsigned int len);
int (*parse)(const struct sk_buff *skb, unsigned char *haddr);
int (*cache)(const struct neighbour *neigh, struct hh_cache *hh, __be16 type);
void (*cache_update)(struct hh_cache *hh,
const struct net_device *dev,
const unsigned char *haddr);
bool (*validate)(const char *ll_header, unsigned int len);
};
/* 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 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
int poll_owner;
#endif
struct net_device *dev;
struct sk_buff *gro_list;
struct sk_buff *skb;
struct hrtimer timer;
struct list_head dev_list;
struct hlist_node napi_hash_node;
unsigned int napi_id;
};
enum {
NAPI_STATE_SCHED, /* Poll is scheduled */
NAPI_STATE_MISSED, /* reschedule a napi */
NAPI_STATE_DISABLE, /* Disable pending */
NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */
NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */
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 */
};
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,
GRO_CONSUMED,
};
typedef enum gro_result gro_result_t;
/*
* enum rx_handler_result - Possible return values for rx_handlers.
* @RX_HANDLER_CONSUMED: skb was consumed by rx_handler, do not process it
* further.
* @RX_HANDLER_ANOTHER: Do another round in receive path. This is indicated in
* case skb->dev was changed by rx_handler.
* @RX_HANDLER_EXACT: Force exact delivery, no wildcard.
* @RX_HANDLER_PASS: Do nothing, pass the skb as if no rx_handler was called.
*
* rx_handlers are functions called from inside __netif_receive_skb(), to do
* special processing of the skb, prior to delivery to protocol handlers.
*
* Currently, a net_device can only have a single rx_handler registered. Trying
* to register a second rx_handler will return -EBUSY.
*
* To register a rx_handler on a net_device, use netdev_rx_handler_register().
* To unregister a rx_handler on a net_device, use
* netdev_rx_handler_unregister().
*
* Upon return, rx_handler is expected to tell __netif_receive_skb() what to
* do with the skb.
*
* If the rx_handler consumed the skb in some way, it should return
* RX_HANDLER_CONSUMED. This is appropriate when the rx_handler arranged for
* the skb to be delivered in some other way.
*
* If the rx_handler changed skb->dev, to divert the skb to another
* net_device, it should return RX_HANDLER_ANOTHER. The rx_handler for the
* new device will be called if it exists.
*
* If the rx_handler decides the skb should be ignored, it should return
* RX_HANDLER_EXACT. The skb will only be delivered to protocol handlers that
* are registered on exact device (ptype->dev == skb->dev).
*
* If the rx_handler didn't change skb->dev, but wants the skb to be normally
* delivered, it should return RX_HANDLER_PASS.
*
* A device without a registered rx_handler will behave as if rx_handler
* returned RX_HANDLER_PASS.
*/
enum rx_handler_result {
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);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| David S. Miller | 23 | 100.00% | 2 | 100.00% |
| Total | 23 | 100.00% | 2 | 100.00% |
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);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Stephen Hemminger | 24 | 100.00% | 1 | 100.00% |
| Total | 24 | 100.00% | 1 | 100.00% |
/**
* 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);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Eric Dumazet | 24 | 100.00% | 1 | 100.00% |
| Total | 24 | 100.00% | 1 | 100.00% |
/* 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;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Roland Dreier | 29 | 90.62% | 1 | 50.00% |
| David S. Miller | 3 | 9.38% | 1 | 50.00% |
| Total | 32 | 100.00% | 2 | 100.00% |
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);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Eric Dumazet | 20 | 100.00% | 2 | 100.00% |
| Total | 20 | 100.00% | 2 | 100.00% |
/**
* 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_atomic();
clear_bit(NAPI_STATE_SCHED, &n->state);
clear_bit(NAPI_STATE_NPSVC, &n->state);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Stephen Hemminger | 44 | 89.80% | 1 | 33.33% |
| Neil Horman | 4 | 8.16% | 1 | 33.33% |
| Peter Zijlstra | 1 | 2.04% | 1 | 33.33% |
| Total | 49 | 100.00% | 3 | 100.00% |
/**
* 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)
{
if (IS_ENABLED(CONFIG_SMP))
while (test_bit(NAPI_STATE_SCHED, &n->state))
msleep(1);
else
barrier();
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Stephen Hemminger | 30 | 73.17% | 1 | 50.00% |
| Arnd Bergmann | 11 | 26.83% | 1 | 50.00% |
| Total | 41 | 100.00% | 2 | 100.00% |
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
unsigned long tx_maxrate;
/*
* Number of TX timeouts for this queue
* (/sys/class/net/DEV/Q/trans_timeout)
*/
unsigned long trans_timeout;
/*
* write-mostly part
*/
spinlock_t _xmit_lock ____cacheline_aligned_in_smp;
int xmit_lock_owner;
/*
* Time (in jiffies) of last Tx
*/
unsigned long trans_start;
unsigned long state;
#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
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Eric Dumazet | 35 | 97.22% | 1 | 50.00% |
| Changli Gao | 1 | 2.78% | 1 | 50.00% |
| Total | 36 | 100.00% | 2 | 100.00% |
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
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Eric Dumazet | 34 | 100.00% | 1 | 100.00% |
| Total | 34 | 100.00% | 1 | 100.00% |
#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).
* Each entry is a 32bit value. Upper part is the high-order bits
* of flow hash, lower part is CPU number.
* rps_cpu_mask is used to partition the space, depending on number of
* possible CPUs : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1
* For example, if 64 CPUs are possible, rps_cpu_mask = 0x3f,
* meaning we use 32-6=26 bits for the hash.
*/
struct rps_sock_flow_table {
u32 mask;
u32 ents[0] ____cacheline_aligned_in_smp;
};
#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num]))
#define RPS_NO_CPU 0xffff
extern u32 rps_cpu_mask;
extern struct rps_sock_flow_table __rcu *rps_sock_flow_table;
static inline void rps_record_sock_flow(struct rps_sock_flow_table *table,
u32 hash)
{
if (table && hash) {
unsigned int index = hash & table->mask;
u32 val = hash & ~rps_cpu_mask;
/* We only give a hint, preemption can change CPU under us */
val |= raw_smp_processor_id();
if (table->ents[index] != val)
table->ents[index] = val;
}
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tom Herbert | 51 | 76.12% | 1 | 25.00% |
| Eric Dumazet | 12 | 17.91% | 1 | 25.00% |
| Stephen Hemminger | 3 | 4.48% | 1 | 25.00% |
| Björn Helgaas | 1 | 1.49% | 1 | 25.00% |
| Total | 67 | 100.00% | 4 | 100.00% |
#ifdef CONFIG_RFS_ACCEL
bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id,
u16 filter_id);
#endif
#endif /* CONFIG_RPS */
/* This structure contains an instance of an RX queue. */
struct netdev_rx_queue {
#ifdef CONFIG_RPS
struct rps_map __rcu *rps_map;
struct rps_dev_flow_table __rcu *rps_flow_table;
#endif
struct kobject kobj;
struct net_device *dev;
} ____cacheline_aligned_in_smp;
/*
* RX queue sysfs structures and functions.
*/
struct rx_queue_attribute {
struct attribute attr;
ssize_t (*show)(struct netdev_rx_queue *queue,
struct rx_queue_attribute *attr, char *buf);
ssize_t (*store)(struct netdev_rx_queue *queue,
struct rx_queue_attribute *attr, const char *buf, size_t len);
};
#ifdef CONFIG_XPS
/*
* This structure holds an XPS map which can be of variable length. The
* map is an array of queues.
*/
struct xps_map {
unsigned int len;
unsigned int alloc_len;
struct rcu_head rcu;
u16 queues[0];
};
#define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + ((_num) * sizeof(u16)))
#define XPS_MIN_MAP_ALLOC ((L1_CACHE_ALIGN(offsetof(struct xps_map, queues[1])) \
- sizeof(struct xps_map)) / sizeof(u16))
/*
* This structure holds all XPS maps for device. Maps are indexed by CPU.
*/
struct xps_dev_maps {
struct rcu_head rcu;
struct xps_map __rcu *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_ITEM_ID_LEN 32
/* This structure holds a unique identifier to identify some
* physical item (port for example) used by a netdevice.
*/
struct netdev_phys_item_id {
unsigned char id[MAX_PHYS_ITEM_ID_LEN];
unsigned char id_len;
};
static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a,
struct netdev_phys_item_id *b)
{
return a->id_len == b->id_len &&
memcmp(a->id, b->id, a->id_len) == 0;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Scott Feldman | 43 | 100.00% | 1 | 100.00% |
| Total | 43 | 100.00% | 1 | 100.00% |
typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
struct sk_buff *skb);
/* These structures hold the attributes of qdisc and classifiers
* that are being passed to the netdevice through the setup_tc op.
*/
enum {
TC_SETUP_MQPRIO,
TC_SETUP_CLSU32,
TC_SETUP_CLSFLOWER,
TC_SETUP_MATCHALL,
TC_SETUP_CLSBPF,
};
struct tc_cls_u32_offload;
struct tc_to_netdev {
unsigned int type;
union {
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;
struct tc_mqprio_qopt *mqprio;
};
bool egress_dev;
};
/* 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,
/* Check if a bpf program is set on the device. The callee should
* return true if a program is currently attached and running.
*/
XDP_QUERY_PROG,
};
struct netlink_ext_ack;
struct netdev_xdp {
enum xdp_netdev_command command;
union {
/* XDP_SETUP_PROG */
struct {
struct bpf_prog *prog;
struct netlink_ext_ack *extack;
};
/* XDP_QUERY_PROG */
bool prog_attached;
};
};
#ifdef CONFIG_XFRM_OFFLOAD
struct xfrmdev_ops {
int (*xdo_dev_state_add) (struct xfrm_state *x);
void (*xdo_dev_state_delete) (struct xfrm_state *x);
void (*xdo_dev_state_free) (struct xfrm_state *x);
bool (*xdo_dev_offload_ok) (struct sk_buff *skb,
struct xfrm_state *x);
};
#endif
/*
* This structure defines the management hooks for network devices.
* The following hooks can be defined; unless noted otherwise, they are
* optional and can be filled with a null pointer.
*
* int (*ndo_init)(struct net_device *dev);
* This function is called once when a network device is registered.
* The network device can use this for any late stage initialization
* or semantic validation. It can fail with an error code which will
* be propagated back to register_netdev.
*
* void (*ndo_uninit)(struct net_device *dev);
* This function is called when device is unregistered or when registration
* fails. It is not called if init fails.
*
* int (*ndo_open)(struct net_device *dev);
* This function is called when a network device transitions to the up
* state.
*
* int (*ndo_stop)(struct net_device *dev);
* This function is called when a network device transitions to the down
* state.
*
* netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb,
* struct net_device *dev);
* Called when a packet needs to be transmitted.
* Returns NETDEV_TX_OK. Can return NETDEV_TX_BUSY, but you should stop
* the queue before that can happen; it's for obsolete devices and weird
* corner cases, but the stack really does a non-trivial amount
* of useless work if you return NETDEV_TX_BUSY.
* Required; cannot be NULL.
*
* netdev_features_t (*ndo_features_check)(struct sk_buff *skb,
* struct net_device *dev
* netdev_features_t features);
* Called by core transmit path to determine if device is capable of
* performing offload operations on a given packet. This is to give
* the device an opportunity to implement any restrictions that cannot
* be otherwise expressed by feature flags. The check is called with
* the set of features that the stack has calculated and it returns
* those the driver believes to be appropriate.
*
* u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
* void *accel_priv, select_queue_fallback_t fallback);
* Called to decide which queue to use when device supports multiple
* transmit queues.
*
* void (*ndo_change_rx_flags)(struct net_device *dev, int flags);
* This function is called to allow device receiver to make
* changes to configuration when multicast or promiscuous is enabled.
*
* void (*ndo_set_rx_mode)(struct net_device *dev);
* This function is called device changes address list filtering.
* If driver handles unicast address filtering, it should set
* IFF_UNICAST_FLT in its priv_flags.
*
* int (*ndo_set_mac_address)(struct net_device *dev, void *addr);
* This function is called when the Media Access Control address
* needs to be changed. If this interface is not defined, the
* MAC address can not be changed.
*
* int (*ndo_validate_addr)(struct net_device *dev);
* Test if Media Access Control address is valid for the device.
*
* int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd);
* Called when a user requests an ioctl which can't be handled by
* the generic interface code. If not defined ioctls return
* not supported error code.
*
* int (*ndo_set_config)(struct net_device *dev, struct ifmap *map);
* Used to set network devices bus interface parameters. This interface
* is retained for legacy reasons; new devices should use the bus
* interface (PCI) for low level management.
*
* int (*ndo_change_mtu)(struct net_device *dev, int new_mtu);
* Called when a user wants to change the Maximum Transfer Unit
* of a device.
*
* void (*ndo_tx_timeout)(struct net_device *dev);
* Callback used when the transmitter has not made any progress
* for dev->watchdog ticks.
*
* void (*ndo_get_stats64)(struct net_device *dev,
* struct rtnl_link_stats64 *storage);
* struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
* Called when a user wants to get the network device usage
* statistics. Drivers must do one of the following:
* 1. Define @ndo_get_stats64 to fill in a zero-initialised
* rtnl_link_stats64 structure passed by the caller.
* 2. Define @ndo_get_stats to update a net_device_stats structure
* (which should normally be dev->stats) and return a pointer to
* it. The structure may be changed asynchronously only if each
* field is written atomically.
* 3. Update dev->stats asynchronously and atomically, and define
* neither operation.
*
* bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id)
* Return true if this device supports offload stats of this attr_id.
*
* int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev,
* void *attr_data)
* Get statistics for offload operations by attr_id. Write it into the
* attr_data pointer.
*
* int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid);
* If device supports VLAN filtering this function is called when a
* VLAN id is registered.
*
* int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid);
* If device supports VLAN filtering this function is called when a
* VLAN id is unregistered.
*
* void (*ndo_poll_controller)(struct net_device *dev);
*
* SR-IOV management functions.
* int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac);
* int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan,
* u8 qos, __be16 proto);
* int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate,
* int max_tx_rate);
* int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting);
* int (*ndo_set_vf_trust)(struct net_device *dev, int vf, bool setting);
* int (*ndo_get_vf_config)(struct net_device *dev,
* int vf, struct ifla_vf_info *ivf);
* int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state);
* int (*ndo_set_vf_port)(struct net_device *dev, int vf,
* struct nlattr *port[]);
*
* Enable or disable the VF ability to query its RSS Redirection Table and
* Hash Key. This is needed since on some devices VF share this information
* with PF and querying it may introduce a theoretical security risk.
* int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting);
* int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb);
* int (*ndo_setup_tc)(struct net_device *dev, u32 handle,
* __be16 protocol, struct tc_to_netdev *tc);
* Called to setup any 'tc' scheduler, classifier or action on @dev.
* This is always called from the stack with the rtnl lock held and netif
* tx queues stopped. This allows the netdevice to perform queue
* management safely.
*
* Fiber Channel over Ethernet (FCoE) offload functions.
* int (*ndo_fcoe_enable)(struct net_device *dev);
* Called when the FCoE protocol stack wants to start using LLD for FCoE
* so the underlying device can perform whatever needed configuration or
* initialization to support acceleration of FCoE traffic.
*
* int (*ndo_fcoe_disable)(struct net_device *dev);
* Called when the FCoE protocol stack wants to stop using LLD for FCoE
* so the underlying device can perform whatever needed clean-ups to
* stop supporting acceleration of FCoE traffic.
*
* int (*ndo_fcoe_ddp_setup)(struct net_device *dev, u16 xid,
* struct scatterlist *sgl, unsigned int sgc);
* Called when the FCoE Initiator wants to initialize an I/O that
* is a possible candidate for Direct Data Placement (DDP). The LLD can
* perform necessary setup and returns 1 to indicate the device is set up
* successfully to perform DDP on this I/O, otherwise this returns 0.
*
* int (*ndo_fcoe_ddp_done)(struct net_device *dev, u16 xid);
* Called when the FCoE Initiator/Target is done with the DDPed I/O as
* indicated by the FC exchange id 'xid', so the underlying device can
* clean up and reuse resources for later DDP requests.
*
* int (*ndo_fcoe_ddp_target)(struct net_device *dev, u16 xid,
* struct scatterlist *sgl, unsigned int sgc);
* Called when the FCoE Target wants to initialize an I/O that
* is a possible candidate for Direct Data Placement (DDP). The LLD can
* perform necessary setup and returns 1 to indicate the device is set up
* successfully to perform DDP on this I/O, otherwise this returns 0.
*
* int (*ndo_fcoe_get_hbainfo)(struct net_device *dev,
* struct netdev_fcoe_hbainfo *hbainfo);
* Called when the FCoE Protocol stack wants information on the underlying
* device. This information is utilized by the FCoE protocol stack to
* register attributes with Fiber Channel management service as per the
* FC-GS Fabric Device Management Information(FDMI) specification.
*
* int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type);
* Called when the underlying device wants to override default World Wide
* Name (WWN) generation mechanism in FCoE protocol stack to pass its own
* World Wide Port Name (WWPN) or World Wide Node Name (WWNN) to the FCoE
* protocol stack to use.
*
* RFS acceleration.
* int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb,
* u16 rxq_index, u32 flow_id);
* Set hardware filter for RFS. rxq_index is the target queue index;
* flow_id is a flow ID to be passed to rps_may_expire_flow() later.
* Return the filter ID on success, or a negative error code.
*
* Slave management functions (for bridge, bonding, etc).
* int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev);
* Called to make another netdev an underling.
*
* int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev);
* Called to release previously enslaved netdev.
*
* 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_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb,
* struct net_device *dev, struct net_device *filter_dev,
* int *idx)
* Used to add FDB entries to dump requests. Implementers should add
* entries to skb and update idx with the number of entries.
*
* int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh,
* u16 flags)
* 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_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.
*
* void* (*ndo_dfwd_add_station)(struct net_device *pdev,
* struct net_device *dev)
* Called by upper layer devices to accelerate switching or other
* station functionality into hardware. 'pdev is the lowerdev
* to use for the offload and 'dev' is the net device that will
* back the offload. Returns a pointer to the private structure
* the upper layer will maintain.
* void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv)
* Called by upper layer device to delete the station created
* by 'ndo_dfwd_add_station'. 'pdev' is the net device backing
* the station and priv is the structure returned by the add
* operation.
* netdev_tx_t (*ndo_dfwd_start_xmit)(struct sk_buff *skb,
* struct net_device *dev,
* void *priv);
* Callback to use for xmit over the accelerated station. This
* is used in place of ndo_start_xmit on accelerated net
* devices.
* int (*ndo_set_tx_maxrate)(struct net_device *dev,
* int queue_index, u32 maxrate);
* Called when a user wants to set a max-rate limitation of specific
* TX queue.
* int (*ndo_get_iflink)(const struct net_device *dev);
* Called to get the iflink value of this device.
* void (*ndo_change_proto_down)(struct net_device *dev,
* bool proto_down);
* This function is used to pass protocol port error state information
* to the switch driver. The switch driver can react to the proto_down
* by doing a phys down on the associated switch port.
* int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb);
* This function is used to get egress tunnel information for given skb.
* This is useful for retrieving outer tunnel header parameters while
* sampling packet.
* void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom);
* This function is used to specify the headroom that the skb must
* consider when allocation skb during packet reception. Setting
* appropriate rx headroom value allows avoiding skb head copy on
* forward. Setting a negative value resets the rx headroom to the
* default value.
* int (*ndo_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.
*
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
void (*ndo_uninit)(struct net_device *dev);
int (*ndo_open)(struct net_device *dev);
int (*ndo_stop)(struct net_device *dev);
netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb,
struct net_device *dev);
netdev_features_t (*ndo_features_check)(struct sk_buff *skb,
struct net_device *dev,
netdev_features_t features);
u16 (*ndo_select_queue)(struct net_device *dev,
struct sk_buff *skb,
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);
int (*ndo_change_mtu)(struct net_device *dev,
int new_mtu);
int (*ndo_neigh_setup)(struct net_device *dev,
struct neigh_parms *);
void (*ndo_tx_timeout) (struct net_device *dev);
void (*ndo_get_stats64)(struct net_device *dev,
struct rtnl_link_stats64 *storage);
bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id);
int (*ndo_get_offload_stats)(int attr_id,
const struct net_device *dev,
void *attr_data);
struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
int (*ndo_vlan_rx_add_vid)(struct net_device *dev,
__be16 proto, u16 vid);
int (*ndo_vlan_rx_kill_vid)(struct net_device *dev,
__be16 proto, u16 vid);
#ifdef CONFIG_NET_POLL_CONTROLLER
void (*ndo_poll_controller)(struct net_device *dev);
int (*ndo_netpoll_setup)(struct net_device *