linux/include/linux/netdevice.h

1184 lines
36 KiB
C
Raw Normal View History

/*
* 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.Cox@linux.org>
* 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/if.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#ifdef __KERNEL__
#include <linux/timer.h>
#include <asm/atomic.h>
#include <asm/cache.h>
#include <asm/byteorder.h>
#include <linux/device.h>
#include <linux/percpu.h>
#include <linux/dmaengine.h>
struct vlan_group;
struct ethtool_ops;
struct netpoll_info;
/* 802.11 specific */
struct wireless_dev;
/* source back-compat hooks */
#define SET_ETHTOOL_OPS(netdev,ops) \
( (netdev)->ethtool_ops = (ops) )
#define HAVE_ALLOC_NETDEV /* feature macro: alloc_xxxdev
functions are available. */
#define HAVE_FREE_NETDEV /* free_netdev() */
#define HAVE_NETDEV_PRIV /* netdev_priv() */
#define NET_XMIT_SUCCESS 0
#define NET_XMIT_DROP 1 /* skb dropped */
#define NET_XMIT_CN 2 /* congestion notification */
#define NET_XMIT_POLICED 3 /* skb is shot by police */
#define NET_XMIT_BYPASS 4 /* packet does not leave via dequeue;
(TC use only - dev_queue_xmit
returns this as NET_XMIT_SUCCESS) */
/* Backlog congestion levels */
#define NET_RX_SUCCESS 0 /* keep 'em coming, baby */
#define NET_RX_DROP 1 /* packet dropped */
#define NET_RX_CN_LOW 2 /* storm alert, just in case */
#define NET_RX_CN_MOD 3 /* Storm on its way! */
#define NET_RX_CN_HIGH 4 /* The storm is here */
#define NET_RX_BAD 5 /* packet dropped due to kernel error */
/* 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)
#endif
#define MAX_ADDR_LEN 32 /* Largest hardware address length */
/* Driver transmit return codes */
#define NETDEV_TX_OK 0 /* driver took care of packet */
#define NETDEV_TX_BUSY 1 /* driver tx path was busy*/
#define NETDEV_TX_LOCKED -1 /* driver tx lock was already taken */
/*
* Compute the worst case header length according to the protocols
* used.
*/
#if !defined(CONFIG_AX25) && !defined(CONFIG_AX25_MODULE) && !defined(CONFIG_TR)
#define LL_MAX_HEADER 32
#else
#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
#define LL_MAX_HEADER 96
#else
#define LL_MAX_HEADER 48
#endif
#endif
#if !defined(CONFIG_NET_IPIP) && !defined(CONFIG_NET_IPIP_MODULE) && \
!defined(CONFIG_NET_IPGRE) && !defined(CONFIG_NET_IPGRE_MODULE) && \
!defined(CONFIG_IPV6_SIT) && !defined(CONFIG_IPV6_SIT_MODULE) && \
!defined(CONFIG_IPV6_TUNNEL) && !defined(CONFIG_IPV6_TUNNEL_MODULE)
#define MAX_HEADER LL_MAX_HEADER
#else
#define MAX_HEADER (LL_MAX_HEADER + 48)
#endif
struct net_device_subqueue
{
/* Give a control state for each queue. This struct may contain
* per-queue locks in the future.
*/
unsigned long state;
};
/*
* Network device statistics. Akin to the 2.0 ether stats but
* with byte counters.
*/
struct net_device_stats
{
unsigned long rx_packets; /* total packets received */
unsigned long tx_packets; /* total packets transmitted */
unsigned long rx_bytes; /* total bytes received */
unsigned long tx_bytes; /* total bytes transmitted */
unsigned long rx_errors; /* bad packets received */
unsigned long tx_errors; /* packet transmit problems */
unsigned long rx_dropped; /* no space in linux buffers */
unsigned long tx_dropped; /* no space available in linux */
unsigned long multicast; /* multicast packets received */
unsigned long collisions;
/* detailed rx_errors: */
unsigned long rx_length_errors;
unsigned long rx_over_errors; /* receiver ring buff overflow */
unsigned long rx_crc_errors; /* recved pkt with crc error */
unsigned long rx_frame_errors; /* recv'd frame alignment error */
unsigned long rx_fifo_errors; /* recv'r fifo overrun */
unsigned long rx_missed_errors; /* receiver missed packet */
/* detailed tx_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;
/* for cslip etc */
unsigned long rx_compressed;
unsigned long tx_compressed;
};
/* Media selection options. */
enum {
IF_PORT_UNKNOWN = 0,
IF_PORT_10BASE2,
IF_PORT_10BASET,
IF_PORT_AUI,
IF_PORT_100BASET,
IF_PORT_100BASETX,
IF_PORT_100BASEFX
};
#ifdef __KERNEL__
#include <linux/cache.h>
#include <linux/skbuff.h>
struct neighbour;
struct neigh_parms;
struct sk_buff;
struct netif_rx_stats
{
unsigned total;
unsigned dropped;
unsigned time_squeeze;
unsigned cpu_collision;
};
DECLARE_PER_CPU(struct netif_rx_stats, netdev_rx_stat);
struct dev_addr_list
{
struct dev_addr_list *next;
u8 da_addr[MAX_ADDR_LEN];
u8 da_addrlen;
u8 da_synced;
int da_users;
int da_gusers;
};
/*
* We tag multicasts with these structures.
*/
#define dev_mc_list dev_addr_list
#define dmi_addr da_addr
#define dmi_addrlen da_addrlen
#define dmi_users da_users
#define dmi_gusers da_gusers
struct hh_cache
{
struct hh_cache *hh_next; /* Next entry */
atomic_t hh_refcnt; /* number of users */
/*
* We want hh_output, hh_len, hh_lock and hh_data be a in a separate
* cache line on SMP.
* They are mostly read, but hh_refcnt may be changed quite frequently,
* incurring cache line ping pongs.
*/
__be16 hh_type ____cacheline_aligned_in_smp;
/* protocol identifier, f.e ETH_P_IP
* NOTE: For VLANs, this will be the
* encapuslated type. --BLG
*/
[NET]: Pack struct hh_cache [acme@newtoy net-2.6.20]$ pahole net/ipv4/tcp.o hh_cache /* /pub/scm/linux/kernel/git/acme/net-2.6.20/include/linux/netdevice.h:190 */ struct hh_cache { struct hh_cache * hh_next; /* 0 4 */ atomic_t hh_refcnt; /* 4 4 */ __be16 hh_type; /* 8 2 */ /* XXX 2 bytes hole, try to pack */ int hh_len; /* 12 4 */ int (*hh_output)(); /* 16 4 */ rwlock_t hh_lock; /* 20 36 */ long unsigned int hh_data[24]; /* 56 96 */ }; /* size: 152, sum members: 150, holes: 1, sum holes: 2 */ [acme@newtoy net-2.6.20]$ find net -name "*.[ch]" | xargs grep 'hh_len.\+=' | sort -u net/atm/br2684.c: hh->hh_len = PADLEN + ETH_HLEN; net/ethernet/eth.c: hh->hh_len = ETH_HLEN; net/ipv4/ipconfig.c: int hh_len = LL_RESERVED_SPACE(dev); net/ipv4/ip_output.c: hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); net/ipv4/ip_output.c: int hh_len = LL_RESERVED_SPACE(dev); net/ipv4/netfilter.c: hh_len = (*pskb)->dst->dev->hard_header_len; net/ipv4/raw.c: hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); net/ipv6/ip6_output.c: hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); net/ipv6/netfilter/ip6t_REJECT.c: hh_len = (dst->dev->hard_header_len + 15)&~15; net/ipv6/raw.c: hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); [acme@newtoy net-2.6.20]$ [acme@newtoy net-2.6.20]$ find include -name "*.h" | xargs grep 'define ETH_HLEN' include/linux/if_ether.h:#define ETH_HLEN 14 /* Total octets in header. */ (((dev)->hard_header_len&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) [acme@newtoy net-2.6.20]$ pahole net/ipv4/tcp.o net_device | grep hard_header_len short unsigned int hard_header_len; /* 106 2 */ [acme@newtoy net-2.6.20]$ So I think we're safe in turning hh_len an u16, end result: [acme@newtoy net-2.6.20]$ codiff -sV /tmp/tcp.o.before net/ipv4/tcp.o /pub/scm/linux/kernel/git/acme/net-2.6.20/net/ipv4/tcp.c: struct hh_cache | -4 hh_len; from: int /* 12(0) 4(0) */ to: u16 /* 10(0) 2(0) */ 1 struct changed [acme@newtoy net-2.6.20]$ Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2006-11-27 20:58:02 +01:00
u16 hh_len; /* length of header */
int (*hh_output)(struct sk_buff *skb);
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&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
#define LL_RESERVED_SPACE_EXTRA(dev,extra) \
((((dev)->hard_header_len+extra)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
/* 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_XOFF=0,
__LINK_STATE_START,
__LINK_STATE_PRESENT,
__LINK_STATE_SCHED,
__LINK_STATE_NOCARRIER,
__LINK_STATE_RX_SCHED,
__LINK_STATE_LINKWATCH_PENDING,
__LINK_STATE_DORMANT,
__LINK_STATE_QDISC_RUNNING,
};
/*
* 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
extern int __init netdev_boot_setup(char *str);
/*
* The DEVICE structure.
* Actually, this whole structure is a big mistake. It mixes I/O
* data with strictly "high-level" data, and it has to know about
* almost every data structure used in the INET module.
*
* FIXME: cleanup struct net_device such that network protocol info
* moves out.
*/
struct net_device
{
/*
* This is the first field of the "visible" part of this structure
* (i.e. as seen by users in the "Space.c" file). It is the name
* the interface.
*/
char name[IFNAMSIZ];
/* device name hash chain */
struct hlist_node name_hlist;
/*
* 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 char if_port; /* Selectable AUI, TP,..*/
unsigned char dma; /* DMA channel */
unsigned long state;
struct list_head dev_list;
/* The device initialization function. Called only once. */
int (*init)(struct net_device *dev);
/* ------- Fields preinitialized in Space.c finish here ------- */
/* Net device features */
unsigned long features;
#define NETIF_F_SG 1 /* Scatter/gather IO. */
#define NETIF_F_IP_CSUM 2 /* Can checksum TCP/UDP over IPv4. */
#define NETIF_F_NO_CSUM 4 /* Does not require checksum. F.e. loopack. */
#define NETIF_F_HW_CSUM 8 /* Can checksum all the packets. */
#define NETIF_F_IPV6_CSUM 16 /* Can checksum TCP/UDP over IPV6 */
#define NETIF_F_HIGHDMA 32 /* Can DMA to high memory. */
#define NETIF_F_FRAGLIST 64 /* Scatter/gather IO. */
#define NETIF_F_HW_VLAN_TX 128 /* Transmit VLAN hw acceleration */
#define NETIF_F_HW_VLAN_RX 256 /* Receive VLAN hw acceleration */
#define NETIF_F_HW_VLAN_FILTER 512 /* Receive filtering on VLAN */
#define NETIF_F_VLAN_CHALLENGED 1024 /* Device cannot handle VLAN packets */
#define NETIF_F_GSO 2048 /* Enable software GSO. */
#define NETIF_F_LLTX 4096 /* LockLess TX */
#define NETIF_F_MULTI_QUEUE 16384 /* Has multiple TX/RX queues */
/* Segmentation offload features */
#define NETIF_F_GSO_SHIFT 16
#define NETIF_F_GSO_MASK 0xffff0000
#define NETIF_F_TSO (SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT)
[IPV6]: Added GSO support for TCPv6 This patch adds GSO support for IPv6 and TCPv6. This is based on a patch by Ananda Raju <Ananda.Raju@neterion.com>. His original description is: This patch enables TSO over IPv6. Currently Linux network stacks restricts TSO over IPv6 by clearing of the NETIF_F_TSO bit from "dev->features". This patch will remove this restriction. This patch will introduce a new flag NETIF_F_TSO6 which will be used to check whether device supports TSO over IPv6. If device support TSO over IPv6 then we don't clear of NETIF_F_TSO and which will make the TCP layer to create TSO packets. Any device supporting TSO over IPv6 will set NETIF_F_TSO6 flag in "dev->features" along with NETIF_F_TSO. In case when user disables TSO using ethtool, NETIF_F_TSO will get cleared from "dev->features". So even if we have NETIF_F_TSO6 we don't get TSO packets created by TCP layer. SKB_GSO_TCPV4 renamed to SKB_GSO_TCP to make it generic GSO packet. SKB_GSO_UDPV4 renamed to SKB_GSO_UDP as UFO is not a IPv4 feature. UFO is supported over IPv6 also The following table shows there is significant improvement in throughput with normal frames and CPU usage for both normal and jumbo. -------------------------------------------------- | | 1500 | 9600 | | ------------------|-------------------| | | thru CPU | thru CPU | -------------------------------------------------- | TSO OFF | 2.00 5.5% id | 5.66 20.0% id | -------------------------------------------------- | TSO ON | 2.63 78.0 id | 5.67 39.0% id | -------------------------------------------------- Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-30 22:37:03 +02:00
#define NETIF_F_UFO (SKB_GSO_UDP << NETIF_F_GSO_SHIFT)
#define NETIF_F_GSO_ROBUST (SKB_GSO_DODGY << NETIF_F_GSO_SHIFT)
[IPV6]: Added GSO support for TCPv6 This patch adds GSO support for IPv6 and TCPv6. This is based on a patch by Ananda Raju <Ananda.Raju@neterion.com>. His original description is: This patch enables TSO over IPv6. Currently Linux network stacks restricts TSO over IPv6 by clearing of the NETIF_F_TSO bit from "dev->features". This patch will remove this restriction. This patch will introduce a new flag NETIF_F_TSO6 which will be used to check whether device supports TSO over IPv6. If device support TSO over IPv6 then we don't clear of NETIF_F_TSO and which will make the TCP layer to create TSO packets. Any device supporting TSO over IPv6 will set NETIF_F_TSO6 flag in "dev->features" along with NETIF_F_TSO. In case when user disables TSO using ethtool, NETIF_F_TSO will get cleared from "dev->features". So even if we have NETIF_F_TSO6 we don't get TSO packets created by TCP layer. SKB_GSO_TCPV4 renamed to SKB_GSO_TCP to make it generic GSO packet. SKB_GSO_UDPV4 renamed to SKB_GSO_UDP as UFO is not a IPv4 feature. UFO is supported over IPv6 also The following table shows there is significant improvement in throughput with normal frames and CPU usage for both normal and jumbo. -------------------------------------------------- | | 1500 | 9600 | | ------------------|-------------------| | | thru CPU | thru CPU | -------------------------------------------------- | TSO OFF | 2.00 5.5% id | 5.66 20.0% id | -------------------------------------------------- | TSO ON | 2.63 78.0 id | 5.67 39.0% id | -------------------------------------------------- Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-30 22:37:03 +02:00
#define NETIF_F_TSO_ECN (SKB_GSO_TCP_ECN << NETIF_F_GSO_SHIFT)
#define NETIF_F_TSO6 (SKB_GSO_TCPV6 << NETIF_F_GSO_SHIFT)
/* List of features with software fallbacks. */
#define NETIF_F_GSO_SOFTWARE (NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6)
#define NETIF_F_GEN_CSUM (NETIF_F_NO_CSUM | NETIF_F_HW_CSUM)
#define NETIF_F_V4_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IP_CSUM)
#define NETIF_F_V6_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IPV6_CSUM)
#define NETIF_F_ALL_CSUM (NETIF_F_V4_CSUM | NETIF_F_V6_CSUM)
struct net_device *next_sched;
/* Interface index. Unique device identifier */
int ifindex;
int iflink;
struct net_device_stats* (*get_stats)(struct net_device *dev);
struct net_device_stats stats;
#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
const struct ethtool_ops *ethtool_ops;
/*
* This marks the end of the "visible" part of the structure. All
* fields hereafter are internal to the system, and may change at
* will (read: may be cleaned up at will).
*/
unsigned int flags; /* interface flags (a la BSD) */
unsigned short gflags;
unsigned short priv_flags; /* Like 'flags' but invisible to userspace. */
unsigned short padded; /* How much padding added by alloc_netdev() */
unsigned char operstate; /* RFC2863 operstate */
unsigned char link_mode; /* mapping policy to operstate */
unsigned mtu; /* interface MTU value */
unsigned short type; /* interface hardware type */
unsigned short hard_header_len; /* hardware hdr length */
struct net_device *master; /* Pointer to master device of a group,
* which this device is member of.
*/
/* Interface address info. */
unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */
unsigned char addr_len; /* hardware address length */
unsigned short dev_id; /* for shared network cards */
struct dev_addr_list *uc_list; /* Secondary unicast mac addresses */
int uc_count; /* Number of installed ucasts */
int uc_promisc;
struct dev_addr_list *mc_list; /* Multicast mac addresses */
int mc_count; /* Number of installed mcasts */
int promiscuity;
int allmulti;
/* Protocol specific pointers */
void *atalk_ptr; /* AppleTalk link */
void *ip_ptr; /* IPv4 specific data */
void *dn_ptr; /* DECnet specific data */
void *ip6_ptr; /* IPv6 specific data */
void *ec_ptr; /* Econet specific data */
void *ax25_ptr; /* AX.25 specific data */
struct wireless_dev *ieee80211_ptr; /* IEEE 802.11 specific data,
assign before registering */
/*
* Cache line mostly used on receive path (including eth_type_trans())
*/
struct list_head poll_list ____cacheline_aligned_in_smp;
/* Link to poll list */
int (*poll) (struct net_device *dev, int *quota);
int quota;
int weight;
unsigned long last_rx; /* Time of last Rx */
/* Interface address info used in eth_type_trans() */
unsigned char dev_addr[MAX_ADDR_LEN]; /* hw address, (before bcast
because most packets are unicast) */
unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */
/*
* Cache line mostly used on queue transmit path (qdisc)
*/
/* device queue lock */
spinlock_t queue_lock ____cacheline_aligned_in_smp;
struct Qdisc *qdisc;
struct Qdisc *qdisc_sleeping;
struct list_head qdisc_list;
unsigned long tx_queue_len; /* Max frames per queue allowed */
/* Partially transmitted GSO packet. */
struct sk_buff *gso_skb;
/* ingress path synchronizer */
spinlock_t ingress_lock;
struct Qdisc *qdisc_ingress;
/*
* One part is mostly used on xmit path (device)
*/
/* hard_start_xmit synchronizer */
[NET]: Add netif_tx_lock Various drivers use xmit_lock internally to synchronise with their transmission routines. They do so without setting xmit_lock_owner. This is fine as long as netpoll is not in use. With netpoll it is possible for deadlocks to occur if xmit_lock_owner isn't set. This is because if a printk occurs while xmit_lock is held and xmit_lock_owner is not set can cause netpoll to attempt to take xmit_lock recursively. While it is possible to resolve this by getting netpoll to use trylock, it is suboptimal because netpoll's sole objective is to maximise the chance of getting the printk out on the wire. So delaying or dropping the message is to be avoided as much as possible. So the only alternative is to always set xmit_lock_owner. The following patch does this by introducing the netif_tx_lock family of functions that take care of setting/unsetting xmit_lock_owner. I renamed xmit_lock to _xmit_lock to indicate that it should not be used directly. I didn't provide irq versions of the netif_tx_lock functions since xmit_lock is meant to be a BH-disabling lock. This is pretty much a straight text substitution except for a small bug fix in winbond. It currently uses netif_stop_queue/spin_unlock_wait to stop transmission. This is unsafe as an IRQ can potentially wake up the queue. So it is safer to use netif_tx_disable. The hamradio bits used spin_lock_irq but it is unnecessary as xmit_lock must never be taken in an IRQ handler. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 21:20:56 +02:00
spinlock_t _xmit_lock ____cacheline_aligned_in_smp;
/* cpu id of processor entered to hard_start_xmit or -1,
if nobody entered there.
*/
int xmit_lock_owner;
void *priv; /* pointer to private data */
int (*hard_start_xmit) (struct sk_buff *skb,
struct net_device *dev);
/* These may be needed for future network-power-down code. */
unsigned long trans_start; /* Time (in jiffies) of last Tx */
int watchdog_timeo; /* used by dev_watchdog() */
struct timer_list watchdog_timer;
/*
* refcnt is a very hot point, so align it on SMP
*/
/* Number of references to this device */
atomic_t refcnt ____cacheline_aligned_in_smp;
/* delayed register/unregister */
struct list_head todo_list;
/* device index hash chain */
struct hlist_node index_hlist;
struct net_device *link_watch_next;
/* 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 */
} reg_state;
/* Called after device is detached from network. */
void (*uninit)(struct net_device *dev);
/* Called after last user reference disappears. */
void (*destructor)(struct net_device *dev);
/* Pointers to interface service routines. */
int (*open)(struct net_device *dev);
int (*stop)(struct net_device *dev);
#define HAVE_NETDEV_POLL
int (*hard_header) (struct sk_buff *skb,
struct net_device *dev,
unsigned short type,
void *daddr,
void *saddr,
unsigned len);
int (*rebuild_header)(struct sk_buff *skb);
[NET]: Add net_device change_rx_mode callback Currently the set_multicast_list (and set_rx_mode) callbacks are responsible for configuring the device according to the IFF_PROMISC, IFF_MULTICAST and IFF_ALLMULTI flags and the mc_list (and uc_list in case of set_rx_mode). These callbacks can be invoked from BH context without the rtnl_mutex by dev_mc_add/dev_mc_delete, which makes reading the device flags and promiscous/allmulti count racy. For real hardware drivers that just commit all changes to the hardware this is not a real problem since the stack guarantees to call them for every change, so at least the final call will not race and commit the correct configuration to the hardware. For software devices that want to synchronize promiscous and multicast state to an underlying device however this can cause corruption of the underlying device's flags or promisc/allmulti counts. When the software device is concurrently put in promiscous or allmulti mode while set_multicast_list is invoked from bottem half context, the device might synchronize the change to the underlying device without holding the rtnl_mutex, which races with concurrent changes to the underlying device. Add a dev->change_rx_flags hook that is invoked when any of the flags that affect rx filtering change (under the rtnl_mutex), which allows drivers to perform synchronization immediately and only synchronize the address lists in set_multicast_list/set_rx_mode. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-15 03:51:31 +02:00
#define HAVE_CHANGE_RX_FLAGS
void (*change_rx_flags)(struct net_device *dev,
int flags);
#define HAVE_SET_RX_MODE
void (*set_rx_mode)(struct net_device *dev);
#define HAVE_MULTICAST
void (*set_multicast_list)(struct net_device *dev);
#define HAVE_SET_MAC_ADDR
int (*set_mac_address)(struct net_device *dev,
void *addr);
#define HAVE_PRIVATE_IOCTL
int (*do_ioctl)(struct net_device *dev,
struct ifreq *ifr, int cmd);
#define HAVE_SET_CONFIG
int (*set_config)(struct net_device *dev,
struct ifmap *map);
#define HAVE_HEADER_CACHE
int (*hard_header_cache)(struct neighbour *neigh,
struct hh_cache *hh);
void (*header_cache_update)(struct hh_cache *hh,
struct net_device *dev,
unsigned char * haddr);
#define HAVE_CHANGE_MTU
int (*change_mtu)(struct net_device *dev, int new_mtu);
#define HAVE_TX_TIMEOUT
void (*tx_timeout) (struct net_device *dev);
void (*vlan_rx_register)(struct net_device *dev,
struct vlan_group *grp);
void (*vlan_rx_add_vid)(struct net_device *dev,
unsigned short vid);
void (*vlan_rx_kill_vid)(struct net_device *dev,
unsigned short vid);
int (*hard_header_parse)(struct sk_buff *skb,
unsigned char *haddr);
int (*neigh_setup)(struct net_device *dev, struct neigh_parms *);
#ifdef CONFIG_NETPOLL
struct netpoll_info *npinfo;
#endif
#ifdef CONFIG_NET_POLL_CONTROLLER
void (*poll_controller)(struct net_device *dev);
#endif
/* bridge stuff */
struct net_bridge_port *br_port;
/* macvlan */
struct macvlan_port *macvlan_port;
/* class/net/name entry */
struct device dev;
/* space for optional statistics and wireless sysfs groups */
struct attribute_group *sysfs_groups[3];
/* rtnetlink link ops */
const struct rtnl_link_ops *rtnl_link_ops;
/* The TX queue control structures */
unsigned int egress_subqueue_count;
struct net_device_subqueue egress_subqueue[1];
};
#define to_net_dev(d) container_of(d, struct net_device, dev)
#define NETDEV_ALIGN 32
#define NETDEV_ALIGN_CONST (NETDEV_ALIGN - 1)
static inline void *netdev_priv(const struct net_device *dev)
{
return dev->priv;
}
#define SET_MODULE_OWNER(dev) do { } while (0)
/* 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))
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 *);
struct sk_buff *(*gso_segment)(struct sk_buff *skb,
int features);
int (*gso_send_check)(struct sk_buff *skb);
void *af_packet_priv;
struct list_head list;
};
#include <linux/interrupt.h>
#include <linux/notifier.h>
extern struct net_device loopback_dev; /* The loopback */
extern struct list_head dev_base_head; /* All devices */
extern rwlock_t dev_base_lock; /* Device list lock */
#define for_each_netdev(d) \
list_for_each_entry(d, &dev_base_head, dev_list)
#define for_each_netdev_safe(d, n) \
list_for_each_entry_safe(d, n, &dev_base_head, dev_list)
#define for_each_netdev_continue(d) \
list_for_each_entry_continue(d, &dev_base_head, dev_list)
#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;
lh = dev->dev_list.next;
return lh == &dev_base_head ? NULL : net_device_entry(lh);
}
static inline struct net_device *first_net_device(void)
{
return list_empty(&dev_base_head) ? NULL :
net_device_entry(dev_base_head.next);
}
extern int netdev_boot_setup_check(struct net_device *dev);
extern unsigned long netdev_boot_base(const char *prefix, int unit);
extern struct net_device *dev_getbyhwaddr(unsigned short type, char *hwaddr);
extern struct net_device *dev_getfirstbyhwtype(unsigned short type);
extern struct net_device *__dev_getfirstbyhwtype(unsigned short type);
extern void dev_add_pack(struct packet_type *pt);
extern void dev_remove_pack(struct packet_type *pt);
extern void __dev_remove_pack(struct packet_type *pt);
extern struct net_device *dev_get_by_flags(unsigned short flags,
unsigned short mask);
extern struct net_device *dev_get_by_name(const char *name);
extern struct net_device *__dev_get_by_name(const char *name);
extern int dev_alloc_name(struct net_device *dev, const char *name);
extern int dev_open(struct net_device *dev);
extern int dev_close(struct net_device *dev);
extern int dev_queue_xmit(struct sk_buff *skb);
extern int register_netdevice(struct net_device *dev);
extern void unregister_netdevice(struct net_device *dev);
extern void free_netdev(struct net_device *dev);
extern void synchronize_net(void);
extern int register_netdevice_notifier(struct notifier_block *nb);
extern int unregister_netdevice_notifier(struct notifier_block *nb);
extern int call_netdevice_notifiers(unsigned long val, void *v);
extern struct net_device *dev_get_by_index(int ifindex);
extern struct net_device *__dev_get_by_index(int ifindex);
extern int dev_restart(struct net_device *dev);
#ifdef CONFIG_NETPOLL_TRAP
extern int netpoll_trap(void);
#endif
typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
extern int register_gifconf(unsigned int family, gifconf_func_t * gifconf);
static inline int unregister_gifconf(unsigned int family)
{
return register_gifconf(family, NULL);
}
/*
* Incoming packets are placed on per-cpu queues so that
* no locking is needed.
*/
struct softnet_data
{
struct net_device *output_queue;
struct sk_buff_head input_pkt_queue;
struct list_head poll_list;
struct sk_buff *completion_queue;
struct net_device backlog_dev; /* Sorry. 8) */
#ifdef CONFIG_NET_DMA
struct dma_chan *net_dma;
#endif
};
DECLARE_PER_CPU(struct softnet_data,softnet_data);
#define HAVE_NETIF_QUEUE
[NET]: Deinline some larger functions from netdevice.h On a allyesconfig'ured kernel: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 95 162 12075 netif_wake_queue include/linux/netdevice.h 129 86 9265 dev_kfree_skb_any include/linux/netdevice.h 127 56 5885 netif_device_attach include/linux/netdevice.h 73 86 4505 dev_kfree_skb_irq include/linux/netdevice.h 46 60 1534 netif_device_detach include/linux/netdevice.h 119 16 1485 __netif_rx_schedule include/linux/netdevice.h 143 5 492 netif_rx_schedule include/linux/netdevice.h 81 7 366 netif_schedule include/linux/netdevice.h netif_wake_queue is big because __netif_schedule is a big inline: static inline void __netif_schedule(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_SCHED, &dev->state)) { unsigned long flags; struct softnet_data *sd; local_irq_save(flags); sd = &__get_cpu_var(softnet_data); dev->next_sched = sd->output_queue; sd->output_queue = dev; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } } static inline void netif_wake_queue(struct net_device *dev) { #ifdef CONFIG_NETPOLL_TRAP if (netpoll_trap()) return; #endif if (test_and_clear_bit(__LINK_STATE_XOFF, &dev->state)) __netif_schedule(dev); } By de-inlining __netif_schedule we are saving a lot of text at each callsite of netif_wake_queue and netif_schedule. __netif_rx_schedule is also big, and it makes more sense to keep both of them out of line. Patch also deinlines dev_kfree_skb_any. We can deinline dev_kfree_skb_irq instead... oh well. netif_device_attach/detach are not hot paths, we can deinline them too. Signed-off-by: Denis Vlasenko <vda@ilport.com.ua> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-30 01:57:29 +02:00
extern void __netif_schedule(struct net_device *dev);
static inline void netif_schedule(struct net_device *dev)
{
if (!test_bit(__LINK_STATE_XOFF, &dev->state))
__netif_schedule(dev);
}
static inline void netif_start_queue(struct net_device *dev)
{
clear_bit(__LINK_STATE_XOFF, &dev->state);
}
static inline void netif_wake_queue(struct net_device *dev)
{
#ifdef CONFIG_NETPOLL_TRAP
if (netpoll_trap()) {
clear_bit(__LINK_STATE_XOFF, &dev->state);
return;
}
#endif
if (test_and_clear_bit(__LINK_STATE_XOFF, &dev->state))
__netif_schedule(dev);
}
static inline void netif_stop_queue(struct net_device *dev)
{
set_bit(__LINK_STATE_XOFF, &dev->state);
}
static inline int netif_queue_stopped(const struct net_device *dev)
{
return test_bit(__LINK_STATE_XOFF, &dev->state);
}
static inline int 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.
*/
static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index)
{
#ifdef CONFIG_NETDEVICES_MULTIQUEUE
clear_bit(__LINK_STATE_XOFF, &dev->egress_subqueue[queue_index].state);
#endif
}
static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index)
{
#ifdef CONFIG_NETDEVICES_MULTIQUEUE
#ifdef CONFIG_NETPOLL_TRAP
if (netpoll_trap())
return;
#endif
set_bit(__LINK_STATE_XOFF, &dev->egress_subqueue[queue_index].state);
#endif
}
static inline int netif_subqueue_stopped(const struct net_device *dev,
u16 queue_index)
{
#ifdef CONFIG_NETDEVICES_MULTIQUEUE
return test_bit(__LINK_STATE_XOFF,
&dev->egress_subqueue[queue_index].state);
#else
return 0;
#endif
}
static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
{
#ifdef CONFIG_NETDEVICES_MULTIQUEUE
#ifdef CONFIG_NETPOLL_TRAP
if (netpoll_trap())
return;
#endif
if (test_and_clear_bit(__LINK_STATE_XOFF,
&dev->egress_subqueue[queue_index].state))
__netif_schedule(dev);
#endif
}
static inline int netif_is_multiqueue(const struct net_device *dev)
{
#ifdef CONFIG_NETDEVICES_MULTIQUEUE
return (!!(NETIF_F_MULTI_QUEUE & dev->features));
#else
return 0;
#endif
}
/* Use this variant when it is known for sure that it
* is executing from interrupt context.
*/
static inline void dev_kfree_skb_irq(struct sk_buff *skb)
{
if (atomic_dec_and_test(&skb->users)) {
struct softnet_data *sd;
unsigned long flags;
local_irq_save(flags);
sd = &__get_cpu_var(softnet_data);
skb->next = sd->completion_queue;
sd->completion_queue = skb;
raise_softirq_irqoff(NET_TX_SOFTIRQ);
local_irq_restore(flags);
}
}
/* Use this variant in places where it could be invoked
* either from interrupt or non-interrupt context.
*/
[NET]: Deinline some larger functions from netdevice.h On a allyesconfig'ured kernel: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 95 162 12075 netif_wake_queue include/linux/netdevice.h 129 86 9265 dev_kfree_skb_any include/linux/netdevice.h 127 56 5885 netif_device_attach include/linux/netdevice.h 73 86 4505 dev_kfree_skb_irq include/linux/netdevice.h 46 60 1534 netif_device_detach include/linux/netdevice.h 119 16 1485 __netif_rx_schedule include/linux/netdevice.h 143 5 492 netif_rx_schedule include/linux/netdevice.h 81 7 366 netif_schedule include/linux/netdevice.h netif_wake_queue is big because __netif_schedule is a big inline: static inline void __netif_schedule(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_SCHED, &dev->state)) { unsigned long flags; struct softnet_data *sd; local_irq_save(flags); sd = &__get_cpu_var(softnet_data); dev->next_sched = sd->output_queue; sd->output_queue = dev; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } } static inline void netif_wake_queue(struct net_device *dev) { #ifdef CONFIG_NETPOLL_TRAP if (netpoll_trap()) return; #endif if (test_and_clear_bit(__LINK_STATE_XOFF, &dev->state)) __netif_schedule(dev); } By de-inlining __netif_schedule we are saving a lot of text at each callsite of netif_wake_queue and netif_schedule. __netif_rx_schedule is also big, and it makes more sense to keep both of them out of line. Patch also deinlines dev_kfree_skb_any. We can deinline dev_kfree_skb_irq instead... oh well. netif_device_attach/detach are not hot paths, we can deinline them too. Signed-off-by: Denis Vlasenko <vda@ilport.com.ua> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-30 01:57:29 +02:00
extern void dev_kfree_skb_any(struct sk_buff *skb);
#define HAVE_NETIF_RX 1
extern int netif_rx(struct sk_buff *skb);
extern int netif_rx_ni(struct sk_buff *skb);
#define HAVE_NETIF_RECEIVE_SKB 1
extern int netif_receive_skb(struct sk_buff *skb);
extern int dev_valid_name(const char *name);
extern int dev_ioctl(unsigned int cmd, void __user *);
extern int dev_ethtool(struct ifreq *);
extern unsigned dev_get_flags(const struct net_device *);
extern int dev_change_flags(struct net_device *, unsigned);
extern int dev_change_name(struct net_device *, char *);
extern int dev_set_mtu(struct net_device *, int);
extern int dev_set_mac_address(struct net_device *,
struct sockaddr *);
extern int dev_hard_start_xmit(struct sk_buff *skb,
struct net_device *dev);
extern void dev_init(void);
extern int netdev_budget;
/* Called by rtnetlink.c:rtnl_unlock() */
extern void netdev_run_todo(void);
static inline void dev_put(struct net_device *dev)
{
atomic_dec(&dev->refcnt);
}
static inline void dev_hold(struct net_device *dev)
{
atomic_inc(&dev->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.
*/
extern void linkwatch_fire_event(struct net_device *dev);
static inline int netif_carrier_ok(const struct net_device *dev)
{
return !test_bit(__LINK_STATE_NOCARRIER, &dev->state);
}
extern void __netdev_watchdog_up(struct net_device *dev);
extern void netif_carrier_on(struct net_device *dev);
extern void netif_carrier_off(struct net_device *dev);
static inline void netif_dormant_on(struct net_device *dev)
{
if (!test_and_set_bit(__LINK_STATE_DORMANT, &dev->state))
linkwatch_fire_event(dev);
}
static inline void netif_dormant_off(struct net_device *dev)
{
if (test_and_clear_bit(__LINK_STATE_DORMANT, &dev->state))
linkwatch_fire_event(dev);
}
static inline int netif_dormant(const struct net_device *dev)
{
return test_bit(__LINK_STATE_DORMANT, &dev->state);
}
static inline int netif_oper_up(const struct net_device *dev) {
return (dev->operstate == IF_OPER_UP ||
dev->operstate == IF_OPER_UNKNOWN /* backward compat */);
}
/* Hot-plugging. */
static inline int netif_device_present(struct net_device *dev)
{
return test_bit(__LINK_STATE_PRESENT, &dev->state);
}
[NET]: Deinline some larger functions from netdevice.h On a allyesconfig'ured kernel: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 95 162 12075 netif_wake_queue include/linux/netdevice.h 129 86 9265 dev_kfree_skb_any include/linux/netdevice.h 127 56 5885 netif_device_attach include/linux/netdevice.h 73 86 4505 dev_kfree_skb_irq include/linux/netdevice.h 46 60 1534 netif_device_detach include/linux/netdevice.h 119 16 1485 __netif_rx_schedule include/linux/netdevice.h 143 5 492 netif_rx_schedule include/linux/netdevice.h 81 7 366 netif_schedule include/linux/netdevice.h netif_wake_queue is big because __netif_schedule is a big inline: static inline void __netif_schedule(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_SCHED, &dev->state)) { unsigned long flags; struct softnet_data *sd; local_irq_save(flags); sd = &__get_cpu_var(softnet_data); dev->next_sched = sd->output_queue; sd->output_queue = dev; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } } static inline void netif_wake_queue(struct net_device *dev) { #ifdef CONFIG_NETPOLL_TRAP if (netpoll_trap()) return; #endif if (test_and_clear_bit(__LINK_STATE_XOFF, &dev->state)) __netif_schedule(dev); } By de-inlining __netif_schedule we are saving a lot of text at each callsite of netif_wake_queue and netif_schedule. __netif_rx_schedule is also big, and it makes more sense to keep both of them out of line. Patch also deinlines dev_kfree_skb_any. We can deinline dev_kfree_skb_irq instead... oh well. netif_device_attach/detach are not hot paths, we can deinline them too. Signed-off-by: Denis Vlasenko <vda@ilport.com.ua> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-30 01:57:29 +02:00
extern void netif_device_detach(struct net_device *dev);
[NET]: Deinline some larger functions from netdevice.h On a allyesconfig'ured kernel: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 95 162 12075 netif_wake_queue include/linux/netdevice.h 129 86 9265 dev_kfree_skb_any include/linux/netdevice.h 127 56 5885 netif_device_attach include/linux/netdevice.h 73 86 4505 dev_kfree_skb_irq include/linux/netdevice.h 46 60 1534 netif_device_detach include/linux/netdevice.h 119 16 1485 __netif_rx_schedule include/linux/netdevice.h 143 5 492 netif_rx_schedule include/linux/netdevice.h 81 7 366 netif_schedule include/linux/netdevice.h netif_wake_queue is big because __netif_schedule is a big inline: static inline void __netif_schedule(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_SCHED, &dev->state)) { unsigned long flags; struct softnet_data *sd; local_irq_save(flags); sd = &__get_cpu_var(softnet_data); dev->next_sched = sd->output_queue; sd->output_queue = dev; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } } static inline void netif_wake_queue(struct net_device *dev) { #ifdef CONFIG_NETPOLL_TRAP if (netpoll_trap()) return; #endif if (test_and_clear_bit(__LINK_STATE_XOFF, &dev->state)) __netif_schedule(dev); } By de-inlining __netif_schedule we are saving a lot of text at each callsite of netif_wake_queue and netif_schedule. __netif_rx_schedule is also big, and it makes more sense to keep both of them out of line. Patch also deinlines dev_kfree_skb_any. We can deinline dev_kfree_skb_irq instead... oh well. netif_device_attach/detach are not hot paths, we can deinline them too. Signed-off-by: Denis Vlasenko <vda@ilport.com.ua> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-30 01:57:29 +02:00
extern void netif_device_attach(struct net_device *dev);
/*
* Network interface message level settings
*/
#define HAVE_NETIF_MSG 1
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;
}
/* Test if receive needs to be scheduled */
static inline int __netif_rx_schedule_prep(struct net_device *dev)
{
return !test_and_set_bit(__LINK_STATE_RX_SCHED, &dev->state);
}
/* Test if receive needs to be scheduled but only if up */
static inline int netif_rx_schedule_prep(struct net_device *dev)
{
return netif_running(dev) && __netif_rx_schedule_prep(dev);
}
/* Add interface to tail of rx poll list. This assumes that _prep has
* already been called and returned 1.
*/
[NET]: Deinline some larger functions from netdevice.h On a allyesconfig'ured kernel: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 95 162 12075 netif_wake_queue include/linux/netdevice.h 129 86 9265 dev_kfree_skb_any include/linux/netdevice.h 127 56 5885 netif_device_attach include/linux/netdevice.h 73 86 4505 dev_kfree_skb_irq include/linux/netdevice.h 46 60 1534 netif_device_detach include/linux/netdevice.h 119 16 1485 __netif_rx_schedule include/linux/netdevice.h 143 5 492 netif_rx_schedule include/linux/netdevice.h 81 7 366 netif_schedule include/linux/netdevice.h netif_wake_queue is big because __netif_schedule is a big inline: static inline void __netif_schedule(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_SCHED, &dev->state)) { unsigned long flags; struct softnet_data *sd; local_irq_save(flags); sd = &__get_cpu_var(softnet_data); dev->next_sched = sd->output_queue; sd->output_queue = dev; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } } static inline void netif_wake_queue(struct net_device *dev) { #ifdef CONFIG_NETPOLL_TRAP if (netpoll_trap()) return; #endif if (test_and_clear_bit(__LINK_STATE_XOFF, &dev->state)) __netif_schedule(dev); } By de-inlining __netif_schedule we are saving a lot of text at each callsite of netif_wake_queue and netif_schedule. __netif_rx_schedule is also big, and it makes more sense to keep both of them out of line. Patch also deinlines dev_kfree_skb_any. We can deinline dev_kfree_skb_irq instead... oh well. netif_device_attach/detach are not hot paths, we can deinline them too. Signed-off-by: Denis Vlasenko <vda@ilport.com.ua> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-30 01:57:29 +02:00
extern void __netif_rx_schedule(struct net_device *dev);
/* Try to reschedule poll. Called by irq handler. */
static inline void netif_rx_schedule(struct net_device *dev)
{
if (netif_rx_schedule_prep(dev))
__netif_rx_schedule(dev);
}
/* Try to reschedule poll. Called by dev->poll() after netif_rx_complete().
* Do not inline this?
*/
static inline int netif_rx_reschedule(struct net_device *dev, int undo)
{
if (netif_rx_schedule_prep(dev)) {
unsigned long flags;
dev->quota += undo;
local_irq_save(flags);
list_add_tail(&dev->poll_list, &__get_cpu_var(softnet_data).poll_list);
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
local_irq_restore(flags);
return 1;
}
return 0;
}
/* same as netif_rx_complete, except that local_irq_save(flags)
* has already been issued
*/
static inline void __netif_rx_complete(struct net_device *dev)
{
BUG_ON(!test_bit(__LINK_STATE_RX_SCHED, &dev->state));
list_del(&dev->poll_list);
smp_mb__before_clear_bit();
clear_bit(__LINK_STATE_RX_SCHED, &dev->state);
}
/* Remove interface from poll list: it must be in the poll list
* on current cpu. This primitive is called by dev->poll(), when
* it completes the work. The device cannot be out of poll list at this
* moment, it is BUG().
*/
static inline void netif_rx_complete(struct net_device *dev)
{
unsigned long flags;
local_irq_save(flags);
__netif_rx_complete(dev);
local_irq_restore(flags);
}
static inline void netif_poll_disable(struct net_device *dev)
{
while (test_and_set_bit(__LINK_STATE_RX_SCHED, &dev->state))
/* No hurry. */
schedule_timeout_interruptible(1);
}
static inline void netif_poll_enable(struct net_device *dev)
{
smp_mb__before_clear_bit();
clear_bit(__LINK_STATE_RX_SCHED, &dev->state);
}
[NET]: Add netif_tx_lock Various drivers use xmit_lock internally to synchronise with their transmission routines. They do so without setting xmit_lock_owner. This is fine as long as netpoll is not in use. With netpoll it is possible for deadlocks to occur if xmit_lock_owner isn't set. This is because if a printk occurs while xmit_lock is held and xmit_lock_owner is not set can cause netpoll to attempt to take xmit_lock recursively. While it is possible to resolve this by getting netpoll to use trylock, it is suboptimal because netpoll's sole objective is to maximise the chance of getting the printk out on the wire. So delaying or dropping the message is to be avoided as much as possible. So the only alternative is to always set xmit_lock_owner. The following patch does this by introducing the netif_tx_lock family of functions that take care of setting/unsetting xmit_lock_owner. I renamed xmit_lock to _xmit_lock to indicate that it should not be used directly. I didn't provide irq versions of the netif_tx_lock functions since xmit_lock is meant to be a BH-disabling lock. This is pretty much a straight text substitution except for a small bug fix in winbond. It currently uses netif_stop_queue/spin_unlock_wait to stop transmission. This is unsafe as an IRQ can potentially wake up the queue. So it is safer to use netif_tx_disable. The hamradio bits used spin_lock_irq but it is unnecessary as xmit_lock must never be taken in an IRQ handler. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 21:20:56 +02:00
static inline void netif_tx_lock(struct net_device *dev)
{
spin_lock(&dev->_xmit_lock);
dev->xmit_lock_owner = smp_processor_id();
}
static inline void netif_tx_lock_bh(struct net_device *dev)
{
spin_lock_bh(&dev->_xmit_lock);
dev->xmit_lock_owner = smp_processor_id();
}
static inline int netif_tx_trylock(struct net_device *dev)
{
int ok = spin_trylock(&dev->_xmit_lock);
if (likely(ok))
[NET]: Add netif_tx_lock Various drivers use xmit_lock internally to synchronise with their transmission routines. They do so without setting xmit_lock_owner. This is fine as long as netpoll is not in use. With netpoll it is possible for deadlocks to occur if xmit_lock_owner isn't set. This is because if a printk occurs while xmit_lock is held and xmit_lock_owner is not set can cause netpoll to attempt to take xmit_lock recursively. While it is possible to resolve this by getting netpoll to use trylock, it is suboptimal because netpoll's sole objective is to maximise the chance of getting the printk out on the wire. So delaying or dropping the message is to be avoided as much as possible. So the only alternative is to always set xmit_lock_owner. The following patch does this by introducing the netif_tx_lock family of functions that take care of setting/unsetting xmit_lock_owner. I renamed xmit_lock to _xmit_lock to indicate that it should not be used directly. I didn't provide irq versions of the netif_tx_lock functions since xmit_lock is meant to be a BH-disabling lock. This is pretty much a straight text substitution except for a small bug fix in winbond. It currently uses netif_stop_queue/spin_unlock_wait to stop transmission. This is unsafe as an IRQ can potentially wake up the queue. So it is safer to use netif_tx_disable. The hamradio bits used spin_lock_irq but it is unnecessary as xmit_lock must never be taken in an IRQ handler. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 21:20:56 +02:00
dev->xmit_lock_owner = smp_processor_id();
return ok;
[NET]: Add netif_tx_lock Various drivers use xmit_lock internally to synchronise with their transmission routines. They do so without setting xmit_lock_owner. This is fine as long as netpoll is not in use. With netpoll it is possible for deadlocks to occur if xmit_lock_owner isn't set. This is because if a printk occurs while xmit_lock is held and xmit_lock_owner is not set can cause netpoll to attempt to take xmit_lock recursively. While it is possible to resolve this by getting netpoll to use trylock, it is suboptimal because netpoll's sole objective is to maximise the chance of getting the printk out on the wire. So delaying or dropping the message is to be avoided as much as possible. So the only alternative is to always set xmit_lock_owner. The following patch does this by introducing the netif_tx_lock family of functions that take care of setting/unsetting xmit_lock_owner. I renamed xmit_lock to _xmit_lock to indicate that it should not be used directly. I didn't provide irq versions of the netif_tx_lock functions since xmit_lock is meant to be a BH-disabling lock. This is pretty much a straight text substitution except for a small bug fix in winbond. It currently uses netif_stop_queue/spin_unlock_wait to stop transmission. This is unsafe as an IRQ can potentially wake up the queue. So it is safer to use netif_tx_disable. The hamradio bits used spin_lock_irq but it is unnecessary as xmit_lock must never be taken in an IRQ handler. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 21:20:56 +02:00
}
static inline void netif_tx_unlock(struct net_device *dev)
{
dev->xmit_lock_owner = -1;
spin_unlock(&dev->_xmit_lock);
}
static inline void netif_tx_unlock_bh(struct net_device *dev)
{
dev->xmit_lock_owner = -1;
spin_unlock_bh(&dev->_xmit_lock);
}
static inline void netif_tx_disable(struct net_device *dev)
{
[NET]: Add netif_tx_lock Various drivers use xmit_lock internally to synchronise with their transmission routines. They do so without setting xmit_lock_owner. This is fine as long as netpoll is not in use. With netpoll it is possible for deadlocks to occur if xmit_lock_owner isn't set. This is because if a printk occurs while xmit_lock is held and xmit_lock_owner is not set can cause netpoll to attempt to take xmit_lock recursively. While it is possible to resolve this by getting netpoll to use trylock, it is suboptimal because netpoll's sole objective is to maximise the chance of getting the printk out on the wire. So delaying or dropping the message is to be avoided as much as possible. So the only alternative is to always set xmit_lock_owner. The following patch does this by introducing the netif_tx_lock family of functions that take care of setting/unsetting xmit_lock_owner. I renamed xmit_lock to _xmit_lock to indicate that it should not be used directly. I didn't provide irq versions of the netif_tx_lock functions since xmit_lock is meant to be a BH-disabling lock. This is pretty much a straight text substitution except for a small bug fix in winbond. It currently uses netif_stop_queue/spin_unlock_wait to stop transmission. This is unsafe as an IRQ can potentially wake up the queue. So it is safer to use netif_tx_disable. The hamradio bits used spin_lock_irq but it is unnecessary as xmit_lock must never be taken in an IRQ handler. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 21:20:56 +02:00
netif_tx_lock_bh(dev);
netif_stop_queue(dev);
[NET]: Add netif_tx_lock Various drivers use xmit_lock internally to synchronise with their transmission routines. They do so without setting xmit_lock_owner. This is fine as long as netpoll is not in use. With netpoll it is possible for deadlocks to occur if xmit_lock_owner isn't set. This is because if a printk occurs while xmit_lock is held and xmit_lock_owner is not set can cause netpoll to attempt to take xmit_lock recursively. While it is possible to resolve this by getting netpoll to use trylock, it is suboptimal because netpoll's sole objective is to maximise the chance of getting the printk out on the wire. So delaying or dropping the message is to be avoided as much as possible. So the only alternative is to always set xmit_lock_owner. The following patch does this by introducing the netif_tx_lock family of functions that take care of setting/unsetting xmit_lock_owner. I renamed xmit_lock to _xmit_lock to indicate that it should not be used directly. I didn't provide irq versions of the netif_tx_lock functions since xmit_lock is meant to be a BH-disabling lock. This is pretty much a straight text substitution except for a small bug fix in winbond. It currently uses netif_stop_queue/spin_unlock_wait to stop transmission. This is unsafe as an IRQ can potentially wake up the queue. So it is safer to use netif_tx_disable. The hamradio bits used spin_lock_irq but it is unnecessary as xmit_lock must never be taken in an IRQ handler. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 21:20:56 +02:00
netif_tx_unlock_bh(dev);
}
/* These functions live elsewhere (drivers/net/net_init.c, but related) */
extern void ether_setup(struct net_device *dev);
/* Support for loadable net-drivers */
extern struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
void (*setup)(struct net_device *),
unsigned int queue_count);
#define alloc_netdev(sizeof_priv, name, setup) \
alloc_netdev_mq(sizeof_priv, name, setup, 1)
extern int register_netdev(struct net_device *dev);
extern void unregister_netdev(struct net_device *dev);
/* Functions used for secondary unicast and multicast support */
extern void dev_set_rx_mode(struct net_device *dev);
extern void __dev_set_rx_mode(struct net_device *dev);
extern int dev_unicast_delete(struct net_device *dev, void *addr, int alen);
extern int dev_unicast_add(struct net_device *dev, void *addr, int alen);
extern int dev_mc_delete(struct net_device *dev, void *addr, int alen, int all);
extern int dev_mc_add(struct net_device *dev, void *addr, int alen, int newonly);
extern int dev_mc_sync(struct net_device *to, struct net_device *from);
extern void dev_mc_unsync(struct net_device *to, struct net_device *from);
extern int __dev_addr_delete(struct dev_addr_list **list, int *count, void *addr, int alen, int all);
extern int __dev_addr_add(struct dev_addr_list **list, int *count, void *addr, int alen, int newonly);
extern void dev_set_promiscuity(struct net_device *dev, int inc);
extern void dev_set_allmulti(struct net_device *dev, int inc);
extern void netdev_state_change(struct net_device *dev);
extern void netdev_features_change(struct net_device *dev);
/* Load a device via the kmod */
extern void dev_load(const char *name);
extern void dev_mcast_init(void);
extern int netdev_max_backlog;
extern int weight_p;
extern int netdev_set_master(struct net_device *dev, struct net_device *master);
extern int skb_checksum_help(struct sk_buff *skb);
extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features);
#ifdef CONFIG_BUG
extern void netdev_rx_csum_fault(struct net_device *dev);
#else
static inline void netdev_rx_csum_fault(struct net_device *dev)
{
}
#endif
/* rx skb timestamps */
extern void net_enable_timestamp(void);
extern void net_disable_timestamp(void);
#ifdef CONFIG_PROC_FS
extern void *dev_seq_start(struct seq_file *seq, loff_t *pos);
extern void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos);
extern void dev_seq_stop(struct seq_file *seq, void *v);
#endif
extern void linkwatch_run_queue(void);
static inline int net_gso_ok(int features, int gso_type)
{
int feature = gso_type << NETIF_F_GSO_SHIFT;
return (features & feature) == feature;
}
static inline int skb_gso_ok(struct sk_buff *skb, int features)
{
return net_gso_ok(features, skb_shinfo(skb)->gso_type);
}
static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb)
{
return skb_is_gso(skb) &&
(!skb_gso_ok(skb, dev->features) ||
unlikely(skb->ip_summed != CHECKSUM_PARTIAL));
}
/* On bonding slaves other than the currently active slave, suppress
* duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and
* ARP on active-backup slaves with arp_validate enabled.
*/
static inline int skb_bond_should_drop(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct net_device *master = dev->master;
if (master &&
(dev->priv_flags & IFF_SLAVE_INACTIVE)) {
if ((dev->priv_flags & IFF_SLAVE_NEEDARP) &&
skb->protocol == __constant_htons(ETH_P_ARP))
return 0;
if (master->priv_flags & IFF_MASTER_ALB) {
if (skb->pkt_type != PACKET_BROADCAST &&
skb->pkt_type != PACKET_MULTICAST)
return 0;
}
if (master->priv_flags & IFF_MASTER_8023AD &&
skb->protocol == __constant_htons(ETH_P_SLOW))
return 0;
return 1;
}
return 0;
}
#endif /* __KERNEL__ */
#endif /* _LINUX_DEV_H */