blob: b24ab0e98eb4d8dd8cef2a20ef2a39b97d9ece92 [file] [log] [blame]
/*
* NET3 Protocol independent device support routines.
*
* 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.
*
* Derived from the non IP parts of dev.c 1.0.19
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
*
* Additional Authors:
* Florian la Roche <rzsfl@rz.uni-sb.de>
* Alan Cox <gw4pts@gw4pts.ampr.org>
* David Hinds <dahinds@users.sourceforge.net>
* Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
* Adam Sulmicki <adam@cfar.umd.edu>
* Pekka Riikonen <priikone@poesidon.pspt.fi>
*
* Changes:
* D.J. Barrow : Fixed bug where dev->refcnt gets set
* to 2 if register_netdev gets called
* before net_dev_init & also removed a
* few lines of code in the process.
* Alan Cox : device private ioctl copies fields back.
* Alan Cox : Transmit queue code does relevant
* stunts to keep the queue safe.
* Alan Cox : Fixed double lock.
* Alan Cox : Fixed promisc NULL pointer trap
* ???????? : Support the full private ioctl range
* Alan Cox : Moved ioctl permission check into
* drivers
* Tim Kordas : SIOCADDMULTI/SIOCDELMULTI
* Alan Cox : 100 backlog just doesn't cut it when
* you start doing multicast video 8)
* Alan Cox : Rewrote net_bh and list manager.
* Alan Cox : Fix ETH_P_ALL echoback lengths.
* Alan Cox : Took out transmit every packet pass
* Saved a few bytes in the ioctl handler
* Alan Cox : Network driver sets packet type before
* calling netif_rx. Saves a function
* call a packet.
* Alan Cox : Hashed net_bh()
* Richard Kooijman: Timestamp fixes.
* Alan Cox : Wrong field in SIOCGIFDSTADDR
* Alan Cox : Device lock protection.
* Alan Cox : Fixed nasty side effect of device close
* changes.
* Rudi Cilibrasi : Pass the right thing to
* set_mac_address()
* Dave Miller : 32bit quantity for the device lock to
* make it work out on a Sparc.
* Bjorn Ekwall : Added KERNELD hack.
* Alan Cox : Cleaned up the backlog initialise.
* Craig Metz : SIOCGIFCONF fix if space for under
* 1 device.
* Thomas Bogendoerfer : Return ENODEV for dev_open, if there
* is no device open function.
* Andi Kleen : Fix error reporting for SIOCGIFCONF
* Michael Chastain : Fix signed/unsigned for SIOCGIFCONF
* Cyrus Durgin : Cleaned for KMOD
* Adam Sulmicki : Bug Fix : Network Device Unload
* A network device unload needs to purge
* the backlog queue.
* Paul Rusty Russell : SIOCSIFNAME
* Pekka Riikonen : Netdev boot-time settings code
* Andrew Morton : Make unregister_netdevice wait
* indefinitely on dev->refcnt
* J Hadi Salim : - Backlog queue sampling
* - netif_rx() feedback
*/
#include <asm/uaccess.h>
#include <linux/bitops.h>
#include <linux/capability.h>
#include <linux/cpu.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/hash.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/mutex.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/if_ether.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/notifier.h>
#include <linux/skbuff.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <linux/rtnetlink.h>
#include <linux/stat.h>
#include <net/dst.h>
#include <net/pkt_sched.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/netpoll.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
#include <net/iw_handler.h>
#include <asm/current.h>
#include <linux/audit.h>
#include <linux/dmaengine.h>
#include <linux/err.h>
#include <linux/ctype.h>
#include <linux/if_arp.h>
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <net/ip.h>
#include <linux/ipv6.h>
#include <linux/in.h>
#include <linux/jhash.h>
#include <linux/random.h>
#include <trace/events/napi.h>
#include <trace/events/net.h>
#include <trace/events/skb.h>
#include <linux/pci.h>
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
#include <linux/static_key.h>
#include "net-sysfs.h"
/* Instead of increasing this, you should create a hash table. */
#define MAX_GRO_SKBS 8
/* This should be increased if a protocol with a bigger head is added. */
#define GRO_MAX_HEAD (MAX_HEADER + 128)
static DEFINE_SPINLOCK(ptype_lock);
static DEFINE_SPINLOCK(offload_lock);
struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
struct list_head ptype_all __read_mostly; /* Taps */
static struct list_head offload_base __read_mostly;
/*
* The @dev_base_head list is protected by @dev_base_lock and the rtnl
* semaphore.
*
* Pure readers hold dev_base_lock for reading, or rcu_read_lock()
*
* Writers must hold the rtnl semaphore while they loop through the
* dev_base_head list, and hold dev_base_lock for writing when they do the
* actual updates. This allows pure readers to access the list even
* while a writer is preparing to update it.
*
* To put it another way, dev_base_lock is held for writing only to
* protect against pure readers; the rtnl semaphore provides the
* protection against other writers.
*
* See, for example usages, register_netdevice() and
* unregister_netdevice(), which must be called with the rtnl
* semaphore held.
*/
DEFINE_RWLOCK(dev_base_lock);
EXPORT_SYMBOL(dev_base_lock);
seqcount_t devnet_rename_seq;
static inline void dev_base_seq_inc(struct net *net)
{
while (++net->dev_base_seq == 0);
}
static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
{
unsigned int hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)];
}
static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex)
{
return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)];
}
static inline void rps_lock(struct softnet_data *sd)
{
#ifdef CONFIG_RPS
spin_lock(&sd->input_pkt_queue.lock);
#endif
}
static inline void rps_unlock(struct softnet_data *sd)
{
#ifdef CONFIG_RPS
spin_unlock(&sd->input_pkt_queue.lock);
#endif
}
/* Device list insertion */
static int list_netdevice(struct net_device *dev)
{
struct net *net = dev_net(dev);
ASSERT_RTNL();
write_lock_bh(&dev_base_lock);
list_add_tail_rcu(&dev->dev_list, &net->dev_base_head);
hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
hlist_add_head_rcu(&dev->index_hlist,
dev_index_hash(net, dev->ifindex));
write_unlock_bh(&dev_base_lock);
dev_base_seq_inc(net);
return 0;
}
/* Device list removal
* caller must respect a RCU grace period before freeing/reusing dev
*/
static void unlist_netdevice(struct net_device *dev)
{
ASSERT_RTNL();
/* Unlink dev from the device chain */
write_lock_bh(&dev_base_lock);
list_del_rcu(&dev->dev_list);
hlist_del_rcu(&dev->name_hlist);
hlist_del_rcu(&dev->index_hlist);
write_unlock_bh(&dev_base_lock);
dev_base_seq_inc(dev_net(dev));
}
/*
* Our notifier list
*/
static RAW_NOTIFIER_HEAD(netdev_chain);
/*
* Device drivers call our routines to queue packets here. We empty the
* queue in the local softnet handler.
*/
DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
EXPORT_PER_CPU_SYMBOL(softnet_data);
#ifdef CONFIG_LOCKDEP
/*
* register_netdevice() inits txq->_xmit_lock and sets lockdep class
* according to dev->type
*/
static const unsigned short netdev_lock_type[] =
{ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25,
ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET,
ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM,
ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP,
ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD,
ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25,
ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP,
ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD,
ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI,
ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE,
ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,
ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM,
ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE,
ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE};
static const char *const netdev_lock_name[] =
{"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
"_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",
"_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",
"_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP",
"_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD",
"_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25",
"_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP",
"_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD",
"_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI",
"_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",
"_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
"_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
"_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM",
"_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE",
"_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"};
static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];
static inline unsigned short netdev_lock_pos(unsigned short dev_type)
{
int i;
for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++)
if (netdev_lock_type[i] == dev_type)
return i;
/* the last key is used by default */
return ARRAY_SIZE(netdev_lock_type) - 1;
}
static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
unsigned short dev_type)
{
int i;
i = netdev_lock_pos(dev_type);
lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i],
netdev_lock_name[i]);
}
static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
{
int i;
i = netdev_lock_pos(dev->type);
lockdep_set_class_and_name(&dev->addr_list_lock,
&netdev_addr_lock_key[i],
netdev_lock_name[i]);
}
#else
static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
unsigned short dev_type)
{
}
static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
{
}
#endif
/*******************************************************************************
Protocol management and registration routines
*******************************************************************************/
/*
* Add a protocol ID to the list. Now that the input handler is
* smarter we can dispense with all the messy stuff that used to be
* here.
*
* BEWARE!!! Protocol handlers, mangling input packets,
* MUST BE last in hash buckets and checking protocol handlers
* MUST start from promiscuous ptype_all chain in net_bh.
* It is true now, do not change it.
* Explanation follows: if protocol handler, mangling packet, will
* be the first on list, it is not able to sense, that packet
* is cloned and should be copied-on-write, so that it will
* change it and subsequent readers will get broken packet.
* --ANK (980803)
*/
static inline struct list_head *ptype_head(const struct packet_type *pt)
{
if (pt->type == htons(ETH_P_ALL))
return &ptype_all;
else
return &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK];
}
/**
* dev_add_pack - add packet handler
* @pt: packet type declaration
*
* Add a protocol handler to the networking stack. The passed &packet_type
* is linked into kernel lists and may not be freed until it has been
* removed from the kernel lists.
*
* This call does not sleep therefore it can not
* guarantee all CPU's that are in middle of receiving packets
* will see the new packet type (until the next received packet).
*/
void dev_add_pack(struct packet_type *pt)
{
struct list_head *head = ptype_head(pt);
spin_lock(&ptype_lock);
list_add_rcu(&pt->list, head);
spin_unlock(&ptype_lock);
}
EXPORT_SYMBOL(dev_add_pack);
/**
* __dev_remove_pack - remove packet handler
* @pt: packet type declaration
*
* Remove a protocol handler that was previously added to the kernel
* protocol handlers by dev_add_pack(). The passed &packet_type is removed
* from the kernel lists and can be freed or reused once this function
* returns.
*
* The packet type might still be in use by receivers
* and must not be freed until after all the CPU's have gone
* through a quiescent state.
*/
void __dev_remove_pack(struct packet_type *pt)
{
struct list_head *head = ptype_head(pt);
struct packet_type *pt1;
spin_lock(&ptype_lock);
list_for_each_entry(pt1, head, list) {
if (pt == pt1) {
list_del_rcu(&pt->list);
goto out;
}
}
pr_warn("dev_remove_pack: %p not found\n", pt);
out:
spin_unlock(&ptype_lock);
}
EXPORT_SYMBOL(__dev_remove_pack);
/**
* dev_remove_pack - remove packet handler
* @pt: packet type declaration
*
* Remove a protocol handler that was previously added to the kernel
* protocol handlers by dev_add_pack(). The passed &packet_type is removed
* from the kernel lists and can be freed or reused once this function
* returns.
*
* This call sleeps to guarantee that no CPU is looking at the packet
* type after return.
*/
void dev_remove_pack(struct packet_type *pt)
{
__dev_remove_pack(pt);
synchronize_net();
}
EXPORT_SYMBOL(dev_remove_pack);
/**
* dev_add_offload - register offload handlers
* @po: protocol offload declaration
*
* Add protocol offload handlers to the networking stack. The passed
* &proto_offload is linked into kernel lists and may not be freed until
* it has been removed from the kernel lists.
*
* This call does not sleep therefore it can not
* guarantee all CPU's that are in middle of receiving packets
* will see the new offload handlers (until the next received packet).
*/
void dev_add_offload(struct packet_offload *po)
{
struct list_head *head = &offload_base;
spin_lock(&offload_lock);
list_add_rcu(&po->list, head);
spin_unlock(&offload_lock);
}
EXPORT_SYMBOL(dev_add_offload);
/**
* __dev_remove_offload - remove offload handler
* @po: packet offload declaration
*
* Remove a protocol offload handler that was previously added to the
* kernel offload handlers by dev_add_offload(). The passed &offload_type
* is removed from the kernel lists and can be freed or reused once this
* function returns.
*
* The packet type might still be in use by receivers
* and must not be freed until after all the CPU's have gone
* through a quiescent state.
*/
void __dev_remove_offload(struct packet_offload *po)
{
struct list_head *head = &offload_base;
struct packet_offload *po1;
spin_lock(&offload_lock);
list_for_each_entry(po1, head, list) {
if (po == po1) {
list_del_rcu(&po->list);
goto out;
}
}
pr_warn("dev_remove_offload: %p not found\n", po);
out:
spin_unlock(&offload_lock);
}
EXPORT_SYMBOL(__dev_remove_offload);
/**
* dev_remove_offload - remove packet offload handler
* @po: packet offload declaration
*
* Remove a packet offload handler that was previously added to the kernel
* offload handlers by dev_add_offload(). The passed &offload_type is
* removed from the kernel lists and can be freed or reused once this
* function returns.
*
* This call sleeps to guarantee that no CPU is looking at the packet
* type after return.
*/
void dev_remove_offload(struct packet_offload *po)
{
__dev_remove_offload(po);
synchronize_net();
}
EXPORT_SYMBOL(dev_remove_offload);
/******************************************************************************
Device Boot-time Settings Routines
*******************************************************************************/
/* Boot time configuration table */
static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX];
/**
* netdev_boot_setup_add - add new setup entry
* @name: name of the device
* @map: configured settings for the device
*
* Adds new setup entry to the dev_boot_setup list. The function
* returns 0 on error and 1 on success. This is a generic routine to
* all netdevices.
*/
static int netdev_boot_setup_add(char *name, struct ifmap *map)
{
struct netdev_boot_setup *s;
int i;
s = dev_boot_setup;
for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
if (s[i].name[0] == '\0' || s[i].name[0] == ' ') {
memset(s[i].name, 0, sizeof(s[i].name));
strlcpy(s[i].name, name, IFNAMSIZ);
memcpy(&s[i].map, map, sizeof(s[i].map));
break;
}
}
return i >= NETDEV_BOOT_SETUP_MAX ? 0 : 1;
}
/**
* netdev_boot_setup_check - check boot time settings
* @dev: the netdevice
*
* Check boot time settings for the device.
* The found settings are set for the device to be used
* later in the device probing.
* Returns 0 if no settings found, 1 if they are.
*/
int netdev_boot_setup_check(struct net_device *dev)
{
struct netdev_boot_setup *s = dev_boot_setup;
int i;
for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
if (s[i].name[0] != '\0' && s[i].name[0] != ' ' &&
!strcmp(dev->name, s[i].name)) {
dev->irq = s[i].map.irq;
dev->base_addr = s[i].map.base_addr;
dev->mem_start = s[i].map.mem_start;
dev->mem_end = s[i].map.mem_end;
return 1;
}
}
return 0;
}
EXPORT_SYMBOL(netdev_boot_setup_check);
/**
* netdev_boot_base - get address from boot time settings
* @prefix: prefix for network device
* @unit: id for network device
*
* Check boot time settings for the base address of device.
* The found settings are set for the device to be used
* later in the device probing.
* Returns 0 if no settings found.
*/
unsigned long netdev_boot_base(const char *prefix, int unit)
{
const struct netdev_boot_setup *s = dev_boot_setup;
char name[IFNAMSIZ];
int i;
sprintf(name, "%s%d", prefix, unit);
/*
* If device already registered then return base of 1
* to indicate not to probe for this interface
*/
if (__dev_get_by_name(&init_net, name))
return 1;
for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++)
if (!strcmp(name, s[i].name))
return s[i].map.base_addr;
return 0;
}
/*
* Saves at boot time configured settings for any netdevice.
*/
int __init netdev_boot_setup(char *str)
{
int ints[5];
struct ifmap map;
str = get_options(str, ARRAY_SIZE(ints), ints);
if (!str || !*str)
return 0;
/* Save settings */
memset(&map, 0, sizeof(map));
if (ints[0] > 0)
map.irq = ints[1];
if (ints[0] > 1)
map.base_addr = ints[2];
if (ints[0] > 2)
map.mem_start = ints[3];
if (ints[0] > 3)
map.mem_end = ints[4];
/* Add new entry to the list */
return netdev_boot_setup_add(str, &map);
}
__setup("netdev=", netdev_boot_setup);
/*******************************************************************************
Device Interface Subroutines
*******************************************************************************/
/**
* __dev_get_by_name - find a device by its name
* @net: the applicable net namespace
* @name: name to find
*
* Find an interface by name. Must be called under RTNL semaphore
* or @dev_base_lock. If the name is found a pointer to the device
* is returned. If the name is not found then %NULL is returned. The
* reference counters are not incremented so the caller must be
* careful with locks.
*/
struct net_device *__dev_get_by_name(struct net *net, const char *name)
{
struct net_device *dev;
struct hlist_head *head = dev_name_hash(net, name);
hlist_for_each_entry(dev, head, name_hlist)
if (!strncmp(dev->name, name, IFNAMSIZ))
return dev;
return NULL;
}
EXPORT_SYMBOL(__dev_get_by_name);
/**
* dev_get_by_name_rcu - find a device by its name
* @net: the applicable net namespace
* @name: name to find
*
* Find an interface by name.
* If the name is found a pointer to the device is returned.
* If the name is not found then %NULL is returned.
* The reference counters are not incremented so the caller must be
* careful with locks. The caller must hold RCU lock.
*/
struct net_device *dev_get_by_name_rcu(struct net *net, const char *name)
{
struct net_device *dev;
struct hlist_head *head = dev_name_hash(net, name);
hlist_for_each_entry_rcu(dev, head, name_hlist)
if (!strncmp(dev->name, name, IFNAMSIZ))
return dev;
return NULL;
}
EXPORT_SYMBOL(dev_get_by_name_rcu);
/**
* dev_get_by_name - find a device by its name
* @net: the applicable net namespace
* @name: name to find
*
* Find an interface by name. This can be called from any
* context and does its own locking. The returned handle has
* the usage count incremented and the caller must use dev_put() to
* release it when it is no longer needed. %NULL is returned if no
* matching device is found.
*/
struct net_device *dev_get_by_name(struct net *net, const char *name)
{
struct net_device *dev;
rcu_read_lock();
dev = dev_get_by_name_rcu(net, name);
if (dev)
dev_hold(dev);
rcu_read_unlock();
return dev;
}
EXPORT_SYMBOL(dev_get_by_name);
/**
* __dev_get_by_index - find a device by its ifindex
* @net: the applicable net namespace
* @ifindex: index of device
*
* Search for an interface by index. Returns %NULL if the device
* is not found or a pointer to the device. The device has not
* had its reference counter increased so the caller must be careful
* about locking. The caller must hold either the RTNL semaphore
* or @dev_base_lock.
*/
struct net_device *__dev_get_by_index(struct net *net, int ifindex)
{
struct net_device *dev;
struct hlist_head *head = dev_index_hash(net, ifindex);
hlist_for_each_entry(dev, head, index_hlist)
if (dev->ifindex == ifindex)
return dev;
return NULL;
}
EXPORT_SYMBOL(__dev_get_by_index);
/**
* dev_get_by_index_rcu - find a device by its ifindex
* @net: the applicable net namespace
* @ifindex: index of device
*
* Search for an interface by index. Returns %NULL if the device
* is not found or a pointer to the device. The device has not
* had its reference counter increased so the caller must be careful
* about locking. The caller must hold RCU lock.
*/
struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex)
{
struct net_device *dev;
struct hlist_head *head = dev_index_hash(net, ifindex);
hlist_for_each_entry_rcu(dev, head, index_hlist)
if (dev->ifindex == ifindex)
return dev;
return NULL;
}
EXPORT_SYMBOL(dev_get_by_index_rcu);
/**
* dev_get_by_index - find a device by its ifindex
* @net: the applicable net namespace
* @ifindex: index of device
*
* Search for an interface by index. Returns NULL if the device
* is not found or a pointer to the device. The device returned has
* had a reference added and the pointer is safe until the user calls
* dev_put to indicate they have finished with it.
*/
struct net_device *dev_get_by_index(struct net *net, int ifindex)
{
struct net_device *dev;
rcu_read_lock();
dev = dev_get_by_index_rcu(net, ifindex);
if (dev)
dev_hold(dev);
rcu_read_unlock();
return dev;
}
EXPORT_SYMBOL(dev_get_by_index);
/**
* dev_getbyhwaddr_rcu - find a device by its hardware address
* @net: the applicable net namespace
* @type: media type of device
* @ha: hardware address
*
* Search for an interface by MAC address. Returns NULL if the device
* is not found or a pointer to the device.
* The caller must hold RCU or RTNL.
* The returned device has not had its ref count increased
* and the caller must therefore be careful about locking
*
*/
struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
const char *ha)
{
struct net_device *dev;
for_each_netdev_rcu(net, dev)
if (dev->type == type &&
!memcmp(dev->dev_addr, ha, dev->addr_len))
return dev;
return NULL;
}
EXPORT_SYMBOL(dev_getbyhwaddr_rcu);
struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type)
{
struct net_device *dev;
ASSERT_RTNL();
for_each_netdev(net, dev)
if (dev->type == type)
return dev;
return NULL;
}
EXPORT_SYMBOL(__dev_getfirstbyhwtype);
struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
{
struct net_device *dev, *ret = NULL;
rcu_read_lock();
for_each_netdev_rcu(net, dev)
if (dev->type == type) {
dev_hold(dev);
ret = dev;
break;
}
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(dev_getfirstbyhwtype);
/**
* dev_get_by_flags_rcu - find any device with given flags
* @net: the applicable net namespace
* @if_flags: IFF_* values
* @mask: bitmask of bits in if_flags to check
*
* Search for any interface with the given flags. Returns NULL if a device
* is not found or a pointer to the device. Must be called inside
* rcu_read_lock(), and result refcount is unchanged.
*/
struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags,
unsigned short mask)
{
struct net_device *dev, *ret;
ret = NULL;
for_each_netdev_rcu(net, dev) {
if (((dev->flags ^ if_flags) & mask) == 0) {
ret = dev;
break;
}
}
return ret;
}
EXPORT_SYMBOL(dev_get_by_flags_rcu);
/**
* dev_valid_name - check if name is okay for network device
* @name: name string
*
* Network device names need to be valid file names to
* to allow sysfs to work. We also disallow any kind of
* whitespace.
*/
bool dev_valid_name(const char *name)
{
if (*name == '\0')
return false;
if (strlen(name) >= IFNAMSIZ)
return false;
if (!strcmp(name, ".") || !strcmp(name, ".."))
return false;
while (*name) {
if (*name == '/' || isspace(*name))
return false;
name++;
}
return true;
}
EXPORT_SYMBOL(dev_valid_name);
/**
* __dev_alloc_name - allocate a name for a device
* @net: network namespace to allocate the device name in
* @name: name format string
* @buf: scratch buffer and result name string
*
* Passed a format string - eg "lt%d" it will try and find a suitable
* id. It scans list of devices to build up a free map, then chooses
* the first empty slot. The caller must hold the dev_base or rtnl lock
* while allocating the name and adding the device in order to avoid
* duplicates.
* Limited to bits_per_byte * page size devices (ie 32K on most platforms).
* Returns the number of the unit assigned or a negative errno code.
*/
static int __dev_alloc_name(struct net *net, const char *name, char *buf)
{
int i = 0;
const char *p;
const int max_netdevices = 8*PAGE_SIZE;
unsigned long *inuse;
struct net_device *d;
p = strnchr(name, IFNAMSIZ-1, '%');
if (p) {
/*
* Verify the string as this thing may have come from
* the user. There must be either one "%d" and no other "%"
* characters.
*/
if (p[1] != 'd' || strchr(p + 2, '%'))
return -EINVAL;
/* Use one page as a bit array of possible slots */
inuse = (unsigned long *) get_zeroed_page(GFP_ATOMIC);
if (!inuse)
return -ENOMEM;
for_each_netdev(net, d) {
if (!sscanf(d->name, name, &i))
continue;
if (i < 0 || i >= max_netdevices)
continue;
/* avoid cases where sscanf is not exact inverse of printf */
snprintf(buf, IFNAMSIZ, name, i);
if (!strncmp(buf, d->name, IFNAMSIZ))
set_bit(i, inuse);
}
i = find_first_zero_bit(inuse, max_netdevices);
free_page((unsigned long) inuse);
}
if (buf != name)
snprintf(buf, IFNAMSIZ, name, i);
if (!__dev_get_by_name(net, buf))
return i;
/* It is possible to run out of possible slots
* when the name is long and there isn't enough space left
* for the digits, or if all bits are used.
*/
return -ENFILE;
}
/**
* dev_alloc_name - allocate a name for a device
* @dev: device
* @name: name format string
*
* Passed a format string - eg "lt%d" it will try and find a suitable
* id. It scans list of devices to build up a free map, then chooses
* the first empty slot. The caller must hold the dev_base or rtnl lock
* while allocating the name and adding the device in order to avoid
* duplicates.
* Limited to bits_per_byte * page size devices (ie 32K on most platforms).
* Returns the number of the unit assigned or a negative errno code.
*/
int dev_alloc_name(struct net_device *dev, const char *name)
{
char buf[IFNAMSIZ];
struct net *net;
int ret;
BUG_ON(!dev_net(dev));
net = dev_net(dev);
ret = __dev_alloc_name(net, name, buf);
if (ret >= 0)
strlcpy(dev->name, buf, IFNAMSIZ);
return ret;
}
EXPORT_SYMBOL(dev_alloc_name);
static int dev_alloc_name_ns(struct net *net,
struct net_device *dev,
const char *name)
{
char buf[IFNAMSIZ];
int ret;
ret = __dev_alloc_name(net, name, buf);
if (ret >= 0)
strlcpy(dev->name, buf, IFNAMSIZ);
return ret;
}
static int dev_get_valid_name(struct net *net,
struct net_device *dev,
const char *name)
{
BUG_ON(!net);
if (!dev_valid_name(name))
return -EINVAL;
if (strchr(name, '%'))
return dev_alloc_name_ns(net, dev, name);
else if (__dev_get_by_name(net, name))
return -EEXIST;
else if (dev->name != name)
strlcpy(dev->name, name, IFNAMSIZ);
return 0;
}
/**
* dev_change_name - change name of a device
* @dev: device
* @newname: name (or format string) must be at least IFNAMSIZ
*
* Change name of a device, can pass format strings "eth%d".
* for wildcarding.
*/
int dev_change_name(struct net_device *dev, const char *newname)
{
char oldname[IFNAMSIZ];
int err = 0;
int ret;
struct net *net;
ASSERT_RTNL();
BUG_ON(!dev_net(dev));
net = dev_net(dev);
if (dev->flags & IFF_UP)
return -EBUSY;
write_seqcount_begin(&devnet_rename_seq);
if (strncmp(newname, dev->name, IFNAMSIZ) == 0) {
write_seqcount_end(&devnet_rename_seq);
return 0;
}
memcpy(oldname, dev->name, IFNAMSIZ);
err = dev_get_valid_name(net, dev, newname);
if (err < 0) {
write_seqcount_end(&devnet_rename_seq);
return err;
}
rollback:
ret = device_rename(&dev->dev, dev->name);
if (ret) {
memcpy(dev->name, oldname, IFNAMSIZ);
write_seqcount_end(&devnet_rename_seq);
return ret;
}
write_seqcount_end(&devnet_rename_seq);
write_lock_bh(&dev_base_lock);
hlist_del_rcu(&dev->name_hlist);
write_unlock_bh(&dev_base_lock);
synchronize_rcu();
write_lock_bh(&dev_base_lock);
hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
write_unlock_bh(&dev_base_lock);
ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev);
ret = notifier_to_errno(ret);
if (ret) {
/* err >= 0 after dev_alloc_name() or stores the first errno */
if (err >= 0) {
err = ret;
write_seqcount_begin(&devnet_rename_seq);
memcpy(dev->name, oldname, IFNAMSIZ);
goto rollback;
} else {
pr_err("%s: name change rollback failed: %d\n",
dev->name, ret);
}
}
return err;
}
/**
* dev_set_alias - change ifalias of a device
* @dev: device
* @alias: name up to IFALIASZ
* @len: limit of bytes to copy from info
*
* Set ifalias for a device,
*/
int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
{
char *new_ifalias;
ASSERT_RTNL();
if (len >= IFALIASZ)
return -EINVAL;
if (!len) {
kfree(dev->ifalias);
dev->ifalias = NULL;
return 0;
}
new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
if (!new_ifalias)
return -ENOMEM;
dev->ifalias = new_ifalias;
strlcpy(dev->ifalias, alias, len+1);
return len;
}
/**
* netdev_features_change - device changes features
* @dev: device to cause notification
*
* Called to indicate a device has changed features.
*/
void netdev_features_change(struct net_device *dev)
{
call_netdevice_notifiers(NETDEV_FEAT_CHANGE, dev);
}
EXPORT_SYMBOL(netdev_features_change);
/**
* netdev_state_change - device changes state
* @dev: device to cause notification
*
* Called to indicate a device has changed state. This function calls
* the notifier chains for netdev_chain and sends a NEWLINK message
* to the routing socket.
*/
void netdev_state_change(struct net_device *dev)
{
if (dev->flags & IFF_UP) {
call_netdevice_notifiers(NETDEV_CHANGE, dev);
rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
}
}
EXPORT_SYMBOL(netdev_state_change);
/**
* netdev_notify_peers - notify network peers about existence of @dev
* @dev: network device
*
* Generate traffic such that interested network peers are aware of
* @dev, such as by generating a gratuitous ARP. This may be used when
* a device wants to inform the rest of the network about some sort of
* reconfiguration such as a failover event or virtual machine
* migration.
*/
void netdev_notify_peers(struct net_device *dev)
{
rtnl_lock();
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev);
rtnl_unlock();
}
EXPORT_SYMBOL(netdev_notify_peers);
static int __dev_open(struct net_device *dev)
{
const struct net_device_ops *ops = dev->netdev_ops;
int ret;
ASSERT_RTNL();
if (!netif_device_present(dev))
return -ENODEV;
/* Block netpoll from trying to do any rx path servicing.
* If we don't do this there is a chance ndo_poll_controller
* or ndo_poll may be running while we open the device
*/
ret = netpoll_rx_disable(dev);
if (ret)
return ret;
ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
ret = notifier_to_errno(ret);
if (ret)
return ret;
set_bit(__LINK_STATE_START, &dev->state);
if (ops->ndo_validate_addr)
ret = ops->ndo_validate_addr(dev);
if (!ret && ops->ndo_open)
ret = ops->ndo_open(dev);
netpoll_rx_enable(dev);
if (ret)
clear_bit(__LINK_STATE_START, &dev->state);
else {
dev->flags |= IFF_UP;
net_dmaengine_get();
dev_set_rx_mode(dev);
dev_activate(dev);
add_device_randomness(dev->dev_addr, dev->addr_len);
}
return ret;
}
/**
* dev_open - prepare an interface for use.
* @dev: device to open
*
* Takes a device from down to up state. The device's private open
* function is invoked and then the multicast lists are loaded. Finally
* the device is moved into the up state and a %NETDEV_UP message is
* sent to the netdev notifier chain.
*
* Calling this function on an active interface is a nop. On a failure
* a negative errno code is returned.
*/
int dev_open(struct net_device *dev)
{
int ret;
if (dev->flags & IFF_UP)
return 0;
ret = __dev_open(dev);
if (ret < 0)
return ret;
rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING);
call_netdevice_notifiers(NETDEV_UP, dev);
return ret;
}
EXPORT_SYMBOL(dev_open);
static int __dev_close_many(struct list_head *head)
{
struct net_device *dev;
ASSERT_RTNL();
might_sleep();
list_for_each_entry(dev, head, unreg_list) {
call_netdevice_notifiers(NETDEV_GOING_DOWN, dev);
clear_bit(__LINK_STATE_START, &dev->state);
/* Synchronize to scheduled poll. We cannot touch poll list, it
* can be even on different cpu. So just clear netif_running().
*
* dev->stop() will invoke napi_disable() on all of it's
* napi_struct instances on this device.
*/
smp_mb__after_clear_bit(); /* Commit netif_running(). */
}
dev_deactivate_many(head);
list_for_each_entry(dev, head, unreg_list) {
const struct net_device_ops *ops = dev->netdev_ops;
/*
* Call the device specific close. This cannot fail.
* Only if device is UP
*
* We allow it to be called even after a DETACH hot-plug
* event.
*/
if (ops->ndo_stop)
ops->ndo_stop(dev);
dev->flags &= ~IFF_UP;
net_dmaengine_put();
}
return 0;
}
static int __dev_close(struct net_device *dev)
{
int retval;
LIST_HEAD(single);
/* Temporarily disable netpoll until the interface is down */
retval = netpoll_rx_disable(dev);
if (retval)
return retval;
list_add(&dev->unreg_list, &single);
retval = __dev_close_many(&single);
list_del(&single);
netpoll_rx_enable(dev);
return retval;
}
static int dev_close_many(struct list_head *head)
{
struct net_device *dev, *tmp;
LIST_HEAD(tmp_list);
list_for_each_entry_safe(dev, tmp, head, unreg_list)
if (!(dev->flags & IFF_UP))
list_move(&dev->unreg_list, &tmp_list);
__dev_close_many(head);
list_for_each_entry(dev, head, unreg_list) {
rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING);
call_netdevice_notifiers(NETDEV_DOWN, dev);
}
/* rollback_registered_many needs the complete original list */
list_splice(&tmp_list, head);
return 0;
}
/**
* dev_close - shutdown an interface.
* @dev: device to shutdown
*
* This function moves an active device into down state. A
* %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device
* is then deactivated and finally a %NETDEV_DOWN is sent to the notifier
* chain.
*/
int dev_close(struct net_device *dev)
{
int ret = 0;
if (dev->flags & IFF_UP) {
LIST_HEAD(single);
/* Block netpoll rx while the interface is going down */
ret = netpoll_rx_disable(dev);
if (ret)
return ret;
list_add(&dev->unreg_list, &single);
dev_close_many(&single);
list_del(&single);
netpoll_rx_enable(dev);
}
return ret;
}
EXPORT_SYMBOL(dev_close);
/**
* dev_disable_lro - disable Large Receive Offload on a device
* @dev: device
*
* Disable Large Receive Offload (LRO) on a net device. Must be
* called under RTNL. This is needed if received packets may be
* forwarded to another interface.
*/
void dev_disable_lro(struct net_device *dev)
{
/*
* If we're trying to disable lro on a vlan device
* use the underlying physical device instead
*/
if (is_vlan_dev(dev))
dev = vlan_dev_real_dev(dev);
dev->wanted_features &= ~NETIF_F_LRO;
netdev_update_features(dev);
if (unlikely(dev->features & NETIF_F_LRO))
netdev_WARN(dev, "failed to disable LRO!\n");
}
EXPORT_SYMBOL(dev_disable_lro);
static int dev_boot_phase = 1;
/**
* register_netdevice_notifier - register a network notifier block
* @nb: notifier
*
* Register a notifier to be called when network device events occur.
* The notifier passed is linked into the kernel structures and must
* not be reused until it has been unregistered. A negative errno code
* is returned on a failure.
*
* When registered all registration and up events are replayed
* to the new notifier to allow device to have a race free
* view of the network device list.
*/
int register_netdevice_notifier(struct notifier_block *nb)
{
struct net_device *dev;
struct net_device *last;
struct net *net;
int err;
rtnl_lock();
err = raw_notifier_chain_register(&netdev_chain, nb);
if (err)
goto unlock;
if (dev_boot_phase)
goto unlock;
for_each_net(net) {
for_each_netdev(net, dev) {
err = nb->notifier_call(nb, NETDEV_REGISTER, dev);
err = notifier_to_errno(err);
if (err)
goto rollback;
if (!(dev->flags & IFF_UP))
continue;
nb->notifier_call(nb, NETDEV_UP, dev);
}
}
unlock:
rtnl_unlock();
return err;
rollback:
last = dev;
for_each_net(net) {
for_each_netdev(net, dev) {
if (dev == last)
goto outroll;
if (dev->flags & IFF_UP) {
nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
nb->notifier_call(nb, NETDEV_DOWN, dev);
}
nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
}
}
outroll:
raw_notifier_chain_unregister(&netdev_chain, nb);
goto unlock;
}
EXPORT_SYMBOL(register_netdevice_notifier);
/**
* unregister_netdevice_notifier - unregister a network notifier block
* @nb: notifier
*
* Unregister a notifier previously registered by
* register_netdevice_notifier(). The notifier is unlinked into the
* kernel structures and may then be reused. A negative errno code
* is returned on a failure.
*
* After unregistering unregister and down device events are synthesized
* for all devices on the device list to the removed notifier to remove
* the need for special case cleanup code.
*/
int unregister_netdevice_notifier(struct notifier_block *nb)
{
struct net_device *dev;
struct net *net;
int err;
rtnl_lock();
err = raw_notifier_chain_unregister(&netdev_chain, nb);
if (err)
goto unlock;
for_each_net(net) {
for_each_netdev(net, dev) {
if (dev->flags & IFF_UP) {
nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
nb->notifier_call(nb, NETDEV_DOWN, dev);
}
nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
}
}
unlock:
rtnl_unlock();
return err;
}
EXPORT_SYMBOL(unregister_netdevice_notifier);
/**
* call_netdevice_notifiers - call all network notifier blocks
* @val: value passed unmodified to notifier function
* @dev: net_device pointer passed unmodified to notifier function
*
* Call all network notifier blocks. Parameters and return value
* are as for raw_notifier_call_chain().
*/
int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
{
ASSERT_RTNL();
return raw_notifier_call_chain(&netdev_chain, val, dev);
}
EXPORT_SYMBOL(call_netdevice_notifiers);
static struct static_key netstamp_needed __read_mostly;
#ifdef HAVE_JUMP_LABEL
/* We are not allowed to call static_key_slow_dec() from irq context
* If net_disable_timestamp() is called from irq context, defer the
* static_key_slow_dec() calls.
*/
static atomic_t netstamp_needed_deferred;
#endif
void net_enable_timestamp(void)
{
#ifdef HAVE_JUMP_LABEL
int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
if (deferred) {
while (--deferred)
static_key_slow_dec(&netstamp_needed);
return;
}
#endif
static_key_slow_inc(&netstamp_needed);
}
EXPORT_SYMBOL(net_enable_timestamp);
void net_disable_timestamp(void)
{
#ifdef HAVE_JUMP_LABEL
if (in_interrupt()) {
atomic_inc(&netstamp_needed_deferred);
return;
}
#endif
static_key_slow_dec(&netstamp_needed);
}
EXPORT_SYMBOL(net_disable_timestamp);
static inline void net_timestamp_set(struct sk_buff *skb)
{
skb->tstamp.tv64 = 0;
if (static_key_false(&netstamp_needed))
__net_timestamp(skb);
}
#define net_timestamp_check(COND, SKB) \
if (static_key_false(&netstamp_needed)) { \
if ((COND) && !(SKB)->tstamp.tv64) \
__net_timestamp(SKB); \
} \
static inline bool is_skb_forwardable(struct net_device *dev,
struct sk_buff *skb)
{
unsigned int len;
if (!(dev->flags & IFF_UP))
return false;
len = dev->mtu + dev->hard_header_len + VLAN_HLEN;
if (skb->len <= len)
return true;
/* if TSO is enabled, we don't care about the length as the packet
* could be forwarded without being segmented before
*/
if (skb_is_gso(skb))
return true;
return false;
}
/**
* dev_forward_skb - loopback an skb to another netif
*
* @dev: destination network device
* @skb: buffer to forward
*
* return values:
* NET_RX_SUCCESS (no congestion)
* NET_RX_DROP (packet was dropped, but freed)
*
* dev_forward_skb can be used for injecting an skb from the
* start_xmit function of one device into the receive queue
* of another device.
*
* The receiving device may be in another namespace, so
* we have to clear all information in the skb that could
* impact namespace isolation.
*/
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
{
if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
if (skb_copy_ubufs(skb, GFP_ATOMIC)) {
atomic_long_inc(&dev->rx_dropped);
kfree_skb(skb);
return NET_RX_DROP;
}
}
skb_orphan(skb);
if (unlikely(!is_skb_forwardable(dev, skb))) {
atomic_long_inc(&dev->rx_dropped);
kfree_skb(skb);
return NET_RX_DROP;
}
skb->skb_iif = 0;
skb->dev = dev;
skb_dst_drop(skb);
skb->tstamp.tv64 = 0;
skb->pkt_type = PACKET_HOST;
skb->protocol = eth_type_trans(skb, dev);
skb->mark = 0;
secpath_reset(skb);
nf_reset(skb);
nf_reset_trace(skb);
return netif_rx(skb);
}
EXPORT_SYMBOL_GPL(dev_forward_skb);
static inline int deliver_skb(struct sk_buff *skb,
struct packet_type *pt_prev,
struct net_device *orig_dev)
{
if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
return -ENOMEM;
atomic_inc(&skb->users);
return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}
static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb)
{
if (!ptype->af_packet_priv || !skb->sk)
return false;
if (ptype->id_match)
return ptype->id_match(ptype, skb->sk);
else if ((struct sock *)ptype->af_packet_priv == skb->sk)
return true;
return false;
}
/*
* Support routine. Sends outgoing frames to any network
* taps currently in use.
*/
static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
{
struct packet_type *ptype;
struct sk_buff *skb2 = NULL;
struct packet_type *pt_prev = NULL;
rcu_read_lock();
list_for_each_entry_rcu(ptype, &ptype_all, list) {
/* Never send packets back to the socket
* they originated from - MvS (miquels@drinkel.ow.org)
*/
if ((ptype->dev == dev || !ptype->dev) &&
(!skb_loop_sk(ptype, skb))) {
if (pt_prev) {
deliver_skb(skb2, pt_prev, skb->dev);
pt_prev = ptype;
continue;
}
skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
break;
net_timestamp_set(skb2);
/* skb->nh should be correctly
set by sender, so that the second statement is
just protection against buggy protocols.
*/
skb_reset_mac_header(skb2);
if (skb_network_header(skb2) < skb2->data ||
skb2->network_header > skb2->tail) {
net_crit_ratelimited("protocol %04x is buggy, dev %s\n",
ntohs(skb2->protocol),
dev->name);
skb_reset_network_header(skb2);
}
skb2->transport_header = skb2->network_header;
skb2->pkt_type = PACKET_OUTGOING;
pt_prev = ptype;
}
}
if (pt_prev)
pt_prev->func(skb2, skb->dev, pt_prev, skb->dev);
rcu_read_unlock();
}
/**
* netif_setup_tc - Handle tc mappings on real_num_tx_queues change
* @dev: Network device
* @txq: number of queues available
*
* If real_num_tx_queues is changed the tc mappings may no longer be
* valid. To resolve this verify the tc mapping remains valid and if
* not NULL the mapping. With no priorities mapping to this
* offset/count pair it will no longer be used. In the worst case TC0
* is invalid nothing can be done so disable priority mappings. If is
* expected that drivers will fix this mapping if they can before
* calling netif_set_real_num_tx_queues.
*/
static void netif_setup_tc(struct net_device *dev, unsigned int txq)
{
int i;
struct netdev_tc_txq *tc = &dev->tc_to_txq[0];
/* If TC0 is invalidated disable TC mapping */
if (tc->offset + tc->count > txq) {
pr_warn("Number of in use tx queues changed invalidating tc mappings. Priority traffic classification disabled!\n");
dev->num_tc = 0;
return;
}
/* Invalidated prio to tc mappings set to TC0 */
for (i = 1; i < TC_BITMASK + 1; i++) {
int q = netdev_get_prio_tc_map(dev, i);
tc = &dev->tc_to_txq[q];
if (tc->offset + tc->count > txq) {
pr_warn("Number of in use tx queues changed. Priority %i to tc mapping %i is no longer valid. Setting map to 0\n",
i, q);
netdev_set_prio_tc_map(dev, i, 0);
}
}
}
#ifdef CONFIG_XPS
static DEFINE_MUTEX(xps_map_mutex);
#define xmap_dereference(P) \
rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex))
static struct xps_map *remove_xps_queue(struct xps_dev_maps *dev_maps,
int cpu, u16 index)
{
struct xps_map *map = NULL;
int pos;
if (dev_maps)
map = xmap_dereference(dev_maps->cpu_map[cpu]);
for (pos = 0; map && pos < map->len; pos++) {
if (map->queues[pos] == index) {
if (map->len > 1) {
map->queues[pos] = map->queues[--map->len];
} else {
RCU_INIT_POINTER(dev_maps->cpu_map[cpu], NULL);
kfree_rcu(map, rcu);
map = NULL;
}
break;
}
}
return map;
}
static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index)
{
struct xps_dev_maps *dev_maps;
int cpu, i;
bool active = false;
mutex_lock(&xps_map_mutex);
dev_maps = xmap_dereference(dev->xps_maps);
if (!dev_maps)
goto out_no_maps;
for_each_possible_cpu(cpu) {
for (i = index; i < dev->num_tx_queues; i++) {
if (!remove_xps_queue(dev_maps, cpu, i))
break;
}
if (i == dev->num_tx_queues)
active = true;
}
if (!active) {
RCU_INIT_POINTER(dev->xps_maps, NULL);
kfree_rcu(dev_maps, rcu);
}
for (i = index; i < dev->num_tx_queues; i++)
netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i),
NUMA_NO_NODE);
out_no_maps:
mutex_unlock(&xps_map_mutex);
}
static struct xps_map *expand_xps_map(struct xps_map *map,
int cpu, u16 index)
{
struct xps_map *new_map;
int alloc_len = XPS_MIN_MAP_ALLOC;
int i, pos;
for (pos = 0; map && pos < map->len; pos++) {
if (map->queues[pos] != index)
continue;
return map;
}
/* Need to add queue to this CPU's existing map */
if (map) {
if (pos < map->alloc_len)
return map;
alloc_len = map->alloc_len * 2;
}
/* Need to allocate new map to store queue on this CPU's map */
new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL,
cpu_to_node(cpu));
if (!new_map)
return NULL;
for (i = 0; i < pos; i++)
new_map->queues[i] = map->queues[i];
new_map->alloc_len = alloc_len;
new_map->len = pos;
return new_map;
}
int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, u16 index)
{
struct xps_dev_maps *dev_maps, *new_dev_maps = NULL;
struct xps_map *map, *new_map;
int maps_sz = max_t(unsigned int, XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES);
int cpu, numa_node_id = -2;
bool active = false;
mutex_lock(&xps_map_mutex);
dev_maps = xmap_dereference(dev->xps_maps);
/* allocate memory for queue storage */
for_each_online_cpu(cpu) {
if (!cpumask_test_cpu(cpu, mask))
continue;
if (!new_dev_maps)
new_dev_maps = kzalloc(maps_sz, GFP_KERNEL);
if (!new_dev_maps) {
mutex_unlock(&xps_map_mutex);
return -ENOMEM;
}
map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) :
NULL;
map = expand_xps_map(map, cpu, index);
if (!map)
goto error;
RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map);
}
if (!new_dev_maps)
goto out_no_new_maps;
for_each_possible_cpu(cpu) {
if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) {
/* add queue to CPU maps */
int pos = 0;
map = xmap_dereference(new_dev_maps->cpu_map[cpu]);
while ((pos < map->len) && (map->queues[pos] != index))
pos++;
if (pos == map->len)
map->queues[map->len++] = index;
#ifdef CONFIG_NUMA
if (numa_node_id == -2)
numa_node_id = cpu_to_node(cpu);
else if (numa_node_id != cpu_to_node(cpu))
numa_node_id = -1;
#endif
} else if (dev_maps) {
/* fill in the new device map from the old device map */
map = xmap_dereference(dev_maps->cpu_map[cpu]);
RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map);
}
}
rcu_assign_pointer(dev->xps_maps, new_dev_maps);
/* Cleanup old maps */
if (dev_maps) {
for_each_possible_cpu(cpu) {
new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]);
map = xmap_dereference(dev_maps->cpu_map[cpu]);
if (map && map != new_map)
kfree_rcu(map, rcu);
}
kfree_rcu(dev_maps, rcu);
}
dev_maps = new_dev_maps;
active = true;
out_no_new_maps:
/* update Tx queue numa node */
netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index),
(numa_node_id >= 0) ? numa_node_id :
NUMA_NO_NODE);
if (!dev_maps)
goto out_no_maps;
/* removes queue from unused CPUs */
for_each_possible_cpu(cpu) {
if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu))
continue;
if (remove_xps_queue(dev_maps, cpu, index))
active = true;
}
/* free map if not active */
if (!active) {
RCU_INIT_POINTER(dev->xps_maps, NULL);
kfree_rcu(dev_maps, rcu);
}
out_no_maps:
mutex_unlock(&xps_map_mutex);
return 0;
error:
/* remove any maps that we added */
for_each_possible_cpu(cpu) {
new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]);
map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) :
NULL;
if (new_map && new_map != map)
kfree(new_map);
}
mutex_unlock(&xps_map_mutex);
kfree(new_dev_maps);
return -ENOMEM;
}
EXPORT_SYMBOL(netif_set_xps_queue);
#endif
/*
* Routine to help set real_num_tx_queues. To avoid skbs mapped to queues
* greater then real_num_tx_queues stale skbs on the qdisc must be flushed.
*/
int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
{
int rc;
if (txq < 1 || txq > dev->num_tx_queues)
return -EINVAL;
if (dev->reg_state == NETREG_REGISTERED ||
dev->reg_state == NETREG_UNREGISTERING) {
ASSERT_RTNL();
rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues,
txq);
if (rc)
return rc;
if (dev->num_tc)
netif_setup_tc(dev, txq);
if (txq < dev->real_num_tx_queues) {
qdisc_reset_all_tx_gt(dev, txq);
#ifdef CONFIG_XPS
netif_reset_xps_queues_gt(dev, txq);
#endif
}
}
dev->real_num_tx_queues = txq;
return 0;
}
EXPORT_SYMBOL(netif_set_real_num_tx_queues);
#ifdef CONFIG_RPS
/**
* netif_set_real_num_rx_queues - set actual number of RX queues used
* @dev: Network device
* @rxq: Actual number of RX queues
*
* This must be called either with the rtnl_lock held or before
* registration of the net device. Returns 0 on success, or a
* negative error code. If called before registration, it always
* succeeds.
*/
int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq)
{
int rc;
if (rxq < 1 || rxq > dev->num_rx_queues)
return -EINVAL;
if (dev->reg_state == NETREG_REGISTERED) {
ASSERT_RTNL();
rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues,
rxq);
if (rc)
return rc;
}
dev->real_num_rx_queues = rxq;
return 0;
}
EXPORT_SYMBOL(netif_set_real_num_rx_queues);
#endif
/**
* netif_get_num_default_rss_queues - default number of RSS queues
*
* This routine should set an upper limit on the number of RSS queues
* used by default by multiqueue devices.
*/
int netif_get_num_default_rss_queues(void)
{
return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
}
EXPORT_SYMBOL(netif_get_num_default_rss_queues);
static inline void __netif_reschedule(struct Qdisc *q)
{
struct softnet_data *sd;
unsigned long flags;
local_irq_save(flags);
sd = &__get_cpu_var(softnet_data);
q->next_sched = NULL;
*sd->output_queue_tailp = q;
sd->output_queue_tailp = &q->next_sched;
raise_softirq_irqoff(NET_TX_SOFTIRQ);
local_irq_restore(flags);
}
void __netif_schedule(struct Qdisc *q)
{
if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state))
__netif_reschedule(q);
}
EXPORT_SYMBOL(__netif_schedule);
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);
}
}
EXPORT_SYMBOL(dev_kfree_skb_irq);
void dev_kfree_skb_any(struct sk_buff *skb)
{
if (in_irq() || irqs_disabled())
dev_kfree_skb_irq(skb);
else
dev_kfree_skb(skb);
}
EXPORT_SYMBOL(dev_kfree_skb_any);
/**
* netif_device_detach - mark device as removed
* @dev: network device
*
* Mark device as removed from system and therefore no longer available.
*/
void netif_device_detach(struct net_device *dev)
{
if (test_and_clear_bit(__LINK_STATE_PRESENT, &dev->state) &&
netif_running(dev)) {
netif_tx_stop_all_queues(dev);
}
}
EXPORT_SYMBOL(netif_device_detach);
/**
* netif_device_attach - mark device as attached
* @dev: network device
*
* Mark device as attached from system and restart if needed.
*/
void netif_device_attach(struct net_device *dev)
{
if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) &&
netif_running(dev)) {
netif_tx_wake_all_queues(dev);
__netdev_watchdog_up(dev);
}
}
EXPORT_SYMBOL(netif_device_attach);
static void skb_warn_bad_offload(const struct sk_buff *skb)
{
static const netdev_features_t null_features = 0;
struct net_device *dev = skb->dev;
const char *driver = "";
if (!net_ratelimit())
return;
if (dev && dev->dev.parent)
driver = dev_driver_string(dev->dev.parent);
WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d gso_size=%d "
"gso_type=%d ip_summed=%d\n",
driver, dev ? &dev->features : &null_features,
skb->sk ? &skb->sk->sk_route_caps : &null_features,
skb->len, skb->data_len, skb_shinfo(skb)->gso_size,
skb_shinfo(skb)->gso_type, skb->ip_summed);
}
/*
* Invalidate hardware checksum when packet is to be mangled, and
* complete checksum manually on outgoing path.
*/
int skb_checksum_help(struct sk_buff *skb)
{
__wsum csum;
int ret = 0, offset;
if (skb->ip_summed == CHECKSUM_COMPLETE)
goto out_set_summed;
if (unlikely(skb_shinfo(skb)->gso_size)) {
skb_warn_bad_offload(skb);
return -EINVAL;
}
/* Before computing a checksum, we should make sure no frag could
* be modified by an external entity : checksum could be wrong.
*/
if (skb_has_shared_frag(skb)) {
ret = __skb_linearize(skb);
if (ret)
goto out;
}
offset = skb_checksum_start_offset(skb);
BUG_ON(offset >= skb_headlen(skb));
csum = skb_checksum(skb, offset, skb->len - offset, 0);
offset += skb->csum_offset;
BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb));
if (skb_cloned(skb) &&
!skb_clone_writable(skb, offset + sizeof(__sum16))) {
ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
if (ret)
goto out;
}
*(__sum16 *)(skb->data + offset) = csum_fold(csum);
out_set_summed:
skb->ip_summed = CHECKSUM_NONE;
out:
return ret;
}
EXPORT_SYMBOL(skb_checksum_help);
/**
* skb_mac_gso_segment - mac layer segmentation handler.
* @skb: buffer to segment
* @features: features for the output path (see dev->features)
*/
struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
struct packet_offload *ptype;
__be16 type = skb->protocol;
int vlan_depth = ETH_HLEN;
while (type == htons(ETH_P_8021Q)) {
struct vlan_hdr *vh;
if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN)))
return ERR_PTR(-EINVAL);
vh = (struct vlan_hdr *)(skb->data + vlan_depth);
type = vh->h_vlan_encapsulated_proto;
vlan_depth += VLAN_HLEN;
}
__skb_pull(skb, skb->mac_len);
rcu_read_lock();
list_for_each_entry_rcu(ptype, &offload_base, list) {
if (ptype->type == type && ptype->callbacks.gso_segment) {
if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
int err;
err = ptype->callbacks.gso_send_check(skb);
segs = ERR_PTR(err);
if (err || skb_gso_ok(skb, features))
break;
__skb_push(skb, (skb->data -
skb_network_header(skb)));
}
segs = ptype->callbacks.gso_segment(skb, features);
break;
}
}
rcu_read_unlock();
__skb_push(skb, skb->data - skb_mac_header(skb));
return segs;
}
EXPORT_SYMBOL(skb_mac_gso_segment);
/* openvswitch calls this on rx path, so we need a different check.
*/
static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
{
if (tx_path)
return skb->ip_summed != CHECKSUM_PARTIAL;
else
return skb->ip_summed == CHECKSUM_NONE;
}
/**
* __skb_gso_segment - Perform segmentation on skb.
* @skb: buffer to segment
* @features: features for the output path (see dev->features)
* @tx_path: whether it is called in TX path
*
* This function segments the given skb and returns a list of segments.
*
* It may return NULL if the skb requires no segmentation. This is
* only possible when GSO is used for verifying header integrity.
*/
struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
netdev_features_t features, bool tx_path)
{
if (unlikely(skb_needs_check(skb, tx_path))) {
int err;
skb_warn_bad_offload(skb);
if (skb_header_cloned(skb) &&
(err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
return ERR_PTR(err);
}
SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb);
skb_reset_mac_header(skb);
skb_reset_mac_len(skb);
return skb_mac_gso_segment(skb, features);
}
EXPORT_SYMBOL(__skb_gso_segment);
/* Take action when hardware reception checksum errors are detected. */
#ifdef CONFIG_BUG
void netdev_rx_csum_fault(struct net_device *dev)
{
if (net_ratelimit()) {
pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>");
dump_stack();
}
}
EXPORT_SYMBOL(netdev_rx_csum_fault);
#endif
/* Actually, we should eliminate this check as soon as we know, that:
* 1. IOMMU is present and allows to map all the memory.
* 2. No high memory really exists on this machine.
*/
static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_HIGHMEM
int i;
if (!(dev->features & NETIF_F_HIGHDMA)) {
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
if (PageHighMem(skb_frag_page(frag)))
return 1;
}
}
if (PCI_DMA_BUS_IS_PHYS) {
struct device *pdev = dev->dev.parent;
if (!pdev)
return 0;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
dma_addr_t addr = page_to_phys(skb_frag_page(frag));
if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask)
return 1;
}
}
#endif
return 0;
}
struct dev_gso_cb {
void (*destructor)(struct sk_buff *skb);
};
#define DEV_GSO_CB(skb) ((struct dev_gso_cb *)(skb)->cb)
static void dev_gso_skb_destructor(struct sk_buff *skb)
{
struct dev_gso_cb *cb;
do {
struct sk_buff *nskb = skb->next;
skb->next = nskb->next;
nskb->next = NULL;
kfree_skb(nskb);
} while (skb->next);
cb = DEV_GSO_CB(skb);
if (cb->destructor)
cb->destructor(skb);
}
/**
* dev_gso_segment - Perform emulated hardware segmentation on skb.
* @skb: buffer to segment
* @features: device features as applicable to this skb
*
* This function segments the given skb and stores the list of segments
* in skb->next.
*/
static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
{
struct sk_buff *segs;
segs = skb_gso_segment(skb, features);
/* Verifying header integrity only. */
if (!segs)
return 0;
if (IS_ERR(segs))
return PTR_ERR(segs);
skb->next = segs;
DEV_GSO_CB(skb)->destructor = skb->destructor;
skb->destructor = dev_gso_skb_destructor;
return 0;
}
static bool can_checksum_protocol(netdev_features_t features, __be16 protocol)
{
return ((features & NETIF_F_GEN_CSUM) ||
((features & NETIF_F_V4_CSUM) &&
protocol == htons(ETH_P_IP)) ||
((features & NETIF_F_V6_CSUM) &&
protocol == htons(ETH_P_IPV6)) ||
((features & NETIF_F_FCOE_CRC) &&
protocol == htons(ETH_P_FCOE)));
}
static netdev_features_t harmonize_features(struct sk_buff *skb,
__be16 protocol, netdev_features_t features)
{
if (skb->ip_summed != CHECKSUM_NONE &&
!can_checksum_protocol(features, protocol)) {
features &= ~NETIF_F_ALL_CSUM;
features &= ~NETIF_F_SG;
} else if (illegal_highdma(skb->dev, skb)) {
features &= ~NETIF_F_SG;
}
return features;
}
netdev_features_t netif_skb_features(struct sk_buff *skb)
{
__be16 protocol = skb->protocol;
netdev_features_t features = skb->dev->features;
if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
features &= ~NETIF_F_GSO_MASK;
if (protocol == htons(ETH_P_8021Q)) {
struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
protocol = veh->h_vlan_encapsulated_proto;
} else if (!vlan_tx_tag_present(skb)) {
return harmonize_features(skb, protocol, features);
}
features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_TX);
if (protocol != htons(ETH_P_8021Q)) {
return harmonize_features(skb, protocol, features);
} else {
features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST |
NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_TX;
return harmonize_features(skb, protocol, features);
}
}
EXPORT_SYMBOL(netif_skb_features);
/*
* Returns true if either:
* 1. skb has frag_list and the device doesn't support FRAGLIST, or
* 2. skb is fragmented and the device does not support SG.
*/
static inline int skb_needs_linearize(struct sk_buff *skb,
int features)
{
return skb_is_nonlinear(skb) &&
((skb_has_frag_list(skb) &&
!(features & NETIF_F_FRAGLIST)) ||
(skb_shinfo(skb)->nr_frags &&
!(features & NETIF_F_SG)));
}
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq)
{
const struct net_device_ops *ops = dev->netdev_ops;
int rc = NETDEV_TX_OK;
unsigned int skb_len;
if (likely(!skb->next)) {
netdev_features_t features;
/*
* If device doesn't need skb->dst, release it right now while
* its hot in this cpu cache
*/
if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
skb_dst_drop(skb);
features = netif_skb_features(skb);
if (vlan_tx_tag_present(skb) &&
!(features & NETIF_F_HW_VLAN_TX)) {
skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb));
if (unlikely(!skb))
goto out;
skb->vlan_tci = 0;
}
/* If encapsulation offload request, verify we are testing
* hardware encapsulation features instead of standard
* features for the netdev
*/
if (skb->encapsulation)
features &= dev->hw_enc_features;
if (netif_needs_gso(skb, features)) {
if (unlikely(dev_gso_segment(skb, features)))
goto out_kfree_skb;
if (skb->next)
goto gso;
} else {
if (skb_needs_linearize(skb, features) &&
__skb_linearize(skb))
goto out_kfree_skb;
/* If packet is not checksummed and device does not
* support checksumming for this protocol, complete
* checksumming here.
*/
if (skb->ip_summed == CHECKSUM_PARTIAL) {
if (skb->encapsulation)
skb_set_inner_transport_header(skb,
skb_checksum_start_offset(skb));
else
skb_set_transport_header(skb,
skb_checksum_start_offset(skb));
if (!(features & NETIF_F_ALL_CSUM) &&
skb_checksum_help(skb))
goto out_kfree_skb;
}
}
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(skb, dev);
skb_len = skb->len;
rc = ops->ndo_start_xmit(skb, dev);
trace_net_dev_xmit(skb, rc, dev, skb_len);
if (rc == NETDEV_TX_OK)
txq_trans_update(txq);
return rc;
}
gso:
do {
struct sk_buff *nskb = skb->next;
skb->next = nskb->next;
nskb->next = NULL;
/*
* If device doesn't need nskb->dst, release it right now while
* its hot in this cpu cache
*/
if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
skb_dst_drop(nskb);
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(nskb, dev);
skb_len = nskb->len;
rc = ops->ndo_start_xmit(nskb, dev);
trace_net_dev_xmit(nskb, rc, dev, skb_len);
if (unlikely(rc != NETDEV_TX_OK)) {
if (rc & ~NETDEV_TX_MASK)
goto out_kfree_gso_skb;
nskb->next = skb->next;
skb->next = nskb;
return rc;
}
txq_trans_update(txq);
if (unlikely(netif_xmit_stopped(txq) && skb->next))
return NETDEV_TX_BUSY;
} while (skb->next);
out_kfree_gso_skb:
if (likely(skb->next == NULL))
skb->destructor = DEV_GSO_CB(skb)->destructor;
out_kfree_skb:
kfree_skb(skb);
out:
return rc;
}
static void qdisc_pkt_len_init(struct sk_buff *skb)
{
const struct skb_shared_info *shinfo = skb_shinfo(skb);
qdisc_skb_cb(skb)->pkt_len = skb->len;
/* To get more precise estimation of bytes sent on wire,
* we add to pkt_len the headers size of all segments
*/
if (shinfo->gso_size) {
unsigned int hdr_len;
/* mac layer + network layer */
hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
/* + transport layer */
if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
hdr_len += tcp_hdrlen(skb);
else
hdr_len += sizeof(struct udphdr);
qdisc_skb_cb(skb)->pkt_len += (shinfo->gso_segs - 1) * hdr_len;
}
}
static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
struct net_device *dev,
struct netdev_queue *txq)
{
spinlock_t *root_lock = qdisc_lock(q);
bool contended;
int rc;
qdisc_pkt_len_init(skb);
qdisc_calculate_pkt_len(skb, q);
/*
* Heuristic to force contended enqueues to serialize on a
* separate lock before trying to get qdisc main lock.
* This permits __QDISC_STATE_RUNNING owner to get the lock more often
* and dequeue packets faster.
*/
contended = qdisc_is_running(q);
if (unlikely(contended))
spin_lock(&q->busylock);
spin_lock(root_lock);
if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
kfree_skb(skb);
rc = NET_XMIT_DROP;
} else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) &&
qdisc_run_begin(q)) {
/*
* This is a work-conserving queue; there are no old skbs
* waiting to be sent out; and the qdisc is not running -
* xmit the skb directly.
*/
if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE))
skb_dst_force(skb);
qdisc_bstats_update(q, skb);
if (sch_direct_xmit(skb, q, dev, txq, root_lock)) {
if (unlikely(contended)) {
spin_unlock(&q->busylock);
contended = false;
}
__qdisc_run(q);
} else
qdisc_run_end(q);
rc = NET_XMIT_SUCCESS;
} else {
skb_dst_force(skb);
rc = q->enqueue(skb, q) & NET_XMIT_MASK;
if (qdisc_run_begin(q)) {
if (unlikely(contended)) {
spin_unlock(&q->busylock);
contended = false;
}
__qdisc_run(q);
}
}
spin_unlock(root_lock);
if (unlikely(contended))
spin_unlock(&q->busylock);
return rc;
}
#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
static void skb_update_prio(struct sk_buff *skb)
{
struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap);
if (!skb->priority && skb->sk && map) {
unsigned int prioidx = skb->sk->sk_cgrp_prioidx;
if (prioidx < map->priomap_len)
skb->priority = map->priomap[prioidx];
}
}
#else
#define skb_update_prio(skb)
#endif
static DEFINE_PER_CPU(int, xmit_recursion);
#define RECURSION_LIMIT 10
/**
* dev_loopback_xmit - loop back @skb
* @skb: buffer to transmit
*/
int dev_loopback_xmit(struct sk_buff *skb)
{
skb_reset_mac_header(skb);
__skb_pull(skb, skb_network_offset(skb));
skb->pkt_type = PACKET_LOOPBACK;
skb->ip_summed = CHECKSUM_UNNECESSARY;
WARN_ON(!skb_dst(skb));
skb_dst_force(skb);
netif_rx_ni(skb);
return 0;
}
EXPORT_SYMBOL(dev_loopback_xmit);
/**
* dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
*
* Queue a buffer for transmission to a network device. The caller must
* have set the device and priority and built the buffer before calling
* this function. The function can be called from an interrupt.
*
* A negative errno code is returned on a failure. A success does not
* guarantee the frame will be transmitted as it may be dropped due
* to congestion or traffic shaping.
*
* -----------------------------------------------------------------------------------
* I notice this method can also return errors from the queue disciplines,
* including NET_XMIT_DROP, which is a positive value. So, errors can also
* be positive.
*
* Regardless of the return value, the skb is consumed, so it is currently
* difficult to retry a send to this method. (You can bump the ref count
* before sending to hold a reference for retry if you are careful.)
*
* When calling this method, interrupts MUST be enabled. This is because
* the BH enable code must have IRQs enabled so that it will not deadlock.
* --BLG
*/
int dev_queue_xmit(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct netdev_queue *txq;
struct Qdisc *q;
int rc = -ENOMEM;
skb_reset_mac_header(skb);
/* Disable soft irqs for various locks below. Also
* stops preemption for RCU.
*/
rcu_read_lock_bh();
skb_update_prio(skb);
txq = netdev_pick_tx(dev, skb);
q = rcu_dereference_bh(txq->qdisc);
#ifdef CONFIG_NET_CLS_ACT
skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS);
#endif
trace_net_dev_queue(skb);
if (q->enqueue) {
rc = __dev_xmit_skb(skb, q, dev, txq);
goto out;
}
/* The device has no queue. Common case for software devices:
loopback, all the sorts of tunnels...
Really, it is unlikely that netif_tx_lock protection is necessary
here. (f.e. loopback and IP tunnels are clean ignoring statistics
counters.)
However, it is possible, that they rely on protection
made by us here.
Check this and shot the lock. It is not prone from deadlocks.
Either shot noqueue qdisc, it is even simpler 8)
*/
if (dev->flags & IFF_UP) {
int cpu = smp_processor_id(); /* ok because BHs are off */
if (txq->xmit_lock_owner != cpu) {
if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT)
goto recursion_alert;
HARD_TX_LOCK(dev, txq, cpu);
if (!netif_xmit_stopped(txq)) {
__this_cpu_inc(xmit_recursion);
rc = dev_hard_start_xmit(skb, dev, txq);
__this_cpu_dec(xmit_recursion);
if (dev_xmit_complete(rc)) {
HARD_TX_UNLOCK(dev, txq);
goto out;
}
}
HARD_TX_UNLOCK(dev, txq);
net_crit_ratelimited("Virtual device %s asks to queue packet!\n",
dev->name);
} else {
/* Recursion is detected! It is possible,
* unfortunately
*/
recursion_alert:
net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
dev->name);
}
}
rc = -ENETDOWN;
rcu_read_unlock_bh();
kfree_skb(skb);
return rc;
out:
rcu_read_unlock_bh();
return rc;
}
EXPORT_SYMBOL(dev_queue_xmit);
/*=======================================================================
Receiver routines
=======================================================================*/
int netdev_max_backlog __read_mostly = 1000;
EXPORT_SYMBOL(netdev_max_backlog);
int netdev_tstamp_prequeue __read_mostly = 1;
int netdev_budget __read_mostly = 300;
int weight_p __read_mostly = 64; /* old backlog weight */
/* Called with irq disabled */
static inline void ____napi_schedule(struct softnet_data *sd,
struct napi_struct *napi)
{
list_add_tail(&napi->poll_list, &sd->poll_list);
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
}
#ifdef CONFIG_RPS
/* One global table that all flow-based protocols share. */
struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly;
EXPORT_SYMBOL(rps_sock_flow_table);
struct static_key rps_needed __read_mostly;
static struct rps_dev_flow *
set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
struct rps_dev_flow *rflow, u16 next_cpu)
{
if (next_cpu != RPS_NO_CPU) {
#ifdef CONFIG_RFS_ACCEL
struct netdev_rx_queue *rxqueue;
struct rps_dev_flow_table *flow_table;
struct rps_dev_flow *old_rflow;
u32 flow_id;
u16 rxq_index;
int rc;
/* Should we steer this flow to a different hardware queue? */
if (!skb_rx_queue_recorded(skb) || !dev->rx_cpu_rmap ||
!(dev->features & NETIF_F_NTUPLE))
goto out;
rxq_index = cpu_rmap_lookup_index(dev->rx_cpu_rmap, next_cpu);
if (rxq_index == skb_get_rx_queue(skb))
goto out;
rxqueue = dev->_rx + rxq_index;
flow_table = rcu_dereference(rxqueue->rps_flow_table);
if (!flow_table)
goto out;
flow_id = skb->rxhash & flow_table->mask;
rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb,
rxq_index, flow_id);
if (rc < 0)
goto out;
old_rflow = rflow;
rflow = &flow_table->flows[flow_id];
rflow->filter = rc;
if (old_rflow->filter == rflow->filter)
old_rflow->filter = RPS_NO_FILTER;
out:
#endif
rflow->last_qtail =
per_cpu(softnet_data, next_cpu).input_queue_head;
}
rflow->cpu = next_cpu;
return rflow;
}
/*
* get_rps_cpu is called from netif_receive_skb and returns the target
* CPU from the RPS map of the receiving queue for a given skb.
* rcu_read_lock must be held on entry.
*/
static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
struct rps_dev_flow **rflowp)
{
struct netdev_rx_queue *rxqueue;
struct rps_map *map;
struct rps_dev_flow_table *flow_table;
struct rps_sock_flow_table *sock_flow_table;
int cpu = -1;
u16 tcpu;
if (skb_rx_queue_recorded(skb)) {
u16 index = skb_get_rx_queue(skb);
if (unlikely(index >= dev->real_num_rx_queues)) {
WARN_ONCE(dev->real_num_rx_queues > 1,
"%s received packet on queue %u, but number "
"of RX queues is %u\n",
dev->name, index, dev->real_num_rx_queues);
goto done;
}
rxqueue = dev->_rx + index;
} else
rxqueue = dev->_rx;
map = rcu_dereference(rxqueue->rps_map);
if (map) {
if (map->len == 1 &&
!rcu_access_pointer(rxqueue->rps_flow_table)) {
tcpu = map->cpus[0];
if (cpu_online(tcpu))
cpu = tcpu;
goto done;
}
} else if (!rcu_access_pointer(rxqueue->rps_flow_table)) {
goto done;
}
skb_reset_network_header(skb);
if (!skb_get_rxhash(skb))
goto done;
flow_table = rcu_dereference(rxqueue->rps_flow_table);
sock_flow_table = rcu_dereference(rps_sock_flow_table);
if (flow_table && sock_flow_table) {
u16 next_cpu;
struct rps_dev_flow *rflow;
rflow = &flow_table->flows[skb->rxhash & flow_table->mask];
tcpu = rflow->cpu;
next_cpu = sock_flow_table->ents[skb->rxhash &
sock_flow_table->mask];
/*
* If the desired CPU (where last recvmsg was done) is
* different from current CPU (one in the rx-queue flow
* table entry), switch if one of the following holds:
* - Current CPU is unset (equal to RPS_NO_CPU).