Skip to content

HTTPS clone URL

Subversion checkout URL

You can clone with
or
.
Download ZIP
Fetching contributors…

Cannot retrieve contributors at this time

6583 lines (5579 sloc) 163.826 kB
/*
* 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/proc_fs.h>
#include <linux/seq_file.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/kmod.h>
#include <linux/module.h>
#include <linux/netpoll.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
#include <net/wext.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/net_tstamp.h>
#include <linux/static_key.h>
#include <net/flow_keys.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)
/*
* The list of packet types we will receive (as opposed to discard)
* and the routines to invoke.
*
* Why 16. Because with 16 the only overlap we get on a hash of the
* low nibble of the protocol value is RARP/SNAP/X.25.
*
* NOTE: That is no longer true with the addition of VLAN tags. Not
* sure which should go first, but I bet it won't make much
* difference if we are running VLANs. The good news is that
* this protocol won't be in the list unless compiled in, so
* the average user (w/out VLANs) will not be adversely affected.
* --BLG
*
* 0800 IP
* 8100 802.1Q VLAN
* 0001 802.3
* 0002 AX.25
* 0004 802.2
* 8035 RARP
* 0005 SNAP
* 0805 X.25
* 0806 ARP
* 8137 IPX
* 0009 Localtalk
* 86DD IPv6
*/
#define PTYPE_HASH_SIZE (16)
#define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1)
static DEFINE_SPINLOCK(ptype_lock);
static struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
static struct list_head ptype_all __read_mostly; /* Taps */
/*
* 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);
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);
/******************************************************************************
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 hlist_node *p;
struct net_device *dev;
struct hlist_head *head = dev_name_hash(net, name);
hlist_for_each_entry(dev, p, 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 hlist_node *p;
struct net_device *dev;
struct hlist_head *head = dev_name_hash(net, name);
hlist_for_each_entry_rcu(dev, p, 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 hlist_node *p;
struct net_device *dev;
struct hlist_head *head = dev_index_hash(net, ifindex);
hlist_for_each_entry(dev, p, 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 hlist_node *p;
struct net_device *dev;
struct hlist_head *head = dev_index_hash(net, ifindex);
hlist_for_each_entry_rcu(dev, p, 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_get_valid_name(struct net_device *dev, const char *name)
{
struct net *net;
BUG_ON(!dev_net(dev));
net = dev_net(dev);
if (!dev_valid_name(name))
return -EINVAL;
if (strchr(name, '%'))
return dev_alloc_name(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;
if (strncmp(newname, dev->name, IFNAMSIZ) == 0)
return 0;
memcpy(oldname, dev->name, IFNAMSIZ);
err = dev_get_valid_name(dev, newname);
if (err < 0)
return err;
rollback:
ret = device_rename(&dev->dev, dev->name);
if (ret) {
memcpy(dev->name, oldname, IFNAMSIZ);
return ret;
}
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;
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)
{
ASSERT_RTNL();
if (len >= IFALIASZ)
return -EINVAL;
if (!len) {
if (dev->ifalias) {
kfree(dev->ifalias);
dev->ifalias = NULL;
}
return 0;
}
dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
if (!dev->ifalias)
return -ENOMEM;
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);
int netdev_bonding_change(struct net_device *dev, unsigned long event)
{
return call_netdevice_notifiers(event, dev);
}
EXPORT_SYMBOL(netdev_bonding_change);
/**
* dev_load - load a network module
* @net: the applicable net namespace
* @name: name of interface
*
* If a network interface is not present and the process has suitable
* privileges this function loads the module. If module loading is not
* available in this kernel then it becomes a nop.
*/
void dev_load(struct net *net, const char *name)
{
struct net_device *dev;
int no_module;
rcu_read_lock();
dev = dev_get_by_name_rcu(net, name);
rcu_read_unlock();
no_module = !dev;
if (no_module && capable(CAP_NET_ADMIN))
no_module = request_module("netdev-%s", name);
if (no_module && capable(CAP_SYS_MODULE)) {
if (!request_module("%s", name))
pr_warn("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n",
name);
}
}
EXPORT_SYMBOL(dev_load);
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;
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);
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);
}
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);
list_add(&dev->unreg_list, &single);
retval = __dev_close_many(&single);
list_del(&single);
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)
{
if (dev->flags & IFF_UP) {
LIST_HEAD(single);
list_add(&dev->unreg_list, &single);
dev_close_many(&single);
list_del(&single);
}
return 0;
}
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);
nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, 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);
nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, 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
WARN_ON(in_interrupt());
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 int net_hwtstamp_validate(struct ifreq *ifr)
{
struct hwtstamp_config cfg;
enum hwtstamp_tx_types tx_type;
enum hwtstamp_rx_filters rx_filter;
int tx_type_valid = 0;
int rx_filter_valid = 0;
if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
return -EFAULT;
if (cfg.flags) /* reserved for future extensions */
return -EINVAL;
tx_type = cfg.tx_type;
rx_filter = cfg.rx_filter;
switch (tx_type) {
case HWTSTAMP_TX_OFF:
case HWTSTAMP_TX_ON:
case HWTSTAMP_TX_ONESTEP_SYNC:
tx_type_valid = 1;
break;
}
switch (rx_filter) {
case HWTSTAMP_FILTER_NONE:
case HWTSTAMP_FILTER_ALL:
case HWTSTAMP_FILTER_SOME:
case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
case HWTSTAMP_FILTER_PTP_V2_EVENT:
case HWTSTAMP_FILTER_PTP_V2_SYNC:
case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
rx_filter_valid = 1;
break;
}
if (!tx_type_valid || !rx_filter_valid)
return -ERANGE;
return 0;
}
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);
nf_reset(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);
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)
{
atomic_inc(&skb->users);
return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}
/*
* 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) &&
(ptype->af_packet_priv == NULL ||
(struct sock *)ptype->af_packet_priv != skb->sk)) {
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);
}
}
}
/*
* 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);
}
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 (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;
}
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_gso_segment - Perform segmentation on skb.
* @skb: buffer to segment
* @features: features for the output path (see dev->features)
*
* 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)
{
struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
struct packet_type *ptype;
__be16 type = skb->protocol;
int vlan_depth = ETH_HLEN;
int err;
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_reset_mac_header(skb);
skb->mac_len = skb->network_header - skb->mac_header;
__skb_pull(skb, skb->mac_len);
if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
skb_warn_bad_offload(skb);
if (skb_header_cloned(skb) &&
(err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
return ERR_PTR(err);
}
rcu_read_lock();
list_for_each_entry_rcu(ptype,
&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
if (ptype->type == type && !ptype->dev && ptype->gso_segment) {
if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
err = ptype->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->gso_segment(skb, features);
break;
}
}
rcu_read_unlock();
__skb_push(skb, skb->data - skb_mac_header(skb));
return segs;
}
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 (!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 (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, or if
* at least one of fragments is in highmem and device does not
* support DMA from it.
*/
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);
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(skb, dev);
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 (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) {
skb_set_transport_header(skb,
skb_checksum_start_offset(skb));
if (!(features & NETIF_F_ALL_CSUM) &&
skb_checksum_help(skb))
goto out_kfree_skb;
}
}
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);
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 u32 hashrnd __read_mostly;
/*
* Returns a Tx hash based on the given packet descriptor a Tx queues' number
* to be used as a distribution range.
*/
u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
unsigned int num_tx_queues)
{
u32 hash;
u16 qoffset = 0;
u16 qcount = num_tx_queues;
if (skb_rx_queue_recorded(skb)) {
hash = skb_get_rx_queue(skb);
while (unlikely(hash >= num_tx_queues))
hash -= num_tx_queues;
return hash;
}
if (dev->num_tc) {
u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
qoffset = dev->tc_to_txq[tc].offset;
qcount = dev->tc_to_txq[tc].count;
}
if (skb->sk && skb->sk->sk_hash)
hash = skb->sk->sk_hash;
else
hash = (__force u16) skb->protocol;
hash = jhash_1word(hash, hashrnd);
return (u16) (((u64) hash * qcount) >> 32) + qoffset;
}
EXPORT_SYMBOL(__skb_tx_hash);
static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
{
if (unlikely(queue_index >= dev->real_num_tx_queues)) {
net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
dev->name, queue_index,
dev->real_num_tx_queues);
return 0;
}
return queue_index;
}
static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_XPS
struct xps_dev_maps *dev_maps;
struct xps_map *map;
int queue_index = -1;
rcu_read_lock();
dev_maps = rcu_dereference(dev->xps_maps);
if (dev_maps) {
map = rcu_dereference(
dev_maps->cpu_map[raw_smp_processor_id()]);
if (map) {
if (map->len == 1)
queue_index = map->queues[0];
else {
u32 hash;
if (skb->sk && skb->sk->sk_hash)
hash = skb->sk->sk_hash;
else
hash = (__force u16) skb->protocol ^
skb->rxhash;
hash = jhash_1word(hash, hashrnd);
queue_index = map->queues[
((u64)hash * map->len) >> 32];
}
if (unlikely(queue_index >= dev->real_num_tx_queues))
queue_index = -1;
}
}
rcu_read_unlock();
return queue_index;
#else
return -1;
#endif
}
static struct netdev_queue *dev_pick_tx(struct net_device *dev,
struct sk_buff *skb)
{
int queue_index;
const struct net_device_ops *ops = dev->netdev_ops;
if (dev->real_num_tx_queues == 1)
queue_index = 0;
else if (ops->ndo_select_queue) {
queue_index = ops->ndo_select_queue(dev, skb);
queue_index = dev_cap_txqueue(dev, queue_index);
} else {
struct sock *sk = skb->sk;
queue_index = sk_tx_queue_get(sk);
if (queue_index < 0 || skb->ooo_okay ||
queue_index >= dev->real_num_tx_queues) {
int old_index = queue_index;
queue_index = get_xps_queue(dev, skb);
if (queue_index < 0)
queue_index = skb_tx_hash(dev, skb);
if (queue_index != old_index && sk) {
struct dst_entry *dst =
rcu_dereference_check(sk->sk_dst_cache, 1);
if (dst && skb_dst(skb) == dst)
sk_tx_queue_set(sk, queue_index);
}
}
}
skb_set_queue_mapping(skb, queue_index);
return netdev_get_tx_queue(dev, queue_index);
}
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_skb_cb(skb)->pkt_len = skb->len;
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)
skb->priority = map->priomap[skb->sk->sk_cgrp_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;
/* Disable soft irqs for various locks below. Also
* stops preemption for RCU.
*/
rcu_read_lock_bh();
skb_update_prio(skb);
txq = dev_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;
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);
}
/*
* __skb_get_rxhash: calculate a flow hash based on src/dst addresses
* and src/dst port numbers. Sets rxhash in skb to non-zero hash value
* on success, zero indicates no valid hash. Also, sets l4_rxhash in skb
* if hash is a canonical 4-tuple hash over transport ports.
*/
void __skb_get_rxhash(struct sk_buff *skb)
{
struct flow_keys keys;
u32 hash;
if (!skb_flow_dissect(skb, &keys))
return;
if (keys.ports) {
if ((__force u16)keys.port16[1] < (__force u16)keys.port16[0])
swap(keys.port16[0], keys.port16[1]);
skb->l4_rxhash = 1;
}
/* get a consistent hash (same value on both flow directions) */
if ((__force u32)keys.dst < (__force u32)keys.src)
swap(keys.dst, keys.src);
hash = jhash_3words((__force u32)keys.dst,
(__force u32)keys.src,
(__force u32)keys.ports, hashrnd);
if (!hash)
hash = 1;
skb->rxhash = hash;
}
EXPORT_SYMBOL(__skb_get_rxhash);
#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).
* - Current CPU is offline.
* - The current CPU's queue tail has advanced beyond the
* last packet that was enqueued using this table entry.
* This guarantees that all previous packets for the flow
* have been dequeued, thus preserving in order delivery.
*/
if (unlikely(tcpu != next_cpu) &&
(tcpu == RPS_NO_CPU || !cpu_online(tcpu) ||
((int)(per_cpu(softnet_data, tcpu).input_queue_head -
rflow->last_qtail)) >= 0))
rflow = set_rps_cpu(dev, skb, rflow, next_cpu);
if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) {
*rflowp = rflow;
cpu = tcpu;
goto done;
}
}
if (map) {
tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
if (cpu_online(tcpu)) {
cpu = tcpu;
goto done;
}
}
done:
return cpu;
}
#ifdef CONFIG_RFS_ACCEL
/**
* rps_may_expire_flow - check whether an RFS hardware filter may be removed
* @dev: Device on which the filter was set
* @rxq_index: RX queue index
* @flow_id: Flow ID passed to ndo_rx_flow_steer()
* @filter_id: Filter ID returned by ndo_rx_flow_steer()
*
* Drivers that implement ndo_rx_flow_steer() should periodically call
* this function for each installed filter and remove the filters for
* which it returns %true.
*/
bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index,
u32 flow_id, u16 filter_id)
{
struct netdev_rx_queue *rxqueue = dev->_rx + rxq_index;
struct rps_dev_flow_table *flow_table;
struct rps_dev_flow *rflow;
bool expire = true;
int cpu;
rcu_read_lock();
flow_table = rcu_dereference(rxqueue->rps_flow_table);
if (flow_table && flow_id <= flow_table->mask) {
rflow = &flow_table->flows[flow_id];
cpu = ACCESS_ONCE(rflow->cpu);
if (rflow->filter == filter_id && cpu != RPS_NO_CPU &&
((int)(per_cpu(softnet_data, cpu).input_queue_head -
rflow->last_qtail) <
(int)(10 * flow_table->mask)))
expire = false;
}
rcu_read_unlock();
return expire;
}
EXPORT_SYMBOL(rps_may_expire_flow);
#endif /* CONFIG_RFS_ACCEL */
/* Called from hardirq (IPI) context */
static void rps_trigger_softirq(void *data)
{
struct softnet_data *sd = data;
____napi_schedule(sd, &sd->backlog);
sd->received_rps++;
}
#endif /* CONFIG_RPS */
/*
* Check if this softnet_data structure is another cpu one
* If yes, queue it to our IPI list and return 1
* If no, return 0
*/
static int rps_ipi_queued(struct softnet_data *sd)
{
#ifdef CONFIG_RPS
struct softnet_data *mysd = &__get_cpu_var(softnet_data);
if (sd != mysd) {
sd->rps_ipi_next = mysd->rps_ipi_list;
mysd->rps_ipi_list = sd;
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
return 1;
}
#endif /* CONFIG_RPS */
return 0;
}
/*
* enqueue_to_backlog is called to queue an skb to a per CPU backlog
* queue (may be a remote CPU queue).
*/
static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
unsigned int *qtail)
{
struct softnet_data *sd;
unsigned long flags;
sd = &per_cpu(softnet_data, cpu);
local_irq_save(flags);
rps_lock(sd);
if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) {
if (skb_queue_len(&sd->input_pkt_queue)) {
enqueue:
__skb_queue_tail(&sd->input_pkt_queue, skb);
input_queue_tail_incr_save(sd, qtail);
rps_unlock(sd);
local_irq_restore(flags);
return NET_RX_SUCCESS;
}
/* Schedule NAPI for backlog device
* We can use non atomic operation since we own the queue lock
*/
if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) {
if (!rps_ipi_queued(sd))
____napi_schedule(sd, &sd->backlog);
}
goto enqueue;
}
sd->dropped++;
rps_unlock(sd);
local_irq_restore(flags);
atomic_long_inc(&skb->dev->rx_dropped);
kfree_skb(skb);
return NET_RX_DROP;
}
/**
* netif_rx - post buffer to the network code
* @skb: buffer to post
*
* This function receives a packet from a device driver and queues it for
* the upper (protocol) levels to process. It always succeeds. The buffer
* may be dropped during processing for congestion control or by the
* protocol layers.
*
* return values:
* NET_RX_SUCCESS (no congestion)
* NET_RX_DROP (packet was dropped)
*
*/
int netif_rx(struct sk_buff *skb)
{
int ret;
/* if netpoll wants it, pretend we never saw it */
if (netpoll_rx(skb))
return NET_RX_DROP;
net_timestamp_check(netdev_tstamp_prequeue, skb);
trace_netif_rx(skb);
#ifdef CONFIG_RPS
if (static_key_false(&rps_needed)) {
struct rps_dev_flow voidflow, *rflow = &voidflow;
int cpu;
preempt_disable();
rcu_read_lock();
cpu = get_rps_cpu(skb->dev, skb, &rflow);
if (cpu < 0)
cpu = smp_processor_id();
ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
rcu_read_unlock();
preempt_enable();
} else
#endif
{
unsigned int qtail;
ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
put_cpu();
}
return ret;
}
EXPORT_SYMBOL(netif_rx);
int netif_rx_ni(struct sk_buff *skb)
{
int err;
preempt_disable();
err = netif_rx(skb);
if (local_softirq_pending())
do_softirq();
preempt_enable();
return err;
}
EXPORT_SYMBOL(netif_rx_ni);
static void net_tx_action(struct softirq_action *h)
{
struct softnet_data *sd = &__get_cpu_var(softnet_data);
if (sd->completion_queue) {
struct sk_buff *clist;
local_irq_disable();
clist = sd->completion_queue;
sd->completion_queue = NULL;
local_irq_enable();
while (clist) {
struct sk_buff *skb = clist;
clist = clist->next;
WARN_ON(atomic_read(&skb->users));
trace_kfree_skb(skb, net_tx_action);
__kfree_skb(skb);
}
}
if (sd->output_queue) {
struct Qdisc *head;
local_irq_disable();
head = sd->output_queue;
sd->output_queue = NULL;
sd->output_queue_tailp = &sd->output_queue;
local_irq_enable();
while (head) {
struct Qdisc *q = head;
spinlock_t *root_lock;
head = head->next_sched;
root_lock = qdisc_lock(q);
if (spin_trylock(root_lock)) {
smp_mb__before_clear_bit();
clear_bit(__QDISC_STATE_SCHED,
&q->state);
qdisc_run(q);
spin_unlock(root_lock);
} else {
if (!test_bit(__QDISC_STATE_DEACTIVATED,
&q->state)) {
__netif_reschedule(q);
} else {
smp_mb__before_clear_bit();
clear_bit(__QDISC_STATE_SCHED,
&q->state);
}
}
}
}
}
#if (defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)) && \
(defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE))
/* This hook is defined here for ATM LANE */
int (*br_fdb_test_addr_hook)(struct net_device *dev,
unsigned char *addr) __read_mostly;
EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
#endif
#ifdef CONFIG_NET_CLS_ACT
/* TODO: Maybe we should just force sch_ingress to be compiled in
* when CONFIG_NET_CLS_ACT is? otherwise some useless instructions
* a compare and 2 stores extra right now if we dont have it on
* but have CONFIG_NET_CLS_ACT
* NOTE: This doesn't stop any functionality; if you dont have
* the ingress scheduler, you just can't add policies on ingress.
*
*/
static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq)
{
struct net_device *dev = skb->dev;
u32 ttl = G_TC_RTTL(skb->tc_verd);
int result = TC_ACT_OK;
struct Qdisc *q;
if (unlikely(MAX_RED_LOOP < ttl++)) {
net_warn_ratelimited("Redir loop detected Dropping packet (%d->%d)\n",
skb->skb_iif, dev->ifindex);
return TC_ACT_SHOT;
}
skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl);
skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
q = rxq->qdisc;
if (q != &noop_qdisc) {
spin_lock(qdisc_lock(q));
if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
result = qdisc_enqueue_root(skb, q);
spin_unlock(qdisc_lock(q));
}
return result;
}
static inline struct sk_buff *handle_ing(struct sk_buff *skb,
struct packet_type **pt_prev,
int *ret, struct net_device *orig_dev)
{
struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue);
if (!rxq || rxq->qdisc == &noop_qdisc)
goto out;
if (*pt_prev) {
*ret = deliver_skb(skb, *pt_prev, orig_dev);
*pt_prev = NULL;
}
switch (ing_filter(skb, rxq)) {
case TC_ACT_SHOT:
case TC_ACT_STOLEN:
kfree_skb(skb);
return NULL;
}
out:
skb->tc_verd = 0;
return skb;
}
#endif
/**
* netdev_rx_handler_register - register receive handler
* @dev: device to register a handler for
* @rx_handler: receive handler to register
* @rx_handler_data: data pointer that is used by rx handler
*
* Register a receive hander for a device. This handler will then be
* called from __netif_receive_skb. A negative errno code is returned
* on a failure.
*
* The caller must hold the rtnl_mutex.
*
* For a general description of rx_handler, see enum rx_handler_result.
*/
int netdev_rx_handler_register(struct net_device *dev,
rx_handler_func_t *rx_handler,
void *rx_handler_data)
{
ASSERT_RTNL();
if (dev->rx_handler)
return -EBUSY;
rcu_assign_pointer(dev->rx_handler_data, rx_handler_data);
rcu_assign_pointer(dev->rx_handler, rx_handler);
return 0;
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_register);
/**
* netdev_rx_handler_unregister - unregister receive handler
* @dev: device to unregister a handler from
*
* Unregister a receive hander from a device.
*
* The caller must hold the rtnl_mutex.
*/
void netdev_rx_handler_unregister(struct net_device *dev)
{
ASSERT_RTNL();
RCU_INIT_POINTER(dev->rx_handler, NULL);
RCU_INIT_POINTER(dev->rx_handler_data, NULL);
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
static int __netif_receive_skb(struct sk_buff *skb)
{
struct packet_type *ptype, *pt_prev;
rx_handler_func_t *rx_handler;
struct net_device *orig_dev;
struct net_device *null_or_dev;
bool deliver_exact = false;
int ret = NET_RX_DROP;
__be16 type;
net_timestamp_check(!netdev_tstamp_prequeue, skb);
trace_netif_receive_skb(skb);
/* if we've gotten here through NAPI, check netpoll */
if (netpoll_receive_skb(skb))
return NET_RX_DROP;
if (!skb->skb_iif)
skb->skb_iif = skb->dev->ifindex;
orig_dev = skb->dev;
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
skb_reset_mac_len(skb);
pt_prev = NULL;
rcu_read_lock();
another_round:
__this_cpu_inc(softnet_data.processed);
if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
skb = vlan_untag(skb);
if (unlikely(!skb))
goto out;
}
#ifdef CONFIG_NET_CLS_ACT
if (skb->tc_verd & TC_NCLS) {
skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
goto ncls;
}
#endif
list_for_each_entry_rcu(ptype, &ptype_all, list) {
if (!ptype->dev || ptype->dev == skb->dev) {
if (pt_prev)
ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = ptype;
}
}
#ifdef CONFIG_NET_CLS_ACT
skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
if (!skb)
goto out;
ncls:
#endif
rx_handler = rcu_dereference(skb->dev->rx_handler);
if (vlan_tx_tag_present(skb)) {
if (pt_prev) {
ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = NULL;
}
if (vlan_do_receive(&skb, !rx_handler))
goto another_round;
else if (unlikely(!skb))
goto out;
}
if (rx_handler) {
if (pt_prev) {
ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = NULL;
}
switch (rx_handler(&skb)) {
case RX_HANDLER_CONSUMED:
goto out;
case RX_HANDLER_ANOTHER:
goto another_round;
case RX_HANDLER_EXACT:
deliver_exact = true;
case RX_HANDLER_PASS:
break;
default:
BUG();
}
}
/* deliver only exact match when indicated */
null_or_dev = deliver_exact ? skb->dev : NULL;
type = skb->protocol;
list_for_each_entry_rcu(ptype,
&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
if (ptype->type == type &&
(ptype->dev == null_or_dev || ptype->dev == skb->dev ||
ptype->dev == orig_dev)) {
if (pt_prev)
ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = ptype;
}
}
if (pt_prev) {
ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
} else {
atomic_long_inc(&skb->dev->rx_dropped);
kfree_skb(skb);
/* Jamal, now you will not able to escape explaining
* me how you were going to use this. :-)
*/
ret = NET_RX_DROP;
}
out:
rcu_read_unlock();
return ret;
}
/**
* netif_receive_skb - process receive buffer from network
* @skb: buffer to process
*
* netif_receive_skb() is the main receive data processing function.
* It always succeeds. The buffer may be dropped during processing
* for congestion control or by the protocol layers.
*
* This function may only be called from softirq context and interrupts
* should be enabled.
*
* Return values (usually ignored):
* NET_RX_SUCCESS: no congestion
* NET_RX_DROP: packet was dropped
*/
int netif_receive_skb(struct sk_buff *skb)
{
net_timestamp_check(netdev_tstamp_prequeue, skb);
if (skb_defer_rx_timestamp(skb))
return NET_RX_SUCCESS;
#ifdef CONFIG_RPS
if (static_key_false(&rps_needed)) {
struct rps_dev_flow voidflow, *rflow = &voidflow;
int cpu, ret;
rcu_read_lock();
cpu = get_rps_cpu(skb->dev, skb, &rflow);
if (cpu >= 0) {
ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
rcu_read_unlock();
return ret;
}
rcu_read_unlock();
}
#endif
return __netif_receive_skb(skb);
}
EXPORT_SYMBOL(netif_receive_skb);
/* Network device is going away, flush any packets still pending
* Called with irqs disabled.
*/
static void flush_backlog(void *arg)
{
struct net_device *dev = arg;
struct softnet_data *sd = &__get_cpu_var(softnet_data);
struct sk_buff *skb, *tmp;
rps_lock(sd);
skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
if (skb->dev == dev) {
__skb_unlink(skb, &sd->input_pkt_queue);
kfree_skb(skb);
input_queue_head_incr(sd);
}
}
rps_unlock(sd);
skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
if (skb->dev == dev) {
__skb_unlink(skb, &sd->process_queue);
kfree_skb(skb);
input_queue_head_incr(sd);
}
}
}
static int napi_gro_complete(struct sk_buff *skb)
{
struct packet_type *ptype;
__be16 type = skb->protocol;
struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
int err = -ENOENT;
if (NAPI_GRO_CB(skb)->count == 1) {
skb_shinfo(skb)->gso_size = 0;
goto out;
}
rcu_read_lock();
list_for_each_entry_rcu(ptype, head, list) {
if (ptype->type != type || ptype->dev || !ptype->gro_complete)
continue;
err = ptype->gro_complete(skb);
break;
}
rcu_read_unlock();
if (err) {
WARN_ON(&ptype->list == head);
kfree_skb(skb);
return NET_RX_SUCCESS;
}
out:
return netif_receive_skb(skb);
}
inline void napi_gro_flush(struct napi_struct *napi)
{
struct sk_buff *skb, *next;
for (skb = napi->gro_list; skb; skb = next) {
next = skb->next;
skb->next = NULL;
napi_gro_complete(skb);
}
napi->gro_count = 0;
napi->gro_list = NULL;
}
EXPORT_SYMBOL(napi_gro_flush);
enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
struct sk_buff **pp = NULL;
struct packet_type *ptype;
__be16 type = skb->protocol;
struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
int same_flow;
int mac_len;
enum gro_result ret;
if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb))
goto normal;
if (skb_is_gso(skb) || skb_has_frag_list(skb))
goto normal;
rcu_read_lock();
list_for_each_entry_rcu(ptype, head, list) {
if (ptype->type != type || ptype->dev || !ptype->gro_receive)
continue;
skb_set_network_header(skb, skb_gro_offset(skb));
mac_len = skb->network_header - skb->mac_header;
skb->mac_len = mac_len;
NAPI_GRO_CB(skb)->same_flow = 0;
NAPI_GRO_CB(skb)->flush = 0;
NAPI_GRO_CB(skb)->free = 0;
pp = ptype->gro_receive(&napi->gro_list, skb);
break;
}
rcu_read_unlock();
if (&ptype->list == head)
goto normal;
same_flow = NAPI_GRO_CB(skb)->same_flow;
ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED;
if (pp) {
struct sk_buff *nskb = *pp;
*pp = nskb->next;
nskb->next = NULL;
napi_gro_complete(nskb);
napi->gro_count--;
}
if (same_flow)
goto ok;
if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS)
goto normal;
napi->gro_count++;
NAPI_GRO_CB(skb)->count = 1;
skb_shinfo(skb)->gso_size = skb_gro_len(skb);
skb->next = napi->gro_list;
napi->gro_list = skb;
ret = GRO_HELD;
pull:
if (skb_headlen(skb) < skb_gro_offset(skb)) {
int grow = skb_gro_offset(skb) - skb_headlen(skb);
BUG_ON(skb->end - skb->tail < grow);
memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow);
skb->tail += grow;
skb->data_len -= grow;
skb_shinfo(skb)->frags[0].page_offset += grow;
skb_frag_size_sub(&skb_shinfo(skb)->frags[0], grow);
if (unlikely(!skb_frag_size(&skb_shinfo(skb)->frags[0]))) {
skb_frag_unref(skb, 0);
memmove(skb_shinfo(skb)->frags,
skb_shinfo(skb)->frags + 1,
--skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t));
}
}
ok:
return ret;
normal:
ret = GRO_NORMAL;
goto pull;
}
EXPORT_SYMBOL(dev_gro_receive);
static inline gro_result_t
__napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
struct sk_buff *p;
unsigned int maclen = skb->dev->hard_header_len;
for (p = napi->gro_list; p; p = p->next) {
unsigned long diffs;
diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
diffs |= p->vlan_tci ^ skb->vlan_tci;
if (maclen == ETH_HLEN)
diffs |= compare_ether_header(skb_mac_header(p),
skb_gro_mac_header(skb));
else if (!diffs)
diffs = memcmp(skb_mac_header(p),
skb_gro_mac_header(skb),
maclen);
NAPI_GRO_CB(p)->same_flow = !diffs;
NAPI_GRO_CB(p)->flush = 0;
}
return dev_gro_receive(napi, skb);
}
gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
{
switch (ret) {
case GRO_NORMAL:
if (netif_receive_skb(skb))
ret = GRO_DROP;
break;
case GRO_DROP:
kfree_skb(skb);
break;
case GRO_MERGED_FREE:
if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD)
kmem_cache_free(skbuff_head_cache, skb);
else
__kfree_skb(skb);
break;
case GRO_HELD:
case GRO_MERGED:
break;
}
return ret;
}
EXPORT_SYMBOL(napi_skb_finish);
void skb_gro_reset_offset(struct sk_buff *skb)
{
NAPI_GRO_CB(skb)->data_offset = 0;
NAPI_GRO_CB(skb)->frag0 = NULL;
NAPI_GRO_CB(skb)->frag0_len = 0;
if (skb->mac_header == skb->tail &&
!PageHighMem(skb_frag_page(&skb_shinfo(skb)->frags[0]))) {
NAPI_GRO_CB(skb)->frag0 =
skb_frag_address(&skb_shinfo(skb)->frags[0]);
NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(&skb_shinfo(skb)->frags[0]);
}
}
EXPORT_SYMBOL(skb_gro_reset_offset);
gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
skb_gro_reset_offset(skb);
return napi_skb_finish(__napi_gro_receive(napi, skb), skb);
}
EXPORT_SYMBOL(napi_gro_receive);
static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
{
__skb_pull(skb, skb_headlen(skb));
/* restore the reserve we had after netdev_alloc_skb_ip_align() */
skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb));
skb->vlan_tci = 0;
skb->dev = napi->dev;
skb->skb_iif = 0;
napi->skb = skb;
}
struct sk_buff *napi_get_frags(struct napi_struct *napi)
{
struct sk_buff *skb = napi->skb;
if (!skb) {
skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD);
if (skb)
napi->skb = skb;
}
return skb;
}
EXPORT_SYMBOL(napi_get_frags);
gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
gro_result_t ret)
{
switch (ret) {
case GRO_NORMAL:
case GRO_HELD:
skb->protocol = eth_type_trans(skb, skb->dev);
if (ret == GRO_HELD)
skb_gro_pull(skb, -ETH_HLEN);
else if (netif_receive_skb(skb))
ret = GRO_DROP;
break;
case GRO_DROP:
case GRO_MERGED_FREE:
napi_reuse_skb(napi, skb);
break;
case GRO_MERGED:
break;
}
return ret;
}
EXPORT_SYMBOL(napi_frags_finish);
static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
{
struct sk_buff *skb = napi->skb;
struct ethhdr *eth;
unsigned int hlen;
unsigned int off;
napi->skb = NULL;
skb_reset_mac_header(skb);
skb_gro_reset_offset(skb);
off = skb_gro_offset(skb);
hlen = off + sizeof(*eth);
eth = skb_gro_header_fast(skb, off);
if (skb_gro_header_hard(skb, hlen)) {
eth = skb_gro_header_slow(skb, hlen, off);
if (unlikely(!eth)) {
napi_reuse_skb(napi, skb);
skb = NULL;
goto out;
}
}
skb_gro_pull(skb, sizeof(*eth));
/*
* This works because the only protocols we care about don't require
* special handling. We'll fix it up properly at the end.
*/
skb->protocol = eth->h_proto;
out:
return skb;
}
gro_result_t napi_gro_frags(struct napi_struct *napi)
{
struct sk_buff *skb = napi_frags_skb(napi);
if (!skb)
return GRO_DROP;
return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb));
}
EXPORT_SYMBOL(napi_gro_frags);
/*
* net_rps_action sends any pending IPI's for rps.
* Note: called with local irq disabled, but exits with local irq enabled.
*/
static void net_rps_action_and_irq_enable(struct softnet_data *sd)
{
#ifdef CONFIG_RPS
struct softnet_data *remsd = sd->rps_ipi_list;
if (remsd) {
sd->rps_ipi_list = NULL;
local_irq_enable();
/* Send pending IPI's to kick RPS processing on remote cpus. */
while (remsd) {
struct softnet_data *next = remsd->rps_ipi_next;
if (cpu_online(remsd->cpu))
__smp_call_function_single(remsd->cpu,
&remsd->csd, 0);
remsd = next;
}
} else
#endif
local_irq_enable();
}
static int process_backlog(struct napi_struct *napi, int quota)
{
int work = 0;
struct softnet_data *sd = container_of(napi, struct softnet_data, backlog);
#ifdef CONFIG_RPS
/* Check if we have pending ipi, its better to send them now,
* not waiting net_rx_action() end.
*/
if (sd->rps_ipi_list) {
local_irq_disable();
net_rps_action_and_irq_enable(sd);
}
#endif
napi->weight = weight_p;
local_irq_disable();
while (work < quota) {
struct sk_buff *skb;
unsigned int qlen;
while ((skb = __skb_dequeue(&sd->process_queue))) {
local_irq_enable();
__netif_receive_skb(skb);
local_irq_disable();
input_queue_head_incr(sd);
if (++work >= quota) {
local_irq_enable();
return work;
}
}
rps_lock(sd);
qlen = skb_queue_len(&sd->input_pkt_queue);
if (qlen)
skb_queue_splice_tail_init(&sd->input_pkt_queue,
&sd->process_queue);
if (qlen < quota - work) {
/*
* Inline a custom version of __napi_complete().
* only current cpu owns and manipulates this napi,
* and NAPI_STATE_SCHED is the only possible flag set on backlog.
* we can use a plain write instead of clear_bit(),
* and we dont need an smp_mb() memory barrier.
*/
list_del(&napi->poll_list);
napi->state = 0;
quota = work + qlen;
}
rps_unlock(sd);
}
local_irq_enable();
return work;
}
/**
* __napi_schedule - schedule for receive
* @n: entry to schedule
*
* The entry's receive function will be scheduled to run
*/
void __napi_schedule(struct napi_struct *n)
{
unsigned long flags;
local_irq_save(flags);
____napi_schedule(&__get_cpu_var(softnet_data), n);
local_irq_restore(flags);
}
EXPORT_SYMBOL(__napi_schedule);
void __napi_complete(struct napi_struct *n)
{
BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
BUG_ON(n->gro_list);
list_del(&n->poll_list);
smp_mb__before_clear_bit();
clear_bit(NAPI_STATE_SCHED, &n->state);
}
EXPORT_SYMBOL(__napi_complete);
void napi_complete(struct napi_struct *n)
{
unsigned long flags;
/*
* don't let napi dequeue from the cpu poll list
* just in case its running on a different cpu
*/
if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state)))
return;
napi_gro_flush(n);
local_irq_save(flags);
__napi_complete(n);
local_irq_restore(flags);
}
EXPORT_SYMBOL(napi_complete);
void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int), int weight)
{
INIT_LIST_HEAD(&napi->poll_list);
napi->gro_count = 0;
napi->gro_list = NULL;
napi->skb = NULL;
napi->poll = poll;
napi->weight = weight;
list_add(&napi->dev_list, &dev->napi_list);
napi->dev = dev;
#ifdef CONFIG_NETPOLL
spin_lock_init(&napi->poll_lock);
napi->poll_owner = -1;
#endif
set_bit(NAPI_STATE_SCHED, &napi->state);
}
EXPORT_SYMBOL(netif_napi_add);
void netif_napi_del(struct napi_struct *napi)
{
struct sk_buff *skb, *next;
list_del_init(&napi->dev_list);
napi_free_frags(napi);
for (skb = napi->gro_list; skb; skb = next) {
next = skb->next;
skb->next = NULL;
kfree_skb(skb);
}
napi->gro_list = NULL;
napi->gro_count = 0;
}
EXPORT_SYMBOL(netif_napi_del);
static void net_rx_action(struct softirq_action *h)
{
struct softnet_data *sd = &__get_cpu_var(softnet_data);
unsigned long time_limit = jiffies + 2;
int budget = netdev_budget;
void *have;
local_irq_disable();
while (!list_empty(&sd->poll_list)) {
struct napi_struct *n;
int work, weight;
/* If softirq window is exhuasted then punt.
* Allow this to run for 2 jiffies since which will allow
* an average latency of 1.5/HZ.
*/
if (unlikely(budget <= 0 || time_after(jiffies, time_limit)))
goto softnet_break;
local_irq_enable();
/* Even though interrupts have been re-enabled, this
* access is safe because interrupts can only add new
* entries to the tail of this list, and only ->poll()
* calls can remove this head entry from the list.
*/
n = list_first_entry(&sd->poll_list, struct napi_struct, poll_list);
have = netpoll_poll_lock(n);
weight = n->weight;
/* This NAPI_STATE_SCHED test is for avoiding a race
* with netpoll's poll_napi(). Only the entity which
* obtains the lock and sees NAPI_STATE_SCHED set will
* actually make the ->poll() call. Therefore we avoid
* accidentally calling ->poll() when NAPI is not scheduled.
*/
work = 0;
if (test_bit(NAPI_STATE_SCHED, &n->state)) {
work = n->poll(n, weight);
trace_napi_poll(n);
}
WARN_ON_ONCE(work > weight);
budget -= work;
local_irq_disable();
/* Drivers must not modify the NAPI state if they
* consume the entire weight. In such cases this code
* still "owns" the NAPI instance and therefore can
* move the instance around on the list at-will.
*/
if (unlikely(work == weight)) {
if (unlikely(napi_disable_pending(n))) {
local_irq_enable();
napi_complete(n);
local_irq_disable();
} else
list_move_tail(&n->poll_list, &sd->poll_list);
}
netpoll_poll_unlock(have);
}
out:
net_rps_action_and_irq_enable(sd);
#ifdef CONFIG_NET_DMA
/*
* There may not be any more sk_buffs coming right now, so push
* any pending DMA copies to hardware
*/
dma_issue_pending_all();
#endif
return;
softnet_break:
sd->time_squeeze++;
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
goto out;
}
static gifconf_func_t *gifconf_list[NPROTO];
/**
* register_gifconf - register a SIOCGIF handler
* @family: Address family
* @gifconf: Function handler
*
* Register protocol dependent address dumping routines. The handler
* that is passed must not be freed or reused until it has been replaced
* by another handler.
*/
int register_gifconf(unsigned int family, gifconf_func_t *gifconf)
{
if (family >= NPROTO)
return -EINVAL;
gifconf_list[family] = gifconf;
return 0;
}
EXPORT_SYMBOL(register_gifconf);
/*
* Map an interface index to its name (SIOCGIFNAME)
*/
/*
* We need this ioctl for efficient implementation of the
* if_indextoname() function required by the IPv6 API. Without
* it, we would have to search all the interfaces to find a
* match. --pb
*/
static int dev_ifname(struct net *net, struct ifreq __user *arg)
{
struct net_device *dev;
struct ifreq ifr;
/*
* Fetch the caller's info block.
*/
if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
return -EFAULT;
rcu_read_lock();
dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex);
if (!dev) {
rcu_read_unlock();
return -ENODEV;
}
strcpy(ifr.ifr_name, dev->name);
rcu_read_unlock();
if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
return -EFAULT;
return 0;
}
/*
* Perform a SIOCGIFCONF call. This structure will change
* size eventually, and there is nothing I can do about it.
* Thus we will need a 'compatibility mode'.
*/
static int dev_ifconf(struct net *net, char __user *arg)
{
struct ifconf ifc;
struct net_device *dev;
char __user *pos;
int len;
int total;
int i;
/*
* Fetch the caller's info block.
*/
if (copy_from_user(&ifc, arg, sizeof(struct ifconf)))
return -EFAULT;
pos = ifc.ifc_buf;
len = ifc.ifc_len;
/*
* Loop over the interfaces, and write an info block for each.
*/
total = 0;
for_each_netdev(net, dev) {
for (i = 0; i < NPROTO; i++) {
if (gifconf_list[i]) {
int done;
if (!pos)
done = gifconf_list[i](dev, NULL, 0);
else
done = gifconf_list[i](dev, pos + total,
len - total);
if (done < 0)
return -EFAULT;
total += done;
}
}
}
/*
* All done. Write the updated control block back to the caller.
*/
ifc.ifc_len = total;
/*
* Both BSD and Solaris return 0 here, so we do too.
*/
return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0;
}
#ifdef CONFIG_PROC_FS
#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1)
#define get_bucket(x) ((x) >> BUCKET_SPACE)
#define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1))
#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o))
static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos)
{
struct net *net = seq_file_net(seq);
struct net_device *dev;
struct hlist_node *p;
struct hlist_head *h;
unsigned int count = 0, offset = get_offset(*pos);
h = &net->dev_name_head[get_bucket(*pos)];
hlist_for_each_entry_rcu(dev, p, h, name_hlist) {
if (++count == offset)
return dev;
}
return NULL;
}
static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos)
{
struct net_device *dev;
unsigned int bucket;
do {
dev = dev_from_same_bucket(seq, pos);
if (dev)
return dev;
bucket = get_bucket(*pos) + 1;
*pos = set_bucket_offset(bucket, 1);
} while (bucket < NETDEV_HASHENTRIES);
return NULL;
}
/*
* This is invoked by the /proc filesystem handler to display a device
* in detail.
*/
void *dev_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(RCU)
{
rcu_read_lock();
if (!*pos)
return SEQ_START_TOKEN;
if (get_bucket(*pos) >= NETDEV_HASHENTRIES)
return NULL;
return dev_from_bucket(seq, pos);
}
void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
++*pos;
return dev_from_bucket(seq, pos);
}
void dev_seq_stop(struct seq_file *seq, void *v)
__releases(RCU)
{
rcu_read_unlock();
}
static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
{
struct rtnl_link_stats64 temp;
const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp);
seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu "
"%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n",