| /* |
| * 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 <asm/system.h> |
| #include <linux/bitops.h> |
| #include <linux/capability.h> |
| #include <linux/cpu.h> |
| #include <linux/types.h> |
| #include <linux/kernel.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 <linux/if_bridge.h> |
| #include <linux/if_macvlan.h> |
| #include <net/dst.h> |
| #include <net/pkt_sched.h> |
| #include <net/checksum.h> |
| #include <linux/highmem.h> |
| #include <linux/init.h> |
| #include <linux/kmod.h> |
| #include <linux/module.h> |
| #include <linux/kallsyms.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 "net-sysfs.h" |
| |
| /* |
| * 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 */ |
| |
| #ifdef CONFIG_NET_DMA |
| struct net_dma { |
| struct dma_client client; |
| spinlock_t lock; |
| cpumask_t channel_mask; |
| struct dma_chan **channels; |
| }; |
| |
| static enum dma_state_client |
| netdev_dma_event(struct dma_client *client, struct dma_chan *chan, |
| enum dma_state state); |
| |
| static struct net_dma net_dma = { |
| .client = { |
| .event_callback = netdev_dma_event, |
| }, |
| }; |
| #endif |
| |
| /* |
| * The @dev_base_head list is protected by @dev_base_lock and the rtnl |
| * semaphore. |
| * |
| * Pure readers hold dev_base_lock for reading. |
| * |
| * 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); |
| |
| #define NETDEV_HASHBITS 8 |
| #define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS) |
| |
| static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) |
| { |
| unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ)); |
| return &net->dev_name_head[hash & ((1 << NETDEV_HASHBITS) - 1)]; |
| } |
| |
| static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) |
| { |
| return &net->dev_index_head[ifindex & ((1 << NETDEV_HASHBITS) - 1)]; |
| } |
| |
| /* 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(&dev->dev_list, &net->dev_base_head); |
| hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name)); |
| hlist_add_head(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); |
| write_unlock_bh(&dev_base_lock); |
| return 0; |
| } |
| |
| /* Device list removal */ |
| static void unlist_netdevice(struct net_device *dev) |
| { |
| ASSERT_RTNL(); |
| |
| /* Unlink dev from the device chain */ |
| write_lock_bh(&dev_base_lock); |
| list_del(&dev->dev_list); |
| hlist_del(&dev->name_hlist); |
| hlist_del(&dev->index_hlist); |
| write_unlock_bh(&dev_base_lock); |
| } |
| |
| /* |
| * 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(struct softnet_data, 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_IEEE802_TR, ARPHRD_IEEE80211, |
| ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_VOID, |
| ARPHRD_NONE}; |
| |
| static const char *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_IEEE802_TR", "_xmit_IEEE80211", |
| "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_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) |
| */ |
| |
| /** |
| * 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) |
| { |
| int hash; |
| |
| spin_lock_bh(&ptype_lock); |
| if (pt->type == htons(ETH_P_ALL)) |
| list_add_rcu(&pt->list, &ptype_all); |
| else { |
| hash = ntohs(pt->type) & PTYPE_HASH_MASK; |
| list_add_rcu(&pt->list, &ptype_base[hash]); |
| } |
| spin_unlock_bh(&ptype_lock); |
| } |
| |
| /** |
| * __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; |
| struct packet_type *pt1; |
| |
| spin_lock_bh(&ptype_lock); |
| |
| if (pt->type == htons(ETH_P_ALL)) |
| head = &ptype_all; |
| else |
| head = &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; |
| |
| list_for_each_entry(pt1, head, list) { |
| if (pt == pt1) { |
| list_del_rcu(&pt->list); |
| goto out; |
| } |
| } |
| |
| printk(KERN_WARNING "dev_remove_pack: %p not found.\n", pt); |
| out: |
| spin_unlock_bh(&ptype_lock); |
| } |
| /** |
| * 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(); |
| } |
| |
| /****************************************************************************** |
| |
| 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; |
| } |
| |
| |
| /** |
| * 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; |
| |
| hlist_for_each(p, dev_name_hash(net, name)) { |
| struct net_device *dev |
| = hlist_entry(p, struct net_device, name_hlist); |
| if (!strncmp(dev->name, name, IFNAMSIZ)) |
| return dev; |
| } |
| return NULL; |
| } |
| |
| /** |
| * 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; |
| |
| read_lock(&dev_base_lock); |
| dev = __dev_get_by_name(net, name); |
| if (dev) |
| dev_hold(dev); |
| read_unlock(&dev_base_lock); |
| return dev; |
| } |
| |
| /** |
| * __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; |
| |
| hlist_for_each(p, dev_index_hash(net, ifindex)) { |
| struct net_device *dev |
| = hlist_entry(p, struct net_device, index_hlist); |
| if (dev->ifindex == ifindex) |
| return dev; |
| } |
| return NULL; |
| } |
| |
| |
| /** |
| * 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; |
| |
| read_lock(&dev_base_lock); |
| dev = __dev_get_by_index(net, ifindex); |
| if (dev) |
| dev_hold(dev); |
| read_unlock(&dev_base_lock); |
| return dev; |
| } |
| |
| /** |
| * dev_getbyhwaddr - 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 the |
| * rtnl semaphore. The returned device has not had its ref count increased |
| * and the caller must therefore be careful about locking |
| * |
| * BUGS: |
| * If the API was consistent this would be __dev_get_by_hwaddr |
| */ |
| |
| struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, char *ha) |
| { |
| struct net_device *dev; |
| |
| ASSERT_RTNL(); |
| |
| for_each_netdev(net, dev) |
| if (dev->type == type && |
| !memcmp(dev->dev_addr, ha, dev->addr_len)) |
| return dev; |
| |
| return NULL; |
| } |
| |
| EXPORT_SYMBOL(dev_getbyhwaddr); |
| |
| 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; |
| |
| rtnl_lock(); |
| dev = __dev_getfirstbyhwtype(net, type); |
| if (dev) |
| dev_hold(dev); |
| rtnl_unlock(); |
| return dev; |
| } |
| |
| EXPORT_SYMBOL(dev_getfirstbyhwtype); |
| |
| /** |
| * dev_get_by_flags - 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. 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_flags(struct net *net, unsigned short if_flags, unsigned short mask) |
| { |
| struct net_device *dev, *ret; |
| |
| ret = NULL; |
| read_lock(&dev_base_lock); |
| for_each_netdev(net, dev) { |
| if (((dev->flags ^ if_flags) & mask) == 0) { |
| dev_hold(dev); |
| ret = dev; |
| break; |
| } |
| } |
| read_unlock(&dev_base_lock); |
| return ret; |
| } |
| |
| /** |
| * 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. |
| */ |
| int dev_valid_name(const char *name) |
| { |
| if (*name == '\0') |
| return 0; |
| if (strlen(name) >= IFNAMSIZ) |
| return 0; |
| if (!strcmp(name, ".") || !strcmp(name, "..")) |
| return 0; |
| |
| while (*name) { |
| if (*name == '/' || isspace(*name)) |
| return 0; |
| name++; |
| } |
| return 1; |
| } |
| |
| /** |
| * __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); |
| } |
| |
| 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; |
| } |
| |
| |
| /** |
| * 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 (!dev_valid_name(newname)) |
| return -EINVAL; |
| |
| if (strncmp(newname, dev->name, IFNAMSIZ) == 0) |
| return 0; |
| |
| memcpy(oldname, dev->name, IFNAMSIZ); |
| |
| if (strchr(newname, '%')) { |
| err = dev_alloc_name(dev, newname); |
| if (err < 0) |
| return err; |
| } |
| else if (__dev_get_by_name(net, newname)) |
| return -EEXIST; |
| else |
| strlcpy(dev->name, newname, IFNAMSIZ); |
| |
| 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(&dev->name_hlist); |
| hlist_add_head(&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) { |
| if (err) { |
| printk(KERN_ERR |
| "%s: name change rollback failed: %d.\n", |
| dev->name, ret); |
| } else { |
| err = ret; |
| memcpy(dev->name, oldname, IFNAMSIZ); |
| goto rollback; |
| } |
| } |
| |
| 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); |
| } |
| } |
| |
| void netdev_bonding_change(struct net_device *dev) |
| { |
| call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, 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; |
| |
| read_lock(&dev_base_lock); |
| dev = __dev_get_by_name(net, name); |
| read_unlock(&dev_base_lock); |
| |
| if (!dev && capable(CAP_SYS_MODULE)) |
| request_module("%s", name); |
| } |
| |
| /** |
| * 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 = 0; |
| |
| ASSERT_RTNL(); |
| |
| /* |
| * Is it already up? |
| */ |
| |
| if (dev->flags & IFF_UP) |
| return 0; |
| |
| /* |
| * Is it even present? |
| */ |
| if (!netif_device_present(dev)) |
| return -ENODEV; |
| |
| /* |
| * Call device private open method |
| */ |
| set_bit(__LINK_STATE_START, &dev->state); |
| |
| if (dev->validate_addr) |
| ret = dev->validate_addr(dev); |
| |
| if (!ret && dev->open) |
| ret = dev->open(dev); |
| |
| /* |
| * If it went open OK then: |
| */ |
| |
| if (ret) |
| clear_bit(__LINK_STATE_START, &dev->state); |
| else { |
| /* |
| * Set the flags. |
| */ |
| dev->flags |= IFF_UP; |
| |
| /* |
| * Initialize multicasting status |
| */ |
| dev_set_rx_mode(dev); |
| |
| /* |
| * Wakeup transmit queue engine |
| */ |
| dev_activate(dev); |
| |
| /* |
| * ... and announce new interface. |
| */ |
| call_netdevice_notifiers(NETDEV_UP, dev); |
| } |
| |
| return ret; |
| } |
| |
| /** |
| * 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) |
| { |
| ASSERT_RTNL(); |
| |
| might_sleep(); |
| |
| if (!(dev->flags & IFF_UP)) |
| return 0; |
| |
| /* |
| * Tell people we are going down, so that they can |
| * prepare to death, when device is still operating. |
| */ |
| 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(dev); |
| |
| /* |
| * 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 (dev->stop) |
| dev->stop(dev); |
| |
| /* |
| * Device is now down. |
| */ |
| |
| dev->flags &= ~IFF_UP; |
| |
| /* |
| * Tell people we are down |
| */ |
| call_netdevice_notifiers(NETDEV_DOWN, dev); |
| |
| return 0; |
| } |
| |
| |
| /** |
| * 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 (dev->ethtool_ops && dev->ethtool_ops->get_flags && |
| dev->ethtool_ops->set_flags) { |
| u32 flags = dev->ethtool_ops->get_flags(dev); |
| if (flags & ETH_FLAG_LRO) { |
| flags &= ~ETH_FLAG_LRO; |
| dev->ethtool_ops->set_flags(dev, flags); |
| } |
| } |
| WARN_ON(dev->features & NETIF_F_LRO); |
| } |
| EXPORT_SYMBOL(dev_disable_lro); |
| |
| |
| static int dev_boot_phase = 1; |
| |
| /* |
| * Device change register/unregister. These are not inline or static |
| * as we export them to the world. |
| */ |
| |
| /** |
| * 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) |
| break; |
| |
| 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); |
| } |
| } |
| |
| raw_notifier_chain_unregister(&netdev_chain, nb); |
| goto unlock; |
| } |
| |
| /** |
| * 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. |
| */ |
| |
| int unregister_netdevice_notifier(struct notifier_block *nb) |
| { |
| int err; |
| |
| rtnl_lock(); |
| err = raw_notifier_chain_unregister(&netdev_chain, nb); |
| rtnl_unlock(); |
| return err; |
| } |
| |
| /** |
| * 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) |
| { |
| return raw_notifier_call_chain(&netdev_chain, val, dev); |
| } |
| |
| /* When > 0 there are consumers of rx skb time stamps */ |
| static atomic_t netstamp_needed = ATOMIC_INIT(0); |
| |
| void net_enable_timestamp(void) |
| { |
| atomic_inc(&netstamp_needed); |
| } |
| |
| void net_disable_timestamp(void) |
| { |
| atomic_dec(&netstamp_needed); |
| } |
| |
| static inline void net_timestamp(struct sk_buff *skb) |
| { |
| if (atomic_read(&netstamp_needed)) |
| __net_timestamp(skb); |
| else |
| skb->tstamp.tv64 = 0; |
| } |
| |
| /* |
| * 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; |
| |
| net_timestamp(skb); |
| |
| 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)) { |
| struct sk_buff *skb2= skb_clone(skb, GFP_ATOMIC); |
| if (!skb2) |
| break; |
| |
| /* 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) { |
| if (net_ratelimit()) |
| printk(KERN_CRIT "protocol %04x is " |
| "buggy, dev %s\n", |
| skb2->protocol, dev->name); |
| skb_reset_network_header(skb2); |
| } |
| |
| skb2->transport_header = skb2->network_header; |
| skb2->pkt_type = PACKET_OUTGOING; |
| ptype->func(skb2, skb->dev, ptype, skb->dev); |
| } |
| } |
| rcu_read_unlock(); |
| } |
| |
| |
| 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 = sd->output_queue; |
| sd->output_queue = q; |
| 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_stop_queue(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_wake_queue(dev); |
| __netdev_watchdog_up(dev); |
| } |
| } |
| EXPORT_SYMBOL(netif_device_attach); |
| |
| static bool can_checksum_protocol(unsigned long features, __be16 protocol) |
| { |
| return ((features & NETIF_F_GEN_CSUM) || |
| ((features & NETIF_F_IP_CSUM) && |
| protocol == htons(ETH_P_IP)) || |
| ((features & NETIF_F_IPV6_CSUM) && |
| protocol == htons(ETH_P_IPV6))); |
| } |
| |
| static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb) |
| { |
| if (can_checksum_protocol(dev->features, skb->protocol)) |
| return true; |
| |
| if (skb->protocol == htons(ETH_P_8021Q)) { |
| struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; |
| if (can_checksum_protocol(dev->features & dev->vlan_features, |
| veh->h_vlan_encapsulated_proto)) |
| return true; |
| } |
| |
| return false; |
| } |
| |
| /* |
| * 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)) { |
| /* Let GSO fix up the checksum. */ |
| goto out_set_summed; |
| } |
| |
| offset = skb->csum_start - skb_headroom(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; |
| } |
| |
| /** |
| * 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, int features) |
| { |
| struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); |
| struct packet_type *ptype; |
| __be16 type = skb->protocol; |
| int err; |
| |
| BUG_ON(skb_shinfo(skb)->frag_list); |
| |
| skb_reset_mac_header(skb); |
| skb->mac_len = skb->network_header - skb->mac_header; |
| __skb_pull(skb, skb->mac_len); |
| |
| if (WARN_ON(skb->ip_summed != CHECKSUM_PARTIAL)) { |
| 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()) { |
| printk(KERN_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 inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb) |
| { |
| #ifdef CONFIG_HIGHMEM |
| int i; |
| |
| if (dev->features & NETIF_F_HIGHDMA) |
| return 0; |
| |
| for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) |
| if (PageHighMem(skb_shinfo(skb)->frags[i].page)) |
| 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 |
| * |
| * This function segments the given skb and stores the list of segments |
| * in skb->next. |
| */ |
| static int dev_gso_segment(struct sk_buff *skb) |
| { |
| struct net_device *dev = skb->dev; |
| struct sk_buff *segs; |
| int features = dev->features & ~(illegal_highdma(dev, skb) ? |
| NETIF_F_SG : 0); |
| |
| 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; |
| } |
| |
| int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, |
| struct netdev_queue *txq) |
| { |
| if (likely(!skb->next)) { |
| if (!list_empty(&ptype_all)) |
| dev_queue_xmit_nit(skb, dev); |
| |
| if (netif_needs_gso(dev, skb)) { |
| if (unlikely(dev_gso_segment(skb))) |
| goto out_kfree_skb; |
| if (skb->next) |
| goto gso; |
| } |
| |
| return dev->hard_start_xmit(skb, dev); |
| } |
| |
| gso: |
| do { |
| struct sk_buff *nskb = skb->next; |
| int rc; |
| |
| skb->next = nskb->next; |
| nskb->next = NULL; |
| rc = dev->hard_start_xmit(nskb, dev); |
| if (unlikely(rc)) { |
| nskb->next = skb->next; |
| skb->next = nskb; |
| return rc; |
| } |
| if (unlikely(netif_tx_queue_stopped(txq) && skb->next)) |
| return NETDEV_TX_BUSY; |
| } while (skb->next); |
| |
| skb->destructor = DEV_GSO_CB(skb)->destructor; |
| |
| out_kfree_skb: |
| kfree_skb(skb); |
| return 0; |
| } |
| |
| static u32 simple_tx_hashrnd; |
| static int simple_tx_hashrnd_initialized = 0; |
| |
| static u16 simple_tx_hash(struct net_device *dev, struct sk_buff *skb) |
| { |
| u32 addr1, addr2, ports; |
| u32 hash, ihl; |
| u8 ip_proto = 0; |
| |
| if (unlikely(!simple_tx_hashrnd_initialized)) { |
| get_random_bytes(&simple_tx_hashrnd, 4); |
| simple_tx_hashrnd_initialized = 1; |
| } |
| |
| switch (skb->protocol) { |
| case htons(ETH_P_IP): |
| if (!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET))) |
| ip_proto = ip_hdr(skb)->protocol; |
| addr1 = ip_hdr(skb)->saddr; |
| addr2 = ip_hdr(skb)->daddr; |
| ihl = ip_hdr(skb)->ihl; |
| break; |
| case htons(ETH_P_IPV6): |
| ip_proto = ipv6_hdr(skb)->nexthdr; |
| addr1 = ipv6_hdr(skb)->saddr.s6_addr32[3]; |
| addr2 = ipv6_hdr(skb)->daddr.s6_addr32[3]; |
| ihl = (40 >> 2); |
| break; |
| default: |
| return 0; |
| } |
| |
| |
| switch (ip_proto) { |
| case IPPROTO_TCP: |
| case IPPROTO_UDP: |
| case IPPROTO_DCCP: |
| case IPPROTO_ESP: |
| case IPPROTO_AH: |
| case IPPROTO_SCTP: |
| case IPPROTO_UDPLITE: |
| ports = *((u32 *) (skb_network_header(skb) + (ihl * 4))); |
| break; |
| |
| default: |
| ports = 0; |
| break; |
| } |
| |
| hash = jhash_3words(addr1, addr2, ports, simple_tx_hashrnd); |
| |
| return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32); |
| } |
| |
| static struct netdev_queue *dev_pick_tx(struct net_device *dev, |
| struct sk_buff *skb) |
| { |
| u16 queue_index = 0; |
| |
| if (dev->select_queue) |
| queue_index = dev->select_queue(dev, skb); |
| else if (dev->real_num_tx_queues > 1) |
| queue_index = simple_tx_hash(dev, skb); |
| |
| skb_set_queue_mapping(skb, queue_index); |
| return netdev_get_tx_queue(dev, queue_index); |
| } |
| |
| /** |
| * 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; |
| |
| /* GSO will handle the following emulations directly. */ |
| if (netif_needs_gso(dev, skb)) |
| goto gso; |
| |
| if (skb_shinfo(skb)->frag_list && |
| !(dev->features & NETIF_F_FRAGLIST) && |
| __skb_linearize(skb)) |
| goto out_kfree_skb; |
| |
| /* Fragmented skb is linearized if device does not support SG, |
| * or if at least one of fragments is in highmem and device |
| * does not support DMA from it. |
| */ |
| if (skb_shinfo(skb)->nr_frags && |
| (!(dev->features & NETIF_F_SG) || illegal_highdma(dev, skb)) && |
| __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->csum_start - |
| skb_headroom(skb)); |
| if (!dev_can_checksum(dev, skb) && skb_checksum_help(skb)) |
| goto out_kfree_skb; |
| } |
| |
| gso: |
| /* Disable soft irqs for various locks below. Also |
| * stops preemption for RCU. |
| */ |
| rcu_read_lock_bh(); |
| |
| txq = dev_pick_tx(dev, skb); |
| q = rcu_dereference(txq->qdisc); |
| |
| #ifdef CONFIG_NET_CLS_ACT |
| skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS); |
| #endif |
| if (q->enqueue) { |
| spinlock_t *root_lock = qdisc_lock(q); |
| |
| spin_lock(root_lock); |
| |
| if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { |
| kfree_skb(skb); |
| rc = NET_XMIT_DROP; |
| } else { |
| rc = qdisc_enqueue_root(skb, q); |
| qdisc_run(q); |
| } |
| spin_unlock(root_lock); |
| |
| 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) { |
| |
| HARD_TX_LOCK(dev, txq, cpu); |
| |
| if (!netif_tx_queue_stopped(txq)) { |
| rc = 0; |
| if (!dev_hard_start_xmit(skb, dev, txq)) { |
| HARD_TX_UNLOCK(dev, txq); |
| goto out; |
| } |
| } |
| HARD_TX_UNLOCK(dev, txq); |
| if (net_ratelimit()) |
| printk(KERN_CRIT "Virtual device %s asks to " |
| "queue packet!\n", dev->name); |
| } else { |
| /* Recursion is detected! It is possible, |
| * unfortunately */ |
| if (net_ratelimit()) |
| printk(KERN_CRIT "Dead loop on virtual device " |
| "%s, fix it urgently!\n", dev->name); |
| } |
| } |
| |
| rc = -ENETDOWN; |
| rcu_read_unlock_bh(); |
| |
| out_kfree_skb: |
| kfree_skb(skb); |
| return rc; |
| out: |
| rcu_read_unlock_bh(); |
| return rc; |
| } |
| |
| |
| /*======================================================================= |
| Receiver routines |
| =======================================================================*/ |
| |
| int netdev_max_backlog __read_mostly = 1000; |
| int netdev_budget __read_mostly = 300; |
| int weight_p __read_mostly = 64; /* old backlog weight */ |
| |
| DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, }; |
| |
| |
| /** |
| * 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) |
| { |
| struct softnet_data *queue; |
| unsigned long flags; |
| |
| /* if netpoll wants it, pretend we never saw it */ |
| if (netpoll_rx(skb)) |
| return NET_RX_DROP; |
| |
| if (!skb->tstamp.tv64) |
| net_timestamp(skb); |
| |
| /* |
| * The code is rearranged so that the path is the most |
| * short when CPU is congested, but is still operating. |
| */ |
| local_irq_save(flags); |
| queue = &__get_cpu_var(softnet_data); |
| |
| __get_cpu_var(netdev_rx_stat).total++; |
| if (queue->input_pkt_queue.qlen <= netdev_max_backlog) { |
| if (queue->input_pkt_queue.qlen) { |
| enqueue: |
| __skb_queue_tail(&queue->input_pkt_queue, skb); |
| local_irq_restore(flags); |
| return NET_RX_SUCCESS; |
| } |
| |
| napi_schedule(&queue->backlog); |
| goto enqueue; |
| } |
| |
| __get_cpu_var(netdev_rx_stat).dropped++; |
| local_irq_restore(flags); |
| |
| kfree_skb(skb); |
| return NET_RX_DROP; |
| } |
| |
| 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)); |
| __kfree_skb(skb); |
| } |
| } |
| |
| if (sd->output_queue) { |
| struct Qdisc *head; |
| |
| local_irq_disable(); |
| head = sd->output_queue; |
| sd->output_queue = NULL; |
| 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); |
| } |
| } |
| } |
| } |
| } |
| |
| 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); |
| } |
| |
| #if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE) |
| /* These hooks defined here for ATM */ |
| struct net_bridge; |
| struct net_bridge_fdb_entry *(*br_fdb_get_hook)(struct net_bridge *br, |
| unsigned char *addr); |
| void (*br_fdb_put_hook)(struct net_bridge_fdb_entry *ent) __read_mostly; |
| |
| /* |
| * If bridge module is loaded call bridging hook. |
| * returns NULL if packet was consumed. |
| */ |
| struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p, |
| struct sk_buff *skb) __read_mostly; |
| static inline struct sk_buff *handle_bridge(struct sk_buff *skb, |
| struct packet_type **pt_prev, int *ret, |
| struct net_device *orig_dev) |
| { |
| struct net_bridge_port *port; |
| |
| if (skb->pkt_type == PACKET_LOOPBACK || |
| (port = rcu_dereference(skb->dev->br_port)) == NULL) |
| return skb; |
| |
| if (*pt_prev) { |
| *ret = deliver_skb(skb, *pt_prev, orig_dev); |
| *pt_prev = NULL; |
| } |
| |
| return br_handle_frame_hook(port, skb); |
| } |
| #else |
| #define handle_bridge(skb, pt_prev, ret, orig_dev) (skb) |
| #endif |
| |
| #if defined(CONFIG_MACVLAN) || defined(CONFIG_MACVLAN_MODULE) |
| struct sk_buff *(*macvlan_handle_frame_hook)(struct sk_buff *skb) __read_mostly; |
| EXPORT_SYMBOL_GPL(macvlan_handle_frame_hook); |
| |
| static inline struct sk_buff *handle_macvlan(struct sk_buff *skb, |
| struct packet_type **pt_prev, |
| int *ret, |
| struct net_device *orig_dev) |
| { |
| if (skb->dev->macvlan_port == NULL) |
| return skb; |
| |
| if (*pt_prev) { |
| *ret = deliver_skb(skb, *pt_prev, orig_dev); |
| *pt_prev = NULL; |
| } |
| return macvlan_handle_frame_hook(skb); |
| } |
| #else |
| #define handle_macvlan(skb, pt_prev, ret, orig_dev) (skb) |
| #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 doesnt stop any functionality; if you dont have |
| * the ingress scheduler, you just cant add policies on ingress. |
| * |
| */ |
| static int ing_filter(struct sk_buff *skb) |
| { |
| struct net_device *dev = skb->dev; |
| u32 ttl = G_TC_RTTL(skb->tc_verd); |
| struct netdev_queue *rxq; |
| int result = TC_ACT_OK; |
| struct Qdisc *q; |
| |
| if (MAX_RED_LOOP < ttl++) { |
| printk(KERN_WARNING |
| "Redir loop detected Dropping packet (%d->%d)\n", |
| 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); |
| |
| rxq = &dev->rx_queue; |
| |
| 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) |
| { |
| if (skb->dev->rx_queue.qdisc == &noop_qdisc) |
| goto out; |
| |
| if (*pt_prev) { |
| *ret = deliver_skb(skb, *pt_prev, orig_dev); |
| *pt_prev = NULL; |
| } else { |
| /* Huh? Why does turning on AF_PACKET affect this? */ |
| skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd); |
| } |
| |
| switch (ing_filter(skb)) { |
| case TC_ACT_SHOT: |
| case TC_ACT_STOLEN: |
| kfree_skb(skb); |
| return NULL; |
| } |
| |
| out: |
| skb->tc_verd = 0; |
| return skb; |
| } |
| #endif |
| |
| /* |
| * netif_nit_deliver - deliver received packets to network taps |
| * @skb: buffer |
| * |
| * This function is used to deliver incoming packets to network |
| * taps. It should be used when the normal netif_receive_skb path |
| * is bypassed, for example because of VLAN acceleration. |
| */ |
| void netif_nit_deliver(struct sk_buff *skb) |
| { |
| struct packet_type *ptype; |
| |
| if (list_empty(&ptype_all)) |
| return; |
| |
| skb_reset_network_header(skb); |
| skb_reset_transport_header(skb); |
| skb->mac_len = skb->network_header - skb->mac_header; |
| |
| rcu_read_lock(); |
| list_for_each_entry_rcu(ptype, &ptype_all, list) { |
| if (!ptype->dev || ptype->dev == skb->dev) |
| deliver_skb(skb, ptype, skb->dev); |
| } |
| rcu_read_unlock(); |
| } |
| |
| /** |
| * 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) |
| { |
| struct packet_type *ptype, *pt_prev; |
| struct net_device *orig_dev; |
| struct net_device *null_or_orig; |
| int ret = NET_RX_DROP; |
| __be16 type; |
| |
| /* if we've gotten here through NAPI, check netpoll */ |
| if (netpoll_receive_skb(skb)) |
| return NET_RX_DROP; |
| |
| if (!skb->tstamp.tv64) |
| net_timestamp(skb); |
| |
| if (!skb->iif) |
| skb->iif = skb->dev->ifindex; |
| |
| null_or_orig = NULL; |
| orig_dev = skb->dev; |
| if (orig_dev->master) { |
| if (skb_bond_should_drop(skb)) |
| null_or_orig = orig_dev; /* deliver only exact match */ |
| else |
| skb->dev = orig_dev->master; |
| } |
| |
| __get_cpu_var(netdev_rx_stat).total++; |
| |
| skb_reset_network_header(skb); |
| skb_reset_transport_header(skb); |
| skb->mac_len = skb->network_header - skb->mac_header; |
| |
| pt_prev = NULL; |
| |
| rcu_read_lock(); |
| |
| /* Don't receive packets in an exiting network namespace */ |
| if (!net_alive(dev_net(skb->dev))) |
| 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 == null_or_orig || ptype->dev == skb->dev || |
| ptype->dev == orig_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 |
| |
| skb = handle_bridge(skb, &pt_prev, &ret, orig_dev); |
| if (!skb) |
| goto out; |
| skb = handle_macvlan(skb, &pt_prev, &ret, orig_dev); |
| if (!skb) |
| goto out; |
| |
| 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_orig || 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 { |
| 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; |
| } |
| |
| /* Network device is going away, flush any packets still pending */ |
| static void flush_backlog(void *arg) |
| { |
| struct net_device *dev = arg; |
| struct softnet_data *queue = &__get_cpu_var(softnet_data); |
| struct sk_buff *skb, *tmp; |
| |
| skb_queue_walk_safe(&queue->input_pkt_queue, skb, tmp) |
| if (skb->dev == dev) { |
| __skb_unlink(skb, &queue->input_pkt_queue); |
| kfree_skb(skb); |
| } |
| } |
| |
| static int process_backlog(struct napi_struct *napi, int quota) |
| { |
| int work = 0; |
| struct softnet_data *queue = &__get_cpu_var(softnet_data); |
| unsigned long start_time = jiffies; |
| |
| napi->weight = weight_p; |
| do { |
| struct sk_buff *skb; |
| |
| local_irq_disable(); |
| skb = __skb_dequeue(&queue->input_pkt_queue); |
| if (!skb) { |
| __napi_complete(napi); |
| local_irq_enable(); |
| break; |
| } |
| local_irq_enable(); |
| |
| netif_receive_skb(skb); |
| } while (++work < quota && jiffies == start_time); |
| |
| 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); |
| list_add_tail(&n->poll_list, &__get_cpu_var(softnet_data).poll_list); |
| __raise_softirq_irqoff(NET_RX_SOFTIRQ); |
| local_irq_restore(flags); |
| } |
| EXPORT_SYMBOL(__napi_schedule); |
| |
| |
| static void net_rx_action(struct softirq_action *h) |
| { |
| struct list_head *list = &__get_cpu_var(softnet_data).poll_list; |
| unsigned long start_time = jiffies; |
| int budget = netdev_budget; |
| void *have; |
| |
| local_irq_disable(); |
| |
| while (!list_empty(list)) { |
| struct napi_struct *n; |
| int work, weight; |
| |
| /* If softirq window is exhuasted then punt. |
| * |
| * Note that this is a slight policy change from the |
| * previous NAPI code, which would allow up to 2 |
| * jiffies to pass before breaking out. The test |
| * used to be "jiffies - start_time > 1". |
| */ |
| if (unlikely(budget <= 0 || jiffies != start_time)) |
| 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_entry(list->next, 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 |
| * accidently calling ->poll() when NAPI is not scheduled. |
| */ |
| work = 0; |
| if (test_bit(NAPI_STATE_SCHED, &n->state)) |
| work = n->poll(n, weight); |
| |
| 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))) |
| __napi_complete(n); |
| else |
| list_move_tail(&n->poll_list, list); |
| } |
| |
| netpoll_poll_unlock(have); |
| } |
| out: |
| local_irq_enable(); |
| |
| #ifdef CONFIG_NET_DMA |
| /* |
| * There may not be any more sk_buffs coming right now, so push |
| * any pending DMA copies to hardware |
| */ |
| if (!cpus_empty(net_dma.channel_mask)) { |
| int chan_idx; |
| for_each_cpu_mask_nr(chan_idx, net_dma.channel_mask) { |
| struct dma_chan *chan = net_dma.channels[chan_idx]; |
| if (chan) |
| dma_async_memcpy_issue_pending(chan); |
| } |
| } |
| #endif |
| |
| return; |
| |
| softnet_break: |
| __get_cpu_var(netdev_rx_stat).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; |
| } |
| |
| |
| /* |
| * 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; |
| |
| read_lock(&dev_base_lock); |
| dev = __dev_get_by_index(net, ifr.ifr_ifindex); |
| if (!dev) { |
| read_unlock(&dev_base_lock); |
| return -ENODEV; |
| } |
| |
| strcpy(ifr.ifr_name, dev->name); |
| read_unlock(&dev_base_lock); |
| |
| 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 |
| /* |
| * 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(dev_base_lock) |
| { |
| struct net *net = seq_file_net(seq); |
| loff_t off; |
| struct net_device *dev; |
| |
| read_lock(&dev_base_lock); |
| if (!*pos) |
| return SEQ_START_TOKEN; |
| |
| off = 1; |
| for_each_netdev(net, dev) |
| if (off++ == *pos) |
| return dev; |
| |
| return NULL; |
| } |
| |
| void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) |
| { |
| struct net *net = seq_file_net(seq); |
| ++*pos; |
| return v == SEQ_START_TOKEN ? |
| first_net_device(net) : next_net_device((struct net_device *)v); |
| } |
| |
| void dev_seq_stop(struct seq_file *seq, void *v) |
| __releases(dev_base_lock) |
| { |
| read_unlock(&dev_base_lock); |
| } |
| |
| static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) |
| { |
| struct net_device_stats *stats = dev->get_stats(dev); |
| |
| seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu " |
| "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n", |
| dev->name, stats->rx_bytes, stats->rx_packets, |
| stats->rx_errors, |
| stats->rx_dropped + stats->rx_missed_errors, |
| stats->rx_fifo_errors, |
| stats->rx_length_errors + stats->rx_over_errors + |
| stats->rx_crc_errors + stats->rx_frame_errors, |
| stats->rx_compressed, stats->multicast, |
| stats->tx_bytes, stats->tx_packets, |
| stats->tx_errors, stats->tx_dropped, |
| stats->tx_fifo_errors, stats->collisions, |
| stats->tx_carrier_errors + |
| stats->tx_aborted_errors + |
| stats->tx_window_errors + |
| stats->tx_heartbeat_errors, |
| stats->tx_compressed); |
| } |
| |
| /* |
| * Called from the PROCfs module. This now uses the new arbitrary sized |
| * /proc/net interface to create /proc/net/dev |
| */ |
| static int dev_seq_show(struct seq_file *seq, void *v) |
| { |
| if (v == SEQ_START_TOKEN) |
| seq_puts(seq, "Inter-| Receive " |
| " | Transmit\n" |
| " face |bytes packets errs drop fifo frame " |
| "compressed multicast|bytes packets errs " |
| "drop fifo colls carrier compressed\n"); |
| else |
| dev_seq_printf_stats(seq, v); |
| return 0; |
| } |
| |
| static struct netif_rx_stats *softnet_get_online(loff_t *pos) |
| { |
| struct netif_rx_stats *rc = NULL; |
| |
| while (*pos < nr_cpu_ids) |
| if (cpu_online(*pos)) { |
| rc = &per_cpu(netdev_rx_stat, *pos); |
| break; |
| } else |
| ++*pos; |
| return rc; |
| } |
| |
| static void *softnet_seq_start(struct seq_file *seq, loff_t *pos) |
| { |
| return softnet_get_online(pos); |
| } |
| |
| static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos) |
| { |
| ++*pos; |
| return softnet_get_online(pos); |
| } |
| |
| static void softnet_seq_stop(struct seq_file *seq, void *v) |
| { |
| } |
| |
| static int softnet_seq_show(struct seq_file *seq, void *v) |
| { |
| struct netif_rx_stats *s = v; |
| |
| seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n", |
| s->total, s->dropped, s->time_squeeze, 0, |
| 0, 0, 0, 0, /* was fastroute */ |
| s->cpu_collision ); |
| return 0; |
| } |
| |
| static const struct seq_operations dev_seq_ops = { |
| .start = dev_seq_start, |
| .next = dev_seq_next, |
| .stop = dev_seq_stop, |
| .show = dev_seq_show, |
| }; |
| |
| static int dev_seq_open(struct inode *inode, struct file *file) |
| { |
| return seq_open_net(inode, file, &dev_seq_ops, |
| sizeof(struct seq_net_private)); |
| } |
| |
| static const struct file_operations dev_seq_fops = { |
| .owner = THIS_MODULE, |
| .open = dev_seq_open, |
| .read = seq_read, |
| .llseek = seq_lseek, |
| .release = seq_release_net, |
| }; |
| |
| static const struct seq_operations softnet_seq_ops = { |
| .start = softnet_seq_start, |
| .next = softnet_seq_next, |
| .stop = softnet_seq_stop, |
| .show = softnet_seq_show, |
| }; |
| |
| static int softnet_seq_open(struct inode *inode, struct file *file) |
| { |
| return seq_open(file, &softnet_seq_ops); |
| } |
| |
| static const struct file_operations softnet_seq_fops = { |
| .owner = THIS_MODULE, |
| .open = softnet_seq_open, |
| .read = seq_read, |
| .llseek = seq_lseek, |
| .release = seq_release, |
| }; |
| |
| static void *ptype_get_idx(loff_t pos) |
| { |
| struct packet_type *pt = NULL; |
| loff_t i = 0; |
| int t; |
| |
| list_for_each_entry_rcu(pt, &ptype_all, list) { |
| if (i == pos) |
| return pt; |
| ++i; |
| } |
| |
| for (t = 0; t < PTYPE_HASH_SIZE; t++) { |
| list_for_each_entry_rcu(pt, &ptype_base[t], list) { |
| if (i == pos) |
| return pt; |
| ++i; |
| } |
| } |
| return NULL; |
| } |
| |
| static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) |
| __acquires(RCU) |
| { |
| rcu_read_lock(); |
| return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN; |
| } |
| |
| static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) |
| { |
| struct packet_type *pt; |
| struct list_head *nxt; |
| int hash; |
| |
| ++*pos; |
| if (v == SEQ_START_TOKEN) |
| return ptype_get_idx(0); |
| |
| pt = v; |
| nxt = pt->list.next; |
| if (pt->type == htons(ETH_P_ALL)) { |
| if (nxt != &ptype_all) |
| goto found; |
| hash = 0; |
| nxt = ptype_base[0].next; |
| } else |
| hash = ntohs(pt->type) & PTYPE_HASH_MASK; |
| |
| while (nxt == &ptype_base[hash]) { |
| if (++hash >= PTYPE_HASH_SIZE) |
| return NULL; |
| nxt = ptype_base[hash].next; |
| } |
| found: |
| return list_entry(nxt, struct packet_type, list); |
| } |
| |
| static void ptype_seq_stop(struct seq_file *seq, void *v) |
| __releases(RCU) |
| { |
| rcu_read_unlock(); |
| } |
| |
| static void ptype_seq_decode(struct seq_file *seq, void *sym) |
| { |
| #ifdef CONFIG_KALLSYMS |
| unsigned long offset = 0, symsize; |
| const char *symname; |
| char *modname; |
| char namebuf[128]; |
| |
| symname = kallsyms_lookup((unsigned long)sym, &symsize, &offset, |
| &modname, namebuf); |
| |
| if (symname) { |
| char *delim = ":"; |
| |
| if (!modname) |
| modname = delim = ""; |
| seq_printf(seq, "%s%s%s%s+0x%lx", delim, modname, delim, |
| symname, offset); |
| return; |
| } |
| #endif |
| |
| seq_printf(seq, "[%p]", sym); |
| } |
| |
| static int ptype_seq_show(struct seq_file *seq, void *v) |
| { |
| struct packet_type *pt = v; |
| |
| if (v == SEQ_START_TOKEN) |
| seq_puts(seq, "Type Device Function\n"); |
| else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { |
| if (pt->type == htons(ETH_P_ALL)) |
| seq_puts(seq, "ALL "); |
| else |
| seq_printf(seq, "%04x", ntohs(pt->type)); |
| |
| seq_printf(seq, " %-8s ", |
| pt->dev ? pt->dev->name : ""); |
| ptype_seq_decode(seq, pt->func); |
| seq_putc(seq, '\n'); |
| } |
| |
| return 0; |
| } |
| |
| static const struct seq_operations ptype_seq_ops = { |
| .start = ptype_seq_start, |
| .next = ptype_seq_next, |
| .stop = ptype_seq_stop, |
| .show = ptype_seq_show, |
| }; |
| |
| static int ptype_seq_open(struct inode *inode, struct file *file) |
| { |
| return seq_open_net(inode, file, &ptype_seq_ops, |
| sizeof(struct seq_net_private)); |
| } |
| |
| static const struct file_operations ptype_seq_fops = { |
| .owner = THIS_MODULE, |
| .open = ptype_seq_open, |
| .read = seq_read, |
| .llseek = seq_lseek, |
| .release = seq_release_net, |
| }; |
| |
| |
| static int __net_init dev_proc_net_init(struct net *net) |
| { |
| int rc = -ENOMEM; |
| |
| if (!proc_net_fops_create(net, "dev", S_IRUGO, &dev_seq_fops)) |
| goto out; |
| if (!proc_net_fops_create(net, "softnet_stat", S_IRUGO, &softnet_seq_fops)) |
| goto out_dev; |
| if (!proc_net_fops_create(net, "ptype", S_IRUGO, &ptype_seq_fops)) |
| goto out_softnet; |
| |
| if (wext_proc_init(net)) |
| goto out_ptype; |
| rc = 0; |
| out: |
| return rc; |
| out_ptype: |
| proc_net_remove(net, "ptype"); |
| out_softnet: |
| proc_net_remove(net, "softnet_stat"); |
| out_dev: |
| proc_net_remove(net, "dev"); |
| goto out; |
| } |
| |
| static void __net_exit dev_proc_net_exit(struct net *net) |
| { |
| wext_proc_exit(net); |
| |
| proc_net_remove(net, "ptype"); |
| proc_net_remove(net, "softnet_stat"); |
| proc_net_remove(net, "dev"); |
| } |
| |
| static struct pernet_operations __net_initdata dev_proc_ops = { |
| .init = dev_proc_net_init, |
| .exit = dev_proc_net_exit, |
| }; |
| |
| static int __init dev_proc_init(void) |
| { |
| return register_pernet_subsys(&dev_proc_ops); |
| } |
| #else |
| #define dev_proc_init() 0 |
| #endif /* CONFIG_PROC_FS */ |
| |
| |
| /** |
| * netdev_set_master - set up master/slave pair |
| * @slave: slave device |
| * @master: new master device |
| * |
| * Changes the master device of the slave. Pass %NULL to break the |
| * bonding. The caller must hold the RTNL semaphore. On a failure |
| * a negative errno code is returned. On success the reference counts |
| * are adjusted, %RTM_NEWLINK is sent to the routing socket and the |
| * function returns zero. |
| */ |
| int netdev_set_master(struct net_device *slave, struct net_device *master) |
| { |
| struct net_device *old = slave->master; |
| |
| ASSERT_RTNL(); |
| |
| if (master) { |
| if (old) |
| return -EBUSY; |
| dev_hold(master); |
| } |
| |
| slave->master = master; |
| |
| synchronize_net(); |
| |
| if (old) |
| dev_put(old); |
| |
| if (master) |
| slave->flags |= IFF_SLAVE; |
| else |
| slave->flags &= ~IFF_SLAVE; |
| |
| rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE); |
| return 0; |
| } |
| |
| static void dev_change_rx_flags(struct net_device *dev, int flags) |
| { |
| if (dev->flags & IFF_UP && dev->change_rx_flags) |
| dev->change_rx_flags(dev, flags); |
| } |
| |
| static int __dev_set_promiscuity(struct net_device *dev, int inc) |
| { |
| unsigned short old_flags = dev->flags; |
| |
| ASSERT_RTNL(); |
| |
| dev->flags |= IFF_PROMISC; |
| dev->promiscuity += inc; |
| if (dev->promiscuity == 0) { |
| /* |
| * Avoid overflow. |
| * If inc causes overflow, untouch promisc and return error. |
| */ |
| if (inc < 0) |
| dev->flags &= ~IFF_PROMISC; |
| else { |
| dev->promiscuity -= inc; |
| printk(KERN_WARNING "%s: promiscuity touches roof, " |
| "set promiscuity failed, promiscuity feature " |
| "of device might be broken.\n", dev->name); |
| return -EOVERFLOW; |
| } |
| } |
| if (dev->flags != old_flags) { |
| printk(KERN_INFO "device %s %s promiscuous mode\n", |
| dev->name, (dev->flags & IFF_PROMISC) ? "entered" : |
| "left"); |
| if (audit_enabled) |
| audit_log(current->audit_context, GFP_ATOMIC, |
| AUDIT_ANOM_PROMISCUOUS, |
| "dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u", |
| dev->name, (dev->flags & IFF_PROMISC), |
| (old_flags & IFF_PROMISC), |
| audit_get_loginuid(current), |
| current->uid, current->gid, |
| audit_get_sessionid(current)); |
| |
| dev_change_rx_flags(dev, IFF_PROMISC); |
| } |
| return 0; |
| } |
| |
| /** |
| * dev_set_promiscuity - update promiscuity count on a device |
| * @dev: device |
| * @inc: modifier |
| * |
| * Add or remove promiscuity from a device. While the count in the device |
| * remains above zero the interface remains promiscuous. Once it hits zero |
| * the device reverts back to normal filtering operation. A negative inc |
| * value is used to drop promiscuity on the device. |
| * Return 0 if successful or a negative errno code on error. |
| */ |
| int dev_set_promiscuity(struct net_device *dev, int inc) |
| { |
| unsigned short old_flags = dev->flags; |
| int err; |
| |
| err = __dev_set_promiscuity(dev, inc); |
| if (err < 0) |
| return err; |
| if (dev->flags != old_flags) |
| dev_set_rx_mode(dev); |
| return err; |
| } |
| |
| /** |
| * dev_set_allmulti - update allmulti count on a device |
| * @dev: device |
| * @inc: modifier |
| * |
| * Add or remove reception of all multicast frames to a device. While the |
| * count in the device remains above zero the interface remains listening |
| * to all interfaces. Once it hits zero the device reverts back to normal |
| * filtering operation. A negative @inc value is used to drop the counter |
| * when releasing a resource needing all multicasts. |
| * Return 0 if successful or a negative errno code on error. |
| */ |
| |
| int dev_set_allmulti(struct net_device *dev, int inc) |
| { |
| unsigned short old_flags = dev->flags; |
| |
| ASSERT_RTNL(); |
| |
| dev->flags |= IFF_ALLMULTI; |
| dev->allmulti += inc; |
| if (dev->allmulti == 0) { |
| /* |
| * Avoid overflow. |
| * If inc causes overflow, untouch allmulti and return error. |
| */ |
| if (inc < 0) |
| dev->flags &= ~IFF_ALLMULTI; |
| else { |
| dev->allmulti -= inc; |
| printk(KERN_WARNING "%s: allmulti touches roof, " |
| "set allmulti failed, allmulti feature of " |
| "device might be broken.\n", dev->name); |
| return -EOVERFLOW; |
| } |
| } |
| if (dev->flags ^ old_flags) { |
| dev_change_rx_flags(dev, IFF_ALLMULTI); |
| dev_set_rx_mode(dev); |
| } |
| return 0; |
| } |
| |
| /* |
| * Upload unicast and multicast address lists to device and |
| * configure RX filtering. When the device doesn't support unicast |
| * filtering it is put in promiscuous mode while unicast addresses |
| * are present. |
| */ |
| void __dev_set_rx_mode(struct net_device *dev) |
| { |
| /* dev_open will call this function so the list will stay sane. */ |
| if (!(dev->flags&IFF_UP)) |
| return; |
| |
| if (!netif_device_present(dev)) |
| return; |
| |
| if (dev->set_rx_mode) |
| dev->set_rx_mode(dev); |
| else { |
| /* Unicast addresses changes may only happen under the rtnl, |
| * therefore calling __dev_set_promiscuity here is safe. |
| */ |
| if (dev->uc_count > 0 && !dev->uc_promisc) { |
| __dev_set_promiscuity(dev, 1); |
| dev->uc_promisc = 1; |
| } else if (dev->uc_count == 0 && dev->uc_promisc) { |
| __dev_set_promiscuity(dev, -1); |
| dev->uc_promisc = 0; |
| } |
| |
| if (dev->set_multicast_list) |
| dev->set_multicast_list(dev); |
| } |
| } |
| |
| void dev_set_rx_mode(struct net_device *dev) |
| { |
| netif_addr_lock_bh(dev); |
| __dev_set_rx_mode(dev); |
| netif_addr_unlock_bh(dev); |
| } |
| |
| int __dev_addr_delete(struct dev_addr_list **list, int *count, |
| void *addr, int alen, int glbl) |
| { |
| struct dev_addr_list *da; |
| |
| for (; (da = *list) != NULL; list = &da->next) { |
| if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 && |
| alen == da->da_addrlen) { |
| if (glbl) { |
| int old_glbl = da->da_gusers; |
| da->da_gusers = 0; |
| if (old_glbl == 0) |
| break; |
| } |
| if (--da->da_users) |
| return 0; |
| |
| *list = da->next; |
| kfree(da); |
| (*count)--; |
| return 0; |
| } |
| } |
| return -ENOENT; |
| } |
| |
| int __dev_addr_add(struct dev_addr_list **list, int *count, |
| void *addr, int alen, int glbl) |
| { |
| struct dev_addr_list *da; |
| |
| for (da = *list; da != NULL; da = da->next) { |
| if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 && |
| da->da_addrlen == alen) { |
| if (glbl) { |
| int old_glbl = da->da_gusers; |
| da->da_gusers = 1; |
| if (old_glbl) |
| return 0; |
| } |
| da->da_users++; |
| return 0; |
| } |
| } |
| |
| da = kzalloc(sizeof(*da), GFP_ATOMIC); |
| if (da == NULL) |
| return -ENOMEM; |
| memcpy(da->da_addr, addr, alen); |
| da->da_addrlen = alen; |
| da->da_users = 1; |
| da->da_gusers = glbl ? 1 : 0; |
| da->next = *list; |
| *list = da; |
| (*count)++; |
| return 0; |
| } |
| |
| /** |
| * dev_unicast_delete - Release secondary unicast address. |
| * @dev: device |
| * @addr: address to delete |
| * @alen: length of @addr |
| * |
| * Release reference to a secondary unicast address and remove it |
| * from the device if the reference count drops to zero. |
| * |
| * The caller must hold the rtnl_mutex. |
| */ |
| int dev_unicast_delete(struct net_device *dev, void *addr, int alen) |
| { |
| int err; |
| |
| ASSERT_RTNL(); |
| |
| netif_addr_lock_bh(dev); |
| err = __dev_addr_delete(&dev->uc_list, &dev->uc_count, addr, alen, 0); |
| if (!err) |
| __dev_set_rx_mode(dev); |
| netif_addr_unlock_bh(dev); |
| return err; |
| } |
| EXPORT_SYMBOL(dev_unicast_delete); |
| |
| /** |
| * dev_unicast_add - add a secondary unicast address |
| * @dev: device |
| * @addr: address to add |
| * @alen: length of @addr |
| * |
| * Add a secondary unicast address to the device or increase |
| * the reference count if it already exists. |
| * |
| * The caller must hold the rtnl_mutex. |
| */ |
| int dev_unicast_add(struct net_device *dev, void *addr, int alen) |
| { |
| int err; |
| |
| ASSERT_RTNL(); |
| |
| netif_addr_lock_bh(dev); |
| err = __dev_addr_add(&dev->uc_list, &dev->uc_count, addr, alen, 0); |
| if (!err) |
| __dev_set_rx_mode(dev); |
| netif_addr_unlock_bh(dev); |
| return err; |
| } |
| EXPORT_SYMBOL(dev_unicast_add); |
| |
| int __dev_addr_sync(struct dev_addr_list **to, int *to_count, |
| struct dev_addr_list **from, int *from_count) |
| { |
| struct dev_addr_list *da, *next; |
| int err = 0; |
| |
| da = *from; |
| while (da != NULL) { |
| next = da->next; |
| if (!da->da_synced) { |
| err = __dev_addr_add(to, to_count, |
| da->da_addr, da->da_addrlen, 0); |
| if (err < 0) |
| break; |
| da->da_synced = 1; |
| da->da_users++; |
| } else if (da->da_users == 1) { |
| __dev_addr_delete(to, to_count, |
| da->da_addr, da->da_addrlen, 0); |
| __dev_addr_delete(from, from_count, |
| da->da_addr, da->da_addrlen, 0); |
| } |
| da = next; |
| } |
| return err; |
| } |
| |
| void __dev_addr_unsync(struct dev_addr_list **to, int *to_count, |
| struct dev_addr_list **from, int *from_count) |
| { |
| struct dev_addr_list *da, *next; |
| |
| da = *from; |
| while (da != NULL) { |
| next = da->next; |
| if (da->da_synced) { |
| __dev_addr_delete(to, to_count, |
| da->da_addr, da->da_addrlen, 0); |
| da->da_synced = 0; |
| __dev_addr_delete(from, from_count, |
| da->da_addr, da->da_addrlen, 0); |
| } |
| da = next; |
| } |
| } |
| |
| /** |
| * dev_unicast_sync - Synchronize device's unicast list to another device |
| * @to: destination device |
| * @from: source device |
| * |
| * Add newly added addresses to the destination device and release |
| * addresses that have no users left. The source device must be |
| * locked by netif_tx_lock_bh. |
| * |
| * This function is intended to be called from the dev->set_rx_mode |
| * function of layered software devices. |
| */ |
| int dev_unicast_sync(struct net_device *to, struct net_device *from) |
| { |
| int err = 0; |
| |
| netif_addr_lock_bh(to); |
| err = __dev_addr_sync(&to->uc_list, &to->uc_count, |
| &from->uc_list, &from->uc_count); |
| if (!err) |
| __dev_set_rx_mode(to); |
| netif_addr_unlock_bh(to); |
| return err; |
| } |
| EXPORT_SYMBOL(dev_unicast_sync); |
| |
| /** |
| * dev_unicast_unsync - Remove synchronized addresses from the destination device |
| * @to: destination device |
| * @from: source device |
| * |
| * Remove all addresses that were added to the destination device by |
| * dev_unicast_sync(). This function is intended to be called from the |
| * dev->stop function of layered software devices. |
| */ |
| void dev_unicast_unsync(struct net_device *to, struct net_device *from) |
| { |
| netif_addr_lock_bh(from); |
| netif_addr_lock(to); |
| |
| __dev_addr_unsync(&to->uc_list, &to->uc_count, |
| &from->uc_list, &from->uc_count); |
| __dev_set_rx_mode(to); |
| |
| netif_addr_unlock(to); |
| netif_addr_unlock_bh(from); |
| } |
| EXPORT_SYMBOL(dev_unicast_unsync); |
| |
| static void __dev_addr_discard(struct dev_addr_list **list) |
| { |
| struct dev_addr_list *tmp; |
| |
| while (*list != NULL) { |
|