/*
 *      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 <linux/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/sched/mm.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/skbuff.h>
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/busy_poll.h>
#include <linux/rtnetlink.h>
#include <linux/stat.h>
#include <net/dst.h>
#include <net/dst_metadata.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/netpoll.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
#include <net/iw_handler.h>
#include <asm/current.h>
#include <linux/audit.h>
#include <linux/dmaengine.h>
#include <linux/err.h>
#include <linux/ctype.h>
#include <linux/if_arp.h>
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <net/ip.h>
#include <net/mpls.h>
#include <linux/ipv6.h>
#include <linux/in.h>
#include <linux/jhash.h>
#include <linux/random.h>
#include <trace/events/napi.h>
#include <trace/events/net.h>
#include <trace/events/skb.h>
#include <linux/pci.h>
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
#include <linux/static_key.h>
#include <linux/hashtable.h>
#include <linux/vmalloc.h>
#include <linux/if_macvlan.h>
#include <linux/errqueue.h>
#include <linux/hrtimer.h>
#include <linux/netfilter_ingress.h>
#include <linux/crash_dump.h>
#include <linux/sctp.h>
#include <net/udp_tunnel.h>
#include <linux/net_namespace.h>
#include <linux/indirect_call_wrapper.h>

#include "net-sysfs.h"

#define MAX_GRO_SKBS 8

/* This should be increased if a protocol with a bigger head is added. */
#define GRO_MAX_HEAD (MAX_HEADER + 128)

static DEFINE_SPINLOCK(ptype_lock);
static DEFINE_SPINLOCK(offload_lock);
struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
struct list_head ptype_all __read_mostly;       /* Taps */
static struct list_head offload_base __read_mostly;

static int netif_rx_internal(struct sk_buff *skb);
static int call_netdevice_notifiers_info(unsigned long val,
                                         struct netdev_notifier_info *info);
static int call_netdevice_notifiers_extack(unsigned long val,
                                           struct net_device *dev,
                                           struct netlink_ext_ack *extack);
static struct napi_struct *napi_by_id(unsigned int napi_id);

/*
 * 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 DEFINE_MUTEX(ifalias_mutex);

/* protects napi_hash addition/deletion and napi_gen_id */
static DEFINE_SPINLOCK(napi_hash_lock);

static unsigned int napi_gen_id = NR_CPUS;
static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8);

static seqcount_t devnet_rename_seq;

static inline void dev_base_seq_inc(struct net *net)
{
        while (++net->dev_base_seq == 0)
                ;
}

static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
{
        unsigned int hash = full_name_hash(net, 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 void 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);
}

/* 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 pt->dev ? &pt->dev->ptype_all : &ptype_all;
        else
                return pt->dev ? &pt->dev->ptype_specific :
                                 &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK];
}

/**
 *      dev_add_pack - add packet handler
 *      @pt: packet type declaration
 *
 *      Add a protocol handler to the networking stack. The passed &packet_type
 *      is linked into kernel lists and may not be freed until it has been
 *      removed from the kernel lists.
 *
 *      This call does not sleep therefore it can not
 *      guarantee all CPU's that are in middle of receiving packets
 *      will see the new packet type (until the next received packet).
 */

void dev_add_pack(struct packet_type *pt)
{
        struct list_head *head = ptype_head(pt);

        spin_lock(&ptype_lock);
        list_add_rcu(&pt->list, head);
        spin_unlock(&ptype_lock);
}
EXPORT_SYMBOL(dev_add_pack);

/**
 *      __dev_remove_pack        - remove packet handler
 *      @pt: packet type declaration
 *
 *      Remove a protocol handler that was previously added to the kernel
 *      protocol handlers by dev_add_pack(). The passed &packet_type is removed
 *      from the kernel lists and can be freed or reused once this function
 *      returns.
 *
 *      The packet type might still be in use by receivers
 *      and must not be freed until after all the CPU's have gone
 *      through a quiescent state.
 */
void __dev_remove_pack(struct packet_type *pt)
{
        struct list_head *head = ptype_head(pt);
        struct packet_type *pt1;

        spin_lock(&ptype_lock);

        list_for_each_entry(pt1, head, list) {
                if (pt == pt1) {
                        list_del_rcu(&pt->list);
                        goto out;
                }
        }

        pr_warn("dev_remove_pack: %p not found\n", pt);
out:
        spin_unlock(&ptype_lock);
}
EXPORT_SYMBOL(__dev_remove_pack);

/**
 *      dev_remove_pack  - remove packet handler
 *      @pt: packet type declaration
 *
 *      Remove a protocol handler that was previously added to the kernel
 *      protocol handlers by dev_add_pack(). The passed &packet_type is removed
 *      from the kernel lists and can be freed or reused once this function
 *      returns.
 *
 *      This call sleeps to guarantee that no CPU is looking at the packet
 *      type after return.
 */
void dev_remove_pack(struct packet_type *pt)
{
        __dev_remove_pack(pt);

        synchronize_net();
}
EXPORT_SYMBOL(dev_remove_pack);


/**
 *      dev_add_offload - register offload handlers
 *      @po: protocol offload declaration
 *
 *      Add protocol offload handlers to the networking stack. The passed
 *      &proto_offload is linked into kernel lists and may not be freed until
 *      it has been removed from the kernel lists.
 *
 *      This call does not sleep therefore it can not
 *      guarantee all CPU's that are in middle of receiving packets
 *      will see the new offload handlers (until the next received packet).
 */
void dev_add_offload(struct packet_offload *po)
{
        struct packet_offload *elem;

        spin_lock(&offload_lock);
        list_for_each_entry(elem, &offload_base, list) {
                if (po->priority < elem->priority)
                        break;
        }
        list_add_rcu(&po->list, elem->list.prev);
        spin_unlock(&offload_lock);
}
EXPORT_SYMBOL(dev_add_offload);

/**
 *      __dev_remove_offload     - remove offload handler
 *      @po: packet offload declaration
 *
 *      Remove a protocol offload handler that was previously added to the
 *      kernel offload handlers by dev_add_offload(). The passed &offload_type
 *      is removed from the kernel lists and can be freed or reused once this
 *      function returns.
 *
 *      The packet type might still be in use by receivers
 *      and must not be freed until after all the CPU's have gone
 *      through a quiescent state.
 */
static void __dev_remove_offload(struct packet_offload *po)
{
        struct list_head *head = &offload_base;
        struct packet_offload *po1;

        spin_lock(&offload_lock);

        list_for_each_entry(po1, head, list) {
                if (po == po1) {
                        list_del_rcu(&po->list);
                        goto out;
                }
        }

        pr_warn("dev_remove_offload: %p not found\n", po);
out:
        spin_unlock(&offload_lock);
}

/**
 *      dev_remove_offload       - remove packet offload handler
 *      @po: packet offload declaration
 *
 *      Remove a packet offload handler that was previously added to the kernel
 *      offload handlers by dev_add_offload(). The passed &offload_type is
 *      removed from the kernel lists and can be freed or reused once this
 *      function returns.
 *
 *      This call sleeps to guarantee that no CPU is looking at the packet
 *      type after return.
 */
void dev_remove_offload(struct packet_offload *po)
{
        __dev_remove_offload(po);

        synchronize_net();
}
EXPORT_SYMBOL(dev_remove_offload);

/******************************************************************************
 *
 *                    Device Boot-time Settings Routines
 *
 ******************************************************************************/

/* Boot time configuration table */
static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX];

/**
 *      netdev_boot_setup_add   - add new setup entry
 *      @name: name of the device
 *      @map: configured settings for the device
 *
 *      Adds new setup entry to the dev_boot_setup list.  The function
 *      returns 0 on error and 1 on success.  This is a generic routine to
 *      all netdevices.
 */
static int netdev_boot_setup_add(char *name, struct ifmap *map)
{
        struct netdev_boot_setup *s;
        int i;

        s = dev_boot_setup;
        for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
                if (s[i].name[0] == '\0' || s[i].name[0] == ' ') {
                        memset(s[i].name, 0, sizeof(s[i].name));
                        strlcpy(s[i].name, name, IFNAMSIZ);
                        memcpy(&s[i].map, map, sizeof(s[i].map));
                        break;
                }
        }

        return i >= NETDEV_BOOT_SETUP_MAX ? 0 : 1;
}

/**
 * netdev_boot_setup_check      - check boot time settings
 * @dev: the netdevice
 *
 * Check boot time settings for the device.
 * The found settings are set for the device to be used
 * later in the device probing.
 * Returns 0 if no settings found, 1 if they are.
 */
int netdev_boot_setup_check(struct net_device *dev)
{
        struct netdev_boot_setup *s = dev_boot_setup;
        int i;

        for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
                if (s[i].name[0] != '\0' && s[i].name[0] != ' ' &&
                    !strcmp(dev->name, s[i].name)) {
                        dev->irq = s[i].map.irq;
                        dev->base_addr = s[i].map.base_addr;
                        dev->mem_start = s[i].map.mem_start;
                        dev->mem_end = s[i].map.mem_end;
                        return 1;
                }
        }
        return 0;
}
EXPORT_SYMBOL(netdev_boot_setup_check);


/**
 * netdev_boot_base     - get address from boot time settings
 * @prefix: prefix for network device
 * @unit: id for network device
 *
 * Check boot time settings for the base address of device.
 * The found settings are set for the device to be used
 * later in the device probing.
 * Returns 0 if no settings found.
 */
unsigned long netdev_boot_base(const char *prefix, int unit)
{
        const struct netdev_boot_setup *s = dev_boot_setup;
        char name[IFNAMSIZ];
        int i;

        sprintf(name, "%s%d", prefix, unit);

        /*
         * If device already registered then return base of 1
         * to indicate not to probe for this interface
         */
        if (__dev_get_by_name(&init_net, name))
                return 1;

        for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++)
                if (!strcmp(name, s[i].name))
                        return s[i].map.base_addr;
        return 0;
}

/*
 * Saves at boot time configured settings for any netdevice.
 */
int __init netdev_boot_setup(char *str)
{
        int ints[5];
        struct ifmap map;

        str = get_options(str, ARRAY_SIZE(ints), ints);
        if (!str || !*str)
                return 0;

        /* Save settings */
        memset(&map, 0, sizeof(map));
        if (ints[0] > 0)
                map.irq = ints[1];
        if (ints[0] > 1)
                map.base_addr = ints[2];
        if (ints[0] > 2)
                map.mem_start = ints[3];
        if (ints[0] > 3)
                map.mem_end = ints[4];

        /* Add new entry to the list */
        return netdev_boot_setup_add(str, &map);
}

__setup("netdev=", netdev_boot_setup);

/*******************************************************************************
 *
 *                          Device Interface Subroutines
 *
 *******************************************************************************/

/**
 *      dev_get_iflink  - get 'iflink' value of a interface
 *      @dev: targeted interface
 *
 *      Indicates the ifindex the interface is linked to.
 *      Physical interfaces have the same 'ifindex' and 'iflink' values.
 */

int dev_get_iflink(const struct net_device *dev)
{
        if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink)
                return dev->netdev_ops->ndo_get_iflink(dev);

        return dev->ifindex;
}
EXPORT_SYMBOL(dev_get_iflink);

/**
 *      dev_fill_metadata_dst - Retrieve tunnel egress information.
 *      @dev: targeted interface
 *      @skb: The packet.
 *
 *      For better visibility of tunnel traffic OVS needs to retrieve
 *      egress tunnel information for a packet. Following API allows
 *      user to get this info.
 */
int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
{
        struct ip_tunnel_info *info;

        if (!dev->netdev_ops  || !dev->netdev_ops->ndo_fill_metadata_dst)
                return -EINVAL;

        info = skb_tunnel_info_unclone(skb);
        if (!info)
                return -ENOMEM;
        if (unlikely(!(info->mode & IP_TUNNEL_INFO_TX)))
                return -EINVAL;

        return dev->netdev_ops->ndo_fill_metadata_dst(dev, skb);
}
EXPORT_SYMBOL_GPL(dev_fill_metadata_dst);

/**
 *      __dev_get_by_name       - find a device by its name
 *      @net: the applicable net namespace
 *      @name: name to find
 *
 *      Find an interface by name. Must be called under RTNL semaphore
 *      or @dev_base_lock. If the name is found a pointer to the device
 *      is returned. If the name is not found then %NULL is returned. The
 *      reference counters are not incremented so the caller must be
 *      careful with locks.
 */

struct net_device *__dev_get_by_name(struct net *net, const char *name)
{
        struct net_device *dev;
        struct hlist_head *head = dev_name_hash(net, name);

        hlist_for_each_entry(dev, head, name_hlist)
                if (!strncmp(dev->name, name, IFNAMSIZ))
                        return dev;

        return NULL;
}
EXPORT_SYMBOL(__dev_get_by_name);

/**
 * dev_get_by_name_rcu  - find a device by its name
 * @net: the applicable net namespace
 * @name: name to find
 *
 * Find an interface by name.
 * If the name is found a pointer to the device is returned.
 * If the name is not found then %NULL is returned.
 * The reference counters are not incremented so the caller must be
 * careful with locks. The caller must hold RCU lock.
 */

struct net_device *dev_get_by_name_rcu(struct net *net, const char *name)
{
        struct net_device *dev;
        struct hlist_head *head = dev_name_hash(net, name);

        hlist_for_each_entry_rcu(dev, head, name_hlist)
                if (!strncmp(dev->name, name, IFNAMSIZ))
                        return dev;

        return NULL;
}
EXPORT_SYMBOL(dev_get_by_name_rcu);

/**
 *      dev_get_by_name         - find a device by its name
 *      @net: the applicable net namespace
 *      @name: name to find
 *
 *      Find an interface by name. This can be called from any
 *      context and does its own locking. The returned handle has
 *      the usage count incremented and the caller must use dev_put() to
 *      release it when it is no longer needed. %NULL is returned if no
 *      matching device is found.
 */

struct net_device *dev_get_by_name(struct net *net, const char *name)
{
        struct net_device *dev;

        rcu_read_lock();
        dev = dev_get_by_name_rcu(net, name);
        if (dev)
                dev_hold(dev);
        rcu_read_unlock();
        return dev;
}
EXPORT_SYMBOL(dev_get_by_name);

/**
 *      __dev_get_by_index - find a device by its ifindex
 *      @net: the applicable net namespace
 *      @ifindex: index of device
 *
 *      Search for an interface by index. Returns %NULL if the device
 *      is not found or a pointer to the device. The device has not
 *      had its reference counter increased so the caller must be careful
 *      about locking. The caller must hold either the RTNL semaphore
 *      or @dev_base_lock.
 */

struct net_device *__dev_get_by_index(struct net *net, int ifindex)
{
        struct net_device *dev;
        struct hlist_head *head = dev_index_hash(net, ifindex);

        hlist_for_each_entry(dev, head, index_hlist)
                if (dev->ifindex == ifindex)
                        return dev;

        return NULL;
}
EXPORT_SYMBOL(__dev_get_by_index);

/**
 *      dev_get_by_index_rcu - find a device by its ifindex
 *      @net: the applicable net namespace
 *      @ifindex: index of device
 *
 *      Search for an interface by index. Returns %NULL if the device
 *      is not found or a pointer to the device. The device has not
 *      had its reference counter increased so the caller must be careful
 *      about locking. The caller must hold RCU lock.
 */

struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex)
{
        struct net_device *dev;
        struct hlist_head *head = dev_index_hash(net, ifindex);

        hlist_for_each_entry_rcu(dev, head, index_hlist)
                if (dev->ifindex == ifindex)
                        return dev;

        return NULL;
}
EXPORT_SYMBOL(dev_get_by_index_rcu);


/**
 *      dev_get_by_index - find a device by its ifindex
 *      @net: the applicable net namespace
 *      @ifindex: index of device
 *
 *      Search for an interface by index. Returns NULL if the device
 *      is not found or a pointer to the device. The device returned has
 *      had a reference added and the pointer is safe until the user calls
 *      dev_put to indicate they have finished with it.
 */

struct net_device *dev_get_by_index(struct net *net, int ifindex)
{
        struct net_device *dev;

        rcu_read_lock();
        dev = dev_get_by_index_rcu(net, ifindex);
        if (dev)
                dev_hold(dev);
        rcu_read_unlock();
        return dev;
}
EXPORT_SYMBOL(dev_get_by_index);

/**
 *      dev_get_by_napi_id - find a device by napi_id
 *      @napi_id: ID of the NAPI struct
 *
 *      Search for an interface by NAPI ID. 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_napi_id(unsigned int napi_id)
{
        struct napi_struct *napi;

        WARN_ON_ONCE(!rcu_read_lock_held());

        if (napi_id < MIN_NAPI_ID)
                return NULL;

        napi = napi_by_id(napi_id);

        return napi ? napi->dev : NULL;
}
EXPORT_SYMBOL(dev_get_by_napi_id);

/**
 *      netdev_get_name - get a netdevice name, knowing its ifindex.
 *      @net: network namespace
 *      @name: a pointer to the buffer where the name will be stored.
 *      @ifindex: the ifindex of the interface to get the name from.
 *
 *      The use of raw_seqcount_begin() and cond_resched() before
 *      retrying is required as we want to give the writers a chance
 *      to complete when CONFIG_PREEMPT is not set.
 */
int netdev_get_name(struct net *net, char *name, int ifindex)
{
        struct net_device *dev;
        unsigned int seq;

retry:
        seq = raw_seqcount_begin(&devnet_rename_seq);
        rcu_read_lock();
        dev = dev_get_by_index_rcu(net, ifindex);
        if (!dev) {
                rcu_read_unlock();
                return -ENODEV;
        }

        strcpy(name, dev->name);
        rcu_read_unlock();
        if (read_seqcount_retry(&devnet_rename_seq, seq)) {
                cond_resched();
                goto retry;
        }

        return 0;
}

/**
 *      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 - 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
 *      rtnl_lock(), and result refcount is unchanged.
 */

struct net_device *__dev_get_by_flags(struct net *net, unsigned short if_flags,
                                      unsigned short mask)
{
        struct net_device *dev, *ret;

        ASSERT_RTNL();

        ret = NULL;
        for_each_netdev(net, dev) {
                if (((dev->flags ^ if_flags) & mask) == 0) {
                        ret = dev;
                        break;
                }
        }
        return ret;
}
EXPORT_SYMBOL(__dev_get_by_flags);

/**
 *      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 (strnlen(name, IFNAMSIZ) == IFNAMSIZ)
                return false;
        if (!strcmp(name, ".") || !strcmp(name, ".."))
                return false;

        while (*name) {
                if (*name == '/' || *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;

        if (!dev_valid_name(name))
                return -EINVAL;

        p = strchr(name, '%');
        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;
}

static int dev_alloc_name_ns(struct net *net,
                             struct net_device *dev,
                             const char *name)
{
        char buf[IFNAMSIZ];
        int ret;

        BUG_ON(!net);
        ret = __dev_alloc_name(net, name, buf);
        if (ret >= 0)
                strlcpy(dev->name, buf, IFNAMSIZ);
        return ret;
}

/**
 *      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)
{
        return dev_alloc_name_ns(dev_net(dev), dev, name);
}
EXPORT_SYMBOL(dev_alloc_name);

int dev_get_valid_name(struct net *net, struct net_device *dev,
                       const char *name)
{
        BUG_ON(!net);

        if (!dev_valid_name(name))
                return -EINVAL;

        if (strchr(name, '%'))
                return dev_alloc_name_ns(net, dev, name);
        else if (__dev_get_by_name(net, name))
                return -EEXIST;
        else if (dev->name != name)
                strlcpy(dev->name, name, IFNAMSIZ);

        return 0;
}
EXPORT_SYMBOL(dev_get_valid_name);

/**
 *      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)
{
        unsigned char old_assign_type;
        char oldname[IFNAMSIZ];
        int err = 0;
        int ret;
        struct net *net;

        ASSERT_RTNL();
        BUG_ON(!dev_net(dev));

        net = dev_net(dev);
        if (dev->flags & IFF_UP)
                return -EBUSY;

        write_seqcount_begin(&devnet_rename_seq);

        if (strncmp(newname, dev->name, IFNAMSIZ) == 0) {
                write_seqcount_end(&devnet_rename_seq);
                return 0;
        }

        memcpy(oldname, dev->name, IFNAMSIZ);

        err = dev_get_valid_name(net, dev, newname);
        if (err < 0) {
                write_seqcount_end(&devnet_rename_seq);
                return err;
        }

        if (oldname[0] && !strchr(oldname, '%'))
                netdev_info(dev, "renamed from %s\n", oldname);

        old_assign_type = dev->name_assign_type;
        dev->name_assign_type = NET_NAME_RENAMED;

rollback:
        ret = device_rename(&dev->dev, dev->name);
        if (ret) {
                memcpy(dev->name, oldname, IFNAMSIZ);
                dev->name_assign_type = old_assign_type;
                write_seqcount_end(&devnet_rename_seq);
                return ret;
        }

        write_seqcount_end(&devnet_rename_seq);

        netdev_adjacent_rename_links(dev, oldname);

        write_lock_bh(&dev_base_lock);
        hlist_del_rcu(&dev->name_hlist);
        write_unlock_bh(&dev_base_lock);

        synchronize_rcu();

        write_lock_bh(&dev_base_lock);
        hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
        write_unlock_bh(&dev_base_lock);

        ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev);
        ret = notifier_to_errno(ret);

        if (ret) {
                /* err >= 0 after dev_alloc_name() or stores the first errno */
                if (err >= 0) {
                        err = ret;
                        write_seqcount_begin(&devnet_rename_seq);
                        memcpy(dev->name, oldname, IFNAMSIZ);
                        memcpy(oldname, newname, IFNAMSIZ);
                        dev->name_assign_type = old_assign_type;
                        old_assign_type = NET_NAME_RENAMED;
                        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)
{
        struct dev_ifalias *new_alias = NULL;

        if (len >= IFALIASZ)
                return -EINVAL;

        if (len) {
                new_alias = kmalloc(sizeof(*new_alias) + len + 1, GFP_KERNEL);
                if (!new_alias)
                        return -ENOMEM;

                memcpy(new_alias->ifalias, alias, len);
                new_alias->ifalias[len] = 0;
        }

        mutex_lock(&ifalias_mutex);
        rcu_swap_protected(dev->ifalias, new_alias,
                           mutex_is_locked(&ifalias_mutex));
        mutex_unlock(&ifalias_mutex);

        if (new_alias)
                kfree_rcu(new_alias, rcuhead);

        return len;
}
EXPORT_SYMBOL(dev_set_alias);

/**
 *      dev_get_alias - get ifalias of a device
 *      @dev: device
 *      @name: buffer to store name of ifalias
 *      @len: size of buffer
 *
 *      get ifalias for a device.  Caller must make sure dev cannot go
 *      away,  e.g. rcu read lock or own a reference count to device.
 */
int dev_get_alias(const struct net_device *dev, char *name, size_t len)
{
        const struct dev_ifalias *alias;
        int ret = 0;

        rcu_read_lock();
        alias = rcu_dereference(dev->ifalias);
        if (alias)
                ret = snprintf(name, len, "%s", alias->ifalias);
        rcu_read_unlock();

        return ret;
}

/**
 *      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) {
                struct netdev_notifier_change_info change_info = {
                        .info.dev = dev,
                };

                call_netdevice_notifiers_info(NETDEV_CHANGE,
                                              &change_info.info);
                rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
        }
}
EXPORT_SYMBOL(netdev_state_change);

/**
 * netdev_notify_peers - notify network peers about existence of @dev
 * @dev: network device
 *
 * Generate traffic such that interested network peers are aware of
 * @dev, such as by generating a gratuitous ARP. This may be used when
 * a device wants to inform the rest of the network about some sort of
 * reconfiguration such as a failover event or virtual machine
 * migration.
 */
void netdev_notify_peers(struct net_device *dev)
{
        rtnl_lock();
        call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev);
        call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev);
        rtnl_unlock();
}
EXPORT_SYMBOL(netdev_notify_peers);

static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
{
        const struct net_device_ops *ops = dev->netdev_ops;
        int ret;

        ASSERT_RTNL();

        if (!netif_device_present(dev))
                return -ENODEV;

        /* Block netpoll from trying to do any rx path servicing.
         * If we don't do this there is a chance ndo_poll_controller
         * or ndo_poll may be running while we open the device
         */
        netpoll_poll_disable(dev);

        ret = call_netdevice_notifiers_extack(NETDEV_PRE_UP, dev, extack);
        ret = notifier_to_errno(ret);
        if (ret)
                return ret;

        set_bit(__LINK_STATE_START, &dev->state);

        if (ops->ndo_validate_addr)
                ret = ops->ndo_validate_addr(dev);

        if (!ret && ops->ndo_open)
                ret = ops->ndo_open(dev);

        netpoll_poll_enable(dev);

        if (ret)
                clear_bit(__LINK_STATE_START, &dev->state);
        else {
                dev->flags |= IFF_UP;
                dev_set_rx_mode(dev);
                dev_activate(dev);
                add_device_randomness(dev->dev_addr, dev->addr_len);
        }

        return ret;
}

/**
 *      dev_open        - prepare an interface for use.
 *      @dev: device to open
 *      @extack: netlink extended ack
 *
 *      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, struct netlink_ext_ack *extack)
{
        int ret;

        if (dev->flags & IFF_UP)
                return 0;

        ret = __dev_open(dev, extack);
        if (ret < 0)
                return ret;

        rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL);
        call_netdevice_notifiers(NETDEV_UP, dev);

        return ret;
}
EXPORT_SYMBOL(dev_open);

static void __dev_close_many(struct list_head *head)
{
        struct net_device *dev;

        ASSERT_RTNL();
        might_sleep();

        list_for_each_entry(dev, head, close_list) {
                /* Temporarily disable netpoll until the interface is down */
                netpoll_poll_disable(dev);

                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_atomic(); /* Commit netif_running(). */
        }

        dev_deactivate_many(head);

        list_for_each_entry(dev, head, close_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;
                netpoll_poll_enable(dev);
        }
}

static void __dev_close(struct net_device *dev)
{
        LIST_HEAD(single);

        list_add(&dev->close_list, &single);
        __dev_close_many(&single);
        list_del(&single);
}

void dev_close_many(struct list_head *head, bool unlink)
{
        struct net_device *dev, *tmp;

        /* Remove the devices that don't need to be closed */
        list_for_each_entry_safe(dev, tmp, head, close_list)
                if (!(dev->flags & IFF_UP))
                        list_del_init(&dev->close_list);

        __dev_close_many(head);

        list_for_each_entry_safe(dev, tmp, head, close_list) {
                rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL);
                call_netdevice_notifiers(NETDEV_DOWN, dev);
                if (unlink)
                        list_del_init(&dev->close_list);
        }
}
EXPORT_SYMBOL(dev_close_many);

/**
 *      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.
 */
void dev_close(struct net_device *dev)
{
        if (dev->flags & IFF_UP) {
                LIST_HEAD(single);

                list_add(&dev->close_list, &single);
                dev_close_many(&single, true);
                list_del(&single);
        }
}
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)
{
        struct net_device *lower_dev;
        struct list_head *iter;

        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");

        netdev_for_each_lower_dev(dev, lower_dev, iter)
                dev_disable_lro(lower_dev);
}
EXPORT_SYMBOL(dev_disable_lro);

/**
 *      dev_disable_gro_hw - disable HW Generic Receive Offload on a device
 *      @dev: device
 *
 *      Disable HW Generic Receive Offload (GRO_HW) on a net device.  Must be
 *      called under RTNL.  This is needed if Generic XDP is installed on
 *      the device.
 */
static void dev_disable_gro_hw(struct net_device *dev)
{
        dev->wanted_features &= ~NETIF_F_GRO_HW;
        netdev_update_features(dev);

        if (unlikely(dev->features & NETIF_F_GRO_HW))
                netdev_WARN(dev, "failed to disable GRO_HW!\n");
}

const char *netdev_cmd_to_name(enum netdev_cmd cmd)
{
#define N(val)                                          \
        case NETDEV_##val:                              \
                return "NETDEV_" __stringify(val);
        switch (cmd) {
        N(UP) N(DOWN) N(REBOOT) N(CHANGE) N(REGISTER) N(UNREGISTER)
        N(CHANGEMTU) N(CHANGEADDR) N(GOING_DOWN) N(CHANGENAME) N(FEAT_CHANGE)
        N(BONDING_FAILOVER) N(PRE_UP) N(PRE_TYPE_CHANGE) N(POST_TYPE_CHANGE)
        N(POST_INIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) N(CHANGEUPPER)
        N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) N(BONDING_INFO)
        N(PRECHANGEUPPER) N(CHANGELOWERSTATE) N(UDP_TUNNEL_PUSH_INFO)
        N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN)
        N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO)
        N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO)
        N(PRE_CHANGEADDR)
        }
#undef N
        return "UNKNOWN_NETDEV_EVENT";
}
EXPORT_SYMBOL_GPL(netdev_cmd_to_name);

static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val,
                                   struct net_device *dev)
{
        struct netdev_notifier_info info = {
                .dev = dev,
        };

        return nb->notifier_call(nb, val, &info);
}

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;

        /* Close race with setup_net() and cleanup_net() */
        down_write(&pernet_ops_rwsem);
        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 = call_netdevice_notifier(nb, NETDEV_REGISTER, dev);
                        err = notifier_to_errno(err);
                        if (err)
                                goto rollback;

                        if (!(dev->flags & IFF_UP))
                                continue;

                        call_netdevice_notifier(nb, NETDEV_UP, dev);
                }
        }

unlock:
        rtnl_unlock();
        up_write(&pernet_ops_rwsem);
        return err;

rollback:
        last = dev;
        for_each_net(net) {
                for_each_netdev(net, dev) {
                        if (dev == last)
                                goto outroll;

                        if (dev->flags & IFF_UP) {
                                call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
                                                        dev);
                                call_netdevice_notifier(nb, NETDEV_DOWN, dev);
                        }
                        call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
                }
        }

outroll:
        raw_notifier_chain_unregister(&netdev_chain, nb);
        goto unlock;
}
EXPORT_SYMBOL(register_netdevice_notifier);

/**
 * unregister_netdevice_notifier - unregister a network notifier block
 * @nb: notifier
 *
 * Unregister a notifier previously registered by
 * register_netdevice_notifier(). The notifier is unlinked into the
 * kernel structures and may then be reused. A negative errno code
 * is returned on a failure.
 *
 * After unregistering unregister and down device events are synthesized
 * for all devices on the device list to the removed notifier to remove
 * the need for special case cleanup code.
 */

int unregister_netdevice_notifier(struct notifier_block *nb)
{
        struct net_device *dev;
        struct net *net;
        int err;

        /* Close race with setup_net() and cleanup_net() */
        down_write(&pernet_ops_rwsem);
        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) {
                                call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
                                                        dev);
                                call_netdevice_notifier(nb, NETDEV_DOWN, dev);
                        }
                        call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
                }
        }
unlock:
        rtnl_unlock();
        up_write(&pernet_ops_rwsem);
        return err;
}
EXPORT_SYMBOL(unregister_netdevice_notifier);

/**
 *      call_netdevice_notifiers_info - call all network notifier blocks
 *      @val: value passed unmodified to notifier function
 *      @info: notifier information data
 *
 *      Call all network notifier blocks.  Parameters and return value
 *      are as for raw_notifier_call_chain().
 */

static int call_netdevice_notifiers_info(unsigned long val,
                                         struct netdev_notifier_info *info)
{
        ASSERT_RTNL();
        return raw_notifier_call_chain(&netdev_chain, val, info);
}

static int call_netdevice_notifiers_extack(unsigned long val,
                                           struct net_device *dev,
                                           struct netlink_ext_ack *extack)
{
        struct netdev_notifier_info info = {
                .dev = dev,
                .extack = extack,
        };

        return call_netdevice_notifiers_info(val, &info);
}

/**
 *      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 call_netdevice_notifiers_extack(val, dev, NULL);
}
EXPORT_SYMBOL(call_netdevice_notifiers);

/**
 *      call_netdevice_notifiers_mtu - call all network notifier blocks
 *      @val: value passed unmodified to notifier function
 *      @dev: net_device pointer passed unmodified to notifier function
 *      @arg: additional u32 argument passed to the notifier function
 *
 *      Call all network notifier blocks.  Parameters and return value
 *      are as for raw_notifier_call_chain().
 */
static int call_netdevice_notifiers_mtu(unsigned long val,
                                        struct net_device *dev, u32 arg)
{
        struct netdev_notifier_info_ext info = {
                .info.dev = dev,
                .ext.mtu = arg,
        };

        BUILD_BUG_ON(offsetof(struct netdev_notifier_info_ext, info) != 0);

        return call_netdevice_notifiers_info(val, &info.info);
}

#ifdef CONFIG_NET_INGRESS
static DEFINE_STATIC_KEY_FALSE(ingress_needed_key);

void net_inc_ingress_queue(void)
{
        static_branch_inc(&ingress_needed_key);
}
EXPORT_SYMBOL_GPL(net_inc_ingress_queue);

void net_dec_ingress_queue(void)
{
        static_branch_dec(&ingress_needed_key);
}
EXPORT_SYMBOL_GPL(net_dec_ingress_queue);
#endif

#ifdef CONFIG_NET_EGRESS
static DEFINE_STATIC_KEY_FALSE(egress_needed_key);

void net_inc_egress_queue(void)
{
        static_branch_inc(&egress_needed_key);
}
EXPORT_SYMBOL_GPL(net_inc_egress_queue);

void net_dec_egress_queue(void)
{
        static_branch_dec(&egress_needed_key);
}
EXPORT_SYMBOL_GPL(net_dec_egress_queue);
#endif

static DEFINE_STATIC_KEY_FALSE(netstamp_needed_key);
#ifdef CONFIG_JUMP_LABEL
static atomic_t netstamp_needed_deferred;
static atomic_t netstamp_wanted;
static void netstamp_clear(struct work_struct *work)
{
        int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
        int wanted;

        wanted = atomic_add_return(deferred, &netstamp_wanted);
        if (wanted > 0)
                static_branch_enable(&netstamp_needed_key);
        else
                static_branch_disable(&netstamp_needed_key);
}
static DECLARE_WORK(netstamp_work, netstamp_clear);
#endif

void net_enable_timestamp(void)
{
#ifdef CONFIG_JUMP_LABEL
        int wanted;

        while (1) {
                wanted = atomic_read(&netstamp_wanted);
                if (wanted <= 0)
                        break;
                if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted)
                        return;
        }
        atomic_inc(&netstamp_needed_deferred);
        schedule_work(&netstamp_work);
#else
        static_branch_inc(&netstamp_needed_key);
#endif
}
EXPORT_SYMBOL(net_enable_timestamp);

void net_disable_timestamp(void)
{
#ifdef CONFIG_JUMP_LABEL
        int wanted;

        while (1) {
                wanted = atomic_read(&netstamp_wanted);
                if (wanted <= 1)
                        break;
                if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted)
                        return;
        }
        atomic_dec(&netstamp_needed_deferred);
        schedule_work(&netstamp_work);
#else
        static_branch_dec(&netstamp_needed_key);
#endif
}
EXPORT_SYMBOL(net_disable_timestamp);

static inline void net_timestamp_set(struct sk_buff *skb)
{
        skb->tstamp = 0;
        if (static_branch_unlikely(&netstamp_needed_key))
                __net_timestamp(skb);
}

#define net_timestamp_check(COND, SKB)                          \
        if (static_branch_unlikely(&netstamp_needed_key)) {     \
                if ((COND) && !(SKB)->tstamp)                   \
                        __net_timestamp(SKB);                   \
        }                                                       \

bool is_skb_forwardable(const struct net_device *dev, const 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;
}
EXPORT_SYMBOL_GPL(is_skb_forwardable);

int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
{
        int ret = ____dev_forward_skb(dev, skb);

        if (likely(!ret)) {
                skb->protocol = eth_type_trans(skb, dev);
                skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
        }

        return ret;
}
EXPORT_SYMBOL_GPL(__dev_forward_skb);

/**
 * 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)
{
        return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb);
}
EXPORT_SYMBOL_GPL(dev_forward_skb);

static inline int deliver_skb(struct sk_buff *skb,
                              struct packet_type *pt_prev,
                              struct net_device *orig_dev)
{
        if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
                return -ENOMEM;
        refcount_inc(&skb->users);
        return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}

static inline void deliver_ptype_list_skb(struct sk_buff *skb,
                                          struct packet_type **pt,
                                          struct net_device *orig_dev,
                                          __be16 type,
                                          struct list_head *ptype_list)
{
        struct packet_type *ptype, *pt_prev = *pt;

        list_for_each_entry_rcu(ptype, ptype_list, list) {
                if (ptype->type != type)
                        continue;
                if (pt_prev)
                        deliver_skb(skb, pt_prev, orig_dev);
                pt_prev = ptype;
        }
        *pt = pt_prev;
}

static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb)
{
        if (!ptype->af_packet_priv || !skb->sk)
                return false;

        if (ptype->id_match)
                return ptype->id_match(ptype, skb->sk);
        else if ((struct sock *)ptype->af_packet_priv == skb->sk)
                return true;

        return false;
}

/**
 * dev_nit_active - return true if any network interface taps are in use
 *
 * @dev: network device to check for the presence of taps
 */
bool dev_nit_active(struct net_device *dev)
{
        return !list_empty(&ptype_all) || !list_empty(&dev->ptype_all);

}
EXPORT_SYMBOL_GPL(dev_nit_active);

/*
 *      Support routine. Sends outgoing frames to any network
 *      taps currently in use.
 */

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;
        struct list_head *ptype_list = &ptype_all;

        rcu_read_lock();
again:
        list_for_each_entry_rcu(ptype, ptype_list, list) {
                if (ptype->ignore_outgoing)
                        continue;

                /* Never send packets back to the socket
                 * they originated from - MvS (miquels@drinkel.ow.org)
                 */
                if (skb_loop_sk(ptype, skb))
                        continue;

                if (pt_prev) {
                        deliver_skb(skb2, pt_prev, skb->dev);
                        pt_prev = ptype;
                        continue;
                }

                /* need to clone skb, done only once */
                skb2 = skb_clone(skb, GFP_ATOMIC);
                if (!skb2)
                        goto out_unlock;

                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 ||
                    skb_network_header(skb2) > skb_tail_pointer(skb2)) {
                        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 (ptype_list == &ptype_all) {
                ptype_list = &dev->ptype_all;
                goto again;
        }
out_unlock:
        if (pt_prev) {
                if (!skb_orphan_frags_rx(skb2, GFP_ATOMIC))
                        pt_prev->func(skb2, skb->dev, pt_prev, skb->dev);
                else
                        kfree_skb(skb2);
        }
        rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(dev_queue_xmit_nit);

/**
 * 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);
                }
        }
}

int netdev_txq_to_tc(struct net_device *dev, unsigned int txq)
{
        if (dev->num_tc) {
                struct netdev_tc_txq *tc = &dev->tc_to_txq[0];
                int i;

                /* walk through the TCs and see if it falls into any of them */
                for (i = 0; i < TC_MAX_QUEUE; i++, tc++) {
                        if ((txq - tc->offset) < tc->count)
                                return i;
                }

                /* didn't find it, just return -1 to indicate no match */
                return -1;
        }

        return 0;
}
EXPORT_SYMBOL(netdev_txq_to_tc);

#ifdef CONFIG_XPS
struct static_key xps_needed __read_mostly;
EXPORT_SYMBOL(xps_needed);
struct static_key xps_rxqs_needed __read_mostly;
EXPORT_SYMBOL(xps_rxqs_needed);
static DEFINE_MUTEX(xps_map_mutex);
#define xmap_dereference(P)             \
        rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex))

static bool remove_xps_queue(struct xps_dev_maps *dev_maps,
                             int tci, u16 index)
{
        struct xps_map *map = NULL;
        int pos;

        if (dev_maps)
                map = xmap_dereference(dev_maps->attr_map[tci]);
        if (!map)
                return false;

        for (pos = map->len; pos--;) {
                if (map->queues[pos] != index)
                        continue;

                if (map->len > 1) {
                        map->queues[pos] = map->queues[--map->len];
                        break;
                }

                RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL);
                kfree_rcu(map, rcu);
                return false;
        }

        return true;
}

static bool remove_xps_queue_cpu(struct net_device *dev,
                                 struct xps_dev_maps *dev_maps,
                                 int cpu, u16 offset, u16 count)
{
        int num_tc = dev->num_tc ? : 1;
        bool active = false;
        int tci;

        for (tci = cpu * num_tc; num_tc--; tci++) {
                int i, j;

                for (i = count, j = offset; i--; j++) {
                        if (!remove_xps_queue(dev_maps, tci, j))
                                break;
                }

                active |= i < 0;
        }

        return active;
}

static void reset_xps_maps(struct net_device *dev,
                           struct xps_dev_maps *dev_maps,
                           bool is_rxqs_map)
{
        if (is_rxqs_map) {
                static_key_slow_dec_cpuslocked(&xps_rxqs_needed);
                RCU_INIT_POINTER(dev->xps_rxqs_map, NULL);
        } else {
                RCU_INIT_POINTER(dev->xps_cpus_map, NULL);
        }
        static_key_slow_dec_cpuslocked(&xps_needed);
        kfree_rcu(dev_maps, rcu);
}

static void clean_xps_maps(struct net_device *dev, const unsigned long *mask,
                           struct xps_dev_maps *dev_maps, unsigned int nr_ids,
                           u16 offset, u16 count, bool is_rxqs_map)
{
        bool active = false;
        int i, j;

        for (j = -1; j = netif_attrmask_next(j, mask, nr_ids),
             j < nr_ids;)
                active |= remove_xps_queue_cpu(dev, dev_maps, j, offset,
                                               count);
        if (!active)
                reset_xps_maps(dev, dev_maps, is_rxqs_map);

        if (!is_rxqs_map) {
                for (i = offset + (count - 1); count--; i--) {
                        netdev_queue_numa_node_write(
                                netdev_get_tx_queue(dev, i),
                                NUMA_NO_NODE);
                }
        }
}

static void netif_reset_xps_queues(struct net_device *dev, u16 offset,
                                   u16 count)
{
        const unsigned long *possible_mask = NULL;
        struct xps_dev_maps *dev_maps;
        unsigned int nr_ids;

        if (!static_key_false(&xps_needed))
                return;

        cpus_read_lock();
        mutex_lock(&xps_map_mutex);

        if (static_key_false(&xps_rxqs_needed)) {
                dev_maps = xmap_dereference(dev->xps_rxqs_map);
                if (dev_maps) {
                        nr_ids = dev->num_rx_queues;
                        clean_xps_maps(dev, possible_mask, dev_maps, nr_ids,
                                       offset, count, true);
                }
        }

        dev_maps = xmap_dereference(dev->xps_cpus_map);
        if (!dev_maps)
                goto out_no_maps;

        if (num_possible_cpus() > 1)
                possible_mask = cpumask_bits(cpu_possible_mask);
        nr_ids = nr_cpu_ids;
        clean_xps_maps(dev, possible_mask, dev_maps, nr_ids, offset, count,
                       false);

out_no_maps:
        mutex_unlock(&xps_map_mutex);
        cpus_read_unlock();
}

static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index)
{
        netif_reset_xps_queues(dev, index, dev->num_tx_queues - index);
}

static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index,
                                      u16 index, bool is_rxqs_map)
{
        struct xps_map *new_map;
        int alloc_len = XPS_MIN_MAP_ALLOC;
        int i, pos;

        for (pos = 0; map && pos < map->len; pos++) {
                if (map->queues[pos] != index)
                        continue;
                return map;
        }

        /* Need to add tx-queue to this CPU's/rx-queue's existing map */
        if (map) {
                if (pos < map->alloc_len)
                        return map;

                alloc_len = map->alloc_len * 2;
        }

        /* Need to allocate new map to store tx-queue on this CPU's/rx-queue's
         *  map
         */
        if (is_rxqs_map)
                new_map = kzalloc(XPS_MAP_SIZE(alloc_len), GFP_KERNEL);
        else
                new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL,
                                       cpu_to_node(attr_index));
        if (!new_map)
                return NULL;

        for (i = 0; i < pos; i++)
                new_map->queues[i] = map->queues[i];
        new_map->alloc_len = alloc_len;
        new_map->len = pos;

        return new_map;
}

/* Must be called under cpus_read_lock */
int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
                          u16 index, bool is_rxqs_map)
{
        const unsigned long *online_mask = NULL, *possible_mask = NULL;
        struct xps_dev_maps *dev_maps, *new_dev_maps = NULL;
        int i, j, tci, numa_node_id = -2;
        int maps_sz, num_tc = 1, tc = 0;
        struct xps_map *map, *new_map;
        bool active = false;
        unsigned int nr_ids;

        if (dev->num_tc) {
                /* Do not allow XPS on subordinate device directly */
                num_tc = dev->num_tc;
                if (num_tc < 0)
                        return -EINVAL;

                /* If queue belongs to subordinate dev use its map */
                dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;

                tc = netdev_txq_to_tc(dev, index);
                if (tc < 0)
                        return -EINVAL;
        }

        mutex_lock(&xps_map_mutex);
        if (is_rxqs_map) {
                maps_sz = XPS_RXQ_DEV_MAPS_SIZE(num_tc, dev->num_rx_queues);
                dev_maps = xmap_dereference(dev->xps_rxqs_map);
                nr_ids = dev->num_rx_queues;
        } else {
                maps_sz = XPS_CPU_DEV_MAPS_SIZE(num_tc);
                if (num_possible_cpus() > 1) {
                        online_mask = cpumask_bits(cpu_online_mask);
                        possible_mask = cpumask_bits(cpu_possible_mask);
                }
                dev_maps = xmap_dereference(dev->xps_cpus_map);
                nr_ids = nr_cpu_ids;
        }

        if (maps_sz < L1_CACHE_BYTES)
                maps_sz = L1_CACHE_BYTES;

        /* allocate memory for queue storage */
        for (j = -1; j = netif_attrmask_next_and(j, online_mask, mask, nr_ids),
             j < nr_ids;) {
                if (!new_dev_maps)
                        new_dev_maps = kzalloc(maps_sz, GFP_KERNEL);
                if (!new_dev_maps) {
                        mutex_unlock(&xps_map_mutex);
                        return -ENOMEM;
                }

                tci = j * num_tc + tc;
                map = dev_maps ? xmap_dereference(dev_maps->attr_map[tci]) :
                                 NULL;

                map = expand_xps_map(map, j, index, is_rxqs_map);
                if (!map)
                        goto error;

                RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
        }

        if (!new_dev_maps)
                goto out_no_new_maps;

        if (!dev_maps) {
                /* Increment static keys at most once per type */
                static_key_slow_inc_cpuslocked(&xps_needed);
                if (is_rxqs_map)
                        static_key_slow_inc_cpuslocked(&xps_rxqs_needed);
        }

        for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
             j < nr_ids;) {
                /* copy maps belonging to foreign traffic classes */
                for (i = tc, tci = j * num_tc; dev_maps && i--; tci++) {
                        /* fill in the new device map from the old device map */
                        map = xmap_dereference(dev_maps->attr_map[tci]);
                        RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
                }

                /* We need to explicitly update tci as prevous loop
                 * could break out early if dev_maps is NULL.
                 */
                tci = j * num_tc + tc;

                if (netif_attr_test_mask(j, mask, nr_ids) &&
                    netif_attr_test_online(j, online_mask, nr_ids)) {
                        /* add tx-queue to CPU/rx-queue maps */
                        int pos = 0;

                        map = xmap_dereference(new_dev_maps->attr_map[tci]);
                        while ((pos < map->len) && (map->queues[pos] != index))
                                pos++;

                        if (pos == map->len)
                                map->queues[map->len++] = index;
#ifdef CONFIG_NUMA
                        if (!is_rxqs_map) {
                                if (numa_node_id == -2)
                                        numa_node_id = cpu_to_node(j);
                                else if (numa_node_id != cpu_to_node(j))
                                        numa_node_id = -1;
                        }
#endif
                } else if (dev_maps) {
                        /* fill in the new device map from the old device map */
                        map = xmap_dereference(dev_maps->attr_map[tci]);
                        RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
                }

                /* copy maps belonging to foreign traffic classes */
                for (i = num_tc - tc, tci++; dev_maps && --i; tci++) {
                        /* fill in the new device map from the old device map */
                        map = xmap_dereference(dev_maps->attr_map[tci]);
                        RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
                }
        }

        if (is_rxqs_map)
                rcu_assign_pointer(dev->xps_rxqs_map, new_dev_maps);
        else
                rcu_assign_pointer(dev->xps_cpus_map, new_dev_maps);

        /* Cleanup old maps */
        if (!dev_maps)
                goto out_no_old_maps;

        for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
             j < nr_ids;) {
                for (i = num_tc, tci = j * num_tc; i--; tci++) {
                        new_map = xmap_dereference(new_dev_maps->attr_map[tci]);
                        map = xmap_dereference(dev_maps->attr_map[tci]);
                        if (map && map != new_map)
                                kfree_rcu(map, rcu);
                }
        }

        kfree_rcu(dev_maps, rcu);

out_no_old_maps:
        dev_maps = new_dev_maps;
        active = true;

out_no_new_maps:
        if (!is_rxqs_map) {
                /* update Tx queue numa node */
                netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index),
                                             (numa_node_id >= 0) ?
                                             numa_node_id : NUMA_NO_NODE);
        }

        if (!dev_maps)
                goto out_no_maps;

        /* removes tx-queue from unused CPUs/rx-queues */
        for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
             j < nr_ids;) {
                for (i = tc, tci = j * num_tc; i--; tci++)
                        active |= remove_xps_queue(dev_maps, tci, index);
                if (!netif_attr_test_mask(j, mask, nr_ids) ||
                    !netif_attr_test_online(j, online_mask, nr_ids))
                        active |= remove_xps_queue(dev_maps, tci, index);
                for (i = num_tc - tc, tci++; --i; tci++)
                        active |= remove_xps_queue(dev_maps, tci, index);
        }

        /* free map if not active */
        if (!active)
                reset_xps_maps(dev, dev_maps, is_rxqs_map);

out_no_maps:
        mutex_unlock(&xps_map_mutex);

        return 0;
error:
        /* remove any maps that we added */
        for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
             j < nr_ids;) {
                for (i = num_tc, tci = j * num_tc; i--; tci++) {
                        new_map = xmap_dereference(new_dev_maps->attr_map[tci]);
                        map = dev_maps ?
                              xmap_dereference(dev_maps->attr_map[tci]) :
                              NULL;
                        if (new_map && new_map != map)
                                kfree(new_map);
                }
        }

        mutex_unlock(&xps_map_mutex);

        kfree(new_dev_maps);
        return -ENOMEM;
}
EXPORT_SYMBOL_GPL(__netif_set_xps_queue);

int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
                        u16 index)
{
        int ret;

        cpus_read_lock();
        ret =  __netif_set_xps_queue(dev, cpumask_bits(mask), index, false);
        cpus_read_unlock();

        return ret;
}
EXPORT_SYMBOL(netif_set_xps_queue);

#endif
static void netdev_unbind_all_sb_channels(struct net_device *dev)
{
        struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues];

        /* Unbind any subordinate channels */
        while (txq-- != &dev->_tx[0]) {
                if (txq->sb_dev)
                        netdev_unbind_sb_channel(dev, txq->sb_dev);
        }
}

void netdev_reset_tc(struct net_device *dev)
{
#ifdef CONFIG_XPS
        netif_reset_xps_queues_gt(dev, 0);
#endif
        netdev_unbind_all_sb_channels(dev);

        /* Reset TC configuration of device */
        dev->num_tc = 0;
        memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq));
        memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map));
}
EXPORT_SYMBOL(netdev_reset_tc);

int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset)
{
        if (tc >= dev->num_tc)
                return -EINVAL;

#ifdef CONFIG_XPS
        netif_reset_xps_queues(dev, offset, count);
#endif
        dev->tc_to_txq[tc].count = count;
        dev->tc_to_txq[tc].offset = offset;
        return 0;
}
EXPORT_SYMBOL(netdev_set_tc_queue);

int netdev_set_num_tc(struct net_device *dev, u8 num_tc)
{
        if (num_tc > TC_MAX_QUEUE)
                return -EINVAL;

#ifdef CONFIG_XPS
        netif_reset_xps_queues_gt(dev, 0);
#endif
        netdev_unbind_all_sb_channels(dev);

        dev->num_tc = num_tc;
        return 0;
}
EXPORT_SYMBOL(netdev_set_num_tc);

void netdev_unbind_sb_channel(struct net_device *dev,
                              struct net_device *sb_dev)
{
        struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues];

#ifdef CONFIG_XPS
        netif_reset_xps_queues_gt(sb_dev, 0);
#endif
        memset(sb_dev->tc_to_txq, 0, sizeof(sb_dev->tc_to_txq));
        memset(sb_dev->prio_tc_map, 0, sizeof(sb_dev->prio_tc_map));

        while (txq-- != &dev->_tx[0]) {
                if (txq->sb_dev == sb_dev)
                        txq->sb_dev = NULL;
        }
}
EXPORT_SYMBOL(netdev_unbind_sb_channel);

int netdev_bind_sb_channel_queue(struct net_device *dev,
                                 struct net_device *sb_dev,
                                 u8 tc, u16 count, u16 offset)
{
        /* Make certain the sb_dev and dev are already configured */
        if (sb_dev->num_tc >= 0 || tc >= dev->num_tc)
                return -EINVAL;

        /* We cannot hand out queues we don't have */
        if ((offset + count) > dev->real_num_tx_queues)
                return -EINVAL;

        /* Record the mapping */
        sb_dev->tc_to_txq[tc].count = count;
        sb_dev->tc_to_txq[tc].offset = offset;

        /* Provide a way for Tx queue to find the tc_to_txq map or
         * XPS map for itself.
         */
        while (count--)
                netdev_get_tx_queue(dev, count + offset)->sb_dev = sb_dev;

        return 0;
}
EXPORT_SYMBOL(netdev_bind_sb_channel_queue);

int netdev_set_sb_channel(struct net_device *dev, u16 channel)
{
        /* Do not use a multiqueue device to represent a subordinate channel */
        if (netif_is_multiqueue(dev))
                return -ENODEV;

        /* We allow channels 1 - 32767 to be used for subordinate channels.
         * Channel 0 is meant to be "native" mode and used only to represent
         * the main root device. We allow writing 0 to reset the device back
         * to normal mode after being used as a subordinate channel.
         */
        if (channel > S16_MAX)
                return -EINVAL;

        dev->num_tc = -channel;

        return 0;
}
EXPORT_SYMBOL(netdev_set_sb_channel);

/*
 * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues
 * greater than 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)
{
        bool disabling;
        int rc;

        disabling = txq < dev->real_num_tx_queues;

        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);

                dev->real_num_tx_queues = txq;

                if (disabling) {
                        synchronize_net();
                        qdisc_reset_all_tx_gt(dev, txq);
#ifdef CONFIG_XPS
                        netif_reset_xps_queues_gt(dev, txq);
#endif
                }
        } else {
                dev->real_num_tx_queues = txq;
        }

        return 0;
}
EXPORT_SYMBOL(netif_set_real_num_tx_queues);

#ifdef CONFIG_SYSFS
/**
 *      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 is_kdump_kernel() ?
                1 : min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
}
EXPORT_SYMBOL(netif_get_num_default_rss_queues);

static void __netif_reschedule(struct Qdisc *q)
{
        struct softnet_data *sd;
        unsigned long flags;

        local_irq_save(flags);
        sd = this_cpu_ptr(&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);

struct dev_kfree_skb_cb {
        enum skb_free_reason reason;
};

static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb)
{
        return (struct dev_kfree_skb_cb *)skb->cb;
}

void netif_schedule_queue(struct netdev_queue *txq)
{
        rcu_read_lock();
        if (!(txq->state & QUEUE_STATE_ANY_XOFF)) {
                struct Qdisc *q = rcu_dereference(txq->qdisc);

                __netif_schedule(q);
        }
        rcu_read_unlock();
}
EXPORT_SYMBOL(netif_schedule_queue);

void netif_tx_wake_queue(struct netdev_queue *dev_queue)
{
        if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) {
                struct Qdisc *q;

                rcu_read_lock();
                q = rcu_dereference(dev_queue->qdisc);
                __netif_schedule(q);
                rcu_read_unlock();
        }
}
EXPORT_SYMBOL(netif_tx_wake_queue);

void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
{
        unsigned long flags;

        if (unlikely(!skb))
                return;

        if (likely(refcount_read(&skb->users) == 1)) {
                smp_rmb();
                refcount_set(&skb->users, 0);
        } else if (likely(!refcount_dec_and_test(&skb->users))) {
                return;
        }
        get_kfree_skb_cb(skb)->reason = reason;
        local_irq_save(flags);
        skb->next = __this_cpu_read(softnet_data.completion_queue);
        __this_cpu_write(softnet_data.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, enum skb_free_reason reason)
{
        if (in_irq() || irqs_disabled())
                __dev_kfree_skb_irq(skb, reason);
        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);

/*
 * Returns a Tx hash based on the given packet descriptor a Tx queues' number
 * to be used as a distribution range.
 */
static u16 skb_tx_hash(const struct net_device *dev,
                       const struct net_device *sb_dev,
                       struct sk_buff *skb)
{
        u32 hash;
        u16 qoffset = 0;
        u16 qcount = dev->real_num_tx_queues;

        if (dev->num_tc) {
                u8 tc = netdev_get_prio_tc_map(dev, skb->priority);

                qoffset = sb_dev->tc_to_txq[tc].offset;
                qcount = sb_dev->tc_to_txq[tc].count;
        }

        if (skb_rx_queue_recorded(skb)) {
                hash = skb_get_rx_queue(skb);
                while (unlikely(hash >= qcount))
                        hash -= qcount;
                return hash + qoffset;
        }

        return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
}

static void skb_warn_bad_offload(const struct sk_buff *skb)
{
        static const netdev_features_t null_features;
        struct net_device *dev = skb->dev;
        const char *name = "";

        if (!net_ratelimit())
                return;

        if (dev) {
                if (dev->dev.parent)
                        name = dev_driver_string(dev->dev.parent);
                else
                        name = netdev_name(dev);
        }
        WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d gso_size=%d "
             "gso_type=%d ip_summed=%d\n",
             name, dev ? &dev->features : &null_features,
             skb->sk ? &skb->sk->sk_route_caps : &null_features,
             skb->len, skb->data_len, skb_shinfo(skb)->gso_size,
             skb_shinfo(skb)->gso_type, skb->ip_summed);
}

/*
 * Invalidate hardware checksum when packet is to be mangled, and
 * complete checksum manually on outgoing path.
 */
int skb_checksum_help(struct sk_buff *skb)
{
        __wsum csum;
        int ret = 0, offset;

        if (skb->ip_summed == CHECKSUM_COMPLETE)
                goto out_set_summed;

        if (unlikely(skb_shinfo(skb)->gso_size)) {
                skb_warn_bad_offload(skb);
                return -EINVAL;
        }

        /* Before computing a checksum, we should make sure no frag could
         * be modified by an external entity : checksum could be wrong.
         */
        if (skb_has_shared_frag(skb)) {
                ret = __skb_linearize(skb);
                if (ret)
                        goto out;
        }

        offset = skb_checksum_start_offset(skb);
        BUG_ON(offset >= skb_headlen(skb));
        csum = skb_checksum(skb, offset, skb->len - offset, 0);

        offset += skb->csum_offset;
        BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb));

        if (skb_cloned(skb) &&
            !skb_clone_writable(skb, offset + sizeof(__sum16))) {
                ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
                if (ret)
                        goto out;
        }

        *(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0;
out_set_summed:
        skb->ip_summed = CHECKSUM_NONE;
out:
        return ret;
}
EXPORT_SYMBOL(skb_checksum_help);

int skb_crc32c_csum_help(struct sk_buff *skb)
{
        __le32 crc32c_csum;
        int ret = 0, offset, start;

        if (skb->ip_summed != CHECKSUM_PARTIAL)
                goto out;

        if (unlikely(skb_is_gso(skb)))
                goto out;

        /* Before computing a checksum, we should make sure no frag could
         * be modified by an external entity : checksum could be wrong.
         */
        if (unlikely(skb_has_shared_frag(skb))) {
                ret = __skb_linearize(skb);
                if (ret)
                        goto out;
        }
        start = skb_checksum_start_offset(skb);
        offset = start + offsetof(struct sctphdr, checksum);
        if (WARN_ON_ONCE(offset >= skb_headlen(skb))) {
                ret = -EINVAL;
                goto out;
        }
        if (skb_cloned(skb) &&
            !skb_clone_writable(skb, offset + sizeof(__le32))) {
                ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
                if (ret)
                        goto out;
        }
        crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start,
                                                  skb->len - start, ~(__u32)0,
                                                  crc32c_csum_stub));
        *(__le32 *)(skb->data + offset) = crc32c_csum;
        skb->ip_summed = CHECKSUM_NONE;
        skb->csum_not_inet = 0;
out:
        return ret;
}

__be16 skb_network_protocol(struct sk_buff *skb, int *depth)
{
        __be16 type = skb->protocol;

        /* Tunnel gso handlers can set protocol to ethernet. */
        if (type == htons(ETH_P_TEB)) {
                struct ethhdr *eth;

                if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr))))
                        return 0;

                eth = (struct ethhdr *)skb->data;
                type = eth->h_proto;
        }

        return __vlan_get_protocol(skb, type, depth);
}

/**
 *      skb_mac_gso_segment - mac layer segmentation handler.
 *      @skb: buffer to segment
 *      @features: features for the output path (see dev->features)
 */
struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
                                    netdev_features_t features)
{
        struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
        struct packet_offload *ptype;
        int vlan_depth = skb->mac_len;
        __be16 type = skb_network_protocol(skb, &vlan_depth);

        if (unlikely(!type))
                return ERR_PTR(-EINVAL);

        __skb_pull(skb, vlan_depth);

        rcu_read_lock();
        list_for_each_entry_rcu(ptype, &offload_base, list) {
                if (ptype->type == type && ptype->callbacks.gso_segment) {
                        segs = ptype->callbacks.gso_segment(skb, features);
                        break;
                }
        }
        rcu_read_unlock();

        __skb_push(skb, skb->data - skb_mac_header(skb));

        return segs;
}
EXPORT_SYMBOL(skb_mac_gso_segment);


/* openvswitch calls this on rx path, so we need a different check.
 */
static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
{
        if (tx_path)
                return skb->ip_summed != CHECKSUM_PARTIAL &&
                       skb->ip_summed != CHECKSUM_UNNECESSARY;

        return skb->ip_summed == CHECKSUM_NONE;
}

/**
 *      __skb_gso_segment - Perform segmentation on skb.
 *      @skb: buffer to segment
 *      @features: features for the output path (see dev->features)
 *      @tx_path: whether it is called in TX path
 *
 *      This function segments the given skb and returns a list of segments.
 *
 *      It may return NULL if the skb requires no segmentation.  This is
 *      only possible when GSO is used for verifying header integrity.
 *
 *      Segmentation preserves SKB_SGO_CB_OFFSET bytes of previous skb cb.
 */
struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
                                  netdev_features_t features, bool tx_path)
{
        struct sk_buff *segs;

        if (unlikely(skb_needs_check(skb, tx_path))) {
                int err;

                /* We're going to init ->check field in TCP or UDP header */
                err = skb_cow_head(skb, 0);
                if (err < 0)
                        return ERR_PTR(err);
        }

        /* Only report GSO partial support if it will enable us to
         * support segmentation on this frame without needing additional
         * work.
         */
        if (features & NETIF_F_GSO_PARTIAL) {
                netdev_features_t partial_features = NETIF_F_GSO_ROBUST;
                struct net_device *dev = skb->dev;

                partial_features |= dev->features & dev->gso_partial_features;
                if (!skb_gso_ok(skb, features | partial_features))
                        features &= ~NETIF_F_GSO_PARTIAL;
        }

        BUILD_BUG_ON(SKB_SGO_CB_OFFSET +
                     sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb));

        SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb);
        SKB_GSO_CB(skb)->encap_level = 0;

        skb_reset_mac_header(skb);
        skb_reset_mac_len(skb);

        segs = skb_mac_gso_segment(skb, features);

        if (unlikely(skb_needs_check(skb, tx_path) && !IS_ERR(segs)))
                skb_warn_bad_offload(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, struct sk_buff *skb)
{
        if (net_ratelimit()) {
                pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>");
                if (dev)
                        pr_err("dev features: %pNF\n", &dev->features);
                pr_err("skb len=%u data_len=%u pkt_type=%u gso_size=%u gso_type=%u nr_frags=%u ip_summed=%u csum=%x csum_complete_sw=%d csum_valid=%d csum_level=%u\n",
                       skb->len, skb->data_len, skb->pkt_type,
                       skb_shinfo(skb)->gso_size, skb_shinfo(skb)->gso_type,
                       skb_shinfo(skb)->nr_frags, skb->ip_summed, skb->csum,
                       skb->csum_complete_sw, skb->csum_valid, skb->csum_level);
                dump_stack();
        }
}
EXPORT_SYMBOL(netdev_rx_csum_fault);
#endif

/* XXX: check that highmem exists at all on the given 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;
                }
        }
#endif
        return 0;
}

/* If MPLS offload request, verify we are testing hardware MPLS features
 * instead of standard features for the netdev.
 */
#if IS_ENABLED(CONFIG_NET_MPLS_GSO)
static netdev_features_t net_mpls_features(struct sk_buff *skb,
                                           netdev_features_t features,
                                           __be16 type)
{
        if (eth_p_mpls(type))
                features &= skb->dev->mpls_features;

        return features;
}
#else
static netdev_features_t net_mpls_features(struct sk_buff *skb,
                                           netdev_features_t features,
                                           __be16 type)
{
        return features;
}
#endif

static netdev_features_t harmonize_features(struct sk_buff *skb,
        netdev_features_t features)
{
        int tmp;
        __be16 type;

        type = skb_network_protocol(skb, &tmp);
        features = net_mpls_features(skb, features, type);

        if (skb->ip_summed != CHECKSUM_NONE &&
            !can_checksum_protocol(features, type)) {
                features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
        }
        if (illegal_highdma(skb->dev, skb))
                features &= ~NETIF_F_SG;

        return features;
}

netdev_features_t passthru_features_check(struct sk_buff *skb,
                                          struct net_device *dev,
                                          netdev_features_t features)
{
        return features;
}
EXPORT_SYMBOL(passthru_features_check);

static netdev_features_t dflt_features_check(struct sk_buff *skb,
                                             struct net_device *dev,
                                             netdev_features_t features)
{
        return vlan_features_check(skb, features);
}

static netdev_features_t gso_features_check(const struct sk_buff *skb,
                                            struct net_device *dev,
                                            netdev_features_t features)
{
        u16 gso_segs = skb_shinfo(skb)->gso_segs;

        if (gso_segs > dev->gso_max_segs)
                return features & ~NETIF_F_GSO_MASK;

        /* Support for GSO partial features requires software
         * intervention before we can actually process the packets
         * so we need to strip support for any partial features now
         * and we can pull them back in after we have partially
         * segmented the frame.
         */
        if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL))
                features &= ~dev->gso_partial_features;

        /* Make sure to clear the IPv4 ID mangling feature if the
         * IPv4 header has the potential to be fragmented.
         */
        if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) {
                struct iphdr *iph = skb->encapsulation ?
                                    inner_ip_hdr(skb) : ip_hdr(skb);

                if (!(iph->frag_off & htons(IP_DF)))
                        features &= ~NETIF_F_TSO_MANGLEID;
        }

        return features;
}

netdev_features_t netif_skb_features(struct sk_buff *skb)
{
        struct net_device *dev = skb->dev;
        netdev_features_t features = dev->features;

        if (skb_is_gso(skb))
                features = gso_features_check(skb, dev, features);

        /* If encapsulation offload request, verify we are testing
         * hardware encapsulation features instead of standard
         * features for the netdev
         */
        if (skb->encapsulation)
                features &= dev->hw_enc_features;

        if (skb_vlan_tagged(skb))
                features = netdev_intersect_features(features,
                                                     dev->vlan_features |
                                                     NETIF_F_HW_VLAN_CTAG_TX |
                                                     NETIF_F_HW_VLAN_STAG_TX);

        if (dev->netdev_ops->ndo_features_check)
                features &= dev->netdev_ops->ndo_features_check(skb, dev,
                                                                features);
        else
                features &= dflt_features_check(skb, dev, features);

        return harmonize_features(skb, features);
}
EXPORT_SYMBOL(netif_skb_features);

static int xmit_one(struct sk_buff *skb, struct net_device *dev,
                    struct netdev_queue *txq, bool more)
{
        unsigned int len;
        int rc;

        if (dev_nit_active(dev))
                dev_queue_xmit_nit(skb, dev);

        len = skb->len;
        trace_net_dev_start_xmit(skb, dev);
        rc = netdev_start_xmit(skb, dev, txq, more);
        trace_net_dev_xmit(skb, rc, dev, len);

        return rc;
}

struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *dev,
                                    struct netdev_queue *txq, int *ret)
{
        struct sk_buff *skb = first;
        int rc = NETDEV_TX_OK;

        while (skb) {
                struct sk_buff *next = skb->next;

                skb_mark_not_on_list(skb);
                rc = xmit_one(skb, dev, txq, next != NULL);
                if (unlikely(!dev_xmit_complete(rc))) {
                        skb->next = next;
                        goto out;
                }

                skb = next;
                if (netif_tx_queue_stopped(txq) && skb) {
                        rc = NETDEV_TX_BUSY;
                        break;
                }
        }

out:
        *ret = rc;
        return skb;
}

static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb,
                                          netdev_features_t features)
{
        if (skb_vlan_tag_present(skb) &&
            !vlan_hw_offload_capable(features, skb->vlan_proto))
                skb = __vlan_hwaccel_push_inside(skb);
        return skb;
}

int skb_csum_hwoffload_help(struct sk_buff *skb,
                            const netdev_features_t features)
{
        if (unlikely(skb->csum_not_inet))
                return !!(features & NETIF_F_SCTP_CRC) ? 0 :
                        skb_crc32c_csum_help(skb);

        return !!(features & NETIF_F_CSUM_MASK) ? 0 : skb_checksum_help(skb);
}
EXPORT_SYMBOL(skb_csum_hwoffload_help);

static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev, bool *again)
{
        netdev_features_t features;

        features = netif_skb_features(skb);
        skb = validate_xmit_vlan(skb, features);
        if (unlikely(!skb))
                goto out_null;

        skb = sk_validate_xmit_skb(skb, dev);
        if (unlikely(!skb))
                goto out_null;

        if (netif_needs_gso(skb, features)) {
                struct sk_buff *segs;

                segs = skb_gso_segment(skb, features);
                if (IS_ERR(segs)) {
                        goto out_kfree_skb;
                } else if (segs) {
                        consume_skb(skb);
                        skb = segs;
                }
        } else {
                if (skb_needs_linearize(skb, features) &&
                    __skb_linearize(skb))
                        goto out_kfree_skb;

                /* If packet is not checksummed and device does not
                 * support checksumming for this protocol, complete
                 * checksumming here.
                 */
                if (skb->ip_summed == CHECKSUM_PARTIAL) {
                        if (skb->encapsulation)
                                skb_set_inner_transport_header(skb,
                                                               skb_checksum_start_offset(skb));
                        else
                                skb_set_transport_header(skb,
                                                         skb_checksum_start_offset(skb));
                        if (skb_csum_hwoffload_help(skb, features))
                                goto out_kfree_skb;
                }
        }

        skb = validate_xmit_xfrm(skb, features, again);

        return skb;

out_kfree_skb:
        kfree_skb(skb);
out_null:
        atomic_long_inc(&dev->tx_dropped);
        return NULL;
}

struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again)
{
        struct sk_buff *next, *head = NULL, *tail;

        for (; skb != NULL; skb = next) {
                next = skb->next;
                skb_mark_not_on_list(skb);

                /* in case skb wont be segmented, point to itself */
                skb->prev = skb;

                skb = validate_xmit_skb(skb, dev, again);
                if (!skb)
                        continue;

                if (!head)
                        head = skb;
                else
                        tail->next = skb;
                /* If skb was segmented, skb->prev points to
                 * the last segment. If not, it still contains skb.
                 */
                tail = skb->prev;
        }
        return head;
}
EXPORT_SYMBOL_GPL(validate_xmit_skb_list);

static void qdisc_pkt_len_init(struct sk_buff *skb)
{
        const struct skb_shared_info *shinfo = skb_shinfo(skb);

        qdisc_skb_cb(skb)->pkt_len = skb->len;

        /* To get more precise estimation of bytes sent on wire,
         * we add to pkt_len the headers size of all segments
         */
        if (shinfo->gso_size)  {
                unsigned int hdr_len;
                u16 gso_segs = shinfo->gso_segs;

                /* mac layer + network layer */
                hdr_len = skb_transport_header(skb) - skb_mac_header(skb);

                /* + transport layer */
                if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) {
                        const struct tcphdr *th;
                        struct tcphdr _tcphdr;

                        th = skb_header_pointer(skb, skb_transport_offset(skb),
                                                sizeof(_tcphdr), &_tcphdr);
                        if (likely(th))
                                hdr_len += __tcp_hdrlen(th);
                } else {
                        struct udphdr _udphdr;

                        if (skb_header_pointer(skb, skb_transport_offset(skb),
                                               sizeof(_udphdr), &_udphdr))
                                hdr_len += sizeof(struct udphdr);
                }

                if (shinfo->gso_type & SKB_GSO_DODGY)
                        gso_segs = DIV_ROUND_UP(skb->len - hdr_len,
                                                shinfo->gso_size);

                qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len;
        }
}

static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
                                 struct net_device *dev,
                                 struct netdev_queue *txq)
{
        spinlock_t *root_lock = qdisc_lock(q);
        struct sk_buff *to_free = NULL;
        bool contended;
        int rc;

        qdisc_calculate_pkt_len(skb, q);

        if (q->flags & TCQ_F_NOLOCK) {
                if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
                        __qdisc_drop(skb, &to_free);
                        rc = NET_XMIT_DROP;
                } else {
                        rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
                        qdisc_run(q);
                }

                if (unlikely(to_free))
                        kfree_skb_list(to_free);
                return rc;
        }

        /*
         * Heuristic to force contended enqueues to serialize on a
         * separate lock before trying to get qdisc main lock.
         * This permits qdisc->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))) {
                __qdisc_drop(skb, &to_free);
                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.
                 */

                qdisc_bstats_update(q, skb);

                if (sch_direct_xmit(skb, q, dev, txq, root_lock, true)) {
                        if (unlikely(contended)) {
                                spin_unlock(&q->busylock);
                                contended = false;
                        }
                        __qdisc_run(q);
                }

                qdisc_run_end(q);
                rc = NET_XMIT_SUCCESS;
        } else {
                rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
                if (qdisc_run_begin(q)) {
                        if (unlikely(contended)) {
                                spin_unlock(&q->busylock);
                                contended = false;
                        }
                        __qdisc_run(q);
                        qdisc_run_end(q);
                }
        }
        spin_unlock(root_lock);
        if (unlikely(to_free))
                kfree_skb_list(to_free);
        if (unlikely(contended))
                spin_unlock(&q->busylock);
        return rc;
}

#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
static void skb_update_prio(struct sk_buff *skb)
{
        const struct netprio_map *map;
        const struct sock *sk;
        unsigned int prioidx;

        if (skb->priority)
                return;
        map = rcu_dereference_bh(skb->dev->priomap);
        if (!map)
                return;
        sk = skb_to_full_sk(skb);
        if (!sk)
                return;

        prioidx = sock_cgroup_prioidx(&sk->sk_cgrp_data);

        if (prioidx < map->priomap_len)
                skb->priority = map->priomap[prioidx];
}
#else
#define skb_update_prio(skb)
#endif

DEFINE_PER_CPU(int, xmit_recursion);
EXPORT_SYMBOL(xmit_recursion);

/**
 *      dev_loopback_xmit - loop back @skb
 *      @net: network namespace this loopback is happening in
 *      @sk:  sk needed to be a netfilter okfn
 *      @skb: buffer to transmit
 */
int dev_loopback_xmit(struct net *net, struct sock *sk, 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);

#ifdef CONFIG_NET_EGRESS
static struct sk_buff *
sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
{
        struct mini_Qdisc *miniq = rcu_dereference_bh(dev->miniq_egress);
        struct tcf_result cl_res;

        if (!miniq)
                return skb;

        /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
        mini_qdisc_bstats_cpu_update(miniq, skb);

        switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) {
        case TC_ACT_OK:
        case TC_ACT_RECLASSIFY:
                skb->tc_index = TC_H_MIN(cl_res.classid);
                break;
        case TC_ACT_SHOT:
                mini_qdisc_qstats_cpu_drop(miniq);
                *ret = NET_XMIT_DROP;
                kfree_skb(skb);
                return NULL;
        case TC_ACT_STOLEN:
        case TC_ACT_QUEUED:
        case TC_ACT_TRAP:
                *ret = NET_XMIT_SUCCESS;
                consume_skb(skb);
                return NULL;
        case TC_ACT_REDIRECT:
                /* No need to push/pop skb's mac_header here on egress! */
                skb_do_redirect(skb);
                *ret = NET_XMIT_SUCCESS;
                return NULL;
        default:
                break;
        }

        return skb;
}
#endif /* CONFIG_NET_EGRESS */

#ifdef CONFIG_XPS
static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb,
                               struct xps_dev_maps *dev_maps, unsigned int tci)
{
        struct xps_map *map;
        int queue_index = -1;

        if (dev->num_tc) {
                tci *= dev->num_tc;
                tci += netdev_get_prio_tc_map(dev, skb->priority);
        }

        map = rcu_dereference(dev_maps->attr_map[tci]);
        if (map) {
                if (map->len == 1)
                        queue_index = map->queues[0];
                else
                        queue_index = map->queues[reciprocal_scale(
                                                skb_get_hash(skb), map->len)];
                if (unlikely(queue_index >= dev->real_num_tx_queues))
                        queue_index = -1;
        }
        return queue_index;
}
#endif

static int get_xps_queue(struct net_device *dev, struct net_device *sb_dev,
                         struct sk_buff *skb)
{
#ifdef CONFIG_XPS
        struct xps_dev_maps *dev_maps;
        struct sock *sk = skb->sk;
        int queue_index = -1;

        if (!static_key_false(&xps_needed))
                return -1;

        rcu_read_lock();
        if (!static_key_false(&xps_rxqs_needed))
                goto get_cpus_map;

        dev_maps = rcu_dereference(sb_dev->xps_rxqs_map);
        if (dev_maps) {
                int tci = sk_rx_queue_get(sk);

                if (tci >= 0 && tci < dev->num_rx_queues)
                        queue_index = __get_xps_queue_idx(dev, skb, dev_maps,
                                                          tci);
        }

get_cpus_map:
        if (queue_index < 0) {
                dev_maps = rcu_dereference(sb_dev->xps_cpus_map);
                if (dev_maps) {
                        unsigned int tci = skb->sender_cpu - 1;

                        queue_index = __get_xps_queue_idx(dev, skb, dev_maps,
                                                          tci);
                }
        }
        rcu_read_unlock();

        return queue_index;
#else
        return -1;
#endif
}

u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
                     struct net_device *sb_dev,
                     select_queue_fallback_t fallback)
{
        return 0;
}
EXPORT_SYMBOL(dev_pick_tx_zero);

u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
                       struct net_device *sb_dev,
                       select_queue_fallback_t fallback)
{
        return (u16)raw_smp_processor_id() % dev->real_num_tx_queues;
}
EXPORT_SYMBOL(dev_pick_tx_cpu_id);

static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
                            struct net_device *sb_dev)
{
        struct sock *sk = skb->sk;
        int queue_index = sk_tx_queue_get(sk);

        sb_dev = sb_dev ? : dev;

        if (queue_index < 0 || skb->ooo_okay ||
            queue_index >= dev->real_num_tx_queues) {
                int new_index = get_xps_queue(dev, sb_dev, skb);

                if (new_index < 0)
                        new_index = skb_tx_hash(dev, sb_dev, skb);

                if (queue_index != new_index && sk &&
                    sk_fullsock(sk) &&
                    rcu_access_pointer(sk->sk_dst_cache))
                        sk_tx_queue_set(sk, new_index);

                queue_index = new_index;
        }

        return queue_index;
}

struct netdev_queue *netdev_pick_tx(struct net_device *dev,
                                    struct sk_buff *skb,
                                    struct net_device *sb_dev)
{
        int queue_index = 0;

#ifdef CONFIG_XPS
        u32 sender_cpu = skb->sender_cpu - 1;

        if (sender_cpu >= (u32)NR_CPUS)
                skb->sender_cpu = raw_smp_processor_id() + 1;
#endif

        if (dev->real_num_tx_queues != 1) {
                const struct net_device_ops *ops = dev->netdev_ops;

                if (ops->ndo_select_queue)
                        queue_index = ops->ndo_select_queue(dev, skb, sb_dev,
                                                            __netdev_pick_tx);
                else
                        queue_index = __netdev_pick_tx(dev, skb, sb_dev);

                queue_index = netdev_cap_txqueue(dev, queue_index);
        }

        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
 *      @sb_dev: suboordinate device used for L2 forwarding offload
 *
 *      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
 */
static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
{
        struct net_device *dev = skb->dev;
        struct netdev_queue *txq;
        struct Qdisc *q;
        int rc = -ENOMEM;
        bool again = false;

        skb_reset_mac_header(skb);

        if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP))
                __skb_tstamp_tx(skb, NULL, skb->sk, SCM_TSTAMP_SCHED);

        /* Disable soft irqs for various locks below. Also
         * stops preemption for RCU.
         */
        rcu_read_lock_bh();

        skb_update_prio(skb);

        qdisc_pkt_len_init(skb);
#ifdef CONFIG_NET_CLS_ACT
        skb->tc_at_ingress = 0;
# ifdef CONFIG_NET_EGRESS
        if (static_branch_unlikely(&egress_needed_key)) {
                skb = sch_handle_egress(skb, &rc, dev);
                if (!skb)
                        goto out;
        }
# endif
#endif
        /* If device/qdisc don'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);
        else
                skb_dst_force(skb);

        txq = netdev_pick_tx(dev, skb, sb_dev);
        q = rcu_dereference_bh(txq->qdisc);

        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 (unlikely(__this_cpu_read(xmit_recursion) >
                                     XMIT_RECURSION_LIMIT))
                                goto recursion_alert;

                        skb = validate_xmit_skb(skb, dev, &again);
                        if (!skb)
                                goto out;

                        HARD_TX_LOCK(dev, txq, cpu);

                        if (!netif_xmit_stopped(txq)) {
                                __this_cpu_inc(xmit_recursion);
                                skb = dev_hard_start_xmit(skb, dev, txq, &rc);
                                __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();

        atomic_long_inc(&dev->tx_dropped);
        kfree_skb_list(skb);
        return rc;
out:
        rcu_read_unlock_bh();
        return rc;
}

int dev_queue_xmit(struct sk_buff *skb)
{
        return __dev_queue_xmit(skb, NULL);
}
EXPORT_SYMBOL(dev_queue_xmit);

int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev)
{
        return __dev_queue_xmit(skb, sb_dev);
}
EXPORT_SYMBOL(dev_queue_xmit_accel);

int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
{
        struct net_device *dev = skb->dev;
        struct sk_buff *orig_skb = skb;
        struct netdev_queue *txq;
        int ret = NETDEV_TX_BUSY;
        bool again = false;

        if (unlikely(!netif_running(dev) ||
                     !netif_carrier_ok(dev)))
                goto drop;

        skb = validate_xmit_skb_list(skb, dev, &again);
        if (skb != orig_skb)
                goto drop;

        skb_set_queue_mapping(skb, queue_id);
        txq = skb_get_tx_queue(dev, skb);

        local_bh_disable();

        HARD_TX_LOCK(dev, txq, smp_processor_id());
        if (!netif_xmit_frozen_or_drv_stopped(txq))
                ret = netdev_start_xmit(skb, dev, txq, false);
        HARD_TX_UNLOCK(dev, txq);

        local_bh_enable();

        if (!dev_xmit_complete(ret))
                kfree_skb(skb);

        return ret;
drop:
        atomic_long_inc(&dev->tx_dropped);
        kfree_skb_list(skb);
        return NET_XMIT_DROP;
}
EXPORT_SYMBOL(dev_direct_xmit);

/*************************************************************************
 *                      Receiver routines
 *************************************************************************/

int netdev_max_backlog __read_mostly = 1000;
EXPORT_SYMBOL(netdev_max_backlog);

int netdev_tstamp_prequeue __read_mostly = 1;
int netdev_budget __read_mostly = 300;
unsigned int __read_mostly netdev_budget_usecs = 2000;
int weight_p __read_mostly = 64;           /* old backlog weight */
int dev_weight_rx_bias __read_mostly = 1;  /* bias for backlog weight */
int dev_weight_tx_bias __read_mostly = 1;  /* bias for output_queue quota */
int dev_rx_weight __read_mostly = 64;
int dev_tx_weight __read_mostly = 64;

/* Called with irq disabled */
static inline void ____napi_schedule(struct softnet_data *sd,
                                     struct napi_struct *napi)
{
        list_add_tail(&napi->poll_list, &sd->poll_list);
        __raise_softirq_irqoff(NET_RX_SOFTIRQ);
}

#ifdef CONFIG_RPS

/* One global table that all flow-based protocols share. */
struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly;
EXPORT_SYMBOL(rps_sock_flow_table);
u32 rps_cpu_mask __read_mostly;
EXPORT_SYMBOL(rps_cpu_mask);

struct static_key rps_needed __read_mostly;
EXPORT_SYMBOL(rps_needed);
struct static_key rfs_needed __read_mostly;
EXPORT_SYMBOL(rfs_needed);

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 < nr_cpu_ids) {
#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);