// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * INET         An implementation of the TCP/IP protocol suite for the LINUX
 *              operating system.  INET is implemented using the  BSD Socket
 *              interface as the means of communication with the user level.
 *
 *              PACKET - implements raw packet sockets.
 *
 * Authors:     Ross Biro
 *              Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *              Alan Cox, <gw4pts@gw4pts.ampr.org>
 *
 * Fixes:
 *              Alan Cox        :       verify_area() now used correctly
 *              Alan Cox        :       new skbuff lists, look ma no backlogs!
 *              Alan Cox        :       tidied skbuff lists.
 *              Alan Cox        :       Now uses generic datagram routines I
 *                                      added. Also fixed the peek/read crash
 *                                      from all old Linux datagram code.
 *              Alan Cox        :       Uses the improved datagram code.
 *              Alan Cox        :       Added NULL's for socket options.
 *              Alan Cox        :       Re-commented the code.
 *              Alan Cox        :       Use new kernel side addressing
 *              Rob Janssen     :       Correct MTU usage.
 *              Dave Platt      :       Counter leaks caused by incorrect
 *                                      interrupt locking and some slightly
 *                                      dubious gcc output. Can you read
 *                                      compiler: it said _VOLATILE_
 *      Richard Kooijman        :       Timestamp fixes.
 *              Alan Cox        :       New buffers. Use sk->mac.raw.
 *              Alan Cox        :       sendmsg/recvmsg support.
 *              Alan Cox        :       Protocol setting support
 *      Alexey Kuznetsov        :       Untied from IPv4 stack.
 *      Cyrus Durgin            :       Fixed kerneld for kmod.
 *      Michal Ostrowski        :       Module initialization cleanup.
 *         Ulises Alonso        :       Frame number limit removal and
 *                                      packet_set_ring memory leak.
 *              Eric Biederman  :       Allow for > 8 byte hardware addresses.
 *                                      The convention is that longer addresses
 *                                      will simply extend the hardware address
 *                                      byte arrays at the end of sockaddr_ll
 *                                      and packet_mreq.
 *              Johann Baudy    :       Added TX RING.
 *              Chetan Loke     :       Implemented TPACKET_V3 block abstraction
 *                                      layer.
 *                                      Copyright (C) 2011, <lokec@ccs.neu.edu>
 */

#include <linux/ethtool.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/capability.h>
#include <linux/fcntl.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/if_packet.h>
#include <linux/wireless.h>
#include <linux/kernel.h>
#include <linux/kmod.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <net/net_namespace.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/uaccess.h>
#include <asm/ioctls.h>
#include <asm/page.h>
#include <asm/cacheflush.h>
#include <asm/io.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/poll.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/mutex.h>
#include <linux/if_vlan.h>
#include <linux/virtio_net.h>
#include <linux/errqueue.h>
#include <linux/net_tstamp.h>
#include <linux/percpu.h>
#ifdef CONFIG_INET
#include <net/inet_common.h>
#endif
#include <linux/bpf.h>
#include <net/compat.h>

#include "internal.h"

/*
   Assumptions:
   - If the device has no dev->header_ops->create, there is no LL header
     visible above the device. In this case, its hard_header_len should be 0.
     The device may prepend its own header internally. In this case, its
     needed_headroom should be set to the space needed for it to add its
     internal header.
     For example, a WiFi driver pretending to be an Ethernet driver should
     set its hard_header_len to be the Ethernet header length, and set its
     needed_headroom to be (the real WiFi header length - the fake Ethernet
     header length).
   - packet socket receives packets with pulled ll header,
     so that SOCK_RAW should push it back.

On receive:
-----------

Incoming, dev_has_header(dev) == true
   mac_header -> ll header
   data       -> data

Outgoing, dev_has_header(dev) == true
   mac_header -> ll header
   data       -> ll header

Incoming, dev_has_header(dev) == false
   mac_header -> data
     However drivers often make it point to the ll header.
     This is incorrect because the ll header should be invisible to us.
   data       -> data

Outgoing, dev_has_header(dev) == false
   mac_header -> data. ll header is invisible to us.
   data       -> data

Resume
  If dev_has_header(dev) == false we are unable to restore the ll header,
    because it is invisible to us.


On transmit:
------------

dev_has_header(dev) == true
   mac_header -> ll header
   data       -> ll header

dev_has_header(dev) == false (ll header is invisible to us)
   mac_header -> data
   data       -> data

   We should set network_header on output to the correct position,
   packet classifier depends on it.
 */

/* Private packet socket structures. */

/* identical to struct packet_mreq except it has
 * a longer address field.
 */
struct packet_mreq_max {
        int             mr_ifindex;
        unsigned short  mr_type;
        unsigned short  mr_alen;
        unsigned char   mr_address[MAX_ADDR_LEN];
};

union tpacket_uhdr {
        struct tpacket_hdr  *h1;
        struct tpacket2_hdr *h2;
        struct tpacket3_hdr *h3;
        void *raw;
};

static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
                int closing, int tx_ring);

#define V3_ALIGNMENT    (8)

#define BLK_HDR_LEN     (ALIGN(sizeof(struct tpacket_block_desc), V3_ALIGNMENT))

#define BLK_PLUS_PRIV(sz_of_priv) \
        (BLK_HDR_LEN + ALIGN((sz_of_priv), V3_ALIGNMENT))

#define BLOCK_STATUS(x) ((x)->hdr.bh1.block_status)
#define BLOCK_NUM_PKTS(x)       ((x)->hdr.bh1.num_pkts)
#define BLOCK_O2FP(x)           ((x)->hdr.bh1.offset_to_first_pkt)
#define BLOCK_LEN(x)            ((x)->hdr.bh1.blk_len)
#define BLOCK_SNUM(x)           ((x)->hdr.bh1.seq_num)
#define BLOCK_O2PRIV(x) ((x)->offset_to_priv)

struct packet_sock;
static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
                       struct packet_type *pt, struct net_device *orig_dev);

static void *packet_previous_frame(struct packet_sock *po,
                struct packet_ring_buffer *rb,
                int status);
static void packet_increment_head(struct packet_ring_buffer *buff);
static int prb_curr_blk_in_use(struct tpacket_block_desc *);
static void *prb_dispatch_next_block(struct tpacket_kbdq_core *,
                        struct packet_sock *);
static void prb_retire_current_block(struct tpacket_kbdq_core *,
                struct packet_sock *, unsigned int status);
static int prb_queue_frozen(struct tpacket_kbdq_core *);
static void prb_open_block(struct tpacket_kbdq_core *,
                struct tpacket_block_desc *);
static void prb_retire_rx_blk_timer_expired(struct timer_list *);
static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *);
static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *);
static void prb_clear_rxhash(struct tpacket_kbdq_core *,
                struct tpacket3_hdr *);
static void prb_fill_vlan_info(struct tpacket_kbdq_core *,
                struct tpacket3_hdr *);
static void packet_flush_mclist(struct sock *sk);
static u16 packet_pick_tx_queue(struct sk_buff *skb);

struct packet_skb_cb {
        union {
                struct sockaddr_pkt pkt;
                union {
                        /* Trick: alias skb original length with
                         * ll.sll_family and ll.protocol in order
                         * to save room.
                         */
                        unsigned int origlen;
                        struct sockaddr_ll ll;
                };
        } sa;
};

#define vio_le() virtio_legacy_is_little_endian()

#define PACKET_SKB_CB(__skb)    ((struct packet_skb_cb *)((__skb)->cb))

#define GET_PBDQC_FROM_RB(x)    ((struct tpacket_kbdq_core *)(&(x)->prb_bdqc))
#define GET_PBLOCK_DESC(x, bid) \
        ((struct tpacket_block_desc *)((x)->pkbdq[(bid)].buffer))
#define GET_CURR_PBLOCK_DESC_FROM_CORE(x)       \
        ((struct tpacket_block_desc *)((x)->pkbdq[(x)->kactive_blk_num].buffer))
#define GET_NEXT_PRB_BLK_NUM(x) \
        (((x)->kactive_blk_num < ((x)->knum_blocks-1)) ? \
        ((x)->kactive_blk_num+1) : 0)

static void __fanout_unlink(struct sock *sk, struct packet_sock *po);
static void __fanout_link(struct sock *sk, struct packet_sock *po);

static int packet_direct_xmit(struct sk_buff *skb)
{
        return dev_direct_xmit(skb, packet_pick_tx_queue(skb));
}

static struct net_device *packet_cached_dev_get(struct packet_sock *po)
{
        struct net_device *dev;

        rcu_read_lock();
        dev = rcu_dereference(po->cached_dev);
        if (likely(dev))
                dev_hold(dev);
        rcu_read_unlock();

        return dev;
}

static void packet_cached_dev_assign(struct packet_sock *po,
                                     struct net_device *dev)
{
        rcu_assign_pointer(po->cached_dev, dev);
}

static void packet_cached_dev_reset(struct packet_sock *po)
{
        RCU_INIT_POINTER(po->cached_dev, NULL);
}

static bool packet_use_direct_xmit(const struct packet_sock *po)
{
        return po->xmit == packet_direct_xmit;
}

static u16 packet_pick_tx_queue(struct sk_buff *skb)
{
        struct net_device *dev = skb->dev;
        const struct net_device_ops *ops = dev->netdev_ops;
        int cpu = raw_smp_processor_id();
        u16 queue_index;

#ifdef CONFIG_XPS
        skb->sender_cpu = cpu + 1;
#endif
        skb_record_rx_queue(skb, cpu % dev->real_num_tx_queues);
        if (ops->ndo_select_queue) {
                queue_index = ops->ndo_select_queue(dev, skb, NULL);
                queue_index = netdev_cap_txqueue(dev, queue_index);
        } else {
                queue_index = netdev_pick_tx(dev, skb, NULL);
        }

        return queue_index;
}

/* __register_prot_hook must be invoked through register_prot_hook
 * or from a context in which asynchronous accesses to the packet
 * socket is not possible (packet_create()).
 */
static void __register_prot_hook(struct sock *sk)
{
        struct packet_sock *po = pkt_sk(sk);

        if (!po->running) {
                if (po->fanout)
                        __fanout_link(sk, po);
                else
                        dev_add_pack(&po->prot_hook);

                sock_hold(sk);
                po->running = 1;
        }
}

static void register_prot_hook(struct sock *sk)
{
        lockdep_assert_held_once(&pkt_sk(sk)->bind_lock);
        __register_prot_hook(sk);
}

/* If the sync parameter is true, we will temporarily drop
 * the po->bind_lock and do a synchronize_net to make sure no
 * asynchronous packet processing paths still refer to the elements
 * of po->prot_hook.  If the sync parameter is false, it is the
 * callers responsibility to take care of this.
 */
static void __unregister_prot_hook(struct sock *sk, bool sync)
{
        struct packet_sock *po = pkt_sk(sk);

        lockdep_assert_held_once(&po->bind_lock);

        po->running = 0;

        if (po->fanout)
                __fanout_unlink(sk, po);
        else
                __dev_remove_pack(&po->prot_hook);

        __sock_put(sk);

        if (sync) {
                spin_unlock(&po->bind_lock);
                synchronize_net();
                spin_lock(&po->bind_lock);
        }
}

static void unregister_prot_hook(struct sock *sk, bool sync)
{
        struct packet_sock *po = pkt_sk(sk);

        if (po->running)
                __unregister_prot_hook(sk, sync);
}

static inline struct page * __pure pgv_to_page(void *addr)
{
        if (is_vmalloc_addr(addr))
                return vmalloc_to_page(addr);
        return virt_to_page(addr);
}

static void __packet_set_status(struct packet_sock *po, void *frame, int status)
{
        union tpacket_uhdr h;

        h.raw = frame;
        switch (po->tp_version) {
        case TPACKET_V1:
                h.h1->tp_status = status;
                flush_dcache_page(pgv_to_page(&h.h1->tp_status));
                break;
        case TPACKET_V2:
                h.h2->tp_status = status;
                flush_dcache_page(pgv_to_page(&h.h2->tp_status));
                break;
        case TPACKET_V3:
                h.h3->tp_status = status;
                flush_dcache_page(pgv_to_page(&h.h3->tp_status));
                break;
        default:
                WARN(1, "TPACKET version not supported.\n");
                BUG();
        }

        smp_wmb();
}

static int __packet_get_status(const struct packet_sock *po, void *frame)
{
        union tpacket_uhdr h;

        smp_rmb();

        h.raw = frame;
        switch (po->tp_version) {
        case TPACKET_V1:
                flush_dcache_page(pgv_to_page(&h.h1->tp_status));
                return h.h1->tp_status;
        case TPACKET_V2:
                flush_dcache_page(pgv_to_page(&h.h2->tp_status));
                return h.h2->tp_status;
        case TPACKET_V3:
                flush_dcache_page(pgv_to_page(&h.h3->tp_status));
                return h.h3->tp_status;
        default:
                WARN(1, "TPACKET version not supported.\n");
                BUG();
                return 0;
        }
}

static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts,
                                   unsigned int flags)
{
        struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);

        if (shhwtstamps &&
            (flags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
            ktime_to_timespec64_cond(shhwtstamps->hwtstamp, ts))
                return TP_STATUS_TS_RAW_HARDWARE;

        if ((flags & SOF_TIMESTAMPING_SOFTWARE) &&
            ktime_to_timespec64_cond(skb->tstamp, ts))
                return TP_STATUS_TS_SOFTWARE;

        return 0;
}

static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame,
                                    struct sk_buff *skb)
{
        union tpacket_uhdr h;
        struct timespec64 ts;
        __u32 ts_status;

        if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
                return 0;

        h.raw = frame;
        /*
         * versions 1 through 3 overflow the timestamps in y2106, since they
         * all store the seconds in a 32-bit unsigned integer.
         * If we create a version 4, that should have a 64-bit timestamp,
         * either 64-bit seconds + 32-bit nanoseconds, or just 64-bit
         * nanoseconds.
         */
        switch (po->tp_version) {
        case TPACKET_V1:
                h.h1->tp_sec = ts.tv_sec;
                h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC;
                break;
        case TPACKET_V2:
                h.h2->tp_sec = ts.tv_sec;
                h.h2->tp_nsec = ts.tv_nsec;
                break;
        case TPACKET_V3:
                h.h3->tp_sec = ts.tv_sec;
                h.h3->tp_nsec = ts.tv_nsec;
                break;
        default:
                WARN(1, "TPACKET version not supported.\n");
                BUG();
        }

        /* one flush is safe, as both fields always lie on the same cacheline */
        flush_dcache_page(pgv_to_page(&h.h1->tp_sec));
        smp_wmb();

        return ts_status;
}

static void *packet_lookup_frame(const struct packet_sock *po,
                                 const struct packet_ring_buffer *rb,
                                 unsigned int position,
                                 int status)
{
        unsigned int pg_vec_pos, frame_offset;
        union tpacket_uhdr h;

        pg_vec_pos = position / rb->frames_per_block;
        frame_offset = position % rb->frames_per_block;

        h.raw = rb->pg_vec[pg_vec_pos].buffer +
                (frame_offset * rb->frame_size);

        if (status != __packet_get_status(po, h.raw))
                return NULL;

        return h.raw;
}

static void *packet_current_frame(struct packet_sock *po,
                struct packet_ring_buffer *rb,
                int status)
{
        return packet_lookup_frame(po, rb, rb->head, status);
}

static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc)
{
        del_timer_sync(&pkc->retire_blk_timer);
}

static void prb_shutdown_retire_blk_timer(struct packet_sock *po,
                struct sk_buff_head *rb_queue)
{
        struct tpacket_kbdq_core *pkc;

        pkc = GET_PBDQC_FROM_RB(&po->rx_ring);

        spin_lock_bh(&rb_queue->lock);
        pkc->delete_blk_timer = 1;
        spin_unlock_bh(&rb_queue->lock);

        prb_del_retire_blk_timer(pkc);
}

static void prb_setup_retire_blk_timer(struct packet_sock *po)
{
        struct tpacket_kbdq_core *pkc;

        pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
        timer_setup(&pkc->retire_blk_timer, prb_retire_rx_blk_timer_expired,
                    0);
        pkc->retire_blk_timer.expires = jiffies;
}

static int prb_calc_retire_blk_tmo(struct packet_sock *po,
                                int blk_size_in_bytes)
{
        struct net_device *dev;
        unsigned int mbits, div;
        struct ethtool_link_ksettings ecmd;
        int err;

        rtnl_lock();
        dev = __dev_get_by_index(sock_net(&po->sk), po->ifindex);
        if (unlikely(!dev)) {
                rtnl_unlock();
                return DEFAULT_PRB_RETIRE_TOV;
        }
        err = __ethtool_get_link_ksettings(dev, &ecmd);
        rtnl_unlock();
        if (err)
                return DEFAULT_PRB_RETIRE_TOV;

        /* If the link speed is so slow you don't really
         * need to worry about perf anyways
         */
        if (ecmd.base.speed < SPEED_1000 ||
            ecmd.base.speed == SPEED_UNKNOWN)
                return DEFAULT_PRB_RETIRE_TOV;

        div = ecmd.base.speed / 1000;
        mbits = (blk_size_in_bytes * 8) / (1024 * 1024);

        if (div)
                mbits /= div;

        if (div)
                return mbits + 1;
        return mbits;
}

static void prb_init_ft_ops(struct tpacket_kbdq_core *p1,
                        union tpacket_req_u *req_u)
{
        p1->feature_req_word = req_u->req3.tp_feature_req_word;
}

static void init_prb_bdqc(struct packet_sock *po,
                        struct packet_ring_buffer *rb,
                        struct pgv *pg_vec,
                        union tpacket_req_u *req_u)
{
        struct tpacket_kbdq_core *p1 = GET_PBDQC_FROM_RB(rb);
        struct tpacket_block_desc *pbd;

        memset(p1, 0x0, sizeof(*p1));

        p1->knxt_seq_num = 1;
        p1->pkbdq = pg_vec;
        pbd = (struct tpacket_block_desc *)pg_vec[0].buffer;
        p1->pkblk_start = pg_vec[0].buffer;
        p1->kblk_size = req_u->req3.tp_block_size;
        p1->knum_blocks = req_u->req3.tp_block_nr;
        p1->hdrlen = po->tp_hdrlen;
        p1->version = po->tp_version;
        p1->last_kactive_blk_num = 0;
        po->stats.stats3.tp_freeze_q_cnt = 0;
        if (req_u->req3.tp_retire_blk_tov)
                p1->retire_blk_tov = req_u->req3.tp_retire_blk_tov;
        else
                p1->retire_blk_tov = prb_calc_retire_blk_tmo(po,
                                                req_u->req3.tp_block_size);
        p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov);
        p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv;
        rwlock_init(&p1->blk_fill_in_prog_lock);

        p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv);
        prb_init_ft_ops(p1, req_u);
        prb_setup_retire_blk_timer(po);
        prb_open_block(p1, pbd);
}

/*  Do NOT update the last_blk_num first.
 *  Assumes sk_buff_head lock is held.
 */
static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc)
{
        mod_timer(&pkc->retire_blk_timer,
                        jiffies + pkc->tov_in_jiffies);
        pkc->last_kactive_blk_num = pkc->kactive_blk_num;
}

/*
 * Timer logic:
 * 1) We refresh the timer only when we open a block.
 *    By doing this we don't waste cycles refreshing the timer
 *        on packet-by-packet basis.
 *
 * With a 1MB block-size, on a 1Gbps line, it will take
 * i) ~8 ms to fill a block + ii) memcpy etc.
 * In this cut we are not accounting for the memcpy time.
 *
 * So, if the user sets the 'tmo' to 10ms then the timer
 * will never fire while the block is still getting filled
 * (which is what we want). However, the user could choose
 * to close a block early and that's fine.
 *
 * But when the timer does fire, we check whether or not to refresh it.
 * Since the tmo granularity is in msecs, it is not too expensive
 * to refresh the timer, lets say every '8' msecs.
 * Either the user can set the 'tmo' or we can derive it based on
 * a) line-speed and b) block-size.
 * prb_calc_retire_blk_tmo() calculates the tmo.
 *
 */
static void prb_retire_rx_blk_timer_expired(struct timer_list *t)
{
        struct packet_sock *po =
                from_timer(po, t, rx_ring.prb_bdqc.retire_blk_timer);
        struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
        unsigned int frozen;
        struct tpacket_block_desc *pbd;

        spin_lock(&po->sk.sk_receive_queue.lock);

        frozen = prb_queue_frozen(pkc);
        pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc);

        if (unlikely(pkc->delete_blk_timer))
                goto out;

        /* We only need to plug the race when the block is partially filled.
         * tpacket_rcv:
         *              lock(); increment BLOCK_NUM_PKTS; unlock()
         *              copy_bits() is in progress ...
         *              timer fires on other cpu:
         *              we can't retire the current block because copy_bits
         *              is in progress.
         *
         */
        if (BLOCK_NUM_PKTS(pbd)) {
                /* Waiting for skb_copy_bits to finish... */
                write_lock(&pkc->blk_fill_in_prog_lock);
                write_unlock(&pkc->blk_fill_in_prog_lock);
        }

        if (pkc->last_kactive_blk_num == pkc->kactive_blk_num) {
                if (!frozen) {
                        if (!BLOCK_NUM_PKTS(pbd)) {
                                /* An empty block. Just refresh the timer. */
                                goto refresh_timer;
                        }
                        prb_retire_current_block(pkc, po, TP_STATUS_BLK_TMO);
                        if (!prb_dispatch_next_block(pkc, po))
                                goto refresh_timer;
                        else
                                goto out;
                } else {
                        /* Case 1. Queue was frozen because user-space was
                         *         lagging behind.
                         */
                        if (prb_curr_blk_in_use(pbd)) {
                                /*
                                 * Ok, user-space is still behind.
                                 * So just refresh the timer.
                                 */
                                goto refresh_timer;
                        } else {
                               /* Case 2. queue was frozen,user-space caught up,
                                * now the link went idle && the timer fired.
                                * We don't have a block to close.So we open this
                                * block and restart the timer.
                                * opening a block thaws the queue,restarts timer
                                * Thawing/timer-refresh is a side effect.
                                */
                                prb_open_block(pkc, pbd);
                                goto out;
                        }
                }
        }

refresh_timer:
        _prb_refresh_rx_retire_blk_timer(pkc);

out:
        spin_unlock(&po->sk.sk_receive_queue.lock);
}

static void prb_flush_block(struct tpacket_kbdq_core *pkc1,
                struct tpacket_block_desc *pbd1, __u32 status)
{
        /* Flush everything minus the block header */

#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1
        u8 *start, *end;

        start = (u8 *)pbd1;

        /* Skip the block header(we know header WILL fit in 4K) */
        start += PAGE_SIZE;

        end = (u8 *)PAGE_ALIGN((unsigned long)pkc1->pkblk_end);
        for (; start < end; start += PAGE_SIZE)
                flush_dcache_page(pgv_to_page(start));

        smp_wmb();
#endif

        /* Now update the block status. */

        BLOCK_STATUS(pbd1) = status;

        /* Flush the block header */

#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1
        start = (u8 *)pbd1;
        flush_dcache_page(pgv_to_page(start));

        smp_wmb();
#endif
}

/*
 * Side effect:
 *
 * 1) flush the block
 * 2) Increment active_blk_num
 *
 * Note:We DONT refresh the timer on purpose.
 *      Because almost always the next block will be opened.
 */
static void prb_close_block(struct tpacket_kbdq_core *pkc1,
                struct tpacket_block_desc *pbd1,
                struct packet_sock *po, unsigned int stat)
{
        __u32 status = TP_STATUS_USER | stat;

        struct tpacket3_hdr *last_pkt;
        struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1;
        struct sock *sk = &po->sk;

        if (atomic_read(&po->tp_drops))
                status |= TP_STATUS_LOSING;

        last_pkt = (struct tpacket3_hdr *)pkc1->prev;
        last_pkt->tp_next_offset = 0;

        /* Get the ts of the last pkt */
        if (BLOCK_NUM_PKTS(pbd1)) {
                h1->ts_last_pkt.ts_sec = last_pkt->tp_sec;
                h1->ts_last_pkt.ts_nsec = last_pkt->tp_nsec;
        } else {
                /* Ok, we tmo'd - so get the current time.
                 *
                 * It shouldn't really happen as we don't close empty
                 * blocks. See prb_retire_rx_blk_timer_expired().
                 */
                struct timespec64 ts;
                ktime_get_real_ts64(&ts);
                h1->ts_last_pkt.ts_sec = ts.tv_sec;
                h1->ts_last_pkt.ts_nsec = ts.tv_nsec;
        }

        smp_wmb();

        /* Flush the block */
        prb_flush_block(pkc1, pbd1, status);

        sk->sk_data_ready(sk);

        pkc1->kactive_blk_num = GET_NEXT_PRB_BLK_NUM(pkc1);
}

static void prb_thaw_queue(struct tpacket_kbdq_core *pkc)
{
        pkc->reset_pending_on_curr_blk = 0;
}

/*
 * Side effect of opening a block:
 *
 * 1) prb_queue is thawed.
 * 2) retire_blk_timer is refreshed.
 *
 */
static void prb_open_block(struct tpacket_kbdq_core *pkc1,
        struct tpacket_block_desc *pbd1)
{
        struct timespec64 ts;
        struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1;

        smp_rmb();

        /* We could have just memset this but we will lose the
         * flexibility of making the priv area sticky
         */

        BLOCK_SNUM(pbd1) = pkc1->knxt_seq_num++;
        BLOCK_NUM_PKTS(pbd1) = 0;
        BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv);

        ktime_get_real_ts64(&ts);

        h1->ts_first_pkt.ts_sec = ts.tv_sec;
        h1->ts_first_pkt.ts_nsec = ts.tv_nsec;

        pkc1->pkblk_start = (char *)pbd1;
        pkc1->nxt_offset = pkc1->pkblk_start + BLK_PLUS_PRIV(pkc1->blk_sizeof_priv);

        BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv);
        BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN;

        pbd1->version = pkc1->version;
        pkc1->prev = pkc1->nxt_offset;
        pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size;

        prb_thaw_queue(pkc1);
        _prb_refresh_rx_retire_blk_timer(pkc1);

        smp_wmb();
}

/*
 * Queue freeze logic:
 * 1) Assume tp_block_nr = 8 blocks.
 * 2) At time 't0', user opens Rx ring.
 * 3) Some time past 't0', kernel starts filling blocks starting from 0 .. 7
 * 4) user-space is either sleeping or processing block '0'.
 * 5) tpacket_rcv is currently filling block '7', since there is no space left,
 *    it will close block-7,loop around and try to fill block '0'.
 *    call-flow:
 *    __packet_lookup_frame_in_block
 *      prb_retire_current_block()
 *      prb_dispatch_next_block()
 *        |->(BLOCK_STATUS == USER) evaluates to true
 *    5.1) Since block-0 is currently in-use, we just freeze the queue.
 * 6) Now there are two cases:
 *    6.1) Link goes idle right after the queue is frozen.
 *         But remember, the last open_block() refreshed the timer.
 *         When this timer expires,it will refresh itself so that we can
 *         re-open block-0 in near future.
 *    6.2) Link is busy and keeps on receiving packets. This is a simple
 *         case and __packet_lookup_frame_in_block will check if block-0
 *         is free and can now be re-used.
 */
static void prb_freeze_queue(struct tpacket_kbdq_core *pkc,
                                  struct packet_sock *po)
{
        pkc->reset_pending_on_curr_blk = 1;
        po->stats.stats3.tp_freeze_q_cnt++;
}

#define TOTAL_PKT_LEN_INCL_ALIGN(length) (ALIGN((length), V3_ALIGNMENT))

/*
 * If the next block is free then we will dispatch it
 * and return a good offset.
 * Else, we will freeze the queue.
 * So, caller must check the return value.
 */
static void *prb_dispatch_next_block(struct tpacket_kbdq_core *pkc,
                struct packet_sock *po)
{
        struct tpacket_block_desc *pbd;

        smp_rmb();

        /* 1. Get current block num */
        pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc);

        /* 2. If this block is currently in_use then freeze the queue */
        if (TP_STATUS_USER & BLOCK_STATUS(pbd)) {
                prb_freeze_queue(pkc, po);
                return NULL;
        }

        /*
         * 3.
         * open this block and return the offset where the first packet
         * needs to get stored.
         */
        prb_open_block(pkc, pbd);
        return (void *)pkc->nxt_offset;
}

static void prb_retire_current_block(struct tpacket_kbdq_core *pkc,
                struct packet_sock *po, unsigned int status)
{
        struct tpacket_block_desc *pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc);

        /* retire/close the current block */
        if (likely(TP_STATUS_KERNEL == BLOCK_STATUS(pbd))) {
                /*
                 * Plug the case where copy_bits() is in progress on
                 * cpu-0 and tpacket_rcv() got invoked on cpu-1, didn't
                 * have space to copy the pkt in the current block and
                 * called prb_retire_current_block()
                 *
                 * We don't need to worry about the TMO case because
                 * the timer-handler already handled this case.
                 */
                if (!(status & TP_STATUS_BLK_TMO)) {
                        /* Waiting for skb_copy_bits to finish... */
                        write_lock(&pkc->blk_fill_in_prog_lock);
                        write_unlock(&pkc->blk_fill_in_prog_lock);
                }
                prb_close_block(pkc, pbd, po, status);
                return;
        }
}

static int prb_curr_blk_in_use(struct tpacket_block_desc *pbd)
{
        return TP_STATUS_USER & BLOCK_STATUS(pbd);
}

static int prb_queue_frozen(struct tpacket_kbdq_core *pkc)
{
        return pkc->reset_pending_on_curr_blk;
}

static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb)
        __releases(&pkc->blk_fill_in_prog_lock)
{
        struct tpacket_kbdq_core *pkc  = GET_PBDQC_FROM_RB(rb);

        read_unlock(&pkc->blk_fill_in_prog_lock);
}

static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc,
                        struct tpacket3_hdr *ppd)
{
        ppd->hv1.tp_rxhash = skb_get_hash(pkc->skb);
}

static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc,
                        struct tpacket3_hdr *ppd)
{
        ppd->hv1.tp_rxhash = 0;
}

static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
                        struct tpacket3_hdr *ppd)
{
        if (skb_vlan_tag_present(pkc->skb)) {
                ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb);
                ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto);
                ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
        } else {
                ppd->hv1.tp_vlan_tci = 0;
                ppd->hv1.tp_vlan_tpid = 0;
                ppd->tp_status = TP_STATUS_AVAILABLE;
        }
}

static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc,
                        struct tpacket3_hdr *ppd)
{
        ppd->hv1.tp_padding = 0;
        prb_fill_vlan_info(pkc, ppd);

        if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH)
                prb_fill_rxhash(pkc, ppd);
        else
                prb_clear_rxhash(pkc, ppd);
}

static void prb_fill_curr_block(char *curr,
                                struct tpacket_kbdq_core *pkc,
                                struct tpacket_block_desc *pbd,
                                unsigned int len)
        __acquires(&pkc->blk_fill_in_prog_lock)
{
        struct tpacket3_hdr *ppd;

        ppd  = (struct tpacket3_hdr *)curr;
        ppd->tp_next_offset = TOTAL_PKT_LEN_INCL_ALIGN(len);
        pkc->prev = curr;
        pkc->nxt_offset += TOTAL_PKT_LEN_INCL_ALIGN(len);
        BLOCK_LEN(pbd) += TOTAL_PKT_LEN_INCL_ALIGN(len);
        BLOCK_NUM_PKTS(pbd) += 1;
        read_lock(&pkc->blk_fill_in_prog_lock);
        prb_run_all_ft_ops(pkc, ppd);
}

/* Assumes caller has the sk->rx_queue.lock */
static void *__packet_lookup_frame_in_block(struct packet_sock *po,
                                            struct sk_buff *skb,
                                            unsigned int len
                                            )
{
        struct tpacket_kbdq_core *pkc;
        struct tpacket_block_desc *pbd;
        char *curr, *end;

        pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
        pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc);

        /* Queue is frozen when user space is lagging behind */
        if (prb_queue_frozen(pkc)) {
                /*
                 * Check if that last block which caused the queue to freeze,
                 * is still in_use by user-space.
                 */
                if (prb_curr_blk_in_use(pbd)) {
                        /* Can't record this packet */
                        return NULL;
                } else {
                        /*
                         * Ok, the block was released by user-space.
                         * Now let's open that block.
                         * opening a block also thaws the queue.
                         * Thawing is a side effect.
                         */
                        prb_open_block(pkc, pbd);
                }
        }

        smp_mb();
        curr = pkc->nxt_offset;
        pkc->skb = skb;
        end = (char *)pbd + pkc->kblk_size;

        /* first try the current block */
        if (curr+TOTAL_PKT_LEN_INCL_ALIGN(len) < end) {
                prb_fill_curr_block(curr, pkc, pbd, len);
                return (void *)curr;
        }

        /* Ok, close the current block */
        prb_retire_current_block(pkc, po, 0);

        /* Now, try to dispatch the next block */
        curr = (char *)prb_dispatch_next_block(pkc, po);
        if (curr) {
                pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc);
                prb_fill_curr_block(curr, pkc, pbd, len);
                return (void *)curr;
        }

        /*
         * No free blocks are available.user_space hasn't caught up yet.
         * Queue was just frozen and now this packet will get dropped.
         */
        return NULL;
}

static void *packet_current_rx_frame(struct packet_sock *po,
                                            struct sk_buff *skb,
                                            int status, unsigned int len)
{
        char *curr = NULL;
        switch (po->tp_version) {
        case TPACKET_V1:
        case TPACKET_V2:
                curr = packet_lookup_frame(po, &po->rx_ring,
                                        po->rx_ring.head, status);
                return curr;
        case TPACKET_V3:
                return __packet_lookup_frame_in_block(po, skb, len);
        default:
                WARN(1, "TPACKET version not supported\n");
                BUG();
                return NULL;
        }
}

static void *prb_lookup_block(const struct packet_sock *po,
                              const struct packet_ring_buffer *rb,
                              unsigned int idx,
                              int status)
{
        struct tpacket_kbdq_core *pkc  = GET_PBDQC_FROM_RB(rb);
        struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, idx);

        if (status != BLOCK_STATUS(pbd))
                return NULL;
        return pbd;
}

static int prb_previous_blk_num(struct packet_ring_buffer *rb)
{
        unsigned int prev;
        if (rb->prb_bdqc.kactive_blk_num)
                prev = rb->prb_bdqc.kactive_blk_num-1;
        else
                prev = rb->prb_bdqc.knum_blocks-1;
        return prev;
}

/* Assumes caller has held the rx_queue.lock */
static void *__prb_previous_block(struct packet_sock *po,
                                         struct packet_ring_buffer *rb,
                                         int status)
{
        unsigned int previous = prb_previous_blk_num(rb);
        return prb_lookup_block(po, rb, previous, status);
}

static void *packet_previous_rx_frame(struct packet_sock *po,
                                             struct packet_ring_buffer *rb,
                                             int status)
{
        if (po->tp_version <= TPACKET_V2)
                return packet_previous_frame(po, rb, status);

        return __prb_previous_block(po, rb, status);
}

static void packet_increment_rx_head(struct packet_sock *po,
                                            struct packet_ring_buffer *rb)
{
        switch (po->tp_version) {
        case TPACKET_V1:
        case TPACKET_V2:
                return packet_increment_head(rb);
        case TPACKET_V3:
        default:
                WARN(1, "TPACKET version not supported.\n");
                BUG();
                return;
        }
}

static void *packet_previous_frame(struct packet_sock *po,
                struct packet_ring_buffer *rb,
                int status)
{
        unsigned int previous = rb->head ? rb->head - 1 : rb->frame_max;
        return packet_lookup_frame(po, rb, previous, status);
}

static void packet_increment_head(struct packet_ring_buffer *buff)
{
        buff->head = buff->head != buff->frame_max ? buff->head+1 : 0;
}

static void packet_inc_pending(struct packet_ring_buffer *rb)
{
        this_cpu_inc(*rb->pending_refcnt);
}

static void packet_dec_pending(struct packet_ring_buffer *rb)
{
        this_cpu_dec(*rb->pending_refcnt);
}

static unsigned int packet_read_pending(const struct packet_ring_buffer *rb)
{
        unsigned int refcnt = 0;
        int cpu;

        /* We don't use pending refcount in rx_ring. */
        if (rb->pending_refcnt == NULL)
                return 0;

        for_each_possible_cpu(cpu)
                refcnt += *per_cpu_ptr(rb->pending_refcnt, cpu);

        return refcnt;
}

static int packet_alloc_pending(struct packet_sock *po)
{
        po->rx_ring.pending_refcnt = NULL;

        po->tx_ring.pending_refcnt = alloc_percpu(unsigned int);
        if (unlikely(po->tx_ring.pending_refcnt == NULL))
                return -ENOBUFS;

        return 0;
}

static void packet_free_pending(struct packet_sock *po)
{
        free_percpu(po->tx_ring.pending_refcnt);
}

#define ROOM_POW_OFF    2
#define ROOM_NONE       0x0
#define ROOM_LOW        0x1
#define ROOM_NORMAL     0x2

static bool __tpacket_has_room(const struct packet_sock *po, int pow_off)
{
        int idx, len;

        len = READ_ONCE(po->rx_ring.frame_max) + 1;
        idx = READ_ONCE(po->rx_ring.head);
        if (pow_off)
                idx += len >> pow_off;
        if (idx >= len)
                idx -= len;
        return packet_lookup_frame(po, &po->rx_ring, idx, TP_STATUS_KERNEL);
}

static bool __tpacket_v3_has_room(const struct packet_sock *po, int pow_off)
{
        int idx, len;

        len = READ_ONCE(po->rx_ring.prb_bdqc.knum_blocks);
        idx = READ_ONCE(po->rx_ring.prb_bdqc.kactive_blk_num);
        if (pow_off)
                idx += len >> pow_off;
        if (idx >= len)
                idx -= len;
        return prb_lookup_block(po, &po->rx_ring, idx, TP_STATUS_KERNEL);
}

static int __packet_rcv_has_room(const struct packet_sock *po,
                                 const struct sk_buff *skb)
{
        const struct sock *sk = &po->sk;
        int ret = ROOM_NONE;

        if (po->prot_hook.func != tpacket_rcv) {
                int rcvbuf = READ_ONCE(sk->sk_rcvbuf);
                int avail = rcvbuf - atomic_read(&sk->sk_rmem_alloc)
                                   - (skb ? skb->truesize : 0);

                if (avail > (rcvbuf >> ROOM_POW_OFF))
                        return ROOM_NORMAL;
                else if (avail > 0)
                        return ROOM_LOW;
                else
                        return ROOM_NONE;
        }

        if (po->tp_version == TPACKET_V3) {
                if (__tpacket_v3_has_room(po, ROOM_POW_OFF))
                        ret = ROOM_NORMAL;
                else if (__tpacket_v3_has_room(po, 0))
                        ret = ROOM_LOW;
        } else {
                if (__tpacket_has_room(po, ROOM_POW_OFF))
                        ret = ROOM_NORMAL;
                else if (__tpacket_has_room(po, 0))
                        ret = ROOM_LOW;
        }

        return ret;
}

static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb)
{
        int pressure, ret;

        ret = __packet_rcv_has_room(po, skb);
        pressure = ret != ROOM_NORMAL;

        if (READ_ONCE(po->pressure) != pressure)
                WRITE_ONCE(po->pressure, pressure);

        return ret;
}

static void packet_rcv_try_clear_pressure(struct packet_sock *po)
{
        if (READ_ONCE(po->pressure) &&
            __packet_rcv_has_room(po, NULL) == ROOM_NORMAL)
                WRITE_ONCE(po->pressure,  0);
}

static void packet_sock_destruct(struct sock *sk)
{
        skb_queue_purge(&sk->sk_error_queue);

        WARN_ON(atomic_read(&sk->sk_rmem_alloc));
        WARN_ON(refcount_read(&sk->sk_wmem_alloc));

        if (!sock_flag(sk, SOCK_DEAD)) {
                pr_err("Attempt to release alive packet socket: %p\n", sk);
                return;
        }

        sk_refcnt_debug_dec(sk);
}

static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb)
{
        u32 *history = po->rollover->history;
        u32 victim, rxhash;
        int i, count = 0;

        rxhash = skb_get_hash(skb);
        for (i = 0; i < ROLLOVER_HLEN; i++)
                if (READ_ONCE(history[i]) == rxhash)
                        count++;

        victim = prandom_u32() % ROLLOVER_HLEN;

        /* Avoid dirtying the cache line if possible */
        if (READ_ONCE(history[victim]) != rxhash)
                WRITE_ONCE(history[victim], rxhash);

        return count > (ROLLOVER_HLEN >> 1);
}

static unsigned int fanout_demux_hash(struct packet_fanout *f,
                                      struct sk_buff *skb,
                                      unsigned int num)
{
        return reciprocal_scale(__skb_get_hash_symmetric(skb), num);
}

static unsigned int fanout_demux_lb(struct packet_fanout *f,
                                    struct sk_buff *skb,
                                    unsigned int num)
{
        unsigned int val = atomic_inc_return(&f->rr_cur);

        return val % num;
}

static unsigned int fanout_demux_cpu(struct packet_fanout *f,
                                     struct sk_buff *skb,
                                     unsigned int num)
{
        return smp_processor_id() % num;
}

static unsigned int fanout_demux_rnd(struct packet_fanout *f,
                                     struct sk_buff *skb,
                                     unsigned int num)
{
        return prandom_u32_max(num);
}

static unsigned int fanout_demux_rollover(struct packet_fanout *f,
                                          struct sk_buff *skb,
                                          unsigned int idx, bool try_self,
                                          unsigned int num)
{
        struct packet_sock *po, *po_next, *po_skip = NULL;
        unsigned int i, j, room = ROOM_NONE;

        po = pkt_sk(rcu_dereference(f->arr[idx]));

        if (try_self) {
                room = packet_rcv_has_room(po, skb);
                if (room == ROOM_NORMAL ||
                    (room == ROOM_LOW && !fanout_flow_is_huge(po, skb)))
                        return idx;
                po_skip = po;
        }

        i = j = min_t(int, po->rollover->sock, num - 1);
        do {
                po_next = pkt_sk(rcu_dereference(f->arr[i]));
                if (po_next != po_skip && !READ_ONCE(po_next->pressure) &&
                    packet_rcv_has_room(po_next, skb) == ROOM_NORMAL) {
                        if (i != j)
                                po->rollover->sock = i;
                        atomic_long_inc(&po->rollover->num);
                        if (room == ROOM_LOW)
                                atomic_long_inc(&po->rollover->num_huge);
                        return i;
                }

                if (++i == num)
                        i = 0;
        } while (i != j);

        atomic_long_inc(&po->rollover->num_failed);
        return idx;
}

static unsigned int fanout_demux_qm(struct packet_fanout *f,
                                    struct sk_buff *skb,
                                    unsigned int num)
{
        return skb_get_queue_mapping(skb) % num;
}

static unsigned int fanout_demux_bpf(struct packet_fanout *f,
                                     struct sk_buff *skb,
                                     unsigned int num)
{
        struct bpf_prog *prog;
        unsigned int ret = 0;

        rcu_read_lock();
        prog = rcu_dereference(f->bpf_prog);
        if (prog)
                ret = bpf_prog_run_clear_cb(prog, skb) % num;
        rcu_read_unlock();

        return ret;
}

static bool fanout_has_flag(struct packet_fanout *f, u16 flag)
{
        return f->flags & (flag >> 8);
}

static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
                             struct packet_type *pt, struct net_device *orig_dev)
{
        struct packet_fanout *f = pt->af_packet_priv;
        unsigned int num = READ_ONCE(f->num_members);
        struct net *net = read_pnet(&f->net);
        struct packet_sock *po;
        unsigned int idx;

        if (!net_eq(dev_net(dev), net) || !num) {
                kfree_skb(skb);
                return 0;
        }

        if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) {
                skb = ip_check_defrag(net, skb, IP_DEFRAG_AF_PACKET);
                if (!skb)
                        return 0;
        }
        switch (f->type) {
        case PACKET_FANOUT_HASH:
        default:
                idx = fanout_demux_hash(f, skb, num);
                break;
        case PACKET_FANOUT_LB:
                idx = fanout_demux_lb(f, skb, num);
                break;
        case PACKET_FANOUT_CPU:
                idx = fanout_demux_cpu(f, skb, num);
                break;
        case PACKET_FANOUT_RND:
                idx = fanout_demux_rnd(f, skb, num);
                break;
        case PACKET_FANOUT_QM:
                idx = fanout_demux_qm(f, skb, num);
                break;
        case PACKET_FANOUT_ROLLOVER:
                idx = fanout_demux_rollover(f, skb, 0, false, num);
                break;
        case PACKET_FANOUT_CBPF:
        case PACKET_FANOUT_EBPF:
                idx = fanout_demux_bpf(f, skb, num);
                break;
        }

        if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER))
                idx = fanout_demux_rollover(f, skb, idx, true, num);

        po = pkt_sk(rcu_dereference(f->arr[idx]));
        return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev);
}

DEFINE_MUTEX(fanout_mutex);
EXPORT_SYMBOL_GPL(fanout_mutex);
static LIST_HEAD(fanout_list);
static u16 fanout_next_id;

static void __fanout_link(struct sock *sk, struct packet_sock *po)
{
        struct packet_fanout *f = po->fanout;

        spin_lock(&f->lock);
        rcu_assign_pointer(f->arr[f->num_members], sk);
        smp_wmb();
        f->num_members++;
        if (f->num_members == 1)
                dev_add_pack(&f->prot_hook);
        spin_unlock(&f->lock);
}

static void __fanout_unlink(struct sock *sk, struct packet_sock *po)
{
        struct packet_fanout *f = po->fanout;
        int i;

        spin_lock(&f->lock);
        for (i = 0; i < f->num_members; i++) {
                if (rcu_dereference_protected(f->arr[i],
                                              lockdep_is_held(&f->lock)) == sk)
                        break;
        }
        BUG_ON(i >= f->num_members);
        rcu_assign_pointer(f->arr[i],
                           rcu_dereference_protected(f->arr[f->num_members - 1],
                                                     lockdep_is_held(&f->lock)));
        f->num_members--;
        if (f->num_members == 0)
                __dev_remove_pack(&f->prot_hook);
        spin_unlock(&f->lock);
}

static bool match_fanout_group(struct packet_type *ptype, struct sock *sk)
{
        if (sk->sk_family != PF_PACKET)
                return false;

        return ptype->af_packet_priv == pkt_sk(sk)->fanout;
}

static void fanout_init_data(struct packet_fanout *f)
{
        switch (f->type) {
        case PACKET_FANOUT_LB:
                atomic_set(&f->rr_cur, 0);
                break;
        case PACKET_FANOUT_CBPF:
        case PACKET_FANOUT_EBPF:
                RCU_INIT_POINTER(f->bpf_prog, NULL);
                break;
        }
}

static void __fanout_set_data_bpf(struct packet_fanout *f, struct bpf_prog *new)
{
        struct bpf_prog *old;

        spin_lock(&f->lock);
        old = rcu_dereference_protected(f->bpf_prog, lockdep_is_held(&f->lock));
        rcu_assign_pointer(f->bpf_prog, new);
        spin_unlock(&f->lock);

        if (old) {
                synchronize_net();
                bpf_prog_destroy(old);
        }
}

static int fanout_set_data_cbpf(struct packet_sock *po, sockptr_t data,
                                unsigned int len)
{
        struct bpf_prog *new;
        struct sock_fprog fprog;
        int ret;

        if (sock_flag(&po->sk, SOCK_FILTER_LOCKED))
                return -EPERM;

        ret = copy_bpf_fprog_from_user(&fprog, data, len);
        if (ret)
                return ret;

        ret = bpf_prog_create_from_user(&new, &fprog, NULL, false);
        if (ret)
                return ret;

        __fanout_set_data_bpf(po->fanout, new);
        return 0;
}

static int fanout_set_data_ebpf(struct packet_sock *po, sockptr_t data,
                                unsigned int len)
{
        struct bpf_prog *new;
        u32 fd;

        if (sock_flag(&po->sk, SOCK_FILTER_LOCKED))
                return -EPERM;
        if (len != sizeof(fd))
                return -EINVAL;
        if (copy_from_sockptr(&fd, data, len))
                return -EFAULT;

        new = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER);
        if (IS_ERR(new))
                return PTR_ERR(new);

        __fanout_set_data_bpf(po->fanout, new);
        return 0;
}

static int fanout_set_data(struct packet_sock *po, sockptr_t data,
                           unsigned int len)
{
        switch (po->fanout->type) {
        case PACKET_FANOUT_CBPF:
                return fanout_set_data_cbpf(po, data, len);
        case PACKET_FANOUT_EBPF:
                return fanout_set_data_ebpf(po, data, len);
        default:
                return -EINVAL;
        }
}

static void fanout_release_data(struct packet_fanout *f)
{
        switch (f->type) {
        case PACKET_FANOUT_CBPF:
        case PACKET_FANOUT_EBPF:
                __fanout_set_data_bpf(f, NULL);
        }
}

static bool __fanout_id_is_free(struct sock *sk, u16 candidate_id)
{
        struct packet_fanout *f;

        list_for_each_entry(f, &fanout_list, list) {
                if (f->id == candidate_id &&
                    read_pnet(&f->net) == sock_net(sk)) {
                        return false;
                }
        }
        return true;
}

static bool fanout_find_new_id(struct sock *sk, u16 *new_id)
{
        u16 id = fanout_next_id;

        do {
                if (__fanout_id_is_free(sk, id)) {
                        *new_id = id;
                        fanout_next_id = id + 1;
                        return true;
                }

                id++;
        } while (id != fanout_next_id);

        return false;
}

static int fanout_add(struct sock *sk, struct fanout_args *args)
{
        struct packet_rollover *rollover = NULL;
        struct packet_sock *po = pkt_sk(sk);
        u16 type_flags = args->type_flags;
        struct packet_fanout *f, *match;
        u8 type = type_flags & 0xff;
        u8 flags = type_flags >> 8;
        u16 id = args->id;
        int err;

        switch (type) {
        case PACKET_FANOUT_ROLLOVER:
                if (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)
                        return -EINVAL;
                break;
        case PACKET_FANOUT_HASH:
        case PACKET_FANOUT_LB:
        case PACKET_FANOUT_CPU:
        case PACKET_FANOUT_RND:
        case PACKET_FANOUT_QM:
        case PACKET_FANOUT_CBPF:
        case PACKET_FANOUT_EBPF:
                break;
        default:
                return -EINVAL;
        }

        mutex_lock(&fanout_mutex);

        err = -EALREADY;
        if (po->fanout)
                goto out;

        if (type == PACKET_FANOUT_ROLLOVER ||
            (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) {
                err = -ENOMEM;
                rollover = kzalloc(sizeof(*rollover), GFP_KERNEL);
                if (!rollover)
                        goto out;
                atomic_long_set(&rollover->num, 0);
                atomic_long_set(&rollover->num_huge, 0);
                atomic_long_set(&rollover->num_failed, 0);
        }

        if (type_flags & PACKET_FANOUT_FLAG_UNIQUEID) {
                if (id != 0) {
                        err = -EINVAL;
                        goto out;
                }
                if (!fanout_find_new_id(sk, &id)) {
                        err = -ENOMEM;
                        goto out;
                }
                /* ephemeral flag for the first socket in the group: drop it */
                flags &= ~(PACKET_FANOUT_FLAG_UNIQUEID >> 8);
        }

        match = NULL;
        list_for_each_entry(f, &fanout_list, list) {
                if (f->id == id &&
                    read_pnet(&f->net) == sock_net(sk)) {
                        match = f;
                        break;
                }
        }
        err = -EINVAL;
        if (match) {
                if (match->flags != flags)
                        goto out;
                if (args->max_num_members &&
                    args->max_num_members != match->max_num_members)
                        goto out;
        } else {
                if (args->max_num_members > PACKET_FANOUT_MAX)
                        goto out;
                if (!args->max_num_members)
                        /* legacy PACKET_FANOUT_MAX */
                        args->max_num_members = 256;
                err = -ENOMEM;
                match = kvzalloc(struct_size(match, arr, args->max_num_members),
                                 GFP_KERNEL);
                if (!match)
                        goto out;
                write_pnet(&match->net, sock_net(sk));
                match->id = id;
                match->type = type;
                match->flags = flags;
                INIT_LIST_HEAD(&match->list);
                spin_lock_init(&match->lock);
                refcount_set(&match->sk_ref, 0);
                fanout_init_data(match);
                match->prot_hook.type = po->prot_hook.type;
                match->prot_hook.dev = po->prot_hook.dev;
                match->prot_hook.func = packet_rcv_fanout;
                match->prot_hook.af_packet_priv = match;
                match->prot_hook.id_match = match_fanout_group;
                match->max_num_members = args->max_num_members;
                list_add(&match->list, &fanout_list);
        }
        err = -EINVAL;

        spin_lock(&po->bind_lock);
        if (po->running &&
            match->type == type &&
            match->prot_hook.type == po->prot_hook.type &&
            match->prot_hook.dev == po->prot_hook.dev) {
                err = -ENOSPC;
                if (refcount_read(&match->sk_ref) < match->max_num_members) {
                        __dev_remove_pack(&po->prot_hook);
                        po->fanout = match;
                        po->rollover = rollover;
                        rollover = NULL;
                        refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1);
                        __fanout_link(sk, po);
                        err = 0;
                }
        }
        spin_unlock(&po->bind_lock);

        if (err && !refcount_read(&match->sk_ref)) {
                list_del(&match->list);
                kvfree(match);
        }

out:
        kfree(rollover);
        mutex_unlock(&fanout_mutex);
        return err;
}

/* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes
 * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout.
 * It is the responsibility of the caller to call fanout_release_data() and
 * free the returned packet_fanout (after synchronize_net())
 */
static struct packet_fanout *fanout_release(struct sock *sk)
{
        struct packet_sock *po = pkt_sk(sk);
        struct packet_fanout *f;

        mutex_lock(&fanout_mutex);
        f = po->fanout;
        if (f) {
                po->fanout = NULL;

                if (refcount_dec_and_test(&f->sk_ref))
                        list_del(&f->list);
                else
                        f = NULL;
        }
        mutex_unlock(&fanout_mutex);

        return f;
}

static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
                                          struct sk_buff *skb)
{
        /* Earlier code assumed this would be a VLAN pkt, double-check
         * this now that we have the actual packet in hand. We can only
         * do this check on Ethernet devices.
         */
        if (unlikely(dev->type != ARPHRD_ETHER))
                return false;

        skb_reset_mac_header(skb);
        return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q));
}

static const struct proto_ops packet_ops;

static const struct proto_ops packet_ops_spkt;

static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev,
                           struct packet_type *pt, struct net_device *orig_dev)
{
        struct sock *sk;
        struct sockaddr_pkt *spkt;

        /*
         *      When we registered the protocol we saved the socket in the data
         *      field for just this event.
         */

        sk = pt->af_packet_priv;

        /*
         *      Yank back the headers [hope the device set this
         *      right or kerboom...]
         *
         *      Incoming packets have ll header pulled,
         *      push it back.
         *
         *      For outgoing ones skb->data == skb_mac_header(skb)
         *      so that this procedure is noop.
         */

        if (skb->pkt_type == PACKET_LOOPBACK)
                goto out;

        if (!net_eq(dev_net(dev), sock_net(sk)))
                goto out;

        skb = skb_share_check(skb, GFP_ATOMIC);
        if (skb == NULL)
                goto oom;

        /* drop any routing info */
        skb_dst_drop(skb);

        /* drop conntrack reference */
        nf_reset_ct(skb);

        spkt = &PACKET_SKB_CB(skb)->sa.pkt;

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

        /*
         *      The SOCK_PACKET socket receives _all_ frames.
         */

        spkt->spkt_family = dev->type;
        strlcpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device));
        spkt->spkt_protocol = skb->protocol;

        /*
         *      Charge the memory to the socket. This is done specifically
         *      to prevent sockets using all the memory up.
         */

        if (sock_queue_rcv_skb(sk, skb) == 0)
                return 0;

out:
        kfree_skb(skb);
oom:
        return 0;
}

static void packet_parse_headers(struct sk_buff *skb, struct socket *sock)
{
        if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) &&
            sock->type == SOCK_RAW) {
                skb_reset_mac_header(skb);
                skb->protocol = dev_parse_header_protocol(skb);
        }

        skb_probe_transport_header(skb);
}

/*
 *      Output a raw packet to a device layer. This bypasses all the other
 *      protocol layers and you must therefore supply it with a complete frame
 */

static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg,
                               size_t len)
{
        struct sock *sk = sock->sk;
        DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name);
        struct sk_buff *skb = NULL;
        struct net_device *dev;
        struct sockcm_cookie sockc;
        __be16 proto = 0;
        int err;
        int extra_len = 0;

        /*
         *      Get and verify the address.
         */

        if (saddr) {
                if (msg->msg_namelen < sizeof(struct sockaddr))
                        return -EINVAL;
                if (msg->msg_namelen == sizeof(struct sockaddr_pkt))
                        proto = saddr->spkt_protocol;
        } else
                return -ENOTCONN;       /* SOCK_PACKET must be sent giving an address */

        /*
         *      Find the device first to size check it
         */

        saddr->spkt_device[sizeof(saddr->spkt_device) - 1] = 0;
retry:
        rcu_read_lock();
        dev = dev_get_by_name_rcu(sock_net(sk), saddr->spkt_device);
        err = -ENODEV;
        if (dev == NULL)
                goto out_unlock;

        err = -ENETDOWN;
        if (!(dev->flags & IFF_UP))
                goto out_unlock;

        /*
         * You may not queue a frame bigger than the mtu. This is the lowest level
         * raw protocol and you must do your own fragmentation at this level.
         */

        if (unlikely(sock_flag(sk, SOCK_NOFCS))) {
                if (!netif_supports_nofcs(dev)) {
                        err = -EPROTONOSUPPORT;
                        goto out_unlock;
                }
                extra_len = 4; /* We're doing our own CRC */
        }

        err = -EMSGSIZE;
        if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN + extra_len)
                goto out_unlock;

        if (!skb) {
                size_t reserved = LL_RESERVED_SPACE(dev);
                int tlen = dev->needed_tailroom;
                unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0;

                rcu_read_unlock();
                skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL);
                if (skb == NULL)
                        return -ENOBUFS;
                /* FIXME: Save some space for broken drivers that write a hard
                 * header at transmission time by themselves. PPP is the notable
                 * one here. This should really be fixed at the driver level.
                 */
                skb_reserve(skb, reserved);
                skb_reset_network_header(skb);

                /* Try to align data part correctly */
                if (hhlen) {
                        skb->data -= hhlen;
                        skb->tail -= hhlen;
                        if (len < hhlen)
                                skb_reset_network_header(skb);
                }
                err = memcpy_from_msg(skb_put(skb, len), msg, len);
                if (err)
                        goto out_free;
                goto retry;
        }

        if (!dev_validate_header(dev, skb->data, len)) {
                err = -EINVAL;
                goto out_unlock;
        }
        if (len > (dev->mtu + dev->hard_header_len + extra_len) &&
            !packet_extra_vlan_len_allowed(dev, skb)) {
                err = -EMSGSIZE;
                goto out_unlock;
        }

        sockcm_init(&sockc, sk);
        if (msg->msg_controllen) {
                err = sock_cmsg_send(sk, msg, &sockc);
                if (unlikely(err))
                        goto out_unlock;