// 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.
 *
 *              Generic socket support routines. Memory allocators, socket lock/release
 *              handler for protocols to use and generic option handler.
 *
 * Authors:     Ross Biro
 *              Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *              Florian La Roche, <flla@stud.uni-sb.de>
 *              Alan Cox, <A.Cox@swansea.ac.uk>
 *
 * Fixes:
 *              Alan Cox        :       Numerous verify_area() problems
 *              Alan Cox        :       Connecting on a connecting socket
 *                                      now returns an error for tcp.
 *              Alan Cox        :       sock->protocol is set correctly.
 *                                      and is not sometimes left as 0.
 *              Alan Cox        :       connect handles icmp errors on a
 *                                      connect properly. Unfortunately there
 *                                      is a restart syscall nasty there. I
 *                                      can't match BSD without hacking the C
 *                                      library. Ideas urgently sought!
 *              Alan Cox        :       Disallow bind() to addresses that are
 *                                      not ours - especially broadcast ones!!
 *              Alan Cox        :       Socket 1024 _IS_ ok for users. (fencepost)
 *              Alan Cox        :       sock_wfree/sock_rfree don't destroy sockets,
 *                                      instead they leave that for the DESTROY timer.
 *              Alan Cox        :       Clean up error flag in accept
 *              Alan Cox        :       TCP ack handling is buggy, the DESTROY timer
 *                                      was buggy. Put a remove_sock() in the handler
 *                                      for memory when we hit 0. Also altered the timer
 *                                      code. The ACK stuff can wait and needs major
 *                                      TCP layer surgery.
 *              Alan Cox        :       Fixed TCP ack bug, removed remove sock
 *                                      and fixed timer/inet_bh race.
 *              Alan Cox        :       Added zapped flag for TCP
 *              Alan Cox        :       Move kfree_skb into skbuff.c and tidied up surplus code
 *              Alan Cox        :       for new sk_buff allocations wmalloc/rmalloc now call alloc_skb
 *              Alan Cox        :       kfree_s calls now are kfree_skbmem so we can track skb resources
 *              Alan Cox        :       Supports socket option broadcast now as does udp. Packet and raw need fixing.
 *              Alan Cox        :       Added RCVBUF,SNDBUF size setting. It suddenly occurred to me how easy it was so...
 *              Rick Sladkey    :       Relaxed UDP rules for matching packets.
 *              C.E.Hawkins     :       IFF_PROMISC/SIOCGHWADDR support
 *      Pauline Middelink       :       identd support
 *              Alan Cox        :       Fixed connect() taking signals I think.
 *              Alan Cox        :       SO_LINGER supported
 *              Alan Cox        :       Error reporting fixes
 *              Anonymous       :       inet_create tidied up (sk->reuse setting)
 *              Alan Cox        :       inet sockets don't set sk->type!
 *              Alan Cox        :       Split socket option code
 *              Alan Cox        :       Callbacks
 *              Alan Cox        :       Nagle flag for Charles & Johannes stuff
 *              Alex            :       Removed restriction on inet fioctl
 *              Alan Cox        :       Splitting INET from NET core
 *              Alan Cox        :       Fixed bogus SO_TYPE handling in getsockopt()
 *              Adam Caldwell   :       Missing return in SO_DONTROUTE/SO_DEBUG code
 *              Alan Cox        :       Split IP from generic code
 *              Alan Cox        :       New kfree_skbmem()
 *              Alan Cox        :       Make SO_DEBUG superuser only.
 *              Alan Cox        :       Allow anyone to clear SO_DEBUG
 *                                      (compatibility fix)
 *              Alan Cox        :       Added optimistic memory grabbing for AF_UNIX throughput.
 *              Alan Cox        :       Allocator for a socket is settable.
 *              Alan Cox        :       SO_ERROR includes soft errors.
 *              Alan Cox        :       Allow NULL arguments on some SO_ opts
 *              Alan Cox        :       Generic socket allocation to make hooks
 *                                      easier (suggested by Craig Metz).
 *              Michael Pall    :       SO_ERROR returns positive errno again
 *              Steve Whitehouse:       Added default destructor to free
 *                                      protocol private data.
 *              Steve Whitehouse:       Added various other default routines
 *                                      common to several socket families.
 *              Chris Evans     :       Call suser() check last on F_SETOWN
 *              Jay Schulist    :       Added SO_ATTACH_FILTER and SO_DETACH_FILTER.
 *              Andi Kleen      :       Add sock_kmalloc()/sock_kfree_s()
 *              Andi Kleen      :       Fix write_space callback
 *              Chris Evans     :       Security fixes - signedness again
 *              Arnaldo C. Melo :       cleanups, use skb_queue_purge
 *
 * To Fix:
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <asm/unaligned.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/errqueue.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/poll.h>
#include <linux/tcp.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/user_namespace.h>
#include <linux/static_key.h>
#include <linux/memcontrol.h>
#include <linux/prefetch.h>
#include <linux/compat.h>

#include <linux/uaccess.h>

#include <linux/netdevice.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/net_namespace.h>
#include <net/request_sock.h>
#include <net/sock.h>
#include <linux/net_tstamp.h>
#include <net/xfrm.h>
#include <linux/ipsec.h>
#include <net/cls_cgroup.h>
#include <net/netprio_cgroup.h>
#include <linux/sock_diag.h>

#include <linux/filter.h>
#include <net/sock_reuseport.h>
#include <net/bpf_sk_storage.h>

#include <trace/events/sock.h>

#include <net/tcp.h>
#include <net/busy_poll.h>

#include <linux/ethtool.h>

#include "dev.h"

static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);

static void sock_def_write_space_wfree(struct sock *sk);
static void sock_def_write_space(struct sock *sk);

/**
 * sk_ns_capable - General socket capability test
 * @sk: Socket to use a capability on or through
 * @user_ns: The user namespace of the capability to use
 * @cap: The capability to use
 *
 * Test to see if the opener of the socket had when the socket was
 * created and the current process has the capability @cap in the user
 * namespace @user_ns.
 */
bool sk_ns_capable(const struct sock *sk,
                   struct user_namespace *user_ns, int cap)
{
        return file_ns_capable(sk->sk_socket->file, user_ns, cap) &&
                ns_capable(user_ns, cap);
}
EXPORT_SYMBOL(sk_ns_capable);

/**
 * sk_capable - Socket global capability test
 * @sk: Socket to use a capability on or through
 * @cap: The global capability to use
 *
 * Test to see if the opener of the socket had when the socket was
 * created and the current process has the capability @cap in all user
 * namespaces.
 */
bool sk_capable(const struct sock *sk, int cap)
{
        return sk_ns_capable(sk, &init_user_ns, cap);
}
EXPORT_SYMBOL(sk_capable);

/**
 * sk_net_capable - Network namespace socket capability test
 * @sk: Socket to use a capability on or through
 * @cap: The capability to use
 *
 * Test to see if the opener of the socket had when the socket was created
 * and the current process has the capability @cap over the network namespace
 * the socket is a member of.
 */
bool sk_net_capable(const struct sock *sk, int cap)
{
        return sk_ns_capable(sk, sock_net(sk)->user_ns, cap);
}
EXPORT_SYMBOL(sk_net_capable);

/*
 * Each address family might have different locking rules, so we have
 * one slock key per address family and separate keys for internal and
 * userspace sockets.
 */
static struct lock_class_key af_family_keys[AF_MAX];
static struct lock_class_key af_family_kern_keys[AF_MAX];
static struct lock_class_key af_family_slock_keys[AF_MAX];
static struct lock_class_key af_family_kern_slock_keys[AF_MAX];

/*
 * Make lock validator output more readable. (we pre-construct these
 * strings build-time, so that runtime initialization of socket
 * locks is fast):
 */

#define _sock_locks(x)                                            \
  x "AF_UNSPEC",        x "AF_UNIX"     ,       x "AF_INET"     , \
  x "AF_AX25"  ,        x "AF_IPX"      ,       x "AF_APPLETALK", \
  x "AF_NETROM",        x "AF_BRIDGE"   ,       x "AF_ATMPVC"   , \
  x "AF_X25"   ,        x "AF_INET6"    ,       x "AF_ROSE"     , \
  x "AF_DECnet",        x "AF_NETBEUI"  ,       x "AF_SECURITY" , \
  x "AF_KEY"   ,        x "AF_NETLINK"  ,       x "AF_PACKET"   , \
  x "AF_ASH"   ,        x "AF_ECONET"   ,       x "AF_ATMSVC"   , \
  x "AF_RDS"   ,        x "AF_SNA"      ,       x "AF_IRDA"     , \
  x "AF_PPPOX" ,        x "AF_WANPIPE"  ,       x "AF_LLC"      , \
  x "27"       ,        x "28"          ,       x "AF_CAN"      , \
  x "AF_TIPC"  ,        x "AF_BLUETOOTH",       x "IUCV"        , \
  x "AF_RXRPC" ,        x "AF_ISDN"     ,       x "AF_PHONET"   , \
  x "AF_IEEE802154",    x "AF_CAIF"     ,       x "AF_ALG"      , \
  x "AF_NFC"   ,        x "AF_VSOCK"    ,       x "AF_KCM"      , \
  x "AF_QIPCRTR",       x "AF_SMC"      ,       x "AF_XDP"      , \
  x "AF_MCTP"  , \
  x "AF_MAX"

static const char *const af_family_key_strings[AF_MAX+1] = {
        _sock_locks("sk_lock-")
};
static const char *const af_family_slock_key_strings[AF_MAX+1] = {
        _sock_locks("slock-")
};
static const char *const af_family_clock_key_strings[AF_MAX+1] = {
        _sock_locks("clock-")
};

static const char *const af_family_kern_key_strings[AF_MAX+1] = {
        _sock_locks("k-sk_lock-")
};
static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = {
        _sock_locks("k-slock-")
};
static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = {
        _sock_locks("k-clock-")
};
static const char *const af_family_rlock_key_strings[AF_MAX+1] = {
        _sock_locks("rlock-")
};
static const char *const af_family_wlock_key_strings[AF_MAX+1] = {
        _sock_locks("wlock-")
};
static const char *const af_family_elock_key_strings[AF_MAX+1] = {
        _sock_locks("elock-")
};

/*
 * sk_callback_lock and sk queues locking rules are per-address-family,
 * so split the lock classes by using a per-AF key:
 */
static struct lock_class_key af_callback_keys[AF_MAX];
static struct lock_class_key af_rlock_keys[AF_MAX];
static struct lock_class_key af_wlock_keys[AF_MAX];
static struct lock_class_key af_elock_keys[AF_MAX];
static struct lock_class_key af_kern_callback_keys[AF_MAX];

/* Run time adjustable parameters. */
__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX;
EXPORT_SYMBOL(sysctl_wmem_max);
__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;
EXPORT_SYMBOL(sysctl_rmem_max);
__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;

/* Maximal space eaten by iovec or ancillary data plus some space */
int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
EXPORT_SYMBOL(sysctl_optmem_max);

int sysctl_tstamp_allow_data __read_mostly = 1;

DEFINE_STATIC_KEY_FALSE(memalloc_socks_key);
EXPORT_SYMBOL_GPL(memalloc_socks_key);

/**
 * sk_set_memalloc - sets %SOCK_MEMALLOC
 * @sk: socket to set it on
 *
 * Set %SOCK_MEMALLOC on a socket for access to emergency reserves.
 * It's the responsibility of the admin to adjust min_free_kbytes
 * to meet the requirements
 */
void sk_set_memalloc(struct sock *sk)
{
        sock_set_flag(sk, SOCK_MEMALLOC);
        sk->sk_allocation |= __GFP_MEMALLOC;
        static_branch_inc(&memalloc_socks_key);
}
EXPORT_SYMBOL_GPL(sk_set_memalloc);

void sk_clear_memalloc(struct sock *sk)
{
        sock_reset_flag(sk, SOCK_MEMALLOC);
        sk->sk_allocation &= ~__GFP_MEMALLOC;
        static_branch_dec(&memalloc_socks_key);

        /*
         * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward
         * progress of swapping. SOCK_MEMALLOC may be cleared while
         * it has rmem allocations due to the last swapfile being deactivated
         * but there is a risk that the socket is unusable due to exceeding
         * the rmem limits. Reclaim the reserves and obey rmem limits again.
         */
        sk_mem_reclaim(sk);
}
EXPORT_SYMBOL_GPL(sk_clear_memalloc);

int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
        int ret;
        unsigned int noreclaim_flag;

        /* these should have been dropped before queueing */
        BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));

        noreclaim_flag = memalloc_noreclaim_save();
        ret = INDIRECT_CALL_INET(sk->sk_backlog_rcv,
                                 tcp_v6_do_rcv,
                                 tcp_v4_do_rcv,
                                 sk, skb);
        memalloc_noreclaim_restore(noreclaim_flag);

        return ret;
}
EXPORT_SYMBOL(__sk_backlog_rcv);

void sk_error_report(struct sock *sk)
{
        sk->sk_error_report(sk);

        switch (sk->sk_family) {
        case AF_INET:
                fallthrough;
        case AF_INET6:
                trace_inet_sk_error_report(sk);
                break;
        default:
                break;
        }
}
EXPORT_SYMBOL(sk_error_report);

int sock_get_timeout(long timeo, void *optval, bool old_timeval)
{
        struct __kernel_sock_timeval tv;

        if (timeo == MAX_SCHEDULE_TIMEOUT) {
                tv.tv_sec = 0;
                tv.tv_usec = 0;
        } else {
                tv.tv_sec = timeo / HZ;
                tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ;
        }

        if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
                struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec };
                *(struct old_timeval32 *)optval = tv32;
                return sizeof(tv32);
        }

        if (old_timeval) {
                struct __kernel_old_timeval old_tv;
                old_tv.tv_sec = tv.tv_sec;
                old_tv.tv_usec = tv.tv_usec;
                *(struct __kernel_old_timeval *)optval = old_tv;
                return sizeof(old_tv);
        }

        *(struct __kernel_sock_timeval *)optval = tv;
        return sizeof(tv);
}
EXPORT_SYMBOL(sock_get_timeout);

int sock_copy_user_timeval(struct __kernel_sock_timeval *tv,
                           sockptr_t optval, int optlen, bool old_timeval)
{
        if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
                struct old_timeval32 tv32;

                if (optlen < sizeof(tv32))
                        return -EINVAL;

                if (copy_from_sockptr(&tv32, optval, sizeof(tv32)))
                        return -EFAULT;
                tv->tv_sec = tv32.tv_sec;
                tv->tv_usec = tv32.tv_usec;
        } else if (old_timeval) {
                struct __kernel_old_timeval old_tv;

                if (optlen < sizeof(old_tv))
                        return -EINVAL;
                if (copy_from_sockptr(&old_tv, optval, sizeof(old_tv)))
                        return -EFAULT;
                tv->tv_sec = old_tv.tv_sec;
                tv->tv_usec = old_tv.tv_usec;
        } else {
                if (optlen < sizeof(*tv))
                        return -EINVAL;
                if (copy_from_sockptr(tv, optval, sizeof(*tv)))
                        return -EFAULT;
        }

        return 0;
}
EXPORT_SYMBOL(sock_copy_user_timeval);

static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
                            bool old_timeval)
{
        struct __kernel_sock_timeval tv;
        int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval);

        if (err)
                return err;

        if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC)
                return -EDOM;

        if (tv.tv_sec < 0) {
                static int warned __read_mostly;

                *timeo_p = 0;
                if (warned < 10 && net_ratelimit()) {
                        warned++;
                        pr_info("%s: `%s' (pid %d) tries to set negative timeout\n",
                                __func__, current->comm, task_pid_nr(current));
                }
                return 0;
        }
        *timeo_p = MAX_SCHEDULE_TIMEOUT;
        if (tv.tv_sec == 0 && tv.tv_usec == 0)
                return 0;
        if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1))
                *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ);
        return 0;
}

static bool sock_needs_netstamp(const struct sock *sk)
{
        switch (sk->sk_family) {
        case AF_UNSPEC:
        case AF_UNIX:
                return false;
        default:
                return true;
        }
}

static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
{
        if (sk->sk_flags & flags) {
                sk->sk_flags &= ~flags;
                if (sock_needs_netstamp(sk) &&
                    !(sk->sk_flags & SK_FLAGS_TIMESTAMP))
                        net_disable_timestamp();
        }
}


int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
        unsigned long flags;
        struct sk_buff_head *list = &sk->sk_receive_queue;

        if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) {
                atomic_inc(&sk->sk_drops);
                trace_sock_rcvqueue_full(sk, skb);
                return -ENOMEM;
        }

        if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
                atomic_inc(&sk->sk_drops);
                return -ENOBUFS;
        }

        skb->dev = NULL;
        skb_set_owner_r(skb, sk);

        /* we escape from rcu protected region, make sure we dont leak
         * a norefcounted dst
         */
        skb_dst_force(skb);

        spin_lock_irqsave(&list->lock, flags);
        sock_skb_set_dropcount(sk, skb);
        __skb_queue_tail(list, skb);
        spin_unlock_irqrestore(&list->lock, flags);

        if (!sock_flag(sk, SOCK_DEAD))
                sk->sk_data_ready(sk);
        return 0;
}
EXPORT_SYMBOL(__sock_queue_rcv_skb);

int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb,
                              enum skb_drop_reason *reason)
{
        enum skb_drop_reason drop_reason;
        int err;

        err = sk_filter(sk, skb);
        if (err) {
                drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
                goto out;
        }
        err = __sock_queue_rcv_skb(sk, skb);
        switch (err) {
        case -ENOMEM:
                drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF;
                break;
        case -ENOBUFS:
                drop_reason = SKB_DROP_REASON_PROTO_MEM;
                break;
        default:
                drop_reason = SKB_NOT_DROPPED_YET;
                break;
        }
out:
        if (reason)
                *reason = drop_reason;
        return err;
}
EXPORT_SYMBOL(sock_queue_rcv_skb_reason);

int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
                     const int nested, unsigned int trim_cap, bool refcounted)
{
        int rc = NET_RX_SUCCESS;

        if (sk_filter_trim_cap(sk, skb, trim_cap))
                goto discard_and_relse;

        skb->dev = NULL;

        if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
                atomic_inc(&sk->sk_drops);
                goto discard_and_relse;
        }
        if (nested)
                bh_lock_sock_nested(sk);
        else
                bh_lock_sock(sk);
        if (!sock_owned_by_user(sk)) {
                /*
                 * trylock + unlock semantics:
                 */
                mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_);

                rc = sk_backlog_rcv(sk, skb);

                mutex_release(&sk->sk_lock.dep_map, _RET_IP_);
        } else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) {
                bh_unlock_sock(sk);
                atomic_inc(&sk->sk_drops);
                goto discard_and_relse;
        }

        bh_unlock_sock(sk);
out:
        if (refcounted)
                sock_put(sk);
        return rc;
discard_and_relse:
        kfree_skb(skb);
        goto out;
}
EXPORT_SYMBOL(__sk_receive_skb);

INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *,
                                                          u32));
INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *,
                                                           u32));
struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
{
        struct dst_entry *dst = __sk_dst_get(sk);

        if (dst && dst->obsolete &&
            INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check,
                               dst, cookie) == NULL) {
                sk_tx_queue_clear(sk);
                sk->sk_dst_pending_confirm = 0;
                RCU_INIT_POINTER(sk->sk_dst_cache, NULL);
                dst_release(dst);
                return NULL;
        }

        return dst;
}
EXPORT_SYMBOL(__sk_dst_check);

struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie)
{
        struct dst_entry *dst = sk_dst_get(sk);

        if (dst && dst->obsolete &&
            INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check,
                               dst, cookie) == NULL) {
                sk_dst_reset(sk);
                dst_release(dst);
                return NULL;
        }

        return dst;
}
EXPORT_SYMBOL(sk_dst_check);

static int sock_bindtoindex_locked(struct sock *sk, int ifindex)
{
        int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
        struct net *net = sock_net(sk);

        /* Sorry... */
        ret = -EPERM;
        if (sk->sk_bound_dev_if && !ns_capable(net->user_ns, CAP_NET_RAW))
                goto out;

        ret = -EINVAL;
        if (ifindex < 0)
                goto out;

        /* Paired with all READ_ONCE() done locklessly. */
        WRITE_ONCE(sk->sk_bound_dev_if, ifindex);

        if (sk->sk_prot->rehash)
                sk->sk_prot->rehash(sk);
        sk_dst_reset(sk);

        ret = 0;

out:
#endif

        return ret;
}

int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk)
{
        int ret;

        if (lock_sk)
                lock_sock(sk);
        ret = sock_bindtoindex_locked(sk, ifindex);
        if (lock_sk)
                release_sock(sk);

        return ret;
}
EXPORT_SYMBOL(sock_bindtoindex);

static int sock_setbindtodevice(struct sock *sk, sockptr_t optval, int optlen)
{
        int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
        struct net *net = sock_net(sk);
        char devname[IFNAMSIZ];
        int index;

        ret = -EINVAL;
        if (optlen < 0)
                goto out;

        /* Bind this socket to a particular device like "eth0",
         * as specified in the passed interface name. If the
         * name is "" or the option length is zero the socket
         * is not bound.
         */
        if (optlen > IFNAMSIZ - 1)
                optlen = IFNAMSIZ - 1;
        memset(devname, 0, sizeof(devname));

        ret = -EFAULT;
        if (copy_from_sockptr(devname, optval, optlen))
                goto out;

        index = 0;
        if (devname[0] != '\0') {
                struct net_device *dev;

                rcu_read_lock();
                dev = dev_get_by_name_rcu(net, devname);
                if (dev)
                        index = dev->ifindex;
                rcu_read_unlock();
                ret = -ENODEV;
                if (!dev)
                        goto out;
        }

        return sock_bindtoindex(sk, index, true);
out:
#endif

        return ret;
}

static int sock_getbindtodevice(struct sock *sk, char __user *optval,
                                int __user *optlen, int len)
{
        int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
        int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
        struct net *net = sock_net(sk);
        char devname[IFNAMSIZ];

        if (bound_dev_if == 0) {
                len = 0;
                goto zero;
        }

        ret = -EINVAL;
        if (len < IFNAMSIZ)
                goto out;

        ret = netdev_get_name(net, devname, bound_dev_if);
        if (ret)
                goto out;

        len = strlen(devname) + 1;

        ret = -EFAULT;
        if (copy_to_user(optval, devname, len))
                goto out;

zero:
        ret = -EFAULT;
        if (put_user(len, optlen))
                goto out;

        ret = 0;

out:
#endif

        return ret;
}

bool sk_mc_loop(struct sock *sk)
{
        if (dev_recursion_level())
                return false;
        if (!sk)
                return true;
        switch (sk->sk_family) {
        case AF_INET:
                return inet_sk(sk)->mc_loop;
#if IS_ENABLED(CONFIG_IPV6)
        case AF_INET6:
                return inet6_sk(sk)->mc_loop;
#endif
        }
        WARN_ON_ONCE(1);
        return true;
}
EXPORT_SYMBOL(sk_mc_loop);

void sock_set_reuseaddr(struct sock *sk)
{
        lock_sock(sk);
        sk->sk_reuse = SK_CAN_REUSE;
        release_sock(sk);
}
EXPORT_SYMBOL(sock_set_reuseaddr);

void sock_set_reuseport(struct sock *sk)
{
        lock_sock(sk);
        sk->sk_reuseport = true;
        release_sock(sk);
}
EXPORT_SYMBOL(sock_set_reuseport);

void sock_no_linger(struct sock *sk)
{
        lock_sock(sk);
        sk->sk_lingertime = 0;
        sock_set_flag(sk, SOCK_LINGER);
        release_sock(sk);
}
EXPORT_SYMBOL(sock_no_linger);

void sock_set_priority(struct sock *sk, u32 priority)
{
        lock_sock(sk);
        sk->sk_priority = priority;
        release_sock(sk);
}
EXPORT_SYMBOL(sock_set_priority);

void sock_set_sndtimeo(struct sock *sk, s64 secs)
{
        lock_sock(sk);
        if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1)
                sk->sk_sndtimeo = secs * HZ;
        else
                sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
        release_sock(sk);
}
EXPORT_SYMBOL(sock_set_sndtimeo);

static void __sock_set_timestamps(struct sock *sk, bool val, bool new, bool ns)
{
        if (val)  {
                sock_valbool_flag(sk, SOCK_TSTAMP_NEW, new);
                sock_valbool_flag(sk, SOCK_RCVTSTAMPNS, ns);
                sock_set_flag(sk, SOCK_RCVTSTAMP);
                sock_enable_timestamp(sk, SOCK_TIMESTAMP);
        } else {
                sock_reset_flag(sk, SOCK_RCVTSTAMP);
                sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
        }
}

void sock_enable_timestamps(struct sock *sk)
{
        lock_sock(sk);
        __sock_set_timestamps(sk, true, false, true);
        release_sock(sk);
}
EXPORT_SYMBOL(sock_enable_timestamps);

void sock_set_timestamp(struct sock *sk, int optname, bool valbool)
{
        switch (optname) {
        case SO_TIMESTAMP_OLD:
                __sock_set_timestamps(sk, valbool, false, false);
                break;
        case SO_TIMESTAMP_NEW:
                __sock_set_timestamps(sk, valbool, true, false);
                break;
        case SO_TIMESTAMPNS_OLD:
                __sock_set_timestamps(sk, valbool, false, true);
                break;
        case SO_TIMESTAMPNS_NEW:
                __sock_set_timestamps(sk, valbool, true, true);
                break;
        }
}

static int sock_timestamping_bind_phc(struct sock *sk, int phc_index)
{
        struct net *net = sock_net(sk);
        struct net_device *dev = NULL;
        bool match = false;
        int *vclock_index;
        int i, num;

        if (sk->sk_bound_dev_if)
                dev = dev_get_by_index(net, sk->sk_bound_dev_if);

        if (!dev) {
                pr_err("%s: sock not bind to device\n", __func__);
                return -EOPNOTSUPP;
        }

        num = ethtool_get_phc_vclocks(dev, &vclock_index);
        dev_put(dev);

        for (i = 0; i < num; i++) {
                if (*(vclock_index + i) == phc_index) {
                        match = true;
                        break;
                }
        }

        if (num > 0)
                kfree(vclock_index);

        if (!match)
                return -EINVAL;

        sk->sk_bind_phc = phc_index;

        return 0;
}

int sock_set_timestamping(struct sock *sk, int optname,
                          struct so_timestamping timestamping)
{
        int val = timestamping.flags;
        int ret;

        if (val & ~SOF_TIMESTAMPING_MASK)
                return -EINVAL;

        if (val & SOF_TIMESTAMPING_OPT_ID &&
            !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
                if (sk_is_tcp(sk)) {
                        if ((1 << sk->sk_state) &
                            (TCPF_CLOSE | TCPF_LISTEN))
                                return -EINVAL;
                        atomic_set(&sk->sk_tskey, tcp_sk(sk)->snd_una);
                } else {
                        atomic_set(&sk->sk_tskey, 0);
                }
        }

        if (val & SOF_TIMESTAMPING_OPT_STATS &&
            !(val & SOF_TIMESTAMPING_OPT_TSONLY))
                return -EINVAL;

        if (val & SOF_TIMESTAMPING_BIND_PHC) {
                ret = sock_timestamping_bind_phc(sk, timestamping.bind_phc);
                if (ret)
                        return ret;
        }

        sk->sk_tsflags = val;
        sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);

        if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
                sock_enable_timestamp(sk,
                                      SOCK_TIMESTAMPING_RX_SOFTWARE);
        else
                sock_disable_timestamp(sk,
                                       (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
        return 0;
}

void sock_set_keepalive(struct sock *sk)
{
        lock_sock(sk);
        if (sk->sk_prot->keepalive)
                sk->sk_prot->keepalive(sk, true);
        sock_valbool_flag(sk, SOCK_KEEPOPEN, true);
        release_sock(sk);
}
EXPORT_SYMBOL(sock_set_keepalive);

static void __sock_set_rcvbuf(struct sock *sk, int val)
{
        /* Ensure val * 2 fits into an int, to prevent max_t() from treating it
         * as a negative value.
         */
        val = min_t(int, val, INT_MAX / 2);
        sk->sk_userlocks |= SOCK_RCVBUF_LOCK;

        /* We double it on the way in to account for "struct sk_buff" etc.
         * overhead.   Applications assume that the SO_RCVBUF setting they make
         * will allow that much actual data to be received on that socket.
         *
         * Applications are unaware that "struct sk_buff" and other overheads
         * allocate from the receive buffer during socket buffer allocation.
         *
         * And after considering the possible alternatives, returning the value
         * we actually used in getsockopt is the most desirable behavior.
         */
        WRITE_ONCE(sk->sk_rcvbuf, max_t(int, val * 2, SOCK_MIN_RCVBUF));
}

void sock_set_rcvbuf(struct sock *sk, int val)
{
        lock_sock(sk);
        __sock_set_rcvbuf(sk, val);
        release_sock(sk);
}
EXPORT_SYMBOL(sock_set_rcvbuf);

static void __sock_set_mark(struct sock *sk, u32 val)
{
        if (val != sk->sk_mark) {
                sk->sk_mark = val;
                sk_dst_reset(sk);
        }
}

void sock_set_mark(struct sock *sk, u32 val)
{
        lock_sock(sk);
        __sock_set_mark(sk, val);
        release_sock(sk);
}
EXPORT_SYMBOL(sock_set_mark);

static void sock_release_reserved_memory(struct sock *sk, int bytes)
{
        /* Round down bytes to multiple of pages */
        bytes = round_down(bytes, PAGE_SIZE);

        WARN_ON(bytes > sk->sk_reserved_mem);
        sk->sk_reserved_mem -= bytes;
        sk_mem_reclaim(sk);
}

static int sock_reserve_memory(struct sock *sk, int bytes)
{
        long allocated;
        bool charged;
        int pages;

        if (!mem_cgroup_sockets_enabled || !sk->sk_memcg || !sk_has_account(sk))
                return -EOPNOTSUPP;

        if (!bytes)
                return 0;

        pages = sk_mem_pages(bytes);

        /* pre-charge to memcg */
        charged = mem_cgroup_charge_skmem(sk->sk_memcg, pages,
                                          GFP_KERNEL | __GFP_RETRY_MAYFAIL);
        if (!charged)
                return -ENOMEM;

        /* pre-charge to forward_alloc */
        sk_memory_allocated_add(sk, pages);
        allocated = sk_memory_allocated(sk);
        /* If the system goes into memory pressure with this
         * precharge, give up and return error.
         */
        if (allocated > sk_prot_mem_limits(sk, 1)) {
                sk_memory_allocated_sub(sk, pages);
                mem_cgroup_uncharge_skmem(sk->sk_memcg, pages);
                return -ENOMEM;
        }
        sk->sk_forward_alloc += pages << PAGE_SHIFT;

        sk->sk_reserved_mem += pages << PAGE_SHIFT;

        return 0;
}

/*
 *      This is meant for all protocols to use and covers goings on
 *      at the socket level. Everything here is generic.
 */

int sock_setsockopt(struct socket *sock, int level, int optname,
                    sockptr_t optval, unsigned int optlen)
{
        struct so_timestamping timestamping;
        struct sock_txtime sk_txtime;
        struct sock *sk = sock->sk;
        int val;
        int valbool;
        struct linger ling;
        int ret = 0;

        /*
         *      Options without arguments
         */

        if (optname == SO_BINDTODEVICE)
                return sock_setbindtodevice(sk, optval, optlen);

        if (optlen < sizeof(int))
                return -EINVAL;

        if (copy_from_sockptr(&val, optval, sizeof(val)))
                return -EFAULT;

        valbool = val ? 1 : 0;

        lock_sock(sk);

        switch (optname) {
        case SO_DEBUG:
                if (val && !capable(CAP_NET_ADMIN))
                        ret = -EACCES;
                else
                        sock_valbool_flag(sk, SOCK_DBG, valbool);
                break;
        case SO_REUSEADDR:
                sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE);
                break;
        case SO_REUSEPORT:
                sk->sk_reuseport = valbool;
                break;
        case SO_TYPE:
        case SO_PROTOCOL:
        case SO_DOMAIN:
        case SO_ERROR:
                ret = -ENOPROTOOPT;
                break;
        case SO_DONTROUTE:
                sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool);
                sk_dst_reset(sk);
                break;
        case SO_BROADCAST:
                sock_valbool_flag(sk, SOCK_BROADCAST, valbool);
                break;
        case SO_SNDBUF:
                /* Don't error on this BSD doesn't and if you think
                 * about it this is right. Otherwise apps have to
                 * play 'guess the biggest size' games. RCVBUF/SNDBUF
                 * are treated in BSD as hints
                 */
                val = min_t(u32, val, READ_ONCE(sysctl_wmem_max));
set_sndbuf:
                /* Ensure val * 2 fits into an int, to prevent max_t()
                 * from treating it as a negative value.
                 */
                val = min_t(int, val, INT_MAX / 2);
                sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
                WRITE_ONCE(sk->sk_sndbuf,
                           max_t(int, val * 2, SOCK_MIN_SNDBUF));
                /* Wake up sending tasks if we upped the value. */
                sk->sk_write_space(sk);
                break;

        case SO_SNDBUFFORCE:
                if (!capable(CAP_NET_ADMIN)) {
                        ret = -EPERM;
                        break;
                }

                /* No negative values (to prevent underflow, as val will be
                 * multiplied by 2).
                 */
                if (val < 0)
                        val = 0;
                goto set_sndbuf;

        case SO_RCVBUF:
                /* Don't error on this BSD doesn't and if you think
                 * about it this is right. Otherwise apps have to
                 * play 'guess the biggest size' games. RCVBUF/SNDBUF
                 * are treated in BSD as hints
                 */
                __sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max)));
                break;

        case SO_RCVBUFFORCE:
                if (!capable(CAP_NET_ADMIN)) {
                        ret = -EPERM;
                        break;
                }

                /* No negative values (to prevent underflow, as val will be
                 * multiplied by 2).
                 */
                __sock_set_rcvbuf(sk, max(val, 0));
                break;

        case SO_KEEPALIVE:
                if (sk->sk_prot->keepalive)
                        sk->sk_prot->keepalive(sk, valbool);
                sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
                break;

        case SO_OOBINLINE:
                sock_valbool_flag(sk, SOCK_URGINLINE, valbool);
                break;

        case SO_NO_CHECK:
                sk->sk_no_check_tx = valbool;
                break;

        case SO_PRIORITY:
                if ((val >= 0 && val <= 6) ||
                    ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
                    ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
                        sk->sk_priority = val;
                else
                        ret = -EPERM;
                break;

        case SO_LINGER:
                if (optlen < sizeof(ling)) {
                        ret = -EINVAL;  /* 1003.1g */
                        break;
                }
                if (copy_from_sockptr(&ling, optval, sizeof(ling))) {
                        ret = -EFAULT;
                        break;
                }
                if (!ling.l_onoff)
                        sock_reset_flag(sk, SOCK_LINGER);
                else {
#if (BITS_PER_LONG == 32)
                        if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ)
                                sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT;
                        else
#endif
                                sk->sk_lingertime = (unsigned int)ling.l_linger * HZ;
                        sock_set_flag(sk, SOCK_LINGER);
                }
                break;

        case SO_BSDCOMPAT:
                break;

        case SO_PASSCRED:
                if (valbool)
                        set_bit(SOCK_PASSCRED, &sock->flags);
                else
                        clear_bit(SOCK_PASSCRED, &sock->flags);
                break;

        case SO_TIMESTAMP_OLD:
        case SO_TIMESTAMP_NEW:
        case SO_TIMESTAMPNS_OLD:
        case SO_TIMESTAMPNS_NEW:
                sock_set_timestamp(sk, optname, valbool);
                break;

        case SO_TIMESTAMPING_NEW:
        case SO_TIMESTAMPING_OLD:
                if (optlen == sizeof(timestamping)) {
                        if (copy_from_sockptr(&timestamping, optval,
                                              sizeof(timestamping))) {
                                ret = -EFAULT;
                                break;
                        }
                } else {
                        memset(&timestamping, 0, sizeof(timestamping));
                        timestamping.flags = val;
                }
                ret = sock_set_timestamping(sk, optname, timestamping);
                break;

        case SO_RCVLOWAT:
                if (val < 0)
                        val = INT_MAX;
                if (sock->ops->set_rcvlowat)
                        ret = sock->ops->set_rcvlowat(sk, val);
                else
                        WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
                break;

        case SO_RCVTIMEO_OLD:
        case SO_RCVTIMEO_NEW:
                ret = sock_set_timeout(&sk->sk_rcvtimeo, optval,
                                       optlen, optname == SO_RCVTIMEO_OLD);
                break;

        case SO_SNDTIMEO_OLD:
        case SO_SNDTIMEO_NEW:
                ret = sock_set_timeout(&sk->sk_sndtimeo, optval,
                                       optlen, optname == SO_SNDTIMEO_OLD);
                break;

        case SO_ATTACH_FILTER: {
                struct sock_fprog fprog;

                ret = copy_bpf_fprog_from_user(&fprog, optval, optlen);
                if (!ret)
                        ret = sk_attach_filter(&fprog, sk);
                break;
        }
        case SO_ATTACH_BPF:
                ret = -EINVAL;
                if (optlen == sizeof(u32)) {
                        u32 ufd;

                        ret = -EFAULT;
                        if (copy_from_sockptr(&ufd, optval, sizeof(ufd)))
                                break;

                        ret = sk_attach_bpf(ufd, sk);
                }
                break;

        case SO_ATTACH_REUSEPORT_CBPF: {
                struct sock_fprog fprog;

                ret = copy_bpf_fprog_from_user(&fprog, optval, optlen);
                if (!ret)
                        ret = sk_reuseport_attach_filter(&fprog, sk);
                break;
        }
        case SO_ATTACH_REUSEPORT_EBPF:
                ret = -EINVAL;
                if (optlen == sizeof(u32)) {
                        u32 ufd;

                        ret = -EFAULT;
                        if (copy_from_sockptr(&ufd, optval, sizeof(ufd)))
                                break;

                        ret = sk_reuseport_attach_bpf(ufd, sk);
                }
                break;

        case SO_DETACH_REUSEPORT_BPF:
                ret = reuseport_detach_prog(sk);
                break;

        case SO_DETACH_FILTER:
                ret = sk_detach_filter(sk);
                break;

        case SO_LOCK_FILTER:
                if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool)
                        ret = -EPERM;
                else
                        sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool);
                break;

        case SO_PASSSEC:
                if (valbool)
                        set_bit(SOCK_PASSSEC, &sock->flags);
                else
                        clear_bit(SOCK_PASSSEC, &sock->flags);
                break;
        case SO_MARK:
                if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
                    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
                        ret = -EPERM;
                        break;
                }

                __sock_set_mark(sk, val);
                break;
        case SO_RCVMARK:
                if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
                    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
                        ret = -EPERM;
                        break;
                }

                sock_valbool_flag(sk, SOCK_RCVMARK, valbool);
                break;

        case SO_RXQ_OVFL:
                sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool);
                break;

        case SO_WIFI_STATUS:
                sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool);
                break;

        case SO_PEEK_OFF:
                if (sock->ops->set_peek_off)
                        ret = sock->ops->set_peek_off(sk, val);
                else
                        ret = -EOPNOTSUPP;
                break;

        case SO_NOFCS:
                sock_valbool_flag(sk, SOCK_NOFCS, valbool);
                break;

        case SO_SELECT_ERR_QUEUE:
                sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool);
                break;

#ifdef CONFIG_NET_RX_BUSY_POLL
        case SO_BUSY_POLL:
                /* allow unprivileged users to decrease the value */
                if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN))
                        ret = -EPERM;
                else {
                        if (val < 0)
                                ret = -EINVAL;
                        else
                                WRITE_ONCE(sk->sk_ll_usec, val);
                }
                break;
        case SO_PREFER_BUSY_POLL:
                if (valbool && !capable(CAP_NET_ADMIN))
                        ret = -EPERM;
                else
                        WRITE_ONCE(sk->sk_prefer_busy_poll, valbool);
                break;
        case SO_BUSY_POLL_BUDGET:
                if (val > READ_ONCE(sk->sk_busy_poll_budget) && !capable(CAP_NET_ADMIN)) {
                        ret = -EPERM;
                } else {
                        if (val < 0 || val > U16_MAX)
                                ret = -EINVAL;
                        else
                                WRITE_ONCE(sk->sk_busy_poll_budget, val);
                }
                break;
#endif

        case SO_MAX_PACING_RATE:
                {
                unsigned long ulval = (val == ~0U) ? ~0UL : (unsigned int)val;

                if (sizeof(ulval) != sizeof(val) &&
                    optlen >= sizeof(ulval) &&
                    copy_from_sockptr(&ulval, optval, sizeof(ulval))) {
                        ret = -EFAULT;
                        break;
                }
                if (ulval != ~0UL)
                        cmpxchg(&sk->sk_pacing_status,
                                SK_PACING_NONE,
                                SK_PACING_NEEDED);
                sk->sk_max_pacing_rate = ulval;
                sk->sk_pacing_rate = min(sk->sk_pacing_rate, ulval);
                break;
                }
        case SO_INCOMING_CPU:
                WRITE_ONCE(sk->sk_incoming_cpu, val);
                break;

        case SO_CNX_ADVICE:
                if (val == 1)
                        dst_negative_advice(sk);
                break;

        case SO_ZEROCOPY:
                if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6) {
                        if (!(sk_is_tcp(sk) ||
                              (sk->sk_type == SOCK_DGRAM &&
                               sk->sk_protocol == IPPROTO_UDP)))
                                ret = -EOPNOTSUPP;
                } else if (sk->sk_family != PF_RDS) {
                        ret = -EOPNOTSUPP;
                }
                if (!ret) {
                        if (val < 0 || val > 1)
                                ret = -EINVAL;
                        else
                                sock_valbool_flag(sk, SOCK_ZEROCOPY, valbool);
                }
                break;

        case SO_TXTIME:
                if (optlen != sizeof(struct sock_txtime)) {
                        ret = -EINVAL;
                        break;
                } else if (copy_from_sockptr(&sk_txtime, optval,
                           sizeof(struct sock_txtime))) {
                        ret = -EFAULT;
                        break;
                } else if (sk_txtime.flags & ~SOF_TXTIME_FLAGS_MASK) {
                        ret = -EINVAL;
                        break;
                }
                /* CLOCK_MONOTONIC is only used by sch_fq, and this packet
                 * scheduler has enough safe guards.
                 */
                if (sk_txtime.clockid != CLOCK_MONOTONIC &&
                    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
                        ret = -EPERM;
                        break;
                }
                sock_valbool_flag(sk, SOCK_TXTIME, true);
                sk->sk_clockid = sk_txtime.clockid;
                sk->sk_txtime_deadline_mode =
                        !!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE);
                sk->sk_txtime_report_errors =
                        !!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS);
                break;

        case SO_BINDTOIFINDEX:
                ret = sock_bindtoindex_locked(sk, val);
                break;

        case SO_BUF_LOCK:
                if (val & ~SOCK_BUF_LOCK_MASK) {
                        ret = -EINVAL;
                        break;
                }
                sk->sk_userlocks = val | (sk->sk_userlocks &
                                          ~SOCK_BUF_LOCK_MASK);
                break;

        case SO_RESERVE_MEM:
        {
                int delta;

                if (val < 0) {
                        ret = -EINVAL;
                        break;
                }

                delta = val - sk->sk_reserved_mem;
                if (delta < 0)
                        sock_release_reserved_memory(sk, -delta);
                else
                        ret = sock_reserve_memory(sk, delta);
                break;
        }

        case SO_TXREHASH:
                if (val < -1 || val > 1) {
                        ret = -EINVAL;
                        break;
                }
                /* Paired with READ_ONCE() in tcp_rtx_synack() */
                WRITE_ONCE(sk->sk_txrehash, (u8)val);
                break;

        default:
                ret = -ENOPROTOOPT;
                break;
        }
        release_sock(sk);
        return ret;
}
EXPORT_SYMBOL(sock_setsockopt);

static const struct cred *sk_get_peer_cred(struct sock *sk)
{
        const struct cred *cred;

        spin_lock(&sk->sk_peer_lock);
        cred = get_cred(sk->sk_peer_cred);
        spin_unlock(&sk->sk_peer_lock);

        return cred;
}

static void cred_to_ucred(struct pid *pid, const struct cred *cred,
                          struct ucred *ucred)
{
        ucred->pid = pid_vnr(pid);
        ucred->uid = ucred->gid = -1;
        if (cred) {
                struct user_namespace *current_ns = current_user_ns();

                ucred->uid = from_kuid_munged(current_ns, cred->euid);
                ucred->gid = from_kgid_munged(current_ns, cred->egid);
        }
}

static int groups_to_user(gid_t __user *dst, const struct group_info *src)
{
        struct user_namespace *user_ns = current_user_ns();
        int i;

        for (i = 0; i < src->ngroups; i++)
                if (put_user(from_kgid_munged(user_ns, src->gid[i]), dst + i))
                        return -EFAULT;

        return 0;
}

int sock_getsockopt(struct socket *sock, int level, int optname,
                    char __user *optval, int __user *optlen)
{
        struct sock *sk = sock->sk;

        union {
                int val;
                u64 val64;
                unsigned long ulval;
                struct linger ling;
                struct old_timeval32 tm32;
                struct __kernel_old_timeval tm;
                struct  __kernel_sock_timeval stm;
                struct sock_txtime txtime;
                struct so_timestamping timestamping;
        } v;

        int lv = sizeof(int);
        int len;

        if (get_user(len, optlen))
                return -EFAULT;
        if (len < 0)
                return -EINVAL;

        memset(&v, 0, sizeof(v));

        switch (optname) {
        case SO_DEBUG:
                v.val = sock_flag(sk, SOCK_DBG);
                break;

        case SO_DONTROUTE:
                v.val = sock_flag(sk, SOCK_LOCALROUTE);
                break;

        case SO_BROADCAST:
                v.val = sock_flag(sk, SOCK_BROADCAST);
                break;

        case SO_SNDBUF:
                v.val = sk->sk_sndbuf;
                break;

        case SO_RCVBUF:
                v.val = sk->sk_rcvbuf;
                break;

        case SO_REUSEADDR:
                v.val = sk->sk_reuse;
                break;

        case SO_REUSEPORT:
                v.val = sk->sk_reuseport;
                break;

        case SO_KEEPALIVE:
                v.val = sock_flag(sk, SOCK_KEEPOPEN);
                break;

        case SO_TYPE:
                v.val = sk->sk_type;
                break;

        case SO_PROTOCOL:
                v.val = sk->sk_protocol;
                break;

        case SO_DOMAIN:
                v.val = sk->sk_family;
                break;

        case SO_ERROR:
                v.val = -sock_error(sk);
                if (v.val == 0)
                        v.val = xchg(&sk->sk_err_soft, 0);
                break;

        case SO_OOBINLINE:
                v.val = sock_flag(sk, SOCK_URGINLINE);
                break;

        case SO_NO_CHECK:
                v.val = sk->sk_no_check_tx;
                break;

        case SO_PRIORITY:
                v.val = sk->sk_priority;
                break;

        case SO_LINGER:
                lv              = sizeof(v.ling);
                v.ling.l_onoff  = sock_flag(sk, SOCK_LINGER);
                v.ling.l_linger = sk->sk_lingertime / HZ;
                break;

        case SO_BSDCOMPAT:
                break;

        case SO_TIMESTAMP_OLD:
                v.val = sock_flag(sk, SOCK_RCVTSTAMP) &&
                                !sock_flag(sk, SOCK_TSTAMP_NEW) &&
                                !sock_flag(sk, SOCK_RCVTSTAMPNS);
                break;

        case SO_TIMESTAMPNS_OLD:
                v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && !sock_flag(sk, SOCK_TSTAMP_NEW);
                break;

        case SO_TIMESTAMP_NEW:
                v.val = sock_flag(sk, SOCK_RCVTSTAMP) && sock_flag(sk, SOCK_TSTAMP_NEW);
                break;

        case SO_TIMESTAMPNS_NEW:
                v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && sock_flag(sk, SOCK_TSTAMP_NEW);
                break;

        case SO_TIMESTAMPING_OLD:
                lv = sizeof(v.timestamping);
                v.timestamping.flags = sk->sk_tsflags;
                v.timestamping.bind_phc = sk->sk_bind_phc;
                break;

        case SO_RCVTIMEO_OLD:
        case SO_RCVTIMEO_NEW:
                lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname);
                break;

        case SO_SNDTIMEO_OLD:
        case SO_SNDTIMEO_NEW:
                lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname);
                break;

        case SO_RCVLOWAT:
                v.val = sk->sk_rcvlowat;
                break;

        case SO_SNDLOWAT:
                v.val = 1;
                break;

        case SO_PASSCRED:
                v.val = !!test_bit(SOCK_PASSCRED, &sock->flags);
                break;

        case SO_PEERCRED:
        {
                struct ucred peercred;
                if (len > sizeof(peercred))
                        len = sizeof(peercred);

                spin_lock(&sk->sk_peer_lock);
                cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred);
                spin_unlock(&sk->sk_peer_lock);

                if (copy_to_user(optval, &peercred, len))
                        return -EFAULT;
                goto lenout;
        }

        case SO_PEERGROUPS:
        {
                const struct cred *cred;
                int ret, n;

                cred = sk_get_peer_cred(sk);
                if (!cred)
                        return -ENODATA;

                n = cred->group_info->ngroups;
                if (len < n * sizeof(gid_t)) {
                        len = n * sizeof(gid_t);
                        put_cred(cred);
                        return put_user(len, optlen) ? -EFAULT : -ERANGE;
                }
                len = n * sizeof(gid_t);

                ret = groups_to_user((gid_t __user *)optval, cred->group_info);
                put_cred(cred);
                if (ret)
                        return ret;
                goto lenout;
        }

        case SO_PEERNAME:
        {
                char address[128];

                lv = sock->ops->getname(sock, (struct sockaddr *)address, 2);
                if (lv < 0)
                        return -ENOTCONN;
                if (lv < len)
                        return -EINVAL;
                if (copy_to_user(optval, address, len))
                        return -EFAULT;
                goto lenout;
        }

        /* Dubious BSD thing... Probably nobody even uses it, but
         * the UNIX standard wants it for whatever reason... -DaveM
         */
        case SO_ACCEPTCONN:
                v.val = sk->sk_state == TCP_LISTEN;
                break;

        case SO_PASSSEC:
                v.val = !!test_bit(SOCK_PASSSEC, &sock->flags);
                break;

        case SO_PEERSEC:
                return security_socket_getpeersec_stream(sock, optval, optlen, len);

        case SO_MARK:
                v.val = sk->sk_mark;
                break;

        case SO_RCVMARK:
                v.val = sock_flag(sk, SOCK_RCVMARK);
                break;

        case SO_RXQ_OVFL:
                v.val = sock_flag(sk, SOCK_RXQ_OVFL);
                break;

        case SO_WIFI_STATUS:
                v.val = sock_flag(sk, SOCK_WIFI_STATUS);
                break;

        case SO_PEEK_OFF:
                if (!sock->ops->set_peek_off)
                        return -EOPNOTSUPP;

                v.val = sk->sk_peek_off;
                break;
        case SO_NOFCS:
                v.val = sock_flag(sk, SOCK_NOFCS);
                break;

        case SO_BINDTODEVICE:
                return sock_getbindtodevice(sk, optval, optlen, len);

        case SO_GET_FILTER:
                len = sk_get_filter(sk, (struct sock_filter __user *)optval, len);
                if (len < 0)
                        return len;

                goto lenout;

        case SO_LOCK_FILTER:
                v.val = sock_flag(sk, SOCK_FILTER_LOCKED);
                break;

        case SO_BPF_EXTENSIONS:
                v.val = bpf_tell_extensions();
                break;

        case SO_SELECT_ERR_QUEUE:
                v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE);
                break;

#ifdef CONFIG_NET_RX_BUSY_POLL
        case SO_BUSY_POLL:
                v.val = sk->sk_ll_usec;
                break;
        case SO_PREFER_BUSY_POLL:
                v.val = READ_ONCE(sk->sk_prefer_busy_poll);
                break;
#endif

        case SO_MAX_PACING_RATE:
                if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) {
                        lv = sizeof(v.ulval);
                        v.ulval = sk->sk_max_pacing_rate;
                } else {
                        /* 32bit version */
                        v.val = min_t(unsigned long, sk->sk_max_pacing_rate, ~0U);
                }
                break;

        case SO_INCOMING_CPU:
                v.val = READ_ONCE(sk->sk_incoming_cpu);
                break;

        case SO_MEMINFO:
        {
                u32 meminfo[SK_MEMINFO_VARS];

                sk_get_meminfo(sk, meminfo);

                len = min_t(unsigned int, len, sizeof(meminfo));
                if (copy_to_user(optval, &meminfo, len))
                        return -EFAULT;

                goto lenout;
        }

#ifdef CONFIG_NET_RX_BUSY_POLL
        case SO_INCOMING_NAPI_ID:
                v.val = READ_ONCE(sk->sk_napi_id);

                /* aggregate non-NAPI IDs down to 0 */
                if (v.val < MIN_NAPI_ID)
                        v.val = 0;

                break;
#endif

        case SO_COOKIE:
                lv = sizeof(u64);
                if (len < lv)
                        return -EINVAL;
                v.val64 = sock_gen_cookie(sk);
                break;

        case SO_ZEROCOPY:
                v.val = sock_flag(sk, SOCK_ZEROCOPY);
                break;

        case SO_TXTIME:
                lv = sizeof(v.txtime);
                v.txtime.clockid = sk->sk_clockid;
                v.txtime.flags |= sk->sk_txtime_deadline_mode ?
                                  SOF_TXTIME_DEADLINE_MODE : 0;
                v.txtime.flags |= sk->sk_txtime_report_errors ?
                                  SOF_TXTIME_REPORT_ERRORS : 0;
                break;

        case SO_BINDTOIFINDEX:
                v.val = READ_ONCE(sk->sk_bound_dev_if);
                break;

        case SO_NETNS_COOKIE:
                lv = sizeof(u64);
                if (len != lv)
                        return -EINVAL;
                v.val64 = sock_net(sk)->net_cookie;
                break;

        case SO_BUF_LOCK:
                v.val = sk->sk_userlocks & SOCK_BUF_LOCK_MASK;
                break;

        case SO_RESERVE_MEM:
                v.val = sk->sk_reserved_mem;
                break;

        case SO_TXREHASH:
                v.val = sk->sk_txrehash;
                break;

        default:
                /* We implement the SO_SNDLOWAT etc to not be settable
                 * (1003.1g 7).
                 */
                return -ENOPROTOOPT;
        }

        if (len > lv)
                len = lv;
        if (copy_to_user(optval, &v, len))
                return -EFAULT;
lenout:
        if (put_user(len, optlen))
                return -EFAULT;
        return 0;
}

/*
 * Initialize an sk_lock.
 *
 * (We also register the sk_lock with the lock validator.)
 */
static inline void sock_lock_init(struct sock *sk)
{
        if (sk->sk_kern_sock)
                sock_lock_init_class_and_name(
                        sk,
                        af_family_kern_slock_key_strings[sk->sk_family],
                        af_family_kern_slock_keys + sk->sk_family,
                        af_family_kern_key_strings[sk->sk_family],
                        af_family_kern_keys + sk->sk_family);
        else
                sock_lock_init_class_and_name(
                        sk,
                        af_family_slock_key_strings[sk->sk_family],
                        af_family_slock_keys + sk->sk_family,
                        af_family_key_strings[sk->sk_family],
                        af_family_keys + sk->sk_family);
}

/*
 * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet,
 * even temporarly, because of RCU lookups. sk_node should also be left as is.
 * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end
 */
static void sock_copy(struct sock *nsk, const struct sock *osk)
{
        const struct proto *prot = READ_ONCE(osk->sk_prot);
#ifdef CONFIG_SECURITY_NETWORK
        void *sptr = nsk->sk_security;
#endif

        /* If we move sk_tx_queue_mapping out of the private section,
         * we must check if sk_tx_queue_clear() is called after
         * sock_copy() in sk_clone_lock().
         */
        BUILD_BUG_ON(offsetof(struct sock, sk_tx_queue_mapping) <
                     offsetof(struct sock, sk_dontcopy_begin) ||
                     offsetof(struct sock, sk_tx_queue_mapping) >=
                     offsetof(struct sock, sk_dontcopy_end));

        memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin));

        memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end,
               prot->obj_size - offsetof(struct sock, sk_dontcopy_end));

#ifdef CONFIG_SECURITY_NETWORK
        nsk->sk_security = sptr;
        security_sk_clone(osk, nsk);
#endif
}

static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
                int family)
{
        struct sock *sk;
        struct kmem_cache *slab;

        slab = prot->slab;
        if (slab != NULL) {
                sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO);
                if (!sk)
                        return sk;
                if (want_init_on_alloc(priority))
                        sk_prot_clear_nulls(sk, prot->obj_size);
        } else
                sk = kmalloc(prot->obj_size, priority);

        if (sk != NULL) {
                if (security_sk_alloc(sk, family, priority))
                        goto out_free;

                if (!try_module_get(prot->owner))
                        goto out_free_sec;
        }

        return sk;

out_free_sec:
        security_sk_free(sk);
out_free:
        if (slab != NULL)
                kmem_cache_free(slab, sk);
        else
                kfree(sk);
        return NULL;
}

static void sk_prot_free(struct proto *prot, struct sock *sk)
{
        struct kmem_cache *slab;