sock.c

// 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/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>

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

static void sock_inuse_add(struct net *net, int val);

/**
 * 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_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 = sk->sk_backlog_rcv(sk, skb);
	memalloc_noreclaim_restore(noreclaim_flag);

	return ret;
}
EXPORT_SYMBOL(__sk_backlog_rcv);

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

	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;
		size = sizeof(old_tv);
	} else {
		*(struct __kernel_sock_timeval *)optval = tv;
		size = sizeof(tv);
	}

	return size;
}

static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool old_timeval)
{
	struct __kernel_sock_timeval tv;

	if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
		struct old_timeval32 tv32;

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

		if (copy_from_user(&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_user(&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_user(&tv, optval, sizeof(tv)))
			return -EFAULT;
	}
	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 void sock_warn_obsolete_bsdism(const char *name)
{
	static int warned;
	static char warncomm[TASK_COMM_LEN];
	if (strcmp(warncomm, current->comm) && warned < 5) {
		strcpy(warncomm,  current->comm);
		pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n",
			warncomm, name);
		warned++;
	}
}

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(struct sock *sk, struct sk_buff *skb)
{
	int err;

	err = sk_filter(sk, skb);
	if (err)
		return err;

	return __sock_queue_rcv_skb(sk, skb);
}
EXPORT_SYMBOL(sock_queue_rcv_skb);

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, 1, _RET_IP_);
	} else if (sk_add_backlog(sk, skb, 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);

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

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

	return dst;
}
EXPORT_SYMBOL(sk_dst_check);

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

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

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

	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;
}

static int sock_setbindtodevice(struct sock *sk, char __user *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_user(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;
	}

	lock_sock(sk);
	ret = sock_setbindtodevice_locked(sk, index);
	release_sock(sk);

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
	struct net *net = sock_net(sk);
	char devname[IFNAMSIZ];

	if (sk->sk_bound_dev_if == 0) {
		len = 0;
		goto zero;
	}

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

	ret = netdev_get_name(net, devname, sk->sk_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;
}

static inline void sock_valbool_flag(struct sock *sk, enum sock_flags bit,
				     int valbool)
{
	if (valbool)
		sock_set_flag(sk, bit);
	else
		sock_reset_flag(sk, bit);
}

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(1);
	return true;
}
EXPORT_SYMBOL(sk_mc_loop);

/*
 *	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,
		    char __user *optval, unsigned int optlen)
{
	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 (get_user(val, (int __user *)optval))
		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, 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;
		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
		 */
		val = min_t(u32, val, sysctl_rmem_max);
set_rcvbuf:
		/* 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.
		 */
		sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
		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).
		 */
		if (val < 0)
			val = 0;
		goto set_rcvbuf;

	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_ADMIN))
			sk->sk_priority = val;
		else
			ret = -EPERM;
		break;

	case SO_LINGER:
		if (optlen < sizeof(ling)) {
			ret = -EINVAL;	/* 1003.1g */
			break;
		}
		if (copy_from_user(&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:
		sock_warn_obsolete_bsdism("setsockopt");
		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:
		if (valbool)  {
			if (optname == SO_TIMESTAMP_NEW || optname == SO_TIMESTAMPNS_NEW)
				sock_set_flag(sk, SOCK_TSTAMP_NEW);
			else
				sock_reset_flag(sk, SOCK_TSTAMP_NEW);

			if (optname == SO_TIMESTAMP_OLD || optname == SO_TIMESTAMP_NEW)
				sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
			else
				sock_set_flag(sk, SOCK_RCVTSTAMPNS);
			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);
			sock_reset_flag(sk, SOCK_TSTAMP_NEW);
		}
		break;

	case SO_TIMESTAMPING_NEW:
		sock_set_flag(sk, SOCK_TSTAMP_NEW);
		/* fall through */
	case SO_TIMESTAMPING_OLD:
		if (val & ~SOF_TIMESTAMPING_MASK) {
			ret = -EINVAL;
			break;
		}

		if (val & SOF_TIMESTAMPING_OPT_ID &&
		    !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
			if (sk->sk_protocol == IPPROTO_TCP &&
			    sk->sk_type == SOCK_STREAM) {
				if ((1 << sk->sk_state) &
				    (TCPF_CLOSE | TCPF_LISTEN)) {
					ret = -EINVAL;
					break;
				}
				sk->sk_tskey = tcp_sk(sk)->snd_una;
			} else {
				sk->sk_tskey = 0;
			}
		}

		if (val & SOF_TIMESTAMPING_OPT_STATS &&
		    !(val & SOF_TIMESTAMPING_OPT_TSONLY)) {
			ret = -EINVAL;
			break;
		}

		sk->sk_tsflags = val;
		if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
			sock_enable_timestamp(sk,
					      SOCK_TIMESTAMPING_RX_SOFTWARE);
		else {
			if (optname == SO_TIMESTAMPING_NEW)
				sock_reset_flag(sk, SOCK_TSTAMP_NEW);

			sock_disable_timestamp(sk,
					       (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
		}
		break;

	case SO_RCVLOWAT:
		if (val < 0)
			val = INT_MAX;
		if (sock->ops->set_rcvlowat)
			ret = sock->ops->set_rcvlowat(sk, val);
		else
			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:
		ret = -EINVAL;
		if (optlen == sizeof(struct sock_fprog)) {
			struct sock_fprog fprog;

			ret = -EFAULT;
			if (copy_from_user(&fprog, optval, sizeof(fprog)))
				break;

			ret = sk_attach_filter(&fprog, sk);