sock.c

	 */
	if (sk_user_data_is_nocopy(newsk))
		newsk->sk_user_data = NULL;

	newsk->sk_err	   = 0;
	newsk->sk_err_soft = 0;
	newsk->sk_priority = 0;
	newsk->sk_incoming_cpu = raw_smp_processor_id();
	if (likely(newsk->sk_net_refcnt))
		sock_inuse_add(sock_net(newsk), 1);

	/* Before updating sk_refcnt, we must commit prior changes to memory
	 * (Documentation/RCU/rculist_nulls.rst for details)
	 */
	smp_wmb();
	refcount_set(&newsk->sk_refcnt, 2);

	/* Increment the counter in the same struct proto as the master
	 * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that
	 * is the same as sk->sk_prot->socks, as this field was copied
	 * with memcpy).
	 *
	 * This _changes_ the previous behaviour, where
	 * tcp_create_openreq_child always was incrementing the
	 * equivalent to tcp_prot->socks (inet_sock_nr), so this have
	 * to be taken into account in all callers. -acme
	 */
	sk_refcnt_debug_inc(newsk);
	sk_set_socket(newsk, NULL);
	sk_tx_queue_clear(newsk);
	RCU_INIT_POINTER(newsk->sk_wq, NULL);

	if (newsk->sk_prot->sockets_allocated)
		sk_sockets_allocated_inc(newsk);

	if (sock_needs_netstamp(sk) && newsk->sk_flags & SK_FLAGS_TIMESTAMP)
		net_enable_timestamp();
out:
	return newsk;
}
EXPORT_SYMBOL_GPL(sk_clone_lock);

void sk_free_unlock_clone(struct sock *sk)
{
	/* It is still raw copy of parent, so invalidate
	 * destructor and make plain sk_free() */
	sk->sk_destruct = NULL;
	bh_unlock_sock(sk);
	sk_free(sk);
}
EXPORT_SYMBOL_GPL(sk_free_unlock_clone);

void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
{
	u32 max_segs = 1;

	sk_dst_set(sk, dst);
	sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps;
	if (sk->sk_route_caps & NETIF_F_GSO)
		sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
	sk->sk_route_caps &= ~sk->sk_route_nocaps;
	if (sk_can_gso(sk)) {
		if (dst->header_len && !xfrm_dst_offload_ok(dst)) {
			sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
		} else {
			sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
			sk->sk_gso_max_size = dst->dev->gso_max_size;
			max_segs = max_t(u32, dst->dev->gso_max_segs, 1);
		}
	}
	sk->sk_gso_max_segs = max_segs;
}
EXPORT_SYMBOL_GPL(sk_setup_caps);

/*
 *	Simple resource managers for sockets.
 */


/*
 * Write buffer destructor automatically called from kfree_skb.
 */
void sock_wfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;
	unsigned int len = skb->truesize;

	if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) {
		/*
		 * Keep a reference on sk_wmem_alloc, this will be released
		 * after sk_write_space() call
		 */
		WARN_ON(refcount_sub_and_test(len - 1, &sk->sk_wmem_alloc));
		sk->sk_write_space(sk);
		len = 1;
	}
	/*
	 * if sk_wmem_alloc reaches 0, we must finish what sk_free()
	 * could not do because of in-flight packets
	 */
	if (refcount_sub_and_test(len, &sk->sk_wmem_alloc))
		__sk_free(sk);
}
EXPORT_SYMBOL(sock_wfree);

/* This variant of sock_wfree() is used by TCP,
 * since it sets SOCK_USE_WRITE_QUEUE.
 */
void __sock_wfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;

	if (refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc))
		__sk_free(sk);
}

void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
{
	skb_orphan(skb);
	skb->sk = sk;
#ifdef CONFIG_INET
	if (unlikely(!sk_fullsock(sk))) {
		skb->destructor = sock_edemux;
		sock_hold(sk);
		return;
	}
#endif
	skb->destructor = sock_wfree;
	skb_set_hash_from_sk(skb, sk);
	/*
	 * We used to take a refcount on sk, but following operation
	 * is enough to guarantee sk_free() wont free this sock until
	 * all in-flight packets are completed
	 */
	refcount_add(skb->truesize, &sk->sk_wmem_alloc);
}
EXPORT_SYMBOL(skb_set_owner_w);

static bool can_skb_orphan_partial(const struct sk_buff *skb)
{
#ifdef CONFIG_TLS_DEVICE
	/* Drivers depend on in-order delivery for crypto offload,
	 * partial orphan breaks out-of-order-OK logic.
	 */
	if (skb->decrypted)
		return false;
#endif
	return (skb->destructor == sock_wfree ||
		(IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree));
}

/* This helper is used by netem, as it can hold packets in its
 * delay queue. We want to allow the owner socket to send more
 * packets, as if they were already TX completed by a typical driver.
 * But we also want to keep skb->sk set because some packet schedulers
 * rely on it (sch_fq for example).
 */
void skb_orphan_partial(struct sk_buff *skb)
{
	if (skb_is_tcp_pure_ack(skb))
		return;

	if (can_skb_orphan_partial(skb) && skb_set_owner_sk_safe(skb, skb->sk))
		return;

	skb_orphan(skb);
}
EXPORT_SYMBOL(skb_orphan_partial);

/*
 * Read buffer destructor automatically called from kfree_skb.
 */
void sock_rfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;
	unsigned int len = skb->truesize;

	atomic_sub(len, &sk->sk_rmem_alloc);
	sk_mem_uncharge(sk, len);
}
EXPORT_SYMBOL(sock_rfree);

/*
 * Buffer destructor for skbs that are not used directly in read or write
 * path, e.g. for error handler skbs. Automatically called from kfree_skb.
 */
void sock_efree(struct sk_buff *skb)
{
	sock_put(skb->sk);
}
EXPORT_SYMBOL(sock_efree);

/* Buffer destructor for prefetch/receive path where reference count may
 * not be held, e.g. for listen sockets.
 */
#ifdef CONFIG_INET
void sock_pfree(struct sk_buff *skb)
{
	if (sk_is_refcounted(skb->sk))
		sock_gen_put(skb->sk);
}
EXPORT_SYMBOL(sock_pfree);
#endif /* CONFIG_INET */

kuid_t sock_i_uid(struct sock *sk)
{
	kuid_t uid;

	read_lock_bh(&sk->sk_callback_lock);
	uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : GLOBAL_ROOT_UID;
	read_unlock_bh(&sk->sk_callback_lock);
	return uid;
}
EXPORT_SYMBOL(sock_i_uid);

unsigned long sock_i_ino(struct sock *sk)
{
	unsigned long ino;

	read_lock_bh(&sk->sk_callback_lock);
	ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
	read_unlock_bh(&sk->sk_callback_lock);
	return ino;
}
EXPORT_SYMBOL(sock_i_ino);

/*
 * Allocate a skb from the socket's send buffer.
 */
struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
			     gfp_t priority)
{
	if (force ||
	    refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) {
		struct sk_buff *skb = alloc_skb(size, priority);

		if (skb) {
			skb_set_owner_w(skb, sk);
			return skb;
		}
	}
	return NULL;
}
EXPORT_SYMBOL(sock_wmalloc);

static void sock_ofree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;

	atomic_sub(skb->truesize, &sk->sk_omem_alloc);
}

struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
			     gfp_t priority)
{
	struct sk_buff *skb;

	/* small safe race: SKB_TRUESIZE may differ from final skb->truesize */
	if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) >
	    sysctl_optmem_max)
		return NULL;

	skb = alloc_skb(size, priority);
	if (!skb)
		return NULL;

	atomic_add(skb->truesize, &sk->sk_omem_alloc);
	skb->sk = sk;
	skb->destructor = sock_ofree;
	return skb;
}

/*
 * Allocate a memory block from the socket's option memory buffer.
 */
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
{
	if ((unsigned int)size <= sysctl_optmem_max &&
	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
		void *mem;
		/* First do the add, to avoid the race if kmalloc
		 * might sleep.
		 */
		atomic_add(size, &sk->sk_omem_alloc);
		mem = kmalloc(size, priority);
		if (mem)
			return mem;
		atomic_sub(size, &sk->sk_omem_alloc);
	}
	return NULL;
}
EXPORT_SYMBOL(sock_kmalloc);

/* Free an option memory block. Note, we actually want the inline
 * here as this allows gcc to detect the nullify and fold away the
 * condition entirely.
 */
static inline void __sock_kfree_s(struct sock *sk, void *mem, int size,
				  const bool nullify)
{
	if (WARN_ON_ONCE(!mem))
		return;
	if (nullify)
		kfree_sensitive(mem);
	else
		kfree(mem);
	atomic_sub(size, &sk->sk_omem_alloc);
}

void sock_kfree_s(struct sock *sk, void *mem, int size)
{
	__sock_kfree_s(sk, mem, size, false);
}
EXPORT_SYMBOL(sock_kfree_s);

void sock_kzfree_s(struct sock *sk, void *mem, int size)
{
	__sock_kfree_s(sk, mem, size, true);
}
EXPORT_SYMBOL(sock_kzfree_s);

/* It is almost wait_for_tcp_memory minus release_sock/lock_sock.
   I think, these locks should be removed for datagram sockets.
 */
static long sock_wait_for_wmem(struct sock *sk, long timeo)
{
	DEFINE_WAIT(wait);

	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
	for (;;) {
		if (!timeo)
			break;
		if (signal_pending(current))
			break;
		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
		if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf))
			break;
		if (sk->sk_shutdown & SEND_SHUTDOWN)
			break;
		if (sk->sk_err)
			break;
		timeo = schedule_timeout(timeo);
	}
	finish_wait(sk_sleep(sk), &wait);
	return timeo;
}


/*
 *	Generic send/receive buffer handlers
 */

struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
				     unsigned long data_len, int noblock,
				     int *errcode, int max_page_order)
{
	struct sk_buff *skb;
	long timeo;
	int err;

	timeo = sock_sndtimeo(sk, noblock);
	for (;;) {
		err = sock_error(sk);
		if (err != 0)
			goto failure;

		err = -EPIPE;
		if (sk->sk_shutdown & SEND_SHUTDOWN)
			goto failure;

		if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf))
			break;

		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
		err = -EAGAIN;
		if (!timeo)
			goto failure;
		if (signal_pending(current))
			goto interrupted;
		timeo = sock_wait_for_wmem(sk, timeo);
	}
	skb = alloc_skb_with_frags(header_len, data_len, max_page_order,
				   errcode, sk->sk_allocation);
	if (skb)
		skb_set_owner_w(skb, sk);
	return skb;

interrupted:
	err = sock_intr_errno(timeo);
failure:
	*errcode = err;
	return NULL;
}
EXPORT_SYMBOL(sock_alloc_send_pskb);

struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
				    int noblock, int *errcode)
{
	return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0);
}
EXPORT_SYMBOL(sock_alloc_send_skb);

int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
		     struct sockcm_cookie *sockc)
{
	u32 tsflags;

	switch (cmsg->cmsg_type) {
	case SO_MARK:
		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
			return -EPERM;
		if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
			return -EINVAL;
		sockc->mark = *(u32 *)CMSG_DATA(cmsg);
		break;
	case SO_TIMESTAMPING_OLD:
		if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
			return -EINVAL;

		tsflags = *(u32 *)CMSG_DATA(cmsg);
		if (tsflags & ~SOF_TIMESTAMPING_TX_RECORD_MASK)
			return -EINVAL;

		sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK;
		sockc->tsflags |= tsflags;
		break;
	case SCM_TXTIME:
		if (!sock_flag(sk, SOCK_TXTIME))
			return -EINVAL;
		if (cmsg->cmsg_len != CMSG_LEN(sizeof(u64)))
			return -EINVAL;
		sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg));
		break;
	/* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */
	case SCM_RIGHTS:
	case SCM_CREDENTIALS:
		break;
	default:
		return -EINVAL;
	}
	return 0;
}
EXPORT_SYMBOL(__sock_cmsg_send);

int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
		   struct sockcm_cookie *sockc)
{
	struct cmsghdr *cmsg;
	int ret;

	for_each_cmsghdr(cmsg, msg) {
		if (!CMSG_OK(msg, cmsg))
			return -EINVAL;
		if (cmsg->cmsg_level != SOL_SOCKET)
			continue;
		ret = __sock_cmsg_send(sk, msg, cmsg, sockc);
		if (ret)
			return ret;
	}
	return 0;
}
EXPORT_SYMBOL(sock_cmsg_send);

static void sk_enter_memory_pressure(struct sock *sk)
{
	if (!sk->sk_prot->enter_memory_pressure)
		return;

	sk->sk_prot->enter_memory_pressure(sk);
}

static void sk_leave_memory_pressure(struct sock *sk)
{
	if (sk->sk_prot->leave_memory_pressure) {
		sk->sk_prot->leave_memory_pressure(sk);
	} else {
		unsigned long *memory_pressure = sk->sk_prot->memory_pressure;

		if (memory_pressure && READ_ONCE(*memory_pressure))
			WRITE_ONCE(*memory_pressure, 0);
	}
}

#define SKB_FRAG_PAGE_ORDER	get_order(32768)
DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key);

/**
 * skb_page_frag_refill - check that a page_frag contains enough room
 * @sz: minimum size of the fragment we want to get
 * @pfrag: pointer to page_frag
 * @gfp: priority for memory allocation
 *
 * Note: While this allocator tries to use high order pages, there is
 * no guarantee that allocations succeed. Therefore, @sz MUST be
 * less or equal than PAGE_SIZE.
 */
bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp)
{
	if (pfrag->page) {
		if (page_ref_count(pfrag->page) == 1) {
			pfrag->offset = 0;
			return true;
		}
		if (pfrag->offset + sz <= pfrag->size)
			return true;
		put_page(pfrag->page);
	}

	pfrag->offset = 0;
	if (SKB_FRAG_PAGE_ORDER &&
	    !static_branch_unlikely(&net_high_order_alloc_disable_key)) {
		/* Avoid direct reclaim but allow kswapd to wake */
		pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) |
					  __GFP_COMP | __GFP_NOWARN |
					  __GFP_NORETRY,
					  SKB_FRAG_PAGE_ORDER);
		if (likely(pfrag->page)) {
			pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER;
			return true;
		}
	}
	pfrag->page = alloc_page(gfp);
	if (likely(pfrag->page)) {
		pfrag->size = PAGE_SIZE;
		return true;
	}
	return false;
}
EXPORT_SYMBOL(skb_page_frag_refill);

bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
{
	if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation)))
		return true;

	sk_enter_memory_pressure(sk);
	sk_stream_moderate_sndbuf(sk);
	return false;
}
EXPORT_SYMBOL(sk_page_frag_refill);

void __lock_sock(struct sock *sk)
	__releases(&sk->sk_lock.slock)
	__acquires(&sk->sk_lock.slock)
{
	DEFINE_WAIT(wait);

	for (;;) {
		prepare_to_wait_exclusive(&sk->sk_lock.wq, &wait,
					TASK_UNINTERRUPTIBLE);
		spin_unlock_bh(&sk->sk_lock.slock);
		schedule();
		spin_lock_bh(&sk->sk_lock.slock);
		if (!sock_owned_by_user(sk))
			break;
	}
	finish_wait(&sk->sk_lock.wq, &wait);
}

void __release_sock(struct sock *sk)
	__releases(&sk->sk_lock.slock)
	__acquires(&sk->sk_lock.slock)
{
	struct sk_buff *skb, *next;

	while ((skb = sk->sk_backlog.head) != NULL) {
		sk->sk_backlog.head = sk->sk_backlog.tail = NULL;

		spin_unlock_bh(&sk->sk_lock.slock);

		do {
			next = skb->next;
			prefetch(next);
			WARN_ON_ONCE(skb_dst_is_noref(skb));
			skb_mark_not_on_list(skb);
			sk_backlog_rcv(sk, skb);

			cond_resched();

			skb = next;
		} while (skb != NULL);

		spin_lock_bh(&sk->sk_lock.slock);
	}

	/*
	 * Doing the zeroing here guarantee we can not loop forever
	 * while a wild producer attempts to flood us.
	 */
	sk->sk_backlog.len = 0;
}

void __sk_flush_backlog(struct sock *sk)
{
	spin_lock_bh(&sk->sk_lock.slock);
	__release_sock(sk);
	spin_unlock_bh(&sk->sk_lock.slock);
}

/**
 * sk_wait_data - wait for data to arrive at sk_receive_queue
 * @sk:    sock to wait on
 * @timeo: for how long
 * @skb:   last skb seen on sk_receive_queue
 *
 * Now socket state including sk->sk_err is changed only under lock,
 * hence we may omit checks after joining wait queue.
 * We check receive queue before schedule() only as optimization;
 * it is very likely that release_sock() added new data.
 */
int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
{
	DEFINE_WAIT_FUNC(wait, woken_wake_function);
	int rc;

	add_wait_queue(sk_sleep(sk), &wait);
	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
	rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb, &wait);
	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
	remove_wait_queue(sk_sleep(sk), &wait);
	return rc;
}
EXPORT_SYMBOL(sk_wait_data);

/**
 *	__sk_mem_raise_allocated - increase memory_allocated
 *	@sk: socket
 *	@size: memory size to allocate
 *	@amt: pages to allocate
 *	@kind: allocation type
 *
 *	Similar to __sk_mem_schedule(), but does not update sk_forward_alloc
 */
int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind)
{
	struct proto *prot = sk->sk_prot;
	long allocated = sk_memory_allocated_add(sk, amt);
	bool charged = true;

	if (mem_cgroup_sockets_enabled && sk->sk_memcg &&
	    !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt)))
		goto suppress_allocation;

	/* Under limit. */
	if (allocated <= sk_prot_mem_limits(sk, 0)) {
		sk_leave_memory_pressure(sk);
		return 1;
	}

	/* Under pressure. */
	if (allocated > sk_prot_mem_limits(sk, 1))
		sk_enter_memory_pressure(sk);

	/* Over hard limit. */
	if (allocated > sk_prot_mem_limits(sk, 2))
		goto suppress_allocation;

	/* guarantee minimum buffer size under pressure */
	if (kind == SK_MEM_RECV) {
		if (atomic_read(&sk->sk_rmem_alloc) < sk_get_rmem0(sk, prot))
			return 1;

	} else { /* SK_MEM_SEND */
		int wmem0 = sk_get_wmem0(sk, prot);

		if (sk->sk_type == SOCK_STREAM) {
			if (sk->sk_wmem_queued < wmem0)
				return 1;
		} else if (refcount_read(&sk->sk_wmem_alloc) < wmem0) {
				return 1;
		}
	}

	if (sk_has_memory_pressure(sk)) {
		u64 alloc;

		if (!sk_under_memory_pressure(sk))
			return 1;
		alloc = sk_sockets_allocated_read_positive(sk);
		if (sk_prot_mem_limits(sk, 2) > alloc *
		    sk_mem_pages(sk->sk_wmem_queued +
				 atomic_read(&sk->sk_rmem_alloc) +
				 sk->sk_forward_alloc))
			return 1;
	}

suppress_allocation:

	if (kind == SK_MEM_SEND && sk->sk_type == SOCK_STREAM) {
		sk_stream_moderate_sndbuf(sk);

		/* Fail only if socket is _under_ its sndbuf.
		 * In this case we cannot block, so that we have to fail.
		 */
		if (sk->sk_wmem_queued + size >= sk->sk_sndbuf)
			return 1;
	}

	if (kind == SK_MEM_SEND || (kind == SK_MEM_RECV && charged))
		trace_sock_exceed_buf_limit(sk, prot, allocated, kind);

	sk_memory_allocated_sub(sk, amt);

	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
		mem_cgroup_uncharge_skmem(sk->sk_memcg, amt);

	return 0;
}
EXPORT_SYMBOL(__sk_mem_raise_allocated);

/**
 *	__sk_mem_schedule - increase sk_forward_alloc and memory_allocated
 *	@sk: socket
 *	@size: memory size to allocate
 *	@kind: allocation type
 *
 *	If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means
 *	rmem allocation. This function assumes that protocols which have
 *	memory_pressure use sk_wmem_queued as write buffer accounting.
 */
int __sk_mem_schedule(struct sock *sk, int size, int kind)
{
	int ret, amt = sk_mem_pages(size);

	sk->sk_forward_alloc += amt << SK_MEM_QUANTUM_SHIFT;
	ret = __sk_mem_raise_allocated(sk, size, amt, kind);
	if (!ret)
		sk->sk_forward_alloc -= amt << SK_MEM_QUANTUM_SHIFT;
	return ret;
}
EXPORT_SYMBOL(__sk_mem_schedule);

/**
 *	__sk_mem_reduce_allocated - reclaim memory_allocated
 *	@sk: socket
 *	@amount: number of quanta
 *
 *	Similar to __sk_mem_reclaim(), but does not update sk_forward_alloc
 */
void __sk_mem_reduce_allocated(struct sock *sk, int amount)
{
	sk_memory_allocated_sub(sk, amount);

	if (mem_cgroup_sockets_enabled && sk->sk_memcg)
		mem_cgroup_uncharge_skmem(sk->sk_memcg, amount);

	if (sk_under_memory_pressure(sk) &&
	    (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
		sk_leave_memory_pressure(sk);
}
EXPORT_SYMBOL(__sk_mem_reduce_allocated);

/**
 *	__sk_mem_reclaim - reclaim sk_forward_alloc and memory_allocated
 *	@sk: socket
 *	@amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple)
 */
void __sk_mem_reclaim(struct sock *sk, int amount)
{
	amount >>= SK_MEM_QUANTUM_SHIFT;
	sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT;
	__sk_mem_reduce_allocated(sk, amount);
}
EXPORT_SYMBOL(__sk_mem_reclaim);

int sk_set_peek_off(struct sock *sk, int val)
{
	sk->sk_peek_off = val;
	return 0;
}
EXPORT_SYMBOL_GPL(sk_set_peek_off);

/*
 * Set of default routines for initialising struct proto_ops when
 * the protocol does not support a particular function. In certain
 * cases where it makes no sense for a protocol to have a "do nothing"
 * function, some default processing is provided.
 */

int sock_no_bind(struct socket *sock, struct sockaddr *saddr, int len)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_bind);

int sock_no_connect(struct socket *sock, struct sockaddr *saddr,
		    int len, int flags)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_connect);

int sock_no_socketpair(struct socket *sock1, struct socket *sock2)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_socketpair);

int sock_no_accept(struct socket *sock, struct socket *newsock, int flags,
		   bool kern)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_accept);

int sock_no_getname(struct socket *sock, struct sockaddr *saddr,
		    int peer)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_getname);

int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_ioctl);

int sock_no_listen(struct socket *sock, int backlog)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_listen);

int sock_no_shutdown(struct socket *sock, int how)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_shutdown);

int sock_no_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_sendmsg);

int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *m, size_t len)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_sendmsg_locked);

int sock_no_recvmsg(struct socket *sock, struct msghdr *m, size_t len,
		    int flags)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_recvmsg);

int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma)
{
	/* Mirror missing mmap method error code */
	return -ENODEV;
}
EXPORT_SYMBOL(sock_no_mmap);

/*
 * When a file is received (via SCM_RIGHTS, etc), we must bump the
 * various sock-based usage counts.
 */
void __receive_sock(struct file *file)
{
	struct socket *sock;

	sock = sock_from_file(file);
	if (sock) {
		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
		sock_update_classid(&sock->sk->sk_cgrp_data);
	}
}

ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags)
{
	ssize_t res;
	struct msghdr msg = {.msg_flags = flags};
	struct kvec iov;
	char *kaddr = kmap(page);
	iov.iov_base = kaddr + offset;
	iov.iov_len = size;
	res = kernel_sendmsg(sock, &msg, &iov, 1, size);
	kunmap(page);
	return res;
}
EXPORT_SYMBOL(sock_no_sendpage);

ssize_t sock_no_sendpage_locked(struct sock *sk, struct page *page,
				int offset, size_t size, int flags)
{
	ssize_t res;
	struct msghdr msg = {.msg_flags = flags};
	struct kvec iov;
	char *kaddr = kmap(page);

	iov.iov_base = kaddr + offset;
	iov.iov_len = size;
	res = kernel_sendmsg_locked(sk, &msg, &iov, 1, size);
	kunmap(page);
	return res;
}
EXPORT_SYMBOL(sock_no_sendpage_locked);

/*
 *	Default Socket Callbacks
 */

static void sock_def_wakeup(struct sock *sk)
{
	struct socket_wq *wq;

	rcu_read_lock();
	wq = rcu_dereference(sk->sk_wq);
	if (skwq_has_sleeper(wq))
		wake_up_interruptible_all(&wq->wait);
	rcu_read_unlock();
}

static void sock_def_error_report(struct sock *sk)
{
	struct socket_wq *wq;

	rcu_read_lock();
	wq = rcu_dereference(sk->sk_wq);
	if (skwq_has_sleeper(wq))
		wake_up_interruptible_poll(&wq->wait, EPOLLERR);
	sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
	rcu_read_unlock();
}

void sock_def_readable(struct sock *sk)
{
	struct socket_wq *wq;

	rcu_read_lock();
	wq = rcu_dereference(sk->sk_wq);
	if (skwq_has_sleeper(wq))
		wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI |
						EPOLLRDNORM | EPOLLRDBAND);
	sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
	rcu_read_unlock();
}

static void sock_def_write_space(struct sock *sk)
{
	struct socket_wq *wq;

	rcu_read_lock();

	/* Do not wake up a writer until he can make "significant"
	 * progress.  --DaveM
	 */
	if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) {
		wq = rcu_dereference(sk->sk_wq);
		if (skwq_has_sleeper(wq))
			wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
						EPOLLWRNORM | EPOLLWRBAND);

		/* Should agree with poll, otherwise some programs break */
		if (sock_writeable(sk))
			sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
	}

	rcu_read_unlock();
}

static void sock_def_destruct(struct sock *sk)
{
}

void sk_send_sigurg(struct sock *sk)
{
	if (sk->sk_socket && sk->sk_socket->file)
		if (send_sigurg(&sk->sk_socket->file->f_owner))
			sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI);
}
EXPORT_SYMBOL(sk_send_sigurg);

void sk_reset_timer(struct sock *sk, struct timer_list* timer,
		    unsigned long expires)
{
	if (!mod_timer(timer, expires))
		sock_hold(sk);
}
EXPORT_SYMBOL(sk_reset_timer);

void sk_stop_timer(struct sock *sk, struct timer_list* timer)
{
	if (del_timer(timer))
		__sock_put(sk);
}
EXPORT_SYMBOL(sk_stop_timer);

void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer)
{
	if (del_timer_sync(timer))
		__sock_put(sk);
}
EXPORT_SYMBOL(sk_stop_timer_sync);