sock.h

	if (skb_get_dst_pending_confirm(skb)) {
		struct sock *sk = skb->sk;
		unsigned long now = jiffies;

		/* avoid dirtying neighbour */
		if (READ_ONCE(n->confirmed) != now)
			WRITE_ONCE(n->confirmed, now);
		if (sk && READ_ONCE(sk->sk_dst_pending_confirm))
			WRITE_ONCE(sk->sk_dst_pending_confirm, 0);
	}
}

bool sk_mc_loop(struct sock *sk);

static inline bool sk_can_gso(const struct sock *sk)
{
	return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type);
}

void sk_setup_caps(struct sock *sk, struct dst_entry *dst);

static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags)
{
	sk->sk_route_nocaps |= flags;
	sk->sk_route_caps &= ~flags;
}

static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb,
					   struct iov_iter *from, char *to,
					   int copy, int offset)
{
	if (skb->ip_summed == CHECKSUM_NONE) {
		__wsum csum = 0;
		if (!csum_and_copy_from_iter_full(to, copy, &csum, from))
			return -EFAULT;
		skb->csum = csum_block_add(skb->csum, csum, offset);
	} else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) {
		if (!copy_from_iter_full_nocache(to, copy, from))
			return -EFAULT;
	} else if (!copy_from_iter_full(to, copy, from))
		return -EFAULT;

	return 0;
}

static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb,
				       struct iov_iter *from, int copy)
{
	int err, offset = skb->len;

	err = skb_do_copy_data_nocache(sk, skb, from, skb_put(skb, copy),
				       copy, offset);
	if (err)
		__skb_trim(skb, offset);

	return err;
}

static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *from,
					   struct sk_buff *skb,
					   struct page *page,
					   int off, int copy)
{
	int err;

	err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + off,
				       copy, skb->len);
	if (err)
		return err;

	skb->len	     += copy;
	skb->data_len	     += copy;
	skb->truesize	     += copy;
	sk_wmem_queued_add(sk, copy);
	sk_mem_charge(sk, copy);
	return 0;
}

/**
 * sk_wmem_alloc_get - returns write allocations
 * @sk: socket
 *
 * Return: sk_wmem_alloc minus initial offset of one
 */
static inline int sk_wmem_alloc_get(const struct sock *sk)
{
	return refcount_read(&sk->sk_wmem_alloc) - 1;
}

/**
 * sk_rmem_alloc_get - returns read allocations
 * @sk: socket
 *
 * Return: sk_rmem_alloc
 */
static inline int sk_rmem_alloc_get(const struct sock *sk)
{
	return atomic_read(&sk->sk_rmem_alloc);
}

/**
 * sk_has_allocations - check if allocations are outstanding
 * @sk: socket
 *
 * Return: true if socket has write or read allocations
 */
static inline bool sk_has_allocations(const struct sock *sk)
{
	return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk);
}

/**
 * skwq_has_sleeper - check if there are any waiting processes
 * @wq: struct socket_wq
 *
 * Return: true if socket_wq has waiting processes
 *
 * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory
 * barrier call. They were added due to the race found within the tcp code.
 *
 * Consider following tcp code paths::
 *
 *   CPU1                CPU2
 *   sys_select          receive packet
 *   ...                 ...
 *   __add_wait_queue    update tp->rcv_nxt
 *   ...                 ...
 *   tp->rcv_nxt check   sock_def_readable
 *   ...                 {
 *   schedule               rcu_read_lock();
 *                          wq = rcu_dereference(sk->sk_wq);
 *                          if (wq && waitqueue_active(&wq->wait))
 *                              wake_up_interruptible(&wq->wait)
 *                          ...
 *                       }
 *
 * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay
 * in its cache, and so does the tp->rcv_nxt update on CPU2 side.  The CPU1
 * could then endup calling schedule and sleep forever if there are no more
 * data on the socket.
 *
 */
static inline bool skwq_has_sleeper(struct socket_wq *wq)
{
	return wq && wq_has_sleeper(&wq->wait);
}

/**
 * sock_poll_wait - place memory barrier behind the poll_wait call.
 * @filp:           file
 * @sock:           socket to wait on
 * @p:              poll_table
 *
 * See the comments in the wq_has_sleeper function.
 */
static inline void sock_poll_wait(struct file *filp, struct socket *sock,
				  poll_table *p)
{
	if (!poll_does_not_wait(p)) {
		poll_wait(filp, &sock->wq.wait, p);
		/* We need to be sure we are in sync with the
		 * socket flags modification.
		 *
		 * This memory barrier is paired in the wq_has_sleeper.
		 */
		smp_mb();
	}
}

static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk)
{
	if (sk->sk_txhash) {
		skb->l4_hash = 1;
		skb->hash = sk->sk_txhash;
	}
}

void skb_set_owner_w(struct sk_buff *skb, struct sock *sk);

/*
 *	Queue a received datagram if it will fit. Stream and sequenced
 *	protocols can't normally use this as they need to fit buffers in
 *	and play with them.
 *
 *	Inlined as it's very short and called for pretty much every
 *	packet ever received.
 */
static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
{
	skb_orphan(skb);
	skb->sk = sk;
	skb->destructor = sock_rfree;
	atomic_add(skb->truesize, &sk->sk_rmem_alloc);
	sk_mem_charge(sk, skb->truesize);
}

void sk_reset_timer(struct sock *sk, struct timer_list *timer,
		    unsigned long expires);

void sk_stop_timer(struct sock *sk, struct timer_list *timer);

void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer);

int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue,
			struct sk_buff *skb, unsigned int flags,
			void (*destructor)(struct sock *sk,
					   struct sk_buff *skb));
int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);

int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb);
struct sk_buff *sock_dequeue_err_skb(struct sock *sk);

/*
 *	Recover an error report and clear atomically
 */

static inline int sock_error(struct sock *sk)
{
	int err;
	if (likely(!sk->sk_err))
		return 0;
	err = xchg(&sk->sk_err, 0);
	return -err;
}

static inline unsigned long sock_wspace(struct sock *sk)
{
	int amt = 0;

	if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
		amt = sk->sk_sndbuf - refcount_read(&sk->sk_wmem_alloc);
		if (amt < 0)
			amt = 0;
	}
	return amt;
}

/* Note:
 *  We use sk->sk_wq_raw, from contexts knowing this
 *  pointer is not NULL and cannot disappear/change.
 */
static inline void sk_set_bit(int nr, struct sock *sk)
{
	if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) &&
	    !sock_flag(sk, SOCK_FASYNC))
		return;

	set_bit(nr, &sk->sk_wq_raw->flags);
}

static inline void sk_clear_bit(int nr, struct sock *sk)
{
	if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) &&
	    !sock_flag(sk, SOCK_FASYNC))
		return;

	clear_bit(nr, &sk->sk_wq_raw->flags);
}

static inline void sk_wake_async(const struct sock *sk, int how, int band)
{
	if (sock_flag(sk, SOCK_FASYNC)) {
		rcu_read_lock();
		sock_wake_async(rcu_dereference(sk->sk_wq), how, band);
		rcu_read_unlock();
	}
}

/* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might
 * need sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak.
 * Note: for send buffers, TCP works better if we can build two skbs at
 * minimum.
 */
#define TCP_SKB_MIN_TRUESIZE	(2048 + SKB_DATA_ALIGN(sizeof(struct sk_buff)))

#define SOCK_MIN_SNDBUF		(TCP_SKB_MIN_TRUESIZE * 2)
#define SOCK_MIN_RCVBUF		 TCP_SKB_MIN_TRUESIZE

static inline void sk_stream_moderate_sndbuf(struct sock *sk)
{
	u32 val;

	if (sk->sk_userlocks & SOCK_SNDBUF_LOCK)
		return;

	val = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1);

	WRITE_ONCE(sk->sk_sndbuf, max_t(u32, val, SOCK_MIN_SNDBUF));
}

struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
				    bool force_schedule);

/**
 * sk_page_frag - return an appropriate page_frag
 * @sk: socket
 *
 * Use the per task page_frag instead of the per socket one for
 * optimization when we know that we're in the normal context and owns
 * everything that's associated with %current.
 *
 * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest
 * inside other socket operations and end up recursing into sk_page_frag()
 * while it's already in use.
 *
 * Return: a per task page_frag if context allows that,
 * otherwise a per socket one.
 */
static inline struct page_frag *sk_page_frag(struct sock *sk)
{
	if (gfpflags_normal_context(sk->sk_allocation))
		return &current->task_frag;

	return &sk->sk_frag;
}

bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag);

/*
 *	Default write policy as shown to user space via poll/select/SIGIO
 */
static inline bool sock_writeable(const struct sock *sk)
{
	return refcount_read(&sk->sk_wmem_alloc) < (READ_ONCE(sk->sk_sndbuf) >> 1);
}

static inline gfp_t gfp_any(void)
{
	return in_softirq() ? GFP_ATOMIC : GFP_KERNEL;
}

static inline long sock_rcvtimeo(const struct sock *sk, bool noblock)
{
	return noblock ? 0 : sk->sk_rcvtimeo;
}

static inline long sock_sndtimeo(const struct sock *sk, bool noblock)
{
	return noblock ? 0 : sk->sk_sndtimeo;
}

static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len)
{
	int v = waitall ? len : min_t(int, READ_ONCE(sk->sk_rcvlowat), len);

	return v ?: 1;
}

/* Alas, with timeout socket operations are not restartable.
 * Compare this to poll().
 */
static inline int sock_intr_errno(long timeo)
{
	return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR;
}

struct sock_skb_cb {
	u32 dropcount;
};

/* Store sock_skb_cb at the end of skb->cb[] so protocol families
 * using skb->cb[] would keep using it directly and utilize its
 * alignement guarantee.
 */
#define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \
			    sizeof(struct sock_skb_cb)))

#define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \
			    SOCK_SKB_CB_OFFSET))

#define sock_skb_cb_check_size(size) \
	BUILD_BUG_ON((size) > SOCK_SKB_CB_OFFSET)

static inline void
sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb)
{
	SOCK_SKB_CB(skb)->dropcount = sock_flag(sk, SOCK_RXQ_OVFL) ?
						atomic_read(&sk->sk_drops) : 0;
}

static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb)
{
	int segs = max_t(u16, 1, skb_shinfo(skb)->gso_segs);

	atomic_add(segs, &sk->sk_drops);
}

static inline ktime_t sock_read_timestamp(struct sock *sk)
{
#if BITS_PER_LONG==32
	unsigned int seq;
	ktime_t kt;

	do {
		seq = read_seqbegin(&sk->sk_stamp_seq);
		kt = sk->sk_stamp;
	} while (read_seqretry(&sk->sk_stamp_seq, seq));

	return kt;
#else
	return READ_ONCE(sk->sk_stamp);
#endif
}

static inline void sock_write_timestamp(struct sock *sk, ktime_t kt)
{
#if BITS_PER_LONG==32
	write_seqlock(&sk->sk_stamp_seq);
	sk->sk_stamp = kt;
	write_sequnlock(&sk->sk_stamp_seq);
#else
	WRITE_ONCE(sk->sk_stamp, kt);
#endif
}

void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
			   struct sk_buff *skb);
void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
			     struct sk_buff *skb);

static inline void
sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
{
	ktime_t kt = skb->tstamp;
	struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb);

	/*
	 * generate control messages if
	 * - receive time stamping in software requested
	 * - software time stamp available and wanted
	 * - hardware time stamps available and wanted
	 */
	if (sock_flag(sk, SOCK_RCVTSTAMP) ||
	    (sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) ||
	    (kt && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) ||
	    (hwtstamps->hwtstamp &&
	     (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
		__sock_recv_timestamp(msg, sk, skb);
	else
		sock_write_timestamp(sk, kt);

	if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid)
		__sock_recv_wifi_status(msg, sk, skb);
}

void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
			      struct sk_buff *skb);

#define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC)
static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
					  struct sk_buff *skb)
{
#define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL)			| \
			   (1UL << SOCK_RCVTSTAMP))
#define TSFLAGS_ANY	  (SOF_TIMESTAMPING_SOFTWARE			| \
			   SOF_TIMESTAMPING_RAW_HARDWARE)

	if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
		__sock_recv_ts_and_drops(msg, sk, skb);
	else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
		sock_write_timestamp(sk, skb->tstamp);
	else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP))
		sock_write_timestamp(sk, 0);
}

void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags);

/**
 * _sock_tx_timestamp - checks whether the outgoing packet is to be time stamped
 * @sk:		socket sending this packet
 * @tsflags:	timestamping flags to use
 * @tx_flags:	completed with instructions for time stamping
 * @tskey:      filled in with next sk_tskey (not for TCP, which uses seqno)
 *
 * Note: callers should take care of initial ``*tx_flags`` value (usually 0)
 */
static inline void _sock_tx_timestamp(struct sock *sk, __u16 tsflags,
				      __u8 *tx_flags, __u32 *tskey)
{
	if (unlikely(tsflags)) {
		__sock_tx_timestamp(tsflags, tx_flags);
		if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey &&
		    tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK)
			*tskey = sk->sk_tskey++;
	}
	if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS)))
		*tx_flags |= SKBTX_WIFI_STATUS;
}

static inline void sock_tx_timestamp(struct sock *sk, __u16 tsflags,
				     __u8 *tx_flags)
{
	_sock_tx_timestamp(sk, tsflags, tx_flags, NULL);
}

static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags)
{
	_sock_tx_timestamp(skb->sk, tsflags, &skb_shinfo(skb)->tx_flags,
			   &skb_shinfo(skb)->tskey);
}

DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
/**
 * sk_eat_skb - Release a skb if it is no longer needed
 * @sk: socket to eat this skb from
 * @skb: socket buffer to eat
 *
 * This routine must be called with interrupts disabled or with the socket
 * locked so that the sk_buff queue operation is ok.
*/
static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb)
{
	__skb_unlink(skb, &sk->sk_receive_queue);
	if (static_branch_unlikely(&tcp_rx_skb_cache_key) &&
	    !sk->sk_rx_skb_cache) {
		sk->sk_rx_skb_cache = skb;
		skb_orphan(skb);
		return;
	}
	__kfree_skb(skb);
}

static inline
struct net *sock_net(const struct sock *sk)
{
	return read_pnet(&sk->sk_net);
}

static inline
void sock_net_set(struct sock *sk, struct net *net)
{
	write_pnet(&sk->sk_net, net);
}

static inline bool
skb_sk_is_prefetched(struct sk_buff *skb)
{
#ifdef CONFIG_INET
	return skb->destructor == sock_pfree;
#else
	return false;
#endif /* CONFIG_INET */
}

/* This helper checks if a socket is a full socket,
 * ie _not_ a timewait or request socket.
 */
static inline bool sk_fullsock(const struct sock *sk)
{
	return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV);
}

static inline bool
sk_is_refcounted(struct sock *sk)
{
	/* Only full sockets have sk->sk_flags. */
	return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE);
}

/**
 * skb_steal_sock - steal a socket from an sk_buff
 * @skb: sk_buff to steal the socket from
 * @refcounted: is set to true if the socket is reference-counted
 */
static inline struct sock *
skb_steal_sock(struct sk_buff *skb, bool *refcounted)
{
	if (skb->sk) {
		struct sock *sk = skb->sk;

		*refcounted = true;
		if (skb_sk_is_prefetched(skb))
			*refcounted = sk_is_refcounted(sk);
		skb->destructor = NULL;
		skb->sk = NULL;
		return sk;
	}
	*refcounted = false;
	return NULL;
}

/* Checks if this SKB belongs to an HW offloaded socket
 * and whether any SW fallbacks are required based on dev.
 * Check decrypted mark in case skb_orphan() cleared socket.
 */
static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb,
						   struct net_device *dev)
{
#ifdef CONFIG_SOCK_VALIDATE_XMIT
	struct sock *sk = skb->sk;

	if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) {
		skb = sk->sk_validate_xmit_skb(sk, dev, skb);
#ifdef CONFIG_TLS_DEVICE
	} else if (unlikely(skb->decrypted)) {
		pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n");
		kfree_skb(skb);
		skb = NULL;
#endif
	}
#endif

	return skb;
}

/* This helper checks if a socket is a LISTEN or NEW_SYN_RECV
 * SYNACK messages can be attached to either ones (depending on SYNCOOKIE)
 */
static inline bool sk_listener(const struct sock *sk)
{
	return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV);
}

void sock_enable_timestamp(struct sock *sk, enum sock_flags flag);
int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level,
		       int type);

bool sk_ns_capable(const struct sock *sk,
		   struct user_namespace *user_ns, int cap);
bool sk_capable(const struct sock *sk, int cap);
bool sk_net_capable(const struct sock *sk, int cap);

void sk_get_meminfo(const struct sock *sk, u32 *meminfo);

/* Take into consideration the size of the struct sk_buff overhead in the
 * determination of these values, since that is non-constant across
 * platforms.  This makes socket queueing behavior and performance
 * not depend upon such differences.
 */
#define _SK_MEM_PACKETS		256
#define _SK_MEM_OVERHEAD	SKB_TRUESIZE(256)
#define SK_WMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
#define SK_RMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)

extern __u32 sysctl_wmem_max;
extern __u32 sysctl_rmem_max;

extern int sysctl_tstamp_allow_data;
extern int sysctl_optmem_max;

extern __u32 sysctl_wmem_default;
extern __u32 sysctl_rmem_default;

DECLARE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key);

static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto)
{
	/* Does this proto have per netns sysctl_wmem ? */
	if (proto->sysctl_wmem_offset)
		return *(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset);

	return *proto->sysctl_wmem;
}

static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto)
{
	/* Does this proto have per netns sysctl_rmem ? */
	if (proto->sysctl_rmem_offset)
		return *(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset);

	return *proto->sysctl_rmem;
}

/* Default TCP Small queue budget is ~1 ms of data (1sec >> 10)
 * Some wifi drivers need to tweak it to get more chunks.
 * They can use this helper from their ndo_start_xmit()
 */
static inline void sk_pacing_shift_update(struct sock *sk, int val)
{
	if (!sk || !sk_fullsock(sk) || READ_ONCE(sk->sk_pacing_shift) == val)
		return;
	WRITE_ONCE(sk->sk_pacing_shift, val);
}

/* if a socket is bound to a device, check that the given device
 * index is either the same or that the socket is bound to an L3
 * master device and the given device index is also enslaved to
 * that L3 master
 */
static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif)
{
	int mdif;

	if (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif)
		return true;

	mdif = l3mdev_master_ifindex_by_index(sock_net(sk), dif);
	if (mdif && mdif == sk->sk_bound_dev_if)
		return true;

	return false;
}

void sock_def_readable(struct sock *sk);

int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk);
void sock_enable_timestamps(struct sock *sk);
void sock_no_linger(struct sock *sk);
void sock_set_keepalive(struct sock *sk);
void sock_set_priority(struct sock *sk, u32 priority);
void sock_set_rcvbuf(struct sock *sk, int val);
void sock_set_mark(struct sock *sk, u32 val);
void sock_set_reuseaddr(struct sock *sk);
void sock_set_reuseport(struct sock *sk);
void sock_set_sndtimeo(struct sock *sk, s64 secs);

int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len);

#endif	/* _SOCK_H */