sock.c

linux 内核源代码

EXPORT_SYMBOL_GPL(sk_clone);

void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
{
	__sk_dst_set(sk, dst);
	sk->sk_route_caps = dst->dev->features;
	if (sk->sk_route_caps & NETIF_F_GSO)
		sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
	if (sk_can_gso(sk)) {
		if (dst->header_len)
			sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
		else
			sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
	}
}
EXPORT_SYMBOL_GPL(sk_setup_caps);

void __init sk_init(void)
{
	if (num_physpages <= 4096) {
		sysctl_wmem_max = 32767;
		sysctl_rmem_max = 32767;
		sysctl_wmem_default = 32767;
		sysctl_rmem_default = 32767;
	} else if (num_physpages >= 131072) {
		sysctl_wmem_max = 131071;
		sysctl_rmem_max = 131071;
	}
}

/*
 *	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;

	/* In case it might be waiting for more memory. */
	atomic_sub(skb->truesize, &sk->sk_wmem_alloc);
	if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE))
		sk->sk_write_space(sk);
	sock_put(sk);
}

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

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


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

	read_lock(&sk->sk_callback_lock);
	uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0;
	read_unlock(&sk->sk_callback_lock);
	return uid;
}

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

	read_lock(&sk->sk_callback_lock);
	ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
	read_unlock(&sk->sk_callback_lock);
	return 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 || atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
		struct sk_buff * skb = alloc_skb(size, priority);
		if (skb) {
			skb_set_owner_w(skb, sk);
			return skb;
		}
	}
	return NULL;
}

/*
 * Allocate a skb from the socket's receive buffer.
 */
struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force,
			     gfp_t priority)
{
	if (force || atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) {
		struct sk_buff *skb = alloc_skb(size, priority);
		if (skb) {
			skb_set_owner_r(skb, sk);
			return skb;
		}
	}
	return NULL;
}

/*
 * Allocate a memory block from the socket's option memory buffer.
 */
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
{
	if ((unsigned)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;
}

/*
 * Free an option memory block.
 */
void sock_kfree_s(struct sock *sk, void *mem, int size)
{
	kfree(mem);
	atomic_sub(size, &sk->sk_omem_alloc);
}

/* 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);

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


/*
 *	Generic send/receive buffer handlers
 */

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

	gfp_mask = sk->sk_allocation;
	if (gfp_mask & __GFP_WAIT)
		gfp_mask |= __GFP_REPEAT;

	timeo = sock_sndtimeo(sk, noblock);
	while (1) {
		err = sock_error(sk);
		if (err != 0)
			goto failure;

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

		if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
			skb = alloc_skb(header_len, gfp_mask);
			if (skb) {
				int npages;
				int i;

				/* No pages, we're done... */
				if (!data_len)
					break;

				npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
				skb->truesize += data_len;
				skb_shinfo(skb)->nr_frags = npages;
				for (i = 0; i < npages; i++) {
					struct page *page;
					skb_frag_t *frag;

					page = alloc_pages(sk->sk_allocation, 0);
					if (!page) {
						err = -ENOBUFS;
						skb_shinfo(skb)->nr_frags = i;
						kfree_skb(skb);
						goto failure;
					}

					frag = &skb_shinfo(skb)->frags[i];
					frag->page = page;
					frag->page_offset = 0;
					frag->size = (data_len >= PAGE_SIZE ?
						      PAGE_SIZE :
						      data_len);
					data_len -= PAGE_SIZE;
				}

				/* Full success... */
				break;
			}
			err = -ENOBUFS;
			goto failure;
		}
		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
		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_set_owner_w(skb, sk);
	return skb;

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

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);
}

static void __lock_sock(struct sock *sk)
{
	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);
}

static void __release_sock(struct sock *sk)
{
	struct sk_buff *skb = sk->sk_backlog.head;

	do {
		sk->sk_backlog.head = sk->sk_backlog.tail = NULL;
		bh_unlock_sock(sk);

		do {
			struct sk_buff *next = skb->next;

			skb->next = NULL;
			sk->sk_backlog_rcv(sk, skb);

			/*
			 * We are in process context here with softirqs
			 * disabled, use cond_resched_softirq() to preempt.
			 * This is safe to do because we've taken the backlog
			 * queue private:
			 */
			cond_resched_softirq();

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

		bh_lock_sock(sk);
	} while ((skb = sk->sk_backlog.head) != NULL);
}

/**
 * sk_wait_data - wait for data to arrive at sk_receive_queue
 * @sk:    sock to wait on
 * @timeo: for how long
 *
 * 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)
{
	int rc;
	DEFINE_WAIT(wait);

	prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
	set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
	rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue));
	clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
	finish_wait(sk->sk_sleep, &wait);
	return rc;
}

EXPORT_SYMBOL(sk_wait_data);

/*
 * 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;
}

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

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

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

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

unsigned int sock_no_poll(struct file * file, struct socket *sock, poll_table *pt)
{
	return 0;
}

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

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

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

int sock_no_setsockopt(struct socket *sock, int level, int optname,
		    char __user *optval, int optlen)
{
	return -EOPNOTSUPP;
}

int sock_no_getsockopt(struct socket *sock, int level, int optname,
		    char __user *optval, int __user *optlen)
{
	return -EOPNOTSUPP;
}

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

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

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

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;
}

/*
 *	Default Socket Callbacks
 */

static void sock_def_wakeup(struct sock *sk)
{
	read_lock(&sk->sk_callback_lock);
	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
		wake_up_interruptible_all(sk->sk_sleep);
	read_unlock(&sk->sk_callback_lock);
}

static void sock_def_error_report(struct sock *sk)
{
	read_lock(&sk->sk_callback_lock);
	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
		wake_up_interruptible(sk->sk_sleep);
	sk_wake_async(sk,0,POLL_ERR);
	read_unlock(&sk->sk_callback_lock);
}

static void sock_def_readable(struct sock *sk, int len)
{
	read_lock(&sk->sk_callback_lock);
	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
		wake_up_interruptible(sk->sk_sleep);
	sk_wake_async(sk,1,POLL_IN);
	read_unlock(&sk->sk_callback_lock);
}

static void sock_def_write_space(struct sock *sk)
{
	read_lock(&sk->sk_callback_lock);

	/* Do not wake up a writer until he can make "significant"
	 * progress.  --DaveM
	 */
	if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
		if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
			wake_up_interruptible(sk->sk_sleep);

		/* Should agree with poll, otherwise some programs break */
		if (sock_writeable(sk))
			sk_wake_async(sk, 2, POLL_OUT);
	}

	read_unlock(&sk->sk_callback_lock);
}

static void sock_def_destruct(struct sock *sk)
{
	kfree(sk->sk_protinfo);
}

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, 3, POLL_PRI);
}

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 (timer_pending(timer) && del_timer(timer))
		__sock_put(sk);
}

EXPORT_SYMBOL(sk_stop_timer);

void sock_init_data(struct socket *sock, struct sock *sk)
{
	skb_queue_head_init(&sk->sk_receive_queue);
	skb_queue_head_init(&sk->sk_write_queue);
	skb_queue_head_init(&sk->sk_error_queue);
#ifdef CONFIG_NET_DMA
	skb_queue_head_init(&sk->sk_async_wait_queue);
#endif

	sk->sk_send_head	=	NULL;

	init_timer(&sk->sk_timer);

	sk->sk_allocation	=	GFP_KERNEL;
	sk->sk_rcvbuf		=	sysctl_rmem_default;
	sk->sk_sndbuf		=	sysctl_wmem_default;