svcsock.c

linux 内核源代码

svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr)
{
	struct svc_sock	*svsk = rqstp->rq_sock;
	struct socket	*sock = svsk->sk_sock;
	int		slen;
	union {
		struct cmsghdr	hdr;
		long		all[SVC_PKTINFO_SPACE / sizeof(long)];
	} buffer;
	struct cmsghdr *cmh = &buffer.hdr;
	int		len = 0;
	int		result;
	int		size;
	struct page	**ppage = xdr->pages;
	size_t		base = xdr->page_base;
	unsigned int	pglen = xdr->page_len;
	unsigned int	flags = MSG_MORE;
	char		buf[RPC_MAX_ADDRBUFLEN];

	slen = xdr->len;

	if (rqstp->rq_prot == IPPROTO_UDP) {
		struct msghdr msg = {
			.msg_name	= &rqstp->rq_addr,
			.msg_namelen	= rqstp->rq_addrlen,
			.msg_control	= cmh,
			.msg_controllen	= sizeof(buffer),
			.msg_flags	= MSG_MORE,
		};

		svc_set_cmsg_data(rqstp, cmh);

		if (sock_sendmsg(sock, &msg, 0) < 0)
			goto out;
	}

	/* send head */
	if (slen == xdr->head[0].iov_len)
		flags = 0;
	len = kernel_sendpage(sock, rqstp->rq_respages[0], 0,
				  xdr->head[0].iov_len, flags);
	if (len != xdr->head[0].iov_len)
		goto out;
	slen -= xdr->head[0].iov_len;
	if (slen == 0)
		goto out;

	/* send page data */
	size = PAGE_SIZE - base < pglen ? PAGE_SIZE - base : pglen;
	while (pglen > 0) {
		if (slen == size)
			flags = 0;
		result = kernel_sendpage(sock, *ppage, base, size, flags);
		if (result > 0)
			len += result;
		if (result != size)
			goto out;
		slen -= size;
		pglen -= size;
		size = PAGE_SIZE < pglen ? PAGE_SIZE : pglen;
		base = 0;
		ppage++;
	}
	/* send tail */
	if (xdr->tail[0].iov_len) {
		result = kernel_sendpage(sock, rqstp->rq_respages[0],
					     ((unsigned long)xdr->tail[0].iov_base)
						& (PAGE_SIZE-1),
					     xdr->tail[0].iov_len, 0);

		if (result > 0)
			len += result;
	}
out:
	dprintk("svc: socket %p sendto([%p %Zu... ], %d) = %d (addr %s)\n",
		rqstp->rq_sock, xdr->head[0].iov_base, xdr->head[0].iov_len,
		xdr->len, len, svc_print_addr(rqstp, buf, sizeof(buf)));

	return len;
}

/*
 * Report socket names for nfsdfs
 */
static int one_sock_name(char *buf, struct svc_sock *svsk)
{
	int len;

	switch(svsk->sk_sk->sk_family) {
	case AF_INET:
		len = sprintf(buf, "ipv4 %s %u.%u.%u.%u %d\n",
			      svsk->sk_sk->sk_protocol==IPPROTO_UDP?
			      "udp" : "tcp",
			      NIPQUAD(inet_sk(svsk->sk_sk)->rcv_saddr),
			      inet_sk(svsk->sk_sk)->num);
		break;
	default:
		len = sprintf(buf, "*unknown-%d*\n",
			       svsk->sk_sk->sk_family);
	}
	return len;
}

int
svc_sock_names(char *buf, struct svc_serv *serv, char *toclose)
{
	struct svc_sock *svsk, *closesk = NULL;
	int len = 0;

	if (!serv)
		return 0;
	spin_lock_bh(&serv->sv_lock);
	list_for_each_entry(svsk, &serv->sv_permsocks, sk_list) {
		int onelen = one_sock_name(buf+len, svsk);
		if (toclose && strcmp(toclose, buf+len) == 0)
			closesk = svsk;
		else
			len += onelen;
	}
	spin_unlock_bh(&serv->sv_lock);
	if (closesk)
		/* Should unregister with portmap, but you cannot
		 * unregister just one protocol...
		 */
		svc_close_socket(closesk);
	else if (toclose)
		return -ENOENT;
	return len;
}
EXPORT_SYMBOL(svc_sock_names);

/*
 * Check input queue length
 */
static int
svc_recv_available(struct svc_sock *svsk)
{
	struct socket	*sock = svsk->sk_sock;
	int		avail, err;

	err = kernel_sock_ioctl(sock, TIOCINQ, (unsigned long) &avail);

	return (err >= 0)? avail : err;
}

/*
 * Generic recvfrom routine.
 */
static int
svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr, int buflen)
{
	struct svc_sock *svsk = rqstp->rq_sock;
	struct msghdr msg = {
		.msg_flags	= MSG_DONTWAIT,
	};
	struct sockaddr *sin;
	int len;

	len = kernel_recvmsg(svsk->sk_sock, &msg, iov, nr, buflen,
				msg.msg_flags);

	/* sock_recvmsg doesn't fill in the name/namelen, so we must..
	 */
	memcpy(&rqstp->rq_addr, &svsk->sk_remote, svsk->sk_remotelen);
	rqstp->rq_addrlen = svsk->sk_remotelen;

	/* Destination address in request is needed for binding the
	 * source address in RPC callbacks later.
	 */
	sin = (struct sockaddr *)&svsk->sk_local;
	switch (sin->sa_family) {
	case AF_INET:
		rqstp->rq_daddr.addr = ((struct sockaddr_in *)sin)->sin_addr;
		break;
	case AF_INET6:
		rqstp->rq_daddr.addr6 = ((struct sockaddr_in6 *)sin)->sin6_addr;
		break;
	}

	dprintk("svc: socket %p recvfrom(%p, %Zu) = %d\n",
		svsk, iov[0].iov_base, iov[0].iov_len, len);

	return len;
}

/*
 * Set socket snd and rcv buffer lengths
 */
static inline void
svc_sock_setbufsize(struct socket *sock, unsigned int snd, unsigned int rcv)
{
#if 0
	mm_segment_t	oldfs;
	oldfs = get_fs(); set_fs(KERNEL_DS);
	sock_setsockopt(sock, SOL_SOCKET, SO_SNDBUF,
			(char*)&snd, sizeof(snd));
	sock_setsockopt(sock, SOL_SOCKET, SO_RCVBUF,
			(char*)&rcv, sizeof(rcv));
#else
	/* sock_setsockopt limits use to sysctl_?mem_max,
	 * which isn't acceptable.  Until that is made conditional
	 * on not having CAP_SYS_RESOURCE or similar, we go direct...
	 * DaveM said I could!
	 */
	lock_sock(sock->sk);
	sock->sk->sk_sndbuf = snd * 2;
	sock->sk->sk_rcvbuf = rcv * 2;
	sock->sk->sk_userlocks |= SOCK_SNDBUF_LOCK|SOCK_RCVBUF_LOCK;
	release_sock(sock->sk);
#endif
}
/*
 * INET callback when data has been received on the socket.
 */
static void
svc_udp_data_ready(struct sock *sk, int count)
{
	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;

	if (svsk) {
		dprintk("svc: socket %p(inet %p), count=%d, busy=%d\n",
			svsk, sk, count, test_bit(SK_BUSY, &svsk->sk_flags));
		set_bit(SK_DATA, &svsk->sk_flags);
		svc_sock_enqueue(svsk);
	}
	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
		wake_up_interruptible(sk->sk_sleep);
}

/*
 * INET callback when space is newly available on the socket.
 */
static void
svc_write_space(struct sock *sk)
{
	struct svc_sock	*svsk = (struct svc_sock *)(sk->sk_user_data);

	if (svsk) {
		dprintk("svc: socket %p(inet %p), write_space busy=%d\n",
			svsk, sk, test_bit(SK_BUSY, &svsk->sk_flags));
		svc_sock_enqueue(svsk);
	}

	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) {
		dprintk("RPC svc_write_space: someone sleeping on %p\n",
		       svsk);
		wake_up_interruptible(sk->sk_sleep);
	}
}

static inline void svc_udp_get_dest_address(struct svc_rqst *rqstp,
					    struct cmsghdr *cmh)
{
	switch (rqstp->rq_sock->sk_sk->sk_family) {
	case AF_INET: {
		struct in_pktinfo *pki = CMSG_DATA(cmh);
		rqstp->rq_daddr.addr.s_addr = pki->ipi_spec_dst.s_addr;
		break;
		}
	case AF_INET6: {
		struct in6_pktinfo *pki = CMSG_DATA(cmh);
		ipv6_addr_copy(&rqstp->rq_daddr.addr6, &pki->ipi6_addr);
		break;
		}
	}
}

/*
 * Receive a datagram from a UDP socket.
 */
static int
svc_udp_recvfrom(struct svc_rqst *rqstp)
{
	struct svc_sock	*svsk = rqstp->rq_sock;
	struct svc_serv	*serv = svsk->sk_server;
	struct sk_buff	*skb;
	union {
		struct cmsghdr	hdr;
		long		all[SVC_PKTINFO_SPACE / sizeof(long)];
	} buffer;
	struct cmsghdr *cmh = &buffer.hdr;
	int		err, len;
	struct msghdr msg = {
		.msg_name = svc_addr(rqstp),
		.msg_control = cmh,
		.msg_controllen = sizeof(buffer),
		.msg_flags = MSG_DONTWAIT,
	};

	if (test_and_clear_bit(SK_CHNGBUF, &svsk->sk_flags))
	    /* udp sockets need large rcvbuf as all pending
	     * requests are still in that buffer.  sndbuf must
	     * also be large enough that there is enough space
	     * for one reply per thread.  We count all threads
	     * rather than threads in a particular pool, which
	     * provides an upper bound on the number of threads
	     * which will access the socket.
	     */
	    svc_sock_setbufsize(svsk->sk_sock,
				(serv->sv_nrthreads+3) * serv->sv_max_mesg,
				(serv->sv_nrthreads+3) * serv->sv_max_mesg);

	if ((rqstp->rq_deferred = svc_deferred_dequeue(svsk))) {
		svc_sock_received(svsk);
		return svc_deferred_recv(rqstp);
	}

	if (test_bit(SK_CLOSE, &svsk->sk_flags)) {
		svc_delete_socket(svsk);
		return 0;
	}

	clear_bit(SK_DATA, &svsk->sk_flags);
	skb = NULL;
	err = kernel_recvmsg(svsk->sk_sock, &msg, NULL,
			     0, 0, MSG_PEEK | MSG_DONTWAIT);
	if (err >= 0)
		skb = skb_recv_datagram(svsk->sk_sk, 0, 1, &err);

	if (skb == NULL) {
		if (err != -EAGAIN) {
			/* possibly an icmp error */
			dprintk("svc: recvfrom returned error %d\n", -err);
			set_bit(SK_DATA, &svsk->sk_flags);
		}
		svc_sock_received(svsk);
		return -EAGAIN;
	}
	rqstp->rq_addrlen = sizeof(rqstp->rq_addr);
	if (skb->tstamp.tv64 == 0) {
		skb->tstamp = ktime_get_real();
		/* Don't enable netstamp, sunrpc doesn't
		   need that much accuracy */
	}
	svsk->sk_sk->sk_stamp = skb->tstamp;
	set_bit(SK_DATA, &svsk->sk_flags); /* there may be more data... */

	/*
	 * Maybe more packets - kick another thread ASAP.
	 */
	svc_sock_received(svsk);

	len  = skb->len - sizeof(struct udphdr);
	rqstp->rq_arg.len = len;

	rqstp->rq_prot = IPPROTO_UDP;

	if (cmh->cmsg_level != IPPROTO_IP ||
	    cmh->cmsg_type != IP_PKTINFO) {
		if (net_ratelimit())
			printk("rpcsvc: received unknown control message:"
			       "%d/%d\n",
			       cmh->cmsg_level, cmh->cmsg_type);
		skb_free_datagram(svsk->sk_sk, skb);
		return 0;
	}
	svc_udp_get_dest_address(rqstp, cmh);

	if (skb_is_nonlinear(skb)) {
		/* we have to copy */
		local_bh_disable();
		if (csum_partial_copy_to_xdr(&rqstp->rq_arg, skb)) {
			local_bh_enable();
			/* checksum error */
			skb_free_datagram(svsk->sk_sk, skb);
			return 0;
		}
		local_bh_enable();
		skb_free_datagram(svsk->sk_sk, skb);
	} else {
		/* we can use it in-place */
		rqstp->rq_arg.head[0].iov_base = skb->data + sizeof(struct udphdr);
		rqstp->rq_arg.head[0].iov_len = len;
		if (skb_checksum_complete(skb)) {
			skb_free_datagram(svsk->sk_sk, skb);
			return 0;
		}
		rqstp->rq_skbuff = skb;
	}

	rqstp->rq_arg.page_base = 0;
	if (len <= rqstp->rq_arg.head[0].iov_len) {
		rqstp->rq_arg.head[0].iov_len = len;
		rqstp->rq_arg.page_len = 0;
		rqstp->rq_respages = rqstp->rq_pages+1;
	} else {
		rqstp->rq_arg.page_len = len - rqstp->rq_arg.head[0].iov_len;
		rqstp->rq_respages = rqstp->rq_pages + 1 +
			DIV_ROUND_UP(rqstp->rq_arg.page_len, PAGE_SIZE);
	}

	if (serv->sv_stats)
		serv->sv_stats->netudpcnt++;

	return len;
}

static int
svc_udp_sendto(struct svc_rqst *rqstp)
{
	int		error;

	error = svc_sendto(rqstp, &rqstp->rq_res);
	if (error == -ECONNREFUSED)
		/* ICMP error on earlier request. */
		error = svc_sendto(rqstp, &rqstp->rq_res);

	return error;
}

static void
svc_udp_init(struct svc_sock *svsk)
{
	int one = 1;
	mm_segment_t oldfs;

	svsk->sk_sk->sk_data_ready = svc_udp_data_ready;
	svsk->sk_sk->sk_write_space = svc_write_space;
	svsk->sk_recvfrom = svc_udp_recvfrom;
	svsk->sk_sendto = svc_udp_sendto;

	/* initialise setting must have enough space to
	 * receive and respond to one request.
	 * svc_udp_recvfrom will re-adjust if necessary
	 */
	svc_sock_setbufsize(svsk->sk_sock,
			    3 * svsk->sk_server->sv_max_mesg,
			    3 * svsk->sk_server->sv_max_mesg);

	set_bit(SK_DATA, &svsk->sk_flags); /* might have come in before data_ready set up */
	set_bit(SK_CHNGBUF, &svsk->sk_flags);

	oldfs = get_fs();
	set_fs(KERNEL_DS);
	/* make sure we get destination address info */
	svsk->sk_sock->ops->setsockopt(svsk->sk_sock, IPPROTO_IP, IP_PKTINFO,
				       (char __user *)&one, sizeof(one));
	set_fs(oldfs);
}

/*
 * A data_ready event on a listening socket means there's a connection
 * pending. Do not use state_change as a substitute for it.
 */
static void
svc_tcp_listen_data_ready(struct sock *sk, int count_unused)
{
	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;

	dprintk("svc: socket %p TCP (listen) state change %d\n",
		sk, sk->sk_state);

	/*
	 * This callback may called twice when a new connection
	 * is established as a child socket inherits everything
	 * from a parent LISTEN socket.
	 * 1) data_ready method of the parent socket will be called
	 *    when one of child sockets become ESTABLISHED.
	 * 2) data_ready method of the child socket may be called
	 *    when it receives data before the socket is accepted.
	 * In case of 2, we should ignore it silently.
	 */
	if (sk->sk_state == TCP_LISTEN) {
		if (svsk) {
			set_bit(SK_CONN, &svsk->sk_flags);
			svc_sock_enqueue(svsk);
		} else
			printk("svc: socket %p: no user data\n", sk);
	}

	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
		wake_up_interruptible_all(sk->sk_sleep);
}

/*
 * A state change on a connected socket means it's dying or dead.
 */
static void
svc_tcp_state_change(struct sock *sk)
{
	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;

	dprintk("svc: socket %p TCP (connected) state change %d (svsk %p)\n",
		sk, sk->sk_state, sk->sk_user_data);

	if (!svsk)
		printk("svc: socket %p: no user data\n", sk);
	else {
		set_bit(SK_CLOSE, &svsk->sk_flags);
		svc_sock_enqueue(svsk);
	}
	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))