xprtsock.c

linux 内核源代码

static inline void xs_tcp_read_discard(struct sock_xprt *transport, struct xdr_skb_reader *desc)
{
	size_t len;

	len = transport->tcp_reclen - transport->tcp_offset;
	if (len > desc->count)
		len = desc->count;
	desc->count -= len;
	desc->offset += len;
	transport->tcp_offset += len;
	dprintk("RPC:       discarded %Zu bytes\n", len);
	xs_tcp_check_fraghdr(transport);
}

static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, unsigned int offset, size_t len)
{
	struct rpc_xprt *xprt = rd_desc->arg.data;
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
	struct xdr_skb_reader desc = {
		.skb	= skb,
		.offset	= offset,
		.count	= len,
	};

	dprintk("RPC:       xs_tcp_data_recv started\n");
	do {
		/* Read in a new fragment marker if necessary */
		/* Can we ever really expect to get completely empty fragments? */
		if (transport->tcp_flags & TCP_RCV_COPY_FRAGHDR) {
			xs_tcp_read_fraghdr(xprt, &desc);
			continue;
		}
		/* Read in the xid if necessary */
		if (transport->tcp_flags & TCP_RCV_COPY_XID) {
			xs_tcp_read_xid(transport, &desc);
			continue;
		}
		/* Read in the request data */
		if (transport->tcp_flags & TCP_RCV_COPY_DATA) {
			xs_tcp_read_request(xprt, &desc);
			continue;
		}
		/* Skip over any trailing bytes on short reads */
		xs_tcp_read_discard(transport, &desc);
	} while (desc.count);
	dprintk("RPC:       xs_tcp_data_recv done\n");
	return len - desc.count;
}

/**
 * xs_tcp_data_ready - "data ready" callback for TCP sockets
 * @sk: socket with data to read
 * @bytes: how much data to read
 *
 */
static void xs_tcp_data_ready(struct sock *sk, int bytes)
{
	struct rpc_xprt *xprt;
	read_descriptor_t rd_desc;

	dprintk("RPC:       xs_tcp_data_ready...\n");

	read_lock(&sk->sk_callback_lock);
	if (!(xprt = xprt_from_sock(sk)))
		goto out;
	if (xprt->shutdown)
		goto out;

	/* We use rd_desc to pass struct xprt to xs_tcp_data_recv */
	rd_desc.arg.data = xprt;
	rd_desc.count = 65536;
	tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv);
out:
	read_unlock(&sk->sk_callback_lock);
}

/**
 * xs_tcp_state_change - callback to handle TCP socket state changes
 * @sk: socket whose state has changed
 *
 */
static void xs_tcp_state_change(struct sock *sk)
{
	struct rpc_xprt *xprt;

	read_lock(&sk->sk_callback_lock);
	if (!(xprt = xprt_from_sock(sk)))
		goto out;
	dprintk("RPC:       xs_tcp_state_change client %p...\n", xprt);
	dprintk("RPC:       state %x conn %d dead %d zapped %d\n",
			sk->sk_state, xprt_connected(xprt),
			sock_flag(sk, SOCK_DEAD),
			sock_flag(sk, SOCK_ZAPPED));

	switch (sk->sk_state) {
	case TCP_ESTABLISHED:
		spin_lock_bh(&xprt->transport_lock);
		if (!xprt_test_and_set_connected(xprt)) {
			struct sock_xprt *transport = container_of(xprt,
					struct sock_xprt, xprt);

			/* Reset TCP record info */
			transport->tcp_offset = 0;
			transport->tcp_reclen = 0;
			transport->tcp_copied = 0;
			transport->tcp_flags =
				TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID;

			xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
			xprt_wake_pending_tasks(xprt, 0);
		}
		spin_unlock_bh(&xprt->transport_lock);
		break;
	case TCP_SYN_SENT:
	case TCP_SYN_RECV:
		break;
	case TCP_CLOSE_WAIT:
		/* Try to schedule an autoclose RPC calls */
		set_bit(XPRT_CLOSE_WAIT, &xprt->state);
		if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0)
			queue_work(rpciod_workqueue, &xprt->task_cleanup);
	default:
		xprt_disconnect(xprt);
	}
 out:
	read_unlock(&sk->sk_callback_lock);
}

/**
 * xs_udp_write_space - callback invoked when socket buffer space
 *                             becomes available
 * @sk: socket whose state has changed
 *
 * Called when more output buffer space is available for this socket.
 * We try not to wake our writers until they can make "significant"
 * progress, otherwise we'll waste resources thrashing kernel_sendmsg
 * with a bunch of small requests.
 */
static void xs_udp_write_space(struct sock *sk)
{
	read_lock(&sk->sk_callback_lock);

	/* from net/core/sock.c:sock_def_write_space */
	if (sock_writeable(sk)) {
		struct socket *sock;
		struct rpc_xprt *xprt;

		if (unlikely(!(sock = sk->sk_socket)))
			goto out;
		if (unlikely(!(xprt = xprt_from_sock(sk))))
			goto out;
		if (unlikely(!test_and_clear_bit(SOCK_NOSPACE, &sock->flags)))
			goto out;

		xprt_write_space(xprt);
	}

 out:
	read_unlock(&sk->sk_callback_lock);
}

/**
 * xs_tcp_write_space - callback invoked when socket buffer space
 *                             becomes available
 * @sk: socket whose state has changed
 *
 * Called when more output buffer space is available for this socket.
 * We try not to wake our writers until they can make "significant"
 * progress, otherwise we'll waste resources thrashing kernel_sendmsg
 * with a bunch of small requests.
 */
static void xs_tcp_write_space(struct sock *sk)
{
	read_lock(&sk->sk_callback_lock);

	/* from net/core/stream.c:sk_stream_write_space */
	if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) {
		struct socket *sock;
		struct rpc_xprt *xprt;

		if (unlikely(!(sock = sk->sk_socket)))
			goto out;
		if (unlikely(!(xprt = xprt_from_sock(sk))))
			goto out;
		if (unlikely(!test_and_clear_bit(SOCK_NOSPACE, &sock->flags)))
			goto out;

		xprt_write_space(xprt);
	}

 out:
	read_unlock(&sk->sk_callback_lock);
}

static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
	struct sock *sk = transport->inet;

	if (transport->rcvsize) {
		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
		sk->sk_rcvbuf = transport->rcvsize * xprt->max_reqs * 2;
	}
	if (transport->sndsize) {
		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
		sk->sk_sndbuf = transport->sndsize * xprt->max_reqs * 2;
		sk->sk_write_space(sk);
	}
}

/**
 * xs_udp_set_buffer_size - set send and receive limits
 * @xprt: generic transport
 * @sndsize: requested size of send buffer, in bytes
 * @rcvsize: requested size of receive buffer, in bytes
 *
 * Set socket send and receive buffer size limits.
 */
static void xs_udp_set_buffer_size(struct rpc_xprt *xprt, size_t sndsize, size_t rcvsize)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);

	transport->sndsize = 0;
	if (sndsize)
		transport->sndsize = sndsize + 1024;
	transport->rcvsize = 0;
	if (rcvsize)
		transport->rcvsize = rcvsize + 1024;

	xs_udp_do_set_buffer_size(xprt);
}

/**
 * xs_udp_timer - called when a retransmit timeout occurs on a UDP transport
 * @task: task that timed out
 *
 * Adjust the congestion window after a retransmit timeout has occurred.
 */
static void xs_udp_timer(struct rpc_task *task)
{
	xprt_adjust_cwnd(task, -ETIMEDOUT);
}

static unsigned short xs_get_random_port(void)
{
	unsigned short range = xprt_max_resvport - xprt_min_resvport;
	unsigned short rand = (unsigned short) net_random() % range;
	return rand + xprt_min_resvport;
}

/**
 * xs_set_port - reset the port number in the remote endpoint address
 * @xprt: generic transport
 * @port: new port number
 *
 */
static void xs_set_port(struct rpc_xprt *xprt, unsigned short port)
{
	struct sockaddr *addr = xs_addr(xprt);

	dprintk("RPC:       setting port for xprt %p to %u\n", xprt, port);

	switch (addr->sa_family) {
	case AF_INET:
		((struct sockaddr_in *)addr)->sin_port = htons(port);
		break;
	case AF_INET6:
		((struct sockaddr_in6 *)addr)->sin6_port = htons(port);
		break;
	default:
		BUG();
	}
}

static int xs_bind4(struct sock_xprt *transport, struct socket *sock)
{
	struct sockaddr_in myaddr = {
		.sin_family = AF_INET,
	};
	struct sockaddr_in *sa;
	int err;
	unsigned short port = transport->port;

	if (!transport->xprt.resvport)
		port = 0;
	sa = (struct sockaddr_in *)&transport->addr;
	myaddr.sin_addr = sa->sin_addr;
	do {
		myaddr.sin_port = htons(port);
		err = kernel_bind(sock, (struct sockaddr *) &myaddr,
						sizeof(myaddr));
		if (!transport->xprt.resvport)
			break;
		if (err == 0) {
			transport->port = port;
			break;
		}
		if (port <= xprt_min_resvport)
			port = xprt_max_resvport;
		else
			port--;
	} while (err == -EADDRINUSE && port != transport->port);
	dprintk("RPC:       %s "NIPQUAD_FMT":%u: %s (%d)\n",
			__FUNCTION__, NIPQUAD(myaddr.sin_addr),
			port, err ? "failed" : "ok", err);
	return err;
}

static int xs_bind6(struct sock_xprt *transport, struct socket *sock)
{
	struct sockaddr_in6 myaddr = {
		.sin6_family = AF_INET6,
	};
	struct sockaddr_in6 *sa;
	int err;
	unsigned short port = transport->port;

	if (!transport->xprt.resvport)
		port = 0;
	sa = (struct sockaddr_in6 *)&transport->addr;
	myaddr.sin6_addr = sa->sin6_addr;
	do {
		myaddr.sin6_port = htons(port);
		err = kernel_bind(sock, (struct sockaddr *) &myaddr,
						sizeof(myaddr));
		if (!transport->xprt.resvport)
			break;
		if (err == 0) {
			transport->port = port;
			break;
		}
		if (port <= xprt_min_resvport)
			port = xprt_max_resvport;
		else
			port--;
	} while (err == -EADDRINUSE && port != transport->port);
	dprintk("RPC:       xs_bind6 "NIP6_FMT":%u: %s (%d)\n",
		NIP6(myaddr.sin6_addr), port, err ? "failed" : "ok", err);
	return err;
}

#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key xs_key[2];
static struct lock_class_key xs_slock_key[2];

static inline void xs_reclassify_socket4(struct socket *sock)
{
	struct sock *sk = sock->sk;

	BUG_ON(sock_owned_by_user(sk));
	sock_lock_init_class_and_name(sk, "slock-AF_INET-RPC",
		&xs_slock_key[0], "sk_lock-AF_INET-RPC", &xs_key[0]);
}

static inline void xs_reclassify_socket6(struct socket *sock)
{
	struct sock *sk = sock->sk;

	BUG_ON(sock_owned_by_user(sk));
	sock_lock_init_class_and_name(sk, "slock-AF_INET6-RPC",
		&xs_slock_key[1], "sk_lock-AF_INET6-RPC", &xs_key[1]);
}
#else
static inline void xs_reclassify_socket4(struct socket *sock)
{
}

static inline void xs_reclassify_socket6(struct socket *sock)
{
}
#endif

static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);

	if (!transport->inet) {
		struct sock *sk = sock->sk;

		write_lock_bh(&sk->sk_callback_lock);

		sk->sk_user_data = xprt;
		transport->old_data_ready = sk->sk_data_ready;
		transport->old_state_change = sk->sk_state_change;
		transport->old_write_space = sk->sk_write_space;
		sk->sk_data_ready = xs_udp_data_ready;
		sk->sk_write_space = xs_udp_write_space;
		sk->sk_no_check = UDP_CSUM_NORCV;
		sk->sk_allocation = GFP_ATOMIC;

		xprt_set_connected(xprt);

		/* Reset to new socket */
		transport->sock = sock;
		transport->inet = sk;

		write_unlock_bh(&sk->sk_callback_lock);
	}
	xs_udp_do_set_buffer_size(xprt);
}

/**
 * xs_udp_connect_worker4 - set up a UDP socket
 * @work: RPC transport to connect
 *
 * Invoked by a work queue tasklet.
 */
static void xs_udp_connect_worker4(struct work_struct *work)
{
	struct sock_xprt *transport =
		container_of(work, struct sock_xprt, connect_worker.work);
	struct rpc_xprt *xprt = &transport->xprt;
	struct socket *sock = transport->sock;
	int err, status = -EIO;

	if (xprt->shutdown || !xprt_bound(xprt))
		goto out;

	/* Start by resetting any existing state */
	xs_close(xprt);

	if ((err = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock)) < 0) {
		dprintk("RPC:       can't create UDP transport socket (%d).\n", -err);
		goto out;
	}
	xs_reclassify_socket4(sock);

	if (xs_bind4(transport, sock)) {
		sock_release(sock);
		goto out;
	}

	dprintk("RPC:       worker connecting xprt %p to address: %s\n",
			xprt, xprt->address_strings[RPC_DISPLAY_ALL]);

	xs_udp_finish_connecting(xprt, sock);
	status = 0;
out:
	xprt_wake_pending_tasks(xprt, status);
	xprt_clear_connecting(xprt);
}

/**
 * xs_udp_connect_worker6 - set up a UDP socket
 * @work: RPC transport to connect
 *
 * Invoked by a work queue tasklet.
 */
static void xs_udp_connect_worker6(struct work_struct *work)
{
	struct sock_xprt *transport =
		container_of(work, struct sock_xprt, connect_worker.work);
	struct rpc_xprt *xprt = &transport->xprt;
	struct socket *sock = transport->sock;
	int err, status = -EIO;

	if (xprt->shutdown || !xprt_bound(xprt))
		goto out;

	/* Start by resetting any existing state */
	xs_close(xprt);

	if ((err = sock_create_kern(PF_INET6, SOCK_DGRAM, IPPROTO_UDP, &sock)) < 0) {
		dprintk("RPC:       can't create UDP transport socket (%d).\n", -err);
		goto out;
	}
	xs_reclassify_socket6(sock);

	if (xs_bind6(transport, sock) < 0) {
		sock_release(sock);
		goto out;
	}

	dprintk("RPC:       worker connecting xprt %p to address: %s\n",
			xprt, xprt->address_strings[RPC_DISPLAY_ALL]);

	xs_udp_finish_connecting(xprt, sock);
	status = 0;
out:
	xprt_wake_pending_tasks(xprt, status);
	xprt_clear_connecting(xprt);
}

/*
 * We need to preserve the port number so the reply cache on the server can
 * find our cached RPC replies when we get around to reconnecting.
 */
static void xs_tcp_reuse_connection(struct rpc_xprt *xprt)
{
	int result;
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
	struct sockaddr any;

	dprintk("RPC:       disconnecting xprt %p to reuse port\n", xprt);

	/*
	 * Disconnect the transport socket by doing a connect operation
	 * with AF_UNSPEC.  This should return immediately...
	 */
	memset(&any, 0, sizeof(any));