uipc_usrreq.c

早期freebsd实现

/*
 * Copyright (c) 1982, 1986, 1989, 1991, 1993
 *	The Regents of the University of California.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *	This product includes software developed by the University of
 *	California, Berkeley and its contributors.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)uipc_usrreq.c	8.3 (Berkeley) 1/4/94
 */

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/proc.h>
#include <sys/filedesc.h>
#include <sys/domain.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/unpcb.h>
#include <sys/un.h>
#include <sys/namei.h>
#include <sys/vnode.h>
#include <sys/file.h>
#include <sys/stat.h>
#include <sys/mbuf.h>

/*
 * Unix communications domain.
 *
 * TODO:
 *	SEQPACKET, RDM
 *	rethink name space problems
 *	need a proper out-of-band
 */
struct	sockaddr sun_noname = { sizeof(sun_noname), AF_UNIX };
ino_t	unp_ino;			/* prototype for fake inode numbers */

/*ARGSUSED*/
uipc_usrreq(so, req, m, nam, control)
	struct socket *so;
	int req;
	struct mbuf *m, *nam, *control;
{
	struct unpcb *unp = sotounpcb(so);
	register struct socket *so2;
	register int error = 0;
	struct proc *p = curproc;	/* XXX */

	if (req == PRU_CONTROL)
		return (EOPNOTSUPP);
	if (req != PRU_SEND && control && control->m_len) {
		error = EOPNOTSUPP;
		goto release;
	}
	if (unp == 0 && req != PRU_ATTACH) {
		error = EINVAL;
		goto release;
	}
	switch (req) {

	case PRU_ATTACH:
		if (unp) {
			error = EISCONN;
			break;
		}
		error = unp_attach(so);
		break;

	case PRU_DETACH:
		unp_detach(unp);
		break;

	case PRU_BIND:
		error = unp_bind(unp, nam, p);
		break;

	case PRU_LISTEN:
		if (unp->unp_vnode == 0)
			error = EINVAL;
		break;

	case PRU_CONNECT:
		error = unp_connect(so, nam, p);
		break;

	case PRU_CONNECT2:
		error = unp_connect2(so, (struct socket *)nam);
		break;

	case PRU_DISCONNECT:
		unp_disconnect(unp);
		break;

	case PRU_ACCEPT:
		/*
		 * Pass back name of connected socket,
		 * if it was bound and we are still connected
		 * (our peer may have closed already!).
		 */
		if (unp->unp_conn && unp->unp_conn->unp_addr) {
			nam->m_len = unp->unp_conn->unp_addr->m_len;
			bcopy(mtod(unp->unp_conn->unp_addr, caddr_t),
			    mtod(nam, caddr_t), (unsigned)nam->m_len);
		} else {
			nam->m_len = sizeof(sun_noname);
			*(mtod(nam, struct sockaddr *)) = sun_noname;
		}
		break;

	case PRU_SHUTDOWN:
		socantsendmore(so);
		unp_shutdown(unp);
		break;

	case PRU_RCVD:
		switch (so->so_type) {

		case SOCK_DGRAM:
			panic("uipc 1");
			/*NOTREACHED*/

		case SOCK_STREAM:
#define	rcv (&so->so_rcv)
#define snd (&so2->so_snd)
			if (unp->unp_conn == 0)
				break;
			so2 = unp->unp_conn->unp_socket;
			/*
			 * Adjust backpressure on sender
			 * and wakeup any waiting to write.
			 */
			snd->sb_mbmax += unp->unp_mbcnt - rcv->sb_mbcnt;
			unp->unp_mbcnt = rcv->sb_mbcnt;
			snd->sb_hiwat += unp->unp_cc - rcv->sb_cc;
			unp->unp_cc = rcv->sb_cc;
			sowwakeup(so2);
#undef snd
#undef rcv
			break;

		default:
			panic("uipc 2");
		}
		break;

	case PRU_SEND:
		if (control && (error = unp_internalize(control, p)))
			break;
		switch (so->so_type) {

		case SOCK_DGRAM: {
			struct sockaddr *from;

			if (nam) {
				if (unp->unp_conn) {
					error = EISCONN;
					break;
				}
				error = unp_connect(so, nam, p);
				if (error)
					break;
			} else {
				if (unp->unp_conn == 0) {
					error = ENOTCONN;
					break;
				}
			}
			so2 = unp->unp_conn->unp_socket;
			if (unp->unp_addr)
				from = mtod(unp->unp_addr, struct sockaddr *);
			else
				from = &sun_noname;
			if (sbappendaddr(&so2->so_rcv, from, m, control)) {
				sorwakeup(so2);
				m = 0;
				control = 0;
			} else
				error = ENOBUFS;
			if (nam)
				unp_disconnect(unp);
			break;
		}

		case SOCK_STREAM:
#define	rcv (&so2->so_rcv)
#define	snd (&so->so_snd)
			if (so->so_state & SS_CANTSENDMORE) {
				error = EPIPE;
				break;
			}
			if (unp->unp_conn == 0)
				panic("uipc 3");
			so2 = unp->unp_conn->unp_socket;
			/*
			 * Send to paired receive port, and then reduce
			 * send buffer hiwater marks to maintain backpressure.
			 * Wake up readers.
			 */
			if (control) {
				if (sbappendcontrol(rcv, m, control))
					control = 0;
			} else
				sbappend(rcv, m);
			snd->sb_mbmax -=
			    rcv->sb_mbcnt - unp->unp_conn->unp_mbcnt;
			unp->unp_conn->unp_mbcnt = rcv->sb_mbcnt;
			snd->sb_hiwat -= rcv->sb_cc - unp->unp_conn->unp_cc;
			unp->unp_conn->unp_cc = rcv->sb_cc;
			sorwakeup(so2);
			m = 0;
#undef snd
#undef rcv
			break;

		default:
			panic("uipc 4");
		}
		break;

	case PRU_ABORT:
		unp_drop(unp, ECONNABORTED);
		break;

	case PRU_SENSE:
		((struct stat *) m)->st_blksize = so->so_snd.sb_hiwat;
		if (so->so_type == SOCK_STREAM && unp->unp_conn != 0) {
			so2 = unp->unp_conn->unp_socket;
			((struct stat *) m)->st_blksize += so2->so_rcv.sb_cc;
		}
		((struct stat *) m)->st_dev = NODEV;
		if (unp->unp_ino == 0)
			unp->unp_ino = unp_ino++;
		((struct stat *) m)->st_ino = unp->unp_ino;
		return (0);

	case PRU_RCVOOB:
		return (EOPNOTSUPP);

	case PRU_SENDOOB:
		error = EOPNOTSUPP;
		break;

	case PRU_SOCKADDR:
		if (unp->unp_addr) {
			nam->m_len = unp->unp_addr->m_len;
			bcopy(mtod(unp->unp_addr, caddr_t),
			    mtod(nam, caddr_t), (unsigned)nam->m_len);
		} else
			nam->m_len = 0;
		break;

	case PRU_PEERADDR:
		if (unp->unp_conn && unp->unp_conn->unp_addr) {
			nam->m_len = unp->unp_conn->unp_addr->m_len;
			bcopy(mtod(unp->unp_conn->unp_addr, caddr_t),
			    mtod(nam, caddr_t), (unsigned)nam->m_len);
		} else
			nam->m_len = 0;
		break;

	case PRU_SLOWTIMO:
		break;

	default:
		panic("piusrreq");
	}
release:
	if (control)
		m_freem(control);
	if (m)
		m_freem(m);
	return (error);
}

/*
 * Both send and receive buffers are allocated PIPSIZ bytes of buffering
 * for stream sockets, although the total for sender and receiver is
 * actually only PIPSIZ.
 * Datagram sockets really use the sendspace as the maximum datagram size,
 * and don't really want to reserve the sendspace.  Their recvspace should
 * be large enough for at least one max-size datagram plus address.
 */
#define	PIPSIZ	4096
u_long	unpst_sendspace = PIPSIZ;
u_long	unpst_recvspace = PIPSIZ;
u_long	unpdg_sendspace = 2*1024;	/* really max datagram size */
u_long	unpdg_recvspace = 4*1024;

int	unp_rights;			/* file descriptors in flight */

unp_attach(so)
	struct socket *so;
{
	register struct mbuf *m;
	register struct unpcb *unp;
	int error;
	
	if (so->so_snd.sb_hiwat == 0 || so->so_rcv.sb_hiwat == 0) {
		switch (so->so_type) {

		case SOCK_STREAM:
			error = soreserve(so, unpst_sendspace, unpst_recvspace);
			break;

		case SOCK_DGRAM:
			error = soreserve(so, unpdg_sendspace, unpdg_recvspace);
			break;

		default:
			panic("unp_attach");
		}
		if (error)
			return (error);
	}
	m = m_getclr(M_DONTWAIT, MT_PCB);
	if (m == NULL)
		return (ENOBUFS);
	unp = mtod(m, struct unpcb *);
	so->so_pcb = (caddr_t)unp;
	unp->unp_socket = so;
	return (0);
}

unp_detach(unp)
	register struct unpcb *unp;
{
	
	if (unp->unp_vnode) {
		unp->unp_vnode->v_socket = 0;
		vrele(unp->unp_vnode);
		unp->unp_vnode = 0;
	}
	if (unp->unp_conn)
		unp_disconnect(unp);
	while (unp->unp_refs)
		unp_drop(unp->unp_refs, ECONNRESET);
	soisdisconnected(unp->unp_socket);
	unp->unp_socket->so_pcb = 0;
	m_freem(unp->unp_addr);
	(void) m_free(dtom(unp));
	if (unp_rights) {
		/*
		 * Normally the receive buffer is flushed later,
		 * in sofree, but if our receive buffer holds references
		 * to descriptors that are now garbage, we will dispose
		 * of those descriptor references after the garbage collector
		 * gets them (resulting in a "panic: closef: count < 0").
		 */
		sorflush(unp->unp_socket);
		unp_gc();
	}
}

unp_bind(unp, nam, p)
	struct unpcb *unp;
	struct mbuf *nam;
	struct proc *p;
{
	struct sockaddr_un *soun = mtod(nam, struct sockaddr_un *);
	register struct vnode *vp;
	struct vattr vattr;
	int error;
	struct nameidata nd;

	NDINIT(&nd, CREATE, FOLLOW | LOCKPARENT, UIO_SYSSPACE,
		soun->sun_path, p);
	if (unp->unp_vnode != NULL)
		return (EINVAL);
	if (nam->m_len == MLEN) {
		if (*(mtod(nam, caddr_t) + nam->m_len - 1) != 0)
			return (EINVAL);
	} else
		*(mtod(nam, caddr_t) + nam->m_len) = 0;
/* SHOULD BE ABLE TO ADOPT EXISTING AND wakeup() ALA FIFO's */
	if (error = namei(&nd))
		return (error);
	vp = nd.ni_vp;
	if (vp != NULL) {
		VOP_ABORTOP(nd.ni_dvp, &nd.ni_cnd);
		if (nd.ni_dvp == vp)
			vrele(nd.ni_dvp);
		else
			vput(nd.ni_dvp);
		vrele(vp);
		return (EADDRINUSE);
	}
	VATTR_NULL(&vattr);