tools/adflib: build only host variant which is used by Sam440 target

[AROS.git] / workbench / network / stacks / AROSTCP / bsdsocket / kern / uipc_socket.c

/*
 * Copyright (C) 1993 AmiTCP/IP Group, <amitcp-group@hut.fi>
 *                    Helsinki University of Technology, Finland.
 *                    All rights reserved.
 * Copyright (C) 2005 - 2007 The AROS Dev Team
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston,
 * MA 02111-1307, USA.
 *
 */

/* 
 * Mach Operating System
 * Copyright (c) 1992 Carnegie Mellon University
 * All Rights Reserved.
 * 
 * Permission to use, copy, modify and distribute this software and its
 * documentation is hereby granted, provided that both the copyright
 * notice and this permission notice appear in all copies of the
 * software, derivative works or modified versions, and any portions
 * thereof, and that both notices appear in supporting documentation.
 * 
 * CARNEGIE MELLON ALLOWS FREE USE OF THIS SOFTWARE IN ITS "AS IS"
 * CONDITION.  CARNEGIE MELLON DISCLAIMS ANY LIABILITY OF ANY KIND FOR
 * ANY DAMAGES WHATSOEVER RESULTING FROM THE USE OF THIS SOFTWARE.
 * 
 * Carnegie Mellon requests users of this software to return to
 * 
 *  Software Distribution Coordinator  or  Software.Distribution@CS.CMU.EDU
 *  School of Computer Science
 *  Carnegie Mellon University
 *  Pittsburgh PA 15213-3890
 * 
 * any improvements or extensions that they make and grant Carnegie Mellon 
 * the rights to redistribute these changes.
 */

/*
 * Copyright (c) 1982, 1986, 1988, 1990 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_socket.c       7.28 (Berkeley) 5/4/91
 */

#include <conf.h>

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/domain.h>
#include <sys/kernel.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>

#include <sys/synch.h>
#include <api/amiga_api.h>

#include <kern/amiga_includes.h>

#include <kern/uipc_socket_protos.h>
#include <kern/uipc_socket2_protos.h>
#include <kern/uipc_domain_protos.h>
#include <kern/amiga_select_protos.h>

#include <sys/uio.h>

/*
 * Socket operation routines.
 * These routines are called by the routines in
 * sys_socket.c or from a system process, and
 * implement the semantics of socket operations by
 * switching out to the protocol specific routines.
 */
int
socreate(dom, aso, type, proto)
        int dom;
        struct socket **aso;
        register int type;
        int proto;
{
#ifndef AMITCP
        struct proc *p = (struct proc*)cthread_data(cthread_self());
#endif /* AMITCP */
        register struct protosw *prp;
        register struct socket *so;
        register int error;

        if (proto)
                prp = pffindproto(dom, proto, type);
        else
                prp = pffindtype(dom, type);
        if (prp == 0)
                return (EPROTONOSUPPORT);
        if (prp->pr_type != type)
                return (EPROTOTYPE);
        MALLOC(so, struct socket *, sizeof(*so), M_SOCKET, M_WAIT);
        aligned_bzero_const((caddr_t)so, sizeof(*so));
        so->so_type = type;
#ifndef AMITCP
        if (p->p_ucred->cr_uid == 0)
#endif /* AMITCP */
                so->so_state = SS_PRIV; /* all sockets have the force  now */
        so->so_proto = prp;
        error =
            (*prp->pr_usrreq)(so, PRU_ATTACH,
                (struct mbuf *)0, (struct mbuf *)(long)proto, (struct mbuf *)0);
        if (error) {
                so->so_state |= SS_NOFDREF;
                sofree(so);
                return (error);
        }
        *aso = so;
        return (0);
}

int
sobind(so, nam)
        struct socket *so;
        struct mbuf *nam;
{
        spl_t s = splnet();
        int error;

        error =
            (*so->so_proto->pr_usrreq)(so, PRU_BIND,
                (struct mbuf *)0, nam, (struct mbuf *)0);
        splx(s);
        return (error);
}

int
solisten(so, backlog)
        register struct socket *so;
        int backlog;
{
        spl_t s = splnet(), error;

        error =
            (*so->so_proto->pr_usrreq)(so, PRU_LISTEN,
                (struct mbuf *)0, (struct mbuf *)0, (struct mbuf *)0);
        if (error) {
                splx(s);
                return (error);
        }
        if (so->so_q == 0)
                so->so_options |= SO_ACCEPTCONN;
        if (backlog < 0)
                backlog = 0;
        so->so_qlimit = MIN(backlog, SOMAXCONN);
        splx(s);
        return (0);
}

void
sofree(so)
        register struct socket *so;
{

        if (so->so_pcb || (so->so_state & SS_NOFDREF) == 0)
                return;
        if (so->so_head) {
                if (!soqremque(so, 0) && !soqremque(so, 1))
                        panic("sofree dq");
                so->so_head = 0;
        }
        sbrelease(&so->so_snd);
        sorflush(so);
        FREE(so, M_SOCKET);
}

/*
 * Close a socket on last file table reference removal.
 * Initiate disconnect if connected.
 * Free socket when disconnect complete.
 */
int
soclose(so)
        register struct socket *so;
{
        spl_t s = splnet();             /* conservative */
        int error = 0;
        struct SocketBase *socketBase;
        struct timeval *timeo;

        if (so->so_options & SO_ACCEPTCONN) {
                while (so->so_q0)
                        (void) soabort(so->so_q0);
                while (so->so_q)
                        (void) soabort(so->so_q);
        }
        if (so->so_pcb == 0)
                goto discard;
        if (so->so_state & SS_ISCONNECTED) {
                if ((so->so_state & SS_ISDISCONNECTING) == 0) {
                        error = sodisconnect(so);
                        if (error)
                                goto drop;
                }
                if (so->so_options & SO_LINGER) {
                        if ((so->so_state & SS_ISDISCONNECTING) &&
                            (so->so_state & SS_NBIO))
                                goto drop;
                        /*
                         * Find socket base for the tsleep()
                         */
                        if ((socketBase = FindSocketBase(FindTask(NULL)))
                            == NULL)
                                goto drop; /* couldn't find */
                        timeo = (so->so_linger.tv_sec 
                                 || so->so_linger.tv_usec) ?
                                         &so->so_linger : NULL;
                        while (so->so_state & SS_ISCONNECTED)
                                if (error = tsleep(socketBase,
                                                   (caddr_t)&so->so_timeo,
                                                   netcls, timeo))
                                        break;
                }
        }
drop:
        if (so->so_pcb) {
                int error2 =
                    (*so->so_proto->pr_usrreq)(so, PRU_DETACH,
                        (struct mbuf *)0, (struct mbuf *)0, (struct mbuf *)0);
                if (error == 0)
                        error = error2;
        }
discard:
        if (so->so_state & SS_NOFDREF)
                panic("soclose: NOFDREF");
        so->so_state |= SS_NOFDREF;
        sofree(so);
        splx(s);
        return (error);
}

/*
 * Must be called at splnet...
 */
int
soabort(so)
        struct socket *so;
{

        return (
            (*so->so_proto->pr_usrreq)(so, PRU_ABORT,
                (struct mbuf *)0, (struct mbuf *)0, (struct mbuf *)0));
}

int
soaccept(so, nam)
        register struct socket *so;
        struct mbuf *nam;
{
        spl_t s = splnet();
        int error;

        if ((so->so_state & SS_NOFDREF) == 0)
                panic("soaccept: !NOFDREF");
        so->so_state &= ~SS_NOFDREF;
        error = (*so->so_proto->pr_usrreq)(so, PRU_ACCEPT,
            (struct mbuf *)0, nam, (struct mbuf *)0);
        splx(s);
        return (error);
}

int
soconnect(so, nam)
        register struct socket *so;
        struct mbuf *nam;
{
        spl_t s;
        int error;

        if (so->so_options & SO_ACCEPTCONN)
                return (EOPNOTSUPP);
        s = splnet();
        /*
         * If protocol is connection-based, can only connect once.
         * Otherwise, if connected, try to disconnect first.
         * This allows user to disconnect by connecting to, e.g.,
         * a null address.
         */
        if (so->so_state & (SS_ISCONNECTED|SS_ISCONNECTING) &&
            ((so->so_proto->pr_flags & PR_CONNREQUIRED) ||
            (error = sodisconnect(so))))
                error = EISCONN;
        else
                error = (*so->so_proto->pr_usrreq)(so, PRU_CONNECT,
                    (struct mbuf *)0, nam, (struct mbuf *)0);
        splx(s);
        return (error);
}

#ifndef AMITCP
soconnect2(so1, so2)
        register struct socket *so1;
        struct socket *so2;
{
        spl_t s = splnet();
        int error;

        error = (*so1->so_proto->pr_usrreq)(so1, PRU_CONNECT2,
            (struct mbuf *)0, (struct mbuf *)so2, (struct mbuf *)0);
        splx(s);
        return (error);
}
#endif

int
sodisconnect(so)
        register struct socket *so;
{
        spl_t s = splnet();
        int error;

        if ((so->so_state & SS_ISCONNECTED) == 0) {
                error = ENOTCONN;
                goto bad;
        }
        if (so->so_state & SS_ISDISCONNECTING) {
                error = EALREADY;
                goto bad;
        }
        error = (*so->so_proto->pr_usrreq)(so, PRU_DISCONNECT,
            (struct mbuf *)0, (struct mbuf *)0, (struct mbuf *)0);
bad:
        splx(s);
        return (error);
}

#ifdef AMITCP
/*
 * uioread() replaces uiomove() in sosend
 */

static inline void uioread(caddr_t cp, int n, struct uio *uio)
{
  struct iovec *iov;
  u_int cnt;

  while (n > 0 && uio->uio_resid) {
    iov = uio->uio_iov;
    cnt = iov->iov_len;
    if (cnt == 0) {
      uio->uio_iov++;
      uio->uio_iovcnt--;
      continue;
    }
    if (cnt > n)
      cnt = n;

    bcopy(iov->iov_base, cp, cnt); /* wrong direction //pp */

    iov->iov_base += cnt;
    iov->iov_len -= cnt;
    uio->uio_resid -= cnt;
    cp += cnt;
    n -= cnt;
  }
}

#endif /* AMITCP */


/*
 * Send on a socket.
 * If send must go all at once and message is larger than
 * send buffering, then hard error.
 * Lock against other senders.
 * If must go all at once and not enough room now, then
 * inform user that this would block and do nothing.
 * Otherwise, if nonblocking, send as much as possible.
 * The data to be sent is described by "uio" if nonzero,
 * otherwise by the mbuf chain "top" (which must be null
 * if uio is not).  Data provided in mbuf chain must be small
 * enough to send all at once.
 *
 * Returns nonzero on error, timeout or signal; callers
 * must check for short counts if EINTR/ERESTART are returned.
 * Data and control buffers are freed on return.
 */
int
sosend(so, addr, uio, top, control, flags)
        register struct socket *so;
        struct mbuf *addr;
        struct uio *uio;
        struct mbuf *top;
        struct mbuf *control;
        int flags;
{
#ifndef AMITCP /* proc not defined */
        struct proc *p = (struct proc*)cthread_data(cthread_self());
#endif /* AMITCP */
        struct mbuf **mp;
        register struct mbuf *m;
        register long space, len, resid;
        int clen = 0, error, dontroute, mlen;
        spl_t s;
        int atomic = sosendallatonce(so) || top;

        if (uio)
                resid = uio->uio_resid;
        else
                resid = top->m_pkthdr.len;

        dontroute =
            (flags & MSG_DONTROUTE) && (so->so_options & SO_DONTROUTE) == 0 &&
            (so->so_proto->pr_flags & PR_ATOMIC);
#ifndef AMITCP
        p->p_stats->p_ru.ru_msgsnd++;
#endif /* AMITCP */
        if (control)
                clen = control->m_len;
#define snderr(errno)   { error = errno; splx(s); goto release; }

restart:
        if (error = sblock(&so->so_snd, uio->uio_procp))
                goto out;
        do {
                s = splnet();
                if (so->so_state & SS_CANTSENDMORE)
                        snderr(EPIPE);
                if (so->so_error)
                        snderr(so->so_error);
                if ((so->so_state & SS_ISCONNECTED) == 0) {
                        if (so->so_proto->pr_flags & PR_CONNREQUIRED) {
                                if ((so->so_state & SS_ISCONFIRMING) == 0 &&
                                    !(resid == 0 && clen != 0))
                                        snderr(ENOTCONN);
                        } else if (addr == 0)
                                snderr(EDESTADDRREQ);
                }
                space = sbspace(&so->so_snd);
                if (flags & MSG_OOB)
                        space += 1024;
                if (space < resid + clen &&
                    (atomic || space < so->so_snd.sb_lowat || space < clen)) {
                        if ((atomic && resid > so->so_snd.sb_hiwat) ||
                            clen > so->so_snd.sb_hiwat)
                                snderr(EMSGSIZE);
                        if (so->so_state & SS_NBIO)
                                snderr(EWOULDBLOCK);
                        sbunlock(&so->so_snd);
                        error = sbwait(&so->so_snd, uio->uio_procp);
                        splx(s);
                        if (error)
                                goto out;
                        goto restart;
                }
                splx(s);
                mp = &top;
                space -= clen;
                do {
                    if (uio == NULL) {
                        /*
                         * Data is prepackaged in "top".
                         */
                        resid = 0;
#ifdef USE_M_EOR
                        if (flags & MSG_EOR)
                                top->m_flags |= M_EOR;
#endif
                    } else do {
                        if (top == 0) {
                                MGETHDR(m, M_WAIT, MT_DATA);
                                mlen = MHLEN;
                                m->m_pkthdr.len = 0;
                                m->m_pkthdr.rcvif = (struct ifnet *)0;
                        } else {
                                MGET(m, M_WAIT, MT_DATA);
                                mlen = MLEN;
                        }
                        if (resid >= mlen && space >= mbconf.mclbytes) {
                                MCLGET(m, M_WAIT);
                                if ((m->m_flags & M_EXT) == 0)
                                        goto nopages;
                                mlen = mbconf.mclbytes;
#ifdef  MAPPED_MBUFS
                                len = MIN(mbconf.mclbytes, resid);
#else
                                if (top == 0) {
                                        len = MIN(mbconf.mclbytes - max_hdr, resid);
                                        m->m_data += max_hdr;
                                } else
                                        len = MIN(mbconf.mclbytes, resid);
#endif
                                space -= mbconf.mclbytes;
                        } else
                          {
nopages:
                                len = MIN(MIN(mlen, resid), space);
                                space -= len;
                                /*
                                 * For datagram protocols, leave room
                                 * for protocol headers in first mbuf.
                                 */
                                if (atomic && top == 0 && len < mlen)
                                        MH_ALIGN(m, len);
                        }
                        uioread(mtod(m, caddr_t), (int)len, uio);
                        resid = uio->uio_resid;
                        m->m_len = len;
                        *mp = m;
                        top->m_pkthdr.len += len;
                        if (error)
                                goto release;
                        mp = &m->m_next;
                        if (resid <= 0) {
#ifdef USE_M_EOR
                                if (flags & MSG_EOR)
                                        top->m_flags |= M_EOR;
#endif
                                break;
                        }
                    } 
#if defined(AMITCP) && 0
                    /* all the data in 1 mbuf chain */
                    while (space > 0);
#else
                    while (space > 0 && atomic);
#endif
                    if (dontroute)
                            so->so_options |= SO_DONTROUTE;
                    s = splnet();                               /* XXX */
                    error = (*so->so_proto->pr_usrreq)(so,
                        (flags & MSG_OOB) ? PRU_SENDOOB : //PRU_SEND,
                        /*
                         * If the user set MSG_EOF, the protocol
                         * understands this flag and nothing left to
                         * send then use PRU_SEND_EOF instead of PRU_SEND.
                         */
                        ((flags & MSG_EOF) &&
                         (so->so_proto->pr_flags & PR_IMPLOPCL) &&
                         (resid <= 0)) ?
                                PRU_SEND_EOF : PRU_SEND,
                        top, addr, control);
                    splx(s);
                    if (dontroute)
                            so->so_options &= ~SO_DONTROUTE;
                    clen = 0;
                    control = 0;
                    top = 0;
                    mp = &top;
                    if (error)
                        goto release;
                } while (resid && space > 0);
        } while (resid);

release:
        sbunlock(&so->so_snd);
out:
        if (top)
                m_freem(top);
        if (control)
                m_freem(control);
        return (error);
}


#ifdef AMITCP
/*
 * uiowrite() replaces uiomove() in soreceive
 */

static inline void uiowrite(caddr_t cp, int n, struct uio *uio)
{
  struct iovec *iov;
  u_int cnt;

  while (n > 0 && uio->uio_resid) {
    iov = uio->uio_iov;
    cnt = iov->iov_len;
    if (cnt == 0) {
      uio->uio_iov++;
      uio->uio_iovcnt--;
      continue;
    }
    if (cnt > n)
      cnt = n;

    bcopy(cp, iov->iov_base, cnt);

    iov->iov_base += cnt;
    iov->iov_len -= cnt;
    uio->uio_resid -= cnt;
    cp += cnt;
    n -= cnt;
  }
}
#endif /* AMITCP */

/*
 * Implement receive operations on a socket.
 * We depend on the way that records are added to the sockbuf
 * by sbappend*.  In particular, each record (mbufs linked through m_next)
 * must begin with an address if the protocol so specifies,
 * followed by an optional mbuf or mbufs containing ancillary data,
 * and then zero or more mbufs of data.
 * In order to avoid blocking network interrupts for the entire time here,
 * we splx() while doing the actual copy to user space.
 * Although the sockbuf is locked, new data may still be appended,
 * and thus we must maintain consistency of the sockbuf during that time.
 *
 * The caller may receive the data as a single mbuf chain by supplying
 * an mbuf **mp0 for use in returning the chain.  The uio is then used
 * only for the count in uio_resid.
 */
int
soreceive(so, paddr, uio, mp0, controlp, flagsp)
        register struct socket *so;
        struct mbuf **paddr;
        struct uio *uio;
        struct mbuf **mp0;
        struct mbuf **controlp;
        int *flagsp;
{
#ifndef AMITCP
        struct proc *p = (struct proc*)cthread_data(cthread_self());
#endif
        register struct mbuf *m, **mp;
        register int flags, len, error, offset;
        spl_t s;
        struct protosw *pr = so->so_proto;
        struct mbuf *nextrecord;
        int moff, type;

        mp = mp0;
        if (paddr)
                *paddr = 0;
        if (controlp)
                *controlp = 0;
        if (flagsp)
                flags = *flagsp &~ MSG_EOR;
        else
                flags = 0;
        if (flags & MSG_OOB) {
                m = m_get(M_WAIT, MT_DATA);
                error = (*pr->pr_usrreq)(so, PRU_RCVOOB,
                    m, (struct mbuf *)(long)(flags & MSG_PEEK), (struct mbuf *)0);
                if (error)
                        goto bad;

                do {
                        uiowrite(mtod(m, caddr_t),
                            (int) MIN(uio->uio_resid, m->m_len), uio);
                        m = m_free(m);
                } while (uio->uio_resid && error == 0 && m);

bad:
                if (m)
                        m_freem(m);
                return (error);
        }
        if (mp)
                *mp = (struct mbuf *)0;

        if (so->so_state & SS_ISCONFIRMING && uio->uio_resid)
                (*pr->pr_usrreq)(so, PRU_RCVD, (struct mbuf *)0,
                    (struct mbuf *)0, (struct mbuf *)0);


restart:
        if (error = sblock(&so->so_rcv, uio->uio_procp))
                return (error);
        s = splnet();

        m = so->so_rcv.sb_mb;
        /*
         * If we have less data than requested, block awaiting more
         * (subject to any timeout) if:
         *   1. the current count is less than the low water mark, or
         *   2. MSG_WAITALL is set, and it is possible to do the entire
         *      receive operation at once if we block (resid <= hiwat).
         * If MSG_WAITALL is set but resid is larger than the receive buffer,
         * we have to do the receive in sections, and thus risk returning
         * a short count if a timeout or signal occurs after we start.
         */

        while (m == 0 || (so->so_rcv.sb_cc < uio->uio_resid &&
                          (so->so_rcv.sb_cc < so->so_rcv.sb_lowat ||
                           ((flags & MSG_WAITALL)
                            && uio->uio_resid <= so->so_rcv.sb_hiwat)) &&
                          m->m_nextpkt == 0)) {
#if DIAGNOSTIC
                if (m == 0 && so->so_rcv.sb_cc)
                        panic("receive 1");
#endif
                if (so->so_error) {
                        if (m)
                                break;
                        error = so->so_error;
                        if ((flags & MSG_PEEK) == 0)
                                so->so_error = 0;
                        goto release;
                }
                if (so->so_state & SS_CANTRCVMORE) {
                        if (m)
                                break;
                        else
                                goto release;
                }
                for (; m; m = m->m_next)
                        if (m->m_type == MT_OOBDATA
#ifdef USE_M_EOR
  || (m->m_flags & M_EOR)
#endif
                            ) {
                                m = so->so_rcv.sb_mb;
                                goto dontblock;
                        }
                if ((so->so_state & (SS_ISCONNECTED|SS_ISCONNECTING)) == 0 &&
                    (so->so_proto->pr_flags & PR_CONNREQUIRED)) {
                        error = ENOTCONN;
                        goto release;
                }

                if (uio->uio_resid == 0)
                        goto release;

                if (so->so_state & SS_NBIO) {
                        error = EWOULDBLOCK;
                        goto release;
                }
                sbunlock(&so->so_rcv);
                error = sbwait(&so->so_rcv, uio->uio_procp);
                splx(s);
                if (error)
                        return (error);
                goto restart;
        }
dontblock:
#ifndef AMITCP
        p->p_stats->p_ru.ru_msgrcv++;
#endif
        nextrecord = m->m_nextpkt;
        if (pr->pr_flags & PR_ADDR) {
#if DIAGNOSTIC
                if (m->m_type != MT_SONAME)
                        panic("receive 1a");
#endif
                if (flags & MSG_PEEK) {
                        if (paddr)
                                *paddr = m_copy(m, 0, m->m_len);
                        m = m->m_next;
                } else {
                        sbfree(&so->so_rcv, m);
                        if (paddr) {
                                *paddr = m;
                                so->so_rcv.sb_mb = m->m_next;
                                m->m_next = 0;
                                m = so->so_rcv.sb_mb;
                        } else {
                                MFREE(m, so->so_rcv.sb_mb);
                                m = so->so_rcv.sb_mb;
                        }
                }
        }
        while (m && m->m_type == MT_CONTROL && error == 0) {
                if (flags & MSG_PEEK) {
                        if (controlp)
                                *controlp = m_copy(m, 0, m->m_len);
                        m = m->m_next;
                } else {
                        sbfree(&so->so_rcv, m);
                        if (controlp) {
                                if (pr->pr_domain->dom_externalize &&
                                    mtod(m, struct cmsghdr *)->cmsg_type ==
                                    SCM_RIGHTS)
                                   error = (*pr->pr_domain->dom_externalize)(m);
                                *controlp = m;
                                so->so_rcv.sb_mb = m->m_next;
                                m->m_next = 0;
                                m = so->so_rcv.sb_mb;
                        } else {
                                MFREE(m, so->so_rcv.sb_mb);
                                m = so->so_rcv.sb_mb;
                        }
                }
                if (controlp)
                        controlp = &(*controlp)->m_next;
        }
        if (m) {
                if ((flags & MSG_PEEK) == 0)
                        m->m_nextpkt = nextrecord;
                type = m->m_type;
                if (type == MT_OOBDATA)
                        flags |= MSG_OOB;
        }
        moff = 0;
        offset = 0;
        while (m &&  uio->uio_resid > 0 &&  error == 0) {
                if (m->m_type == MT_OOBDATA) {
                        if (type != MT_OOBDATA)
                                break;
                } else if (type == MT_OOBDATA)
                        break;
#if DIAGNOSTIC
                else if (m->m_type != MT_DATA && m->m_type != MT_HEADER)
                        panic("receive 3");
#endif
                so->so_state &= ~SS_RCVATMARK;

                len = uio->uio_resid;

                if (so->so_oobmark && len > so->so_oobmark - offset)
                        len = so->so_oobmark - offset;
                if (len > m->m_len - moff)
                        len = m->m_len - moff;
                /*
                 * If mp is set, just pass back the mbufs.
                 * Otherwise copy them out via the uio, then free.
                 * Sockbuf must be consistent here (points to current mbuf,
                 * it points to next record) when we drop priority;
                 * we must note any additions to the sockbuf when we
                 * block interrupts again.
                 */

                if (mp == 0) {
                        splx(s);
                        uiowrite(mtod(m, caddr_t) + moff, (int)len, uio);
                        s = splnet();
                } else
                        uio->uio_resid -= len;

                if (len == m->m_len - moff) {
#ifdef USE_M_EOR
                        if (m->m_flags & M_EOR)
                                flags |= MSG_EOR;
#endif
                        if (flags & MSG_PEEK) {
                                m = m->m_next;
                                moff = 0;
                        } else {
                                nextrecord = m->m_nextpkt;
                                sbfree(&so->so_rcv, m);
                                if (mp) {
                                        *mp = m;
                                        mp = &m->m_next;
                                        so->so_rcv.sb_mb = m = m->m_next;
                                        *mp = (struct mbuf *)0;
                                } else {
                                        MFREE(m, so->so_rcv.sb_mb);
                                        m = so->so_rcv.sb_mb;
                                }
                                if (m)
                                        m->m_nextpkt = nextrecord;
                        }
                } else {
                        if (flags & MSG_PEEK)
                                moff += len;
                        else {
                                if (mp)
                                        *mp = m_copym(m, 0, len, M_WAIT);
                                m->m_data += len;
                                m->m_len -= len;
                                so->so_rcv.sb_cc -= len;
                        }
                }
                if (so->so_oobmark) {
                        if ((flags & MSG_PEEK) == 0) {
                                so->so_oobmark -= len;
                                if (so->so_oobmark == 0) {
                                        so->so_state |= SS_RCVATMARK;
                                        break;
                                }
                        } else
                                offset += len;
                }
                if (flags & MSG_EOR)
                        break;
                /*
                 * If the MSG_WAITALL flag is set (for non-atomic socket),
                 * we must not quit until "uio->uio_resid == 0" or an error
                 * termination.  If a signal/timeout occurs, return
                 * with a short count but without error.
                 * Keep sockbuf locked against other readers.
                 */
                while (flags & MSG_WAITALL && m == 0 && uio->uio_resid > 0 &&
                       !sosendallatonce(so)) {
                        if (so->so_error || so->so_state & SS_CANTRCVMORE)
                                break;
                        error = sbwait(&so->so_rcv, uio->uio_procp);
                        if (error) {
                                sbunlock(&so->so_rcv);
                                splx(s);
                                return (0);
                        }
                        if (m = so->so_rcv.sb_mb)
                                nextrecord = m->m_nextpkt;
                }
        }
        if ((flags & MSG_PEEK) == 0) {
                if (m == 0)
                        so->so_rcv.sb_mb = nextrecord;
                else if (pr->pr_flags & PR_ATOMIC) {
                        flags |= MSG_TRUNC;
                        (void) sbdroprecord(&so->so_rcv);
                }
                if (pr->pr_flags & PR_WANTRCVD && so->so_pcb)
                        (*pr->pr_usrreq)(so, PRU_RCVD, (struct mbuf *)0,
                            (struct mbuf *)(long)flags, /* (struct mbuf *)0, */
                            (struct mbuf *)0); /* BUG! One extra arg! */
        }
        if (flagsp)
                *flagsp |= flags;
release:
        sbunlock(&so->so_rcv);
        splx(s);
        return (error);
}

int
soshutdown(so, how)
        register struct socket *so;
        register int how;
{
        register struct protosw *pr = so->so_proto;

        how++; /* now how: 1 - no receives, 2 - no sends, 3 - no either */
        if (how & 1)
          sorflush(so);
        if (how & 2)
          return ((*pr->pr_usrreq)(so, PRU_SHUTDOWN, (struct mbuf *)0, 
                                   (struct mbuf *)0, (struct mbuf *)0));
        return (0);
}

void
sorflush(so)
        register struct socket *so;
{
        register struct sockbuf *sb = &so->so_rcv;
        register struct protosw *pr = so->so_proto;
        register spl_t s;
        struct sockbuf asb;

        sb->sb_flags |= SB_NOINTR;
        (void) sblock(sb, NULL);
        s = splimp();
        socantrcvmore(so);
        sbunlock(sb);
        asb = *sb;
        aligned_bzero_const((caddr_t)sb, sizeof (*sb));
        splx(s);
        if (pr->pr_flags & PR_RIGHTS && pr->pr_domain->dom_dispose)
                (*pr->pr_domain->dom_dispose)(asb.sb_mb);
        sbrelease(&asb);
}

/*
 * in some fields of socket structure previous short fields of ticks are
 * changed to struct timeval fields. (actually so_linger and sb_timeo)
 * sosetopt() and sogetopt() does transformations needed for those.
 */

int
sosetopt(so, level, optname, m0)
        register struct socket *so;
        int level, optname;
        struct mbuf *m0;
{
        int error = 0;
        register struct mbuf *m = m0;

#ifdef ENABLE_TTCP_SHUTUP
        if ((optname == TCP_NOPUSH) && (level == IPPROTO_TCP)) {
                if (m == NULL || m->m_len < sizeof (int))
                        error = EINVAL;
                else {
                        if (*mtod(m, int *))
                                so->so_options |= SO_TTCP_SHUTUP;
                        else
                                so->so_options &= ~SO_TTCP_SHUTUP;
                }
                goto bad;
        }
#endif
        if (level != SOL_SOCKET) {
                if (so->so_proto && so->so_proto->pr_ctloutput)
                        return ((*so->so_proto->pr_ctloutput)
                                  (PRCO_SETOPT, so, level, optname, &m0));
                error = ENOPROTOOPT;
        } else {
                switch (optname) {

                case SO_LINGER:
                        if (m == NULL || m->m_len != sizeof (struct linger)) {
                                error = EINVAL;
                                goto bad;
                        }
                        {
                          int val = mtod(m, struct linger *)->l_linger;
#ifdef AMITCP
                          /*
                           * l_linger is in seconds
                           */
                          so->so_linger.tv_sec = val;
                          so->so_linger.tv_usec = 0;
#else
                          so->so_linger.tv_sec = val / hz;
                          so->so_linger.tv_usec = (val % hz) * tick;
#endif
                        }
                        /* fall thru... */

                case SO_DEBUG:
                case SO_KEEPALIVE:
                case SO_DONTROUTE:
                case SO_USELOOPBACK:
                case SO_BROADCAST:
                case SO_REUSEADDR:
                case SO_REUSEPORT:
                case SO_OOBINLINE:
                        if (m == NULL || m->m_len < sizeof (int)) {
                                error = EINVAL;
                                goto bad;
                        }
                        if (*mtod(m, int *))
                                so->so_options |= optname;
                        else
                                so->so_options &= ~optname;
                        break;

                case SO_SNDBUF:
                case SO_RCVBUF:
                case SO_SNDLOWAT:
                case SO_RCVLOWAT:
                case SO_EVENTMASK:
                        if (m == NULL || m->m_len < sizeof (int)) {
                                error = EINVAL;
                                goto bad;
                        }
                        switch (optname) {

                        case SO_SNDBUF:
                        case SO_RCVBUF:
                                if (sbreserve(optname == SO_SNDBUF ?
                                    &so->so_snd : &so->so_rcv,
                                    (u_long) *mtod(m, int *)) == 0) {
                                        error = ENOBUFS;
                                        goto bad;
                                }
                                break;

                        case SO_SNDLOWAT:
                                so->so_snd.sb_lowat = *mtod(m, int *);
                                break;
                        case SO_RCVLOWAT:
                                so->so_rcv.sb_lowat = *mtod(m, int *);
                                break;
                        case SO_EVENTMASK:
                                so->so_eventmask = *mtod(m, int *);
                                so->so_state |= SS_ASYNC;
                                so->so_rcv.sb_flags |= SB_ASYNC;
                                so->so_snd.sb_flags |= SB_ASYNC;
                                DEVENTS(log(LOG_DEBUG, "Setting SO_EVENTMASK = 0x%08lx", so->so_eventmask);)
                        }
                        break;

                case SO_SNDTIMEO:
                case SO_RCVTIMEO:
                    {
                        struct timeval *tv;

                        if (m == NULL || m->m_len < sizeof (*tv)) {
                                error = EINVAL;
                                goto bad;
                        }
                        tv = mtod(m, struct timeval *);

                        switch (optname) {

                        case SO_SNDTIMEO:
                                so->so_snd.sb_timeo = *tv;
                                break;
                        case SO_RCVTIMEO:
                                so->so_rcv.sb_timeo = *tv;
                                break;
                        }
                        break;
                    }

                default:
                        error = ENOPROTOOPT;
                        break;
                }
        }
bad:
        if (m)
                (void) m_free(m);
        return (error);
}

int
sogetopt(so, level, optname, mp)
        register struct socket *so;
        int level, optname;
        struct mbuf **mp;
{
        register struct mbuf *m;

        if (level != SOL_SOCKET) {
                if (so->so_proto && so->so_proto->pr_ctloutput) {
                        return ((*so->so_proto->pr_ctloutput)
                                  (PRCO_GETOPT, so, level, optname, mp));
                } else
                        return (ENOPROTOOPT);
        } else {
                m = m_get(M_WAIT, MT_SOOPTS);
                m->m_len = sizeof (int);

                switch (optname) {

                case SO_LINGER:
                        m->m_len = sizeof (struct linger);
                        mtod(m, struct linger *)->l_onoff =
                                so->so_options & SO_LINGER;
                        mtod(m, struct linger *)->l_linger =
#ifndef AMITCP
                          so->so_linger.tv_sec * hz +
                            so->so_linger.tv_usec / tick;
#else
                        /*
                         * l_linger is in seconds
                         */
                          so->so_linger.tv_sec;
#endif                  
                        break;

                case SO_USELOOPBACK:
                case SO_DONTROUTE:
                case SO_DEBUG:
                case SO_KEEPALIVE:
                case SO_REUSEADDR:
                case SO_REUSEPORT:
                case SO_BROADCAST:
                case SO_OOBINLINE:
                        *mtod(m, int *) = so->so_options & optname;
                        break;

                case SO_TYPE:
                        *mtod(m, int *) = so->so_type;
                        break;

                case SO_ERROR:
                        *mtod(m, int *) = so->so_error;
                        so->so_error = 0;
                        break;

                case SO_SNDBUF:
                        *mtod(m, int *) = so->so_snd.sb_hiwat;
                        break;

                case SO_RCVBUF:
                        *mtod(m, int *) = so->so_rcv.sb_hiwat;
                        break;

                case SO_SNDLOWAT:
                        *mtod(m, int *) = so->so_snd.sb_lowat;
                        break;

                case SO_RCVLOWAT:
                        *mtod(m, int *) = so->so_rcv.sb_lowat;
                        break;

                case SO_EVENTMASK:
                        DEVENTS(log(LOG_DEBUG, "Getting SO_EVENTMASK = 0x%08lx", so->so_eventmask);)
                        *mtod(m, int *) = so->so_eventmask;
                        break;

                case SO_SNDTIMEO:
                case SO_RCVTIMEO:
                    {
                        struct timeval *tv= (optname == SO_SNDTIMEO ?
                             &so->so_snd.sb_timeo : &so->so_rcv.sb_timeo);

                        m->m_len = sizeof(struct timeval);
                        mtod(m, struct timeval *)->tv_sec = tv->tv_sec;
                        mtod(m, struct timeval *)->tv_usec = tv->tv_usec;
                        break;
                    }

                default:
                        (void)m_free(m);
                        return (ENOPROTOOPT);
                }
                *mp = m;
                return (0);
        }
}

void
sohasoutofband(so)
        register struct socket *so;
{
#ifdef AMITCP
        if (so->so_pgid)
                Signal(so->so_pgid->thisTask, so->so_pgid->sigUrgMask);
        soevent(so, FD_OOB);
#else
        struct proc *p;

        if (so->so_pgid < 0)
                gsignal(-so->so_pgid, SIGURG);
        else if (so->so_pgid > 0 && (p = pfind(so->so_pgid)) != 0)
                psignal(p, SIGURG);
#endif
        if (so->so_rcv.sb_flags & SB_SEL) {
                so->so_rcv.sb_flags &= ~SB_SEL; /* do not notify us any more */
                selwakeup(&so->so_rcv.sb_sel);
        }
}