mirror/freebsd
1
0
Fork 0
mirror of https://git.FreeBSD.org/src.git synced 2024-12-20 11:11:24 +00:00
Code Issues Releases Activity
c1f192193d
freebsd/sys/net/if_tap.c
Konstantin Belousov d8b0556c6d Adapt vfs kqfilter to the shared vnode lock used by zfs write vop. Use 
vnode interlock to protect the knote fields [1]. The locking assumes
that shared vnode lock is held, thus we get exclusive access to knote
either by exclusive vnode lock protection, or by shared vnode lock +
vnode interlock.

Do not use kl_locked() method to assert either lock ownership or the
fact that curthread does not own the lock. For shared locks, ownership
is not recorded, e.g. VOP_ISLOCKED can return LK_SHARED for the shared
lock not owned by curthread, causing false positives in kqueue subsystem
assertions about knlist lock.

Remove kl_locked method from knlist lock vector, and add two separate
assertion methods kl_assert_locked and kl_assert_unlocked, that are
supposed to use proper asserts. Change knlist_init accordingly.

Add convenience function knlist_init_mtx to reduce number of arguments
for typical knlist initialization.

Submitted by:	jhb [1]
Noted by:	jhb [2]
Reviewed by:	jhb
Tested by:	rnoland
2009-06-10 20:59:32 +00:00

1116 lines
25 KiB
C
Raw Blame History

/*-
* Copyright (C) 1999-2000 by Maksim Yevmenkin <m_evmenkin@yahoo.com>
* 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.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 AUTHOR 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.
*
* BASED ON:
* -------------------------------------------------------------------------
*
* Copyright (c) 1988, Julian Onions <jpo@cs.nott.ac.uk>
* Nottingham University 1987.
*/
/*
* $FreeBSD$
* $Id: if_tap.c,v 0.21 2000/07/23 21:46:02 max Exp $
*/
#include "opt_compat.h"
#include "opt_inet.h"
#include <sys/param.h>
#include <sys/conf.h>
#include <sys/fcntl.h>
#include <sys/filio.h>
#include <sys/kernel.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/module.h>
#include <sys/poll.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/selinfo.h>
#include <sys/signalvar.h>
#include <sys/socket.h>
#include <sys/sockio.h>
#include <sys/sysctl.h>
#include <sys/systm.h>
#include <sys/ttycom.h>
#include <sys/uio.h>
#include <sys/queue.h>
#include <net/bpf.h>
#include <net/ethernet.h>
#include <net/if.h>
#include <net/if_clone.h>
#include <net/if_dl.h>
#include <net/route.h>
#include <net/if_types.h>
#include <netinet/in.h>
#include <net/if_tapvar.h>
#include <net/if_tap.h>
#define CDEV_NAME "tap"
#define TAPDEBUG if (tapdebug) printf
#define TAP "tap"
#define VMNET "vmnet"
#define TAPMAXUNIT 0x7fff
#define VMNET_DEV_MASK CLONE_FLAG0
/* module */
static int tapmodevent(module_t, int, void *);
/* device */
static void tapclone(void *, struct ucred *, char *, int,
struct cdev **);
static void tapcreate(struct cdev *);
/* network interface */
static void tapifstart(struct ifnet *);
static int tapifioctl(struct ifnet *, u_long, caddr_t);
static void tapifinit(void *);
static int tap_clone_create(struct if_clone *, int, caddr_t);
static void tap_clone_destroy(struct ifnet *);
static int vmnet_clone_create(struct if_clone *, int, caddr_t);
static void vmnet_clone_destroy(struct ifnet *);
IFC_SIMPLE_DECLARE(tap, 0);
IFC_SIMPLE_DECLARE(vmnet, 0);
/* character device */
static d_open_t tapopen;
static d_close_t tapclose;
static d_read_t tapread;
static d_write_t tapwrite;
static d_ioctl_t tapioctl;
static d_poll_t tappoll;
static d_kqfilter_t tapkqfilter;
/* kqueue(2) */
static int tapkqread(struct knote *, long);
static int tapkqwrite(struct knote *, long);
static void tapkqdetach(struct knote *);
static struct filterops tap_read_filterops = {
.f_isfd = 1,
.f_attach = NULL,
.f_detach = tapkqdetach,
.f_event = tapkqread,
};
static struct filterops tap_write_filterops = {
.f_isfd = 1,
.f_attach = NULL,
.f_detach = tapkqdetach,
.f_event = tapkqwrite,
};
static struct cdevsw tap_cdevsw = {
.d_version = D_VERSION,
.d_flags = D_PSEUDO | D_NEEDGIANT | D_NEEDMINOR,
.d_open = tapopen,
.d_close = tapclose,
.d_read = tapread,
.d_write = tapwrite,
.d_ioctl = tapioctl,
.d_poll = tappoll,
.d_name = CDEV_NAME,
.d_kqfilter = tapkqfilter,
};
/*
* All global variables in if_tap.c are locked with tapmtx, with the
* exception of tapdebug, which is accessed unlocked; tapclones is
* static at runtime.
*/
static struct mtx tapmtx;
static int tapdebug = 0; /* debug flag */
static int tapuopen = 0; /* allow user open() */
static int tapuponopen = 0; /* IFF_UP on open() */
static int tapdclone = 1; /* enable devfs cloning */
static SLIST_HEAD(, tap_softc) taphead; /* first device */
static struct clonedevs *tapclones;
MALLOC_DECLARE(M_TAP);
MALLOC_DEFINE(M_TAP, CDEV_NAME, "Ethernet tunnel interface");
SYSCTL_INT(_debug, OID_AUTO, if_tap_debug, CTLFLAG_RW, &tapdebug, 0, "");
SYSCTL_DECL(_net_link);
SYSCTL_NODE(_net_link, OID_AUTO, tap, CTLFLAG_RW, 0,
"Ethernet tunnel software network interface");
SYSCTL_INT(_net_link_tap, OID_AUTO, user_open, CTLFLAG_RW, &tapuopen, 0,
"Allow user to open /dev/tap (based on node permissions)");
SYSCTL_INT(_net_link_tap, OID_AUTO, up_on_open, CTLFLAG_RW, &tapuponopen, 0,
"Bring interface up when /dev/tap is opened");
SYSCTL_INT(_net_link_tap, OID_AUTO, devfs_cloning, CTLFLAG_RW, &tapdclone, 0,
"Enably legacy devfs interface creation");
SYSCTL_INT(_net_link_tap, OID_AUTO, debug, CTLFLAG_RW, &tapdebug, 0, "");
TUNABLE_INT("net.link.tap.devfs_cloning", &tapdclone);
DEV_MODULE(if_tap, tapmodevent, NULL);
static int
tap_clone_create(struct if_clone *ifc, int unit, caddr_t params)
{
struct cdev *dev;
int i;
int extra;
if (strcmp(ifc->ifc_name, VMNET) == 0)
extra = VMNET_DEV_MASK;
else
extra = 0;
/* find any existing device, or allocate new unit number */
i = clone_create(&tapclones, &tap_cdevsw, &unit, &dev, extra);
if (i) {
dev = make_dev(&tap_cdevsw, unit | extra,
UID_ROOT, GID_WHEEL, 0600, "%s%d", ifc->ifc_name, unit);
if (dev != NULL) {
dev_ref(dev);
dev->si_flags |= SI_CHEAPCLONE;
}
}
tapcreate(dev);
return (0);
}
/* vmnet devices are tap devices in disguise */
static int
vmnet_clone_create(struct if_clone *ifc, int unit, caddr_t params)
{
return tap_clone_create(ifc, unit, params);
}
static void
tap_destroy(struct tap_softc *tp)
{
struct ifnet *ifp = tp->tap_ifp;
int s;
/* Unlocked read. */
KASSERT(!(tp->tap_flags & TAP_OPEN),
("%s flags is out of sync", ifp->if_xname));
knlist_destroy(&tp->tap_rsel.si_note);
destroy_dev(tp->tap_dev);
s = splimp();
ether_ifdetach(ifp);
if_free_type(ifp, IFT_ETHER);
splx(s);
mtx_destroy(&tp->tap_mtx);
free(tp, M_TAP);
}
static void
tap_clone_destroy(struct ifnet *ifp)
{
struct tap_softc *tp = ifp->if_softc;
mtx_lock(&tapmtx);
SLIST_REMOVE(&taphead, tp, tap_softc, tap_next);
mtx_unlock(&tapmtx);
tap_destroy(tp);
}
/* vmnet devices are tap devices in disguise */
static void
vmnet_clone_destroy(struct ifnet *ifp)
{
tap_clone_destroy(ifp);
}
/*
* tapmodevent
*
* module event handler
*/
static int
tapmodevent(module_t mod, int type, void *data)
{
static eventhandler_tag eh_tag = NULL;
struct tap_softc *tp = NULL;
struct ifnet *ifp = NULL;
switch (type) {
case MOD_LOAD:
/* intitialize device */
mtx_init(&tapmtx, "tapmtx", NULL, MTX_DEF);
SLIST_INIT(&taphead);
clone_setup(&tapclones);
eh_tag = EVENTHANDLER_REGISTER(dev_clone, tapclone, 0, 1000);
if (eh_tag == NULL) {
clone_cleanup(&tapclones);
mtx_destroy(&tapmtx);
return (ENOMEM);
}
if_clone_attach(&tap_cloner);
if_clone_attach(&vmnet_cloner);
return (0);
case MOD_UNLOAD:
/*
* The EBUSY algorithm here can't quite atomically
* guarantee that this is race-free since we have to
* release the tap mtx to deregister the clone handler.
*/
mtx_lock(&tapmtx);
SLIST_FOREACH(tp, &taphead, tap_next) {
mtx_lock(&tp->tap_mtx);
if (tp->tap_flags & TAP_OPEN) {
mtx_unlock(&tp->tap_mtx);
mtx_unlock(&tapmtx);
return (EBUSY);
}
mtx_unlock(&tp->tap_mtx);
}
mtx_unlock(&tapmtx);
EVENTHANDLER_DEREGISTER(dev_clone, eh_tag);
if_clone_detach(&tap_cloner);
if_clone_detach(&vmnet_cloner);
mtx_lock(&tapmtx);
while ((tp = SLIST_FIRST(&taphead)) != NULL) {
SLIST_REMOVE_HEAD(&taphead, tap_next);
mtx_unlock(&tapmtx);
ifp = tp->tap_ifp;
TAPDEBUG("detaching %s\n", ifp->if_xname);
tap_destroy(tp);
mtx_lock(&tapmtx);
}
mtx_unlock(&tapmtx);
clone_cleanup(&tapclones);
mtx_destroy(&tapmtx);
break;
default:
return (EOPNOTSUPP);
}
return (0);
} /* tapmodevent */
/*
* DEVFS handler
*
* We need to support two kind of devices - tap and vmnet
*/
static void
tapclone(void *arg, struct ucred *cred, char *name, int namelen, struct cdev **dev)
{
char devname[SPECNAMELEN + 1];
int i, unit, append_unit;
int extra;
if (*dev != NULL)
return;
if (!tapdclone ||
(!tapuopen && priv_check_cred(cred, PRIV_NET_IFCREATE, 0) != 0))
return;
unit = 0;
append_unit = 0;
extra = 0;
/* We're interested in only tap/vmnet devices. */
if (strcmp(name, TAP) == 0) {
unit = -1;
} else if (strcmp(name, VMNET) == 0) {
unit = -1;
extra = VMNET_DEV_MASK;
} else if (dev_stdclone(name, NULL, TAP, &unit) != 1) {
if (dev_stdclone(name, NULL, VMNET, &unit) != 1) {
return;
} else {
extra = VMNET_DEV_MASK;
}
}
if (unit == -1)
append_unit = 1;
/* find any existing device, or allocate new unit number */
i = clone_create(&tapclones, &tap_cdevsw, &unit, dev, extra);
if (i) {
if (append_unit) {
/*
* We were passed 'tun' or 'tap', with no unit specified
* so we'll need to append it now.
*/
namelen = snprintf(devname, sizeof(devname), "%s%d", name,
unit);
name = devname;
}
*dev = make_dev(&tap_cdevsw, unit | extra,
UID_ROOT, GID_WHEEL, 0600, "%s", name);
if (*dev != NULL) {
dev_ref(*dev);
(*dev)->si_flags |= SI_CHEAPCLONE;
}
}
if_clone_create(name, namelen, NULL);
} /* tapclone */
/*
* tapcreate
*
* to create interface
*/
static void
tapcreate(struct cdev *dev)
{
struct ifnet *ifp = NULL;
struct tap_softc *tp = NULL;
unsigned short macaddr_hi;
uint32_t macaddr_mid;
int unit, s;
char *name = NULL;
u_char eaddr[6];
dev->si_flags &= ~SI_CHEAPCLONE;
/* allocate driver storage and create device */
tp = malloc(sizeof(*tp), M_TAP, M_WAITOK | M_ZERO);
mtx_init(&tp->tap_mtx, "tap_mtx", NULL, MTX_DEF);
mtx_lock(&tapmtx);
SLIST_INSERT_HEAD(&taphead, tp, tap_next);
mtx_unlock(&tapmtx);
unit = dev2unit(dev);
/* select device: tap or vmnet */
if (unit & VMNET_DEV_MASK) {
name = VMNET;
tp->tap_flags |= TAP_VMNET;
} else
name = TAP;
unit &= TAPMAXUNIT;
TAPDEBUG("tapcreate(%s%d). minor = %#x\n", name, unit, dev2unit(dev));
/* generate fake MAC address: 00 bd xx xx xx unit_no */
macaddr_hi = htons(0x00bd);
macaddr_mid = (uint32_t) ticks;
bcopy(&macaddr_hi, eaddr, sizeof(short));
bcopy(&macaddr_mid, &eaddr[2], sizeof(uint32_t));
eaddr[5] = (u_char)unit;
/* fill the rest and attach interface */
ifp = tp->tap_ifp = if_alloc(IFT_ETHER);
if (ifp == NULL)
panic("%s%d: can not if_alloc()", name, unit);
ifp->if_softc = tp;
if_initname(ifp, name, unit);
ifp->if_init = tapifinit;
ifp->if_start = tapifstart;
ifp->if_ioctl = tapifioctl;
ifp->if_mtu = ETHERMTU;
ifp->if_flags = (IFF_BROADCAST|IFF_SIMPLEX|IFF_MULTICAST);
ifp->if_snd.ifq_maxlen = ifqmaxlen;
dev->si_drv1 = tp;
tp->tap_dev = dev;
s = splimp();
ether_ifattach(ifp, eaddr);
splx(s);
mtx_lock(&tp->tap_mtx);
tp->tap_flags |= TAP_INITED;
mtx_unlock(&tp->tap_mtx);
knlist_init_mtx(&tp->tap_rsel.si_note, NULL);
TAPDEBUG("interface %s is created. minor = %#x\n",
ifp->if_xname, dev2unit(dev));
} /* tapcreate */
/*
* tapopen
*
* to open tunnel. must be superuser
*/
static int
tapopen(struct cdev *dev, int flag, int mode, struct thread *td)
{
struct tap_softc *tp = NULL;
struct ifnet *ifp = NULL;
int error, s;
if (tapuopen == 0) {
error = priv_check(td, PRIV_NET_TAP);
if (error)
return (error);
}
if ((dev2unit(dev) & CLONE_UNITMASK) > TAPMAXUNIT)
return (ENXIO);
tp = dev->si_drv1;
mtx_lock(&tp->tap_mtx);
if (tp->tap_flags & TAP_OPEN) {
mtx_unlock(&tp->tap_mtx);
return (EBUSY);
}
bcopy(IF_LLADDR(tp->tap_ifp), tp->ether_addr, sizeof(tp->ether_addr));
tp->tap_pid = td->td_proc->p_pid;
tp->tap_flags |= TAP_OPEN;
ifp = tp->tap_ifp;
mtx_unlock(&tp->tap_mtx);
s = splimp();
ifp->if_drv_flags |= IFF_DRV_RUNNING;
ifp->if_drv_flags &= ~IFF_DRV_OACTIVE;
if (tapuponopen)
ifp->if_flags |= IFF_UP;
splx(s);
TAPDEBUG("%s is open. minor = %#x\n", ifp->if_xname, dev2unit(dev));
return (0);
} /* tapopen */
/*
* tapclose
*
* close the device - mark i/f down & delete routing info
*/
static int
tapclose(struct cdev *dev, int foo, int bar, struct thread *td)
{
struct ifaddr *ifa;
struct tap_softc *tp = dev->si_drv1;
struct ifnet *ifp = tp->tap_ifp;
int s;
/* junk all pending output */
IF_DRAIN(&ifp->if_snd);
/*
* do not bring the interface down, and do not anything with
* interface, if we are in VMnet mode. just close the device.
*/
mtx_lock(&tp->tap_mtx);
if (((tp->tap_flags & TAP_VMNET) == 0) && (ifp->if_flags & IFF_UP)) {
mtx_unlock(&tp->tap_mtx);
s = splimp();
if_down(ifp);
if (ifp->if_drv_flags & IFF_DRV_RUNNING) {
TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
rtinit(ifa, (int)RTM_DELETE, 0);
}
if_purgeaddrs(ifp);
ifp->if_drv_flags &= ~IFF_DRV_RUNNING;
}
splx(s);
} else
mtx_unlock(&tp->tap_mtx);
funsetown(&tp->tap_sigio);
selwakeuppri(&tp->tap_rsel, PZERO+1);
KNOTE_UNLOCKED(&tp->tap_rsel.si_note, 0);
mtx_lock(&tp->tap_mtx);
tp->tap_flags &= ~TAP_OPEN;
tp->tap_pid = 0;
mtx_unlock(&tp->tap_mtx);
TAPDEBUG("%s is closed. minor = %#x\n",
ifp->if_xname, dev2unit(dev));
return (0);
} /* tapclose */
/*
* tapifinit
*
* network interface initialization function
*/
static void
tapifinit(void *xtp)
{
struct tap_softc *tp = (struct tap_softc *)xtp;
struct ifnet *ifp = tp->tap_ifp;
TAPDEBUG("initializing %s\n", ifp->if_xname);
ifp->if_drv_flags |= IFF_DRV_RUNNING;
ifp->if_drv_flags &= ~IFF_DRV_OACTIVE;
/* attempt to start output */
tapifstart(ifp);
} /* tapifinit */
/*
* tapifioctl
*
* Process an ioctl request on network interface
*/
static int
tapifioctl(struct ifnet *ifp, u_long cmd, caddr_t data)
{
struct tap_softc *tp = ifp->if_softc;
struct ifreq *ifr = (struct ifreq *)data;
struct ifstat *ifs = NULL;
int s, dummy;
switch (cmd) {
case SIOCSIFFLAGS: /* XXX -- just like vmnet does */
case SIOCADDMULTI:
case SIOCDELMULTI:
break;
case SIOCSIFMTU:
ifp->if_mtu = ifr->ifr_mtu;
break;
case SIOCGIFSTATUS:
s = splimp();
ifs = (struct ifstat *)data;
dummy = strlen(ifs->ascii);
mtx_lock(&tp->tap_mtx);
if (tp->tap_pid != 0 && dummy < sizeof(ifs->ascii))
snprintf(ifs->ascii + dummy,
sizeof(ifs->ascii) - dummy,
"\tOpened by PID %d\n", tp->tap_pid);
mtx_unlock(&tp->tap_mtx);
splx(s);
break;
default:
s = splimp();
dummy = ether_ioctl(ifp, cmd, data);
splx(s);
return (dummy);
/* NOT REACHED */
}
return (0);
} /* tapifioctl */
/*
* tapifstart
*
* queue packets from higher level ready to put out
*/
static void
tapifstart(struct ifnet *ifp)
{
struct tap_softc *tp = ifp->if_softc;
int s;
TAPDEBUG("%s starting\n", ifp->if_xname);
/*
* do not junk pending output if we are in VMnet mode.
* XXX: can this do any harm because of queue overflow?
*/
mtx_lock(&tp->tap_mtx);
if (((tp->tap_flags & TAP_VMNET) == 0) &&
((tp->tap_flags & TAP_READY) != TAP_READY)) {
struct mbuf *m = NULL;
mtx_unlock(&tp->tap_mtx);
/* Unlocked read. */
TAPDEBUG("%s not ready, tap_flags = 0x%x\n", ifp->if_xname,
tp->tap_flags);
s = splimp();
do {
IF_DEQUEUE(&ifp->if_snd, m);
if (m != NULL)
m_freem(m);
ifp->if_oerrors ++;
} while (m != NULL);
splx(s);
return;
}
mtx_unlock(&tp->tap_mtx);
s = splimp();
ifp->if_drv_flags |= IFF_DRV_OACTIVE;
if (ifp->if_snd.ifq_len != 0) {
mtx_lock(&tp->tap_mtx);
if (tp->tap_flags & TAP_RWAIT) {
tp->tap_flags &= ~TAP_RWAIT;
wakeup(tp);
}
if ((tp->tap_flags & TAP_ASYNC) && (tp->tap_sigio != NULL)) {
mtx_unlock(&tp->tap_mtx);
pgsigio(&tp->tap_sigio, SIGIO, 0);
} else
mtx_unlock(&tp->tap_mtx);
selwakeuppri(&tp->tap_rsel, PZERO+1);
KNOTE_UNLOCKED(&tp->tap_rsel.si_note, 0);
ifp->if_opackets ++; /* obytes are counted in ether_output */
}
ifp->if_drv_flags &= ~IFF_DRV_OACTIVE;
splx(s);
} /* tapifstart */
/*
* tapioctl
*
* the cdevsw interface is now pretty minimal
*/
static int
tapioctl(struct cdev *dev, u_long cmd, caddr_t data, int flag, struct thread *td)
{
struct tap_softc *tp = dev->si_drv1;
struct ifnet *ifp = tp->tap_ifp;
struct tapinfo *tapp = NULL;
int s;
int f;
#if defined(COMPAT_FREEBSD6) || defined(COMPAT_FREEBSD5) || \
defined(COMPAT_FREEBSD4)
int ival;
#endif
switch (cmd) {
case TAPSIFINFO:
s = splimp();
tapp = (struct tapinfo *)data;
ifp->if_mtu = tapp->mtu;
ifp->if_type = tapp->type;
ifp->if_baudrate = tapp->baudrate;
splx(s);
break;
case TAPGIFINFO:
tapp = (struct tapinfo *)data;
tapp->mtu = ifp->if_mtu;
tapp->type = ifp->if_type;
tapp->baudrate = ifp->if_baudrate;
break;
case TAPSDEBUG:
tapdebug = *(int *)data;
break;
case TAPGDEBUG:
*(int *)data = tapdebug;
break;
case TAPGIFNAME: {
struct ifreq *ifr = (struct ifreq *) data;
strlcpy(ifr->ifr_name, ifp->if_xname, IFNAMSIZ);
} break;
case FIONBIO:
break;
case FIOASYNC:
s = splimp();
mtx_lock(&tp->tap_mtx);
if (*(int *)data)
tp->tap_flags |= TAP_ASYNC;
else
tp->tap_flags &= ~TAP_ASYNC;
mtx_unlock(&tp->tap_mtx);
splx(s);
break;
case FIONREAD:
s = splimp();
if (ifp->if_snd.ifq_head) {
struct mbuf *mb = ifp->if_snd.ifq_head;
for(*(int *)data = 0;mb != NULL;mb = mb->m_next)
*(int *)data += mb->m_len;
} else
*(int *)data = 0;
splx(s);
break;
case FIOSETOWN:
return (fsetown(*(int *)data, &tp->tap_sigio));
case FIOGETOWN:
*(int *)data = fgetown(&tp->tap_sigio);
return (0);
/* this is deprecated, FIOSETOWN should be used instead */
case TIOCSPGRP:
return (fsetown(-(*(int *)data), &tp->tap_sigio));
/* this is deprecated, FIOGETOWN should be used instead */
case TIOCGPGRP:
*(int *)data = -fgetown(&tp->tap_sigio);
return (0);
/* VMware/VMnet port ioctl's */
case SIOCGIFFLAGS: /* get ifnet flags */
bcopy(&ifp->if_flags, data, sizeof(ifp->if_flags));
break;
#if defined(COMPAT_FREEBSD6) || defined(COMPAT_FREEBSD5) || \
defined(COMPAT_FREEBSD4)
case _IO('V', 0):
ival = IOCPARM_IVAL(data);
data = (caddr_t)&ival;
/* FALLTHROUGH */
#endif
case VMIO_SIOCSIFFLAGS: /* VMware/VMnet SIOCSIFFLAGS */
f = *(int *)data;
f &= 0x0fff;
f &= ~IFF_CANTCHANGE;
f |= IFF_UP;
s = splimp();
ifp->if_flags = f | (ifp->if_flags & IFF_CANTCHANGE);
splx(s);
break;
case OSIOCGIFADDR: /* get MAC address of the remote side */
case SIOCGIFADDR:
mtx_lock(&tp->tap_mtx);
bcopy(tp->ether_addr, data, sizeof(tp->ether_addr));
mtx_unlock(&tp->tap_mtx);
break;
case SIOCSIFADDR: /* set MAC address of the remote side */
mtx_lock(&tp->tap_mtx);
bcopy(data, tp->ether_addr, sizeof(tp->ether_addr));
mtx_unlock(&tp->tap_mtx);
break;
default:
return (ENOTTY);
}
return (0);
} /* tapioctl */
/*
* tapread
*
* the cdevsw read interface - reads a packet at a time, or at
* least as much of a packet as can be read
*/
static int
tapread(struct cdev *dev, struct uio *uio, int flag)
{
struct tap_softc *tp = dev->si_drv1;
struct ifnet *ifp = tp->tap_ifp;
struct mbuf *m = NULL;
int error = 0, len, s;
TAPDEBUG("%s reading, minor = %#x\n", ifp->if_xname, dev2unit(dev));
mtx_lock(&tp->tap_mtx);
if ((tp->tap_flags & TAP_READY) != TAP_READY) {
mtx_unlock(&tp->tap_mtx);
/* Unlocked read. */
TAPDEBUG("%s not ready. minor = %#x, tap_flags = 0x%x\n",
ifp->if_xname, dev2unit(dev), tp->tap_flags);
return (EHOSTDOWN);
}
tp->tap_flags &= ~TAP_RWAIT;
mtx_unlock(&tp->tap_mtx);
/* sleep until we get a packet */
do {
s = splimp();
IF_DEQUEUE(&ifp->if_snd, m);
splx(s);
if (m == NULL) {
if (flag & O_NONBLOCK)
return (EWOULDBLOCK);
mtx_lock(&tp->tap_mtx);
tp->tap_flags |= TAP_RWAIT;
mtx_unlock(&tp->tap_mtx);
error = tsleep(tp,PCATCH|(PZERO+1),"taprd",0);
if (error)
return (error);
}
} while (m == NULL);
/* feed packet to bpf */
BPF_MTAP(ifp, m);
/* xfer packet to user space */
while ((m != NULL) && (uio->uio_resid > 0) && (error == 0)) {
len = min(uio->uio_resid, m->m_len);
if (len == 0)
break;
error = uiomove(mtod(m, void *), len, uio);
m = m_free(m);
}
if (m != NULL) {
TAPDEBUG("%s dropping mbuf, minor = %#x\n", ifp->if_xname,
dev2unit(dev));
m_freem(m);
}
return (error);
} /* tapread */
/*
* tapwrite
*
* the cdevsw write interface - an atomic write is a packet - or else!
*/
static int
tapwrite(struct cdev *dev, struct uio *uio, int flag)
{
struct ether_header *eh;
struct tap_softc *tp = dev->si_drv1;
struct ifnet *ifp = tp->tap_ifp;
struct mbuf *m;
TAPDEBUG("%s writting, minor = %#x\n",
ifp->if_xname, dev2unit(dev));
if (uio->uio_resid == 0)
return (0);
if ((uio->uio_resid < 0) || (uio->uio_resid > TAPMRU)) {
TAPDEBUG("%s invalid packet len = %d, minor = %#x\n",
ifp->if_xname, uio->uio_resid, dev2unit(dev));
return (EIO);
}
if ((m = m_uiotombuf(uio, M_DONTWAIT, 0, ETHER_ALIGN,
M_PKTHDR)) == NULL) {
ifp->if_ierrors ++;
return (ENOBUFS);
}
m->m_pkthdr.rcvif = ifp;
/*
* Only pass a unicast frame to ether_input(), if it would actually
* have been received by non-virtual hardware.
*/
if (m->m_len < sizeof(struct ether_header)) {
m_freem(m);
return (0);
}
eh = mtod(m, struct ether_header *);
if (eh && (ifp->if_flags & IFF_PROMISC) == 0 &&
!ETHER_IS_MULTICAST(eh->ether_dhost) &&
bcmp(eh->ether_dhost, IF_LLADDR(ifp), ETHER_ADDR_LEN) != 0) {
m_freem(m);
return (0);
}
/* Pass packet up to parent. */
(*ifp->if_input)(ifp, m);
ifp->if_ipackets ++; /* ibytes are counted in parent */
return (0);
} /* tapwrite */
/*
* tappoll
*
* the poll interface, this is only useful on reads
* really. the write detect always returns true, write never blocks
* anyway, it either accepts the packet or drops it
*/
static int
tappoll(struct cdev *dev, int events, struct thread *td)
{
struct tap_softc *tp = dev->si_drv1;
struct ifnet *ifp = tp->tap_ifp;
int s, revents = 0;
TAPDEBUG("%s polling, minor = %#x\n",
ifp->if_xname, dev2unit(dev));
s = splimp();
if (events & (POLLIN | POLLRDNORM)) {
if (ifp->if_snd.ifq_len > 0) {
TAPDEBUG("%s have data in queue. len = %d, " \
"minor = %#x\n", ifp->if_xname,
ifp->if_snd.ifq_len, dev2unit(dev));
revents |= (events & (POLLIN | POLLRDNORM));
} else {
TAPDEBUG("%s waiting for data, minor = %#x\n",
ifp->if_xname, dev2unit(dev));
selrecord(td, &tp->tap_rsel);
}
}
if (events & (POLLOUT | POLLWRNORM))
revents |= (events & (POLLOUT | POLLWRNORM));
splx(s);
return (revents);
} /* tappoll */
/*
* tap_kqfilter
*
* support for kevent() system call
*/
static int
tapkqfilter(struct cdev *dev, struct knote *kn)
{
int s;
struct tap_softc *tp = dev->si_drv1;
struct ifnet *ifp = tp->tap_ifp;
s = splimp();
switch (kn->kn_filter) {
case EVFILT_READ:
TAPDEBUG("%s kqfilter: EVFILT_READ, minor = %#x\n",
ifp->if_xname, dev2unit(dev));
kn->kn_fop = &tap_read_filterops;
break;
case EVFILT_WRITE:
TAPDEBUG("%s kqfilter: EVFILT_WRITE, minor = %#x\n",
ifp->if_xname, dev2unit(dev));
kn->kn_fop = &tap_write_filterops;
break;
default:
TAPDEBUG("%s kqfilter: invalid filter, minor = %#x\n",
ifp->if_xname, dev2unit(dev));
splx(s);
return (EINVAL);
/* NOT REACHED */
}
splx(s);
kn->kn_hook = (caddr_t) dev;
knlist_add(&tp->tap_rsel.si_note, kn, 0);
return (0);
} /* tapkqfilter */
/*
* tap_kqread
*
* Return true if there is data in the interface queue
*/
static int
tapkqread(struct knote *kn, long hint)
{
int ret, s;
struct cdev *dev = (struct cdev *)(kn->kn_hook);
struct tap_softc *tp = dev->si_drv1;
struct ifnet *ifp = tp->tap_ifp;
s = splimp();
if ((kn->kn_data = ifp->if_snd.ifq_len) > 0) {
TAPDEBUG("%s have data in queue. len = %d, minor = %#x\n",
ifp->if_xname, ifp->if_snd.ifq_len, dev2unit(dev));
ret = 1;
} else {
TAPDEBUG("%s waiting for data, minor = %#x\n",
ifp->if_xname, dev2unit(dev));
ret = 0;
}
splx(s);
return (ret);
} /* tapkqread */
/*
* tap_kqwrite
*
* Always can write. Return the MTU in kn->data
*/
static int
tapkqwrite(struct knote *kn, long hint)
{
int s;
struct tap_softc *tp = ((struct cdev *) kn->kn_hook)->si_drv1;
struct ifnet *ifp = tp->tap_ifp;
s = splimp();
kn->kn_data = ifp->if_mtu;
splx(s);
return (1);
} /* tapkqwrite */
static void
tapkqdetach(struct knote *kn)
{
struct tap_softc *tp = ((struct cdev *) kn->kn_hook)->si_drv1;
knlist_remove(&tp->tap_rsel.si_note, kn, 0);
} /* tapkqdetach */
Reference in New Issue View Git Blame Copy Permalink