File:  [DragonFly] / src / sys / kern / subr_log.c
Revision 1.7: download - view: text, annotated - select for diffs
Wed May 19 22:52:58 2004 UTC (10 years, 5 months ago) by dillon
Branches: MAIN
CVS tags: HEAD, DragonFly_Stable, DragonFly_Snap29Sep2004, DragonFly_Snap13Sep2004, DragonFly_RELEASE_1_2_Slip, DragonFly_RELEASE_1_2, DragonFly_1_0_REL, DragonFly_1_0_RC1, DragonFly_1_0A_REL
Device layer rollup commit.

* cdevsw_add() is now required.  cdevsw_add() and cdevsw_remove() may specify
  a mask/match indicating the range of supported minor numbers.  Multiple
  cdevsw_add()'s using the same major number, but distinctly different
  ranges, may be issued.  All devices that failed to call cdevsw_add() before
  now do.

* cdevsw_remove() now automatically marks all devices within its supported
  range as being destroyed.

* vnode->v_rdev is no longer resolved when the vnode is created.  Instead,
  only v_udev (a newly added field) is resolved.  v_rdev is resolved when
  the vnode is opened and cleared on the last close.

* A great deal of code was making rather dubious assumptions with regards
  to the validity of devices associated with vnodes, primarily due to
  the persistence of a device structure due to being indexed by (major, minor)
  instead of by (cdevsw, major, minor).  In particular, if you run a program
  which connects to a USB device and then you pull the USB device and plug
  it back in, the vnode subsystem will continue to believe that the device
  is open when, in fact, it isn't (because it was destroyed and recreated).

  In particular, note that all the VFS mount procedures now check devices
  via v_udev instead of v_rdev prior to calling VOP_OPEN(), since v_rdev
  is NULL prior to the first open.

* The disk layer's device interaction has been rewritten.  The disk layer
  (i.e. the slice and disklabel management layer) no longer overloads
  its data onto the device structure representing the underlying physical
  disk.  Instead, the disk layer uses the new cdevsw_add() functionality
  to register its own cdevsw using the underlying device's major number,
  and simply does NOT register the underlying device's cdevsw.  No
  confusion is created because the device hash is now based on
  (cdevsw,major,minor) rather then (major,minor).

  NOTE: This also means that underlying raw disk devices may use the entire
  device minor number instead of having to reserve the bits used by the disk
  layer, and also means that can we (theoretically) stack a fully
  disklabel-supported 'disk' on top of any block device.

* The new reference counting scheme prevents this by associating a device
  with a cdevsw and disconnecting the device from its cdevsw when the cdevsw
  is removed.  Additionally, all udev2dev() lookups run through the cdevsw
  mask/match and only successfully find devices still associated with an
  active cdevsw.

* Major work on MFS:  MFS no longer shortcuts vnode and device creation.  It
  now creates a real vnode and a real device and implements real open and
  close VOPs.  Additionally, due to the disk layer changes, MFS is no longer
  limited to 255 mounts.  The new limit is 16 million.  Since MFS creates a
  real device node, mount_mfs will now create a real /dev/mfs<PID> device
  that can be read from userland (e.g. so you can dump an MFS filesystem).

* BUF AND DEVICE STRATEGY changes.  The struct buf contains a b_dev field.
  In order to properly handle stacked devices we now require that the b_dev
  field be initialized before the device strategy routine is called.  This
  required some additional work in various VFS implementations.  To enforce
  this requirement, biodone() now sets b_dev to NODEV.  The new disk layer
  will adjust b_dev before forwarding a request to the actual physical
  device.

* A bug in the ISO CD boot sequence which resulted in a panic has been fixed.

Testing by: lots of people, but David Rhodus found the most aggregious bugs.

/*
 * Copyright (c) 1982, 1986, 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.
 *
 *	@(#)subr_log.c	8.1 (Berkeley) 6/10/93
 * $FreeBSD: src/sys/kern/subr_log.c,v 1.39.2.2 2001/06/02 08:11:25 phk Exp $
 * $DragonFly: src/sys/kern/subr_log.c,v 1.7 2004/05/19 22:52:58 dillon Exp $
 */

/*
 * Error log buffer for kernel printf's.
 */

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/conf.h>
#include <sys/proc.h>
#include <sys/vnode.h>
#include <sys/filio.h>
#include <sys/ttycom.h>
#include <sys/msgbuf.h>
#include <sys/signalvar.h>
#include <sys/kernel.h>
#include <sys/poll.h>
#include <sys/filedesc.h>
#include <sys/sysctl.h>

#define LOG_ASYNC	0x04
#define LOG_RDWAIT	0x08

static	d_open_t	logopen;
static	d_close_t	logclose;
static	d_read_t	logread;
static	d_ioctl_t	logioctl;
static	d_poll_t	logpoll;

static	void logtimeout(void *arg);

#define CDEV_MAJOR 7
static struct cdevsw log_cdevsw = {
	/* name */	"log",
	/* maj */	CDEV_MAJOR,
	/* flags */	0,
	/* port */	NULL,
	/* clone */	NULL,

	/* open */	logopen,
	/* close */	logclose,
	/* read */	logread,
	/* write */	nowrite,
	/* ioctl */	logioctl,
	/* poll */	logpoll,
	/* mmap */	nommap,
	/* strategy */	nostrategy,
	/* dump */	nodump,
	/* psize */	nopsize
};

static struct logsoftc {
	int	sc_state;		/* see above for possibilities */
	struct	selinfo sc_selp;	/* process waiting on select call */
	struct  sigio *sc_sigio;	/* information for async I/O */
	struct	callout sc_callout;	/* callout to wakeup syslog  */
} logsoftc;

int	log_open;			/* also used in log() */

/* Times per second to check for a pending syslog wakeup. */
static int	log_wakeups_per_second = 5;
SYSCTL_INT(_kern, OID_AUTO, log_wakeups_per_second, CTLFLAG_RW,
    &log_wakeups_per_second, 0, "");

/*ARGSUSED*/
static	int
logopen(dev_t dev, int flags, int mode, struct thread *td)
{
	struct proc *p = td->td_proc;

	KKASSERT(p != NULL);
	if (log_open)
		return (EBUSY);
	log_open = 1;
	callout_init(&logsoftc.sc_callout);
	fsetown(p->p_pid, &logsoftc.sc_sigio);	/* signal process only */
	callout_reset(&logsoftc.sc_callout, hz / log_wakeups_per_second,
	    logtimeout, NULL);
	return (0);
}

/*ARGSUSED*/
static	int
logclose(dev_t dev, int flag, int mode, struct thread *td)
{

	log_open = 0;
	callout_stop(&logsoftc.sc_callout);
	logsoftc.sc_state = 0;
	funsetown(logsoftc.sc_sigio);
	return (0);
}

/*ARGSUSED*/
static	int
logread(dev_t dev, struct uio *uio, int flag)
{
	struct msgbuf *mbp = msgbufp;
	long l;
	int s;
	int error = 0;

	s = splhigh();
	while (mbp->msg_bufr == mbp->msg_bufx) {
		if (flag & IO_NDELAY) {
			splx(s);
			return (EWOULDBLOCK);
		}
		logsoftc.sc_state |= LOG_RDWAIT;
		if ((error = tsleep((caddr_t)mbp, PCATCH, "klog", 0))) {
			splx(s);
			return (error);
		}
	}
	splx(s);
	logsoftc.sc_state &= ~LOG_RDWAIT;

	while (uio->uio_resid > 0) {
		l = mbp->msg_bufx - mbp->msg_bufr;
		if (l < 0)
			l = mbp->msg_size - mbp->msg_bufr;
		l = min(l, uio->uio_resid);
		if (l == 0)
			break;
		error = uiomove((caddr_t)msgbufp->msg_ptr + mbp->msg_bufr,
		    (int)l, uio);
		if (error)
			break;
		mbp->msg_bufr += l;
		if (mbp->msg_bufr >= mbp->msg_size)
			mbp->msg_bufr = 0;
	}
	return (error);
}

/*ARGSUSED*/
static	int
logpoll(dev_t dev, int events, struct thread *td)
{
	int s;
	int revents = 0;

	s = splhigh();

	if (events & (POLLIN | POLLRDNORM)) {
		if (msgbufp->msg_bufr != msgbufp->msg_bufx)
			revents |= events & (POLLIN | POLLRDNORM);
		else
			selrecord(td, &logsoftc.sc_selp);
	}
	splx(s);
	return (revents);
}

static void
logtimeout(void *arg)
{

	if (!log_open)
		return;
	if (msgbuftrigger == 0) {
		callout_reset(&logsoftc.sc_callout,
		    hz / log_wakeups_per_second, logtimeout, NULL);
		return;
	}
	msgbuftrigger = 0;
	selwakeup(&logsoftc.sc_selp);
	if ((logsoftc.sc_state & LOG_ASYNC) && logsoftc.sc_sigio != NULL)
		pgsigio(logsoftc.sc_sigio, SIGIO, 0);
	if (logsoftc.sc_state & LOG_RDWAIT) {
		wakeup((caddr_t)msgbufp);
		logsoftc.sc_state &= ~LOG_RDWAIT;
	}
	callout_reset(&logsoftc.sc_callout, hz / log_wakeups_per_second,
	    logtimeout, NULL);
}

/*ARGSUSED*/
static	int
logioctl(dev_t dev, u_long com, caddr_t data, int flag, struct thread *td)
{
	long l;
	int s;

	switch (com) {

	/* return number of characters immediately available */
	case FIONREAD:
		s = splhigh();
		l = msgbufp->msg_bufx - msgbufp->msg_bufr;
		splx(s);
		if (l < 0)
			l += msgbufp->msg_size;
		*(int *)data = l;
		break;

	case FIONBIO:
		break;

	case FIOASYNC:
		if (*(int *)data)
			logsoftc.sc_state |= LOG_ASYNC;
		else
			logsoftc.sc_state &= ~LOG_ASYNC;
		break;

	case FIOSETOWN:
		return (fsetown(*(int *)data, &logsoftc.sc_sigio));

	case FIOGETOWN:
		*(int *)data = fgetown(logsoftc.sc_sigio);
		break;

	/* This is deprecated, FIOSETOWN should be used instead. */
	case TIOCSPGRP:
		return (fsetown(-(*(int *)data), &logsoftc.sc_sigio));

	/* This is deprecated, FIOGETOWN should be used instead */
	case TIOCGPGRP:
		*(int *)data = -fgetown(logsoftc.sc_sigio);
		break;

	default:
		return (ENOTTY);
	}
	return (0);
}

static void
log_drvinit(void *unused)
{
	cdevsw_add(&log_cdevsw, 0, 0);
	make_dev(&log_cdevsw, 0, UID_ROOT, GID_WHEEL, 0600, "klog");
}

SYSINIT(logdev,SI_SUB_DRIVERS,SI_ORDER_MIDDLE+CDEV_MAJOR,log_drvinit,NULL)