 @@ -1,14 +1,14 @@
-.\"	$NetBSD: kqueue.2,v 1.50 2019/12/23 01:46:09 kamil Exp $
+.\"	$NetBSD: kqueue.2,v 1.51 2020/10/31 01:08:31 christos Exp $
 .\"
 .\" Copyright (c) 2000 Jonathan Lemon
 .\" All rights reserved.
 .\"
 .\" Copyright (c) 2001, 2002, 2003 The NetBSD Foundation, Inc.
 .\" All rights reserved.
 .\"
 .\" Portions of this documentation is derived from text contributed by
 .\" Luke Mewburn.
 .\"
 .\" Redistribution and use in source and binary forms, with or without
 .\" modification, are permitted provided that the following conditions
 .\" are met:
 @@ -22,185 +22,208 @@
 .\" 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.
 .\"
 .\" $FreeBSD: src/lib/libc/sys/kqueue.2,v 1.22 2001/06/27 19:55:57 dd Exp $
 .\"
-.Dd December 22, 2019
+.Dd October 30, 2020
 .Dt KQUEUE 2
 .Os
 .Sh NAME
 .Nm kqueue ,
 .Nm kqueue1 ,
 .Nm kevent ,
 .Nm EV_SET
 .Nd kernel event notification mechanism
 .Sh LIBRARY
 .Lb libc
 .Sh SYNOPSIS
 .In sys/event.h
 .In sys/time.h
 .Ft int
 .Fn kqueue "void"
 .Ft int
 .Fn kqueue1 "int flags"
 .Ft int
 .Fn kevent "int kq" "const struct kevent *changelist" "size_t nchanges" "struct kevent *eventlist" "size_t nevents" "const struct timespec *timeout"
 .Fn EV_SET "&kev" ident filter flags fflags data udata
 .Sh DESCRIPTION
 The
 .Fn kqueue
 system call
 provides a generic method of notifying the user when an event
 happens or a condition holds, based on the results of small
 pieces of kernel code termed filters.
 A kevent is identified by the (ident, filter) pair; there may only
 be one unique kevent per kqueue.
 .Pp
 The filter is executed upon the initial registration of a kevent
 in order to detect whether a preexisting condition is present, and is also
 executed whenever an event is passed to the filter for evaluation.
 If the filter determines that the condition should be reported,
 then the kevent is placed on the kqueue for the user to retrieve.
 .Pp
 The filter is also run when the user attempts to retrieve the kevent
 from the kqueue.
 If the filter indicates that the condition that triggered
 the event no longer holds, the kevent is removed from the kqueue and
 is not returned.
 .Pp
 Multiple events which trigger the filter do not result in multiple
 kevents being placed on the kqueue; instead, the filter will aggregate
 the events into a single struct kevent.
 Calling
 .Xr close 2
 on a file descriptor will remove any kevents that reference the descriptor.
 .Pp
 The
 .Fn kqueue
 system call
 creates a new kernel event queue and returns a descriptor.
 .Pp
 The
 .Fn kqueue1
-function also allows to set the following
+system call also allows to set the following
 .Fa flags
 on the returned file descriptor:
 .Bl -column O_NONBLOCK -offset indent
 .It Dv O_CLOEXEC
 Set the close on exec property.
 .It Dv O_NONBLOCK
 Set non-blocking I/O.
 .It Dv O_NOSIGPIPE
 Return
 .Er EPIPE
 instead of raising
 .Dv SIGPIPE .
 .El
 .Pp
 The queue is not inherited by a child created with
 .Xr fork 2 .
 .\" However, if
 .\" .Xr rfork 2
 .\" is called without the
 .\" .Dv RFFDG
 .\" flag, then the descriptor table is shared,
 .\" which will allow sharing of the kqueue between two processes.
 .Pp
 The
 .Fn kevent
 system call
 is used to register events with the queue, and return any pending
 events to the user.
 The
 .Fa changelist
 argument
 is a pointer to an array of
 .Va kevent
 structures, as defined in
 .In sys/event.h .
 All changes contained in the
 .Fa changelist
 are applied before any pending events are read from the queue.
 The
 .Fa nchanges
 argument
 gives the size of
 .Fa changelist .
 The
 .Fa eventlist
 argument
 is a pointer to an array of kevent structures.
 The
 .Fa nevents
 argument
 determines the size of
 .Fa eventlist .
 When
 .Fa nevents
 is zero,
 .Fn kevent
 will return immediately even if there is a
 .Fa timeout
 specified unlike
 .Xr select 2 .
 If
 .Fa timeout
 is a
 .No non- Ns Dv NULL
 pointer, it specifies a maximum interval to wait
 for an event, which will be interpreted as a
 .Li struct timespec .
 If
 .Fa timeout
 is a
 .Dv NULL
 pointer,
 .Fn kevent
 waits indefinitely.
 To effect a poll, the
 .Fa timeout
 argument should be
 .No non- Ns Dv NULL ,
 pointing to a zero-valued
 .Xr timespec 3
 structure.
 The same array may be used for the
 .Fa changelist
 and
 .Fa eventlist .
 .Pp
 The
 .Fn EV_SET
-is a macro which is provided for ease of initializing a kevent structure.
+macro is provided for ease of initializing a kevent structure.
 This macro does not evaluate its parameters multiple times.
 .Pp
 The
 .Va kevent
 structure is defined as:
 .Bd -literal
 struct kevent {
 	uintptr_t ident;	/* identifier for this event */
 	uint32_t  filter;	/* filter for event */
 	uint32_t  flags;	/* action flags for kqueue */
 	uint32_t  fflags;	/* filter flag value */
 	int64_t   data;		/* filter data value */
 	void     *udata;	/* opaque user data identifier */
 };
 .Ed
 .Pp
 The fields of
 .Fa struct kevent
 are:
-.Bl -tag -width XXXfilter -offset indent
+.Bl -tag -width "Fa filter" -offset indent
 .It ident
 Value used to identify this event.
 The exact interpretation is determined by the attached filter,
 but often is a file descriptor.
-.It filter
+.It Fa filter
 Identifies the kernel filter used to process this event.
 There are pre-defined system filters (which are described below), and
 other filters may be added by kernel subsystems as necessary.
-.It flags
+.It Fa flags
 Actions to perform on the event.
-.It fflags
+.It Fa fflags
 Filter-specific flags.
-.It data
+.It Fa data
 Filter-specific data value.
-.It udata
+.It Fa udata
 Opaque user-defined value passed through the kernel unchanged.
 .El
 .Pp
 The
 .Va flags
 field can contain the following values:
 .Bl -tag -width XXXEV_ONESHOT -offset indent
 .It Dv EV_ADD
 Adds the event to the kqueue.
 Re-adding an existing event will modify the parameters of the original
 event, and not result in a duplicate entry.
 Adding an event automatically enables it,
 unless overridden by the EV_DISABLE flag.
 @@ -221,26 +244,31 @@ above.
 .It Dv EV_DELETE
 Removes the event from the kqueue.
 Events which are attached to file descriptors are automatically deleted
 on the last close of the descriptor.
 .It Dv EV_RECEIPT
 This flag is useful for making bulk changes to a kqueue without draining
 any pending events.
 When passed as input, it forces
 .Dv EV_ERROR
 to always be returned.
 When a filter is successfully added the
 .Va data
 field will be zero.
 Note that if this flag is encountered and there is no remaining space in
 .Fa eventlist
 to hold the
 .Dv EV_ERROR
 event, then subsequent changes will not get processed.
 .It Dv EV_ONESHOT
 Causes the event to return only the first occurrence of the filter
 being triggered.
 After the user retrieves the event from the kqueue, it is deleted.
 .It Dv EV_CLEAR
 After the event is retrieved by the user, its state is reset.
 This is useful for filters which report state transitions
 instead of the current state.
 Note that some filters may automatically set this flag internally.
 .It Dv EV_EOF
 Filters may set this flag to indicate filter-specific EOF condition.
 .It Dv EV_ERROR
 See
 @@ -279,26 +307,27 @@ to
 is ignored.
 .El
 .Pp
 The following structure is used to pass arguments in and out of the
 .Xr ioctl 2 :
 .Bd -literal -offset indent
 struct kfilter_mapping {
 	char	 *name;		/* name to lookup or return */
 	size_t	 len;		/* length of name */
 	uint32_t filter;	/* filter to lookup or return */
 };
 .Ed
 .Pp
 The predefined system filters are listed below.
 Arguments may be passed to and from the filter via the
 .Va fflags
 and
 .Va data
 fields in the kevent structure.
 .Pp
 The predefined system filters are:
 .Bl -tag -width EVFILT_SIGNAL
 .It Dv EVFILT_READ
 Takes a descriptor as the identifier, and returns whenever
 there is data available to read.
 The behavior of the filter is slightly different depending
 on the descriptor type.
 @@ -329,36 +358,50 @@ contains the number of bytes in the sock
 .Pp
 If the read direction of the socket has shutdown, then the filter
 also sets EV_EOF in
 .Va flags ,
 and returns the socket error (if any) in
 .Va fflags .
 It is possible for EOF to be returned (indicating the connection is gone)
 while there is still data pending in the socket buffer.
 .It Vnodes
 Returns when the file pointer is not at the end of file.
 .Va data
 contains the offset from current position to end of file,
 and may be negative.
 .\" .Pp
 .\" This behavior is different from
 .\" .Xr poll 2 ,
 .\" where read events are triggered for regular files unconditionally.
 .\" This event can be triggered unconditionally by setting the
 .\" .Dv NOTE_FILE_POLL
 .\" flag in
 .\" .Va fflags .
 .It "Fifos, Pipes"
 Returns when there is data to read;
 .Va data
 contains the number of bytes available.
 .Pp
 When the last writer disconnects, the filter will set EV_EOF in
 .Va flags .
 This may be cleared by passing in EV_CLEAR, at which point the
 filter will resume waiting for data to become available before
 returning.
 .It "BPF devices"
 Returns when the BPF buffer is full, the BPF timeout has expired, or
 when the BPF has
 .Dq immediate mode
 enabled and there is any data to read;
 .Va data
 .El
 .It Dv EVFILT_WRITE
 Takes a descriptor as the identifier, and returns whenever
 it is possible to write to the descriptor.
 For sockets, pipes, fifos, and ttys,
 .Va data
 will contain the amount of space remaining in the write buffer.
 The filter will set EV_EOF when the reader disconnects, and for
 the fifo case, this may be cleared by use of EV_CLEAR.
 Note that this filter is not supported for vnodes.
 .Pp
 For sockets, the low water mark and socket error handling is
 identical to the EVFILT_READ case.
 @@ -477,36 +520,88 @@ Establishes an arbitrary timer identifie
 .Va ident .
 When adding a timer,
 .Va data
 specifies the timeout period in milliseconds.
 The timer will be periodic unless EV_ONESHOT is specified.
 On return,
 .Va data
 contains the number of times the timeout has expired since the last call to
 .Fn kevent .
 This filter automatically sets the EV_CLEAR flag internally.
 .It Dv EVFILT_FS
 Establishes a file system monitor.
 Currently it only monitors file system mount and unmount actions.
 .It Dv EVFILT_USER
 Establishes a user event identified by
 .Va ident
 which is not associated with any kernel mechanism but is triggered by
 user level code.
 The lower 24 bits of the
 .Va fflags
 may be used for user defined flags and manipulated using the following:
 .Bl -tag -width "Dv NOTE_FFLAGSMASK"
 .It Dv NOTE_FFNOP
 Ignore the input
 .Va fflags .
 .It Dv NOTE_FFAND
 Bitwise AND
 .Va fflags .
 .It Dv NOTE_FFOR
 Bitwise OR
 .Va fflags .
 .It Dv NOTE_FFCOPY
 Copy
 .Va fflags .
 .It Dv NOTE_FFCTRLMASK
 Control mask for
 .Va fflags .
 .It Dv NOTE_FFLAGSMASK
 User defined flag mask for
 .Va fflags .
 .El
 .Pp
 A user event is triggered for output with the following:
 .Bl -tag -width "Dv NOTE_FFLAGSMASK"
 .It Dv NOTE_TRIGGER
 Cause the event to be triggered.
 .El
 .Pp
 On return,
 .Va fflags
 contains the users defined flags in the lower 24 bits.
 .El
 .Sh CANCELLATION BEHAVIOUR
 If
 .Fa nevents
 is non-zero, i.e., the function is potentially blocking, the call
 is a cancellation point.
 Otherwise, i.e., if
 .Fa nevents
 is zero, the call is not cancellable.
 Cancellation can only occur before any changes are made to the kqueue,
 or when the call was blocked and no changes to the queue were requested.
 .Sh RETURN VALUES
 The
 .Fn kqueue
 system call
 creates a new kernel event queue and returns a file descriptor.
 If there was an error creating the kernel event queue, a value of \-1 is
 returned and
 .Dv errno
 is set.
 .Pp
 The
 .Fn kevent
 system call
 returns the number of events placed in the
 .Fa eventlist ,
 up to the value given by
 .Fa nevents .
 If an error occurs while processing an element of the
 .Fa changelist
 and there is enough room in the
 .Fa eventlist ,
 then the event will be placed in the
 .Fa eventlist
 with
 .Dv EV_ERROR
 set in

 @@ -1,14 +1,14 @@
-/*	$NetBSD: kern_event.c,v 1.107 2020/05/23 23:42:43 ad Exp $	*/
+/*	$NetBSD: kern_event.c,v 1.108 2020/10/31 01:08:32 christos Exp $	*/
 /*-
  * Copyright (c) 2008, 2009 The NetBSD Foundation, Inc.
  * All rights reserved.
+ *
  * This code is derived from software contributed to The NetBSD Foundation
  * by Andrew Doran.
+ *
  * 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.
 @@ -21,26 +21,27 @@
  * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
  * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE FOUNDATION 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.
  */
 /*-
  * Copyright (c) 1999,2000,2001 Jonathan Lemon <jlemon@FreeBSD.org>
  * Copyright (c) 2009 Apple, Inc
  * 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
 @@ -48,27 +49,27 @@
  * 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.
+ *
  * FreeBSD: src/sys/kern/kern_event.c,v 1.27 2001/07/05 17:10:44 rwatson Exp
  */
 #include <sys/cdefs.h>
-__KERNEL_RCSID(0, "$NetBSD: kern_event.c,v 1.107 2020/05/23 23:42:43 ad Exp $");
+__KERNEL_RCSID(0, "$NetBSD: kern_event.c,v 1.108 2020/10/31 01:08:32 christos Exp $");
 #include <sys/param.h>
 #include <sys/systm.h>
 #include <sys/kernel.h>
 #include <sys/wait.h>
 #include <sys/proc.h>
 #include <sys/file.h>
 #include <sys/select.h>
 #include <sys/queue.h>
 #include <sys/event.h>
 #include <sys/eventvar.h>
 #include <sys/poll.h>
 #include <sys/kmem.h>
 @@ -99,26 +100,30 @@ static void	knote_activate(struct knote
 static void	filt_kqdetach(struct knote *);
 static int	filt_kqueue(struct knote *, long hint);
 static int	filt_procattach(struct knote *);
 static void	filt_procdetach(struct knote *);
 static int	filt_proc(struct knote *, long hint);
 static int	filt_fileattach(struct knote *);
 static void	filt_timerexpire(void *x);
 static int	filt_timerattach(struct knote *);
 static void	filt_timerdetach(struct knote *);
 static int	filt_timer(struct knote *, long hint);
 static int	filt_fsattach(struct knote *kn);
 static void	filt_fsdetach(struct knote *kn);
 static int	filt_fs(struct knote *kn, long hint);
 static int	filt_userattach(struct knote *);
 static void	filt_userdetach(struct knote *);
 static int	filt_user(struct knote *, long hint);
 static void	filt_usertouch(struct knote *, struct kevent *, long type);
 static const struct fileops kqueueops = {
 	.fo_name = "kqueue",
 	.fo_read = (void *)enxio,
 	.fo_write = (void *)enxio,
 	.fo_ioctl = kqueue_ioctl,
 	.fo_fcntl = kqueue_fcntl,
 	.fo_poll = kqueue_poll,
 	.fo_stat = kqueue_stat,
 	.fo_close = kqueue_close,
 	.fo_kqfilter = kqueue_kqfilter,
 	.fo_restart = fnullop_restart,
 };
 @@ -148,26 +153,34 @@ static const struct filterops timer_filt
 	.f_isfd = 0,
 	.f_attach = filt_timerattach,
 	.f_detach = filt_timerdetach,
 	.f_event = filt_timer,
 };
 static const struct filterops fs_filtops = {
 	.f_isfd = 0,
 	.f_attach = filt_fsattach,
 	.f_detach = filt_fsdetach,
 	.f_event = filt_fs,
 };
 static const struct filterops user_filtops = {
 	.f_isfd = 0,
 	.f_attach = filt_userattach,
 	.f_detach = filt_userdetach,
 	.f_event = filt_user,
 	.f_touch = filt_usertouch,
 };
 static u_int	kq_ncallouts = 0;
 static int	kq_calloutmax = (4 * 1024);
 #define	KN_HASHSIZE		64		/* XXX should be tunable */
 #define	KN_HASH(val, mask)	(((val) ^ (val >> 8)) & (mask))
 extern const struct filterops sig_filtops;
 /*
  * Table for for all system-defined filters.
  * These should be listed in the numeric order of the EVFILT_* defines.
  * If filtops is NULL, the filter isn't implemented in NetBSD.
  * End of list is when name is NULL.
 @@ -182,26 +195,27 @@ struct kfilter {
 	size_t		namelen;	/* length of name string */
 };
 /* System defined filters */
 static struct kfilter sys_kfilters[] = {
 	{ "EVFILT_READ",	EVFILT_READ,	0, &file_filtops, 0 },
 	{ "EVFILT_WRITE",	EVFILT_WRITE,	0, &file_filtops, 0, },
 	{ "EVFILT_AIO",		EVFILT_AIO,	0, NULL, 0 },
 	{ "EVFILT_VNODE",	EVFILT_VNODE,	0, &file_filtops, 0 },
 	{ "EVFILT_PROC",	EVFILT_PROC,	0, &proc_filtops, 0 },
 	{ "EVFILT_SIGNAL",	EVFILT_SIGNAL,	0, &sig_filtops, 0 },
 	{ "EVFILT_TIMER",	EVFILT_TIMER,	0, &timer_filtops, 0 },
 	{ "EVFILT_FS",		EVFILT_FS,	0, &fs_filtops, 0 },
 	{ "EVFILT_USER",	EVFILT_USER,	0, &user_filtops, 0 },
 	{ NULL,			0,		0, NULL, 0 },
 };
 /* User defined kfilters */
 static struct kfilter	*user_kfilters;		/* array */
 static int		user_kfilterc;		/* current offset */
 static int		user_kfiltermaxc;	/* max size so far */
 static size_t		user_kfiltersz;		/* size of allocated memory */
 /*
  * Global Locks.
+ *
  * Lock order:
 @@ -766,26 +780,126 @@ filt_fsdetach(struct knote *kn)
 static int
 filt_fs(struct knote *kn, long hint)
+{
 	int rv;
 	mutex_enter(&kqueue_misc_lock);
 	kn->kn_fflags |= hint;
 	rv = (kn->kn_fflags != 0);
 	mutex_exit(&kqueue_misc_lock);
 	return rv;
+}
 static int
 filt_userattach(struct knote *kn)
+{
 	struct kqueue *kq = kn->kn_kq;
 	/*
 	 * EVFILT_USER knotes are not attached to anything in the kernel.
 	 */
 	mutex_spin_enter(&kq->kq_lock);
 	kn->kn_hook = NULL;
 	if (kn->kn_fflags & NOTE_TRIGGER)
 		kn->kn_hookid = 1;
 	else
 		kn->kn_hookid = 0;
 	mutex_spin_exit(&kq->kq_lock);
 	return (0);
+}
 static void
 filt_userdetach(struct knote *kn)
+{
 	/*
 	 * EVFILT_USER knotes are not attached to anything in the kernel.
 	 */
+}
 static int
 filt_user(struct knote *kn, long hint)
+{
 	struct kqueue *kq = kn->kn_kq;
 	int hookid;
 	mutex_spin_enter(&kq->kq_lock);
 	hookid = kn->kn_hookid;
 	mutex_spin_exit(&kq->kq_lock);
 	return hookid;
+}
 static void
 filt_usertouch(struct knote *kn, struct kevent *kev, long type)
+{
 	struct kqueue *kq = kn->kn_kq;
 	int ffctrl;
 	mutex_spin_enter(&kq->kq_lock);
 	switch (type) {
 	case EVENT_REGISTER:
 		if (kev->fflags & NOTE_TRIGGER)
 			kn->kn_hookid = 1;
 		ffctrl = kev->fflags & NOTE_FFCTRLMASK;
 		kev->fflags &= NOTE_FFLAGSMASK;
 		switch (ffctrl) {
 		case NOTE_FFNOP:
 			break;
 		case NOTE_FFAND:
 			kn->kn_sfflags &= kev->fflags;
 			break;
 		case NOTE_FFOR:
 			kn->kn_sfflags |= kev->fflags;
 			break;
 		case NOTE_FFCOPY:
 			kn->kn_sfflags = kev->fflags;
 			break;
 		default:
 			/* XXX Return error? */
 			break;
+		}
 		kn->kn_sdata = kev->data;
 		if (kev->flags & EV_CLEAR) {
 			kn->kn_hookid = 0;
 			kn->kn_data = 0;
 			kn->kn_fflags = 0;
+		}
 		break;
 	case EVENT_PROCESS:
 		*kev = kn->kn_kevent;
 		kev->fflags = kn->kn_sfflags;
 		kev->data = kn->kn_sdata;
 		if (kn->kn_flags & EV_CLEAR) {
 			kn->kn_hookid = 0;
 			kn->kn_data = 0;
 			kn->kn_fflags = 0;
+		}
 		break;
 	default:
 		panic("filt_usertouch() - invalid type (%ld)", type);
 		break;
+	}
 	mutex_spin_exit(&kq->kq_lock);
+}
 /*
  * filt_seltrue:
+ *
  *	This filter "event" routine simulates seltrue().
  */
 int
 filt_seltrue(struct knote *kn, long hint)
+{
 	/*
 	 * We don't know how much data can be read/written,
 	 * but we know that it *can* be.  This is about as
 	 * good as select/poll does as well.
 @@ -799,26 +913,27 @@ filt_seltrue(struct knote *kn, long hint
  * has same effect as filter using filt_seltrue() as filter method.
  */
 static void
 filt_seltruedetach(struct knote *kn)
+{
 	/* Nothing to do */
+}
 const struct filterops seltrue_filtops = {
 	.f_isfd = 1,
 	.f_attach = NULL,
 	.f_detach = filt_seltruedetach,
 	.f_event = filt_seltrue,
 	.f_touch = NULL,
 };
 int
 seltrue_kqfilter(dev_t dev, struct knote *kn)
+{
 	switch (kn->kn_filter) {
 	case EVFILT_READ:
 	case EVFILT_WRITE:
 		kn->kn_fop = &seltrue_filtops;
 		break;
 	default:
 		return (EINVAL);
+	}
 @@ -1062,28 +1177,28 @@ kqueue_register(struct kqueue *kq, struc
 			    KN_HASH((u_long)kev->ident, fdp->fd_knhashmask)];
 			SLIST_FOREACH(kn, list, kn_link) {
 				if (kev->ident == kn->kn_id &&
 				    kq == kn->kn_kq &&
 				    kev->filter == kn->kn_filter)
 					break;
+			}
+		}
+	}
 	/*
 	 * kn now contains the matching knote, or NULL if no match
 	 */
-	if (kev->flags & EV_ADD) {
+	if (kn == NULL) {
-		if (kn == NULL) {
+		if (kev->flags & EV_ADD) {
 			/* create new knote */
 			kn = newkn;
 			newkn = NULL;
 			kn->kn_obj = fp;
 			kn->kn_id = kev->ident;
 			kn->kn_kq = kq;
 			kn->kn_fop = kfilter->filtops;
 			kn->kn_kfilter = kfilter;
 			kn->kn_sfflags = kev->fflags;
 			kn->kn_sdata = kev->data;
 			kev->fflags = 0;
 			kev->data = 0;
 			kn->kn_kevent = *kev;
 @@ -1127,61 +1242,71 @@ kqueue_register(struct kqueue *kq, struc
 				printf("%s: %s[%d]: event type %d not "
 				    "supported for file type %d/%s "
 				    "(error %d)\n", __func__,
 				    p->p_comm, p->p_pid,
 				    kn->kn_filter, ft ? ft->f_type : -1,
 				    ft ? ft->f_ops->fo_name : "?", error);
 #endif
 				/* knote_detach() drops fdp->fd_lock */
 				knote_detach(kn, fdp, false);
 				goto done;
+			}
 			atomic_inc_uint(&kfilter->refcnt);
 			goto done_ev_add;
 		} else {
-			/*
+			/* No matching knote and the EV_ADD flag is not set. */
-			 * The user may change some filter values after the
+			error = ENOENT;
-			 * initial EV_ADD, but doing so will not reset any
+			goto doneunlock;
 			 * filter which have already been triggered.
 			 */
 			kn->kn_sfflags = kev->fflags;
 			kn->kn_sdata = kev->data;
 			kn->kn_kevent.udata = kev->udata;
+		}
 		/*
 		 * We can get here if we are trying to attach
-		 * an event to a file descriptor that does not
+	if (kev->flags & EV_DELETE) {
-		 * support events, and the attach routine is
+		/* knote_detach() drops fdp->fd_lock */
-		 * broken and does not return an error.
+		knote_detach(kn, fdp, true);
-		 */
+		goto done;
 		KASSERT(kn->kn_fop != NULL);
 		KASSERT(kn->kn_fop->f_event != NULL);
 	/*
 	 * The user may change some filter values after the
 	 * initial EV_ADD, but doing so will not reset any
 	 * filter which have already been triggered.
 	 */
 	kn->kn_kevent.udata = kev->udata;
 	KASSERT(kn->kn_fop != NULL);
 	if (!kn->kn_fop->f_isfd && kn->kn_fop->f_touch != NULL) {
 		KERNEL_LOCK(1, NULL);			/* XXXSMP */
-		rv = (*kn->kn_fop->f_event)(kn, 0);
+		(*kn->kn_fop->f_touch)(kn, kev, EVENT_REGISTER);
 		KERNEL_UNLOCK_ONE(NULL);		/* XXXSMP */
 		if (rv)
 			knote_activate(kn);
 	} else {
-		if (kn == NULL) {
+		kn->kn_sfflags = kev->fflags;
-			error = ENOENT;
+		kn->kn_sdata = kev->data;
 			goto doneunlock;
 		if (kev->flags & EV_DELETE) {
 			/* knote_detach() drops fdp->fd_lock */
 			knote_detach(kn, fdp, true);
 			goto done;
+	}
 	/*
 	 * We can get here if we are trying to attach
 	 * an event to a file descriptor that does not
 	 * support events, and the attach routine is
 	 * broken and does not return an error.
 	 */
 done_ev_add:
 	KASSERT(kn->kn_fop != NULL);
 	KASSERT(kn->kn_fop->f_event != NULL);
 	KERNEL_LOCK(1, NULL);			/* XXXSMP */
 	rv = (*kn->kn_fop->f_event)(kn, 0);
 	KERNEL_UNLOCK_ONE(NULL);		/* XXXSMP */
 	if (rv)
 		knote_activate(kn);
 	/* disable knote */
 	if ((kev->flags & EV_DISABLE)) {
 		mutex_spin_enter(&kq->kq_lock);
 		if ((kn->kn_status & KN_DISABLED) == 0)
 			kn->kn_status |= KN_DISABLED;
 		mutex_spin_exit(&kq->kq_lock);
+	}
 	/* enable knote */
 	if ((kev->flags & EV_ENABLE)) {
 		knote_enqueue(kn);
+	}
 doneunlock:
 @@ -1261,27 +1386,27 @@ bad:
  * as appropriate.
  */
 static int
 kqueue_scan(file_t *fp, size_t maxevents, struct kevent *ulistp,
 	    const struct timespec *tsp, register_t *retval,
 	    const struct kevent_ops *keops, struct kevent *kevbuf,
 	    size_t kevcnt)
+{
 	struct kqueue	*kq;
 	struct kevent	*kevp;
 	struct timespec	ats, sleepts;
 	struct knote	*kn, *marker, morker;
 	size_t		count, nkev, nevents;
-	int		timeout, error, rv;
+	int		timeout, error, touch, rv;
 	filedesc_t	*fdp;
 	fdp = curlwp->l_fd;
 	kq = fp->f_kqueue;
 	count = maxevents;
 	nkev = nevents = error = 0;
 	if (count == 0) {
 		*retval = 0;
 		return 0;
+	}
 	if (tsp) {				/* timeout supplied */
 		ats = *tsp;
 @@ -1372,40 +1497,60 @@ kqueue_scan(file_t *fp, size_t maxevents
 				if ((kn->kn_status & KN_QUEUED) != 0) {
 					kn->kn_status &= ~KN_BUSY;
 					continue;
+				}
 				if (rv == 0) {
 					/*
 					 * non-ONESHOT event that hasn't
 					 * triggered again, so de-queue.
 					 */
 					kn->kn_status &= ~(KN_ACTIVE|KN_BUSY);
 					continue;
+				}
+			}
 			KASSERT(kn->kn_fop != NULL);
 			touch = (!kn->kn_fop->f_isfd &&
 					kn->kn_fop->f_touch != NULL);
 			/* XXXAD should be got from f_event if !oneshot. */
-			*kevp++ = kn->kn_kevent;
+			if (touch) {
 				mutex_spin_exit(&kq->kq_lock);
 				KERNEL_LOCK(1, NULL);		/* XXXSMP */
 				(*kn->kn_fop->f_touch)(kn, kevp, EVENT_PROCESS);
 				KERNEL_UNLOCK_ONE(NULL);	/* XXXSMP */
 				mutex_spin_enter(&kq->kq_lock);
 			} else {
 				*kevp = kn->kn_kevent;
+			}
 			kevp++;
 			nkev++;
 			if (kn->kn_flags & EV_ONESHOT) {
 				/* delete ONESHOT events after retrieval */
 				kn->kn_status &= ~KN_BUSY;
 				mutex_spin_exit(&kq->kq_lock);
 				knote_detach(kn, fdp, true);
 				mutex_enter(&fdp->fd_lock);
 				mutex_spin_enter(&kq->kq_lock);
 			} else if (kn->kn_flags & EV_CLEAR) {
 				/* clear state after retrieval */
 				kn->kn_data = 0;
 				kn->kn_fflags = 0;
 				/*
 				 * Manually clear knotes who weren't
 				 * 'touch'ed.
 				 */
 				if (touch == 0) {
 					kn->kn_data = 0;
 					kn->kn_fflags = 0;
+				}
 				kn->kn_status &= ~(KN_QUEUED|KN_ACTIVE|KN_BUSY);
 			} else if (kn->kn_flags & EV_DISPATCH) {
 				kn->kn_status |= KN_DISABLED;
 				kn->kn_status &= ~(KN_QUEUED|KN_ACTIVE|KN_BUSY);
 			} else {
 				/* add event back on list */
 				kq_check(kq);
 				kn->kn_status |= KN_QUEUED;
 				kn->kn_status &= ~KN_BUSY;
 				TAILQ_INSERT_TAIL(&kq->kq_head, kn, kn_tqe);
 				kq->kq_count++;
 				kq_check(kq);
+			}

 @@ -1,14 +1,14 @@
-/*	$NetBSD: event.h,v 1.38 2019/10/03 22:16:52 kamil Exp $	*/
+/*	$NetBSD: event.h,v 1.39 2020/10/31 01:08:32 christos Exp $	*/
 /*-
  * Copyright (c) 1999,2000,2001 Jonathan Lemon <jlemon@FreeBSD.org>
  * 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.
 @@ -34,27 +34,28 @@
 #include <sys/featuretest.h>
 #include <sys/types.h>			/* for size_t */
 #include <sys/inttypes.h>		/* for uintptr_t */
 #include <sys/null.h>			/* for NULL */
 #define	EVFILT_READ		0U
 #define	EVFILT_WRITE		1U
 #define	EVFILT_AIO		2U	/* attached to aio requests */
 #define	EVFILT_VNODE		3U	/* attached to vnodes */
 #define	EVFILT_PROC		4U	/* attached to struct proc */
 #define	EVFILT_SIGNAL		5U	/* attached to struct proc */
 #define	EVFILT_TIMER		6U	/* arbitrary timer (in ms) */
 #define	EVFILT_FS		7U	/* filesystem events */
-#define	EVFILT_SYSCOUNT		8U	/* number of filters */
+#define	EVFILT_USER		8U	/* user events */
 #define	EVFILT_SYSCOUNT		9U	/* number of filters */
 struct kevent {
 	uintptr_t	ident;		/* identifier for this event */
 	uint32_t	filter;		/* filter for event */
 	uint32_t	flags;		/* action flags for kqueue */
 	uint32_t	fflags;		/* filter flag value */
 	int64_t		data;		/* filter data value */
 	void		*udata;		/* opaque user data identifier */
 };
 static __inline void
 _EV_SET(struct kevent *_kevp, uintptr_t _ident, uint32_t _filter,
     uint32_t _flags, uint32_t _fflags, int64_t _data, void *_udata)
 @@ -81,26 +82,45 @@ _EV_SET(struct kevent *_kevp, uintptr_t
 #define	EV_ONESHOT	0x0010U		/* only report one occurrence */
 #define	EV_CLEAR	0x0020U		/* clear event state after reporting */
 #define EV_RECEIPT	0x0040U		/* force EV_ERROR on success, data=0 */
 #define EV_DISPATCH	0x0080U		/* disable event after reporting */
 #define	EV_SYSFLAGS	0xF000U		/* reserved by system */
 #define	EV_FLAG1	0x2000U		/* filter-specific flag */
 /* returned values */
 #define	EV_EOF		0x8000U		/* EOF detected */
 #define	EV_ERROR	0x4000U		/* error, data contains errno */
 /*
  * data/hint flags/masks for EVFILT_USER, shared with userspace
+ *
  * On input, the top two bits of fflags specifies how the lower twenty four
  * bits should be applied to the stored value of fflags.
+ *
  * On output, the top two bits will always be set to NOTE_FFNOP and the
  * remaining twenty four bits will contain the stored fflags value.
  */
 #define	NOTE_FFNOP	0x00000000U		/* ignore input fflags */
 #define	NOTE_FFAND	0x40000000U		/* AND fflags */
 #define	NOTE_FFOR	0x80000000U		/* OR fflags */
 #define	NOTE_FFCOPY	0xc0000000U		/* copy fflags */
 #define	NOTE_FFCTRLMASK	0xc0000000U		/* masks for operations */
 #define	NOTE_FFLAGSMASK	0x00ffffffU
 #define	NOTE_TRIGGER	0x01000000U		/* Cause the event to be
 						   triggered for output. */
 /*
  * hint flag for in-kernel use - must not equal any existing note
  */
 #ifdef _KERNEL
 #define NOTE_SUBMIT	0x01000000U		/* initial knote submission */
 #endif
 /*
  * data/hint flags for EVFILT_{READ|WRITE}, shared with userspace
  */
 #define	NOTE_LOWAT	0x0001U			/* low water mark */
 /*
  * data/hint flags for EVFILT_VNODE, shared with userspace
  */
 @@ -152,60 +172,72 @@ struct kfilter_mapping {
 #define KFILTER_BYNAME		_IOWR('k', 1, struct kfilter_mapping)
 #ifdef _KERNEL
 #define	KNOTE(list, hint)	if (!SLIST_EMPTY(list)) knote(list, hint)
 /*
  * Flag indicating hint is a signal.  Used by EVFILT_SIGNAL, and also
  * shared by EVFILT_PROC  (all knotes attached to p->p_klist)
  */
 #define	NOTE_SIGNAL	0x08000000U
 /*
  * Hint values for the optional f_touch event filter.  If f_touch is not set
  * to NULL and f_isfd is zero the f_touch filter will be called with the type
  * argument set to EVENT_REGISTER during a kevent() system call.  It is also
  * called under the same conditions with the type argument set to EVENT_PROCESS
  * when the event has been triggered.
  */
 #define	EVENT_REGISTER	1
 #define	EVENT_PROCESS	2
 /*
  * Callback methods for each filter type.
  */
 struct filterops {
 	int	f_isfd;			/* true if ident == filedescriptor */
 	int	(*f_attach)	(struct knote *);
 					/* called when knote is ADDed */
 	void	(*f_detach)	(struct knote *);
 					/* called when knote is DELETEd */
 	int	(*f_event)	(struct knote *, long);
 					/* called when event is triggered */
 	void	(*f_touch)	(struct knote *, struct kevent *, long);
 };
 /*
  * Field locking:
+ *
  * f	kn_kq->kq_fdp->fd_lock
  * q	kn_kq->kq_lock
  * o	object mutex (e.g. device driver or vnode interlock)
  */
 struct kfilter;
 struct knote {
 	SLIST_ENTRY(knote)	kn_link;	/* f: for fd */
 	SLIST_ENTRY(knote)	kn_selnext;	/* o: for struct selinfo */
 	TAILQ_ENTRY(knote)	kn_tqe;		/* q: for struct kqueue */
 	struct kqueue		*kn_kq;		/* q: which queue we are on */
 	struct kevent		kn_kevent;
 	uint32_t		kn_status;	/* q: flags below */
 	uint32_t		kn_sfflags;	/*    saved filter flags */
 	uintptr_t		kn_sdata;	/*    saved data field */
 	void			*kn_obj;	/*    monitored obj */
 	const struct filterops	*kn_fop;
 	struct kfilter		*kn_kfilter;
 	void 			*kn_hook;
 	int			kn_hookid;
 #define	KN_ACTIVE	0x01U			/* event has been triggered */
 #define	KN_QUEUED	0x02U			/* event is on queue */
 #define	KN_DISABLED	0x04U			/* event is disabled */
 #define	KN_DETACHED	0x08U			/* knote is detached */
 #define	KN_MARKER	0x10U			/* is a marker */
 #define	KN_BUSY		0x20U			/* is being scanned */
 /* Toggling KN_BUSY also requires kn_kq->kq_fdp->fd_lock. */
 #define __KN_FLAG_BITS \
     "\20" \
     "\1ACTIVE" \
     "\2QUEUED" \
     "\3DISABLED" \

 @@ -1,14 +1,14 @@
-/*	$NetBSD: t_kevent.c,v 1.8 2020/06/25 11:12:03 jruoho Exp $ */
+/*	$NetBSD: t_kevent.c,v 1.9 2020/10/31 01:08:32 christos Exp $ */
 /*-
  * Copyright (c) 2011 The NetBSD Foundation, Inc.
  * All rights reserved.
+ *
  * This code is derived from software contributed to The NetBSD Foundatiom
  * by Christos Zoulas.
+ *
  * 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.
 @@ -19,27 +19,27 @@
  * THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. 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 FOUNDATION 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.
  */
 #include <sys/cdefs.h>
-__RCSID("$NetBSD: t_kevent.c,v 1.8 2020/06/25 11:12:03 jruoho Exp $");
+__RCSID("$NetBSD: t_kevent.c,v 1.9 2020/10/31 01:08:32 christos Exp $");
 #include <sys/types.h>
 #include <sys/event.h>
 #include <atf-c.h>
 #include <errno.h>
 #include <time.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
 #include <fcntl.h>
 #include <err.h>
 @@ -162,25 +162,58 @@ ATF_TC_BODY(kqueue_unsupported_fd, tc)
+		}
+	}
 	ATF_REQUIRE(fd != -1);
 	ATF_REQUIRE((kq = kqueue()) != -1);
 	EV_SET(&ev, fd, EVFILT_VNODE, EV_ADD | EV_ENABLE | EV_CLEAR,
 	   NOTE_DELETE|NOTE_WRITE|NOTE_EXTEND|NOTE_ATTRIB|NOTE_LINK|
 	   NOTE_RENAME|NOTE_REVOKE, 0, 0);
 	ATF_REQUIRE(kevent(kq, &ev, 1, NULL, 0, NULL) == -1);
 	ATF_REQUIRE_ERRNO(EOPNOTSUPP, true);
 	(void)close(fd);
 	(void)close(kq);
+}
 ATF_TC(kqueue_EVFILT_USER);
 ATF_TC_HEAD(kqueue_EVFILT_USER, tc)
+{
 	atf_tc_set_md_var(tc, "descr", "Checks usability of EVFILT_USER");
+}
 ATF_TC_BODY(kqueue_EVFILT_USER, tc)
+{
 	/* mqueue and semaphore use fnullop_kqueue also */
 	int kq;
 	struct kevent ev, rev;
 	ATF_REQUIRE((kq = kqueue()) != -1);
 	EV_SET(&ev, 666, EVFILT_USER, EV_ADD | EV_ENABLE, 0, 0, 0);
 	ATF_REQUIRE(kevent(kq, &ev, 1, NULL, 0, NULL) == 0);
 	EV_SET(&ev, 666, EVFILT_USER, 0, NOTE_FFCOPY | NOTE_TRIGGER | 8, 0, 0);
 	ATF_REQUIRE(kevent(kq, &ev, 1, NULL, 0, NULL) == 0);
 	const struct timespec timeout = {
 		.tv_sec = 1,
 		.tv_nsec = 0,
 	};
 	ATF_REQUIRE(kevent(kq, NULL, 0, &rev, 1, &timeout) == 1);
 	ATF_REQUIRE(rev.ident == 666);
 	ATF_REQUIRE(rev.filter == EVFILT_USER);
 	ATF_REQUIRE(rev.fflags == 8);
 	(void)close(kq);
+}
 ATF_TP_ADD_TCS(tp)
+{
 	ATF_TP_ADD_TC(tp, kevent_zerotimer);
 	ATF_TP_ADD_TC(tp, kqueue_desc_passing);
 	ATF_TP_ADD_TC(tp, kqueue_unsupported_fd);
 	ATF_TP_ADD_TC(tp, kqueue_EVFILT_USER);
 	return atf_no_error();
+}