a2p
accept
access
acct
addftinfo
addr2line
adjtime
afmtodit
after
aio_cancel
aio_error
aio_read
aio_return
aio_suspend
aio_waitcomplete
aio_write
alias
aliases
alloc
anvil
append
apply
apropos
ar
array
as
asa
asn1parse
at
atq
atrm
attemptckalloc
attemptckrealloc
authlib
authtest
autopoint
awk
b64decode
b64encode
basename
batch
bc
bdes
bell
bg
bgerror
biff
big5
binary
bind
bindkey
bindtags
bindtextdomain
bio
bitmap
blowfish
bn
bootparams
bootptab
bounce
brandelf
break
breaksw
brk
bsdiff
bsdtar
bsnmpd
bspatch
bthost
btsockstat
buffer
builtin
builtins
bunzip2
button
byacc
bzcat
bzegrep
bzfgrep
bzgrep
bzip2
c2ph
c89
c99
ca
cal
calendar
canvas
cap_mkdb
case
cat
catch
catman
cc
cd
cdcontrol
chdir
checkbutton
checknr
chflags
chfn
chgrp
chio
chkey
chmod
chown
chpass
chroot
chsh
ci
ciphers
ckalloc
ckdist
ckfree
ckrealloc
cksum
cleanup
clear
clipboard
clock
clock_getres
clock_gettime
clock_settime
close
cmp
co
col
colcrt
colldef
colors
colrm
column
comm
command
compile_et
complete
compress
concat
config
connect
console
continue
core
courierlogger
couriertcpd
cp
cpan
cpio
cpp
creat
crl
crontab
crunchgen
crunchide
crypt
crypto
csh
csplit
ctags
ctm
ctm_dequeue
ctm_rmail
ctm_smail
cu
cursor
cursors
cut
cvs
date
dbiprof
dbiproxy
dc
dcgettext
dcngettext
dd
dde
default
defer
deliverquota
des
destroy
devfs
df
dgettext
dgst
dh
dhparam
dialog
diff
diff3
dig
dir
dirent
dirname
dirs
discard
disktab
dngettext
do
domainname
done
dprofpp
dsa
dsaparam
dtmfdecode
du
dup
dup2
eaccess
ec
ecdsa
echo
echotc
ecparam
ed
edit
editrc
ee
egrep
elf
elfdump
elif
else
enc
enc2xs
encoding
end
endif
endsw
engine
enigma
entry
env
envsubst
eof
eqn
err
errno
error
errstr
esac
ethers
euc
eui64
eval
event
evp
ex
exec
execve
exit
expand
export
exports
expr
extattr
extattr_delete_fd
extattr_delete_file
extattr_get_fd
extattr_get_file
extattr_set_fd
extattr_set_file
f77
false
famm
famx
fblocked
fbtab
fc
fchdir
fchflags
fchmod
fchown
fcntl
fconfigure
fcopy
fdescfs
fdformat
fdread
fdwrite
fetch
fg
fgrep
fhopen
fhstat
fhstatfs
fi
file
file2c
fileevent
filename
filetest
find
find2perl
finger
flex
flock
flush
fmt
focus
fold
font
fontedit
for
foreach
fork
format
forward
fpathconf
frame
from
fs
fstab
fstat
fstatfs
fsync
ftp
ftpchroot
ftpusers
ftruncate
futimes
g711conv
gb2312
gb18030
gbk
gcc
gcore
gcov
gdb
gencat
gendsa
genrsa
gensnmptree
getconf
getdents
getdirentries
getdtablesize
getegid
geteuid
getfacl
getfh
getfsstat
getgid
getgroups
getitimer
getlogin
getopt
getopts
getpeername
getpgid
getpgrp
getpid
getppid
getpriority
getresgid
getresuid
getrlimit
getrusage
gets
getsid
getsockname
getsockopt
gettext
gettextize
gettimeofday
gettytab
getuid
glob
global
gmake
goto
gperf
gprof
grab
grep
grid
grn
grodvi
groff
groff_font
groff_out
groff_tmac
grog
grolbp
grolj4
grops
grotty
group
groups
gunzip
gzcat
gzexe
gzip
h2ph
h2xs
hash
hashstat
hd
head
help2man
hesinfo
hexdump
history
host
hostname
hosts
hosts_access
hosts_options
hpftodit
http
hup
i386_get_ioperm
i386_get_ldt
i386_set_ioperm
i386_set_ldt
i386_vm86
iconv
id
ident
idprio
if
ifnames253
ifnames259
image
imapd
incr
indent
indxbib
info
infokey
inode
install
instmodsh
interp
intro
introduction
ioctl
ipcrm
ipcs
ipf
ipftest
ipnat
ippool
ipresend
issetugid
jail
jail_attach
jobid
jobs
join
jot
kbdcontrol
kbdmap
kcon
kdestroy
kdump
kenv
kevent
keycap
keylogin
keylogout
keymap
keysyms
kgdb
kill
killall
killpg
kinit
kldfind
kldfirstmod
kldload
kldnext
kldstat
kldsym
kldunload
klist
kpasswd
kqueue
kse
kse_create
kse_exit
kse_release
kse_switchin
kse_thr_interrupt
kse_wakeup
ktrace
label
labelframe
lam
lappend
last
lastcomm
lastlog
lchflags
lchmod
lchown
ld
ldap
ldapadd
ldapcompare
ldapdelete
ldapmodify
ldapmodrdn
ldappasswd
ldapsearch
ldapwhoami
ldd
leave
less
lesskey
lex
lgetfh
lhash
libnetcfg
library
limit
limits
lindex
link
linprocfs
linsert
lint
lio_listio
list
listbox
listen
lj4_font
lkbib
llength
lmtp
ln
load
loadfont
local
locale
locate
lock
lockf
log
logger
login
logins
logname
logout
look
lookbib
lorder
lower
lp
lpq
lpr
lprm
lptest
lrange
lreplace
ls
lsearch
lseek
lset
lsort
lstat
lsvfs
lutimes
lynx
m4
madvise
magic
mail
maildiracl
maildirkw
maildirmake
mailq
mailx
make
makeinfo
makewhatis
man
manpath
master
mc
mcedit
mcview
md2
md4
md5
mdc2
memory
menu
menubar
menubutton
merge
mesg
message
mincore
minherit
minigzip
mkdep
mkdir
mkfifo
mkimapdcert
mklocale
mknod
mkpop3dcert
mkstr
mktemp
mlock
mlockall
mmap
mmroff
modfind
modfnext
modnext
modstat
moduli
more
motd
mount
mprotect
mptable
msdos
msdosfs
msgattrib
msgcat
msgcmp
msgcomm
msgconv
msgen
msgexec
msgfilter
msgfmt
msggrep
msginit
msgmerge
msgs
msgunfmt
msguniq
mskanji
msql2mysql
msync
mt
munlock
munlockall
munmap
mv
myisamchk
myisamlog
myisampack
mysql
mysqlaccess
mysqladmin
mysqlbinlog
mysqlcheck
mysqld
mysqldump
mysqld_multi
mysqld_safe
mysqlhotcopy
mysqlimport
mysqlshow
mysql_config
mysql_fix_privilege_tables
mysql_zap
namespace
nanosleep
nawk
nc
ncal
ncplist
ncplogin
ncplogout
neqn
netconfig
netgroup
netid
netstat
networks
newaliases
newgrp
nex
nfsstat
nfssvc
ngettext
nice
nl
nm
nmount
nohup
nologin
notify
nroff
nseq
nslookup
ntp_adjtime
ntp_gettime
nvi
nview
objcopy
objdump
objformat
ocsp
od
onintr
open
openssl
opieaccess
opieinfo
opiekey
opiekeys
opiepasswd
option
options
oqmgr
pack
package
packagens
pagesize
palette
pam_auth
panedwindow
parray
passwd
paste
patch
pathchk
pathconf
pawd
pax
pbm
pcre
pcreapi
pcrebuild
pcrecallout
pcrecompat
pcrecpp
pcregrep
pcrematching
pcrepartial
pcrepattern
pcreperform
pcreposix
pcreprecompile
pcresample
pcretest
perl
perl56delta
perl58delta
perl561delta
perl570delta
perl571delta
perl572delta
perl573delta
perl581delta
perl582delta
perl583delta
perl584delta
perl585delta
perl586delta
perl587delta
perl588delta
perl5004delta
perl5005delta
perlaix
perlamiga
perlapi
perlapio
perlapollo
perlartistic
perlbeos
perlbook
perlboot
perlbot
perlbs2000
perlbug
perlcall
perlcc
perlce
perlcheat
perlclib
perlcn
perlcompile
perlcygwin
perldata
perldbmfilter
perldebguts
perldebtut
perldebug
perldelta
perldgux
perldiag
perldoc
perldos
perldsc
perlebcdic
perlembed
perlepoc
perlfaq
perlfaq1
perlfaq2
perlfaq3
perlfaq4
perlfaq5
perlfaq6
perlfaq7
perlfaq8
perlfaq9
perlfilter
perlfork
perlform
perlfreebsd
perlfunc
perlglossary
perlgpl
perlguts
perlhack
perlhist
perlhpux
perlhurd
perlintern
perlintro
perliol
perlipc
perlirix
perlivp
perljp
perlko
perllexwarn
perllinux
perllocale
perllol
perlmachten
perlmacos
perlmacosx
perlmint
perlmod
perlmodinstall
perlmodlib
perlmodstyle
perlmpeix
perlnetware
perlnewmod
perlnumber
perlobj
perlop
perlopenbsd
perlopentut
perlos2
perlos390
perlos400
perlothrtut
perlpacktut
perlplan9
perlpod
perlpodspec
perlport
perlqnx
perlre
perlref
perlreftut
perlrequick
perlreref
perlretut
perlrun
perlsec
perlsolaris
perlstyle
perlsub
perlsyn
perlthrtut
perltie
perltoc
perltodo
perltooc
perltoot
perltrap
perltru64
perltw
perlunicode
perluniintro
perlutil
perluts
perlvar
perlvmesa
perlvms
perlvos
perlwin32
perlxs
perlxstut
perror
pfbtops
pftp
pgrep
phones
photo
pic
pickup
piconv
pid
pipe
pkcs7
pkcs8
pkcs12
pkg_add
pkg_check
pkg_create
pkg_delete
pkg_info
pkg_sign
pkg_version
pkill
pl2pm
place
pod2html
pod2latex
pod2man
pod2text
pod2usage
podchecker
podselect
poll
popd
popup
posix_madvise
postalias
postcat
postconf
postdrop
postfix
postkick
postlock
postlog
postmap
postqueue
postsuper
pr
pread
preadv
printcap
printenv
printf
proc
procfs
profil
protocols
prove
proxymap
ps
psed
psroff
pstruct
ptrace
publickey
pushd
puts
pwd
pwrite
pwritev
qmgr
qmqpd
quota
quotactl
radiobutton
raise
rand
ranlib
rcp
rcs
rcsclean
rcsdiff
rcsfile
rcsfreeze
rcsintro
rcsmerge
read
readelf
readlink
readonly
readv
realpath
reboot
recv
recvfrom
recvmsg
red
ree
refer
regexp
registry
regsub
rehash
remote
rename
repeat
replace
req
reset
resolver
resource
return
rev
revoke
rfcomm_sppd
rfork
rhosts
ripemd
ripemd160
rlog
rlogin
rm
rmd160
rmdir
rpc
rpcgen
rs
rsa
rsautl
rsh
rtld
rtprio
rup
ruptime
rusers
rwall
rwho
s2p
safe
sasl
sasldblistusers2
saslpasswd2
sbrk
scache
scale
scan
sched
sched_getparam
sched_getscheduler
sched_get_priority_max
sched_get_priority_min
sched_rr_get_interval
sched_setparam
sched_setscheduler
sched_yield
scon
scp
script
scrollbar
sdiff
sed
seek
select
selection
semctl
semget
semop
send
sendbug
sendfile
sendmail
sendmsg
sendto
services
sess_id
set
setegid
setenv
seteuid
setfacl
setgid
setgroups
setitimer
setlogin
setpgid
setpgrp
setpriority
setregid
setresgid
setresuid
setreuid
setrlimit
setsid
setsockopt
settc
settimeofday
setty
setuid
setvar
sftp
sh
sha
sha1
sha256
shar
shells
shift
shmat
shmctl
shmdt
shmget
showq
shutdown
sigaction
sigaltstack
sigblock
sigmask
sigpause
sigpending
sigprocmask
sigreturn
sigsetmask
sigstack
sigsuspend
sigvec
sigwait
size
slapadd
slapcat
slapd
slapdn
slapindex
slappasswd
slaptest
sleep
slogin
slurpd
smbutil
smime
smtp
smtpd
socket
socketpair
sockstat
soelim
sort
source
spawn
speed
spinbox
spkac
splain
split
squid
squid_ldap_auth
squid_ldap_group
squid_unix_group
sscop
ssh
sshd_config
ssh_config
stab
startslip
stat
statfs
stop
string
strings
strip
stty
su
subst
sum
suspend
swapoff
swapon
switch
symlink
sync
sysarch
syscall
sysconftool
sysconftoolcheck
systat
s_client
s_server
s_time
tabs
tail
talk
tar
tbl
tclsh
tcltest
tclvars
tcopy
tcpdump
tcpslice
tcsh
tee
tell
telltc
telnet
term
termcap
terminfo
test
texindex
texinfo
text
textdomain
tfmtodit
tftp
then
threads
time
tip
tk
tkerror
tkvars
tkwait
tlsmgr
tmac
top
toplevel
touch
tput
tr
trace
trafshow
trap
troff
true
truncate
truss
tset
tsort
tty
ttys
type
tzfile
ui
ul
ulimit
umask
unalias
uname
uncomplete
uncompress
undelete
unexpand
unhash
unifdef
unifdefall
uniq
units
unknown
unlimit
unlink
unmount
unset
unsetenv
until
unvis
update
uplevel
uptime
upvar
usbhidaction
usbhidctl
users
utf8
utimes
utmp
utrace
uudecode
uuencode
uuidgen
vacation
variable
verify
version
vfork
vgrind
vgrindefs
vi
vidcontrol
vidfont
view
virtual
vis
vt220keys
vwait
w
wait
wait3
wait4
waitpid
wall
wc
wget
what
whatis
where
whereis
which
while
who
whoami
whois
window
winfo
wish
wm
write
writev
wtmp
x509
xargs
xgettext
xmlwf
xstr
xsubpp
yacc
yes
ypcat
ypchfn
ypchpass
ypchsh
ypmatch
yppasswd
ypwhich
yyfix
zcat
zcmp
zdiff
zegrep
zfgrep
zforce
zgrep
zmore
znew
_exit
__syscall
 
FreeBSD/Linux/UNIX General Commands Manual
Hypertext Man Pages
kse_switchin
 
KSE(2)			  FreeBSD System Calls Manual			KSE(2)

NAME
     kse -- kernel support for user threads

LIBRARY
     Standard C Library (libc, -lc)

SYNOPSIS
     #include 
     #include 

     int
     kse_create(struct kse_mailbox *mbx, int newgroup);

     int
     kse_exit(void);

     int
     kse_release(struct timespec *timeout);

     int
     kse_switchin(mcontext_t *mcp, long val, long *loc);

     int
     kse_thr_interrupt(struct kse_thr_mailbox *tmbx);

     int
     kse_wakeup(struct kse_mailbox *mbx);

DESCRIPTION
     These system calls implement kernel support for multi-threaded processes.

   Overview
     Traditionally, user threading has been implemented in one of two ways:
     either all threads are managed in user space and the kernel is unaware of
     any threading (also known as ``N to 1''), or else separate processes
     sharing a common memory space are created for each thread (also known as
     ``N to N'').  These approaches have advantages and disadvantages:

     User threading		       Kernel threading
     + Lightweight		       - Heavyweight
     + User controls scheduling        - Kernel controls scheduling
     - Syscalls must be wrapped        + No syscall wrapping required
     - Cannot utilize multiple CPUs    + Can utilize multiple CPUs

     The KSE system is a hybrid approach that achieves the advantages of both
     the user and kernel threading approaches.	The underlying philosophy of
     the KSE system is to give kernel support for user threading without tak-
     ing away any of the user threading library's ability to make scheduling
     decisions.  A kernel-to-user upcall mechanism is used to pass control to
     the user threading library whenever a scheduling decision needs to be
     made.  An arbitrarily number of user threads are multiplexed onto a fixed
     number of virtual CPUs supplied by the kernel.  This can be thought of as
     an ``N to M'' threading scheme.

     Some general implications of this approach include:

     o	 The user process can run multiple threads simultaneously on multi-
	 processor machines.  The kernel grants the process virtual CPUs to
	 schedule as it wishes; these may run concurrently on real CPUs.

     o	 All operations that block in the kernel become asynchronous, allowing
	 the user process to schedule another thread when any thread blocks.

     o	 Multiple thread schedulers within the same process are possible, and
	 they may operate independently of each other.

   Definitions
     KSE allows a user process to have multiple threads of execution in exis-
     tence at the same time, some of which may be blocked in the kernel while
     others may be executing or blocked in user space.	A kernel scheduling
     entity (KSE) is a ``virtual CPU'' granted to the process for the purpose
     of executing threads.  A thread that is currently executing is always
     associated with exactly one KSE, whether executing in user space or in
     the kernel.  The KSE is said to be assigned to the thread.

     The KSE becomes unassigned, and the associated thread is suspended, when
     the KSE has an associated mailbox, (see below) the thread has an associ-
     ated thread mailbox, (also see below) and any of the following occurs:

     o	 The thread invokes a system call that blocks.

     o	 The thread makes any other demand of the kernel that cannot be imme-
	 diately satisfied, e.g., touches a page of memory that needs to be
	 fetched from disk, causing a page fault.

     o	 Another thread that was previously blocked in the kernel completes
	 its work in the kernel (or is interrupted) and becomes ready to
	 return to user space, and the current thread is returning to user
	 space.

     o	 A signal is delivered to the process, and this KSE is chosen to
	 deliver it.

     In other words, as soon as there is a scheduling decision to be made, the
     KSE becomes unassigned, because the kernel does not presume to know how
     the process' other runnable threads should be scheduled.  Unassigned KSEs
     always return to user space as soon as possible via the upcall mechanism
     (described below), allowing the user process to decide how that KSE
     should be utilized next.  KSEs always complete as much work as possible
     in the kernel before becoming unassigned.

     A KSE group is a collection of KSEs that are scheduled uniformly and
     which share access to the same pool of threads, which are associated with
     the KSE group.  A KSE group is the smallest entity to which a kernel
     scheduling priority may be assigned.  For the purposes of process sched-
     uling and accounting, each KSE group counts similarly to a traditional
     unthreaded process.  Individual KSEs within a KSE group are effectively
     indistinguishable, and any KSE in a KSE group may be assigned by the ker-
     nel to any runnable (in the kernel) thread associated with that KSE
     group.  In practice, the kernel attempts to preserve the affinity between
     threads and actual CPUs to optimize cache behavior, but this is invisible
     to the user process.  (Affinity is not yet implemented.)

     Each KSE has a unique KSE mailbox supplied by the user process.  A mail-
     box consists of a control structure containing a pointer to an upcall
     function and a user stack.  The KSE invokes this function whenever it
     becomes unassigned.  The kernel updates this structure with information
     about threads that have become runnable and signals that have been deliv-
     ered before each upcall.  Upcalls may be temporarily blocked by the user
     thread scheduling code during critical sections.

     Each user thread has a unique thread mailbox as well.  Threads are
     referred to using pointers to these mailboxes when communicating between
     the kernel and the user thread scheduler.	Each KSE's mailbox contains a
     pointer to the mailbox of the user thread that the KSE is currently exe-
     cuting.  This pointer is saved when the thread blocks in the kernel.

     Whenever a thread blocked in the kernel is ready to return to user space,
     it is added to the KSE group's list of completed threads.	This list is
     presented to the user code at the next upcall as a linked list of thread
     mailboxes.

     There is a kernel-imposed limit on the number of threads in a KSE group
     that may be simultaneously blocked in the kernel (this number is not cur-
     rently visible to the user).  When this limit is reached, upcalls are
     blocked and no work is performed for the KSE group until one of the
     threads completes (or a signal is received).

   Managing KSEs
     To become multi-threaded, a process must first invoke kse_create().  The
     kse_create() system call creates a new KSE (except for the very first
     invocation; see below).  The KSE will be associated with the mailbox
     pointed to by mbx.  If newgroup is non-zero, a new KSE group is also cre-
     ated containing the KSE.  Otherwise, the new KSE is added to the current
     KSE group.  Newly created KSEs are initially unassigned; therefore, they
     will upcall immediately.

     Each process initially has a single KSE in a single KSE group executing a
     single user thread.  Since the KSE does not have an associated mailbox,
     it must remain assigned to the thread and does not perform any upcalls.
     The result is the traditional, unthreaded mode of operation.  Therefore,
     as a special case, the first call to kse_create() by this initial thread
     with newgroup equal to zero does not create a new KSE; instead, it simply
     associates the current KSE with the supplied KSE mailbox, and no immedi-
     ate upcall results.  However, an upcall will be triggered the next time
     the thread blocks and the required conditions are met.

     The kernel does not allow more KSEs to exist in a KSE group than the num-
     ber of physical CPUs in the system (this number is available as the
     sysctl(3) variable hw.ncpu).  Having more KSEs than CPUs would not add
     any value to the user process, as the additional KSEs would just compete
     with each other for access to the real CPUs.  Since the extra KSEs would
     always be side-lined, the result to the application would be exactly the
     same as having fewer KSEs.  There may however be arbitrarily many user
     threads, and it is up to the user thread scheduler to handle mapping the
     application's user threads onto the available KSEs.

     The kse_exit() system call causes the KSE assigned to the currently run-
     ning thread to be destroyed.  If this KSE is the last one in the KSE
     group, there must be no remaining threads associated with the KSE group
     blocked in the kernel.  This system call does not return unless there is
     an error.

     As a special case, if the last remaining KSE in the last remaining KSE
     group invokes this system call, then the KSE is not destroyed; instead,
     the KSE just looses the association with its mailbox and kse_exit()
     returns normally.	This returns the process to its original, unthreaded
     state.

     The kse_release() system call is used to ``park'' the KSE assigned to the
     currently running thread when it is not needed, e.g., when there are more
     available KSEs than runnable user threads.  The thread converts to an
     upcall but does not get scheduled until there is a new reason to do so,
     e.g., a previously blocked thread becomes runnable, or the timeout
     expires.  If successful, kse_release() does not return to the caller.

     The kse_switchin() system call can be used by the UTS, when it has
     selected a new thread, to switch to the context of that thread.  The use
     of kse_switchin() is machine dependent.  Some platforms do not need a
     system call to switch to a new context, while others require its use in
     particular cases.

     The kse_wakeup() system call is the opposite of kse_release().  It causes
     the (parked) KSE associated with the mailbox pointed to by mbx to be
     woken up, causing it to upcall.  If the KSE has already woken up for
     another reason, this system call has no effect.  The mbx argument may be
     NULL to specify ``any KSE in the current KSE group''.

     The kse_thr_interrupt() system call is used to interrupt a currently
     blocked thread.  The thread must either be blocked in the kernel or
     assigned to a KSE (i.e., executing).  The thread is then marked as inter-
     rupted.  As soon as the thread invokes an interruptible system call (or
     immediately for threads already blocked in one), the thread will be made
     runnable again, even though the kernel operation may not have completed.
     The effect on the interrupted system call is the same as if it had been
     interrupted by a signal; typically this means an error is returned with
     errno set to EINTR.

   Signals
     The current implementation creates a special signal thread.  Kernel
     threads (KSEs) in a process mask all signals, and only the signal thread
     waits for signals to be delivered to the process, the signal thread is
     responsible for dispatching signals to user threads.

     A downside of this is that if a multiplexed thread calls the execve()
     syscall, its signal mask and pending signals may not be available in the
     kernel.  They are stored in userland and the kernel does not know where
     to get them, however POSIX requires them to be restored and passed them
     to new process.  Just setting the mask for the thread before calling
     execve() is only a close approximation to the problem as it does not re-
     deliver back to the kernel any pending signals that the old process may
     have blocked, and it allows a window in which new signals may be deliv-
     ered to the process between the setting of the mask and the execve().

     For now this problem has been solved by adding a special combined
     kse_thr_interrupt()/execve() mode to the kse_thr_interrupt() syscall.
     The kse_thr_interrupt() syscall has a sub command KSE_INTR_EXECVE, that
     allows it to accept a kse_execv_args structure, and allowing it to adjust
     the signals and then atomically convert into an execve() call.  Addi-
     tional pending signals and the correct signal mask can be passed to the
     kernel in this way.  The thread library overrides the execve() syscall
     and translates it into kse_intr_interrupt() call, allowing a multiplexed
     thread to restore pending signals and the correct signal mask before
     doing the exec().	This solution to the problem may change.

   KSE Mailboxes
     Each KSE has a unique mailbox for user-kernel communication defined in
     <sys/kse.h>.  Some of the fields there are:

     km_version describes the version of this structure and must be equal to
     KSE_VER_0.  km_udata is an opaque pointer ignored by the kernel.

     km_func points to the KSE's upcall function; it will be invoked using
     km_stack, which must remain valid for the lifetime of the KSE.

     km_curthread always points to the thread that is currently assigned to
     this KSE if any, or NULL otherwise.  This field is modified by both the
     kernel and the user process as follows.

     When km_curthread is not NULL, it is assumed to be pointing at the mail-
     box for the currently executing thread, and the KSE may be unassigned,
     e.g., if the thread blocks in the kernel.	The kernel will then save the
     contents of km_curthread with the blocked thread, set km_curthread to
     NULL, and upcall to invoke km_func().

     When km_curthread is NULL, the kernel will never perform any upcalls with
     this KSE; in other words, the KSE remains assigned to the thread even if
     it blocks.  km_curthread must be NULL while the KSE is executing critical
     user thread scheduler code that would be disrupted by an intervening
     upcall; in particular, while km_func() itself is executing.

     Before invoking km_func() in any upcall, the kernel always sets
     km_curthread to NULL.  Once the user thread scheduler has chosen a new
     thread to run, it should point km_curthread at the thread's mailbox, re-
     enabling upcalls, and then resume the thread.  Note: modification of
     km_curthread by the user thread scheduler must be atomic with the loading
     of the context of the new thread, to avoid the situation where the thread
     context area may be modified by a blocking async operation, while there
     is still valid information to be read out of it.

     km_completed points to a linked list of user threads that have completed
     their work in the kernel since the last upcall.  The user thread sched-
     uler should put these threads back into its own runnable queue.  Each
     thread in a KSE group that completes a kernel operation (synchronous or
     asynchronous) that results in an upcall is guaranteed to be linked into
     exactly one KSE's km_completed list; which KSE in the group, however, is
     indeterminate.  Furthermore, the completion will be reported in only one
     upcall.

     km_sigscaught contains the list of signals caught by this process since
     the previous upcall to any KSE in the process.  As long as there exists
     one or more KSEs with an associated mailbox in the user process, signals
     are delivered this way rather than the traditional way.  (This has not
     been implemented and may change.)

     km_timeofday is set by the kernel to the current system time before per-
     forming each upcall.

     km_flags may contain any of the following bits OR'ed together:

     KMF_NOUPCALL
	     Block upcalls from happening.  The thread is in some critical
	     section.

     KMF_NOCOMPLETED, KMF_DONE, KMF_BOUND
	     This thread should be considered to be permanently bound to its
	     KSE, and treated much like a non-threaded process would be.  It
	     is a ``long term'' version of KMF_NOUPCALL in some ways.

     KMF_WAITSIGEVENT
	     Implement characteristics needed for the signal delivery thread.

   Thread Mailboxes
     Each user thread must have associated with it a unique struct
     kse_thr_mailbox as defined in <sys/kse.h>.  It includes the following
     fields.

     tm_udata is an opaque pointer ignored by the kernel.

     tm_context stores the context for the thread when the thread is blocked
     in user space.  This field is also updated by the kernel before a com-
     pleted thread is returned to the user thread scheduler via km_completed.

     tm_next links the km_completed threads together when returned by the ker-
     nel with an upcall.  The end of the list is marked with a NULL pointer.

     tm_uticks and tm_sticks are time counters for user mode and kernel mode
     execution, respectively.  These counters count ticks of the statistics
     clock (see clocks(7)).  While any thread is actively executing in the
     kernel, the corresponding tm_sticks counter is incremented.  While any
     KSE is executing in user space and that KSE's km_curthread pointer is not
     equal to NULL, the corresponding tm_uticks counter is incremented.

     tm_flags may contain any of the following bits OR'ed together:

     TMF_NOUPCALL
	     Similar to KMF_NOUPCALL.  This flag inhibits upcalling for criti-
	     cal sections.  Some architectures require this to be in one place
	     and some in the other.

RETURN VALUES
     The kse_create(), kse_wakeup(), and kse_thr_interrupt() system calls
     return zero if successful.  The kse_exit() and kse_release() system calls
     do not return if successful.

     All of these system calls return a non-zero error code in case of an
     error.

ERRORS
     The kse_create() system call will fail if:

     [ENXIO]		There are already as many KSEs in the KSE group as
			hardware processors.

     [EAGAIN]		The system-imposed limit on the total number of KSE
			groups under execution would be exceeded.  The limit
			is given by the sysctl(3) MIB variable KERN_MAXPROC.
			(The limit is actually ten less than this except for
			the super user.)

     [EAGAIN]		The user is not the super user, and the system-imposed
			limit on the total number of KSE groups under execu-
			tion by a single user would be exceeded.  The limit is
			given by the sysctl(3) MIB variable
			KERN_MAXPROCPERUID.

     [EAGAIN]		The user is not the super user, and the soft resource
			limit corresponding to the resource argument
			RLIMIT_NPROC would be exceeded (see getrlimit(2)).

     [EFAULT]		The mbx argument points to an address which is not a
			valid part of the process address space.

     The kse_exit() system call will fail if:

     [EDEADLK]		The current KSE is the last in its KSE group and there
			are still one or more threads associated with the KSE
			group blocked in the kernel.

     [ESRCH]		The current KSE has no associated mailbox, i.e., the
			process is operating in traditional, unthreaded mode
			(in this case use _exit(2) to exit the process).

     The kse_release() system call will fail if:

     [ESRCH]		The current KSE has no associated mailbox, i.e., the
			process is operating is traditional, unthreaded mode.

     The kse_wakeup() system call will fail if:

     [ESRCH]		The mbx argument is not NULL and the mailbox pointed
			to by mbx is not associated with any KSE in the
			process.

     [ESRCH]		The mbx argument is NULL and the current KSE has no
			associated mailbox, i.e., the process is operating in
			traditional, unthreaded mode.

     The kse_thr_interrupt() system call will fail if:

     [ESRCH]		The thread corresponding to tmbx is neither currently
			assigned to any KSE in the process nor blocked in the
			kernel.

SEE ALSO
     rfork(2), pthread(3), ucontext(3)

     Thomas E. Anderson, Brian N. Bershad, Edward D. Lazowska, and Henry M.
     Levy, "Scheduler activations: effective kernel support for the user-level
     management of parallelism", ACM Press, ACM Transactions on Computer
     Systems, Issue 1, Volume 10, pp. 53-79, February 1992.

HISTORY
     The KSE system calls first appeared in FreeBSD 5.0.

AUTHORS
     KSE was originally implemented by Julian Elischer ,
     with additional contributions by Jonathan Mini , Daniel
     Eischen , and David Xu .

     This manual page was written by Archie Cobbs .

BUGS
     The KSE code is currently under development.

FreeBSD 6.1		      September 10, 2002		   FreeBSD 6.1
=21045
+2364
(91)