Commit Graph

7695 Commits

Author SHA1 Message Date
Julian Elischer
e8807f22f9 Oops accidentally removed #ifdef SCHED_4BSD
as part of another commit
This function is not yet used in ULE
2004-09-15 03:51:51 +00:00
John-Mark Gurney
31580e6817 unlock global lock in kqueue_scan before msleep'ing to prevent dead
lock..  we didn't unlock global lock earlier to prevent just having
to reaquire it again..

Found by:	peter
Reviewed by:	ps
MFC after:	3 days
2004-09-14 18:38:16 +00:00
Julian Elischer
1f9f5df61d Commit a fix for some panics we've been seeing with preemption.
MFC after:	2 days
2004-09-13 23:06:39 +00:00
Julian Elischer
b2578c6c06 Add some kasserts 2004-09-13 23:02:52 +00:00
Julian Elischer
a3aa559270 make some of these conditions apply equally to both threading systems. 2004-09-13 22:10:04 +00:00
Poul-Henning Kamp
67673e6677 Create struct snapdata which contains the snapshot fields from cdev
and the previously malloc'ed snapshot lock.

Malloc struct snapdata instead of just the lock.

Replace snapshot fields in cdev with pointer to snapdata (saves 16 bytes).

While here, give the private readblock() function a vnode argument
in preparation for moving UFS to access GEOM directly.
2004-09-13 07:29:45 +00:00
Poul-Henning Kamp
883d3c0c07 Remove the buffercache/vnode side of BIO_DELETE processing in
preparation for integration of p4::phk_bufwork.  In the future,
local filesystems will talk to GEOM directly and they will consequently
be able to issue BIO_DELETE directly.  Since the removal of the fla
driver, BIO_DELETE has effectively been a no-op anyway.
2004-09-13 06:50:42 +00:00
Scott Long
1e7fad6b6a Revert the previous round of changes to td_pinned. The scheduler isn't
fully initialed when the pmap layer tries to call sched_pini() early in the
boot and results in an quick panic.  Use ke_pinned instead as was originally
done with Tor's patch.

Approved by: julian
2004-09-11 10:07:22 +00:00
Julian Elischer
513efa5b39 Try committing from the right tree this time
MFC after:	2 days
2004-09-11 00:11:09 +00:00
Julian Elischer
5c854accc1 Make up my mind if cpu pinning is stored in the thread structure or the
scheduler specific extension to it. Put it in the extension as
the implimentation details of how the pinning is done needn't be visible
outside the scheduler.

Submitted by:	tegge  (of course!)   (with changes)
MFC after:	3 days
2004-09-10 22:28:33 +00:00
Julian Elischer
3389af30e8 Add some code to allow threads to nominat a sibling to run if theyu are going to sleep.
MFC after:	1 week
2004-09-10 21:04:38 +00:00
John-Mark Gurney
ca95b2de43 remove giant required from kqueue_close..
Reported by:	kuriyama
MFC after:	3 days
2004-09-10 03:14:32 +00:00
Robert Watson
030c6fb156 Hard code witness lock order for BPF locks. 2004-09-09 05:01:37 +00:00
Poul-Henning Kamp
1affa3adc8 Create simple function init_va_filerev() for initializing a va_filerev
field.

Replace three instances of longhaired initialization va_filerev fields.

Added XXX comment wondering why we don't use random bits instead of
uptime of the system for this purpose.
2004-09-07 09:17:05 +00:00
Julian Elischer
246409821c fix typo
MFC after:	2 days
2004-09-07 07:04:47 +00:00
Julian Elischer
5498350529 Make debug printf less threatenning and make it only print out once.
MFC after:	2 days
2004-09-07 06:38:22 +00:00
Julian Elischer
a8b491c121 Give libthr a choice (per system) of scope_system or scope_thread
scheduling.

MFC after:	4 days
2004-09-07 06:33:39 +00:00
John-Mark Gurney
80e6bbe95b make witness it's own sysctl branch instead of using _ to do this. I have
left the old tunables in to give people a few days to transition their
loader.conf and sysctl.conf's over to the new names..

MFC after:	5 days
2004-09-06 23:27:28 +00:00
John-Mark Gurney
9b90387dcf don't call f_detach if the filter has alread removed the knote.. This
happens when a proc exits, but needs to inform the user that this has
happened..  This also means we can remove the check for detached from
proc and sig f_detach functions as this is doing in kqueue now...

MFC after:	5 days
2004-09-06 19:02:42 +00:00
Julian Elischer
6a574b2afc Don't do IPIs on behalf of interrupt threads.
just punt straight on through to teh preemption code.

Make a KASSSERT out of a condition that can no longer occur.
MFC after:	1 week
2004-09-06 07:23:14 +00:00
Julian Elischer
0fe38d47b7 slight code cleanup
MFC after:	1 week
2004-09-05 23:23:58 +00:00
Alfred Perlstein
4c0bef6230 It's too easy to panic the machine when INVARIANTS are turned on
and you botch a call to nmount(2).

This is because there is an INVARIANTS check that asserts that
opt->len must be zero if opt->val is not NULL.  The problem is that
the code does not actually follow this invariant if there is an
error while processing mount options.

Fix the code to honor the INVARIANT.

Silence on: fs@
2004-09-05 22:24:28 +00:00
Robert Watson
76f6939888 Expand the scope of the socket buffer locks in sopoll() to include the
state test as well as set, or we risk a race between a socket wakeup
and registering for select() or poll() on the socket.  This does
increase the cost of the poll operation, but can probably be optimized
some in the future.

This appears to correct poll() "wedges" experienced with X11 on SMP
systems with highly interactive applications, and might affect a plethora
of other select() driven applications.

RELENG_5 candidate.

Problem reported by:	Maxim Maximov <mcsi at mcsi dot pp dot ru>
Debugged with help of:	dwhite
2004-09-05 14:33:21 +00:00
Julian Elischer
bce73aeddb turn on IPIs for 4bsd scheduler by default.
MFC after:	1 week
2004-09-05 02:19:53 +00:00
Julian Elischer
ed062c8d66 Refactor a bunch of scheduler code to give basically the same behaviour
but with slightly cleaned up interfaces.

The KSE structure has become the same as the "per thread scheduler
private data" structure. In order to not make the diffs too great
one is #defined as the other at this time.

The KSE (or td_sched) structure is  now allocated per thread and has no
allocation code of its own.

Concurrency for a KSEGRP is now kept track of via a simple pair of counters
rather than using KSE structures as tokens.

Since the KSE structure is different in each scheduler, kern_switch.c
is now included at the end of each scheduler. Nothing outside the
scheduler knows the contents of the KSE (aka td_sched) structure.

The fields in the ksegrp structure that are to do with the scheduler's
queueing mechanisms are now moved to the kg_sched structure.
(per ksegrp scheduler private data structure). In other words how the
scheduler queues and keeps track of threads is no-one's business except
the scheduler's. This should allow people to write experimental
schedulers with completely different internal structuring.

A scheduler call sched_set_concurrency(kg, N) has been added that
notifies teh scheduler that no more than N threads from that ksegrp
should be allowed to be on concurrently scheduled. This is also
used to enforce 'fainess' at this time so that a ksegrp with
10000 threads can not swamp a the run queue and force out a process
with 1 thread, since the current code will not set the concurrency above
NCPU, and both schedulers will not allow more than that many
onto the system run queue at a time. Each scheduler should eventualy develop
their own methods to do this now that they are effectively separated.

Rejig libthr's kernel interface to follow the same code paths as
linkse for scope system threads. This has slightly hurt libthr's performance
but I will work to recover as much of it as I can.

Thread exit code has been cleaned up greatly.
exit and exec code now transitions a process back to
'standard non-threaded mode' before taking the next step.
Reviewed by:	scottl, peter
MFC after:	1 week
2004-09-05 02:09:54 +00:00
Julian Elischer
00b0483d5c Don't declare a function we are not defining. 2004-09-03 09:19:49 +00:00
Julian Elischer
37c28a022b fix compile for UP 2004-09-03 09:15:10 +00:00
Julian Elischer
293968d8d3 ooops finish last commit.
moved the variables but not the declarations.
2004-09-03 08:19:31 +00:00
Julian Elischer
82a1dfc16d Move 4bsd specific experimental IP code into the 4bsd file.
Move the sysctls into kern.sched
2004-09-03 07:42:31 +00:00
Alan Cox
94ddc7076d Push Giant deep into vm_forkproc(), acquiring it only if the process has
mapped System V shared memory segments (see shmfork_myhook()) or requires
the allocation of an ldt (see vm_fault_wire()).
2004-09-03 05:11:32 +00:00
Robert Watson
b6ac582880 Tag AIO as requiring Giant over the network stack using
NET_NEEDS_GIANT().

RELENG_5 candidate.
2004-09-03 03:19:14 +00:00
Julian Elischer
44692526be remove unused code
MFC after:	 2 days
2004-09-02 23:37:41 +00:00
Scott Long
9923b511ed Turn PREEMPTION into a kernel option. Make sure that it's defined if
FULL_PREEMPTION is defined.  Add a runtime warning to ULE if PREEMPTION is
enabled (code inspired by the PREEMPTION warning in kern_switch.c).  This
is a possible MT5 candidate.
2004-09-02 18:59:15 +00:00
Julian Elischer
7e37fb1729 *Blush* forgot to test non SMP builds.. oddly enough some UP code (particularly
in the acpi code) seems to want this in a UP build. (I guess so you can have
a sigle kernel module that works for both)
2004-09-01 18:05:43 +00:00
Julian Elischer
6804a3ab6d Give the 4bsd scheduler the ability to wake up idle processors
when there is new work to be done.

MFC after:	5 days
2004-09-01 06:42:02 +00:00
Julian Elischer
2630e4c90c Give setrunqueue() and sched_add() more of a clue as to
where they are coming from and what is expected from them.

MFC after:	2 days
2004-09-01 02:11:28 +00:00
David Xu
cf1867f932 Remove TDP_USTATCLOCK, we no longer need it because we now always
update tick count for userland in thread_userret. This change
also removes a "no upcall owned" panic because fuword() schedules
an upcall under heavily loaded, and code assumes there is no upcall
can occur.

Reported and Tested by: Peter Holm <peter@holm.cc>
2004-08-31 11:52:05 +00:00
Julian Elischer
5995adc206 Remove an unneeded argument..
The removed argument could trivially be derived from the remaining one.
That in turn should be the same as curthread, but it is possible that curthread could be expensive to derive on some syste,s so leave it as an argument.
Having both proc and thread as an argumen tjust gives an opportunity for
them to get out sync.

MFC after:	3 days
2004-08-31 07:34:54 +00:00
Julian Elischer
99e9dcb817 Remove sched_free_thread() which was only used
in diagnostics. It has outlived its usefulness and has started
causing panics for people who turn on DIAGNOSTIC, in what is otherwise
good code.

MFC after:	2 days
2004-08-31 06:12:13 +00:00
Warner Losh
2063e05140 Fix BUS_DEBUG case 2004-08-30 05:48:49 +00:00
Pawel Jakub Dawidek
2e4db7cfd7 Add a missing '\n'. 2004-08-30 01:10:20 +00:00
David Xu
45a4bfa17d Only test return_instead if P_SINGLE_EXIT is set, otherwise a fork()
syscall can interrupt other thread's syscall in sleepq_catch_signals().
Current, all callers know thread_suspend_check may suspend thread
itself, so we need't to check return_instead for normal suspension
flags (no P_SINGLE_EXIT set).

Tested by: deischen
Reported by: Maarten L. Hekkelman <m.hekkelman@cmbi.kun.nl>
2004-08-29 23:10:02 +00:00
Warner Losh
f52c5866ea Initial support (disabled) for rebidding devices. I've been running
this in my tree for a while and in its disabled state there are no
issues.  It isn't enabled yet because some drivers (in acpi) have side
effects in their probe routines that need to be resolved in some
manner before this can be turned on.  The consensus at the last
developer's summit was to provide a static method for each driver
class that will return characteristics of the driver, one of which is
if can be reprobed idempotently.
2004-08-29 18:25:21 +00:00
Warner Losh
3cdf2a3f20 MFp4: Merge in the patches, submitted long ago by someone whose email
address I've lost, that move the location information to the atttach
routine as well.  While one could use devinfo to get this data, that
is difficult and error prone and subject to races for short lived
devices.

Would make a good MT5 candidate.
2004-08-29 18:11:10 +00:00
Dag-Erling Smørgrav
0eac4495db Remove the HW_WDOG option; it serves no purpose.
MFC after:	3 days
2004-08-29 11:10:09 +00:00
Ian Dowse
70b7ffee1b Add support for completing the installation of ELF relocatable
object format modules that were read in by the loader. Loading
modules via the loader should now work on the amd64 platform.
2004-08-29 01:21:51 +00:00
David Xu
5897f840f0 1. try to use existing mailbox address in thread_update_usr_ticks.
2. remove '\n' in KASSERT.
2004-08-28 04:16:32 +00:00
David Xu
ad1280b593 Move TDF_CAN_UNBIND to thread private flags td_pflags, this eliminates
need of sched_lock in some places. Also in thread_userret, remove
spare thread allocation code, it is already done in thread_user_enter.

Reviewed by: julian
2004-08-28 04:08:05 +00:00
Peter Wemm
6f96710c60 Backout the previous backout (with scott's ok). sched_ule.c:1.122 is
believed to fix the problem with ULE that this change triggered.
2004-08-28 01:04:44 +00:00
David E. O'Brien
dd68efd05b s/smp_rv_mtx/smp_ipi_mtx/g
Requested by:	jhb
2004-08-28 00:49:55 +00:00
Peter Wemm
91c1172a5a Commit Jeff's suggested changes for avoiding a bug that is exposed by
preemption and/or the rev 1.79 kern_switch.c change that was backed out.

The thread was being assigned to a runq without adding in the load, which
would cause the counter to hit -1.
2004-08-28 00:49:22 +00:00
Andre Oppermann
2580f4e584 Poll() uses the array smallbits that is big enough to hold 32 struct
pollfd's to avoid calling malloc() on small numbers of fd's.  Because
smalltype's members have type char, its address might be misaligned
for a struct pollfd.  Change the array of char to an array of struct
pollfd.

PR:		kern/58214
Submitted by:	Stefan Farfeleder <stefan@fafoe.narf.at>
Reviewed by:	bde (a long time ago)
MFC after:	3 days
2004-08-27 21:23:50 +00:00
Alexander Kabaev
4cef6d5a53 Reintroduce slightly modified patch from kern/69964. Check for
LK_HAVE_EXL in both acquire invocations.

MFC after:	5 days
2004-08-27 01:41:28 +00:00
Ian Dowse
0ca311f6a1 When trying each linker class in turn with a preloaded module, exit
the loop if the preload was successful. Previously a successful
preload was ignored if the linker class was not the last in the
list.
2004-08-27 01:20:26 +00:00
Robert Watson
161a0c7cff Don't hold the UNIX domain socket subsystem lock over the body of the
UNIX domain socket garbage collection implementation, as that risks
holding the mutex over potentially sleeping operations (as well as
introducing some nasty lock order issues, etc).  unp_gc() will hold
the lock long enough to do necessary deferal checks and set that it's
running, but then release it until it needs to reset the gc state.

RELENG_5 candidate.

Discussed with:	alfred
2004-08-25 21:24:36 +00:00
Robert Watson
fe0f2d4e11 Conditional acquisition of socket buffer mutexes when testing socket
buffers with kqueue filters is no longer required: the kqueue framework
will guarantee that the mutex is held on entering the filter, either
due to a call from the socket code already holding the mutex, or by
explicitly acquiring it.  This removes the last of the conditional
socket locking.
2004-08-24 05:28:18 +00:00
Warner Losh
0160658e84 Set the description to NULL in the right detach routine. This should
keep dangling pointers to strings in loaded modules from hanging
around after the drivers are unloaded.
2004-08-24 05:19:15 +00:00
David Xu
d30412a8db Remove checking of single exit flag in thread_user_enter(), this is
generic code for threaded process, should not be here.
2004-08-23 22:54:37 +00:00
Peter Wemm
f1009e1e1f Commit Doug White and Alan Cox's fix for the cross-ipi smp deadlock.
We were obtaining different spin mutexes (which disable interrupts after
aquisition) and spin waiting for delivery.  For example, KSE processes
do LDT operations which use smp_rendezvous, while other parts of the
system are doing things like tlb shootdowns with a different mutex.

This patch uses the common smp_rendezvous mutex for all MD home-grown
IPIs that spinwait for delivery.  Having the single mutex means that
the spinloop to aquire it will enable interrupts periodically, thus
avoiding the cross-ipi deadlock.

Obtained from: dwhite, alc
Reviewed by:   jhb
2004-08-23 21:39:29 +00:00
Alexander Kabaev
cffdaf2dce Temporarily back out r1.74 as it seems to cause a number of regressions
accordimg to numerous reports. It  might get reintroduced some time later
when an exact failure mode is understood better.
2004-08-23 02:39:45 +00:00
Robert Watson
d963815baf Make debug.kdb.stop_cpus also a TUNABLE() so it can be set prior to boot
to help debug early nasty hangs.
2004-08-22 15:10:52 +00:00
Julian Elischer
ad59c36ba1 diff reduction for upcoming patch. Use a macro that masks
some of the odd goings on with sub-structures, because they will
go away anyhow.
2004-08-22 05:21:41 +00:00
Don Lewis
1a1c04b6b3 Don't bother calling the module event handlers from module_shutdown()
in the shutdown_final state if the RB_NOSYNC flag is set.

The specific motivation in this case is that a system panic in an
interrupt context results in a call to module_shutdown(), which
calls g_modevent(), which calls g_malloc(..., M_WAITOK), which
results in a second panic.   While g_modevent() could be fixed to
not call malloc() for MOD_SHUTDOWN events (which it doesn't handle
in any case), it is probably also a good idea to entirely skip the
execution of the module shutdown handlers after a panic.

This may be a MFC candidate for RELENG_5.
2004-08-20 21:47:48 +00:00
Don Lewis
8ded654028 Don't attempt to trigger the syncer thread final sync code in the
shutdown_pre_sync state if the RB_NOSYNC flag is set.  This is the
likely cause of hangs after a system panic that are keeping crash
dumps from being done.

This is a MFC candidate for RELENG_5.

MFC after:	3 days
2004-08-20 19:21:47 +00:00
John Baldwin
55c45354ff Remove some dead code under a straggling APIC_IO #ifdef that I missed
back before 5.2.
2004-08-20 17:24:52 +00:00
Robert Watson
7b38f0d3c3 Back out uipc_socket.c:1.208, as it incorrectly assumes that all
sockets are connection-oriented for the purposes of kqueue
registration.  Since UDP sockets aren't connection-oriented, this
appeared to break a great many things, such as RPC-based
applications and services (i.e., NFS).  Since jmg isn't around I'm
backing this out before too many more feet are shot, but intend to
investigate the right solution with him once he's available.

Apologies to:	jmg
Discussed with:	imp, scottl
2004-08-20 16:24:23 +00:00
Scott Long
2384290ced Revert the previous change. It works great for 4BSD but causes major
problems for ULE.  The reason is quite unknown and worrisome.
2004-08-20 05:58:38 +00:00
Scott Long
2c86298c6c In maybe_preempt(), ignore threads that are in an inconsistent state. This
is an effective band-aid for at least some of the scheduler corruption seen
recently.  The real fix will involve protecting threads while they are
inconsistent, and will come later.

Submitted by: julian
2004-08-20 05:18:50 +00:00
John-Mark Gurney
5d6dd4685a make sure that the socket is either accepting connections or is connected
when attaching a knote to it...  otherwise return EINVAL...

Pointed out by:	benno
2004-08-20 04:15:30 +00:00
Nate Lawson
0b54748fec Add a newline. 2004-08-19 20:16:09 +00:00
Poul-Henning Kamp
d298f91974 Add bioq_takefirst().
If the bioq is empty, NULL is returned.  Otherwise the front element
is removed and returned.

This can simplify locking in many drivers from:

	lock()
	bp = bioq_first(bq);
	if (bp == NULL) {
		unlock()
		return
	}
	bioq_remove(bp, bq)
	unlock
to:
	lock()
	bp = bioq_takefirst(bq);
	unlock()
	if (bp == NULL)
		return;
2004-08-19 19:51:51 +00:00
Nate Lawson
c003dab8ff Add debugging to rman_manage_region() as well. This is useful since we
manage subregions in ACPI.

MFC after:	3 days
2004-08-19 16:41:12 +00:00
Robert Watson
16239786ca Remove GIANT_REQUIRED from setugidsafety() as knote_fdclose() no longer
requires Giant.
2004-08-19 14:59:51 +00:00
John Baldwin
007ddf7e7a Now that the return value semantics of cv's for multithreaded processes
have been unified with that of msleep(9), further refine the sleepq
interface and consolidate some duplicated code:
- Move the pre-sleep checks for theaded processes into a
  thread_sleep_check() function in kern_thread.c.
- Move all handling of TDF_SINTR to be internal to subr_sleepqueue.c.
  Specifically, if a thread is awakened by something other than a signal
  while checking for signals before going to sleep, clear TDF_SINTR in
  sleepq_catch_signals().  This removes a sched_lock lock/unlock combo in
  that edge case during an interruptible sleep.  Also, fix
  sleepq_check_signals() to properly handle the condition if TDF_SINTR is
  clear rather than requiring the callers of the sleepq API to notice
  this edge case and call a non-_sig variant of sleepq_wait().
- Clarify the flags arguments to sleepq_add(), sleepq_signal() and
  sleepq_broadcast() by creating an explicit submask for sleepq types.
  Also, add an explicit SLEEPQ_MSLEEP type rather than a magic number of
  0.  Also, add a SLEEPQ_INTERRUPTIBLE flag for use with sleepq_add() and
  move the setting of TDF_SINTR to sleepq_add() if this flag is set rather
  than sleepq_catch_signals().  Note that it is the caller's responsibility
  to ensure that sleepq_catch_signals() is called if and only if this flag
  is passed to the preceeding sleepq_add().  Note that this also removes a
  sched_lock lock/unlock pair from sleepq_catch_signals().  It also ensures
  that for an interruptible sleep, TDF_SINTR is always set when
  TD_ON_SLEEPQ() is true.
2004-08-19 11:31:42 +00:00
John-Mark Gurney
000968010a add options MPROF_BUFFERS and MPROF_HASH_SIZE that adjust the sizes of
the mutex profiling buffers.  Document them in the man page and in NOTES.
Ensure _HASH_SIZE is larger than _BUFFERS with a cpp error.
2004-08-19 06:38:26 +00:00
Robert Watson
4c5bc1ca39 Add UNP_UNLOCK_ASSERT() to asser that the UNIX domain socket subsystem
lock is not held.

Rather than annotating that the lock is released after calls to
unp_detach() with a comment, annotate with an assertion.

Assert that the UNIX domain socket subsystem lock is not held when
unp_externalize() and unp_internalize() are called.
2004-08-19 01:45:16 +00:00
Robert Watson
2cfe973b62 Annotate call to DELAY() in interrupt storm mitigation as being
something to revisit.

Approved by:	re (scottl)
2004-08-17 04:09:09 +00:00
Alexander Kabaev
c8b876219f Upgrading a lock does not play well together with acquiring an exclusive lock
and can lead to two threads being granted exclusive access. Check that no one
has the same lock in exclusive  mode before proceeding to acquire it.

The LK_WANT_EXCL and LK_WANT_UPGRADE bits act as mini-locks and can block
other threads.  Normally this is not a problem since the mini locks are
upgraded to full locks and the release of the locks will unblock the other
threads.  However if a thread reset the bits without obtaining a full lock
other threads are not awoken. Add missing wakeups for these cases.

PR:		kern/69964
Submitted by:	Stephan Uphoff <ups at tree dot com>
Very good catch by: Stephan Uphoff <ups at tree dot com>
2004-08-16 15:01:22 +00:00
David E. O'Brien
78c37b0de8 s/MAX_SAFE_MAXVNODES/MAXVNODES_MAX/g 2004-08-16 08:33:37 +00:00
Robert Watson
40f2ac28a0 Always acquire the UNIX domain socket subsystem lock (UNP lock)
before dereferencing sotounpcb() and checking its value, as so_pcb
is protected by protocol locking, not subsystem locking.  This
prevents races during close() by one thread and use of ths socket
in another.

unp_bind() now assert the UNP lock, and uipc_bind() now acquires
the lock around calls to unp_bind().
2004-08-16 04:41:03 +00:00
Brian Feldman
8912c44d9f Add the missing knote_fdclose(). 2004-08-16 03:09:01 +00:00
Brian Feldman
1c0f9af5b5 Allocate the marker, when scanning a kqueue, from the "heap" instead of the
stack.  When swapped out, a process's kernel stack would be unavailable,
and we could get a page fault when scanning the same kqueue.

PR:	kern/61849
2004-08-16 03:08:38 +00:00
Robert Watson
ce5f32de11 Annotate the current UNIX domain socket locking strategies, order,
strengths, and weaknesses in a comment.  Assert a copyright over the
changes made as part of the locking work.
2004-08-16 01:52:04 +00:00
Mike Silbersack
5173e8f567 Major enhancements to pipe memory usage:
- pipespace is now able to resize non-empty pipes; this allows
  for many more resizing opportunities

- Backing is no longer pre-allocated for the reverse direction
  of pipes.  This direction is rarely (if ever) used, so this cuts the
  amount of map space allocated to a pipe in half.

- Pipe growth is now much more dynamic; a pipe will now grow when
  the total amount of data it contains and the size of the write are
  larger than the size of pipe.  Previously, only individual writes greater
  than the size of the pipe would cause growth.

- In low memory situations, pipes will now shrink during both read
  and write operations, where possible.  Once the memory shortage
  ends, the growth code will cause these pipes to grow back to an appropriate
  size.

- If the full PIPE_SIZE allocation fails when a new pipe is created, the
  allocation will be retried with SMALL_PIPE_SIZE.  This helps to deal
  with the situation of a fragmented map after a low memory period has
  ended.

- Minor documentation + code changes to support the above.

In total, these changes increase the total number of pipes that
can be allocated simultaneously, drastically reducing the chances that
pipe allocation will fail.

Performance appears unchanged due to dynamic resizing.
2004-08-16 01:27:24 +00:00
Don Lewis
b6915bdbe5 Yet another tweak to the shutdown messages in boot():
Don't count busy buffers before the initial call to sync() and
  don't skip the initial sync() if no busy buffers were called.
  Always call sync() at least once if syncing is requested.  This
  defers the "Syncing disks, buffers remaining..." message until
  after the initial sync() call and the first count of busy
  buffers.  This backs out changes in kern_shutdown 1.162.

  Print a different message when there are no busy buffers after the
  initial sync(), which is now the expected situation.

  Print an additional message when syncing has completed successfully
  in the unusual situation where the work of syncing was done by
  boot().

  Uppercase one message to make it consistent with all of the other
  kernel shutdown messages.

Discussed with:	bde (in a much earlier form, prior to 1.162)
Reviewed by:	njl (in an earlier form)
2004-08-15 19:17:23 +00:00
John-Mark Gurney
ad3b9257c2 Add locking to the kqueue subsystem. This also makes the kqueue subsystem
a more complete subsystem, and removes the knowlege of how things are
implemented from the drivers.  Include locking around filter ops, so a
module like aio will know when not to be unloaded if there are outstanding
knotes using it's filter ops.

Currently, it uses the MTX_DUPOK even though it is not always safe to
aquire duplicate locks.  Witness currently doesn't support the ability
to discover if a dup lock is ok (in some cases).

Reviewed by:	green, rwatson (both earlier versions)
2004-08-15 06:24:42 +00:00
Robert Watson
d8939d82cb Add a new sysctl, debug.kdb.stop_cpus, which controls whether or not we
attempt to IPI other cpus when entering the debugger in order to stop
them while in the debugger.  The default remains to issue the stop;
however, that can result in a hang if another cpu has interrupts disabled
and is spinning, since the IPI won't be received and the KDB will wait
indefinitely.  We probably need to add a timeout, but this is a useful
stopgap in the mean time.

Reviewed by:	marcel
2004-08-15 02:06:27 +00:00
Robert Watson
6cbea71c82 Cause pfind() not to return processes in the PRS_NEW state. As a result,
threads consuming the result of pfind() will not need to check for a NULL
credential pointer or other signs of an incompletely created process.
However, this also means that pfind() cannot be used to test for the
existence or find such a process.  Annotate pfind() to indicate that this
is the case.  A review of curent consumers seems to indicate that this is
not a problem for any of them.  This closes a number of race conditions
that could result in NULL pointer dereferences and related failure modes.
Other related races continue to exist, especially during iteration of the
allproc list without due caution.

Discussed with:	tjr, green
2004-08-14 17:15:16 +00:00
Poul-Henning Kamp
d8e8b6755c Add some KASSERTS. 2004-08-14 08:33:49 +00:00
Julian Elischer
f0017f3321 Whitespace nit. 2004-08-14 07:21:20 +00:00
Robert Watson
b295bdcded After completing a name lookup for a target UNIX domain socket to
connect to, re-check that the local UNIX domain socket hasn't been
closed while we slept, and if so, return EINVAL.  This affects the
system running both with and without Giant over the network stack,
and recent ULE changes appear to cause it to trigger more
frequently than previously under load.  While here, improve catching
of possibly closed UNIX domain sockets in one or two additional
circumstances.  I have a much larger set of related changes in
Perforce, but they require more testing before they can be merged.

One debugging printf is left in place to indicate when such a race
takes place: this is typically triggered by a buggy application
that simultaenously connect()'s and close()'s a UNIX domain socket
file descriptor.  I'll remove this at some point in the future, but
am interested in seeing how frequently this is reported.  In the
case of Martin's reported problem, it appears to be a result of a
non-thread safe syslog() implementation in the C library, which
does not synchronize access to its logging file descriptor.

Reported by:	mbr
2004-08-14 03:43:49 +00:00
John-Mark Gurney
ac77164d64 clean up whitespace... 2004-08-13 17:43:53 +00:00
John-Mark Gurney
7d5e45a391 looks like rwatson forgot tabs... :) 2004-08-13 07:38:58 +00:00
Julian Elischer
c00661f83c Don't keep evaluating our own cpu mask..
it's not likely to have changed....
2004-08-13 00:57:43 +00:00
Robert Watson
44f31f7556 Trim trailing white space. 2004-08-12 18:06:21 +00:00
Warner Losh
9f7f340a0f Minor formatting fixes for lines > 80 characters 2004-08-12 17:26:22 +00:00
Jeff Roberson
f2b74cbf28 - Introduce a new flag KEF_HOLD that prevents sched_add() from doing a
migration.  Use this in sched_prio() and sched_switch() to stop us from
   migrating threads that are in short term sleeps or are runnable.  These
   extra migrations were added in the patches to support KSE.
 - Only set NEEDRESCHED if the thread we're adding in sched_add() is a
   lower priority and is being placed on the current queue.
 - Fix some minor whitespace problems.
2004-08-12 07:56:33 +00:00
Julian Elischer
0f54f48225 Properly keep track of how many kses are on the system run queue(s). 2004-08-11 20:54:48 +00:00
Robert Watson
217a4b6e4e Replace a reference to splnet() with a reference to locking in a comment. 2004-08-11 03:43:10 +00:00
Marcel Moolenaar
4da47b2fec Add __elfN(dump_thread). This function is called from __elfN(coredump)
to allow dumping per-thread machine specific notes. On ia64 we use this
function to flush the dirty registers onto the backingstore before we
write out the PRSTATUS notes.

Tested on: alpha, amd64, i386, ia64 & sparc64
Not tested on: arm, powerpc
2004-08-11 02:35:06 +00:00