Commit Graph

117 Commits

Author SHA1 Message Date
Jeff Roberson
e8245292a7 - Convert two timeout users to the new callout_reset_curcpu() api.
Sponsored by:	Nokia
2008-04-02 11:21:42 +00:00
Robert Watson
237fdd787b In keeping with style(9)'s recommendations on macros, use a ';'
after each SYSINIT() macro invocation.  This makes a number of
lightweight C parsers much happier with the FreeBSD kernel
source, including cflow's prcc and lxr.

MFC after:	1 month
Discussed with:	imp, rink
2008-03-16 10:58:09 +00:00
John Baldwin
e46502943a Make ftruncate a 'struct file' operation rather than a vnode operation.
This makes it possible to support ftruncate() on non-vnode file types in
the future.
- 'struct fileops' grows a 'fo_truncate' method to handle an ftruncate() on
  a given file descriptor.
- ftruncate() moves to kern/sys_generic.c and now just fetches a file
  object and invokes fo_truncate().
- The vnode-specific portions of ftruncate() move to vn_truncate() in
  vfs_vnops.c which implements fo_truncate() for vnode file types.
- Non-vnode file types return EINVAL in their fo_truncate() method.

Submitted by:	rwatson
2008-01-07 20:05:19 +00:00
Jeff Roberson
397c19d175 Remove explicit locking of struct file.
- Introduce a finit() which is used to initailize the fields of struct file
   in such a way that the ops vector is only valid after the data, type,
   and flags are valid.
 - Protect f_flag and f_count with atomic operations.
 - Remove the global list of all files and associated accounting.
 - Rewrite the unp garbage collection such that it no longer requires
   the global list of all files and instead uses a list of all unp sockets.
 - Mark sockets in the accept queue so we don't incorrectly gc them.

Tested by:	kris, pho
2007-12-30 01:42:15 +00:00
Jeff Roberson
ace8398da0 Refactor select to reduce contention and hide internal implementation
details from consumers.

 - Track individual selecters on a per-descriptor basis such that there
   are no longer collisions and after sleeping for events only those
   descriptors which triggered events must be rescaned.
 - Protect the selinfo (per descriptor) structure with a mtx pool mutex.
   mtx pool mutexes were chosen to preserve api compatibility with
   existing code which does nothing but bzero() to setup selinfo
   structures.
 - Use a per-thread wait channel rather than a global wait channel.
 - Hide select implementation details in a seltd structure which is
   opaque to the rest of the kernel.
 - Provide a 'selsocket' interface for those kernel consumers who wish to
   select on a socket when they have no fd so they no longer have to
   be aware of select implementation details.

Tested by:	kris
Reviewed on:	arch
2007-12-16 06:21:20 +00:00
Craig Rodrigues
d7f81adbd4 Revert previous commits which I committed by mistake.
Approved by:	re (implicit)
Pointy hat to:	me
2007-07-14 21:23:31 +00:00
Craig Rodrigues
d678780e60 The last entry in the ext2_opts array must be NULL,
otherwise the kernel with crash in vfs_filteropt() if an invalid
mount option is passed to ext2fs.

Approved by:	re (kensmith)
2007-07-14 21:18:19 +00:00
Robert Watson
dede2ab3b2 In kern_kevent(), unconditionally fdrop() fp once fget() has succeeded,
as we never have an opportunity to set it to NULL.

Found with:	Coverity Prevent(tm)
CID:		2161
2007-05-28 17:15:05 +00:00
Robert Watson
87066f04c6 Select a more appealing spelling for the word acquire. 2007-05-27 19:24:00 +00:00
Robert Watson
5e3f7694b1 Replace custom file descriptor array sleep lock constructed using a mutex
and flags with an sxlock.  This leads to a significant and measurable
performance improvement as a result of access to shared locking for
frequent lookup operations, reduced general overhead, and reduced overhead
in the event of contention.  All of these are imported for threaded
applications where simultaneous access to a shared file descriptor array
occurs frequently.  Kris has reported 2x-4x transaction rate improvements
on 8-core MySQL benchmarks; smaller improvements can be expected for many
workloads as a result of reduced overhead.

- Generally eliminate the distinction between "fast" and regular
  acquisisition of the filedesc lock; the plan is that they will now all
  be fast.  Change all locking instances to either shared or exclusive
  locks.

- Correct a bug (pointed out by kib) in fdfree() where previously msleep()
  was called without the mutex held; sx_sleep() is now always called with
  the sxlock held exclusively.

- Universally hold the struct file lock over changes to struct file,
  rather than the filedesc lock or no lock.  Always update the f_ops
  field last. A further memory barrier is required here in the future
  (discussed with jhb).

- Improve locking and reference management in linux_at(), which fails to
  properly acquire vnode references before using vnode pointers.  Annotate
  improper use of vn_fullpath(), which will be replaced at a future date.

In fcntl(), we conservatively acquire an exclusive lock, even though in
some cases a shared lock may be sufficient, which should be revisited.
The dropping of the filedesc lock in fdgrowtable() is no longer required
as the sxlock can be held over the sleep operation; we should consider
removing that (pointed out by attilio).

Tested by:	kris
Discussed with:	jhb, kris, attilio, jeff
2007-04-04 09:11:34 +00:00
Robert Watson
0c14ff0eb5 Remove 'MPSAFE' annotations from the comments above most system calls: all
system calls now enter without Giant held, and then in some cases, acquire
Giant explicitly.

Remove a number of other MPSAFE annotations in the credential code and
tweak one or two other adjacent comments.
2007-03-04 22:36:48 +00:00
John Baldwin
6600b45d88 Save exit status of an exiting process in kn_data in the knote.
Submitted by:	Jared Yanovich ^phirerunner at comcast.net^
MFC after:	2 weeks
2006-11-20 22:17:50 +00:00
John-Mark Gurney
33fabe46da remove unnecessary NULL check...
Coverity ID:	1545
2006-09-25 01:29:48 +00:00
John-Mark Gurney
4db71d27a1 hide kqueue_register from public view, and replace it w/ kqfd_register...
this eliminates a possible race in aio registering a kevent..
2006-09-24 04:47:47 +00:00
John-Mark Gurney
9edac6f3f9 add KTRACE hooks into kevent... This will help people debug their kqueue
programs to find out exactly which events were registered and which were
returned...  This should be lower in kern_kevent, but that would require
special munging due to locks and the functions used to copyin/copyout
kevents...

If someone wants to teach ktrace how to output pretty kevents, I have a
kevent prety printer that can be used...
2006-09-24 02:23:29 +00:00
John Baldwin
5c69ad8374 Use fget() in kqueue_register() instead of doing all the work by hand. 2006-06-12 21:46:23 +00:00
Pawel Jakub Dawidek
f420242b2b Don't forget to unlock kq lock in low memory situations.
OK'ed by:	jmg
2006-06-02 13:23:39 +00:00
Pawel Jakub Dawidek
8ebab14c70 Remove confusing done_noglobal label. The KQ_GLOBAL_UNLOCK() macro know
how to handle both situations - when kq_global lock is and is not held.

OK'ed by:	jmg
2006-06-02 13:21:21 +00:00
Pawel Jakub Dawidek
241321abc0 Use SLIST_FOREACH_SAFE() macro, because knote_drop() can free an element
which can be then used to find next element in the list.

OK'ed by:	jmg
2006-06-02 13:18:59 +00:00
John Baldwin
a29b4f6eec Drop the kqueue global mutex as soon as we are finished with it rather
than keeping it locked until we exit the function to optimize the case
where the lock would be dropped and later reacquired.  The optimization
was broken when kevent's were moved from UFS to VFS and the knote list
lock for a vnode kevent became the lockmgr vnode lock.  If one tried
to use a kqueue that contained events for a kqueue fd followed by a vnode,
then the kq global lock would end up being held when the vnode lock was
acquired which could result in sleeping with a mutex held (and subsequent
panics) if the vnode lock was contested.

Reviewed by:	jmg
Tested by:	ps (on 6.x)
MFC after:	3 days
2006-04-14 14:27:28 +00:00
John-Mark Gurney
1c4ca5e5fe spell unlock correctly, this is relatively minor as it's rare someone would
provide a lock method, and want the default unlock, but it is a bug...

PR:		95356
Submitted by:	Stephen Corteselli
MFC after:	3 days
2006-04-07 17:21:27 +00:00
John-Mark Gurney
5e6125891f mask out any action when copying the flags from the event to the knote..
Pointed out by:	Václav Haisman
Submitted by:	Dan Nelson (slightly modifed patch)
MFC after:	3 days
2006-04-01 20:15:39 +00:00
John-Mark Gurney
4e095bc045 hold the list lock over the f_event and KNOTE_ACTIVATE calls... This closes
a race where data could come in before we clear the INFLUX flag, and get
skipped over by knote (and hence never be activated, though it should of
been)...

Found by:	glebius & co.
Reviewed by:	glebius
MFC after:	3 days
2006-03-29 18:15:30 +00:00
Doug Ambrisko
69cd28dacb Add in kqueue support to LIO event notification and fix how it handled
notifications when LIO operations completed.  These were the problems
with LIO event complete notification:
      -	Move all LIO/AIO event notification into one general function
	so we don't have bugs in different data paths.  This unification
	got rid of several notification bugs one of which if kqueue was
	used a SIGILL could get sent to the process.
      -	Change the LIO event accounting to count all AIO request that
	could have been split across the fast path and daemon mode.
	The prior accounting only kept track of AIO op's in that
	mode and not the entire list of operations.  This could cause
	a bogus LIO event complete notification to occur when all of
	the fast path AIO op's completed and not the AIO op's that
	ended up queued for the daemon.

Suggestions from:	alc
2005-10-12 17:51:31 +00:00
Stephan Uphoff
19b2dff7b0 Fix race condition that caused activation of an event to
be ignored immediately after it was deactivated.

Found by: 	Yahoo!
MFC after:	3 days
2005-09-15 21:10:12 +00:00
Suleiman Souhlal
571dcd15e2 Fix the recent panics/LORs/hangs created by my kqueue commit by:
- Introducing the possibility of using locks different than mutexes
for the knlist locking. In order to do this, we add three arguments to
knlist_init() to specify the functions to use to lock, unlock and
check if the lock is owned. If these arguments are NULL, we assume
mtx_lock, mtx_unlock and mtx_owned, respectively.

- Using the vnode lock for the knlist locking, when doing kqueue operations
on a vnode. This way, we don't have to lock the vnode while holding a
mutex, in filt_vfsread.

Reviewed by:	jmg
Approved by:	re (scottl), scottl (mentor override)
Pointyhat to:	ssouhlal
Will be happy:	everyone
2005-07-01 16:28:32 +00:00
Paul Saab
efe5becafa Wrap copyin/copyout for kevent so the 32bit wrapper does not have
to malloc nchanges * sizeof(struct kevent) AND/OR nevents *
sizeof(struct kevent) on every syscall.

Glanced at by:	peter, jmg
Obtained from:	Yahoo!
MFC after:	2 weeks
2005-06-03 23:15:01 +00:00
John-Mark Gurney
b633f50dd8 make stat return an zero'd struct, and be a FIFO again... This is only
to fix libc_r since it requires stat to close fd's, and so commented in
the code...

PR:		threads/75795
Reviewed by:	ps
MFC after:	1 week
2005-05-24 23:42:50 +00:00
John-Mark Gurney
c4c44d2935 fix aio+kq... I've been running ambrisko's test program for much longer
w/o problems than I was before...  This simply brings back the knote_delete
as knlist_delete which will also drop the knote's, instead of just clearing
the list and seeing _ONESHOT...

Fix a race where if a note was _INFLUX and _DETACHED, it could end up being
modified... whoopse..

MFC after:	1 week
Prodded by:	ambrisko and dwhite
2005-03-18 01:11:39 +00:00
Paul Saab
b8a4edc17e Use kern_kevent instead of the stackgap for 32bit syscall wrapping.
Submitted by:	jhb
Tested on:	amd64
2005-03-01 17:45:55 +00:00
Robert Watson
4f7fd28ee1 When invoking callout_init(), spell '1' as "CALLOUT_MPSAFE".
MFC after:	3 days
2005-02-22 13:11:33 +00:00
Poul-Henning Kamp
c711aea6ca Make a bunch of malloc types static.
Found by:	src/tools/tools/kernxref
2005-02-10 12:02:37 +00:00
Poul-Henning Kamp
1b5cd47aa0 Move a FILEDESC_UNLOCK upwards to silence witness. 2004-11-16 14:41:31 +00:00
Poul-Henning Kamp
124e4c3be8 Introduce an alias for FILEDESC_{UN}LOCK() with the suffix _FAST.
Use this in all the places where sleeping with the lock held is not
an issue.

The distinction will become significant once we finalize the exact
lock-type to use for this kind of case.
2004-11-13 11:53:02 +00:00
John-Mark Gurney
583ef6b6d2 /me gets the wrong patch out of the pr :(
/me had the write patch w/o comments on his test system.

Pointed out by:	kuriyama and ache
Pointy hat to:	jmg
2004-10-14 03:26:50 +00:00
John-Mark Gurney
d46316e8f9 fix a bug where signal events didn't set the flags for attach/detach..
PR:		72234
MFC after:	2 days
2004-10-13 20:55:19 +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
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
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
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
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
John-Mark Gurney
7d5e45a391 looks like rwatson forgot tabs... :) 2004-08-13 07:38:58 +00:00
Robert Watson
44f31f7556 Trim trailing white space. 2004-08-12 18:06:21 +00:00
Robert Watson
a6719c82b1 Push Giant acquisition down into fo_stat() from most callers. Acquire
Giant conditional on debug.mpsafenet in the socket soo_stat() routine,
unconditionally in vn_statfile() for VFS, and otherwise don't acquire
Giant.  Accept an unlocked read in kqueue_stat(), and cryptof_stat() is
a no-op.  Don't acquire Giant in fstat() system call.

Note: in fdescfs, fo_stat() is called while holding Giant due to the VFS
stack sitting on top, and therefore there will still be Giant recursion
in this case.
2004-07-22 20:40:23 +00:00
Robert Watson
1c1ce9253f Push acquisition of Giant from fdrop_closed() into fo_close() so that
individual file object implementations can optionally acquire Giant if
they require it:

- soo_close(): depends on debug.mpsafenet
- pipe_close(): Giant not acquired
- kqueue_close(): Giant required
- vn_close(): Giant required
- cryptof_close(): Giant required (conservative)

Notes:

  Giant is still acquired in close() even when closing MPSAFE objects
  due to kqueue requiring Giant in the calling closef() code.
  Microbenchmarks indicate that this removal of Giant cuts 3%-3% off
  of pipe create/destroy pairs from user space with SMP compiled into
  the kernel.

  The cryptodev and opencrypto code appears MPSAFE, but I'm unable to
  test it extensively and so have left Giant over fo_close().  It can
  probably be removed given some testing and review.
2004-07-22 18:35:43 +00:00
Alfred Perlstein
a88295bb83 Disable SIGIO for now, leave a comment as to why it's busted and hard
to fix.
2004-07-15 03:49:52 +00:00
Alfred Perlstein
67543ab1e3 Make FIOASYNC, FIOSETOWN and FIOGETOWN work on kqueues. 2004-07-14 07:02:03 +00:00
Alfred Perlstein
94ed9c8af5 Introduce a new kevent filter. EVFILT_FS that will be used to signal
generic filesystem events to userspace.  Currently only mount and unmount
of filesystems are signalled.  Soon to be added, up/down status of NFS.

Introduce a sysctl node used to route requests to/from filesystems
based on filesystem ids.

Introduce a new vfsop, vfs_sysctl(mp, req) that is used as the callback/
entrypoint by the sysctl code to change individual filesystems.
2004-07-04 10:52:54 +00:00
Robert Watson
948a4734ed Add GIANT_REQUIRED to kqueue_close(), since kqueue currently requires
Giant.
2004-06-01 18:05:41 +00:00
Colin Percival
ec513ff759 Fix filt_timer* races: Finish initializing a knote before we pass it to
a callout, and use the new callout_drain API to make sure that a callout
has finished before we deallocate memory it is using.

PR:		kern/64121
Discussed with:	gallatin
2004-04-07 05:59:57 +00:00