Commit Graph

117 Commits

Author SHA1 Message Date
Attilio Rao
22db15c06f VOP_LOCK1() (and so VOP_LOCK()) and VOP_UNLOCK() are only used in
conjuction with 'thread' argument passing which is always curthread.
Remove the unuseful extra-argument and pass explicitly curthread to lower
layer functions, when necessary.

KPI results broken by this change, which should affect several ports, so
version bumping and manpage update will be further committed.

Tested by: kris, pho, Diego Sardina <siarodx at gmail dot com>
2008-01-13 14:44:15 +00:00
Attilio Rao
cb05b60a89 vn_lock() is currently only used with the 'curthread' passed as argument.
Remove this argument and pass curthread directly to underlying
VOP_LOCK1() VFS method. This modify makes the code cleaner and in
particular remove an annoying dependence helping next lockmgr() cleanup.
KPI results, obviously, changed.

Manpage and FreeBSD_version will be updated through further commits.

As a side note, would be valuable to say that next commits will address
a similar cleanup about VFS methods, in particular vop_lock1 and
vop_unlock.

Tested by:	Diego Sardina <siarodx at gmail dot com>,
		Andrea Di Pasquale <whyx dot it at gmail dot com>
2008-01-10 01:10:58 +00:00
Kris Kennaway
e6d64a0f15 Remove remaining Giant acquisition around vn_fullpath1. This was missed
in r1.106 and has not been required for some years now.

Reviewed by:  jeff
MFC After:    1 week
2007-11-22 21:26:25 +00:00
Pawel Jakub Dawidek
b4d7e2983c Fix some locking cases where we ask for exclusively locked vnode, but we get
shared locked vnode in instead when vfs.lookup_shared is set to 1.

Discussed with:	kib, kris
Tested by:	kris
Approved by:	re (kensmith)
2007-09-21 10:16:56 +00:00
Pawel Jakub Dawidek
dfe97ff4a5 We only flush entries related to the given file system. Currently there are
no 'invalid' cache entires - file system is responsible for keeping it that
way. The comment should have been updated in rev.1.25.
2007-06-18 09:28:24 +00:00
Pawel Jakub Dawidek
6e042171bd To avoid a deadlock when handling .. directory during a lookup, we unlock
parent vnode and relock it after locking child vnode. The problem was that
we always relock it exclusively, even when it was share-locked.

Discussed with:	jeff
2007-05-25 22:23:38 +00:00
Pawel Jakub Dawidek
b4c85af977 We no longer need to put namecache entries onto temporary mplist.
It was useful in revision 1.86, but should have been removed in 1.89.
2007-05-25 22:19:49 +00:00
Pawel Jakub Dawidek
950afe9972 The cache_leaf_test() function seems to be unused, so remove it. 2007-05-25 22:16:17 +00:00
Pawel Jakub Dawidek
f013ccb768 - Remove redundant initialization.
- Compare pointer with NULL.
2007-05-22 23:05:48 +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
873fbcd776 Further system call comment cleanup:
- Remove also "MP SAFE" after prior "MPSAFE" pass. (suggested by bde)
- Remove extra blank lines in some cases.
- Add extra blank lines in some cases.
- Remove no-op comments consisting solely of the function name, the word
  "syscall", or the system call name.
- Add punctuation.
- Re-wrap some comments.
2007-03-05 13:10:58 +00:00
Christian S.J. Peron
4f0840f348 Axe Giant from vn_fullpath(9). The vnode -> pathname lookup should be
filesystem agnostic. We are not touching any file system specific functions
in this code path. Since we have a cache lock, there is really no need to
keep Giant around here.

This eliminates Giant acquisitions for any syscall which is auditing pathnames.

Discussed with:	jeff
2006-06-16 05:09:28 +00:00
John-Mark Gurney
e98b5a89de remove duplicate sizeof vnode entry (debug.sizeof.vnode already existed)...
move ncsize into debug.sizeof and rename to namecache...
2006-04-16 18:38:30 +00:00
Jeff Roberson
2f0bca553a - Don't check v_mount for NULL to determine if a vnode has been recycled.
Use the more appropriate VI_DOOMED flag instead.

Sponsored by:	Isilon Systems, Inc.
MFC After:	1 week
2006-02-06 10:15:27 +00:00
Jeff Roberson
32b6dcd8a4 - Fix a leaked reference to a vnode via v_dd. We rely on cache_purge() and
cache_zap() to clear the v_dd pointers when a directory vnode is forcibly
   discarded.  For this to work, all vnodes with v_dd pointers to a directory
   must also have name cache entries linked via v_cache_dst to that dvp
   otherwise we could not find them at cache_purge() time.  The following
   code snipit could break this guarantee by unlinking a directory before
   fetching it's dotdot.  The dotdot lookup would initialize the v_dd field
   of the unlinked directory which could never be cleared.  To fix this
   we don't initialize v_dd for orphaned vnodes.
        printf("rmdir: %d\n", rmdir("../foo")); /* foo is cwd */
        printf("chdir: %d\n", chdir(".."));
        printf("%s\n", getwd(NULL));

Sponsored by:	Isilon Systems, Inc.
Discovered by:	kkenn
Approved by:	re (blanket vfs)
2005-06-17 01:05:13 +00:00
Jeff Roberson
6bd8103d33 - Clear v_dd in cache_zap() instead of cache_purge() as cache_purge() may
not be called in all cases where we free the cnp.

Sponsored by:	Isilon Systems, Inc.
2005-06-13 05:59:59 +00:00
Jeff Roberson
eff2d12635 - Add KTR_VFS messages for various name cache related events.
Sponsored by:	Isilon Systems, Inc.
2005-06-13 00:46:03 +00:00
Jeff Roberson
1b2da2d0fa - Assert that we're not adding a doomed vnode to the name cache.
Sponsored by:	Isilon Systems, Inc.
2005-06-11 08:47:30 +00:00
Jeff Roberson
4585e3ac5a - Change all filesystems and vfs_cache to relock the dvp once the child is
locked in the ISDOTDOT case.  Se vfs_lookup.c r1.79 for details.

Sponsored by:	Isilon Systems, Inc.
2005-04-13 10:59:09 +00:00
David Schultz
7ce7f713ee Eliminate v_id and v_ddid. The name cache now holds references to
vnodes whose names it caches, so we no longer need a `generation
number' to tell us if a referenced vnode is invalid.  Replace the use
of the parent's v_id in the hash function with the address of the
parent vnode.

Tested by:	Peter Holm
Glanced at by:	jeff, phk
2005-03-30 03:01:36 +00:00
David Schultz
dd33f0d92f Merge kern___cwd() and vn_fullpath(), which were virtually identical,
except for places where people forget to update one of them.  We now
collect only one set of stats for both of these routines.  Other
changes in this commit include:

- Start acquiring Giant again in vn_fullpath(), since it is required
  when crossing a mount point.

- Expand the scope of the cache lock to avoid dropping it and
  picking it up again for every pathname component.  This also
  makes it trivial to avoid races in stats collection.

- Assert that nc_dvp == v_dd for directories instead of returning
  an error to userland when this is not true.  AFAIK, it should
  always be true when v_dd is non-null.

- For vn_fullpath(), handle the first (non-directory) vnode
  separately.

Glanced at by:  jeff, phk
2005-03-30 02:59:32 +00:00
Jeff Roberson
5280e61f2f - Move the logic that locks and refs the new vnode from vfs_cache_lookup()
to cache_lookup().  This allows us to acquire the vnode interlock before
   dropping the cache lock.  This protects the vnodes identity until we
   have locked it.

Sponsored by:	Isilon Systems, Inc.
2005-03-29 12:59:06 +00:00
Jeff Roberson
571211c454 - Get rid of the old LOOKUP_SHARED code. namei() now supplies the
proper lock flags via cn_lkflag.

Sponsored by:	Isilon Systems, Inc.
2005-03-29 10:08:23 +00:00
Jeff Roberson
b75719afea - Invalidate the childrens v_dd pointers when we cache_purge() a directory.
Otherwise the stale pointer may be accessed after a vnode is freed.

Sponsored by:	Isilon Systems, Inc.
2005-03-29 09:58:41 +00:00
Jeff Roberson
f7b404d88f - Remove an unused variable.
Sponsored by:	Isilon Systems, Inc.
2005-03-28 13:29:48 +00:00
Jeff Roberson
ee5a0a2d7c - We no longer have to bother with PDIRUNLOCK, lookup() handles it for us.
Sponsored by:	Isilon Systems, Inc.
2005-03-28 09:26:17 +00:00
Jeff Roberson
fdd6a3ff3c - All of the bugs which lead to the complication of the LOOKUP_SHARED
config option have now been fixed.  All filesystems are properly locked
   and checked via DEBUG_VFS_LOCKS.  Remove the workaround code.

Sponsored by:	Isilon Systems, Inc.
2005-03-24 06:00:45 +00:00
Poul-Henning Kamp
2adc2b87c7 Make a SYSCTL_NODE and a mutex static 2005-02-10 12:16:42 +00:00
Jeff Roberson
799cc2dcee - Simplify the cache locking. The lock order relationship with the
vnode lock is much simpler than I originally thought it would be.
   Now, the cache lock is  always acquired before the vnode lock.
 - Provide some gotos in __getcwd() to simplify the unlocking a bit.
 - Move Giant acquisition down into __getcwd().

Sponsored By:	Isilon Systems, Inc.
2005-01-24 10:24:12 +00:00
Warner Losh
9454b2d864 /* -> /*- for copyright notices, minor format tweaks as necessary 2005-01-06 23:35:40 +00:00
Warner Losh
7f8a436ff2 Remove advertising clause from University of California Regent's license,
per letter dated July 22, 1999.

Approved by: core
2004-04-05 21:03:37 +00:00
Jeff Roberson
98d7d155c1 - Apply a big giant lock around the namecache. This has been sitting in
my tree since BSDcon.
2003-10-05 07:13:50 +00:00
Dag-Erling Smørgrav
c2935410f6 Make the VFS cache use zones instead of malloc(9). This results in a
small but noticeable increase in performance for name lookup operations.

The code uses two zones, one for short names (less than 32 characters)
and one for long names (up to NAME_MAX).  Since most file names are
fairly short, this saves a considerable amount of space that would
otherwise be wasted if we always allocated NAME_MAX bytes.  The cutoff
value of 32 characters was picked arbitrarily and may benefit from some
tweaking; it could also be made into a tunable.

Submitted by:	hmp
2003-06-13 08:46:13 +00:00
Dag-Erling Smørgrav
ffe92432e3 Whitespace cleanup. 2003-06-11 07:35:56 +00:00
David E. O'Brien
677b542ea2 Use __FBSDID(). 2003-06-11 00:56:59 +00:00
Poul-Henning Kamp
cc34e37e5b Backout the getcwd changes, a more comprehensive effort will be needed. 2003-03-20 10:40:45 +00:00
Poul-Henning Kamp
9eaf5abceb (This commit certainly increases the need for a wash&clean of vfs_cache.c,
but I decided that it was important for this patch to not bit-rot, and
since it is mainly moving code around, the total amount of entropy is
epsilon /phk)

This is a patch to move the common parts of linux_getcwd() back into
kern/vfs_cache.c so that the standard FreeBSD libc getcwd() can use it's
extended functionality.  The linux syscall linux_getcwd() in
compat/linux/linux_getcwd.c has been rewritten to use it too.  It should
be possible to simplify libc's getcwd() after this.  No doubt this code
needs some cleaning up, since I've left in the sysctl variables I used
for debugging.

PR:	48169
Submitted by:	James Whitwell <abacau@yahoo.com.au>
2003-03-17 12:21:08 +00:00
Warner Losh
a163d034fa Back out M_* changes, per decision of the TRB.
Approved by: trb
2003-02-19 05:47:46 +00:00
Andrew R. Reiter
1f5a94d5f6 - Update a couple of comments to make sense with what today's code is
doing (stale comments make arr something something ;)).
2003-02-15 23:25:12 +00:00
Andrew R. Reiter
da8f0c8429 - Remove old comment for PURGE() as it no longer exists and implied it
was a comment to cache_zap().
- Add a comment to quickly state what cache_zap() does.

Reviewed by:	phk, mux
2003-02-15 18:58:06 +00:00
Alfred Perlstein
44956c9863 Remove M_TRYWAIT/M_WAITOK/M_WAIT. Callers should use 0.
Merge M_NOWAIT/M_DONTWAIT into a single flag M_NOWAIT.
2003-01-21 08:56:16 +00:00
Ian Dowse
48b52b7a32 Split up __getcwd so that kernel callers of the internal version
can specify whether the buffer is in user or system space.
2002-09-02 22:40:30 +00:00
Jeff Roberson
18c6acee26 - Move a VOP assert to the right place.
Spotted by:	i386 tinderbox
2002-08-05 08:55:53 +00:00
Jeff Roberson
e6e370a7fe - Replace v_flag with v_iflag and v_vflag
- v_vflag is protected by the vnode lock and is used when synchronization
   with VOP calls is needed.
 - v_iflag is protected by interlock and is used for dealing with vnode
   management issues.  These flags include X/O LOCK, FREE, DOOMED, etc.
 - All accesses to v_iflag and v_vflag have either been locked or marked with
   mp_fixme's.
 - Many ASSERT_VOP_LOCKED calls have been added where the locking was not
   clear.
 - Many functions in vfs_subr.c were restructured to provide for stronger
   locking.

Idea stolen from:	BSD/OS
2002-08-04 10:29:36 +00:00
Alfred Perlstein
210a5a7169 nuke caddr_t. 2002-06-28 23:17:36 +00:00
Jeff Roberson
0e2d6cc899 Disable the shared locking namei() code for now. It breaks several stacking
filesystems.  This is on hold until the rest of VFS Locking is reviewed and
deemed safe.  It can be enabled with 'options LOOKUP_SHARED'.
2002-05-14 21:59:49 +00:00
Jeff Roberson
a59f8b9e6c Turn #ifdef LOOKUP_SHARED into #ifndef LOOKUP_EXCLUSIVE to enable this
behavior by default.  Also, change the options line to reflect this.

If there are no problems reported this will become the only behavior and the
knob will be removed in a month or so.

Demanded by:	obrien
2002-04-09 05:14:17 +00:00
David Malone
cf4ce70bb3 Remove a comment which relates to the old name cache code, which
was replaced in 1997.

Approved by:	phk
2002-04-07 08:58:31 +00:00
Alfred Perlstein
4d77a549fe Remove __P. 2002-03-19 21:25:46 +00:00
Jeff Roberson
8de00f4a87 This patch adds the "LOCKSHARED" option to namei which causes it to only acquire shared locks on leafs.
The stat() and open() calls have been changed to make use of this new functionality.  Using shared locks in
these cases is sufficient and can significantly reduce their latency if IO is pending to these vnodes.  Also,
this reduces the number of exclusive locks that are floating around in the system, which helps reduce the
number of deadlocks that occur.

A new kernel option "LOOKUP_SHARED" has been added.  It defaults to off so this patch can be turned on for
testing, and should eventually go away once it is proven to be stable.  I have personally been running this
patch for over a year now, so it is believed to be fully stable.

Reviewed by:	jake, obrien
Approved by:	jake
2002-03-12 04:00:11 +00:00