Commit Graph

8368 Commits

Author SHA1 Message Date
Jeff Roberson
2bbd6c9818 - Move NDFREE() from vfs_subr to vfs_lookup where namei() is. 2005-04-05 08:58:49 +00:00
Jeff Roberson
22fdc83f93 - Use taskqueue_thread rather than taskqueue_swi since our task is going
to vrele, which may vop lock.  This is not safe in a software interrupt
   context.
2005-04-05 08:51:45 +00:00
Christian S.J. Peron
f3e89267c0 Assert that the vnode is locked. This is meant to catch bugs or
mis-use of the vnode API in conditions where IO_NODELOCKED has been
used without the vnode actually being locked.
2005-04-05 01:11:43 +00:00
John Baldwin
c6a37e8413 Divorce critical sections from spinlocks. Critical sections as denoted by
critical_enter() and critical_exit() are now solely a mechanism for
deferring kernel preemptions.  They no longer have any affect on
interrupts.  This means that standalone critical sections are now very
cheap as they are simply unlocked integer increments and decrements for the
common case.

Spin mutexes now use a separate KPI implemented in MD code: spinlock_enter()
and spinlock_exit().  This KPI is responsible for providing whatever MD
guarantees are needed to ensure that a thread holding a spin lock won't
be preempted by any other code that will try to lock the same lock.  For
now all archs continue to block interrupts in a "spinlock section" as they
did formerly in all critical sections.  Note that I've also taken this
opportunity to push a few things into MD code rather than MI.  For example,
critical_fork_exit() no longer exists.  Instead, MD code ensures that new
threads have the correct state when they are created.  Also, we no longer
try to fixup the idlethreads for APs in MI code.  Instead, each arch sets
the initial curthread and adjusts the state of the idle thread it borrows
in order to perform the initial context switch.

This change is largely a big NOP, but the cleaner separation it provides
will allow for more efficient alternative locking schemes in other parts
of the kernel (bare critical sections rather than per-CPU spin mutexes
for per-CPU data for example).

Reviewed by:	grehan, cognet, arch@, others
Tested on:	i386, alpha, sparc64, powerpc, arm, possibly more
2005-04-04 21:53:56 +00:00
Nate Lawson
4abfd70c87 Document that devclass_get_maxunit(9) returns one greater than the current
highest unit.

Reviewed by:	dfr
MFC after:	2 weeks
2005-04-04 15:37:59 +00:00
Nate Lawson
fada20b989 Add devclass_get_drivers(9) which provides an array of pointers to driver
instances in a given devclass.  This is useful for systems that want to
call code in driver static methods, similar to device_identify().

Reviewed by:	dfr
MFC after:	2 weeks
2005-04-04 15:26:51 +00:00
Jeff Roberson
d1cc6041e6 - Add a missing unlock of the vnode_free_list_mtx.
Spotted by:	Antoine Brodin
2005-04-04 12:07:16 +00:00
Jeff Roberson
92b8231d4f - Instead of waiting forever to get a vnode in getnewvnode() wait for
one to become available for one second and then return ENFILE.  We
   can run out of vnodes, and there must be a hard limit because without
   one we can quickly run out of KVA on x86.  Presently the system can
   deadlock if there are maxvnodes directories in the namecache.  The
   original 4.x BSD behavior was to return ENFILE if we reached the max,
   but 4.x BSD did not have the vnlru proc so it was less profitable to
   wait.
2005-04-04 11:43:44 +00:00
Jeff Roberson
9a6bb8ad8f - Include opt_vfs.h for LOOKUP_SHARED.
- Control the behavior of shared lookups with the lookup_shared sysctl
   which has its default behavior set via the LOOKUP_SHARED option.
2005-04-03 23:50:20 +00:00
Nate Lawson
a44732323f maxunit is actually one higher than the greatest currently-allocated unit
in a devclass.  All the other uses of maxunit are correct and this one was
safe since it checks the return value of devclass_get_device(), which would
always say that the highest unit device doesn't exist.

Reviewed by:	dfr
MFC after:	3 days
2005-04-03 22:23:18 +00:00
Jeff Roberson
20728d8f63 - Slightly restructure acquire() so I can add more ktr information and
an assert to help find two strange bugs.
 - Remove some nearby spls.
2005-04-03 11:49:02 +00:00
Jeff Roberson
f0ddc75ed0 - Now that writes to character devices supporting softupdates can
generate dirty bufs even with a locked vnode, 100 retries is not that
   many.  This should probably change from a retry count to an abort when
   we are no longer cleaning any buffers.
 - Don't call vprint() while we still hold the vnode locked.  Move the call
   to later in the function.
 - Clean up a comment.
2005-04-03 10:24:03 +00:00
Alan Cox
9f65fb13aa Remove GIANT_REQUIRED from elfN_load_section(). 2005-04-03 07:57:47 +00:00
John Baldwin
98df9218da - Change the vm_mmap() function to accept an objtype_t parameter specifying
the type of object represented by the handle argument.
- Allow vm_mmap() to map device memory via cdev objects in addition to
  vnodes and anonymous memory.  Note that mmaping a cdev directly does not
  currently perform any MAC checks like mapping a vnode does.
- Unbreak the DRM getbufs ioctl by having it call vm_mmap() directly on the
  cdev the ioctl is acting on rather than trying to find a suitable vnode
  to map from.

Reviewed by:	alc, arch@
2005-04-01 20:00:11 +00:00
John Baldwin
fe24ab5fc5 Actually commit the code for kern_sched_get_rr_interval(). 2005-03-31 22:54:48 +00:00
John Baldwin
b88ec951e1 Implement kern_adjtime(), kern_readv(), kern_sched_rr_get_interval(),
kern_settimeofday(), and kern_writev() to allow for further stackgap
reduction in the compat ABIs.
2005-03-31 22:51:18 +00:00
John Baldwin
ea2b9b3e36 - Denote a few places where kobj class references are manipulated without
holding the appropriate lock.
- Add a comment explaining why we bump a driver's kobj class reference
  when loading a module.
2005-03-31 22:49:31 +00:00
John Baldwin
2945387fee Drop a bogus mp_fixme(). Adding a lock would do nothing to reduce userland
races regarding changing of jail-related sysctls.
2005-03-31 22:47:57 +00:00
John Baldwin
b80ed61487 Don't recursively panic when we call mi_switch() in a critical section,
even though calling mi_switch() after a panic is likely a bug anyway as
the recursive panic only serves to make things worse.
2005-03-31 20:36:44 +00:00
Nate Lawson
71ab130c9b Add a check for cpufreq_unregister() being called with no cpufreq device
active.  Note that the logic indicates this should not be possible so
generate a warning if this ever happens.

Found by:	Coverity Prevent (via sam)
2005-03-31 18:56:54 +00:00
Poul-Henning Kamp
f4f6abcb4e Explicitly hold a reference to the cdev we have just cloned. This
closes the race where the cdev was reclaimed before it ever made it
back to devfs lookup.
2005-03-31 12:19:44 +00:00
Poul-Henning Kamp
9477d73e32 cdev (still) needs per instance uid/gid/mode
Add unlocked version of dev_ref()

Clean up various stuff in sys/conf.h
2005-03-31 10:29:57 +00:00
Poul-Henning Kamp
eb151cb989 Rename dev_ref() to dev_refl() 2005-03-31 06:51:54 +00:00
Jeff Roberson
e451d879a1 - Disable vfs shared locks by default. They must be specifically enabled
on filesystems which safely support them.  It appears that many
   network filesystems specifically are not shared lock safe.

Sponsored by:	Isilon Systems, Inc.
2005-03-31 05:22:45 +00:00
Jeff Roberson
c4c0ec5ba7 - Add a LK_NOSHARE flag which forces all shared lock requests to be
treated as exclusive lock requests.

Sponsored by:	Isilon Systems, Inc.
2005-03-31 05:18:19 +00:00
Jeff Roberson
f247a5240d - LK_NOPAUSE is a nop now.
Sponsored by:   Isilon Systems, Inc.
2005-03-31 04:37:09 +00:00
Jeff Roberson
b641353e3a - Remove apause(). It makes no sense with our present mutex implementation
since simply unlocking a mutex does not ensure that one of the waiters
   will run and acquire it.  We're more likely to reacquire the mutex
   before anyone else has a chance.  It has also bit me three times now, as
   it's not safe to drop the interlock before sleeping in many cases.

Sponsored by:	Isilon Systems, Inc.
2005-03-31 04:25:59 +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
Poul-Henning Kamp
b3d82c03fc Remove the global cdev hash and use the cdevsw list instead.
Don't remove the now unused element from cdev yet, wait until
we have a better reason to bump the version.

There is now no longer any upper limit on how many device drivers
a FreeBSD kernel can have.
2005-03-29 11:15:54 +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
99f3c87034 - Set cn_lkflags to LK_SHARED in the LOOKUP_SHARED case so that we only
acquire shared locks on intermediate directories.
 - For the LASTCN, we may have to LK_UPGRADE the parent directory before
   we lookup the last component.
 - Acquire VFS_ROOT and dp locks based on the cn_lkflag.

Sponsored by:	Isilon Systems, Inc.
2005-03-29 10:07:15 +00:00
Jeff Roberson
0fbc3b7df0 - Dont clear OWEINACT in vbusy(), we still owe an inactive call if someone
vhold()s us.
 - Avoid an extra mutex acquire and release in the common case of vgonel()
   by checking for OWEINACT at the start of the function.
 - Fix the case where we set OWEINACT in vput().  LK_EXCLUPGRADE drops our
   shared lock if it fails.

Sponsored by:	Isilon Systems, Inc.
2005-03-29 10:02:48 +00:00
Jeff Roberson
cb34b95ba4 - Don't initial v_dd here, let cache_purge() do it for us.
Sponsored by:	Isilon Systems, Inc.
2005-03-29 09:59:34 +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
Poul-Henning Kamp
ff7284eeb4 Remove the global cdev hash and use the cdevsw list instead.
Don't remove the now unused element from cdev yet, wait until
we have a better reason to bump the version.
2005-03-29 09:56:21 +00:00
Poul-Henning Kamp
fd5f6f4cf2 Privatize major(). 2005-03-29 08:13:17 +00:00
Poul-Henning Kamp
97eb8cfae0 Print name of device instead of useless major/minor numbers. 2005-03-29 08:13:01 +00:00
Jeff Roberson
ea9aa09dd1 - Remove an unused variable from relookup().
- Assert that REMOVE, CREATE, and RENAME callers have WANTPARENT
   or LOCKPARENT set.  You can't complete any of these operations without
   at least a reference to the parent.  Many filesystems check for this case
   even though it isn't possible in the current system.
2005-03-28 13:56:56 +00:00
Jeff Roberson
f7b404d88f - Remove an unused variable.
Sponsored by:	Isilon Systems, Inc.
2005-03-28 13:29:48 +00:00
Jeff Roberson
9d65cdf6ff - Rev 1.83 of kern_lock.c fixes the td_locks assert, reenable it here.
Sponsored by:	Isilon Systems, Inc.
2005-03-28 12:52:46 +00:00
Jeff Roberson
bf5c2a1940 - Don't bump the count twice in the LK_DRAIN case.
Sponsored by:	Isilon Systems, Inc.
2005-03-28 12:52:10 +00:00
Jeff Roberson
9dcc5da318 - Move code that should probably be an assert above the main body of
vrele so that we can decrease the indentation of the real work and
   make things slightly more clear.

Sponsored by:	Isilon Systems, Inc.
2005-03-28 11:18:47 +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
d36f0a4ff8 - Adjust asserts in vop_lookup_post() to match the new post PDIRUNLOCK
vfs.

Sponsored by:	Isilon Systems, Inc.
2005-03-28 09:25:25 +00:00
Jeff Roberson
1e38e08e76 - Get rid of PDIRUNLOCK, instead, we fixup the lock state immediately after
calling VOP_LOOKUP().  Rather than having each filesystem check the
   LOCKPARENT flag, we simply check it once here and unlock as required.
   The only unusual case is ISDOTDOT, where we require an unlocked vnode
   on return.  Relocking this vnode with the child locked is allowed since
   the child is actually its parent.
 - Add a few asserts for some unusual conditions that I do not believe can
   happen.  These will later go away and turn into implementations for these
   conditions.

Sponsored by:	Isilon Systems, Inc.
2005-03-28 09:24:50 +00:00
Poul-Henning Kamp
3b73a3c079 Remove another ';' after if().
Also spotted by:	bz
2005-03-27 07:53:13 +00:00
Poul-Henning Kamp
2d8dfb2836 Remove extra ; at end of if().
Found by:	bz
2005-03-27 07:52:12 +00:00
Poul-Henning Kamp
4a650cc291 Make (some) serial ports implement the PPS-API again. This change
appearantly fell out during the tty code cleanup.
2005-03-26 20:12:39 +00:00