src/sys/fs/pseudofs, branch releng/6.2

MFC:

2006-07-08T14:06:56+00:00

- linux_misc.c 1.179
  Don't copyout/do unneccesary work if the buffer is a NULL pointer.

  Noticed by:     Dmitry Ganenko 
  Reviewed by:    rdivacky (the original version as in emulation@)

- linprocfs.c 1.96:
  Improve linprovfs to provide/fix the
   - process state (idle, sleeping, running, ...) [1]
   - the process group ID of the process which owns the connected tty
   - some page fault stats
   - time spend in kernel/userland
   - priority/nice value
   - starttime [1]
   - memory/swap stats
   - scheduling policy

  Additionally add some new fields and correct some not filled out ones.

  This brings us down to 15 dummy fields.

  The fields marked with [1] are needed to get Oracle 10 running. The starttime
  field is not completely right, since it displays the _same_ starttime for
  _every_ process, but at least it is not 0 and Oracle accepts this.

  Noticed by:     Dmitry Ganenko  [1]
  Reviewed by:    des, rdivacky

- pseudofs_vnops.c 1.60:
  Correctly calculate a buffer length. It was off by one so a read() returned
  one byte less than needed.

  Noticed by:     Dmitry Ganenko 
  Testcase by:    Dmitry Ganenko 
  Reviewed by:    des
  Submitted by:   rdivacky
  Sponsored by:   Google SoC 2006

All of those are needed for Oracle 10. Since previous Oracle versions work
just fine without those fixes, these patches can be seen as regression fixes
too. Because of this I think they are a RELENG_6_x candidate (MFC reminder
set).

MFC after:	1 month

MFC: Close some races between procfs/ptrace and exit1() by changing

2006-03-07T18:08:09+00:00

exit1() to block until any current PHOLD's are released.  This includes
Simplifying the cleanup code in kern_ptrace() and removing the now
unnecessary vmspace ref counting magic from proc_rwmem().  Also, the
locking for ptrace_single_step(), ptrace_set_pc(), and
ptrace_clear_single_step() have been fixed to be consistent across the
tree.

Approved by:	re (scottl)

MFC: Change pfs_visible() to optionally return with the process still

2006-03-01T20:54:33+00:00

locked to simplify some locking and close some races.

Approved by:	re (scottl)

MFC (by des)

2005-10-09T08:59:34+00:00

| Eliminate an unnecessary bcopy().
|
| Revision  Changes    Path
| 1.57      +15 -15    src/sys/fs/pseudofs/pseudofs_vnops.c

Approved by:	re (scottl)
No objection:	des

- Since we don't hold a usecount in pfs_exit we have to get a holdcnt

2005-07-07T07:33:10+00:00

   prior to calling vgone() to prevent any races.

Sponsored by:	Isilon Systems, Inc.
Approved by:	re (vfs blanket)

Fix an old pasto.

2005-04-30T16:27:20+00:00

- Change all filesystems and vfs_cache to relock the dvp once the child is

2005-04-13T10:59:09+00:00

   locked in the ISDOTDOT case.  Se vfs_lookup.c r1.79 for details.

Sponsored by:	Isilon Systems, Inc.

- We no longer have to bother with PDIRUNLOCK, lookup() handles it for us.

2005-03-28T09:34:36+00:00

Sponsored by:   Isilon Systems, Inc.

- Update vfs_root implementations to match the new prototype. None of

2005-03-24T07:36:16+00:00

   these filesystems will support shared locks until they are explicitly
   modified to do so.  Careful review must be done to ensure that this
   is safe for each individual filesystem.

Sponsored by:	Isilon Systems, Inc.

Use subr_unit

2005-03-19T08:22:36+00:00