IFC @ r227804

Pull in the virtio drivers from head.

Consistently use process spin lock for protection of the
p->p_boundary_count. Race could cause the execve(2) from the threaded
process to hung since thread boundary counter was incorrect and
single-t

Consistently use process spin lock for protection of the
p->p_boundary_count. Race could cause the execve(2) from the threaded
process to hung since thread boundary counter was incorrect and
single-threading never finished.

Reported by: pluknet, pho
Tested by: pho
MFC after: 1 week

show more ...

Fix some locking nits with the p_state field of struct proc:
- Hold the proc lock while changing the state from PRS_NEW to PRS_NORMAL
in fork to honor the locking requirements. While here, expand

Fix some locking nits with the p_state field of struct proc:
- Hold the proc lock while changing the state from PRS_NEW to PRS_NORMAL
in fork to honor the locking requirements. While here, expand the scope
of the PROC_LOCK() on the new process (p2) to avoid some LORs. Previously
the code was locking the new child process (p2) after it had locked the
parent process (p1). However, when locking two processes, the safe order
is to lock the child first, then the parent.
- Fix various places that were checking p_state against PRS_NEW without
having the process locked to use PROC_LOCK(). Every place was already
locking the process, just after the PRS_NEW check.
- Remove or reduce the use of PROC_SLOCK() for places that were checking
p_state against PRS_NEW. The PROC_LOCK() alone is sufficient for reading
the current state.
- Reorder fill_kinfo_proc() slightly so it only acquires PROC_SLOCK() once.

MFC after: 1 week

show more ...

Merge svn+ssh://svn.freebsd.org/base/head@219553

Clean up the now unused #include statement.

Approved by: kib (mentor)
MFC after: 1 week
X-MFC with: r218972

Move the max_threads_per_proc and max_threads_hits variables to the
file where they are used. Declare the kern.threads sysctl node at the
same location. Since no external use for the variables exist

Move the max_threads_per_proc and max_threads_hits variables to the
file where they are used. Declare the kern.threads sysctl node at the
same location. Since no external use for the variables exists, make them
static.

Discussed with: dchagin
MFC after: 1 week

show more ...

Merge svn+ssh://svn.freebsd.org/base/head@218816

Sync: merge r216133 through r216338 from ^/head.

MFp4:
The unit number allocator reuses ID too fast, this may hide bugs in
other code, add a ring buffer to delay freeing a thread ID.

MFp4:
It is possible a lower priority thread lending priority to higher priority
thread, in old code, it is ignored, however the lending should always be
recorded, add field td_lend_user_pri to fix t

MFp4:
It is possible a lower priority thread lending priority to higher priority
thread, in old code, it is ignored, however the lending should always be
recorded, add field td_lend_user_pri to fix the problem, if a thread does
not have borrowed priority, its value is PRI_MAX.

MFC after: 1 week

show more ...

Merge svn+ssh://svn.freebsd.org/base/head@214309

- Insert thread0 into correct thread hash link list.
- In thr_exit() and kthread_exit(), only remove thread from
hash if it can directly exit, otherwise let exit1() do it.
- In thread_suspend_check

- Insert thread0 into correct thread hash link list.
- In thr_exit() and kthread_exit(), only remove thread from
hash if it can directly exit, otherwise let exit1() do it.
- In thread_suspend_check(), fix cleanup code when thread needs
to exit.
This change seems fixed the "Bad link elm " panic found by
Peter Holm.

Stress testing: pho

show more ...

Add a flag TDF_TIDHASH to prevent a thread from being
added to or removed from thread hash table multiple times.

Create a global thread hash table to speed up thread lookup, use
rwlock to protect the table. In old code, thread lookup is done with
process lock held, to find a thread, kernel has to iterate throug

Create a global thread hash table to speed up thread lookup, use
rwlock to protect the table. In old code, thread lookup is done with
process lock held, to find a thread, kernel has to iterate through
process and thread list, this is quite inefficient.
With this change, test shows in extreme case performance is
dramatically improved.

Earlier patch was reviewed by: jhb, julian

show more ...

Merge svn+ssh://svn.freebsd.org/base/head@211344

Retire td_syscalls now that it is no longer needed.

MFC r208488:
Fix the double counting of the last process thread td_incruntime
on exit, that is done once in thread_exit() and the second time in
proc_reap(), by clearing td_incruntime.

Approved by:

MFC r208488:
Fix the double counting of the last process thread td_incruntime
on exit, that is done once in thread_exit() and the second time in
proc_reap(), by clearing td_incruntime.

Approved by: re (kensmith)

show more ...

Merge svn+ssh://svn.freebsd.org/base/head@208557

Fix the double counting of the last process thread td_incruntime
on exit, that is done once in thread_exit() and the second time in
proc_reap(), by clearing td_incruntime.

Use the opportunity to rev

Fix the double counting of the last process thread td_incruntime
on exit, that is done once in thread_exit() and the second time in
proc_reap(), by clearing td_incruntime.

Use the opportunity to revert to the pre-RUSAGE_THREAD exporting of ruxagg()
instead of ruxagg_locked() and use it from thread_exit().

Diagnosed and tested by: neel
MFC after: 3 days

show more ...

MFC r207605:
Remove a comment that merely repeats code.

MFC r207468:
Extract thread_lock()/ruxagg()/thread_unlock() fragment into utility
function ruxagg_tlock().
Convert the definition of kern_getrusage() to ANSI C.

MFC r207602:
Implement RUSAGE_THREAD.

MFC r207468:
Extract thread_lock()/ruxagg()/thread_unlock() fragment into utility
function ruxagg_tlock().
Convert the definition of kern_getrusage() to ANSI C.

MFC r207602:
Implement RUSAGE_THREAD. Add td_rux to keep extended runtime and ticks
information for thread to allow calcru1() (re)use.

Rename ruxagg()->ruxagg_locked(), ruxagg_tlock()->ruxagg() [1].
The ruxagg_locked() function no longer clears thread ticks nor
td_incruntime.

Not an MFC: the td_rux is added to the end of struct thread to keep
the KBI. Explicit bzero() of td_rux is added to new thread initialization
points.

show more ...

Merge svn+ssh://svn.freebsd.org/base/head@207793

MFC r207606:
Fix typo in comment.

Final update to current version of head in preparation for reintegration.

Fix typo in comment.

MFC after: 3 days