The last half year I've been working on a replacement TTY layer for the
FreeBSD kernel. The new TTY layer was designed to improve the following:
- Improved driver model:
The old TTY layer has a driver model that is not abstract enough to
make it friendly to use. A good example is the output path, where the
device drivers directly access the output buffers. This means that an
in-kernel PPP implementation must always convert network buffers into
TTY buffers.
If a PPP implementation would be built on top of the new TTY layer
(still needs a hooks layer, though), it would allow the PPP
implementation to directly hand the data to the TTY driver.
- Improved hotplugging:
With the old TTY layer, it isn't entirely safe to destroy TTY's from
the system. This implementation has a two-step destructing design,
where the driver first abandons the TTY. After all threads have left
the TTY, the TTY layer calls a routine in the driver, which can be
used to free resources (unit numbers, etc).
The pts(4) driver also implements this feature, which means
posix_openpt() will now return PTY's that are created on the fly.
- Improved performance:
One of the major improvements is the per-TTY mutex, which is expected
to improve scalability when compared to the old Giant locking.
Another change is the unbuffered copying to userspace, which is both
used on TTY device nodes and PTY masters.
Upgrading should be quite straightforward. Unlike previous versions,
existing kernel configuration files do not need to be changed, except
when they reference device drivers that are listed in UPDATING.
Obtained from: //depot/projects/mpsafetty/...
Approved by: philip (ex-mentor)
Discussed: on the lists, at BSDCan, at the DevSummit
Sponsored by: Snow B.V., the Netherlands
dcons(4) fixed by: kan
requiring the per-process spinlock to only requiring the process lock.
- Reflect these changes in the proc.h documentation and consumers throughout
the kernel. This is a substantial reduction in locking cost for these
fields and was made possible by recent changes to threading support.
While the KSE project was quite successful in bringing threading to
FreeBSD, the M:N approach taken by the kse library was never developed
to its full potential. Backwards compatibility will be provided via
libmap.conf for dynamically linked binaries and static binaries will
be broken.
maintain a separate td_incruntime to hold unbilled CPU usage for
the thread that has the previous properties of td_runtime.
When thread information is requested using the thread monitoring
sysctls, export thread td_runtime instead of process rusage runtime
in kinfo_proc.
This restores the display of individual ithread and other kernel
thread CPU usage since inception in ps -H and top -SH, as well for
libthr user threads, valuable debugging information lost with the
move to try kthreads since they are no longer independent processes.
There is universal agreement that we should rewrite the process and
thread export sysctls, but this commit gets things going a bit
better in the mean time. Likewise, there are resevations about the
continued validity of statclock given the speed of modern processors.
Reviewed by: attilio, emaste, jhb, julian
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>
p_candebug() will return EAGAIN which, if the other process never
leaves execve(), will result in the sysctl spinning and never returning
to userspace. Processes should always eventually leave execve(), but
spinning in kernel while we wait is bad for countless reasons, and
particularly harmful if execve() itself is deadlocked.
Possibly we should return another error, or return a marker indicating
the thread is in execve() so it can be reported that way in userspace.
Reported by: kris
support its -k argument:
kern.proc.kstack - dump the kernel stack of a process, if debugging
is permitted.
This sysctl is present if either "options DDB" or "options STACK" is
compiled into the kernel. Having support for tracing the kernel
stacks of processes from user space makes it much easier to debug
(or understand) specific wmesg's while avoiding the need to enter
DDB in order to determine the path by which a process came to be
blocked on a particular wait channel or lock.
its -f and -v arguments:
kern.proc.filedesc - dump file descriptor information for a process, if
debugging is permitted, including socket addresses, open flags, file
offsets, file paths, etc.
kern.proc.vmmap - dump virtual memory mapping information for a process,
if debugging is permitted, including layout and information on
underlying objects, such as the type of object and path.
These provide a superset of the information historically available
through the now-deprecated procfs(4), and are intended to be exported
in an ABI-robust form.
- process_ctor,dtor, init and fini
- thread_ctor,dtor, init and fini
This allows the ability to add on additional things
during construction/destruction of threads and processes.
Reviewed by: rwatson
silent NULL pointer dereference in the i386 and sparc64 pmap_pinit()
when the kmem_alloc_nofault() failed to allocate address space. Both
functions now return error instead of panicing or dereferencing NULL.
As consequence, vmspace_exec() and vmspace_unshare() returns the errno
int. struct vmspace arg was added to vm_forkproc() to avoid dealing
with failed allocation when most of the fork1() job is already done.
The kernel stack for the thread is now set up in the thread_alloc(),
that itself may return NULL. Also, allocation of the first process
thread is performed in the fork1() to properly deal with stack
allocation failure. proc_linkup() is separated into proc_linkup()
called from fork1(), and proc_linkup0(), that is used to set up the
kernel process (was known as swapper).
In collaboration with: Peter Holm
Reviewed by: jhb
changes the units from seconds to the value of 'ticks' when swapped
in/out. ULE does not have a periodic timer that scans all threads in
the system and as such maintaining a per-second counter is difficult.
- Change computations requiring the unit in seconds to subtract ticks
and divide by hz. This does make the wraparound condition hz times
more frequent but this is still in the range of several months to
years and the adverse effects are minimal.
Approved by: re
- p_sflag was mostly protected by PROC_LOCK rather than the PROC_SLOCK or
previously the sched_lock. These bugs have existed for some time.
- Allow swapout to try each thread in a process individually and then
swapin the whole process if any of these fail. This allows us to move
most scheduler related swap flags into td_flags.
- Keep ki_sflag for backwards compat but change all in source tools to
use the new and more correct location of P_INMEM.
Reported by: pho
Reviewed by: attilio, kib
Approved by: re (kensmith)
This patch fixes places where they should be called atomically changing
their locking requirements (both assume per-proc spinlock held) and
introducing rufetchcalc which wrappers both calls to be performed in
atomic way.
Reviewed by: jeff
Approved by: jeff (mentor)
- Use thread_lock() rather than sched_lock for per-thread scheduling
sychronization.
- Use the per-process spinlock rather than the sched_lock for per-process
scheduling synchronization.
Tested by: kris, current@
Tested on: i386, amd64, ULE, 4BSD, libthr, libkse, PREEMPTION, etc.
Discussed with: kris, attilio, kmacy, jhb, julian, bde (small parts each)
td_ru. This removes the requirement for per-process synchronization in
statclock() and mi_switch(). This was previously supported by
sched_lock which is going away. All modifications to rusage are now
done in the context of the owning thread. reads proceed without locks.
- Aggregate exiting threads rusage in thread_exit() such that the exiting
thread's rusage is not lost.
- Provide a new routine, rufetch() to fetch an aggregate of all rusage
structures from all threads in a process. This routine must be used
in any place requiring a rusage from a process prior to it's exit. The
exited process's rusage is still available via p_ru.
- Aggregate tick statistics only on demand via rufetch() or when a thread
exits. Tick statistics are kept in the thread and protected by sched_lock
until it exits.
Initial patch by: attilio
Reviewed by: attilio, bde (some objections), arch (mostly silent)
Make part of John Birrell's KSE patch permanent..
Specifically, remove:
Any reference of the ksegrp structure. This feature was
never fully utilised and made things overly complicated.
All code in the scheduler that tried to make threaded programs
fair to unthreaded programs. Libpthread processes will already
do this to some extent and libthr processes already disable it.
Also:
Since this makes such a big change to the scheduler(s), take the opportunity
to rename some structures and elements that had to be moved anyhow.
This makes the code a lot more readable.
The ULE scheduler compiles again but I have no idea if it works.
The 4bsd scheduler still reqires a little cleaning and some functions that now do
ALMOST nothing will go away, but I thought I'd do that as a separate commit.
Tested by David Xu, and Dan Eischen using libthr and libpthread.
code is still under giant lock, but the session/pgrp release code just used
proctree_locks. This explains why moving the proctree_lock in sys/kern/tty.c
rev. 1.258 did fix the panics in our SMP systems.
This should also fix some race panics with revoked ttys.
Reviewed by: jhb
MFC after: 1 week
Keep accounting time (in per-cpu) cputicks and the statistics counts
in the thread and summarize into struct proc when at context switch.
Don't reach across CPUs in calcru().
Add code to calibrate the top speed of cpu_tickrate() for variable
cpu_tick hardware (like TSC on power managed machines).
Don't enforce monotonicity (at least for now) in calcru. While the
calibrated cpu_tickrate ramps up it may not be true.
Use 27MHz counter on i386/Geode.
Use TSC on amd64 & i386 if present.
Use tick counter on sparc64
Keep track of time spent by the cpu in various contexts in units of
"cputicks" and scale to real-world microsec^H^H^H^H^H^H^H^Hclock_t
only when somebody wants to inspect the numbers.
For now "cputicks" are still derived from the current timecounter
and therefore things should by definition remain sensible also on
SMP machines. (The main reason for this first milestone commit is
to verify that hypothesis.)
On slower machines, the avoided multiplications to normalize timestams
at every context switch, comes out as a 5-7% better score on the
unixbench/context1 microbenchmark. On more modern hardware no change
in performance is seen.
equal to NULL several times later. p_ucred "should probably not" be NULL
if the process isn't PRS_NEW anyway. This is strongly reinforced by the fact
that we don't see frequent crashes here. Remove the checks after p_cansee and
add a KASSERT right before it.
Found by: Coverity Prevent (tm)
Also trim one nearby trailing space.
reliability when tracing fast-moving processes or writing traces to
slow file systems by avoiding unbounded queueuing and dropped records.
Record loss was previously possible when the global pool of records
become depleted as a result of record generation outstripping record
commit, which occurred quickly in many common situations.
These changes partially restore the 4.x model of committing ktrace
records at the point of trace generation (synchronous), but maintain
the 5.x deferred record commit behavior (asynchronous) for situations
where entering VFS and sleeping is not possible (i.e., in the
scheduler). Records are now queued per-process as opposed to
globally, with processes responsible for committing records from their
own context as required.
- Eliminate the ktrace worker thread and global record queue, as they
are no longer used. Keep the global free record list, as records
are still used.
- Add a per-process record queue, which will hold any asynchronously
generated records, such as from context switches. This replaces the
global queue as the place to submit asynchronous records to.
- When a record is committed asynchronously, simply queue it to the
process.
- When a record is committed synchronously, first drain any pending
per-process records in order to maintain ordering as best we can.
Currently ordering between competing threads is provided via a global
ktrace_sx, but a per-process flag or lock may be desirable in the
future.
- When a process returns to user space following a system call, trap,
signal delivery, etc, flush any pending records.
- When a process exits, flush any pending records.
- Assert on process tear-down that there are no pending records.
- Slightly abstract the notion of being "in ktrace", which is used to
prevent the recursive generation of records, as well as generating
traces for ktrace events.
Future work here might look at changing the set of events marked for
synchronous and asynchronous record generation, re-balancing queue
depth, timeliness of commit to disk, and so on. I.e., performing a
drain every (n) records.
MFC after: 1 month
Discussed with: jhb
Requested by: Marc Olzheim <marcolz at stack dot nl>
For each child process whose status has been changed, a SIGCHLD instance
is queued, if the signal is stilling pending, and process changed status
several times, signal information is updated to reflect latest process
status. If wait() returns because the status of a child process is
available, pending SIGCHLD signal associated with the child process is
discarded. Any other pending SIGCHLD signals remain pending.
The signal information is allocated at the same time when proc structure
is allocated, if process signal queue is fully filled or there is a memory
shortage, it can still send the signal to process.
There is a booting time tunable kern.sigqueue.queue_sigchild which
can control the behavior, setting it to zero disables the SIGCHLD queueing
feature, the tunable will be removed if the function is proved that it is
stable enough.
Tested on: i386 (SMP and UP)
calling sysctl_out_proc(). -- fix from jhb
Move the code in fill_kinfo_thread() that gathers data from struct proc
into the new function fill_kinfo_proc_only().
Change all callers of fill_kinfo_thread() to call both
fill_kinfo_proc_only() and fill_kinfo() thread. When gathering
data from a multi-threaded process, fill_kinfo_proc_only() only needs
to be called once.
Grab sched_lock before accessing the process thread list or calling
fill_kinfo_thread().
PR: kern/84684
MFC after: 3 days
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
session in tprintf(). SESSRELE() needs to properly dispose of the
sessions mutex.
Add sessrele() which does the proper cleanup and have SESSRELE() call it.
Use SESSRELE also in pgdelete().
Found by: Coverity (ID:526)
the raw values including for child process statistics and only compute the
system and user timevals on demand.
- Fix the various kern_wait() syscall wrappers to only pass in a rusage
pointer if they are going to use the result.
- Add a kern_getrusage() function for the ABI syscalls to use so that they
don't have to play stackgap games to call getrusage().
- Fix the svr4_sys_times() syscall to just call calcru() to calculate the
times it needs rather than calling getrusage() twice with associated
stackgap, etc.
- Add a new rusage_ext structure to store raw time stats such as tick counts
for user, system, and interrupt time as well as a bintime of the total
runtime. A new p_rux field in struct proc replaces the same inline fields
from struct proc (i.e. p_[isu]ticks, p_[isu]u, and p_runtime). A new p_crux
field in struct proc contains the "raw" child time usage statistics.
ruadd() has been changed to handle adding the associated rusage_ext
structures as well as the values in rusage. Effectively, the values in
rusage_ext replace the ru_utime and ru_stime values in struct rusage. These
two fields in struct rusage are no longer used in the kernel.
- calcru() has been split into a static worker function calcru1() that
calculates appropriate timevals for user and system time as well as updating
the rux_[isu]u fields of a passed in rusage_ext structure. calcru() uses a
copy of the process' p_rux structure to compute the timevals after updating
the runtime appropriately if any of the threads in that process are
currently executing. It also now only locks sched_lock internally while
doing the rux_runtime fixup. calcru() now only requires the caller to
hold the proc lock and calcru1() only requires the proc lock internally.
calcru() also no longer allows callers to ask for an interrupt timeval
since none of them actually did.
- calcru() now correctly handles threads executing on other CPUs.
- A new calccru() function computes the child system and user timevals by
calling calcru1() on p_crux. Note that this means that any code that wants
child times must now call this function rather than reading from p_cru
directly. This function also requires the proc lock.
- This finishes the locking for rusage and friends so some of the Giant locks
in exit1() and kern_wait() are now gone.
- The locking in ttyinfo() has been tweaked so that a shared lock of the
proctree lock is used to protect the process group rather than the process
group lock. By holding this lock until the end of the function we now
ensure that the process/thread that we pick to dump info about will no
longer vanish while we are trying to output its info to the console.
Submitted by: bde (mostly)
MFC after: 1 month
