but with slightly cleaned up interfaces.
The KSE structure has become the same as the "per thread scheduler
private data" structure. In order to not make the diffs too great
one is #defined as the other at this time.
The KSE (or td_sched) structure is now allocated per thread and has no
allocation code of its own.
Concurrency for a KSEGRP is now kept track of via a simple pair of counters
rather than using KSE structures as tokens.
Since the KSE structure is different in each scheduler, kern_switch.c
is now included at the end of each scheduler. Nothing outside the
scheduler knows the contents of the KSE (aka td_sched) structure.
The fields in the ksegrp structure that are to do with the scheduler's
queueing mechanisms are now moved to the kg_sched structure.
(per ksegrp scheduler private data structure). In other words how the
scheduler queues and keeps track of threads is no-one's business except
the scheduler's. This should allow people to write experimental
schedulers with completely different internal structuring.
A scheduler call sched_set_concurrency(kg, N) has been added that
notifies teh scheduler that no more than N threads from that ksegrp
should be allowed to be on concurrently scheduled. This is also
used to enforce 'fainess' at this time so that a ksegrp with
10000 threads can not swamp a the run queue and force out a process
with 1 thread, since the current code will not set the concurrency above
NCPU, and both schedulers will not allow more than that many
onto the system run queue at a time. Each scheduler should eventualy develop
their own methods to do this now that they are effectively separated.
Rejig libthr's kernel interface to follow the same code paths as
linkse for scope system threads. This has slightly hurt libthr's performance
but I will work to recover as much of it as I can.
Thread exit code has been cleaned up greatly.
exit and exec code now transitions a process back to
'standard non-threaded mode' before taking the next step.
Reviewed by: scottl, peter
MFC after: 1 week
FULL_PREEMPTION is defined. Add a runtime warning to ULE if PREEMPTION is
enabled (code inspired by the PREEMPTION warning in kern_switch.c). This
is a possible MT5 candidate.
is an effective band-aid for at least some of the scheduler corruption seen
recently. The real fix will involve protecting threads while they are
inconsistent, and will come later.
Submitted by: julian
is here so that we can gather stats on the nature of the recent rash of
hard lockups, and in this particular case panic the machine instead of
letting it deadlock forever.
dereference curthread. It is called only from critical_{enter,exit}(),
which already dereferences curthread. This doesn't seem to affect SMP
performance in my benchmarks, but improves MySQL transaction throughput
by about 1% on UP on my Xeon.
Head nodding: jhb, bmilekic
since they are only accessed by curthread and thus do not need any
locking.
- Move pr_addr and pr_ticks out of struct uprof (which is per-process)
and directly into struct thread as td_profil_addr and td_profil_ticks
as these variables are really per-thread. (They are used to defer an
addupc_intr() that was too "hard" until ast()).
o Make debugging code conditional upon KDB instead of DDB.
o Call kdb_enter() instead of Debugger().
o Call kdb_backtrace() instead of db_print_backtrace() or backtrace().
kern_mutex.c:
o Replace checks for db_active with checks for kdb_active and make
them unconditional.
kern_shutdown.c:
o s/DDB_UNATTENDED/KDB_UNATTENDED/g
o s/DDB_TRACE/KDB_TRACE/g
o Save the TID of the thread doing the kernel dump so the debugger
knows which thread to select as the current when debugging the
kernel core file.
o Clear kdb_active instead of db_active and do so unconditionally.
o Remove backtrace() implementation.
kern_synch.c:
o Call kdb_reenter() instead of db_error().
than as one-off hacks in various other parts of the kernel:
- Add a function maybe_preempt() that is called from sched_add() to
determine if a thread about to be added to a run queue should be
preempted to directly. If it is not safe to preempt or if the new
thread does not have a high enough priority, then the function returns
false and sched_add() adds the thread to the run queue. If the thread
should be preempted to but the current thread is in a nested critical
section, then the flag TDF_OWEPREEMPT is set and the thread is added
to the run queue. Otherwise, mi_switch() is called immediately and the
thread is never added to the run queue since it is switch to directly.
When exiting an outermost critical section, if TDF_OWEPREEMPT is set,
then clear it and call mi_switch() to perform the deferred preemption.
- Remove explicit preemption from ithread_schedule() as calling
setrunqueue() now does all the correct work. This also removes the
do_switch argument from ithread_schedule().
- Do not use the manual preemption code in mtx_unlock if the architecture
supports native preemption.
- Don't call mi_switch() in a loop during shutdown to give ithreads a
chance to run if the architecture supports native preemption since
the ithreads will just preempt DELAY().
- Don't call mi_switch() from the page zeroing idle thread for
architectures that support native preemption as it is unnecessary.
- Native preemption is enabled on the same archs that supported ithread
preemption, namely alpha, i386, and amd64.
This change should largely be a NOP for the default case as committed
except that we will do fewer context switches in a few cases and will
avoid the run queues completely when preempting.
Approved by: scottl (with his re@ hat)
- This is heavily derived from John Baldwin's apic/pci cleanup on i386.
- I have completely rewritten or drastically cleaned up some other parts.
(in particular, bootstrap)
- This is still a WIP. It seems that there are some highly bogus bioses
on nVidia nForce3-150 boards. I can't stress how broken these boards
are. I have a workaround in mind, but right now the Asus SK8N is broken.
The Gigabyte K8NPro (nVidia based) is also mind-numbingly hosed.
- Most of my testing has been with SCHED_ULE. SCHED_4BSD works.
- the apic and acpi components are 'standard'.
- If you have an nVidia nForce3-150 board, you are stuck with 'device
atpic' in addition, because they somehow managed to forget to connect the
8254 timer to the apic, even though its in the same silicon! ARGH!
This directly violates the ACPI spec.
keep the thread state variable consistent with its real state.
i.e. Don't say it's on the run queue when it isn't.
Also clarify the associated comment.
Turns a double panic back to a single panic :-/
Approved by: re@ (jhb)
as it could be and can do with some more cleanup. Currently its under
options LAZY_SWITCH. What this does is avoid %cr3 reloads for short
context switches that do not involve another user process. ie: we can
take an interrupt, switch to a kthread and return to the user without
explicitly flushing the tlb. However, this isn't as exciting as it could
be, the interrupt overhead is still high and too much blocks on Giant
still. There are some debug sysctls, for stats and for an on/off switch.
The main problem with doing this has been "what if the process that you're
running on exits while we're borrowing its address space?" - in this case
we use an IPI to give it a kick when we're about to reclaim the pmap.
Its not compiled in unless you add the LAZY_SWITCH option. I want to fix a
few more things and get some more feedback before turning it on by default.
This is NOT a replacement for Bosko's lazy interrupt stuff. This was more
meant for the kthread case, while his was for interrupts. Mine helps a
little for interrupts, but his helps a lot more.
The stats are enabled with options SWTCH_OPTIM_STATS - this has been a
pseudo-option for years, I just added a bunch of stuff to it.
One non-trivial change was to select a new thread before calling
cpu_switch() in the first place. This allows us to catch the silly
case of doing a cpu_switch() to the current process. This happens
uncomfortably often. This simplifies a bit of the asm code in cpu_switch
(no longer have to call choosethread() in the middle). This has been
implemented on i386 and (thanks to jake) sparc64. The others will come
soon. This is actually seperate to the lazy switch stuff.
Glanced at by: jake, jhb
kse_mailbox to schedule an upcall, this is useful for userland timeout
routine, for example pthread_cond_timedwait().
Also extract upcall scheduling code from kse_reassign and create
a new function called thread_switchout to include these code.
Reviewed by: julain
I was in two minds as to where to put them in the first case..
I should have listenned to the other mind.
Submitted by: parts by davidxu@
Reviewed by: jeff@ mini@
I'm not convinced there is anything major wrong with the patch but
them's the rules..
I am using my "David's mentor" hat to revert this as he's
offline for a while.
data structure called kse_upcall to manage UPCALL. All KSE binding
and loaning code are gone.
A thread owns an upcall can collect all completed syscall contexts in
its ksegrp, turn itself into UPCALL mode, and takes those contexts back
to userland. Any thread without upcall structure has to export their
contexts and exit at user boundary.
Any thread running in user mode owns an upcall structure, when it enters
kernel, if the kse mailbox's current thread pointer is not NULL, then
when the thread is blocked in kernel, a new UPCALL thread is created and
the upcall structure is transfered to the new UPCALL thread. if the kse
mailbox's current thread pointer is NULL, then when a thread is blocked
in kernel, no UPCALL thread will be created.
Each upcall always has an owner thread. Userland can remove an upcall by
calling kse_exit, when all upcalls in ksegrp are removed, the group is
atomatically shutdown. An upcall owner thread also exits when process is
in exiting state. when an owner thread exits, the upcall it owns is also
removed.
KSE is a pure scheduler entity. it represents a virtual cpu. when a thread
is running, it always has a KSE associated with it. scheduler is free to
assign a KSE to thread according thread priority, if thread priority is changed,
KSE can be moved from one thread to another.
When a ksegrp is created, there is always N KSEs created in the group. the
N is the number of physical cpu in the current system. This makes it is
possible that even an userland UTS is single CPU safe, threads in kernel still
can execute on different cpu in parallel. Userland calls kse_create to add more
upcall structures into ksegrp to increase concurrent in userland itself, kernel
is not restricted by number of upcalls userland provides.
The code hasn't been tested under SMP by author due to lack of hardware.
Reviewed by: julian
(show thread {address})
Remove the IDLE kse state and replace it with a change in
the way threads sahre KSEs. Every KSE now has a thread, which is
considered its "owner" however a KSE may also be lent to other
threads in the same group to allow completion of in-kernel work.
n this case the owner remains the same and the KSE will revert to the
owner when the other work has been completed.
All creations of upcalls etc. is now done from
kse_reassign() which in turn is called from mi_switch or
thread_exit(). This means that special code can be removed from
msleep() and cv_wait().
kse_release() does not leave a KSE with no thread any more but
converts the existing thread into teh KSE's owner, and sets it up
for doing an upcall. It is just inhibitted from being scheduled until
there is some reason to do an upcall.
Remove all trace of the kse_idle queue since it is no-longer needed.
"Idle" KSEs are now on the loanable queue.
- Begin moving scheduler specific functionality into sched_4bsd.c
- Replace direct manipulation of scheduler data with hooks provided by the
new api.
- Remove KSE specific state modifications and single runq assumptions from
kern_switch.c
Reviewed by: -arch
in specific situations. The owner thread must be blocked, and the
borrower can not proceed back to user space with the borrowed KSE.
The borrower will return the KSE on the next context switch where
teh owner wants it back. This removes a lot of possible
race conditions and deadlocks. It is consceivable that the
borrower should inherit the priority of the owner too.
that's another discussion and would be simple to do.
Also, as part of this, the "preallocatd spare thread" is attached to the
thread doing a syscall rather than the KSE. This removes the need to lock
the scheduler when we want to access it, as it's now "at hand".
DDB now shows a lot mor info for threaded proceses though it may need
some optimisation to squeeze it all back into 80 chars again.
(possible JKH project)
Upcalls are now "bound" threads, but "KSE Lending" now means that
other completing syscalls can be completed using that KSE before the upcall
finally makes it back to the UTS. (getting threads OUT OF THE KERNEL is
one of the highest priorities in the KSE system.) The upcall when it happens
will present all the completed syscalls to the KSE for selection.
from stopping another thread from completing a syscall, and this allows it to
release its resources etc. Probably more related commits to follow (at least
one I know of)
Initial concept by: julian, dillon
Submitted by: davidxu
next step is to allow > 1 to be allocated per process. This would give
multi-processor threads. (when the rest of the infrastructure is
in place)
While doing this I noticed libkvm and sys/kern/kern_proc.c:fill_kinfo_proc
are diverging more than they should.. corrective action needed soon.
idle. What was there before was surprisingly ALMOST correct.
Peter and I fried our brains on this for a couple of hours figuring out
what this actually means in the context of multiple threads.
Reviewed by: peter@freebsd.org
swapped in, we do not have to ask for the scheduler thread to do
that.
- Assert that a process is not swapped out in runq functions and
swapout().
- Introduce thread_safetoswapout() for readability.
- In swapout_procs(), perform a test that may block (check of a
thread working on its vm map) first. This lets us call swapout()
with the sched_lock held, providing a better atomicity.
after a panic which is not an interrupt thread, or the thread which
caused the panic. Also, remove panicstr checks from msleep() and from
cv_wait() in order to allow threads to go to sleep and yeild the cpu
to the panicing thread, or to an interrupt thread which might
be doing the crashdump.
Reviewed by: jhb (and it was mostly his idea too)
formulated. The correct states should be:
IDLE: On the idle KSE list for that KSEG
RUNQ: Linked onto the system run queue.
THREAD: Attached to a thread and slaved to whatever state the thread is in.
This means that most places where we were adjusting kse state can go away
as it is just moving around because the thread is..
The only places we need to adjust the KSE state is in transition to and from
the idle and run queues.
Reviewed by: jhb@freebsd.org
choosethread() in MI C code instead of doing it in in assembly in all the
various cpu_switch() functions. This fixes problems on ia64 and sparc64.
Reviewed by: julian, peter, benno
Tested on: i386, alpha, sparc64
The ability to schedule multiple threads per process
(one one cpu) by making ALL system calls optionally asynchronous.
to come: ia64 and power-pc patches, patches for gdb, test program (in tools)
Reviewed by: Almost everyone who counts
(at various times, peter, jhb, matt, alfred, mini, bernd,
and a cast of thousands)
NOTE: this is still Beta code, and contains lots of debugging stuff.
expect slight instability in signals..
implementations can provide a base zero ffs function if they wish.
This changes
#define RQB_FFS(mask) (ffs64(mask))
foo = RQB_FFS(mask) - 1;
to
#define RQB_FFS(mask) (ffs64(mask) - 1)
foo = RQB_FFS(mask);
On some platforms we can get the "- 1" for free, eg: those that use the
C code for ffs64().
Reviewed by: jake (in principle)
and cpu_critical_exit() and moves associated critical prototypes into their
own header file, <arch>/<arch>/critical.h, which is only included by the
three MI source files that need it.
Backout and re-apply improperly comitted syntactical cleanups made to files
that were still under active development. Backout improperly comitted program
structure changes that moved localized declarations to the top of two
procedures. Partially re-apply one of the program structure changes to
move 'mask' into an intermediate block rather then in three separate
sub-blocks to make the code more readable. Re-integrate bug fixes that Jake
made to the sparc64 code.
Note: In general, developers should not gratuitously move declarations out
of sub-blocks. They are where they are for reasons of structure, grouping,
readability, compiler-localizability, and to avoid developer-introduced bugs
similar to several found in recent years in the VFS and VM code.
Reviewed by: jake
disablement assumptions in kern_fork.c by adding another API call,
cpu_critical_fork_exit(). Cleanup the td_savecrit field by moving it
from MI to MD. Temporarily move cpu_critical*() from <arch>/include/cpufunc.h
to <arch>/<arch>/critical.c (stage-2 will clean this up).
Implement interrupt deferral for i386 that allows interrupts to remain
enabled inside critical sections. This also fixes an IPI interlock bug,
and requires uses of icu_lock to be enclosed in a true interrupt disablement.
This is the stage-1 commit. Stage-2 will occur after stage-1 has stabilized,
and will move cpu_critical*() into its own header file(s) + other things.
This commit may break non-i386 architectures in trivial ways. This should
be temporary.
Reviewed by: core
Approved by: core
enabled in critical sections and streamline critical_enter() and
critical_exit().
This commit allows an architecture to leave interrupts enabled inside
critical sections if it so wishes. Architectures that do not wish to do
this are not effected by this change.
This commit implements the feature for the I386 architecture and provides
a sysctl, debug.critical_mode, which defaults to 1 (use the feature). For
now you can turn the sysctl on and off at any time in order to test the
architectural changes or track down bugs.
This commit is just the first stage. Some areas of the code, specifically
the MACHINE_CRITICAL_ENTER #ifdef'd code, is strictly temporary and will
be cleaned up in the STAGE-2 commit when the critical_*() functions are
moved entirely into MD files.
The following changes have been made:
* critical_enter() and critical_exit() for I386 now simply increment
and decrement curthread->td_critnest. They no longer disable
hard interrupts. When critical_exit() decrements the counter to
0 it effectively calls a routine to deal with whatever interrupts
were deferred during the time the code was operating in a critical
section.
Other architectures are unaffected.
* fork_exit() has been conditionalized to remove MD assumptions for
the new code. Old code will still use the old MD assumptions
in regards to hard interrupt disablement. In STAGE-2 this will
be turned into a subroutine call into MD code rather then hardcoded
in MI code.
The new code places the burden of entering the critical section
in the trampoline code where it belongs.
* I386: interrupts are now enabled while we are in a critical section.
The interrupt vector code has been adjusted to deal with the fact.
If it detects that we are in a critical section it currently defers
the interrupt by adding the appropriate bit to an interrupt mask.
* In order to accomplish the deferral, icu_lock is required. This
is i386-specific. Thus icu_lock can only be obtained by mainline
i386 code while interrupts are hard disabled. This change has been
made.
* Because interrupts may or may not be hard disabled during a
context switch, cpu_switch() can no longer simply assume that
PSL_I will be in a consistent state. Therefore, it now saves and
restores eflags.
* FAST INTERRUPT PROVISION. Fast interrupts are currently deferred.
The intention is to eventually allow them to operate either while
we are in a critical section or, if we are able to restrict the
use of sched_lock, while we are not holding the sched_lock.
* ICU and APIC vector assembly for I386 cleaned up. The ICU code
has been cleaned up to match the APIC code in regards to format
and macro availability. Additionally, the code has been adjusted
to deal with deferred interrupts.
* Deferred interrupts use a per-cpu boolean int_pending, and
masks ipending, spending, and fpending. Being per-cpu variables
it is not currently necessary to lock; bus cycles modifying them.
Note that the same mechanism will enable preemption to be
incorporated as a true software interrupt without having to
further hack up the critical nesting code.
* Note: the old critical_enter() code in kern/kern_switch.c is
currently #ifdef to be compatible with both the old and new
methodology. In STAGE-2 it will be moved entirely to MD code.
Performance issues:
One of the purposes of this commit is to enhance critical section
performance, specifically to greatly reduce bus overhead to allow
the critical section code to be used to protect per-cpu caches.
These caches, such as Jeff's slab allocator work, can potentially
operate very quickly making the effective savings of the new
critical section code's performance very significant.
The second purpose of this commit is to allow architectures to
enable certain interrupts while in a critical section. Specifically,
the intention is to eventually allow certain FAST interrupts to
operate rather then defer.
The third purpose of this commit is to begin to clean up the
critical_enter()/critical_exit()/cpu_critical_enter()/
cpu_critical_exit() API which currently has serious cross pollution
in MI code (in fork_exit() and ast() for example).
The fourth purpose of this commit is to provide a framework that
allows kernel-preempting software interrupts to be implemented
cleanly. This is currently used for two forward interrupts in I386.
Other architectures will have the choice of using this infrastructure
or building the functionality directly into critical_enter()/
critical_exit().
Finally, this commit is designed to greatly improve the flexibility
of various architectures to manage critical section handling,
software interrupts, preemption, and other highly integrated
architecture-specific details.
- The MD functions critical_enter/exit are renamed to start with a cpu_
prefix.
- MI wrapper functions critical_enter/exit maintain a per-thread nesting
count and a per-thread critical section saved state set when entering
a critical section while at nesting level 0 and restored when exiting
to nesting level 0. This moves the saved state out of spin mutexes so
that interlocking spin mutexes works properly.
- Most low-level MD code that used critical_enter/exit now use
cpu_critical_enter/exit. MI code such as device drivers and spin
mutexes use the MI wrappers. Note that since the MI wrappers store
the state in the current thread, they do not have any return values or
arguments.
- mtx_intr_enable() is replaced with a constant CRITICAL_FORK which is
assigned to curthread->td_savecrit during fork_exit().
Tested on: i386, alpha
Note ALL MODULES MUST BE RECOMPILED
make the kernel aware that there are smaller units of scheduling than the
process. (but only allow one thread per process at this time).
This is functionally equivalent to teh previousl -current except
that there is a thread associated with each process.
Sorry john! (your next MFC will be a doosie!)
Reviewed by: peter@freebsd.org, dillon@freebsd.org
X-MFC after: ha ha ha ha
- All processes go into the same array of queues, with different
scheduling classes using different portions of the array. This
allows user processes to have their priorities propogated up into
interrupt thread range if need be.
- I chose 64 run queues as an arbitrary number that is greater than
32. We used to have 4 separate arrays of 32 queues each, so this
may not be optimal. The new run queue code was written with this
in mind; changing the number of run queues only requires changing
constants in runq.h and adjusting the priority levels.
- The new run queue code takes the run queue as a parameter. This
is intended to be used to create per-cpu run queues. Implement
wrappers for compatibility with the old interface which pass in
the global run queue structure.
- Group the priority level, user priority, native priority (before
propogation) and the scheduling class into a struct priority.
- Change any hard coded priority levels that I found to use
symbolic constants (TTIPRI and TTOPRI).
- Remove the curpriority global variable and use that of curproc.
This was used to detect when a process' priority had lowered and
it should yield. We now effectively yield on every interrupt.
- Activate propogate_priority(). It should now have the desired
effect without needing to also propogate the scheduling class.
- Temporarily comment out the call to vm_page_zero_idle() in the
idle loop. It interfered with propogate_priority() because
the idle process needed to do a non-blocking acquire of Giant
and then other processes would try to propogate their priority
onto it. The idle process should not do anything except idle.
vm_page_zero_idle() will return in the form of an idle priority
kernel thread which is woken up at apprioriate times by the vm
system.
- Update struct kinfo_proc to the new priority interface. Deliberately
change its size by adjusting the spare fields. It remained the same
size, but the layout has changed, so userland processes that use it
would parse the data incorrectly. The size constraint should really
be changed to an arbitrary version number. Also add a debug.sizeof
sysctl node for struct kinfo_proc.
include:
* Mutual exclusion is used instead of spl*(). See mutex(9). (Note: The
alpha port is still in transition and currently uses both.)
* Per-CPU idle processes.
* Interrupts are run in their own separate kernel threads and can be
preempted (i386 only).
Partially contributed by: BSDi (BSD/OS)
Submissions by (at least): cp, dfr, dillon, grog, jake, jhb, sheldonh
syscall path inward. A system call may select whether it needs the MP
lock or not (the default being that it does need it).
A great deal of conditional SMP code for various deadended experiments
has been removed. 'cil' and 'cml' have been removed entirely, and the
locking around the cpl has been removed. The conditional
separately-locked fast-interrupt code has been removed, meaning that
interrupts must hold the CPL now (but they pretty much had to anyway).
Another reason for doing this is that the original separate-lock for
interrupts just doesn't apply to the interrupt thread mechanism being
contemplated.
Modifications to the cpl may now ONLY occur while holding the MP
lock. For example, if an otherwise MP safe syscall needs to mess with
the cpl, it must hold the MP lock for the duration and must (as usual)
save/restore the cpl in a nested fashion.
This is precursor work for the real meat coming later: avoiding having
to hold the MP lock for common syscalls and I/O's and interrupt threads.
It is expected that the spl mechanisms and new interrupt threading
mechanisms will be able to run in tandem, allowing a slow piecemeal
transition to occur.
This patch should result in a moderate performance improvement due to
the considerable amount of code that has been removed from the critical
path, especially the simplification of the spl*() calls. The real
performance gains will come later.
Approved by: jkh
Reviewed by: current, bde (exception.s)
Some work taken from: luoqi's patch
