happen in interrupt context; 1) sleep locks, and 2) malloc/free
calls.
1) is fixed by using spin locks instead.
2) is fixed by preallocating a FIFO (implemented with a STAILQ)
and using elements from this FIFO instead. This turns out
to be rather fast.
OK'ed by: re (scottl)
Thanks to: peter, jhb, rwatson, jake
Apologies to: *
- 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.
turnstiles to implement blocking isntead of implementing a thread queue
directly. These turnstiles are somewhat similar to those used in Solaris 7
as described in Solaris Internals but are also different.
Turnstiles do not come out of a fixed-sized pool. Rather, each thread is
assigned a turnstile when it is created that it frees when it is destroyed.
When a thread blocks on a lock, it donates its turnstile to that lock to
serve as queue of blocked threads. The queue associated with a given lock
is found by a lookup in a simple hash table. The turnstile itself is
protected by a lock associated with its entry in the hash table. This
means that sched_lock is no longer needed to contest on a mutex. Instead,
sched_lock is only used when manipulating run queues or thread priorities.
Turnstiles also implement priority propagation inherently.
Currently turnstiles only support mutexes. Eventually, however, turnstiles
may grow two queue's to support a non-sleepable reader/writer lock
implementation. For more details, see the comments in sys/turnstile.h and
kern/subr_turnstile.c.
The two primary advantages from the turnstile code include: 1) the size
of struct mutex shrinks by four pointers as it no longer stores the
thread queue linkages directly, and 2) less contention on sched_lock in
SMP systems including the ability for multiple CPUs to contend on different
locks simultaneously (not that this last detail is necessarily that much of
a big win). Note that 1) means that this commit is a kernel ABI breaker,
so don't mix old modules with a new kernel and vice versa.
Tested on: i386 SMP, sparc64 SMP, alpha SMP
another thread. We use the td_oncpu member of the other field to locate
it's associated CPU and then search the that CPU's list of spin locks
contained in its per-CPU data. This is not always safe and may in fact
panic or just not work, but it is useful in at least one case.
by allprison_mtx), a unique prison/jail identifier field, two path
fields (pr_path for reporting and pr_root vnode instance) to store
the chroot() point of each jail.
o Add jail_attach(2) to allow a process to bind to an existing jail.
o Add change_root() to perform the chroot operation on a specified
vnode.
o Generalize change_dir() to accept a vnode, and move namei() calls
to callers of change_dir().
o Add a new sysctl (security.jail.list) which is a group of
struct xprison instances that represent a snapshot of active jails.
Reviewed by: rwatson, tjr
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
is set to 0, it now has the same affect as setting witness_dead used to
have.
- Added a sysctl handler that allows root to change witness_watch from a
non-zero value to zero to disable witness at runtime. Note that you
can't turn witness back on once it is off. You can only turn it off as
a one-way switch.
- Added a comment describing the possible values of witness_watch.
a parameter instead of using the level of a given witness. When
recursing, pass an indent level of indent + 1.
- Make use of the information witness_levelall() provides in
witness_display_list() to use an O(n) algorithm instead of an O(n^2)
algo to decide which witnesses to display hierarchies from. Basically,
we only display a hierarchy for witnesses with a level of 0.
- Add a new per-witness flag that is reset at the start of
witness_display() for all witness's and is set the first time a witness
is displayed in witness_displaydescendants(). If a witness is
encountered more than once in the lock order tree (which happens often),
witness_displaydescendants() marks the later occurrences with the string
"(already displayed)" and doesn't display the subtree under that
witness. This avoids duplicating large amounts of the lock order tree
in the 'show witness' output in DDB.
All these changes serve to make 'show witness' a lot more readable and
useful than it was previously.
adds a witness to the child list of a parent witness. rebalancetree()
runs through the entire tree removing direct descendants of witnesses
who already have said child witness as an indirect descendant through
another direct descendant. itismychild() now calls insertchild()
followed by rebalancetree() and no longer needs the evil hack of
having static recursed variable.
- Add a function reparentchildren() that adds all the direct descendants
of one witness as direct descendants of another witness.
- Change the return value of itismychild() and similar functions so that
they return 0 in the case of failure due to lack of resources instead
of 1. This makes the return value more intuitive.
- Check the return value of itismychild() when defining the static lock
order in witness_initialize().
- Don't try to setup a lock instance in witness_lock() if itismychild()
fails. Witness is hosed anyways so no need to do any more witness
related activity at that point. It also makes the code flow easier to
understand.
- Add a new depart() function as the opposite of enroll(). When the
reference count of a witness drops to 0 in witness_destroy(), this
function is called on that witness. First, it runs through the
lock order tree using reparentchildren() to reparent direct descendants
of the departing witness to each of the witness' parents in the tree.
Next, it releases it's own child list and other associated resources.
Finally it calls rebalanacetree() to rebalance the lock order tree.
- Sort function prototypes into something closer to alphabetical order.
As a result of these changes, there should no longer be 'dead' witnesses
in the order tree, and repeatedly loading and unloading a module should no
longer exhaust witness of its internal resources.
Inspired by: gallatin
recursing on a lock instead of before. This fixes a bug where WITNESS
could get a little confused if you did an sx_tryslock() on a sx lock that
you already had an slock on. WITNESS would still function correctly but
it could result in weirdness in the output of 'show locks'. This also
makes it possible for mtx_trylock() to recurse on a lock.
ddb 'show locks' command. Thus, move witness_list() to the #ifdef DDB
section and remove extra checks for calling this function outside of
DDB. Also, witness_list() now returns void instead of returning an int.
Reported by: Steve Ames <steve@energistic.com>
Prodded by: davidxu
witness. Sleepable locks such as sx locks always come before all mutexes
including Giant. However, the static lock order list placed Giant before
the proctree and allproc sx locks. This resulted in witness creating a
cycle in its lock order "tree" (real trees don't have cycles) leading to
infinite recursion and eventually a double fault. To fix, put Giant after
sx locks in the lock order list.
- Add a comment about special lock order rules and Giant near the top of
subr_witness.c. Specifically, this documents and explains the real lock
order relationship between Giant and sleepable locks (i.e. lockmgr locks
and sx locks). Basically, Giant can be safely acquired either before or
after sleepable locks and the case of Giant before a sleepable lock is
exempted as a special case.
- Add a new static function 'witness_list_lock()' that displays a single
line of information about a struct lock_instance. This is used to
make the output of witness messages more consistent and reduce some code
duplication.
- Fixup a few comments in witness_lock().
- Properly handle the Giant-before-sleepable-lock lock order exception in
a more general fashion and remove the no longer needed LI_SLEPT flag.
- Break up the last condition before assuming a reversal a bit to try
and make the logic less confusing in witness_lock().
- Axe WITNESS_SLEEP() now that LI_SLEPT is no longer needed and replace it
with a more general WITNESS_WARN() macro/function combination.
WITNESS_WARN() allows you to output a customized message out to the
console along with a list of held locks. It will optionally drop into
the debugger as well. You can exempt a single lock from the check by
passing it in as the second argument. You can also use flags to specify
if Giant should be exempt from the check, if all sleepable locks should
be exempt from the check, and if witness should panic if any non-exempt
locks are found.
- Make the witness_list() function static. Other areas of the kernel
should use the new WITNESS_WARN() instead.
#if'ed out for a while. Complete the deed and tidy up some other bits.
We need to be able to call this stuff from outer edges of interrupt
handlers for devices that have the ISR bits in pci config space. Making
the bios code mpsafe was just too hairy. We had also stubbed it out some
time ago due to there simply being too much brokenness in too many systems.
This adds a leaf lock so that it is safe to use pci_read_config() and
pci_write_config() from interrupt handlers. We still will use pcibios
to do interrupt routing if there is no acpi.. [yes, I tested this]
Briefly glanced at by: imp
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
earlier acquired lock with the same witness as the lock currently being
acquired. If we had released several earlier acquired locks after
acquiring enough locks to require another lock_list_entry bucket in the
lock list, then subsequent lock_list_entry buckets could contain only one
lock instance in which case i would be zero.
Reported by: Joel M. Baldwin <qumqats@outel.org>
- Get the initial mode from the prom settings and don't clobber the mode
on open.
- Copy output into an internal ring buffer instead of accessing the tty
outq directly in the interrupt handler. This fixes a problem where
garbage would show up in the output stream.
- Reset the console port completely and reprogram all the parameters
before enabling it. This fixes seemingly random hangs on startup
when using a fast interrupt handler.
- Add minimal locking in place of spls.
- Remove dead code and minor cleanups.
- It actually works this time, honest!
- Fine grained TLB shootdowns for SMP on i386. IPI's are very expensive,
so try and optimize things where possible.
- Introduce ranged shootdowns that can be done as a single IPI.
- PG_G support for i386
- Specific-cpu targeted shootdowns. For example, there is no sense in
globally purging the TLB cache for where we are stealing a page from
the local unshared process on the local cpu. Use pm_active to track
this.
- Add some instrumentation for the tlb shootdown code.
- Rip out SMP code from <machine/cpufunc.h>
- Try and fix some very bogus PG_G and PG_PS interactions that were bad
enough to cause vm86 bios calls to break. vm86 depended on our existing
bugs and this was the cause of the VESA panics last time.
- Fix the silly one-line error that caused the 'panic: bad pte' last time.
- Fix a couple of other silly one-line errors that should have caused more
pain than they did.
Some more work is needed:
- pmap_{zero,copy}_page[_idle]. These can be done without IPI's if we
have a hook in cpu_switch.
- The IPI handlers need some cleanup. I have a bogus %ds load that can
be avoided.
- APTD handling is rather bogus and appears to be a large source of
global TLB IPI shootdowns for no really good reason.
I see speedups of between 1.5% and ~4% on buildworlds in a while 1 loop.
I expect to see a bigger difference when there is significant pageout
activity or the system otherwise has memory shortages.
I have backed out a few optimizations that I had been using over the last
few days in order to be a little more conservative. I'll revisit these
again over the next few days as the dust settles.
New option: DISABLE_PG_G - In case I missed something.
queue lock (revision 1.33 of vm/vm_page.c removed them).
o Make the free queue lock a spin lock because it's sometimes acquired
inside of a critical section.
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..
lock_object by another pointer (though all of lock_object should be
conditional on LOCK_DEBUG anyways) in exchange for an O(1) TAILQ_REMOVE()
in witness_destroy() (called for every mtx_destroy() and sx_destroy())
instead of an O(n) STAILQ_REMOVE. Since WITNESS is so dog slow as it is,
the speed-up is worth the space cost.
Suggested by: iedowse
being created and destroyed without a single long-term one around to ensure
the witness associated with that group of locks stays alive. The pipe
mutexes are an example of this group. For a dead witness we no longer
clear the witness name. Instead, when looking up the witness for a lock,
if a dead witness' (a witness with a refcount of 0) w_name pointer is
identical to the witness name of the lock then we revive that witness
instead of using a new witness for the lock. This results in far fewer
dead witness objects and also better preserves locking orders over the long
term resulting in more correct lock order checking. Note that we can't
ever derefence w_name of a dead witness since we don't know if the string
it is pointing to has been free()'d or kldunload()'d out from under us.
yet. We just return without performing any checks.
- Don't explicitly enter and exit critical sections when walking lock
lists. We don't need a critical section to walk the list of sleep
locks for a thread. We check to see if a spin lock list is empty
before we walk it. If the list is empty we don't need to walk it. If
it isn't then we already hold at least one spin lock and are already in
a critical section and thus don't need our own explicit critical
section.
be done internally.
Ensure that no one can fsetown() to a dying process/pgrp. We need
to check the process for P_WEXIT to see if it's exiting. Process
groups are already safe because there is no such thing as a pgrp
zombie, therefore the proctree lock completely protects the pgrp
from having sigio structures associated with it after it runs
funsetownlst.
Add sigio lock to witness list under proctree and allproc, but over
proc and pgrp.
Seigo Tanimura helped with this.
sx lock. Trying to get the lock order between these locks was getting
too complicated as the locking in wait1() was being fixed.
- leavepgrp() now requires an exclusive lock of proctree_lock to be held
when it is called.
- fixjobc() no longer gets a shared lock of proctree_lock now that it
requires an xlock be held by the caller.
- Locking notes in sys/proc.h are adjusted to note that everything that
used to be protected by the pgrpsess_lock is now protected by the
proctree_lock.
point to a more generic name for a lock that is more suitable for use by
witness when grouping locks. For example, although network driver locks
use the interface name for the name of each lock, they should all use the
same witness and be treated the same as witness. Another example is that
all UMA zone locks should be treated the same. The witness code has also
been updated to print out the lock type in addition to the lock name in a
few places where it is relevant.
with this flag. Remove the dup_list and dup_ok code from subr_witness. Now
we just check for the flag instead of doing string compares.
Also, switch the process lock, process group lock, and uma per cpu locks over
to this interface. The original mechanism did not work well for uma because
per cpu lock names are unique to each zone.
Approved by: jhb
simply need to prevent switching from another CPU and do not need
interrupts disabled.
- Add a comment to witness_list() about why displaying spin locks for
threads on other CPU's really is just a bad idea and probably shouldn't
be done.
There is some unresolved badness that has been eluding me, particularly
affecting uniprocessor kernels. Turning off PG_G helped (which is a bad
sign) but didn't solve it entirely. Userland programs still crashed.
on for a while:
- fine grained TLB shootdown for SMP on i386
- ranged TLB shootdowns.. eg: specify a range of pages to shoot down with
a single IPI, since the IPI is very expensive. Adjust some callers
that used to trigger this inside tight loops to do a ranged shootdown
at the end instead.
- PG_G support for SMP on i386 (options ENABLE_PG_G)
- defer PG_G activation till after we decide what we are going to do with
PSE and the 4MB pages at the start of the kernel. This should solve
some rumored strangeness about stale PG_G entries getting stuck
underneath the 4MB pages.
- add some instrumentation for the fine TLB shootdown
- convert some asm instruction wrappers from functions to inlines. gcc
seems to do a fair bit better with this.
- [temporarily!] pessimize the tlb shootdown IPI handlers. I will fix
this again shortly.
This has been working fairly well for me for a while, but I have tweaked
it again prior to commit since my last major testing round. The only
outstanding problem that I know of is PG_G related, which is why there
is an option for it (not on by default for SMP). I have seen a world
speedups by a few percent (as much as 4 or 5% in one case) but I have
*not* accurately measured this - I am a bit sceptical of these numbers.
New locks are:
- pgrpsess_lock which locks the whole pgrps and sessions,
- pg_mtx which protects the pgrp members, and
- s_mtx which protects the session members.
Please refer to sys/proc.h for the coverage of these locks.
Changes on the pgrp/session interface:
- pgfind() needs the pgrpsess_lock held.
- The caller of enterpgrp() is responsible to allocate a new pgrp and
session.
- Call enterthispgrp() in order to enter an existing pgrp.
- pgsignal() requires a pgrp lock held.
Reviewed by: jhb, alfred
Tested on: cvsup.jp.FreeBSD.org
(which is a quad-CPU machine running -current)
this is a low-functionality change that changes the kernel to access the main
thread of a process via the linked list of threads rather than
assuming that it is embedded in the process. It IS still embeded there
but remove all teh code that assumes that in preparation for the next commit
which will actually move it out.
Reviewed by: peter@freebsd.org, gallatin@cs.duke.edu, benno rice,
- Create a private list of active pmaps rather than abusing the list of all
processes when we need to look up pmaps. The process list needs a sx lock
and we can't be getting sx locks in the middle of cpu_switch()
(pmap_activate() can call pmap_get_asn() from cpu_switch()). Instead, we
protect the list with a spinlock. This also means the list is shorter
since a pmap can be used by more than one process and we could (at least
in thoery) dink with pmap's more than once, but now we only touch each
pmap once when we have to update all of them.
- Wrap pmap_activate()'s code to get a new ASN in an explicit critical section
so that when it is called while doing an exec() we can't get preempted.
- Replace splhigh() in pmap_growkernel() with a critical section to prevent
preemption while we are adjusting the kernel page tables.
- Fixes abuse of PCPU_GET(), which doesn't return an L-value.
- Also adds some slight cleanups to the ASN handling by adding some macros
instead of magic numbers in relation to the ASN and ASN generations.
Reviewed by: dfr
mutex releases to not require flags for the cases when preemption is
not allowed:
The purpose of the MTX_NOSWITCH and SWI_NOSWITCH flags is to prevent
switching to a higher priority thread on mutex releease and swi schedule,
respectively when that switch is not safe. Now that the critical section
API maintains a per-thread nesting count, the kernel can easily check
whether or not it should switch without relying on flags from the
programmer. This fixes a few bugs in that all current callers of
swi_sched() used SWI_NOSWITCH, when in fact, only the ones called from
fast interrupt handlers and the swi_sched of softclock needed this flag.
Note that to ensure that swi_sched()'s in clock and fast interrupt
handlers do not switch, these handlers have to be explicitly wrapped
in critical_enter/exit pairs. Presently, just wrapping the handlers is
sufficient, but in the future with the fully preemptive kernel, the
interrupt must be EOI'd before critical_exit() is called. (critical_exit()
can switch due to a deferred preemption in a fully preemptive kernel.)
I've tested the changes to the interrupt code on i386 and alpha. I have
not tested ia64, but the interrupt code is almost identical to the alpha
code, so I expect it will work fine. PowerPC and ARM do not yet have
interrupt code in the tree so they shouldn't be broken. Sparc64 is
broken, but that's been ok'd by jake and tmm who will be fixing the
interrupt code for sparc64 shortly.
Reviewed by: peter
Tested on: i386, alpha
and it's associated state variables: icu_lock with the name "icu". This
renames the imen_mtx for x86 SMP, but also uses the lock to protect
access to the 8259 PIC on x86 UP. This also adds an appropriate lock to
the various Alpha chipsets which fixes problems with Alpha SMP machines
dropping interrupts with an SMP kernel.
- 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
In this case, C99's __func__ is properly defined as:
static const char __func__[] = "function-name";
and GCC 3.1 will not allow it to be used in bogus string concatenation.
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
- Clean up the KTR tracepoints to be slighlty more consistent and useful
- Fix a bug in WITNESS where we would recurse indefinitely and blow the
stack when acquiring Giant after sleeping with a sleepable lock held.
Reported by: tanimura (3)
may need the clock lock for nanotime().
- Add KTR trace events for lock list manipulations and other witness
operations.
- Use a temporary variable instead of setting the lock list head directly
and then setting up the links to add a new lock list entry to the lock
list. This small race could result in witness "forgetting" about all
the locks held by this process temporarily during an interrupt.
- Close a more fatal race condition when removing a lock from a list.
Removing a lock from the list entails both decrementing the count of
items in this bucket as well as shuffling items in the current bucket up
a notch to replace the gap left by the removed item. Wrap these
operations in a critical section.
around, use a common function for looking up and extracting the tunables
from the kernel environment. This saves duplicating the same function
over and over again. This way typically has an overhead of 8 bytes + the
path string, versus about 26 bytes + the path string.
lock. Since we won't actually block on a try lock operation, it's not
a problem. Add a comment explaining why it is safe to skip lock order
checking with try locks.
- Remove the ithread list lock spin lock from the order list.
fail due to witness exhausting its internal resources and shutting down.
Reported by: Szilveszter Adam <sziszi@petra.hos.u-szeged.hu>
Tested by: David Wolfskill <david@catwhisker.org>
struct lock_instance that is stored in the per-process and per-CPU lock
lists. Previously, the lock lists just kept a pointer to each lock held.
That pointer is now replaced by a lock instance which contains a pointer
to the lock object, the file and line of the last acquisition of a lock,
and various flags about a lock including its recursion count.
- If we sleep while holding a sleepable lock, then mark that lock instance
as having slept and ignore any lock order violations that occur while
acquiring Giant when we wake up with slept locks. This is ok because of
Giant's special nature.
- Allow witness to differentiate between shared and exclusive locks and
unlocks of a lock. Witness will now detect the case when a lock is
acquired first in one mode and then in another. Mutexes are always
locked and unlocked exclusively. Witness will also now detect the case
where a process attempts to unlock a shared lock while holding an
exclusive lock and vice versa.
- Fix a bug in the lock list implementation where we used the wrong
constant to detect the case where a lock list entry was full.
can happen if witness runs out of resources during initialization or if
witness_skipspin is enabled.
Sleuthing by: Peter Jeremy <peter.jeremy@alcatel.com.au>
count drops to 0 in witness_destroy, set the w_name and w_file pointers
to point to the string "(dead)" and the w_line field to 0. This way,
if a mutex of a given name is used only in a module, then as long as
all mutexes in the module are destroyed when the module is unloaded,
witness will not maintain stale references to the mutex's name in the
module's data section causing a panic later on when the w_name or w_file
field's are examined.
list into a public witness_list_locks() function. Call this function
twice in witness_list() instead of using an evil goto.
- Adjust the 'show locks' command to take an optional parameter which
specifies the pid of a process to list the locks of. By default the
locks held by the current process are displayed.
locks were held, we could be preempted and switch CPU's in between the time
that we set a variable to the list of spin locks on our CPU and the time
that we checked that variable to ensure no spinlocks were held while
grabbing a sleep lock. Losing the race resulted in checking some other
CPU's spin lock list and bogusly panicing.
- Introduce lock classes and lock objects. Each lock class specifies a
name and set of flags (or properties) shared by all locks of a given
type. Currently there are three lock classes: spin mutexes, sleep
mutexes, and sx locks. A lock object specifies properties of an
additional lock along with a lock name and all of the extra stuff needed
to make witness work with a given lock. This abstract lock stuff is
defined in sys/lock.h. The lockmgr constants, types, and prototypes have
been moved to sys/lockmgr.h. For temporary backwards compatability,
sys/lock.h includes sys/lockmgr.h.
- Replace proc->p_spinlocks with a per-CPU list, PCPU(spinlocks), of spin
locks held. By making this per-cpu, we do not have to jump through
magic hoops to deal with sched_lock changing ownership during context
switches.
- Replace proc->p_heldmtx, formerly a list of held sleep mutexes, with
proc->p_sleeplocks, which is a list of held sleep locks including sleep
mutexes and sx locks.
- Add helper macros for logging lock events via the KTR_LOCK KTR logging
level so that the log messages are consistent.
- Add some new flags that can be passed to mtx_init():
- MTX_NOWITNESS - specifies that this lock should be ignored by witness.
This is used for the mutex that blocks a sx lock for example.
- MTX_QUIET - this is not new, but you can pass this to mtx_init() now
and no events will be logged for this lock, so that one doesn't have
to change all the individual mtx_lock/unlock() operations.
- All lock objects maintain an initialized flag. Use this flag to export
a mtx_initialized() macro that can be safely called from drivers. Also,
we on longer walk the all_mtx list if MUTEX_DEBUG is defined as witness
performs the corresponding checks using the initialized flag.
- The lock order reversal messages have been improved to output slightly
more accurate file and line numbers.
and change the u_int mtx_saveintr member of struct mtx to a critical_t
mtx_savecrit.
- On the alpha we no longer need a custom _get_spin_lock() macro to avoid
an extra PAL call, so remove it.
- Partially fix using mutexes with WITNESS in modules. Change all the
_mtx_{un,}lock_{spin,}_flags() macros to accept explicit file and line
parameters and rename them to use a prefix of two underscores. Inside
of kern_mutex.c, generate wrapper functions for
_mtx_{un,}lock_{spin,}_flags() (only using a prefix of one underscore)
that are called from modules. The macros mtx_{un,}lock_{spin,}_flags()
are mapped to the __mtx_* macros inside of the kernel to inline the
usual case of mutex operations and map to the internal _mtx_* functions
in the module case so that modules will use WITNESS and KTR logging if
the kernel is compiled with support for it.
if we hold a spin mutex, since we can trivially get into deadlocks if we
start switching out of processes that hold spinlocks. Checking to see if
interrupts were disabled was a sort of cheap way of doing this since most
of the time interrupts were only disabled when holding a spin lock. At
least on the i386. To fix this properly, use a per-process counter
p_spinlocks that counts the number of spin locks currently held, and
instead of checking to see if interrupts are disabled in the witness code,
check to see if we hold any spin locks. Since child processes always
start up with the sched lock magically held in fork_exit(), we initialize
p_spinlocks to 1 for child processes. Note that proc0 doesn't go through
fork_exit(), so it starts with no spin locks held.
Consulting from: cp
don't end up back at ourselves which would indicate deadlock.
- Add the proc lock to the witness dup_list as we may hold more than one
process lock at a time.
- Don't assert a mutex is owned in _mtx_unlock_sleep() as that is too late.
We do the checks in the macros instead.
update native priority, it is diffcult to get right and likely
to end up horribly wrong. Use an honestly wrong fixed value
that seems to work; PUSER for user threads, and the interrupt
priority for ithreads. Set it once when the process is created
and forget about it.
Suggested by: bde
Pointy hat: me
process's priority go through the roof when it released a (contested)
mutex. Only set the native priority in mtx_lock if hasn't already
been set.
Reviewed by: jhb
passed in filename and line number in the KTR tracepoint message.
- Even though it is #if 0'd code, change the code to detect that a process
is an interrupt thread to check p->p_ithd against NULL rather than
checking non-existant process flags from BSD/OS.
- Use '%p' to print pointers in KTR log messages instead of assuming
sizeof(int) == sizeof(void *).
- Don't set p_mtxname to NULL when releasing a mutex. It doesn't hurt
to leave it set (we don't clear w_mesg for example) and at least at
one time in the past, there used to be race conditions in the kernel
that would result in setting this to NULL causing the kernel to
dereference NULL.
- Make the _mtx_assert() function be compiled in if INVARIANTS_SUPPORT is
defined rather than if INVARIANTS is defined so that a KLD compiled
with INVARIANTS that uses mtx_assert() can be used with a kernel that
just has INVARIANT_SUPPORT compiled in.
- 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.
tracing in order to avoid duplication.
- Insert some tracepoints back into the mutex acq/rel code, thus ensuring
that we can trace all lock acq/rel's again.
- All CURPROC != NULL checks are MPASS()es (under MUTEX_DEBUG) because they
signify a serious mutex corruption.
- Change up some KASSERT()s to MPASS()es, and vice-versa, depending on the
type of problem we're debugging (INVARIANTS is used here to check that
the API is being used properly whereas MUTEX_DEBUG is used to ensure that
something general isn't happening that will have bad impact on mutex
locks).
Reminded by: jhb, jake, asmodai
will only display sleep mutexes held by the current process.
- Clean up some nits in the witness_display() function and add a ddb
command 'show witness' that dumps the hierarchy and order lists to the
console.
- Use queue(3) macros where appropriate.
- Resort the spin lock order list so that "com" is before "sched_lock".
Also, add appropriate #ifdef's around SMP and i386-specific mutexes.
- Add two new mutexes used to protect the ithread lists and tables to the
order list.
Requested by: bde (1)
mtx_enter(lock, type) becomes:
mtx_lock(lock) for sleep locks (MTX_DEF-initialized locks)
mtx_lock_spin(lock) for spin locks (MTX_SPIN-initialized)
similarily, for releasing a lock, we now have:
mtx_unlock(lock) for MTX_DEF and mtx_unlock_spin(lock) for MTX_SPIN.
We change the caller interface for the two different types of locks
because the semantics are entirely different for each case, and this
makes it explicitly clear and, at the same time, it rids us of the
extra `type' argument.
The enter->lock and exit->unlock change has been made with the idea
that we're "locking data" and not "entering locked code" in mind.
Further, remove all additional "flags" previously passed to the
lock acquire/release routines with the exception of two:
MTX_QUIET and MTX_NOSWITCH
The functionality of these flags is preserved and they can be passed
to the lock/unlock routines by calling the corresponding wrappers:
mtx_{lock, unlock}_flags(lock, flag(s)) and
mtx_{lock, unlock}_spin_flags(lock, flag(s)) for MTX_DEF and MTX_SPIN
locks, respectively.
Re-inline some lock acq/rel code; in the sleep lock case, we only
inline the _obtain_lock()s in order to ensure that the inlined code
fits into a cache line. In the spin lock case, we inline recursion and
actually only perform a function call if we need to spin. This change
has been made with the idea that we generally tend to avoid spin locks
and that also the spin locks that we do have and are heavily used
(i.e. sched_lock) do recurse, and therefore in an effort to reduce
function call overhead for some architectures (such as alpha), we
inline recursion for this case.
Create a new malloc type for the witness code and retire from using
the M_DEV type. The new type is called M_WITNESS and is only declared
if WITNESS is enabled.
Begin cleaning up some machdep/mutex.h code - specifically updated the
"optimized" inlined code in alpha/mutex.h and wrote MTX_LOCK_SPIN
and MTX_UNLOCK_SPIN asm macros for the i386/mutex.h as we presently
need those.
Finally, caught up to the interface changes in all sys code.
Contributors: jake, jhb, jasone (in no particular order)
mtx right now as it makes debugging harder. When we are in optimizing
mode, we can revisit this.
- Fix the KTR trace messages to use %p rather than 0x%p to avoid duplicate
0x's in KTR output.
- During witness_fixup, release Giant so that witness doesn't get confused.
Also, grab all_mtx while walking the list of mutexes.
- Remove w_sleep and w_recurse. Instead, perform checks on mutexes using
the mutex's mtx_flags field.
- Allow debug.witness_ddb and debug.witness_skipspin to be set from the
loader.
- Add Giant to the front of existing order_list entries to help ensure
Giant is always first.
- Add an order entry for the various proc locks. Note that this only
helps keep proc in order mostly as the allproc and proctree mutexes are
only obtained during a lockmgr operation on the specified mutex.
inline functions non-inlined. Hide parts of the mutex implementation that
should not be exposed.
Make sure that WITNESS code is not executed during boot until the mutexes
are fully initialized by SI_SUB_MUTEX (the original motivation for this
commit).
Submitted by: peter
initialization until after malloc() is safe to call, then iterate through
all mutexes and complete their initialization.
This change is necessary in order to avoid some circular bootstrapping
dependencies.
All calls to mtx_init() for mutexes that recurse must now include
the MTX_RECURSE bit in the flag argument variable. This change is in
preparation for an upcoming (further) mutex API cleanup.
The witness code will call panic() if a lock is found to recurse but
the MTX_RECURSE bit was not set during the lock's initialization.
The old MTX_RECURSE "state" bit (in mtx_lock) has been renamed to
MTX_RECURSED, which is more appropriate given its meaning.
The following locks have been made "recursive," thus far:
eventhandler, Giant, callout, sched_lock, possibly some others declared
in the architecture-specific code, all of the network card driver locks
in pci/, as well as some other locks in dev/ stuff that I've found to
be recursive.
Reviewed by: jhb
functions. If this flag is set, then no KTR log messages are issued.
This is useful for blocking excessive logging, such as with the internal
mutex used by the witness code.
- Use MTX_QUIET on all of the mtx_enter/exit operations on the internal
mutex used by the witness code.
- If we are in a panic, don't do witness checks in witness_enter(),
witness_exit(), and witness_try_enter(), just return.
held and panic if so (conditional on witness).
- Change witness_list to return the number of locks held so this is easier.
- Add kern/syscalls.c to the kernel build if witness is defined so that the
panic message can contain the name of the offending system call.
- Add assertions that Giant and sched_lock are not held when returning from
a system call, which were missing for alpha and ia64.
depend on MUTEX_DEBUG. The MUTEX_DEBUG option turns on extra assertions
and checks to verify that mutexes themselves are implemented properly.
The WITNESS option uses extra checks and diagnostics to verify that other
code is using mutexes properly.
- Use a better test for determining when a process is running.
- Convert some checks to assertions.
- Remove unnecessary tests.
- Save the priority before acquiring a mutex rather than in msleep(9).
- Use the mutex in hardclock to ensure no races between it and
softclock.
- Make softclock be INTR_MPSAFE and provide a flag,
CALLOUT_MPSAFE, which specifies that a callout handler does not
need giant. There is still no way to set this flag when
regstering a callout.
Reviewed by: -smp@, jlemon
may block on a mutex while on the sleep queue without corrupting
it.
- Move dropping of Giant to after the acquire of sched_lock.
Tested by: John Hay <jhay@icomtek.csir.co.za>
jhb
acquire Giant as needed in functions that call mi_switch(). The releases
need to be done outside of the sched_lock to avoid potential deadlocks
from trying to acquire Giant while interrupts are disabled.
Submitted by: witness
it can function before malloc(9) is up and running.
- Add two new options WITNESS_DDB and WITNESS_SKIPSPIN. If WITNESS_SKIPSPIN
is enabled, then spin mutexes are ignored by the WITNESS code. If
WITNESS_DDB is turned on and DDB is compiled into the kernel, then the
kernel will drop into DDB when either a lock hierarchy violation occurs
or mutexes are held when going to sleep.
- Add some new sysctls:
debug.witness_ddb is a read-write sysctl that corresponds to WITNESS_DDB.
The kernel option merely changes the default value to on at boot.
debug.witness_skipspin is a read-only sysctl that one can use to determine
if the kernel was compiled with WITNESS_SKIPSPIN.
- Wipe out the BSD/OS-specific lock order lists. We get to build our own
lists now as we add mutexes to the kernel.
reducues the maintenance load for the mutex code. The only MD portions
of the mutex code are in machine/mutex.h now, which include the assembly
macros for handling mutexes as well as optionally overriding the mutex
micro-operations. For example, we use optimized micro-ops on the x86
platform #ifndef I386_CPU.
- Change the behavior of the SMP_DEBUG kernel option. In the new code,
mtx_assert() only depends on INVARIANTS, allowing other kernel developers
to have working mutex assertiions without having to include all of the
mutex debugging code. The SMP_DEBUG kernel option has been renamed to
MUTEX_DEBUG and now just controls extra mutex debugging code.
- Abolish the ugly mtx_f hack. Instead, we dynamically allocate
seperate mtx_debug structures on the fly in mtx_init, except for mutexes
that are initiated very early in the boot process. These mutexes
are declared using a special MUTEX_DECLARE() macro, and use a new
flag MTX_COLD when calling mtx_init. This is still somewhat hackish,
but it is less evil than the mtx_f filler struct, and the mtx struct is
now the same size with and without mutex debugging code.
- Add some micro-micro-operation macros for doing the actual atomic
operations on the mutex mtx_lock field to make it easier for other archs
to override/optimize mutex ops if needed. These new tiny ops also clean
up the code in some places by replacing long atomic operation function
calls that spanned 2-3 lines with a short 1-line macro call.
- Don't call mi_switch() from mtx_enter_hard() when we block while trying
to obtain a sleep mutex. Calling mi_switch() would bogusly release
Giant before switching to the next process. Instead, inline most of the
code from mi_switch() in the mtx_enter_hard() function. Note that when
we finally kill Giant we can back this out and go back to calling
mi_switch().
macros that expand to pass filename and line number information. This is
necessary since we're using inline functions instead of macros now.
Add const to the filename pointers passed througout the mtx and witness
code.
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
