We are pleased to announce "lightweight userspace priority inheritance" (PI)
support for futexes. The following patchset and glibc patch implements it,
ontop of the robust-futexes patchset which is included in 2.6.16-mm1.
We are calling it lightweight for 3 reasons:
- in the user-space fastpath a PI-enabled futex involves no kernel work
(or any other PI complexity) at all. No registration, no extra kernel
calls - just pure fast atomic ops in userspace.
- in the slowpath (in the lock-contention case), the system call and
scheduling pattern is in fact better than that of normal futexes, due to
the 'integrated' nature of FUTEX_LOCK_PI. [more about that further down]
- the in-kernel PI implementation is streamlined around the mutex
abstraction, with strict rules that keep the implementation relatively
simple: only a single owner may own a lock (i.e. no read-write lock
support), only the owner may unlock a lock, no recursive locking, etc.
Priority Inheritance - why, oh why???
-------------------------------------
Many of you heard the horror stories about the evil PI code circling Linux for
years, which makes no real sense at all and is only used by buggy applications
and which has horrible overhead. Some of you have dreaded this very moment,
when someone actually submits working PI code ;-)
So why would we like to see PI support for futexes?
We'd like to see it done purely for technological reasons. We dont think it's
a buggy concept, we think it's useful functionality to offer to applications,
which functionality cannot be achieved in other ways. We also think it's the
right thing to do, and we think we've got the right arguments and the right
numbers to prove that. We also believe that we can address all the
counter-arguments as well. For these reasons (and the reasons outlined below)
we are submitting this patch-set for upstream kernel inclusion.
What are the benefits of PI?
The short reply:
----------------
User-space PI helps achieving/improving determinism for user-space
applications. In the best-case, it can help achieve determinism and
well-bound latencies. Even in the worst-case, PI will improve the statistical
distribution of locking related application delays.
The longer reply:
-----------------
Firstly, sharing locks between multiple tasks is a common programming
technique that often cannot be replaced with lockless algorithms. As we can
see it in the kernel [which is a quite complex program in itself], lockless
structures are rather the exception than the norm - the current ratio of
lockless vs. locky code for shared data structures is somewhere between 1:10
and 1:100. Lockless is hard, and the complexity of lockless algorithms often
endangers to ability to do robust reviews of said code. I.e. critical RT
apps often choose lock structures to protect critical data structures, instead
of lockless algorithms. Furthermore, there are cases (like shared hardware,
or other resource limits) where lockless access is mathematically impossible.
Media players (such as Jack) are an example of reasonable application design
with multiple tasks (with multiple priority levels) sharing short-held locks:
for example, a highprio audio playback thread is combined with medium-prio
construct-audio-data threads and low-prio display-colory-stuff threads. Add
video and decoding to the mix and we've got even more priority levels.
So once we accept that synchronization objects (locks) are an unavoidable fact
of life, and once we accept that multi-task userspace apps have a very fair
expectation of being able to use locks, we've got to think about how to offer
the option of a deterministic locking implementation to user-space.
Most of the technical counter-arguments against doing priority inheritance
only apply to kernel-space locks. But user-space locks are different, there
we cannot disable interrupts or make the task non-preemptible in a critical
section, so the 'use spinlocks' argument does not apply (user-space spinlocks
have the same priority inversion problems as other user-space locking
constructs). Fact is, pretty much the only technique that currently enables
good determinism for userspace locks (such as futex-based pthread mutexes) is
priority inheritance:
Currently (without PI), if a high-prio and a low-prio task shares a lock [this
is a quite common scenario for most non-trivial RT applications], even if all
critical sections are coded carefully to be deterministic (i.e. all critical
sections are short in duration and only execute a limited number of
instructions), the kernel cannot guarantee any deterministic execution of the
high-prio task: any medium-priority task could preempt the low-prio task while
it holds the shared lock and executes the critical section, and could delay it
indefinitely.
Implementation:
---------------
As mentioned before, the userspace fastpath of PI-enabled pthread mutexes
involves no kernel work at all - they behave quite similarly to normal
futex-based locks: a 0 value means unlocked, and a value==TID means locked.
(This is the same method as used by list-based robust futexes.) Userspace uses
atomic ops to lock/unlock these mutexes without entering the kernel.
To handle the slowpath, we have added two new futex ops:
FUTEX_LOCK_PI
FUTEX_UNLOCK_PI
If the lock-acquire fastpath fails, [i.e. an atomic transition from 0 to TID
fails], then FUTEX_LOCK_PI is called. The kernel does all the remaining work:
if there is no futex-queue attached to the futex address yet then the code
looks up the task that owns the futex [it has put its own TID into the futex
value], and attaches a 'PI state' structure to the futex-queue. The pi_state
includes an rt-mutex, which is a PI-aware, kernel-based synchronization
object. The 'other' task is made the owner of the rt-mutex, and the
FUTEX_WAITERS bit is atomically set in the futex value. Then this task tries
to lock the rt-mutex, on which it blocks. Once it returns, it has the mutex
acquired, and it sets the futex value to its own TID and returns. Userspace
has no other work to perform - it now owns the lock, and futex value contains
FUTEX_WAITERS|TID.
If the unlock side fastpath succeeds, [i.e. userspace manages to do a TID ->
0 atomic transition of the futex value], then no kernel work is triggered.
If the unlock fastpath fails (because the FUTEX_WAITERS bit is set), then
FUTEX_UNLOCK_PI is called, and the kernel unlocks the futex on the behalf of
userspace - and it also unlocks the attached pi_state->rt_mutex and thus wakes
up any potential waiters.
Note that under this approach, contrary to other PI-futex approaches, there is
no prior 'registration' of a PI-futex. [which is not quite possible anyway,
due to existing ABI properties of pthread mutexes.]
Also, under this scheme, 'robustness' and 'PI' are two orthogonal properties
of futexes, and all four combinations are possible: futex, robust-futex,
PI-futex, robust+PI-futex.
glibc support:
--------------
Ulrich Drepper and Jakub Jelinek have written glibc support for PI-futexes
(and robust futexes), enabling robust and PI (PTHREAD_PRIO_INHERIT) POSIX
mutexes. (PTHREAD_PRIO_PROTECT support will be added later on too, no
additional kernel changes are needed for that). [NOTE: The glibc patch is
obviously inofficial and unsupported without matching upstream kernel
functionality.]
the patch-queue and the glibc patch can also be downloaded from:
http://redhat.com/~mingo/PI-futex-patches/
Many thanks go to the people who helped us create this kernel feature: Steven
Rostedt, Esben Nielsen, Benedikt Spranger, Daniel Walker, John Cooper, Arjan
van de Ven, Oleg Nesterov and others. Credits for related prior projects goes
to Dirk Grambow, Inaky Perez-Gonzalez, Bill Huey and many others.
Clean up the futex code, before adding more features to it:
- use u32 as the futex field type - that's the ABI
- use __user and pointers to u32 instead of unsigned long
- code style / comment style cleanups
- rename hash-bucket name from 'bh' to 'hb'.
I checked the pre and post futex.o object files to make sure this
patch has no code effects.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Ulrich Drepper <drepper@redhat.com>
Cc: Jakub Jelinek <jakub@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Extend the get_sb() filesystem operation to take an extra argument that
permits the VFS to pass in the target vfsmount that defines the mountpoint.
The filesystem is then required to manually set the superblock and root dentry
pointers. For most filesystems, this should be done with simple_set_mnt()
which will set the superblock pointer and then set the root dentry to the
superblock's s_root (as per the old default behaviour).
The get_sb() op now returns an integer as there's now no need to return the
superblock pointer.
This patch permits a superblock to be implicitly shared amongst several mount
points, such as can be done with NFS to avoid potential inode aliasing. In
such a case, simple_set_mnt() would not be called, and instead the mnt_root
and mnt_sb would be set directly.
The patch also makes the following changes:
(*) the get_sb_*() convenience functions in the core kernel now take a vfsmount
pointer argument and return an integer, so most filesystems have to change
very little.
(*) If one of the convenience function is not used, then get_sb() should
normally call simple_set_mnt() to instantiate the vfsmount. This will
always return 0, and so can be tail-called from get_sb().
(*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the
dcache upon superblock destruction rather than shrink_dcache_anon().
This is required because the superblock may now have multiple trees that
aren't actually bound to s_root, but that still need to be cleaned up. The
currently called functions assume that the whole tree is rooted at s_root,
and that anonymous dentries are not the roots of trees which results in
dentries being left unculled.
However, with the way NFS superblock sharing are currently set to be
implemented, these assumptions are violated: the root of the filesystem is
simply a dummy dentry and inode (the real inode for '/' may well be
inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries
with child trees.
[*] Anonymous until discovered from another tree.
(*) The documentation has been adjusted, including the additional bit of
changing ext2_* into foo_* in the documentation.
[akpm@osdl.org: convert ipath_fs, do other stuff]
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Nathan Scott <nathans@sgi.com>
Cc: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The futex timeval is not checked for correctness. The change does not
break existing applications as the timeval is supplied by glibc (and glibc
always passes a correct value), but the glibc-internal tests for this
functionality fail.
Signed-off-by: Thomas Gleixner <tglx@tglx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
- fix: initialize the robust list(s) to NULL in copy_process.
- doc update
- cleanup: rename _inuser to _inatomic
- __user cleanups and other small cleanups
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Ulrich Drepper <drepper@redhat.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add the core infrastructure for robust futexes: structure definitions, the new
syscalls and the do_exit() based cleanup mechanism.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Acked-by: Ulrich Drepper <drepper@redhat.com>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Make the futex code compilable and usable on NOMMU by making the attempt to
handle page faults conditional on CONFIG_MMU. If this is not enabled, then
we can assume that EFAULT returned from futex_atomic_op_inuser() is not
recoverable, and that the address lies outside of valid memory.
handle_mm_fault() is made to BUG if called on NOMMU without attempting to
invoke the actual handler (__handle_mm_fault).
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Fix a memory ordering problem that occurs on IA64. The "store" to q->lock_ptr
in wake_futex() can become visible before wake_up_all() clears the lock in the
futex_q.
Signed-off-by: Jack Steiner <steiner@sgi.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The follow_page changes in get_futex_key have left it with two almost
identical blocks, when handling the rare case of a futex in a nonlinear vma.
get_user_pages will itself do that follow_page, and its additional
find_extend_vma is hardly any overhead since the vma is already cached. Let's
just delete the follow_page block and let get_user_pages do it.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The code for FUTEX_WAKE_OP calls an arch callback,
futex_atomic_op_inuser(). That callback can return an error code, but
currently the caller assumes any error is EFAULT, and will try various
things to resolve the fault before eventually giving up with EFAULT
(regardless of the original error code). This is not a theoretical case -
arch callbacks currently return -ENOSYS if the opcode they are given is
bogus.
This patch alters the code to detect non-EFAULT errors and return them
directly to the user.
Of course, whether -ENOSYS is the correct return value for the bogus opcode
case, or whether EINVAL would be more appropriate is another question.
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jamie Lokier <jamie@shareable.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Final step in pushing down common core's page_table_lock. follow_page no
longer wants caller to hold page_table_lock, uses pte_offset_map_lock itself;
and so no page_table_lock is taken in get_user_pages itself.
But get_user_pages (and get_futex_key) do then need follow_page to pin the
page for them: take Daniel's suggestion of bitflags to follow_page.
Need one for WRITE, another for TOUCH (it was the accessed flag before:
vanished along with check_user_page_readable, but surely get_numa_maps is
wrong to mark every page it finds as accessed), another for GET.
And another, ANON to dispose of untouched_anonymous_page: it seems silly for
that to descend a second time, let follow_page observe if there was no page
table and return ZERO_PAGE if so. Fix minor bug in that: check VM_LOCKED -
make_pages_present ought to make readonly anonymous present.
Give get_numa_maps a cond_resched while we're there.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch cleans up the error path of futex_fd() by removing duplicate
code.
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ATM pthread_cond_signal is unnecessarily slow, because it wakes one waiter
(which at least on UP usually means an immediate context switch to one of
the waiter threads). This waiter wakes up and after a few instructions it
attempts to acquire the cv internal lock, but that lock is still held by
the thread calling pthread_cond_signal. So it goes to sleep and eventually
the signalling thread is scheduled in, unlocks the internal lock and wakes
the waiter again.
Now, before 2003-09-21 NPTL was using FUTEX_REQUEUE in pthread_cond_signal
to avoid this performance issue, but it was removed when locks were
redesigned to the 3 state scheme (unlocked, locked uncontended, locked
contended).
Following scenario shows why simply using FUTEX_REQUEUE in
pthread_cond_signal together with using lll_mutex_unlock_force in place of
lll_mutex_unlock is not enough and probably why it has been disabled at
that time:
The number is value in cv->__data.__lock.
thr1 thr2 thr3
0 pthread_cond_wait
1 lll_mutex_lock (cv->__data.__lock)
0 lll_mutex_unlock (cv->__data.__lock)
0 lll_futex_wait (&cv->__data.__futex, futexval)
0 pthread_cond_signal
1 lll_mutex_lock (cv->__data.__lock)
1 pthread_cond_signal
2 lll_mutex_lock (cv->__data.__lock)
2 lll_futex_wait (&cv->__data.__lock, 2)
2 lll_futex_requeue (&cv->__data.__futex, 0, 1, &cv->__data.__lock)
# FUTEX_REQUEUE, not FUTEX_CMP_REQUEUE
2 lll_mutex_unlock_force (cv->__data.__lock)
0 cv->__data.__lock = 0
0 lll_futex_wake (&cv->__data.__lock, 1)
1 lll_mutex_lock (cv->__data.__lock)
0 lll_mutex_unlock (cv->__data.__lock)
# Here, lll_mutex_unlock doesn't know there are threads waiting
# on the internal cv's lock
Now, I believe it is possible to use FUTEX_REQUEUE in pthread_cond_signal,
but it will cost us not one, but 2 extra syscalls and, what's worse, one of
these extra syscalls will be done for every single waiting loop in
pthread_cond_*wait.
We would need to use lll_mutex_unlock_force in pthread_cond_signal after
requeue and lll_mutex_cond_lock in pthread_cond_*wait after lll_futex_wait.
Another alternative is to do the unlocking pthread_cond_signal needs to do
(the lock can't be unlocked before lll_futex_wake, as that is racy) in the
kernel.
I have implemented both variants, futex-requeue-glibc.patch is the first
one and futex-wake_op{,-glibc}.patch is the unlocking inside of the kernel.
The kernel interface allows userland to specify how exactly an unlocking
operation should look like (some atomic arithmetic operation with optional
constant argument and comparison of the previous futex value with another
constant).
It has been implemented just for ppc*, x86_64 and i?86, for other
architectures I'm including just a stub header which can be used as a
starting point by maintainers to write support for their arches and ATM
will just return -ENOSYS for FUTEX_WAKE_OP. The requeue patch has been
(lightly) tested just on x86_64, the wake_op patch on ppc64 kernel running
32-bit and 64-bit NPTL and x86_64 kernel running 32-bit and 64-bit NPTL.
With the following benchmark on UP x86-64 I get:
for i in nptl-orig nptl-requeue nptl-wake_op; do echo time elf/ld.so --library-path .:$i /tmp/bench; \
for j in 1 2; do echo ( time elf/ld.so --library-path .:$i /tmp/bench ) 2>&1; done; done
time elf/ld.so --library-path .:nptl-orig /tmp/bench
real 0m0.655s user 0m0.253s sys 0m0.403s
real 0m0.657s user 0m0.269s sys 0m0.388s
time elf/ld.so --library-path .:nptl-requeue /tmp/bench
real 0m0.496s user 0m0.225s sys 0m0.271s
real 0m0.531s user 0m0.242s sys 0m0.288s
time elf/ld.so --library-path .:nptl-wake_op /tmp/bench
real 0m0.380s user 0m0.176s sys 0m0.204s
real 0m0.382s user 0m0.175s sys 0m0.207s
The benchmark is at:
http://sourceware.org/ml/libc-alpha/2005-03/txt00001.txt
Older futex-requeue-glibc.patch version is at:
http://sourceware.org/ml/libc-alpha/2005-03/txt00002.txt
Older futex-wake_op-glibc.patch version is at:
http://sourceware.org/ml/libc-alpha/2005-03/txt00003.txt
Will post a new version (just x86-64 fixes so that the patch
applies against pthread_cond_signal.S) to libc-hacker ml soon.
Attached is the kernel FUTEX_WAKE_OP patch as well as a simple-minded
testcase that will not test the atomicity of the operation, but at least
check if the threads that should have been woken up are woken up and
whether the arithmetic operation in the kernel gave the expected results.
Acked-by: Ingo Molnar <mingo@redhat.com>
Cc: Ulrich Drepper <drepper@redhat.com>
Cc: Jamie Lokier <jamie@shareable.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Yoichi Yuasa <yuasa@hh.iij4u.or.jp>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Convert most of the current code that uses _NSIG directly to instead use
valid_signal(). This avoids gcc -W warnings and off-by-one errors.
Signed-off-by: Jesper Juhl <juhl-lkml@dif.dk>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
