This patch introduces a new generic queued spinlock implementation that
can serve as an alternative to the default ticket spinlock. Compared
with the ticket spinlock, this queued spinlock should be almost as fair
as the ticket spinlock. It has about the same speed in single-thread
and it can be much faster in high contention situations especially when
the spinlock is embedded within the data structure to be protected.
Only in light to moderate contention where the average queue depth
is around 1-3 will this queued spinlock be potentially a bit slower
due to the higher slowpath overhead.
This queued spinlock is especially suit to NUMA machines with a large
number of cores as the chance of spinlock contention is much higher
in those machines. The cost of contention is also higher because of
slower inter-node memory traffic.
Due to the fact that spinlocks are acquired with preemption disabled,
the process will not be migrated to another CPU while it is trying
to get a spinlock. Ignoring interrupt handling, a CPU can only be
contending in one spinlock at any one time. Counting soft IRQ, hard
IRQ and NMI, a CPU can only have a maximum of 4 concurrent lock waiting
activities. By allocating a set of per-cpu queue nodes and used them
to form a waiting queue, we can encode the queue node address into a
much smaller 24-bit size (including CPU number and queue node index)
leaving one byte for the lock.
Please note that the queue node is only needed when waiting for the
lock. Once the lock is acquired, the queue node can be released to
be used later.
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Daniel J Blueman <daniel@numascale.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Douglas Hatch <doug.hatch@hp.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paolo Bonzini <paolo.bonzini@gmail.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: virtualization@lists.linux-foundation.org
Cc: xen-devel@lists.xenproject.org
Link: http://lkml.kernel.org/r/1429901803-29771-2-git-send-email-Waiman.Long@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
We have two flavors of the MCS spinlock: standard and cancelable (OSQ).
While each one is independent of the other, we currently mix and match
them. This patch:
- Moves the OSQ code out of mcs_spinlock.h (which only deals with the traditional
version) into include/linux/osq_lock.h. No unnecessary code is added to the
more global header file, anything locks that make use of OSQ must include
it anyway.
- Renames mcs_spinlock.c to osq_lock.c. This file only contains osq code.
- Introduces a CONFIG_LOCK_SPIN_ON_OWNER in order to only build osq_lock
if there is support for it.
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mikulas Patocka <mpatocka@redhat.com>
Cc: Waiman Long <Waiman.Long@hp.com>
Link: http://lkml.kernel.org/r/1420573509-24774-5-git-send-email-dave@stgolabs.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This rwlock uses the arch_spin_lock_t as a waitqueue, and assuming the
arch_spin_lock_t is a fair lock (ticket,mcs etc..) the resulting
rwlock is a fair lock.
It fits in the same 8 bytes as the regular rwlock_t by folding the
reader and writer count into a single integer, using the remaining 4
bytes for the arch_spinlock_t.
Architectures that can single-copy adress bytes can optimize
queue_write_unlock() with a 0 write to the LSB (the write count).
Performance as measured by Davidlohr Bueso (rwlock_t -> qrwlock_t):
+--------------+-------------+---------------+
| Workload | #users | delta |
+--------------+-------------+---------------+
| alltests | > 1400 | -4.83% |
| custom | 0-100,> 100 | +1.43%,-1.57% |
| high_systime | > 1000 | -2.61 |
| shared | all | +0.32 |
+--------------+-------------+---------------+
http://www.stgolabs.net/qrwlock-stuff/aim7-results-vs-rwsem_optsin/
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
[peterz: near complete rewrite]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: "Paul E.McKenney" <paulmck@linux.vnet.ibm.com>
Cc: linux-arch@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Link: http://lkml.kernel.org/n/tip-gac1nnl3wvs2ij87zv2xkdzq@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The Kconfig symbols ARCH_INLINE_READ_UNLOCK_IRQ,
ARCH_INLINE_SPIN_UNLOCK_IRQ, and ARCH_INLINE_WRITE_UNLOCK_IRQ were added
in v2.6.33, but have never actually been used. Ingo Molnar spotted that
this is caused by three identical copy/paste erros. Eg, the Kconfig
entry for
INLINE_READ_UNLOCK_IRQ
has an (optional) dependency on:
ARCH_INLINE_READ_UNLOCK_BH
were it apparently should depend on:
ARCH_INLINE_READ_UNLOCK_IRQ
instead. Likewise for the Kconfig entries for INLINE_SPIN_UNLOCK_IRQ and
INLINE_WRITE_UNLOCK_IRQ. Fix these three errors.
This never really caused any real problems as these symbols are set (or
unset) in a group - but it's worth fixing it nevertheless.
Reported-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1368780693.1350.228.camel@x61.thuisdomein
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Break out the DEBUG_SPINLOCK dependency (requires moving up
UNINLINE_SPIN_UNLOCK, as this was the only one in that block not
depending on that option).
Avoid putting values not selected into the resulting .config -
they are not useful for anything, make the output less legible,
and just consume space: Use "depends on" rather than directly
setting the default from the combined dependency values.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/504DF2AC020000780009A2DF@nat28.tlf.novell.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
commit 892a7c67 (locking: Allow arch-inlined spinlocks) implements the
selection of which lock functions are inlined based on defines in
arch/.../spinlock.h: #define __always_inline__LOCK_FUNCTION
Despite of the name __always_inline__* the lock functions can be built
out of line depending on config options. Also if the arch does not set
some inline defines the generic code might set them; again depending on
config options.
This makes it unnecessary hard to figure out when and which lock
functions are inlined. Aside of that it makes it way harder and
messier for -rt to manipulate the lock functions.
Convert the inlining decision to CONFIG switches. Each lock function
is inlined depending on CONFIG_INLINE_*. The configs implement the
existing dependencies. The architecture code can select ARCH_INLINE_*
to signal that it wants the corresponding lock function inlined.
ARCH_INLINE_* is necessary as Kconfig ignores "depends on"
restrictions when a config element is selected.
No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <20091109151428.504477141@linutronix.de>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Reviewed-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
