Valentin Rothberg reported that we use CONFIG_QUEUED_SPINLOCKS
in arch/x86/kernel/paravirt_patch_32.c, while the symbol is
called CONFIG_QUEUED_SPINLOCK. (Note the extra 'S')
But the typo was natural: the proper English term for such
a generic object would be 'queued spinlocks' - so rename
this and related symbols accordingly to the plural form.
Reported-by: Valentin Rothberg <valentinrothberg@gmail.com>
Cc: Douglas Hatch <doug.hatch@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <Waiman.Long@hp.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch makes the necessary changes at the x86 architecture
specific layer to enable the use of queued spinlocks for x86-64. As
x86-32 machines are typically not multi-socket. The benefit of queue
spinlock may not be apparent. So queued spinlocks are not enabled.
Currently, there is some incompatibilities between the para-virtualized
spinlock code (which hard-codes the use of ticket spinlock) and the
queued spinlocks. Therefore, the use of queued spinlocks is disabled
when the para-virtualized spinlock is enabled.
The arch/x86/include/asm/qspinlock.h header file includes some x86
specific optimization which will make the queueds spinlock code
perform better than the generic implementation.
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/1429901803-29771-3-git-send-email-Waiman.Long@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
A spinlock is regarded as contended when there is at least one waiter.
Currently, the code that checks whether there are any waiters rely on
tail value being greater than head. However, this is not true if tail
reaches the max value and wraps back to zero, so arch_spin_is_contended()
incorrectly returns 0 (not contended) when tail is smaller than head.
The original code (before regression) handled this case by casting the
(tail - head) to an unsigned value. This change simply restores that
behavior.
Fixes: d6abfdb202 ("x86/spinlocks/paravirt: Fix memory corruption on unlock")
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Cc: peterz@infradead.org
Cc: Waiman.Long@hp.com
Cc: borntraeger@de.ibm.com
Cc: oleg@redhat.com
Cc: raghavendra.kt@linux.vnet.ibm.com
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1430799331-20445-1-git-send-email-tahsin@google.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Paravirt spinlock clears slowpath flag after doing unlock.
As explained by Linus currently it does:
prev = *lock;
add_smp(&lock->tickets.head, TICKET_LOCK_INC);
/* add_smp() is a full mb() */
if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG))
__ticket_unlock_slowpath(lock, prev);
which is *exactly* the kind of things you cannot do with spinlocks,
because after you've done the "add_smp()" and released the spinlock
for the fast-path, you can't access the spinlock any more. Exactly
because a fast-path lock might come in, and release the whole data
structure.
Linus suggested that we should not do any writes to lock after unlock(),
and we can move slowpath clearing to fastpath lock.
So this patch implements the fix with:
1. Moving slowpath flag to head (Oleg):
Unlocked locks don't care about the slowpath flag; therefore we can keep
it set after the last unlock, and clear it again on the first (try)lock.
-- this removes the write after unlock. note that keeping slowpath flag would
result in unnecessary kicks.
By moving the slowpath flag from the tail to the head ticket we also avoid
the need to access both the head and tail tickets on unlock.
2. use xadd to avoid read/write after unlock that checks the need for
unlock_kick (Linus):
We further avoid the need for a read-after-release by using xadd;
the prev head value will include the slowpath flag and indicate if we
need to do PV kicking of suspended spinners -- on modern chips xadd
isn't (much) more expensive than an add + load.
Result:
setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
benchmark overcommit %improve
kernbench 1x -0.13
kernbench 2x 0.02
dbench 1x -1.77
dbench 2x -0.63
[Jeremy: Hinted missing TICKET_LOCK_INC for kick]
[Oleg: Moved slowpath flag to head, ticket_equals idea]
[PeterZ: Added detailed changelog]
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Cc: Andrew Jones <drjones@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jones <davej@redhat.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Waiman Long <Waiman.Long@hp.com>
Cc: a.ryabinin@samsung.com
Cc: dave@stgolabs.net
Cc: hpa@zytor.com
Cc: jasowang@redhat.com
Cc: jeremy@goop.org
Cc: paul.gortmaker@windriver.com
Cc: riel@redhat.com
Cc: tglx@linutronix.de
Cc: waiman.long@hp.com
Cc: xen-devel@lists.xenproject.org
Link: http://lkml.kernel.org/r/20150215173043.GA7471@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
As discussed on LKML http://marc.info/?i=54611D86.4040306%40de.ibm.com
ACCESS_ONCE might fail with specific compilers for non-scalar accesses.
Here is a set of patches to tackle that problem.
The first patch introduce READ_ONCE and ASSIGN_ONCE. If the data structure
is larger than the machine word size memcpy is used and a warning is emitted.
The next patches fix up several in-tree users of ACCESS_ONCE on non-scalar
types.
This merge does not yet contain a patch that forces ACCESS_ONCE to work only
on scalar types. This is targetted for the next merge window as Linux next
already contains new offenders regarding ACCESS_ONCE vs. non-scalar types.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.14 (GNU/Linux)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=IQ5o
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/borntraeger/linux
Pull ACCESS_ONCE cleanup preparation from Christian Borntraeger:
"kernel: Provide READ_ONCE and ASSIGN_ONCE
As discussed on LKML http://marc.info/?i=54611D86.4040306%40de.ibm.com
ACCESS_ONCE might fail with specific compilers for non-scalar
accesses.
Here is a set of patches to tackle that problem.
The first patch introduce READ_ONCE and ASSIGN_ONCE. If the data
structure is larger than the machine word size memcpy is used and a
warning is emitted. The next patches fix up several in-tree users of
ACCESS_ONCE on non-scalar types.
This does not yet contain a patch that forces ACCESS_ONCE to work only
on scalar types. This is targetted for the next merge window as Linux
next already contains new offenders regarding ACCESS_ONCE vs.
non-scalar types"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/borntraeger/linux:
s390/kvm: REPLACE barrier fixup with READ_ONCE
arm/spinlock: Replace ACCESS_ONCE with READ_ONCE
arm64/spinlock: Replace ACCESS_ONCE READ_ONCE
mips/gup: Replace ACCESS_ONCE with READ_ONCE
x86/gup: Replace ACCESS_ONCE with READ_ONCE
x86/spinlock: Replace ACCESS_ONCE with READ_ONCE
mm: replace ACCESS_ONCE with READ_ONCE or barriers
kernel: Provide READ_ONCE and ASSIGN_ONCE
ACCESS_ONCE does not work reliably on non-scalar types. For
example gcc 4.6 and 4.7 might remove the volatile tag for such
accesses during the SRA (scalar replacement of aggregates) step
(https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145)
Change the spinlock code to replace ACCESS_ONCE with READ_ONCE.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Pull locking tree changes from Ingo Molnar:
"Two changes: a documentation update and a ticket locks live lock fix"
* 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/ticketlock: Fix spin_unlock_wait() livelock
locking/lglocks: Add documentation of current lglocks implementation
arch_spin_unlock_wait() looks very suboptimal, to the point I
think this is just wrong and can lead to livelock: if the lock
is heavily contended we can never see head == tail.
But we do not need to wait for arch_spin_is_locked() == F. If it
is locked we only need to wait until the current owner drops
this lock. So we could simply spin until old_head !=
lock->tickets.head in this case, but .head can overflow and thus
we can't check "unlocked" only once before the main loop.
Also, the "unlocked" check can ignore TICKET_SLOWPATH_FLAG bit.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Paul E.McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Waiman Long <Waiman.Long@hp.com>
Link: http://lkml.kernel.org/r/20141201213417.GA5842@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
As the x86 architecture now uses qrwlock for its read/write lock
implementation, it is no longer necessary to keep the old rwlock code
around. This patch removes the old rwlock code in the asm/spinlock.h
and asm/spinlock_types.h files. Now the ARCH_USE_QUEUE_RWLOCK
config parameter cannot be removed from x86/Kconfig or there will be
a compilation error.
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Waiman Long <Waiman.Long@hp.com>
Link: http://lkml.kernel.org/r/1408037251-45918-2-git-send-email-Waiman.Long@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Make x86 use the fair rwlock_t.
Implement the custom queue_write_unlock() for best performance.
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
[peterz: near complete rewrite]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Dave Jones <davej@redhat.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: "Paul E.McKenney" <paulmck@linux.vnet.ibm.com>
Cc: linux-kernel@vger.kernel.org
Cc: x86@kernel.org
Link: http://lkml.kernel.org/n/tip-r1xuzmdysvuhl3h86n5fbxi7@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This was an optimization that made memcpy type benchmarks a little
faster on ancient (Circa 1998) IDT Winchip CPUs. In real-life
workloads, it wasn't even noticable, and I doubt anyone is running
benchmarks on 16 year old silicon any more.
Given this code has likely seen very little use over the last decade,
let's just remove it.
Signed-off-by: Dave Jones <davej@fedoraproject.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull x86 spinlock changes from Ingo Molnar:
"The biggest change here are paravirtualized ticket spinlocks (PV
spinlocks), which bring a nice speedup on various benchmarks.
The KVM host side will come to you via the KVM tree"
* 'x86-spinlocks-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/kvm/guest: Fix sparse warning: "symbol 'klock_waiting' was not declared as static"
kvm: Paravirtual ticketlocks support for linux guests running on KVM hypervisor
kvm guest: Add configuration support to enable debug information for KVM Guests
kvm uapi: Add KICK_CPU and PV_UNHALT definition to uapi
xen, pvticketlock: Allow interrupts to be enabled while blocking
x86, ticketlock: Add slowpath logic
jump_label: Split jumplabel ratelimit
x86, pvticketlock: When paravirtualizing ticket locks, increment by 2
x86, pvticketlock: Use callee-save for lock_spinning
xen, pvticketlocks: Add xen_nopvspin parameter to disable xen pv ticketlocks
xen, pvticketlock: Xen implementation for PV ticket locks
xen: Defer spinlock setup until boot CPU setup
x86, ticketlock: Collapse a layer of functions
x86, ticketlock: Don't inline _spin_unlock when using paravirt spinlocks
x86, spinlock: Replace pv spinlocks with pv ticketlocks
Instead of taking the spinlock, the lockless versions atomically check
that the lock is not taken, and do the reference count update using a
cmpxchg() loop. This is semantically identical to doing the reference
count update protected by the lock, but avoids the "wait for lock"
contention that you get when accesses to the reference count are
contended.
Note that a "lockref" is absolutely _not_ equivalent to an atomic_t.
Even when the lockref reference counts are updated atomically with
cmpxchg, the fact that they also verify the state of the spinlock means
that the lockless updates can never happen while somebody else holds the
spinlock.
So while "lockref_put_or_lock()" looks a lot like just another name for
"atomic_dec_and_lock()", and both optimize to lockless updates, they are
fundamentally different: the decrement done by atomic_dec_and_lock() is
truly independent of any lock (as long as it doesn't decrement to zero),
so a locked region can still see the count change.
The lockref structure, in contrast, really is a *locked* reference
count. If you hold the spinlock, the reference count will be stable and
you can modify the reference count without using atomics, because even
the lockless updates will see and respect the state of the lock.
In order to enable the cmpxchg lockless code, the architecture needs to
do three things:
(1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit
in an aligned u64, and have a "cmpxchg()" implementation that works
on such a u64 data type.
(2) define a helper function to test for a spinlock being unlocked
("arch_spin_value_unlocked()")
(3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its
Kconfig file.
This enables it for x86-64 (but not 32-bit, we'd need to make sure
cmpxchg() turns into the proper cmpxchg8b in order to enable it for
32-bit mode).
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This is only theoretical, but after try_to_wake_up(p) was changed
to check p->state under p->pi_lock the code like
__set_current_state(TASK_INTERRUPTIBLE);
schedule();
can miss a signal. This is the special case of wait-for-condition,
it relies on try_to_wake_up/schedule interaction and thus it does
not need mb() between __set_current_state() and if(signal_pending).
However, this __set_current_state() can move into the critical
section protected by rq->lock, now that try_to_wake_up() takes
another lock we need to ensure that it can't be reordered with
"if (signal_pending(current))" check inside that section.
The patch is actually one-liner, it simply adds smp_wmb() before
spin_lock_irq(rq->lock). This is what try_to_wake_up() already
does by the same reason.
We turn this wmb() into the new helper, smp_mb__before_spinlock(),
for better documentation and to allow the architectures to change
the default implementation.
While at it, kill smp_mb__after_lock(), it has no callers.
Perhaps we can also add smp_mb__before/after_spinunlock() for
prepare_to_wait().
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Maintain a flag in the LSB of the ticket lock tail which indicates
whether anyone is in the lock slowpath and may need kicking when
the current holder unlocks. The flags are set when the first locker
enters the slowpath, and cleared when unlocking to an empty queue (ie,
no contention).
In the specific implementation of lock_spinning(), make sure to set
the slowpath flags on the lock just before blocking. We must do
this before the last-chance pickup test to prevent a deadlock
with the unlocker:
Unlocker Locker
test for lock pickup
-> fail
unlock
test slowpath
-> false
set slowpath flags
block
Whereas this works in any ordering:
Unlocker Locker
set slowpath flags
test for lock pickup
-> fail
block
unlock
test slowpath
-> true, kick
If the unlocker finds that the lock has the slowpath flag set but it is
actually uncontended (ie, head == tail, so nobody is waiting), then it
clears the slowpath flag.
The unlock code uses a locked add to update the head counter. This also
acts as a full memory barrier so that its safe to subsequently
read back the slowflag state, knowing that the updated lock is visible
to the other CPUs. If it were an unlocked add, then the flag read may
just be forwarded from the store buffer before it was visible to the other
CPUs, which could result in a deadlock.
Unfortunately this means we need to do a locked instruction when
unlocking with PV ticketlocks. However, if PV ticketlocks are not
enabled, then the old non-locked "add" is the only unlocking code.
Note: this code relies on gcc making sure that unlikely() code is out of
line of the fastpath, which only happens when OPTIMIZE_SIZE=n. If it
doesn't the generated code isn't too bad, but its definitely suboptimal.
Thanks to Srivatsa Vaddagiri for providing a bugfix to the original
version of this change, which has been folded in.
Thanks to Stephan Diestelhorst for commenting on some code which relied
on an inaccurate reading of the x86 memory ordering rules.
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-11-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Stephan Diestelhorst <stephan.diestelhorst@amd.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Increment ticket head/tails by 2 rather than 1 to leave the LSB free
to store a "is in slowpath state" bit. This halves the number
of possible CPUs for a given ticket size, but this shouldn't matter
in practice - kernels built for 32k+ CPU systems are probably
specially built for the hardware rather than a generic distro
kernel.
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-9-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Attilio Rao <attilio.rao@citrix.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Now that the paravirtualization layer doesn't exist at the spinlock
level any more, we can collapse the __ticket_ functions into the arch_
functions.
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-4-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Attilio Rao <attilio.rao@citrix.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Rather than outright replacing the entire spinlock implementation in
order to paravirtualize it, keep the ticket lock implementation but add
a couple of pvops hooks on the slow patch (long spin on lock, unlocking
a contended lock).
Ticket locks have a number of nice properties, but they also have some
surprising behaviours in virtual environments. They enforce a strict
FIFO ordering on cpus trying to take a lock; however, if the hypervisor
scheduler does not schedule the cpus in the correct order, the system can
waste a huge amount of time spinning until the next cpu can take the lock.
(See Thomas Friebel's talk "Prevent Guests from Spinning Around"
http://www.xen.org/files/xensummitboston08/LHP.pdf for more details.)
To address this, we add two hooks:
- __ticket_spin_lock which is called after the cpu has been
spinning on the lock for a significant number of iterations but has
failed to take the lock (presumably because the cpu holding the lock
has been descheduled). The lock_spinning pvop is expected to block
the cpu until it has been kicked by the current lock holder.
- __ticket_spin_unlock, which on releasing a contended lock
(there are more cpus with tail tickets), it looks to see if the next
cpu is blocked and wakes it if so.
When compiled with CONFIG_PARAVIRT_SPINLOCKS disabled, a set of stub
functions causes all the extra code to go away.
Results:
=======
setup: 32 core machine with 32 vcpu KVM guest (HT off) with 8GB RAM
base = 3.11-rc
patched = base + pvspinlock V12
+-----------------+----------------+--------+
dbench (Throughput in MB/sec. Higher is better)
+-----------------+----------------+--------+
| base (stdev %)|patched(stdev%) | %gain |
+-----------------+----------------+--------+
| 15035.3 (0.3) |15150.0 (0.6) | 0.8 |
| 1470.0 (2.2) | 1713.7 (1.9) | 16.6 |
| 848.6 (4.3) | 967.8 (4.3) | 14.0 |
| 652.9 (3.5) | 685.3 (3.7) | 5.0 |
+-----------------+----------------+--------+
pvspinlock shows benefits for overcommit ratio > 1 for PLE enabled cases,
and undercommits results are flat
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-2-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Attilio Rao <attilio.rao@citrix.com>
[ Raghavendra: Changed SPIN_THRESHOLD, fixed redefinition of arch_spinlock_t]
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
This comment is no longer true. We support up to 2^16 CPUs
because __ticket_t is an u16 if NR_CPUS is larger than 256.
Signed-off-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The definition of it being questionable already (unnecessarily
including a cast), and it being used in a single place that can
be written shorter without it, remove this #define.
Along the same lines, simplify __ticket_spin_is_locked()'s main
expression, which was the more convoluted way because of needs
that went away with the recent type changes by Jeremy.
This is pure cleanup, no functional change intended.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/4F2C06020200007800071066@nat28.tlf.novell.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The note about partial registers is not really relevent now that we
rely on gcc to generate all the assembler.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Make trylock code common regardless of ticket size.
(Also, rename arch_spinlock.slock to head_tail.)
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Link: http://lkml.kernel.org/r/4E5BCC40.3030501@goop.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Convert the two variants of __ticket_spin_lock() to use xadd(), which
has the effect of making them identical, so remove the duplicate function.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Link: http://lkml.kernel.org/r/4E5BCC40.3030501@goop.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
The inner loop of __ticket_spin_lock isn't doing anything very special,
so reimplement it in C.
For the 8 bit ticket lock variant, we use a register union to get direct
access to the lower and upper bytes in the tickets, but unfortunately gcc
won't generate a direct comparison between the two halves of the register,
so the generated asm isn't quite as pretty as the hand-coded version.
However benchmarking shows that this is actually a small improvement in
runtime performance on some benchmarks, and never a slowdown.
We also need to make sure there's a barrier at the end of the lock loop
to make sure that the compiler doesn't move any instructions from within
the locked region into the region where we don't yet own the lock.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Link: http://lkml.kernel.org/r/4E5BCC40.3030501@goop.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
A few cleanups to the way spinlocks are defined and accessed:
- define __ticket_t which is the size of a spinlock ticket (ie, enough
bits to hold all the cpus)
- Define struct arch_spinlock as a union containing plain slock and
the head and tail tickets
- Use head and tail to implement some of the spinlock predicates.
- Make all ticket variables unsigned.
- Use TICKET_SHIFT to form constants
Most of this will be used in later patches.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Link: http://lkml.kernel.org/r/4E5BCC40.3030501@goop.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
This allows us to move duplicated code in <asm/atomic.h>
(atomic_inc_not_zero() for now) to <linux/atomic.h>
Signed-off-by: Arun Sharma <asharma@fb.com>
Reviewed-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: David Miller <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Mike Frysinger <vapier@gentoo.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
With the write lock path simply subtracting RW_LOCK_BIAS there
is, on large systems, the theoretical possibility of overflowing
the 32-bit value that was used so far (namely if 128 or more
CPUs manage to do the subtraction, but don't get to do the
inverse addition in the failure path quickly enough).
A first measure is to modify RW_LOCK_BIAS itself - with the new
value chosen, it is good for up to 2048 CPUs each allowed to
nest over 2048 times on the read path without causing an issue.
Quite possibly it would even be sufficient to adjust the bias a
little further, assuming that allowing for significantly less
nesting would suffice.
However, as the original value chosen allowed for even more
nesting levels, to support more than 2048 CPUs (possible
currently only for 64-bit kernels) the lock itself gets widened
to 64 bits.
Signed-off-by: Jan Beulich <jbeulich@novell.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/4E258E0D020000780004E3F0@nat28.tlf.novell.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Name space cleanup for rwlock functions. No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: linux-arch@vger.kernel.org
Not strictly necessary for -rt as -rt does not have non sleeping
rwlocks, but it's odd to not have a consistent naming convention.
No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: linux-arch@vger.kernel.org
Name space cleanup. No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: linux-arch@vger.kernel.org
The raw_spin* namespace was taken by lockdep for the architecture
specific implementations. raw_spin_* would be the ideal name space for
the spinlocks which are not converted to sleeping locks in preempt-rt.
Linus suggested to convert the raw_ to arch_ locks and cleanup the
name space instead of using an artifical name like core_spin,
atomic_spin or whatever
No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: linux-arch@vger.kernel.org
Adding smp_mb__after_lock define to be used as a smp_mb call after
a lock.
Making it nop for x86, since {read|write|spin}_lock() on x86 are
full memory barriers.
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Xiaohui Xin and some other folks at Intel have been looking into what's
behind the performance hit of paravirt_ops when running native.
It appears that the hit is entirely due to the paravirtualized
spinlocks introduced by:
| commit 8efcbab674
| Date: Mon Jul 7 12:07:51 2008 -0700
|
| paravirt: introduce a "lock-byte" spinlock implementation
The extra call/return in the spinlock path is somehow
causing an increase in the cycles/instruction of somewhere around 2-7%
(seems to vary quite a lot from test to test). The working theory is
that the CPU's pipeline is getting upset about the
call->call->locked-op->return->return, and seems to be failing to
speculate (though I haven't seen anything definitive about the precise
reasons). This doesn't entirely make sense, because the performance
hit is also visible on unlock and other operations which don't involve
locked instructions. But spinlock operations clearly swamp all the
other pvops operations, even though I can't imagine that they're
nearly as common (there's only a .05% increase in instructions
executed).
If I disable just the pv-spinlock calls, my tests show that pvops is
identical to non-pvops performance on native (my measurements show that
it is actually about .1% faster, but Xiaohui shows a .05% slowdown).
Summary of results, averaging 10 runs of the "mmperf" test, using a
no-pvops build as baseline:
nopv Pv-nospin Pv-spin
CPU cycles 100.00% 99.89% 102.18%
instructions 100.00% 100.10% 100.15%
CPI 100.00% 99.79% 102.03%
cache ref 100.00% 100.84% 100.28%
cache miss 100.00% 90.47% 88.56%
cache miss rate 100.00% 89.72% 88.31%
branches 100.00% 99.93% 100.04%
branch miss 100.00% 103.66% 107.72%
branch miss rt 100.00% 103.73% 107.67%
wallclock 100.00% 99.90% 102.20%
The clear effect here is that the 2% increase in CPI is
directly reflected in the final wallclock time.
(The other interesting effect is that the more ops are
out of line calls via pvops, the lower the cache access
and miss rates. Not too surprising, but it suggests that
the non-pvops kernel is over-inlined. On the flipside,
the branch misses go up correspondingly...)
So, what's the fix?
Paravirt patching turns all the pvops calls into direct calls, so
_spin_lock etc do end up having direct calls. For example, the compiler
generated code for paravirtualized _spin_lock is:
<_spin_lock+0>: mov %gs:0xb4c8,%rax
<_spin_lock+9>: incl 0xffffffffffffe044(%rax)
<_spin_lock+15>: callq *0xffffffff805a5b30
<_spin_lock+22>: retq
The indirect call will get patched to:
<_spin_lock+0>: mov %gs:0xb4c8,%rax
<_spin_lock+9>: incl 0xffffffffffffe044(%rax)
<_spin_lock+15>: callq <__ticket_spin_lock>
<_spin_lock+20>: nop; nop /* or whatever 2-byte nop */
<_spin_lock+22>: retq
One possibility is to inline _spin_lock, etc, when building an
optimised kernel (ie, when there's no spinlock/preempt
instrumentation/debugging enabled). That will remove the outer
call/return pair, returning the instruction stream to a single
call/return, which will presumably execute the same as the non-pvops
case. The downsides arel 1) it will replicate the
preempt_disable/enable code at eack lock/unlock callsite; this code is
fairly small, but not nothing; and 2) the spinlock definitions are
already a very heavily tangled mass of #ifdefs and other preprocessor
magic, and making any changes will be non-trivial.
The other obvious answer is to disable pv-spinlocks. Making them a
separate config option is fairly easy, and it would be trivial to
enable them only when Xen is enabled (as the only non-default user).
But it doesn't really address the common case of a distro build which
is going to have Xen support enabled, and leaves the open question of
whether the native performance cost of pv-spinlocks is worth the
performance improvement on a loaded Xen system (10% saving of overall
system CPU when guests block rather than spin). Still it is a
reasonable short-term workaround.
[ Impact: fix pvops performance regression when running native ]
Analysed-by: "Xin Xiaohui" <xiaohui.xin@intel.com>
Analysed-by: "Li Xin" <xin.li@intel.com>
Analysed-by: "Nakajima Jun" <jun.nakajima@intel.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Xen-devel <xen-devel@lists.xensource.com>
LKML-Reference: <4A0B62F7.5030802@goop.org>
[ fixed the help text ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Pass the original flags to rwlock arch-code, so that it can re-enable
interrupts if implemented for that architecture.
Initially, make __raw_read_lock_flags and __raw_write_lock_flags stubs
which just do the same thing as non-flags variants.
Signed-off-by: Petr Tesarik <ptesarik@suse.cz>
Signed-off-by: Robin Holt <holt@sgi.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: <linux-arch@vger.kernel.org>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: "Luck, Tony" <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Architectures other than mips and x86 are not using ticket spinlocks.
Therefore, the contention on the lock is meaningless, since there is
nobody known to be waiting on it (arguably /fairly/ unfair locks).
Dummy it out to return 0 on other architectures.
Signed-off-by: Kyle McMartin <kyle@redhat.com>
Acked-by: Ralf Baechle <ralf@linux-mips.org>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The current version of __raw_read_trylock starts with decrementing the lock
and read its new value as a separate operation after that.
That makes 3 dereferences (read, write (after sub), read) whereas
a single atomic_dec_return does only two pointers dereferences (read, write).
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: cleanup
Remove byte locks implementation, which was introduced by Jeremy in
8efcbab6 ("paravirt: introduce a "lock-byte" spinlock implementation"),
but turned out to be dead code that is not used by any in-kernel
virtualization guest (Xen uses its own variant of spinlocks implementation
and KVM is not planning to move to byte locks).
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Change header guards named "ASM_X86__*" to "_ASM_X86_*" since:
a. the double underscore is ugly and pointless.
b. no leading underscore violates namespace constraints.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
