linux/arch/x86/kernel/paravirt-spinlocks.c

45 lines
1.1 KiB
C
Raw Normal View History

/*
* Split spinlock implementation out into its own file, so it can be
* compiled in a FTRACE-compatible way.
*/
#include <linux/spinlock.h>
#include <linux/export.h>
x86, ticketlock: Add slowpath logic 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>
2013-08-09 16:21:58 +02:00
#include <linux/jump_label.h>
#include <asm/paravirt.h>
locking/pvqspinlock, x86: Implement the paravirt qspinlock call patching We use the regular paravirt call patching to switch between: native_queued_spin_lock_slowpath() __pv_queued_spin_lock_slowpath() native_queued_spin_unlock() __pv_queued_spin_unlock() We use a callee saved call for the unlock function which reduces the i-cache footprint and allows 'inlining' of SPIN_UNLOCK functions again. We further optimize the unlock path by patching the direct call with a "movb $0,%arg1" if we are indeed using the native unlock code. This makes the unlock code almost as fast as the !PARAVIRT case. This significantly lowers the overhead of having CONFIG_PARAVIRT_SPINLOCKS enabled, even for native code. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> 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/1429901803-29771-10-git-send-email-Waiman.Long@hp.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-24 20:56:38 +02:00
__visible void __native_queued_spin_unlock(struct qspinlock *lock)
{
native_queued_spin_unlock(lock);
}
PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock);
bool pv_is_native_spin_unlock(void)
{
return pv_lock_ops.queued_spin_unlock.func ==
__raw_callee_save___native_queued_spin_unlock;
}
__visible bool __native_vcpu_is_preempted(long cpu)
{
return false;
}
PV_CALLEE_SAVE_REGS_THUNK(__native_vcpu_is_preempted);
bool pv_is_native_vcpu_is_preempted(void)
{
return pv_lock_ops.vcpu_is_preempted.func ==
__raw_callee_save___native_vcpu_is_preempted;
}
struct pv_lock_ops pv_lock_ops = {
#ifdef CONFIG_SMP
locking/pvqspinlock, x86: Implement the paravirt qspinlock call patching We use the regular paravirt call patching to switch between: native_queued_spin_lock_slowpath() __pv_queued_spin_lock_slowpath() native_queued_spin_unlock() __pv_queued_spin_unlock() We use a callee saved call for the unlock function which reduces the i-cache footprint and allows 'inlining' of SPIN_UNLOCK functions again. We further optimize the unlock path by patching the direct call with a "movb $0,%arg1" if we are indeed using the native unlock code. This makes the unlock code almost as fast as the !PARAVIRT case. This significantly lowers the overhead of having CONFIG_PARAVIRT_SPINLOCKS enabled, even for native code. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> 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/1429901803-29771-10-git-send-email-Waiman.Long@hp.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-24 20:56:38 +02:00
.queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
.queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock),
.wait = paravirt_nop,
.kick = paravirt_nop,
.vcpu_is_preempted = PV_CALLEE_SAVE(__native_vcpu_is_preempted),
locking/pvqspinlock, x86: Implement the paravirt qspinlock call patching We use the regular paravirt call patching to switch between: native_queued_spin_lock_slowpath() __pv_queued_spin_lock_slowpath() native_queued_spin_unlock() __pv_queued_spin_unlock() We use a callee saved call for the unlock function which reduces the i-cache footprint and allows 'inlining' of SPIN_UNLOCK functions again. We further optimize the unlock path by patching the direct call with a "movb $0,%arg1" if we are indeed using the native unlock code. This makes the unlock code almost as fast as the !PARAVIRT case. This significantly lowers the overhead of having CONFIG_PARAVIRT_SPINLOCKS enabled, even for native code. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> 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/1429901803-29771-10-git-send-email-Waiman.Long@hp.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-24 20:56:38 +02:00
#endif /* SMP */
};
EXPORT_SYMBOL(pv_lock_ops);