search for: __queue_kick_cpu

...rch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -711,7 +711,12 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, } #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS) - +#ifdef CONFIG_QUEUE_SPINLOCK +static __always_inline void __queue_kick_cpu(int cpu, enum pv_kick_type type) +{ + PVOP_VCALL2(pv_lock_ops.kick_cpu, cpu, type); +} +#else static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, __ticket_t ticket) { @@ -723,7 +728,7 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock...

.../arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -711,7 +711,17 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, } #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS) +#ifdef CONFIG_QUEUE_SPINLOCK +static __always_inline void __queue_kick_cpu(int cpu, enum pv_kick_type type) +{ + PVOP_VCALL2(pv_lock_ops.kick_cpu, cpu, type); +} +static __always_inline void __queue_hibernate(void) +{ + PVOP_VCALL0(pv_lock_ops.hibernate); +} +#else static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, __ticket_t ticket)...

On 12/03/14 18:54, Waiman Long wrote: > This patch adds para-virtualization support to the queue spinlock in > the same way as was done in the PV ticket lock code. In essence, the > lock waiters will spin for a specified number of times (QSPIN_THRESHOLD > = 2^14) and then halted itself. The queue head waiter will spins > 2*QSPIN_THRESHOLD times before halting itself. When it has

On 12/03/14 18:54, Waiman Long wrote: > This patch adds para-virtualization support to the queue spinlock in > the same way as was done in the PV ticket lock code. In essence, the > lock waiters will spin for a specified number of times (QSPIN_THRESHOLD > = 2^14) and then halted itself. The queue head waiter will spins > 2*QSPIN_THRESHOLD times before halting itself. When it has

...? More important, I think a barrier is missing: Lock holder --------------------------------------- // queue_spin_unlock barrier(); ACCESS_ONCE(qlock->lock) = 0; barrier(); // pv_kick_node: if (pv->cpustate != PV_CPU_HALTED) return; ACCESS_ONCE(pv->cpustate) = PV_CPU_KICKED; __queue_kick_cpu(pv->mycpu, PV_KICK_QUEUE_HEAD); Waiter ------------------------------------------- // pv_head_spin_check ACCESS_ONCE(pv->cpustate) = PV_CPU_HALTED; lockval = cmpxchg(&qlock->lock, _QSPINLOCK_LOCKED, _QSPINLOCK_LOCKED_SLOWPATH); if (lockval == 0) { /* * Ca...

...else queue_spin_unlock_slowpath(lock); } else { __queue_spin_unlock(lock); } > // pv_kick_node: > if (pv->cpustate != PV_CPU_HALTED) > return; > ACCESS_ONCE(pv->cpustate) = PV_CPU_KICKED; > __queue_kick_cpu(pv->mycpu, PV_KICK_QUEUE_HEAD); > > Waiter ------------------------------------------- > > // pv_head_spin_check > ACCESS_ONCE(pv->cpustate) = PV_CPU_HALTED; > lockval = cmpxchg(&qlock->lock, > _QSPINLOCK_LOCKED, &g...

...else queue_spin_unlock_slowpath(lock); } else { __queue_spin_unlock(lock); } > // pv_kick_node: > if (pv->cpustate != PV_CPU_HALTED) > return; > ACCESS_ONCE(pv->cpustate) = PV_CPU_KICKED; > __queue_kick_cpu(pv->mycpu, PV_KICK_QUEUE_HEAD); > > Waiter ------------------------------------------- > > // pv_head_spin_check > ACCESS_ONCE(pv->cpustate) = PV_CPU_HALTED; > lockval = cmpxchg(&qlock->lock, > _QSPINLOCK_LOCKED, &g...

v4->v5: - Move the optimized 2-task contending code to the generic file to enable more architectures to use it without code duplication. - Address some of the style-related comments by PeterZ. - Allow the use of unfair queue spinlock in a real para-virtualized execution environment. - Add para-virtualization support to the qspinlock code by ensuring that the lock holder and queue

v4->v5: - Move the optimized 2-task contending code to the generic file to enable more architectures to use it without code duplication. - Address some of the style-related comments by PeterZ. - Allow the use of unfair queue spinlock in a real para-virtualized execution environment. - Add para-virtualization support to the qspinlock code by ensuring that the lock holder and queue

v4->v5: - Move the optimized 2-task contending code to the generic file to enable more architectures to use it without code duplication. - Address some of the style-related comments by PeterZ. - Allow the use of unfair queue spinlock in a real para-virtualized execution environment. - Add para-virtualization support to the qspinlock code by ensuring that the lock holder and queue

v4->v5: - Move the optimized 2-task contending code to the generic file to enable more architectures to use it without code duplication. - Address some of the style-related comments by PeterZ. - Allow the use of unfair queue spinlock in a real para-virtualized execution environment. - Add para-virtualization support to the qspinlock code by ensuring that the lock holder and queue

...k_node(struct mcs_spinlock *mcs) +{ + struct pv_qnode *pv = (struct pv_qnode *)mcs; + s8 oldstate = xchg(&pv->cpustate, PV_CPU_KICKED); + + /* + * Kick up the CPU only if the state was set to PV_CPU_HALTED + */ + if (oldstate != PV_CPU_HALTED) + __queue_lockstat(PV_KICK_NOHALT); + else + __queue_kick_cpu(pv->mycpu); +} + +#endif /* _ASM_X86_PVQSPINLOCK_H */ diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index 448de8b..5ddc456 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -19,13 +19,46 @@ extern struct static_key virt_unf...

v5->v6: - Change the optimized 2-task contending code to make it fairer at the expense of a bit of performance. - Add a patch to support unfair queue spinlock for Xen. - Modify the PV qspinlock code to follow what was done in the PV ticketlock. - Add performance data for the unfair lock as well as the PV support code. v4->v5: - Move the optimized 2-task contending code to the

v5->v6: - Change the optimized 2-task contending code to make it fairer at the expense of a bit of performance. - Add a patch to support unfair queue spinlock for Xen. - Modify the PV qspinlock code to follow what was done in the PV ticketlock. - Add performance data for the unfair lock as well as the PV support code. v4->v5: - Move the optimized 2-task contending code to the

v6->v7: - Remove an atomic operation from the 2-task contending code - Shorten the names of some macros - Make the queue waiter to attempt to steal lock when unfair lock is enabled. - Remove lock holder kick from the PV code and fix a race condition - Run the unfair lock & PV code on overcommitted KVM guests to collect performance data. v5->v6: - Change the optimized

v6->v7: - Remove an atomic operation from the 2-task contending code - Shorten the names of some macros - Make the queue waiter to attempt to steal lock when unfair lock is enabled. - Remove lock holder kick from the PV code and fix a race condition - Run the unfair lock & PV code on overcommitted KVM guests to collect performance data. v5->v6: - Change the optimized

v10->v11: - Use a simple test-and-set unfair lock to simplify the code, but performance may suffer a bit for large guest with many CPUs. - Take out Raghavendra KT's test results as the unfair lock changes may render some of his results invalid. - Add PV support without increasing the size of the core queue node structure. - Other minor changes to address some of the

v10->v11: - Use a simple test-and-set unfair lock to simplify the code, but performance may suffer a bit for large guest with many CPUs. - Take out Raghavendra KT's test results as the unfair lock changes may render some of his results invalid. - Add PV support without increasing the size of the core queue node structure. - Other minor changes to address some of the

v7->v8: - Remove one unneeded atomic operation from the slowpath, thus improving performance. - Simplify some of the codes and add more comments. - Test for X86_FEATURE_HYPERVISOR CPU feature bit to enable/disable unfair lock. - Reduce unfair lock slowpath lock stealing frequency depending on its distance from the queue head. - Add performance data for IvyBridge-EX CPU.

v7->v8: - Remove one unneeded atomic operation from the slowpath, thus improving performance. - Simplify some of the codes and add more comments. - Test for X86_FEATURE_HYPERVISOR CPU feature bit to enable/disable unfair lock. - Reduce unfair lock slowpath lock stealing frequency depending on its distance from the queue head. - Add performance data for IvyBridge-EX CPU.