search for: spin_threshold

...sq_lock, rwsem_spin_on_owner and mutex_spin_on_owner. >> These spin_on_onwer variant also cause rcu stall before we apply this patch set >> > Paolo, could you help out with an (x86) KVM interface for this? > > Waiman, could you see if you can utilize this to get rid of the > SPIN_THRESHOLD in qspinlock_paravirt? That API is certainly useful to make the paravirt spinlock perform better. However, I am not sure if we can completely get rid of the SPIN_THRESHOLD at this point. It is not just the kvm, the xen code need to be modified as well. Cheers, Longman

...sq_lock, rwsem_spin_on_owner and mutex_spin_on_owner. >> These spin_on_onwer variant also cause rcu stall before we apply this patch set >> > Paolo, could you help out with an (x86) KVM interface for this? > > Waiman, could you see if you can utilize this to get rid of the > SPIN_THRESHOLD in qspinlock_paravirt? That API is certainly useful to make the paravirt spinlock perform better. However, I am not sure if we can completely get rid of the SPIN_THRESHOLD at this point. It is not just the kvm, the xen code need to be modified as well. Cheers, Longman

...x_spin_on_owner. >>> These spin_on_onwer variant also cause rcu stall before we apply this >>> patch set >>> >> Paolo, could you help out with an (x86) KVM interface for this? >> >> Waiman, could you see if you can utilize this to get rid of the >> SPIN_THRESHOLD in qspinlock_paravirt? > > That API is certainly useful to make the paravirt spinlock perform > better. However, I am not sure if we can completely get rid of the > SPIN_THRESHOLD at this point. It is not just the kvm, the xen code need > to be modified as well. This should be rath...

...x 9b4ac3d..41ee033 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -19,7 +19,8 @@ * native_queue_spin_unlock(). */ -#define _Q_SLOW_VAL (3U << _Q_LOCKED_OFFSET) +#define _Q_SLOW_VAL (3U << _Q_LOCKED_OFFSET) +#define MAYHALT_THRESHOLD (SPIN_THRESHOLD >> 4) /* * The vcpu_hashed is a special state that is set by the new lock holder on @@ -39,6 +40,7 @@ struct pv_node { int cpu; u8 state; + u8 mayhalt; }; /* @@ -198,6 +200,7 @@ static void pv_init_node(struct mcs_spinlock *node) pn->cpu = smp_processor_id(); pn-...

This series replaces the existing paravirtualized spinlock mechanism with a paravirtualized ticketlock mechanism. The series provides implementation for both Xen and KVM. Changes in V9: - Changed spin_threshold to 32k to avoid excess halt exits that are causing undercommit degradation (after PLE handler improvement). - Added kvm_irq_delivery_to_apic (suggested by Gleb) - Optimized halt exit path to use PLE handler V8 of PVspinlock was posted last year. After Avi's suggestions to look at PLE handl...

This series replaces the existing paravirtualized spinlock mechanism with a paravirtualized ticketlock mechanism. The series provides implementation for both Xen and KVM. Changes in V9: - Changed spin_threshold to 32k to avoid excess halt exits that are causing undercommit degradation (after PLE handler improvement). - Added kvm_irq_delivery_to_apic (suggested by Gleb) - Optimized halt exit path to use PLE handler V8 of PVspinlock was posted last year. After Avi's suggestions to look at PLE handl...

This series replaces the existing paravirtualized spinlock mechanism with a paravirtualized ticketlock mechanism. The series provides implementation for both Xen and KVM. Changes in V9: - Changed spin_threshold to 32k to avoid excess halt exits that are causing undercommit degradation (after PLE handler improvement). - Added kvm_irq_delivery_to_apic (suggested by Gleb) - Optimized halt exit path to use PLE handler V8 of PVspinlock was posted last year. After Avi's suggestions to look at PLE handl...

change fomr v1: a simplier definition of default vcpu_is_preempted skip mahcine type check on ppc, and add config. remove dedicated macro. add one patch to drop overload of rwsem_spin_on_owner and mutex_spin_on_owner. add more comments thanks boqun and Peter's suggestion. This patch set aims to fix lock holder preemption issues. test-case: perf record -a perf bench sched messaging -g

change fomr v1: a simplier definition of default vcpu_is_preempted skip mahcine type check on ppc, and add config. remove dedicated macro. add one patch to drop overload of rwsem_spin_on_owner and mutex_spin_on_owner. add more comments thanks boqun and Peter's suggestion. This patch set aims to fix lock holder preemption issues. test-case: perf record -a perf bench sched messaging -g

...>>+{ > >>+ struct __qspinlock *l = (void *)lock; > >>+ struct qspinlock **lp = NULL; > >>+ struct pv_node *pn = (struct pv_node *)node; > >>+ int slow_set = false; > >>+ int loop; > >>+ > >>+ for (;;) { > >>+ for (loop = SPIN_THRESHOLD; loop; loop--) { > >>+ if (!READ_ONCE(l->locked)) > >>+ return; > >>+ > >>+ cpu_relax(); > >>+ } > >>+ > >>+ WRITE_ONCE(pn->state, vcpu_halted); > >>+ if (!lp) > >>+ lp = pv_hash(lock, pn); > >&...

...>>+{ > >>+ struct __qspinlock *l = (void *)lock; > >>+ struct qspinlock **lp = NULL; > >>+ struct pv_node *pn = (struct pv_node *)node; > >>+ int slow_set = false; > >>+ int loop; > >>+ > >>+ for (;;) { > >>+ for (loop = SPIN_THRESHOLD; loop; loop--) { > >>+ if (!READ_ONCE(l->locked)) > >>+ return; > >>+ > >>+ cpu_relax(); > >>+ } > >>+ > >>+ WRITE_ONCE(pn->state, vcpu_halted); > >>+ if (!lp) > >>+ lp = pv_hash(lock, pn); > >&...

...u_running; +} + +/* + * Wait for node->locked to become true, halt the vcpu after a short spin. + * pv_kick_node() is used to wake the vcpu again. + */ +static void pv_wait_node(struct mcs_spinlock *node) +{ + struct pv_node *pn = (struct pv_node *)node; + int loop; + + for (;;) { + for (loop = SPIN_THRESHOLD; loop; loop--) { + if (READ_ONCE(node->locked)) + return; + cpu_relax(); + } + + /* + * Order pn->state vs pn->locked thusly: + * + * [S] pn->state = vcpu_halted [S] next->locked = 1 + * MB MB + * [L] pn->locked [RmW] pn->state = vcpu_running +...

...- Added break in patch 5 since now we know exact cpu to wakeup - Dropped patch 12 and Konrad needs to revert two patches to enable xen on hvm 70dd4998, f10cd522c - Remove TIMEOUT and corrected spacing in patch 15 - Kicked spelling and correct spacing in patches 17, 18 Changes in V9: - Changed spin_threshold to 32k to avoid excess halt exits that are causing undercommit degradation (after PLE handler improvement). - Added kvm_irq_delivery_to_apic (suggested by Gleb) - Optimized halt exit path to use PLE handler V8 of PVspinlock was posted last year. After Avi''s suggestions to look at PLE...

...- Added break in patch 5 since now we know exact cpu to wakeup - Dropped patch 12 and Konrad needs to revert two patches to enable xen on hvm 70dd4998, f10cd522c - Remove TIMEOUT and corrected spacing in patch 15 - Kicked spelling and correct spacing in patches 17, 18 Changes in V9: - Changed spin_threshold to 32k to avoid excess halt exits that are causing undercommit degradation (after PLE handler improvement). - Added kvm_irq_delivery_to_apic (suggested by Gleb) - Optimized halt exit path to use PLE handler V8 of PVspinlock was posted last year. After Avi''s suggestions to look at PLE...

...- Added break in patch 5 since now we know exact cpu to wakeup - Dropped patch 12 and Konrad needs to revert two patches to enable xen on hvm 70dd4998, f10cd522c - Remove TIMEOUT and corrected spacing in patch 15 - Kicked spelling and correct spacing in patches 17, 18 Changes in V9: - Changed spin_threshold to 32k to avoid excess halt exits that are causing undercommit degradation (after PLE handler improvement). - Added kvm_irq_delivery_to_apic (suggested by Gleb) - Optimized halt exit path to use PLE handler V8 of PVspinlock was posted last year. After Avi''s suggestions to look at PLE...

...t; new file mode 100644 > index 0000000..fc83cd2 > --- /dev/null > +++ b/arch/powerpc/include/asm/qspinlock.h > @@ -0,0 +1,26 @@ > +#ifndef _ASM_POWERPC_QSPINLOCK_H > +#define _ASM_POWERPC_QSPINLOCK_H > + > +#include <asm-generic/qspinlock_types.h> > + > +#define SPIN_THRESHOLD (1 << 15) > +#define queued_spin_unlock queued_spin_unlock > + > +static inline void native_queued_spin_unlock(struct qspinlock *lock) > +{ > + u8 *locked = (u8 *)lock; > +#ifdef __BIG_ENDIAN > + locked += 3; > +#endif > + /* no load/store can be across the unlock()...

...t; new file mode 100644 > index 0000000..fc83cd2 > --- /dev/null > +++ b/arch/powerpc/include/asm/qspinlock.h > @@ -0,0 +1,26 @@ > +#ifndef _ASM_POWERPC_QSPINLOCK_H > +#define _ASM_POWERPC_QSPINLOCK_H > + > +#include <asm-generic/qspinlock_types.h> > + > +#define SPIN_THRESHOLD (1 << 15) > +#define queued_spin_unlock queued_spin_unlock > + > +static inline void native_queued_spin_unlock(struct qspinlock *lock) > +{ > + u8 *locked = (u8 *)lock; > +#ifdef __BIG_ENDIAN > + locked += 3; > +#endif > + /* no load/store can be across the unlock()...

...truct mcs_spinlock *node) +static void pv_wait_node(u32 old, struct mcs_spinlock *node) { + struct pv_node *ppn = pv_decode_tail(old); struct pv_node *pn = (struct pv_node *)node; int loop; + pv_propagate_head(pn, ppn); + for (;;) { for (loop = SPIN_THRESHOLD; loop; loop--) { if (READ_ONCE(node->locked)) @@ -107,13 +145,33 @@ static void pv_kick_node(struct mcs_spin pv_kick(pn->cpu); } -static DEFINE_PER_CPU(struct qspinlock *, __pv_lock_wait); +static void pv_set_head(struct qspinlock *lock, struct pv_no...

...truct mcs_spinlock *node) +static void pv_wait_node(u32 old, struct mcs_spinlock *node) { + struct pv_node *ppn = pv_decode_tail(old); struct pv_node *pn = (struct pv_node *)node; int loop; + pv_propagate_head(pn, ppn); + for (;;) { for (loop = SPIN_THRESHOLD; loop; loop--) { if (READ_ONCE(node->locked)) @@ -107,13 +145,33 @@ static void pv_kick_node(struct mcs_spin pv_kick(pn->cpu); } -static DEFINE_PER_CPU(struct qspinlock *, __pv_lock_wait); +static void pv_set_head(struct qspinlock *lock, struct pv_no...

...u_running; +} + +/* + * Wait for node->locked to become true, halt the vcpu after a short spin. + * pv_kick_node() is used to wake the vcpu again. + */ +static void pv_wait_node(struct mcs_spinlock *node) +{ + struct pv_node *pn = (struct pv_node *)node; + int loop; + + for (;;) { + for (loop = SPIN_THRESHOLD; loop; loop--) { + if (READ_ONCE(node->locked)) + goto done; + + cpu_relax(); + } + + /* + * Order pn->state vs pn->locked thusly: + * + * [S] pn->state = vcpu_halted [S] next->locked = 1 + * MB MB + * [L] pn->locked [RmW] pn->state = vcpu_runn...