search for: queue_code_xchg

...> + } > + /* > + * Nothing need to be done if the old value is > + * (_QSPINLOCK_WAITING | _QSPINLOCK_LOCKED). > + */ > + return 0; > +} > @@ -296,6 +478,9 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, int qsval) > return; > } > > +#ifdef queue_code_xchg > + prev_qcode = queue_code_xchg(lock, my_qcode); > +#else > /* > * Exchange current copy of the queue node code > */ > @@ -329,6 +514,7 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, int qsval) > } else > prev_qcode &= ~_QSPINLOCK_LOCKED; /* Clear...

...> + } > + /* > + * Nothing need to be done if the old value is > + * (_QSPINLOCK_WAITING | _QSPINLOCK_LOCKED). > + */ > + return 0; > +} > @@ -296,6 +478,9 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, int qsval) > return; > } > > +#ifdef queue_code_xchg > + prev_qcode = queue_code_xchg(lock, my_qcode); > +#else > /* > * Exchange current copy of the queue node code > */ > @@ -329,6 +514,7 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, int qsval) > } else > prev_qcode &= ~_QSPINLOCK_LOCKED; /* Clear...

...done if the old value is >> + * (_QSPINLOCK_WAITING | _QSPINLOCK_LOCKED). >> + */ >> + return 0; >> +} > > > >> @@ -296,6 +478,9 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, int qsval) >> return; >> } >> >> +#ifdef queue_code_xchg >> + prev_qcode = queue_code_xchg(lock, my_qcode); >> +#else >> /* >> * Exchange current copy of the queue node code >> */ >> @@ -329,6 +514,7 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, int qsval) >> } else >> prev_qcod...

...ady waiting while it steals the lock. + * A bit of unfairness here won't change the big picture. + * So just take the lock and return. + */ + return 1; + } + /* + * Nothing need to be done if the old value is + * (_QSPINLOCK_WAITING | _QSPINLOCK_LOCKED). + */ + return 0; +} + +#define queue_code_xchg queue_code_xchg +/** + * queue_code_xchg - exchange a queue code value + * @lock : Pointer to queue spinlock structure + * @qcode: New queue code to be exchanged + * Return: The original qcode value in the queue spinlock + */ +static inline u32 queue_code_xchg(struct qspinlock *lock, u32 qcode) +{...

...ady waiting while it steals the lock. + * A bit of unfairness here won't change the big picture. + * So just take the lock and return. + */ + return 1; + } + /* + * Nothing need to be done if the old value is + * (_QSPINLOCK_WAITING | _QSPINLOCK_LOCKED). + */ + return 0; +} + +#define queue_code_xchg queue_code_xchg +/** + * queue_code_xchg - exchange a queue code value + * @lock : Pointer to queue spinlock structure + * @qcode: New queue code to be exchanged + * Return: The original qcode value in the queue spinlock + */ +static inline u32 queue_code_xchg(struct qspinlock *lock, u32 qcode) +{...

...mp;qlock->lock_wait, _QSPINLOCK_LOCKED); + BUG_ON(lw != _QSPINLOCK_WAITING); + } + return 1; + } + return 0; +} + +/* + * With the qspinlock quickpath logic activated, disable the trylock logic + * in the slowpath as it will be redundant. + */ +#define queue_spin_trylock(lock) (0) #define queue_code_xchg queue_code_xchg /** @@ -131,13 +226,40 @@ static DEFINE_PER_CPU_ALIGNED(struct qnode_set, qnset) = { { { 0 } }, 0 }; * @lock : Pointer to queue spinlock structure * @ocode: Old queue code in the lock [OUT] * @ncode: New queue code to be exchanged - * Return: 0 is always returned + * Return:...

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

...node index + * Return : A qnode code that can be saved into the qspinlock structure + */ +static inline u32 queue_encode_qcode(u32 cpu_nr, u8 qn_idx) +{ + return ((cpu_nr + 1) << (_QCODE_VAL_OFFSET + 2)) | + (qn_idx << _QCODE_VAL_OFFSET); +} +#endif /* queue_encode_qcode */ + +#ifndef queue_code_xchg +/** + * queue_code_xchg - exchange a queue code value + * @lock : Pointer to queue spinlock structure + * @ocode: Old queue code in the lock [OUT] + * @ncode: New queue code to be exchanged + * Return: An enum exitval value + */ +static inline enum exitval +queue_code_xchg(struct qspinlock *lock,...

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.

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

N.B. Sorry for the duplicate. This patch series were resent as the original one was rejected by the vger.kernel.org list server due to long header. There is no change in content. 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

N.B. Sorry for the duplicate. This patch series were resent as the original one was rejected by the vger.kernel.org list server due to long header. There is no change in content. 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

...2934 5392 5 3736 3658 7696 6 4942 4434 9876 7 6304 5176 11901 8 7736 5955 14551 Below is the code that I used: static inline u32 queue_code_xchg(struct qspinlock *lock, u32 *ocode, u32 ncode) { while (true) { u32 qlcode = atomic_read(&lock->qlcode); if (qlcode == 0) { /* * Try to get the lock */...

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