search for: qn_idx

On 02/26, Waiman Long wrote: > > +void queue_spin_lock_slowpath(struct qspinlock *lock, int qsval) > +{ > + unsigned int cpu_nr, qn_idx; > + struct qnode *node, *next; > + u32 prev_qcode, my_qcode; > + > + /* > + * Get the queue node > + */ > + cpu_nr = smp_processor_id(); > + node = get_qnode(&qn_idx); > + > + /* > + * It should never happen that all the queue nodes are being used. > +...

On 02/26, Waiman Long wrote: > > +void queue_spin_lock_slowpath(struct qspinlock *lock, int qsval) > +{ > + unsigned int cpu_nr, qn_idx; > + struct qnode *node, *next; > + u32 prev_qcode, my_qcode; > + > + /* > + * Get the queue node > + */ > + cpu_nr = smp_processor_id(); > + node = get_qnode(&qn_idx); > + > + /* > + * It should never happen that all the queue nodes are being used. > +...

...*lock, u32 qcode) +{ + return atomic_cmpxchg(&lock->qlcode, qcode, _QSPINLOCK_LOCKED) == qcode; +} +#endif /* queue_spin_trylock_and_clr_qcode */ + +#ifndef queue_encode_qcode +/** + * queue_encode_qcode - Encode the CPU number & node index into a qnode code + * @cpu_nr: CPU number + * @qn_idx: Queue node index + * Return : A qnode code that can be saved into the qspinlock structure + * + * The lock bit is set in the encoded 32-bit value as the need to encode + * a qnode means that the lock should have been taken. + */ +static u32 queue_encode_qcode(u32 cpu_nr, u8 qn_idx) +{ + return ((c...

...*lock, u32 qcode) +{ + return atomic_cmpxchg(&lock->qlcode, qcode, _QSPINLOCK_LOCKED) == qcode; +} +#endif /* queue_spin_trylock_and_clr_qcode */ + +#ifndef queue_encode_qcode +/** + * queue_encode_qcode - Encode the CPU number & node index into a qnode code + * @cpu_nr: CPU number + * @qn_idx: Queue node index + * Return : A qnode code that can be saved into the qspinlock structure + * + * The lock bit is set in the encoded 32-bit value as the need to encode + * a qnode means that the lock should have been taken. + */ +static u32 queue_encode_qcode(u32 cpu_nr, u8 qn_idx) +{ + return ((c...

...lock *lock, u32 qcode) +{ + return atomic_cmpxchg(&lock->qlcode, qcode, _QLOCK_LOCKED) == qcode; +} +#endif /* queue_spin_trylock_and_clr_qcode */ + +#ifndef queue_encode_qcode +/** + * queue_encode_qcode - Encode the CPU number & node index into a qnode code + * @cpu_nr: CPU number + * @qn_idx: Queue 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 */ + +#...

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

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

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

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

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.

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

...rs pv; /* Para-virtualization */ struct qnode *next; /* Next queue node addr */ }; +#define PV_OFFSET offsetof(struct qnode, pv) struct qnode_set { struct qnode nodes[MAX_QNODES]; @@ -441,6 +459,7 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, int qsval) unsigned int cpu_nr, qn_idx; struct qnode *node, *next; u32 prev_qcode, my_qcode; + PV_SET_VAR(int, hcnt, 0); /* * Try the quick spinning code path @@ -468,6 +487,7 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, int qsval) */ node->wait = true; node->next = NULL; + pv_init_vars(&node->...

...e_get_qcode(lock) (atomic_read(&(lock)->qlcode) &\ + ~_QSPINLOCK_LOCKED) +#endif + #ifndef queue_get_lock_qcode /** * queue_get_lock_qcode - get the lock & qcode values @@ -496,6 +527,7 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, int qsval) unsigned int cpu_nr, qn_idx; struct qnode *node, *next; u32 prev_qcode, my_qcode; + PV_SET_VAR(int, hcnt, 0); /* * Try the quick spinning code path @@ -523,6 +555,7 @@ void queue_spin_lock_slowpath(struct qspinlock *lock, int qsval) */ node->wait = true; node->next = NULL; + pv_init_vars(&node->...