search for: _q_tail_offset

...e _Q_PENDING_BITS 1 +#endif #define _Q_PENDING_MASK _Q_SET_MASK(PENDING) #define _Q_TAIL_IDX_OFFSET (_Q_PENDING_OFFSET + _Q_PENDING_BITS) @@ -61,6 +73,7 @@ typedef struct qspinlock { #define _Q_TAIL_CPU_BITS (32 - _Q_TAIL_CPU_OFFSET) #define _Q_TAIL_CPU_MASK _Q_SET_MASK(TAIL_CPU) +#define _Q_TAIL_OFFSET _Q_TAIL_IDX_OFFSET #define _Q_TAIL_MASK (_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK) #define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET) --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -22,6 +22,7 @@ #include <linux/percpu.h> #include <linux/hardirq.h> #include...

...e _Q_PENDING_BITS 1 +#endif #define _Q_PENDING_MASK _Q_SET_MASK(PENDING) #define _Q_TAIL_IDX_OFFSET (_Q_PENDING_OFFSET + _Q_PENDING_BITS) @@ -61,6 +73,7 @@ typedef struct qspinlock { #define _Q_TAIL_CPU_BITS (32 - _Q_TAIL_CPU_OFFSET) #define _Q_TAIL_CPU_MASK _Q_SET_MASK(TAIL_CPU) +#define _Q_TAIL_OFFSET _Q_TAIL_IDX_OFFSET #define _Q_TAIL_MASK (_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK) #define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET) diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index fcf06cb..55601b4 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinloc...

...ail(struct qspinlock *lock, u32 tail, u32 newtail) +// API-incompatible with set_pending and the shifting is ugly, so I'd rather +// refactor this one, xchg_tail() and encode_tail() ... another day +{ + struct __qspinlock *l = (void *)lock; + + return (u32)cmpxchg(&l->tail, tail >> _Q_TAIL_OFFSET, + newtail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET; +} + /** * queue_spin_lock_slowpath - acquire the queue spinlock * @lock: Pointer to queue spinlock structure @@ -324,21 +381,21 @@ static inline int trylock_pending(struct qspinlock *lock, u32 *pval) *...

...ne _Q_PENDING_MASK _Q_SET_MASK(PENDING) > > #define _Q_TAIL_IDX_OFFSET (_Q_PENDING_OFFSET + _Q_PENDING_BITS) > @@ -61,6 +73,7 @@ typedef struct qspinlock { > #define _Q_TAIL_CPU_BITS (32 - _Q_TAIL_CPU_OFFSET) > #define _Q_TAIL_CPU_MASK _Q_SET_MASK(TAIL_CPU) > > +#define _Q_TAIL_OFFSET _Q_TAIL_IDX_OFFSET > #define _Q_TAIL_MASK (_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK) > > #define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET) > --- a/kernel/locking/qspinlock.c > +++ b/kernel/locking/qspinlock.c > @@ -22,6 +22,7 @@ > #include <linux/percpu.h> > #in...

...ne _Q_PENDING_MASK _Q_SET_MASK(PENDING) > > #define _Q_TAIL_IDX_OFFSET (_Q_PENDING_OFFSET + _Q_PENDING_BITS) > @@ -61,6 +73,7 @@ typedef struct qspinlock { > #define _Q_TAIL_CPU_BITS (32 - _Q_TAIL_CPU_OFFSET) > #define _Q_TAIL_CPU_MASK _Q_SET_MASK(TAIL_CPU) > > +#define _Q_TAIL_OFFSET _Q_TAIL_IDX_OFFSET > #define _Q_TAIL_MASK (_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK) > > #define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET) > --- a/kernel/locking/qspinlock.c > +++ b/kernel/locking/qspinlock.c > @@ -22,6 +22,7 @@ > #include <linux/percpu.h> > #in...

2014-05-14 19:00+0200, Peter Zijlstra: > On Wed, May 14, 2014 at 06:51:24PM +0200, Radim Kr?m?? wrote: > > Ok. > > I've seen merit in pvqspinlock even with slightly slower first-waiter, > > so I would have happily sacrificed those horrible branches. > > (I prefer elegant to optimized code, but I can see why we want to be > > strictly better than ticketlock.)

2014-05-14 19:00+0200, Peter Zijlstra: > On Wed, May 14, 2014 at 06:51:24PM +0200, Radim Kr?m?? wrote: > > Ok. > > I've seen merit in pvqspinlock even with slightly slower first-waiter, > > so I would have happily sacrificed those horrible branches. > > (I prefer elegant to optimized code, but I can see why we want to be > > strictly better than ticketlock.)

Since Waiman seems incapable of doing simple things; here's my take on the paravirt crap. The first few patches are taken from Waiman's latest series, but the virt support is completely new. Its primary aim is to not mess up the native code. I've not stress tested it, but the virt and paravirt (kvm) cases boot on simple smp guests. I've not done Xen, but the patch should be

Since Waiman seems incapable of doing simple things; here's my take on the paravirt crap. The first few patches are taken from Waiman's latest series, but the virt support is completely new. Its primary aim is to not mess up the native code. I've not stress tested it, but the virt and paravirt (kvm) cases boot on simple smp guests. I've not done Xen, but the patch should be

v8->v9: - Integrate PeterZ's version of the queue spinlock patch with some modification: http://lkml.kernel.org/r/20140310154236.038181843 at infradead.org - Break the more complex patches into smaller ones to ease review effort. - Fix a racing condition in the PV qspinlock code. v7->v8: - Remove one unneeded atomic operation from the slowpath, thus improving

v8->v9: - Integrate PeterZ's version of the queue spinlock patch with some modification: http://lkml.kernel.org/r/20140310154236.038181843 at infradead.org - Break the more complex patches into smaller ones to ease review effort. - Fix a racing condition in the PV qspinlock code. v7->v8: - Remove one unneeded atomic operation from the slowpath, thus improving

v9->v10: - Make some minor changes to qspinlock.c to accommodate review feedback. - Change author to PeterZ for 2 of the patches. - Include Raghavendra KT's test results in patch 18. v8->v9: - Integrate PeterZ's version of the queue spinlock patch with some modification: http://lkml.kernel.org/r/20140310154236.038181843 at infradead.org - Break the more complex

v9->v10: - Make some minor changes to qspinlock.c to accommodate review feedback. - Change author to PeterZ for 2 of the patches. - Include Raghavendra KT's test results in patch 18. v8->v9: - Integrate PeterZ's version of the queue spinlock patch with some modification: http://lkml.kernel.org/r/20140310154236.038181843 at infradead.org - Break the more complex

v11->v12: - Based on PeterZ's version of the qspinlock patch (https://lkml.org/lkml/2014/6/15/63). - Incorporated many of the review comments from Konrad Wilk and Paolo Bonzini. - The pvqspinlock code is largely from my previous version with PeterZ's way of going from queue tail to head and his idea of using callee saved calls to KVM and XEN codes. v10->v11: - Use a

v11->v12: - Based on PeterZ's version of the qspinlock patch (https://lkml.org/lkml/2014/6/15/63). - Incorporated many of the review comments from Konrad Wilk and Paolo Bonzini. - The pvqspinlock code is largely from my previous version with PeterZ's way of going from queue tail to head and his idea of using callee saved calls to KVM and XEN codes. v10->v11: - Use a

v13->v14: - Patches 1 & 2: Add queue_spin_unlock_wait() to accommodate commit 78bff1c86 from Oleg Nesterov. - Fix the system hang problem when using PV qspinlock in an over-committed guest due to a racing condition in the pv_set_head_in_tail() function. - Increase the MAYHALT_THRESHOLD from 10 to 1024. - Change kick_cpu into a regular function pointer instead of a

v13->v14: - Patches 1 & 2: Add queue_spin_unlock_wait() to accommodate commit 78bff1c86 from Oleg Nesterov. - Fix the system hang problem when using PV qspinlock in an over-committed guest due to a racing condition in the pv_set_head_in_tail() function. - Increase the MAYHALT_THRESHOLD from 10 to 1024. - Change kick_cpu into a regular function pointer instead of a

Hi Waiman, As promised; here is the paravirt stuff I did during the trip to BOS last week. All the !paravirt patches are more or less the same as before (the only real change is the copyright lines in the first patch). The paravirt stuff is 'simple' and KVM only -- the Xen code was a little more convoluted and I've no real way to test that but it should be stright fwd to make work.

Hi Waiman, As promised; here is the paravirt stuff I did during the trip to BOS last week. All the !paravirt patches are more or less the same as before (the only real change is the copyright lines in the first patch). The paravirt stuff is 'simple' and KVM only -- the Xen code was a little more convoluted and I've no real way to test that but it should be stright fwd to make work.

v12->v13: - Change patch 9 to generate separate versions of the queue_spin_lock_slowpath functions for bare metal and PV guest. This reduces the performance impact of the PV code on bare metal systems. v11->v12: - Based on PeterZ's version of the qspinlock patch (https://lkml.org/lkml/2014/6/15/63). - Incorporated many of the review comments from Konrad Wilk and Paolo