[PATCH 10/17] powerpc/qspinlock: allow stealing when head of queue yields

[Jordan Niethe]

On Thu, 2022-07-28 at 16:31 +1000, Nicholas Piggin wrote:
[resend as utf-8, not utf-7]
> If the head of queue is preventing stealing but it finds the owner vCPU
> is preempted, it will yield its cycles to the owner which could cause it
> to become preempted. Add an option to re-allow stealers before yielding,
> and disallow them again after returning from the yield.
> 
> Disable this option by default for now, i.e., no logical change.
> ---
>  arch/powerpc/lib/qspinlock.c | 56 ++++++++++++++++++++++++++++++++++--
>  1 file changed, 53 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/powerpc/lib/qspinlock.c b/arch/powerpc/lib/qspinlock.c
> index b39f8c5b329c..94f007f66942 100644
> --- a/arch/powerpc/lib/qspinlock.c
> +++ b/arch/powerpc/lib/qspinlock.c
> @@ -26,6 +26,7 @@ static bool MAYBE_STEALERS __read_mostly = true;
>  static int HEAD_SPINS __read_mostly = (1<<8);
>  
>  static bool pv_yield_owner __read_mostly = true;
> +static bool pv_yield_allow_steal __read_mostly = false;

To me this one does read as a boolean, but if you go with those other changes
I'd make it pv_yield_steal_enable to be consistent.

>  static bool pv_yield_prev __read_mostly = true;
>  
>  static DEFINE_PER_CPU_ALIGNED(struct qnodes, qnodes);
> @@ -173,6 +174,23 @@ static __always_inline u32 lock_set_mustq(struct qspinlock *lock)
>  	return prev;
>  }
>  
> +static __always_inline u32 lock_clear_mustq(struct qspinlock *lock)
> +{
> +	u32 new = _Q_MUST_Q_VAL;
> +	u32 prev;
> +
> +	asm volatile(
> +"1:	lwarx	%0,0,%1		# lock_clear_mustq			\n"
> +"	andc	%0,%0,%2						\n"
> +"	stwcx.	%0,0,%1							\n"
> +"	bne-	1b							\n"
> +	: "=&r" (prev)
> +	: "r" (&lock->val), "r" (new)
> +	: "cr0", "memory");
> +

This is pretty similar to the DEFINE_TESTOP() pattern again with the same llong caveat.


> +	return prev;
> +}
> +
>  static struct qnode *get_tail_qnode(struct qspinlock *lock, u32 val)
>  {
>  	int cpu = get_tail_cpu(val);
> @@ -188,7 +206,7 @@ static struct qnode *get_tail_qnode(struct qspinlock *lock, u32 val)
>  	BUG();
>  }
>  
> -static __always_inline void yield_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt)
> +static __always_inline void __yield_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt, bool clear_mustq)

 /* See yield_to_locked_owner comment */ comment needs to be updated now.


>  {
>  	int owner;
>  	u32 yield_count;
> @@ -217,7 +235,11 @@ static __always_inline void yield_to_locked_owner(struct qspinlock *lock, u32 va
>  	smp_rmb();
>  
>  	if (READ_ONCE(lock->val) == val) {
> +		if (clear_mustq)
> +			lock_clear_mustq(lock);
>  		yield_to_preempted(owner, yield_count);
> +		if (clear_mustq)
> +			lock_set_mustq(lock);
>  		/* Don't relax if we yielded. Maybe we should? */
>  		return;
>  	}
> @@ -225,6 +247,16 @@ static __always_inline void yield_to_locked_owner(struct qspinlock *lock, u32 va
>  	cpu_relax();
>  }
>  
> +static __always_inline void yield_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt)
> +{
> +	__yield_to_locked_owner(lock, val, paravirt, false);
> +}
> +
> +static __always_inline void yield_head_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt, bool clear_mustq)
> +{

The check for pv_yield_allow_steal seems like it could go here instead of
being done by the caller.
__yield_to_locked_owner() checks for pv_yield_owner so it seems more
  consistent.



> +	__yield_to_locked_owner(lock, val, paravirt, clear_mustq);
> +}
> +
>  static __always_inline void yield_to_prev(struct qspinlock *lock, struct qnode *node, int prev_cpu, bool paravirt)
>  {
>  	u32 yield_count;
> @@ -332,7 +364,7 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
>  	if (!MAYBE_STEALERS) {
>  		/* We're at the head of the waitqueue, wait for the lock. */
>  		while ((val = READ_ONCE(lock->val)) & _Q_LOCKED_VAL)
> -			yield_to_locked_owner(lock, val, paravirt);
> +			yield_head_to_locked_owner(lock, val, paravirt, false);
>  
>  		/* If we're the last queued, must clean up the tail. */
>  		if ((val & _Q_TAIL_CPU_MASK) == tail) {
> @@ -350,7 +382,8 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
>  again:
>  		/* We're at the head of the waitqueue, wait for the lock. */
>  		while ((val = READ_ONCE(lock->val)) & _Q_LOCKED_VAL) {
> -			yield_to_locked_owner(lock, val, paravirt);
> +			yield_head_to_locked_owner(lock, val, paravirt,
> +					pv_yield_allow_steal && set_mustq);
>  
>  			iters++;
>  			if (!set_mustq && iters >= get_head_spins(paravirt)) {
> @@ -475,6 +508,22 @@ static int pv_yield_owner_get(void *data, u64 *val)
>  
>  DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_owner, pv_yield_owner_get, pv_yield_owner_set, "%llu\n");
>  
> +static int pv_yield_allow_steal_set(void *data, u64 val)
> +{
> +	pv_yield_allow_steal = !!val;
> +
> +	return 0;
> +}
> +
> +static int pv_yield_allow_steal_get(void *data, u64 *val)
> +{
> +	*val = pv_yield_allow_steal;
> +
> +	return 0;
> +}
> +
> +DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_allow_steal, pv_yield_allow_steal_get, pv_yield_allow_steal_set, "%llu\n");
> +
>  static int pv_yield_prev_set(void *data, u64 val)
>  {
>  	pv_yield_prev = !!val;
> @@ -497,6 +546,7 @@ static __init int spinlock_debugfs_init(void)
>  	debugfs_create_file("qspl_head_spins", 0600, arch_debugfs_dir, NULL, &fops_head_spins);
>  	if (is_shared_processor()) {
>  		debugfs_create_file("qspl_pv_yield_owner", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_owner);
> +		debugfs_create_file("qspl_pv_yield_allow_steal", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_allow_steal);
>  		debugfs_create_file("qspl_pv_yield_prev", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_prev);
>  	}
>