Re: [PATCH v2] percpu_counter: add a cmpxchg-based _add_batch variant

[Vlastimil Babka]

On 5/20/24 9:14 AM, Mateusz Guzik wrote:
> This was "percpu_counter: reimplement _add_batch with __this_cpu_cmpxchg".
> 
> I chatted with vbabka a little bit and he pointed me at mod_zone_state,
> which does the same thing I needed except dodges preemption -- turns out
> cmpxchg with a gs-prefixed argument is safe here.
> 
> ================ cut here ================
> 
> Interrupt disable/enable trips are quite expensive on x86-64 compared to
> a mere cmpxchg (note: no lock prefix!) and percpu counters are used
> quite often.
> 
> With this change I get a bump of 1% ops/s for negative path lookups,
> plugged into will-it-scale:
> 
> void testcase(unsigned long long *iterations, unsigned long nr)
> {
>         while (1) {
>                 int fd = open("/tmp/nonexistent", O_RDONLY);
>                 assert(fd == -1);
> 
>                 (*iterations)++;
>         }
> }
> 
> The win would be higher if it was not for other slowdowns, but one has
> to start somewhere.
> 
> v2:
> - dodge preemption
> - use this_cpu_try_cmpxchg
> - keep the old variant depending on CONFIG_HAVE_CMPXCHG_LOCAL
> 
> Signed-off-by: Mateusz Guzik <mjguzik@xxxxxxxxx>

Acked-by: Vlastimil Babka <vbabka@xxxxxxx>

I tried a stupid microbenchmark just doing percpu_counter_inc() in a loop
and this cut the time by almost 50%.

As we discussed, should be also possible to make the fastpath inlined as the
next step, to avoid the function calls that are stupid expensive with cpu
mitigations.

> ---
>  lib/percpu_counter.c | 44 +++++++++++++++++++++++++++++++++++++++-----
>  1 file changed, 39 insertions(+), 5 deletions(-)
> 
> diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
> index 44dd133594d4..80ec2ffc981a 100644
> --- a/lib/percpu_counter.c
> +++ b/lib/percpu_counter.c
> @@ -73,17 +73,50 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
>  EXPORT_SYMBOL(percpu_counter_set);
>  
>  /*
> - * local_irq_save() is needed to make the function irq safe:
> - * - The slow path would be ok as protected by an irq-safe spinlock.
> - * - this_cpu_add would be ok as it is irq-safe by definition.
> - * But:
> - * The decision slow path/fast path and the actual update must be atomic, too.
> + * Add to a counter while respecting batch size.
> + *
> + * There are 2 implementations, both dealing with the following problem:
> + *
> + * The decision slow path/fast path and the actual update must be atomic.
>   * Otherwise a call in process context could check the current values and
>   * decide that the fast path can be used. If now an interrupt occurs before
>   * the this_cpu_add(), and the interrupt updates this_cpu(*fbc->counters),
>   * then the this_cpu_add() that is executed after the interrupt has completed
>   * can produce values larger than "batch" or even overflows.
>   */
> +#ifdef CONFIG_HAVE_CMPXCHG_LOCAL
> +/*
> + * Safety against interrupts is achieved in 2 ways:
> + * 1. the fast path uses local cmpxchg (note: no lock prefix)
> + * 2. the slow path operates with interrupts disabled
> + */
> +void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
> +{
> +	s64 count;
> +	unsigned long flags;
> +
> +	count = this_cpu_read(*fbc->counters);
> +	do {
> +		if (unlikely(abs(count + amount)) >= batch) {
> +			raw_spin_lock_irqsave(&fbc->lock, flags);
> +			/*
> +			 * Note: by now might have migrated to another CPU or
> +			 * the value might have changed.
> +			 */
> +			count = __this_cpu_read(*fbc->counters);
> +			fbc->count += count + amount;
> +			__this_cpu_sub(*fbc->counters, count);
> +			raw_spin_unlock_irqrestore(&fbc->lock, flags);
> +			return;
> +		}
> +	} while (!this_cpu_try_cmpxchg(*fbc->counters, &count, count + amount));
> +}
> +#else
> +/*
> + * local_irq_save() is used to make the function irq safe:
> + * - The slow path would be ok as protected by an irq-safe spinlock.
> + * - this_cpu_add would be ok as it is irq-safe by definition.
> + */
>  void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
>  {
>  	s64 count;
> @@ -101,6 +134,7 @@ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
>  	}
>  	local_irq_restore(flags);
>  }
> +#endif
>  EXPORT_SYMBOL(percpu_counter_add_batch);
>  
>  /*