Re: [PATCH] x86/alternatives: remove false sharing in poke_int3_handler()

[Ingo Molnar]

* Eric Dumazet <edumazet@xxxxxxxxxx> wrote:

> eBPF programs can be run 20,000,000+ times per second on busy servers.
> 
> Whenever /proc/sys/kernel/bpf_stats_enabled is turned off,
> hundreds of calls sites are patched from text_poke_bp_batch()
> and we see a critical loss of performance due to false sharing
> on bp_desc.refs lasting up to three seconds.

> @@ -2413,8 +2415,12 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
>  	/*
>  	 * Remove and wait for refs to be zero.
>  	 */
> -	if (!atomic_dec_and_test(&bp_desc.refs))
> -		atomic_cond_read_acquire(&bp_desc.refs, !VAL);
> +	for_each_possible_cpu(i) {
> +		atomic_t *refs = per_cpu_ptr(&bp_refs, i);
> +
> +		if (!atomic_dec_and_test(refs))
> +			atomic_cond_read_acquire(refs, !VAL);
> +	}

So your patch changes text_poke_bp_batch() to busy-spin-wait for 
bp_refs to go to zero on all 480 CPUs.

Your measurement is using /proc/sys/kernel/bpf_stats_enabled on a 
single CPU, right?

What's the adversarial workload here? Spamming bpf_stats_enabled on all 
CPUs in parallel? Or mixing it with some other text_poke_bp_batch() 
user if bpf_stats_enabled serializes access?

Does anything undesirable happen in that case?

Thanks,

	Ingo