Re: [PATCH 0/6] Optimize the cpu hotplug locking -v2

[Oleg Nesterov]

On 10/10, Peter Zijlstra wrote:
>
> That said, Oleg wants to use the same scheme for percpu_rwsem,

Yes, and later then (I hope) get_online_cpus() will be just
current->cpuhp_ref++ || percpu_down_read().

(just in case, we only need ->cpuhp_ref to ensure that the readers
 can't starve the writers as it currently possible. iow to block the
 new readers but ensure that the recursive get/down_read can't block)

And please look at sb_wait_write/sb_start_write. It uses the same
logic except:

	- it doesn't have the "true" fast-path for readers

	- its "slow" mode is slower than necessary

	- it is buggy (afaics)

> and I'm
> not sure his write-side (something in uprobes) wants to do the same.

surely not ;)

Oleg.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/