Re: [PATCH 12/12] locking/rwsem: Make MSbit of count as guard bit to fail readlock

[Waiman Long]

On 03/28/2019 04:56 PM, Linus Torvalds wrote:
> On Thu, Mar 28, 2019 at 1:47 PM Linus Torvalds
> <torvalds@xxxxxxxxxxxxxxxxxxxx> wrote:
>> On Thu, Mar 28, 2019 at 11:12 AM Waiman Long <longman@xxxxxxxxxx> wrote:
>>> With the merging of owner into count for x86-64, there is only 16 bits
>>> left for reader count. It is theoretically possible for an application to
>>> cause more than 64k readers to acquire a rwsem leading to count overflow.
>> Ahh, and here's the thing that makes 16 bits work for readers.
> Hmm. Does it?
>
> Isn't there a race here? We're adding the READ bias, and then noticing
> that it his the guard bit, and then the down_read_failed will make it
> all good again.
>
> But this isn't actually done with preemption disabled, so things
> *could* get preempted in between, and if we have a huge run of bad
> luck, it can still overflow.
>
> Ok, so you need to have a 32k series run of bad luck (and hit
> *exactly* the right small preemption point window every time), and I'm
> certainly willing to say "yeah, not an issue", but maybe it's still
> worth at least documenting?
>
>                   Linus

I think it is theoretically possible that this can happen, but I doubt
we will ever see that. Will document that possibility in the comment.

Thanks,
Longman