Re: [PATCH] fix wait_task_inactive race (was Re: Race condition in ptrace)

[Nick Piggin <nickpiggin@yahoo.com.au>]

Nick Piggin wrote:
> Ingo Molnar wrote:
> 
>> * Nick Piggin <nickpiggin@yahoo.com.au> wrote:
>>
>>
>>> When a task is put to sleep, it is dequeued from the runqueue
>>> while it is still running. The problem is that the runqueue
>>> lock can be dropped and retaken in schedule() before the task
>>> actually schedules off, and wait_task_inactive did not account
>>> for this.
>>
>>
>>
>> ugh. This has been the Nth time we got bitten by the fundamental
>> unrobustness of non-atomic scheduling on some architectures ...
>> (And i'll say the N+1th time that this is not good.)
>>
> 
> This is actually due to wake_sleeping_dependent and
> dependent_sleeper dropping the runqueue lock.
> 

Hmph, *and* unlocked context switch architectures as you say.
In fact, I'm surprised those haven't been bitten by this problem
earlier.

So that makes us each half right! :)