[PATCH] workqueue: Fix memory ordering race in queue_work*()

[Hector Martin]

On 2022/08/16 16:48, Herbert Xu wrote:
> On Tue, Aug 16, 2022 at 03:28:50PM +0900, Hector Martin wrote:
>>
>> This is the same reason I argued queue_work() itself needs to have a
>> similar guarantee, even when it doesn't queue work (and I updated the
>> doc to match). If test_and_set_bit() is used in this kind of context
>> often in the kernel, clearly the current implementation/doc clashes with
>> that.
> 
> Kernel code all over the place rely on the fact that test_and_set_bit
> provides a memory barrier.  So this bug that you've discovered is
> not at all isolated to the workqeueue system.  It'll break the kernel
> in lots of places in exactly the same way.

Now I'm surprised this isn't failing all over the place, given that...
these things are annoyingly subtle.

Still would want Will & Peter to chime in, of course.

>> As I said, I don't have any particular beef in this fight, but this is
>> horribly broken on M1/2 right now, so I'll send a patch to change the
>> bitops instead and you all can fight it out over which way is correct :)
> 
> Please do.

Already did, but I just realized I forgot to Cc you. Sorry about that,
hope you can pick it up through the MLs:

https://lore.kernel.org/asahi/20220816070311.89186-1-marcan@marcan.st/T/#u

- Hector