Re: [PATCH v6 18/24] mm: Try spin lock in speculative path

[Laurent Dufour]

On 12/01/2018 19:18, Matthew Wilcox wrote:
> On Fri, Jan 12, 2018 at 06:26:02PM +0100, Laurent Dufour wrote:
>> There is a deadlock when a CPU is doing a speculative page fault and
>> another one is calling do_unmap().
>>
>> The deadlock occurred because the speculative path try to spinlock the
>> pte while the interrupt are disabled. When the other CPU in the
>> unmap's path has locked the pte then is waiting for all the CPU to
>> invalidate the TLB. As the CPU doing the speculative fault have the
>> interrupt disable it can't invalidate the TLB, and can't get the lock.
>>
>> Since we are in a speculative path, we can race with other mm action.
>> So let assume that the lock may not get acquired and fail the
>> speculative page fault.
> 
> It seems like you introduced this bug in the previous patch, and now
> you're fixing it in this patch?  Why not merge the two?

You're right this is a fix from the previous patch. Initially my idea was
to keep the original Peter's patch as is, but sounds that this is not a
good idea.
I'll merge it in the previous one.

Thanks,
Laurent.