From: "Michael S. Tsirkin" <m...@redhat.com>
Date: Tue, 2 Jan 2018 19:01:33 +0200
> On Tue, Jan 02, 2018 at 11:52:19AM -0500, David Miller wrote:
>> From: John Fastabend <john.fastab...@gmail.com>
>> Date: Wed, 27 Dec 2017 19:50:25 -0800
>>
>> > When running consumer and/or producer operations and empty checks in
>> > parallel its possible to have the empty check run past the end of the
>> > array. The scenario occurs when an empty check is run while
>> > __ptr_ring_discard_one() is in progress. Specifically after the
>> > consumer_head is incremented but before (consumer_head >= ring_size)
>> > check is made and the consumer head is zeroe'd.
>> >
>> > To resolve this, without having to rework how consumer/producer ops
>> > work on the array, simply add an extra dummy slot to the end of the
>> > array. Even if we did a rework to avoid the extra slot it looks
>> > like the normal case checks would suffer some so best to just
>> > allocate an extra pointer.
>> >
>> > Reported-by: Jakub Kicinski <jakub.kicin...@netronome.com>
>> > Fixes: c5ad119fb6c09 ("net: sched: pfifo_fast use skb_array")
>> > Signed-off-by: John Fastabend <john.fastab...@gmail.com>
>>
>> Applied, thanks John.
>
> I think that patch is wrong. I'd rather it got reverted.
I agree with John's logic, the asynchronous test is always safe in
this parallel access case and John's change solves the out-of-bounds
test.
If you propose a cleaner way to handle this as a follow-on patch I'll
be happy to consider it.
Thanks.
