On 05/20/2010 05:34 PM, Rusty Russell wrote:
Have just one ring, no indexes. The producer places descriptors into
the ring and updates the head, The consumer copies out descriptors to
be processed and copies back in completed descriptors. Chaining is
always linear. The descriptors contain a tag that allow the producer to
identify the completion.
This could definitely work. The original reason for the page boundaries
was for untrusted inter-guest communication: with appropriate page protections
they could see each other's rings and a simply inter-guest copy hypercall
could verify that the other guest really exposed that data via virtio ring.
But, cute as that is, we never did that. And it's not clear that it wins
much over simply having the hypervisor read both rings directly.
AFAICS having separate avail_ring/used_ring/desc_pool is orthogonal to
this cuteness.
Can we do better? The obvious idea is to try to get rid of last_used and
used, and use the ring itself. We would use an invalid entry to mark the
head of the ring.
Interesting! So a peer will read until it hits a wall. But how to
update the wall atomically?
Maybe we can have a flag in the descriptor indicate headness or
tailness. Update looks ugly though: write descriptor with head flag,
write next descriptor with head flag, remove flag from previous descriptor.
I was thinking a separate magic "invalid" entry. To publish an 3 descriptor
chain, you would write descriptors 2 and 3, write an invalid entry at 4,
barrier, write entry 1. It is a bit ugly, yes, but not terrible.
Worth exploring. This amortizes the indexes into the ring, a good thing.
Another thing we can do is place the tail a half ring away from the head
(and limit ring utilization to 50%), reducing bounces on short kicks.
Or equivalently have an avail ring and used ring, but both containing
tagged descriptors instead of pointers to descriptors.
I think that a simple simulator for this is worth writing, which tracks
cacheline moves under various fullness scenarios...
Yup.
--
Do not meddle in the internals of kernels, for they are subtle and quick to panic.
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
