To summarize the discussion from my POV:
Open point: __ptr_ring_zero_tail() is only called after
consuming ring.batch elements.
1) Consumer wakes up the producer but the slot is not cleaned.
--> I disagree, the consumer only wakes after consuming ring.size/2.
Then __ptr_ring_zero_tail() was called at least once.
2) Producer is woken up but see the ring is full, so it need to
drop the packet.
--> I disagree, because then NETDEV_TX_BUSY is returned. This is
noticeable as qdisc requeue and only happens very rarely.
Points I will address:
- Minor nit on patch 2 by MST.
- Rebase patch 3 because of commit d748047
("ptr_ring: disable KCSAN warnings").
- Document the pair of the smp_mb__after_atomic() in tun_net_xmit
with tun_ring_consume().
- Use 1 ptr_ring spinlock instead of 2 (currently used for consume
and empty check), not sure how to implement it pretty rn.
- Run pktgen benchmarks with pg_set SHARED.
