On Sun, Apr 30, 2023 at 06:15:03PM +0000, Alvaro Karsz wrote: > > > > This patchset follows a discussion in the mailing list [1]. > > > > > > This fixes only part of the bug, rings with less than 4 entries won't > > > work. > > > > Why the difference? > > > > Because the RING_SIZE < 4 case requires much more adjustments. > > * We may need to squeeze the virtio header into the headroom. > * We may need to squeeze the GSO header into the headroom, or block the > features.
We alread do this though no? I think we'll need to tweak hard_header_len to guarantee it's there as opposed to needed_headroom ... > * At the moment, without NETIF_F_SG, we can receive a skb with 2 segments, we > may need to reduce it to 1. You are saying clearing NETIF_F_SG does not guarantee a linear skb? > * We may need to change all the control commands, so class, command and > command specific data will fit in a single segment. > * We may need to disable the control command and all the features depending > on it. well if we don't commands just fail as we can't add them right? no corruption or stalls ... > * We may need to disable NAPI? hmm why napi? > There may be more changes.. > > I was thinking that it may be easier to start with the easier case RING_SIZE > >= 4, make sure everything is working fine, then send a follow up patchset > with the required adjustments for RING_SIZE < 4. it's ok but I'm just trying to figure out where does 4 come from. _______________________________________________ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
