Re: [net-next PATCH v2 0/8] tc offload for cls_u32 on ixgbe

On Tue, Feb 16, 2016 at 9:50 PM, David Miller [off-list ref] wrote:

From: Or Gerlitz <redacted>
Date: Tue, 16 Feb 2016 21:30:18 +0200

quoted

I thought we've got into agreement in netdev that the offloading
directive would be a tri-state creature (sw, hw and fail the op if
can't, hw and fallback to sw). Can you please elaborate what do you
mean by "make the offload decision per rule using flags similar to how
we do l2 mac updates"

I think John's changes are an intermediate step in a long term evolution.

sure

I'm going to apply John's changes as-is, and people can submit relative
changes on top if they want.

Understood, still I'd be happy to hear what does make the offload
decision per rule using flags similar to how we do l2 mac updates
means. Re the tri-state which you've referred to in netdev -- my
understanding is that we're talking on that flag coming from the user
as part of the tc command line.

Or.