Re: [PATCH RFC 0/9] sk_buff: optimize layout for GRO

On Sat, Jul 24, 2021 at 2:51 PM Florian Westphal [off-list ref] wrote:

Paul Moore [off-list ref] wrote:
 > Tow main drivers on my side:

quoted

quoted

- there are use cases/deployments that do not use them.
- moving them around was doable in term of required changes.

There are no "slow-path" implications on my side. For example, vlan_*
fields are very critical performance wise, if the traffic is tagged.
But surely there are busy servers not using tagget traffic which will
enjoy the reduced cachelines footprint, and this changeset will not
impact negatively the first case.

WRT to the vlan example, secmark and nfct require an extra conditional
to fetch the data. My understanding is that such additional conditional
is not measurable performance-wise when benchmarking the security
modules (or conntrack) because they have to do much more intersting
things after fetching a few bytes from an already hot cacheline.

Not sure if the above somehow clarify my statements.

As for expanding secmark to 64 bits, I guess that could be an
interesting follow-up discussion :)

The intersection between netdev and the LSM has a long and somewhat
tortured past with each party making sacrifices along the way to get
where we are at today.  It is far from perfect, at least from a LSM
perspective, but it is what we've got and since performance is usually
used as a club to beat back any changes proposed by the LSM side, I
would like to object to these changes that negatively impact the LSM
performance without some concession in return.  It has been a while
since Casey and I have spoken about this, but I think the prefered
option would be to exchange the current __u32 "sk_buff.secmark" field
with a void* "sk_buff.security" field, like so many other kernel level
objects.  Previous objections have eventually boiled down to the
additional space in the sk_buff for the extra bits (there is some
additional editorializing that could be done here, but I'll refrain),
but based on the comments thus far in this thread it sounds like
perhaps we can now make a deal here: move the LSM field down to a
"colder" cacheline in exchange for converting the LSM field to a
proper pointer.

Thoughts?

Is there a summary disucssion somewhere wrt. what exactly LSMs need?

My network access is limited for the next week so I don't have the
ability to dig through the list archives, but if you look through the
netdev/LSM/lists over the past decade (maybe go back ~15 years?) you
will see multiple instances where we/I've brought up different
solutions with the netdev folks only to hit a brick wall.  The LSM ask
for sk_buff is really the same as any other kernel object that we want
to control with LSM access controls, e.g. inodes; we basically want a
void* blob with the necessary hooks so that the opaque blob can be
managed through the skb's lifetime.

There is the skb extension infra, does that work for you?

I was hopeful that when the skb_ext capability was introduced we might
be able to use it for the LSM(s), but when I asked netdev if they
would be willing to accept patches to leverage the skb_ext
infrastructure I was told "no".

-- 
paul moore
www.paul-moore.com