Re: [PATCH net v1] net: netmem: fix skb_ensure_writable with unreadable skbs

[Stanislav Fomichev]

On 06/16, Mina Almasry wrote:
> On Mon, Jun 16, 2025 at 7:38 AM Stanislav Fomichev <stfomichev@xxxxxxxxx> wrote:
> >
> > On 06/15, Mina Almasry wrote:
> > > skb_ensure_writable should succeed when it's trying to write to the
> > > header of the unreadable skbs, so it doesn't need an unconditional
> > > skb_frags_readable check. The preceding pskb_may_pull() call will
> > > succeed if write_len is within the head and fail if we're trying to
> > > write to the unreadable payload, so we don't need an additional check.
> > >
> > > Removing this check restores DSCP functionality with unreadable skbs as
> > > it's called from dscp_tg.
> >
> > Can you share more info on which use-case (or which call sites) you're
> > trying to fix?
> 
> Hi Stan,
> 
> It's the use case of setting a DSCP header, and the call site is
> dscp_tg() -> skb_ensure_writable.
> 
> Repro steps should roughly be:
> 
> # Set DSCP header
> sudo iptables -tmangle -A POSTROUTING -p tcp -m comment --comment
> "foo" -j DSCP --set-dscp 0x08
> 
> # then run some unreadable netmem workload.
> 
> Before this change you should see 0 throughput, after this change the
> unreadable netmem workload should work as expected.

Ah, so this is basically all netfilter, makes sense, thanks!

Acked-by: Stanislav Fomichev <sdf@xxxxxxxxxxx>