RE: [EXTERNAL] Re: [net PATCH] octeontx2-pf: Do not use HW TSO when gso_size < 16bytes

[Geethasowjanya Akula]

> -----Original Message-----
> From: Eric Dumazet <edumazet@xxxxxxxxxx>
> Sent: Friday, March 8, 2024 7:29 PM
> To: Geethasowjanya Akula <gakula@xxxxxxxxxxx>
> Cc: netdev@xxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx; kuba@xxxxxxxxxx;
> davem@xxxxxxxxxxxxx; pabeni@xxxxxxxxxx; Sunil Kovvuri Goutham
> <sgoutham@xxxxxxxxxxx>; Subbaraya Sundeep Bhatta
> <sbhatta@xxxxxxxxxxx>; Hariprasad Kelam <hkelam@xxxxxxxxxxx>
> Subject: [EXTERNAL] Re: [net PATCH] octeontx2-pf: Do not use HW TSO when
> gso_size < 16bytes
> On Fri, Mar 8, 2024 at 12:57 PM Geetha sowjanya <gakula@xxxxxxxxxxx>
> wrote:
> >
> > Hardware doesn't support packet segmentation when segment size is < 16
> > bytes. Hence add an additional check and use SW segmentation in such
> > case.
> >
> > Fixes: 86d7476078b8 ("octeontx2-pf: TCP segmentation offload support").
> > Signed-off-by: Geetha sowjanya <gakula@xxxxxxxxxxx>
> > ---
> >  drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c | 7 +++++++
> >  1 file changed, 7 insertions(+)
> >
> > diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
> > b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
> > index f828d32737af..2ac56abb3a0e 100644
> > --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
> > +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
> > @@ -967,6 +967,13 @@ static bool is_hw_tso_supported(struct otx2_nic
> > *pfvf,  {
> >         int payload_len, last_seg_size;
> >
> > +       /* Due to hw issue segment size less than 16 bytes
> > +        * are not supported. Hence do not offload such TSO
> > +        * segments.
> > +        */
> > +       if (skb_shinfo(skb)->gso_size < 16)
> > +               return false;
> > +
> >         if (test_bit(HW_TSO, &pfvf->hw.cap_flag))
> >                 return true;
> 
> How is this driver doing SW segmentation at this stage ?
> 
> You might perform this check in ndo_features_check() instead ?
> 
> otx2_sq_append_skb() is also forcing a linearization if skb_shinfo(skb)-
> >nr_frags >= OTX2_MAX_FRAGS_IN_SQE
> 
> This is quite bad, this one definitely should use ndo_features_check() to mask
> NETIF_F_GSO_MASK for GSO packets.
> 
> Look at typhoon_features_check() for an example.

Thanks for the suggestions. Will submit v2 with suggested changes.