[dpdk-dev,2/4] doc: Corrected info for tx_checksum set mask function, in testpmd UG
Commit Message
tx_checksum set mask function now allows 4 extra bits in the mask
for TX checksum offload
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
---
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 10 +++++++++-
1 files changed, 9 insertions(+), 1 deletions(-)
Comments
Hi Pablo,
On 11/15/2014 08:13 PM, Pablo de Lara wrote:
> tx_checksum set mask function now allows 4 extra bits in the mask
> for TX checksum offload
>
> Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
> ---
> doc/guides/testpmd_app_ug/testpmd_funcs.rst | 10 +++++++++-
> 1 files changed, 9 insertions(+), 1 deletions(-)
A patch reworking the csumonly API is pending:
http://dpdk.org/ml/archives/dev/2014-November/008188.html
I don't know if it will be accepted, but just to mention that
these 2 patches will conflict in this case.
Regards,
Olivier
Hi Olivier,
> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Olivier MATZ
> Sent: Monday, November 17, 2014 10:39 AM
> To: De Lara Guarch, Pablo; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 2/4] doc: Corrected info for tx_checksum set
> mask function, in testpmd UG
>
> Hi Pablo,
>
> On 11/15/2014 08:13 PM, Pablo de Lara wrote:
> > tx_checksum set mask function now allows 4 extra bits in the mask
> > for TX checksum offload
> >
> > Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
> > ---
> > doc/guides/testpmd_app_ug/testpmd_funcs.rst | 10 +++++++++-
> > 1 files changed, 9 insertions(+), 1 deletions(-)
>
> A patch reworking the csumonly API is pending:
> http://dpdk.org/ml/archives/dev/2014-November/008188.html
>
> I don't know if it will be accepted, but just to mention that
> these 2 patches will conflict in this case.
Thanks for spotting it! I guess that at this point, all we can do is wait.
If you patch gets applied before mine, I will send a v2 with the changes.
If it gets applied after, then I will send another patch to fix it.
Pablo
>
> Regards,
> Olivier
Hi Pablo,
2014-11-17 10:47, De Lara Guarch, Pablo:
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Olivier MATZ
> > On 11/15/2014 08:13 PM, Pablo de Lara wrote:
> > > tx_checksum set mask function now allows 4 extra bits in the mask
> > > for TX checksum offload
> > >
> > > Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
> > > ---
> > > doc/guides/testpmd_app_ug/testpmd_funcs.rst | 10 +++++++++-
> > > 1 files changed, 9 insertions(+), 1 deletions(-)
> >
> > A patch reworking the csumonly API is pending:
> > http://dpdk.org/ml/archives/dev/2014-November/008188.html
> >
> > I don't know if it will be accepted, but just to mention that
> > these 2 patches will conflict in this case.
>
> Thanks for spotting it! I guess that at this point, all we can do is wait.
> If you patch gets applied before mine, I will send a v2 with the changes.
> If it gets applied after, then I will send another patch to fix it.
Oliver will send a v4 of his TSO patchset which should be applied shortly.
Please could you adjust the documentation and make a v2?
Bernard, we have to wait for this change.
Thanks to all
> -----Original Message-----
> From: Thomas Monjalon [mailto:thomas.monjalon@6wind.com]
> Sent: Wednesday, November 26, 2014 12:41 PM
> To: De Lara Guarch, Pablo
> Cc: dev@dpdk.org; Olivier MATZ; Iremonger, Bernard
> Subject: Re: [dpdk-dev] [PATCH 2/4] doc: Corrected info for tx_checksum set
> mask function, in testpmd UG
>
> Hi Pablo,
>
> 2014-11-17 10:47, De Lara Guarch, Pablo:
> > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Olivier MATZ
> > > On 11/15/2014 08:13 PM, Pablo de Lara wrote:
> > > > tx_checksum set mask function now allows 4 extra bits in the mask
> > > > for TX checksum offload
> > > >
> > > > Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
> > > > ---
> > > > doc/guides/testpmd_app_ug/testpmd_funcs.rst | 10 +++++++++-
> > > > 1 files changed, 9 insertions(+), 1 deletions(-)
> > >
> > > A patch reworking the csumonly API is pending:
> > > http://dpdk.org/ml/archives/dev/2014-November/008188.html
> > >
> > > I don't know if it will be accepted, but just to mention that
> > > these 2 patches will conflict in this case.
> >
> > Thanks for spotting it! I guess that at this point, all we can do is wait.
> > If you patch gets applied before mine, I will send a v2 with the changes.
> > If it gets applied after, then I will send another patch to fix it.
>
> Oliver will send a v4 of his TSO patchset which should be applied shortly.
> Please could you adjust the documentation and make a v2?
>
> Bernard, we have to wait for this change.
Sure, no problem.
>
> Thanks to all
> --
> Thomas
@@ -510,7 +510,7 @@ tx_vlan reset (port_id)
tx_checksum set mask
~~~~~~~~~~~~~~~~~~~~
-Enable hardware insertion of checksum offload with a 4-bit mask, 0x0 - 0xF, in packets sent on a port:
+Enable hardware insertion of checksum offload with a 8-bit mask, 0x0 - 0xFF, in packets sent on a port:
tx_checksum set (mask) (port_id)
@@ -524,6 +524,14 @@ bit 2 - if set insert tcp checksum offload
bit 3 - if set insert sctp checksum offload
+bit 4 - if set insert inner ip checksum offload
+
+bit 5 - if set insert inner udp checksum offload
+
+bit 6 - if set insert inner tcp checksum offload
+
+bit 7 - if set insert inner sctp checksum offload
+
.. note::
Check the NIC Datasheet for hardware limits.