[dpdk-dev] [PATCH v3 13/13] net/bnxt: add enhancements to TF ULP
Ferruh Yigit
ferruh.yigit at intel.com
Thu Sep 16 16:06:02 CEST 2021
On 9/11/2021 4:30 PM, Venkat Duvvuru wrote:
> From: Kishore Padmanabha <kishore.padmanabha at broadcom.com>
>
> 1. Added support to specify l4 port masks in the template. Also enabled
> source mac in the wild card key for ingress flows.
>
> 2. Added support to enable offload for ipv6 traffic within the vxlan
> tunnel connection.
>
> 3. The flow counters is reduced from 7168 to 6912 for Whitney.
> The stats operation is updated to reflect counts for packets
> at egress from CFA instead of ingress to CFA
>
> 4. The miss path for the l2 context table is updated with correct
> parif and default action handler to handle the miss path for
> egress flows.
>
> 5. This support enables allocation of encapsulation, modification and
> action records dynamically based on a given flow actions.
>
> 6. Reduce the l2context resource requests during open_session. Move the
> SMAC from the L2Context to the EM/WM
>
> 7. Remap the parif in the bd action in order to eliminate incorrect
> replication of broadcast packets. The layer 4 source port mask
> was incorrectly updated in the outer layer 4 source port mask
> instead of inner layer 4. Add the l3 proto to egress rules, switch
> to using computed fields for l4 ports, add internal smac to f1/f2
> flows, add l3 proto to ingress ipv6 flows
>
> Signed-off-by: Kishore Padmanabha <kishore.padmanabha at broadcom.com>
> Signed-off-by: Mike Baucom <michael.baucom at broadcom.com>
> Signed-off-by: Venkat Duvvuru <venkatkumar.duvvuru at broadcom.com>
> Reviewed-by: Randy Schacher <stuart.schacher at broadcom.com>
> ---
> drivers/net/bnxt/tf_core/tf_tbl_sram.c | 7 -
> .../generic_templates/ulp_template_db_class.c | 8102 ++++++++++++-----
> .../generic_templates/ulp_template_db_enum.h | 675 +-
> .../generic_templates/ulp_template_db_field.h | 195 +-
> .../generic_templates/ulp_template_db_tbl.c | 2136 ++++-
> .../ulp_template_db_thor_act.c | 996 +-
> .../ulp_template_db_thor_class.c | 7495 ++++++++-------
> .../ulp_template_db_wh_plus_class.c | 14 +-
> drivers/net/bnxt/tf_ulp/ulp_gen_tbl.c | 4 +-
> drivers/net/bnxt/tf_ulp/ulp_mapper.c | 135 +-
> drivers/net/bnxt/tf_ulp/ulp_rte_parser.c | 175 +-
> drivers/net/bnxt/tf_ulp/ulp_template_struct.h | 10 +
> drivers/net/bnxt/tf_ulp/ulp_utils.c | 3 +-
> 13 files changed, 13538 insertions(+), 6409 deletions(-)
Hi Ajit,
I can see release notes ('release_21_11.rst') updated in the commit in net-brcm
tree [1], but that change doesn't exist in the original patchset.
I think it is crucial to be in sync on this, that content of the patches
shouldn't be changed in our sub-trees. cc'ed other subtree maintainers too, to
be sure we are all in same page.
Time to time we are doing simple changes/fixes in the repos, to help to the
developer, but changes shouldn't go beyond it, and I believe even those changes
should be communicated in the mail list for the record.
If the content of the patches needs to be changed, I think that should be done
by sending a new version of the set. I am aware it is additional overhead, but
still doing otherwise can cause more trouble in long term.
Thanks,
ferruh
[1]
https://git.dpdk.org/next/dpdk-next-net-brcm/commit/?id=840e8bd01b6493940ac6130e1280713ec708d000
More information about the dev
mailing list