* [dpdk-dev] [PATCH] net/mlx5: fix LRO dependency to include DV flow
@ 2019-10-24 12:46 Dekel Peled
2019-10-24 13:42 ` Slava Ovsiienko
2019-10-29 8:57 ` Raslan Darawsheh
0 siblings, 2 replies; 3+ messages in thread
From: Dekel Peled @ 2019-10-24 12:46 UTC (permalink / raw)
To: matan, viacheslavo, shahafs; +Cc: orika, dev, stable
Rx queue for LRO is created using DevX. Flows created on this queue
must use the DV flow engine.
This patch adds check of dv_flow_en=1 when configuring LRO support
on device spawn.
Documentation is updated accordingly.
Fixes: 175f1c21d033 ("net/mlx5: check conditions to enable LRO")
Cc: stable@dpdk.org
Signed-off-by: Dekel Peled <dekelp@mellanox.com>
---
doc/guides/nics/mlx5.rst | 2 +-
drivers/net/mlx5/mlx5.c | 3 ++-
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst
index 600cea7..45fa968 100644
--- a/doc/guides/nics/mlx5.rst
+++ b/doc/guides/nics/mlx5.rst
@@ -203,7 +203,7 @@ Limitations
- LRO:
- - Requires DevX to be enabled.
+ - Requires DevX and DV flow to be enabled.
- KEEP_CRC offload cannot be supported with LRO.
- The first mbuf length, without head-room, must be big enough to include the
TCP header (122B).
diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
index b99c5a9..5977d06 100644
--- a/drivers/net/mlx5/mlx5.c
+++ b/drivers/net/mlx5/mlx5.c
@@ -2033,7 +2033,8 @@ struct mlx5_dev_spawn_data {
if (priv->counter_fallback)
DRV_LOG(INFO, "Use fall-back DV counter management\n");
/* Check for LRO support. */
- if (config.dest_tir && config.hca_attr.lro_cap) {
+ if (config.dest_tir && config.hca_attr.lro_cap &&
+ config.dv_flow_en) {
/* TBD check tunnel lro caps. */
config.lro.supported = config.hca_attr.lro_cap;
DRV_LOG(DEBUG, "Device supports LRO");
--
1.8.3.1
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [dpdk-dev] [PATCH] net/mlx5: fix LRO dependency to include DV flow
2019-10-24 12:46 [dpdk-dev] [PATCH] net/mlx5: fix LRO dependency to include DV flow Dekel Peled
@ 2019-10-24 13:42 ` Slava Ovsiienko
2019-10-29 8:57 ` Raslan Darawsheh
1 sibling, 0 replies; 3+ messages in thread
From: Slava Ovsiienko @ 2019-10-24 13:42 UTC (permalink / raw)
To: Dekel Peled, Matan Azrad, Shahaf Shuler; +Cc: Ori Kam, dev, stable
> -----Original Message-----
> From: Dekel Peled <dekelp@mellanox.com>
> Sent: Thursday, October 24, 2019 15:47
> To: Matan Azrad <matan@mellanox.com>; Slava Ovsiienko
> <viacheslavo@mellanox.com>; Shahaf Shuler <shahafs@mellanox.com>
> Cc: Ori Kam <orika@mellanox.com>; dev@dpdk.org; stable@dpdk.org
> Subject: [PATCH] net/mlx5: fix LRO dependency to include DV flow
>
> Rx queue for LRO is created using DevX. Flows created on this queue must
> use the DV flow engine.
>
> This patch adds check of dv_flow_en=1 when configuring LRO support on
> device spawn.
> Documentation is updated accordingly.
>
> Fixes: 175f1c21d033 ("net/mlx5: check conditions to enable LRO")
> Cc: stable@dpdk.org
>
> Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
> ---
> doc/guides/nics/mlx5.rst | 2 +-
> drivers/net/mlx5/mlx5.c | 3 ++-
> 2 files changed, 3 insertions(+), 2 deletions(-)
>
> diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst index
> 600cea7..45fa968 100644
> --- a/doc/guides/nics/mlx5.rst
> +++ b/doc/guides/nics/mlx5.rst
> @@ -203,7 +203,7 @@ Limitations
>
> - LRO:
>
> - - Requires DevX to be enabled.
> + - Requires DevX and DV flow to be enabled.
> - KEEP_CRC offload cannot be supported with LRO.
> - The first mbuf length, without head-room, must be big enough to include
> the
> TCP header (122B).
> diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c index
> b99c5a9..5977d06 100644
> --- a/drivers/net/mlx5/mlx5.c
> +++ b/drivers/net/mlx5/mlx5.c
> @@ -2033,7 +2033,8 @@ struct mlx5_dev_spawn_data {
> if (priv->counter_fallback)
> DRV_LOG(INFO, "Use fall-back DV counter
> management\n");
> /* Check for LRO support. */
> - if (config.dest_tir && config.hca_attr.lro_cap) {
> + if (config.dest_tir && config.hca_attr.lro_cap &&
> + config.dv_flow_en) {
> /* TBD check tunnel lro caps. */
> config.lro.supported = config.hca_attr.lro_cap;
> DRV_LOG(DEBUG, "Device supports LRO");
> --
> 1.8.3.1
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [dpdk-dev] [PATCH] net/mlx5: fix LRO dependency to include DV flow
2019-10-24 12:46 [dpdk-dev] [PATCH] net/mlx5: fix LRO dependency to include DV flow Dekel Peled
2019-10-24 13:42 ` Slava Ovsiienko
@ 2019-10-29 8:57 ` Raslan Darawsheh
1 sibling, 0 replies; 3+ messages in thread
From: Raslan Darawsheh @ 2019-10-29 8:57 UTC (permalink / raw)
To: Dekel Peled, Matan Azrad, Slava Ovsiienko, Shahaf Shuler
Cc: Ori Kam, dev, stable
Hi,
> -----Original Message-----
> From: dev <dev-bounces@dpdk.org> On Behalf Of Dekel Peled
> Sent: Thursday, October 24, 2019 3:47 PM
> To: Matan Azrad <matan@mellanox.com>; Slava Ovsiienko
> <viacheslavo@mellanox.com>; Shahaf Shuler <shahafs@mellanox.com>
> Cc: Ori Kam <orika@mellanox.com>; dev@dpdk.org; stable@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/mlx5: fix LRO dependency to include DV
> flow
>
> Rx queue for LRO is created using DevX. Flows created on this queue
> must use the DV flow engine.
>
> This patch adds check of dv_flow_en=1 when configuring LRO support
> on device spawn.
> Documentation is updated accordingly.
>
> Fixes: 175f1c21d033 ("net/mlx5: check conditions to enable LRO")
> Cc: stable@dpdk.org
>
> Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Patch applied to next-net-mlx,
Kindest regards,
Raslan Darawsheh
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2019-10-29 8:57 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-10-24 12:46 [dpdk-dev] [PATCH] net/mlx5: fix LRO dependency to include DV flow Dekel Peled
2019-10-24 13:42 ` Slava Ovsiienko
2019-10-29 8:57 ` Raslan Darawsheh
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).