DPDK patches and discussions
 help / color / mirror / Atom feed
From: Tal Shnaiderman <talshn@nvidia.com>
To: <dev@dpdk.org>
Cc: <thomas@monjalon.net>, <matan@nvidia.com>, <rasland@nvidia.com>,
	<asafp@nvidia.com>, <viacheslavo@nvidia.com>, <eilong@nvidia.com>,
	<kcollins@nvidia.com>, <idanhac@nvidia.com>
Subject: [dpdk-dev] [RFC PATCH 03/12] net/mlx5: query software parsing support on Windows
Date: Wed, 15 Sep 2021 13:43:39 +0300	[thread overview]
Message-ID: <20210915104348.12920-4-talshn@nvidia.com> (raw)
In-Reply-To: <20210915104348.12920-1-talshn@nvidia.com>

Query software parsing supported on the NIC.

Save the offloads values in a config parameter.
This is needed for the outer IPv4 checksum and
IP and UPD tunneled packet TSO support.

Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
---
 drivers/net/mlx5/mlx5.c            | 16 ++++++++++++++++
 drivers/net/mlx5/mlx5.h            |  2 ++
 drivers/net/mlx5/windows/mlx5_os.c |  6 +++++-
 drivers/net/mlx5/windows/mlx5_os.h |  6 ++++++
 4 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
index f84e061fe7..80fc9e3168 100644
--- a/drivers/net/mlx5/mlx5.c
+++ b/drivers/net/mlx5/mlx5.c
@@ -947,6 +947,22 @@ mlx5_flex_parser_ecpri_release(struct rte_eth_dev *dev)
 	prf->obj = NULL;
 }
 
+uint32_t
+mlx5_get_supported_sw_parsing_offloads(const struct mlx5_hca_attr *attr)
+{
+	uint32_t sw_parsing_offloads = 0;
+
+	if (attr->swp) {
+		sw_parsing_offloads |= MLX5_SW_PARSING_CAP;
+		if (attr->swp_csum)
+			sw_parsing_offloads |= MLX5_SW_PARSING_CSUM_CAP;
+
+		if (attr->swp_lso)
+			sw_parsing_offloads |= MLX5_SW_PARSING_TSO_CAP;
+	}
+	return sw_parsing_offloads;
+}
+
 /*
  * Allocate Rx and Tx UARs in robust fashion.
  * This routine handles the following UAR allocation issues:
diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index a56f39cd5f..45713d1709 100644
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -1827,5 +1827,7 @@ int mlx5_aso_ct_query_by_wqe(struct mlx5_dev_ctx_shared *sh,
 			     struct rte_flow_action_conntrack *profile);
 int mlx5_aso_ct_available(struct mlx5_dev_ctx_shared *sh,
 			  struct mlx5_aso_ct_action *ct);
+uint32_t
+mlx5_get_supported_sw_parsing_offloads(const struct mlx5_hca_attr *attr);
 
 #endif /* RTE_PMD_MLX5_H_ */
diff --git a/drivers/net/mlx5/windows/mlx5_os.c b/drivers/net/mlx5/windows/mlx5_os.c
index 26fa927039..1e258e044e 100644
--- a/drivers/net/mlx5/windows/mlx5_os.c
+++ b/drivers/net/mlx5/windows/mlx5_os.c
@@ -169,6 +169,8 @@ mlx5_os_get_dev_attr(void *ctx, struct mlx5_dev_attr *device_attr)
 		device_attr->max_rwq_indirection_table_size =
 			1 << hca_attr.rss_ind_tbl_cap;
 	}
+	device_attr->sw_parsing_offloads =
+		mlx5_get_supported_sw_parsing_offloads(&hca_attr);
 	pv_iseg = mlx5_glue->query_hca_iseg(mlx5_ctx, &cb_iseg);
 	if (pv_iseg == NULL) {
 		DRV_LOG(ERR, "Failed to get device hca_iseg");
@@ -393,7 +395,9 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
 	}
 	DRV_LOG(DEBUG, "MPW isn't supported");
 	mlx5_os_get_dev_attr(sh->ctx, &device_attr);
-	config->swp = 0;
+	config->swp = device_attr.sw_parsing_offloads &
+		(MLX5_SW_PARSING_CAP | MLX5_SW_PARSING_CSUM_CAP |
+		 MLX5_SW_PARSING_TSO_CAP);
 	config->ind_table_max_size =
 		sh->device_attr.max_rwq_indirection_table_size;
 	cqe_comp = 0;
diff --git a/drivers/net/mlx5/windows/mlx5_os.h b/drivers/net/mlx5/windows/mlx5_os.h
index 7fe41d4e90..6de683357c 100644
--- a/drivers/net/mlx5/windows/mlx5_os.h
+++ b/drivers/net/mlx5/windows/mlx5_os.h
@@ -16,4 +16,10 @@ enum {
 
 #define MLX5_NAMESIZE MLX5_FS_NAME_MAX
 
+enum mlx5_sw_parsing_offloads {
+	MLX5_SW_PARSING_CAP =      1 << 0,
+	MLX5_SW_PARSING_CSUM_CAP = 1 << 1,
+	MLX5_SW_PARSING_TSO_CAP =  1 << 2,
+};
+
 #endif /* RTE_PMD_MLX5_OS_H_ */
-- 
2.16.1.windows.4


  parent reply	other threads:[~2021-09-15 10:44 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-15 10:43 [dpdk-dev] [RFC PATCH 00/12] Expand NIC offloads " Tal Shnaiderman
2021-09-15 10:43 ` [dpdk-dev] [RFC PATCH 01/12] net/mlx5: fix software parsing support query Tal Shnaiderman
2021-09-15 10:43 ` [dpdk-dev] [RFC PATCH 02/12] common/mlx5: read software parsing capabilities from DevX Tal Shnaiderman
2021-09-15 10:43 ` Tal Shnaiderman [this message]
2021-09-15 10:43 ` [dpdk-dev] [RFC PATCH 04/12] net/mlx5: fix tunneling support query Tal Shnaiderman
2021-09-15 10:43 ` [dpdk-dev] [RFC PATCH 05/12] common/mlx5: read tunneling capabilities from DevX Tal Shnaiderman
2021-09-15 10:43 ` [dpdk-dev] [RFC PATCH 06/12] net/mlx5: query tunneling support on Windows Tal Shnaiderman
2021-09-15 10:43 ` [dpdk-dev] [RFC PATCH 07/12] common/mlx5: read TSO capability from DevX Tal Shnaiderman
2021-09-15 10:43 ` [dpdk-dev] [RFC PATCH 08/12] net/mlx5: support TSO offload on Windows Tal Shnaiderman
2021-09-15 10:43 ` [dpdk-dev] [RFC PATCH 09/12] common/mlx5: read VLAN capability from DevX Tal Shnaiderman
2021-09-15 10:43 ` [dpdk-dev] [RFC PATCH 10/12] net/mlx5: support VLAN stripping offload on Windows Tal Shnaiderman
2021-09-15 10:43 ` [dpdk-dev] [RFC PATCH 11/12] common/mlx5: read FCS scattering capability from DevX Tal Shnaiderman
2021-09-15 10:43 ` [dpdk-dev] [RFC PATCH 12/12] net/mlx5: support keep-CRC offload on Windows Tal Shnaiderman

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210915104348.12920-4-talshn@nvidia.com \
    --to=talshn@nvidia.com \
    --cc=asafp@nvidia.com \
    --cc=dev@dpdk.org \
    --cc=eilong@nvidia.com \
    --cc=idanhac@nvidia.com \
    --cc=kcollins@nvidia.com \
    --cc=matan@nvidia.com \
    --cc=rasland@nvidia.com \
    --cc=thomas@monjalon.net \
    --cc=viacheslavo@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).