From: Dariusz Sosnowski <dsosnowski@nvidia.com>
To: Viacheslav Ovsiienko <viacheslavo@nvidia.com>,
Ori Kam <orika@nvidia.com>, Suanming Mou <suanmingm@nvidia.com>,
Matan Azrad <matan@nvidia.com>,
"Yevgeny Kliteynik" <kliteyn@nvidia.com>
Cc: <dev@dpdk.org>, Alex Vesker <valex@nvidia.com>, <stable@dpdk.org>
Subject: [PATCH 1/4] net/mlx5/hws: fix direct index insert on dep wqe
Date: Wed, 6 Mar 2024 21:21:47 +0100 [thread overview]
Message-ID: <20240306202150.79577-1-dsosnowski@nvidia.com> (raw)
From: Alex Vesker <valex@nvidia.com>
In case a depend WQE was required and direct index was
needed we would not set the direct index on the dep_wqe.
This leads to incorrect insertion to index zero.
Fixes: 38b5bf6452a6 ("net/mlx5/hws: support insert/distribute RTC properties")
Cc: stable@dpdk.org
Signed-off-by: Alex Vesker <valex@nvidia.com>
Acked-by: Dariusz Sosnowski <dsosnowski@nvidia.com>
---
drivers/net/mlx5/hws/mlx5dr_rule.c | 15 ++++++++-------
drivers/net/mlx5/hws/mlx5dr_send.c | 1 +
drivers/net/mlx5/hws/mlx5dr_send.h | 1 +
3 files changed, 10 insertions(+), 7 deletions(-)
diff --git a/drivers/net/mlx5/hws/mlx5dr_rule.c b/drivers/net/mlx5/hws/mlx5dr_rule.c
index aa00c54e53..f14e1e6ecd 100644
--- a/drivers/net/mlx5/hws/mlx5dr_rule.c
+++ b/drivers/net/mlx5/hws/mlx5dr_rule.c
@@ -58,14 +58,16 @@ static void mlx5dr_rule_init_dep_wqe(struct mlx5dr_send_ring_dep_wqe *dep_wqe,
struct mlx5dr_rule *rule,
const struct rte_flow_item *items,
struct mlx5dr_match_template *mt,
- void *user_data)
+ struct mlx5dr_rule_attr *attr)
{
struct mlx5dr_matcher *matcher = rule->matcher;
struct mlx5dr_table *tbl = matcher->tbl;
bool skip_rx, skip_tx;
dep_wqe->rule = rule;
- dep_wqe->user_data = user_data;
+ dep_wqe->user_data = attr->user_data;
+ dep_wqe->direct_index = mlx5dr_matcher_is_insert_by_idx(matcher) ?
+ attr->rule_idx : 0;
if (!items) { /* rule update */
dep_wqe->rtc_0 = rule->rtc_0;
@@ -374,8 +376,8 @@ static int mlx5dr_rule_create_hws_fw_wqe(struct mlx5dr_rule *rule,
}
mlx5dr_rule_create_init(rule, &ste_attr, &apply, false);
- mlx5dr_rule_init_dep_wqe(&match_wqe, rule, items, mt, attr->user_data);
- mlx5dr_rule_init_dep_wqe(&range_wqe, rule, items, mt, attr->user_data);
+ mlx5dr_rule_init_dep_wqe(&match_wqe, rule, items, mt, attr);
+ mlx5dr_rule_init_dep_wqe(&range_wqe, rule, items, mt, attr);
ste_attr.direct_index = 0;
ste_attr.rtc_0 = match_wqe.rtc_0;
@@ -482,7 +484,7 @@ static int mlx5dr_rule_create_hws(struct mlx5dr_rule *rule,
* dep_wqe buffers (ctrl, data) are also reused for all STE writes.
*/
dep_wqe = mlx5dr_send_add_new_dep_wqe(queue);
- mlx5dr_rule_init_dep_wqe(dep_wqe, rule, items, mt, attr->user_data);
+ mlx5dr_rule_init_dep_wqe(dep_wqe, rule, items, mt, attr);
ste_attr.wqe_ctrl = &dep_wqe->wqe_ctrl;
ste_attr.wqe_data = &dep_wqe->wqe_data;
@@ -544,8 +546,7 @@ static int mlx5dr_rule_create_hws(struct mlx5dr_rule *rule,
ste_attr.used_id_rtc_1 = &rule->rtc_1;
ste_attr.retry_rtc_0 = dep_wqe->retry_rtc_0;
ste_attr.retry_rtc_1 = dep_wqe->retry_rtc_1;
- ste_attr.direct_index = mlx5dr_matcher_is_insert_by_idx(matcher) ?
- attr->rule_idx : 0;
+ ste_attr.direct_index = dep_wqe->direct_index;
} else {
apply.next_direct_idx = --ste_attr.direct_index;
}
diff --git a/drivers/net/mlx5/hws/mlx5dr_send.c b/drivers/net/mlx5/hws/mlx5dr_send.c
index 64138279a1..f749401c6f 100644
--- a/drivers/net/mlx5/hws/mlx5dr_send.c
+++ b/drivers/net/mlx5/hws/mlx5dr_send.c
@@ -50,6 +50,7 @@ void mlx5dr_send_all_dep_wqe(struct mlx5dr_send_engine *queue)
ste_attr.used_id_rtc_1 = &dep_wqe->rule->rtc_1;
ste_attr.wqe_ctrl = &dep_wqe->wqe_ctrl;
ste_attr.wqe_data = &dep_wqe->wqe_data;
+ ste_attr.direct_index = dep_wqe->direct_index;
mlx5dr_send_ste(queue, &ste_attr);
diff --git a/drivers/net/mlx5/hws/mlx5dr_send.h b/drivers/net/mlx5/hws/mlx5dr_send.h
index c1e8616f7e..c4eaea52ab 100644
--- a/drivers/net/mlx5/hws/mlx5dr_send.h
+++ b/drivers/net/mlx5/hws/mlx5dr_send.h
@@ -106,6 +106,7 @@ struct mlx5dr_send_ring_dep_wqe {
uint32_t rtc_1;
uint32_t retry_rtc_0;
uint32_t retry_rtc_1;
+ uint32_t direct_index;
void *user_data;
};
--
2.39.2
next reply other threads:[~2024-03-06 20:23 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-03-06 20:21 Dariusz Sosnowski [this message]
2024-03-06 20:21 ` [PATCH 2/4] net/mlx5: fix templates clean up of FDB control flow rules Dariusz Sosnowski
2024-03-06 20:21 ` [PATCH 3/4] net/mlx5: fix rollback on failed flow configure Dariusz Sosnowski
2024-03-06 20:21 ` [PATCH 4/4] net/mlx5: fix flow configure validation Dariusz Sosnowski
2024-03-13 7:46 ` [PATCH 1/4] net/mlx5/hws: fix direct index insert on dep wqe Raslan Darawsheh
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=20240306202150.79577-1-dsosnowski@nvidia.com \
--to=dsosnowski@nvidia.com \
--cc=dev@dpdk.org \
--cc=kliteyn@nvidia.com \
--cc=matan@nvidia.com \
--cc=orika@nvidia.com \
--cc=stable@dpdk.org \
--cc=suanmingm@nvidia.com \
--cc=valex@nvidia.com \
--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).