From: Tariq Toukan <tariqt@nvidia.com>
To: Andrew Lunn <andrew+netdev@lunn.ch>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, <netdev@vger.kernel.org>,
Paolo Abeni <pabeni@redhat.com>
Cc: Akiva Goldberger <agoldberger@nvidia.com>,
Alexei Lazar <alazar@nvidia.com>, Alex Vesker <valex@nvidia.com>,
Cosmin Ratiu <cratiu@nvidia.com>,
Dragos Tatulea <dtatulea@nvidia.com>,
Erez Shitrit <erezsh@nvidia.com>, Feng Liu <feliu@nvidia.com>,
Gal Pressman <gal@nvidia.com>,
Jacob Keller <jacob.e.keller@intel.com>,
Kees Cook <kees@kernel.org>, Leon Romanovsky <leon@kernel.org>,
<linux-kernel@vger.kernel.org>, <linux-rdma@vger.kernel.org>,
Mark Bloch <mbloch@nvidia.com>, Moshe Shemesh <moshe@nvidia.com>,
Parav Pandit <parav@nvidia.com>,
Saeed Mahameed <saeedm@nvidia.com>, Shay Drory <shayd@nvidia.com>,
Simon Horman <horms@kernel.org>, Tariq Toukan <tariqt@nvidia.com>,
Vlad Dogaru <vdogaru@nvidia.com>,
Yevgeny Kliteynik <kliteyn@nvidia.com>
Subject: [PATCH net-next V2 1/5] net/mlx5: HWS, Print more details for bad completion
Date: Mon, 10 Aug 2026 12:26:26 +0300 [thread overview]
Message-ID: <20260810092630.3137666-2-tariqt@nvidia.com> (raw)
In-Reply-To: <20260810092630.3137666-1-tariqt@nvidia.com>
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
When polling for completion returned completion with error,
parse some more details: QP number and WQE count.
Also, extract all the long value-to-string if conditions
to a short value-to-string functions: do it for rule
resize state, rule status, and syndrome.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Erez Shitrit <erezsh@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
.../mellanox/mlx5/core/steering/hws/send.c | 68 +++++++++++++------
1 file changed, 49 insertions(+), 19 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
index aed009aec4fe..1c9206f74aaa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
@@ -344,6 +344,36 @@ hws_send_engine_update_rule_resize(struct mlx5hws_send_engine *queue,
}
}
+static const char *hws_rule_status_to_string(enum mlx5hws_rule_status status)
+{
+ switch (status) {
+ case MLX5HWS_RULE_STATUS_CREATING: return "CREATING";
+ case MLX5HWS_RULE_STATUS_UPDATING: return "UPDATING";
+ case MLX5HWS_RULE_STATUS_DELETING: return "DELETING";
+ case MLX5HWS_RULE_STATUS_FAILING: return "FAILING";
+ default: return "NA";
+ }
+}
+
+static const char *hws_rule_resize_state_to_string(u8 state)
+{
+ switch (state) {
+ case MLX5HWS_RULE_RESIZE_STATE_IDLE: return "IDLE";
+ case MLX5HWS_RULE_RESIZE_STATE_WRITING: return "WRITING";
+ case MLX5HWS_RULE_RESIZE_STATE_DELETING: return "DELETING";
+ default: return "UNKNOWN";
+ }
+}
+
+static const char *hws_gta_syndrome_to_string(u8 syndrome)
+{
+ switch (syndrome) {
+ case 1: return "SET_FLOW_FAIL";
+ case 2: return "DISABLE_FLOW_FAIL";
+ default: return "UNKNOWN";
+ }
+}
+
static void hws_send_engine_dump_error_cqe(struct mlx5hws_send_engine *queue,
struct mlx5hws_send_ring_priv *priv,
struct mlx5_cqe64 *cqe)
@@ -352,6 +382,7 @@ static void hws_send_engine_dump_error_cqe(struct mlx5hws_send_engine *queue,
struct mlx5hws_context *ctx = priv->rule->matcher->tbl->ctx;
u32 opcode = cqe ? get_cqe_opcode(cqe) : 0;
struct mlx5hws_rule *rule = priv->rule;
+ u8 syndrome;
/* If something bad happens and lots of rules are failing, we don't
* want to pollute dmesg. Print only the first bad cqe per engine,
@@ -364,26 +395,17 @@ static void hws_send_engine_dump_error_cqe(struct mlx5hws_send_engine *queue,
if (mlx5hws_rule_move_in_progress(rule))
mlx5hws_err(ctx,
- "--- rule 0x%08llx: error completion moving rule: phase %s, wqes left %d\n",
+ "--- rule 0x%08llx: error completion moving rule: phase %s (%d), wqes left %d\n",
HWS_PTR_TO_ID(rule),
- rule->resize_info->state ==
- MLX5HWS_RULE_RESIZE_STATE_WRITING ? "WRITING" :
- rule->resize_info->state ==
- MLX5HWS_RULE_RESIZE_STATE_DELETING ? "DELETING" :
- "UNKNOWN",
+ hws_rule_resize_state_to_string
+ (rule->resize_info->state),
+ rule->resize_info->state,
rule->pending_wqes);
else
mlx5hws_err(ctx,
"--- rule 0x%08llx: error completion %s (%d), wqes left %d\n",
HWS_PTR_TO_ID(rule),
- rule->status ==
- MLX5HWS_RULE_STATUS_CREATING ? "CREATING" :
- rule->status ==
- MLX5HWS_RULE_STATUS_DELETING ? "DELETING" :
- rule->status ==
- MLX5HWS_RULE_STATUS_FAILING ? "FAILING" :
- rule->status ==
- MLX5HWS_RULE_STATUS_UPDATING ? "UPDATING" : "NA",
+ hws_rule_status_to_string(rule->status),
rule->status,
rule->pending_wqes);
@@ -423,6 +445,15 @@ static void hws_send_engine_dump_error_cqe(struct mlx5hws_send_engine *queue,
" rule 0x%08llx: |--- syndrome = 0x%x\n",
HWS_PTR_TO_ID(rule),
err_cqe->syndrome);
+ mlx5hws_err(ctx,
+ " rule 0x%08llx: |--- QPN = 0x%x\n",
+ HWS_PTR_TO_ID(rule),
+ be32_to_cpu(err_cqe->s_wqe_opcode_qpn) &
+ 0xffffff);
+ mlx5hws_err(ctx,
+ " rule 0x%08llx: |--- WQE_CNT = 0x%04x\n",
+ HWS_PTR_TO_ID(rule),
+ (u32)be16_to_cpu(err_cqe->wqe_counter));
}
mlx5hws_err(ctx,
@@ -433,13 +464,12 @@ static void hws_send_engine_dump_error_cqe(struct mlx5hws_send_engine *queue,
HWS_PTR_TO_ID(rule),
(be32_to_cpu(cqe->byte_cnt) & 0x80000000) ?
"FAILURE" : "SUCCESS");
+ /* syndrome is in the lower 2 bits of byte_cnt */
+ syndrome = be32_to_cpu(cqe->byte_cnt) & 3;
mlx5hws_err(ctx,
- " rule 0x%08llx: |------- SYNDROME = %s\n",
+ " rule 0x%08llx: |------- SYNDROME = %s (%u)\n",
HWS_PTR_TO_ID(rule),
- ((be32_to_cpu(cqe->byte_cnt) & 0x00000003) == 1) ?
- "SET_FLOW_FAIL" :
- ((be32_to_cpu(cqe->byte_cnt) & 0x00000003) == 2) ?
- "DISABLE_FLOW_FAIL" : "UNKNOWN");
+ hws_gta_syndrome_to_string(syndrome), syndrome);
mlx5hws_err(ctx,
" rule 0x%08llx: cqe->sop_drop_qpn = 0x%08x\n",
HWS_PTR_TO_ID(rule), be32_to_cpu(cqe->sop_drop_qpn));
--
2.44.0
next prev parent reply other threads:[~2026-08-10 9:27 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-10 9:26 [PATCH net-next V2 0/5] net/mlx5: HWS misc enhancements Tariq Toukan
2026-08-10 9:26 ` Tariq Toukan [this message]
2026-08-10 9:26 ` [PATCH net-next V2 2/5] net/mlx5: HWS, Log syndrome on STC modify failure Tariq Toukan
2026-08-10 9:26 ` [PATCH net-next V2 3/5] net/mlx5: HWS, Set the num of queues only when alloc succeeded Tariq Toukan
2026-08-10 9:26 ` [PATCH net-next V2 4/5] net/mlx5: HWS, Remove redundant MLX5_SET in RTC creation Tariq Toukan
2026-08-10 9:26 ` [PATCH net-next V2 5/5] net/mlx5: HWS, Remove redundant FW command when reading caps Tariq Toukan
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=20260810092630.3137666-2-tariqt@nvidia.com \
--to=tariqt@nvidia.com \
--cc=agoldberger@nvidia.com \
--cc=alazar@nvidia.com \
--cc=andrew+netdev@lunn.ch \
--cc=cratiu@nvidia.com \
--cc=davem@davemloft.net \
--cc=dtatulea@nvidia.com \
--cc=edumazet@google.com \
--cc=erezsh@nvidia.com \
--cc=feliu@nvidia.com \
--cc=gal@nvidia.com \
--cc=horms@kernel.org \
--cc=jacob.e.keller@intel.com \
--cc=kees@kernel.org \
--cc=kliteyn@nvidia.com \
--cc=kuba@kernel.org \
--cc=leon@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=mbloch@nvidia.com \
--cc=moshe@nvidia.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=parav@nvidia.com \
--cc=saeedm@nvidia.com \
--cc=shayd@nvidia.com \
--cc=valex@nvidia.com \
--cc=vdogaru@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