[PATCH mlx5-next] RDMA/mlx5: Add Qcounters req_transport_retries_exceeded/req_rnr_retries_exceeded

[PATCH mlx5-next] RDMA/mlx5: Add Qcounters req_transport_retries_exceeded/req_rnr_retries_exceeded

[Leon Romanovsky]

From: Patrisious Haddad <phaddad@nvidia.com>

The req_transport_retries_exceeded counter shows the number of times
requester detected transport retries exceed error.

The req_rnr_retries_exceeded counter show the number of times the
requester detected RNR NAKs retries exceed error.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/counters.c | 4 ++++
 include/linux/mlx5/mlx5_ifc.h         | 6 +++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c
index 8300ce622835..4f6c1968a2ee 100644
--- a/drivers/infiniband/hw/mlx5/counters.c
+++ b/drivers/infiniband/hw/mlx5/counters.c
@@ -83,6 +83,8 @@ static const struct mlx5_ib_counter extended_err_cnts[] = {
 	INIT_Q_COUNTER(resp_remote_access_errors),
 	INIT_Q_COUNTER(resp_cqe_flush_error),
 	INIT_Q_COUNTER(req_cqe_flush_error),
+	INIT_Q_COUNTER(req_transport_retries_exceeded),
+	INIT_Q_COUNTER(req_rnr_retries_exceeded),
 };
 
 static const struct mlx5_ib_counter roce_accl_cnts[] = {
@@ -102,6 +104,8 @@ static const struct mlx5_ib_counter vport_extended_err_cnts[] = {
 	INIT_VPORT_Q_COUNTER(resp_remote_access_errors),
 	INIT_VPORT_Q_COUNTER(resp_cqe_flush_error),
 	INIT_VPORT_Q_COUNTER(req_cqe_flush_error),
+	INIT_VPORT_Q_COUNTER(req_transport_retries_exceeded),
+	INIT_VPORT_Q_COUNTER(req_rnr_retries_exceeded),
 };
 
 static const struct mlx5_ib_counter vport_roce_accl_cnts[] = {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index ea5d569862d7..ae8e13a883f2 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -5672,7 +5672,11 @@ struct mlx5_ifc_query_q_counter_out_bits {
 
 	u8         local_ack_timeout_err[0x20];
 
-	u8         reserved_at_320[0xa0];
+	u8         reserved_at_320[0x60];
+
+	u8         req_rnr_retries_exceeded[0x20];
+
+	u8         reserved_at_3a0[0x20];
 
 	u8         resp_local_length_error[0x20];
 
-- 
2.45.2

Re: [PATCH mlx5-next] RDMA/mlx5: Add Qcounters req_transport_retries_exceeded/req_rnr_retries_exceeded

[Simon Horman]

On Thu, Jun 13, 2024 at 09:00:04PM +0300, Leon Romanovsky wrote:
> From: Patrisious Haddad <phaddad@nvidia.com>
> 
> The req_transport_retries_exceeded counter shows the number of times
> requester detected transport retries exceed error.
> 
> The req_rnr_retries_exceeded counter show the number of times the
> requester detected RNR NAKs retries exceed error.
> 
> Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
> Signed-off-by: Leon Romanovsky <leonro@nvidia.com>

Reviewed-by: Simon Horman <horms@kernel.org>

Re: [PATCH mlx5-next] RDMA/mlx5: Add Qcounters req_transport_retries_exceeded/req_rnr_retries_exceeded

[Leon Romanovsky]

On Thu, 13 Jun 2024 21:00:04 +0300, Leon Romanovsky wrote:
> The req_transport_retries_exceeded counter shows the number of times
> requester detected transport retries exceed error.
> 
> The req_rnr_retries_exceeded counter show the number of times the
> requester detected RNR NAKs retries exceed error.
> 
> 
> [...]

Applied, thanks!

[1/1] RDMA/mlx5: Add Qcounters req_transport_retries_exceeded/req_rnr_retries_exceeded
      https://git.kernel.org/rdma/rdma/c/b339e0a39dc377

Best regards,
-- 
Leon Romanovsky <leon@kernel.org>