net/mlx5e: Expose SQ SW state as part of SQ health diagnostics

Add SQ SW state textual representation to devlink health diagnostics
for tx reporter.

SQ SW state can be retrieved by issuing the devlink command below:

$ devlink health diagnose auxiliary/mlx5_core.eth.0/65535 reporter tx

Output
=======================================================================
 Common Config:
    SQ:
      stride size: 64 size: 1024 ts_format: FRC
      CQ:
        stride size: 64 size: 1024
  SQs:
      channel ix: 0 tc: 0 txq ix: 0 sqn: 4170 HW state: 1 stopped: false cc: 0 pc: 0
        SW State:
          enabled: 1 mpwqe: 1 recovering: 0 ipsec: 0 am: 1 vlan_need_l2_inline: 1 pending_xsk_tx: 0 pending_tls_rx_resync: 0 xdp_multibuf: 0
      CQ:
        cqn: 1031 HW status: 0 ci: 0 size: 1024
      EQ:
        eqn: 7 irqn: 32 vecidx: 0 ci: 2 size: 2048

Signed-off-by: Adham Faris <afaris@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://lore.kernel.org/r/20230314054234.267365-9-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 6c01da3..67f7e24 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -389,8 +389,11 @@ struct mlx5e_sq_dma {
        enum mlx5e_dma_map_type type;
 };
 
+/* Keep this enum consistent with with the corresponding strings array
+ * declared in en/reporter_tx.c
+ */
 enum {
-       MLX5E_SQ_STATE_ENABLED,
+       MLX5E_SQ_STATE_ENABLED = 0,
        MLX5E_SQ_STATE_MPWQE,
        MLX5E_SQ_STATE_RECOVERING,
        MLX5E_SQ_STATE_IPSEC,
@@ -399,6 +402,7 @@ enum {
        MLX5E_SQ_STATE_PENDING_XSK_TX,
        MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC,
        MLX5E_SQ_STATE_XDP_MULTIBUF,
+       MLX5E_NUM_SQ_STATES, /* Must be kept last */
 };
 
 struct mlx5e_tx_mpwqe {

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 34666e2..44c1926 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -6,6 +6,19 @@
 #include "en/devlink.h"
 #include "lib/tout.h"
 
+/* Keep this string array consistent with the MLX5E_SQ_STATE_* enums in en.h */
+static const char * const sq_sw_state_type_name[] = {
+       [MLX5E_SQ_STATE_ENABLED] = "enabled",
+       [MLX5E_SQ_STATE_MPWQE] = "mpwqe",
+       [MLX5E_SQ_STATE_RECOVERING] = "recovering",
+       [MLX5E_SQ_STATE_IPSEC] = "ipsec",
+       [MLX5E_SQ_STATE_DIM] = "dim",
+       [MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE] = "vlan_need_l2_inline",
+       [MLX5E_SQ_STATE_PENDING_XSK_TX] = "pending_xsk_tx",
+       [MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC] = "pending_tls_rx_resync",
+       [MLX5E_SQ_STATE_XDP_MULTIBUF] = "xdp_multibuf",
+};
+
 static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq)
 {
        struct mlx5_core_dev *dev = sq->mdev;
@@ -37,6 +50,35 @@ static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq)
        sq->pc = 0;
 }
 
+static int mlx5e_health_sq_put_sw_state(struct devlink_fmsg *fmsg, struct mlx5e_txqsq *sq)
+{
+       int err;
+       int i;
+
+       BUILD_BUG_ON_MSG(ARRAY_SIZE(sq_sw_state_type_name) != MLX5E_NUM_SQ_STATES,
+                        "sq_sw_state_type_name string array must be consistent with MLX5E_SQ_STATE_* enum in en.h");
+       err = devlink_fmsg_obj_nest_start(fmsg);
+       if (err)
+               return err;
+
+       err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SW State");
+       if (err)
+               return err;
+
+       for (i = 0; i < ARRAY_SIZE(sq_sw_state_type_name); ++i) {
+               err = devlink_fmsg_u32_pair_put(fmsg, sq_sw_state_type_name[i],
+                                               test_bit(i, &sq->state));
+               if (err)
+                       return err;
+       }
+
+       err = mlx5e_health_fmsg_named_obj_nest_end(fmsg);
+       if (err)
+               return err;
+
+       return devlink_fmsg_obj_nest_end(fmsg);
+}
+
 static int mlx5e_tx_reporter_err_cqe_recover(void *ctx)
 {
        struct mlx5_core_dev *mdev;
@@ -190,6 +232,10 @@ mlx5e_tx_reporter_build_diagnose_output_sq_common(struct devlink_fmsg *fmsg,
        if (err)
                return err;
 
+       err = mlx5e_health_sq_put_sw_state(fmsg, sq);
+       if (err)
+               return err;
+
        err = mlx5e_health_cq_diag_fmsg(&sq->cq, fmsg);
        if (err)
                return err;