Blob Blame History Raw
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 7 May 2019 08:56:38 -0700
Subject: net/mlx5e: TX, Dump WQs wqe descriptors on CQE with error events
Patch-mainline: v5.5-rc1
Git-commit: 130c7b46c93d313ca07d85a30d90021e424c7e9b
References: jsc#SLE-8464

Dump the Work Queue's TX WQE descriptor when a completion with
error is received.

Example:
[5.331832] mlx5_core 0000:00:04.0 enp0s4: Error cqe on cqn 0xa, ci 0x1, TXQ-SQ qpn 0xe, opcode 0xd, syndrome 0x2, vendor syndrome 0x0
[5.333127] 00000000: 55 65 02 75 31 fe c2 d2 6b 6c 62 1e f9 e1 d8 5c
[5.333837] 00000010: d3 b2 6c b8 89 e4 84 20 0b f4 3c e0 f3 75 41 ca
[5.334568] 00000020: 46 00 00 00 cd 70 a0 92 18 3a 01 de 00 00 00 00
[5.335313] 00000030: 7d bc 05 89 b2 e9 00 02 1e 00 00 0e 00 00 30 d2
[5.335972] WQE DUMP: WQ size 1024 WQ cur size 0, WQE index 0x0, len: 64
[5.336710] 00000000: 00 00 00 1e 00 00 0e 04 00 00 00 08 00 00 00 00
[5.337524] 00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 12 33 33
[5.338151] 00000020: 00 00 00 16 52 54 00 00 00 01 86 dd 60 00 00 00
[5.338740] 00000030: 00 00 00 48 00 00 00 00 00 00 00 00 66 ba 58 14

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c |    6 ++++++
 drivers/net/ethernet/mellanox/mlx5/core/wq.c    |   18 ++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/wq.h    |    1 +
 3 files changed, 25 insertions(+)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -461,8 +461,14 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *c
 		if (unlikely(get_cqe_opcode(cqe) == MLX5_CQE_REQ_ERR)) {
 			if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING,
 					      &sq->state)) {
+				struct mlx5e_tx_wqe_info *wi;
+				u16 ci;
+
+				ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
+				wi = &sq->db.wqe_info[ci];
 				mlx5e_dump_error_cqe(sq,
 						     (struct mlx5_err_cqe *)cqe);
+				mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs);
 				queue_work(cq->channel->priv->wq,
 					   &sq->recover_work);
 			}
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -96,6 +96,24 @@ err_db_free:
 	return err;
 }
 
+void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides)
+{
+	size_t len;
+	void *wqe;
+
+	if (!net_ratelimit())
+		return;
+
+	nstrides = max_t(u8, nstrides, 1);
+
+	len = nstrides << wq->fbc.log_stride;
+	wqe = mlx5_wq_cyc_get_wqe(wq, ix);
+
+	pr_info("WQE DUMP: WQ size %d WQ cur size %d, WQE index 0x%x, len: %ld\n",
+		mlx5_wq_cyc_get_size(wq), wq->cur_sz, ix, len);
+	print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, wqe, len, false);
+}
+
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl)
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -79,6 +79,7 @@ struct mlx5_wq_ll {
 int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		       void *wqc, struct mlx5_wq_cyc *wq,
 		       struct mlx5_wq_ctrl *wq_ctrl);
+void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides);
 u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq);
 
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,