diff mbox series

[rdma-next,3/4] RDMA/mlx5: Implement ib_get_qp_err_syndrome

Message ID 20220907113800.22182-4-phaddad@nvidia.com (mailing list archive)
State Changes Requested
Headers show
Series Provide more error details when a QP moves to | expand

Commit Message

Patrisious Haddad Sept. 7, 2022, 11:37 a.m. UTC 
Implement ib_get_qp_err_syndrome using a query_qp FW call
and return the result in a human readable string.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/main.c    |  1 +
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  1 +
 drivers/infiniband/hw/mlx5/qp.c      | 42 +++++++++++++++++++++++++++-
 drivers/infiniband/hw/mlx5/qp.h      |  2 +-
 drivers/infiniband/hw/mlx5/qpc.c     |  4 ++-
 5 files changed, 47 insertions(+), 3 deletions(-)
diff mbox series

Patch

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 7c40efae96a3..c18d3e36542b 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3716,6 +3716,7 @@  static const struct ib_device_ops mlx5_ib_dev_ops = {
 	.get_dev_fw_str = get_dev_fw_str,
 	.get_dma_mr = mlx5_ib_get_dma_mr,
 	.get_link_layer = mlx5_ib_port_link_layer,
+	.get_qp_err_syndrome = mlx5_ib_get_qp_err_syndrome,
 	.map_mr_sg = mlx5_ib_map_mr_sg,
 	.map_mr_sg_pi = mlx5_ib_map_mr_sg_pi,
 	.mmap = mlx5_ib_mmap,
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 2e2ad3918385..bbd414cbd695 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1232,6 +1232,7 @@  int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		      int attr_mask, struct ib_udata *udata);
 int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr_mask,
 		     struct ib_qp_init_attr *qp_init_attr);
+int mlx5_ib_get_qp_err_syndrome(struct ib_qp *ibqp, char *str);
 int mlx5_ib_destroy_qp(struct ib_qp *qp, struct ib_udata *udata);
 void mlx5_ib_drain_sq(struct ib_qp *qp);
 void mlx5_ib_drain_rq(struct ib_qp *qp);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 40d9410ec303..7cf2fe549b9a 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -4806,7 +4806,8 @@  static int query_qp_attr(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	if (!outb)
 		return -ENOMEM;
 
-	err = mlx5_core_qp_query(dev, &qp->trans_qp.base.mqp, outb, outlen);
+	err = mlx5_core_qp_query(dev, &qp->trans_qp.base.mqp, outb, outlen,
+				 false);
 	if (err)
 		goto out;
 
@@ -4992,6 +4993,45 @@  int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
 	return err;
 }
 
+int mlx5_ib_get_qp_err_syndrome(struct ib_qp *ibqp, char *str)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
+	int outlen = MLX5_ST_SZ_BYTES(query_qp_out);
+	struct mlx5_ib_qp *qp = to_mqp(ibqp);
+	void *pas_ext_union, *err_syn;
+	u32 *outb;
+	int err;
+
+	if (!MLX5_CAP_GEN(dev->mdev, qpc_extension) ||
+	    !MLX5_CAP_GEN(dev->mdev, qp_error_syndrome))
+		return -EOPNOTSUPP;
+
+	outb = kzalloc(outlen, GFP_KERNEL);
+	if (!outb)
+		return -ENOMEM;
+
+	err = mlx5_core_qp_query(dev, &qp->trans_qp.base.mqp, outb, outlen,
+				 true);
+	if (err)
+		goto out;
+
+	pas_ext_union =
+		MLX5_ADDR_OF(query_qp_out, outb, qp_pas_or_qpc_ext_and_pas);
+	err_syn = MLX5_ADDR_OF(qpc_extension_and_pas_list_in, pas_ext_union,
+			       qpc_data_extension.error_syndrome);
+
+	scnprintf(str, IB_ERR_SYNDROME_LENGTH, "%s (0x%x 0x%x 0x%x)\n",
+		  ib_wc_status_msg(
+			  MLX5_GET(cqe_error_syndrome, err_syn, syndrome)),
+		  MLX5_GET(cqe_error_syndrome, err_syn, vendor_error_syndrome),
+		  MLX5_GET(cqe_error_syndrome, err_syn, hw_syndrome_type),
+		  MLX5_GET(cqe_error_syndrome, err_syn, hw_error_syndrome));
+
+out:
+	kfree(outb);
+	return err;
+}
+
 int mlx5_ib_alloc_xrcd(struct ib_xrcd *ibxrcd, struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibxrcd->device);
diff --git a/drivers/infiniband/hw/mlx5/qp.h b/drivers/infiniband/hw/mlx5/qp.h
index 5d4e140db99c..8d792ca00b32 100644
--- a/drivers/infiniband/hw/mlx5/qp.h
+++ b/drivers/infiniband/hw/mlx5/qp.h
@@ -20,7 +20,7 @@  int mlx5_core_qp_modify(struct mlx5_ib_dev *dev, u16 opcode, u32 opt_param_mask,
 int mlx5_core_destroy_qp(struct mlx5_ib_dev *dev, struct mlx5_core_qp *qp);
 int mlx5_core_destroy_dct(struct mlx5_ib_dev *dev, struct mlx5_core_dct *dct);
 int mlx5_core_qp_query(struct mlx5_ib_dev *dev, struct mlx5_core_qp *qp,
-		       u32 *out, int outlen);
+		       u32 *out, int outlen, bool qpc_ext);
 int mlx5_core_dct_query(struct mlx5_ib_dev *dev, struct mlx5_core_dct *dct,
 			u32 *out, int outlen);
 
diff --git a/drivers/infiniband/hw/mlx5/qpc.c b/drivers/infiniband/hw/mlx5/qpc.c
index 542e4c63a8de..7a1854aab441 100644
--- a/drivers/infiniband/hw/mlx5/qpc.c
+++ b/drivers/infiniband/hw/mlx5/qpc.c
@@ -504,12 +504,14 @@  void mlx5_cleanup_qp_table(struct mlx5_ib_dev *dev)
 }
 
 int mlx5_core_qp_query(struct mlx5_ib_dev *dev, struct mlx5_core_qp *qp,
-		       u32 *out, int outlen)
+		       u32 *out, int outlen, bool qpc_ext)
 {
 	u32 in[MLX5_ST_SZ_DW(query_qp_in)] = {};
 
 	MLX5_SET(query_qp_in, in, opcode, MLX5_CMD_OP_QUERY_QP);
 	MLX5_SET(query_qp_in, in, qpn, qp->qpn);
+	MLX5_SET(query_qp_in, in, qpc_ext, qpc_ext);
+
 	return mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, outlen);
 }