From f86e34374a05635332229d1928796d04017ddf16 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Mon, 20 Apr 2020 09:22:13 +0300 Subject: RDMA/efa: Count admin commands errors Add a new stat that counts admin commands failures, which might help when debugging different issues. Link: https://lore.kernel.org/r/20200420062213.44577-4-galpress@amazon.com Reviewed-by: Daniel Kranzdorf Reviewed-by: Yossi Leybovich Signed-off-by: Gal Pressman Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/efa/efa_com.c | 5 ++++- drivers/infiniband/hw/efa/efa_com.h | 3 ++- drivers/infiniband/hw/efa/efa_verbs.c | 2 ++ 3 files changed, 8 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/infiniband/hw/efa/efa_com.c b/drivers/infiniband/hw/efa/efa_com.c index 7fce69f5568f..336bc2c57bb1 100644 --- a/drivers/infiniband/hw/efa/efa_com.c +++ b/drivers/infiniband/hw/efa/efa_com.c @@ -631,17 +631,20 @@ int efa_com_cmd_exec(struct efa_com_admin_queue *aq, cmd->aq_common_descriptor.opcode, PTR_ERR(comp_ctx)); up(&aq->avail_cmds); + atomic64_inc(&aq->stats.cmd_err); return PTR_ERR(comp_ctx); } err = efa_com_wait_and_process_admin_cq(comp_ctx, aq); - if (err) + if (err) { ibdev_err_ratelimited( aq->efa_dev, "Failed to process command %s (opcode %u) comp_status %d err %d\n", efa_com_cmd_str(cmd->aq_common_descriptor.opcode), cmd->aq_common_descriptor.opcode, comp_ctx->comp_status, err); + atomic64_inc(&aq->stats.cmd_err); + } up(&aq->avail_cmds); diff --git a/drivers/infiniband/hw/efa/efa_com.h b/drivers/infiniband/hw/efa/efa_com.h index c67dd8109d1c..5e4c88877ddb 100644 --- a/drivers/infiniband/hw/efa/efa_com.h +++ b/drivers/infiniband/hw/efa/efa_com.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */ /* - * Copyright 2018-2019 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2020 Amazon.com, Inc. or its affiliates. All rights reserved. */ #ifndef _EFA_COM_H_ @@ -47,6 +47,7 @@ struct efa_com_admin_sq { struct efa_com_stats_admin { atomic64_t submitted_cmd; atomic64_t completed_cmd; + atomic64_t cmd_err; atomic64_t no_completion; }; diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 1f8162b2067d..08313f7c73bc 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -37,6 +37,7 @@ struct efa_user_mmap_entry { op(EFA_RX_DROPS, "rx_drops") \ op(EFA_SUBMITTED_CMDS, "submitted_cmds") \ op(EFA_COMPLETED_CMDS, "completed_cmds") \ + op(EFA_CMDS_ERR, "cmds_err") \ op(EFA_NO_COMPLETION_CMDS, "no_completion_cmds") \ op(EFA_KEEP_ALIVE_RCVD, "keep_alive_rcvd") \ op(EFA_ALLOC_PD_ERR, "alloc_pd_err") \ @@ -1752,6 +1753,7 @@ int efa_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats, as = &dev->edev.aq.stats; stats->value[EFA_SUBMITTED_CMDS] = atomic64_read(&as->submitted_cmd); stats->value[EFA_COMPLETED_CMDS] = atomic64_read(&as->completed_cmd); + stats->value[EFA_CMDS_ERR] = atomic64_read(&as->cmd_err); stats->value[EFA_NO_COMPLETION_CMDS] = atomic64_read(&as->no_completion); s = &dev->stats; -- cgit v1.2.3