From bd9de1badac7e4ff6780365d4aa38983f5e2a436 Mon Sep 17 00:00:00 2001
From: Mark Zhang <markzhang@nvidia.com>
Date: Thu, 30 Mar 2023 10:23:51 +0300
Subject: [PATCH 1/1] RDMA/cm: Trace icm_send_rej event before the cm state is
 reset
Git-commit: bd9de1badac7e4ff6780365d4aa38983f5e2a436
Patch-mainline: v6.4-rc1
References: git-fixes

Trace icm_send_rej event before the cm state is reset to idle, so that
correct cm state will be logged. For example when an incoming request is
rejected, the old trace log was:
    icm_send_rej: local_id=961102742 remote_id=3829151631 state=IDLE reason=REJ_CONSUMER_DEFINED
With this patch:
    icm_send_rej: local_id=312971016 remote_id=3778819983 state=MRA_REQ_SENT reason=REJ_CONSUMER_DEFINED

Fixes: 8dc105befe16 ("RDMA/cm: Add tracepoints to track MAD send operations")
Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Link: https://lore.kernel.org/r/20230330072351.481200-1-markzhang@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Acked-by: Nicolas Morey <nmorey@suse.com>
---
 drivers/infiniband/core/cm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 603c0aecc361..ff58058aeadc 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -2912,6 +2912,8 @@ static int cm_send_rej_locked(struct cm_id_private *cm_id_priv,
 	    (ari && ari_length > IB_CM_REJ_ARI_LENGTH))
 		return -EINVAL;
 
+	trace_icm_send_rej(&cm_id_priv->id, reason);
+
 	switch (state) {
 	case IB_CM_REQ_SENT:
 	case IB_CM_MRA_REQ_RCVD:
@@ -2942,7 +2944,6 @@ static int cm_send_rej_locked(struct cm_id_private *cm_id_priv,
 		return -EINVAL;
 	}
 
-	trace_icm_send_rej(&cm_id_priv->id, reason);
 	ret = ib_post_send_mad(msg, NULL);
 	if (ret) {
 		cm_free_msg(msg);
-- 
2.39.1.1.gbe015eda0162