From 43f0058037a376c0d5a4f0b88ac4b095dee84e19 Mon Sep 17 00:00:00 2001
From: Amir Shehata <amir.shehata@intel.com>
Date: Tue, 23 May 2017 17:15:49 -0700
Subject: [PATCH] LU-9549 lnet: prevent assert on ln_state

lnet_peer_primary_nid() is called from lnet_parse. It checks
ln_state outside the net lock, causing a race condition
during shutdown where the code expects the state to be
running, but it's stopping or shutdown.

Fixed the issue by renaming lnet_peer_primary_nid() to
lnet_peer_primary_nid_locked(). This function is now called
when lnet_net_lock is held in lnet_parse().

In lnet_create_reply_msg() we already have access to the
msg_txpeer, so we lookup the primary_nid directly

Signed-off-by: Amir Shehata <amir.shehata@intel.com>
Change-Id: I0518cdbec95b38bd8690517320b601676ae259f0
Reviewed-on: https://review.whamcloud.com/27262
Tested-by: Jenkins
Tested-by: Maloo <hpdd-maloo@intel.com>
Reviewed-by: Doug Oucharek <doug.s.oucharek@intel.com>
Reviewed-by: Sonia Sharma <sonia.sharma@intel.com>
Reviewed-by: Olaf Weber <olaf.weber@hpe.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
---
 lnet/include/lnet/lib-lnet.h | 2 +-
 lnet/lnet/lib-move.c         | 7 +++----
 lnet/lnet/peer.c             | 5 +----
 3 files changed, 5 insertions(+), 9 deletions(-)

diff --git a/lnet/include/lnet/lib-lnet.h b/lnet/include/lnet/lib-lnet.h
index 37a0b11608..ee75b198c3 100644
--- a/lnet/include/lnet/lib-lnet.h
+++ b/lnet/include/lnet/lib-lnet.h
@@ -805,7 +805,7 @@ struct lnet_peer_ni *lnet_nid2peerni_locked(lnet_nid_t nid, int cpt);
 struct lnet_peer_ni *lnet_nid2peerni_ex(lnet_nid_t nid, int cpt);
 struct lnet_peer_ni *lnet_find_peer_ni_locked(lnet_nid_t nid);
 void lnet_peer_net_added(struct lnet_net *net);
-lnet_nid_t lnet_peer_primary_nid(lnet_nid_t nid);
+lnet_nid_t lnet_peer_primary_nid_locked(lnet_nid_t nid);
 void lnet_peer_tables_cleanup(struct lnet_net *net);
 void lnet_peer_uninit(void);
 int lnet_peer_tables_create(void);
diff --git a/lnet/lnet/lib-move.c b/lnet/lnet/lib-move.c
index 9dc6565353..b05df552f5 100644
--- a/lnet/lnet/lib-move.c
+++ b/lnet/lnet/lib-move.c
@@ -2524,8 +2524,6 @@ lnet_parse(struct lnet_ni *ni, struct lnet_hdr *hdr, lnet_nid_t from_nid,
 		msg->msg_hdr.dest_pid	= dest_pid;
 		msg->msg_hdr.payload_length = payload_length;
 	}
-	/* Multi-Rail: Primary NID of source. */
-	msg->msg_initiator = lnet_peer_primary_nid(src_nid);
 
 	lnet_net_lock(cpt);
 	lpni = lnet_nid2peerni_locked(from_nid, cpt);
@@ -2544,6 +2542,8 @@ lnet_parse(struct lnet_ni *ni, struct lnet_hdr *hdr, lnet_nid_t from_nid,
 	msg->msg_rxpeer = lpni;
 	msg->msg_rxni = ni;
 	lnet_ni_addref_locked(ni, cpt);
+	/* Multi-Rail: Primary NID of source. */
+	msg->msg_initiator = lnet_peer_primary_nid_locked(src_nid);
 
 	if (lnet_isrouter(msg->msg_rxpeer)) {
 		lnet_peer_set_alive(msg->msg_rxpeer);
@@ -2845,8 +2845,7 @@ lnet_create_reply_msg(struct lnet_ni *ni, struct lnet_msg *getmsg)
 	       libcfs_nid2str(ni->ni_nid), libcfs_id2str(peer_id), getmd);
 
 	/* setup information for lnet_build_msg_event */
-	msg->msg_initiator = lnet_peer_primary_nid(peer_id.nid);
-	/* Cheaper: msg->msg_initiator = getmsg->msg_txpeer->lp_nid; */
+	msg->msg_initiator = getmsg->msg_txpeer->lpni_peer_net->lpn_peer->lp_primary_nid;
 	msg->msg_from = peer_id.nid;
 	msg->msg_type = LNET_MSG_GET; /* flag this msg as an "optimized" GET */
 	msg->msg_hdr.src_nid = peer_id.nid;
diff --git a/lnet/lnet/peer.c b/lnet/lnet/peer.c
index 47e5ce26d8..612af87d47 100644
--- a/lnet/lnet/peer.c
+++ b/lnet/lnet/peer.c
@@ -587,19 +587,16 @@ lnet_peer_is_ni_pref_locked(struct lnet_peer_ni *lpni, struct lnet_ni *ni)
 }
 
 lnet_nid_t
-lnet_peer_primary_nid(lnet_nid_t nid)
+lnet_peer_primary_nid_locked(lnet_nid_t nid)
 {
 	struct lnet_peer_ni *lpni;
 	lnet_nid_t primary_nid = nid;
-	int cpt;
 
-	cpt = lnet_net_lock_current();
 	lpni = lnet_find_peer_ni_locked(nid);
 	if (lpni) {
 		primary_nid = lpni->lpni_peer_net->lpn_peer->lp_primary_nid;
 		lnet_peer_ni_decref_locked(lpni);
 	}
-	lnet_net_unlock(cpt);
 
 	return primary_nid;
 }
-- 
GitLab