LU-16552 test: add new lnet test for Multi-Rail setups

You can crash lnet kernel module by setting up a interface with
lctl net up and then attempting to setup the interface with
the import function. This is due to improper clearing the net_cpts
array.

Currently sanity-lnet.sh doesn't real test MR setups. Because of
this a few bugs slipped in. Add two new test to ensure MR setups
behave properly. Test 107 is to see if deleting a second interface
for a MR setup doesn't crash a node. Test 108 creates a multi rail
setup of a tcp LNet net with two interfaces, one real and the
other fake. A bug was preventing the second fake interface from
being added.

Test-Parameters: trivial testlist=sanity-lnet
Change-Id: Ic69e14bd0617f4d6fe931140b5b6d43b795843cf
Signed-off-by: James Simmons <jsimmons@infradead.org>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/50302
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Reviewed-by: Serguei Smirnov <ssmirnov@whamcloud.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

diff --git a/lnet/lnet/config.c b/lnet/lnet/config.c
index d5eb3ed..25c3f47 100644 (file)
--- a/lnet/lnet/config.c
+++ b/lnet/lnet/config.c
@@ -327,8 +327,11 @@ lnet_net_free(struct lnet_net *net)
                lnet_ni_free(ni);
        }
 
-       if (net->net_cpts != NULL)
+       if (net->net_cpts != NULL) {
                CFS_FREE_PTR_ARRAY(net->net_cpts, net->net_ncpts);
+               net->net_ncpts = LNET_CPT_NUMBER;
+               net->net_cpts = NULL;
+       }
 
        LIBCFS_FREE(net, sizeof(*net));
 }

diff --git a/lustre/tests/sanity-lnet.sh b/lustre/tests/sanity-lnet.sh
index e7ae70f..d25b586 100755 (executable)
--- a/lustre/tests/sanity-lnet.sh
+++ b/lustre/tests/sanity-lnet.sh
@@ -1065,6 +1065,14 @@ add_net() {
                error "Failed to add net ${net} on if ${if}"
 }
 
+del_net() {
+       local net="$1"
+       local if="$2"
+
+       do_lnetctl net del --net ${net} --if ${if} ||
+               error "Failed to del net ${net} on if ${if}"
+}
+
 compare_route_add() {
        local rnet="$1"
        local gw="$2"
@@ -1314,6 +1322,62 @@ test_106() {
 }
 run_test 106 "Deleting GW peer should fail"
 
+test_107() {
+       [[ ${NETTYPE} == tcp* ]] || skip "Need tcp NETTYPE"
+
+       cleanup_netns || error "Failed to cleanup netns before test execution"
+       cleanup_lnet || error "Failed to unload modules before test execution"
+
+       setup_fakeif || error "Failed to add fake IF"
+       have_interface "$FAKE_IF" ||
+               error "Expect $FAKE_IF configured but not found"
+
+       reinit_dlc || return $?
+
+       add_net "tcp" "${INTERFACES[0]}" || return $?
+       add_net "tcp" "$FAKE_IF" || return $?
+
+       del_net "tcp" "$FAKE_IF" || return $?
+
+       cleanup_fakeif
+       cleanup_lnet
+       setup_netns
+}
+run_test 107 "Deleting extra interface doesn't crash node"
+
+test_108() {
+       [[ ${NETTYPE} == tcp* ]] || skip "Need tcp NETTYPE"
+
+       cleanup_netns || error "Failed to cleanup netns before test execution"
+       cleanup_lnet || error "Failed to unload modules before test execution"
+
+       setup_fakeif || error "Failed to add fake IF"
+       have_interface "$FAKE_IF" ||
+               error "Expect $FAKE_IF configured but not found"
+
+       reinit_dlc || return $?
+
+       add_net "tcp" "${INTERFACES[0]}" || return $?
+       $LNETCTL net show > $TMP/sanity-lnet-$testnum-expected.yaml
+       add_net "tcp" "$FAKE_IF" || return $?
+
+       cat <<EOF >> $TMP/sanity-lnet-$testnum-expected.yaml
+        - nid: ${FAKE_IP}@tcp
+          status: up
+          interfaces:
+              0: ${FAKE_IF}
+EOF
+       $LNETCTL net show > $TMP/sanity-lnet-$testnum-actual.yaml
+       compare_yaml_files || error "not all interfaces were setup"
+
+       cleanup_fakeif
+       cleanup_lnet
+       setup_netns
+
+       return 0
+}
+run_test 108 "Check Multi-Rail setup"
+
 test_200() {
        [[ ${NETTYPE} == tcp* ]] ||
                skip "Need tcp NETTYPE"