ktest: introduce REBOOT_RETURN_CODE to confirm the result of REBOOT

Unexpected power cycle occurs while the installation of the
kernel.

   ssh root@Test sync ... [0 seconds] SUCCESS
   ssh root@Test reboot ... [1 second] FAILED!
   virsh destroy Test; sleep 5; virsh start Test ... [6 seconds] SUCCESS

That is because REBOOT, the default is "ssh $SSH_USER@$MACHINE
reboot", exits as 255 even if the reboot is successfully done,
like as:

   ]# ssh root@Test reboot
   Connection to Test closed by remote host.
   ]# echo $?
   255
   ]#

To avoid the unexpected power cycle, introduce a new parameter,
REBOOT_RETURN_CODE to judge whether REBOOT is successfully done
or not.

Link: http://lkml.kernel.org/r/20190418135943.12640-1-msys.mizuma@gmail.com

Signed-off-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>

2 files changed, 13 insertions, 0 deletions

diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 3bec099a6cf4..275ad8ac8872 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -58,6 +58,7 @@ my %default = (
     "SCP_TO_TARGET"             => "scp \$SRC_FILE \$SSH_USER\@\$MACHINE:\$DST_FILE",
     "SCP_TO_TARGET_INSTALL"     => "\${SCP_TO_TARGET}",
     "REBOOT"                    => "ssh \$SSH_USER\@\$MACHINE reboot",
+    "REBOOT_RETURN_CODE"        => 255,
     "STOP_AFTER_SUCCESS"        => 10,
     "STOP_AFTER_FAILURE"        => 60,
     "STOP_TEST_AFTER"           => 600,
@@ -105,6 +106,7 @@ my $reboot_type;
 my $reboot_script;
 my $power_cycle;
 my $reboot;
+my $reboot_return_code;
 my $reboot_on_error;
 my $switch_to_good;
 my $switch_to_test;
@@ -278,6 +280,7 @@ my %option_map = (
     "POST_BUILD_DIE"            => \$post_build_die,
     "POWER_CYCLE"               => \$power_cycle,
     "REBOOT"                    => \$reboot,
+    "REBOOT_RETURN_CODE"        => \$reboot_return_code,
     "BUILD_NOCLEAN"             => \$noclean,
     "MIN_CONFIG"                => \$minconfig,
     "OUTPUT_MIN_CONFIG"         => \$output_minconfig,
@@ -1749,6 +1752,7 @@ sub run_command {
     my $dord = 0;
     my $dostdout = 0;
     my $pid;
+    my $command_orig = $command;
 
     $command =~ s/\$SSH_USER/$ssh_user/g;
     $command =~ s/\$MACHINE/$machine/g;
@@ -1803,6 +1807,11 @@ sub run_command {
     # shift 8 for real exit status
     $run_command_status = $? >> 8;
 
+    if ($command_orig eq $default{REBOOT} &&
+        $run_command_status == $reboot_return_code) {
+        $run_command_status = 0;
+    }
+
     close(CMD);
     close(LOG) if ($dolog);
     close(RD)  if ($dord);
diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf
index 6ca6ca0ce695..8c893a58b68e 100644
--- a/tools/testing/ktest/sample.conf
+++ b/tools/testing/ktest/sample.conf
@@ -887,6 +887,10 @@
 # The variables SSH_USER and MACHINE are defined.
 #REBOOT = ssh $SSH_USER@$MACHINE reboot
 
+# The return code of REBOOT
+# (default 255)
+#REBOOT_RETURN_CODE = 255
+
 # The way triple faults are detected is by testing the kernel
 # banner. If the kernel banner for the kernel we are testing is
 # found, and then later a kernel banner for another kernel version