On Thu, 5 Nov 2020 18:50:51 +0800 Po-Hsu Lin wrote:
> This test will treat all non-zero return codes as failures, it will
> make the pmtu.sh test script being marked as FAILED when some
> sub-test got skipped.
>
> Improve the result processing by
> * Only mark the whole test script as SKIP when all of the
> sub-tests were skipped
> * If the sub-tests were either passed or skipped, the overall
> result will be PASS
> * If any of them has failed, the overall result will be FAIL
> * Treat other return codes (e.g. 127 for command not found) as FAIL
>
> Signed-off-by: Po-Hsu Lin <po-hsu.lin@xxxxxxxxxxxxx>
Patch 1 looks like a cleanup while patch 2 is more of a fix, can we
separate the two and apply the former to -next and latter to 5.10?
They shouldn't conflict, right?
> diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
> index fb53987..5c86fb1 100755
> --- a/tools/testing/selftests/net/pmtu.sh
> +++ b/tools/testing/selftests/net/pmtu.sh
> @@ -1652,7 +1652,23 @@ run_test() {
> return $ret
> )
> ret=$?
> - [ $ret -ne 0 ] && exitcode=1
> + case $ret in
> + 0)
> + all_skipped=false
> + [ $exitcode=$ksft_skip ] && exitcode=0
> + ;;
> + 1)
> + all_skipped=false
> + exitcode=1
> + ;;
Does it make sense to remove this case? The handling is identical to
the default case *).
> + $ksft_skip)
> + [ $all_skipped = true ] && exitcode=$ksft_skip
> + ;;
> + *)
> + all_skipped=false
> + exitcode=1
> + ;;
> + esac
>
> return $ret
> }
> @@ -1786,6 +1802,7 @@ usage() {
> #
> exitcode=0
> desc=0
> +all_skipped=true
>
> while getopts :ptv o
> do
