linux-kernel - Re: [PATCH] selftests/landlock: fix broken include of linux/landlock.h

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <c0c65ade-1d2a-5466-2c12-8e016904817f@digikod.net>
Date:   Fri, 12 Aug 2022 17:29:55 +0200
From:   Mickaël Salaün <mic@...ikod.net>
To:     Guillaume Tucker <guillaume.tucker@...labora.com>,
        Shuah Khan <shuah@...nel.org>
Cc:     Anders Roxell <anders.roxell@...aro.org>, Tim.Bird@...y.com,
        kernel@...labora.com, linux-kernel@...r.kernel.org,
        linux-kselftest@...r.kernel.org,
        linux-security-module@...r.kernel.org
Subject: Re: [PATCH] selftests/landlock: fix broken include of
 linux/landlock.h

Shuah, do you plan to send a pull request before merge window closes?

On 05/08/2022 19:16, Mickaël Salaün wrote:
> 
> On 04/08/2022 21:38, Guillaume Tucker wrote:
>> On 04/08/2022 12:36, Mickaël Salaün wrote:
>>>
>>> On 03/08/2022 22:13, Guillaume Tucker wrote:
>>>> Revert part of the earlier changes to fix the kselftest build when
>>>> using a sub-directory from the top of the tree as this broke the
>>>> landlock test build as a side-effect when building with "make -C
>>>> tools/testing/selftests/landlock".
>>>>
>>>> Reported-by: Mickaël Salaün <mic@...ikod.net>
>>>> Fixes: a917dd94b832 ("selftests/landlock: drop deprecated headers dependency")
>>>> Fixes: f2745dc0ba3d ("selftests: stop using KSFT_KHDR_INSTALL")
>>>> Signed-off-by: Guillaume Tucker <guillaume.tucker@...labora.com>
>>>> ---
>>>>     tools/testing/selftests/landlock/Makefile | 7 +++++--
>>>>     1 file changed, 5 insertions(+), 2 deletions(-)
>>>>
>>>> diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile
>>>> index a6959df28eb0..02868ac3bc71 100644
>>>> --- a/tools/testing/selftests/landlock/Makefile
>>>> +++ b/tools/testing/selftests/landlock/Makefile
>>>> @@ -9,10 +9,13 @@ TEST_GEN_PROGS := $(src_test:.c=)
>>>>     TEST_GEN_PROGS_EXTENDED := true
>>>>       OVERRIDE_TARGETS := 1
>>>> +top_srcdir := ../../../..
>>>
>>> Not sure it changes much, but most other selftests Makefiles use "top_srcdir = ../../../.." (without ":="). Why this change?
>>
>> I didn't simply apply your diff but edited the file by hand to
>> test various combinations and see what side effects it might
>> have.  So when I added top_srcdir I typed it by hand and used :=
>> as a reflex since it's the standard way of assigning variables.
>> Using = instead only makes a difference when the r-value has
>> something dynamic as it will be re-evaluated every time it's
>> used.  So for constant values, I guess it's more of a question of
>> coding style and conventions.  Maybe all the top_srcdir variables
>> should be changed to := but that's unnecessary churn...  Either
>> way, it's benign.
>>
>> Shuah, feel free to change this back to = in this particular case
>> if it's more consistent with other Makefiles.  Consistency is
>> often better than arbitrary rules.  Or conversely, change to :=
>> for the khdr_dir definition...  Entirely up to you I think.
> 
> Looks good to me, thanks! Shuah, feel free to add
> Signed-off-by: Mickaël Salaün <mic@...ikod.net>
> 
>>
>> Thanks,
>> Guillaume
>>
>>>>     include ../lib.mk
>>>>     +khdr_dir = $(top_srcdir)/usr/include
>>>> +
>>>>     $(OUTPUT)/true: true.c
>>>>         $(LINK.c) $< $(LDLIBS) -o $@ -static
>>>>     -$(OUTPUT)/%_test: %_test.c ../kselftest_harness.h common.h
>>>> -    $(LINK.c) $< $(LDLIBS) -o $@ -lcap
>>>> +$(OUTPUT)/%_test: %_test.c $(khdr_dir)/linux/landlock.h ../kselftest_harness.h common.h
>>>> +    $(LINK.c) $< $(LDLIBS) -o $@ -lcap -I$(khdr_dir)
>>