[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <3de9a64e-6f27-8f76-9626-6ee082d382ea@digikod.net>
Date: Fri, 5 Aug 2022 19:16:04 +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
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)
>
Powered by blists - more mailing lists