Niklas Söderlund <niklas.soderlund@xxxxxxxxxxxx> writes: > Some warnings did not increment the warnings counter making the behavior > of running kernel-doc with -Werror unlogical as some warnings would be > generated but not treated as errors. > > Fix this by always incrementing the warnings counter every time a > warning related to the input documentation is generated. There is one > location in get_sphinx_version() where a warning is printed and the > counter is not touched as it concerns the execution environment of the > kernel-doc and not the documentation being processed. So this seems like an improvement, but I have to ask: wouldn't it be far better to just add a function to emit a warning and use that rather than all these print/++$warnings pairings? The current way seems repetitive and error-prone. I also have to ask... > Incrementing the counter only have effect when running kernel-doc in > either verbose mode (-v or environment variable KBUILD_VERBOSE) or when > treating warnings as errors (-Werror or environment variable > KDOC_WERROR). In both cases the number of warnings printed is printed to > stderr and for the later the exit code of kernel-doc is non-zero if > warnings where encountered. > > Simple test case to demo one of the warnings, > > $ cat test.c > /** > * foo() - Description > */ > int bar(); > > # Without this change > $ ./scripts/kernel-doc -Werror -none test.c > test.c:4: warning: expecting prototype for foo(). Prototype was for > bar() instead > > # With this change > $ ./scripts/kernel-doc -Werror -none test.c > test.c:4: warning: expecting prototype for foo(). Prototype was for > bar() instead > 1 warnings as Errors > > Signed-off-by: Niklas Söderlund <niklas.soderlund@xxxxxxxxxxxx> > Signed-off-by: Simon Horman <simon.horman@xxxxxxxxxxxx> > Signed-off-by: Louis Peens <louis.peens@xxxxxxxxxxxx> What does this signoff chain mean? If it really took three people to make this patch, then we need Co-developed-by tags to reflect that. Thanks, jon
