Re: Meson build leaks host 'sh' path to target build when cross-compiled

[Patrick Steinhardt <ps@pks.im>]

On Sun, Feb 09, 2025 at 01:30:27PM +0100, Peter Seiderer wrote:
[snip]
>   The meson build tries to execute the non-existent '/usr/bin/sh' (instead of
>   '/bin/sh' as the autoconf build), 'which sh' on the host returns
>   '/usr/bin/sh'...
> 
>   From meson.build
> 
>    [...]
>    186 shell = find_program('sh', dirs: program_path)
>    [...]
>    685   '-DSHELL_PATH="' + fs.as_posix(shell.full_path()) + '"',
> 
>   Do not use the result of 'find_program('sh',...)' for '-DSHELL_PATH='
>   (at least not for cross-compile), use fix '/bin/sh' instead or make it
>   configurable via a meson option?

Hm, very true. We're mixing up concerns here by treating the build
environment and the target environment the same.

I guess the proper fix is to wire up the "native:" parameter when we
call `find_program()`, which allows us to tell Meson whether it should
find an executable for the build or the target host. And then, for those
binaries where we actually need to know about both the build and target
host's locations, we'd end up calling `find_program()` twice.

For executables that are supposed to be used on the target host Meson
would then know to first consult the cross file, which could look like
this:

    [binaries]
    sh = '/target/path/to/sh'
    perl = '/target/path/to/perl'

Meson would then pick up that file via `meson setup --cross-file
<CROSSFILE_PATH> <BUILDDIR>`.

The patch should look somewhat like the attached patch, but it conflicts
with my in-flight patch series at [1]. I'll wait for that series to be
merged to `next` before sending out the fix.

Thanks for your report!

Patrick

[1]: <20250129-b4-pks-meson-improvements-v1-0-ab709f0be12c@pks.im>

-- >8 --

diff --git a/Documentation/meson.build b/Documentation/meson.build
index c6117366ff..b033f4a93a 100644
--- a/Documentation/meson.build
+++ b/Documentation/meson.build
@@ -206,9 +206,9 @@ manpages = {
 
 docs_backend = get_option('docs_backend')
 if docs_backend == 'auto'
-  if find_program('asciidoc', dirs: program_path, required: false).found()
+  if find_program('asciidoc', dirs: program_path, native: true, required: false).found()
     docs_backend = 'asciidoc'
-  elif find_program('asciidoctor', dirs: program_path, required: false).found()
+  elif find_program('asciidoctor', dirs: program_path, native: true, required: false).found()
     docs_backend = 'asciidoctor'
   else
     error('Neither asciidoc nor asciidoctor were found.')
@@ -216,7 +216,7 @@ if docs_backend == 'auto'
 endif
 
 if docs_backend == 'asciidoc'
-  asciidoc = find_program('asciidoc', dirs: program_path)
+  asciidoc = find_program('asciidoc', native: true, dirs: program_path)
   asciidoc_html = 'xhtml11'
   asciidoc_docbook = 'docbook'
   xmlto_extra = [ ]
@@ -245,7 +245,7 @@ if docs_backend == 'asciidoc'
     asciidoc_conf,
   ]
 elif docs_backend == 'asciidoctor'
-  asciidoctor = find_program('asciidoctor', dirs: program_path)
+  asciidoctor = find_program('asciidoctor', native: true, dirs: program_path)
   asciidoc_html = 'xhtml5'
   asciidoc_docbook = 'docbook5'
   xmlto_extra = [
@@ -283,7 +283,7 @@ elif docs_backend == 'asciidoctor'
   ]
 endif
 
-xmlto = find_program('xmlto', dirs: program_path)
+xmlto = find_program('xmlto', dirs: program_path, native: true)
 
 cmd_lists = [
   'cmds-ancillaryinterrogators.txt',
@@ -404,7 +404,7 @@ if get_option('docs').contains('html')
     pointing_to: 'git.html',
   )
 
-  xsltproc = find_program('xsltproc', dirs: program_path)
+  xsltproc = find_program('xsltproc', dirs: program_path, native: true)
 
   user_manual_xml = custom_target(
     command: asciidoc_common_options + [
diff --git a/gitweb/meson.build b/gitweb/meson.build
index 89b403dc9d..88a54b4dc9 100644
--- a/gitweb/meson.build
+++ b/gitweb/meson.build
@@ -1,5 +1,5 @@
 gitweb_config = configuration_data()
-gitweb_config.set_quoted('PERL_PATH', perl.full_path())
+gitweb_config.set_quoted('PERL_PATH', target_perl.full_path())
 gitweb_config.set_quoted('CSSMIN', '')
 gitweb_config.set_quoted('JSMIN', '')
 gitweb_config.set_quoted('GIT_BINDIR', get_option('prefix') / get_option('bindir'))
diff --git a/meson.build b/meson.build
index e153a43918..5a5662bc02 100644
--- a/meson.build
+++ b/meson.build
@@ -173,7 +173,7 @@ project('git', 'c',
   # The version is only of cosmetic nature, so if we cannot find a shell yet we
   # simply don't set up a version at all. This may be the case for example on
   # Windows systems, where we first have to bootstrap the host environment.
-  version: find_program('sh', required: false).found() ? run_command(
+  version: find_program('sh', native: true, required: false).found() ? run_command(
     'GIT-VERSION-GEN', meson.current_source_dir(), '--format=@GIT_VERSION@',
     capture: true,
     check: true,
@@ -198,16 +198,18 @@ elif host_machine.system() == 'windows'
   program_path = [ 'C:/Program Files/Git/bin', 'C:/Program Files/Git/usr/bin' ]
 endif
 
-cygpath = find_program('cygpath', dirs: program_path, required: false)
-diff = find_program('diff', dirs: program_path)
-git = find_program('git', dirs: program_path, required: false)
-sed = find_program('sed', dirs: program_path)
-shell = find_program('sh', dirs: program_path)
-tar = find_program('tar', dirs: program_path)
+cygpath = find_program('cygpath', dirs: program_path, native: true, required: false)
+diff = find_program('diff', dirs: program_path, native: true)
+git = find_program('git', dirs: program_path, native: true, required: false)
+sed = find_program('sed', dirs: program_path, native: true)
+shell = find_program('sh', dirs: program_path, native: true)
+tar = find_program('tar', dirs: program_path, native: true)
+
+target_shell = find_program('sh', dirs: program_path, native: false)
 
 # Sanity-check that programs required for the build exist.
 foreach tool : ['cat', 'cut', 'grep', 'sort', 'tr', 'uname']
-  find_program(tool, dirs: program_path)
+  find_program(tool, dirs: program_path, native: true)
 endforeach
 
 script_environment = environment()
@@ -758,6 +760,7 @@ endif
 build_options_config.set_quoted('X', executable_suffix)
 
 python = import('python').find_installation('python3', required: get_option('python'))
+target_python = find_program('python3', native: false, required: python.found())
 if python.found()
   build_options_config.set('NO_PYTHON', '')
 else
@@ -775,7 +778,8 @@ endif
 
 # Note that we only set NO_PERL if the Perl features were disabled by the user.
 # It may not be set when we have found Perl, but only use it to run tests.
-perl = find_program('perl', version: '>=5.8.1', dirs: program_path, required: perl_required)
+perl = find_program('perl', version: '>=5.8.1', dirs: program_path, native: true, required: perl_required)
+target_perl = find_program('perl', version: '>=5.8.1', native: false, required: perl.found())
 perl_features_enabled = perl.found() and get_option('perl').allowed()
 if perl_features_enabled
   build_options_config.set('NO_PERL', '')
@@ -825,7 +829,7 @@ else
   build_options_config.set('NO_PTHREADS', '1')
 endif
 
-msgfmt = find_program('msgfmt', dirs: program_path, required: false)
+msgfmt = find_program('msgfmt', dirs: program_path, native: true, required: false)
 gettext_option = get_option('gettext').disable_auto_if(not msgfmt.found())
 if not msgfmt.found() and gettext_option.enabled()
   error('Internationalization via libintl requires msgfmt')
@@ -1954,9 +1958,9 @@ foreach key, value : {
   'GIT_TEST_TEMPLATE_DIR': meson.project_build_root() / 'templates',
   'GIT_TEST_TEXTDOMAINDIR': meson.project_build_root() / 'po',
   'PAGER_ENV': get_option('pager_environment'),
-  'PERL_PATH': perl.found() ? perl.full_path() : '',
-  'PYTHON_PATH': python.found () ? python.full_path() : '',
-  'SHELL_PATH': shell.full_path(),
+  'PERL_PATH': target_perl.found() ? target_perl.full_path() : '',
+  'PYTHON_PATH': target_python.found () ? target_python.full_path() : '',
+  'SHELL_PATH': target_shell.full_path(),
   'TAR': tar.full_path(),
   'TEST_OUTPUT_DIRECTORY': test_output_directory,
   'TEST_SHELL_PATH': shell.full_path(),
diff --git a/templates/meson.build b/templates/meson.build
index 1faf9a44ce..986c2e03be 100644
--- a/templates/meson.build
+++ b/templates/meson.build
@@ -1,6 +1,6 @@
 template_config = configuration_data()
-template_config.set('PERL_PATH', perl.found() ? fs.as_posix(perl.full_path()) : '')
-template_config.set('SHELL_PATH', fs.as_posix(shell.full_path()))
+template_config.set('PERL_PATH', perl.found() ? fs.as_posix(target_perl.full_path()) : '')
+template_config.set('SHELL_PATH', fs.as_posix(target_shell.full_path()))
 template_config.set('GITWEBDIR', fs.as_posix(get_option('prefix') / get_option('datadir') / 'gitweb'))
 
 configure_file(