Commit Graph

4 Commits

Author SHA1 Message Date
Damien George 9e29217c73 unix/modffi: Use a union for passing/returning FFI values.
This fixes a bug where double arguments on a 32-bit architecture would not
be passed correctly because they only had 4 bytes of storage (not 8).  It
also fixes a compiler warning/error in return_ffi_value on certian
architectures: array subscript 'double[0]' is partly outside array bounds
of 'ffi_arg[1]' {aka 'long unsigned int[1]'}.

Fixes issue #7064.

Signed-off-by: Damien George <damien@micropython.org>
2021-05-06 12:17:10 +10:00
Paul Sokolovsky 5cb524673e tests/ffi_float: Split tgammaf() testcase to a separate test.
Some libc's may implement tgammaf as a header macro using tgamma(), so
don't assume it'll be in the library.
2015-08-29 17:24:29 +03:00
Damien George 6bbbb1ab41 unix/modffi: Support passing float/double args. 2015-04-28 19:40:34 +01:00
Damien George 17598d49e1 unix: Don't use -Wno-error=cpp or #warning; fix strict alias warning.
For the sake of older versions of gcc (and other compilers), don't use
the #warning CPP directive, nor the -Wno-error=cpp option.

Also, fix a strict alias warning in modffi.c for older compilers, and
add a test for ffi module.

Addresses issue #847.
2014-09-06 17:46:52 +01:00