On Wed, 12 Oct 2022 17:00:15 GMT, Andrew Haley <a...@openjdk.org> wrote:
>> A bug in GCC causes shared libraries linked with -ffast-math to disable >> denormal arithmetic. This breaks Java's floating-point semantics. >> >> The bug is https://gcc.gnu.org/bugzilla/show_bug.cgi?id=55522 >> >> One solution is to save and restore the floating-point control word around >> System.loadLibrary(). This isn't perfect, because some shared library might >> load another shared library at runtime, but it's a lot better than what we >> do now. >> >> However, this fix is not complete. `dlopen()` is called from many places in >> the JDK. I guess the best thing to do is find and wrap them all. I'd like to >> hear people's opinions. > > Andrew Haley has updated the pull request incrementally with one additional > commit since the last revision: > > 8295159: DSO created with -ffast-math breaks Java floating-point arithmetic There's another option to consider: check MXCSR register consistency at safepoints. It's already too late to fix the corruption (the damage could be already done and the only way to proceed is to initiate a JVM crash), but it should pretty reliably catch the corruption in a prompt manner (so far, by default JVM checks and adjusts MXCSR on x86-64 only during upcalls into Java). Also, looks like it should mix well with the fast approximate check on JNI calls (which should be able to catch & heal some of the possible corruptions). ------------- PR: https://git.openjdk.org/jdk/pull/10661
