In other words, if a program blocks SIGFPE, does something that
generates a floating-point exception, then clears the exception status
in FPSCR, then unblocks SIGFPE, should it get a SIGFPE signal
delivered to it at that point ?

AFAIK posix says that blocked signals have to be queued (at least one
of them) and that signals have to be delivered when those signals are
unblocked. I don't know if it makes sense about hardware signals, but
that's the spec.

I agree with the signal modes you proposed, but you should also
allow the user to set the 11 mode in some way. Debuggers could need that.


Bye.


** Sent via the linuxppc-dev mail list. See http://lists.linuxppc.org/