On Tue, Mar 27, 2018 at 7:22 PM, Richard Henderson < richard.hender...@linaro.org> wrote:
> Since it was my patch that broke FP state tracking in the > first place, I feel obligated to fix it again. > > Mark mstatus[fs] as dirty whenever we write to the file. > This can be optimized by only doing so once within a TB > which initially began with a clean file. > > I have not yet put together an environment that can test > this, so I'll need someone else to give it a go. > I have tested it with the simple test case running SMP Linux and it appears okay (Note it must be compiled with -O2): http://oirase.annexia.org/tmp/sched.c It is clearly broken without your two patches.
