On Thu, 21 Apr 2016, Paul Burton wrote: > Fix this by broadcasting an IPI if other CPUs may have live FP context > for an affected thread, with a handler causing those CPUs to relinquish > their FPU ownership. Threads will then be allowed to continue running > but will stall on the wait_on_atomic_t in enable_restore_fp_context if > they attempt to use FP again whilst the mode switch is still in > progress. The end result is less fragile poking at scheduler context > switch counts & a more expedient completion of the mode switch. Reviewed-by: Maciej W. Rozycki <macro@xxxxxxxxxx> Thanks, Paul, for your work on this problem! I'll rebase my outstanding NaN interlinking stuff (https://patchwork.linux-mips.org/patch/11491/) on top of your patches -- they address the concern expressed there. Maciej
