Richard Henderson writes:
> The old sparc64 implementation may replace two insns, which leaves
> a race condition in which a thread could be stopped at a PC in the
> middle of the sequence, and when restarted does not see the complete
> address computation and branches to nowhere.
>
> The new i
The old sparc64 implementation may replace two insns, which leaves
a race condition in which a thread could be stopped at a PC in the
middle of the sequence, and when restarted does not see the complete
address computation and branches to nowhere.
The new implemetation replaces only one insn, swap