FWIW, I agree this is the right fix, but: Andrew Bennett <andrew.benn...@imgtec.com> writes: > + /* When using branch likely (-mfix-r10000), the delay slot instruction > + will be annulled on false. The normal delay slot instructions > + calculate the overall result of the atomic operation and must not > + be annulled. To ensure this behaviour unconditionally use a NOP > + in the delay slot for the branch likely case. */
remember to use US spelling: "behavior" rather than "behaviour". Thanks, Richard
