Andi Kleen wrote:
>> +
>> + do {
>> + state_time = state->state_entry_time;
>> + barrier();
>>
>
> Should be likely rmb
We discussed this, and decided that it wasn't necessary. The state is
always updated by the current CPU, so if it changes under our feet it
will be because we were preempted, and so that should shoot down any
speculated reads.
J
_______________________________________________
Virtualization mailing list
Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linux-foundation.org/mailman/listinfo/virtualization
