>> Changes in v2 (addressed comments from Kevin): >> - measure/estimate the impact to non-IPC-intensive cases >> - don't tie PID.SN to vcpu->mode. Instead, clear PID.SN >> right before VM-entry and set it after VM-exit. > >One correction here. My comment in v1 [1] was actually close to Sean's >suggestion, i.e. opposite to above description: Hi Kevin, Yes. The changelog is misleading. You suggested using a dedicate hook. And I indeed agreed to follow the suggestion. But as you said, what v2 does is the complete opposite of the suggestion. The reason is when I started v2 recently, the idea of clearing SN right before VM-entry came to my mind. Since it could also solve some problems of v1 without a hook (hence, more self-contained), I thought it was slightly better. But I missed that clearing SN right before VM-entry can cause unnecessary SN toggling to VM-exit fast-path.
