On 27/12/2017 16:33, Liran Alon wrote: > > > 2. Re-order patches to be similar to the following: > (a) Simple bug-fix for the race-condition issue: Just changing order > like I did in v1 and adding a kvm_vcpu_kick() like in patch 10 of this > series. > (b) Get rid of pi_pending and instead use virtual LAPIC IRR bit and > process it specially in case vCPU in non-root-mode & posted-interrupts > is active. > (c) Get rid of software simulation of nested posted-interrupts > processing and instead use self-IPI trick to make CPU process it for us. > > What do you think? Sounds good, in the meanwhile I can do 2(a) myself. Paolo
