On 28 January 2014 01:28, Peter Crosthwaite <peter.crosthwaite@xxxxxxxxxx> wrote: > On Wed, Jan 22, 2014 at 6:12 AM, Peter Maydell <peter.maydell@xxxxxxxxxx> wrote: >> We already implicitly rely on the exception level being >> part of the TB flags for coprocessor access, > > Maybe that's the issue? Why not just treat the exception level as > state like any other and generate the TCG to just check it at > execution time? That would be ferociously expensive, because "am I privileged or not?" is baked into every single guest load or store. Including privilege level in the tb flags is standard for every target CPU we have. thanks -- PMM _______________________________________________ kvmarm mailing list kvmarm@xxxxxxxxxxxxxxxxxxxxx https://lists.cs.columbia.edu/cucslists/listinfo/kvmarm
