RE: [PATCH v13 24/35] x86/fred: Add a NMI entry stub for FRED

2023-12-15 Thread Li, Xin3
> So we have recently discovered an overlooked interaction with VT-x. > Immediately before VMENTER and after VMEXIT, CR2 is live with the > *guest* CR2. Regardless of if the guest uses FRED or not, this is guest > state and SHOULD NOT be corrupted. Furthermore, host state MUST NOT leak > into the g

Re: [PATCH v13 24/35] x86/fred: Add a NMI entry stub for FRED

2023-12-14 Thread H. Peter Anvin
So we have recently discovered an overlooked interaction with VT-x. Immediately before VMENTER and after VMEXIT, CR2 is live with the *guest* CR2. Regardless of if the guest uses FRED or not, this is guest state and SHOULD NOT be corrupted. Furthermore, host state MUST NOT leak into the guest.