On 10/12/21 3:57 AM, Paolo Bonzini wrote: > For bare-metal SGX on real hardware, the hardware provides guarantees > SGX state at reboot. For instance, all pages start out uninitialized. > The vepc driver provides a similar guarantee today for freshly-opened > vepc instances, but guests such as Windows expect all pages to be in > uninitialized state on startup, including after every guest reboot. > > Some userspace implementations of virtual SGX would rather avoid having > to close and reopen the /dev/sgx_vepc file descriptor and re-mmap the > virtual EPC. For example, they could sandbox themselves after the guest > starts and forbid further calls to open(), in order to mitigate exploits > from untrusted guests. > > Therefore, add a ioctl that does this with EREMOVE. Userspace can > invoke the ioctl to bring its vEPC pages back to uninitialized state. > There is a possibility that some pages fail to be removed if they are > SECS pages, and the child and SECS pages could be in separate vEPC > regions. Therefore, the ioctl returns the number of EREMOVE failures, > telling userspace to try the ioctl again after it's done with all > vEPC regions. A more verbose description of the correct usage and > the possible error conditions is documented in sgx.rst. > > Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx> The new approach and revised changelogs look fine to me: Reviewed-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx> Like Jarkko mentioned, it would be _nice_ to have some self-contained selftests around this. Would it be a pain to rig something up in selftests/kvm that at least trivially poked at /dev/sgx_vepc?
