Hi Andrew On Fri, Jun 26, 2015 at 6:25 PM, Andrew Jones <drjo...@redhat.com> wrote:
> This is only true with glibc < 2.19, > see glibc commit b20de2c3d9d751eb259c321426188eefc64fcbe9, "Properly > handle shm_open validation. Fixes bug 16274." > > Thanks, I made a patch to solve this on ivshmem-server side (This probably isn't the right place to bring this up, but...) > > Would it make sense to turn ivshmem into a frontend for the hostmem > backend? If we do that, then we can use hugetlbfs backed memory, and > possibly get other benefits as well, right? > Yes, this seems quite simple to do, will be in next update: https://github.com/elmarco/qemu/commit/d22138bebd5143b1729287265775d261f66b7178 -- Marc-André Lureau
