On Fri, Dec 9, 2016 at 11:10 AM, Florian Weimer <fweimer@xxxxxxxxxx> wrote: > We would like to enable hardware-assisted lock optimizations in glibc on > multiple architectures. In general, this feature works only on production > hardware with current firmware, and not on pre-production machines some > vendors provide for architecture bringup. Have you got an overview of the required instructions/generations of CPU architecture needed for each different architecture by chance? >From there it might be easier to give details of where all the build HW is at. In the case of build VMs (x86/aarch64/Power64) does this need to be emulated by qemu/kvm or is it passed through from the host CPU? > Are the Fedora builders using hardware with support contracts, and are > vendor firmware updates applied occasionally, so that we can rely on what > the CPU/firmware reports about CPU features? (Some vendors had to disable > lock optimizations through firmware updates because the CPU implementation > was buggy.) > > Do we at least apply microcode updates early during Linux boot on the > builders? Only for x86, the cpu microcode update utility is only supported on that architecture. I believe all the other architectures apply any CPU firmware via the OS firmware/BIOS/what ever it's called on the various platforms. > What about default Fedora installations? Do they come with early boot > microcode updates? See the microcode_ctl package. > If all this is covered on the Fedora side, we probably can just enable lock > optimizations, and we do not need to implement complicated hardware > blacklisting. All builders run Fedora, some are physical hardware, some are VMs running on a RHEL hypervisor. As I mentioned above what does the virtual hardware need to support in this regard? Have you got some upstream docs about it for the various architectures? Peter _______________________________________________ devel mailing list -- devel@xxxxxxxxxxxxxxxxxxxxxxx To unsubscribe send an email to devel-leave@xxxxxxxxxxxxxxxxxxxxxxx
