On Wed, 19 Feb 2020 at 19:59, Heinrich Schuchardt <xypron.glpk@xxxxxx> wrote: > > On 2/19/20 6:18 PM, Ard Biesheuvel wrote: > > The UEFI spec version 2.8 errata A defines a configuration table called > > EFI_RT_PROPERTIES_TABLE that carries a mask describing which EFI runtime > > services are still functional at OS runtime. > This configuration table defined in UEFI spec 2.8A is replacing the > RuntimeServicesSupported variable introduced in UEFI spec 2.8 (which is > already implemented in U-Boot). > Indeed. But using a variable was a mistake, and no OS implemented support for it yet, so we decided it was best to issue an errata and pretend that the variable never existed. > Replacing APIs as an "erratum" is unfortunate. > It was a dilemma. Having the two solutions co-exist was not a great prospect either. > I am wondering whether in your implementation you will have to check for > both the variable if the firmware implements UEFI 2.8 and for the table > if the firmware implements UEFI 2.8A. > No, Linux will only look for the config table - that was the whole point.
