Messages in this thread | | | Date | Thu, 13 Oct 2022 13:05:09 -0700 | From | "H. Peter Anvin" <> | Subject | RE: [PATCH v2 1/6] x86/cpufeature: add cpu feature bit for LKGS |
| |
On October 13, 2022 12:35:23 PM PDT, "Li, Xin3" <xin3.li@intel.com> wrote: > >> > diff --git a/arch/x86/include/asm/cpufeatures.h >> > b/arch/x86/include/asm/cpufeatures.h >> > index ef4775c6db01..459fb0c21dd4 100644 >> > --- a/arch/x86/include/asm/cpufeatures.h >> > +++ b/arch/x86/include/asm/cpufeatures.h >> > @@ -308,6 +308,7 @@ >> > /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ >> > #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI >> instructions */ >> > #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 >> BFLOAT16 instructions */ >> > +#define X86_FEATURE_LKGS (12*32+ 18) /* Load "kernel" >> (userspace) gs */ >> >> The spec says [1]: >> "Execution of LKGS causes an invalid-opcode exception (#UD) if CPL > >> 0." >> >> Perhaps userspace has no interest in this. Then, we can add "" not to show >> "lkgs" in /proc/cpuinfo: >> +#define X86_FEATURE_LKGS (12*32+ 18) /* "" Load "kernel" >> (userspace) gs */ > >Good point! > >> >> Thanks, >> Chang >> >> [1] https://cdrdv2.intel.com/v1/dl/getContent/678938 >
It would be useful for reviewers to mention that this is was a policy change on the maintainers' part. This is totally valid, of course, but making it explicit would perhaps help reduce potential confusion.
| |