Re: [PATCH 3/3] MIPS: cpu-probe: Vulnerabilities for Loongson cores

[Jiaxun Yang]

在 2020/12/31 23:43, WANG Xuerui 写道:
> Hi Jiaxun,
>
> On 12/30/20 11:23 AM, Jiaxun Yang wrote:
> > Loongson64C is known to be vulnerable to meltdown according to
> > PoC from Rui Wang <r@xxxxxx>.
> >
> > Loongson64G defended these side-channel attack by silicon.
> "Loongson64G mitigated it in hardware"?
> > Signed-off-by: Jiaxun Yang <jiaxun.yang@xxxxxxxxxxx>
> > ---
> >   arch/mips/kernel/cpu-probe.c | 4 ++++
> >   1 file changed, 4 insertions(+)
> >
> > diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
> > index 2460783dbdb1..24b21f51353c 100644
> > --- a/arch/mips/kernel/cpu-probe.c
> > +++ b/arch/mips/kernel/cpu-probe.c
> > @@ -2092,6 +2092,8 @@ static inline void cpu_probe_loongson(struct 
> > cpuinfo_mips *c, unsigned int cpu)
> >           c->ases |= (MIPS_ASE_LOONGSON_MMI | MIPS_ASE_LOONGSON_CAM |
> >               MIPS_ASE_LOONGSON_EXT | MIPS_ASE_LOONGSON_EXT2);
> >           c->ases &= ~MIPS_ASE_VZ; /* VZ of Loongson-3A2000/3000 is 
> > incomplete */
> > +        c->vulnerabilities |= MIPS_VULNBL_MELTDOWN;
> > +        c->vulnerable |= MIPS_VULNBL_MELTDOWN;
> >           break;
> >       case PRID_IMP_LOONGSON_64G:
> >           c->cputype = CPU_LOONGSON64;
> > @@ -2100,6 +2102,8 @@ static inline void cpu_probe_loongson(struct 
> > cpuinfo_mips *c, unsigned int cpu)
> >           set_isa(c, MIPS_CPU_ISA_M64R2);
> >           decode_cpucfg(c);
> >           c->writecombine = _CACHE_UNCACHED_ACCELERATED;
> > +        c->vulnerabilities |= MIPS_VULNBL_MELTDOWN |
> > +                  MIPS_VULNBL_SPECTRE_V1 | MIPS_VULNBL_SPECTRE_V2;
>
> Of course you forgot to set the "mitigated" mask... Oh wait.

Hi Xuerui,

Actually it belongs to not affected category as there is no action
to take in kernel.

> It seems the "mitigated" mask in the 1st patch is never used, so 
> either code there or here must be amended.

Yes, it's just a place holder for future kernel mitigations~
Or I should leave it until we find out these mitigations?

Thanks.

- Jiaxun

> >           break;
> >       default:
> >           panic("Unknown Loongson Processor ID!");