Re: [PATCH v2] RISC-V: Don't trust V from the riscv,isa DT property on T-Head CPUs

[Guo Ren <guoren@kernel.org>]

On Thu, Jul 13, 2023 at 12:48 PM Jisheng Zhang <jszhang@kernel.org> wrote:
>
> On Wed, Jul 12, 2023 at 06:48:02PM +0100, Conor Dooley wrote:
> > From: Palmer Dabbelt <palmer@rivosinc.com>
> >
> > The last merge window contained both V support and the deprecation of
> > the riscv,isa DT property, with the V implementation reading riscv,isa
> > to determine the presence of the V extension.  At the time that was the
> > only way to do it, but there's a lot of ambiguity around V in ISA
> > strings.  In particular, there is a lot of firmware in the wild that
> > uses "v" in the riscv,isa DT property to communicate support for the
> > 0.7.1 version of the Vector specification implemented by T-Head CPU
> > cores.
>
> Add Guo
>
> Hi Conor, Palmer,
>
> FWICT, new T-HEAD's riscv cores such as C908 support standard RVV-1.0,
> this patch looks like a big hammer for T-HEAD. I do understand why
> this patch is provided, but can we mitigate the situation by carefully
> review the DTs? Per my understanding, dts is also part of linux kernel.
>
> Thanks
>
> >
> > Rather than forcing use of the newly added interface that has strict
> > meanings for extensions to detect the presence of vector support, as
> > that would penalise those who have behaved, only ignore v in riscv,isa
> > on CPUs that report T-Head's vendor ID.
> >
> > Fixes: dc6667a4e7e3 ("riscv: Extending cpufeature.c to detect V-extension")
> > Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
> > Co-developed-by: Conor Dooley <conor.dooley@microchip.com>
> > Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
> > ---
> > Changes in v2:
> > - Use my version of the patch that touches hwcap and isainfo uniformly
> > - Don't penalise those who behaved
> > ---
> >  arch/riscv/kernel/cpufeature.c | 22 ++++++++++++++++++++++
> >  1 file changed, 22 insertions(+)
> >
> > diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
> > index bdcf460ea53d..05362715e1b7 100644
> > --- a/arch/riscv/kernel/cpufeature.c
> > +++ b/arch/riscv/kernel/cpufeature.c
> > @@ -21,6 +21,7 @@
> >  #include <asm/hwcap.h>
> >  #include <asm/patch.h>
> >  #include <asm/processor.h>
> > +#include <asm/sbi.h>
> >  #include <asm/vector.h>
> >
> >  #define NUM_ALPHA_EXTS ('z' - 'a' + 1)
> > @@ -334,6 +335,27 @@ void __init riscv_fill_hwcap(void)
> >                       set_bit(RISCV_ISA_EXT_ZIHPM, isainfo->isa);
> >               }
> >
> > +             /*
> > +              * "V" in ISA strings is ambiguous in practice: it should mean
> > +              * just the standard V-1.0 but vendors aren't well behaved.
> > +              * Many vendors with T-Head CPU cores which implement the 0.7.1
> > +              * version of the vector specification put "v" into their DTs
> > +              * and no T-Head CPU cores with the standard version of vector
> > +              * are in circulation yet.
T-HEAD's vector 1.0 SoCs is in circulation. Kendryte K230 is the
shipped SoC chip, which vendor id = THEAD_VENDOR_ID and with vector
1.0.

> > +              * Platforms with T-Head CPU cores that support the standard
> > +              * version of vector must provide the explicit V property,
> > +              * which is well defined.
> > +              */
> > +             if (acpi_disabled && riscv_cached_mvendorid(cpu) == THEAD_VENDOR_ID) {
If you insist on doing this, please:

if (acpi_disabled && riscv_cached_mvendorid(cpu) == THEAD_VENDOR_ID &&
riscv_cached_marchid(cpu) == 0 && riscv_cached_mimpid(cpu) == 0) {

> > +                     if (of_property_match_string(node, "riscv,isa-extensions", "v") >= 0) {
> > +                             this_hwcap |= isa2hwcap[RISCV_ISA_EXT_v];
> > +                             set_bit(RISCV_ISA_EXT_v, isainfo->isa);
> > +                     } else {
> > +                             this_hwcap &= ~isa2hwcap[RISCV_ISA_EXT_v];
> > +                             clear_bit(RISCV_ISA_EXT_v, isainfo->isa);
> > +                     }
> > +             }
> > +
> >               /*
> >                * All "okay" hart should have same isa. Set HWCAP based on
> >                * common capabilities of every "okay" hart, in case they don't
> > --
> > 2.39.2
> >
> >
> > _______________________________________________
> > linux-riscv mailing list
> > linux-riscv@lists.infradead.org
> > http://lists.infradead.org/mailman/listinfo/linux-riscv



-- 
Best Regards
 Guo Ren

_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv