Re: [PATCH v2] RISC-V: Increase range and default value of NR_CPUS

[Atish Patra]

On Fri, Apr 8, 2022 at 9:45 AM Anup Patel <anup@xxxxxxxxxxxxxx> wrote:
>
> On Fri, Apr 8, 2022 at 10:08 PM Heinrich Schuchardt
> <heinrich.schuchardt@xxxxxxxxxxxxx> wrote:
> >
> > On 4/6/22 12:10, Anup Patel wrote:
> > > On Wed, Apr 6, 2022 at 3:25 PM Heinrich Schuchardt
> > > <heinrich.schuchardt@xxxxxxxxxxxxx> wrote:
> > >>
> > >> On 3/31/22 21:42, Palmer Dabbelt wrote:
> > >>> On Sat, 19 Mar 2022 05:12:06 PDT (-0700), apatel@xxxxxxxxxxxxxxxx wrote:
> > >>>> Currently, the range and default value of NR_CPUS is too restrictive
> > >>>> for high-end RISC-V systems with large number of HARTs. The latest
> > >>>> QEMU virt machine supports upto 512 CPUs so the current NR_CPUS is
> > >>>> restrictive for QEMU as well. Other major architectures (such as
> > >>>> ARM64, x86_64, MIPS, etc) have a much higher range and default
> > >>>> value of NR_CPUS.
> > >>>>
> > >>>> This patch increases NR_CPUS range to 2-512 and default value to
> > >>>> XLEN (i.e. 32 for RV32 and 64 for RV64).
> > >>>>
> > >>>> Signed-off-by: Anup Patel <apatel@xxxxxxxxxxxxxxxx>
> > >>>> ---
> > >>>> Changes since v1:
> > >>>>   - Updated NR_CPUS range to 2-512 which reflects maximum number of
> > >>>>     CPUs supported by QEMU virt machine.
> > >>>> ---
> > >>>>   arch/riscv/Kconfig | 7 ++++---
> > >>>>   1 file changed, 4 insertions(+), 3 deletions(-)
> > >>>>
> > >>>> diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> > >>>> index 5adcbd9b5e88..423ac17f598c 100644
> > >>>> --- a/arch/riscv/Kconfig
> > >>>> +++ b/arch/riscv/Kconfig
> > >>>> @@ -274,10 +274,11 @@ config SMP
> > >>>>         If you don't know what to do here, say N.
> > >>>>
> > >>>>   config NR_CPUS
> > >>>> -    int "Maximum number of CPUs (2-32)"
> > >>>> -    range 2 32
> > >>>> +    int "Maximum number of CPUs (2-512)"
> > >>>> +    range 2 512
> > >>
> > >> For SBI_V01=y there seems to be a hard constraint to XLEN bits.
> > >> See __sbi_v01_cpumask_to_hartmask() in rch/riscv/kernel/sbi.c.
> > >>
> > >> So shouldn't this be something like:
> > >>
> > >> range 2 512 !SBI_V01
> > >> range 2 32 SBI_V01 && 32BIT
> > >> range 2 64 SBI_V01 && 64BIT
> > >
> > > This is just making it unnecessarily complicated for supporting
> > > SBI v0.1
> > >
> > > How about removing SBI v0.1 support and the spin-wait CPU
> > > operations from arch/riscv ?
> >
> > The SBI v0.1 specification was only a draft. Only the v1.0 version has
> > ever been ratified.
> >
> > It would be good to remove this legacy code from Linux and U-Boot.
> >
> > By the way, why does upstream OpenSBI claim to be conformant to SBI v0.3
> > and not to v1.0?
>
> The ratification process for SBI v1.0 was in early stages when OpenSBI v1.0
> was being released so we decided to keep the SBI v0.3 spec version. The
> next OpenSBI v1.1 release (due in June 2022) will change to SBI v1.0
>

Yes. We are in the final stages of the official ratification of SBI
v1.0. Once that ratified version is released,
OpenSBI will be upgraded to support that.

> Regards,
> Anup
>
> >
> > include/sbi/sbi_ecall.h:16:
> >
> > #define SBI_ECALL_VERSION_MAJOR 0
> > #define SBI_ECALL_VERSION_MINOR 3
> >
> > Best regards
> >
> > Heinrich
> >
> > >
> > >>
> > >>>>       depends on SMP
> > >>>> -    default "8"
> > >>>> +    default "32" if 32BIT
> > >>>> +    default "64" if 64BIT
> > >>>>
> > >>>>   config HOTPLUG_CPU
> > >>>>       bool "Support for hot-pluggable CPUs"
> > >>>
> > >>> I'm getting all sorts of boot issues with more than 32 CPUs, even on the
> > >>> latest QEMU master.  I'm not opposed to increasing the CPU count in
> > >>> theory, but if we're going to have a setting that goes up to a huge
> > >>> number it needs to at least boot.  I've got 64 host threads, so it
> > >>> shouldn't just be a scheduling thing.
> > >>
> > >> Currently high performing hardware for RISC-V is missing. So it makes
> > >> sense to build software via QEMU on x86_64 or arm64 with as many
> > >> hardware threads as available (128 is not uncommon).
> > >>
> > >> OpenSBI currently is limited to 128 threads:
> > >> include/sbi/sbi_hartmask.h:22:
> > >> #define SBI_HARTMASK_MAX_BITS 128
> > >> This is just an arbitrary value we can be modified.
> > >
> > > Yes, this limit will be gradually increased with some improvements
> > > to optimize runtime memory used by OpenSBI.
> > >
> > >>
> > >> U-Boot v2022.04 qemu-riscv64_smode_defconfig has a value of
> > >> CONFIG_SYS_MALLOC_F_LEN that is to low. This leads to a boot failure for
> > >> more than 16 harts. A patch to correct this is pending:
> > >> [PATCH v2 1/1] riscv: alloc space exhausted
> > >> https://lore.kernel.org/u-boot/CAN5B=eKt=tFLZ2z3aNHJqsnJzpdA0oikcrC2i1_=ZDD=f+M0jA@xxxxxxxxxxxxxx/T/#t
> > >>
> > >> With QEMU 7.0 and the U-Boot fix booting into a 5.17 defconfig kernel
> > >> with 64 virtual cores worked fine for me.
> > >
> > > Thanks for trying this patch.
> > >
> > > Regards,
> > > Anup
> > >
> > >>
> > >> Best regards
> > >>
> > >> Heinrich
> > >>
> > >>>
> > >>> If there was some hardware that actually boots on these I'd be happy to
> > >>> take it, but given that it's just QEMU I'd prefer to sort out the bugs
> > >>> first.  It's probably just latent bugs somewhere, but allowing users to
> > >>> turn on configs we know don't work just seems like the wrong way to go.
> > >>>



-- 
Regards,
Atish