Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
Message-ID: <cd8d6641-4a29-7deb-49ae-a80baab0344f@canonical.com>
Date:   Wed, 6 Apr 2022 11:55:43 +0200
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.7.0
Subject: Re: [PATCH v2] RISC-V: Increase range and default value of NR_CPUS
Content-Language: en-US
To:     Palmer Dabbelt <palmer@dabbelt.com>
Cc:     Paul Walmsley <paul.walmsley@sifive.com>,
        Arnd Bergmann <arnd@arndb.de>, atishp@atishpatra.org,
        Alistair Francis <Alistair.Francis@wdc.com>,
        anup@brainfault.org, linux-riscv@lists.infradead.org,
        linux-kernel@vger.kernel.org, apatel@ventanamicro.com
References: <mhng-9cbb2a46-8bcb-4bfe-b927-0ed469dbd3a6@palmer-mbp2014>
From:   Heinrich Schuchardt <heinrich.schuchardt@canonical.com>
In-Reply-To: <mhng-9cbb2a46-8bcb-4bfe-b927-0ed469dbd3a6@palmer-mbp2014>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Precedence: bulk

On 3/31/22 21:42, Palmer Dabbelt wrote:
> On Sat, 19 Mar 2022 05:12:06 PDT (-0700), apatel@ventanamicro.com 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@ventanamicro.com>
>> ---
>> 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

>>      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.

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@mail.gmail.com/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.

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