linux-kernel - Re: [PATCH v3] ARM64: Dynamically allocate cpumasks and increase supported CPUs to 512

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date: Thu, 7 Mar 2024 17:49:12 +0000
From: Mark Rutland <mark.rutland@....com>
To: "Christoph Lameter (Ampere)" <cl@...two.org>, catalin.marinas@....com
Cc: Will Deacon <will@...nel.org>, Jonathan.Cameron@...wei.com,
	Matteo.Carlini@....com, Valentin.Schneider@....com,
	akpm@...ux-foundation.org, anshuman.khandual@....com,
	Eric Mackay <eric.mackay@...cle.com>, dave.kleikamp@...cle.com,
	linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
	linux-mm@...ck.org, linux@...linux.org.uk, robin.murphy@....com,
	vanshikonda@...amperecomputing.com, yang@...amperecomputing.com
Subject: Re: [PATCH v3] ARM64: Dynamically allocate cpumasks and increase
 supported CPUs to 512

Hi Christoph,

On Wed, Mar 06, 2024 at 05:45:04PM -0800, Christoph Lameter (Ampere) wrote:
> Currently defconfig selects NR_CPUS=256, but some vendors (e.g. Ampere
> Computing) are planning to ship systems with 512 CPUs. So that all CPUs on
> these systems can be used with defconfig, we'd like to bump NR_CPUS to 512.
> Therefore this patch increases the default NR_CPUS from 256 to 512.
> 
> As increasing NR_CPUS will increase the size of cpumasks, there's a fear that
> this might have a significant impact on stack usage due to code which places
> cpumasks on the stack. To mitigate that concern, we can select
> CPUMASK_OFFSTACK. As that doesn't seem to be a problem today with
> NR_CPUS=256, we only select this when NR_CPUS > 256.
> 
> CPUMASK_OFFSTACK configures the cpumasks in the kernel to be
> dynamically allocated. This was used in the X86 architecture in the
> past to enable support for larger CPU configurations up to 8k cpus.
> 
> With that is becomes possible to dynamically size the allocation of
> the cpu bitmaps depending on the quantity of processors detected on
> bootup. Memory used for cpumasks will increase if the kernel is
> run on a machine with more cores.
> 
> Further increases may be needed if ARM processor vendors start
> supporting more processors. Given the current inflationary trends
> in core counts from multiple processor manufacturers this may occur.
> 
> There are minor regressions for hackbench. The kernel data size
> for 512 cpus is smaller with offstack than with onstack.
> 
> Benchmark results using hackbench average over 10 runs of
> 
> 	hackbench -s 512 -l 2000 -g 15 -f 25 -P
> 
> on Altra 80 Core
> 
> Support for 256 CPUs on stack. Baseline
> 
> 	7.8564 sec
> 
> Support for 512 CUs on stack.
> 
> 	7.8713 sec + 0.18%
> 
> 512 CPUS offstack
> 
> 	7.8916 sec + 0.44%
> 
> Kernel size comparison:
> 
>    text		   data	    filename				Difference to onstack256 baseline
> 25755648	9589248	    vmlinuz-6.8.0-rc4-onstack256
> 25755648	9607680	    vmlinuz-6.8.0-rc4-onstack512	+0.19%
> 25755648	9603584	    vmlinuz-6.8.0-rc4-offstack512	+0.14%

Thanks for this data; I think that's a strong justification that this isn't
likely to cause a big problem for us, and so I thing it makes sense to go with
this.

I have two minor comments below.

> Tested-by: Eric Mackay <eric.mackay@...cle.com>
> Reviewed-by: Russell King (Oracle) <rmk+kernel@...linux.org.uk>
> Signed-off-by: Christoph Lameter (Ampere) <cl@...ux.com>
> ---
> 
> 
> Original post: https://www.spinics.net/lists/linux-mm/msg369701.html
> V2: https://lkml.org/lkml/2024/2/7/505
> 
> 
> V1->V2
> 
> - Keep quotation marks
> - Remove whiltespace damage
> - Add tested by
> 
> V2->V3:
> - Add test results
> - Rework descriptions
> 
> 
>  arch/arm64/Kconfig | 16 +++++++++++++++-
>  1 file changed, 15 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index aa7c1d435139..4e767dede47d 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -1427,7 +1427,21 @@ config SCHED_SMT
>  config NR_CPUS
>  	int "Maximum number of CPUs (2-4096)"
>  	range 2 4096
> -	default "256"
> +	default "512"
> +
> +#
> +# Determines the placement of cpumasks.
> +#
> +# With CPUMASK_OFFSTACK the cpumasks are dynamically allocated.
> +# Useful for machines with lots of core because it avoids increasing
> +# the size of many of the data structures in the kernel.
> +#
> +# If this is off then the cpumasks have a static sizes and are
> +# embedded within data structures.
> +#
> +	config CPUMASK_OFFSTACK
> +	def_bool y
> +	depends on NR_CPUS > 256

As before, can we please delete the comment? That's the general semantic of
CPUMASK_OFFSTACK, not why we're selecting it.

That aside, this config option is defined in lib/Kconfig, so we should select
it rather than redefining it. i.e. this should be:

	select CPUMASK_OFFSTACK if NR_CPUS > 256

Sorry for not spotting that before.

With those changes:

Acked-by: Mark Rutland <mark.rutland@....com>

Catalin, are you happy to fix that up when applying?

Mark.

> 
>  config HOTPLUG_CPU
>  	bool "Support for hot-pluggable CPUs"
> -- 
> 2.39.2
>