Message-ID: <89c7106e-a431-443a-9527-3d5fbce77fe1@samsung.com>
Date: Fri, 21 Nov 2025 23:56:44 +0100
From: Marek Szyprowski <m.szyprowski@...sung.com>
To: Thomas Gleixner <tglx@...utronix.de>, LKML
	<linux-kernel@...r.kernel.org>
Cc: Peter Zijlstra <peterz@...radead.org>, Gabriele Monaco
	<gmonaco@...hat.com>, Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
	Michael Jeanson <mjeanson@...icios.com>, Jens Axboe <axboe@...nel.dk>, "Paul
 E. McKenney" <paulmck@...nel.org>, "Gautham R. Shenoy"
	<gautham.shenoy@....com>, Florian Weimer <fweimer@...hat.com>, Tim Chen
	<tim.c.chen@...el.com>, Yury Norov <yury.norov@...il.com>, Shrikanth Hegde
	<sshegde@...ux.ibm.com>
Subject: Re: [patch V5 09/20] cpumask: Cache num_possible_cpus()

Hi

On 19.11.2025 18:27, Thomas Gleixner wrote:
> Reevaluating num_possible_cpus() over and over does not make sense. That
> becomes a constant after init as cpu_possible_mask is marked ro_after_init.
>
> Cache the value during initialization and provide that for consumption.
>
> Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
> Reviewed-by: Yury Norov <yury.norov@...il.com>
> Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
> Reviewed-by: Shrikanth Hegde <sshegde@...ux.ibm.com>

This patch landed recently in linux-next as commit d0f23ccf6ba9 
("cpumask: Cache num_possible_cpus()"). I found that it triggers the 
following warning during boot on some of my test systems (namely 
Raspberry Pi 3 and 4):

kvm [1]: nv: 568 coarse grained trap handlers
kvm [1]: IPA Size Limit: 40 bits
------------[ cut here ]------------
WARNING: CPU: 1 PID: 1 at arch/arm64/kvm/vmid.c:183 
kvm_arm_vmid_alloc_init+0x98/0xac
Modules linked in:
CPU: 1 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.18.0-rc4+ #16195 PREEMPT
Hardware name: Raspberry Pi 3 Model B (DT)
pstate: 20000005 (nzCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : kvm_arm_vmid_alloc_init+0x98/0xac
lr : kvm_arm_vmid_alloc_init+0x1c/0xac
...
Call trace:
  kvm_arm_vmid_alloc_init+0x98/0xac (P)
  kvm_arm_init+0x144/0x153c
  do_one_initcall+0x64/0x308
  kernel_init_freeable+0x280/0x4fc
  kernel_init+0x20/0x1d8
  ret_from_fork+0x10/0x20
irq event stamp: 65606
hardirqs last  enabled at (65605): [<ffff8000801534e4>] 
__up_console_sem+0x6c/0x80
hardirqs last disabled at (65606): [<ffff800081358f7c>] el1_brk64+0x20/0x60
softirqs last  enabled at (65262): [<ffff8000800c4b1c>] 
handle_softirqs+0x4c4/0x4dc
softirqs last disabled at (65257): [<ffff8000800106a0>] 
__do_softirq+0x14/0x20
---[ end trace 0000000000000000 ]---
kvm [1]: Hyp nVHE mode initialized successfully


Reverting it on top of linux-next fixes the issue. Let me know how can I 
help debugging it.


> ---
> V4: Add comment why this is not marked __init ....
> V2: New patch
> ---
>   include/linux/cpumask.h |   10 ++++++++--
>   kernel/cpu.c            |   19 +++++++++++++++++++
>   2 files changed, 27 insertions(+), 2 deletions(-)
> --- a/include/linux/cpumask.h
> +++ b/include/linux/cpumask.h
> @@ -126,6 +126,7 @@ extern struct cpumask __cpu_dying_mask;
>   #define cpu_dying_mask    ((const struct cpumask *)&__cpu_dying_mask)
>   
>   extern atomic_t __num_online_cpus;
> +extern unsigned int __num_possible_cpus;
>   
>   extern cpumask_t cpus_booted_once_mask;
>   
> @@ -1152,13 +1153,13 @@ void init_cpu_possible(const struct cpum
>   #define __assign_cpu(cpu, mask, val)	\
>   	__assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val))
>   
> -#define set_cpu_possible(cpu, possible)	assign_cpu((cpu), &__cpu_possible_mask, (possible))
>   #define set_cpu_enabled(cpu, enabled)	assign_cpu((cpu), &__cpu_enabled_mask, (enabled))
>   #define set_cpu_present(cpu, present)	assign_cpu((cpu), &__cpu_present_mask, (present))
>   #define set_cpu_active(cpu, active)	assign_cpu((cpu), &__cpu_active_mask, (active))
>   #define set_cpu_dying(cpu, dying)	assign_cpu((cpu), &__cpu_dying_mask, (dying))
>   
>   void set_cpu_online(unsigned int cpu, bool online);
> +void set_cpu_possible(unsigned int cpu, bool possible);
>   
>   /**
>    * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask *
> @@ -1211,7 +1212,12 @@ static __always_inline unsigned int num_
>   {
>   	return raw_atomic_read(&__num_online_cpus);
>   }
> -#define num_possible_cpus()	cpumask_weight(cpu_possible_mask)
> +
> +static __always_inline unsigned int num_possible_cpus(void)
> +{
> +	return __num_possible_cpus;
> +}
> +
>   #define num_enabled_cpus()	cpumask_weight(cpu_enabled_mask)
>   #define num_present_cpus()	cpumask_weight(cpu_present_mask)
>   #define num_active_cpus()	cpumask_weight(cpu_active_mask)
> --- a/kernel/cpu.c
> +++ b/kernel/cpu.c
> @@ -3108,6 +3108,9 @@ EXPORT_SYMBOL(__cpu_dying_mask);
>   atomic_t __num_online_cpus __read_mostly;
>   EXPORT_SYMBOL(__num_online_cpus);
>   
> +unsigned int __num_possible_cpus __ro_after_init = NR_CPUS;
> +EXPORT_SYMBOL(__num_possible_cpus);
> +
>   void init_cpu_present(const struct cpumask *src)
>   {
>   	cpumask_copy(&__cpu_present_mask, src);
> @@ -3116,6 +3119,7 @@ void init_cpu_present(const struct cpuma
>   void init_cpu_possible(const struct cpumask *src)
>   {
>   	cpumask_copy(&__cpu_possible_mask, src);
> +	__num_possible_cpus = cpumask_weight(&__cpu_possible_mask);
>   }
>   
>   void set_cpu_online(unsigned int cpu, bool online)
> @@ -3139,6 +3143,21 @@ void set_cpu_online(unsigned int cpu, bo
>   	}
>   }
>   
> +/*
> + * This should be marked __init, but there is a boatload of call sites
> + * which need to be fixed up to do so. Sigh...
> + */
> +void set_cpu_possible(unsigned int cpu, bool possible)
> +{
> +	if (possible) {
> +		if (!cpumask_test_and_set_cpu(cpu, &__cpu_possible_mask))
> +			__num_possible_cpus++;
> +	} else {
> +		if (cpumask_test_and_clear_cpu(cpu, &__cpu_possible_mask))
> +			__num_possible_cpus--;
> +	}
> +}
> +
>   /*
>    * Activate the first processor.
>    */
>
>
>
Best regards
-- 
Marek Szyprowski, PhD
Samsung R&D Institute Poland

Powered by blists - more mailing lists