Message-ID: <bb9a75dc-8c34-41da-b064-e31bf5fe6cb2@huaweicloud.com>
Date: Tue, 21 Oct 2025 09:46:29 +0800
From: Chen Ridong <chenridong@...weicloud.com>
To: Frederic Weisbecker <frederic@...nel.org>,
 LKML <linux-kernel@...r.kernel.org>
Cc: Michal Koutný <mkoutny@...e.com>,
 Andrew Morton <akpm@...ux-foundation.org>,
 Bjorn Helgaas <bhelgaas@...gle.com>,
 Catalin Marinas <catalin.marinas@....com>, Danilo Krummrich
 <dakr@...nel.org>, "David S . Miller" <davem@...emloft.net>,
 Eric Dumazet <edumazet@...gle.com>, Gabriele Monaco <gmonaco@...hat.com>,
 Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
 Ingo Molnar <mingo@...hat.com>, Jakub Kicinski <kuba@...nel.org>,
 Jens Axboe <axboe@...nel.dk>, Johannes Weiner <hannes@...xchg.org>,
 Lai Jiangshan <jiangshanlai@...il.com>,
 Marco Crivellari <marco.crivellari@...e.com>, Michal Hocko
 <mhocko@...e.com>, Muchun Song <muchun.song@...ux.dev>,
 Paolo Abeni <pabeni@...hat.com>, Peter Zijlstra <peterz@...radead.org>,
 Phil Auld <pauld@...hat.com>, "Rafael J . Wysocki" <rafael@...nel.org>,
 Roman Gushchin <roman.gushchin@...ux.dev>,
 Shakeel Butt <shakeel.butt@...ux.dev>, Simon Horman <horms@...nel.org>,
 Tejun Heo <tj@...nel.org>, Thomas Gleixner <tglx@...utronix.de>,
 Vlastimil Babka <vbabka@...e.cz>, Waiman Long <longman@...hat.com>,
 Will Deacon <will@...nel.org>, cgroups@...r.kernel.org,
 linux-arm-kernel@...ts.infradead.org, linux-block@...r.kernel.org,
 linux-mm@...ck.org, linux-pci@...r.kernel.org, netdev@...r.kernel.org
Subject: Re: [PATCH 12/33] sched/isolation: Convert housekeeping cpumasks to
 rcu pointers



On 2025/10/14 4:31, Frederic Weisbecker wrote:
> HK_TYPE_DOMAIN's cpumask will soon be made modifyable by cpuset.
> A synchronization mechanism is then needed to synchronize the updates
> with the housekeeping cpumask readers.
> 
> Turn the housekeeping cpumasks into RCU pointers. Once a housekeeping
> cpumask will be modified, the update side will wait for an RCU grace
> period and propagate the change to interested subsystem when deemed
> necessary.
> 
> Signed-off-by: Frederic Weisbecker <frederic@...nel.org>
> ---
>  kernel/sched/isolation.c | 58 +++++++++++++++++++++++++---------------
>  kernel/sched/sched.h     |  1 +
>  2 files changed, 37 insertions(+), 22 deletions(-)
> 
> diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
> index 8690fb705089..b46c20b5437f 100644
> --- a/kernel/sched/isolation.c
> +++ b/kernel/sched/isolation.c
> @@ -21,7 +21,7 @@ DEFINE_STATIC_KEY_FALSE(housekeeping_overridden);
>  EXPORT_SYMBOL_GPL(housekeeping_overridden);
>  
>  struct housekeeping {
> -	cpumask_var_t cpumasks[HK_TYPE_MAX];
> +	struct cpumask __rcu *cpumasks[HK_TYPE_MAX];
>  	unsigned long flags;
>  };
>  
> @@ -33,17 +33,28 @@ bool housekeeping_enabled(enum hk_type type)
>  }
>  EXPORT_SYMBOL_GPL(housekeeping_enabled);
>  
> +const struct cpumask *housekeeping_cpumask(enum hk_type type)
> +{
> +	if (static_branch_unlikely(&housekeeping_overridden)) {
> +		if (housekeeping.flags & BIT(type)) {
> +			return rcu_dereference_check(housekeeping.cpumasks[type], 1);
> +		}
> +	}
> +	return cpu_possible_mask;
> +}
> +EXPORT_SYMBOL_GPL(housekeeping_cpumask);
> +
>  int housekeeping_any_cpu(enum hk_type type)
>  {
>  	int cpu;
>  
>  	if (static_branch_unlikely(&housekeeping_overridden)) {
>  		if (housekeeping.flags & BIT(type)) {
> -			cpu = sched_numa_find_closest(housekeeping.cpumasks[type], smp_processor_id());
> +			cpu = sched_numa_find_closest(housekeeping_cpumask(type), smp_processor_id());
>  			if (cpu < nr_cpu_ids)
>  				return cpu;
>  
> -			cpu = cpumask_any_and_distribute(housekeeping.cpumasks[type], cpu_online_mask);
> +			cpu = cpumask_any_and_distribute(housekeeping_cpumask(type), cpu_online_mask);
>  			if (likely(cpu < nr_cpu_ids))
>  				return cpu;
>  			/*
> @@ -59,28 +70,18 @@ int housekeeping_any_cpu(enum hk_type type)
>  }
>  EXPORT_SYMBOL_GPL(housekeeping_any_cpu);
>  
> -const struct cpumask *housekeeping_cpumask(enum hk_type type)
> -{
> -	if (static_branch_unlikely(&housekeeping_overridden))
> -		if (housekeeping.flags & BIT(type))
> -			return housekeeping.cpumasks[type];
> -	return cpu_possible_mask;
> -}
> -EXPORT_SYMBOL_GPL(housekeeping_cpumask);
> -
>  void housekeeping_affine(struct task_struct *t, enum hk_type type)
>  {
>  	if (static_branch_unlikely(&housekeeping_overridden))
>  		if (housekeeping.flags & BIT(type))
> -			set_cpus_allowed_ptr(t, housekeeping.cpumasks[type]);
> +			set_cpus_allowed_ptr(t, housekeeping_cpumask(type));
>  }
>  EXPORT_SYMBOL_GPL(housekeeping_affine);
>  
>  bool housekeeping_test_cpu(int cpu, enum hk_type type)
>  {
> -	if (static_branch_unlikely(&housekeeping_overridden))
> -		if (housekeeping.flags & BIT(type))
> -			return cpumask_test_cpu(cpu, housekeeping.cpumasks[type]);
> +	if (housekeeping.flags & BIT(type))
> +		return cpumask_test_cpu(cpu, housekeeping_cpumask(type));
>  	return true;
>  }
>  EXPORT_SYMBOL_GPL(housekeeping_test_cpu);
> @@ -96,20 +97,33 @@ void __init housekeeping_init(void)
>  
>  	if (housekeeping.flags & HK_FLAG_KERNEL_NOISE)
>  		sched_tick_offload_init();
> -
> +	/*
> +	 * Realloc with a proper allocator so that any cpumask update
> +	 * can indifferently free the old version with kfree().
> +	 */
>  	for_each_set_bit(type, &housekeeping.flags, HK_TYPE_MAX) {
> +		struct cpumask *omask, *nmask = kmalloc(cpumask_size(), GFP_KERNEL);
> +
> +		if (WARN_ON_ONCE(!nmask))
> +			return;
> +
> +		omask = rcu_dereference(housekeeping.cpumasks[type]);
> +
>  		/* We need at least one CPU to handle housekeeping work */
> -		WARN_ON_ONCE(cpumask_empty(housekeeping.cpumasks[type]));
> +		WARN_ON_ONCE(cpumask_empty(omask));
> +		cpumask_copy(nmask, omask);
> +		RCU_INIT_POINTER(housekeeping.cpumasks[type], nmask);
> +		memblock_free(omask, cpumask_size());
>  	}
>  }
>  
>  static void __init housekeeping_setup_type(enum hk_type type,
>  					   cpumask_var_t housekeeping_staging)
>  {
> +	struct cpumask *mask = memblock_alloc_or_panic(cpumask_size(), SMP_CACHE_BYTES);
>  
> -	alloc_bootmem_cpumask_var(&housekeeping.cpumasks[type]);
> -	cpumask_copy(housekeeping.cpumasks[type],
> -		     housekeeping_staging);
> +	cpumask_copy(mask, housekeeping_staging);
> +	RCU_INIT_POINTER(housekeeping.cpumasks[type], mask);
>  }
>  
>  static int __init housekeeping_setup(char *str, unsigned long flags)
> @@ -162,7 +176,7 @@ static int __init housekeeping_setup(char *str, unsigned long flags)
>  
>  		for_each_set_bit(type, &iter_flags, HK_TYPE_MAX) {
>  			if (!cpumask_equal(housekeeping_staging,
> -					   housekeeping.cpumasks[type])) {
> +					   housekeeping_cpumask(type))) {
>  				pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
>  				goto free_housekeeping_staging;
>  			}
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 1f5d07067f60..0c0ef8999fd6 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -42,6 +42,7 @@
>  #include <linux/ktime_api.h>
>  #include <linux/lockdep_api.h>
>  #include <linux/lockdep.h>
> +#include <linux/memblock.h>
>  #include <linux/minmax.h>
>  #include <linux/mm.h>
>  #include <linux/module.h>

A warning was detected:

=============================
WARNING: suspicious RCU usage
6.17.0-next-20251009-00033-g4444da88969b #808 Not tainted
-----------------------------
kernel/sched/isolation.c:60 suspicious rcu_dereference_check() usage!

other info that might help us debug this:


rcu_scheduler_active = 2, debug_locks = 1
1 lock held by swapper/0/1:
 #0: ffff888100600ce0 (&type->i_mutex_dir_key#3){++++}-{4:4}, at: walk_compone

stack backtrace:
CPU: 3 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.17.0-next-20251009-00033-g4
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239
Call Trace:
 <TASK>
 dump_stack_lvl+0x68/0xa0
 lockdep_rcu_suspicious+0x148/0x1b0
 housekeeping_cpumask+0xaa/0xb0
 housekeeping_test_cpu+0x25/0x40
 find_get_block_common+0x41/0x3e0
 bdev_getblk+0x28/0xa0
 ext4_getblk+0xba/0x2d0
 ext4_bread_batch+0x56/0x170
 __ext4_find_entry+0x17c/0x410
 ? lock_release+0xc6/0x290
 ext4_lookup+0x7a/0x1d0
 __lookup_slow+0xf9/0x1b0
 walk_component+0xe0/0x150
 link_path_walk+0x201/0x3e0
 path_openat+0xb1/0xb30
 ? stack_depot_save_flags+0x41e/0xa00
 do_filp_open+0xbc/0x170
 ? _raw_spin_unlock_irqrestore+0x2c/0x50
 ? __create_object+0x59/0x80
 ? trace_kmem_cache_alloc+0x1d/0xa0
 ? vprintk_emit+0x2b2/0x360
 do_open_execat+0x56/0x100
 alloc_bprm+0x1a/0x200
 ? __pfx_kernel_init+0x10/0x10
 kernel_execve+0x4b/0x160
 kernel_init+0xe5/0x1c0
 ret_from_fork+0x185/0x1d0
 ? __pfx_kernel_init+0x10/0x10
 ret_from_fork_asm+0x1a/0x30
 </TASK>
random: crng init done

-- 
Best regards,
Ridong

Powered by blists - more mailing lists