linux-kernel - Re: [PATCH v4 21/24] x86/resctrl: Allow overflow/limbo handlers to be scheduled on any-but cpu

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, 15 Jun 2023 15:25:49 -0700
From:   Reinette Chatre <reinette.chatre@...el.com>
To:     James Morse <james.morse@....com>, <x86@...nel.org>,
        <linux-kernel@...r.kernel.org>
CC:     Fenghua Yu <fenghua.yu@...el.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
        H Peter Anvin <hpa@...or.com>,
        Babu Moger <Babu.Moger@....com>,
        <shameerali.kolothum.thodi@...wei.com>,
        D Scott Phillips OS <scott@...amperecomputing.com>,
        <carl@...amperecomputing.com>, <lcherian@...vell.com>,
        <bobo.shaobowang@...wei.com>, <tan.shaopeng@...itsu.com>,
        <xingxin.hx@...nanolis.org>, <baolin.wang@...ux.alibaba.com>,
        Jamie Iles <quic_jiles@...cinc.com>,
        Xin Hao <xhao@...ux.alibaba.com>, <peternewman@...gle.com>,
        <dfustini@...libre.com>
Subject: Re: [PATCH v4 21/24] x86/resctrl: Allow overflow/limbo handlers to be
 scheduled on any-but cpu

Hi James,

On 5/25/2023 11:02 AM, James Morse wrote:

...

> diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
> index 021a8956518c..9cba8fc405b9 100644
> --- a/arch/x86/kernel/cpu/resctrl/internal.h
> +++ b/arch/x86/kernel/cpu/resctrl/internal.h
> @@ -79,6 +79,37 @@ static inline unsigned int cpumask_any_housekeeping(const struct cpumask *mask)
>  	return cpu;
>  }
>  
> +/**
> + * cpumask_any_housekeeping_but() - Chose any cpu in @mask, preferring those
> + *			            that aren't marked nohz_full, excluding
> + *				    the provided CPU
> + * @mask:	The mask to pick a CPU from.
> + * @exclude_cpu:The CPU to avoid picking.
> + *
> + * Returns a CPU from @mask, but not @but. If there are housekeeping CPUs that

"but not @exclude_cpu"

> + * don't use nohz_full, these are preferred.
> + * Returns >= nr_cpu_ids if no CPUs are available.
> + */
> +static inline unsigned int
> +cpumask_any_housekeeping_but(const struct cpumask *mask, int exclude_cpu)
> +{
> +	int cpu, hk_cpu;

Should these be unsigned int?

> +
> +	cpu = cpumask_any_but(mask, exclude_cpu);
> +	if (tick_nohz_full_cpu(cpu)) {
> +		hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask);
> +		if  (hk_cpu == exclude_cpu) {
> +			hk_cpu = cpumask_nth_andnot(1, mask,
> +						    tick_nohz_full_mask);
> +		}
> +

These braces are not necessary. If they are added to help readability then
perhaps the indentation can be reduced by using an earlier:

	if (!tick_nohz_full_cpu(cpu))
		return cpu;


> +		if (hk_cpu < nr_cpu_ids)
> +			cpu = hk_cpu;
> +	}
> +
> +	return cpu;
> +}
> +
>  struct rdt_fs_context {
>  	struct kernfs_fs_context	kfc;
>  	bool				enable_cdpl2;
> @@ -564,11 +595,13 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
>  		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
>  		    int evtid, int first);
>  void mbm_setup_overflow_handler(struct rdt_domain *dom,
> -				unsigned long delay_ms);
> +				unsigned long delay_ms,
> +				int exclude_cpu);
>  void mbm_handle_overflow(struct work_struct *work);
>  void __init intel_rdt_mbm_apply_quirk(void);
>  bool is_mba_sc(struct rdt_resource *r);
> -void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
> +void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms,
> +			     int exclude_cpu);
>  void cqm_handle_limbo(struct work_struct *work);
>  bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
>  void __check_limbo(struct rdt_domain *d, bool force_free);
> diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
> index ced933694f60..ae02185f3354 100644
> --- a/arch/x86/kernel/cpu/resctrl/monitor.c
> +++ b/arch/x86/kernel/cpu/resctrl/monitor.c
> @@ -485,7 +485,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
>  		 * setup up the limbo worker.
>  		 */
>  		if (!has_busy_rmid(r, d))
> -			cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL);
> +			cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL, -1);

Should this -1 be RESCTRL_PICK_ANY_CPU?

>  		set_bit(idx, d->rmid_busy_llc);
>  		entry->busy++;
>  	}
> @@ -810,15 +810,28 @@ void cqm_handle_limbo(struct work_struct *work)
>  	mutex_unlock(&rdtgroup_mutex);
>  }
>  
> -void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
> +/**
> + * cqm_setup_limbo_handler() - Schedule the limbo handler to run for this
> + *                             domain.
> + * @delay_ms:      How far in the future the handler should run.
> + * @exclude_cpu:   Which CPU the handler should not run on, -1 to pick any CPU.

Should -1 be RESCTRL_PICK_ANY_CPU? 

> + */
> +void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms,
> +			     int exclude_cpu)
>  {
>  	unsigned long delay = msecs_to_jiffies(delay_ms);
>  	int cpu;
>  
> -	cpu = cpumask_any_housekeeping(&dom->cpu_mask);
> -	dom->cqm_work_cpu = cpu;
> +	if (exclude_cpu == RESCTRL_PICK_ANY_CPU)
> +		cpu = cpumask_any_housekeeping(&dom->cpu_mask);
> +	else
> +		cpu = cpumask_any_housekeeping_but(&dom->cpu_mask,
> +						   exclude_cpu);
>  
> -	schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
> +	if (cpu < nr_cpu_ids) {
> +		dom->cqm_work_cpu = cpu;

Should cqm_work_cpu not perhaps be set to nr_cpu_ids on failure? If it keeps
pointing to CPU that ran worker previously there may be unexpected behavior. 

Note the different behavior between cqm_setup_limbo_handler() and
mbm_setup_overflow_handler() in this regard.

> +		schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
> +	}
>  }
>  
>  void mbm_handle_overflow(struct work_struct *work)
> @@ -864,7 +877,14 @@ void mbm_handle_overflow(struct work_struct *work)
>  	mutex_unlock(&rdtgroup_mutex);
>  }
>  
> -void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
> +/**
> + * mbm_setup_overflow_handler() - Schedule the overflow handler to run for this
> + *                                domain.
> + * @delay_ms:      How far in the future the handler should run.
> + * @exclude_cpu:   Which CPU the handler should not run on, -1 to pick any CPU.

RESCTRL_PICK_ANY_CPU?

> + */
> +void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms,
> +				int exclude_cpu)
>  {
>  	unsigned long delay = msecs_to_jiffies(delay_ms);
>  	int cpu;
> @@ -875,9 +895,15 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
>  	 */
>  	if (!resctrl_mounted || !resctrl_arch_mon_capable())
>  		return;
> -	cpu = cpumask_any_housekeeping(&dom->cpu_mask);
> +	if (exclude_cpu == -1)

same

> +		cpu = cpumask_any_housekeeping(&dom->cpu_mask);
> +	else
> +		cpu = cpumask_any_housekeeping_but(&dom->cpu_mask,
> +						   exclude_cpu);
>  	dom->mbm_work_cpu = cpu;
> -	schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
> +
> +	if (cpu < nr_cpu_ids)
> +		schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
>  }
>  

...

> diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
> index ecd41762d61a..089b91133e5e 100644
> --- a/include/linux/resctrl.h
> +++ b/include/linux/resctrl.h
> @@ -9,6 +9,9 @@
>  /* CLOSID value used by the default control group */
>  #define RESCTRL_RESERVED_CLOSID		0
>  
> +/* Indicates no CPU needs to be excluded */

This comment seems to just be a rewrite of the macro name.

> +#define RESCTRL_PICK_ANY_CPU		-1
> +
>  #ifdef CONFIG_PROC_CPU_RESCTRL
>  
>  int proc_resctrl_show(struct seq_file *m,

Reinette