linux-kernel - Re: [PATCH v9 4/9] x86/resctrl: Compute memory bandwidth for all supported events

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]

Message-ID: <6fada5bb-7ca2-4f6b-9174-109c429e8d68@intel.com>
Date: Tue, 19 Nov 2024 19:45:01 -0800
From: Reinette Chatre <reinette.chatre@...el.com>
To: Tony Luck <tony.luck@...el.com>, Fenghua Yu <fenghua.yu@...el.com>, "Peter
 Newman" <peternewman@...gle.com>, Jonathan Corbet <corbet@....net>,
	<x86@...nel.org>
CC: James Morse <james.morse@....com>, Jamie Iles <quic_jiles@...cinc.com>,
	Babu Moger <babu.moger@....com>, Randy Dunlap <rdunlap@...radead.org>,
	"Shaopeng Tan (Fujitsu)" <tan.shaopeng@...itsu.com>,
	<linux-kernel@...r.kernel.org>, <linux-doc@...r.kernel.org>,
	<patches@...ts.linux.dev>
Subject: Re: [PATCH v9 4/9] x86/resctrl: Compute memory bandwidth for all
 supported events

Hi Tony,

On 11/13/24 4:17 PM, Tony Luck wrote:
> Computing the bandwidth for an event is cheap, and only done once
> per second. Doing so simplifies switching between events and allows
> choosing different events per ctrl_mon group.

This just reads like some a general statement. There surely can be
some context, problem and *some* description about how this patch goes
about addressing the problem?

> 
> Suggested-by: Reinette Chatre <reinette.chatre@...el.com>
> Signed-off-by: Tony Luck <tony.luck@...el.com>
> ---
>  arch/x86/kernel/cpu/resctrl/monitor.c | 72 ++++++++++++---------------
>  1 file changed, 33 insertions(+), 39 deletions(-)
> 
> diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
> index 2176e355e864..da4ae21350c8 100644
> --- a/arch/x86/kernel/cpu/resctrl/monitor.c
> +++ b/arch/x86/kernel/cpu/resctrl/monitor.c
> @@ -663,9 +663,12 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
>   */
>  static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr)
>  {
> -	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
> -	struct mbm_state *m = &rr->d->mbm_local[idx];
>  	u64 cur_bw, bytes, cur_bytes;
> +	struct mbm_state *m;
> +
> +	m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
> +	if (WARN_ON_ONCE(!m))
> +		return;
>  
>  	cur_bytes = rr->val;
>  	bytes = cur_bytes - m->prev_bw_bytes;
> @@ -826,54 +829,45 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
>  	resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
>  }
>  
> -static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
> -		       u32 closid, u32 rmid)
> +static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *d,
> +				 u32 closid, u32 rmid, enum resctrl_event_id evtid)
>  {
>  	struct rmid_read rr = {0};
>  
>  	rr.r = r;
>  	rr.d = d;
> +	rr.evtid = evtid;
> +	rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
> +	if (IS_ERR(rr.arch_mon_ctx)) {
> +		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
> +				    PTR_ERR(rr.arch_mon_ctx));
> +		return;
> +	}
> +
> +	__mon_event_count(closid, rmid, &rr);
>  
>  	/*
> -	 * This is protected from concurrent reads from user
> -	 * as both the user and we hold the global mutex.
> +	 * If the software controller is enabled, compute the
> +	 * bandwidth for this event id.
>  	 */
> -	if (is_mbm_total_enabled()) {
> -		rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
> -		rr.val = 0;
> -		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
> -		if (IS_ERR(rr.arch_mon_ctx)) {
> -			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
> -					    PTR_ERR(rr.arch_mon_ctx));
> -			return;
> -		}
> -
> -		__mon_event_count(closid, rmid, &rr);
> +	if (is_mba_sc(NULL))
> +		mbm_bw_count(closid, rmid, &rr);
>  
> -		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
> -	}
> -	if (is_mbm_local_enabled()) {
> -		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
> -		rr.val = 0;
> -		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
> -		if (IS_ERR(rr.arch_mon_ctx)) {
> -			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
> -					    PTR_ERR(rr.arch_mon_ctx));
> -			return;
> -		}
> -
> -		__mon_event_count(closid, rmid, &rr);
> +	resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
> +}
>  
> -		/*
> -		 * Call the MBA software controller only for the
> -		 * control groups and when user has enabled
> -		 * the software controller explicitly.
> -		 */
> -		if (is_mba_sc(NULL))
> -			mbm_bw_count(closid, rmid, &rr);
> +static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
> +		       u32 closid, u32 rmid)
> +{
> +	/*
> +	 * This is protected from concurrent reads from user
> +	 * as both the user and we hold the global mutex.

I understand that you are just copy&pasting a comment here but could you please
help to avoid any obstacles by removing the code impersonation? Perhaps something like:

	 * This is protected from concurrent reads from user
	 * as both the user and overflow handler hold the global mutex.

(please feel free to improve)

> +	 */
> +	if (is_mbm_total_enabled())
> +		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID);
>  
> -		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
> -	}
> +	if (is_mbm_local_enabled())
> +		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID);
>  }
>  
>  /*

Reinette