Re: [PATCH] x86/resctrl: mba_MBps: Fall back to total b/w if local b/w unavailable

[Moger, Babu]

Hi Tony,

> -----Original Message-----
> From: Tony Luck <tony.luck@xxxxxxxxx>
> Sent: Tuesday, October 24, 2023 1:16 PM
> To: Fenghua Yu <fenghua.yu@xxxxxxxxx>; Reinette Chatre
> <reinette.chatre@xxxxxxxxx>; Peter Newman <peternewman@xxxxxxxxxx>;
> Jonathan Corbet <corbet@xxxxxxx>; Shuah Khan <skhan@xxxxxxxxxxxxxxxxxxx>;
> x86@xxxxxxxxxx
> Cc: Shaopeng Tan <tan.shaopeng@xxxxxxxxxxx>; James Morse
> <james.morse@xxxxxxx>; Jamie Iles <quic_jiles@xxxxxxxxxxx>; Moger, Babu
> <Babu.Moger@xxxxxxx>; Randy Dunlap <rdunlap@xxxxxxxxxxxxx>; linux-
> kernel@xxxxxxxxxxxxxxx; linux-doc@xxxxxxxxxxxxxxx; patches@xxxxxxxxxxxxxxx;
> Tony Luck <tony.luck@xxxxxxxxx>
> Subject: [PATCH] x86/resctrl: mba_MBps: Fall back to total b/w if local b/w
> unavailable
>
> On Intel the various resource director technology (RDT) features are all
> orthogonal and independently enumerated. Thus it is possible to have a system
> that  provides "total" memory bandwidth measurements without providing
> "local" bandwidth measurements.
>
> If local bandwidth measurement is not available, do not give up on providing
> the "mba_MBps" feedback option completely, make the code fall back to using
> total bandwidth.


Is this customer requirement ?
What do you mean by " If local bandwidth measurement is not available" ?
Is the hardware supports only total bandwidth and not local?

It can get real ugly if we try to handle one special case.

thanks
Babu

> Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
> ---
>  arch/x86/kernel/cpu/resctrl/monitor.c  | 34 ++++++++++++++++----------
> arch/x86/kernel/cpu/resctrl/rdtgroup.c |  2 +-
>  2 files changed, 22 insertions(+), 14 deletions(-)
>
> diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c
> b/arch/x86/kernel/cpu/resctrl/monitor.c
> index f136ac046851..3b9531cce807 100644
> --- a/arch/x86/kernel/cpu/resctrl/monitor.c
> +++ b/arch/x86/kernel/cpu/resctrl/monitor.c
> @@ -418,6 +418,14 @@ static int __mon_event_count(u32 rmid, struct
> rmid_read *rr)
>  	return 0;
>  }
>
> +static struct mbm_state *get_mbm_data(struct rdt_domain *dom_mbm, int
> +rmid) {
> +	if (is_mbm_local_enabled())
> +		return &dom_mbm->mbm_local[rmid];
> +
> +	return &dom_mbm->mbm_total[rmid];
> +}
> +
>  /*
>   * mbm_bw_count() - Update bw count from values previously read by
>   *		    __mon_event_count().
> @@ -431,7 +439,7 @@ static int __mon_event_count(u32 rmid, struct
> rmid_read *rr)
>   */
>  static void mbm_bw_count(u32 rmid, struct rmid_read *rr)  {
> -	struct mbm_state *m = &rr->d->mbm_local[rmid];
> +	struct mbm_state *m = get_mbm_data(rr->d, rmid);
>  	u64 cur_bw, bytes, cur_bytes;
>
>  	cur_bytes = rr->val;
> @@ -526,14 +534,14 @@ static void update_mba_bw(struct rdtgroup *rgrp,
> struct rdt_domain *dom_mbm)
>  	struct list_head *head;
>  	struct rdtgroup *entry;
>
> -	if (!is_mbm_local_enabled())
> +	if (!is_mbm_enabled())
>  		return;
>
>  	r_mba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
>
>  	closid = rgrp->closid;
>  	rmid = rgrp->mon.rmid;
> -	pmbm_data = &dom_mbm->mbm_local[rmid];
> +	pmbm_data = get_mbm_data(dom_mbm, rmid);
>
>  	dom_mba = get_domain_from_cpu(smp_processor_id(), r_mba);
>  	if (!dom_mba) {
> @@ -553,7 +561,7 @@ static void update_mba_bw(struct rdtgroup *rgrp,
> struct rdt_domain *dom_mbm)
>  	 */
>  	head = &rgrp->mon.crdtgrp_list;
>  	list_for_each_entry(entry, head, mon.crdtgrp_list) {
> -		cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
> +		cmbm_data = get_mbm_data(dom_mbm, entry->mon.rmid);
>  		cur_bw += cmbm_data->prev_bw;
>  		delta_bw += cmbm_data->delta_bw;
>  	}
> @@ -595,7 +603,7 @@ static void update_mba_bw(struct rdtgroup *rgrp,
> struct rdt_domain *dom_mbm)
>  	 */
>  	pmbm_data->delta_comp = true;
>  	list_for_each_entry(entry, head, mon.crdtgrp_list) {
> -		cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
> +		cmbm_data = get_mbm_data(dom_mbm, entry->mon.rmid);
>  		cmbm_data->delta_comp = true;
>  	}
>  }
> @@ -621,15 +629,15 @@ static void mbm_update(struct rdt_resource *r, struct
> rdt_domain *d, int rmid)
>  		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
>  		rr.val = 0;
>  		__mon_event_count(rmid, &rr);
> -
> -		/*
> -		 * 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(rmid, &rr);
>  	}
> +
> +	/*
> +	 * 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(rmid, &rr);
>  }
>
>  /*
> diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> index 69a1de92384a..0c4f8a1b8df0 100644
> --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> @@ -2294,7 +2294,7 @@ static bool supports_mba_mbps(void)  {
>  	struct rdt_resource *r =
> &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
>
> -	return (is_mbm_local_enabled() &&
> +	return (is_mbm_enabled() &&
>  		r->alloc_capable && is_mba_linear());  }
>
> --
> 2.41.0