mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Reinette Chatre <reinette.chatre@intel.com>
To: Babu Moger <babu.moger@amd.com>, <corbet@lwn.net>,
	<fenghua.yu@intel.com>, <tglx@linutronix.de>, <mingo@redhat.com>,
	<bp@alien8.de>, <dave.hansen@linux.intel.com>
Cc: <x86@kernel.org>, <hpa@zytor.com>, <paulmck@kernel.org>,
	<rdunlap@infradead.org>, <tj@kernel.org>, <peterz@infradead.org>,
	<yanjiewtw@gmail.com>, <kim.phillips@amd.com>,
	<lukas.bulwahn@gmail.com>, <seanjc@google.com>,
	<jmattson@google.com>, <leitao@debian.org>, <jpoimboe@kernel.org>,
	<rick.p.edgecombe@intel.com>, <kirill.shutemov@linux.intel.com>,
	<jithu.joseph@intel.com>, <kai.huang@intel.com>,
	<kan.liang@linux.intel.com>, <daniel.sneddon@linux.intel.com>,
	<pbonzini@redhat.com>, <sandipan.das@amd.com>,
	<ilpo.jarvinen@linux.intel.com>, <peternewman@google.com>,
	<maciej.wieczor-retman@intel.com>, <linux-doc@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>, <eranian@google.com>,
	<james.morse@arm.com>
Subject: Re: [PATCH v6 20/22] x86/resctrl: Enable AMD ABMC feature by default when supported
Date: Fri, 16 Aug 2024 15:33:15 -0700	[thread overview]
Message-ID: <ab979768-a98b-417b-b319-6f14da88b857@intel.com> (raw)
In-Reply-To: <1061a60166f2fdb508aaf2dd9163b2bab3705063.1722981659.git.babu.moger@amd.com>

Hi Babu,

On 8/6/24 3:00 PM, Babu Moger wrote:
> Enable ABMC by default when supported during the boot up.
> 
> Users will not see any difference in the behavior when resctrl is
> mounted. With automatic assignment everything will work as running
> in the legacy monitor mode.
> 
> Signed-off-by: Babu Moger <babu.moger@amd.com>
> ---
> v6 : Keeping the default enablement in arch init code for now.
>       This may need some discussion.
>       Renamed resctrl_arch_configure_abmc to resctrl_arch_mbm_cntr_assign_configure.
> 
> v5: New patch to enable ABMC by default.
> ---
>   arch/x86/kernel/cpu/resctrl/core.c     |  2 ++
>   arch/x86/kernel/cpu/resctrl/internal.h |  1 +
>   arch/x86/kernel/cpu/resctrl/rdtgroup.c | 17 +++++++++++++++++
>   3 files changed, 20 insertions(+)
> 
> diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
> index 6fb0cfdb5529..a7980f84c487 100644
> --- a/arch/x86/kernel/cpu/resctrl/core.c
> +++ b/arch/x86/kernel/cpu/resctrl/core.c
> @@ -599,6 +599,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
>   		d = container_of(hdr, struct rdt_mon_domain, hdr);
>   
>   		cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
> +		resctrl_arch_mbm_cntr_assign_configure();
>   		return;
>   	}
>   
> @@ -620,6 +621,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
>   	arch_mon_domain_online(r, d);
>   
>   	resctrl_mbm_evt_config_init(hw_dom);
> +	resctrl_arch_mbm_cntr_assign_configure();
>   
>   	if (arch_domain_mbm_alloc(r->mon.num_rmid, hw_dom)) {
>   		mon_domain_free(hw_dom);
> diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
> index cc832955b787..ba3012f8f940 100644
> --- a/arch/x86/kernel/cpu/resctrl/internal.h
> +++ b/arch/x86/kernel/cpu/resctrl/internal.h
> @@ -685,6 +685,7 @@ int mbm_cntr_alloc(struct rdt_resource *r);
>   void mbm_cntr_free(u32 cntr_id);
>   void resctrl_mbm_evt_config_init(struct rdt_hw_mon_domain *hw_dom);
>   unsigned int mon_event_config_index_get(u32 evtid);
> +void resctrl_arch_mbm_cntr_assign_configure(void);
>   int resctrl_arch_assign_cntr(struct rdt_mon_domain *d, enum resctrl_event_id evtid,
>   			     u32 rmid, u32 cntr_id, u32 closid, bool assign);
>   int rdtgroup_assign_cntr(struct rdtgroup *rdtgrp, enum resctrl_event_id evtid);
> diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> index 66febff2a3d3..d15fd1bde5f4 100644
> --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> @@ -2756,6 +2756,23 @@ void resctrl_arch_mbm_cntr_assign_disable(void)
>   	}
>   }
>   
> +void resctrl_arch_mbm_cntr_assign_configure(void)
> +{
> +	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
> +	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
> +	bool enable = true;
> +
> +	mutex_lock(&rdtgroup_mutex);
> +
> +	if (r->mon.mbm_cntr_assignable) {
> +		if (!hw_res->mbm_cntr_assign_enabled)
> +			hw_res->mbm_cntr_assign_enabled = true;
> +		resctrl_abmc_set_one_amd(&enable);

Earlier changelogs mentioned that counters are reset when ABMC is enabled.
How does that behave here when one CPU comes online? Consider the scenario where
a system is booted without all CPUs online. ABMC is initially enabled on all online
CPUs with this flow ... user space could start using resctrl fs and create
monitor groups that start accumulating architectural state. If the remaining
CPUs come online at this point and this snippet enables ABMC, would it reset
all counters? Should the architectural state be cleared?

Also, it still does not look right that the architecture decides the policy.
Could this enabling be moved to resctrl_online_cpu() for resctrl fs to
request architecture to enable assignable counters if it is supported?

> +	}
> +
> +	mutex_unlock(&rdtgroup_mutex);
> +}
> +
>   /*
>    * We don't allow rdtgroup directories to be created anywhere
>    * except the root directory. Thus when looking for the rdtgroup

Reinette

  parent reply	other threads:[~2024-08-16 22:33 UTC|newest]

Thread overview: 96+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-08-06 22:00 [PATCH v6 00/22] x86/resctrl : Support AMD Assignable Bandwidth Monitoring Counters (ABMC) Babu Moger
2024-08-06 22:00 ` [PATCH v6 01/22] x86/cpufeatures: Add support for " Babu Moger
2024-08-07 16:32   ` Thomas Gleixner
2024-08-08 14:46     ` Moger, Babu
2024-08-06 22:00 ` [PATCH v6 02/22] x86/resctrl: Add ABMC feature in the command line options Babu Moger
2024-08-06 22:00 ` [PATCH v6 03/22] x86/resctrl: Consolidate monitoring related data from rdt_resource Babu Moger
2024-08-16 21:29   ` Reinette Chatre
2024-08-19 14:46     ` Moger, Babu
2024-08-06 22:00 ` [PATCH v6 04/22] x86/resctrl: Detect Assignable Bandwidth Monitoring feature details Babu Moger
2024-08-07 16:33   ` Thomas Gleixner
2024-08-16 21:30   ` Reinette Chatre
2024-08-19 15:37     ` Moger, Babu
2024-08-06 22:00 ` [PATCH v6 05/22] x86/resctrl: Introduce resctrl_file_fflags_init() to initialize fflags Babu Moger
2024-08-06 22:00 ` [PATCH v6 06/22] x86/resctrl: Add support to enable/disable AMD ABMC feature Babu Moger
2024-08-16 16:29   ` James Morse
2024-08-16 20:38     ` Moger, Babu
2024-08-16 21:31   ` Reinette Chatre
2024-08-19 18:07     ` Moger, Babu
2024-08-20 18:17       ` Reinette Chatre
2024-08-06 22:00 ` [PATCH v6 07/22] x86/resctrl: Introduce the interface to display monitor mode Babu Moger
2024-08-16 16:56   ` James Morse
2024-08-16 20:38     ` Moger, Babu
2024-08-16 21:32   ` Reinette Chatre
2024-08-19 19:27     ` Moger, Babu
2024-08-06 22:00 ` [PATCH v6 08/22] x86/resctrl: Introduce interface to display number of monitoring counters Babu Moger
2024-08-16 21:34   ` Reinette Chatre
2024-08-20 15:56     ` Moger, Babu
2024-08-20 18:08       ` Reinette Chatre
2024-08-06 22:00 ` [PATCH v6 09/22] x86/resctrl: Introduce MBM counters bitmap Babu Moger
2024-08-16 16:29   ` James Morse
2024-08-16 20:39     ` Moger, Babu
2024-08-16 21:35   ` Reinette Chatre
2024-08-19 15:49     ` Moger, Babu
2024-08-20 18:08       ` Reinette Chatre
2024-08-06 22:00 ` [PATCH v6 10/22] x86/resctrl: Introduce mbm_total_cfg and mbm_local_cfg Babu Moger
2024-08-06 22:00 ` [PATCH v6 11/22] x86/resctrl: Remove MSR reading of event configuration value Babu Moger
2024-08-16 21:36   ` Reinette Chatre
2024-08-20 16:19     ` Moger, Babu
2024-08-20 18:09       ` Reinette Chatre
2024-08-06 22:00 ` [PATCH v6 12/22] x86/resctrl: Introduce mbm_cntr_map to track counters at domain Babu Moger
2024-08-16 21:37   ` Reinette Chatre
2024-08-20 18:24     ` Moger, Babu
2024-08-06 22:00 ` [PATCH v6 13/22] x86/resctrl: Add data structures and definitions for ABMC assignment Babu Moger
2024-08-16 21:38   ` Reinette Chatre
2024-08-20 20:56     ` Moger, Babu
2024-08-20 21:09       ` Reinette Chatre
2024-08-06 22:00 ` [PATCH v6 14/22] x86/resctrl: Introduce cntr_id in mongroup for assignments Babu Moger
2024-08-16 21:38   ` Reinette Chatre
2024-08-20 22:42     ` Moger, Babu
2024-08-06 22:00 ` [PATCH v6 15/22] x86/resctrl: Add the interface to assign a hardware counter Babu Moger
2024-08-16 16:30   ` James Morse
2024-08-16 20:39     ` Moger, Babu
2024-08-16 21:41   ` Reinette Chatre
2024-08-21 15:04     ` Moger, Babu
2024-08-06 22:00 ` [PATCH v6 16/22] x86/resctrl: Add the interface to unassign a MBM counter Babu Moger
2024-08-16 21:41   ` Reinette Chatre
2024-08-21 16:01     ` Moger, Babu
2024-08-23 20:18       ` Reinette Chatre
2024-08-23 22:05         ` Moger, Babu
2024-08-06 22:00 ` [PATCH v6 17/22] x86/resctrl: Assign/unassign counters by default when ABMC is enabled Babu Moger
2024-08-16 21:42   ` Reinette Chatre
2024-08-21 17:20     ` Moger, Babu
2024-08-06 22:00 ` [PATCH v6 18/22] x86/resctrl: Report "Unassigned" for MBM events in ABMC mode Babu Moger
2024-08-16 21:42   ` Reinette Chatre
2024-08-21 17:30     ` Moger, Babu
2024-08-06 22:00 ` [PATCH v6 19/22] x86/resctrl: Introduce the interface to switch between monitor modes Babu Moger
2024-08-16 16:31   ` James Morse
2024-08-16 17:01     ` Reinette Chatre
2024-08-16 17:16       ` Peter Newman
2024-08-16 18:09         ` Reinette Chatre
2024-08-19 14:52           ` Reinette Chatre
2024-08-19 18:27             ` Peter Newman
2024-08-20 18:11               ` Reinette Chatre
2024-08-16 21:42   ` Reinette Chatre
2024-08-21 18:08     ` Moger, Babu
2024-08-06 22:00 ` [PATCH v6 20/22] x86/resctrl: Enable AMD ABMC feature by default when supported Babu Moger
2024-08-16 16:32   ` James Morse
2024-08-16 20:40     ` Moger, Babu
2024-08-16 22:33   ` Reinette Chatre [this message]
2024-08-19 18:18     ` Moger, Babu
2024-08-20 18:12       ` Reinette Chatre
2024-08-20 20:04         ` Moger, Babu
2024-08-20 20:18           ` Moger, Babu
2024-08-20 20:37             ` Reinette Chatre
2024-08-06 22:00 ` [PATCH v6 21/22] x86/resctrl: Introduce interface to list monitor states of all the groups Babu Moger
2024-08-16 16:28   ` James Morse
2024-08-16 20:40     ` Moger, Babu
2024-08-06 22:00 ` [PATCH v6 22/22] x86/resctrl: Introduce interface to modify assignment states of " Babu Moger
2024-08-16 22:33   ` Reinette Chatre
2024-08-21 20:11     ` Moger, Babu
2024-08-23 20:18       ` Reinette Chatre
2024-08-23 22:04         ` Moger, Babu
2024-08-16 21:28 ` [PATCH v6 00/22] x86/resctrl : Support AMD Assignable Bandwidth Monitoring Counters (ABMC) Reinette Chatre
2024-08-22  1:31   ` Moger, Babu
2024-08-23 20:29     ` Reinette Chatre
2024-08-23 22:14       ` Moger, Babu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=ab979768-a98b-417b-b319-6f14da88b857@intel.com \
    --to=reinette.chatre@intel.com \
    --cc=babu.moger@amd.com \
    --cc=bp@alien8.de \
    --cc=corbet@lwn.net \
    --cc=daniel.sneddon@linux.intel.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=eranian@google.com \
    --cc=fenghua.yu@intel.com \
    --cc=hpa@zytor.com \
    --cc=ilpo.jarvinen@linux.intel.com \
    --cc=james.morse@arm.com \
    --cc=jithu.joseph@intel.com \
    --cc=jmattson@google.com \
    --cc=jpoimboe@kernel.org \
    --cc=kai.huang@intel.com \
    --cc=kan.liang@linux.intel.com \
    --cc=kim.phillips@amd.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=leitao@debian.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lukas.bulwahn@gmail.com \
    --cc=maciej.wieczor-retman@intel.com \
    --cc=mingo@redhat.com \
    --cc=paulmck@kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=peternewman@google.com \
    --cc=peterz@infradead.org \
    --cc=rdunlap@infradead.org \
    --cc=rick.p.edgecombe@intel.com \
    --cc=sandipan.das@amd.com \
    --cc=seanjc@google.com \
    --cc=tglx@linutronix.de \
    --cc=tj@kernel.org \
    --cc=x86@kernel.org \
    --cc=yanjiewtw@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®