linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Reinette Chatre <reinette.chatre@intel.com>
To: James Morse <james.morse@arm.com>, <x86@kernel.org>,
	<linux-kernel@vger.kernel.org>
Cc: Fenghua Yu <fenghua.yu@intel.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	H Peter Anvin <hpa@zytor.com>, Babu Moger <Babu.Moger@amd.com>,
	<shameerali.kolothum.thodi@huawei.com>,
	Jamie Iles <jamie@nuviainc.com>,
	"D Scott Phillips OS" <scott@os.amperecomputing.com>,
	<lcherian@marvell.com>, <bobo.shaobowang@huawei.com>
Subject: Re: [PATCH v1 06/20] x86/resctrl: Switch over to the resctrl mbps_val list
Date: Fri, 17 Sep 2021 11:20:18 -0700	[thread overview]
Message-ID: <b211c9c0-5f4c-75b2-2966-2bc1b848ab31@intel.com> (raw)
In-Reply-To: <18228404-0f65-c5f5-4070-7ba256fb9b72@arm.com>

Hi James,

On 9/17/2021 9:57 AM, James Morse wrote:
> Hi Reinette,
> 
> On 01/09/2021 22:25, Reinette Chatre wrote:
>> On 7/29/2021 3:35 PM, James Morse wrote:
>>> Updates to resctrl's software controller follow the same path as
>>> other configuration updates, but they don't modify the hardware state.
>>> rdtgroup_schemata_write() uses parse_line() and the resource's
>>> ctrlval_parse function to stage the configuration.
>>> resctrl_arch_update_domains() then updates the mbps_val[] array
>>> instead, and resctrl_arch_update_domains() skips the rdt_ctrl_update()
>>> call that would update hardware.
>>>
>>> This complicates the interface between resctrl's filesystem parts
>>> and architecture specific code. It should be possible for mba_sc
>>> to be completely implemented by the filesystem parts of resctrl. This
>>> would allow it to work on a second architecture with no additional code.
>>>
>>> Change parse_bw() to write the configuration value directly to the
>>> mba_sc[] array in the domain structure. Change rdtgroup_schemata_write()
>>> to skip the call to resctrl_arch_update_domains(), meaning all the
>>> mba_sc specific code in resctrl_arch_update_domains() can be removed.
>>> On the read-side, show_doms() and update_mba_bw() are changed to read
>>> the mba_sc[] array from the domain structure. With this,
>>> resctrl_arch_get_config() no longer needs to consider mba_sc resources.
>>>
>>> Change parse_bw() to write these values directly, meaning
>>> rdtgroup_schemata_write() never needs to call update_domains()
>>> for mba_sc resources.
> 
>> The above paragraph seems to contain duplicate information from the paragraph that
>> precedes it.
> 
> Looks like two commit messages got combined. I've removed this, and the below paragraphs
> as its already covered.
> 
> 
>>> Get show_doms() to test is_mba_sc() and retrieve the value
>>> directly, instead of using get_config() for the hardware value.
>>>
>>> This means the arch code's resctrl_arch_get_config() and
>>> resctrl_arch_update_domains() no longer need to be aware of
>>> mba_sc, and we can get rid of the update_mba_bw() code that
>>> reaches into the hw_dom to get the msr value.
> 
>>> @@ -406,6 +406,14 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
>>>          list_for_each_entry(s, &resctrl_schema_all, list) {
>>>            r = s->res;
>>> +
>>> +        /*
>>> +         * Writes to mba_sc resources update the software controller,
>>> +         * not the control msr.
>>> +         */
>>> +        if (is_mba_sc(r))
>>> +            continue;
>>> +
>>
>> A few resources can be updated in a single write to the schemata file. It is thus possible
>> to update the cache allocation resource as well as memory bandwidth allocation in a single
>> write.
> 
> i.e. echo "L3:0=7ff;1=7ff\nMB:0=100;1=50" > schemata

I do not think something like the above would show the issue. If you 
want to test this via the shell you need to use ANSI-C quoting. 
Adjusting what you show to something like:

echo -n $'L3:0=7ff;1=7ff\nMB:0=100;1=50\n'

>> As I understand this change in this scenario all configuration updates will be
>> skipped, not just the memory bandwidth allocation ones.
> 
> The loop is per-schema, so its not a problem for L2/L3. This would only be a problem if
> the is_mba_sc() resource had multiple schema. Only CDP does this, which the MBA controls
> don't support.

The loop iterates through the entire buffer provided to the schemata 
file and the buffer could contain multiple schema. This is more typical 
when interacting with the schemata file with a SDK perhaps.

Reinette

  reply	other threads:[~2021-09-17 18:20 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-29 22:35 [PATCH v1 00/20] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes James Morse
2021-07-29 22:35 ` [PATCH v1 01/20] x86/resctrl: Kill off alloc_enabled James Morse
2021-08-11 12:12   ` Jamie Iles
2021-09-01 21:18   ` Reinette Chatre
2021-07-29 22:35 ` [PATCH v1 02/20] x86/resctrl: Merge mon_capable and mon_enabled James Morse
2021-08-11 12:15   ` Jamie Iles
2021-08-11 15:16     ` James Morse
2021-07-29 22:35 ` [PATCH v1 03/20] x86/resctrl: Add domain online callback for resctrl work James Morse
2021-09-01 21:19   ` Reinette Chatre
2021-09-17 16:57     ` James Morse
2021-07-29 22:35 ` [PATCH v1 04/20] x86/resctrl: Add domain offline " James Morse
2021-08-11 16:10   ` Jamie Iles
2021-09-01 21:21   ` Reinette Chatre
2021-07-29 22:35 ` [PATCH v1 05/20] x86/resctrl: Create mba_sc configuration in the rdt_domain James Morse
2021-08-11 16:32   ` Jamie Iles
2021-08-31 16:24     ` James Morse
2021-09-01 21:22   ` Reinette Chatre
2021-09-17 16:57     ` James Morse
2021-07-29 22:35 ` [PATCH v1 06/20] x86/resctrl: Switch over to the resctrl mbps_val list James Morse
2021-09-01 21:25   ` Reinette Chatre
2021-09-17 16:57     ` James Morse
2021-09-17 18:20       ` Reinette Chatre [this message]
2021-10-01 16:02         ` James Morse
2021-07-29 22:35 ` [PATCH v1 07/20] x86/resctrl: Remove architecture copy of mbps_val James Morse
2021-09-01 21:26   ` Reinette Chatre
2021-09-17 16:57     ` James Morse
2021-07-29 22:35 ` [PATCH v1 08/20] x86/resctrl: Remove set_mba_sc()s control array re-initialisation James Morse
2021-07-29 22:35 ` [PATCH v1 09/20] x86/resctrl: Abstract and use supports_mba_mbps() James Morse
2021-09-01 21:27   ` Reinette Chatre
2021-09-17 16:57     ` James Morse
2021-09-24  6:23   ` tan.shaopeng
2021-10-01 16:01     ` James Morse
2021-07-29 22:36 ` [PATCH v1 10/20] x86/resctrl: Allow update_mba_bw() to update controls directly James Morse
2021-09-01 21:28   ` Reinette Chatre
2021-07-29 22:36 ` [PATCH v1 11/20] x86/resctrl: Calculate bandwidth from the total bytes counter James Morse
2021-09-01 21:31   ` Reinette Chatre
2021-09-17 16:58     ` James Morse
2021-07-29 22:36 ` [PATCH v1 12/20] x86/recstrl: Add per-rmid arch private storage for overflow and chunks James Morse
2021-08-11 17:14   ` Jamie Iles
2021-08-31 16:25     ` James Morse
2021-07-29 22:36 ` [PATCH v1 13/20] x86/recstrl: Allow per-rmid arch private storage to be reset James Morse
2021-09-24  6:34   ` tan.shaopeng
2021-10-01 16:01     ` James Morse
2021-07-29 22:36 ` [PATCH v1 14/20] x86/resctrl: Abstract __rmid_read() James Morse
2021-07-29 22:36 ` [PATCH v1 15/20] x86/resctrl: Pass the required parameters into resctrl_arch_rmid_read() James Morse
2021-07-29 22:36 ` [PATCH v1 16/20] x86/resctrl: Move mbm_overflow_count() " James Morse
2021-07-29 22:36 ` [PATCH v1 17/20] x86/resctrl: Move get_corrected_mbm_count() " James Morse
2021-07-29 22:36 ` [PATCH v1 18/20] x86/resctrl: Rename and change the units of resctrl_cqm_threshold James Morse
2021-07-29 22:36 ` [PATCH v1 19/20] x86/resctrl: Add resctrl_rmid_realloc_limit to abstract x86's boot_cpu_data James Morse
2021-07-29 22:36 ` [PATCH v1 20/20] x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes James Morse

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=b211c9c0-5f4c-75b2-2966-2bc1b848ab31@intel.com \
    --to=reinette.chatre@intel.com \
    --cc=Babu.Moger@amd.com \
    --cc=bobo.shaobowang@huawei.com \
    --cc=bp@alien8.de \
    --cc=fenghua.yu@intel.com \
    --cc=hpa@zytor.com \
    --cc=james.morse@arm.com \
    --cc=jamie@nuviainc.com \
    --cc=lcherian@marvell.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=scott@os.amperecomputing.com \
    --cc=shameerali.kolothum.thodi@huawei.com \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.org \
    --subject='Re: [PATCH v1 06/20] x86/resctrl: Switch over to the resctrl mbps_val list' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).