All of lore.kernel.org
 help / color / mirror / Atom feed
From: Chao Peng <chao.p.peng@linux.intel.com>
To: Yi Sun <yi.y.sun@linux.intel.com>, xen-devel@lists.xenproject.org
Cc: kevin.tian@intel.com, wei.liu2@citrix.com,
	andrew.cooper3@citrix.com, dario.faggioli@citrix.com,
	ian.jackson@eu.citrix.com, julien.grall@arm.com,
	mengxu@cis.upenn.edu, jbeulich@suse.com, roger.pau@citrix.com
Subject: Re: [PATCH v1 07/13] x86: implement set value flow for MBA
Date: Fri, 18 Aug 2017 11:32:08 +0800	[thread overview]
Message-ID: <1503027128.3857.14.camel@linux.intel.com> (raw)
In-Reply-To: <1502264512-4648-8-git-send-email-yi.y.sun@linux.intel.com>


> +    if ( feat->mba_info.linear )
> +    {
> +        unsigned int mod;
> +
> +        if ( feat->mba_info.thrtl_max >= 100 )
> +            return false;

Can we do this check earlier, e.g. when it gets enumerated from CPUID?

> +
> +        mod = *thrtl % (100 - feat->mba_info.thrtl_max);
> +        *thrtl -= mod;
> +    }
> +    else
> +    {
> +        /* Not power of 2. */
> +        if ( *thrtl & (*thrtl - 1) )
> +            *thrtl = *thrtl & (1 << (flsl(*thrtl) - 1));
> +    }
> +

Is it possible for *thrtl to be zero? Otherwise we need check that at
the beginning.

>  
> +/*
> + * Because multiple features may co-exist, we need handle all
> features to write
> + * values of them into a COS register with new COS ID. E.g:
> + * 1. L3 CAT and MBA co-exist.
> + * 2. Dom1 and Dom2 share a same COS ID (2). The L3 CAT CBM of Dom1
> is 0x1ff,
> + *    the MBA Thrtle of Dom1 is 0xa.
> + * 3. User wants to change MBA Thrtl of Dom1 to be 0x14. Because COS
> ID 2 is
> + *    used by Dom2 too, we have to pick a new COS ID 3. The original
> values of
> + *    Dom1 on COS ID 3 may be below:
> + *            ---------
> + *            | COS 3 |
> + *            ---------
> + *    L3 CAT  | 0x7ff |
> + *            ---------
> + *    MBA     | 0x0   |
> + *            ---------
> + * 4. After setting, the L3 CAT CBM value of Dom1 should be kept and
> the new MBA
> + *    Thrtl is set. So, the values on COS ID 3 should be below.
> + *            ---------
> + *            | COS 3 |
> + *            ---------
> + *    L3 CAT  | 0x1ff |
> + *            ---------
> + *    MBA     | 0x14  |
> + *            ---------
> + *
> + * So, we should write all features values into their MSRs. That
> requires the
> + * feature array, feature properties array and value array are input.
> + */

Although I understand them, I still have a feeling of the necessity to
reword these comments.

Chao

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel

  reply	other threads:[~2017-08-18  3:32 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-08-09  7:41 [PATCH v1 00/13] Enable Memory Bandwidth Allocation in Xen Yi Sun
2017-08-09  7:41 ` [PATCH v1 01/13] docs: create Memory Bandwidth Allocation (MBA) feature document Yi Sun
2017-08-14  7:35   ` Chao Peng
2017-08-14  8:23     ` Yi Sun
2017-08-14  9:36       ` Chao Peng
2017-08-15 10:08   ` Wei Liu
2017-08-16  2:51     ` Yi Sun
2017-08-09  7:41 ` [PATCH v1 02/13] Rename PSR sysctl/domctl interfaces and xsm policy to make them be general Yi Sun
2017-08-15 10:12   ` Wei Liu
2017-08-16  2:48     ` Yi Sun
2017-08-15 14:03   ` Daniel De Graaf
2017-08-09  7:41 ` [PATCH v1 03/13] x86: rename 'cbm_type' to 'psr_val_type' to make it general Yi Sun
2017-08-15 10:13   ` Wei Liu
2017-08-16  2:17   ` Chao Peng
2017-08-09  7:41 ` [PATCH v1 04/13] x86: implement data structure and CPU init flow for MBA Yi Sun
2017-08-15 10:50   ` Wei Liu
2017-08-16  7:18     ` Yi Sun
2017-08-17  9:49       ` Wei Liu
2017-08-16  3:14   ` Chao Peng
2017-08-09  7:41 ` [PATCH v1 05/13] x86: implement get hw info " Yi Sun
2017-08-16  3:23   ` Chao Peng
2017-08-09  7:41 ` [PATCH v1 06/13] x86: implement get value interface " Yi Sun
2017-08-16  6:38   ` Chao Peng
2017-08-16  6:43     ` Yi Sun
2017-08-17  7:51       ` Chao Peng
2017-08-09  7:41 ` [PATCH v1 07/13] x86: implement set value flow " Yi Sun
2017-08-18  3:32   ` Chao Peng [this message]
2017-08-18  9:25     ` Yi Sun
2017-08-21  7:54       ` Chao Peng
2017-08-09  7:41 ` [PATCH v1 08/13] tools: create general interfaces to support psr allocation features Yi Sun
2017-08-21 10:12   ` Chao Peng
2017-08-22  2:38     ` Yi Sun
2017-08-22  6:42       ` Chao Peng
2017-08-09  7:41 ` [PATCH v1 09/13] tools: implement the new get hw info interface suitable to all " Yi Sun
2017-08-15 11:14   ` Wei Liu
2017-08-21 10:13   ` Chao Peng
2017-08-22  2:38     ` Yi Sun
2017-08-09  7:41 ` [PATCH v1 10/13] tools: rename 'xc_psr_cat_type' to 'xc_psr_val_type' Yi Sun
2017-08-15 11:15   ` Wei Liu
2017-08-21 10:13   ` Chao Peng
2017-08-09  7:41 ` [PATCH v1 11/13] tools: implemet new get value interface suitable for all psr allocation features Yi Sun
2017-08-15 11:24   ` Wei Liu
2017-08-21 10:14   ` Chao Peng
2017-08-22  2:24     ` Yi Sun
2017-08-22  6:44       ` Chao Peng
2017-08-09  7:41 ` [PATCH v1 12/13] tools: implemet new set " Yi Sun
2017-08-15 11:25   ` Wei Liu
2017-08-21 10:15     ` Chao Peng
2017-08-09  7:41 ` [PATCH v1 13/13] docs: add MBA description in docs Yi Sun
2017-08-15 11:26   ` Wei Liu

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=1503027128.3857.14.camel@linux.intel.com \
    --to=chao.p.peng@linux.intel.com \
    --cc=andrew.cooper3@citrix.com \
    --cc=dario.faggioli@citrix.com \
    --cc=ian.jackson@eu.citrix.com \
    --cc=jbeulich@suse.com \
    --cc=julien.grall@arm.com \
    --cc=kevin.tian@intel.com \
    --cc=mengxu@cis.upenn.edu \
    --cc=roger.pau@citrix.com \
    --cc=wei.liu2@citrix.com \
    --cc=xen-devel@lists.xenproject.org \
    --cc=yi.y.sun@linux.intel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.