linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH] Documentation: Chinese translation of Documentation/arm64/perf.rst
@ 2020-09-26 10:22 Bailu Lin
  2020-09-26 14:35 ` Alex Shi
  0 siblings, 1 reply; 8+ messages in thread
From: Bailu Lin @ 2020-09-26 10:22 UTC (permalink / raw)
  To: Catalin Marinas, Will Deacon, Jonathan Corbet, Harry Wei,
	Alex Shi, Bailu Lin, linux-arm-kernel, linux-doc, linux-kernel
  Cc: kernel

This is a Chinese translated version of Documentation/arm64/perf.rst

Signed-off-by: Bailu Lin <bailu.lin@vivo.com>
---
 Documentation/arm64/perf.rst                  |  2 +
 .../translations/zh_CN/arm64/index.rst        |  1 +
 .../translations/zh_CN/arm64/perf.rst         | 85 +++++++++++++++++++
 3 files changed, 88 insertions(+)
 create mode 100644 Documentation/translations/zh_CN/arm64/perf.rst

diff --git a/Documentation/arm64/perf.rst b/Documentation/arm64/perf.rst
index 9c76a97baf28..b567f177d385 100644
--- a/Documentation/arm64/perf.rst
+++ b/Documentation/arm64/perf.rst
@@ -1,5 +1,7 @@
 .. SPDX-License-Identifier: GPL-2.0
 
+.. _perf_index:
+
 =====================
 Perf Event Attributes
 =====================
diff --git a/Documentation/translations/zh_CN/arm64/index.rst b/Documentation/translations/zh_CN/arm64/index.rst
index e31a6090384d..f51fed166326 100644
--- a/Documentation/translations/zh_CN/arm64/index.rst
+++ b/Documentation/translations/zh_CN/arm64/index.rst
@@ -15,3 +15,4 @@ ARM64 架构
 
     amu
     hugetlbpage
+    perf
diff --git a/Documentation/translations/zh_CN/arm64/perf.rst b/Documentation/translations/zh_CN/arm64/perf.rst
new file mode 100644
index 000000000000..ffa0b8ec801d
--- /dev/null
+++ b/Documentation/translations/zh_CN/arm64/perf.rst
@@ -0,0 +1,85 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: :ref:`Documentation/arm64/perf.rst <perf_index>`
+
+Translator: Bailu Lin <bailu.lin@vivo.com>
+
+============
+Perf 事件属性
+============
+
+:作者: Andrew Murray <andrew.murray@arm.com>
+:日期: 2019-03-06
+
+exclude_user
+------------
+
+该属性不包括用户空间。
+
+用户空间始终在 EL0 上运行,因此该属性将排除 EL0。
+
+
+exclude_kernel
+--------------
+
+该属性不包括内核空间。
+
+打开VHE时内核运行在 EL2,不打开时运行在 EL1。客户端的内核总是运行
+在 EL1。
+
+对于主机端,该属性不包括 EL1 和 VHE 上的 EL2。
+
+对于客户端,该属性不包括 EL1。请注意 EL2 从来不算是客户端。
+
+
+exclude_hv
+----------
+
+该属性不包括系统管理程序。
+
+对于 VHE 主机该属性将被忽略,因为我们认为主机端内核是系统管理程序。
+
+对于 non-VHE 的主机端该属性将排除 EL2,因为我们认为系统管理程序运
+行在 EL2 的任何代码主要用于客户端和主机端的切换。
+
+对于客户端该属性无效。请注意 EL2 从来不算是客户端。
+
+
+exclude_host / exclude_guest
+----------------------------
+
+这些属性分别排除了 KVM 主机端和客户端。
+
+KVM 主机端可能运行在 EL0(用户空间),EL1(non-VHE 内核)和
+EL2(VHE 内核 或 non-VHE 系统管理程序)。
+
+KVM 客户端可能运行在 EL0(用户空间)和 EL1(内核)。
+
+由于主机端和客户端之间重叠的异常级别,我们不能仅仅依靠 PMU 的硬件异
+常过滤-因此我们必须启用/禁用对于客户端进入和退出的计数。这在 VHE 和
+non-VHE 系统上表现不同。
+
+对于 non-VHE 系统,我们排除 EL2 的 exclude_host 属性 -  在进入和退
+出客户端时,我们会根据 exclude_host 和 exclude_guest属性在适当的情
+况下禁用/启用该事件。
+
+对于 VHE 系统,我们排除 EL1 的 exclude_guest 属性和 EL0,EL2的两者
+的 exclude_host 属性。在进入和退出客户端时,我们会适当地根据包括/排
+除 EL0 的 exclude_host 和 exclude_guest 属性修改事件。
+
+以上声明也适用于在 not-VHE 客户端使用这些属性时。但是请注意,EL2
+从来不算客户端。
+
+
+准确性
+------
+
+在 non-VHE 主机端上,我们在 EL2 进入/退出主机端/客户端切换时启用/关闭
+计数器 -但是在启用/禁用计数器和进入/退出客户端之间存在一段时间。对于
+exclude_host 当统计客户端事件通过过滤 EL2,我们能够消除客户端进入/退出
+边界上的计数主机端事件的计数。但是当使用 !exclude_hv 时,在客户端进入/
+退出有一个小的暗窗口,无法捕获主机的事件。
+
+在VHE系统尚没有暗窗口。
-- 
2.20.1


^ permalink raw reply related	[flat|nested] 8+ messages in thread

* Re: [PATCH] Documentation: Chinese translation of Documentation/arm64/perf.rst
  2020-09-26 10:22 [PATCH] Documentation: Chinese translation of Documentation/arm64/perf.rst Bailu Lin
@ 2020-09-26 14:35 ` Alex Shi
  2020-09-26 20:15   ` Jonathan Corbet
  0 siblings, 1 reply; 8+ messages in thread
From: Alex Shi @ 2020-09-26 14:35 UTC (permalink / raw)
  To: Bailu Lin, Catalin Marinas, Will Deacon, Jonathan Corbet,
	Harry Wei, linux-arm-kernel, linux-doc, linux-kernel
  Cc: kernel

Why your patch repeatly has encoding issue which fails on 'git am'
Could you like to check the problem before send out?
Could you please fix your editor issue by Documentation/process/email-clients.rst
or send patch by git send-email.

And please don't waste other time on meaningless issue again!

Thanks
Alex

在 2020/9/26 下午6:22, Bailu Lin 写道:
> This is a Chinese translated version of Documentation/arm64/perf.rst
> 
> Signed-off-by: Bailu Lin <bailu.lin@vivo.com>
> ---
>  Documentation/arm64/perf.rst                  |  2 +
>  .../translations/zh_CN/arm64/index.rst        |  1 +
>  .../translations/zh_CN/arm64/perf.rst         | 85 +++++++++++++++++++
>  3 files changed, 88 insertions(+)
>  create mode 100644 Documentation/translations/zh_CN/arm64/perf.rst
> 
> diff --git a/Documentation/arm64/perf.rst b/Documentation/arm64/perf.rst
> index 9c76a97baf28..b567f177d385 100644
> --- a/Documentation/arm64/perf.rst
> +++ b/Documentation/arm64/perf.rst
> @@ -1,5 +1,7 @@
>  .. SPDX-License-Identifier: GPL-2.0
>  
> +.. _perf_index:
> +
>  =====================
>  Perf Event Attributes
>  =====================
> diff --git a/Documentation/translations/zh_CN/arm64/index.rst b/Documentation/translations/zh_CN/arm64/index.rst
> index e31a6090384d..f51fed166326 100644
> --- a/Documentation/translations/zh_CN/arm64/index.rst
> +++ b/Documentation/translations/zh_CN/arm64/index.rst
> @@ -15,3 +15,4 @@ ARM64 架构
>  
>      amu
>      hugetlbpage
> +    perf
> diff --git a/Documentation/translations/zh_CN/arm64/perf.rst b/Documentation/translations/zh_CN/arm64/perf.rst
> new file mode 100644
> index 000000000000..ffa0b8ec801d
> --- /dev/null
> +++ b/Documentation/translations/zh_CN/arm64/perf.rst
> @@ -0,0 +1,85 @@
> +.. SPDX-License-Identifier: GPL-2.0
> +
> +.. include:: ../disclaimer-zh_CN.rst
> +
> +:Original: :ref:`Documentation/arm64/perf.rst <perf_index>`
> +
> +Translator: Bailu Lin <bailu.lin@vivo.com>
> +
> +============
> +Perf 事件属性
> +============
> +
> +:作者: Andrew Murray <andrew.murray@arm.com>
> +:日期: 2019-03-06
> +
> +exclude_user
> +------------
> +
> +该属性不包括用户空间。
> +
> +用户空间始终在 EL0 上运行,因此该属性将排除 EL0。
> +
> +
> +exclude_kernel
> +--------------
> +
> +该属性不包括内核空间。
> +
> +打开VHE时内核运行在 EL2,不打开时运行在 EL1。客户端的内核总是运行
> +在 EL1。
> +
> +对于主机端,该属性不包括 EL1 和 VHE 上的 EL2。
> +
> +对于客户端,该属性不包括 EL1。请注意 EL2 从来不算是客户端。
> +
> +
> +exclude_hv
> +----------
> +
> +该属性不包括系统管理程序。
> +
> +对于 VHE 主机该属性将被忽略,因为我们认为主机端内核是系统管理程序。
> +
> +对于 non-VHE 的主机端该属性将排除 EL2,因为我们认为系统管理程序运
> +行在 EL2 的任何代码主要用于客户端和主机端的切换。
> +
> +对于客户端该属性无效。请注意 EL2 从来不算是客户端。
> +
> +
> +exclude_host / exclude_guest
> +----------------------------
> +
> +这些属性分别排除了 KVM 主机端和客户端。
> +
> +KVM 主机端可能运行在 EL0(用户空间),EL1(non-VHE 内核)和
> +EL2(VHE 内核 或 non-VHE 系统管理程序)。
> +
> +KVM 客户端可能运行在 EL0(用户空间)和 EL1(内核)。
> +
> +由于主机端和客户端之间重叠的异常级别,我们不能仅仅依靠 PMU 的硬件异
> +常过滤-因此我们必须启用/禁用对于客户端进入和退出的计数。这在 VHE 和
> +non-VHE 系统上表现不同。
> +
> +对于 non-VHE 系统,我们排除 EL2 的 exclude_host 属性 -  在进入和退
> +出客户端时,我们会根据 exclude_host 和 exclude_guest属性在适当的情
> +况下禁用/启用该事件。
> +
> +对于 VHE 系统,我们排除 EL1 的 exclude_guest 属性和 EL0,EL2的两者
> +的 exclude_host 属性。在进入和退出客户端时,我们会适当地根据包括/排
> +除 EL0 的 exclude_host 和 exclude_guest 属性修改事件。
> +
> +以上声明也适用于在 not-VHE 客户端使用这些属性时。但是请注意,EL2
> +从来不算客户端。
> +
> +
> +准确性
> +------
> +
> +在 non-VHE 主机端上,我们在 EL2 进入/退出主机端/客户端切换时启用/关闭
> +计数器 -但是在启用/禁用计数器和进入/退出客户端之间存在一段时间。对于
> +exclude_host 当统计客户端事件通过过滤 EL2,我们能够消除客户端进入/退出
> +边界上的计数主机端事件的计数。但是当使用 !exclude_hv 时,在客户端进入/
> +退出有一个小的暗窗口,无法捕获主机的事件。
> +
> +在VHE系统尚没有暗窗口。
> 

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH] Documentation: Chinese translation of Documentation/arm64/perf.rst
  2020-09-26 14:35 ` Alex Shi
@ 2020-09-26 20:15   ` Jonathan Corbet
  2020-09-27  2:12     ` Alex Shi
  0 siblings, 1 reply; 8+ messages in thread
From: Jonathan Corbet @ 2020-09-26 20:15 UTC (permalink / raw)
  To: Alex Shi
  Cc: Bailu Lin, Catalin Marinas, Will Deacon, Harry Wei,
	linux-arm-kernel, linux-doc, linux-kernel, kernel

On Sat, 26 Sep 2020 22:35:51 +0800
Alex Shi <alex.shi@linux.alibaba.com> wrote:

> Why your patch repeatly has encoding issue which fails on 'git am'
> Could you like to check the problem before send out?
> Could you please fix your editor issue by Documentation/process/email-clients.rst
> or send patch by git send-email.
> 
> And please don't waste other time on meaningless issue again!

The way to be sure you have solved this kind of problem is to first email
the patch to you, then be sure that what you receive can be applied.
Please get to the point where that works, then I'll be glad to apply your
translations.

Thanks,

jon

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH] Documentation: Chinese translation of Documentation/arm64/perf.rst
  2020-09-26 20:15   ` Jonathan Corbet
@ 2020-09-27  2:12     ` Alex Shi
  2020-09-28  6:59       ` 林白鹭
  0 siblings, 1 reply; 8+ messages in thread
From: Alex Shi @ 2020-09-27  2:12 UTC (permalink / raw)
  To: Jonathan Corbet
  Cc: Bailu Lin, Catalin Marinas, Will Deacon, Harry Wei,
	linux-arm-kernel, linux-doc, linux-kernel, kernel, Wang Qing

		

在 2020/9/27 上午4:15, Jonathan Corbet 写道:
> On Sat, 26 Sep 2020 22:35:51 +0800
> Alex Shi <alex.shi@linux.alibaba.com> wrote:
> 
>> Why your patch repeatly has encoding issue which fails on 'git am'
>> Could you like to check the problem before send out?
>> Could you please fix your editor issue by Documentation/process/email-clients.rst
>> or send patch by git send-email.
>>
>> And please don't waste other time on meaningless issue again!
> 
> The way to be sure you have solved this kind of problem is to first email
> the patch to you, then be sure that what you receive can be applied.
> Please get to the point where that works, then I'll be glad to apply your
> translations.
> 

CC Qing,

There are few documents of how to join the community development
  https://www.kernel.org/doc/html/latest/translations/zh_CN/index.html
Shortly, sth could be summaried as following in pariticular documents.

1, setup well your email client, to be sure all your patch from your email system
could be applied by 'git am'. Current email client often cover the endcoding issue
but git will failed on that.

2, 'make help' show couple of doc related options:
  htmldocs        - HTML
  latexdocs       - LaTeX
  pdfdocs         - PDF
  epubdocs        - EPUB
  xmldocs         - XML
  linkcheckdocs   - check for broken external links
                    (will connect to external hosts)
  refcheckdocs    - check for references to non-existing files under
                    Documentation
  cleandocs       - clean all generated files

Do 'make linkcheckdocs/refcheckdocs/htmldocs', and check if the result works as
expected, of course it would be better if you can make/check all type docs, but
at least finish above 3 kinds of checks.

3, As to related docs, sending them as a couple series could help people retrieve
easy.

looking forward for your new translation docs.

Thanks
Alex

> Thanks,
> 
> jon
> 

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re:Re: [PATCH] Documentation: Chinese translation of Documentation/arm64/perf.rst
  2020-09-27  2:12     ` Alex Shi
@ 2020-09-28  6:59       ` 林白鹭
  0 siblings, 0 replies; 8+ messages in thread
From: 林白鹭 @ 2020-09-28  6:59 UTC (permalink / raw)
  To: Alex Shi
  Cc: Jonathan Corbet, Catalin Marinas, Will Deacon, Harry Wei,
	linux-arm-kernel, linux-doc, linux-kernel, kernel, Wang Qing

>在 2020/9/27 上午4:15, Jonathan Corbet 写道:
>> On Sat, 26 Sep 2020 22:35:51 +0800
>> Alex Shi <alex.shi@linux.alibaba.com> wrote:
>> 
>>> Why your patch repeatly has encoding issue which fails on 'git am'
>>> Could you like to check the problem before send out?
>>> Could you please fix your editor issue by Documentation/process/email-clients.rst
>>> or send patch by git send-email.
>>>
>>> And please don't waste other time on meaningless issue again!
>> 
>> The way to be sure you have solved this kind of problem is to first email
>> the patch to you, then be sure that what you receive can be applied.
>> Please get to the point where that works, then I'll be glad to apply your
>> translations.
>> 
>
>CC Qing,
>
>There are few documents of how to join the community development
>  https://www.kernel.org/doc/html/latest/translations/zh_CN/index.html
>Shortly, sth could be summaried as following in pariticular documents.
>
>1, setup well your email client, to be sure all your patch from your email system
>could be applied by 'git am'. Current email client often cover the endcoding issue
>but git will failed on that.
>
>2, 'make help' show couple of doc related options:
>  htmldocs        - HTML
>  latexdocs       - LaTeX
>  pdfdocs         - PDF
>  epubdocs        - EPUB
>  xmldocs         - XML
>  linkcheckdocs   - check for broken external links
>                    (will connect to external hosts)
>  refcheckdocs    - check for references to non-existing files under
>                    Documentation
>  cleandocs       - clean all generated files
>
>Do 'make linkcheckdocs/refcheckdocs/htmldocs', and check if the result works as
>expected, of course it would be better if you can make/check all type docs, but
>at least finish above 3 kinds of checks.
>
>3, As to related docs, sending them as a couple series could help people retrieve
>easy.
>
>looking forward for your new translation docs.
>

Sorry for bringing trouble. I used 'git send-email' with UTF-8, also built with 
'make htmldocs'. I think that caused by two patches(translation of 
Documentation/arm64/hugetlbpage.rst and Documentation/arm64/perf.rst)
sequence, hugetlbpage first perf.rst second. It's my mistake,I'll send with patch
Series for this two patch.

Thanks
Bailu

>Thanks
>Alex
>




^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH] Documentation: Chinese translation of Documentation/arm64/perf.rst
  2020-10-29 15:14 Bailu Lin
@ 2020-10-30  2:33 ` Alex Shi
  0 siblings, 0 replies; 8+ messages in thread
From: Alex Shi @ 2020-10-30  2:33 UTC (permalink / raw)
  To: Bailu Lin
  Cc: Catalin Marinas, Will Deacon, Jonathan Corbet, Harry Wei,
	linux-arm-kernel, linux-doc, linux-kernel, kernel



在 2020/10/29 下午11:14, Bailu Lin 写道:
>> 暗窗口 maynot the best, but I have no better on blackout window..
>>
> Is "灰色的窗口期" better ?

Google translation suggest: 停电窗口, 
Baidu translation suggest: 遮光窗

I personally prefer google's translation here. :)

Thanks

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH] Documentation: Chinese translation of Documentation/arm64/perf.rst
  2020-10-28 13:48 Bailu Lin
@ 2020-10-29  5:55 ` Alex Shi
  0 siblings, 0 replies; 8+ messages in thread
From: Alex Shi @ 2020-10-29  5:55 UTC (permalink / raw)
  To: Bailu Lin, Catalin Marinas, Will Deacon, Jonathan Corbet,
	Harry Wei, linux-arm-kernel, linux-doc, linux-kernel
  Cc: kernel



在 2020/10/28 下午9:48, Bailu Lin 写道:
> This is a Chinese translated version of
>  Documentation/arm64/perf.rst
> 
> Signed-off-by: Bailu Lin <bailu.lin@vivo.com>
> ---
>  Documentation/arm64/perf.rst                  |  2 +
>  .../translations/zh_CN/arm64/index.rst        |  1 +
>  .../translations/zh_CN/arm64/perf.rst         | 85 +++++++++++++++++++
>  3 files changed, 88 insertions(+)
>  create mode 100644 Documentation/translations/zh_CN/arm64/perf.rst
> 
> diff --git a/Documentation/arm64/perf.rst b/Documentation/arm64/perf.rst
> index 9c76a97baf28..b567f177d385 100644
> --- a/Documentation/arm64/perf.rst
> +++ b/Documentation/arm64/perf.rst
> @@ -1,5 +1,7 @@
>  .. SPDX-License-Identifier: GPL-2.0
>  
> +.. _perf_index:
> +
>  =====================
>  Perf Event Attributes
>  =====================
> diff --git a/Documentation/translations/zh_CN/arm64/index.rst b/Documentation/translations/zh_CN/arm64/index.rst
> index e31a6090384d..f51fed166326 100644
> --- a/Documentation/translations/zh_CN/arm64/index.rst
> +++ b/Documentation/translations/zh_CN/arm64/index.rst
> @@ -15,3 +15,4 @@ ARM64 架构
>  
>      amu
>      hugetlbpage
> +    perf
> diff --git a/Documentation/translations/zh_CN/arm64/perf.rst b/Documentation/translations/zh_CN/arm64/perf.rst
> new file mode 100644
> index 000000000000..be8269dd5d9a
> --- /dev/null
> +++ b/Documentation/translations/zh_CN/arm64/perf.rst
> @@ -0,0 +1,85 @@
> +.. SPDX-License-Identifier: GPL-2.0
> +
> +.. include:: ../disclaimer-zh_CN.rst
> +
> +:Original: :ref:`Documentation/arm64/perf.rst <perf_index>`
> +
> +Translator: Bailu Lin <bailu.lin@vivo.com>
> +
> +=============
> +Perf 事件属性
> +=============
> +
> +:作者: Andrew Murray <andrew.murray@arm.com>
> +:日期: 2019-03-06
> +
> +exclude_user
> +------------
> +
> +该属性排除用户空间。
> +
> +用户空间始终运行在 EL0,因此该属性将排除 EL0。
> +
> +
> +exclude_kernel
> +--------------
> +
> +该属性排除内核空间。
> +
> +打开 VHE 时内核运行在 EL2,不打开 VHE 时内核运行在 EL1。客户端

guest kernel could be better translated as '客户内核' ? 
'客户端' is easy to confuse with aonther word 'client'
So shall we better to use 客户, or 客户机 for 'guest/guest machine'

And 'host' here means 宿主/宿主机 better than 主机。 

Also couple wiki tranlates hypervisor as 虚拟机监视器

> +内核总是运行在 EL1。
> +
> +对于主机端,该属性排除 EL1 和 VHE 上的 EL2。
> +
> +对于客户端,该属性排除 EL1。请注意客户端从来不会运行在 EL2。
> +
> +
> +exclude_hv
> +----------
> +
> +该属性排除虚拟机监控器。
> +
> +对于 VHE 主机端该属性将被忽略,因为此时主机端内核是虚拟机监控器。

s/此时/我们认为/

> +
> +对于 non-VHE 主机端该属性将排除 EL2,因为虚拟机监控器运行在 EL2
> +的任何代码主要用于客户端和主机端的切换。
> +
> +对于客户端该属性无效。请注意客户端从来不会运行在 EL2。
> +
> +
> +exclude_host / exclude_guest
> +----------------------------
> +
> +这些属性分别排除了 KVM 主机端和客户端。
> +
> +KVM 主机端可能运行在 EL0(用户空间),EL1(non-VHE 内核)和
> +EL2(VHE 内核 或 non-VHE 虚拟机监控器)。
> +
> +KVM 客户端可能运行在 EL0(用户空间)和 EL1(内核)。
> +
> +由于主机端和客户端之间重叠的异常级别,我们不能仅仅依靠 PMU 的硬件异
> +常过滤机制-因此我们必须启用/禁用对于客户端进入和退出的计数。而这在
> +VHE 和 non-VHE 系统上表现不同。
> +
> +对于 non-VHE 系统的 exclude_host 属性排除 EL2 -  在进入和退出客户
> +端时,我们会根据 exclude_host 和 exclude_guest 属性在适当的情况下
> +禁用/启用该事件。
> +
> +对于 VHE 系统的 exclude_guest 属性排除 EL1,而对其中的 exclude_host
> +属性同时排除 EL0,EL2。在进入和退出客户端时,我们会适当地根据
> +exclude_host 和 exclude_guest 属性包括/排除 EL0。
> +
> +以上声明也适用于在 not-VHE 客户端使用这些属性时,但是请注意客户端从
> +来不会运行在 EL2。
> +
> +
> +准确性
> +------
> +
> +在 non-VHE 主机端上,我们在 EL2 进入/退出主机端/客户端的切换时启用/
> +关闭计数器 -但是在启用/禁用计数器和进入/退出客户端之间存在一段延时。
> +对于 exclude_host, 我们可以通过过滤 EL2 消除在客户端进入/退出边界
> +上用于计数客户端事件的主机端事件计数器。但是当使用 !exclude_hv 时,
> +在客户端进入/退出有一个小的暗窗口无法捕获到主机端的事件。
> +
> +在VHE系统尚没有暗窗口。
> 

暗窗口 maynot the best, but I have no better on blackout window..

Thanks
Alex

^ permalink raw reply	[flat|nested] 8+ messages in thread

* [PATCH] Documentation: Chinese translation of  Documentation/arm64/perf.rst
@ 2020-10-28 13:48 Bailu Lin
  2020-10-29  5:55 ` Alex Shi
  0 siblings, 1 reply; 8+ messages in thread
From: Bailu Lin @ 2020-10-28 13:48 UTC (permalink / raw)
  To: Catalin Marinas, Will Deacon, Jonathan Corbet, Harry Wei,
	Alex Shi, Bailu Lin, linux-arm-kernel, linux-doc, linux-kernel
  Cc: kernel

This is a Chinese translated version of
 Documentation/arm64/perf.rst

Signed-off-by: Bailu Lin <bailu.lin@vivo.com>
---
 Documentation/arm64/perf.rst                  |  2 +
 .../translations/zh_CN/arm64/index.rst        |  1 +
 .../translations/zh_CN/arm64/perf.rst         | 85 +++++++++++++++++++
 3 files changed, 88 insertions(+)
 create mode 100644 Documentation/translations/zh_CN/arm64/perf.rst

diff --git a/Documentation/arm64/perf.rst b/Documentation/arm64/perf.rst
index 9c76a97baf28..b567f177d385 100644
--- a/Documentation/arm64/perf.rst
+++ b/Documentation/arm64/perf.rst
@@ -1,5 +1,7 @@
 .. SPDX-License-Identifier: GPL-2.0
 
+.. _perf_index:
+
 =====================
 Perf Event Attributes
 =====================
diff --git a/Documentation/translations/zh_CN/arm64/index.rst b/Documentation/translations/zh_CN/arm64/index.rst
index e31a6090384d..f51fed166326 100644
--- a/Documentation/translations/zh_CN/arm64/index.rst
+++ b/Documentation/translations/zh_CN/arm64/index.rst
@@ -15,3 +15,4 @@ ARM64 架构
 
     amu
     hugetlbpage
+    perf
diff --git a/Documentation/translations/zh_CN/arm64/perf.rst b/Documentation/translations/zh_CN/arm64/perf.rst
new file mode 100644
index 000000000000..be8269dd5d9a
--- /dev/null
+++ b/Documentation/translations/zh_CN/arm64/perf.rst
@@ -0,0 +1,85 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: :ref:`Documentation/arm64/perf.rst <perf_index>`
+
+Translator: Bailu Lin <bailu.lin@vivo.com>
+
+=============
+Perf 事件属性
+=============
+
+:作者: Andrew Murray <andrew.murray@arm.com>
+:日期: 2019-03-06
+
+exclude_user
+------------
+
+该属性排除用户空间。
+
+用户空间始终运行在 EL0,因此该属性将排除 EL0。
+
+
+exclude_kernel
+--------------
+
+该属性排除内核空间。
+
+打开 VHE 时内核运行在 EL2,不打开 VHE 时内核运行在 EL1。客户端
+内核总是运行在 EL1。
+
+对于主机端,该属性排除 EL1 和 VHE 上的 EL2。
+
+对于客户端,该属性排除 EL1。请注意客户端从来不会运行在 EL2。
+
+
+exclude_hv
+----------
+
+该属性排除虚拟机监控器。
+
+对于 VHE 主机端该属性将被忽略,因为此时主机端内核是虚拟机监控器。
+
+对于 non-VHE 主机端该属性将排除 EL2,因为虚拟机监控器运行在 EL2
+的任何代码主要用于客户端和主机端的切换。
+
+对于客户端该属性无效。请注意客户端从来不会运行在 EL2。
+
+
+exclude_host / exclude_guest
+----------------------------
+
+这些属性分别排除了 KVM 主机端和客户端。
+
+KVM 主机端可能运行在 EL0(用户空间),EL1(non-VHE 内核)和
+EL2(VHE 内核 或 non-VHE 虚拟机监控器)。
+
+KVM 客户端可能运行在 EL0(用户空间)和 EL1(内核)。
+
+由于主机端和客户端之间重叠的异常级别,我们不能仅仅依靠 PMU 的硬件异
+常过滤机制-因此我们必须启用/禁用对于客户端进入和退出的计数。而这在
+VHE 和 non-VHE 系统上表现不同。
+
+对于 non-VHE 系统的 exclude_host 属性排除 EL2 -  在进入和退出客户
+端时,我们会根据 exclude_host 和 exclude_guest 属性在适当的情况下
+禁用/启用该事件。
+
+对于 VHE 系统的 exclude_guest 属性排除 EL1,而对其中的 exclude_host
+属性同时排除 EL0,EL2。在进入和退出客户端时,我们会适当地根据
+exclude_host 和 exclude_guest 属性包括/排除 EL0。
+
+以上声明也适用于在 not-VHE 客户端使用这些属性时,但是请注意客户端从
+来不会运行在 EL2。
+
+
+准确性
+------
+
+在 non-VHE 主机端上,我们在 EL2 进入/退出主机端/客户端的切换时启用/
+关闭计数器 -但是在启用/禁用计数器和进入/退出客户端之间存在一段延时。
+对于 exclude_host, 我们可以通过过滤 EL2 消除在客户端进入/退出边界
+上用于计数客户端事件的主机端事件计数器。但是当使用 !exclude_hv 时,
+在客户端进入/退出有一个小的暗窗口无法捕获到主机端的事件。
+
+在VHE系统尚没有暗窗口。
-- 
2.20.1


^ permalink raw reply related	[flat|nested] 8+ messages in thread

end of thread, other threads:[~2020-10-30  2:35 UTC | newest]

Thread overview: 8+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-09-26 10:22 [PATCH] Documentation: Chinese translation of Documentation/arm64/perf.rst Bailu Lin
2020-09-26 14:35 ` Alex Shi
2020-09-26 20:15   ` Jonathan Corbet
2020-09-27  2:12     ` Alex Shi
2020-09-28  6:59       ` 林白鹭
2020-10-28 13:48 Bailu Lin
2020-10-29  5:55 ` Alex Shi
2020-10-29 15:14 Bailu Lin
2020-10-30  2:33 ` Alex Shi

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).