<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: is MSR access in only-read mode safe? in Software Tuning, Performance Optimization &amp; Platform Monitoring</title>
    <link>https://community.intel.com/t5/Software-Tuning-Performance/is-MSR-access-in-only-read-mode-safe/m-p/1602466#M8352</link>
    <description>&lt;P&gt;I routinely read all the MSRs on systems to document the system state -- this has never caused any crashes or misbehavior, so it is "safe" in that limited sense.&lt;/P&gt;&lt;P&gt;Read access to MSRs is "unsafe" in the sense of system security. &amp;nbsp;It allows any user with access to read a whole lot of state that is supposed to be private to the OS or to other users. &amp;nbsp;I don't know of any specific exploits that I could name, but some of the problematic content includes:&lt;/P&gt;&lt;UL&gt;&lt;LI&gt;Read the core performance counter programming and performance counter values on any core.&lt;/LI&gt;&lt;LI&gt;Read the CHA/SF/LLC performance counter programming and counter values for any CHA/SF/LLC block.&lt;/LI&gt;&lt;LI&gt;Machine Check Architecture records&lt;UL&gt;&lt;LI&gt;(May help with RowHammer-type attacks?)&lt;/LI&gt;&lt;/UL&gt;&lt;/LI&gt;&lt;/UL&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Thu, 30 May 2024 15:40:35 GMT</pubDate>
    <dc:creator>McCalpinJohn</dc:creator>
    <dc:date>2024-05-30T15:40:35Z</dc:date>
    <item>
      <title>is MSR access in only-read mode safe?</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/is-MSR-access-in-only-read-mode-safe/m-p/1297800#M7907</link>
      <description>&lt;P&gt;Hello,&lt;/P&gt;
&lt;P&gt;I developed a tool based on&amp;nbsp; (Linux) rdmsr to read some MSR registers (RAPL). And I would like to have this tool installed on large computing clusters.&lt;/P&gt;
&lt;P&gt;I know that allowing read AND write of MSR registers for all the users is not safe, mainly due to the write capability.&lt;/P&gt;
&lt;P&gt;I suppose that allowing only read (even for all users) is safe, but I failed to find literature on it.&lt;/P&gt;
&lt;P&gt;Is there any? Is it obvious?&lt;/P&gt;
&lt;P&gt;Thanks in advance for your help,&lt;/P&gt;
&lt;P&gt;hervem&lt;/P&gt;</description>
      <pubDate>Mon, 12 Jul 2021 12:14:02 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/is-MSR-access-in-only-read-mode-safe/m-p/1297800#M7907</guid>
      <dc:creator>hervem</dc:creator>
      <dc:date>2021-07-12T12:14:02Z</dc:date>
    </item>
    <item>
      <title>Re: is MSR access in only-read mode safe?</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/is-MSR-access-in-only-read-mode-safe/m-p/1305287#M7926</link>
      <description>&lt;P&gt;"Safe" can mean several different things in this context....&lt;/P&gt;
&lt;P&gt;Write access to MSRs can fairly easily crash a system. &amp;nbsp;Read access to MSRs should not be able to crash a system.&lt;/P&gt;
&lt;P&gt;Read access to MSRs opens a fair number of security risks.&lt;/P&gt;
&lt;P&gt;The project&amp;nbsp;&lt;A href="https://github.com/LLNL/msr-safe" target="_blank"&gt;https://github.com/LLNL/msr-safe&lt;/A&gt;&amp;nbsp;provides the ability grant different permissions to different MSRs. &amp;nbsp;Limiting the accessible MSRs to the ones of interest can reduce the uncertainty about security risks. &amp;nbsp;I have not deployed this package on production systems, but had no trouble getting it to work properly on a test cluster.&lt;/P&gt;</description>
      <pubDate>Tue, 10 Aug 2021 14:45:17 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/is-MSR-access-in-only-read-mode-safe/m-p/1305287#M7926</guid>
      <dc:creator>McCalpinJohn</dc:creator>
      <dc:date>2021-08-10T14:45:17Z</dc:date>
    </item>
    <item>
      <title>Re: is MSR access in only-read mode safe?</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/is-MSR-access-in-only-read-mode-safe/m-p/1311086#M7931</link>
      <description>&lt;P&gt;Thanks for your help.&lt;BR /&gt;&lt;BR /&gt;I agree, msr-safe is a good candidate to limit the risks. I did not use it yet.&amp;nbsp;&lt;BR /&gt;&lt;BR /&gt;BTW &lt;BR /&gt;In HPC context the users allocate usually nodes with exclusivity access (not shared).&lt;BR /&gt;NB : If the node is not allocated in an exclusive mode, you can have a look on what is running on the node (from yourself or not), with or without msr_read.&lt;BR /&gt;&lt;BR /&gt;So safe could be understood as :&lt;BR /&gt;By using (only) msr_read, can we access information we should not access as a basic user (eg password, code&amp;amp;data of other users) ? or can we modify the cluster behavior ?&lt;BR /&gt;I would say NO, but perhaps I am wrong.&lt;/P&gt;</description>
      <pubDate>Tue, 31 Aug 2021 11:17:01 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/is-MSR-access-in-only-read-mode-safe/m-p/1311086#M7931</guid>
      <dc:creator>hervem</dc:creator>
      <dc:date>2021-08-31T11:17:01Z</dc:date>
    </item>
    <item>
      <title>Re: is MSR access in only-read mode safe?</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/is-MSR-access-in-only-read-mode-safe/m-p/1602304#M8349</link>
      <description>&lt;P&gt;Hello&amp;nbsp;&lt;SPAN&gt;McCalpinJohn,&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;What are the risks for read access to the MSRs?&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Thanks,&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Uri&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Thu, 30 May 2024 08:00:00 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/is-MSR-access-in-only-read-mode-safe/m-p/1602304#M8349</guid>
      <dc:creator>urimashi</dc:creator>
      <dc:date>2024-05-30T08:00:00Z</dc:date>
    </item>
    <item>
      <title>Re: is MSR access in only-read mode safe?</title>
      <link>https://community.intel.com/t5/Software-Tuning-Performance/is-MSR-access-in-only-read-mode-safe/m-p/1602466#M8352</link>
      <description>&lt;P&gt;I routinely read all the MSRs on systems to document the system state -- this has never caused any crashes or misbehavior, so it is "safe" in that limited sense.&lt;/P&gt;&lt;P&gt;Read access to MSRs is "unsafe" in the sense of system security. &amp;nbsp;It allows any user with access to read a whole lot of state that is supposed to be private to the OS or to other users. &amp;nbsp;I don't know of any specific exploits that I could name, but some of the problematic content includes:&lt;/P&gt;&lt;UL&gt;&lt;LI&gt;Read the core performance counter programming and performance counter values on any core.&lt;/LI&gt;&lt;LI&gt;Read the CHA/SF/LLC performance counter programming and counter values for any CHA/SF/LLC block.&lt;/LI&gt;&lt;LI&gt;Machine Check Architecture records&lt;UL&gt;&lt;LI&gt;(May help with RowHammer-type attacks?)&lt;/LI&gt;&lt;/UL&gt;&lt;/LI&gt;&lt;/UL&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 30 May 2024 15:40:35 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Tuning-Performance/is-MSR-access-in-only-read-mode-safe/m-p/1602466#M8352</guid>
      <dc:creator>McCalpinJohn</dc:creator>
      <dc:date>2024-05-30T15:40:35Z</dc:date>
    </item>
  </channel>
</rss>

