<?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 Is VT-d necessary for TXT in Software Archive</title>
    <link>https://community.intel.com/t5/Software-Archive/Is-VT-d-necessary-for-TXT/m-p/876510#M8983</link>
    <description>&lt;P&gt;I know TXT requires that TXT heap, AC and MLE must reside in DMA-protected region. DPR and PMR are two methods to handle it. The DPR (DMA protected range) is said to work at final check after VT-d in official development guide. It should be locked once initialized by BIOS. I guess it is a chipset function and can work without VT-d because it is controlled by TXT.DPR and I never found it in VT-d document.&lt;/P&gt;
&lt;P&gt;&lt;/P&gt;
&lt;P&gt;So, if DPR is defined large enough to cover MLE (it said currently DPR is 3MB), can I say GETSEC[SENTER] can be executed without VT-d? Will AC check VT-d even if DPR is correctly set?&lt;/P&gt;
&lt;P&gt;&lt;/P&gt;
&lt;P&gt;I want to know it beacuse my machine, Dell T3400 is equipped with X38 chipset. It is VT-d capable but I'm afraid BIOS do not enable it since I cannot find DMAR entry in ACPI. I prefer to do some experiments before I upgrade to a newer machine (it is unavoidable because the lastest AC module discontinues to support X38).&lt;/P&gt;
&lt;P&gt;&lt;/P&gt;
&lt;P&gt;Thanks.&lt;/P&gt;</description>
    <pubDate>Fri, 05 Mar 2010 12:30:25 GMT</pubDate>
    <dc:creator>haojn</dc:creator>
    <dc:date>2010-03-05T12:30:25Z</dc:date>
    <item>
      <title>Is VT-d necessary for TXT</title>
      <link>https://community.intel.com/t5/Software-Archive/Is-VT-d-necessary-for-TXT/m-p/876510#M8983</link>
      <description>&lt;P&gt;I know TXT requires that TXT heap, AC and MLE must reside in DMA-protected region. DPR and PMR are two methods to handle it. The DPR (DMA protected range) is said to work at final check after VT-d in official development guide. It should be locked once initialized by BIOS. I guess it is a chipset function and can work without VT-d because it is controlled by TXT.DPR and I never found it in VT-d document.&lt;/P&gt;
&lt;P&gt;&lt;/P&gt;
&lt;P&gt;So, if DPR is defined large enough to cover MLE (it said currently DPR is 3MB), can I say GETSEC[SENTER] can be executed without VT-d? Will AC check VT-d even if DPR is correctly set?&lt;/P&gt;
&lt;P&gt;&lt;/P&gt;
&lt;P&gt;I want to know it beacuse my machine, Dell T3400 is equipped with X38 chipset. It is VT-d capable but I'm afraid BIOS do not enable it since I cannot find DMAR entry in ACPI. I prefer to do some experiments before I upgrade to a newer machine (it is unavoidable because the lastest AC module discontinues to support X38).&lt;/P&gt;
&lt;P&gt;&lt;/P&gt;
&lt;P&gt;Thanks.&lt;/P&gt;</description>
      <pubDate>Fri, 05 Mar 2010 12:30:25 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Archive/Is-VT-d-necessary-for-TXT/m-p/876510#M8983</guid>
      <dc:creator>haojn</dc:creator>
      <dc:date>2010-03-05T12:30:25Z</dc:date>
    </item>
    <item>
      <title>Is VT-d necessary for TXT</title>
      <link>https://community.intel.com/t5/Software-Archive/Is-VT-d-necessary-for-TXT/m-p/876511#M8984</link>
      <description>&lt;P&gt;Updates:&lt;/P&gt;
&lt;P&gt;&lt;/P&gt;
&lt;P&gt;I just got reply from Dell. They said for T3400 with A09 BIOS, VT-d will be enabled whenever VT is enabled.&lt;/P&gt;
&lt;P&gt;&lt;/P&gt;
&lt;P&gt;But I cannot confirm it since I am failed to find "DMAR" in ACPI list. Interestingly, when I dump PCI configure space into file, I can see bit to indicate "VT-d enabled" is set on memory controller hub (B0/D0/F0). Yet, bit for "TXT mode disabled" is also set. I am going to test SENTER to check it.&lt;/P&gt;
&lt;P&gt;&lt;/P&gt;
&lt;P&gt;Before that, I wonder is there any convention for DRHD table base address? In Flicker, it is 0xfed90000. ?Is that a common address?&lt;/P&gt;</description>
      <pubDate>Tue, 16 Mar 2010 07:04:27 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Archive/Is-VT-d-necessary-for-TXT/m-p/876511#M8984</guid>
      <dc:creator>haojn</dc:creator>
      <dc:date>2010-03-16T07:04:27Z</dc:date>
    </item>
    <item>
      <title>Is VT-d necessary for TXT</title>
      <link>https://community.intel.com/t5/Software-Archive/Is-VT-d-necessary-for-TXT/m-p/876512#M8985</link>
      <description>Ibrought yourquestion to the attention ofa TXT engineer and have been waiting on a reply. Will post result asap.&lt;BR /&gt;&lt;BR /&gt;David Ott</description>
      <pubDate>Wed, 17 Mar 2010 17:38:18 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Archive/Is-VT-d-necessary-for-TXT/m-p/876512#M8985</guid>
      <dc:creator>David_O_Intel1</dc:creator>
      <dc:date>2010-03-17T17:38:18Z</dc:date>
    </item>
    <item>
      <title>Is VT-d necessary for TXT</title>
      <link>https://community.intel.com/t5/Software-Archive/Is-VT-d-necessary-for-TXT/m-p/876513#M8986</link>
      <description>About your first posting above, I received this comment from an expert on the subject:&lt;BR /&gt;&lt;BR /&gt;"Even though the MLE can be put in the DPR and the DPR does not depend on VT-d, VT-d is still required on the platform. SINIT will verify the VT-d DMAR ACPI tables so that any MLE code that wants to use VT-d can do so safely. The MLE, however, does not have to use VT-d; the platform/BIOS simply must enable it."&lt;BR /&gt;&lt;BR /&gt;David Ott</description>
      <pubDate>Wed, 17 Mar 2010 22:17:06 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Archive/Is-VT-d-necessary-for-TXT/m-p/876513#M8986</guid>
      <dc:creator>David_O_Intel1</dc:creator>
      <dc:date>2010-03-17T22:17:06Z</dc:date>
    </item>
    <item>
      <title>Is VT-d necessary for TXT</title>
      <link>https://community.intel.com/t5/Software-Archive/Is-VT-d-necessary-for-TXT/m-p/876514#M8987</link>
      <description>About your second posting above, I received this comment from another expert:&lt;BR /&gt;&lt;BR /&gt;"VT-d MMIO address differs from platform to platform. The base address should be documented in chipset datasheet."&lt;BR /&gt;&lt;BR /&gt;David Ott</description>
      <pubDate>Wed, 17 Mar 2010 22:20:42 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Archive/Is-VT-d-necessary-for-TXT/m-p/876514#M8987</guid>
      <dc:creator>David_O_Intel1</dc:creator>
      <dc:date>2010-03-17T22:20:42Z</dc:date>
    </item>
    <item>
      <title>Is VT-d necessary for TXT</title>
      <link>https://community.intel.com/t5/Software-Archive/Is-VT-d-necessary-for-TXT/m-p/876515#M8988</link>
      <description>Many thanks!&lt;BR /&gt;&lt;BR /&gt;Then it drives me to buy a new platform. I'd appreciate it if you can give me some advices on how to choose the processor and chipset.&lt;BR /&gt;&lt;BR /&gt;I am going to design a security framework based on TXT and MLE for real-time application. My basic requirement is:&lt;BR /&gt;1. TXT-capable. In other words, it can run tboot.&lt;BR /&gt;2. Some new features in VT-x: EPT, Preemption Timer&lt;BR /&gt;&lt;BR /&gt;My understand is that VT-x is a CPU feature but TXT is related to both CPU and chipset. i7-800, i5-700, i5-600 are said to support EPT and Preemption Timer according to specification. A desktop i5-600 dual-core CPU (their AC modules just released) is a possible choice. Other quad-core CPUs like i7-800, i5-700 are said to support TXT in specification but AC module is absent currently. The latest Xeon with 6 cores has similar situation.&lt;BR /&gt;&lt;BR /&gt;For the chipset, I compared Q57, P55, H57, H55 (&lt;A title="http://ark.intel.com/Compare.aspx?ids=42706,42690,42700,42703," href="http://ark.intel.com/Compare.aspx?ids=42706,42690,42700,42703,"&gt;http://ark.intel.com/Compare.aspx?ids=42706,42690,42700,42703,&lt;/A&gt;) and only Q57 is clearly labled with TXT and VT-d capability. Capabilities of P55 are undocumented but I really concern it since it is widely used by manufactures. &lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;So, is there any off-the-shelf desktop can satisfy my requirements? Or can I say all products with i5-600+Q57 (of course, with TPM and proper BIOS) are ok for me? Please correct me if I am wrong.&lt;BR /&gt;&lt;BR /&gt;Also, can I know is there any new revision of TXT being released soon (e.g. within 6 months)?&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;Thanks in advance!&lt;BR /&gt;</description>
      <pubDate>Fri, 19 Mar 2010 09:50:13 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Archive/Is-VT-d-necessary-for-TXT/m-p/876515#M8988</guid>
      <dc:creator>haojn</dc:creator>
      <dc:date>2010-03-19T09:50:13Z</dc:date>
    </item>
    <item>
      <title>Is VT-d necessary for TXT</title>
      <link>https://community.intel.com/t5/Software-Archive/Is-VT-d-necessary-for-TXT/m-p/876516#M8989</link>
      <description>&lt;P&gt;Here are some comments I received:&lt;BR /&gt;&lt;BR /&gt;The P55 supports Intel TXT (see &lt;A href="http://www.intel.com/Assets/PDF/datasheet/322169.pdf" target="_blank"&gt;http://www.intel.com/Assets/PDF/datasheet/322169.pdf&lt;/A&gt; p. 42).&lt;/P&gt;
&lt;P&gt;The SINIT ACM for the quad core TXT-capable processors will be made available shortly.&lt;/P&gt;
&lt;P&gt;No newrevision of TXT is planned, but there will be additional processors that will support it.&lt;BR /&gt;&lt;BR /&gt;David Ott&lt;/P&gt;</description>
      <pubDate>Tue, 23 Mar 2010 17:00:54 GMT</pubDate>
      <guid>https://community.intel.com/t5/Software-Archive/Is-VT-d-necessary-for-TXT/m-p/876516#M8989</guid>
      <dc:creator>David_O_Intel1</dc:creator>
      <dc:date>2010-03-23T17:00:54Z</dc:date>
    </item>
  </channel>
</rss>

