Re: Fwd: SMI tuning

Paolo Mantegazza <[email protected]> Tue, 27 Feb 2018 14:05:26 +0100
Newsgroups gmane.linux.real-time.rtai
Message-ID <[email protected]>
This is a multi-part message in MIME format.
--===============1680149029702314473==
Content-Type: multipart/alternative;
 boundary="------------92879CD63613148C06361615"
Content-Language: en-US

This is a multi-part message in MIME format.
--------------92879CD63613148C06361615
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Transfer-Encoding: quoted-printable

For what I know if you have SMI_LOCK enabled, then you should see if it=20
can be disabled at the BIOS level.
Nonetheless, somebody told to me that there are BIOS allowing it while=20
others do not (most?).

Paolo

On 02/27/2018 01:30 PM, William Montgomery wrote:
> Forgot to CC the list...
> ---------- Forwarded message ----------
> From: *William Montgomery*
> Date: Tue, Feb 27, 2018 at 7:27 AM
> Subject: Re: [Rtai] SMI tuning
> To: Paolo Mantegazza
>
>
> I have used the SMISPV program and see the same results - I am unable=20
> to clear any SMI bits.=C2=A0 It appears as if the SMI control enable bi=
ts=20
> are somehow locked.=C2=A0 It could also be that the UEFI firmware detec=
ts=20
> that I have changed the bits and it then sets them back to the default=20
> value.
>
> I have looked at the related README files trying to find any clues.=C2=A0=
=20
> Now I am reading the Intel datasheet for the chipset and suspect that=20
> the SMI_LOCK bit may be set. I was hoping that someone on this list=20
> may have already run into this problem.
>
> Regards,
> Wm
>
> On Tue, Feb 27, 2018 at 6:53 AM, Paolo Mantegazza=20
> <[email protected] <mailto:[email protected]>> wrote:
>
>     The interacting interface, SMISPV, might be of further help. Have
>     a look also at the related READMEs.
>
>     Paolo
>
>
>     On 02/26/2018 06:33 PM, William Montgomery wrote:
>>     I am moving to a new hardware platform due to obsolescence issues
>>     and testing the latency with the kern/latency app shows some
>>     mostly 10-22usec ovl max but some occasional large spikes
>>     (2msec). In the past I have used rtai_smi module to fix this type
>>     problem and now I have added the new Intel SMI chipset but and
>>     unable to mask the SMI bits.=C2=A0 This motherboard contains:
>>
>>     Intel(R) Xeon(R) W-2133 CPU @ 3.60GHz -- Skylake
>>     Intel C422 chipset
>>
>>     When I load the rtai_smi module, I see:
>>
>>     [ 2386.756382] RTAI: Intel SMI chipset found (8086:a2d3),
>>     enabling SMI workaround.
>>     [ 2386.756409] Bits enabled: GBL_SMI, EOS (special), MCSMI, TCO,
>>     PERIODIC, LEGACY_USB2, INTEL_USB2.
>>     [ 2386.756411] Original SMI configuration value 0xffffff03 has
>>     been cleared with mask =3D 0x1 (saved mask setting 0x1), new value=
 0
>>     xffffff03.
>>     [ 2386.756413] Bits enabled: GBL_SMI, EOS (special), MCSMI, TCO,
>>     PERIODIC, LEGACY_USB2, INTEL_USB2.
>>
>>     Does anyone have experience with these new chipsets?
>>
>>     Regards,
>>     Wm
>>
>>
>>     _______________________________________________
>>     Rtai mailing list
>>     [email protected] <mailto:[email protected]>
>>     https://mail.rtai.org/cgi-bin/mailman/listinfo/rtai
>>     <https://mail.rtai.org/cgi-bin/mailman/listinfo/rtai>
>
>
>
>     _______________________________________________
>     Rtai mailing list
>     [email protected] <mailto:[email protected]>
>     https://mail.rtai.org/cgi-bin/mailman/listinfo/rtai
>     <https://mail.rtai.org/cgi-bin/mailman/listinfo/rtai>
>
>
>
>
>
> _______________________________________________
> Rtai mailing list
> [email protected]
> https://mail.rtai.org/cgi-bin/mailman/listinfo/rtai



--------------92879CD63613148C06361615
Content-Type: text/html; charset=utf-8
Content-Transfer-Encoding: quoted-printable

<html>
  <head>
    <meta http-equiv=3D"Content-Type" content=3D"text/html; charset=3Dutf=
-8">
  </head>
  <body text=3D"#000000" bgcolor=3D"#FFFFFF">
    <div class=3D"moz-cite-prefix">For what I know if you have SMI_LOCK
      enabled, then you should see if it can be disabled at the BIOS
      level. <br>
      Nonetheless, somebody told to me that there are BIOS allowing it
      while others do not (most?).<br>
      <br>
      Paolo<br>
      <br>
      On 02/27/2018 01:30 PM, William Montgomery wrote:<br>
    </div>
    <blockquote type=3D"cite"
cite=3D"mid:[email protected]=
ail.com">
      <meta http-equiv=3D"Content-Type" content=3D"text/html; charset=3Du=
tf-8">
      <div dir=3D"ltr">Forgot to CC the list...<br>
        <div class=3D"gmail_quote">---------- Forwarded message ---------=
-<br>
          From: <b class=3D"gmail_sendername">William Montgomery</b><br>
          Date: Tue, Feb 27, 2018 at 7:27 AM<br>
          Subject: Re: [Rtai] SMI tuning<br>
          To: Paolo Mantegazza<br>
          <br>
          <br>
          <div dir=3D"ltr">I have used the SMISPV program and see the sam=
e
            results - I am unable to clear any SMI bits.=C2=A0 It appears=
 as
            if the SMI control enable bits are somehow locked.=C2=A0 It c=
ould
            also be that the UEFI firmware detects that I have changed
            the bits and it then sets them back to the default value.
            <div><br>
            </div>
            <div>I have looked at the related README files trying to
              find any clues.=C2=A0 Now I am reading the Intel datasheet =
for
              the chipset and suspect that the SMI_LOCK bit may be set.=C2=
=A0
              I was hoping that someone on this list may have already
              run into this problem.</div>
            <div><br>
            </div>
            <div>Regards,</div>
            <div>Wm</div>
          </div>
          <div class=3D"HOEnZb">
            <div class=3D"h5">
              <div class=3D"gmail_extra"><br>
                <div class=3D"gmail_quote">On Tue, Feb 27, 2018 at 6:53
                  AM, Paolo Mantegazza <span dir=3D"ltr">&lt;<a
                      href=3D"mailto:[email protected]"
                      target=3D"_blank" moz-do-not-send=3D"true">paolo.ma=
[email protected]</a>&gt;</span>
                  wrote:<br>
                  <blockquote class=3D"gmail_quote" style=3D"margin:0 0 0
                    .8ex;border-left:1px #ccc solid;padding-left:1ex">
                    <div text=3D"#000000" bgcolor=3D"#FFFFFF">
                      <div
                        class=3D"m_-4386237998365796775m_-480417798545211=
4047moz-cite-prefix">The
                        interacting interface, SMISPV, might be of
                        further help. Have a look also at the related
                        READMEs.<br>
                        <br>
                        Paolo
                        <div>
                          <div class=3D"m_-4386237998365796775h5"><br>
                            <br>
                            On 02/26/2018 06:33 PM, William Montgomery
                            wrote:<br>
                          </div>
                        </div>
                      </div>
                      <blockquote type=3D"cite">
                        <div>
                          <div class=3D"m_-4386237998365796775h5">
                            <div dir=3D"ltr">I am moving to a new hardwar=
e
                              platform due to obsolescence issues and
                              testing the latency with the kern/latency
                              app shows some mostly 10-22usec ovl max
                              but some occasional large spikes (2msec).=C2=
=A0
                              In the past I have used rtai_smi module to
                              fix this type problem and now I have added
                              the new Intel SMI chipset but and unable
                              to mask the SMI bits.=C2=A0 This motherboar=
d
                              contains:
                              <div><br>
                              </div>
                              <div>Intel(R) Xeon(R) W-2133 CPU @ 3.60GHz
                                -- Skylake<br>
                              </div>
                              <div>Intel C422 chipset</div>
                              <div><br>
                              </div>
                              <div>When I load the rtai_smi module, I
                                see:</div>
                              <div><br>
                              </div>
                              <div>
                                <div>[ 2386.756382] RTAI: Intel SMI
                                  chipset found (8086:a2d3), enabling
                                  SMI workaround.</div>
                                <div>[ 2386.756409] Bits enabled:
                                  GBL_SMI, EOS (special), MCSMI, TCO,
                                  PERIODIC, LEGACY_USB2, INTEL_USB2.</div=
>
                                <div>[ 2386.756411] Original SMI
                                  configuration value 0xffffff03 has
                                  been cleared with mask =3D 0x1 (saved
                                  mask setting 0x1), new value 0</div>
                                <div>xffffff03.</div>
                                <div>[ 2386.756413] Bits enabled:
                                  GBL_SMI, EOS (special), MCSMI, TCO,
                                  PERIODIC, LEGACY_USB2, INTEL_USB2.</div=
>
                              </div>
                              <div><br>
                              </div>
                              <div>Does anyone have experience with
                                these new chipsets?</div>
                              <div><br>
                              </div>
                              <div>Regards,</div>
                              <div>Wm</div>
                            </div>
                            <br>
                            <fieldset
                              class=3D"m_-4386237998365796775m_-480417798=
5452114047mimeAttachmentHeader"></fieldset>
                            <br>
                          </div>
                        </div>
                        <pre>______________________________<wbr>_________=
________
Rtai mailing list
<a class=3D"m_-4386237998365796775m_-4804177985452114047moz-txt-link-abbr=
eviated" href=3D"mailto:[email protected]" target=3D"_blank" moz-do-not-send=3D=
"true">[email protected]</a>
<a class=3D"m_-4386237998365796775m_-4804177985452114047moz-txt-link-free=
text" href=3D"https://mail.rtai.org/cgi-bin/mailman/listinfo/rtai" target=
=3D"_blank" moz-do-not-send=3D"true">https://mail.rtai.org/cgi-bin/<wbr>m=
ailman/listinfo/rtai</a></pre>
                      </blockquote>
                      <p><br>
                      </p>
                    </div>
                    <br>
                    ______________________________<wbr>_________________<=
br>
                    Rtai mailing list<br>
                    <a href=3D"mailto:[email protected]" target=3D"_blank"
                      moz-do-not-send=3D"true">[email protected]</a><br>
                    <a
                      href=3D"https://mail.rtai.org/cgi-bin/mailman/listi=
nfo/rtai"
                      rel=3D"noreferrer" target=3D"_blank"
                      moz-do-not-send=3D"true">https://mail.rtai.org/cgi-=
bin/<wbr>mailman/listinfo/rtai</a><br>
                  </blockquote>
                </div>
                <br>
              </div>
            </div>
          </div>
        </div>
        <br>
      </div>
      <br>
      <fieldset class=3D"mimeAttachmentHeader"></fieldset>
      <br>
      <pre wrap=3D"">_______________________________________________
Rtai mailing list
<a class=3D"moz-txt-link-abbreviated" href=3D"mailto:[email protected]">Rtai@=
rtai.org</a>
<a class=3D"moz-txt-link-freetext" href=3D"https://mail.rtai.org/cgi-bin/=
mailman/listinfo/rtai">https://mail.rtai.org/cgi-bin/mailman/listinfo/rta=
i</a></pre>
    </blockquote>
    <p><br>
    </p>
  </body>
</html>

--------------92879CD63613148C06361615--

--===============1680149029702314473==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
Rtai mailing list
[email protected]
https://mail.rtai.org/cgi-bin/mailman/listinfo/rtai
--===============1680149029702314473==--