<html>
  <head>
    <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
  </head>
  <body>
    <div class="moz-cite-prefix">Am 06.09.20 um 18:02 schrieb Jan
      Vesely:<br>
    </div>
    <blockquote type="cite"
cite="mid:CABE_ZV3Uk69RXv9RYj5d7cNXi5pX16Ve8qkkGPB5=OAX5b_6Rg@mail.gmail.com">
      <meta http-equiv="content-type" content="text/html; charset=UTF-8">
      <div dir="ltr">
        <div dir="ltr"><br>
        </div>
        <br>
        <div class="gmail_quote">
          <div dir="ltr" class="gmail_attr">On Sun, Sep 6, 2020 at 4:54
            AM Christian König <<a
              href="mailto:ckoenig.leichtzumerken@gmail.com"
              moz-do-not-send="true">ckoenig.leichtzumerken@gmail.com</a>>
            wrote:<br>
          </div>
          <blockquote class="gmail_quote" style="margin:0px 0px 0px
            0.8ex;border-left:1px solid
            rgb(204,204,204);padding-left:1ex">Am 03.08.19 um 02:09
            schrieb Andi Kleen:<br>
            > From: Andi Kleen <<a
              href="mailto:ak@linux.intel.com" target="_blank"
              moz-do-not-send="true">ak@linux.intel.com</a>><br>
            ><br>
            > I got tired of seeing a lot of radeon-crt kernel
            threads in ps on my<br>
            > workstation, one for each CPU and one for each display,
            which never use any CPU time.<br>
            > Surely a single kernel thread is enough to handle the
            display.<br>
            <br>
            NAK, radeon blocks inside the kernel thread and those need
            to run in <br>
            parallel or otherwise the hardware can hang.<br>
          </blockquote>
          <div><br>
            Shouldn't WQ_UNBOUND create a new worker thread whenever all
            current workers go to sleep/block (and the total number of
            worker threads is below 'max_active') ?<br>
          </div>
        </div>
      </div>
    </blockquote>
    <br>
    If that is guaranteed then this is indeed sufficient, but the
    sentence "Surely a single kernel thread is enough to handle the
    display." sounded like it creates only a single one.<br>
    <br>
    Christian.<br>
    <br>
    <blockquote type="cite"
cite="mid:CABE_ZV3Uk69RXv9RYj5d7cNXi5pX16Ve8qkkGPB5=OAX5b_6Rg@mail.gmail.com">
      <div dir="ltr">
        <div class="gmail_quote">
          <div><br>
          </div>
          <div>Jan</div>
          <blockquote class="gmail_quote" style="margin:0px 0px 0px
            0.8ex;border-left:1px solid
            rgb(204,204,204);padding-left:1ex">
            <br>
            Christian.<br>
            <br>
            ><br>
            > Signed-off-by: Andi Kleen <<a
              href="mailto:ak@linux.intel.com" target="_blank"
              moz-do-not-send="true">ak@linux.intel.com</a>><br>
            > ---<br>
            >   drivers/gpu/drm/radeon/radeon_display.c | 2 +-<br>
            >   1 file changed, 1 insertion(+), 1 deletion(-)<br>
            ><br>
            > diff --git a/drivers/gpu/drm/radeon/radeon_display.c
            b/drivers/gpu/drm/radeon/radeon_display.c<br>
            > index bd52f15e6330..fb0ca688f6fe 100644<br>
            > --- a/drivers/gpu/drm/radeon/radeon_display.c<br>
            > +++ b/drivers/gpu/drm/radeon/radeon_display.c<br>
            > @@ -682,7 +682,7 @@ static void radeon_crtc_init(struct
            drm_device *dev, int index)<br>
            >   <br>
            >     
             drm_mode_crtc_set_gamma_size(&radeon_crtc->base,
            256);<br>
            >       radeon_crtc->crtc_id = index;<br>
            > -     radeon_crtc->flip_queue =
            alloc_workqueue("radeon-crtc", WQ_HIGHPRI, 0);<br>
            > +     radeon_crtc->flip_queue =
            alloc_workqueue("radeon-crtc", WQ_HIGHPRI|WQ_UNBOUND, 0);<br>
            >       rdev->mode_info.crtcs[index] = radeon_crtc;<br>
            >   <br>
            >       if (rdev->family >= CHIP_BONAIRE) {<br>
            <br>
            _______________________________________________<br>
            amd-gfx mailing list<br>
            <a href="mailto:amd-gfx@lists.freedesktop.org"
              target="_blank" moz-do-not-send="true">amd-gfx@lists.freedesktop.org</a><br>
            <a
              href="https://lists.freedesktop.org/mailman/listinfo/amd-gfx"
              rel="noreferrer" target="_blank" moz-do-not-send="true">https://lists.freedesktop.org/mailman/listinfo/amd-gfx</a><br>
          </blockquote>
        </div>
      </div>
      <br>
      <fieldset class="mimeAttachmentHeader"></fieldset>
      <pre class="moz-quote-pre" wrap="">_______________________________________________
amd-gfx mailing list
<a class="moz-txt-link-abbreviated" href="mailto:amd-gfx@lists.freedesktop.org">amd-gfx@lists.freedesktop.org</a>
<a class="moz-txt-link-freetext" href="https://lists.freedesktop.org/mailman/listinfo/amd-gfx">https://lists.freedesktop.org/mailman/listinfo/amd-gfx</a>
</pre>
    </blockquote>
    <br>
  </body>
</html>