<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<p style="font-family:Arial;font-size:10pt;color:#008000;margin:15pt;" align="Left">
[Public]<br>
</p>
<br>
<div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
Reviewed-by: Alex Deucher <alexander.deucher@amd.com><br>
</div>
<div id="appendonsend"></div>
<hr style="display:inline-block;width:98%" tabindex="-1">
<div id="divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" style="font-size:11pt" color="#000000"><b>From:</b> amd-gfx <amd-gfx-bounces@lists.freedesktop.org> on behalf of Joseph Greathouse <Joseph.Greathouse@amd.com><br>
<b>Sent:</b> Thursday, August 4, 2022 12:01 PM<br>
<b>To:</b> amd-gfx@lists.freedesktop.org <amd-gfx@lists.freedesktop.org><br>
<b>Cc:</b> Russell, Kent <Kent.Russell@amd.com>; Greathouse, Joseph <Joseph.Greathouse@amd.com>; Koenig, Christian <Christian.Koenig@amd.com><br>
<b>Subject:</b> [PATCH] drm/amdgpu: Enable translate_further to extend UTCL2 reach</font>
<div> </div>
</div>
<div class="BodyFragment"><font size="2"><span style="font-size:11pt;">
<div class="PlainText">Enable translate_further on Arcturus and Aldebaran server chips<br>
in order to increase the UTCL2 reach from 8 GiB to 64 GiB,<br>
which is more in line with the amount of framebuffer DRAM in<br>
the devices.<br>
<br>
Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com><br>
---<br>
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 3 +++<br>
 1 file changed, 3 insertions(+)<br>
<br>
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c<br>
index 22761a3bb818..ab89d91975ab 100644<br>
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c<br>
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c<br>
@@ -1624,12 +1624,15 @@ static int gmc_v9_0_sw_init(void *handle)<br>
                         amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 47);<br>
                 else<br>
                         amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 48);<br>
+               if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2))<br>
+                       adev->gmc.translate_further = adev->vm_manager.num_level > 1;<br>
                 break;<br>
         case IP_VERSION(9, 4, 1):<br>
                 adev->num_vmhubs = 3;<br>
 <br>
                 /* Keep the vm size same with Vega20 */<br>
                 amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 48);<br>
+               adev->gmc.translate_further = adev->vm_manager.num_level > 1;<br>
                 break;<br>
         default:<br>
                 break;<br>
-- <br>
2.20.1<br>
<br>
</div>
</span></font></div>
</div>
</body>
</html>