<html> <head> <meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1"> <style type="text/css" style="display:none;"></style> </head> <body dir="ltr"> <div id="divtagdefaultwrapper" style="font-size:12pt;color:#000000;background-color:#FFFFFF;font-family:Calibri,Arial,Helvetica,sans-serif;"> <p><br> </p> Disregard that I wasn't printing out the bo_offset but the FW offset.<br> <br> Tom<br> <br> <div style="color: rgb(0, 0, 0);"> <hr tabindex="-1" style="display:inline-block; width:98%"> <div id="divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" color="#000000" style="font-size:11pt"><b>From:</b> StDenis, Tom<br> <b>Sent:</b> Friday, July 15, 2016 13:08<br> <b>To:</b> amd-gfx@lists.freedesktop.org<br> <b>Cc:</b> Deucher, Alexander<br> <b>Subject:</b> Re: [PATCH] drm/amdgpu: disable GFX PG on CZ/BR/ST</font> <div> </div> </div> <div> <div id="divtagdefaultwrapper" style="font-size:12pt; color:#000000; background-color:#FFFFFF; font-family:Calibri,Arial,Helvetica,sans-serif"> <p>I threw a printk in there and got</p> <p><br> </p> <p></p> <div>[ 3415.512743] ME 0, off=2048, size=96</div> <div>[ 3415.512747] ME 1, off=4096, size=96 <--- PFP</div> <div>[ 3415.512748] ME 2, off=4096, size=96 <--- ME</div> <div>[ 3415.512749] ME 3, off=65536, size=96 <--- MEC</div> <div>[ 3415.512751] ME 4, off=65536, size=96 <--- MEC2</div> <div><br> </div> <p></p> <p>MEC/MEC2 having the same offset and pfp/me having the same seems kinda suspicious no?</p> <p><br> </p> <p>It means they're overwriting each other.</p> <p><br> </p> <p>Tom</p> <br> <br> <div style="color:rgb(0,0,0)"> <hr tabindex="-1" style="display:inline-block; width:98%"> <div id="divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" color="#000000" style="font-size:11pt"><b>From:</b> amd-gfx <amd-gfx-bounces@lists.freedesktop.org> on behalf of StDenis, Tom <Tom.StDenis@amd.com><br> <b>Sent:</b> Friday, July 15, 2016 12:59<br> <b>To:</b> amd-gfx@lists.freedesktop.org<br> <b>Cc:</b> Deucher, Alexander<br> <b>Subject:</b> Re: [PATCH] drm/amdgpu: disable GFX PG on CZ/BR/ST</font> <div> </div> </div> <div> <div id="divtagdefaultwrapper" style="font-size:12pt; color:#000000; background-color:#FFFFFF; font-family:Calibri,Arial,Helvetica,sans-serif"> <p>Do we know for a fact the jump tables are being initialized properly? They're only used on CZ/ST with PG turned on so it's entirely possible that code is buggy.</p> <p><br> </p> <p>I don't like the aliasing the structs in amdgpu_ucode.h to random binary data specially since they have no packed pragma's attached. We should either deserialize the firmware properly (implicitly load the struct members) or add a pragma.</p> <p><br> </p> <p>Tom</p> <br> <br> <div style="color:rgb(0,0,0)"> <hr tabindex="-1" style="display:inline-block; width:98%"> <div id="divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" color="#000000" style="font-size:11pt"><b>From:</b> amd-gfx <amd-gfx-bounces@lists.freedesktop.org> on behalf of StDenis, Tom <Tom.StDenis@amd.com><br> <b>Sent:</b> Friday, July 15, 2016 12:25<br> <b>To:</b> amd-gfx@lists.freedesktop.org<br> <b>Cc:</b> Deucher, Alexander<br> <b>Subject:</b> Re: [PATCH] drm/amdgpu: disable GFX PG on CZ/BR/ST</font> <div> </div> </div> <div> <div id="divtagdefaultwrapper" style="font-size:12pt; color:#000000; background-color:#FFFFFF; font-family:Calibri,Arial,Helvetica,sans-serif"> <p>Reviewed-by: Tom St Denis <tom.stdenis@amd.com></p> <p><br> </p> <p><br> </p> <br> <br> <div style="color:rgb(0,0,0)"> <div> <hr tabindex="-1" style="display:inline-block; width:98%"> <div id="x_divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" color="#000000" style="font-size:11pt"><b>From:</b> amd-gfx <amd-gfx-bounces@lists.freedesktop.org> on behalf of Alex Deucher <alexdeucher@gmail.com><br> <b>Sent:</b> Friday, July 15, 2016 12:08<br> <b>To:</b> amd-gfx@lists.freedesktop.org<br> <b>Cc:</b> Deucher, Alexander<br> <b>Subject:</b> [PATCH] drm/amdgpu: disable GFX PG on CZ/BR/ST</font> <div> </div> </div> </div> <font size="2"><span style="font-size:10pt"> <div class="PlainText">Still some stability issues under certain workloads.<br> <br> Signed-off-by: Alex Deucher <alexander.deucher@amd.com><br> ---<br> drivers/gpu/drm/amd/amdgpu/vi.c | 14 --------------<br> 1 file changed, 14 deletions(-)<br> <br> diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c<br> index cda7def..03a31c5 100644<br> --- a/drivers/gpu/drm/amd/amdgpu/vi.c<br> +++ b/drivers/gpu/drm/amd/amdgpu/vi.c<br> @@ -1249,15 +1249,7 @@ static int vi_common_early_init(void *handle)<br> AMD_CG_SUPPORT_HDP_LS |<br> AMD_CG_SUPPORT_SDMA_MGCG |<br> AMD_CG_SUPPORT_SDMA_LS;<br> - /* rev0 hardware doesn't support PG */<br> adev->pg_flags = 0;<br> - if (adev->rev_id != 0x00)<br> - adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |<br> - AMD_PG_SUPPORT_GFX_SMG |<br> - AMD_PG_SUPPORT_GFX_DMG |<br> - AMD_PG_SUPPORT_CP |<br> - AMD_PG_SUPPORT_RLC_SMU_HS |<br> - AMD_PG_SUPPORT_GFX_PIPELINE;<br> adev->external_rev_id = adev->rev_id + 0x1;<br> break;<br> case CHIP_STONEY:<br> @@ -1276,12 +1268,6 @@ static int vi_common_early_init(void *handle)<br> AMD_CG_SUPPORT_HDP_LS |<br> AMD_CG_SUPPORT_SDMA_MGCG |<br> AMD_CG_SUPPORT_SDMA_LS;<br> - adev->pg_flags = AMD_PG_SUPPORT_GFX_PG |<br> - AMD_PG_SUPPORT_GFX_SMG |<br> - AMD_PG_SUPPORT_GFX_DMG |<br> - AMD_PG_SUPPORT_GFX_PIPELINE |<br> - AMD_PG_SUPPORT_CP |<br> - AMD_PG_SUPPORT_RLC_SMU_HS;<br> adev->external_rev_id = adev->rev_id + 0x1;<br> break;<br> default:<br> -- <br> 2.5.5<br> <br> _______________________________________________<br> amd-gfx mailing list<br> amd-gfx@lists.freedesktop.org<br> <a href="https://lists.freedesktop.org/mailman/listinfo/amd-gfx" id="LPlnk768356">https://lists.freedesktop.org/mailman/listinfo/amd-gfx</a><br> </div> </span></font></div> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div> </body> </html>