<html> <head> <base href="https://bugs.freedesktop.org/"> </head> <body> <div> <a class="bz_bug_link bz_status_NEW " title="NEW - [CI][KBL only] igt@* - dmesg-warn - *ERROR* CPU pipe [A|B] FIFO underrun" href="https://bugs.freedesktop.org/show_bug.cgi?id=105604#c8">Comment # 8</a> on <a class="bz_bug_link bz_status_NEW " title="NEW - [CI][KBL only] igt@* - dmesg-warn - *ERROR* CPU pipe [A|B] FIFO underrun" href="https://bugs.freedesktop.org/show_bug.cgi?id=105604">bug 105604</a> from <a class="email" href="mailto:elongbug@gmail.com" title="Mun, Gwan-gyeong <elongbug@gmail.com>"> Mun, Gwan-gyeong</a> <pre>After investigating the issue, I am suspecting a GEN9 hardware issue. I figured out enabling FBC on a plane which has a combination of a 180-degree rotation with having a Height that isn't divisible by 4 occasionally causes FIFO underrun. I tested the issue with igt-gpu-tools. ( multiplane-rotation-cropping-top subtest from kms_rotation_crc). I tested on Gen9 disaply HWs (both Skylake and Kabylake). when I added the patch code which make avoiding the issue case, I could always passed the test case. <a href="https://gitlab.freedesktop.org/elongbug/drm-tip/tree/gen9_fbc_underrun01">https://gitlab.freedesktop.org/elongbug/drm-tip/tree/gen9_fbc_underrun01</a> <a href="https://gitlab.freedesktop.org/elongbug/drm-tip/commit/a3969a959230153a53088a0abbf354c4c233af20">https://gitlab.freedesktop.org/elongbug/drm-tip/commit/a3969a959230153a53088a0abbf354c4c233af20</a> I asked a HW guy this issue to clarify. And for now I am waiting the reply.</pre> </div> <hr> You are receiving this mail because: <ul> <li>You are on the CC list for the bug.</li> <li>You are the QA Contact for the bug.</li> </ul> </body> </html>