regression in dcn linked to -msse2

Deucher, Alexander Alexander.Deucher at
Tue Jan 29 15:29:07 UTC 2019


From: amd-gfx <amd-gfx-bounces at> on behalf of StDenis, Tom <Tom.StDenis at>
Sent: Tuesday, January 29, 2019 8:44:03 AM
To: Wentland, Harry; amd-gfx mailing list
Cc: Deucher, Alexander
Subject: regression in dcn linked to -msse2

Testing with the new 5.0.0-rc1 amd-staging-drm-next branch results in
this commit causing the attached lockup on init with my Raven + Polaris

10117450735c7a7c0858095fb46a860e7037cb9a is the first bad commit
commit 10117450735c7a7c0858095fb46a860e7037cb9a
Author: ndesaulniers at <ndesaulniers at>
Date:   Thu Jan 24 16:52:59 2019 -0800

     drm/amd/display: add -msse2 to prevent Clang from emitting libcalls
to undefined SW FP routines

     arch/x86/Makefile disables SSE and SSE2 for the whole kernel.  The
     AMDGPU drivers modified in this patch re-enable SSE but not SSE2.  Turn
     on SSE2 to support emitting double precision floating point
     rather than calls to non-existent (usually available from gcc_s or
     compiler_rt) floating point helper routines.

     Cc: stable at # 4.19
     Reported-by: S, Shirish <Shirish.S at>
     Reported-by: Matthias Kaehlcke <mka at>
     Suggested-by: James Y Knight <jyknight at>
     Suggested-by: Nathan Chancellor <natechancellor at>
     Signed-off-by: Nick Desaulniers <ndesaulniers at>
     Tested-by: Guenter Roeck <linux at>
     Tested-by:  Matthias Kaehlcke <mka at>
     Tested-by: Nathan Chancellor <natechancellor at>
     Reviewed-by: Harry Wentland <harry.wentland at>
     Signed-off-by: Harry Wentland <harry.wentland at>
     Signed-off-by: Alex Deucher <alexander.deucher at>

:040000 040000 39f89ea177b8a69a3a2aa098aef8b1a7e58056b9
71edb262be0608ffae0996253f47492b2e714b5c M      drivers

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <>

More information about the amd-gfx mailing list