From e8a170ff9a3576730e43c0dbdd27b7cd3dc56848 Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Wed, 16 Oct 2019 16:02:09 -0700
Subject: drm/amdgpu: enable -msse2 for GCC 7.1+ users
Git-commit: e8a170ff9a3576730e43c0dbdd27b7cd3dc56848
Patch-mainline: v5.4-rc6
References: bsc#1152472

A final attempt at enabling sse2 for GCC users.

Orininally attempted in:
commit 10117450735c ("drm/amd/display: add -msse2 to prevent Clang from emitting libcalls to undefined SW FP routines")

Reverted due to "reported instability" in:
commit 193392ed9f69 ("Revert "drm/amd/display: add -msse2 to prevent Clang from emitting libcalls to undefined SW FP routines"")

Re-added just for Clang in:
commit 0f0727d971f6 ("drm/amd/display: readd -msse2 to prevent Clang from emitting libcalls to undefined SW FP routines")

The original report didn't have enough information to know if the GPF
was due to misalignment, but I suspect that it was. (The missing
information was the disassembly of the function at the bottom of the
trace, to see if the instruction pointer pointed to an instruction with
16B alignment memory operand requirements.  The stack trace does show
the stack was only 8B but not 16B aligned though, which makes this a
strong possibility).

Now that the stack misalignment issue has been fixed for users of GCC
7.1+, reattempt adding -msse2. This matches Clang.

It will likely never be safe to enable this for pre-GCC 7.1 AND use a
16B aligned stack in these translation units.

This is only a functional change for GCC 7.1+ users, and should be boot
tested.

Link: https://bugs.freedesktop.org/show_bug.cgi?id=109487
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
---
 drivers/gpu/drm/amd/display/dc/calcs/Makefile |    2 ++
 drivers/gpu/drm/amd/display/dc/dcn20/Makefile |    2 ++
 drivers/gpu/drm/amd/display/dc/dcn21/Makefile |    4 +---
 drivers/gpu/drm/amd/display/dc/dml/Makefile   |    2 ++
 drivers/gpu/drm/amd/display/dc/dsc/Makefile   |    2 ++
 5 files changed, 9 insertions(+), 3 deletions(-)

--- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
@@ -37,6 +37,8 @@ ifdef IS_OLD_GCC
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
 # (8B stack alignment).
 calcs_ccflags += -mpreferred-stack-boundary=4
+else
+calcs_ccflags += -msse2
 endif
 
 CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calcs.o := $(calcs_ccflags)
--- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
@@ -23,6 +23,8 @@ ifdef IS_OLD_GCC
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
 # (8B stack alignment).
 CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -mpreferred-stack-boundary=4
+else
+CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -msse2
 endif
 
 AMD_DAL_DCN20 = $(addprefix $(AMDDALPATH)/dc/dcn20/,$(DCN20))
--- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
@@ -16,9 +16,7 @@ ifdef IS_OLD_GCC
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
 # (8B stack alignment).
 CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -mpreferred-stack-boundary=4
-endif
-
-ifdef CONFIG_CC_IS_CLANG
+else
 CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2
 endif
 
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -37,6 +37,8 @@ ifdef IS_OLD_GCC
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
 # (8B stack alignment).
 dml_ccflags += -mpreferred-stack-boundary=4
+else
+dml_ccflags += -msse2
 endif
 
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
--- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
@@ -14,6 +14,8 @@ ifdef IS_OLD_GCC
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
 # (8B stack alignment).
 dsc_ccflags += -mpreferred-stack-boundary=4
+else
+dsc_ccflags += -msse2
 endif
 
 CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc.o := $(dsc_ccflags)