From c868868f6b6a5272350781f9a19b3a5ba1c00b02 Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Wed, 16 Oct 2019 16:02:07 -0700
Subject: drm/amdgpu: fix stack alignment ABI mismatch for Clang
Git-commit: c868868f6b6a5272350781f9a19b3a5ba1c00b02
Patch-mainline: v5.4-rc6
References: bsc#1152472

The x86 kernel is compiled with an 8B stack alignment via
`-mpreferred-stack-boundary=3` for GCC since 3.6-rc1 via
commit d9b0cde91c60 ("x86-64, gcc: Use -mpreferred-stack-boundary=3 if supported")
or `-mstack-alignment=8` for Clang. Parts of the AMDGPU driver are
compiled with 16B stack alignment.

Generally, the stack alignment is part of the ABI. Linking together two
different translation units with differing stack alignment is dangerous,
particularly when the translation unit with the smaller stack alignment
makes calls into the translation unit with the larger stack alignment.
While 8B aligned stacks are sometimes also 16B aligned, they are not
always.

Multiple users have reported General Protection Faults (GPF) when using
the AMDGPU driver compiled with Clang. Clang is placing objects in stack
slots assuming the stack is 16B aligned, and selecting instructions that
require 16B aligned memory operands.

At runtime, syscall handlers with 8B aligned stack call into code that
assumes 16B stack alignment.  When the stack is a multiple of 8B but not
16B, these instructions result in a GPF.

Remove the code that added compatibility between the differing compiler
flags, as it will result in runtime GPFs when built with Clang. Cleanups
for GCC will be sent in later patches in the series.

Link: https://github.com/ClangBuiltLinux/linux/issues/735
Debugged-by: Yuxuan Shui <yshuiv7@gmail.com>
Reported-by: Shirish S <shirish.s@amd.com>
Reported-by: Yuxuan Shui <yshuiv7@gmail.com>
Suggested-by: Andrew Cooper <andrew.cooper3@citrix.com>
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 |   10 ++++------
 drivers/gpu/drm/amd/display/dc/dcn20/Makefile |   10 ++++------
 drivers/gpu/drm/amd/display/dc/dcn21/Makefile |   10 ++++------
 drivers/gpu/drm/amd/display/dc/dml/Makefile   |   10 ++++------
 drivers/gpu/drm/amd/display/dc/dsc/Makefile   |   10 ++++------
 5 files changed, 20 insertions(+), 30 deletions(-)

--- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
@@ -24,13 +24,11 @@
 # It calculates Bandwidth and Watermarks values for HW programming
 #
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+calcs_ccflags := -mhard-float -msse
 
-calcs_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+calcs_ccflags += -mpreferred-stack-boundary=4
+endif
 
 CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calcs.o := $(calcs_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calc_auto.o := $(calcs_ccflags)
--- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
@@ -10,13 +10,11 @@ ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 DCN20 += dcn20_dsc.o
 endif
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse
 
-CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -mpreferred-stack-boundary=4
+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
@@ -3,13 +3,11 @@
 
 DCN21 = dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse
 
-CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -mpreferred-stack-boundary=4
+endif
 
 ifdef CONFIG_CC_IS_CLANG
 CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -24,13 +24,11 @@
 # It provides the general basic services required by other DAL
 # subcomponents.
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+dml_ccflags := -mhard-float -msse
 
-dml_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+dml_ccflags += -mpreferred-stack-boundary=4
+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
@@ -1,13 +1,11 @@
 #
 # Makefile for the 'dsc' sub-component of DAL.
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+dsc_ccflags := -mhard-float -msse
 
-dsc_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+dsc_ccflags += -mpreferred-stack-boundary=4
+endif
 
 CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc.o := $(dsc_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc_dpi.o := $(dsc_ccflags)