Am 27.10.22 um 02:25 schrieb Ao Zhong:
After moving all FPU code to the DML folder, we can enable DCN support
for the ARM64 platform. Remove the -mgeneral-regs-only CFLAG from the
code in the DML folder that needs to use hardware FPU, and add a control
mechanism for ARM Neon.
It's nice to see that the FPU isolation work is so fruitful :)
Signed-off-by: Ao Zhong <hacc1225@xxxxxxxxx>
Acked-by: Christian König <christian.koenig@xxxxxxx>
---
drivers/gpu/drm/amd/display/Kconfig | 2 +-
.../gpu/drm/amd/display/amdgpu_dm/dc_fpu.c | 6 ++
drivers/gpu/drm/amd/display/dc/dml/Makefile | 64 ++++++++++++-------
3 files changed, 49 insertions(+), 23 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index 0142affcdaa3..a7f1c4e51719 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -6,7 +6,7 @@ config DRM_AMD_DC
bool "AMD DC - Enable new display engine"
default y
select SND_HDA_COMPONENT if SND_HDA_CORE
- select DRM_AMD_DC_DCN if (X86 || PPC64)
+ select DRM_AMD_DC_DCN if (X86 || PPC64 || (ARM64 && KERNEL_MODE_NEON))
help
Choose this option if you want to use the new display engine
support for AMDGPU. This adds required support for Vega and
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
index ab0c6d191038..1743ca0a3641 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
@@ -31,6 +31,8 @@
#elif defined(CONFIG_PPC64)
#include <asm/switch_to.h>
#include <asm/cputable.h>
+#elif defined(CONFIG_ARM64)
+#include <asm/neon.h>
#endif
/**
@@ -99,6 +101,8 @@ void dc_fpu_begin(const char *function_name, const int line)
preempt_disable();
enable_kernel_fp();
}
+#elif defined(CONFIG_ARM64)
+ kernel_neon_begin();
#endif
}
@@ -136,6 +140,8 @@ void dc_fpu_end(const char *function_name, const int line)
disable_kernel_fp();
preempt_enable();
}
+#elif defined(CONFIG_ARM64)
+ kernel_neon_end();
#endif
}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index d0c6cf61c676..3cdd109189e0 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -33,6 +33,12 @@ ifdef CONFIG_PPC64
dml_ccflags := -mhard-float -maltivec
endif
+ifdef CONFIG_ARM64
+ifdef CONFIG_DRM_AMD_DC_DCN
+dml_rcflags_arm64 := -mgeneral-regs-only
+endif
+endif
+
ifdef CONFIG_CC_IS_GCC
ifeq ($(call cc-ifversion, -lt, 0701, y), y)
IS_OLD_GCC = 1
@@ -87,32 +93,46 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dsc/rc_calc_fpu.o := $(dml_ccflags)
CFLAGS_$(AMDDALPATH)/dc/dml/calcs/dcn_calcs.o := $(dml_ccflags)
CFLAGS_$(AMDDALPATH)/dc/dml/calcs/dcn_calc_auto.o := $(dml_ccflags)
CFLAGS_$(AMDDALPATH)/dc/dml/calcs/dcn_calc_math.o := $(dml_ccflags) -Wno-tautological-compare
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_rcflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_rcflags) $(dml_rcflags_arm64)
CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn2x/dcn2x.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn32/display_mode_vba_32.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn32/display_rq_dlg_calc_32.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn32/display_mode_vba_util_32.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn301/dcn301_fpu.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dsc/rc_calc_fpu.o := $(dml_rcflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn32/display_mode_vba_32.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn32/display_rq_dlg_calc_32.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn32/display_mode_vba_util_32.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn301/dcn301_fpu.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dsc/rc_calc_fpu.o := $(dml_rcflags) $(dml_rcflags_arm64)
+ifdef CONFIG_ARM64
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn314/display_mode_vba_314.o := $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn314/display_rq_dlg_calc_314.o := $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn314/dcn314_fpu.o := $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn30/dcn30_fpu.o := $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn32/dcn32_fpu.o := $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn321/dcn321_fpu.o := $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn31/dcn31_fpu.o := $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn302/dcn302_fpu.o := $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn303/dcn303_fpu.o := $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/calcs/dcn_calc_math.o := $(dml_rcflags_arm64)
+endif
endif
CFLAGS_$(AMDDALPATH)/dc/dml/dml1_display_rq_dlg_calc.o := $(dml_ccflags)
CFLAGS_$(AMDDALPATH)/dc/dml/display_rq_dlg_helpers.o := $(dml_ccflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dml1_display_rq_dlg_calc.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/display_rq_dlg_helpers.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/calcs/dcn_calcs.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/calcs/dcn_calc_auto.o := $(dml_rcflags)
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/calcs/dcn_calc_math.o := $(dml_rcflags)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dml1_display_rq_dlg_calc.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/display_rq_dlg_helpers.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/calcs/dcn_calcs.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/calcs/dcn_calc_auto.o := $(dml_rcflags) $(dml_rcflags_arm64)
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/calcs/dcn_calc_math.o := $(dml_rcflags) $(dml_rcflags_arm64)
DML = calcs/dce_calcs.o calcs/custom_float.o calcs/bw_fixed.o