[PATCH v6 4/7] x86: Enable SSE in 64-bit mode

[Simon Glass]

This is needed to support Truetype fonts. In any case, the compiler
expects SSE to be available in 64-bit mode. Provide an option to enable
SSE so that hardware floating-point arithmetic works.

Signed-off-by: Simon Glass <sjg at chromium.org>
Reviewed-by: Tom Rini <trini at konsulko.com>
Suggested-by: Bin Meng <bmeng.cn at gmail.com>
---

(no changes since v4)

Changes in v4:
- Use a Kconfig option

 arch/x86/Kconfig          |  8 ++++++++
 arch/x86/config.mk        |  4 ++++
 arch/x86/cpu/x86_64/cpu.c | 12 ++++++++++++
 drivers/video/Kconfig     |  1 +
 4 files changed, 25 insertions(+)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 99e59d94c60..6b532d712ee 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -723,6 +723,14 @@ config ROM_TABLE_SIZE
 	hex
 	default 0x10000
 
+config X86_HARDFP
+	bool "Support hardware floating point"
+	help
+	  U-Boot generally does not make use of floating point. Where this is
+	  needed, it can be enabled using this option. This adjusts the
+	  start-up code for 64-bit mode and changes the compiler options for
+	  64-bit to enable SSE.
+
 config HAVE_ITSS
 	bool "Enable ITSS"
 	help
diff --git a/arch/x86/config.mk b/arch/x86/config.mk
index 26ec1af2f0b..2e3a7119e79 100644
--- a/arch/x86/config.mk
+++ b/arch/x86/config.mk
@@ -27,9 +27,13 @@ ifeq ($(IS_32BIT),y)
 PLATFORM_CPPFLAGS += -march=i386 -m32
 else
 PLATFORM_CPPFLAGS += $(if $(CONFIG_SPL_BUILD),,-fpic) -fno-common -march=core2 -m64
+
+ifndef CONFIG_X86_HARDFP
 PLATFORM_CPPFLAGS += -mno-mmx -mno-sse
 endif
 
+endif # IS_32BIT
+
 PLATFORM_RELFLAGS += -fdata-sections -ffunction-sections -fvisibility=hidden
 
 KBUILD_LDFLAGS += -Bsymbolic -Bsymbolic-functions
diff --git a/arch/x86/cpu/x86_64/cpu.c b/arch/x86/cpu/x86_64/cpu.c
index 2647bff891f..5ea746ecce4 100644
--- a/arch/x86/cpu/x86_64/cpu.c
+++ b/arch/x86/cpu/x86_64/cpu.c
@@ -10,6 +10,7 @@
 #include <init.h>
 #include <asm/cpu.h>
 #include <asm/global_data.h>
+#include <asm/processor-flags.h>
 
 DECLARE_GLOBAL_DATA_PTR;
 
@@ -39,11 +40,22 @@ int x86_mp_init(void)
 	return 0;
 }
 
+/* enable SSE features for hardware floating point */
+static void setup_sse_features(void)
+{
+	asm ("mov %%cr4, %%rax\n" \
+	"or  %0, %%rax\n" \
+	"mov %%rax, %%cr4\n" \
+	: : "i" (X86_CR4_OSFXSR | X86_CR4_OSXMMEXCPT) : "eax");
+}
+
 int x86_cpu_reinit_f(void)
 {
 	/* set the vendor to Intel so that native_calibrate_tsc() works */
 	gd->arch.x86_vendor = X86_VENDOR_INTEL;
 	gd->arch.has_mtrr = true;
+	if (IS_ENABLED(CONFIG_X86_HARDFP))
+		setup_sse_features();
 
 	return 0;
 }
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index 6f319ba0d54..39c82521be1 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -180,6 +180,7 @@ config CONSOLE_ROTATION
 
 config CONSOLE_TRUETYPE
 	bool "Support a console that uses TrueType fonts"
+	select X86_HARDFP if X86
 	help
 	  TrueTrype fonts can provide outline-drawing capability rather than
 	  needing to provide a bitmap for each font and size that is needed.
-- 
2.34.1