[PATCH 6/6] x86/gsseg: use the LKGS instruction if available for load_gs_index()

[Xin Li]

From: "H. Peter Anvin (Intel)" <hpa@xxxxxxxxx>

The LKGS instruction atomically loads a segment descriptor into the
%gs descriptor registers, *except* that %gs.base is unchanged, and the
base is instead loaded into MSR_IA32_KERNEL_GS_BASE, which is exactly
what we want this function to do.

Signed-off-by: H. Peter Anvin (Intel) <hpa@xxxxxxxxx>
Signed-off-by: Xin Li <xin3.li@xxxxxxxxx>
---
 arch/x86/include/asm/gsseg.h | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/gsseg.h b/arch/x86/include/asm/gsseg.h
index 5e3b56a17098..b8a6a98d88b8 100644
--- a/arch/x86/include/asm/gsseg.h
+++ b/arch/x86/include/asm/gsseg.h
@@ -3,15 +3,41 @@
 #define _ASM_X86_GSSEG_H
 
 #include <linux/types.h>
+
+#include <asm/asm.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative.h>
 #include <asm/processor.h>
+#include <asm/nops.h>
 
 #ifdef CONFIG_X86_64
 
 extern asmlinkage void asm_load_gs_index(u16 selector);
 
+#define LKGS_DI	_ASM_BYTES(0xf2,0x0f,0x00,0xf7)
+
 static inline void native_load_gs_index(unsigned int selector)
 {
-	asm_load_gs_index(selector);
+	u16 sel = selector;
+
+	/*
+	 * Note: the fixup is used for the LKGS instruction, but
+	 * it needs to be attached to the primary instruction sequence
+	 * as it isn't something that gets patched.
+	 *
+	 * %rax is provided to the assembly routine as a scratch
+	 * register.
+	 */
+	alternative_io("1: call asm_load_gs_index\n"
+		       ".pushsection \".fixup\",\"ax\"\n"
+		       "2:	xorl %k[sel], %k[sel]\n"
+		       "	jmp 1b\n"
+		       ".popsection\n"
+		       _ASM_EXTABLE(1b, 2b),
+		       _ASM_BYTES(0x3e) LKGS_DI,
+		       X86_FEATURE_LKGS,
+		       ASM_OUTPUT2([sel] "+D" (sel), ASM_CALL_CONSTRAINT),
+		       ASM_NO_INPUT_CLOBBER(_ASM_AX));
 }
 
 #endif /* CONFIG_X86_64 */
-- 
2.34.1