[PATCH v13 01/35] x86/cpufeatures,opcode,msr: Add the WRMSRNS instruction support

[Xin Li <xin3.li@xxxxxxxxx>]

WRMSRNS is an instruction that behaves exactly like WRMSR, with
the only difference being that it is not a serializing instruction
by default. Under certain conditions, WRMSRNS may replace WRMSR to
improve performance.

Add its CPU feature bit, opcode to the x86 opcode map, and an
always inline API __wrmsrns() to embed WRMSRNS into the code.

Tested-by: Shan Kang <shan.kang@xxxxxxxxx>
Signed-off-by: Xin Li <xin3.li@xxxxxxxxx>
---

Changes since v12:
* Merge the 3 WRMSRNS patches into one (Borislav Petkov).
* s/cpu/CPU/g (Borislav Petkov).
* Shorten the WRMSRNS description (Borislav Petkov).
---
 arch/x86/include/asm/cpufeatures.h       |  1 +
 arch/x86/include/asm/msr.h               | 18 ++++++++++++++++++
 arch/x86/lib/x86-opcode-map.txt          |  2 +-
 tools/arch/x86/include/asm/cpufeatures.h |  1 +
 tools/arch/x86/lib/x86-opcode-map.txt    |  2 +-
 5 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h 
b/arch/x86/include/asm/cpufeatures.h
index 149cc5d5c2ae..a903fc130e49 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -325,6 +325,7 @@
 #define X86_FEATURE_FSRS               (12*32+11) /* "" Fast short REP STOSB */
 #define X86_FEATURE_FSRC               (12*32+12) /* "" Fast short REP 
{CMPSB,SCASB} */
 #define X86_FEATURE_LKGS               (12*32+18) /* "" Load "kernel" 
(userspace) GS */
+#define X86_FEATURE_WRMSRNS            (12*32+19) /* "" Non-serializing WRMSR 
*/
 #define X86_FEATURE_AMX_FP16           (12*32+21) /* "" AMX fp16 Support */
 #define X86_FEATURE_AVX_IFMA            (12*32+23) /* "" Support for 
VPMADD52[H,L]UQ */
 #define X86_FEATURE_LAM                        (12*32+26) /* Linear Address 
Masking */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 65ec1965cd28..c284ff9ebe67 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -97,6 +97,19 @@ static __always_inline void __wrmsr(unsigned int msr, u32 
low, u32 high)
                     : : "c" (msr), "a"(low), "d" (high) : "memory");
 }
 
+/*
+ * WRMSRNS behaves exactly like WRMSR with the only difference being
+ * that it is not a serializing instruction by default.
+ */
+static __always_inline void __wrmsrns(u32 msr, u32 low, u32 high)
+{
+       /* Instruction opcode for WRMSRNS; supported in binutils >= 2.40. */
+       asm volatile("1: .byte 0x0f,0x01,0xc6\n"
+                    "2:\n"
+                    _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR)
+                    : : "c" (msr), "a"(low), "d" (high));
+}
+
 #define native_rdmsr(msr, val1, val2)                  \
 do {                                                   \
        u64 __val = __rdmsr((msr));                     \
@@ -297,6 +310,11 @@ do {                                                       
\
 
 #endif /* !CONFIG_PARAVIRT_XXL */
 
+static __always_inline void wrmsrns(u32 msr, u64 val)
+{
+       __wrmsrns(msr, val, val >> 32);
+}
+
 /*
  * 64-bit version of wrmsr_safe():
  */
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 5168ee0360b2..1efe1d9bf5ce 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -1051,7 +1051,7 @@ GrpTable: Grp6
 EndTable
 
 GrpTable: Grp7
-0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) 
| VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B)
+0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) 
| VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS 
(110),(11B)
 1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC 
(011),(11B) | ENCLS (111),(11B)
 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | 
XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B)
 3: LIDT Ms
diff --git a/tools/arch/x86/include/asm/cpufeatures.h 
b/tools/arch/x86/include/asm/cpufeatures.h
index 4af140cf5719..26a73ae18a86 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -322,6 +322,7 @@
 #define X86_FEATURE_FSRS               (12*32+11) /* "" Fast short REP STOSB */
 #define X86_FEATURE_FSRC               (12*32+12) /* "" Fast short REP 
{CMPSB,SCASB} */
 #define X86_FEATURE_LKGS               (12*32+18) /* "" Load "kernel" 
(userspace) GS */
+#define X86_FEATURE_WRMSRNS            (12*32+19) /* "" Non-serializing WRMSR 
*/
 #define X86_FEATURE_AMX_FP16           (12*32+21) /* "" AMX fp16 Support */
 #define X86_FEATURE_AVX_IFMA            (12*32+23) /* "" Support for 
VPMADD52[H,L]UQ */
 #define X86_FEATURE_LAM                        (12*32+26) /* Linear Address 
Masking */
diff --git a/tools/arch/x86/lib/x86-opcode-map.txt 
b/tools/arch/x86/lib/x86-opcode-map.txt
index 5168ee0360b2..1efe1d9bf5ce 100644
--- a/tools/arch/x86/lib/x86-opcode-map.txt
+++ b/tools/arch/x86/lib/x86-opcode-map.txt
@@ -1051,7 +1051,7 @@ GrpTable: Grp6
 EndTable
 
 GrpTable: Grp7
-0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) 
| VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B)
+0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) 
| VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS 
(110),(11B)
 1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC 
(011),(11B) | ENCLS (111),(11B)
 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | 
XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B)
 3: LIDT Ms
-- 
2.43.0