x86/msr: Switch between WRMSRNS and WRMSR with the alternatives mechanism

Per the discussion about FRED MSR writes with WRMSRNS instruction [1],
use the alternatives mechanism to choose WRMSRNS when it's available,
otherwise fallback to WRMSR.

Remove the dependency on X86_FEATURE_WRMSRNS as WRMSRNS is no longer
dependent on FRED.

[1] https://lore.kernel.org/lkml/15f56e6a-6edd-43d0-8e83-bb6430096514@citrix.com/

Use DS prefix to pad WRMSR instead of a NOP. The prefix is ignored. At
least that's the current information from the hardware folks.

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Xin Li (Intel) <xin@zytor.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20240822073906.2176342-3-xin@zytor.com

3 files changed, 11 insertions, 16 deletions

diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index d642037f9ed5..001853541f1e 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -99,19 +99,6 @@ 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));			\
@@ -312,9 +299,19 @@ do {							\
 
 #endif	/* !CONFIG_PARAVIRT_XXL */
 
+/* Instruction opcode for WRMSRNS supported in binutils >= 2.40 */
+#define WRMSRNS _ASM_BYTES(0x0f,0x01,0xc6)
+
+/* Non-serializing WRMSR, when available.  Falls back to a serializing WRMSR. */
 static __always_inline void wrmsrns(u32 msr, u64 val)
 {
-	__wrmsrns(msr, val, val >> 32);
+	/*
+	 * WRMSR is 2 bytes.  WRMSRNS is 3 bytes.  Pad WRMSR with a redundant
+	 * DS prefix to avoid a trailing NOP.
+	 */
+	asm volatile("1: " ALTERNATIVE("ds wrmsr", WRMSRNS, X86_FEATURE_WRMSRNS)
+		     "2: " _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR)
+		     : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32)));
 }
 
 /*
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index c3bd0c0758c9..e9ded149a9e3 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -71,7 +71,6 @@ static inline void update_task_stack(struct task_struct *task)
 	this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0);
 #else
 	if (cpu_feature_enabled(X86_FEATURE_FRED)) {
-		/* WRMSRNS is a baseline feature for FRED. */
 		wrmsrns(MSR_IA32_FRED_RSP0, (unsigned long)task_stack_page(task) + THREAD_SIZE);
 	} else if (cpu_feature_enabled(X86_FEATURE_XENPV)) {
 		/* Xen PV enters the kernel on the thread stack. */
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index b7d9f530ae16..8bd84114c2d9 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -83,7 +83,6 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_AMX_TILE,			X86_FEATURE_XFD       },
 	{ X86_FEATURE_SHSTK,			X86_FEATURE_XSAVES    },
 	{ X86_FEATURE_FRED,			X86_FEATURE_LKGS      },
-	{ X86_FEATURE_FRED,			X86_FEATURE_WRMSRNS   },
 	{}
 };