Aside from being excessively slow, CPUID is problematic: Linux runs
on a handful of CPUs that don't have CPUID.  MOV to CR2 is always
available, so use it instead.

On my laptop, CPUID(eax=1, ecx=0) is ~83ns and MOV-to-CR2 is ~42ns,
so this should be a nice speedup.

Signed-off-by: Andy Lutomirski <l...@kernel.org>
---
 arch/x86/include/asm/processor.h | 31 ++++++++-----------------------
 1 file changed, 8 insertions(+), 23 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c4402053c663..6727ed1c0ca0 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -594,31 +594,16 @@ static __always_inline void cpu_relax(void)
 /* Stop speculative execution and prefetching of modified code. */
 static inline void native_sync_core(void)
 {
-       int tmp;
-
-#ifdef CONFIG_X86_32
-       /*
-        * Do a CPUID if available, otherwise do a jump.  The jump
-        * can conveniently enough be the jump around CPUID.
-        */
-       asm volatile("cmpl %2,%1\n\t"
-                    "jl 1f\n\t"
-                    "cpuid\n"
-                    "1:"
-                    : "=a" (tmp)
-                    : "rm" (boot_cpu_data.cpuid_level), "ri" (0), "0" (1)
-                    : "ebx", "ecx", "edx", "memory");
-#else
        /*
-        * CPUID is a barrier to speculative execution.
-        * Prefetched instructions are automatically
-        * invalidated when modified.
+        * MOV to CR2 is architecturally defined as a serializing
+        * instruction.  It's nice because it works on all CPUs, it
+        * doesn't clobber registers, and (unlike CPUID) it won't force
+        * a VM exit.
+        *
+        * 0xbf172b23 is random poison just in case something ends up
+        * caring about this value.
         */
-       asm volatile("cpuid"
-                    : "=a" (tmp)
-                    : "0" (1)
-                    : "ebx", "ecx", "edx", "memory");
-#endif
+       native_write_cr2(0xbf172b23);
 }
 
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
-- 
2.9.3

Reply via email to