x86/vdso: Mark the TSC clocksource path likely

Jumping out of line for the TSC clcoksource read is creating awful
code. TSC is likely to be the clocksource at least on bare metal and the PV
interfaces are sufficiently more work that the jump over the TSC read is
just in the noise.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Link: https://lkml.kernel.org/r/20200207124402.328922847@linutronix.de

diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index 6ee1f7dba34bf4bfc87299a592ed38f76eb86b35..264d4fd3ff2c5aac0d7f26845ce2fd21f9639d9f 100644 (file)
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -243,7 +243,7 @@ static u64 vread_hvclock(void)
 
 static inline u64 __arch_get_hw_counter(s32 clock_mode)
 {
-       if (clock_mode == VCLOCK_TSC)
+       if (likely(clock_mode == VCLOCK_TSC))
                return (u64)rdtsc_ordered();
        /*
         * For any memory-mapped vclock type, we need to make sure that gcc