[PATCH v4 3/6] x86-64: Don't generate cmov in vread_tsc

[Andy Lutomirski]

vread_tsc checks whether rdtsc returns something less than
cycle_last, which is an extremely predictable branch.  GCC likes
to generate a cmov anyway, which is several cycles slower than
a predicted branch.  This saves a couple of nanoseconds.

Signed-off-by: Andy Lutomirski <luto@xxxxxxx>
---
 arch/x86/kernel/tsc.c |   18 ++++++++++++++++--
 1 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 7cabdae..db4c6e6 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -767,6 +767,7 @@ static cycle_t read_tsc(struct clocksource *cs)
 static cycle_t __vsyscall_fn vread_tsc(void)
 {
 	cycle_t ret;
+	u64 last;
 
 	/*
 	 * Empirically, a fence (of type that depends on the CPU)
@@ -778,8 +779,21 @@ static cycle_t __vsyscall_fn vread_tsc(void)
 	rdtsc_barrier();
 	ret = (cycle_t)vget_cycles();
 
-	return ret >= VVAR(vsyscall_gtod_data).clock.cycle_last ?
-		ret : VVAR(vsyscall_gtod_data).clock.cycle_last;
+	last = VVAR(vsyscall_gtod_data).clock.cycle_last;
+
+	if (likely(ret >= last))
+		return ret;
+
+	/*
+	 * GCC likes to generate cmov here, but this branch is extremely
+	 * predictable (it's just a funciton of time and the likely is
+	 * very likely) and there's a data dependence, so force GCC
+	 * to generate a branch instead.  I don't barrier() because
+	 * we don't actually need a barrier, and if this function
+	 * ever gets inlined it will generate worse code.
+	 */
+	asm volatile ("");
+	return last;
 }
 #endif
 
-- 
1.7.5.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/