x86/asm/tsc/sync: Use rdtsc_ordered() in check_tsc_warp() and drop extra barriers

Using get_cycles was unnecessary: check_tsc_warp() is not called
on TSC-less systems. Replace rdtsc_barrier(); get_cycles() with
rdtsc_ordered().

While we're at it, make the somewhat more dangerous change of
removing barrier_before_rdtsc after RDTSC in the TSC warp check
code. This should be okay, though -- the vDSO TSC code doesn't
have that barrier, so, if removing the barrier from the warp
check would cause us to detect a warp that we otherwise wouldn't
detect, then we have a genuine bug.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Huang Rui <ray.huang@amd.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Len Brown <lenb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: kvm ML <kvm@vger.kernel.org>
Link: http://lkml.kernel.org/r/387c4c3a75f875bcde6cd68cee013273a744f364.1434501121.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/kernel/tsc_sync.c

@@ -39,16 +39,15 @@ static cycles_t max_warp;
 static int nr_warps;
 
 /*
- * TSC-warp measurement loop running on both CPUs:
+ * TSC-warp measurement loop running on both CPUs.  This is not called
+ * if there is no TSC.
  */
 static void check_tsc_warp(unsigned int timeout)
 {
 	cycles_t start, now, prev, end;
 	int i;
 
-	rdtsc_barrier();
-	start = get_cycles();
-	rdtsc_barrier();
+	start = rdtsc_ordered();
 	/*
 	 * The measurement runs for 'timeout' msecs:
 	 */
@@ -63,9 +62,7 @@ static void check_tsc_warp(unsigned int timeout)
 		 */
 		arch_spin_lock(&sync_lock);
 		prev = last_tsc;
-		rdtsc_barrier();
-		now = get_cycles();
-		rdtsc_barrier();
+		now = rdtsc_ordered();
 		last_tsc = now;
 		arch_spin_unlock(&sync_lock);
 
@@ -126,7 +123,7 @@ void check_tsc_sync_source(int cpu)
 
 	/*
 	 * No need to check if we already know that the TSC is not
-	 * synchronized:
+	 * synchronized or if we have no TSC.
 	 */
 	if (unsynchronized_tsc())
 		return;
@@ -190,6 +187,7 @@ void check_tsc_sync_target(void)
 {
 	int cpus = 2;
 
+	/* Also aborts if there is no TSC. */
 	if (unsynchronized_tsc() || tsc_clocksource_reliable)
 		return;