mm: vmstats: track TLB flush stats on UP too

The previous patch doing vmstats for TLB flushes ("mm: vmstats: tlb flush
counters") effectively missed UP since arch/x86/mm/tlb.c is only compiled
for SMP.

UP systems do not do remote TLB flushes, so compile those counters out on
UP.

arch/x86/kernel/cpu/mtrr/generic.c calls __flush_tlb() directly.  This is
probably an optimization since both the mtrr code and __flush_tlb() write
cr4.  It would probably be safe to make that a flush_tlb_all() (and then
get these statistics), but the mtrr code is ancient and I'm hesitant to
touch it other than to just stick in the counters.

[akpm@linux-foundation.org: tweak comments]
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/x86/kernel/cpu/mtrr/generic.c

@@ -683,6 +683,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 	}
 
 	/* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
+	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Save MTRR state */
@@ -696,6 +697,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 static void post_set(void) __releases(set_atomicity_lock)
 {
 	/* Flush TLBs (no need to flush caches - they are disabled) */
+	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Intel (P6) standard MTRRs */