mm, x86: Account for TLB flushes only when debugging

Bisection between 3.11 and 3.12 fingered commit 9824cf9 ("mm:
vmstats: tlb flush counters") to cause overhead problems.

The counters are undeniably useful but how often do we really
need to debug TLB flush related issues?  It does not justify
taking the penalty everywhere so make it a debugging option.

Signed-off-by: Mel Gorman <[email protected]>
Tested-by: Davidlohr Bueso <[email protected]>
Reviewed-by: Rik van Riel <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Alex Shi <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

arch/x86/include/asm/tlbflush.h

@@ -62,7 +62,7 @@ static inline void __flush_tlb_all(void)
 
 static inline void __flush_tlb_one(unsigned long addr)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 	__flush_tlb_single(addr);
 }
 
@@ -93,13 +93,13 @@ static inline void __flush_tlb_one(unsigned long addr)
  */
 static inline void __flush_tlb_up(void)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 }
 
 static inline void flush_tlb_all(void)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb_all();
 }
 

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

@@ -683,7 +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);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Save MTRR state */
@@ -697,7 +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);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Intel (P6) standard MTRRs */

arch/x86/mm/tlb.c

@@ -103,7 +103,7 @@ static void flush_tlb_func(void *info)
 	if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
 		return;
 
-	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
 		if (f->flush_end == TLB_FLUSH_ALL)
 			local_flush_tlb();
@@ -131,7 +131,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 	info.flush_start = start;
 	info.flush_end = end;
 
-	count_vm_event(NR_TLB_REMOTE_FLUSH);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	if (is_uv_system()) {
 		unsigned int cpu;
 
@@ -151,7 +151,7 @@ void flush_tlb_current_task(void)
 
 	preempt_disable();
 
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	local_flush_tlb();
 	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
 		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
@@ -215,7 +215,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 
 	/* tlb_flushall_shift is on balance point, details in commit log */
 	if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) {
-		count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 		local_flush_tlb();
 	} else {
 		if (has_large_page(mm, start, end)) {
@@ -224,7 +224,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 		}
 		/* flush range by one by one 'invlpg' */
 		for (addr = start; addr < end;	addr += PAGE_SIZE) {
-			count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
+			count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 			__flush_tlb_single(addr);
 		}
 
@@ -262,15 +262,15 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
 
 static void do_flush_tlb_all(void *info)
 {
-	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	__flush_tlb_all();
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
 		leave_mm(smp_processor_id());
 }
 
 void flush_tlb_all(void)
 {
-	count_vm_event(NR_TLB_REMOTE_FLUSH);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	on_each_cpu(do_flush_tlb_all, NULL, 1);
 }
 

include/linux/vm_event_item.h

@@ -71,12 +71,14 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		THP_ZERO_PAGE_ALLOC,
 		THP_ZERO_PAGE_ALLOC_FAILED,
 #endif
+#ifdef CONFIG_DEBUG_TLBFLUSH
 #ifdef CONFIG_SMP
 		NR_TLB_REMOTE_FLUSH,	/* cpu tried to flush others' tlbs */
 		NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */
-#endif
+#endif /* CONFIG_SMP */
 		NR_TLB_LOCAL_FLUSH_ALL,
 		NR_TLB_LOCAL_FLUSH_ONE,
+#endif /* CONFIG_DEBUG_TLBFLUSH */
 		NR_VM_EVENT_ITEMS
 };
 

include/linux/vmstat.h

@@ -83,6 +83,14 @@ static inline void vm_events_fold_cpu(int cpu)
 #define count_vm_numa_events(x, y) do { (void)(y); } while (0)
 #endif /* CONFIG_NUMA_BALANCING */
 
+#ifdef CONFIG_DEBUG_TLBFLUSH
+#define count_vm_tlb_event(x)	   count_vm_event(x)
+#define count_vm_tlb_events(x, y)  count_vm_events(x, y)
+#else
+#define count_vm_tlb_event(x)     do {} while (0)
+#define count_vm_tlb_events(x, y) do { (void)(y); } while (0)
+#endif
+
 #define __count_zone_vm_events(item, zone, delta) \
 		__count_vm_events(item##_NORMAL - ZONE_NORMAL + \
 		zone_idx(zone), delta)

mm/vmstat.c

@@ -851,12 +851,14 @@ const char * const vmstat_text[] = {
 	"thp_zero_page_alloc",
 	"thp_zero_page_alloc_failed",
 #endif
+#ifdef CONFIG_DEBUG_TLBFLUSH
 #ifdef CONFIG_SMP
 	"nr_tlb_remote_flush",
 	"nr_tlb_remote_flush_received",
-#endif
+#endif /* CONFIG_SMP */
 	"nr_tlb_local_flush_all",
 	"nr_tlb_local_flush_one",
+#endif /* CONFIG_DEBUG_TLBFLUSH */
 
 #endif /* CONFIG_VM_EVENTS_COUNTERS */
 };