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>

3 files changed, 34 insertions, 9 deletions

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index cf512003e663..e6d90babc245 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -62,6 +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);
         __flush_tlb_single(addr);
 }
 
@@ -84,14 +85,38 @@ static inline void __flush_tlb_one(unsigned long addr)
 
 #ifndef CONFIG_SMP
 
-#define flush_tlb() __flush_tlb()
-#define flush_tlb_all() __flush_tlb_all()
-#define local_flush_tlb() __flush_tlb()
+/* "_up" is for UniProcessor.
+ *
+ * This is a helper for other header functions.  *Not* intended to be called
+ * directly.  All global TLB flushes need to either call this, or to bump the
+ * vm statistics themselves.
+ */
+static inline void __flush_tlb_up(void)
+{
+        count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+        __flush_tlb();
+}
+
+static inline void flush_tlb_all(void)
+{
+        count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+        __flush_tlb_all();
+}
+
+static inline void flush_tlb(void)
+{
+        __flush_tlb_up();
+}
+
+static inline void local_flush_tlb(void)
+{
+        __flush_tlb_up();
+}
 
 static inline void flush_tlb_mm(struct mm_struct *mm)
 {
         if (mm == current->active_mm)
-                __flush_tlb();
+                __flush_tlb_up();
 }
 
 static inline void flush_tlb_page(struct vm_area_struct *vma,
@@ -105,14 +130,14 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
                                    unsigned long start, unsigned long end)
 {
         if (vma->vm_mm == current->active_mm)
-                __flush_tlb();
+                __flush_tlb_up();
 }
 
 static inline void flush_tlb_mm_range(struct mm_struct *mm,
            unsigned long start, unsigned long end, unsigned long vmflag)
 {
         if (mm == current->active_mm)
-                __flush_tlb();
+                __flush_tlb_up();
 }
 
 static inline void native_flush_tlb_others(const struct cpumask *cpumask,
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index d4cdfa67509e..ce2d0a2c3e4f 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/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 */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index f030cbe669a5..ae699b3bbac8 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -280,10 +280,8 @@ static void do_kernel_range_flush(void *info)
         unsigned long addr;
 
         /* flush range by one by one 'invlpg' */
-        for (addr = f->flush_start; addr < f->flush_end; addr += PAGE_SIZE) {
-                count_vm_event(NR_TLB_LOCAL_FLUSH_ONE_KERNEL);
+        for (addr = f->flush_start; addr < f->flush_end; addr += PAGE_SIZE)
                 __flush_tlb_single(addr);
-        }
 }
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)