mm: vmstats: tlb flush counters

I was investigating some TLB flush scaling issues and realized that we do
not have any good methods for figuring out how many TLB flushes we are
doing.

It would be nice to be able to do these in generic code, but the
arch-independent calls don't explicitly specify whether we actually need
to do remote flushes or not.  In the end, we really need to know if we
actually _did_ global vs.  local invalidations, so that leaves us with few
options other than to muck with the counters from arch-specific code.

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, 24 insertions, 4 deletions

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 282375f13c7e..f030cbe669a5 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -103,6 +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);
         if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
                 if (f->flush_end == TLB_FLUSH_ALL)
                         local_flush_tlb();
@@ -130,6 +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);
         if (is_uv_system()) {
                 unsigned int cpu;
 
@@ -149,6 +151,7 @@ void flush_tlb_current_task(void)
 
         preempt_disable();
 
+        count_vm_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);
@@ -211,16 +214,19 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
         act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm;
 
         /* tlb_flushall_shift is on balance point, details in commit log */
-        if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift)
+        if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) {
+                count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
                 local_flush_tlb();
-        else {
+        } else {
                 if (has_large_page(mm, start, end)) {
                         local_flush_tlb();
                         goto flush_all;
                 }
                 /* flush range by one by one 'invlpg' */
-                for (addr = start; addr < end;  addr += PAGE_SIZE)
+                for (addr = start; addr < end;  addr += PAGE_SIZE) {
+                        count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
                         __flush_tlb_single(addr);
+                }
 
                 if (cpumask_any_but(mm_cpumask(mm),
                                 smp_processor_id()) < nr_cpu_ids)
@@ -256,6 +262,7 @@ 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);
         __flush_tlb_all();
         if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
                 leave_mm(smp_processor_id());
@@ -263,6 +270,7 @@ static void do_flush_tlb_all(void *info)
 
 void flush_tlb_all(void)
 {
+        count_vm_event(NR_TLB_REMOTE_FLUSH);
         on_each_cpu(do_flush_tlb_all, NULL, 1);
 }
 
@@ -272,8 +280,10 @@ 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)
+        for (addr = f->flush_start; addr < f->flush_end; addr += PAGE_SIZE) {
+                count_vm_event(NR_TLB_LOCAL_FLUSH_ONE_KERNEL);
                 __flush_tlb_single(addr);
+        }
 }
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index bd6cf61142be..dc2cdf07ac14 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -70,6 +70,11 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
                 THP_ZERO_PAGE_ALLOC,
                 THP_ZERO_PAGE_ALLOC_FAILED,
 #endif
+                NR_TLB_REMOTE_FLUSH,    /* cpu tried to flush others' tlbs */
+                NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */
+                NR_TLB_LOCAL_FLUSH_ALL,
+                NR_TLB_LOCAL_FLUSH_ONE,
+                NR_TLB_LOCAL_FLUSH_ONE_KERNEL,
                 NR_VM_EVENT_ITEMS
 };
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 20c2ef4458fa..00382c53f582 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -817,6 +817,11 @@ const char * const vmstat_text[] = {
         "thp_zero_page_alloc",
         "thp_zero_page_alloc_failed",
 #endif
+        "nr_tlb_remote_flush",
+        "nr_tlb_remote_flush_received",
+        "nr_tlb_local_flush_all",
+        "nr_tlb_local_flush_one",
+        "nr_tlb_local_flush_one_kernel",
 
 #endif /* CONFIG_VM_EVENTS_COUNTERS */
 };