x86/mm: Add tracepoints for TLB flushes

We don't have any good way to figure out what kinds of flushes
are being attempted.  Right now, we can try to use the vm
counters, but those only tell us what we actually did with the
hardware (one-by-one vs full) and don't tell us what was actually
_requested_.

This allows us to select out "interesting" TLB flushes that we
might want to optimize (like the ranged ones) and ignore the ones
that we have very little control over (the ones at context
switch).

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: http://lkml.kernel.org/r/20140731154059.4C96CBA5@viggo.jf.intel.com
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

2 files changed, 16 insertions, 2 deletions

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index f97130618113..66dba36f2343 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -18,6 +18,13 @@
 #include <asm/dma.h>            /* for MAX_DMA_PFN */
 #include <asm/microcode.h>
 
+/*
+ * We need to define the tracepoints somewhere, and tlb.c
+ * is only compied when SMP=y.
+ */
+#define CREATE_TRACE_POINTS
+#include <trace/events/tlb.h>
+
 #include "mm_internal.h"
 
 static unsigned long __initdata pgt_buf_start;
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index add5a0fc3c5f..6f00ecb9feeb 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -49,6 +49,7 @@ void leave_mm(int cpu)
         if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) {
                 cpumask_clear_cpu(cpu, mm_cpumask(active_mm));
                 load_cr3(swapper_pg_dir);
+                trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
         }
 }
 EXPORT_SYMBOL_GPL(leave_mm);
@@ -107,15 +108,19 @@ static void flush_tlb_func(void *info)
 
         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)
+                if (f->flush_end == TLB_FLUSH_ALL) {
                         local_flush_tlb();
-                else {
+                        trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, TLB_FLUSH_ALL);
+                } else {
                         unsigned long addr;
+                        unsigned long nr_pages =
+                                f->flush_end - f->flush_start / PAGE_SIZE;
                         addr = f->flush_start;
                         while (addr < f->flush_end) {
                                 __flush_tlb_single(addr);
                                 addr += PAGE_SIZE;
                         }
+                        trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, nr_pages);
                 }
         } else
                 leave_mm(smp_processor_id());
@@ -153,6 +158,7 @@ void flush_tlb_current_task(void)
 
         count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
         local_flush_tlb();
+        trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL);
         if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
                 flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
         preempt_enable();
@@ -191,6 +197,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
                         __flush_tlb_single(addr);
                 }
         }
+        trace_tlb_flush(TLB_LOCAL_MM_SHOOTDOWN, base_pages_to_flush);
 out:
         if (base_pages_to_flush == TLB_FLUSH_ALL) {
                 start = 0UL;