diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index be12c534fd592e84fd81ca0b3b6c5182ecb2f6fe..166af2a8e865b370c605cecf6777b79882e6dcb2 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -3,6 +3,10 @@
 
 #include <asm/desc.h>
 #include <linux/atomic.h>
+#include <linux/mm_types.h>
+
+#include <trace/events/tlb.h>
+
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
@@ -44,6 +48,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 
 		/* Re-load page tables */
 		load_cr3(next->pgd);
+		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 
 		/* Stop flush ipis for the previous mm */
 		cpumask_clear_cpu(cpu, mm_cpumask(prev));
@@ -71,6 +76,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 			 * to make sure to use no freed page tables.
 			 */
 			load_cr3(next->pgd);
+			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 			load_LDT_nolock(&next->context);
 		}
 	}
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index f9713061811332100ee6560ec736b0c18c509e45..66dba36f2343571532f09e1c7767a7a85ea28f4f 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 add5a0fc3c5f2ebbb71fe2c50dc7bf4a047e922b..6f00ecb9feebd5f59fcdde37426cc8bf71c37aa2 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;
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 96c5750e3110e7bfd0b58b464738e25aa6bac8ab..796deac19fcfb4bb21d9e8ba9e22c7d4e15df156 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -516,4 +516,12 @@ struct vm_special_mapping
 	struct page **pages;
 };
 
+enum tlb_flush_reason {
+	TLB_FLUSH_ON_TASK_SWITCH,
+	TLB_REMOTE_SHOOTDOWN,
+	TLB_LOCAL_SHOOTDOWN,
+	TLB_LOCAL_MM_SHOOTDOWN,
+	NR_TLB_FLUSH_REASONS,
+};
+
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/include/trace/events/tlb.h b/include/trace/events/tlb.h
new file mode 100644
index 0000000000000000000000000000000000000000..13391d288107a6aa4325c34ba16a00450b7af814
--- /dev/null
+++ b/include/trace/events/tlb.h
@@ -0,0 +1,40 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM tlb
+
+#if !defined(_TRACE_TLB_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_TLB_H
+
+#include <linux/mm_types.h>
+#include <linux/tracepoint.h>
+
+#define TLB_FLUSH_REASON	\
+	{ TLB_FLUSH_ON_TASK_SWITCH,	"flush on task switch" },	\
+	{ TLB_REMOTE_SHOOTDOWN,		"remote shootdown" },		\
+	{ TLB_LOCAL_SHOOTDOWN,		"local shootdown" },		\
+	{ TLB_LOCAL_MM_SHOOTDOWN,	"local mm shootdown" }
+
+TRACE_EVENT(tlb_flush,
+
+	TP_PROTO(int reason, unsigned long pages),
+	TP_ARGS(reason, pages),
+
+	TP_STRUCT__entry(
+		__field(	  int, reason)
+		__field(unsigned long,  pages)
+	),
+
+	TP_fast_assign(
+		__entry->reason = reason;
+		__entry->pages  = pages;
+	),
+
+	TP_printk("pages:%ld reason:%s (%d)",
+		__entry->pages,
+		__print_symbolic(__entry->reason, TLB_FLUSH_REASON),
+		__entry->reason)
+);
+
+#endif /* _TRACE_TLB_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>