diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index 2aabe43c1d04f432bbc35422f0c751b884558164..a9d823a93fe89e9bbf11db6a48169ede758af39e 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -369,6 +369,8 @@ enum perf_event_type {
 	 *
 	 *	{ u64			nr,
 	 *	  u64			ips[nr];  } && PERF_SAMPLE_CALLCHAIN
+	 *	{ u32			size;
+	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
 	 * };
 	 */
 	PERF_EVENT_SAMPLE		= 9,
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 7fb16d90e7b1334ba431e0f7952c78931a58f567..7167b9b97da261a69cbb6006835a06ad02e5c524 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -685,7 +685,8 @@ static void ftrace_profile_##call(proto)				\
 	pc = preempt_count();						\
 									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
-	__entry_size = ALIGN(__data_size + sizeof(*entry), sizeof(u64));\
+	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
+			     sizeof(u64));				\
 									\
 	do {								\
 		char raw_data[__entry_size];				\
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 546e62d629416dd5e714b8b72f5872b223301885..5229d1666fa5d2fdac21a2b2acb733a935b01f82 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -2646,7 +2646,6 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		u64 counter;
 	} group_entry;
 	struct perf_callchain_entry *callchain = NULL;
-	struct perf_raw_record *raw = NULL;
 	int callchain_size = 0;
 	u64 time;
 	struct {
@@ -2716,9 +2715,15 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 	}
 
 	if (sample_type & PERF_SAMPLE_RAW) {
-		raw = data->raw;
-		if (raw)
-			header.size += raw->size;
+		int size = sizeof(u32);
+
+		if (data->raw)
+			size += data->raw->size;
+		else
+			size += sizeof(u32);
+
+		WARN_ON_ONCE(size & (sizeof(u64)-1));
+		header.size += size;
 	}
 
 	ret = perf_output_begin(&handle, counter, header.size, nmi, 1);
@@ -2784,8 +2789,21 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		}
 	}
 
-	if ((sample_type & PERF_SAMPLE_RAW) && raw)
-		perf_output_copy(&handle, raw->data, raw->size);
+	if (sample_type & PERF_SAMPLE_RAW) {
+		if (data->raw) {
+			perf_output_put(&handle, data->raw->size);
+			perf_output_copy(&handle, data->raw->data, data->raw->size);
+		} else {
+			struct {
+				u32	size;
+				u32	data;
+			} raw = {
+				.size = sizeof(u32),
+				.data = 0,
+			};
+			perf_output_put(&handle, raw);
+		}
+	}
 
 	perf_output_end(&handle);
 }