branch_stack struct has bit field definition which
produces different bit ordering for big/little endian.
Because of this, when branch_stack sample is collected
in a BE system and viewed/reported in a LE system, bit
fields of the branch stack are not presented properly.
To address this issue, a evsel__reverse64_branch_stack_flags()
is defined and introduced in evsel__parse_sample.

Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
---
 tools/perf/util/evsel.c | 64 +++++++++++++++++++++++++++++++++++++++--
 tools/perf/util/evsel.h |  5 ++++
 2 files changed, 67 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index dbfeceb2546c..007be66b69a2 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c

@@ -2221,6 +2221,46 @@ void __weak arch_perf_parse_sample_weight(struct perf_sample *data,
 	data->weight = *array;
 }
 
+u64 evsel__reverse64_branch_stack_flags(u64 value)
+{
+	u64 new_val = 0;
+
+	/*
+	 * branch_stack flag (u64)
+	 * union {
+	 * 	u64 values;
+	 * 	struct {
+	 * 		mispred:1	//target mispredicted
+	 * 		predicted:1	//target predicted
+	 * 		in_tx:1		//in transaction
+	 * 		abort:1		//transaction abort
+	 * 		cycles:16	//cycle count to last branch
+	 * 		type:4		//branch type
+	 * 		reserved:40
+	 * 	}
+	 * }
+	 */

+	if (bigendian()) {
+		new_val = reverse_64(value, 0, 1);
+		new_val |= reverse_64(value, 1, 1);
+		new_val |= reverse_64(value, 2, 1);
+		new_val |= reverse_64(value, 3, 1);
+		new_val |= reverse_64(value, 4, 16);
+		new_val |= reverse_64(value, 20, 4);
+		new_val |= reverse_64(value, 24, 40);
+	} else {
+		new_val = reverse_64(value, 63, 1);
+		new_val |= reverse_64(value, 62, 1);
+		new_val |= reverse_64(value, 61, 1);
+		new_val |= reverse_64(value, 60, 1);
+		new_val |= reverse_64(value, 44, 16);
+		new_val |= reverse_64(value, 40, 4);
+		new_val |= reverse_64(value, 0, 40);
+	}
+
+	return new_val;
+}
+
 int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 			struct perf_sample *data)
 {

@@ -2408,6 +2448,8 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
 		const u64 max_branch_nr = UINT64_MAX /
 					  sizeof(struct branch_entry);
+		struct branch_entry *e;
+		unsigned int i;
 
 		OVERFLOW_CHECK_u64(array);
 		data->branch_stack = (struct branch_stack *)array++;

@@ -2416,10 +2458,28 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 			return -EFAULT;
 
 		sz = data->branch_stack->nr * sizeof(struct branch_entry);
-		if (evsel__has_branch_hw_idx(evsel))
+		if (evsel__has_branch_hw_idx(evsel)) {
 			sz += sizeof(u64);
-		else
+			e = &data->branch_stack->entries[0];
+		} else {
 			data->no_hw_idx = true;
+			e = (struct branch_entry *)&data->branch_stack->hw_idx;

+		}
+
+		if (swapped) {
+			/*
+			 * struct branch_flag does not have endian specific
+			 * bit field definition. And bswap will not resolve the
+			 * issue, since these are bit fields.
+			 *
+			 * evsel__reverse64_branch_stack_flags() uses a reverse64
+			 * macro to reverse the bit position based on the host
+			 * endians.
+			 */
+			for (i = 0; i < data->branch_stack->nr; i++, e++)
+				e->flags.value = evsel__reverse64_branch_stack_flags(e->flags.value);
+		}
+
 		OVERFLOW_CHECK(array, sz, max_size);
 		array = (void *)array + sz;
 	}

diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 1f7edfa8568a..1127c23710cf 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h

@@ -482,4 +482,9 @@ struct evsel *evsel__leader(struct evsel *evsel);
 bool evsel__has_leader(struct evsel *evsel, struct evsel *leader);
 bool evsel__is_leader(struct evsel *evsel);
 void evsel__set_leader(struct evsel *evsel, struct evsel *leader);
+
+#define reverse_64(src, pos, size)	\
+	((((src) >> (pos)) & ((1ull << (size)) - 1)) << (63 - ((pos) + (size) - 1)))