File perf-evsel-Add-bitfield_swap-to-handle-branch_stack-endian-issue.patch of Package perf.35610
From: Madhavan Srinivasan <maddy@linux.ibm.com>
Date: Thu, 28 Oct 2021 17:07:13 +0530
Subject: perf evsel: Add bitfield_swap() to handle branch_stack endian issue
Git-commit: 63c12ae2f246dcdc30895ec7c980365a5133433d
Patch-mainline: v5.16-rc1
References: jsc#PED-557
The 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__bitfield_swap_branch_stack() is defined
and introduced in evsel__parse_sample.
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Ellerman <michael@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211028113714.600549-1-maddy@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Tony Jones <tonyj@suse.de>
---
tools/perf/util/evsel.c | 77 +++++++++++++++++++++++++++++++++++++++++++++++--
tools/perf/util/evsel.h | 13 +++++++++
2 files changed, 88 insertions(+), 2 deletions(-)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 96ef6a4a7c14..2cfc2935d1d2 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2238,6 +2238,54 @@ void __weak arch_perf_parse_sample_weight(struct perf_sample *data,
data->weight = *array;
}
+u64 evsel__bitfield_swap_branch_flags(u64 value)
+{
+ u64 new_val = 0;
+
+ /*
+ * branch_flags
+ * 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
+ * }
+ * }
+ *
+ * Avoid bswap64() the entire branch_flag.value,
+ * as it has variable bit-field sizes. Instead the
+ * macro takes the bit-field position/size,
+ * swaps it based on the host endianness.
+ *
+ * tep_is_bigendian() is used here instead of
+ * bigendian() to avoid python test fails.
+ */
+ if (tep_is_bigendian()) {
+ new_val = bitfield_swap(value, 0, 1);
+ new_val |= bitfield_swap(value, 1, 1);
+ new_val |= bitfield_swap(value, 2, 1);
+ new_val |= bitfield_swap(value, 3, 1);
+ new_val |= bitfield_swap(value, 4, 16);
+ new_val |= bitfield_swap(value, 20, 4);
+ new_val |= bitfield_swap(value, 24, 40);
+ } else {
+ new_val = bitfield_swap(value, 63, 1);
+ new_val |= bitfield_swap(value, 62, 1);
+ new_val |= bitfield_swap(value, 61, 1);
+ new_val |= bitfield_swap(value, 60, 1);
+ new_val |= bitfield_swap(value, 44, 16);
+ new_val |= bitfield_swap(value, 40, 4);
+ new_val |= bitfield_swap(value, 0, 40);
+ }
+
+ return new_val;
+}
+
int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
struct perf_sample *data)
{
@@ -2425,6 +2473,8 @@ 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++;
@@ -2433,10 +2483,33 @@ 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;
+ /*
+ * if the PERF_SAMPLE_BRANCH_HW_INDEX is not applied,
+ * only nr and entries[] will be output by kernel.
+ */
+ 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__bitfield_swap_branch_flags() uses a
+ * bitfield_swap macro to swap the bit position
+ * based on the host endians.
+ */
+ for (i = 0; i < data->branch_stack->nr; i++, e++)
+ e->flags.value = evsel__bitfield_swap_branch_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 45476a888942..846c827934de 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -484,4 +484,17 @@ 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);
+
+/*
+ * Macro to swap the bit-field postition and size.
+ * Used when,
+ * - dont need to swap the entire u64 &&
+ * - when u64 has variable bit-field sizes &&
+ * - when presented in a host endian which is different
+ * than the source endian of the perf.data file
+ */
+#define bitfield_swap(src, pos, size) \
+ ((((src) >> (pos)) & ((1ull << (size)) - 1)) << (63 - ((pos) + (size) - 1)))
+
+u64 evsel__bitfield_swap_branch_flags(u64 value);
#endif /* __PERF_EVSEL_H */
