perf tools: Add hw_idx in struct branch_stack

The low level index of raw branch records for the most recent branch can
be recorded in a sample with PERF_SAMPLE_BRANCH_HW_INDEX
branch_sample_type. Extend struct branch_stack to support it.

However, if the PERF_SAMPLE_BRANCH_HW_INDEX is not applied, only nr and
entries[] will be output by kernel. The pointer of entries[] could be
wrong, since the output format is different with new struct
branch_stack.  Add a variable no_hw_idx in struct perf_sample to
indicate whether the hw_idx is output.  Add get_branch_entry() to return
corresponding pointer of entries[0].

To make dummy branch sample consistent as new branch sample, add hw_idx
in struct dummy_branch_stack for cs-etm and intel-pt.

Apply the new struct branch_stack for synthetic events as well.

Extend test case sample-parsing to support new struct branch_stack.

Committer notes:

Renamed get_branch_entries() to perf_sample__branch_entries() to have
proper namespacing and pave the way for this to be moved to libperf,
eventually.

Add 'static' to that inline as it is in a header.

Add 'hw_idx' to 'struct dummy_branch_stack' in cs-etm.c to fix the build
on arm64.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pavel Gerasimov <pavel.gerasimov@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vitaly Slobodskoy <vitaly.slobodskoy@intel.com>
Link: http://lore.kernel.org/lkml/20200228163011.19358-2-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

11 files changed, 82 insertions, 37 deletions

diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h
index 88e00d268f6f..154a05cd03af 100644
--- a/tools/perf/util/branch.h
+++ b/tools/perf/util/branch.h
@@ -12,6 +12,7 @@
 #include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <linux/types.h>
+#include "event.h"
 
 struct branch_flags {
 	u64 mispred:1;
@@ -39,9 +40,30 @@ struct branch_entry {
 
 struct branch_stack {
 	u64			nr;
+	u64			hw_idx;
 	struct branch_entry	entries[0];
 };
 
+/*
+ * The hw_idx is only available when PERF_SAMPLE_BRANCH_HW_INDEX is applied.
+ * Otherwise, the output format of a sample with branch stack is
+ * struct branch_stack {
+ *	u64			nr;
+ *	struct branch_entry	entries[0];
+ * }
+ * Check whether the hw_idx is available,
+ * and return the corresponding pointer of entries[0].
+ */
+static inline struct branch_entry *perf_sample__branch_entries(struct perf_sample *sample)
+{
+	u64 *entry = (u64 *)sample->branch_stack;
+
+	entry++;
+	if (sample->no_hw_idx)
+		return (struct branch_entry *)entry;
+	return (struct branch_entry *)(++entry);
+}
+
 struct branch_type_stat {
 	bool	branch_to;
 	u64	counts[PERF_BR_MAX];
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 5471045ebf5c..b3b3fe3ea345 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1172,6 +1172,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
 	union perf_event *event = tidq->event_buf;
 	struct dummy_branch_stack {
 		u64			nr;
+		u64			hw_idx;
 		struct branch_entry	entries;
 	} dummy_bs;
 	u64 ip;
@@ -1202,6 +1203,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
 	if (etm->synth_opts.last_branch) {
 		dummy_bs = (struct dummy_branch_stack){
 			.nr = 1,
+			.hw_idx = -1ULL,
 			.entries = {
 				.from = sample.ip,
 				.to = sample.addr,
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 85223159737c..3cda40a2fafc 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -139,6 +139,7 @@ struct perf_sample {
 	u16 insn_len;
 	u8  cpumode;
 	u16 misc;
+	bool no_hw_idx;		/* No hw_idx collected in branch_stack */
 	char insn[MAX_INSN];
 	void *raw_data;
 	struct ip_callchain *callchain;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index c8dc4450884c..05883a45de5b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2169,7 +2169,12 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 
 		if (data->branch_stack->nr > max_branch_nr)
 			return -EFAULT;
+
 		sz = data->branch_stack->nr * sizeof(struct branch_entry);
+		if (perf_evsel__has_branch_hw_idx(evsel))
+			sz += sizeof(u64);
+		else
+			data->no_hw_idx = true;
 		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 dc14f4a823cd..99a0cb60c556 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -389,6 +389,11 @@ static inline bool perf_evsel__has_branch_callstack(const struct evsel *evsel)
 	return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
 }
 
+static inline bool perf_evsel__has_branch_hw_idx(const struct evsel *evsel)
+{
+	return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
+}
+
 static inline bool evsel__has_callchain(const struct evsel *evsel)
 {
 	return (evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index ca5a8f4d007e..e74a5acf66d9 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -2584,9 +2584,10 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 			  u64 *total_cycles)
 {
 	struct branch_info *bi;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 
 	/* If we have branch cycles always annotate them. */
-	if (bs && bs->nr && bs->entries[0].flags.cycles) {
+	if (bs && bs->nr && entries[0].flags.cycles) {
 		int i;
 
 		bi = sample__resolve_bstack(sample, al);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 33cf8928cf05..23c8289c2472 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1295,6 +1295,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	struct perf_sample sample = { .ip = 0, };
 	struct dummy_branch_stack {
 		u64			nr;
+		u64			hw_idx;
 		struct branch_entry	entries;
 	} dummy_bs;
 
@@ -1316,6 +1317,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	if (pt->synth_opts.last_branch && sort__mode == SORT_MODE__BRANCH) {
 		dummy_bs = (struct dummy_branch_stack){
 			.nr = 1,
+			.hw_idx = -1ULL,
 			.entries = {
 				.from = sample.ip,
 				.to = sample.addr,
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index fb5c2cd44d30..fd14f1489802 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2081,15 +2081,16 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 {
 	unsigned int i;
 	const struct branch_stack *bs = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	struct branch_info *bi = calloc(bs->nr, sizeof(struct branch_info));
 
 	if (!bi)
 		return NULL;
 
 	for (i = 0; i < bs->nr; i++) {
-		ip__resolve_ams(al->thread, &bi[i].to, bs->entries[i].to);
-		ip__resolve_ams(al->thread, &bi[i].from, bs->entries[i].from);
-		bi[i].flags = bs->entries[i].flags;
+		ip__resolve_ams(al->thread, &bi[i].to, entries[i].to);
+		ip__resolve_ams(al->thread, &bi[i].from, entries[i].from);
+		bi[i].flags = entries[i].flags;
 	}
 	return bi;
 }
@@ -2185,6 +2186,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 	/* LBR only affects the user callchain */
 	if (i != chain_nr) {
 		struct branch_stack *lbr_stack = sample->branch_stack;
+		struct branch_entry *entries = perf_sample__branch_entries(sample);
 		int lbr_nr = lbr_stack->nr, j, k;
 		bool branch;
 		struct branch_flags *flags;
@@ -2210,31 +2212,29 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 					ip = chain->ips[j];
 				else if (j > i + 1) {
 					k = j - i - 2;
-					ip = lbr_stack->entries[k].from;
+					ip = entries[k].from;
 					branch = true;
-					flags = &lbr_stack->entries[k].flags;
+					flags = &entries[k].flags;
 				} else {
-					ip = lbr_stack->entries[0].to;
+					ip = entries[0].to;
 					branch = true;
-					flags = &lbr_stack->entries[0].flags;
-					branch_from =
-						lbr_stack->entries[0].from;
+					flags = &entries[0].flags;
+					branch_from = entries[0].from;
 				}
 			} else {
 				if (j < lbr_nr) {
 					k = lbr_nr - j - 1;
-					ip = lbr_stack->entries[k].from;
+					ip = entries[k].from;
 					branch = true;
-					flags = &lbr_stack->entries[k].flags;
+					flags = &entries[k].flags;
 				}
 				else if (j > lbr_nr)
 					ip = chain->ips[i + 1 - (j - lbr_nr)];
 				else {
-					ip = lbr_stack->entries[0].to;
+					ip = entries[0].to;
 					branch = true;
-					flags = &lbr_stack->entries[0].flags;
-					branch_from =
-						lbr_stack->entries[0].from;
+					flags = &entries[0].flags;
+					branch_from = entries[0].from;
 				}
 			}
 
@@ -2281,6 +2281,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 					    int max_stack)
 {
 	struct branch_stack *branch = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	struct ip_callchain *chain = sample->callchain;
 	int chain_nr = 0;
 	u8 cpumode = PERF_RECORD_MISC_USER;
@@ -2328,7 +2329,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 
 		for (i = 0; i < nr; i++) {
 			if (callchain_param.order == ORDER_CALLEE) {
-				be[i] = branch->entries[i];
+				be[i] = entries[i];
 
 				if (chain == NULL)
 					continue;
@@ -2347,7 +2348,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 				    be[i].from >= chain->ips[first_call] - 8)
 					first_call++;
 			} else
-				be[i] = branch->entries[branch->nr - i - 1];
+				be[i] = entries[branch->nr - i - 1];
 		}
 
 		memset(iter, 0, sizeof(struct iterations) * nr);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 80ca5d0ab7fe..8c1b27cd8b99 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -464,6 +464,7 @@ static PyObject *python_process_brstack(struct perf_sample *sample,
 					struct thread *thread)
 {
 	struct branch_stack *br = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	PyObject *pylist;
 	u64 i;
 
@@ -484,28 +485,28 @@ static PyObject *python_process_brstack(struct perf_sample *sample,
 			Py_FatalError("couldn't create Python dictionary");
 
 		pydict_set_item_string_decref(pyelem, "from",
-		    PyLong_FromUnsignedLongLong(br->entries[i].from));
+		    PyLong_FromUnsignedLongLong(entries[i].from));
 		pydict_set_item_string_decref(pyelem, "to",
-		    PyLong_FromUnsignedLongLong(br->entries[i].to));
+		    PyLong_FromUnsignedLongLong(entries[i].to));
 		pydict_set_item_string_decref(pyelem, "mispred",
-		    PyBool_FromLong(br->entries[i].flags.mispred));
+		    PyBool_FromLong(entries[i].flags.mispred));
 		pydict_set_item_string_decref(pyelem, "predicted",
-		    PyBool_FromLong(br->entries[i].flags.predicted));
+		    PyBool_FromLong(entries[i].flags.predicted));
 		pydict_set_item_string_decref(pyelem, "in_tx",
-		    PyBool_FromLong(br->entries[i].flags.in_tx));
+		    PyBool_FromLong(entries[i].flags.in_tx));
 		pydict_set_item_string_decref(pyelem, "abort",
-		    PyBool_FromLong(br->entries[i].flags.abort));
+		    PyBool_FromLong(entries[i].flags.abort));
 		pydict_set_item_string_decref(pyelem, "cycles",
-		    PyLong_FromUnsignedLongLong(br->entries[i].flags.cycles));
+		    PyLong_FromUnsignedLongLong(entries[i].flags.cycles));
 
 		thread__find_map_fb(thread, sample->cpumode,
-				    br->entries[i].from, &al);
+				    entries[i].from, &al);
 		dsoname = get_dsoname(al.map);
 		pydict_set_item_string_decref(pyelem, "from_dsoname",
 					      _PyUnicode_FromString(dsoname));
 
 		thread__find_map_fb(thread, sample->cpumode,
-				    br->entries[i].to, &al);
+				    entries[i].to, &al);
 		dsoname = get_dsoname(al.map);
 		pydict_set_item_string_decref(pyelem, "to_dsoname",
 					      _PyUnicode_FromString(dsoname));
@@ -561,6 +562,7 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
 					   struct thread *thread)
 {
 	struct branch_stack *br = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	PyObject *pylist;
 	u64 i;
 	char bf[512];
@@ -581,22 +583,22 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
 			Py_FatalError("couldn't create Python dictionary");
 
 		thread__find_symbol_fb(thread, sample->cpumode,
-				       br->entries[i].from, &al);
+				       entries[i].from, &al);
 		get_symoff(al.sym, &al, true, bf, sizeof(bf));
 		pydict_set_item_string_decref(pyelem, "from",
 					      _PyUnicode_FromString(bf));
 
 		thread__find_symbol_fb(thread, sample->cpumode,
-				       br->entries[i].to, &al);
+				       entries[i].to, &al);
 		get_symoff(al.sym, &al, true, bf, sizeof(bf));
 		pydict_set_item_string_decref(pyelem, "to",
 					      _PyUnicode_FromString(bf));
 
-		get_br_mspred(&br->entries[i].flags, bf, sizeof(bf));
+		get_br_mspred(&entries[i].flags, bf, sizeof(bf));
 		pydict_set_item_string_decref(pyelem, "pred",
 					      _PyUnicode_FromString(bf));
 
-		if (br->entries[i].flags.in_tx) {
+		if (entries[i].flags.in_tx) {
 			pydict_set_item_string_decref(pyelem, "in_tx",
 					      _PyUnicode_FromString("X"));
 		} else {
@@ -604,7 +606,7 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
 					      _PyUnicode_FromString("-"));
 		}
 
-		if (br->entries[i].flags.abort) {
+		if (entries[i].flags.abort) {
 			pydict_set_item_string_decref(pyelem, "abort",
 					      _PyUnicode_FromString("A"));
 		} else {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d0d7d25b23e3..055b00abd56d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1007,6 +1007,7 @@ static void callchain__lbr_callstack_printf(struct perf_sample *sample)
 {
 	struct ip_callchain *callchain = sample->callchain;
 	struct branch_stack *lbr_stack = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	u64 kernel_callchain_nr = callchain->nr;
 	unsigned int i;
 
@@ -1043,10 +1044,10 @@ static void callchain__lbr_callstack_printf(struct perf_sample *sample)
 			       i, callchain->ips[i]);
 
 		printf("..... %2d: %016" PRIx64 "\n",
-		       (int)(kernel_callchain_nr), lbr_stack->entries[0].to);
+		       (int)(kernel_callchain_nr), entries[0].to);
 		for (i = 0; i < lbr_stack->nr; i++)
 			printf("..... %2d: %016" PRIx64 "\n",
-			       (int)(i + kernel_callchain_nr + 1), lbr_stack->entries[i].from);
+			       (int)(i + kernel_callchain_nr + 1), entries[i].from);
 	}
 }
 
@@ -1068,6 +1069,7 @@ static void callchain__printf(struct evsel *evsel,
 
 static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 {
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	uint64_t i;
 
 	printf("%s: nr:%" PRIu64 "\n",
@@ -1075,7 +1077,7 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 		sample->branch_stack->nr);
 
 	for (i = 0; i < sample->branch_stack->nr; i++) {
-		struct branch_entry *e = &sample->branch_stack->entries[i];
+		struct branch_entry *e = &entries[i];
 
 		if (!callstack) {
 			printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index c423298fe62d..dd3e6f43fb86 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -1183,7 +1183,8 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
 		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
-		sz += sizeof(u64);
+		/* nr, hw_idx */
+		sz += 2 * sizeof(u64);
 		result += sz;
 	}
 
@@ -1344,7 +1345,8 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
 		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
-		sz += sizeof(u64);
+		/* nr, hw_idx */
+		sz += 2 * sizeof(u64);
 		memcpy(array, sample->branch_stack, sz);
 		array = (void *)array + sz;
 	}