[PATCH 0/9] perf intel-pt: Add support for synthesizing branch stacks for regular events

[PATCH 0/9] perf intel-pt: Add support for synthesizing branch stacks for regular events

[Adrian Hunter]

Hi

This patchset adds Intel PT support for synthesizing branch stacks for
regular events.  This follows on from the patchset that did the same thing
for call chains.

The first 3 patches convert Intel PT to using thread-stack to record branch
stacks, which allows branch stacks to be accumulated separately for each
thread.

The next 3 patches add support for synthesizing branch stacks for regular
events.

The final 2 patches update some documentation.


Adrian Hunter (9):
      perf thread-stack: Add branch stack support
      perf intel-pt: Consolidate thread-stack use condition
      perf intel-pt: Change branch stack support to use thread-stacks
      perf auxtrace: Add option to synthesize branch stack for regular events
      perf evsel: Add support for synthesized branch stack sample type
      perf thread-stack: Add thread_stack__br_sample_late()
      perf intel-pt: Add support for synthesizing branch stacks for regular events
      perf intel-pt: Update documentation about itrace G and L options
      perf intel-pt: Update documentation about using /proc/kcore

 tools/perf/Documentation/itrace.txt        |   5 +
 tools/perf/Documentation/perf-intel-pt.txt |  53 +++++--
 tools/perf/builtin-inject.c                |   3 +-
 tools/perf/builtin-report.c                |   5 +-
 tools/perf/util/auxtrace.c                 |   6 +-
 tools/perf/util/auxtrace.h                 |   2 +
 tools/perf/util/evsel.h                    |  10 ++
 tools/perf/util/intel-bts.c                |   2 +-
 tools/perf/util/intel-pt.c                 | 210 ++++++++++++++--------------
 tools/perf/util/s390-cpumsf.c              |   3 +-
 tools/perf/util/session.c                  |   2 +-
 tools/perf/util/thread-stack.c             | 217 +++++++++++++++++++++++++++--
 tools/perf/util/thread-stack.h             |   8 +-
 13 files changed, 393 insertions(+), 133 deletions(-)


Regards
Adrian

[PATCH 1/9] perf thread-stack: Add branch stack support

[Adrian Hunter]

Intel PT already has support for creating branch stacks for each context
(per-cpu or per-thread). In the more common per-cpu case, the branch stack
is not separated for different threads, instead being cleared in between
each sample. That approach will not work very well for adding branch stacks
to regular events. The branch stacks really need to be accumulated
separately for each thread.

As a start to accomplishing that, this patch adds support for putting
branch stack support into the thread-stack. The advantages are:
1. the branches are accumulated separately for each thread
2. the branch stack is cleared only in between continuous traces

This helps pave the way for adding branch stacks to regular events, not
just synthesized events as at present.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/intel-bts.c    |   2 +-
 tools/perf/util/intel-pt.c     |   2 +-
 tools/perf/util/thread-stack.c | 113 +++++++++++++++++++++++++++++----
 tools/perf/util/thread-stack.h |   5 +-
 4 files changed, 108 insertions(+), 14 deletions(-)

diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 059e1c805ed0..506112f52619 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -432,7 +432,7 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
 					    le64_to_cpu(branch->from),
 					    le64_to_cpu(branch->to),
 					    btsq->intel_pt_insn.length,
-					    buffer->buffer_nr + 1);
+					    buffer->buffer_nr + 1, true, 0, 0);
 		if (filter && !(filter & btsq->sample_flags))
 			continue;
 		err = intel_bts_synth_branch_sample(btsq, branch);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 4be7634dccf5..865e79ccf55b 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2032,7 +2032,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	    pt->synth_opts.thread_stack)
 		thread_stack__event(ptq->thread, ptq->cpu, ptq->flags, state->from_ip,
 				    state->to_ip, ptq->insn_len,
-				    state->trace_nr);
+				    state->trace_nr, true, 0, 0);
 	else
 		thread_stack__set_trace_nr(ptq->thread, ptq->cpu, state->trace_nr);
 
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 83f6c83f5617..79698831b4b9 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -80,6 +80,10 @@ struct thread_stack_entry {
  * @comm: current comm
  * @arr_sz: size of array if this is the first element of an array
  * @rstate: used to detect retpolines
+ * @br_stack_rb: branch stack (ring buffer)
+ * @br_stack_sz: maximum branch stack size
+ * @br_stack_pos: current position in @br_stack_rb
+ * @mispred_all: mark all branches as mispredicted
  */
 struct thread_stack {
 	struct thread_stack_entry *stack;
@@ -95,6 +99,10 @@ struct thread_stack {
 	struct comm *comm;
 	unsigned int arr_sz;
 	enum retpoline_state_t rstate;
+	struct branch_stack *br_stack_rb;
+	unsigned int br_stack_sz;
+	unsigned int br_stack_pos;
+	bool mispred_all;
 };
 
 /*
@@ -126,13 +134,26 @@ static int thread_stack__grow(struct thread_stack *ts)
 }
 
 static int thread_stack__init(struct thread_stack *ts, struct thread *thread,
-			      struct call_return_processor *crp)
+			      struct call_return_processor *crp,
+			      bool callstack, unsigned int br_stack_sz)
 {
 	int err;
 
-	err = thread_stack__grow(ts);
-	if (err)
-		return err;
+	if (callstack) {
+		err = thread_stack__grow(ts);
+		if (err)
+			return err;
+	}
+
+	if (br_stack_sz) {
+		size_t sz = sizeof(struct branch_stack);
+
+		sz += br_stack_sz * sizeof(struct branch_entry);
+		ts->br_stack_rb = zalloc(sz);
+		if (!ts->br_stack_rb)
+			return -ENOMEM;
+		ts->br_stack_sz = br_stack_sz;
+	}
 
 	if (thread->maps && thread->maps->machine) {
 		struct machine *machine = thread->maps->machine;
@@ -150,7 +171,9 @@ static int thread_stack__init(struct thread_stack *ts, struct thread *thread,
 }
 
 static struct thread_stack *thread_stack__new(struct thread *thread, int cpu,
-					      struct call_return_processor *crp)
+					      struct call_return_processor *crp,
+					      bool callstack,
+					      unsigned int br_stack_sz)
 {
 	struct thread_stack *ts = thread->ts, *new_ts;
 	unsigned int old_sz = ts ? ts->arr_sz : 0;
@@ -176,7 +199,7 @@ static struct thread_stack *thread_stack__new(struct thread *thread, int cpu,
 		ts += cpu;
 
 	if (!ts->stack &&
-	    thread_stack__init(ts, thread, crp))
+	    thread_stack__init(ts, thread, crp, callstack, br_stack_sz))
 		return NULL;
 
 	return ts;
@@ -319,6 +342,9 @@ static int __thread_stack__flush(struct thread *thread, struct thread_stack *ts)
 
 	if (!crp) {
 		ts->cnt = 0;
+		ts->br_stack_pos = 0;
+		if (ts->br_stack_rb)
+			ts->br_stack_rb->nr = 0;
 		return 0;
 	}
 
@@ -353,8 +379,33 @@ int thread_stack__flush(struct thread *thread)
 	return err;
 }
 
+static void thread_stack__update_br_stack(struct thread_stack *ts, u32 flags,
+					  u64 from_ip, u64 to_ip)
+{
+	struct branch_stack *bs = ts->br_stack_rb;
+	struct branch_entry *be;
+
+	if (!ts->br_stack_pos)
+		ts->br_stack_pos = ts->br_stack_sz;
+
+	ts->br_stack_pos -= 1;
+
+	be              = &bs->entries[ts->br_stack_pos];
+	be->from        = from_ip;
+	be->to          = to_ip;
+	be->flags.value = 0;
+	be->flags.abort = !!(flags & PERF_IP_FLAG_TX_ABORT);
+	be->flags.in_tx = !!(flags & PERF_IP_FLAG_IN_TX);
+	/* No support for mispredict */
+	be->flags.mispred = ts->mispred_all;
+
+	if (bs->nr < ts->br_stack_sz)
+		bs->nr += 1;
+}
+
 int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
-			u64 to_ip, u16 insn_len, u64 trace_nr)
+			u64 to_ip, u16 insn_len, u64 trace_nr, bool callstack,
+			unsigned int br_stack_sz, bool mispred_all)
 {
 	struct thread_stack *ts = thread__stack(thread, cpu);
 
@@ -362,12 +413,13 @@ int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
 		return -EINVAL;
 
 	if (!ts) {
-		ts = thread_stack__new(thread, cpu, NULL);
+		ts = thread_stack__new(thread, cpu, NULL, callstack, br_stack_sz);
 		if (!ts) {
 			pr_warning("Out of memory: no thread stack\n");
 			return -ENOMEM;
 		}
 		ts->trace_nr = trace_nr;
+		ts->mispred_all = mispred_all;
 	}
 
 	/*
@@ -381,8 +433,14 @@ int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
 		ts->trace_nr = trace_nr;
 	}
 
-	/* Stop here if thread_stack__process() is in use */
-	if (ts->crp)
+	if (br_stack_sz)
+		thread_stack__update_br_stack(ts, flags, from_ip, to_ip);
+
+	/*
+	 * Stop here if thread_stack__process() is in use, or not recording call
+	 * stack.
+	 */
+	if (ts->crp || !callstack)
 		return 0;
 
 	if (flags & PERF_IP_FLAG_CALL) {
@@ -430,6 +488,7 @@ static void __thread_stack__free(struct thread *thread, struct thread_stack *ts)
 {
 	__thread_stack__flush(thread, ts);
 	zfree(&ts->stack);
+	zfree(&ts->br_stack_rb);
 }
 
 static void thread_stack__reset(struct thread *thread, struct thread_stack *ts)
@@ -554,6 +613,38 @@ void thread_stack__sample_late(struct thread *thread, int cpu,
 	}
 }
 
+void thread_stack__br_sample(struct thread *thread, int cpu,
+			     struct branch_stack *dst, unsigned int sz)
+{
+	struct thread_stack *ts = thread__stack(thread, cpu);
+	const size_t bsz = sizeof(struct branch_entry);
+	struct branch_stack *src;
+	struct branch_entry *be;
+	unsigned int nr;
+
+	dst->nr = 0;
+
+	if (!ts)
+		return;
+
+	src = ts->br_stack_rb;
+	if (!src->nr)
+		return;
+
+	dst->nr = min((unsigned int)src->nr, sz);
+
+	be = &dst->entries[0];
+	nr = min(ts->br_stack_sz - ts->br_stack_pos, (unsigned int)dst->nr);
+	memcpy(be, &src->entries[ts->br_stack_pos], bsz * nr);
+
+	if (src->nr >= ts->br_stack_sz) {
+		sz -= nr;
+		be = &dst->entries[nr];
+		nr = min(ts->br_stack_pos, sz);
+		memcpy(be, &src->entries[0], bsz * ts->br_stack_pos);
+	}
+}
+
 struct call_return_processor *
 call_return_processor__new(int (*process)(struct call_return *cr, u64 *parent_db_id, void *data),
 			   void *data)
@@ -921,7 +1012,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 	}
 
 	if (!ts) {
-		ts = thread_stack__new(thread, sample->cpu, crp);
+		ts = thread_stack__new(thread, sample->cpu, crp, true, 0);
 		if (!ts)
 			return -ENOMEM;
 		ts->comm = comm;
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index 8962ddc4e1ab..c279a0cbbdd0 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -81,13 +81,16 @@ struct call_return_processor {
 };
 
 int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
-			u64 to_ip, u16 insn_len, u64 trace_nr);
+			u64 to_ip, u16 insn_len, u64 trace_nr, bool callstack,
+			unsigned int br_stack_sz, bool mispred_all);
 void thread_stack__set_trace_nr(struct thread *thread, int cpu, u64 trace_nr);
 void thread_stack__sample(struct thread *thread, int cpu, struct ip_callchain *chain,
 			  size_t sz, u64 ip, u64 kernel_start);
 void thread_stack__sample_late(struct thread *thread, int cpu,
 			       struct ip_callchain *chain, size_t sz, u64 ip,
 			       u64 kernel_start);
+void thread_stack__br_sample(struct thread *thread, int cpu,
+			     struct branch_stack *dst, unsigned int sz);
 int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
 size_t thread_stack__depth(struct thread *thread, int cpu);
-- 
2.17.1

[PATCH 2/9] perf intel-pt: Consolidate thread-stack use condition

[Adrian Hunter]

The components of the condition do not change, so consolidate them in one
variable.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/intel-pt.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 865e79ccf55b..afc42a6e4e00 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -68,6 +68,7 @@ struct intel_pt {
 	bool est_tsc;
 	bool sync_switch;
 	bool mispred_all;
+	bool use_thread_stack;
 	int have_sched_switch;
 	u32 pmu_type;
 	u64 kernel_start;
@@ -2028,8 +2029,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	if (!(state->type & INTEL_PT_BRANCH))
 		return 0;
 
-	if (pt->synth_opts.callchain || pt->synth_opts.add_callchain ||
-	    pt->synth_opts.thread_stack)
+	if (pt->use_thread_stack)
 		thread_stack__event(ptq->thread, ptq->cpu, ptq->flags, state->from_ip,
 				    state->to_ip, ptq->insn_len,
 				    state->trace_nr, true, 0, 0);
@@ -3440,6 +3440,10 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 			goto err_delete_thread;
 	}
 
+	pt->use_thread_stack = pt->synth_opts.callchain ||
+			       pt->synth_opts.add_callchain ||
+			       pt->synth_opts.thread_stack;
+
 	err = intel_pt_synth_events(pt, session);
 	if (err)
 		goto err_delete_thread;
-- 
2.17.1

[PATCH 3/9] perf intel-pt: Change branch stack support to use thread-stacks

[Adrian Hunter]

Change Intel PT's branch stack support to use thread stacks. The
advantages of using branch stack support from the thread-stack are:
1. the branches are accumulated separately for each thread
2. the branch stack is cleared only in between continuous traces

This helps pave the way for adding branch stacks to regular events, not
just synthesized events as at present.

While the 2 approaches are not identical, in simple cases the results
can be identical e.g.

  Before:

    # perf record --kcore -e intel_pt// uname
    # perf script --itrace=i10usl -F+brstacksym,+addr,+flags > cmp1.txt

  After:

    # perf script --itrace=i10usl -F+brstacksym,+addr,+flags > cmp2.txt
    # diff -s cmp1.txt cmp2.txt
    Files cmp1.txt and cmp2.txt are identical

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/intel-pt.c | 141 ++++++++++---------------------------
 1 file changed, 39 insertions(+), 102 deletions(-)

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index afc42a6e4e00..248a39fd4d0e 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -69,6 +69,8 @@ struct intel_pt {
 	bool sync_switch;
 	bool mispred_all;
 	bool use_thread_stack;
+	bool callstack;
+	unsigned int br_stack_sz;
 	int have_sched_switch;
 	u32 pmu_type;
 	u64 kernel_start;
@@ -146,8 +148,6 @@ struct intel_pt_queue {
 	const struct intel_pt_state *state;
 	struct ip_callchain *chain;
 	struct branch_stack *last_branch;
-	struct branch_stack *last_branch_rb;
-	size_t last_branch_pos;
 	union perf_event *event_buf;
 	bool on_heap;
 	bool stop;
@@ -930,14 +930,10 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 	if (pt->synth_opts.last_branch) {
 		size_t sz = sizeof(struct branch_stack);
 
-		sz += pt->synth_opts.last_branch_sz *
-		      sizeof(struct branch_entry);
+		sz += pt->br_stack_sz * sizeof(struct branch_entry);
 		ptq->last_branch = zalloc(sz);
 		if (!ptq->last_branch)
 			goto out_free;
-		ptq->last_branch_rb = zalloc(sz);
-		if (!ptq->last_branch_rb)
-			goto out_free;
 	}
 
 	ptq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
@@ -1006,7 +1002,6 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 out_free:
 	zfree(&ptq->event_buf);
 	zfree(&ptq->last_branch);
-	zfree(&ptq->last_branch_rb);
 	zfree(&ptq->chain);
 	free(ptq);
 	return NULL;
@@ -1022,7 +1017,6 @@ static void intel_pt_free_queue(void *priv)
 	intel_pt_decoder_free(ptq->decoder);
 	zfree(&ptq->event_buf);
 	zfree(&ptq->last_branch);
-	zfree(&ptq->last_branch_rb);
 	zfree(&ptq->chain);
 	free(ptq);
 }
@@ -1190,58 +1184,6 @@ static int intel_pt_setup_queues(struct intel_pt *pt)
 	return 0;
 }
 
-static inline void intel_pt_copy_last_branch_rb(struct intel_pt_queue *ptq)
-{
-	struct branch_stack *bs_src = ptq->last_branch_rb;
-	struct branch_stack *bs_dst = ptq->last_branch;
-	size_t nr = 0;
-
-	bs_dst->nr = bs_src->nr;
-
-	if (!bs_src->nr)
-		return;
-
-	nr = ptq->pt->synth_opts.last_branch_sz - ptq->last_branch_pos;
-	memcpy(&bs_dst->entries[0],
-	       &bs_src->entries[ptq->last_branch_pos],
-	       sizeof(struct branch_entry) * nr);
-
-	if (bs_src->nr >= ptq->pt->synth_opts.last_branch_sz) {
-		memcpy(&bs_dst->entries[nr],
-		       &bs_src->entries[0],
-		       sizeof(struct branch_entry) * ptq->last_branch_pos);
-	}
-}
-
-static inline void intel_pt_reset_last_branch_rb(struct intel_pt_queue *ptq)
-{
-	ptq->last_branch_pos = 0;
-	ptq->last_branch_rb->nr = 0;
-}
-
-static void intel_pt_update_last_branch_rb(struct intel_pt_queue *ptq)
-{
-	const struct intel_pt_state *state = ptq->state;
-	struct branch_stack *bs = ptq->last_branch_rb;
-	struct branch_entry *be;
-
-	if (!ptq->last_branch_pos)
-		ptq->last_branch_pos = ptq->pt->synth_opts.last_branch_sz;
-
-	ptq->last_branch_pos -= 1;
-
-	be              = &bs->entries[ptq->last_branch_pos];
-	be->from        = state->from_ip;
-	be->to          = state->to_ip;
-	be->flags.abort = !!(state->flags & INTEL_PT_ABORT_TX);
-	be->flags.in_tx = !!(state->flags & INTEL_PT_IN_TX);
-	/* No support for mispredict */
-	be->flags.mispred = ptq->pt->mispred_all;
-
-	if (bs->nr < ptq->pt->synth_opts.last_branch_sz)
-		bs->nr += 1;
-}
-
 static inline bool intel_pt_skip_event(struct intel_pt *pt)
 {
 	return pt->synth_opts.initial_skip &&
@@ -1309,9 +1251,9 @@ static inline int intel_pt_opt_inject(struct intel_pt *pt,
 	return intel_pt_inject_event(event, sample, type);
 }
 
-static int intel_pt_deliver_synth_b_event(struct intel_pt *pt,
-					  union perf_event *event,
-					  struct perf_sample *sample, u64 type)
+static int intel_pt_deliver_synth_event(struct intel_pt *pt,
+					union perf_event *event,
+					struct perf_sample *sample, u64 type)
 {
 	int ret;
 
@@ -1371,8 +1313,8 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 		ptq->last_br_cyc_cnt = ptq->ipc_cyc_cnt;
 	}
 
-	return intel_pt_deliver_synth_b_event(pt, event, &sample,
-					      pt->branches_sample_type);
+	return intel_pt_deliver_synth_event(pt, event, &sample,
+					    pt->branches_sample_type);
 }
 
 static void intel_pt_prep_sample(struct intel_pt *pt,
@@ -1390,27 +1332,12 @@ static void intel_pt_prep_sample(struct intel_pt *pt,
 	}
 
 	if (pt->synth_opts.last_branch) {
-		intel_pt_copy_last_branch_rb(ptq);
+		thread_stack__br_sample(ptq->thread, ptq->cpu, ptq->last_branch,
+					pt->br_stack_sz);
 		sample->branch_stack = ptq->last_branch;
 	}
 }
 
-static inline int intel_pt_deliver_synth_event(struct intel_pt *pt,
-					       struct intel_pt_queue *ptq,
-					       union perf_event *event,
-					       struct perf_sample *sample,
-					       u64 type)
-{
-	int ret;
-
-	ret = intel_pt_deliver_synth_b_event(pt, event, sample, type);
-
-	if (pt->synth_opts.last_branch)
-		intel_pt_reset_last_branch_rb(ptq);
-
-	return ret;
-}
-
 static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
@@ -1435,7 +1362,7 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 
 	ptq->last_insn_cnt = ptq->state->tot_insn_cnt;
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->instructions_sample_type);
 }
 
@@ -1453,7 +1380,7 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
 	sample.id = ptq->pt->transactions_id;
 	sample.stream_id = ptq->pt->transactions_id;
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->transactions_sample_type);
 }
 
@@ -1494,7 +1421,7 @@ static int intel_pt_synth_ptwrite_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->ptwrites_sample_type);
 }
 
@@ -1524,7 +1451,7 @@ static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->pwr_events_sample_type);
 }
 
@@ -1549,7 +1476,7 @@ static int intel_pt_synth_mwait_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->pwr_events_sample_type);
 }
 
@@ -1574,7 +1501,7 @@ static int intel_pt_synth_pwre_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->pwr_events_sample_type);
 }
 
@@ -1599,7 +1526,7 @@ static int intel_pt_synth_exstop_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->pwr_events_sample_type);
 }
 
@@ -1624,7 +1551,7 @@ static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->pwr_events_sample_type);
 }
 
@@ -1844,7 +1771,9 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
 			intel_pt_add_lbrs(&br.br_stack, items);
 			sample.branch_stack = &br.br_stack;
 		} else if (pt->synth_opts.last_branch) {
-			intel_pt_copy_last_branch_rb(ptq);
+			thread_stack__br_sample(ptq->thread, ptq->cpu,
+						ptq->last_branch,
+						pt->br_stack_sz);
 			sample.branch_stack = ptq->last_branch;
 		} else {
 			br.br_stack.nr = 0;
@@ -1879,7 +1808,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
 		sample.transaction = txn;
 	}
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample, sample_type);
+	return intel_pt_deliver_synth_event(pt, event, &sample, sample_type);
 }
 
 static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
@@ -2029,12 +1958,15 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	if (!(state->type & INTEL_PT_BRANCH))
 		return 0;
 
-	if (pt->use_thread_stack)
-		thread_stack__event(ptq->thread, ptq->cpu, ptq->flags, state->from_ip,
-				    state->to_ip, ptq->insn_len,
-				    state->trace_nr, true, 0, 0);
-	else
+	if (pt->use_thread_stack) {
+		thread_stack__event(ptq->thread, ptq->cpu, ptq->flags,
+				    state->from_ip, state->to_ip, ptq->insn_len,
+				    state->trace_nr, pt->callstack,
+				    pt->br_stack_sz,
+				    pt->mispred_all);
+	} else {
 		thread_stack__set_trace_nr(ptq->thread, ptq->cpu, state->trace_nr);
+	}
 
 	if (pt->sample_branches) {
 		err = intel_pt_synth_branch_sample(ptq);
@@ -2042,9 +1974,6 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 			return err;
 	}
 
-	if (pt->synth_opts.last_branch)
-		intel_pt_update_last_branch_rb(ptq);
-
 	if (!ptq->sync_switch)
 		return 0;
 
@@ -3440,9 +3369,17 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 			goto err_delete_thread;
 	}
 
+	if (pt->synth_opts.last_branch)
+		pt->br_stack_sz = pt->synth_opts.last_branch_sz;
+
 	pt->use_thread_stack = pt->synth_opts.callchain ||
 			       pt->synth_opts.add_callchain ||
-			       pt->synth_opts.thread_stack;
+			       pt->synth_opts.thread_stack ||
+			       pt->synth_opts.last_branch;
+
+	pt->callstack = pt->synth_opts.callchain ||
+			pt->synth_opts.add_callchain ||
+			pt->synth_opts.thread_stack;
 
 	err = intel_pt_synth_events(pt, session);
 	if (err)
-- 
2.17.1

[PATCH 4/9] perf auxtrace: Add option to synthesize branch stack for regular events

[Adrian Hunter]

There is an existing option to synthesize branch stacks for synthesized
events. Add a new option to synthesize branch stacks for regular events.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/Documentation/itrace.txt | 1 +
 tools/perf/builtin-inject.c         | 3 ++-
 tools/perf/builtin-report.c         | 5 +++--
 tools/perf/util/auxtrace.c          | 6 +++++-
 tools/perf/util/auxtrace.h          | 2 ++
 tools/perf/util/s390-cpumsf.c       | 3 ++-
 6 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index 671e154ede03..0326050beebd 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -12,6 +12,7 @@
 		g	synthesize a call chain (use with i or x)
 		G	synthesize a call chain on existing event records
 		l	synthesize last branch entries (use with i or x)
+		L	synthesize last branch entries on existing event records
 		s       skip initial number of events
 
 	The default is all events i.e. the same as --itrace=ibxwpe,
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 7e124a7b8bfd..7c4403cf8dcb 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -684,7 +684,8 @@ static int __cmd_inject(struct perf_inject *inject)
 
 			perf_header__clear_feat(&session->header,
 						HEADER_AUXTRACE);
-			if (inject->itrace_synth_opts.last_branch)
+			if (inject->itrace_synth_opts.last_branch ||
+			    inject->itrace_synth_opts.add_last_branch)
 				perf_header__set_feat(&session->header,
 						      HEADER_BRANCH_STACK);
 			evsel = perf_evlist__id2evsel_strict(session->evlist,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 0c32767b1c56..736a54f8e2fc 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -349,7 +349,8 @@ static int report__setup_sample_type(struct report *rep)
 	     !session->itrace_synth_opts->set))
 		sample_type |= PERF_SAMPLE_CALLCHAIN;
 
-	if (session->itrace_synth_opts->last_branch)
+	if (session->itrace_synth_opts->last_branch ||
+	    session->itrace_synth_opts->add_last_branch)
 		sample_type |= PERF_SAMPLE_BRANCH_STACK;
 
 	if (!is_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
@@ -1393,7 +1394,7 @@ int cmd_report(int argc, const char **argv)
 		goto error;
 	}
 
-	if (itrace_synth_opts.last_branch)
+	if (itrace_synth_opts.last_branch || itrace_synth_opts.add_last_branch)
 		has_br_stack = true;
 
 	if (has_br_stack && branch_call_mode)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 33ad33378a90..21d5eddda532 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1463,8 +1463,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 				synth_opts->callchain_sz = val;
 			}
 			break;
+		case 'L':
 		case 'l':
-			synth_opts->last_branch = true;
+			if (p[-1] == 'L')
+				synth_opts->add_last_branch = true;
+			else
+				synth_opts->last_branch = true;
 			synth_opts->last_branch_sz =
 					PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
 			while (*p == ' ' || *p == ',')
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index dd8a4ff8209e..0220a2e86c16 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -77,6 +77,7 @@ enum itrace_period_type {
  * @add_callchain: add callchain to existing event records
  * @thread_stack: feed branches to the thread_stack
  * @last_branch: add branch context to 'instruction' events
+ * @add_last_branch: add branch context to existing event records
  * @callchain_sz: maximum callchain size
  * @last_branch_sz: branch context size
  * @period: 'instructions' events period
@@ -105,6 +106,7 @@ struct itrace_synth_opts {
 	bool			add_callchain;
 	bool			thread_stack;
 	bool			last_branch;
+	bool			add_last_branch;
 	unsigned int		callchain_sz;
 	unsigned int		last_branch_sz;
 	unsigned long long	period;
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index 38a942881d1a..f8861998e5bd 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -1079,7 +1079,8 @@ static bool check_auxtrace_itrace(struct itrace_synth_opts *itops)
 		itops->pwr_events || itops->errors ||
 		itops->dont_decode || itops->calls || itops->returns ||
 		itops->callchain || itops->thread_stack ||
-		itops->last_branch || itops->add_callchain;
+		itops->last_branch || itops->add_callchain ||
+		itops->add_last_branch;
 	if (!ison)
 		return true;
 	pr_err("Unsupported --itrace options specified\n");
-- 
2.17.1

[PATCH 5/9] perf evsel: Add support for synthesized branch stack sample type

[Adrian Hunter]

Allow for a synthesized branch stack to be added to samples. As with
synthesized call chains, the sample type cannot be changed because it is
needed to continue to parse events. So add and use helper function
evsel__has_br_stack() to indicate a branch stack, whether original or
synthesized.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/evsel.h   | 10 ++++++++++
 tools/perf/util/session.c |  2 +-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index a463bc65b001..bf999e3c50c7 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -417,6 +417,16 @@ static inline bool evsel__has_callchain(const struct evsel *evsel)
 	       evsel->synth_sample_type & PERF_SAMPLE_CALLCHAIN;
 }
 
+static inline bool evsel__has_br_stack(const struct evsel *evsel)
+{
+	/*
+	 * For reporting purposes, an evsel sample can have a recorded branch
+	 * stack or a branch stack synthesized from AUX area data.
+	 */
+	return evsel->core.attr.sample_type & PERF_SAMPLE_BRANCH_STACK ||
+	       evsel->synth_sample_type & PERF_SAMPLE_BRANCH_STACK;
+}
+
 struct perf_env *perf_evsel__env(struct evsel *evsel);
 
 int perf_evsel__store_ids(struct evsel *evsel, struct evlist *evlist);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0b0bfe5bef17..2b5a08a92ce5 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1243,7 +1243,7 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 	if (evsel__has_callchain(evsel))
 		callchain__printf(evsel, sample);
 
-	if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+	if (evsel__has_br_stack(evsel))
 		branch_stack__printf(sample, perf_evsel__has_branch_callstack(evsel));
 
 	if (sample_type & PERF_SAMPLE_REGS_USER)
-- 
2.17.1

[PATCH 6/9] perf thread-stack: Add thread_stack__br_sample_late()

[Adrian Hunter]

Add a thread stack function to create a branch stack for hardware events
where the sample records get created some time after the event occurred.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/thread-stack.c | 104 +++++++++++++++++++++++++++++++++
 tools/perf/util/thread-stack.h |   3 +
 2 files changed, 107 insertions(+)

diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 79698831b4b9..1b992bbba4e8 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -645,6 +645,110 @@ void thread_stack__br_sample(struct thread *thread, int cpu,
 	}
 }
 
+/* Start of user space branch entries */
+static bool us_start(struct branch_entry *be, u64 kernel_start, bool *start)
+{
+	if (!*start)
+		*start = be->to && be->to < kernel_start;
+
+	return *start;
+}
+
+/*
+ * Start of branch entries after the ip fell in between 2 branches, or user
+ * space branch entries.
+ */
+static bool ks_start(struct branch_entry *be, u64 sample_ip, u64 kernel_start,
+		     bool *start, struct branch_entry *nb)
+{
+	if (!*start) {
+		*start = (nb && sample_ip >= be->to && sample_ip <= nb->from) ||
+			 be->from < kernel_start ||
+			 (be->to && be->to < kernel_start);
+	}
+
+	return *start;
+}
+
+/*
+ * Hardware sample records, created some time after the event occurred, need to
+ * have subsequent addresses removed from the branch stack.
+ */
+void thread_stack__br_sample_late(struct thread *thread, int cpu,
+				  struct branch_stack *dst, unsigned int sz,
+				  u64 ip, u64 kernel_start)
+{
+	struct thread_stack *ts = thread__stack(thread, cpu);
+	struct branch_entry *d, *s, *spos, *ssz;
+	struct branch_stack *src;
+	unsigned int nr = 0;
+	bool start = false;
+
+	dst->nr = 0;
+
+	if (!ts)
+		return;
+
+	src = ts->br_stack_rb;
+	if (!src->nr)
+		return;
+
+	spos = &src->entries[ts->br_stack_pos];
+	ssz  = &src->entries[ts->br_stack_sz];
+
+	d = &dst->entries[0];
+	s = spos;
+
+	if (ip < kernel_start) {
+		/*
+		 * User space sample: start copying branch entries when the
+		 * branch is in user space.
+		 */
+		for (s = spos; s < ssz && nr < sz; s++) {
+			if (us_start(s, kernel_start, &start)) {
+				*d++ = *s;
+				nr += 1;
+			}
+		}
+
+		if (src->nr >= ts->br_stack_sz) {
+			for (s = &src->entries[0]; s < spos && nr < sz; s++) {
+				if (us_start(s, kernel_start, &start)) {
+					*d++ = *s;
+					nr += 1;
+				}
+			}
+		}
+	} else {
+		struct branch_entry *nb = NULL;
+
+		/*
+		 * Kernel space sample: start copying branch entries when the ip
+		 * falls in between 2 branches (or the branch is in user space
+		 * because then the start must have been missed).
+		 */
+		for (s = spos; s < ssz && nr < sz; s++) {
+			if (ks_start(s, ip, kernel_start, &start, nb)) {
+				*d++ = *s;
+				nr += 1;
+			}
+			nb = s;
+		}
+
+		if (src->nr >= ts->br_stack_sz) {
+			for (s = &src->entries[0]; s < spos && nr < sz; s++) {
+				if (ks_start(s, ip, kernel_start, &start, nb)) {
+					*d++ = *s;
+					nr += 1;
+				}
+				nb = s;
+			}
+		}
+	}
+
+	dst->nr = nr;
+}
+
 struct call_return_processor *
 call_return_processor__new(int (*process)(struct call_return *cr, u64 *parent_db_id, void *data),
 			   void *data)
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index c279a0cbbdd0..3bc47a42af8e 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -91,6 +91,9 @@ void thread_stack__sample_late(struct thread *thread, int cpu,
 			       u64 kernel_start);
 void thread_stack__br_sample(struct thread *thread, int cpu,
 			     struct branch_stack *dst, unsigned int sz);
+void thread_stack__br_sample_late(struct thread *thread, int cpu,
+				  struct branch_stack *dst, unsigned int sz,
+				  u64 sample_ip, u64 kernel_start);
 int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
 size_t thread_stack__depth(struct thread *thread, int cpu);
-- 
2.17.1

[PATCH 7/9] perf intel-pt: Add support for synthesizing branch stacks for regular events

[Adrian Hunter]

Use the new thread_stack__br_sample_late() function to create a thread
stack for regular events.

Example:

 # perf record --kcore --aux-sample -e '{intel_pt//,cycles:ppp}' -c 10000 uname
 Linux
 [ perf record: Woken up 2 times to write data ]
 [ perf record: Captured and wrote 0.743 MB perf.data ]
 # perf report --itrace=Le --stdio | head -30 | tail -18

 # Samples: 11K of event 'cycles:ppp'
 # Event count (approx.): 11648
 #
 # Overhead  Command  Source Shared Object  Source Symbol                                   Target Symbol                                   Basic Block Cycles
 # ........  .......  ....................  ..............................................  ..............................................  ..................
 #
      5.49%  uname    libc-2.30.so          [.] _dl_addr                                    [.] _dl_addr                                    -
      2.41%  uname    ld-2.30.so            [.] _dl_relocate_object                         [.] _dl_relocate_object                         -
      2.31%  uname    ld-2.30.so            [.] do_lookup_x                                 [.] do_lookup_x                                 -
      2.17%  uname    [kernel.kallsyms]     [k] unmap_page_range                            [k] unmap_page_range                            -
      2.05%  uname    ld-2.30.so            [k] _dl_start                                   [k] _dl_start                                   -
      1.97%  uname    ld-2.30.so            [.] _dl_lookup_symbol_x                         [.] _dl_lookup_symbol_x                         -
      1.94%  uname    [kernel.kallsyms]     [k] filemap_map_pages                           [k] filemap_map_pages                           -
      1.60%  uname    [kernel.kallsyms]     [k] __handle_mm_fault                           [k] __handle_mm_fault                           -
      1.44%  uname    [kernel.kallsyms]     [k] page_add_file_rmap                          [k] page_add_file_rmap                          -
      1.12%  uname    [kernel.kallsyms]     [k] vma_interval_tree_insert                    [k] vma_interval_tree_insert                    -
      0.94%  uname    [kernel.kallsyms]     [k] perf_iterate_ctx                            [k] perf_iterate_ctx                            -

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/intel-pt.c | 73 ++++++++++++++++++++++++++++++++++----
 1 file changed, 66 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 248a39fd4d0e..7fb807b91f73 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -71,6 +71,7 @@ struct intel_pt {
 	bool use_thread_stack;
 	bool callstack;
 	unsigned int br_stack_sz;
+	unsigned int br_stack_sz_plus;
 	int have_sched_switch;
 	u32 pmu_type;
 	u64 kernel_start;
@@ -129,6 +130,7 @@ struct intel_pt {
 	unsigned int range_cnt;
 
 	struct ip_callchain *chain;
+	struct branch_stack *br_stack;
 };
 
 enum switch_state {
@@ -910,6 +912,44 @@ static void intel_pt_add_callchain(struct intel_pt *pt,
 	sample->callchain = pt->chain;
 }
 
+static struct branch_stack *intel_pt_alloc_br_stack(struct intel_pt *pt)
+{
+	size_t sz = sizeof(struct branch_stack);
+
+	sz += pt->br_stack_sz * sizeof(struct branch_entry);
+	return zalloc(sz);
+}
+
+static int intel_pt_br_stack_init(struct intel_pt *pt)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(pt->session->evlist, evsel) {
+		if (!(evsel->core.attr.sample_type & PERF_SAMPLE_BRANCH_STACK))
+			evsel->synth_sample_type |= PERF_SAMPLE_BRANCH_STACK;
+	}
+
+	pt->br_stack = intel_pt_alloc_br_stack(pt);
+	if (!pt->br_stack)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void intel_pt_add_br_stack(struct intel_pt *pt,
+				  struct perf_sample *sample)
+{
+	struct thread *thread = machine__findnew_thread(pt->machine,
+							sample->pid,
+							sample->tid);
+
+	thread_stack__br_sample_late(thread, sample->cpu, pt->br_stack,
+				     pt->br_stack_sz, sample->ip,
+				     pt->kernel_start);
+
+	sample->branch_stack = pt->br_stack;
+}
+
 static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 						   unsigned int queue_nr)
 {
@@ -928,10 +968,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 	}
 
 	if (pt->synth_opts.last_branch) {
-		size_t sz = sizeof(struct branch_stack);
-
-		sz += pt->br_stack_sz * sizeof(struct branch_entry);
-		ptq->last_branch = zalloc(sz);
+		ptq->last_branch = intel_pt_alloc_br_stack(pt);
 		if (!ptq->last_branch)
 			goto out_free;
 	}
@@ -1962,7 +1999,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 		thread_stack__event(ptq->thread, ptq->cpu, ptq->flags,
 				    state->from_ip, state->to_ip, ptq->insn_len,
 				    state->trace_nr, pt->callstack,
-				    pt->br_stack_sz,
+				    pt->br_stack_sz_plus,
 				    pt->mispred_all);
 	} else {
 		thread_stack__set_trace_nr(ptq->thread, ptq->cpu, state->trace_nr);
@@ -2608,6 +2645,8 @@ static int intel_pt_process_event(struct perf_session *session,
 	if (event->header.type == PERF_RECORD_SAMPLE) {
 		if (pt->synth_opts.add_callchain && !sample->callchain)
 			intel_pt_add_callchain(pt, sample);
+		if (pt->synth_opts.add_last_branch && !sample->branch_stack)
+			intel_pt_add_br_stack(pt, sample);
 	}
 
 	if (event->header.type == PERF_RECORD_AUX &&
@@ -3369,13 +3408,33 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 			goto err_delete_thread;
 	}
 
-	if (pt->synth_opts.last_branch)
+	if (pt->synth_opts.last_branch || pt->synth_opts.add_last_branch) {
 		pt->br_stack_sz = pt->synth_opts.last_branch_sz;
+		pt->br_stack_sz_plus = pt->br_stack_sz;
+	}
+
+	if (pt->synth_opts.add_last_branch) {
+		err = intel_pt_br_stack_init(pt);
+		if (err)
+			goto err_delete_thread;
+		/*
+		 * Additional branch stack size to cater for tracing from the
+		 * actual sample ip to where the sample time is recorded.
+		 * Measured at about 200 branches, but generously set to 1024.
+		 * If kernel space is not being traced, then add just 1 for the
+		 * branch to kernel space.
+		 */
+		if (intel_pt_tracing_kernel(pt))
+			pt->br_stack_sz_plus += 1024;
+		else
+			pt->br_stack_sz_plus += 1;
+	}
 
 	pt->use_thread_stack = pt->synth_opts.callchain ||
 			       pt->synth_opts.add_callchain ||
 			       pt->synth_opts.thread_stack ||
-			       pt->synth_opts.last_branch;
+			       pt->synth_opts.last_branch ||
+			       pt->synth_opts.add_last_branch;
 
 	pt->callstack = pt->synth_opts.callchain ||
 			pt->synth_opts.add_callchain ||
-- 
2.17.1

[PATCH 8/9] perf intel-pt: Update documentation about itrace G and L options

[Adrian Hunter]

Provide a little more information about the new G and L options,
particularly the issue with large PEBs.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/Documentation/itrace.txt        |  4 +++
 tools/perf/Documentation/perf-intel-pt.txt | 35 ++++++++++++++++++++++
 2 files changed, 39 insertions(+)

diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index 0326050beebd..271484754fee 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -33,6 +33,10 @@
 	Also the number of last branch entries (default 64, max. 1024) for
 	instructions or transactions events can be specified.
 
+	Similar to options g and l, size may also be specified for options G and L.
+	On x86, note that G and L work poorly when data has been recorded with
+	large PEBS. Refer linkperf:perf-intel-pt[1] man page for details.
+
 	It is also possible to skip events generated (instructions, branches, transactions,
 	ptwrite, power) at the beginning. This is useful to ignore initialization code.
 
diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index 456fdcbf26ac..782eb8a65caf 100644
--- a/tools/perf/Documentation/perf-intel-pt.txt
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -821,7 +821,9 @@ The letters are:
 	e	synthesize tracing error events
 	d	create a debug log
 	g	synthesize a call chain (use with i or x)
+	G	synthesize a call chain on existing event records
 	l	synthesize last branch entries (use with i or x)
+	L	synthesize last branch entries on existing event records
 	s	skip initial number of events
 
 "Instructions" events look like they were recorded by "perf record -e
@@ -912,6 +914,39 @@ transactions events can be specified. e.g.
 Note that last branch entries are cleared for each sample, so there is no overlap
 from one sample to the next.
 
+The G and L options are designed in particular for sample mode, and work much
+like g and l but add call chain and branch stack to the other selected events
+instead of synthesized events. For example, to record branch-misses events for
+'ls' and then add a call chain derived from the Intel PT trace:
+
+	perf record --aux-sample -e '{intel_pt//u,branch-misses:u}' -- ls
+	perf report --itrace=Ge
+
+Although in fact G is a default for perf report, so that is the same as just:
+
+	perf report
+
+One caveat with the G and L options is that they work poorly with "Large PEBS".
+Large PEBS means PEBS records will be accumulated by hardware and the written
+into the event buffer in one go.  That reduces interrupts, but can give very
+late timestamps.  Because the Intel PT trace is synchronized by timestamps,
+the PEBS events do not match the trace.  Currently, Large PEBS is used only in
+certain circumstances:
+	- hardware supports it
+	- PEBS is used
+	- event period is specified, instead of frequency
+	- the sample type is limited to the following flags:
+		PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR |
+		PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID |
+		PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER |
+		PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR |
+		PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER |
+		PERF_SAMPLE_PERIOD (and sometimes) | PERF_SAMPLE_TIME
+Because Intel PT sample mode uses a different sample type to the list above,
+Large PEBS is not used with Intel PT sample mode. To avoid Large PEBS in other
+cases, avoid specifying the event period i.e. avoid the 'perf record' -c option,
+--count option, or 'period' config term.
+
 To disable trace decoding entirely, use the option --no-itrace.
 
 It is also possible to skip events generated (instructions, branches, transactions)
-- 
2.17.1

[PATCH 9/9] perf intel-pt: Update documentation about using /proc/kcore

[Adrian Hunter]

Update documentation to reflect the advent of the --kcore option for
'perf record'.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/Documentation/perf-intel-pt.txt | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index 782eb8a65caf..eb8b7d42591a 100644
--- a/tools/perf/Documentation/perf-intel-pt.txt
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -69,22 +69,22 @@ And profiled with 'perf report' e.g.
 To also trace kernel space presents a problem, namely kernel self-modifying
 code.  A fairly good kernel image is available in /proc/kcore but to get an
 accurate image a copy of /proc/kcore needs to be made under the same conditions
-as the data capture.  A script perf-with-kcore can do that, but beware that the
-script makes use of 'sudo' to copy /proc/kcore.  If you have perf installed
-locally from the source tree you can do:
+as the data capture. 'perf record' can make a copy of /proc/kcore if the option
+--kcore is used, but access to /proc/kcore is restricted e.g.
 
-	~/libexec/perf-core/perf-with-kcore record pt_ls -e intel_pt// -- ls
+	sudo perf record -o pt_ls --kcore -e intel_pt// -- ls
 
-which will create a directory named 'pt_ls' and put the perf.data file and
-copies of /proc/kcore, /proc/kallsyms and /proc/modules into it.  Then to use
-'perf report' becomes:
+which will create a directory named 'pt_ls' and put the perf.data file (named
+simply 'data') and copies of /proc/kcore, /proc/kallsyms and /proc/modules into
+it.  The other tools understand the directory format, so to use 'perf report'
+becomes:
 
-	~/libexec/perf-core/perf-with-kcore report pt_ls
+	sudo perf report -i pt_ls
 
 Because samples are synthesized after-the-fact, the sampling period can be
 selected for reporting. e.g. sample every microsecond
 
-	~/libexec/perf-core/perf-with-kcore report pt_ls --itrace=i1usge
+	sudo perf report pt_ls --itrace=i1usge
 
 See the sections below for more information about the --itrace option.
 
-- 
2.17.1

Re: [PATCH 0/9] perf intel-pt: Add support for synthesizing branch stacks for regular events

[Arnaldo Carvalho de Melo]

Em Wed, Apr 29, 2020 at 06:07:42PM +0300, Adrian Hunter escreveu:
> Hi
> 
> This patchset adds Intel PT support for synthesizing branch stacks for
> regular events.  This follows on from the patchset that did the same thing
> for call chains.
> 
> The first 3 patches convert Intel PT to using thread-stack to record branch
> stacks, which allows branch stacks to be accumulated separately for each
> thread.
> 
> The next 3 patches add support for synthesizing branch stacks for regular
> events.
> 
> The final 2 patches update some documentation.

Thanks, applied.

- Arnaldo
 
> 
> Adrian Hunter (9):
>       perf thread-stack: Add branch stack support
>       perf intel-pt: Consolidate thread-stack use condition
>       perf intel-pt: Change branch stack support to use thread-stacks
>       perf auxtrace: Add option to synthesize branch stack for regular events
>       perf evsel: Add support for synthesized branch stack sample type
>       perf thread-stack: Add thread_stack__br_sample_late()
>       perf intel-pt: Add support for synthesizing branch stacks for regular events
>       perf intel-pt: Update documentation about itrace G and L options
>       perf intel-pt: Update documentation about using /proc/kcore
> 
>  tools/perf/Documentation/itrace.txt        |   5 +
>  tools/perf/Documentation/perf-intel-pt.txt |  53 +++++--
>  tools/perf/builtin-inject.c                |   3 +-
>  tools/perf/builtin-report.c                |   5 +-
>  tools/perf/util/auxtrace.c                 |   6 +-
>  tools/perf/util/auxtrace.h                 |   2 +
>  tools/perf/util/evsel.h                    |  10 ++
>  tools/perf/util/intel-bts.c                |   2 +-
>  tools/perf/util/intel-pt.c                 | 210 ++++++++++++++--------------
>  tools/perf/util/s390-cpumsf.c              |   3 +-
>  tools/perf/util/session.c                  |   2 +-
>  tools/perf/util/thread-stack.c             | 217 +++++++++++++++++++++++++++--
>  tools/perf/util/thread-stack.h             |   8 +-
>  13 files changed, 393 insertions(+), 133 deletions(-)
> 
> 
> Regards
> Adrian

-- 

- Arnaldo

Re: [PATCH 8/9] perf intel-pt: Update documentation about itrace G and L options

[Andi Kleen]

> +One caveat with the G and L options is that they work poorly with "Large PEBS".
> +Large PEBS means PEBS records will be accumulated by hardware and the written
> +into the event buffer in one go.  That reduces interrupts, but can give very
> +late timestamps.  Because the Intel PT trace is synchronized by timestamps,

Are you refering to Broadwell here?

On Skylake/Goldmont the PEBS event contains the TSC and the time stamp reported by
perf should report the time the event was sampled based on that TSC. 
Or is that not working for some reason?

-Andi

Re: [PATCH 8/9] perf intel-pt: Update documentation about itrace G and L options

[Adrian Hunter]

On 30/04/20 2:03 am, Andi Kleen wrote:
>> +One caveat with the G and L options is that they work poorly with "Large PEBS".
>> +Large PEBS means PEBS records will be accumulated by hardware and the written
>> +into the event buffer in one go.  That reduces interrupts, but can give very
>> +late timestamps.  Because the Intel PT trace is synchronized by timestamps,
> 
> Are you refering to Broadwell here?

I was testing on Coffee Lake

> 
> On Skylake/Goldmont the PEBS event contains the TSC and the time stamp reported by
> perf should report the time the event was sampled based on that TSC. 
> Or is that not working for some reason?

I guess it is not working like that, but perf tools would probably need
special rules to sort the events because the they would break the rules of
PERF_RECORD_FINISHED_ROUND, wouldn't they?

Re: [PATCH 8/9] perf intel-pt: Update documentation about itrace G and L options

[Andi Kleen]

> > 
> > On Skylake/Goldmont the PEBS event contains the TSC and the time stamp reported by
> > perf should report the time the event was sampled based on that TSC. 
> > Or is that not working for some reason?
> 
> I guess it is not working like that, but perf tools would probably need
> special rules to sort the events because the they would break the rules of
> PERF_RECORD_FINISHED_ROUND, wouldn't they?

Yes it may violate finished round.

It should not be delayed longer than the next context switch though.

The documentation warning would be still correct, but only on Broadwell.

-Andi

[tip: perf/core] perf intel-pt: Update documentation about using /proc/kcore

[tip-bot2 for Adrian Hunter]

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     6dd912cbadb9f9746a525c74f09c0e36cee13ee2
Gitweb:        https://git.kernel.org/tip/6dd912cbadb9f9746a525c74f09c0e36cee13ee2
Author:        Adrian Hunter <adrian.hunter@intel.com>
AuthorDate:    Wed, 29 Apr 2020 18:07:51 +03:00
Committer:     Arnaldo Carvalho de Melo <acme@redhat.com>
CommitterDate: Tue, 05 May 2020 16:35:30 -03:00

perf intel-pt: Update documentation about using /proc/kcore

Update documentation to reflect the advent of the --kcore option for
'perf record'.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lore.kernel.org/lkml/20200429150751.12570-10-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-intel-pt.txt | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index 782eb8a..eb8b7d4 100644
--- a/tools/perf/Documentation/perf-intel-pt.txt
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -69,22 +69,22 @@ And profiled with 'perf report' e.g.
 To also trace kernel space presents a problem, namely kernel self-modifying
 code.  A fairly good kernel image is available in /proc/kcore but to get an
 accurate image a copy of /proc/kcore needs to be made under the same conditions
-as the data capture.  A script perf-with-kcore can do that, but beware that the
-script makes use of 'sudo' to copy /proc/kcore.  If you have perf installed
-locally from the source tree you can do:
+as the data capture. 'perf record' can make a copy of /proc/kcore if the option
+--kcore is used, but access to /proc/kcore is restricted e.g.
 
-	~/libexec/perf-core/perf-with-kcore record pt_ls -e intel_pt// -- ls
+	sudo perf record -o pt_ls --kcore -e intel_pt// -- ls
 
-which will create a directory named 'pt_ls' and put the perf.data file and
-copies of /proc/kcore, /proc/kallsyms and /proc/modules into it.  Then to use
-'perf report' becomes:
+which will create a directory named 'pt_ls' and put the perf.data file (named
+simply 'data') and copies of /proc/kcore, /proc/kallsyms and /proc/modules into
+it.  The other tools understand the directory format, so to use 'perf report'
+becomes:
 
-	~/libexec/perf-core/perf-with-kcore report pt_ls
+	sudo perf report -i pt_ls
 
 Because samples are synthesized after-the-fact, the sampling period can be
 selected for reporting. e.g. sample every microsecond
 
-	~/libexec/perf-core/perf-with-kcore report pt_ls --itrace=i1usge
+	sudo perf report pt_ls --itrace=i1usge
 
 See the sections below for more information about the --itrace option.
 

[tip: perf/core] perf intel-pt: Update documentation about itrace G and L options

[tip-bot2 for Adrian Hunter]

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     43358d9dfb250842383cddad816a7538548a5070
Gitweb:        https://git.kernel.org/tip/43358d9dfb250842383cddad816a7538548a5070
Author:        Adrian Hunter <adrian.hunter@intel.com>
AuthorDate:    Wed, 29 Apr 2020 18:07:50 +03:00
Committer:     Arnaldo Carvalho de Melo <acme@redhat.com>
CommitterDate: Tue, 05 May 2020 16:35:30 -03:00

perf intel-pt: Update documentation about itrace G and L options

Provide a little more information about the new G and L options,
particularly the issue with large PEBs.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lore.kernel.org/lkml/20200429150751.12570-9-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/itrace.txt        |  4 ++-
 tools/perf/Documentation/perf-intel-pt.txt | 35 +++++++++++++++++++++-
 2 files changed, 39 insertions(+)

diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index 0326050..2714847 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -33,6 +33,10 @@
 	Also the number of last branch entries (default 64, max. 1024) for
 	instructions or transactions events can be specified.
 
+	Similar to options g and l, size may also be specified for options G and L.
+	On x86, note that G and L work poorly when data has been recorded with
+	large PEBS. Refer linkperf:perf-intel-pt[1] man page for details.
+
 	It is also possible to skip events generated (instructions, branches, transactions,
 	ptwrite, power) at the beginning. This is useful to ignore initialization code.
 
diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index 456fdcb..782eb8a 100644
--- a/tools/perf/Documentation/perf-intel-pt.txt
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -821,7 +821,9 @@ The letters are:
 	e	synthesize tracing error events
 	d	create a debug log
 	g	synthesize a call chain (use with i or x)
+	G	synthesize a call chain on existing event records
 	l	synthesize last branch entries (use with i or x)
+	L	synthesize last branch entries on existing event records
 	s	skip initial number of events
 
 "Instructions" events look like they were recorded by "perf record -e
@@ -912,6 +914,39 @@ transactions events can be specified. e.g.
 Note that last branch entries are cleared for each sample, so there is no overlap
 from one sample to the next.
 
+The G and L options are designed in particular for sample mode, and work much
+like g and l but add call chain and branch stack to the other selected events
+instead of synthesized events. For example, to record branch-misses events for
+'ls' and then add a call chain derived from the Intel PT trace:
+
+	perf record --aux-sample -e '{intel_pt//u,branch-misses:u}' -- ls
+	perf report --itrace=Ge
+
+Although in fact G is a default for perf report, so that is the same as just:
+
+	perf report
+
+One caveat with the G and L options is that they work poorly with "Large PEBS".
+Large PEBS means PEBS records will be accumulated by hardware and the written
+into the event buffer in one go.  That reduces interrupts, but can give very
+late timestamps.  Because the Intel PT trace is synchronized by timestamps,
+the PEBS events do not match the trace.  Currently, Large PEBS is used only in
+certain circumstances:
+	- hardware supports it
+	- PEBS is used
+	- event period is specified, instead of frequency
+	- the sample type is limited to the following flags:
+		PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR |
+		PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID |
+		PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER |
+		PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR |
+		PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER |
+		PERF_SAMPLE_PERIOD (and sometimes) | PERF_SAMPLE_TIME
+Because Intel PT sample mode uses a different sample type to the list above,
+Large PEBS is not used with Intel PT sample mode. To avoid Large PEBS in other
+cases, avoid specifying the event period i.e. avoid the 'perf record' -c option,
+--count option, or 'period' config term.
+
 To disable trace decoding entirely, use the option --no-itrace.
 
 It is also possible to skip events generated (instructions, branches, transactions)

[tip: perf/core] perf intel-pt: Add support for synthesizing branch stacks for regular events

[tip-bot2 for Adrian Hunter]

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     f0a0251cee800bf90cff92ecfaf4a4d4c9c493b2
Gitweb:        https://git.kernel.org/tip/f0a0251cee800bf90cff92ecfaf4a4d4c9c493b2
Author:        Adrian Hunter <adrian.hunter@intel.com>
AuthorDate:    Wed, 29 Apr 2020 18:07:49 +03:00
Committer:     Arnaldo Carvalho de Melo <acme@redhat.com>
CommitterDate: Tue, 05 May 2020 16:35:30 -03:00

perf intel-pt: Add support for synthesizing branch stacks for regular events

Use the new thread_stack__br_sample_late() function to create a thread
stack for regular events.

Example:

 # perf record --kcore --aux-sample -e '{intel_pt//,cycles:ppp}' -c 10000 uname
 Linux
 [ perf record: Woken up 2 times to write data ]
 [ perf record: Captured and wrote 0.743 MB perf.data ]
 # perf report --itrace=Le --stdio | head -30 | tail -18

 # Samples: 11K of event 'cycles:ppp'
 # Event count (approx.): 11648
 #
 # Overhead  Command  Source Shared Object  Source Symbol                 Target Symbol                 Basic Block Cycles
 # ........  .......  ....................  ............................  ............................  ..................
 #
      5.49%  uname    libc-2.30.so          [.] _dl_addr                  [.] _dl_addr                  -
      2.41%  uname    ld-2.30.so            [.] _dl_relocate_object       [.] _dl_relocate_object       -
      2.31%  uname    ld-2.30.so            [.] do_lookup_x               [.] do_lookup_x               -
      2.17%  uname    [kernel.kallsyms]     [k] unmap_page_range          [k] unmap_page_range          -
      2.05%  uname    ld-2.30.so            [k] _dl_start                 [k] _dl_start                 -
      1.97%  uname    ld-2.30.so            [.] _dl_lookup_symbol_x       [.] _dl_lookup_symbol_x       -
      1.94%  uname    [kernel.kallsyms]     [k] filemap_map_pages         [k] filemap_map_pages         -
      1.60%  uname    [kernel.kallsyms]     [k] __handle_mm_fault         [k] __handle_mm_fault         -
      1.44%  uname    [kernel.kallsyms]     [k] page_add_file_rmap        [k] page_add_file_rmap        -
      1.12%  uname    [kernel.kallsyms]     [k] vma_interval_tree_insert  [k] vma_interval_tree_insert  -
      0.94%  uname    [kernel.kallsyms]     [k] perf_iterate_ctx          [k] perf_iterate_ctx          -

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lore.kernel.org/lkml/20200429150751.12570-8-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt.c | 73 +++++++++++++++++++++++++++++++++----
 1 file changed, 66 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 03b7690..59811b3 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -72,6 +72,7 @@ struct intel_pt {
 	bool use_thread_stack;
 	bool callstack;
 	unsigned int br_stack_sz;
+	unsigned int br_stack_sz_plus;
 	int have_sched_switch;
 	u32 pmu_type;
 	u64 kernel_start;
@@ -130,6 +131,7 @@ struct intel_pt {
 	unsigned int range_cnt;
 
 	struct ip_callchain *chain;
+	struct branch_stack *br_stack;
 };
 
 enum switch_state {
@@ -911,6 +913,44 @@ static void intel_pt_add_callchain(struct intel_pt *pt,
 	sample->callchain = pt->chain;
 }
 
+static struct branch_stack *intel_pt_alloc_br_stack(struct intel_pt *pt)
+{
+	size_t sz = sizeof(struct branch_stack);
+
+	sz += pt->br_stack_sz * sizeof(struct branch_entry);
+	return zalloc(sz);
+}
+
+static int intel_pt_br_stack_init(struct intel_pt *pt)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(pt->session->evlist, evsel) {
+		if (!(evsel->core.attr.sample_type & PERF_SAMPLE_BRANCH_STACK))
+			evsel->synth_sample_type |= PERF_SAMPLE_BRANCH_STACK;
+	}
+
+	pt->br_stack = intel_pt_alloc_br_stack(pt);
+	if (!pt->br_stack)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void intel_pt_add_br_stack(struct intel_pt *pt,
+				  struct perf_sample *sample)
+{
+	struct thread *thread = machine__findnew_thread(pt->machine,
+							sample->pid,
+							sample->tid);
+
+	thread_stack__br_sample_late(thread, sample->cpu, pt->br_stack,
+				     pt->br_stack_sz, sample->ip,
+				     pt->kernel_start);
+
+	sample->branch_stack = pt->br_stack;
+}
+
 static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 						   unsigned int queue_nr)
 {
@@ -929,10 +969,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 	}
 
 	if (pt->synth_opts.last_branch) {
-		size_t sz = sizeof(struct branch_stack);
-
-		sz += pt->br_stack_sz * sizeof(struct branch_entry);
-		ptq->last_branch = zalloc(sz);
+		ptq->last_branch = intel_pt_alloc_br_stack(pt);
 		if (!ptq->last_branch)
 			goto out_free;
 	}
@@ -1963,7 +2000,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 		thread_stack__event(ptq->thread, ptq->cpu, ptq->flags,
 				    state->from_ip, state->to_ip, ptq->insn_len,
 				    state->trace_nr, pt->callstack,
-				    pt->br_stack_sz,
+				    pt->br_stack_sz_plus,
 				    pt->mispred_all);
 	} else {
 		thread_stack__set_trace_nr(ptq->thread, ptq->cpu, state->trace_nr);
@@ -2609,6 +2646,8 @@ static int intel_pt_process_event(struct perf_session *session,
 	if (event->header.type == PERF_RECORD_SAMPLE) {
 		if (pt->synth_opts.add_callchain && !sample->callchain)
 			intel_pt_add_callchain(pt, sample);
+		if (pt->synth_opts.add_last_branch && !sample->branch_stack)
+			intel_pt_add_br_stack(pt, sample);
 	}
 
 	if (event->header.type == PERF_RECORD_AUX &&
@@ -3370,13 +3409,33 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 			goto err_delete_thread;
 	}
 
-	if (pt->synth_opts.last_branch)
+	if (pt->synth_opts.last_branch || pt->synth_opts.add_last_branch) {
 		pt->br_stack_sz = pt->synth_opts.last_branch_sz;
+		pt->br_stack_sz_plus = pt->br_stack_sz;
+	}
+
+	if (pt->synth_opts.add_last_branch) {
+		err = intel_pt_br_stack_init(pt);
+		if (err)
+			goto err_delete_thread;
+		/*
+		 * Additional branch stack size to cater for tracing from the
+		 * actual sample ip to where the sample time is recorded.
+		 * Measured at about 200 branches, but generously set to 1024.
+		 * If kernel space is not being traced, then add just 1 for the
+		 * branch to kernel space.
+		 */
+		if (intel_pt_tracing_kernel(pt))
+			pt->br_stack_sz_plus += 1024;
+		else
+			pt->br_stack_sz_plus += 1;
+	}
 
 	pt->use_thread_stack = pt->synth_opts.callchain ||
 			       pt->synth_opts.add_callchain ||
 			       pt->synth_opts.thread_stack ||
-			       pt->synth_opts.last_branch;
+			       pt->synth_opts.last_branch ||
+			       pt->synth_opts.add_last_branch;
 
 	pt->callstack = pt->synth_opts.callchain ||
 			pt->synth_opts.add_callchain ||

[tip: perf/core] perf thread-stack: Add thread_stack__br_sample_late()

[tip-bot2 for Adrian Hunter]

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     3749e0bbdef24efbf1698bf0dbd9575fddb9ed22
Gitweb:        https://git.kernel.org/tip/3749e0bbdef24efbf1698bf0dbd9575fddb9ed22
Author:        Adrian Hunter <adrian.hunter@intel.com>
AuthorDate:    Wed, 29 Apr 2020 18:07:48 +03:00
Committer:     Arnaldo Carvalho de Melo <acme@redhat.com>
CommitterDate: Tue, 05 May 2020 16:35:29 -03:00

perf thread-stack: Add thread_stack__br_sample_late()

Add a thread stack function to create a branch stack for hardware events
where the sample records get created some time after the event occurred.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lore.kernel.org/lkml/20200429150751.12570-7-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/thread-stack.c | 104 ++++++++++++++++++++++++++++++++-
 tools/perf/util/thread-stack.h |   3 +-
 2 files changed, 107 insertions(+)

diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 7969883..1b992bb 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -645,6 +645,110 @@ void thread_stack__br_sample(struct thread *thread, int cpu,
 	}
 }
 
+/* Start of user space branch entries */
+static bool us_start(struct branch_entry *be, u64 kernel_start, bool *start)
+{
+	if (!*start)
+		*start = be->to && be->to < kernel_start;
+
+	return *start;
+}
+
+/*
+ * Start of branch entries after the ip fell in between 2 branches, or user
+ * space branch entries.
+ */
+static bool ks_start(struct branch_entry *be, u64 sample_ip, u64 kernel_start,
+		     bool *start, struct branch_entry *nb)
+{
+	if (!*start) {
+		*start = (nb && sample_ip >= be->to && sample_ip <= nb->from) ||
+			 be->from < kernel_start ||
+			 (be->to && be->to < kernel_start);
+	}
+
+	return *start;
+}
+
+/*
+ * Hardware sample records, created some time after the event occurred, need to
+ * have subsequent addresses removed from the branch stack.
+ */
+void thread_stack__br_sample_late(struct thread *thread, int cpu,
+				  struct branch_stack *dst, unsigned int sz,
+				  u64 ip, u64 kernel_start)
+{
+	struct thread_stack *ts = thread__stack(thread, cpu);
+	struct branch_entry *d, *s, *spos, *ssz;
+	struct branch_stack *src;
+	unsigned int nr = 0;
+	bool start = false;
+
+	dst->nr = 0;
+
+	if (!ts)
+		return;
+
+	src = ts->br_stack_rb;
+	if (!src->nr)
+		return;
+
+	spos = &src->entries[ts->br_stack_pos];
+	ssz  = &src->entries[ts->br_stack_sz];
+
+	d = &dst->entries[0];
+	s = spos;
+
+	if (ip < kernel_start) {
+		/*
+		 * User space sample: start copying branch entries when the
+		 * branch is in user space.
+		 */
+		for (s = spos; s < ssz && nr < sz; s++) {
+			if (us_start(s, kernel_start, &start)) {
+				*d++ = *s;
+				nr += 1;
+			}
+		}
+
+		if (src->nr >= ts->br_stack_sz) {
+			for (s = &src->entries[0]; s < spos && nr < sz; s++) {
+				if (us_start(s, kernel_start, &start)) {
+					*d++ = *s;
+					nr += 1;
+				}
+			}
+		}
+	} else {
+		struct branch_entry *nb = NULL;
+
+		/*
+		 * Kernel space sample: start copying branch entries when the ip
+		 * falls in between 2 branches (or the branch is in user space
+		 * because then the start must have been missed).
+		 */
+		for (s = spos; s < ssz && nr < sz; s++) {
+			if (ks_start(s, ip, kernel_start, &start, nb)) {
+				*d++ = *s;
+				nr += 1;
+			}
+			nb = s;
+		}
+
+		if (src->nr >= ts->br_stack_sz) {
+			for (s = &src->entries[0]; s < spos && nr < sz; s++) {
+				if (ks_start(s, ip, kernel_start, &start, nb)) {
+					*d++ = *s;
+					nr += 1;
+				}
+				nb = s;
+			}
+		}
+	}
+
+	dst->nr = nr;
+}
+
 struct call_return_processor *
 call_return_processor__new(int (*process)(struct call_return *cr, u64 *parent_db_id, void *data),
 			   void *data)
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index c279a0c..3bc47a4 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -91,6 +91,9 @@ void thread_stack__sample_late(struct thread *thread, int cpu,
 			       u64 kernel_start);
 void thread_stack__br_sample(struct thread *thread, int cpu,
 			     struct branch_stack *dst, unsigned int sz);
+void thread_stack__br_sample_late(struct thread *thread, int cpu,
+				  struct branch_stack *dst, unsigned int sz,
+				  u64 sample_ip, u64 kernel_start);
 int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
 size_t thread_stack__depth(struct thread *thread, int cpu);

[tip: perf/core] perf auxtrace: Add option to synthesize branch stack for regular events

[tip-bot2 for Adrian Hunter]

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     ec90e42ce5142c4ed2a0061fe23bd4495428c52b
Gitweb:        https://git.kernel.org/tip/ec90e42ce5142c4ed2a0061fe23bd4495428c52b
Author:        Adrian Hunter <adrian.hunter@intel.com>
AuthorDate:    Wed, 29 Apr 2020 18:07:46 +03:00
Committer:     Arnaldo Carvalho de Melo <acme@redhat.com>
CommitterDate: Tue, 05 May 2020 16:35:29 -03:00

perf auxtrace: Add option to synthesize branch stack for regular events

There is an existing option to synthesize branch stacks for synthesized
events. Add a new option to synthesize branch stacks for regular events.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lore.kernel.org/lkml/20200429150751.12570-5-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/itrace.txt | 1 +
 tools/perf/builtin-inject.c         | 3 ++-
 tools/perf/builtin-report.c         | 5 +++--
 tools/perf/util/auxtrace.c          | 6 +++++-
 tools/perf/util/auxtrace.h          | 2 ++
 tools/perf/util/s390-cpumsf.c       | 3 ++-
 6 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index 671e154..0326050 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -12,6 +12,7 @@
 		g	synthesize a call chain (use with i or x)
 		G	synthesize a call chain on existing event records
 		l	synthesize last branch entries (use with i or x)
+		L	synthesize last branch entries on existing event records
 		s       skip initial number of events
 
 	The default is all events i.e. the same as --itrace=ibxwpe,
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 7e124a7..7c4403c 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -684,7 +684,8 @@ static int __cmd_inject(struct perf_inject *inject)
 
 			perf_header__clear_feat(&session->header,
 						HEADER_AUXTRACE);
-			if (inject->itrace_synth_opts.last_branch)
+			if (inject->itrace_synth_opts.last_branch ||
+			    inject->itrace_synth_opts.add_last_branch)
 				perf_header__set_feat(&session->header,
 						      HEADER_BRANCH_STACK);
 			evsel = perf_evlist__id2evsel_strict(session->evlist,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 7da1342..0eea667 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -349,7 +349,8 @@ static int report__setup_sample_type(struct report *rep)
 	     !session->itrace_synth_opts->set))
 		sample_type |= PERF_SAMPLE_CALLCHAIN;
 
-	if (session->itrace_synth_opts->last_branch)
+	if (session->itrace_synth_opts->last_branch ||
+	    session->itrace_synth_opts->add_last_branch)
 		sample_type |= PERF_SAMPLE_BRANCH_STACK;
 
 	if (!is_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
@@ -1393,7 +1394,7 @@ repeat:
 		goto error;
 	}
 
-	if (itrace_synth_opts.last_branch)
+	if (itrace_synth_opts.last_branch || itrace_synth_opts.add_last_branch)
 		has_br_stack = true;
 
 	if (has_br_stack && branch_call_mode)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index ac6e099..83ea7ca 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1464,8 +1464,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 				synth_opts->callchain_sz = val;
 			}
 			break;
+		case 'L':
 		case 'l':
-			synth_opts->last_branch = true;
+			if (p[-1] == 'L')
+				synth_opts->add_last_branch = true;
+			else
+				synth_opts->last_branch = true;
 			synth_opts->last_branch_sz =
 					PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
 			while (*p == ' ' || *p == ',')
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index dd8a4ff..0220a2e 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -77,6 +77,7 @@ enum itrace_period_type {
  * @add_callchain: add callchain to existing event records
  * @thread_stack: feed branches to the thread_stack
  * @last_branch: add branch context to 'instruction' events
+ * @add_last_branch: add branch context to existing event records
  * @callchain_sz: maximum callchain size
  * @last_branch_sz: branch context size
  * @period: 'instructions' events period
@@ -105,6 +106,7 @@ struct itrace_synth_opts {
 	bool			add_callchain;
 	bool			thread_stack;
 	bool			last_branch;
+	bool			add_last_branch;
 	unsigned int		callchain_sz;
 	unsigned int		last_branch_sz;
 	unsigned long long	period;
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index 38a9428..f886199 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -1079,7 +1079,8 @@ static bool check_auxtrace_itrace(struct itrace_synth_opts *itops)
 		itops->pwr_events || itops->errors ||
 		itops->dont_decode || itops->calls || itops->returns ||
 		itops->callchain || itops->thread_stack ||
-		itops->last_branch || itops->add_callchain;
+		itops->last_branch || itops->add_callchain ||
+		itops->add_last_branch;
 	if (!ison)
 		return true;
 	pr_err("Unsupported --itrace options specified\n");

[tip: perf/core] perf evsel: Add support for synthesized branch stack sample type

[tip-bot2 for Adrian Hunter]

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     6cd2cbfc6865589c64ac37ec48937e93725622f1
Gitweb:        https://git.kernel.org/tip/6cd2cbfc6865589c64ac37ec48937e93725622f1
Author:        Adrian Hunter <adrian.hunter@intel.com>
AuthorDate:    Wed, 29 Apr 2020 18:07:47 +03:00
Committer:     Arnaldo Carvalho de Melo <acme@redhat.com>
CommitterDate: Tue, 05 May 2020 16:35:29 -03:00

perf evsel: Add support for synthesized branch stack sample type

Allow for a synthesized branch stack to be added to samples. As with
synthesized call chains, the sample type cannot be changed because it is
needed to continue to parse events. So add and use helper function
evsel__has_br_stack() to indicate a branch stack, whether original or
synthesized.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lore.kernel.org/lkml/20200429150751.12570-6-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.h   | 10 ++++++++++
 tools/perf/util/session.c |  2 +-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index a463bc6..bf999e3 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -417,6 +417,16 @@ static inline bool evsel__has_callchain(const struct evsel *evsel)
 	       evsel->synth_sample_type & PERF_SAMPLE_CALLCHAIN;
 }
 
+static inline bool evsel__has_br_stack(const struct evsel *evsel)
+{
+	/*
+	 * For reporting purposes, an evsel sample can have a recorded branch
+	 * stack or a branch stack synthesized from AUX area data.
+	 */
+	return evsel->core.attr.sample_type & PERF_SAMPLE_BRANCH_STACK ||
+	       evsel->synth_sample_type & PERF_SAMPLE_BRANCH_STACK;
+}
+
 struct perf_env *perf_evsel__env(struct evsel *evsel);
 
 int perf_evsel__store_ids(struct evsel *evsel, struct evlist *evlist);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0b0bfe5..2b5a08a 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1243,7 +1243,7 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 	if (evsel__has_callchain(evsel))
 		callchain__printf(evsel, sample);
 
-	if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+	if (evsel__has_br_stack(evsel))
 		branch_stack__printf(sample, perf_evsel__has_branch_callstack(evsel));
 
 	if (sample_type & PERF_SAMPLE_REGS_USER)

[tip: perf/core] perf thread-stack: Add branch stack support

[tip-bot2 for Adrian Hunter]

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     86d67180b920d178ae1c2923f50a0759d6ce1a10
Gitweb:        https://git.kernel.org/tip/86d67180b920d178ae1c2923f50a0759d6ce1a10
Author:        Adrian Hunter <adrian.hunter@intel.com>
AuthorDate:    Wed, 29 Apr 2020 18:07:43 +03:00
Committer:     Arnaldo Carvalho de Melo <acme@redhat.com>
CommitterDate: Tue, 05 May 2020 16:35:29 -03:00

perf thread-stack: Add branch stack support

Intel PT already has support for creating branch stacks for each context
(per-cpu or per-thread). In the more common per-cpu case, the branch stack
is not separated for different threads, instead being cleared in between
each sample.

That approach will not work very well for adding branch stacks to
regular events. The branch stacks really need to be accumulated
separately for each thread.

As a start to accomplishing that, this patch adds support for putting
branch stack support into the thread-stack. The advantages are:

1. the branches are accumulated separately for each thread
2. the branch stack is cleared only in between continuous traces

This helps pave the way for adding branch stacks to regular events, not
just synthesized events as at present.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lore.kernel.org/lkml/20200429150751.12570-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-bts.c    |   2 +-
 tools/perf/util/intel-pt.c     |   2 +-
 tools/perf/util/thread-stack.c | 113 ++++++++++++++++++++++++++++----
 tools/perf/util/thread-stack.h |   5 +-
 4 files changed, 108 insertions(+), 14 deletions(-)

diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 059e1c8..506112f 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -432,7 +432,7 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
 					    le64_to_cpu(branch->from),
 					    le64_to_cpu(branch->to),
 					    btsq->intel_pt_insn.length,
-					    buffer->buffer_nr + 1);
+					    buffer->buffer_nr + 1, true, 0, 0);
 		if (filter && !(filter & btsq->sample_flags))
 			continue;
 		err = intel_bts_synth_branch_sample(btsq, branch);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 30e1ee6..bdb8447 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2033,7 +2033,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	    pt->synth_opts.thread_stack)
 		thread_stack__event(ptq->thread, ptq->cpu, ptq->flags, state->from_ip,
 				    state->to_ip, ptq->insn_len,
-				    state->trace_nr);
+				    state->trace_nr, true, 0, 0);
 	else
 		thread_stack__set_trace_nr(ptq->thread, ptq->cpu, state->trace_nr);
 
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 83f6c83..7969883 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -80,6 +80,10 @@ struct thread_stack_entry {
  * @comm: current comm
  * @arr_sz: size of array if this is the first element of an array
  * @rstate: used to detect retpolines
+ * @br_stack_rb: branch stack (ring buffer)
+ * @br_stack_sz: maximum branch stack size
+ * @br_stack_pos: current position in @br_stack_rb
+ * @mispred_all: mark all branches as mispredicted
  */
 struct thread_stack {
 	struct thread_stack_entry *stack;
@@ -95,6 +99,10 @@ struct thread_stack {
 	struct comm *comm;
 	unsigned int arr_sz;
 	enum retpoline_state_t rstate;
+	struct branch_stack *br_stack_rb;
+	unsigned int br_stack_sz;
+	unsigned int br_stack_pos;
+	bool mispred_all;
 };
 
 /*
@@ -126,13 +134,26 @@ static int thread_stack__grow(struct thread_stack *ts)
 }
 
 static int thread_stack__init(struct thread_stack *ts, struct thread *thread,
-			      struct call_return_processor *crp)
+			      struct call_return_processor *crp,
+			      bool callstack, unsigned int br_stack_sz)
 {
 	int err;
 
-	err = thread_stack__grow(ts);
-	if (err)
-		return err;
+	if (callstack) {
+		err = thread_stack__grow(ts);
+		if (err)
+			return err;
+	}
+
+	if (br_stack_sz) {
+		size_t sz = sizeof(struct branch_stack);
+
+		sz += br_stack_sz * sizeof(struct branch_entry);
+		ts->br_stack_rb = zalloc(sz);
+		if (!ts->br_stack_rb)
+			return -ENOMEM;
+		ts->br_stack_sz = br_stack_sz;
+	}
 
 	if (thread->maps && thread->maps->machine) {
 		struct machine *machine = thread->maps->machine;
@@ -150,7 +171,9 @@ static int thread_stack__init(struct thread_stack *ts, struct thread *thread,
 }
 
 static struct thread_stack *thread_stack__new(struct thread *thread, int cpu,
-					      struct call_return_processor *crp)
+					      struct call_return_processor *crp,
+					      bool callstack,
+					      unsigned int br_stack_sz)
 {
 	struct thread_stack *ts = thread->ts, *new_ts;
 	unsigned int old_sz = ts ? ts->arr_sz : 0;
@@ -176,7 +199,7 @@ static struct thread_stack *thread_stack__new(struct thread *thread, int cpu,
 		ts += cpu;
 
 	if (!ts->stack &&
-	    thread_stack__init(ts, thread, crp))
+	    thread_stack__init(ts, thread, crp, callstack, br_stack_sz))
 		return NULL;
 
 	return ts;
@@ -319,6 +342,9 @@ static int __thread_stack__flush(struct thread *thread, struct thread_stack *ts)
 
 	if (!crp) {
 		ts->cnt = 0;
+		ts->br_stack_pos = 0;
+		if (ts->br_stack_rb)
+			ts->br_stack_rb->nr = 0;
 		return 0;
 	}
 
@@ -353,8 +379,33 @@ int thread_stack__flush(struct thread *thread)
 	return err;
 }
 
+static void thread_stack__update_br_stack(struct thread_stack *ts, u32 flags,
+					  u64 from_ip, u64 to_ip)
+{
+	struct branch_stack *bs = ts->br_stack_rb;
+	struct branch_entry *be;
+
+	if (!ts->br_stack_pos)
+		ts->br_stack_pos = ts->br_stack_sz;
+
+	ts->br_stack_pos -= 1;
+
+	be              = &bs->entries[ts->br_stack_pos];
+	be->from        = from_ip;
+	be->to          = to_ip;
+	be->flags.value = 0;
+	be->flags.abort = !!(flags & PERF_IP_FLAG_TX_ABORT);
+	be->flags.in_tx = !!(flags & PERF_IP_FLAG_IN_TX);
+	/* No support for mispredict */
+	be->flags.mispred = ts->mispred_all;
+
+	if (bs->nr < ts->br_stack_sz)
+		bs->nr += 1;
+}
+
 int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
-			u64 to_ip, u16 insn_len, u64 trace_nr)
+			u64 to_ip, u16 insn_len, u64 trace_nr, bool callstack,
+			unsigned int br_stack_sz, bool mispred_all)
 {
 	struct thread_stack *ts = thread__stack(thread, cpu);
 
@@ -362,12 +413,13 @@ int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
 		return -EINVAL;
 
 	if (!ts) {
-		ts = thread_stack__new(thread, cpu, NULL);
+		ts = thread_stack__new(thread, cpu, NULL, callstack, br_stack_sz);
 		if (!ts) {
 			pr_warning("Out of memory: no thread stack\n");
 			return -ENOMEM;
 		}
 		ts->trace_nr = trace_nr;
+		ts->mispred_all = mispred_all;
 	}
 
 	/*
@@ -381,8 +433,14 @@ int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
 		ts->trace_nr = trace_nr;
 	}
 
-	/* Stop here if thread_stack__process() is in use */
-	if (ts->crp)
+	if (br_stack_sz)
+		thread_stack__update_br_stack(ts, flags, from_ip, to_ip);
+
+	/*
+	 * Stop here if thread_stack__process() is in use, or not recording call
+	 * stack.
+	 */
+	if (ts->crp || !callstack)
 		return 0;
 
 	if (flags & PERF_IP_FLAG_CALL) {
@@ -430,6 +488,7 @@ static void __thread_stack__free(struct thread *thread, struct thread_stack *ts)
 {
 	__thread_stack__flush(thread, ts);
 	zfree(&ts->stack);
+	zfree(&ts->br_stack_rb);
 }
 
 static void thread_stack__reset(struct thread *thread, struct thread_stack *ts)
@@ -554,6 +613,38 @@ out:
 	}
 }
 
+void thread_stack__br_sample(struct thread *thread, int cpu,
+			     struct branch_stack *dst, unsigned int sz)
+{
+	struct thread_stack *ts = thread__stack(thread, cpu);
+	const size_t bsz = sizeof(struct branch_entry);
+	struct branch_stack *src;
+	struct branch_entry *be;
+	unsigned int nr;
+
+	dst->nr = 0;
+
+	if (!ts)
+		return;
+
+	src = ts->br_stack_rb;
+	if (!src->nr)
+		return;
+
+	dst->nr = min((unsigned int)src->nr, sz);
+
+	be = &dst->entries[0];
+	nr = min(ts->br_stack_sz - ts->br_stack_pos, (unsigned int)dst->nr);
+	memcpy(be, &src->entries[ts->br_stack_pos], bsz * nr);
+
+	if (src->nr >= ts->br_stack_sz) {
+		sz -= nr;
+		be = &dst->entries[nr];
+		nr = min(ts->br_stack_pos, sz);
+		memcpy(be, &src->entries[0], bsz * ts->br_stack_pos);
+	}
+}
+
 struct call_return_processor *
 call_return_processor__new(int (*process)(struct call_return *cr, u64 *parent_db_id, void *data),
 			   void *data)
@@ -921,7 +1012,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 	}
 
 	if (!ts) {
-		ts = thread_stack__new(thread, sample->cpu, crp);
+		ts = thread_stack__new(thread, sample->cpu, crp, true, 0);
 		if (!ts)
 			return -ENOMEM;
 		ts->comm = comm;
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index 8962ddc..c279a0c 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -81,13 +81,16 @@ struct call_return_processor {
 };
 
 int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
-			u64 to_ip, u16 insn_len, u64 trace_nr);
+			u64 to_ip, u16 insn_len, u64 trace_nr, bool callstack,
+			unsigned int br_stack_sz, bool mispred_all);
 void thread_stack__set_trace_nr(struct thread *thread, int cpu, u64 trace_nr);
 void thread_stack__sample(struct thread *thread, int cpu, struct ip_callchain *chain,
 			  size_t sz, u64 ip, u64 kernel_start);
 void thread_stack__sample_late(struct thread *thread, int cpu,
 			       struct ip_callchain *chain, size_t sz, u64 ip,
 			       u64 kernel_start);
+void thread_stack__br_sample(struct thread *thread, int cpu,
+			     struct branch_stack *dst, unsigned int sz);
 int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
 size_t thread_stack__depth(struct thread *thread, int cpu);

[tip: perf/core] perf intel-pt: Consolidate thread-stack use condition

[tip-bot2 for Adrian Hunter]

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     1ef998ff1823c8b5b3f7d103ec3971d7baaf677b
Gitweb:        https://git.kernel.org/tip/1ef998ff1823c8b5b3f7d103ec3971d7baaf677b
Author:        Adrian Hunter <adrian.hunter@intel.com>
AuthorDate:    Wed, 29 Apr 2020 18:07:44 +03:00
Committer:     Arnaldo Carvalho de Melo <acme@redhat.com>
CommitterDate: Tue, 05 May 2020 16:35:29 -03:00

perf intel-pt: Consolidate thread-stack use condition

The components of the condition do not change, so consolidate them in
one variable.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lore.kernel.org/lkml/20200429150751.12570-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index bdb8447..b3c4527 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -69,6 +69,7 @@ struct intel_pt {
 	bool est_tsc;
 	bool sync_switch;
 	bool mispred_all;
+	bool use_thread_stack;
 	int have_sched_switch;
 	u32 pmu_type;
 	u64 kernel_start;
@@ -2029,8 +2030,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	if (!(state->type & INTEL_PT_BRANCH))
 		return 0;
 
-	if (pt->synth_opts.callchain || pt->synth_opts.add_callchain ||
-	    pt->synth_opts.thread_stack)
+	if (pt->use_thread_stack)
 		thread_stack__event(ptq->thread, ptq->cpu, ptq->flags, state->from_ip,
 				    state->to_ip, ptq->insn_len,
 				    state->trace_nr, true, 0, 0);
@@ -3441,6 +3441,10 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 			goto err_delete_thread;
 	}
 
+	pt->use_thread_stack = pt->synth_opts.callchain ||
+			       pt->synth_opts.add_callchain ||
+			       pt->synth_opts.thread_stack;
+
 	err = intel_pt_synth_events(pt, session);
 	if (err)
 		goto err_delete_thread;

[tip: perf/core] perf intel-pt: Change branch stack support to use thread-stacks

[tip-bot2 for Adrian Hunter]

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     cf888e08a030b7430889d0c5c804508c09dad843
Gitweb:        https://git.kernel.org/tip/cf888e08a030b7430889d0c5c804508c09dad843
Author:        Adrian Hunter <adrian.hunter@intel.com>
AuthorDate:    Wed, 29 Apr 2020 18:07:45 +03:00
Committer:     Arnaldo Carvalho de Melo <acme@redhat.com>
CommitterDate: Tue, 05 May 2020 16:35:29 -03:00

perf intel-pt: Change branch stack support to use thread-stacks

Change Intel PT's branch stack support to use thread stacks. The
advantages of using branch stack support from the thread-stack are:

1. the branches are accumulated separately for each thread
2. the branch stack is cleared only in between continuous traces

This helps pave the way for adding branch stacks to regular events, not
just synthesized events as at present.

While the 2 approaches are not identical, in simple cases the results
can be identical e.g.

  Before:

    # perf record --kcore -e intel_pt// uname
    # perf script --itrace=i10usl -F+brstacksym,+addr,+flags > cmp1.txt

  After:

    # perf script --itrace=i10usl -F+brstacksym,+addr,+flags > cmp2.txt
    # diff -s cmp1.txt cmp2.txt
    Files cmp1.txt and cmp2.txt are identical

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lore.kernel.org/lkml/20200429150751.12570-4-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt.c | 141 +++++++++---------------------------
 1 file changed, 39 insertions(+), 102 deletions(-)

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index b3c4527..03b7690 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -70,6 +70,8 @@ struct intel_pt {
 	bool sync_switch;
 	bool mispred_all;
 	bool use_thread_stack;
+	bool callstack;
+	unsigned int br_stack_sz;
 	int have_sched_switch;
 	u32 pmu_type;
 	u64 kernel_start;
@@ -147,8 +149,6 @@ struct intel_pt_queue {
 	const struct intel_pt_state *state;
 	struct ip_callchain *chain;
 	struct branch_stack *last_branch;
-	struct branch_stack *last_branch_rb;
-	size_t last_branch_pos;
 	union perf_event *event_buf;
 	bool on_heap;
 	bool stop;
@@ -931,14 +931,10 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 	if (pt->synth_opts.last_branch) {
 		size_t sz = sizeof(struct branch_stack);
 
-		sz += pt->synth_opts.last_branch_sz *
-		      sizeof(struct branch_entry);
+		sz += pt->br_stack_sz * sizeof(struct branch_entry);
 		ptq->last_branch = zalloc(sz);
 		if (!ptq->last_branch)
 			goto out_free;
-		ptq->last_branch_rb = zalloc(sz);
-		if (!ptq->last_branch_rb)
-			goto out_free;
 	}
 
 	ptq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
@@ -1007,7 +1003,6 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 out_free:
 	zfree(&ptq->event_buf);
 	zfree(&ptq->last_branch);
-	zfree(&ptq->last_branch_rb);
 	zfree(&ptq->chain);
 	free(ptq);
 	return NULL;
@@ -1023,7 +1018,6 @@ static void intel_pt_free_queue(void *priv)
 	intel_pt_decoder_free(ptq->decoder);
 	zfree(&ptq->event_buf);
 	zfree(&ptq->last_branch);
-	zfree(&ptq->last_branch_rb);
 	zfree(&ptq->chain);
 	free(ptq);
 }
@@ -1191,58 +1185,6 @@ static int intel_pt_setup_queues(struct intel_pt *pt)
 	return 0;
 }
 
-static inline void intel_pt_copy_last_branch_rb(struct intel_pt_queue *ptq)
-{
-	struct branch_stack *bs_src = ptq->last_branch_rb;
-	struct branch_stack *bs_dst = ptq->last_branch;
-	size_t nr = 0;
-
-	bs_dst->nr = bs_src->nr;
-
-	if (!bs_src->nr)
-		return;
-
-	nr = ptq->pt->synth_opts.last_branch_sz - ptq->last_branch_pos;
-	memcpy(&bs_dst->entries[0],
-	       &bs_src->entries[ptq->last_branch_pos],
-	       sizeof(struct branch_entry) * nr);
-
-	if (bs_src->nr >= ptq->pt->synth_opts.last_branch_sz) {
-		memcpy(&bs_dst->entries[nr],
-		       &bs_src->entries[0],
-		       sizeof(struct branch_entry) * ptq->last_branch_pos);
-	}
-}
-
-static inline void intel_pt_reset_last_branch_rb(struct intel_pt_queue *ptq)
-{
-	ptq->last_branch_pos = 0;
-	ptq->last_branch_rb->nr = 0;
-}
-
-static void intel_pt_update_last_branch_rb(struct intel_pt_queue *ptq)
-{
-	const struct intel_pt_state *state = ptq->state;
-	struct branch_stack *bs = ptq->last_branch_rb;
-	struct branch_entry *be;
-
-	if (!ptq->last_branch_pos)
-		ptq->last_branch_pos = ptq->pt->synth_opts.last_branch_sz;
-
-	ptq->last_branch_pos -= 1;
-
-	be              = &bs->entries[ptq->last_branch_pos];
-	be->from        = state->from_ip;
-	be->to          = state->to_ip;
-	be->flags.abort = !!(state->flags & INTEL_PT_ABORT_TX);
-	be->flags.in_tx = !!(state->flags & INTEL_PT_IN_TX);
-	/* No support for mispredict */
-	be->flags.mispred = ptq->pt->mispred_all;
-
-	if (bs->nr < ptq->pt->synth_opts.last_branch_sz)
-		bs->nr += 1;
-}
-
 static inline bool intel_pt_skip_event(struct intel_pt *pt)
 {
 	return pt->synth_opts.initial_skip &&
@@ -1310,9 +1252,9 @@ static inline int intel_pt_opt_inject(struct intel_pt *pt,
 	return intel_pt_inject_event(event, sample, type);
 }
 
-static int intel_pt_deliver_synth_b_event(struct intel_pt *pt,
-					  union perf_event *event,
-					  struct perf_sample *sample, u64 type)
+static int intel_pt_deliver_synth_event(struct intel_pt *pt,
+					union perf_event *event,
+					struct perf_sample *sample, u64 type)
 {
 	int ret;
 
@@ -1372,8 +1314,8 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 		ptq->last_br_cyc_cnt = ptq->ipc_cyc_cnt;
 	}
 
-	return intel_pt_deliver_synth_b_event(pt, event, &sample,
-					      pt->branches_sample_type);
+	return intel_pt_deliver_synth_event(pt, event, &sample,
+					    pt->branches_sample_type);
 }
 
 static void intel_pt_prep_sample(struct intel_pt *pt,
@@ -1391,27 +1333,12 @@ static void intel_pt_prep_sample(struct intel_pt *pt,
 	}
 
 	if (pt->synth_opts.last_branch) {
-		intel_pt_copy_last_branch_rb(ptq);
+		thread_stack__br_sample(ptq->thread, ptq->cpu, ptq->last_branch,
+					pt->br_stack_sz);
 		sample->branch_stack = ptq->last_branch;
 	}
 }
 
-static inline int intel_pt_deliver_synth_event(struct intel_pt *pt,
-					       struct intel_pt_queue *ptq,
-					       union perf_event *event,
-					       struct perf_sample *sample,
-					       u64 type)
-{
-	int ret;
-
-	ret = intel_pt_deliver_synth_b_event(pt, event, sample, type);
-
-	if (pt->synth_opts.last_branch)
-		intel_pt_reset_last_branch_rb(ptq);
-
-	return ret;
-}
-
 static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
@@ -1436,7 +1363,7 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 
 	ptq->last_insn_cnt = ptq->state->tot_insn_cnt;
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->instructions_sample_type);
 }
 
@@ -1454,7 +1381,7 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
 	sample.id = ptq->pt->transactions_id;
 	sample.stream_id = ptq->pt->transactions_id;
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->transactions_sample_type);
 }
 
@@ -1495,7 +1422,7 @@ static int intel_pt_synth_ptwrite_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->ptwrites_sample_type);
 }
 
@@ -1525,7 +1452,7 @@ static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->pwr_events_sample_type);
 }
 
@@ -1550,7 +1477,7 @@ static int intel_pt_synth_mwait_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->pwr_events_sample_type);
 }
 
@@ -1575,7 +1502,7 @@ static int intel_pt_synth_pwre_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->pwr_events_sample_type);
 }
 
@@ -1600,7 +1527,7 @@ static int intel_pt_synth_exstop_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->pwr_events_sample_type);
 }
 
@@ -1625,7 +1552,7 @@ static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->pwr_events_sample_type);
 }
 
@@ -1845,7 +1772,9 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
 			intel_pt_add_lbrs(&br.br_stack, items);
 			sample.branch_stack = &br.br_stack;
 		} else if (pt->synth_opts.last_branch) {
-			intel_pt_copy_last_branch_rb(ptq);
+			thread_stack__br_sample(ptq->thread, ptq->cpu,
+						ptq->last_branch,
+						pt->br_stack_sz);
 			sample.branch_stack = ptq->last_branch;
 		} else {
 			br.br_stack.nr = 0;
@@ -1880,7 +1809,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
 		sample.transaction = txn;
 	}
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample, sample_type);
+	return intel_pt_deliver_synth_event(pt, event, &sample, sample_type);
 }
 
 static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
@@ -2030,12 +1959,15 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	if (!(state->type & INTEL_PT_BRANCH))
 		return 0;
 
-	if (pt->use_thread_stack)
-		thread_stack__event(ptq->thread, ptq->cpu, ptq->flags, state->from_ip,
-				    state->to_ip, ptq->insn_len,
-				    state->trace_nr, true, 0, 0);
-	else
+	if (pt->use_thread_stack) {
+		thread_stack__event(ptq->thread, ptq->cpu, ptq->flags,
+				    state->from_ip, state->to_ip, ptq->insn_len,
+				    state->trace_nr, pt->callstack,
+				    pt->br_stack_sz,
+				    pt->mispred_all);
+	} else {
 		thread_stack__set_trace_nr(ptq->thread, ptq->cpu, state->trace_nr);
+	}
 
 	if (pt->sample_branches) {
 		err = intel_pt_synth_branch_sample(ptq);
@@ -2043,9 +1975,6 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 			return err;
 	}
 
-	if (pt->synth_opts.last_branch)
-		intel_pt_update_last_branch_rb(ptq);
-
 	if (!ptq->sync_switch)
 		return 0;
 
@@ -3441,9 +3370,17 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 			goto err_delete_thread;
 	}
 
+	if (pt->synth_opts.last_branch)
+		pt->br_stack_sz = pt->synth_opts.last_branch_sz;
+
 	pt->use_thread_stack = pt->synth_opts.callchain ||
 			       pt->synth_opts.add_callchain ||
-			       pt->synth_opts.thread_stack;
+			       pt->synth_opts.thread_stack ||
+			       pt->synth_opts.last_branch;
+
+	pt->callstack = pt->synth_opts.callchain ||
+			pt->synth_opts.add_callchain ||
+			pt->synth_opts.thread_stack;
 
 	err = intel_pt_synth_events(pt, session);
 	if (err)