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

[tip-bot2 for Adrian Hunter]

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

Commit-ID:     4fef41bfb1d8d2ada4a18eb3ab80c2682bcbae12
Gitweb:        https://git.kernel.org/tip/4fef41bfb1d8d2ada4a18eb3ab80c2682bcbae12
Author:        Adrian Hunter <adrian.hunter@xxxxxxxxx>
AuthorDate:    Wed, 01 Apr 2020 13:16:06 +03:00
Committer:     Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
CommitterDate: Thu, 16 Apr 2020 12:19:15 -03:00

perf thread-stack: Add thread_stack__sample_late()

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

Signed-off-by: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Link: http://lore.kernel.org/lkml/20200401101613.6201-10-adrian.hunter@xxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
 tools/perf/util/thread-stack.c | 57 +++++++++++++++++++++++++++++++++-
 tools/perf/util/thread-stack.h |  3 ++-
 2 files changed, 60 insertions(+)

diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 0885967..83f6c83 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -497,6 +497,63 @@ void thread_stack__sample(struct thread *thread, int cpu,
 	chain->nr = i;
 }
 
+/*
+ * Hardware sample records, created some time after the event occurred, need to
+ * have subsequent addresses removed from the call chain.
+ */
+void thread_stack__sample_late(struct thread *thread, int cpu,
+			       struct ip_callchain *chain, size_t sz,
+			       u64 sample_ip, u64 kernel_start)
+{
+	struct thread_stack *ts = thread__stack(thread, cpu);
+	u64 sample_context = callchain_context(sample_ip, kernel_start);
+	u64 last_context, context, ip;
+	size_t nr = 0, j;
+
+	if (sz < 2) {
+		chain->nr = 0;
+		return;
+	}
+
+	if (!ts)
+		goto out;
+
+	/*
+	 * When tracing kernel space, kernel addresses occur at the top of the
+	 * call chain after the event occurred but before tracing stopped.
+	 * Skip them.
+	 */
+	for (j = 1; j <= ts->cnt; j++) {
+		ip = ts->stack[ts->cnt - j].ret_addr;
+		context = callchain_context(ip, kernel_start);
+		if (context == PERF_CONTEXT_USER ||
+		    (context == sample_context && ip == sample_ip))
+			break;
+	}
+
+	last_context = sample_ip; /* Use sample_ip as an invalid context */
+
+	for (; nr < sz && j <= ts->cnt; nr++, j++) {
+		ip = ts->stack[ts->cnt - j].ret_addr;
+		context = callchain_context(ip, kernel_start);
+		if (context != last_context) {
+			if (nr >= sz - 1)
+				break;
+			chain->ips[nr++] = context;
+			last_context = context;
+		}
+		chain->ips[nr] = ip;
+	}
+out:
+	if (nr) {
+		chain->nr = nr;
+	} else {
+		chain->ips[0] = sample_context;
+		chain->ips[1] = sample_ip;
+		chain->nr = 2;
+	}
+}
+
 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 e1ec5a5..8962ddc 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -85,6 +85,9 @@ int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
 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);
 int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
 size_t thread_stack__depth(struct thread *thread, int cpu);