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 <[e-mail]>
Cc: Andi Kleen <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Link: http://lore.kernel.org/lkml/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/util/thread-stack.c

···
 	}
 }
 
+/* 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)

tools/perf/util/thread-stack.h

···
 			       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);