diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index ffa385a029b3fa2613c7629752b1c49d7e4a3ec9..60732213d16a1bcae4c84474c75cd944a33fb21c 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -759,7 +759,8 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 	if (pt->synth_opts.callchain) {
 		size_t sz = sizeof(struct ip_callchain);
 
-		sz += pt->synth_opts.callchain_sz * sizeof(u64);
+		/* Add 1 to callchain_sz for callchain context */
+		sz += (pt->synth_opts.callchain_sz + 1) * sizeof(u64);
 		ptq->chain = zalloc(sz);
 		if (!ptq->chain)
 			goto out_free;
@@ -1160,7 +1161,8 @@ static void intel_pt_prep_sample(struct intel_pt *pt,
 
 	if (pt->synth_opts.callchain) {
 		thread_stack__sample(ptq->thread, ptq->chain,
-				     pt->synth_opts.callchain_sz, sample->ip);
+				     pt->synth_opts.callchain_sz + 1,
+				     sample->ip, pt->kernel_start);
 		sample->callchain = ptq->chain;
 	}
 
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index c091635bf7dcb317d66f1ab8273e5cc90678c5e1..61a4286a74dc9f86c333036013d5abe914b81b3f 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -310,20 +310,46 @@ void thread_stack__free(struct thread *thread)
 	}
 }
 
+static inline u64 callchain_context(u64 ip, u64 kernel_start)
+{
+	return ip < kernel_start ? PERF_CONTEXT_USER : PERF_CONTEXT_KERNEL;
+}
+
 void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
-			  size_t sz, u64 ip)
+			  size_t sz, u64 ip, u64 kernel_start)
 {
-	size_t i;
+	u64 context = callchain_context(ip, kernel_start);
+	u64 last_context;
+	size_t i, j;
 
-	if (!thread || !thread->ts)
-		chain->nr = 1;
-	else
-		chain->nr = min(sz, thread->ts->cnt + 1);
+	if (sz < 2) {
+		chain->nr = 0;
+		return;
+	}
 
-	chain->ips[0] = ip;
+	chain->ips[0] = context;
+	chain->ips[1] = ip;
+
+	if (!thread || !thread->ts) {
+		chain->nr = 2;
+		return;
+	}
+
+	last_context = context;
+
+	for (i = 2, j = 1; i < sz && j <= thread->ts->cnt; i++, j++) {
+		ip = thread->ts->stack[thread->ts->cnt - j].ret_addr;
+		context = callchain_context(ip, kernel_start);
+		if (context != last_context) {
+			if (i >= sz - 1)
+				break;
+			chain->ips[i++] = context;
+			last_context = context;
+		}
+		chain->ips[i] = ip;
+	}
 
-	for (i = 1; i < chain->nr; i++)
-		chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
+	chain->nr = i;
 }
 
 struct call_return_processor *
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index b7e41c4ebfdd98ec038f823e70051a49c3fa6a62..f97c00a8c2514dcc102f8e25d32e474815e2b030 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -84,7 +84,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 			u64 to_ip, u16 insn_len, u64 trace_nr);
 void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
 void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
-			  size_t sz, u64 ip);
+			  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);