4 files changed, 34 insertions, 14 deletions
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fd1d91017b99..9870d768db4c 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1720,7 +1720,7 @@ extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct p
 extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
 extern struct perf_callchain_entry *
 get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
-		   u32 max_stack, bool crosstask, bool add_mark);
+		   u32 max_stack, bool crosstask, bool add_mark, u64 defer_cookie);
 extern int get_callchain_buffers(int max_stack);
 extern void put_callchain_buffers(void);
 extern struct perf_callchain_entry *get_callchain_entry(int *rctx);
diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h
index f4743c8cff4c..bc7ae7d21900 100644
--- a/include/linux/unwind_deferred.h
+++ b/include/linux/unwind_deferred.h
@@ -6,18 +6,6 @@
 #include <linux/unwind_user.h>
 #include <linux/unwind_deferred_types.h>
 
-struct unwind_work;
-
-typedef void (*unwind_callback_t)(struct unwind_work *work,
-				  struct unwind_stacktrace *trace,
-				  u64 cookie);
-
-struct unwind_work {
-	struct list_head		list;
-	unwind_callback_t		func;
-	int				bit;
-};
-
 #ifdef CONFIG_UNWIND_USER
 
 enum {
diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h
index 0a4c8ddbbc57..18fa3932f61c 100644
--- a/include/linux/unwind_deferred_types.h
+++ b/include/linux/unwind_deferred_types.h
@@ -39,4 +39,17 @@ struct unwind_task_info {
 	union unwind_task_id	id;
 };
 
+struct unwind_work;
+struct unwind_stacktrace;
+
+typedef void (*unwind_callback_t)(struct unwind_work *work,
+				  struct unwind_stacktrace *trace,
+				  u64 cookie);
+
+struct unwind_work {
+	struct list_head		list;
+	unwind_callback_t		func;
+	int				bit;
+};
+
 #endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 78a362b80027..d292f96bc06f 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -463,7 +463,9 @@ struct perf_event_attr {
 				inherit_thread :  1, /* children only inherit if cloned with CLONE_THREAD */
 				remove_on_exec :  1, /* event is removed from task on exec */
 				sigtrap        :  1, /* send synchronous SIGTRAP on event */
-				__reserved_1   : 26;
+				defer_callchain:  1, /* request PERF_RECORD_CALLCHAIN_DEFERRED records */
+				defer_output   :  1, /* output PERF_RECORD_CALLCHAIN_DEFERRED records */
+				__reserved_1   : 24;
 
 	union {
 		__u32		wakeup_events;	  /* wake up every n events */
@@ -1239,6 +1241,22 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_AUX_OUTPUT_HW_ID		= 21,
 
+	/*
+	 * This user callchain capture was deferred until shortly before
+	 * returning to user space.  Previous samples would have kernel
+	 * callchains only and they need to be stitched with this to make full
+	 * callchains.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				cookie;
+	 *	u64				nr;
+	 *	u64				ips[nr];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_CALLCHAIN_DEFERRED		= 22,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
@@ -1269,6 +1287,7 @@ enum perf_callchain_context {
 	PERF_CONTEXT_HV				= (__u64)-32,
 	PERF_CONTEXT_KERNEL			= (__u64)-128,
 	PERF_CONTEXT_USER			= (__u64)-512,
+	PERF_CONTEXT_USER_DEFERRED		= (__u64)-640,
 
 	PERF_CONTEXT_GUEST			= (__u64)-2048,
 	PERF_CONTEXT_GUEST_KERNEL		= (__u64)-2176,