perf: Support deferred user unwind

Add support for deferred userspace unwind to perf.

Where perf currently relies on in-place stack unwinding; from NMI
context and all that. This moves the userspace part of the unwind to
right before the return-to-userspace.

This has two distinct benefits, the biggest is that it moves the
unwind to a faultable context. It becomes possible to fault in debug
info (.eh_frame, SFrame etc.) that might not otherwise be readily
available. And secondly, it de-duplicates the user callchain where
multiple samples happen during the same kernel entry.

To facilitate this the perf interface is extended with a new record
type:

  PERF_RECORD_CALLCHAIN_DEFERRED

and two new attribute flags:

  perf_event_attr::defer_callchain - to request the user unwind be deferred
  perf_event_attr::defer_output    - to request PERF_RECORD_CALLCHAIN_DEFERRED records

The existing PERF_RECORD_SAMPLE callchain section gets a new
context type:

  PERF_CONTEXT_USER_DEFERRED

After which will come a single entry, denoting the 'cookie' of the
deferred callchain that should be attached here, matching the 'cookie'
field of the above mentioned PERF_RECORD_CALLCHAIN_DEFERRED.

The 'defer_callchain' flag is expected on all events with
PERF_SAMPLE_CALLCHAIN. The 'defer_output' flag is expect on the event
responsible for collecting side-band events (like mmap, comm etc.).
Setting 'defer_output' on multiple events will get you duplicated
PERF_RECORD_CALLCHAIN_DEFERRED records.

Based on earlier patches by Josh and Steven.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20251023150002.GR4067720@noisy.programming.kicks-ass.net

3 files changed, 14 insertions, 13 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 */