unwind: Finish up unwind when a task exits

On do_exit() when a task is exiting, if a unwind is requested and the
deferred user stacktrace is deferred via the task_work, the task_work
callback is called after exit_mm() is called in do_exit(). This means that
the user stack trace will not be retrieved and an empty stack is created.

Instead, add a function unwind_deferred_task_exit() and call it just
before exit_mm() so that the unwinder can call the requested callbacks
with the user space stack.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Indu Bhagat <indu.bhagat@oracle.com>
Cc: "Jose E. Marchesi" <jemarch@gnu.org>
Cc: Beau Belgrave <beaub@linux.microsoft.com>
Cc: Jens Remus <jremus@linux.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Sam James <sam@gentoo.org>
Link: https://lore.kernel.org/20250729182406.504259474@kernel.org
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

3 files changed, 25 insertions, 3 deletions

diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h
index 2efbda01e959..26122d00708a 100644
--- a/include/linux/unwind_deferred.h
+++ b/include/linux/unwind_deferred.h
@@ -39,6 +39,8 @@ int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func);
 int unwind_deferred_request(struct unwind_work *work, u64 *cookie);
 void unwind_deferred_cancel(struct unwind_work *work);
 
+void unwind_deferred_task_exit(struct task_struct *task);
+
 static __always_inline void unwind_reset_info(void)
 {
 	struct unwind_task_info *info = &current->unwind_info;
@@ -71,6 +73,7 @@ static inline int unwind_deferred_init(struct unwind_work *work, unwind_callback
 static inline int unwind_deferred_request(struct unwind_work *work, u64 *timestamp) { return -ENOSYS; }
 static inline void unwind_deferred_cancel(struct unwind_work *work) {}
 
+static inline void unwind_deferred_task_exit(struct task_struct *task) {}
 static inline void unwind_reset_info(void) {}
 
 #endif /* !CONFIG_UNWIND_USER */
diff --git a/kernel/exit.c b/kernel/exit.c
index bb184a67ac73..1d8c8ac33c4f 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -68,6 +68,7 @@
 #include <linux/rethook.h>
 #include <linux/sysfs.h>
 #include <linux/user_events.h>
+#include <linux/unwind_deferred.h>
 #include <linux/uaccess.h>
 #include <linux/pidfs.h>
 
@@ -938,6 +939,7 @@ void __noreturn do_exit(long code)
 
 	tsk->exit_code = code;
 	taskstats_exit(tsk, group_dead);
+	unwind_deferred_task_exit(tsk);
 	trace_sched_process_exit(tsk, group_dead);
 
 	/*
diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c
index a5ef1c1f915e..dc6040aae3ee 100644
--- a/kernel/unwind/deferred.c
+++ b/kernel/unwind/deferred.c
@@ -114,7 +114,7 @@ int unwind_user_faultable(struct unwind_stacktrace *trace)
 	/* Should always be called from faultable context */
 	might_fault();
 
-	if (current->flags & PF_EXITING)
+	if (!current->mm)
 		return -EINVAL;
 
 	if (!info->cache) {
@@ -147,9 +147,9 @@ int unwind_user_faultable(struct unwind_stacktrace *trace)
 	return 0;
 }
 
-static void unwind_deferred_task_work(struct callback_head *head)
+static void process_unwind_deferred(struct task_struct *task)
 {
-	struct unwind_task_info *info = container_of(head, struct unwind_task_info, work);
+	struct unwind_task_info *info = &task->unwind_info;
 	struct unwind_stacktrace trace;
 	struct unwind_work *work;
 	unsigned long bits;
@@ -186,6 +186,23 @@ static void unwind_deferred_task_work(struct callback_head *head)
 	}
 }
 
+static void unwind_deferred_task_work(struct callback_head *head)
+{
+	process_unwind_deferred(current);
+}
+
+void unwind_deferred_task_exit(struct task_struct *task)
+{
+	struct unwind_task_info *info = &current->unwind_info;
+
+	if (!unwind_pending(info))
+		return;
+
+	process_unwind_deferred(task);
+
+	task_work_cancel(task, &info->work);
+}
+
 /**
  * unwind_deferred_request - Request a user stacktrace on task kernel exit
  * @work: Unwind descriptor requesting the trace