ftrace: Synchronize the initialization of ftrace_opsgrafted

There's some internal state that ftrace_ops needs to have set, but since
it can be declared outside of the ftrace.c code, it calls
ftrace_ops_init() on the ops in every global function. The issue is that
if two tasks call it on the same ops at the same time it is possible to
have the initialization of one corrupt the initialization of the other
call.

Create a ops_mutex to use to synchronize every initialization of the
ftrace_ops. The mutex is taken within checking the ftrace_ops flag that
states it was initializied but the flag is checked again after the mutex
has been taken. Checking first outside the mutex allows it to shortcut
having to take the mutex. But then the check needs to be done again after
the mute is taken in case of races.

Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260902095501.6b59af20@gandalf.local.home
Fixes: f04f24fb7e48d ("ftrace, kprobes: Fix a deadlock on ftrace_regex_lock")
Reported-by: sashiko-bot@kernel.org
Close: https://lore.kernel.org/all/20260829025528.49A831F000E9@smtp.kernel.org/
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

1 files changed, 166 insertions, 0 deletions

diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
new file mode 100644
index 000000000..b1d5b18c4
--- /dev/null
+++ b/include/trace/events/lock.h
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM lock
+
+#if !defined(_TRACE_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_LOCK_H
+
+#include <linux/tracepoint.h>
+
+/* flags for lock:contention_begin */
+#define LCB_F_SPIN	(1U << 0)
+#define LCB_F_READ	(1U << 1)
+#define LCB_F_WRITE	(1U << 2)
+#define LCB_F_RT	(1U << 3)
+#define LCB_F_PERCPU	(1U << 4)
+#define LCB_F_MUTEX	(1U << 5)
+
+
+#ifdef CONFIG_LOCKDEP
+
+#include <linux/lockdep.h>
+
+TRACE_EVENT(lock_acquire,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned int subclass,
+		int trylock, int read, int check,
+		struct lockdep_map *next_lock, unsigned long ip),
+
+	TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, flags)
+		__string(name, lock->name)
+		__field(void *, lockdep_addr)
+	),
+
+	TP_fast_assign(
+		__entry->flags = (trylock ? 1 : 0) | (read ? 2 : 0);
+		__assign_str(name);
+		__entry->lockdep_addr = lock;
+	),
+
+	TP_printk("%p %s%s%s", __entry->lockdep_addr,
+		  (__entry->flags & 1) ? "try " : "",
+		  (__entry->flags & 2) ? "read " : "",
+		  __get_str(name))
+);
+
+DECLARE_EVENT_CLASS(lock,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip),
+
+	TP_STRUCT__entry(
+		__string(	name, 	lock->name	)
+		__field(	void *, lockdep_addr	)
+	),
+
+	TP_fast_assign(
+		__assign_str(name);
+		__entry->lockdep_addr = lock;
+	),
+
+	TP_printk("%p %s",  __entry->lockdep_addr, __get_str(name))
+);
+
+DEFINE_EVENT(lock, lock_release,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip)
+);
+
+#ifdef CONFIG_LOCK_STAT
+
+DEFINE_EVENT(lock, lock_contended,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip)
+);
+
+DEFINE_EVENT(lock, lock_acquired,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip)
+);
+
+#endif /* CONFIG_LOCK_STAT */
+#endif /* CONFIG_LOCKDEP */
+
+TRACE_EVENT(contention_begin,
+
+	TP_PROTO(void *lock, unsigned int flags),
+
+	TP_ARGS(lock, flags),
+
+	TP_STRUCT__entry(
+		__field(void *, lock_addr)
+		__field(unsigned int, flags)
+	),
+
+	TP_fast_assign(
+		__entry->lock_addr = lock;
+		__entry->flags = flags;
+	),
+
+	TP_printk("%p (flags=%s)", __entry->lock_addr,
+		  __print_flags(__entry->flags, "|",
+				{ LCB_F_SPIN,		"SPIN" },
+				{ LCB_F_READ,		"READ" },
+				{ LCB_F_WRITE,		"WRITE" },
+				{ LCB_F_RT,		"RT" },
+				{ LCB_F_PERCPU,		"PERCPU" },
+				{ LCB_F_MUTEX,		"MUTEX" }
+			  ))
+);
+
+TRACE_EVENT(contention_end,
+
+	TP_PROTO(void *lock, int ret),
+
+	TP_ARGS(lock, ret),
+
+	TP_STRUCT__entry(
+		__field(void *, lock_addr)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		__entry->lock_addr = lock;
+		__entry->ret = ret;
+	),
+
+	TP_printk("%p (ret=%d)", __entry->lock_addr, __entry->ret)
+);
+
+/* kernel/locking/mutex.c */
+int arch_contended_release_trace_reg(void);
+void arch_contended_release_trace_unreg(void);
+
+TRACE_EVENT_FN(contended_release,
+
+	TP_PROTO(void *lock),
+
+	TP_ARGS(lock),
+
+	TP_STRUCT__entry(
+		__field(void *, lock_addr)
+	),
+
+	TP_fast_assign(
+		__entry->lock_addr = lock;
+	),
+
+	TP_printk("%p", __entry->lock_addr),
+
+	arch_contended_release_trace_reg, arch_contended_release_trace_unreg
+);
+
+#endif /* _TRACE_LOCK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>