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, 105 insertions, 0 deletions

diff --git a/lib/ratelimit.c b/lib/ratelimit.c
new file mode 100644
index 000000000..e2d65d3b1
--- /dev/null
+++ b/lib/ratelimit.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ratelimit.c - Do something with rate limit.
+ *
+ * Isolated from kernel/printk.c by Dave Young <hidave.darkstar@gmail.com>
+ *
+ * 2008-05-01 rewrite the function and use a ratelimit_state data struct as
+ * parameter. Now every user can use their own standalone ratelimit_state.
+ */
+
+#include <linux/ratelimit.h>
+#include <linux/jiffies.h>
+#include <linux/export.h>
+
+/*
+ * __ratelimit - rate limiting
+ * @rs: ratelimit_state data
+ * @func: name of calling function
+ *
+ * This enforces a rate limit: not more than @rs->burst callbacks
+ * in every @rs->interval
+ *
+ * RETURNS:
+ * 0 means callbacks will be suppressed.
+ * 1 means go ahead and do it.
+ */
+int ___ratelimit(struct ratelimit_state *rs, const char *func)
+{
+	/* Paired with WRITE_ONCE() in .proc_handler().
+	 * Changing two values separately could be inconsistent
+	 * and some message could be lost.  (See: net_ratelimit_state).
+	 */
+	int interval = READ_ONCE(rs->interval);
+	int burst = READ_ONCE(rs->burst);
+	unsigned long flags;
+	int ret = 0;
+
+	/*
+	 * Zero interval says never limit, otherwise, non-positive burst
+	 * says always limit.
+	 */
+	if (interval <= 0 || burst <= 0) {
+		WARN_ONCE(interval < 0 || burst < 0, "Negative interval (%d) or burst (%d): Uninitialized ratelimit_state structure?\n", interval, burst);
+		ret = interval == 0 || burst > 0;
+		if (!(READ_ONCE(rs->flags) & RATELIMIT_INITIALIZED) || (!interval && !burst) ||
+		    !raw_spin_trylock_irqsave(&rs->lock, flags))
+			goto nolock_ret;
+
+		/* Force re-initialization once re-enabled. */
+		rs->flags &= ~RATELIMIT_INITIALIZED;
+		goto unlock_ret;
+	}
+
+	/*
+	 * If we contend on this state's lock then just check if
+	 * the current burst is used or not. It might cause
+	 * false positive when we are past the interval and
+	 * the current lock owner is just about to reset it.
+	 */
+	if (!raw_spin_trylock_irqsave(&rs->lock, flags)) {
+		if (READ_ONCE(rs->flags) & RATELIMIT_INITIALIZED &&
+		    atomic_read(&rs->rs_n_left) > 0 && atomic_dec_return(&rs->rs_n_left) >= 0)
+			ret = 1;
+		goto nolock_ret;
+	}
+
+	if (!(rs->flags & RATELIMIT_INITIALIZED)) {
+		rs->begin = jiffies;
+		rs->flags |= RATELIMIT_INITIALIZED;
+		atomic_set(&rs->rs_n_left, rs->burst);
+	}
+
+	if (time_is_before_jiffies(rs->begin + interval)) {
+		int m;
+
+		/*
+		 * Reset rs_n_left ASAP to reduce false positives
+		 * in parallel calls, see above.
+		 */
+		atomic_set(&rs->rs_n_left, rs->burst);
+		rs->begin = jiffies;
+
+		if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) {
+			m = ratelimit_state_reset_miss(rs);
+			if (m) {
+				printk_deferred(KERN_WARNING
+						"%s: %d callbacks suppressed\n", func, m);
+			}
+		}
+	}
+
+	/* Note that the burst might be taken by a parallel call. */
+	if (atomic_read(&rs->rs_n_left) > 0 && atomic_dec_return(&rs->rs_n_left) >= 0)
+		ret = 1;
+
+unlock_ret:
+	raw_spin_unlock_irqrestore(&rs->lock, flags);
+
+nolock_ret:
+	if (!ret)
+		ratelimit_state_inc_miss(rs);
+
+	return ret;
+}
+EXPORT_SYMBOL(___ratelimit);