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, 84 insertions, 0 deletions

diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
new file mode 100644
index 000000000..856b5e90f
--- /dev/null
+++ b/include/net/gen_stats.h
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NET_GEN_STATS_H
+#define __NET_GEN_STATS_H
+
+#include <linux/gen_stats.h>
+#include <linux/socket.h>
+#include <linux/rtnetlink.h>
+#include <linux/pkt_sched.h>
+
+/* Throughput stats.
+ * Must be initialized beforehand with gnet_stats_basic_sync_init().
+ *
+ * If no reads can ever occur parallel to writes (e.g. stack-allocated
+ * bstats), then the internal stat values can be written to and read
+ * from directly. Otherwise, use _bstats_set/update() for writes and
+ * gnet_stats_add_basic() for reads.
+ */
+struct gnet_stats_basic_sync {
+	u64_stats_t bytes;
+	u64_stats_t packets;
+	struct u64_stats_sync syncp;
+} __aligned(2 * sizeof(u64));
+
+struct net_rate_estimator;
+
+struct gnet_dump {
+	spinlock_t *      lock;
+	struct sk_buff *  skb;
+	struct nlattr *   tail;
+
+	/* Backward compatibility */
+	int               compat_tc_stats;
+	int               compat_xstats;
+	int               padattr;
+	void *            xstats;
+	int               xstats_len;
+	struct tc_stats   tc_stats;
+};
+
+void gnet_stats_basic_sync_init(struct gnet_stats_basic_sync *b);
+int gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock,
+			  struct gnet_dump *d, int padattr);
+
+int gnet_stats_start_copy_compat(struct sk_buff *skb, int type,
+				 int tc_stats_type, int xstats_type,
+				 spinlock_t *lock, struct gnet_dump *d,
+				 int padattr);
+
+int gnet_stats_copy_basic(struct gnet_dump *d,
+			  const struct gnet_stats_basic_sync __percpu *cpu,
+			  const struct gnet_stats_basic_sync *b, bool running);
+void gnet_stats_add_basic(struct gnet_stats_basic_sync *bstats,
+			  const struct gnet_stats_basic_sync __percpu *cpu,
+			  const struct gnet_stats_basic_sync *b, bool running);
+int gnet_stats_copy_basic_hw(struct gnet_dump *d,
+			     const struct gnet_stats_basic_sync __percpu *cpu,
+			     const struct gnet_stats_basic_sync *b, bool running);
+int gnet_stats_copy_rate_est(struct gnet_dump *d,
+			     struct net_rate_estimator __rcu **ptr);
+int gnet_stats_copy_queue(struct gnet_dump *d,
+			  const struct gnet_stats_queue __percpu *cpu_q,
+			  const struct gnet_stats_queue *q, __u32 qlen);
+void gnet_stats_add_queue(struct gnet_stats_queue *qstats,
+			  const struct gnet_stats_queue __percpu *cpu_q,
+			  const struct gnet_stats_queue *q);
+int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len);
+
+int gnet_stats_finish_copy(struct gnet_dump *d);
+
+int gen_new_estimator(struct gnet_stats_basic_sync *bstats,
+		      struct gnet_stats_basic_sync __percpu *cpu_bstats,
+		      struct net_rate_estimator __rcu **rate_est,
+		      spinlock_t *lock,
+		      bool running, struct nlattr *opt);
+void gen_kill_estimator(struct net_rate_estimator __rcu **ptr);
+int gen_replace_estimator(struct gnet_stats_basic_sync *bstats,
+			  struct gnet_stats_basic_sync __percpu *cpu_bstats,
+			  struct net_rate_estimator __rcu **ptr,
+			  spinlock_t *lock,
+			  bool running, struct nlattr *opt);
+bool gen_estimator_active(struct net_rate_estimator __rcu **ptr);
+bool gen_estimator_read(struct net_rate_estimator __rcu **ptr,
+			struct gnet_stats_rate_est64 *sample);
+#endif