kprobes: Fix to delay the kprobes jump optimization

Commit 36dadef2 ("kprobes: Init kprobes in early_initcall")
moved the kprobe setup in early_initcall(), which includes kprobe
jump optimization.
The kprobes jump optimizer involves synchronize_rcu_tasks() which
depends on the ksoftirqd and rcu_spawn_tasks_*(). However, since
those are setup in core_initcall(), kprobes jump optimizer can not
run at the early_initcall().

To avoid this issue, make the kprobe optimization disabled in the
early_initcall() and enables it in subsys_initcall().

Note that non-optimized kprobes is still available after
early_initcall(). Only jump optimization is delayed.

Link: https://lkml.kernel.org/r/161365856280.719838.12423085451287256713.stgit@devnote2

Fixes: 36dadef2 ("kprobes: Init kprobes in early_initcall")
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: RCU <rcu@vger.kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Neeraj Upadhyay <neeraju@codeaurora.org>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "Theodore Y . Ts'o" <tytso@mit.edu>
Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com>
Cc: stable@vger.kernel.org
Reported-by: Paul E. McKenney <paulmck@kernel.org>
Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reported-by: Uladzislau Rezki <urezki@gmail.com>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>

kernel/kprobes.c

@@ -861,7 +861,6 @@ static void try_to_optimize_kprobe(struct kprobe *p)
 	cpus_read_unlock();
 }
 
-#ifdef CONFIG_SYSCTL
 static void optimize_all_kprobes(void)
 {
 	struct hlist_head *head;
@@ -887,6 +886,7 @@ static void optimize_all_kprobes(void)
 	mutex_unlock(&kprobe_mutex);
 }
 
+#ifdef CONFIG_SYSCTL
 static void unoptimize_all_kprobes(void)
 {
 	struct hlist_head *head;
@@ -2500,18 +2500,14 @@ static int __init init_kprobes(void)
 		}
 	}
 
-#if defined(CONFIG_OPTPROBES)
-#if defined(__ARCH_WANT_KPROBES_INSN_SLOT)
-	/* Init kprobe_optinsn_slots */
-	kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE;
-#endif
-	/* By default, kprobes can be optimized */
-	kprobes_allow_optimization = true;
-#endif
-
 	/* By default, kprobes are armed */
 	kprobes_all_disarmed = false;
 
+#if defined(CONFIG_OPTPROBES) && defined(__ARCH_WANT_KPROBES_INSN_SLOT)
+	/* Init kprobe_optinsn_slots for allocation */
+	kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE;
+#endif
+
 	err = arch_init_kprobes();
 	if (!err)
 		err = register_die_notifier(&kprobe_exceptions_nb);
@@ -2526,6 +2522,21 @@ static int __init init_kprobes(void)
 }
 early_initcall(init_kprobes);
 
+#if defined(CONFIG_OPTPROBES)
+static int __init init_optprobes(void)
+{
+	/*
+	 * Enable kprobe optimization - this kicks the optimizer which
+	 * depends on synchronize_rcu_tasks() and ksoftirqd, that is
+	 * not spawned in early initcall. So delay the optimization.
+	 */
+	optimize_all_kprobes();
+
+	return 0;
+}
+subsys_initcall(init_optprobes);
+#endif
+
 #ifdef CONFIG_DEBUG_FS
 static void report_probe(struct seq_file *pi, struct kprobe *p,
 		const char *sym, int offset, char *modname, struct kprobe *pp)