printk: introduce console_list_lock

Currently there exist races in register_console(), where the types
of registered consoles are checked (without holding the console_lock)
and then after acquiring the console_lock, it is assumed that the list
has not changed. Also, some code that performs console_unregister()
make similar assumptions.

It might be possible to fix these races using the console_lock. But
it would require a complex analysis of all console drivers to make
sure that the console_lock is not taken in match() and setup()
callbacks. And we really prefer to split up and reduce the
responsibilities of console_lock rather than expand its complexity.
Therefore, introduce a new console_list_lock to provide full
synchronization for any console list changes.

In addition, also use console_list_lock for synchronization of
console->flags updates. All flags are either static or modified only
during the console registration. There are only two exceptions.

The first exception is CON_ENABLED, which is also modified by
console_start()/console_stop(). Therefore, these functions must
also take the console_list_lock.

The second exception is when the flags are modified by the console
driver init code before the console is registered. These will be
ignored because they are not visible to the rest of the system
via the console_drivers list.

Note that one of the various responsibilities of the console_lock is
also intended to provide console list and console->flags
synchronization. Later changes will update call sites relying on the
console_lock for these purposes. Once all call sites have been
updated, the console_lock will be relieved of synchronizing
console_list and console->flags updates.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/87sficwokr.fsf@jogness.linutronix.de

1 files changed, 80 insertions, 9 deletions

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index c84654444a02a..2b4506673a860 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -79,6 +79,13 @@ int oops_in_progress;
 EXPORT_SYMBOL(oops_in_progress);
 
 /*
+ * console_mutex protects console_list updates and console->flags updates.
+ * The flags are synchronized only for consoles that are registered, i.e.
+ * accessible via the console list.
+ */
+static DEFINE_MUTEX(console_mutex);
+
+/*
  * console_sem protects console_list and console->flags updates, and also
  * provides serialization for access to the entire console driver system.
  */
@@ -103,6 +110,12 @@ static int __read_mostly suppress_panic_printk;
 static struct lockdep_map console_lock_dep_map = {
 	.name = "console_lock"
 };
+
+void lockdep_assert_console_list_lock_held(void)
+{
+	lockdep_assert_held(&console_mutex);
+}
+EXPORT_SYMBOL(lockdep_assert_console_list_lock_held);
 #endif
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -228,6 +241,40 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
 #endif /* CONFIG_PRINTK && CONFIG_SYSCTL */
 
 /**
+ * console_list_lock - Lock the console list
+ *
+ * For console list or console->flags updates
+ */
+void console_list_lock(void)
+{
+	/*
+	 * In unregister_console(), synchronize_srcu() is called with the
+	 * console_list_lock held. Therefore it is not allowed that the
+	 * console_list_lock is taken with the srcu_lock held.
+	 *
+	 * Detecting if this context is really in the read-side critical
+	 * section is only possible if the appropriate debug options are
+	 * enabled.
+	 */
+	WARN_ON_ONCE(debug_lockdep_rcu_enabled() &&
+		     srcu_read_lock_held(&console_srcu));
+
+	mutex_lock(&console_mutex);
+}
+EXPORT_SYMBOL(console_list_lock);
+
+/**
+ * console_list_unlock - Unlock the console list
+ *
+ * Counterpart to console_list_lock()
+ */
+void console_list_unlock(void)
+{
+	mutex_unlock(&console_mutex);
+}
+EXPORT_SYMBOL(console_list_unlock);
+
+/**
  * console_srcu_read_lock - Register a new reader for the
  *	SRCU-protected console list
  *
@@ -3020,9 +3067,11 @@ struct tty_driver *console_device(int *index)
 void console_stop(struct console *console)
 {
 	__pr_flush(console, 1000, true);
+	console_list_lock();
 	console_lock();
 	console->flags &= ~CON_ENABLED;
 	console_unlock();
+	console_list_unlock();
 
 	/*
 	 * Ensure that all SRCU list walks have completed. All contexts must
@@ -3036,9 +3085,11 @@ EXPORT_SYMBOL(console_stop);
 
 void console_start(struct console *console)
 {
+	console_list_lock();
 	console_lock();
 	console->flags |= CON_ENABLED;
 	console_unlock();
+	console_list_unlock();
 	__pr_flush(console, 1000, true);
 }
 EXPORT_SYMBOL(console_start);
@@ -3187,6 +3238,8 @@ static void console_init_seq(struct console *newcon, bool bootcon_registered)
 #define console_first()				\
 	hlist_entry(console_list.first, struct console, node)
 
+static int unregister_console_locked(struct console *console);
+
 /*
  * The console driver calls this routine during kernel initialization
  * to register the console printing procedure with printk() and to
@@ -3213,13 +3266,14 @@ void register_console(struct console *newcon)
 	bool realcon_registered = false;
 	int err;
 
+	console_list_lock();
+
 	for_each_console(con) {
 		if (WARN(con == newcon, "console '%s%d' already registered\n",
-					 con->name, con->index))
-			return;
-	}
+					 con->name, con->index)) {
+			goto unlock;
+		}
 
-	for_each_console(con) {
 		if (con->flags & CON_BOOT)
 			bootcon_registered = true;
 		else
@@ -3230,7 +3284,7 @@ void register_console(struct console *newcon)
 	if ((newcon->flags & CON_BOOT) && realcon_registered) {
 		pr_info("Too late to register bootconsole %s%d\n",
 			newcon->name, newcon->index);
-		return;
+		goto unlock;
 	}
 
 	/*
@@ -3261,7 +3315,7 @@ void register_console(struct console *newcon)
 
 	/* printk() messages are not printed to the Braille console. */
 	if (err || newcon->flags & CON_BRL)
-		return;
+		goto unlock;
 
 	/*
 	 * If we have a bootconsole, and are switching to a real console,
@@ -3320,16 +3374,21 @@ void register_console(struct console *newcon)
 
 		hlist_for_each_entry_safe(con, tmp, &console_list, node) {
 			if (con->flags & CON_BOOT)
-				unregister_console(con);
+				unregister_console_locked(con);
 		}
 	}
+unlock:
+	console_list_unlock();
 }
 EXPORT_SYMBOL(register_console);
 
-int unregister_console(struct console *console)
+/* Must be called under console_list_lock(). */
+static int unregister_console_locked(struct console *console)
 {
 	int res;
 
+	lockdep_assert_console_list_lock_held();
+
 	con_printk(KERN_INFO, console, "disabled\n");
 
 	res = _braille_unregister_console(console);
@@ -3378,6 +3437,16 @@ int unregister_console(struct console *console)
 
 	return res;
 }
+
+int unregister_console(struct console *console)
+{
+	int res;
+
+	console_list_lock();
+	res = unregister_console_locked(console);
+	console_list_unlock();
+	return res;
+}
 EXPORT_SYMBOL(unregister_console);
 
 /*
@@ -3430,6 +3499,7 @@ static int __init printk_late_init(void)
 	struct console *con;
 	int ret;
 
+	console_list_lock();
 	hlist_for_each_entry_safe(con, tmp, &console_list, node) {
 		if (!(con->flags & CON_BOOT))
 			continue;
@@ -3447,9 +3517,10 @@ static int __init printk_late_init(void)
 			 */
 			pr_warn("bootconsole [%s%d] uses init memory and must be disabled even before the real one is ready\n",
 				con->name, con->index);
-			unregister_console(con);
+			unregister_console_locked(con);
 		}
 	}
+	console_list_unlock();
 
 	ret = cpuhp_setup_state_nocalls(CPUHP_PRINTK_DEAD, "printk:dead", NULL,
 					console_cpu_notify);