printk: Wait for the global console lock when the system is going down

There are reports that the console kthreads block the global console
lock when the system is going down, for example, reboot, panic.

First part of the solution was to block kthreads in these problematic
system states so they stopped handling newly added messages.

Second part of the solution is to wait when for the kthreads when
they are actively printing. It solves the problem when a message
was printed before the system entered the problematic state and
the kthreads managed to step in.

A busy waiting has to be used because panic() can be called in any
context and in an unknown state of the scheduler.

There must be a timeout because the kthread might get stuck or sleeping
and never release the lock. The timeout 10s is an arbitrary value
inspired by the softlockup timeout.

Link: https://lore.kernel.org/r/20220610205038.GA3050413@paulmck-ThinkPad-P17-Gen-1
Link: https://lore.kernel.org/r/CAMdYzYpF4FNTBPZsEFeWRuEwSies36QM_As8osPWZSr2q-viEA@mail.gmail.com
Signed-off-by: Petr Mladek <[email protected]>
Tested-by: Paul E. McKenney <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: pmladek

include/linux/printk.h

@@ -174,6 +174,7 @@ extern void printk_prefer_direct_enter(void);
 extern void printk_prefer_direct_exit(void);
 
 extern bool pr_flush(int timeout_ms, bool reset_on_progress);
+extern void try_block_console_kthreads(int timeout_ms);
 
 /*
  * Please don't use printk_ratelimit(), because it shares ratelimiting state
@@ -238,6 +239,10 @@ static inline bool pr_flush(int timeout_ms, bool reset_on_progress)
 	return true;
 }
 
+static inline void try_block_console_kthreads(int timeout_ms)
+{
+}
+
 static inline int printk_ratelimit(void)
 {
 	return 0;

kernel/panic.c

@@ -273,13 +273,15 @@ void panic(const char *fmt, ...)
 		 * unfortunately means it may not be hardened to work in a
 		 * panic situation.
 		 */
+		try_block_console_kthreads(10000);
 		smp_send_stop();
 	} else {
 		/*
 		 * If we want to do crash dump after notifier calls and
 		 * kmsg_dump, we will need architecture dependent extra
 		 * works in addition to stopping other CPUs.
 		 */
+		try_block_console_kthreads(10000);
 		crash_smp_send_stop();
 	}
 

kernel/printk/internal.h

@@ -20,6 +20,8 @@ enum printk_info_flags {
 	LOG_CONT	= 8,	/* text is a fragment of a continuation line */
 };
 
+extern bool block_console_kthreads;
+
 __printf(4, 0)
 int vprintk_store(int facility, int level,
 		  const struct dev_printk_info *dev_info,

kernel/printk/printk.c

@@ -250,6 +250,9 @@ static atomic_t console_kthreads_active = ATOMIC_INIT(0);
 #define console_kthread_printing_exit() \
 	atomic_dec(&console_kthreads_active)
 
+/* Block console kthreads to avoid processing new messages. */
+bool block_console_kthreads;
+
 /*
  * Helper macros to handle lockdep when locking/unlocking console_sem. We use
  * macros instead of functions so that _RET_IP_ contains useful information.
@@ -3730,6 +3733,7 @@ static bool printer_should_wake(struct console *con, u64 seq)
 
 	if (con->blocked ||
 	    console_kthreads_atomically_blocked() ||
+	    block_console_kthreads ||
 	    system_state > SYSTEM_RUNNING ||
 	    oops_in_progress) {
 		return false;

kernel/printk/printk_safe.c

@@ -8,7 +8,9 @@
 #include <linux/smp.h>
 #include <linux/cpumask.h>
 #include <linux/printk.h>
+#include <linux/console.h>
 #include <linux/kprobes.h>
+#include <linux/delay.h>
 
 #include "internal.h"
 
@@ -50,3 +52,33 @@ asmlinkage int vprintk(const char *fmt, va_list args)
 	return vprintk_default(fmt, args);
 }
 EXPORT_SYMBOL(vprintk);
+
+/**
+ * try_block_console_kthreads() - Try to block console kthreads and
+ *	make the global console_lock() avaialble
+ *
+ * @timeout_ms:        The maximum time (in ms) to wait.
+ *
+ * Prevent console kthreads from starting processing new messages. Wait
+ * until the global console_lock() become available.
+ *
+ * Context: Can be called in any context.
+ */
+void try_block_console_kthreads(int timeout_ms)
+{
+	block_console_kthreads = true;
+
+	/* Do not wait when the console lock could not be safely taken. */
+	if (this_cpu_read(printk_context) || in_nmi())
+		return;
+
+	while (timeout_ms > 0) {
+		if (console_trylock()) {
+			console_unlock();
+			return;
+		}
+
+		udelay(1000);
+		timeout_ms -= 1;
+	}
+}

kernel/reboot.c

@@ -74,6 +74,7 @@ void kernel_restart_prepare(char *cmd)
 {
 	blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
 	system_state = SYSTEM_RESTART;
+	try_block_console_kthreads(10000);
 	usermodehelper_disable();
 	device_shutdown();
 }
@@ -262,6 +263,7 @@ static void kernel_shutdown_prepare(enum system_states state)
 	blocking_notifier_call_chain(&reboot_notifier_list,
 		(state == SYSTEM_HALT) ? SYS_HALT : SYS_POWER_OFF, NULL);
 	system_state = state;
+	try_block_console_kthreads(10000);
 	usermodehelper_disable();
 	device_shutdown();
 }