[PATCH printk v6 25/30] printk: Coordinate direct printing in panic

[John Ogness]

Perform printing by nbcon consoles on the panic CPU from the
printk() caller context in order to get panic messages printed
as soon as possible.

If legacy and nbcon consoles are registered, the legacy consoles
will no longer perform direct printing on the panic CPU until
after the backtrace has been stored. This will give the safe
nbcon consoles a chance to print the panic messages before
allowing the unsafe legacy consoles to print.

If no nbcon consoles are registered, there is no change in
behavior (i.e. legacy consoles will always attempt to print
from the printk() caller context).

Signed-off-by: John Ogness <john.ogness@xxxxxxxxxxxxx>
Reviewed-by: Petr Mladek <pmladek@xxxxxxxx>
---
 include/linux/printk.h |  5 ++++
 kernel/panic.c         |  2 ++
 kernel/printk/printk.c | 62 ++++++++++++++++++++++++++++++++++++------
 3 files changed, 61 insertions(+), 8 deletions(-)

diff --git a/include/linux/printk.h b/include/linux/printk.h
index 4d93d95cd5f0..69f40a71c438 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -195,6 +195,7 @@ void show_regs_print_info(const char *log_lvl);
 extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold;
 extern asmlinkage void dump_stack(void) __cold;
 void printk_trigger_flush(void);
+void printk_legacy_allow_panic_sync(void);
 extern bool nbcon_device_try_acquire(struct console *con);
 extern void nbcon_device_release(struct console *con);
 void nbcon_atomic_flush_unsafe(void);
@@ -278,6 +279,10 @@ static inline void printk_trigger_flush(void)
 {
 }
 
+static inline void printk_legacy_allow_panic_sync(void)
+{
+}
+
 static inline bool nbcon_device_try_acquire(struct console *con)
 {
 	return false;
diff --git a/kernel/panic.c b/kernel/panic.c
index c039f8e1ddae..de8115c829cf 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -364,6 +364,8 @@ void panic(const char *fmt, ...)
 
 	panic_other_cpus_shutdown(_crash_kexec_post_notifiers);
 
+	printk_legacy_allow_panic_sync();
+
 	/*
 	 * Run any panic handlers, including those that might need to
 	 * add information to the kmsg dump output.
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index d087711242de..57e190fbecd7 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -471,7 +471,9 @@ static DEFINE_MUTEX(syslog_lock);
 static bool have_legacy_console;
 
 /*
- * Specifies if an nbcon console is registered.
+ * Specifies if an nbcon console is registered. If nbcon consoles are present,
+ * synchronous printing of legacy consoles will not occur during panic until
+ * the backtrace has been stored to the ringbuffer.
  */
 static bool have_nbcon_console;
 
@@ -2330,12 +2332,29 @@ int vprintk_store(int facility, int level,
 	return ret;
 }
 
+static bool legacy_allow_panic_sync;
+
+/*
+ * This acts as a one-way switch to allow legacy consoles to print from
+ * the printk() caller context on a panic CPU. It also attempts to flush
+ * the legacy consoles in this context.
+ */
+void printk_legacy_allow_panic_sync(void)
+{
+	legacy_allow_panic_sync = true;
+
+	if (printing_via_unlock && !in_nmi()) {
+		if (console_trylock())
+			console_unlock();
+	}
+}
+
 asmlinkage int vprintk_emit(int facility, int level,
 			    const struct dev_printk_info *dev_info,
 			    const char *fmt, va_list args)
 {
+	bool do_trylock_unlock = printing_via_unlock;
 	int printed_len;
-	bool in_sched = false;
 
 	/* Suppress unimportant messages after panic happens */
 	if (unlikely(suppress_printk))
@@ -2351,15 +2370,42 @@ asmlinkage int vprintk_emit(int facility, int level,
 
 	if (level == LOGLEVEL_SCHED) {
 		level = LOGLEVEL_DEFAULT;
-		in_sched = true;
+		/* If called from the scheduler, we can not call up(). */
+		do_trylock_unlock = false;
 	}
 
 	printk_delay(level);
 
 	printed_len = vprintk_store(facility, level, dev_info, fmt, args);
 
-	/* If called from the scheduler, we can not call up(). */
-	if (!in_sched && printing_via_unlock) {
+	if (have_nbcon_console && !have_boot_console) {
+		bool is_panic_context = this_cpu_in_panic();
+
+		/*
+		 * In panic, the legacy consoles are not allowed to print from
+		 * the printk calling context unless explicitly allowed. This
+		 * gives the safe nbcon consoles a chance to print out all the
+		 * panic messages first. This restriction only applies if
+		 * there are nbcon consoles registered.
+		 */
+		if (is_panic_context)
+			do_trylock_unlock &= legacy_allow_panic_sync;
+
+		/*
+		 * There are situations where nbcon atomic printing should
+		 * happen in the printk() caller context:
+		 *
+		 * - When this CPU is in panic.
+		 *
+		 * Note that if boot consoles are registered, the console
+		 * lock/unlock dance must be relied upon instead because nbcon
+		 * consoles cannot print simultaneously with boot consoles.
+		 */
+		if (is_panic_context)
+			nbcon_atomic_flush_pending();
+	}
+
+	if (do_trylock_unlock) {
 		/*
 		 * The caller may be holding system-critical or
 		 * timing-sensitive locks. Disable preemption during
@@ -2379,10 +2425,10 @@ asmlinkage int vprintk_emit(int facility, int level,
 		preempt_enable();
 	}
 
-	if (in_sched)
-		defer_console_output();
-	else
+	if (do_trylock_unlock)
 		wake_up_klogd();
+	else
+		defer_console_output();
 
 	return printed_len;
 }
-- 
2.39.2