[PATCH printk v1 1/1] printk: Avoid scheduling irq_work on suspend

[John Ogness <john.ogness@linutronix.de>]

Allowing irq_work to be scheduled while trying to suspend has shown
to cause problems as some architectures interpret the pending
interrupts as a reason to not suspend. This became a problem for
printk() with the introduction of NBCON consoles. With every
printk() call, NBCON console printing kthreads are woken by queueing
irq_work. This means that irq_work continues to be queued due to
printk() calls late in the suspend procedure.

Avoid this problem by preventing printk() from queueing irq_work
once console suspending has begun. This applies to triggering NBCON
and legacy deferred printing as well as klogd waiters.

Since triggering of NBCON threaded printing relies on irq_work, the
pr_flush() within console_suspend_all() is used to perform the final
flushing before suspending consoles and blocking irq_work queueing.
NBCON consoles that are not suspended (due to the usage of the
"no_console_suspend" boot argument) transition to atomic flushing.

Introduce a new global variable @console_offload_blocked to flag
when irq_work queueing is to be avoided. The flag is used by
printk_get_console_flush_type() to avoid allowing deferred printing
and switch NBCON consoles to atomic flushing. It is also used by
vprintk_emit() to avoid klogd waking.

Cc: <stable@vger.kernel.org> # 6.13.x because no drivers in 6.12.x
Fixes: 6b93bb41f6ea ("printk: Add non-BKL (nbcon) console basic infrastructure")
Closes: https://lore.kernel.org/lkml/DB9PR04MB8429E7DDF2D93C2695DE401D92C4A@DB9PR04MB8429.eurprd04.prod.outlook.com
Signed-off-by: John Ogness <john.ogness@linutronix.de>
---
 kernel/printk/internal.h |  8 ++++---
 kernel/printk/printk.c   | 51 ++++++++++++++++++++++++++++------------
 2 files changed, 41 insertions(+), 18 deletions(-)

diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index f72bbfa266d6c..b20929b7d71f5 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -230,6 +230,8 @@ struct console_flush_type {
 	bool	legacy_offload;
 };
 
+extern bool console_irqwork_blocked;
+
 /*
  * Identify which console flushing methods should be used in the context of
  * the caller.
@@ -241,7 +243,7 @@ static inline void printk_get_console_flush_type(struct console_flush_type *ft)
 	switch (nbcon_get_default_prio()) {
 	case NBCON_PRIO_NORMAL:
 		if (have_nbcon_console && !have_boot_console) {
-			if (printk_kthreads_running)
+			if (printk_kthreads_running && !console_irqwork_blocked)
 				ft->nbcon_offload = true;
 			else
 				ft->nbcon_atomic = true;
@@ -251,7 +253,7 @@ static inline void printk_get_console_flush_type(struct console_flush_type *ft)
 		if (have_legacy_console || have_boot_console) {
 			if (!is_printk_legacy_deferred())
 				ft->legacy_direct = true;
-			else
+			else if (!console_irqwork_blocked)
 				ft->legacy_offload = true;
 		}
 		break;
@@ -264,7 +266,7 @@ static inline void printk_get_console_flush_type(struct console_flush_type *ft)
 		if (have_legacy_console || have_boot_console) {
 			if (!is_printk_legacy_deferred())
 				ft->legacy_direct = true;
-			else
+			else if (!console_irqwork_blocked)
 				ft->legacy_offload = true;
 		}
 		break;
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 5aee9ffb16b9a..94fc4a8662d4b 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -462,6 +462,9 @@ bool have_boot_console;
 /* See printk_legacy_allow_panic_sync() for details. */
 bool legacy_allow_panic_sync;
 
+/* Avoid using irq_work when suspending. */
+bool console_irqwork_blocked;
+
 #ifdef CONFIG_PRINTK
 DECLARE_WAIT_QUEUE_HEAD(log_wait);
 static DECLARE_WAIT_QUEUE_HEAD(legacy_wait);
@@ -2426,7 +2429,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 
 	if (ft.legacy_offload)
 		defer_console_output();
-	else
+	else if (!console_irqwork_blocked)
 		wake_up_klogd();
 
 	return printed_len;
@@ -2730,10 +2733,20 @@ void console_suspend_all(void)
 {
 	struct console *con;
 
+	if (console_suspend_enabled)
+		pr_info("Suspending console(s) (use no_console_suspend to debug)\n");
+
+	/*
+	 * Flush any console backlog and then avoid queueing irq_work until
+	 * console_resume_all(). Until then deferred printing is no longer
+	 * triggered, NBCON consoles transition to atomic flushing, and
+	 * any klogd waiters are not triggered.
+	 */
+	pr_flush(1000, true);
+	console_irqwork_blocked = true;
+
 	if (!console_suspend_enabled)
 		return;
-	pr_info("Suspending console(s) (use no_console_suspend to debug)\n");
-	pr_flush(1000, true);
 
 	console_list_lock();
 	for_each_console(con)
@@ -2754,26 +2767,34 @@ void console_resume_all(void)
 	struct console_flush_type ft;
 	struct console *con;
 
-	if (!console_suspend_enabled)
-		return;
-
-	console_list_lock();
-	for_each_console(con)
-		console_srcu_write_flags(con, con->flags & ~CON_SUSPENDED);
-	console_list_unlock();
-
 	/*
-	 * Ensure that all SRCU list walks have completed. All printing
-	 * contexts must be able to see they are no longer suspended so
-	 * that they are guaranteed to wake up and resume printing.
+	 * Allow queueing irq_work. After restoring console state, deferred
+	 * printing and any klogd waiters need to be triggered in case there
+	 * is now a console backlog.
 	 */
-	synchronize_srcu(&console_srcu);
+	console_irqwork_blocked = false;
+
+	if (console_suspend_enabled) {
+		console_list_lock();
+		for_each_console(con)
+			console_srcu_write_flags(con, con->flags & ~CON_SUSPENDED);
+		console_list_unlock();
+
+		/*
+		 * Ensure that all SRCU list walks have completed. All printing
+		 * contexts must be able to see they are no longer suspended so
+		 * that they are guaranteed to wake up and resume printing.
+		 */
+		synchronize_srcu(&console_srcu);
+	}
 
 	printk_get_console_flush_type(&ft);
 	if (ft.nbcon_offload)
 		nbcon_kthreads_wake();
 	if (ft.legacy_offload)
 		defer_console_output();
+	else
+		wake_up_klogd();
 
 	pr_flush(1000, true);
 }
-- 
2.47.3