Merge branch 'for-5.18-panic-deadlocks' into for-linus

1 files changed, 54 insertions, 1 deletions

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 21fb4e1cd7db..49aa47e876db 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -93,6 +93,12 @@ EXPORT_SYMBOL_GPL(console_drivers);
  */
 int __read_mostly suppress_printk;
 
+/*
+ * During panic, heavy printk by other CPUs can delay the
+ * panic and risk deadlock on console resources.
+ */
+static int __read_mostly suppress_panic_printk;
+
 #ifdef CONFIG_LOCKDEP
 static struct lockdep_map console_lock_dep_map = {
 	.name = "console_lock"
@@ -258,6 +264,11 @@ static void __up_console_sem(unsigned long ip)
 }
 #define up_console_sem() __up_console_sem(_RET_IP_)
 
+static bool panic_in_progress(void)
+{
+	return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID);
+}
+
 /*
  * This is used for debugging the mess that is the VT code by
  * keeping track if we have the console semaphore held. It's
@@ -1844,6 +1855,16 @@ static int console_trylock_spinning(void)
 	if (console_trylock())
 		return 1;
 
+	/*
+	 * It's unsafe to spin once a panic has begun. If we are the
+	 * panic CPU, we may have already halted the owner of the
+	 * console_sem. If we are not the panic CPU, then we should
+	 * avoid taking console_sem, so the panic CPU has a better
+	 * chance of cleanly acquiring it later.
+	 */
+	if (panic_in_progress())
+		return 0;
+
 	printk_safe_enter_irqsave(flags);
 
 	raw_spin_lock(&console_owner_lock);
@@ -2219,6 +2240,10 @@ asmlinkage int vprintk_emit(int facility, int level,
 	if (unlikely(suppress_printk))
 		return 0;
 
+	if (unlikely(suppress_panic_printk) &&
+	    atomic_read(&panic_cpu) != raw_smp_processor_id())
+		return 0;
+
 	if (level == LOGLEVEL_SCHED) {
 		level = LOGLEVEL_DEFAULT;
 		in_sched = true;
@@ -2587,6 +2612,25 @@ static int have_callable_console(void)
 }
 
 /*
+ * Return true when this CPU should unlock console_sem without pushing all
+ * messages to the console. This reduces the chance that the console is
+ * locked when the panic CPU tries to use it.
+ */
+static bool abandon_console_lock_in_panic(void)
+{
+	if (!panic_in_progress())
+		return false;
+
+	/*
+	 * We can use raw_smp_processor_id() here because it is impossible for
+	 * the task to be migrated to the panic_cpu, or away from it. If
+	 * panic_cpu has already been set, and we're not currently executing on
+	 * that CPU, then we never will be.
+	 */
+	return atomic_read(&panic_cpu) != raw_smp_processor_id();
+}
+
+/*
  * Can we actually use the console at this time on this cpu?
  *
  * Console drivers may assume that per-cpu resources have been allocated. So
@@ -2616,6 +2660,7 @@ void console_unlock(void)
 {
 	static char ext_text[CONSOLE_EXT_LOG_MAX];
 	static char text[CONSOLE_LOG_MAX];
+	static int panic_console_dropped;
 	unsigned long flags;
 	bool do_cond_resched, retry;
 	struct printk_info info;
@@ -2670,6 +2715,10 @@ skip:
 		if (console_seq != r.info->seq) {
 			console_dropped += r.info->seq - console_seq;
 			console_seq = r.info->seq;
+			if (panic_in_progress() && panic_console_dropped++ > 10) {
+				suppress_panic_printk = 1;
+				pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n");
+			}
 		}
 
 		if (suppress_message_printing(r.info->level)) {
@@ -2729,6 +2778,10 @@ skip:
 		if (handover)
 			return;
 
+		/* Allow panic_cpu to take over the consoles safely */
+		if (abandon_console_lock_in_panic())
+			break;
+
 		if (do_cond_resched)
 			cond_resched();
 	}
@@ -2746,7 +2799,7 @@ skip:
 	 * flush, no worries.
 	 */
 	retry = prb_read_valid(prb, next_seq, NULL);
-	if (retry && console_trylock())
+	if (retry && !abandon_console_lock_in_panic() && console_trylock())
 		goto again;
 }
 EXPORT_SYMBOL(console_unlock);