printk: nbcon: Add unsafe flushing on panic

Add nbcon_atomic_flush_unsafe() to flush all nbcon consoles
using the write_atomic() callback and allowing unsafe hostile
takeovers. Call this at the end of panic() as a final attempt
to flush any pending messages.

Note that legacy consoles use unsafe methods for flushing
from the beginning of panic (see bust_spinlocks()). Therefore,
systems using both legacy and nbcon consoles may still fail to
see panic messages due to unsafe legacy console usage.

Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20240820063001.36405-27-john.ogness@linutronix.de
Signed-off-by: Petr Mladek <pmladek@suse.com>

include/linux/printk.h

@@ -202,6 +202,7 @@ void printk_trigger_flush(void);
 void console_try_replay_all(void);
 extern bool nbcon_device_try_acquire(struct console *con);
 extern void nbcon_device_release(struct console *con);
+void nbcon_atomic_flush_unsafe(void);
 #else
 static inline __printf(1, 0)
 int vprintk(const char *s, va_list args)
@@ -294,6 +295,10 @@ static inline void nbcon_device_release(struct console *con)
 {
 }
 
+static inline void nbcon_atomic_flush_unsafe(void)
+{
+}
+
 #endif
 
 bool this_cpu_in_panic(void);

kernel/panic.c

@@ -463,6 +463,7 @@ void panic(const char *fmt, ...)
 	 * Explicitly flush the kernel log buffer one last time.
 	 */
 	console_flush_on_panic(CONSOLE_FLUSH_PENDING);
+	nbcon_atomic_flush_unsafe();
 
 	local_irq_enable();
 	for (i = 0; ; i += PANIC_TIMER_STEP) {

kernel/printk/nbcon.c

@@ -1083,6 +1083,7 @@ bool nbcon_legacy_emit_next_record(struct console *con, bool *handover,
  *					write_atomic() callback
  * @con:			The nbcon console to flush
  * @stop_seq:			Flush up until this record
+ * @allow_unsafe_takeover:	True, to allow unsafe hostile takeovers
  *
  * Return:	0 if @con was flushed up to @stop_seq Otherwise, error code on
  *		failure.
@@ -1101,7 +1102,8 @@ bool nbcon_legacy_emit_next_record(struct console *con, bool *handover,
  * returned, it cannot be expected that the unfinalized record will become
  * available.
  */
-static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq)
+static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq,
+					    bool allow_unsafe_takeover)
 {
 	struct nbcon_write_context wctxt = { };
 	struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt);
@@ -1110,6 +1112,7 @@ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq)
 	ctxt->console			= con;
 	ctxt->spinwait_max_us		= 2000;
 	ctxt->prio			= nbcon_get_default_prio();
+	ctxt->allow_unsafe_takeover	= allow_unsafe_takeover;
 
 	if (!nbcon_context_try_acquire(ctxt))
 		return -EPERM;
@@ -1140,13 +1143,15 @@ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq)
  *					write_atomic() callback
  * @con:			The nbcon console to flush
  * @stop_seq:			Flush up until this record
+ * @allow_unsafe_takeover:	True, to allow unsafe hostile takeovers
  *
  * This will stop flushing before @stop_seq if another context has ownership.
  * That context is then responsible for the flushing. Likewise, if new records
  * are added while this context was flushing and there is no other context
  * to handle the printing, this context must also flush those records.
  */
-static void nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq)
+static void nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq,
+					   bool allow_unsafe_takeover)
 {
 	unsigned long flags;
 	int err;
@@ -1160,7 +1165,7 @@ again:
 	 */
 	local_irq_save(flags);
 
-	err = __nbcon_atomic_flush_pending_con(con, stop_seq);
+	err = __nbcon_atomic_flush_pending_con(con, stop_seq, allow_unsafe_takeover);
 
 	local_irq_restore(flags);
 
@@ -1190,8 +1195,9 @@ again:
  * __nbcon_atomic_flush_pending - Flush all nbcon consoles using their
  *					write_atomic() callback
  * @stop_seq:			Flush up until this record
+ * @allow_unsafe_takeover:	True, to allow unsafe hostile takeovers
  */
-static void __nbcon_atomic_flush_pending(u64 stop_seq)
+static void __nbcon_atomic_flush_pending(u64 stop_seq, bool allow_unsafe_takeover)
 {
 	struct console *con;
 	int cookie;
@@ -1209,7 +1215,7 @@ static void __nbcon_atomic_flush_pending(u64 stop_seq)
 		if (nbcon_seq_read(con) >= stop_seq)
 			continue;
 
-		nbcon_atomic_flush_pending_con(con, stop_seq);
+		nbcon_atomic_flush_pending_con(con, stop_seq, allow_unsafe_takeover);
 	}
 	console_srcu_read_unlock(cookie);
 }
@@ -1225,7 +1231,19 @@ static void __nbcon_atomic_flush_pending(u64 stop_seq)
  */
 void nbcon_atomic_flush_pending(void)
 {
-	__nbcon_atomic_flush_pending(prb_next_reserve_seq(prb));
+	__nbcon_atomic_flush_pending(prb_next_reserve_seq(prb), false);
+}
+
+/**
+ * nbcon_atomic_flush_unsafe - Flush all nbcon consoles using their
+ *	write_atomic() callback and allowing unsafe hostile takeovers
+ *
+ * Flush the backlog up through the currently newest record. Unsafe hostile
+ * takeovers will be performed, if necessary.
+ */
+void nbcon_atomic_flush_unsafe(void)
+{
+	__nbcon_atomic_flush_pending(prb_next_reserve_seq(prb), true);
 }
 
 /**
@@ -1342,7 +1360,7 @@ void nbcon_device_release(struct console *con)
 	if (console_is_usable(con, console_srcu_read_flags(con)) &&
 	    prb_read_valid(prb, nbcon_seq_read(con), NULL)) {
 		if (!have_boot_console) {
-			__nbcon_atomic_flush_pending_con(con, prb_next_reserve_seq(prb));
+			__nbcon_atomic_flush_pending_con(con, prb_next_reserve_seq(prb), false);
 		} else if (!is_printk_legacy_deferred()) {
 			if (console_trylock())
 				console_unlock();