Received-SPF: pass (google.com: domain of linux-kernel+bounces-128779-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
From: John Ogness <john.ogness@linutronix.de>
To: Petr Mladek <pmladek@suse.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	linux-kernel@vger.kernel.org,
	Andrew Morton <akpm@linux-foundation.org>,
	Josh Poimboeuf <jpoimboe@kernel.org>,
	"Peter Zijlstra (Intel)" <peterz@infradead.org>,
	Lukas Wunner <lukas@wunner.de>,
	Arnd Bergmann <arnd@arndb.de>,
	Uros Bizjak <ubizjak@gmail.com>,
	Kefeng Wang <wangkefeng.wang@huawei.com>
Subject: [PATCH printk v4 19/27] printk: nbcon: Add unsafe flushing on panic
Date: Wed,  3 Apr 2024 00:17:21 +0206
Message-Id: <20240402221129.2613843-20-john.ogness@linutronix.de>
In-Reply-To: <20240402221129.2613843-1-john.ogness@linutronix.de>
References: <20240402221129.2613843-1-john.ogness@linutronix.de>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

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>
---
 include/linux/printk.h |  5 +++++
 kernel/panic.c         |  1 +
 kernel/printk/nbcon.c  | 26 +++++++++++++++++++++-----
 3 files changed, 27 insertions(+), 5 deletions(-)

diff --git a/include/linux/printk.h b/include/linux/printk.h
index 0ad3ee752635..866683a293af 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -197,6 +197,7 @@ extern asmlinkage void dump_stack(void) __cold;
 void printk_trigger_flush(void);
 extern void nbcon_driver_acquire(struct console *con);
 extern void nbcon_driver_release(struct console *con);
+void nbcon_atomic_flush_unsafe(void);
 #else
 static inline __printf(1, 0)
 int vprintk(const char *s, va_list args)
@@ -285,6 +286,10 @@ static inline void nbcon_driver_release(struct console *con)
 {
 }
 
+static inline void nbcon_atomic_flush_unsafe(void)
+{
+}
+
 #endif
 
 bool this_cpu_in_panic(void);
diff --git a/kernel/panic.c b/kernel/panic.c
index f22d8f33ea14..c039f8e1ddae 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -453,6 +453,7 @@ 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) {
diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c
index fe5a96ab1f40..47f39402a22b 100644
--- a/kernel/printk/nbcon.c
+++ b/kernel/printk/nbcon.c
@@ -1033,6 +1033,7 @@ 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:	True if taken over while printing. Otherwise false.
  *
@@ -1041,7 +1042,8 @@ bool nbcon_legacy_emit_next_record(struct console *con, bool *handover,
  * there are no more records available to read or this context is not allowed
  * to acquire the console.
  */
-static bool __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq)
+static bool __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);
@@ -1049,6 +1051,7 @@ static bool __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 false;
@@ -1075,8 +1078,9 @@ static bool __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq)
  * __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;
 	bool should_retry;
@@ -1109,8 +1113,8 @@ static void __nbcon_atomic_flush_pending(u64 stop_seq)
 			 */
 			local_irq_save(irq_flags);
 
-			should_retry |= __nbcon_atomic_flush_pending_con(con, stop_seq);
-
+			should_retry |= __nbcon_atomic_flush_pending_con(con, stop_seq,
+									 allow_unsafe_takeover);
 			local_irq_restore(irq_flags);
 		}
 		console_srcu_read_unlock(cookie);
@@ -1127,7 +1131,19 @@ 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);
 }
 
 /**
-- 
2.39.2