printk: nbcon: Introduce printer kthreads

Provide the main implementation for running a printer kthread
per nbcon console that is takeover/handover aware. This
includes:

- new mandatory write_thread() callback
- kthread creation
- kthread main printing loop
- kthread wakeup mechanism
- kthread shutdown

kthread creation is a bit tricky because consoles may register
before kthreads can be created. In such cases, registration
will succeed, even though no kthread exists. Once kthreads can
be created, an early_initcall will set @printk_kthreads_ready.
If there are no registered boot consoles, the early_initcall
creates the kthreads for all registered nbcon consoles. If
kthread creation fails, the related console is unregistered.

If there are registered boot consoles when
@printk_kthreads_ready is set, no kthreads are created until
the final boot console unregisters.

Once kthread creation finally occurs, @printk_kthreads_running
is set so that the system knows kthreads are available for all
registered nbcon consoles.

If @printk_kthreads_running is already set when the console
is registering, the kthread is created during registration. If
kthread creation fails, the registration will fail.

Until @printk_kthreads_running is set, console printing occurs
directly via the console_lock.

kthread shutdown on system shutdown/reboot is necessary to
ensure the printer kthreads finish their printing so that the
system can cleanly transition back to direct printing via the
console_lock in order to reliably push out the final
shutdown/reboot messages. @printk_kthreads_running is cleared
before shutting down the individual kthreads.

The kthread uses a new mandatory write_thread() callback that
is called with both device_lock() and the console context
acquired.

The console ownership handling is necessary for synchronization
against write_atomic() which is synchronized only via the
console context ownership.

The device_lock() serializes acquiring the console context with
NBCON_PRIO_NORMAL. It is needed in case the device_lock() does
not disable preemption. It prevents the following race:

CPU0				CPU1

 [ task A ]

 nbcon_context_try_acquire()
   # success with NORMAL prio
   # .unsafe == false;  // safe for takeover

 [ schedule: task A -> B ]

				WARN_ON()
				  nbcon_atomic_flush_pending()
				    nbcon_context_try_acquire()
				      # success with EMERGENCY prio

				      # flushing
				      nbcon_context_release()

				      # HERE: con->nbcon_state is free
				      #       to take by anyone !!!

 nbcon_context_try_acquire()
   # success with NORMAL prio [ task B ]

 [ schedule: task B -> A ]

 nbcon_enter_unsafe()
   nbcon_context_can_proceed()

BUG: nbcon_context_can_proceed() returns "true" because
     the console is owned by a context on CPU0 with
     NBCON_PRIO_NORMAL.

     But it should return "false". The console is owned
     by a context from task B and we do the check
     in a context from task A.

Note that with these changes, the printer kthreads do not yet
take over full responsibility for nbcon printing during normal
operation. These changes only focus on the lifecycle of the
kthreads.

Co-developed-by: John Ogness <[email protected]>
Signed-off-by: John Ogness <[email protected]>
Signed-off-by: Thomas Gleixner (Intel) <[email protected]>
Reviewed-by: Petr Mladek <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Petr Mladek <[email protected]>

Author: KAGA-KOKO

include/linux/console.h

@@ -16,7 +16,9 @@
 
 #include <linux/atomic.h>
 #include <linux/bits.h>
+#include <linux/irq_work.h>
 #include <linux/rculist.h>
+#include <linux/rcuwait.h>
 #include <linux/types.h>
 #include <linux/vesa.h>
 
@@ -324,6 +326,9 @@ struct nbcon_write_context {
  * @nbcon_seq:		Sequence number of the next record for nbcon to print
  * @nbcon_device_ctxt:	Context available for non-printing operations
  * @pbufs:		Pointer to nbcon private buffer
+ * @kthread:		Printer kthread for this console
+ * @rcuwait:		RCU-safe wait object for @kthread waking
+ * @irq_work:		Defer @kthread waking to IRQ work context
  */
 struct console {
 	char			name[16];
@@ -377,6 +382,37 @@ struct console {
 	 */
 	void (*write_atomic)(struct console *con, struct nbcon_write_context *wctxt);
 
+	/**
+	 * @write_thread:
+	 *
+	 * NBCON callback to write out text in task context.
+	 *
+	 * This callback must be called only in task context with both
+	 * device_lock() and the nbcon console acquired with
+	 * NBCON_PRIO_NORMAL.
+	 *
+	 * The same rules for console ownership verification and unsafe
+	 * sections handling applies as with write_atomic().
+	 *
+	 * The console ownership handling is necessary for synchronization
+	 * against write_atomic() which is synchronized only via the context.
+	 *
+	 * The device_lock() provides the primary serialization for operations
+	 * on the device. It might be as relaxed (mutex)[*] or as tight
+	 * (disabled preemption and interrupts) as needed. It allows
+	 * the kthread to operate in the least restrictive mode[**].
+	 *
+	 * [*] Standalone nbcon_context_try_acquire() is not safe with
+	 *     the preemption enabled, see nbcon_owner_matches(). But it
+	 *     can be safe when always called in the preemptive context
+	 *     under the device_lock().
+	 *
+	 * [**] The device_lock() makes sure that nbcon_context_try_acquire()
+	 *      would never need to spin which is important especially with
+	 *      PREEMPT_RT.
+	 */
+	void (*write_thread)(struct console *con, struct nbcon_write_context *wctxt);
+
 	/**
 	 * @device_lock:
 	 *
@@ -423,7 +459,11 @@ struct console {
 	atomic_t		__private nbcon_state;
 	atomic_long_t		__private nbcon_seq;
 	struct nbcon_context	__private nbcon_device_ctxt;
+
 	struct printk_buffers	*pbufs;
+	struct task_struct	*kthread;
+	struct rcuwait		rcuwait;
+	struct irq_work		irq_work;
 };
 
 #ifdef CONFIG_LOCKDEP

kernel/printk/internal.h

@@ -48,6 +48,7 @@ struct printk_ringbuffer;
 struct dev_printk_info;
 
 extern struct printk_ringbuffer *prb;
+extern bool printk_kthreads_running;
 
 __printf(4, 0)
 int vprintk_store(int facility, int level,
@@ -90,6 +91,9 @@ enum nbcon_prio nbcon_get_default_prio(void);
 void nbcon_atomic_flush_pending(void);
 bool nbcon_legacy_emit_next_record(struct console *con, bool *handover,
 				   int cookie);
+bool nbcon_kthread_create(struct console *con);
+void nbcon_kthread_stop(struct console *con);
+void nbcon_kthreads_wake(void);
 
 /*
  * Check if the given console is currently capable and allowed to print
@@ -125,12 +129,34 @@ static inline bool console_is_usable(struct console *con, short flags, bool use_
 	return true;
 }
 
+/**
+ * nbcon_kthread_wake - Wake up a console printing thread
+ * @con:	Console to operate on
+ */
+static inline void nbcon_kthread_wake(struct console *con)
+{
+	/*
+	 * Guarantee any new records can be seen by tasks preparing to wait
+	 * before this context checks if the rcuwait is empty.
+	 *
+	 * The full memory barrier in rcuwait_wake_up() pairs with the full
+	 * memory barrier within set_current_state() of
+	 * ___rcuwait_wait_event(), which is called after prepare_to_rcuwait()
+	 * adds the waiter but before it has checked the wait condition.
+	 *
+	 * This pairs with nbcon_kthread_func:A.
+	 */
+	rcuwait_wake_up(&con->rcuwait); /* LMM(nbcon_kthread_wake:A) */
+}
+
 #else
 
 #define PRINTK_PREFIX_MAX	0
 #define PRINTK_MESSAGE_MAX	0
 #define PRINTKRB_RECORD_MAX	0
 
+#define printk_kthreads_running (false)
+
 /*
  * In !PRINTK builds we still export console_sem
  * semaphore and some of console functions (console_unlock()/etc.), so
@@ -149,6 +175,7 @@ static inline enum nbcon_prio nbcon_get_default_prio(void) { return NBCON_PRIO_N
 static inline void nbcon_atomic_flush_pending(void) { }
 static inline bool nbcon_legacy_emit_next_record(struct console *con, bool *handover,
 						 int cookie) { return false; }
+static inline void nbcon_kthread_wake(struct console *con) { }
 
 static inline bool console_is_usable(struct console *con, short flags,
 				     bool use_atomic) { return false; }