Merge tag 'printk-for-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/printk/linux

Pull printk updates from Petr Mladek:

 - Offload writing printk() messages on consoles to per-console
   kthreads.

   It prevents soft-lockups when an extensive amount of messages is
   printed. It was observed, for example, during boot of large systems
   with a lot of peripherals like disks or network interfaces.

   It prevents live-lockups that were observed, for example, when
   messages about allocation failures were reported and a CPU handled
   consoles instead of reclaiming the memory. It was hard to solve even
   with rate limiting because it would need to take into account the
   amount of messages and the speed of all consoles.

   It is a must to have for real time. Otherwise, any printk() might
   break latency guarantees.

   The per-console kthreads allow to handle each console on its own
   speed. Slow consoles do not longer slow down faster ones. And
   printk() does not longer unpredictably slows down various code paths.

   There are situations when the kthreads are either not available or
   not reliable, for example, early boot, suspend, or panic. In these
   situations, printk() uses the legacy mode and tries to handle
   consoles immediately.

 - Add documentation for the printk index.

* tag 'printk-for-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/printk/linux:
  printk, tracing: fix console tracepoint
  printk: remove @console_locked
  printk: extend console_lock for per-console locking
  printk: add kthread console printers
  printk: add functions to prefer direct printing
  printk: add pr_flush()
  printk: move buffer definitions into console_emit_next_record() caller
  printk: refactor and rework printing logic
  printk: add con_printk() macro for console details
  printk: call boot_delay_msec() in printk_delay()
  printk: get caller_id/timestamp after migration disable
  printk: wake waiters for safe and NMI contexts
  printk: wake up all waiters
  printk: add missing memory barrier to wake_up_klogd()
  printk: cpu sync always disable interrupts
  printk: rename cpulock functions
  printk/index: Printk index feature documentation
  MAINTAINERS: Add printk indexing maintainers on mention of printk_index

7 files changed, 953 insertions, 291 deletions

diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 52501e5f7655..02a65d554340 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -127,6 +127,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 	 * complain:
 	 */
 	if (sysctl_hung_task_warnings) {
+		printk_prefer_direct_enter();
+
 		if (sysctl_hung_task_warnings > 0)
 			sysctl_hung_task_warnings--;
 		pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n",
@@ -142,6 +144,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 
 		if (sysctl_hung_task_all_cpu_backtrace)
 			hung_task_show_all_bt = true;
+
+		printk_prefer_direct_exit();
 	}
 
 	touch_nmi_watchdog();
@@ -204,12 +208,17 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
 	}
  unlock:
 	rcu_read_unlock();
-	if (hung_task_show_lock)
+	if (hung_task_show_lock) {
+		printk_prefer_direct_enter();
 		debug_show_all_locks();
+		printk_prefer_direct_exit();
+	}
 
 	if (hung_task_show_all_bt) {
 		hung_task_show_all_bt = false;
+		printk_prefer_direct_enter();
 		trigger_all_cpu_backtrace();
+		printk_prefer_direct_exit();
 	}
 
 	if (hung_task_call_panic)
diff --git a/kernel/panic.c b/kernel/panic.c
index 8355b19676f8..6737b2332275 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -579,6 +579,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 {
 	disable_trace_on_warning();
 
+	printk_prefer_direct_enter();
+
 	if (file)
 		pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n",
 			raw_smp_processor_id(), current->pid, file, line,
@@ -608,6 +610,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 
 	/* Just a warning, don't kill lockdep. */
 	add_taint(taint, LOCKDEP_STILL_OK);
+
+	printk_prefer_direct_exit();
 }
 
 #ifndef __WARN_FLAGS
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index da03c15ecc89..a3e1035929b0 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -224,6 +224,33 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
 static int nr_ext_console_drivers;
 
 /*
+ * Used to synchronize printing kthreads against direct printing via
+ * console_trylock/console_unlock.
+ *
+ * Values:
+ * -1 = console kthreads atomically blocked (via global trylock)
+ *  0 = no kthread printing, console not locked (via trylock)
+ * >0 = kthread(s) actively printing
+ *
+ * Note: For synchronizing against direct printing via
+ *       console_lock/console_unlock, see the @lock variable in
+ *       struct console.
+ */
+static atomic_t console_kthreads_active = ATOMIC_INIT(0);
+
+#define console_kthreads_atomic_tryblock() \
+	(atomic_cmpxchg(&console_kthreads_active, 0, -1) == 0)
+#define console_kthreads_atomic_unblock() \
+	atomic_cmpxchg(&console_kthreads_active, -1, 0)
+#define console_kthreads_atomically_blocked() \
+	(atomic_read(&console_kthreads_active) == -1)
+
+#define console_kthread_printing_tryenter() \
+	atomic_inc_unless_negative(&console_kthreads_active)
+#define console_kthread_printing_exit() \
+	atomic_dec(&console_kthreads_active)
+
+/*
  * Helper macros to handle lockdep when locking/unlocking console_sem. We use
  * macros instead of functions so that _RET_IP_ contains useful information.
  */
@@ -271,19 +298,49 @@ static bool panic_in_progress(void)
 }
 
 /*
- * This is used for debugging the mess that is the VT code by
- * keeping track if we have the console semaphore held. It's
- * definitely not the perfect debug tool (we don't know if _WE_
- * hold it and are racing, but it helps tracking those weird code
- * paths in the console code where we end up in places I want
- * locked without the console semaphore held).
+ * Tracks whether kthread printers are all blocked. A value of true implies
+ * that the console is locked via console_lock() or the console is suspended.
+ * Writing to this variable requires holding @console_sem.
  */
-static int console_locked, console_suspended;
+static bool console_kthreads_blocked;
+
+/*
+ * Block all kthread printers from a schedulable context.
+ *
+ * Requires holding @console_sem.
+ */
+static void console_kthreads_block(void)
+{
+	struct console *con;
+
+	for_each_console(con) {
+		mutex_lock(&con->lock);
+		con->blocked = true;
+		mutex_unlock(&con->lock);
+	}
+
+	console_kthreads_blocked = true;
+}
 
 /*
- * If exclusive_console is non-NULL then only this console is to be printed to.
+ * Unblock all kthread printers from a schedulable context.
+ *
+ * Requires holding @console_sem.
  */
-static struct console *exclusive_console;
+static void console_kthreads_unblock(void)
+{
+	struct console *con;
+
+	for_each_console(con) {
+		mutex_lock(&con->lock);
+		con->blocked = false;
+		mutex_unlock(&con->lock);
+	}
+
+	console_kthreads_blocked = false;
+}
+
+static int console_suspended;
 
 /*
  *	Array of consoles built from command line options (console=)
@@ -366,7 +423,75 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
 /* syslog_lock protects syslog_* variables and write access to clear_seq. */
 static DEFINE_MUTEX(syslog_lock);
 
+/*
+ * A flag to signify if printk_activate_kthreads() has already started the
+ * kthread printers. If true, any later registered consoles must start their
+ * own kthread directly. The flag is write protected by the console_lock.
+ */
+static bool printk_kthreads_available;
+
 #ifdef CONFIG_PRINTK
+static atomic_t printk_prefer_direct = ATOMIC_INIT(0);
+
+/**
+ * printk_prefer_direct_enter - cause printk() calls to attempt direct
+ *                              printing to all enabled consoles
+ *
+ * Since it is not possible to call into the console printing code from any
+ * context, there is no guarantee that direct printing will occur.
+ *
+ * This globally effects all printk() callers.
+ *
+ * Context: Any context.
+ */
+void printk_prefer_direct_enter(void)
+{
+	atomic_inc(&printk_prefer_direct);
+}
+
+/**
+ * printk_prefer_direct_exit - restore printk() behavior
+ *
+ * Context: Any context.
+ */
+void printk_prefer_direct_exit(void)
+{
+	WARN_ON(atomic_dec_if_positive(&printk_prefer_direct) < 0);
+}
+
+/*
+ * Calling printk() always wakes kthread printers so that they can
+ * flush the new message to their respective consoles. Also, if direct
+ * printing is allowed, printk() tries to flush the messages directly.
+ *
+ * Direct printing is allowed in situations when the kthreads
+ * are not available or the system is in a problematic state.
+ *
+ * See the implementation about possible races.
+ */
+static inline bool allow_direct_printing(void)
+{
+	/*
+	 * Checking kthread availability is a possible race because the
+	 * kthread printers can become permanently disabled during runtime.
+	 * However, doing that requires holding the console_lock, so any
+	 * pending messages will be direct printed by console_unlock().
+	 */
+	if (!printk_kthreads_available)
+		return true;
+
+	/*
+	 * Prefer direct printing when the system is in a problematic state.
+	 * The context that sets this state will always see the updated value.
+	 * The other contexts do not care. Anyway, direct printing is just a
+	 * best effort. The direct output is only possible when console_lock
+	 * is not already taken and no kthread printers are actively printing.
+	 */
+	return (system_state > SYSTEM_RUNNING ||
+		oops_in_progress ||
+		atomic_read(&printk_prefer_direct));
+}
+
 DECLARE_WAIT_QUEUE_HEAD(log_wait);
 /* All 3 protected by @syslog_lock. */
 /* the next printk record to read by syslog(READ) or /proc/kmsg */
@@ -374,12 +499,6 @@ static u64 syslog_seq;
 static size_t syslog_partial;
 static bool syslog_time;
 
-/* All 3 protected by @console_sem. */
-/* the next printk record to write to the console */
-static u64 console_seq;
-static u64 exclusive_console_stop_seq;
-static unsigned long console_dropped;
-
 struct latched_seq {
 	seqcount_latch_t	latch;
 	u64			val[2];
@@ -405,6 +524,9 @@ static struct latched_seq clear_seq = {
 /* the maximum size of a formatted record (i.e. with prefix added per line) */
 #define CONSOLE_LOG_MAX		1024
 
+/* the maximum size for a dropped text message */
+#define DROPPED_TEXT_MAX	64
+
 /* the maximum size allowed to be reserved for a record */
 #define LOG_LINE_MAX		(CONSOLE_LOG_MAX - PREFIX_MAX)
 
@@ -746,8 +868,19 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
 			goto out;
 		}
 
+		/*
+		 * Guarantee this task is visible on the waitqueue before
+		 * checking the wake condition.
+		 *
+		 * The full memory barrier within set_current_state() of
+		 * prepare_to_wait_event() pairs with the full memory barrier
+		 * within wq_has_sleeper().
+		 *
+		 * This pairs with __wake_up_klogd:A.
+		 */
 		ret = wait_event_interruptible(log_wait,
-				prb_read_valid(prb, atomic64_read(&user->seq), r));
+				prb_read_valid(prb,
+					atomic64_read(&user->seq), r)); /* LMM(devkmsg_read:A) */
 		if (ret)
 			goto out;
 	}
@@ -1513,7 +1646,18 @@ static int syslog_print(char __user *buf, int size)
 		seq = syslog_seq;
 
 		mutex_unlock(&syslog_lock);
-		len = wait_event_interruptible(log_wait, prb_read_valid(prb, seq, NULL));
+		/*
+		 * Guarantee this task is visible on the waitqueue before
+		 * checking the wake condition.
+		 *
+		 * The full memory barrier within set_current_state() of
+		 * prepare_to_wait_event() pairs with the full memory barrier
+		 * within wq_has_sleeper().
+		 *
+		 * This pairs with __wake_up_klogd:A.
+		 */
+		len = wait_event_interruptible(log_wait,
+				prb_read_valid(prb, seq, NULL)); /* LMM(syslog_print:A) */
 		mutex_lock(&syslog_lock);
 
 		if (len)
@@ -1911,47 +2055,24 @@ static int console_trylock_spinning(void)
 }
 
 /*
- * Call the console drivers, asking them to write out
- * log_buf[start] to log_buf[end - 1].
- * The console_lock must be held.
+ * Call the specified console driver, asking it to write out the specified
+ * text and length. If @dropped_text is non-NULL and any records have been
+ * dropped, a dropped message will be written out first.
  */
-static void call_console_drivers(const char *ext_text, size_t ext_len,
-				 const char *text, size_t len)
+static void call_console_driver(struct console *con, const char *text, size_t len,
+				char *dropped_text)
 {
-	static char dropped_text[64];
-	size_t dropped_len = 0;
-	struct console *con;
-
-	trace_console_rcuidle(text, len);
+	size_t dropped_len;
 
-	if (!console_drivers)
-		return;
-
-	if (console_dropped) {
-		dropped_len = snprintf(dropped_text, sizeof(dropped_text),
+	if (con->dropped && dropped_text) {
+		dropped_len = snprintf(dropped_text, DROPPED_TEXT_MAX,
 				       "** %lu printk messages dropped **\n",
-				       console_dropped);
-		console_dropped = 0;
+				       con->dropped);
+		con->dropped = 0;
+		con->write(con, dropped_text, dropped_len);
 	}
 
-	for_each_console(con) {
-		if (exclusive_console && con != exclusive_console)
-			continue;
-		if (!(con->flags & CON_ENABLED))
-			continue;
-		if (!con->write)
-			continue;
-		if (!cpu_online(smp_processor_id()) &&
-		    !(con->flags & CON_ANYTIME))
-			continue;
-		if (con->flags & CON_EXTENDED)
-			con->write(con, ext_text, ext_len);
-		else {
-			if (dropped_len)
-				con->write(con, dropped_text, dropped_len);
-			con->write(con, text, len);
-		}
-	}
+	con->write(con, text, len);
 }
 
 /*
@@ -2026,8 +2147,10 @@ static u8 *__printk_recursion_counter(void)
 
 int printk_delay_msec __read_mostly;
 
-static inline void printk_delay(void)
+static inline void printk_delay(int level)
 {
+	boot_delay_msec(level);
+
 	if (unlikely(printk_delay_msec)) {
 		int m = printk_delay_msec;
 
@@ -2041,7 +2164,7 @@ static inline void printk_delay(void)
 static inline u32 printk_caller_id(void)
 {
 	return in_task() ? task_pid_nr(current) :
-		0x80000000 + raw_smp_processor_id();
+		0x80000000 + smp_processor_id();
 }
 
 /**
@@ -2115,6 +2238,8 @@ static u16 printk_sprint(char *text, u16 size, int facility,
 		}
 	}
 
+	trace_console_rcuidle(text, text_len);
+
 	return text_len;
 }
 
@@ -2123,7 +2248,6 @@ int vprintk_store(int facility, int level,
 		  const struct dev_printk_info *dev_info,
 		  const char *fmt, va_list args)
 {
-	const u32 caller_id = printk_caller_id();
 	struct prb_reserved_entry e;
 	enum printk_info_flags flags = 0;
 	struct printk_record r;
@@ -2133,10 +2257,14 @@ int vprintk_store(int facility, int level,
 	u8 *recursion_ptr;
 	u16 reserve_size;
 	va_list args2;
+	u32 caller_id;
 	u16 text_len;
 	int ret = 0;
 	u64 ts_nsec;
 
+	if (!printk_enter_irqsave(recursion_ptr, irqflags))
+		return 0;
+
 	/*
 	 * Since the duration of printk() can vary depending on the message
 	 * and state of the ringbuffer, grab the timestamp now so that it is
@@ -2145,8 +2273,7 @@ int vprintk_store(int facility, int level,
 	 */
 	ts_nsec = local_clock();
 
-	if (!printk_enter_irqsave(recursion_ptr, irqflags))
-		return 0;
+	caller_id = printk_caller_id();
 
 	/*
 	 * The sprintf needs to come first since the syslog prefix might be
@@ -2250,23 +2377,25 @@ asmlinkage int vprintk_emit(int facility, int level,
 		in_sched = true;
 	}
 
-	boot_delay_msec(level);
-	printk_delay();
+	printk_delay(level);
 
 	printed_len = vprintk_store(facility, level, dev_info, fmt, args);
 
 	/* If called from the scheduler, we can not call up(). */
-	if (!in_sched) {
+	if (!in_sched && allow_direct_printing()) {
 		/*
-		 * Disable preemption to avoid being preempted while holding
-		 * console_sem which would prevent anyone from printing to
-		 * console
+		 * The caller may be holding system-critical or
+		 * timing-sensitive locks. Disable preemption during direct
+		 * printing of all remaining records to all consoles so that
+		 * this context can return as soon as possible. Hopefully
+		 * another printk() caller will take over the printing.
 		 */
 		preempt_disable();
 		/*
 		 * Try to acquire and then immediately release the console
-		 * semaphore.  The release will print out buffers and wake up
-		 * /dev/kmsg and syslog() users.
+		 * semaphore. The release will print out buffers. With the
+		 * spinning variant, this context tries to take over the
+		 * printing from another printing context.
 		 */
 		if (console_trylock_spinning())
 			console_unlock();
@@ -2297,18 +2426,21 @@ asmlinkage __visible int _printk(const char *fmt, ...)
 }
 EXPORT_SYMBOL(_printk);
 
+static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress);
+
+static void printk_start_kthread(struct console *con);
+
 #else /* CONFIG_PRINTK */
 
 #define CONSOLE_LOG_MAX		0
+#define DROPPED_TEXT_MAX	0
 #define printk_time		false
 
 #define prb_read_valid(rb, seq, r)	false
 #define prb_first_valid_seq(rb)		0
+#define prb_next_seq(rb)		0
 
 static u64 syslog_seq;
-static u64 console_seq;
-static u64 exclusive_console_stop_seq;
-static unsigned long console_dropped;
 
 static size_t record_print_text(const struct printk_record *r,
 				bool syslog, bool time)
@@ -2325,9 +2457,14 @@ static ssize_t msg_print_ext_body(char *buf, size_t size,
 				  struct dev_printk_info *dev_info) { return 0; }
 static void console_lock_spinning_enable(void) { }
 static int console_lock_spinning_disable_and_check(void) { return 0; }
-static void call_console_drivers(const char *ext_text, size_t ext_len,
-				 const char *text, size_t len) {}
+static void call_console_driver(struct console *con, const char *text, size_t len,
+				char *dropped_text)
+{
+}
 static bool suppress_message_printing(int level) { return false; }
+static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; }
+static void printk_start_kthread(struct console *con) { }
+static bool allow_direct_printing(void) { return true; }
 
 #endif /* CONFIG_PRINTK */
 
@@ -2515,6 +2652,7 @@ void suspend_console(void)
 	if (!console_suspend_enabled)
 		return;
 	pr_info("Suspending console(s) (use no_console_suspend to debug)\n");
+	pr_flush(1000, true);
 	console_lock();
 	console_suspended = 1;
 	up_console_sem();
@@ -2527,6 +2665,7 @@ void resume_console(void)
 	down_console_sem();
 	console_suspended = 0;
 	console_unlock();
+	pr_flush(1000, true);
 }
 
 /**
@@ -2544,6 +2683,14 @@ static int console_cpu_notify(unsigned int cpu)
 		/* If trylock fails, someone else is doing the printing */
 		if (console_trylock())
 			console_unlock();
+		else {
+			/*
+			 * If a new CPU comes online, the conditions for
+			 * printer_should_wake() may have changed for some
+			 * kthread printer with !CON_ANYTIME.
+			 */
+			wake_up_klogd();
+		}
 	}
 	return 0;
 }
@@ -2563,7 +2710,7 @@ void console_lock(void)
 	down_console_sem();
 	if (console_suspended)
 		return;
-	console_locked = 1;
+	console_kthreads_block();
 	console_may_schedule = 1;
 }
 EXPORT_SYMBOL(console_lock);
@@ -2584,33 +2731,32 @@ int console_trylock(void)
 		up_console_sem();
 		return 0;
 	}
-	console_locked = 1;
+	if (!console_kthreads_atomic_tryblock()) {
+		up_console_sem();
+		return 0;
+	}
 	console_may_schedule = 0;
 	return 1;
 }
 EXPORT_SYMBOL(console_trylock);
 
-int is_console_locked(void)
-{
-	return console_locked;
-}
-EXPORT_SYMBOL(is_console_locked);
-
 /*
- * Check if we have any console that is capable of printing while cpu is
- * booting or shutting down. Requires console_sem.
+ * This is used to help to make sure that certain paths within the VT code are
+ * running with the console lock held. It is definitely not the perfect debug
+ * tool (it is not known if the VT code is the task holding the console lock),
+ * but it helps tracking those weird code paths in the console code such as
+ * when the console is suspended: where the console is not locked but no
+ * console printing may occur.
+ *
+ * Note: This returns true when the console is suspended but is not locked.
+ *       This is intentional because the VT code must consider that situation
+ *       the same as if the console was locked.
  */
-static int have_callable_console(void)
+int is_console_locked(void)
 {
-	struct console *con;
-
-	for_each_console(con)
-		if ((con->flags & CON_ENABLED) &&
-				(con->flags & CON_ANYTIME))
-			return 1;
-
-	return 0;
+	return (console_kthreads_blocked || atomic_read(&console_kthreads_active));
 }
+EXPORT_SYMBOL(is_console_locked);
 
 /*
  * Return true when this CPU should unlock console_sem without pushing all
@@ -2631,132 +2777,125 @@ static bool abandon_console_lock_in_panic(void)
 	return atomic_read(&panic_cpu) != raw_smp_processor_id();
 }
 
+static inline bool __console_is_usable(short flags)
+{
+	if (!(flags & CON_ENABLED))
+		return false;
+
+	/*
+	 * Console drivers may assume that per-cpu resources have been
+	 * allocated. So unless they're explicitly marked as being able to
+	 * cope (CON_ANYTIME) don't call them until this CPU is officially up.
+	 */
+	if (!cpu_online(raw_smp_processor_id()) &&
+	    !(flags & CON_ANYTIME))
+		return false;
+
+	return true;
+}
+
 /*
- * Can we actually use the console at this time on this cpu?
+ * Check if the given console is currently capable and allowed to print
+ * records.
  *
- * Console drivers may assume that per-cpu resources have been allocated. So
- * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't
- * call them until this CPU is officially up.
+ * Requires holding the console_lock.
  */
-static inline int can_use_console(void)
+static inline bool console_is_usable(struct console *con)
 {
-	return cpu_online(raw_smp_processor_id()) || have_callable_console();
+	if (!con->write)
+		return false;
+
+	return __console_is_usable(con->flags);
 }
 
-/**
- * console_unlock - unlock the console system
+static void __console_unlock(void)
+{
+	/*
+	 * Depending on whether console_lock() or console_trylock() was used,
+	 * appropriately allow the kthread printers to continue.
+	 */
+	if (console_kthreads_blocked)
+		console_kthreads_unblock();
+	else
+		console_kthreads_atomic_unblock();
+
+	/*
+	 * New records may have arrived while the console was locked.
+	 * Wake the kthread printers to print them.
+	 */
+	wake_up_klogd();
+
+	up_console_sem();
+}
+
+/*
+ * Print one record for the given console. The record printed is whatever
+ * record is the next available record for the given console.
  *
- * Releases the console_lock which the caller holds on the console system
- * and the console driver list.
+ * @text is a buffer of size CONSOLE_LOG_MAX.
  *
- * While the console_lock was held, console output may have been buffered
- * by printk().  If this is the case, console_unlock(); emits
- * the output prior to releasing the lock.
+ * If extended messages should be printed, @ext_text is a buffer of size
+ * CONSOLE_EXT_LOG_MAX. Otherwise @ext_text must be NULL.
  *
- * If there is output waiting, we wake /dev/kmsg and syslog() users.
+ * If dropped messages should be printed, @dropped_text is a buffer of size
+ * DROPPED_TEXT_MAX. Otherwise @dropped_text must be NULL.
  *
- * console_unlock(); may be called from any context.
+ * @handover will be set to true if a printk waiter has taken over the
+ * console_lock, in which case the caller is no longer holding the
+ * console_lock. Otherwise it is set to false. A NULL pointer may be provided
+ * to disable allowing the console_lock to be taken over by a printk waiter.
+ *
+ * Returns false if the given console has no next record to print, otherwise
+ * true.
+ *
+ * Requires the console_lock if @handover is non-NULL.
+ * Requires con->lock otherwise.
  */
-void console_unlock(void)
+static bool __console_emit_next_record(struct console *con, char *text, char *ext_text,
+				       char *dropped_text, bool *handover)
 {
-	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;
+	static atomic_t panic_console_dropped = ATOMIC_INIT(0);
 	struct printk_info info;
 	struct printk_record r;
-	u64 __maybe_unused next_seq;
-
-	if (console_suspended) {
-		up_console_sem();
-		return;
-	}
-
-	prb_rec_init_rd(&r, &info, text, sizeof(text));
-
-	/*
-	 * Console drivers are called with interrupts disabled, so
-	 * @console_may_schedule should be cleared before; however, we may
-	 * end up dumping a lot of lines, for example, if called from
-	 * console registration path, and should invoke cond_resched()
-	 * between lines if allowable.  Not doing so can cause a very long
-	 * scheduling stall on a slow console leading to RCU stall and
-	 * softlockup warnings which exacerbate the issue with more
-	 * messages practically incapacitating the system.
-	 *
-	 * console_trylock() is not able to detect the preemptive
-	 * context reliably. Therefore the value must be stored before
-	 * and cleared after the "again" goto label.
-	 */
-	do_cond_resched = console_may_schedule;
-again:
-	console_may_schedule = 0;
-
-	/*
-	 * We released the console_sem lock, so we need to recheck if
-	 * cpu is online and (if not) is there at least one CON_ANYTIME
-	 * console.
-	 */
-	if (!can_use_console()) {
-		console_locked = 0;
-		up_console_sem();
-		return;
-	}
+	unsigned long flags;
+	char *write_text;
+	size_t len;
 
-	for (;;) {
-		size_t ext_len = 0;
-		int handover;
-		size_t len;
+	prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX);
 
-skip:
-		if (!prb_read_valid(prb, console_seq, &r))
-			break;
+	if (handover)
+		*handover = false;
 
-		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 (!prb_read_valid(prb, con->seq, &r))
+		return false;
 
-		if (suppress_message_printing(r.info->level)) {
-			/*
-			 * Skip record we have buffered and already printed
-			 * directly to the console when we received it, and
-			 * record that has level above the console loglevel.
-			 */
-			console_seq++;
-			goto skip;
+	if (con->seq != r.info->seq) {
+		con->dropped += r.info->seq - con->seq;
+		con->seq = r.info->seq;
+		if (panic_in_progress() &&
+		    atomic_fetch_inc_relaxed(&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");
 		}
+	}
 
-		/* Output to all consoles once old messages replayed. */
-		if (unlikely(exclusive_console &&
-			     console_seq >= exclusive_console_stop_seq)) {
-			exclusive_console = NULL;
-		}
+	/* Skip record that has level above the console loglevel. */
+	if (suppress_message_printing(r.info->level)) {
+		con->seq++;
+		goto skip;
+	}
 
-		/*
-		 * Handle extended console text first because later
-		 * record_print_text() will modify the record buffer in-place.
-		 */
-		if (nr_ext_console_drivers) {
-			ext_len = info_print_ext_header(ext_text,
-						sizeof(ext_text),
-						r.info);
-			ext_len += msg_print_ext_body(ext_text + ext_len,
-						sizeof(ext_text) - ext_len,
-						&r.text_buf[0],
-						r.info->text_len,
-						&r.info->dev_info);
-		}
-		len = record_print_text(&r,
-				console_msg_format & MSG_FORMAT_SYSLOG,
-				printk_time);
-		console_seq++;
+	if (ext_text) {
+		write_text = ext_text;
+		len = info_print_ext_header(ext_text, CONSOLE_EXT_LOG_MAX, r.info);
+		len += msg_print_ext_body(ext_text + len, CONSOLE_EXT_LOG_MAX - len,
+					  &r.text_buf[0], r.info->text_len, &r.info->dev_info);
+	} else {
+		write_text = text;
+		len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time);
+	}
 
+	if (handover) {
 		/*
 		 * While actively printing out messages, if another printk()
 		 * were to occur on another CPU, it may wait for this one to
@@ -2770,38 +2909,187 @@ skip:
 		printk_safe_enter_irqsave(flags);
 		console_lock_spinning_enable();
 
-		stop_critical_timings();	/* don't trace print latency */
-		call_console_drivers(ext_text, ext_len, text, len);
-		start_critical_timings();
+		/* don't trace irqsoff print latency */
+		stop_critical_timings();
+	}
 
-		handover = console_lock_spinning_disable_and_check();
-		printk_safe_exit_irqrestore(flags);
-		if (handover)
-			return;
+	call_console_driver(con, write_text, len, dropped_text);
 
-		/* Allow panic_cpu to take over the consoles safely */
-		if (abandon_console_lock_in_panic())
-			break;
+	con->seq++;
+
+	if (handover) {
+		start_critical_timings();
+		*handover = console_lock_spinning_disable_and_check();
+		printk_safe_exit_irqrestore(flags);
+	}
+skip:
+	return true;
+}
 
-		if (do_cond_resched)
-			cond_resched();
+/*
+ * Print a record for a given console, but allow another printk() caller to
+ * take over the console_lock and continue printing.
+ *
+ * Requires the console_lock, but depending on @handover after the call, the
+ * caller may no longer have the console_lock.
+ *
+ * See __console_emit_next_record() for argument and return details.
+ */
+static bool console_emit_next_record_transferable(struct console *con, char *text, char *ext_text,
+						  char *dropped_text, bool *handover)
+{
+	/*
+	 * Handovers are only supported if threaded printers are atomically
+	 * blocked. The context taking over the console_lock may be atomic.
+	 */
+	if (!console_kthreads_atomically_blocked()) {
+		*handover = false;
+		handover = NULL;
 	}
 
-	/* Get consistent value of the next-to-be-used sequence number. */
-	next_seq = console_seq;
+	return __console_emit_next_record(con, text, ext_text, dropped_text, handover);
+}
 
-	console_locked = 0;
-	up_console_sem();
+/*
+ * Print out all remaining records to all consoles.
+ *
+ * @do_cond_resched is set by the caller. It can be true only in schedulable
+ * context.
+ *
+ * @next_seq is set to the sequence number after the last available record.
+ * The value is valid only when this function returns true. It means that all
+ * usable consoles are completely flushed.
+ *
+ * @handover will be set to true if a printk waiter has taken over the
+ * console_lock, in which case the caller is no longer holding the
+ * console_lock. Otherwise it is set to false.
+ *
+ * Returns true when there was at least one usable console and all messages
+ * were flushed to all usable consoles. A returned false informs the caller
+ * that everything was not flushed (either there were no usable consoles or
+ * another context has taken over printing or it is a panic situation and this
+ * is not the panic CPU or direct printing is not preferred). Regardless the
+ * reason, the caller should assume it is not useful to immediately try again.
+ *
+ * Requires the console_lock.
+ */
+static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handover)
+{
+	static char dropped_text[DROPPED_TEXT_MAX];
+	static char ext_text[CONSOLE_EXT_LOG_MAX];
+	static char text[CONSOLE_LOG_MAX];
+	bool any_usable = false;
+	struct console *con;
+	bool any_progress;
+
+	*next_seq = 0;
+	*handover = false;
+
+	do {
+		/* Let the kthread printers do the work if they can. */
+		if (!allow_direct_printing())
+			return false;
+
+		any_progress = false;
+
+		for_each_console(con) {
+			bool progress;
+
+			if (!console_is_usable(con))
+				continue;
+			any_usable = true;
+
+			if (con->flags & CON_EXTENDED) {
+				/* Extended consoles do not print "dropped messages". */
+				progress = console_emit_next_record_transferable(con, &text[0],
+								&ext_text[0], NULL, handover);
+			} else {
+				progress = console_emit_next_record_transferable(con, &text[0],
+								NULL, &dropped_text[0], handover);
+			}
+			if (*handover)
+				return false;
+
+			/* Track the next of the highest seq flushed. */
+			if (con->seq > *next_seq)
+				*next_seq = con->seq;
+
+			if (!progress)
+				continue;
+			any_progress = true;
+
+			/* Allow panic_cpu to take over the consoles safely. */
+			if (abandon_console_lock_in_panic())
+				return false;
+
+			if (do_cond_resched)
+				cond_resched();
+		}
+	} while (any_progress);
+
+	return any_usable;
+}
+
+/**</