Merge tag 'printk-for-6.19' of git://git.kernel.org/pub/scm/linux/kernel/git/printk/linux

Pull printk updates from Petr Mladek:

 - Allow creaing nbcon console drivers with an unsafe write_atomic()
   callback that can only be called by the final nbcon_atomic_flush_unsafe().
   Otherwise, the driver would rely on the kthread.

   It is going to be used as the-best-effort approach for an
   experimental nbcon netconsole driver, see

     https://lore.kernel.org/r/20251121-nbcon-v1-2-503d17b2b4af@debian.org

   Note that a safe .write_atomic() callback is supposed to work in NMI
   context. But some networking drivers are not safe even in IRQ
   context:

     https://lore.kernel.org/r/oc46gdpmmlly5o44obvmoatfqo5bhpgv7pabpvb6sjuqioymcg@gjsma3ghoz35

   In an ideal world, all networking drivers would be fixed first and
   the atomic flush would be blocked only in NMI context. But it brings
   the question how reliable networking drivers are when the system is
   in a bad state. They might block flushing more reliable serial
   consoles which are more suitable for serious debugging anyway.

 - Allow to use the last 4 bytes of the printk ring buffer.

 - Prevent queuing IRQ work and block printk kthreads when consoles are
   suspended. Otherwise, they create non-necessary churn or even block
   the suspend.

 - Release console_lock() between each record in the kthread used for
   legacy consoles on RT. It might significantly speed up the boot.

 - Release nbcon context between each record in the atomic flush. It
   prevents stalls of the related printk kthread after it has lost the
   ownership in the middle of a record

 - Add support for NBCON consoles into KDB

 - Add %ptsP modifier for printing struct timespec64 and use it where
   possible

 - Misc code clean up

* tag 'printk-for-6.19' of git://git.kernel.org/pub/scm/linux/kernel/git/printk/linux: (48 commits)
  printk: Use console_is_usable on console_unblank
  arch: um: kmsg_dump: Use console_is_usable
  drivers: serial: kgdboc: Drop checks for CON_ENABLED and CON_BOOT
  lib/vsprintf: Unify FORMAT_STATE_NUM handlers
  printk: Avoid irq_work for printk_deferred() on suspend
  printk: Avoid scheduling irq_work on suspend
  printk: Allow printk_trigger_flush() to flush all types
  tracing: Switch to use %ptSp
  scsi: snic: Switch to use %ptSp
  scsi: fnic: Switch to use %ptSp
  s390/dasd: Switch to use %ptSp
  ptp: ocp: Switch to use %ptSp
  pps: Switch to use %ptSp
  PCI: epf-test: Switch to use %ptSp
  net: dsa: sja1105: Switch to use %ptSp
  mmc: mmc_test: Switch to use %ptSp
  media: av7110: Switch to use %ptSp
  ipmi: Switch to use %ptSp
  igb: Switch to use %ptSp
  e1000e: Switch to use %ptSp
  ...

1 files changed, 195 insertions, 101 deletions

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 5aee9ffb16b9..7394f1b6033b 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -462,6 +462,9 @@ bool have_boot_console;
 /* See printk_legacy_allow_panic_sync() for details. */
 bool legacy_allow_panic_sync;
 
+/* Avoid using irq_work when suspending. */
+bool console_irqwork_blocked;
+
 #ifdef CONFIG_PRINTK
 DECLARE_WAIT_QUEUE_HEAD(log_wait);
 static DECLARE_WAIT_QUEUE_HEAD(legacy_wait);
@@ -2390,7 +2393,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 	/* If called from the scheduler, we can not call up(). */
 	if (level == LOGLEVEL_SCHED) {
 		level = LOGLEVEL_DEFAULT;
-		ft.legacy_offload |= ft.legacy_direct;
+		ft.legacy_offload |= ft.legacy_direct && !console_irqwork_blocked;
 		ft.legacy_direct = false;
 	}
 
@@ -2426,7 +2429,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 
 	if (ft.legacy_offload)
 		defer_console_output();
-	else
+	else if (!console_irqwork_blocked)
 		wake_up_klogd();
 
 	return printed_len;
@@ -2730,10 +2733,20 @@ void console_suspend_all(void)
 {
 	struct console *con;
 
+	if (console_suspend_enabled)
+		pr_info("Suspending console(s) (use no_console_suspend to debug)\n");
+
+	/*
+	 * Flush any console backlog and then avoid queueing irq_work until
+	 * console_resume_all(). Until then deferred printing is no longer
+	 * triggered, NBCON consoles transition to atomic flushing, and
+	 * any klogd waiters are not triggered.
+	 */
+	pr_flush(1000, true);
+	console_irqwork_blocked = true;
+
 	if (!console_suspend_enabled)
 		return;
-	pr_info("Suspending console(s) (use no_console_suspend to debug)\n");
-	pr_flush(1000, true);
 
 	console_list_lock();
 	for_each_console(con)
@@ -2754,26 +2767,34 @@ void console_resume_all(void)
 	struct console_flush_type ft;
 	struct console *con;
 
-	if (!console_suspend_enabled)
-		return;
-
-	console_list_lock();
-	for_each_console(con)
-		console_srcu_write_flags(con, con->flags & ~CON_SUSPENDED);
-	console_list_unlock();
-
 	/*
-	 * Ensure that all SRCU list walks have completed. All printing
-	 * contexts must be able to see they are no longer suspended so
-	 * that they are guaranteed to wake up and resume printing.
+	 * Allow queueing irq_work. After restoring console state, deferred
+	 * printing and any klogd waiters need to be triggered in case there
+	 * is now a console backlog.
 	 */
-	synchronize_srcu(&console_srcu);
+	console_irqwork_blocked = false;
+
+	if (console_suspend_enabled) {
+		console_list_lock();
+		for_each_console(con)
+			console_srcu_write_flags(con, con->flags & ~CON_SUSPENDED);
+		console_list_unlock();
+
+		/*
+		 * Ensure that all SRCU list walks have completed. All printing
+		 * contexts must be able to see they are no longer suspended so
+		 * that they are guaranteed to wake up and resume printing.
+		 */
+		synchronize_srcu(&console_srcu);
+	}
 
 	printk_get_console_flush_type(&ft);
 	if (ft.nbcon_offload)
 		nbcon_kthreads_wake();
 	if (ft.legacy_offload)
 		defer_console_output();
+	else
+		wake_up_klogd();
 
 	pr_flush(1000, true);
 }
@@ -3002,21 +3023,18 @@ out:
 }
 
 /*
- * Legacy console printing from printk() caller context does not respect
- * raw_spinlock/spinlock nesting. For !PREEMPT_RT the lockdep warning is a
- * false positive. For PREEMPT_RT the false positive condition does not
- * occur.
- *
- * This map is used to temporarily establish LD_WAIT_SLEEP context for the
- * console write() callback when legacy printing to avoid false positive
- * lockdep complaints, thus allowing lockdep to continue to function for
- * real issues.
+ * The legacy console always acquires a spinlock_t from its printing
+ * callback. This violates lock nesting if the caller acquired an always
+ * spinning lock (raw_spinlock_t) while invoking printk(). This is not a
+ * problem on PREEMPT_RT because legacy consoles print always from a
+ * dedicated thread and never from within printk(). Therefore we tell
+ * lockdep that a sleeping spin lock (spinlock_t) is valid here.
  */
 #ifdef CONFIG_PREEMPT_RT
 static inline void printk_legacy_allow_spinlock_enter(void) { }
 static inline void printk_legacy_allow_spinlock_exit(void) { }
 #else
-static DEFINE_WAIT_OVERRIDE_MAP(printk_legacy_map, LD_WAIT_SLEEP);
+static DEFINE_WAIT_OVERRIDE_MAP(printk_legacy_map, LD_WAIT_CONFIG);
 
 static inline void printk_legacy_allow_spinlock_enter(void)
 {
@@ -3134,104 +3152,147 @@ static inline void printk_kthreads_check_locked(void) { }
 
 #endif /* CONFIG_PRINTK */
 
+
 /*
- * Print out all remaining records to all consoles.
+ * Print out one record for each console.
  *
  * @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.
+ * The value is valid only when all usable consoles were flushed. It is
+ * when the function returns true (can do the job) and @try_again parameter
+ * is set to false, see below.
  *
  * @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). Regardless the reason, the caller should assume it
- * is not useful to immediately try again.
+ * @try_again will be set to true when it still makes sense to call this
+ * function again. The function could do the job, see the return value.
+ * And some consoles still make progress.
+ *
+ * Returns true when the function could do the job. Some consoles are usable,
+ * and there was no takeover and no panic_on_other_cpu().
  *
  * Requires the console_lock.
  */
-static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handover)
+static bool console_flush_one_record(bool do_cond_resched, u64 *next_seq, bool *handover,
+				     bool *try_again)
 {
 	struct console_flush_type ft;
 	bool any_usable = false;
 	struct console *con;
-	bool any_progress;
 	int cookie;
 
-	*next_seq = 0;
-	*handover = false;
+	*try_again = false;
 
-	do {
-		any_progress = false;
+	printk_get_console_flush_type(&ft);
 
-		printk_get_console_flush_type(&ft);
+	cookie = console_srcu_read_lock();
+	for_each_console_srcu(con) {
+		short flags = console_srcu_read_flags(con);
+		u64 printk_seq;
+		bool progress;
 
-		cookie = console_srcu_read_lock();
-		for_each_console_srcu(con) {
-			short flags = console_srcu_read_flags(con);
-			u64 printk_seq;
-			bool progress;
+		/*
+		 * console_flush_one_record() is only responsible for
+		 * nbcon consoles when the nbcon consoles cannot print via
+		 * their atomic or threaded flushing.
+		 */
+		if ((flags & CON_NBCON) && (ft.nbcon_atomic || ft.nbcon_offload))
+			continue;
 
-			/*
-			 * console_flush_all() is only responsible for nbcon
-			 * consoles when the nbcon consoles cannot print via
-			 * their atomic or threaded flushing.
-			 */
-			if ((flags & CON_NBCON) && (ft.nbcon_atomic || ft.nbcon_offload))
-				continue;
+		if (!console_is_usable(con, flags, !do_cond_resched))
+			continue;
+		any_usable = true;
 
-			if (!console_is_usable(con, flags, !do_cond_resched))
-				continue;
-			any_usable = true;
+		if (flags & CON_NBCON) {
+			progress = nbcon_legacy_emit_next_record(con, handover, cookie,
+								 !do_cond_resched);
+			printk_seq = nbcon_seq_read(con);
+		} else {
+			progress = console_emit_next_record(con, handover, cookie);
+			printk_seq = con->seq;
+		}
 
-			if (flags & CON_NBCON) {
-				progress = nbcon_legacy_emit_next_record(con, handover, cookie,
-									 !do_cond_resched);
-				printk_seq = nbcon_seq_read(con);
-			} else {
-				progress = console_emit_next_record(con, handover, cookie);
-				printk_seq = con->seq;
-			}
+		/*
+		 * If a handover has occurred, the SRCU read lock
+		 * is already released.
+		 */
+		if (*handover)
+			goto fail;
 
-			/*
-			 * If a handover has occurred, the SRCU read lock
-			 * is already released.
-			 */
-			if (*handover)
-				return false;
+		/* Track the next of the highest seq flushed. */
+		if (printk_seq > *next_seq)
+			*next_seq = printk_seq;
 
-			/* Track the next of the highest seq flushed. */
-			if (printk_seq > *next_seq)
-				*next_seq = printk_seq;
+		if (!progress)
+			continue;
 
-			if (!progress)
-				continue;
-			any_progress = true;
+		/*
+		 * An usable console made a progress. There might still be
+		 * pending messages.
+		 */
+		*try_again = true;
 
-			/* Allow panic_cpu to take over the consoles safely. */
-			if (panic_on_other_cpu())
-				goto abandon;
+		/* Allow panic_cpu to take over the consoles safely. */
+		if (panic_on_other_cpu())
+			goto fail_srcu;
 
-			if (do_cond_resched)
-				cond_resched();
-		}
-		console_srcu_read_unlock(cookie);
-	} while (any_progress);
+		if (do_cond_resched)
+			cond_resched();
+	}
+	console_srcu_read_unlock(cookie);
 
 	return any_usable;
 
-abandon:
+fail_srcu:
 	console_srcu_read_unlock(cookie);
+fail:
+	*try_again = false;
 	return false;
 }
 
+/*
+ * 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). 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)
+{
+	bool try_again;
+	bool ret;
+
+	*next_seq = 0;
+	*handover = false;
+
+	do {
+		ret = console_flush_one_record(do_cond_resched, next_seq,
+					       handover, &try_again);
+	} while (try_again);
+
+	return ret;
+}
+
 static void __console_flush_and_unlock(void)
 {
 	bool do_cond_resched;
@@ -3331,12 +3392,10 @@ void console_unblank(void)
 	 */
 	cookie = console_srcu_read_lock();
 	for_each_console_srcu(c) {
-		short flags = console_srcu_read_flags(c);
-
-		if (flags & CON_SUSPENDED)
+		if (!console_is_usable(c, console_srcu_read_flags(c), true))
 			continue;
 
-		if ((flags & CON_ENABLED) && c->unblank) {
+		if (c->unblank) {
 			found_unblank = true;
 			break;
 		}
@@ -3373,12 +3432,10 @@ void console_unblank(void)
 
 	cookie = console_srcu_read_lock();
 	for_each_console_srcu(c) {
-		short flags = console_srcu_read_flags(c);
-
-		if (flags & CON_SUSPENDED)
+		if (!console_is_usable(c, console_srcu_read_flags(c), true))
 			continue;
 
-		if ((flags & CON_ENABLED) && c->unblank)
+		if (c->unblank)
 			c->unblank();
 	}
 	console_srcu_read_unlock(cookie);
@@ -3601,17 +3658,26 @@ static bool legacy_kthread_should_wakeup(void)
 
 static int legacy_kthread_func(void *unused)
 {
-	for (;;) {
-		wait_event_interruptible(legacy_wait, legacy_kthread_should_wakeup());
+	bool try_again;
+
+wait_for_event:
+	wait_event_interruptible(legacy_wait, legacy_kthread_should_wakeup());
+
+	do {
+		bool handover = false;
+		u64 next_seq = 0;
 
 		if (kthread_should_stop())
-			break;
+			return 0;
 
 		console_lock();
-		__console_flush_and_unlock();
-	}
+		console_flush_one_record(true, &next_seq, &handover, &try_again);
+		if (!handover)
+			__console_unlock();
 
-	return 0;
+	} while (try_again);
+
+	goto wait_for_event;
 }
 
 static bool legacy_kthread_create(void)
@@ -4511,6 +4577,13 @@ static void __wake_up_klogd(int val)
 	if (!printk_percpu_data_ready())
 		return;
 
+	/*
+	 * It is not allowed to call this function when console irq_work
+	 * is blocked.
+	 */
+	if (WARN_ON_ONCE(console_irqwork_blocked))
+		return;
+
 	preempt_disable();
 	/*
 	 * Guarantee any new records can be seen by tasks preparing to wait
@@ -4567,9 +4640,30 @@ void defer_console_output(void)
 	__wake_up_klogd(PRINTK_PENDING_WAKEUP | PRINTK_PENDING_OUTPUT);
 }
 
+/**
+ * printk_trigger_flush - Attempt to flush printk buffer to consoles.
+ *
+ * If possible, flush the printk buffer to all consoles in the caller's
+ * context. If offloading is available, trigger deferred printing.
+ *
+ * This is best effort. Depending on the system state, console states,
+ * and caller context, no actual flushing may result from this call.
+ */
 void printk_trigger_flush(void)
 {
-	defer_console_output();
+	struct console_flush_type ft;
+
+	printk_get_console_flush_type(&ft);
+	if (ft.nbcon_atomic)
+		nbcon_atomic_flush_pending();
+	if (ft.nbcon_offload)
+		nbcon_kthreads_wake();
+	if (ft.legacy_direct) {
+		if (console_trylock())
+			console_unlock();
+	}
+	if (ft.legacy_offload)
+		defer_console_output();
 }
 
 int vprintk_deferred(const char *fmt, va_list args)