Merge branch 'rework/misc-cleanups' into for-linus

5 files changed, 156 insertions, 73 deletions

diff --git a/include/linux/console.h b/include/linux/console.h
index d3195664baa5..7de11c763eb3 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -154,6 +154,8 @@ static inline int con_debug_leave(void)
  *			receiving the printk spam for obvious reasons.
  * @CON_EXTENDED:	The console supports the extended output format of
  *			/dev/kmesg which requires a larger output buffer.
+ * @CON_SUSPENDED:	Indicates if a console is suspended. If true, the
+ *			printing callbacks must not be called.
  */
 enum cons_flags {
 	CON_PRINTBUFFER		= BIT(0),
@@ -163,6 +165,7 @@ enum cons_flags {
 	CON_ANYTIME		= BIT(4),
 	CON_BRL			= BIT(5),
 	CON_EXTENDED		= BIT(6),
+	CON_SUSPENDED		= BIT(7),
 };
 
 /**
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index 5c7e9ba7cd6b..e9139dfc1f0a 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -576,6 +576,8 @@ static void kdb_msg_write(const char *msg, int msg_len)
 			continue;
 		if (c == dbg_io_ops->cons)
 			continue;
+		if (!c->write)
+			continue;
 		/*
 		 * Set oops_in_progress to encourage the console drivers to
 		 * disregard their internal spin locks: in the current calling
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index 2a17704136f1..7d4979d5c3ce 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -103,3 +103,5 @@ struct printk_message {
 	u64			seq;
 	unsigned long		dropped;
 };
+
+bool other_cpu_in_panic(void);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index accfd326e7a1..1524893aebed 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -86,7 +86,7 @@ EXPORT_SYMBOL(oops_in_progress);
 static DEFINE_MUTEX(console_mutex);
 
 /*
- * console_sem protects updates to console->seq and console_suspended,
+ * console_sem protects updates to console->seq
  * and also provides serialization for console printing.
  */
 static DEFINE_SEMAPHORE(console_sem);
@@ -359,7 +359,7 @@ static bool panic_in_progress(void)
  * paths in the console code where we end up in places I want
  * locked without the console semaphore held).
  */
-static int console_locked, console_suspended;
+static int console_locked;
 
 /*
  *	Array of consoles built from command line options (console=)
@@ -2308,7 +2308,11 @@ asmlinkage int vprintk_emit(int facility, int level,
 		preempt_enable();
 	}
 
-	wake_up_klogd();
+	if (in_sched)
+		defer_console_output();
+	else
+		wake_up_klogd();
+
 	return printed_len;
 }
 EXPORT_SYMBOL(vprintk_emit);
@@ -2547,22 +2551,46 @@ MODULE_PARM_DESC(console_no_auto_verbose, "Disable console loglevel raise to hig
  */
 void suspend_console(void)
 {
+	struct console *con;
+
 	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();
+
+	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 that they are suspended so that it
+	 * is guaranteed that all printing has stopped when this function
+	 * completes.
+	 */
+	synchronize_srcu(&console_srcu);
 }
 
 void resume_console(void)
 {
+	struct console *con;
+
 	if (!console_suspend_enabled)
 		return;
-	down_console_sem();
-	console_suspended = 0;
-	console_unlock();
+
+	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);
+
 	pr_flush(1000, true);
 }
 
@@ -2585,6 +2613,26 @@ static int console_cpu_notify(unsigned int cpu)
 	return 0;
 }
 
+/*
+ * Return true if a panic is in progress on a remote CPU.
+ *
+ * On true, the local CPU should immediately release any printing resources
+ * that may be needed by the panic CPU.
+ */
+bool other_cpu_in_panic(void)
+{
+	if (!panic_in_progress())
+		return false;
+
+	/*
+	 * We can use raw_smp_processor_id() here because it is impossible for
+	 * the task to be migrated to the panic_cpu, or away from it. If
+	 * panic_cpu has already been set, and we're not currently executing on
+	 * that CPU, then we never will be.
+	 */
+	return atomic_read(&panic_cpu) != raw_smp_processor_id();
+}
+
 /**
  * console_lock - block the console subsystem from printing
  *
@@ -2597,9 +2645,11 @@ void console_lock(void)
 {
 	might_sleep();
 
+	/* On panic, the console_lock must be left to the panic cpu. */
+	while (other_cpu_in_panic())
+		msleep(1000);
+
 	down_console_sem();
-	if (console_suspended)
-		return;
 	console_locked = 1;
 	console_may_schedule = 1;
 }
@@ -2615,12 +2665,11 @@ EXPORT_SYMBOL(console_lock);
  */
 int console_trylock(void)
 {
-	if (down_trylock_console_sem())
+	/* On panic, the console_lock must be left to the panic cpu. */
+	if (other_cpu_in_panic())
 		return 0;
-	if (console_suspended) {
-		up_console_sem();
+	if (down_trylock_console_sem())
 		return 0;
-	}
 	console_locked = 1;
 	console_may_schedule = 0;
 	return 1;
@@ -2634,25 +2683,6 @@ int is_console_locked(void)
 EXPORT_SYMBOL(is_console_locked);
 
 /*
- * Return true when this CPU should unlock console_sem without pushing all
- * messages to the console. This reduces the chance that the console is
- * locked when the panic CPU tries to use it.
- */
-static bool abandon_console_lock_in_panic(void)
-{
-	if (!panic_in_progress())
-		return false;
-
-	/*
-	 * We can use raw_smp_processor_id() here because it is impossible for
-	 * the task to be migrated to the panic_cpu, or away from it. If
-	 * panic_cpu has already been set, and we're not currently executing on
-	 * that CPU, then we never will be.
-	 */
-	return atomic_read(&panic_cpu) != raw_smp_processor_id();
-}
-
-/*
  * Check if the given console is currently capable and allowed to print
  * records.
  *
@@ -2665,6 +2695,9 @@ static inline bool console_is_usable(struct console *con)
 	if (!(flags & CON_ENABLED))
 		return false;
 
+	if ((flags & CON_SUSPENDED))
+		return false;
+
 	if (!con->write)
 		return false;
 
@@ -2948,7 +2981,7 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove
 			any_progress = true;
 
 			/* Allow panic_cpu to take over the consoles safely. */
-			if (abandon_console_lock_in_panic())
+			if (other_cpu_in_panic())
 				goto abandon;
 
 			if (do_cond_resched)
@@ -2983,11 +3016,6 @@ void console_unlock(void)
 	bool flushed;
 	u64 next_seq;
 
-	if (console_suspended) {
-		up_console_sem();
-		return;
-	}
-
 	/*
 	 * Console drivers are called with interrupts disabled, so
 	 * @console_may_schedule should be cleared before; however, we may
@@ -3045,10 +3073,28 @@ EXPORT_SYMBOL(console_conditional_schedule);
 
 void console_unblank(void)
 {
+	bool found_unblank = false;
 	struct console *c;
 	int cookie;
 
 	/*
+	 * First check if there are any consoles implementing the unblank()
+	 * callback. If not, there is no reason to continue and take the
+	 * console lock, which in particular can be dangerous if
+	 * @oops_in_progress is set.
+	 */
+	cookie = console_srcu_read_lock();
+	for_each_console_srcu(c) {
+		if ((console_srcu_read_flags(c) & CON_ENABLED) && c->unblank) {
+			found_unblank = true;
+			break;
+		}
+	}
+	console_srcu_read_unlock(cookie);
+	if (!found_unblank)
+		return;
+
+	/*
 	 * Stop console printing because the unblank() callback may
 	 * assume the console is not within its write() callback.
 	 *
@@ -3056,6 +3102,16 @@ void console_unblank(void)
 	 * In that case, attempt a trylock as best-effort.
 	 */
 	if (oops_in_progress) {
+		/* Semaphores are not NMI-safe. */
+		if (in_nmi())
+			return;
+
+		/*
+		 * Attempting to trylock the console lock can deadlock
+		 * if another CPU was stopped while modifying the
+		 * semaphore. "Hope and pray" that this is not the
+		 * current situation.
+		 */
 		if (down_trylock_console_sem() != 0)
 			return;
 	} else
@@ -3085,14 +3141,24 @@ void console_unblank(void)
  */
 void console_flush_on_panic(enum con_flush_mode mode)
 {
+	bool handover;
+	u64 next_seq;
+
 	/*
-	 * If someone else is holding the console lock, trylock will fail
-	 * and may_schedule may be set.  Ignore and proceed to unlock so
-	 * that messages are flushed out.  As this can be called from any
-	 * context and we don't want to get preempted while flushing,
-	 * ensure may_schedule is cleared.
+	 * Ignore the console lock and flush out the messages. Attempting a
+	 * trylock would not be useful because:
+	 *
+	 *   - if it is contended, it must be ignored anyway
+	 *   - console_lock() and console_trylock() block and fail
+	 *     respectively in panic for non-panic CPUs
+	 *   - semaphores are not NMI-safe
+	 */
+
+	/*
+	 * If another context is holding the console lock,
+	 * @console_may_schedule might be set. Clear it so that
+	 * this context does not call cond_resched() while flushing.
 	 */
-	console_trylock();
 	console_may_schedule = 0;
 
 	if (mode == CONSOLE_REPLAY_ALL) {
@@ -3105,15 +3171,15 @@ void console_flush_on_panic(enum con_flush_mode mode)
 		cookie = console_srcu_read_lock();
 		for_each_console_srcu(c) {
 			/*
-			 * If the above console_trylock() failed, this is an
-			 * unsynchronized assignment. But in that case, the
+			 * This is an unsynchronized assignment, but the
 			 * kernel is in "hope and pray" mode anyway.
 			 */
 			c->seq = seq;
 		}
 		console_srcu_read_unlock(cookie);
 	}
-	console_unlock();
+
+	console_flush_all(false, &next_seq, &handover);
 }
 
 /*
@@ -3679,8 +3745,7 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
 
 		/*
 		 * Hold the console_lock to guarantee safe access to
-		 * console->seq and to prevent changes to @console_suspended
-		 * until all consoles have been processed.
+		 * console->seq.
 		 */
 		console_lock();
 
@@ -3688,6 +3753,11 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
 		for_each_console_srcu(c) {
 			if (con && con != c)
 				continue;
+			/*
+			 * If consoles are not usable, it cannot be expected
+			 * that they make forward progress, so only increment
+			 * @diff for usable consoles.
+			 */
 			if (!console_is_usable(c))
 				continue;
 			printk_seq = c->seq;
@@ -3696,18 +3766,12 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
 		}
 		console_srcu_read_unlock(cookie);
 
-		/*
-		 * If consoles are suspended, it cannot be expected that they
-		 * make forward progress, so timeout immediately. @diff is
-		 * still used to return a valid flush status.
-		 */
-		if (console_suspended)
-			remaining = 0;
-		else if (diff != last_diff && reset_on_progress)
+		if (diff != last_diff && reset_on_progress)
 			remaining = timeout_ms;
 
 		console_unlock();
 
+		/* Note: @diff is 0 if there are no usable consoles. */
 		if (diff == 0 || remaining == 0)
 			break;
 
@@ -3741,7 +3805,7 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
  * printer has been seen to make some forward progress.
  *
  * Context: Process context. May sleep while acquiring console lock.
- * Return: true if all enabled printers are caught up.
+ * Return: true if all usable printers are caught up.
  */
 static bool pr_flush(int timeout_ms, bool reset_on_progress)
 {
@@ -3798,11 +3862,33 @@ static void __wake_up_klogd(int val)
 	preempt_enable();
 }
 
+/**
+ * wake_up_klogd - Wake kernel logging daemon
+ *
+ * Use this function when new records have been added to the ringbuffer
+ * and the console printing of those records has already occurred or is
+ * known to be handled by some other context. This function will only
+ * wake the logging daemon.
+ *
+ * Context: Any context.
+ */
 void wake_up_klogd(void)
 {
 	__wake_up_klogd(PRINTK_PENDING_WAKEUP);
 }
 
+/**
+ * defer_console_output - Wake kernel logging daemon and trigger
+ *	console printing in a deferred context
+ *
+ * Use this function when new records have been added to the ringbuffer,
+ * this context is responsible for console printing those records, but
+ * the current context is not allowed to perform the console printing.
+ * Trigger an irq_work context to perform the console printing. This
+ * function also wakes the logging daemon.
+ *
+ * Context: Any context.
+ */
 void defer_console_output(void)
 {
 	/*
@@ -3819,12 +3905,7 @@ void printk_trigger_flush(void)
 
 int vprintk_deferred(const char *fmt, va_list args)
 {
-	int r;
-
-	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args);
-	defer_console_output();
-
-	return r;
+	return vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args);
 }
 
 int _printk_deferred(const char *fmt, ...)
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index ef0f9a2044da..6d10927a07d8 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -38,13 +38,8 @@ asmlinkage int vprintk(const char *fmt, va_list args)
 	 * Use the main logbuf even in NMI. But avoid calling console
 	 * drivers that might have their own locks.
 	 */
-	if (this_cpu_read(printk_context) || in_nmi()) {
-		int len;
-
-		len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, fmt, args);
-		defer_console_output();
-		return len;
-	}
+	if (this_cpu_read(printk_context) || in_nmi())
+		return vprintk_deferred(fmt, args);
 
 	/* No obstacles. */
 	return vprintk_default(fmt, args);