1 files changed, 248 insertions, 131 deletions

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 357a4d18f638..f2444b581e16 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -88,7 +88,7 @@ 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, 1);
@@ -102,12 +102,6 @@ DEFINE_STATIC_SRCU(console_srcu);
  */
 int __read_mostly suppress_printk;
 
-/*
- * During panic, heavy printk by other CPUs can delay the
- * panic and risk deadlock on console resources.
- */
-static int __read_mostly suppress_panic_printk;
-
 #ifdef CONFIG_LOCKDEP
 static struct lockdep_map console_lock_dep_map = {
 	.name = "console_lock"
@@ -361,7 +355,7 @@ 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=)
@@ -445,6 +439,12 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
 static DEFINE_MUTEX(syslog_lock);
 
 #ifdef CONFIG_PRINTK
+/*
+ * During panic, heavy printk by other CPUs can delay the
+ * panic and risk deadlock on console resources.
+ */
+static int __read_mostly suppress_panic_printk;
+
 DECLARE_WAIT_QUEUE_HEAD(log_wait);
 /* All 3 protected by @syslog_lock. */
 /* the next printk record to read by syslog(READ) or /proc/kmsg */
@@ -494,7 +494,7 @@ _DEFINE_PRINTKRB(printk_rb_static, CONFIG_LOG_BUF_SHIFT - PRB_AVGBITS,
 
 static struct printk_ringbuffer printk_rb_dynamic;
 
-static struct printk_ringbuffer *prb = &printk_rb_static;
+struct printk_ringbuffer *prb = &printk_rb_static;
 
 /*
  * We cannot access per-CPU data (e.g. per-CPU flush irq_work) before
@@ -698,9 +698,6 @@ out:
 	return len;
 }
 
-static bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
-				    bool is_extended, bool may_supress);
-
 /* /dev/kmsg - userspace message inject/listen interface */
 struct devkmsg_user {
 	atomic64_t seq;
@@ -1669,7 +1666,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 
 	prb_rec_init_rd(&r, &info, text, PRINTK_MESSAGE_MAX);
 
-	len = 0;
 	prb_for_each_record(seq, prb, seq, &r) {
 		int textlen;
 
@@ -2308,7 +2304,11 @@ 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);
@@ -2345,22 +2345,6 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
 
 static u64 syslog_seq;
 
-static size_t record_print_text(const struct printk_record *r,
-				bool syslog, bool time)
-{
-	return 0;
-}
-static ssize_t info_print_ext_header(char *buf, size_t size,
-				     struct printk_info *info)
-{
-	return 0;
-}
-static ssize_t msg_print_ext_body(char *buf, size_t size,
-				  char *text, size_t text_len,
-				  struct dev_printk_info *dev_info) { return 0; }
-static void console_lock_spinning_enable(void) { }
-static int console_lock_spinning_disable_and_check(int cookie) { return 0; }
-static bool suppress_message_printing(int level) { return false; }
 static bool pr_flush(int timeout_ms, bool reset_on_progress) { return true; }
 static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; }
 
@@ -2400,13 +2384,21 @@ static void set_user_specified(struct console_cmdline *c, bool user_specified)
 	console_set_on_cmdline = 1;
 }
 
-static int __add_preferred_console(char *name, int idx, char *options,
+static int __add_preferred_console(const char *name, const short idx, char *options,
 				   char *brl_options, bool user_specified)
 {
 	struct console_cmdline *c;
 	int i;
 
 	/*
+	 * We use a signed short index for struct console for device drivers to
+	 * indicate a not yet assigned index or port. However, a negative index
+	 * value is not valid for preferred console.
+	 */
+	if (idx < 0)
+		return -EINVAL;
+
+	/*
 	 *	See if this tty is not yet registered, and
 	 *	if we have a slot free.
 	 */
@@ -2509,7 +2501,7 @@ __setup("console=", console_setup);
  * commonly to provide a default console (ie from PROM variables) when
  * the user has not supplied one.
  */
-int add_preferred_console(char *name, int idx, char *options)
+int add_preferred_console(const char *name, const short idx, char *options)
 {
 	return __add_preferred_console(name, idx, options, NULL, false);
 }
@@ -2547,22 +2539,46 @@ 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 +2601,26 @@ 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 +2633,11 @@ 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 +2653,11 @@ 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 +2671,6 @@ 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 +2683,9 @@ 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;
 
@@ -2685,6 +2706,8 @@ static void __console_unlock(void)
 	up_console_sem();
 }
 
+#ifdef CONFIG_PRINTK
+
 /*
  * Prepend the message in @pmsg->pbufs->outbuf with a "dropped message". This
  * is achieved by shifting the existing message over and inserting the dropped
@@ -2699,8 +2722,7 @@ static void __console_unlock(void)
  *
  * If @pmsg->pbufs->outbuf is modified, @pmsg->outbuf_len is updated.
  */
-#ifdef CONFIG_PRINTK
-static void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped)
+void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped)
 {
 	struct printk_buffers *pbufs = pmsg->pbufs;
 	const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf);
@@ -2731,9 +2753,6 @@ static void console_prepend_dropped(struct printk_message *pmsg, unsigned long d
 	memcpy(outbuf, scratchbuf, len);
 	pmsg->outbuf_len += len;
 }
-#else
-#define console_prepend_dropped(pmsg, dropped)
-#endif /* CONFIG_PRINTK */
 
 /*
  * Read and format the specified record (or a later record if the specified
@@ -2754,8 +2773,8 @@ static void console_prepend_dropped(struct printk_message *pmsg, unsigned long d
  * of @pmsg are valid. (See the documentation of struct printk_message
  * for information about the @pmsg fields.)
  */
-static bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
-				    bool is_extended, bool may_suppress)
+bool printk_get_next_message(struct printk_message *pmsg, u64 seq,
+			     bool is_extended, bool may_suppress)
 {
 	static int panic_console_dropped;
 
@@ -2814,6 +2833,13 @@ out:
 }
 
 /*
+ * Used as the printk buffers for non-panic, serialized console printing.
+ * This is for legacy (!CON_NBCON) as well as all boot (CON_BOOT) consoles.
+ * Its usage requires the console_lock held.
+ */
+struct printk_buffers printk_shared_pbufs;
+
+/*
  * Print one record for the given console. The record printed is whatever
  * record is the next available record for the given console.
  *
@@ -2830,12 +2856,10 @@ out:
  */
 static bool console_emit_next_record(struct console *con, bool *handover, int cookie)
 {
-	static struct printk_buffers pbufs;
-
 	bool is_extended = console_srcu_read_flags(con) & CON_EXTENDED;
-	char *outbuf = &pbufs.outbuf[0];
+	char *outbuf = &printk_shared_pbufs.outbuf[0];
 	struct printk_message pmsg = {
-		.pbufs = &pbufs,
+		.pbufs = &printk_shared_pbufs,
 	};
 	unsigned long flags;
 
@@ -2886,6 +2910,16 @@ skip:
 	return true;
 }
 
+#else
+
+static bool console_emit_next_record(struct console *con, bool *handover, int cookie)
+{
+	*handover = false;
+	return false;
+}
+
+#endif /* CONFIG_PRINTK */
+
 /*
  * Print out all remaining records to all consoles.
  *
@@ -2948,7 +2982,7 @@ 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 +3017,6 @@ 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 +3074,28 @@ 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 +3103,16 @@ 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
@@ -3085,18 +3142,29 @@ void console_unblank(void)
  */
 void console_flush_on_panic(enum con_flush_mode mode)
 {
+	bool handover;
+	u64 next_seq;
+
+	/*
+	 * 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 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.
+	 * 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) {
 		struct console *c;
+		short flags;
 		int cookie;
 		u64 seq;
 
@@ -3104,16 +3172,22 @@ 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
-			 * kernel is in "hope and pray" mode anyway.
-			 */
-			c->seq = seq;
+			flags = console_srcu_read_flags(c);
+
+			if (flags & CON_NBCON) {
+				nbcon_seq_force(c, seq);
+			} else {
+				/*
+				 * This is an unsynchronized assignment. On
+				 * panic legacy consoles are only best effort.
+				 */
+				c->seq = seq;
+			}
 		}
 		console_srcu_read_unlock(cookie);
 	}
-	console_unlock();
+
+	console_flush_all(false, &next_seq, &handover);
 }
 
 /*
@@ -3260,11 +3334,6 @@ static void try_enable_default_console(struct console *newcon)
 		newcon->flags |= CON_CONSDEV;
 }
 
-#define con_printk(lvl, con, fmt, ...)			\
-	printk(lvl pr_fmt("%sconsole [%s%d] " fmt),	\
-	       (con->flags & CON_BOOT) ? "boot" : "",	\
-	       con->name, con->index, ##__VA_ARGS__)
-
 static void console_init_seq(struct console *newcon, bool bootcon_registered)
 {
 	struct console *con;
@@ -3378,6 +3447,15 @@ void register_console(struct console *newcon)
 		goto unlock;
 	}
 
+	if (newcon->flags & CON_NBCON) {
+		/*
+		 * Ensure the nbcon console buffers can be allocated
+		 * before modifying any global data.
+		 */
+		if (!nbcon_alloc(newcon))
+			goto unlock;
+	}
+
 	/*
 	 * See if we want to enable this console driver by default.
 	 *
@@ -3405,8 +3483,11 @@ void register_console(struct console *newcon)
 		err = try_enable_preferred_console(newcon, false);
 
 	/* printk() messages are not printed to the Braille console. */
-	if (err || newcon->flags & CON_BRL)
+	if (err || newcon->flags & CON_BRL) {
+		if (newcon->flags & CON_NBCON)
+			nbcon_free(newcon);
 		goto unlock;
+	}
 
 	/*
 	 * If we have a bootconsole, and are switching to a real console,
@@ -3422,6 +3503,9 @@ void register_console(struct console *newcon)
 	newcon->dropped = 0;
 	console_init_seq(newcon, bootcon_registered);
 
+	if (newcon->flags & CON_NBCON)
+		nbcon_init(newcon);
+
 	/*
 	 * Put this console in the list - keep the
 	 * preferred driver at the head of the list.
@@ -3513,6 +3597,9 @@ static int unregister_console_locked(struct console *console)
 	 */
 	synchronize_srcu(&console_srcu);
 
+	if (console->flags & CON_NBCON)
+		nbcon_free(console);
+
 	console_sysfs_notify();
 
 	if (console->exit)
@@ -3662,10 +3749,12 @@ late_initcall(printk_late_init);
 /* If @con is specified, only wait for that console. Otherwise wait for all. */
 static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress)
 {
-	int remaining = timeout_ms;
+	unsigned long timeout_jiffies = msecs_to_jiffies(timeout_ms);
+	unsigned long remaining_jiffies = timeout_jiffies;
 	struct console *c;
 	u64 last_diff = 0;
 	u64 printk_seq;
+	short flags;
 	int cookie;
 	u64 diff;
 	u64 seq;
@@ -3674,13 +3763,21 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
 
 	seq = prb_next_seq(prb);
 
+	/* Flush the consoles so that records up to @seq are printed. */
+	console_lock();
+	console_unlock();
+
 	for (;;) {
+		unsigned long begin_jiffies;
+		unsigned long slept_jiffies;
+
 		diff = 0;
 
 		/*
 		 * 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. Releasing console_lock flushes more
+		 * records in case @seq is still not printed on all
+		 * usable consoles.
 		 */
 		console_lock();
 
@@ -3688,39 +3785,43 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
 		for_each_console_srcu(c) {
 			if (con && con != c)
 				continue;
+
+			flags = console_srcu_read_flags(c);
+
+			/*
+			 * 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;
+
+			if (flags & CON_NBCON) {
+				printk_seq = nbcon_seq_read(c);
+			} else {
+				printk_seq = c->seq;
+			}
+
 			if (printk_seq < seq)
 				diff += seq - printk_seq;
 		}
 		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)
-			remaining = timeout_ms;
+		if (diff != last_diff && reset_on_progress)
+			remaining_jiffies = timeout_jiffies;
 
 		console_unlock();
 
-		if (diff == 0 || remaining == 0)
+		/* Note: @diff is 0 if there are no usable consoles. */
+		if (diff == 0 || remaining_jiffies == 0)
 			break;
 
-		if (remaining < 0) {
-			/* no timeout limit */
-			msleep(100);
-		} else if (remaining < 100) {
-			msleep(remaining);
-			remaining = 0;
-		} else {
-			msleep(100);
-			remaining -= 100;
-		}
+		/* msleep(1) might sleep much longer. Check time by jiffies. */
+		begin_jiffies = jiffies;
+		msleep(1);
+		slept_jiffies = jiffies - begin_jiffies;
+
+		remaining_jiffies -= min(slept_jiffies, remaining_jiffies);
 
 		last_diff = diff;
 	}
@@ -3741,7 +3842,7 @@ 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 +3899,33 @@ 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 +3942,7 @@ 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, ...)
@@ -4107,7 +4225,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog,
 
 	prb_rec_init_rd(&r, &info, buf, size);
 
-	len = 0;
 	prb_for_each_record(seq, prb, seq, &r) {
 		if (r.info->seq >= iter->next_seq)
 			break;