Merge branch 'rework/nbcon-in-kdb' into for-linus

arch/um/kernel/kmsg_dump.c

@@ -31,7 +31,7 @@ static void kmsg_dumper_stdout(struct kmsg_dumper *dumper,
 		 * expected to output the crash information.
 		 */
 		if (strcmp(con->name, "ttynull") != 0 &&
-		    (console_srcu_read_flags(con) & CON_ENABLED)) {
+		    console_is_usable(con, console_srcu_read_flags(con), true)) {
 			break;
 		}
 	}

drivers/tty/serial/kgdboc.c

@@ -577,7 +577,6 @@ static int __init kgdboc_earlycon_init(char *opt)
 	console_list_lock();
 	for_each_console(con) {
 		if (con->write && con->read &&
-		    (con->flags & (CON_BOOT | CON_ENABLED)) &&
 		    (!opt || !opt[0] || strcmp(con->name, opt) == 0))
 			break;
 	}

include/linux/console.h

@@ -19,6 +19,7 @@
 #include <linux/irq_work.h>
 #include <linux/rculist.h>
 #include <linux/rcuwait.h>
+#include <linux/smp.h>
 #include <linux/types.h>
 #include <linux/vesa.h>
 
@@ -602,16 +603,70 @@ static inline bool console_is_registered(const struct console *con)
 extern void nbcon_cpu_emergency_enter(void);
 extern void nbcon_cpu_emergency_exit(void);
 extern bool nbcon_can_proceed(struct nbcon_write_context *wctxt);
+extern void nbcon_write_context_set_buf(struct nbcon_write_context *wctxt,
+					char *buf, unsigned int len);
 extern bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt);
 extern bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt);
 extern void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt);
+extern bool nbcon_kdb_try_acquire(struct console *con,
+				  struct nbcon_write_context *wctxt);
+extern void nbcon_kdb_release(struct nbcon_write_context *wctxt);
+
+/*
+ * Check if the given console is currently capable and allowed to print
+ * records. Note that this function does not consider the current context,
+ * which can also play a role in deciding if @con can be used to print
+ * records.
+ */
+static inline bool console_is_usable(struct console *con, short flags, bool use_atomic)
+{
+	if (!(flags & CON_ENABLED))
+		return false;
+
+	if ((flags & CON_SUSPENDED))
+		return false;
+
+	if (flags & CON_NBCON) {
+		/* The write_atomic() callback is optional. */
+		if (use_atomic && !con->write_atomic)
+			return false;
+
+		/*
+		 * For the !use_atomic case, @printk_kthreads_running is not
+		 * checked because the write_thread() callback is also used
+		 * via the legacy loop when the printer threads are not
+		 * available.
+		 */
+	} else {
+		if (!con->write)
+			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;
+}
+
 #else
 static inline void nbcon_cpu_emergency_enter(void) { }
 static inline void nbcon_cpu_emergency_exit(void) { }
 static inline bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { return false; }
+static inline void nbcon_write_context_set_buf(struct nbcon_write_context *wctxt,
+					       char *buf, unsigned int len) { }
 static inline bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { return false; }
 static inline bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { return false; }
 static inline void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) { }
+static inline bool nbcon_kdb_try_acquire(struct console *con,
+					 struct nbcon_write_context *wctxt) { return false; }
+static inline void nbcon_kdb_release(struct nbcon_write_context *wctxt) { }
+static inline bool console_is_usable(struct console *con, short flags,
+				     bool use_atomic) { return false; }
 #endif
 
 extern int console_set_on_cmdline;

include/linux/kdb.h

@@ -14,6 +14,7 @@
  */
 
 #include <linux/list.h>
+#include <linux/smp.h>
 
 /* Shifted versions of the command enable bits are be used if the command
  * has no arguments (see kdb_check_flags). This allows commands, such as
@@ -207,11 +208,26 @@ static inline const char *kdb_walk_kallsyms(loff_t *pos)
 /* Dynamic kdb shell command registration */
 extern int kdb_register(kdbtab_t *cmd);
 extern void kdb_unregister(kdbtab_t *cmd);
+
+/* Return true when KDB as locked for printing a message on this CPU. */
+static inline
+bool kdb_printf_on_this_cpu(void)
+{
+	/*
+	 * We can use raw_smp_processor_id() here because the task could
+	 * not get migrated when KDB has locked for printing on this CPU.
+	 */
+	return unlikely(READ_ONCE(kdb_printf_cpu) == raw_smp_processor_id());
+}
+
 #else /* ! CONFIG_KGDB_KDB */
 static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; }
 static inline void kdb_init(int level) {}
 static inline int kdb_register(kdbtab_t *cmd) { return 0; }
 static inline void kdb_unregister(kdbtab_t *cmd) {}
+
+static inline bool kdb_printf_on_this_cpu(void) { return false; }
+
 #endif	/* CONFIG_KGDB_KDB */
 enum {
 	KDB_NOT_INITIALIZED,

kernel/debug/kdb/kdb_io.c

@@ -589,24 +589,41 @@ static void kdb_msg_write(const char *msg, int msg_len)
 	 */
 	cookie = console_srcu_read_lock();
 	for_each_console_srcu(c) {
-		if (!(console_srcu_read_flags(c) & CON_ENABLED))
+		short flags = console_srcu_read_flags(c);
+
+		if (!console_is_usable(c, flags, true))
 			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
-		 * context the risk of deadlock is a bigger problem than risks
-		 * due to re-entering the console driver. We operate directly on
-		 * oops_in_progress rather than using bust_spinlocks() because
-		 * the calls bust_spinlocks() makes on exit are not appropriate
-		 * for this calling context.
-		 */
-		++oops_in_progress;
-		c->write(c, msg, msg_len);
-		--oops_in_progress;
+
+		if (flags & CON_NBCON) {
+			struct nbcon_write_context wctxt = { };
+
+			/*
+			 * Do not continue if the console is NBCON and the context
+			 * can't be acquired.
+			 */
+			if (!nbcon_kdb_try_acquire(c, &wctxt))
+				continue;
+
+			nbcon_write_context_set_buf(&wctxt, (char *)msg, msg_len);
+
+			c->write_atomic(c, &wctxt);
+			nbcon_kdb_release(&wctxt);
+		} else {
+			/*
+			 * Set oops_in_progress to encourage the console drivers to
+			 * disregard their internal spin locks: in the current calling
+			 * context the risk of deadlock is a bigger problem than risks
+			 * due to re-entering the console driver. We operate directly on
+			 * oops_in_progress rather than using bust_spinlocks() because
+			 * the calls bust_spinlocks() makes on exit are not appropriate
+			 * for this calling context.
+			 */
+			++oops_in_progress;
+			c->write(c, msg, msg_len);
+			--oops_in_progress;
+		}
 		touch_nmi_watchdog();
 	}
 	console_srcu_read_unlock(cookie);

kernel/printk/internal.h

@@ -3,7 +3,6 @@
  * internal.h - printk internal definitions
  */
 #include <linux/console.h>
-#include <linux/percpu.h>
 #include <linux/types.h>
 
 #if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL)
@@ -112,47 +111,6 @@ 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
- * records. Note that this function does not consider the current context,
- * which can also play a role in deciding if @con can be used to print
- * records.
- */
-static inline bool console_is_usable(struct console *con, short flags, bool use_atomic)
-{
-	if (!(flags & CON_ENABLED))
-		return false;
-
-	if ((flags & CON_SUSPENDED))
-		return false;
-
-	if (flags & CON_NBCON) {
-		/* The write_atomic() callback is optional. */
-		if (use_atomic && !con->write_atomic)
-			return false;
-
-		/*
-		 * For the !use_atomic case, @printk_kthreads_running is not
-		 * checked because the write_thread() callback is also used
-		 * via the legacy loop when the printer threads are not
-		 * available.
-		 */
-	} else {
-		if (!con->write)
-			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;
-}
-
 /**
  * nbcon_kthread_wake - Wake up a console printing thread
  * @con:	Console to operate on
@@ -204,9 +162,6 @@ static inline bool nbcon_legacy_emit_next_record(struct console *con, bool *hand
 static inline void nbcon_kthread_wake(struct console *con) { }
 static inline void nbcon_kthreads_wake(void) { }
 
-static inline bool console_is_usable(struct console *con, short flags,
-				     bool use_atomic) { return false; }
-
 #endif /* CONFIG_PRINTK */
 
 extern bool have_boot_console;

kernel/printk/nbcon.c

@@ -10,6 +10,7 @@
 #include <linux/export.h>
 #include <linux/init.h>
 #include <linux/irqflags.h>
+#include <linux/kdb.h>
 #include <linux/kthread.h>
 #include <linux/minmax.h>
 #include <linux/panic.h>
@@ -252,13 +253,16 @@ static int nbcon_context_try_acquire_direct(struct nbcon_context *ctxt,
 		 * since all non-panic CPUs are stopped during panic(), it
 		 * is safer to have them avoid gaining console ownership.
 		 *
-		 * If this acquire is a reacquire (and an unsafe takeover
+		 * One exception is when kdb has locked for printing on this CPU.
+		 *
+		 * Second exception is a reacquire (and an unsafe takeover
 		 * has not previously occurred) then it is allowed to attempt
 		 * a direct acquire in panic. This gives console drivers an
 		 * opportunity to perform any necessary cleanup if they were
 		 * interrupted by the panic CPU while printing.
 		 */
 		if (panic_on_other_cpu() &&
+		    !kdb_printf_on_this_cpu() &&
 		    (!is_reacquire || cur->unsafe_takeover)) {
 			return -EPERM;
 		}
@@ -853,8 +857,8 @@ static bool __nbcon_context_update_unsafe(struct nbcon_context *ctxt, bool unsaf
 	return nbcon_context_can_proceed(ctxt, &cur);
 }
 
-static void nbcon_write_context_set_buf(struct nbcon_write_context *wctxt,
-					char *buf, unsigned int len)
+void nbcon_write_context_set_buf(struct nbcon_write_context *wctxt,
+				 char *buf, unsigned int len)
 {
 	struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt);
 	struct console *con = ctxt->console;
@@ -1894,3 +1898,64 @@ void nbcon_device_release(struct console *con)
 	console_srcu_read_unlock(cookie);
 }
 EXPORT_SYMBOL_GPL(nbcon_device_release);
+
+/**
+ * nbcon_kdb_try_acquire - Try to acquire nbcon console and enter unsafe
+ *			   section
+ * @con:	The nbcon console to acquire
+ * @wctxt:	The nbcon write context to be used on success
+ *
+ * Context:	Under console_srcu_read_lock() for emitting a single kdb message
+ *		using the given con->write_atomic() callback. Can be called
+ *		only when the console is usable at the moment.
+ *
+ * Return:	True if the console was acquired. False otherwise.
+ *
+ * kdb emits messages on consoles registered for printk() without
+ * storing them into the ring buffer. It has to acquire the console
+ * ownerhip so that it could call con->write_atomic() callback a safe way.
+ *
+ * This function acquires the nbcon console using priority NBCON_PRIO_EMERGENCY
+ * and marks it unsafe for handover/takeover.
+ */
+bool nbcon_kdb_try_acquire(struct console *con,
+			   struct nbcon_write_context *wctxt)
+{
+	struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt);
+
+	memset(ctxt, 0, sizeof(*ctxt));
+	ctxt->console = con;
+	ctxt->prio    = NBCON_PRIO_EMERGENCY;
+
+	if (!nbcon_context_try_acquire(ctxt, false))
+		return false;
+
+	if (!nbcon_context_enter_unsafe(ctxt))
+		return false;
+
+	return true;
+}
+
+/**
+ * nbcon_kdb_release - Exit unsafe section and release the nbcon console
+ *
+ * @wctxt:	The nbcon write context initialized by a successful
+ *		nbcon_kdb_try_acquire()
+ */
+void nbcon_kdb_release(struct nbcon_write_context *wctxt)
+{
+	struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt);
+
+	if (!nbcon_context_exit_unsafe(ctxt))
+		return;
+
+	nbcon_context_release(ctxt);
+
+	/*
+	 * Flush any new printk() messages added when the console was blocked.
+	 * Only the console used by the given write context was	blocked.
+	 * The console was locked only when the write_atomic() callback
+	 * was usable.
+	 */
+	__nbcon_atomic_flush_pending_con(ctxt->console, prb_next_reserve_seq(prb), false);
+}

kernel/printk/printk.c

@@ -3331,12 +3331,10 @@ 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 +3371,10 @@ 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);