Merge branch 'rework/kthreads' into for-linus

drivers/tty/sysrq.c

@@ -578,6 +578,7 @@ void __handle_sysrq(int key, bool check_mask)
 
 	rcu_sysrq_start();
 	rcu_read_lock();
+	printk_prefer_direct_enter();
 	/*
 	 * Raise the apparent loglevel to maximum so that the sysrq header
 	 * is shown to provide the user with positive feedback.  We do not
@@ -619,6 +620,7 @@ void __handle_sysrq(int key, bool check_mask)
 		pr_cont("\n");
 		console_loglevel = orig_log_level;
 	}
+	printk_prefer_direct_exit();
 	rcu_read_unlock();
 	rcu_sysrq_end();
 

include/linux/console.h

@@ -16,6 +16,7 @@
 
 #include <linux/atomic.h>
 #include <linux/types.h>
+#include <linux/mutex.h>
 
 struct vc_data;
 struct console_font_op;
@@ -151,6 +152,24 @@ struct console {
 	int	cflag;
 	uint	ispeed;
 	uint	ospeed;
+	u64	seq;
+	unsigned long dropped;
+	struct task_struct *thread;
+	bool	blocked;
+
+	/*
+	 * The per-console lock is used by printing kthreads to synchronize
+	 * this console with callers of console_lock(). This is necessary in
+	 * order to allow printing kthreads to run in parallel to each other,
+	 * while each safely accessing the @blocked field and synchronizing
+	 * against direct printing via console_lock/console_unlock.
+	 *
+	 * Note: For synchronizing against direct printing via
+	 *       console_trylock/console_unlock, see the static global
+	 *       variable @console_kthreads_active.
+	 */
+	struct mutex lock;
+
 	void	*data;
 	struct	 console *next;
 };

include/linux/printk.h

@@ -170,6 +170,11 @@ extern void __printk_safe_exit(void);
 #define printk_deferred_enter __printk_safe_enter
 #define printk_deferred_exit __printk_safe_exit
 
+extern void printk_prefer_direct_enter(void);
+extern void printk_prefer_direct_exit(void);
+
+extern bool pr_flush(int timeout_ms, bool reset_on_progress);
+
 /*
  * Please don't use printk_ratelimit(), because it shares ratelimiting state
  * with all other unrelated printk_ratelimit() callsites.  Instead use
@@ -220,6 +225,19 @@ static inline void printk_deferred_exit(void)
 {
 }
 
+static inline void printk_prefer_direct_enter(void)
+{
+}
+
+static inline void printk_prefer_direct_exit(void)
+{
+}
+
+static inline bool pr_flush(int timeout_ms, bool reset_on_progress)
+{
+	return true;
+}
+
 static inline int printk_ratelimit(void)
 {
 	return 0;
@@ -277,46 +295,58 @@ static inline void printk_trigger_flush(void)
 #endif
 
 #ifdef CONFIG_SMP
-extern int __printk_cpu_trylock(void);
-extern void __printk_wait_on_cpu_lock(void);
-extern void __printk_cpu_unlock(void);
-
-/**
- * printk_cpu_lock_irqsave() - Acquire the printk cpu-reentrant spinning
- *                             lock and disable interrupts.
- * @flags: Stack-allocated storage for saving local interrupt state,
- *         to be passed to printk_cpu_unlock_irqrestore().
- *
- * If the lock is owned by another CPU, spin until it becomes available.
- * Interrupts are restored while spinning.
- */
-#define printk_cpu_lock_irqsave(flags)		\
-	for (;;) {				\
-		local_irq_save(flags);		\
-		if (__printk_cpu_trylock())	\
-			break;			\
-		local_irq_restore(flags);	\
-		__printk_wait_on_cpu_lock();	\
-	}
-
-/**
- * printk_cpu_unlock_irqrestore() - Release the printk cpu-reentrant spinning
- *                                  lock and restore interrupts.
- * @flags: Caller's saved interrupt state, from printk_cpu_lock_irqsave().
- */
-#define printk_cpu_unlock_irqrestore(flags)	\
-	do {					\
-		__printk_cpu_unlock();		\
-		local_irq_restore(flags);	\
-	} while (0)				\
+extern int __printk_cpu_sync_try_get(void);
+extern void __printk_cpu_sync_wait(void);
+extern void __printk_cpu_sync_put(void);
 
 #else
 
-#define printk_cpu_lock_irqsave(flags) ((void)flags)
-#define printk_cpu_unlock_irqrestore(flags) ((void)flags)
-
+#define __printk_cpu_sync_try_get() true
+#define __printk_cpu_sync_wait()
+#define __printk_cpu_sync_put()
 #endif /* CONFIG_SMP */
 
+/**
+ * printk_cpu_sync_get_irqsave() - Disable interrupts and acquire the printk
+ *                                 cpu-reentrant spinning lock.
+ * @flags: Stack-allocated storage for saving local interrupt state,
+ *         to be passed to printk_cpu_sync_put_irqrestore().
+ *
+ * If the lock is owned by another CPU, spin until it becomes available.
+ * Interrupts are restored while spinning.
+ *
+ * CAUTION: This function must be used carefully. It does not behave like a
+ * typical lock. Here are important things to watch out for...
+ *
+ *     * This function is reentrant on the same CPU. Therefore the calling
+ *       code must not assume exclusive access to data if code accessing the
+ *       data can run reentrant or within NMI context on the same CPU.
+ *
+ *     * If there exists usage of this function from NMI context, it becomes
+ *       unsafe to perform any type of locking or spinning to wait for other
+ *       CPUs after calling this function from any context. This includes
+ *       using spinlocks or any other busy-waiting synchronization methods.
+ */
+#define printk_cpu_sync_get_irqsave(flags)		\
+	for (;;) {					\
+		local_irq_save(flags);			\
+		if (__printk_cpu_sync_try_get())	\
+			break;				\
+		local_irq_restore(flags);		\
+		__printk_cpu_sync_wait();		\
+	}
+
+/**
+ * printk_cpu_sync_put_irqrestore() - Release the printk cpu-reentrant spinning
+ *                                    lock and restore interrupts.
+ * @flags: Caller's saved interrupt state, from printk_cpu_sync_get_irqsave().
+ */
+#define printk_cpu_sync_put_irqrestore(flags)	\
+	do {					\
+		__printk_cpu_sync_put();	\
+		local_irq_restore(flags);	\
+	} while (0)
+
 extern int kptr_restrict;
 
 /**

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)

kernel/panic.c

@@ -560,6 +560,8 @@ 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,
@@ -597,6 +599,8 @@ 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

kernel/rcu/tree_stall.h

@@ -619,6 +619,7 @@ static void print_cpu_stall(unsigned long gps)
 	 * See Documentation/RCU/stallwarn.rst for info on how to debug
 	 * RCU CPU stall warnings.
 	 */
+	printk_prefer_direct_enter();
 	trace_rcu_stall_warning(rcu_state.name, TPS("SelfDetected"));
 	pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name);
 	raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags);
@@ -656,6 +657,7 @@ static void print_cpu_stall(unsigned long gps)
 	 */
 	set_tsk_need_resched(current);
 	set_preempt_need_resched();
+	printk_prefer_direct_exit();
 }
 
 static void check_cpu_stall(struct rcu_data *rdp)

kernel/reboot.c

@@ -447,9 +447,11 @@ static int __orderly_reboot(void)
 	ret = run_cmd(reboot_cmd);
 
 	if (ret) {
+		printk_prefer_direct_enter();
 		pr_warn("Failed to start orderly reboot: forcing the issue\n");
 		emergency_sync();
 		kernel_restart(NULL);
+		printk_prefer_direct_exit();
 	}
 
 	return ret;
@@ -462,6 +464,7 @@ static int __orderly_poweroff(bool force)
 	ret = run_cmd(poweroff_cmd);
 
 	if (ret && force) {
+		printk_prefer_direct_enter();
 		pr_warn("Failed to start orderly shutdown: forcing the issue\n");
 
 		/*
@@ -471,6 +474,7 @@ static int __orderly_poweroff(bool force)
 		 */
 		emergency_sync();
 		kernel_power_off();
+		printk_prefer_direct_exit();
 	}
 
 	return ret;
@@ -528,6 +532,8 @@ EXPORT_SYMBOL_GPL(orderly_reboot);
  */
 static void hw_failure_emergency_poweroff_func(struct work_struct *work)
 {
+	printk_prefer_direct_enter();
+
 	/*
 	 * We have reached here after the emergency shutdown waiting period has
 	 * expired. This means orderly_poweroff has not been able to shut off
@@ -544,6 +550,8 @@ static void hw_failure_emergency_poweroff_func(struct work_struct *work)
 	 */
 	pr_emerg("Hardware protection shutdown failed. Trying emergency restart\n");
 	emergency_restart();
+
+	printk_prefer_direct_exit();
 }
 
 static DECLARE_DELAYED_WORK(hw_failure_emergency_poweroff_work,
@@ -582,11 +590,13 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced)
 {
 	static atomic_t allow_proceed = ATOMIC_INIT(1);
 
+	printk_prefer_direct_enter();
+
 	pr_emerg("HARDWARE PROTECTION shutdown (%s)\n", reason);
 
 	/* Shutdown should be initiated only once. */
 	if (!atomic_dec_and_test(&allow_proceed))
-		return;
+		goto out;
 
 	/*
 	 * Queue a backup emergency shutdown in the event of
@@ -594,6 +604,8 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced)
 	 */
 	hw_failure_emergency_poweroff(ms_until_forced);
 	orderly_poweroff(true);
+out:
+	printk_prefer_direct_exit();
 }
 EXPORT_SYMBOL_GPL(hw_protection_shutdown);
 

kernel/watchdog.c

@@ -424,6 +424,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		/* Start period for the next softlockup warning. */
 		update_report_ts();
 
+		printk_prefer_direct_enter();
+
 		pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
 			smp_processor_id(), duration,
 			current->comm, task_pid_nr(current));
@@ -442,6 +444,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK);
 		if (softlockup_panic)
 			panic("softlockup: hung tasks");
+
+		printk_prefer_direct_exit();
 	}
 
 	return HRTIMER_RESTART;

kernel/watchdog_hld.c

@@ -135,6 +135,8 @@ static void watchdog_overflow_callback(struct perf_event *event,
 		if (__this_cpu_read(hard_watchdog_warn) == true)
 			return;
 
+		printk_prefer_direct_enter();
+
 		pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n",
 			 this_cpu);
 		print_modules();
@@ -155,6 +157,8 @@ static void watchdog_overflow_callback(struct perf_event *event,
 		if (hardlockup_panic)
 			nmi_panic(regs, "Hard LOCKUP");
 
+		printk_prefer_direct_exit();
+
 		__this_cpu_write(hard_watchdog_warn, true);
 		return;
 	}

lib/dump_stack.c

@@ -102,9 +102,9 @@ asmlinkage __visible void dump_stack_lvl(const char *log_lvl)
 	 * Permit this cpu to perform nested stack dumps while serialising
 	 * against other CPUs
 	 */
-	printk_cpu_lock_irqsave(flags);
+	printk_cpu_sync_get_irqsave(flags);
 	__dump_stack(log_lvl);
-	printk_cpu_unlock_irqrestore(flags);
+	printk_cpu_sync_put_irqrestore(flags);
 }
 EXPORT_SYMBOL(dump_stack_lvl);
 

lib/nmi_backtrace.c

@@ -99,7 +99,7 @@ bool nmi_cpu_backtrace(struct pt_regs *regs)
 		 * Allow nested NMI backtraces while serializing
 		 * against other CPUs.
 		 */
-		printk_cpu_lock_irqsave(flags);
+		printk_cpu_sync_get_irqsave(flags);
 		if (!READ_ONCE(backtrace_idle) && regs && cpu_in_idle(instruction_pointer(regs))) {
 			pr_warn("NMI backtrace for cpu %d skipped: idling at %pS\n",
 				cpu, (void *)instruction_pointer(regs));
@@ -110,7 +110,7 @@ bool nmi_cpu_backtrace(struct pt_regs *regs)
 			else
 				dump_stack();
 		}
-		printk_cpu_unlock_irqrestore(flags);
+		printk_cpu_sync_put_irqrestore(flags);
 		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
 		return true;
 	}