1 files changed, 116 insertions, 27 deletions

diff --git a/kernel/softirq.c b/kernel/softirq.c
index b315b21fb28c..513b1945987c 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -126,6 +126,18 @@ static DEFINE_PER_CPU(struct softirq_ctrl, softirq_ctrl) = {
 	.lock	= INIT_LOCAL_LOCK(softirq_ctrl.lock),
 };
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static struct lock_class_key bh_lock_key;
+struct lockdep_map bh_lock_map = {
+	.name			= "local_bh",
+	.key			= &bh_lock_key,
+	.wait_type_outer	= LD_WAIT_FREE,
+	.wait_type_inner	= LD_WAIT_CONFIG, /* PREEMPT_RT makes BH preemptible. */
+	.lock_type		= LD_LOCK_PERCPU,
+};
+EXPORT_SYMBOL_GPL(bh_lock_map);
+#endif
+
 /**
  * local_bh_blocked() - Check for idle whether BH processing is blocked
  *
@@ -148,6 +160,8 @@ void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
 
 	WARN_ON_ONCE(in_hardirq());
 
+	lock_map_acquire_read(&bh_lock_map);
+
 	/* First entry of a task into a BH disabled section? */
 	if (!current->softirq_disable_cnt) {
 		if (preemptible()) {
@@ -211,6 +225,8 @@ void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
 	WARN_ON_ONCE(in_hardirq());
 	lockdep_assert_irqs_enabled();
 
+	lock_map_release(&bh_lock_map);
+
 	local_irq_save(flags);
 	curcnt = __this_cpu_read(softirq_ctrl.cnt);
 
@@ -261,6 +277,8 @@ static inline void ksoftirqd_run_begin(void)
 /* Counterpart to ksoftirqd_run_begin() */
 static inline void ksoftirqd_run_end(void)
 {
+	/* pairs with the lock_map_acquire_read() in ksoftirqd_run_begin() */
+	lock_map_release(&bh_lock_map);
 	__local_bh_enable(SOFTIRQ_OFFSET, true);
 	WARN_ON_ONCE(in_interrupt());
 	local_irq_enable();
@@ -280,17 +298,24 @@ static inline void invoke_softirq(void)
 		wakeup_softirqd();
 }
 
+#define SCHED_SOFTIRQ_MASK	BIT(SCHED_SOFTIRQ)
+
 /*
  * flush_smp_call_function_queue() can raise a soft interrupt in a function
- * call. On RT kernels this is undesired and the only known functionality
- * in the block layer which does this is disabled on RT. If soft interrupts
- * get raised which haven't been raised before the flush, warn so it can be
+ * call. On RT kernels this is undesired and the only known functionalities
+ * are in the block layer which is disabled on RT, and in the scheduler for
+ * idle load balancing. If soft interrupts get raised which haven't been
+ * raised before the flush, warn if it is not a SCHED_SOFTIRQ so it can be
  * investigated.
  */
 void do_softirq_post_smp_call_flush(unsigned int was_pending)
 {
-	if (WARN_ON_ONCE(was_pending != local_softirq_pending()))
+	unsigned int is_pending = local_softirq_pending();
+
+	if (unlikely(was_pending != is_pending)) {
+		WARN_ON_ONCE(was_pending != (is_pending & ~SCHED_SOFTIRQ_MASK));
 		invoke_softirq();
+	}
 }
 
 #else /* CONFIG_PREEMPT_RT */
@@ -508,7 +533,7 @@ static inline bool lockdep_softirq_start(void) { return false; }
 static inline void lockdep_softirq_end(bool in_hardirq) { }
 #endif
 
-asmlinkage __visible void __softirq_entry __do_softirq(void)
+static void handle_softirqs(bool ksirqd)
 {
 	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
 	unsigned long old_flags = current->flags;
@@ -551,7 +576,7 @@ restart:
 		kstat_incr_softirqs_this_cpu(vec_nr);
 
 		trace_softirq_entry(vec_nr);
-		h->action(h);
+		h->action();
 		trace_softirq_exit(vec_nr);
 		if (unlikely(prev_count != preempt_count())) {
 			pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n",
@@ -563,8 +588,7 @@ restart:
 		pending >>= softirq_bit;
 	}
 
-	if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
-	    __this_cpu_read(ksoftirqd) == current)
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) && ksirqd)
 		rcu_softirq_qs();
 
 	local_irq_disable();
@@ -584,6 +608,11 @@ restart:
 	current_restore_flags(old_flags, PF_MEMALLOC);
 }
 
+asmlinkage __visible void __softirq_entry __do_softirq(void)
+{
+	handle_softirqs(false);
+}
+
 /**
  * irq_enter_rcu - Enter an interrupt context with RCU watching
  */
@@ -620,6 +649,24 @@ static inline void tick_irq_exit(void)
 #endif
 }
 
+#ifdef CONFIG_IRQ_FORCED_THREADING
+DEFINE_PER_CPU(struct task_struct *, ktimerd);
+DEFINE_PER_CPU(unsigned long, pending_timer_softirq);
+
+static void wake_timersd(void)
+{
+	struct task_struct *tsk = __this_cpu_read(ktimerd);
+
+	if (tsk)
+		wake_up_process(tsk);
+}
+
+#else
+
+static inline void wake_timersd(void) { }
+
+#endif
+
 static inline void __irq_exit_rcu(void)
 {
 #ifndef __ARCH_IRQ_EXIT_IRQS_DISABLED
@@ -632,6 +679,10 @@ static inline void __irq_exit_rcu(void)
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();
 
+	if (IS_ENABLED(CONFIG_IRQ_FORCED_THREADING) && force_irqthreads() &&
+	    local_timers_pending_force_th() && !(in_nmi() | in_hardirq()))
+		wake_timersd();
+
 	tick_irq_exit();
 }
 
@@ -696,7 +747,7 @@ void __raise_softirq_irqoff(unsigned int nr)
 	or_softirq_pending(1UL << nr);
 }
 
-void open_softirq(int nr, void (*action)(struct softirq_action *))
+void open_softirq(int nr, void (*action)(void))
 {
 	softirq_vec[nr].action = action;
 }
@@ -744,10 +795,8 @@ EXPORT_SYMBOL(__tasklet_hi_schedule);
 
 static bool tasklet_clear_sched(struct tasklet_struct *t)
 {
-	if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) {
-		wake_up_var(&t->state);
+	if (test_and_clear_wake_up_bit(TASKLET_STATE_SCHED, &t->state))
 		return true;
-	}
 
 	WARN_ONCE(1, "tasklet SCHED state not set: %s %pS\n",
 		  t->use_callback ? "callback" : "func",
@@ -756,8 +805,7 @@ static bool tasklet_clear_sched(struct tasklet_struct *t)
 	return false;
 }
 
-static void tasklet_action_common(struct softirq_action *a,
-				  struct tasklet_head *tl_head,
+static void tasklet_action_common(struct tasklet_head *tl_head,
 				  unsigned int softirq_nr)
 {
 	struct tasklet_struct *list;
@@ -801,16 +849,16 @@ static void tasklet_action_common(struct softirq_action *a,
 	}
 }
 
-static __latent_entropy void tasklet_action(struct softirq_action *a)
+static __latent_entropy void tasklet_action(void)
 {
 	workqueue_softirq_action(false);
-	tasklet_action_common(a, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ);
+	tasklet_action_common(this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ);
 }
 
-static __latent_entropy void tasklet_hi_action(struct softirq_action *a)
+static __latent_entropy void tasklet_hi_action(void)
 {
 	workqueue_softirq_action(true);
-	tasklet_action_common(a, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ);
+	tasklet_action_common(this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ);
 }
 
 void tasklet_setup(struct tasklet_struct *t,
@@ -868,8 +916,7 @@ void tasklet_kill(struct tasklet_struct *t)
 	if (in_interrupt())
 		pr_notice("Attempt to kill tasklet from interrupt\n");
 
-	while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state))
-		wait_var_event(&t->state, !test_bit(TASKLET_STATE_SCHED, &t->state));
+	wait_on_bit_lock(&t->state, TASKLET_STATE_SCHED, TASK_UNINTERRUPTIBLE);
 
 	tasklet_unlock_wait(t);
 	tasklet_clear_sched(t);
@@ -879,16 +926,13 @@ EXPORT_SYMBOL(tasklet_kill);
 #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
 void tasklet_unlock(struct tasklet_struct *t)
 {
-	smp_mb__before_atomic();
-	clear_bit(TASKLET_STATE_RUN, &t->state);
-	smp_mb__after_atomic();
-	wake_up_var(&t->state);
+	clear_and_wake_up_bit(TASKLET_STATE_RUN, &t->state);
 }
 EXPORT_SYMBOL_GPL(tasklet_unlock);
 
 void tasklet_unlock_wait(struct tasklet_struct *t)
 {
-	wait_var_event(&t->state, !test_bit(TASKLET_STATE_RUN, &t->state));
+	wait_on_bit(&t->state, TASKLET_STATE_RUN, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL_GPL(tasklet_unlock_wait);
 #endif
@@ -921,7 +965,7 @@ static void run_ksoftirqd(unsigned int cpu)
 		 * We can safely run softirq on inline stack, as we are not deep
 		 * in the task stack here.
 		 */
-		__do_softirq();
+		handle_softirqs(true);
 		ksoftirqd_run_end();
 		cond_resched();
 		return;
@@ -968,12 +1012,57 @@ static struct smp_hotplug_thread softirq_threads = {
 	.thread_comm		= "ksoftirqd/%u",
 };
 
+#ifdef CONFIG_IRQ_FORCED_THREADING
+static void ktimerd_setup(unsigned int cpu)
+{
+	/* Above SCHED_NORMAL to handle timers before regular tasks. */
+	sched_set_fifo_low(current);
+}
+
+static int ktimerd_should_run(unsigned int cpu)
+{
+	return local_timers_pending_force_th();
+}
+
+void raise_ktimers_thread(unsigned int nr)
+{
+	trace_softirq_raise(nr);
+	__this_cpu_or(pending_timer_softirq, BIT(nr));
+}
+
+static void run_ktimerd(unsigned int cpu)
+{
+	unsigned int timer_si;
+
+	ksoftirqd_run_begin();
+
+	timer_si = local_timers_pending_force_th();
+	__this_cpu_write(pending_timer_softirq, 0);
+	or_softirq_pending(timer_si);
+
+	__do_softirq();
+
+	ksoftirqd_run_end();
+}
+
+static struct smp_hotplug_thread timer_thread = {
+	.store			= &ktimerd,
+	.setup			= ktimerd_setup,
+	.thread_should_run	= ktimerd_should_run,
+	.thread_fn		= run_ktimerd,
+	.thread_comm		= "ktimers/%u",
+};
+#endif
+
 static __init int spawn_ksoftirqd(void)
 {
 	cpuhp_setup_state_nocalls(CPUHP_SOFTIRQ_DEAD, "softirq:dead", NULL,
 				  takeover_tasklets);
 	BUG_ON(smpboot_register_percpu_thread(&softirq_threads));
-
+#ifdef CONFIG_IRQ_FORCED_THREADING
+	if (force_irqthreads())
+		BUG_ON(smpboot_register_percpu_thread(&timer_thread));
+#endif
 	return 0;
 }
 early_initcall(spawn_ksoftirqd);