1 files changed, 297 insertions, 60 deletions

diff --git a/kernel/softirq.c b/kernel/softirq.c
index 9908ec4a9bfe..4992853ef53d 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -13,6 +13,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
+#include <linux/local_lock.h>
 #include <linux/mm.h>
 #include <linux/notifier.h>
 #include <linux/percpu.h>
@@ -25,6 +26,7 @@
 #include <linux/smpboot.h>
 #include <linux/tick.h>
 #include <linux/irq.h>
+#include <linux/wait_bit.h>
 
 #include <asm/softirq_stack.h>
 
@@ -102,20 +104,204 @@ EXPORT_PER_CPU_SYMBOL_GPL(hardirq_context);
 #endif
 
 /*
- * preempt_count and SOFTIRQ_OFFSET usage:
- * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
- *   softirq processing.
- * - preempt_count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
+ * SOFTIRQ_OFFSET usage:
+ *
+ * On !RT kernels 'count' is the preempt counter, on RT kernels this applies
+ * to a per CPU counter and to task::softirqs_disabled_cnt.
+ *
+ * - count is changed by SOFTIRQ_OFFSET on entering or leaving softirq
+ *   processing.
+ *
+ * - count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
  *   on local_bh_disable or local_bh_enable.
+ *
  * This lets us distinguish between whether we are currently processing
  * softirq and whether we just have bh disabled.
  */
+#ifdef CONFIG_PREEMPT_RT
+
+/*
+ * RT accounts for BH disabled sections in task::softirqs_disabled_cnt and
+ * also in per CPU softirq_ctrl::cnt. This is necessary to allow tasks in a
+ * softirq disabled section to be preempted.
+ *
+ * The per task counter is used for softirq_count(), in_softirq() and
+ * in_serving_softirqs() because these counts are only valid when the task
+ * holding softirq_ctrl::lock is running.
+ *
+ * The per CPU counter prevents pointless wakeups of ksoftirqd in case that
+ * the task which is in a softirq disabled section is preempted or blocks.
+ */
+struct softirq_ctrl {
+	local_lock_t	lock;
+	int		cnt;
+};
+
+static DEFINE_PER_CPU(struct softirq_ctrl, softirq_ctrl) = {
+	.lock	= INIT_LOCAL_LOCK(softirq_ctrl.lock),
+};
+
+/**
+ * local_bh_blocked() - Check for idle whether BH processing is blocked
+ *
+ * Returns false if the per CPU softirq::cnt is 0 otherwise true.
+ *
+ * This is invoked from the idle task to guard against false positive
+ * softirq pending warnings, which would happen when the task which holds
+ * softirq_ctrl::lock was the only running task on the CPU and blocks on
+ * some other lock.
+ */
+bool local_bh_blocked(void)
+{
+	return __this_cpu_read(softirq_ctrl.cnt) != 0;
+}
+
+void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
+{
+	unsigned long flags;
+	int newcnt;
+
+	WARN_ON_ONCE(in_hardirq());
+
+	/* First entry of a task into a BH disabled section? */
+	if (!current->softirq_disable_cnt) {
+		if (preemptible()) {
+			local_lock(&softirq_ctrl.lock);
+			/* Required to meet the RCU bottomhalf requirements. */
+			rcu_read_lock();
+		} else {
+			DEBUG_LOCKS_WARN_ON(this_cpu_read(softirq_ctrl.cnt));
+		}
+	}
+
+	/*
+	 * Track the per CPU softirq disabled state. On RT this is per CPU
+	 * state to allow preemption of bottom half disabled sections.
+	 */
+	newcnt = __this_cpu_add_return(softirq_ctrl.cnt, cnt);
+	/*
+	 * Reflect the result in the task state to prevent recursion on the
+	 * local lock and to make softirq_count() & al work.
+	 */
+	current->softirq_disable_cnt = newcnt;
+
+	if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && newcnt == cnt) {
+		raw_local_irq_save(flags);
+		lockdep_softirqs_off(ip);
+		raw_local_irq_restore(flags);
+	}
+}
+EXPORT_SYMBOL(__local_bh_disable_ip);
+
+static void __local_bh_enable(unsigned int cnt, bool unlock)
+{
+	unsigned long flags;
+	int newcnt;
+
+	DEBUG_LOCKS_WARN_ON(current->softirq_disable_cnt !=
+			    this_cpu_read(softirq_ctrl.cnt));
+
+	if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && softirq_count() == cnt) {
+		raw_local_irq_save(flags);
+		lockdep_softirqs_on(_RET_IP_);
+		raw_local_irq_restore(flags);
+	}
+
+	newcnt = __this_cpu_sub_return(softirq_ctrl.cnt, cnt);
+	current->softirq_disable_cnt = newcnt;
+
+	if (!newcnt && unlock) {
+		rcu_read_unlock();
+		local_unlock(&softirq_ctrl.lock);
+	}
+}
+
+void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
+{
+	bool preempt_on = preemptible();
+	unsigned long flags;
+	u32 pending;
+	int curcnt;
+
+	WARN_ON_ONCE(in_irq());
+	lockdep_assert_irqs_enabled();
+
+	local_irq_save(flags);
+	curcnt = __this_cpu_read(softirq_ctrl.cnt);
+
+	/*
+	 * If this is not reenabling soft interrupts, no point in trying to
+	 * run pending ones.
+	 */
+	if (curcnt != cnt)
+		goto out;
+
+	pending = local_softirq_pending();
+	if (!pending || ksoftirqd_running(pending))
+		goto out;
+
+	/*
+	 * If this was called from non preemptible context, wake up the
+	 * softirq daemon.
+	 */
+	if (!preempt_on) {
+		wakeup_softirqd();
+		goto out;
+	}
+
+	/*
+	 * Adjust softirq count to SOFTIRQ_OFFSET which makes
+	 * in_serving_softirq() become true.
+	 */
+	cnt = SOFTIRQ_OFFSET;
+	__local_bh_enable(cnt, false);
+	__do_softirq();
+
+out:
+	__local_bh_enable(cnt, preempt_on);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(__local_bh_enable_ip);
+
+/*
+ * Invoked from ksoftirqd_run() outside of the interrupt disabled section
+ * to acquire the per CPU local lock for reentrancy protection.
+ */
+static inline void ksoftirqd_run_begin(void)
+{
+	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+	local_irq_disable();
+}
+
+/* Counterpart to ksoftirqd_run_begin() */
+static inline void ksoftirqd_run_end(void)
+{
+	__local_bh_enable(SOFTIRQ_OFFSET, true);
+	WARN_ON_ONCE(in_interrupt());
+	local_irq_enable();
+}
+
+static inline void softirq_handle_begin(void) { }
+static inline void softirq_handle_end(void) { }
+
+static inline bool should_wake_ksoftirqd(void)
+{
+	return !this_cpu_read(softirq_ctrl.cnt);
+}
+
+static inline void invoke_softirq(void)
+{
+	if (should_wake_ksoftirqd())
+		wakeup_softirqd();
+}
+
+#else /* CONFIG_PREEMPT_RT */
 
-#ifdef CONFIG_TRACE_IRQFLAGS
 /*
- * This is for softirq.c-internal use, where hardirqs are disabled
+ * This one is for softirq.c-internal use, where hardirqs are disabled
  * legitimately:
  */
+#ifdef CONFIG_TRACE_IRQFLAGS
 void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
 {
 	unsigned long flags;
@@ -206,12 +392,38 @@ void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
 }
 EXPORT_SYMBOL(__local_bh_enable_ip);
 
+static inline void softirq_handle_begin(void)
+{
+	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+}
+
+static inline void softirq_handle_end(void)
+{
+	__local_bh_enable(SOFTIRQ_OFFSET);
+	WARN_ON_ONCE(in_interrupt());
+}
+
+static inline void ksoftirqd_run_begin(void)
+{
+	local_irq_disable();
+}
+
+static inline void ksoftirqd_run_end(void)
+{
+	local_irq_enable();
+}
+
+static inline bool should_wake_ksoftirqd(void)
+{
+	return true;
+}
+
 static inline void invoke_softirq(void)
 {
 	if (ksoftirqd_running(local_softirq_pending()))
 		return;
 
-	if (!force_irqthreads) {
+	if (!force_irqthreads || !__this_cpu_read(ksoftirqd)) {
 #ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK
 		/*
 		 * We can safely execute softirq on the current stack if
@@ -250,6 +462,8 @@ asmlinkage __visible void do_softirq(void)
 	local_irq_restore(flags);
 }
 
+#endif /* !CONFIG_PREEMPT_RT */
+
 /*
  * We restart softirq processing for at most MAX_SOFTIRQ_RESTART times,
  * but break the loop if need_resched() is set or after 2 ms.
@@ -318,7 +532,7 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
 
 	pending = local_softirq_pending();
 
-	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+	softirq_handle_begin();
 	in_hardirq = lockdep_softirq_start();
 	account_softirq_enter(current);
 
@@ -354,8 +568,10 @@ restart:
 		pending >>= softirq_bit;
 	}
 
-	if (__this_cpu_read(ksoftirqd) == current)
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
+	    __this_cpu_read(ksoftirqd) == current)
 		rcu_softirq_qs();
+
 	local_irq_disable();
 
 	pending = local_softirq_pending();
@@ -369,8 +585,7 @@ restart:
 
 	account_softirq_exit(current);
 	lockdep_softirq_end(in_hardirq);
-	__local_bh_enable(SOFTIRQ_OFFSET);
-	WARN_ON_ONCE(in_interrupt());
+	softirq_handle_end();
 	current_restore_flags(old_flags, PF_MEMALLOC);
 }
 
@@ -465,7 +680,7 @@ inline void raise_softirq_irqoff(unsigned int nr)
 	 * Otherwise we wake up ksoftirqd to make sure we
 	 * schedule the softirq soon.
 	 */
-	if (!in_interrupt())
+	if (!in_interrupt() && should_wake_ksoftirqd())
 		wakeup_softirqd();
 }
 
@@ -531,6 +746,20 @@ void __tasklet_hi_schedule(struct tasklet_struct *t)
 }
 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);
+		return true;
+	}
+
+	WARN_ONCE(1, "tasklet SCHED state not set: %s %pS\n",
+		  t->use_callback ? "callback" : "func",
+		  t->use_callback ? (void *)t->callback : (void *)t->func);
+
+	return false;
+}
+
 static void tasklet_action_common(struct softirq_action *a,
 				  struct tasklet_head *tl_head,
 				  unsigned int softirq_nr)
@@ -550,13 +779,12 @@ static void tasklet_action_common(struct softirq_action *a,
 
 		if (tasklet_trylock(t)) {
 			if (!atomic_read(&t->count)) {
-				if (!test_and_clear_bit(TASKLET_STATE_SCHED,
-							&t->state))
-					BUG();
-				if (t->use_callback)
-					t->callback(t);
-				else
-					t->func(t->data);
+				if (tasklet_clear_sched(t)) {
+					if (t->use_callback)
+						t->callback(t);
+					else
+						t->func(t->data);
+				}
 				tasklet_unlock(t);
 				continue;
 			}
@@ -606,21 +834,62 @@ void tasklet_init(struct tasklet_struct *t,
 }
 EXPORT_SYMBOL(tasklet_init);
 
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
+/*
+ * Do not use in new code. Waiting for tasklets from atomic contexts is
+ * error prone and should be avoided.
+ */
+void tasklet_unlock_spin_wait(struct tasklet_struct *t)
+{
+	while (test_bit(TASKLET_STATE_RUN, &(t)->state)) {
+		if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+			/*
+			 * Prevent a live lock when current preempted soft
+			 * interrupt processing or prevents ksoftirqd from
+			 * running. If the tasklet runs on a different CPU
+			 * then this has no effect other than doing the BH
+			 * disable/enable dance for nothing.
+			 */
+			local_bh_disable();
+			local_bh_enable();
+		} else {
+			cpu_relax();
+		}
+	}
+}
+EXPORT_SYMBOL(tasklet_unlock_spin_wait);
+#endif
+
 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)) {
-		do {
-			yield();
-		} while (test_bit(TASKLET_STATE_SCHED, &t->state));
-	}
+	while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state))
+		wait_var_event(&t->state, !test_bit(TASKLET_STATE_SCHED, &t->state));
+
 	tasklet_unlock_wait(t);
-	clear_bit(TASKLET_STATE_SCHED, &t->state);
+	tasklet_clear_sched(t);
 }
 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);
+}
+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));
+}
+EXPORT_SYMBOL_GPL(tasklet_unlock_wait);
+#endif
+
 void __init softirq_init(void)
 {
 	int cpu;
@@ -643,53 +912,21 @@ static int ksoftirqd_should_run(unsigned int cpu)
 
 static void run_ksoftirqd(unsigned int cpu)
 {
-	local_irq_disable();
+	ksoftirqd_run_begin();
 	if (local_softirq_pending()) {
 		/*
 		 * We can safely run softirq on inline stack, as we are not deep
 		 * in the task stack here.
 		 */
 		__do_softirq();
-		local_irq_enable();
+		ksoftirqd_run_end();
 		cond_resched();
 		return;
 	}
-	local_irq_enable();
+	ksoftirqd_run_end();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-/*
- * tasklet_kill_immediate is called to remove a tasklet which can already be
- * scheduled for execution on @cpu.
- *
- * Unlike tasklet_kill, this function removes the tasklet
- * _immediately_, even if the tasklet is in TASKLET_STATE_SCHED state.
- *
- * When this function is called, @cpu must be in the CPU_DEAD state.
- */
-void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu)
-{
-	struct tasklet_struct **i;
-
-	BUG_ON(cpu_online(cpu));
-	BUG_ON(test_bit(TASKLET_STATE_RUN, &t->state));
-
-	if (!test_bit(TASKLET_STATE_SCHED, &t->state))
-		return;
-
-	/* CPU is dead, so no lock needed. */
-	for (i = &per_cpu(tasklet_vec, cpu).head; *i; i = &(*i)->next) {
-		if (*i == t) {
-			*i = t->next;
-			/* If this was the tail element, move the tail ptr */
-			if (*i == NULL)
-				per_cpu(tasklet_vec, cpu).tail = i;
-			return;
-		}
-	}
-	BUG();
-}
-
 static int takeover_tasklets(unsigned int cpu)
 {
 	/* CPU is dead, so no lock needed. */