rcu: Track idleness independent of idle tasks

Earlier versions of RCU used the scheduling-clock tick to detect idleness
by checking for the idle task, but handled idleness differently for
CONFIG_NO_HZ=y.  But there are now a number of uses of RCU read-side
critical sections in the idle task, for example, for tracing.  A more
fine-grained detection of idleness is therefore required.

This commit presses the old dyntick-idle code into full-time service,
so that rcu_idle_enter(), previously known as rcu_enter_nohz(), is
always invoked at the beginning of an idle loop iteration.  Similarly,
rcu_idle_exit(), previously known as rcu_exit_nohz(), is always invoked
at the end of an idle-loop iteration.  This allows the idle task to
use RCU everywhere except between consecutive rcu_idle_enter() and
rcu_idle_exit() calls, in turn allowing architecture maintainers to
specify exactly where in the idle loop that RCU may be used.

Because some of the userspace upcall uses can result in what looks
to RCU like half of an interrupt, it is not possible to expect that
the irq_enter() and irq_exit() hooks will give exact counts.  This
patch therefore expands the ->dynticks_nesting counter to 64 bits
and uses two separate bitfields to count process/idle transitions
and interrupt entry/exit transitions.  It is presumed that userspace
upcalls do not happen in the idle loop or from usermode execution
(though usermode might do a system call that results in an upcall).
The counter is hard-reset on each process/idle transition, which
avoids the interrupt entry/exit error from accumulating.  Overflow
is avoided by the 64-bitness of the ->dyntick_nesting counter.

This commit also adds warnings if a non-idle task asks RCU to enter
idle state (and these checks will need some adjustment before applying
Frederic's OS-jitter patches (http://lkml.org/lkml/2011/10/7/246).
In addition, validation of ->dynticks and ->dynticks_nesting is added.

Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>

1 files changed, 162 insertions, 67 deletions

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 5d0b55a3a8c0..1c40326724f6 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -195,12 +195,10 @@ void rcu_note_context_switch(int cpu)
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 
-#ifdef CONFIG_NO_HZ
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
-	.dynticks_nesting = 1,
+	.dynticks_nesting = LLONG_MAX / 2,
 	.dynticks = ATOMIC_INIT(1),
 };
-#endif /* #ifdef CONFIG_NO_HZ */
 
 static int blimit = 10;		/* Maximum callbacks per rcu_do_batch. */
 static int qhimark = 10000;	/* If this many pending, ignore blimit. */
@@ -328,11 +326,11 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp)
 		return 1;
 	}
 
-	/* If preemptible RCU, no point in sending reschedule IPI. */
-	if (rdp->preemptible)
-		return 0;
-
-	/* The CPU is online, so send it a reschedule IPI. */
+	/*
+	 * The CPU is online, so send it a reschedule IPI.  This forces
+	 * it through the scheduler, and (inefficiently) also handles cases
+	 * where idle loops fail to inform RCU about the CPU being idle.
+	 */
 	if (rdp->cpu != smp_processor_id())
 		smp_send_reschedule(rdp->cpu);
 	else
@@ -343,51 +341,97 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp)
 
 #endif /* #ifdef CONFIG_SMP */
 
-#ifdef CONFIG_NO_HZ
+/*
+ * rcu_idle_enter_common - inform RCU that current CPU is moving towards idle
+ *
+ * If the new value of the ->dynticks_nesting counter now is zero,
+ * we really have entered idle, and must do the appropriate accounting.
+ * The caller must have disabled interrupts.
+ */
+static void rcu_idle_enter_common(struct rcu_dynticks *rdtp)
+{
+	if (rdtp->dynticks_nesting) {
+		trace_rcu_dyntick("--=", rdtp->dynticks_nesting);
+		return;
+	}
+	trace_rcu_dyntick("Start", rdtp->dynticks_nesting);
+	if (!idle_cpu(smp_processor_id())) {
+		WARN_ON_ONCE(1);	/* must be idle task! */
+		trace_rcu_dyntick("Error on entry: not idle task",
+				   rdtp->dynticks_nesting);
+		ftrace_dump(DUMP_ALL);
+	}
+	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
+	smp_mb__before_atomic_inc();  /* See above. */
+	atomic_inc(&rdtp->dynticks);
+	smp_mb__after_atomic_inc();  /* Force ordering with next sojourn. */
+	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+}
 
 /**
- * rcu_enter_nohz - inform RCU that current CPU is entering nohz
+ * rcu_idle_enter - inform RCU that current CPU is entering idle
  *
- * Enter nohz mode, in other words, -leave- the mode in which RCU
+ * Enter idle mode, in other words, -leave- the mode in which RCU
  * read-side critical sections can occur.  (Though RCU read-side
- * critical sections can occur in irq handlers in nohz mode, a possibility
- * handled by rcu_irq_enter() and rcu_irq_exit()).
+ * critical sections can occur in irq handlers in idle, a possibility
+ * handled by irq_enter() and irq_exit().)
+ *
+ * We crowbar the ->dynticks_nesting field to zero to allow for
+ * the possibility of usermode upcalls having messed up our count
+ * of interrupt nesting level during the prior busy period.
  */
-void rcu_enter_nohz(void)
+void rcu_idle_enter(void)
 {
 	unsigned long flags;
 	struct rcu_dynticks *rdtp;
 
 	local_irq_save(flags);
 	rdtp = &__get_cpu_var(rcu_dynticks);
-	if (--rdtp->dynticks_nesting) {
-		local_irq_restore(flags);
-		return;
-	}
-	trace_rcu_dyntick("Start");
-	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
-	smp_mb__before_atomic_inc();  /* See above. */
-	atomic_inc(&rdtp->dynticks);
-	smp_mb__after_atomic_inc();  /* Force ordering with next sojourn. */
-	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+	rdtp->dynticks_nesting = 0;
+	rcu_idle_enter_common(rdtp);
 	local_irq_restore(flags);
 }
 
-/*
- * rcu_exit_nohz - inform RCU that current CPU is leaving nohz
+/**
+ * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
+ *
+ * Exit from an interrupt handler, which might possibly result in entering
+ * idle mode, in other words, leaving the mode in which read-side critical
+ * sections can occur.
  *
- * Exit nohz mode, in other words, -enter- the mode in which RCU
- * read-side critical sections normally occur.
+ * This code assumes that the idle loop never does anything that might
+ * result in unbalanced calls to irq_enter() and irq_exit().  If your
+ * architecture violates this assumption, RCU will give you what you
+ * deserve, good and hard.  But very infrequently and irreproducibly.
+ *
+ * Use things like work queues to work around this limitation.
+ *
+ * You have been warned.
  */
-void rcu_exit_nohz(void)
+void rcu_irq_exit(void)
 {
 	unsigned long flags;
 	struct rcu_dynticks *rdtp;
 
 	local_irq_save(flags);
 	rdtp = &__get_cpu_var(rcu_dynticks);
-	if (rdtp->dynticks_nesting++) {
-		local_irq_restore(flags);
+	rdtp->dynticks_nesting--;
+	WARN_ON_ONCE(rdtp->dynticks_nesting < 0);
+	rcu_idle_enter_common(rdtp);
+	local_irq_restore(flags);
+}
+
+/*
+ * rcu_idle_exit_common - inform RCU that current CPU is moving away from idle
+ *
+ * If the new value of the ->dynticks_nesting counter was previously zero,
+ * we really have exited idle, and must do the appropriate accounting.
+ * The caller must have disabled interrupts.
+ */
+static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval)
+{
+	if (oldval) {
+		trace_rcu_dyntick("++=", rdtp->dynticks_nesting);
 		return;
 	}
 	smp_mb__before_atomic_inc();  /* Force ordering w/previous sojourn. */
@@ -395,7 +439,71 @@ void rcu_exit_nohz(void)
 	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
 	smp_mb__after_atomic_inc();  /* See above. */
 	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
-	trace_rcu_dyntick("End");
+	trace_rcu_dyntick("End", oldval);
+	if (!idle_cpu(smp_processor_id())) {
+		WARN_ON_ONCE(1);	/* must be idle task! */
+		trace_rcu_dyntick("Error on exit: not idle task", oldval);
+		ftrace_dump(DUMP_ALL);
+	}
+}
+
+/**
+ * rcu_idle_exit - inform RCU that current CPU is leaving idle
+ *
+ * Exit idle mode, in other words, -enter- the mode in which RCU
+ * read-side critical sections can occur.
+ *
+ * We crowbar the ->dynticks_nesting field to LLONG_MAX/2 to allow for
+ * the possibility of usermode upcalls messing up our count
+ * of interrupt nesting level during the busy period that is just
+ * now starting.
+ */
+void rcu_idle_exit(void)
+{
+	unsigned long flags;
+	struct rcu_dynticks *rdtp;
+	long long oldval;
+
+	local_irq_save(flags);
+	rdtp = &__get_cpu_var(rcu_dynticks);
+	oldval = rdtp->dynticks_nesting;
+	WARN_ON_ONCE(oldval != 0);
+	rdtp->dynticks_nesting = LLONG_MAX / 2;
+	rcu_idle_exit_common(rdtp, oldval);
+	local_irq_restore(flags);
+}
+
+/**
+ * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
+ *
+ * Enter an interrupt handler, which might possibly result in exiting
+ * idle mode, in other words, entering the mode in which read-side critical
+ * sections can occur.
+ *
+ * Note that the Linux kernel is fully capable of entering an interrupt
+ * handler that it never exits, for example when doing upcalls to
+ * user mode!  This code assumes that the idle loop never does upcalls to
+ * user mode.  If your architecture does do upcalls from the idle loop (or
+ * does anything else that results in unbalanced calls to the irq_enter()
+ * and irq_exit() functions), RCU will give you what you deserve, good
+ * and hard.  But very infrequently and irreproducibly.
+ *
+ * Use things like work queues to work around this limitation.
+ *
+ * You have been warned.
+ */
+void rcu_irq_enter(void)
+{
+	unsigned long flags;
+	struct rcu_dynticks *rdtp;
+	long long oldval;
+
+	local_irq_save(flags);
+	rdtp = &__get_cpu_var(rcu_dynticks);
+	oldval = rdtp->dynticks_nesting;
+	rdtp->dynticks_nesting++;
+	WARN_ON_ONCE(rdtp->dynticks_nesting == 0);
+	rcu_idle_exit_common(rdtp, oldval);
 	local_irq_restore(flags);
 }
 
@@ -442,27 +550,32 @@ void rcu_nmi_exit(void)
 	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
 }
 
+#ifdef CONFIG_PROVE_RCU
+
 /**
- * rcu_irq_enter - inform RCU of entry to hard irq context
+ * rcu_is_cpu_idle - see if RCU thinks that the current CPU is idle
  *
- * If the CPU was idle with dynamic ticks active, this updates the
- * rdtp->dynticks to let the RCU handling know that the CPU is active.
+ * If the current CPU is in its idle loop and is neither in an interrupt
+ * or NMI handler, return true.  The caller must have at least disabled
+ * preemption.
  */
-void rcu_irq_enter(void)
+int rcu_is_cpu_idle(void)
 {
-	rcu_exit_nohz();
+	return (atomic_read(&__get_cpu_var(rcu_dynticks).dynticks) & 0x1) == 0;
 }
 
+#endif /* #ifdef CONFIG_PROVE_RCU */
+
 /**
- * rcu_irq_exit - inform RCU of exit from hard irq context
+ * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle
  *
- * If the CPU was idle with dynamic ticks active, update the rdp->dynticks
- * to put let the RCU handling be aware that the CPU is going back to idle
- * with no ticks.
+ * If the current CPU is idle or running at a first-level (not nested)
+ * interrupt from idle, return true.  The caller must have at least
+ * disabled preemption.
  */
-void rcu_irq_exit(void)
+int rcu_is_cpu_rrupt_from_idle(void)
 {
-	rcu_enter_nohz();
+	return __get_cpu_var(rcu_dynticks).dynticks_nesting <= 1;
 }
 
 #ifdef CONFIG_SMP
@@ -512,24 +625,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 
 #endif /* #ifdef CONFIG_SMP */
 
-#else /* #ifdef CONFIG_NO_HZ */
-
-#ifdef CONFIG_SMP
-
-static int dyntick_save_progress_counter(struct rcu_data *rdp)
-{
-	return 0;
-}
-
-static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
-{
-	return rcu_implicit_offline_qs(rdp);
-}
-
-#endif /* #ifdef CONFIG_SMP */
-
-#endif /* #else #ifdef CONFIG_NO_HZ */
-
 int rcu_cpu_stall_suppress __read_mostly;
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
@@ -1334,16 +1429,14 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
  * (user mode or idle loop for rcu, non-softirq execution for rcu_bh).
  * Also schedule RCU core processing.
  *
- * This function must be called with hardirqs disabled.  It is normally
+ * This function must be called from hardirq context.  It is normally
  * invoked from the scheduling-clock interrupt.  If rcu_pending returns
  * false, there is no point in invoking rcu_check_callbacks().
  */
 void rcu_check_callbacks(int cpu, int user)
 {
 	trace_rcu_utilization("Start scheduler-tick");
-	if (user ||
-	    (idle_cpu(cpu) && rcu_scheduler_active &&
-	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+	if (user || rcu_is_cpu_rrupt_from_idle()) {
 
 		/*
 		 * Get here if this CPU took its interrupt from user
@@ -1913,9 +2006,9 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	for (i = 0; i < RCU_NEXT_SIZE; i++)
 		rdp->nxttail[i] = &rdp->nxtlist;
 	rdp->qlen = 0;
-#ifdef CONFIG_NO_HZ
 	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
-#endif /* #ifdef CONFIG_NO_HZ */
+	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != LLONG_MAX / 2);
+	WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
 	rdp->cpu = cpu;
 	rdp->rsp = rsp;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -1942,6 +2035,8 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
 	rdp->qlen_last_fqs_check = 0;
 	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
+	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != LLONG_MAX / 2);
+	WARN_ON_ONCE((atomic_read(&rdp->dynticks->dynticks) & 0x1) != 1);
 	raw_spin_unlock(&rnp->lock);		/* irqs remain disabled. */
 
 	/*