rcu/nocb: Detect unsafe checks for offloaded rdp

Provide CONFIG_PROVE_RCU sanity checks to ensure we are always reading
the offloaded state of an rdp in a safe and stable way and prevent from
its value to be changed under us. We must either hold the barrier mutex,
the cpu-hotplug lock (read or write) or the nocb lock.
Local non-preemptible reads are also safe. NOCB kthreads and timers have
their own means of synchronization against the offloaded state updaters.

Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Neeraj Upadhyay <neeraju@codeaurora.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

1 files changed, 76 insertions, 14 deletions

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 2d603771c7dc..cd513ea7b0f9 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -16,8 +16,70 @@
 #ifdef CONFIG_RCU_NOCB_CPU
 static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
 static bool __read_mostly rcu_nocb_poll;    /* Offload kthread are to poll. */
+static inline int rcu_lockdep_is_held_nocb(struct rcu_data *rdp)
+{
+	return lockdep_is_held(&rdp->nocb_lock);
+}
+
+static inline bool rcu_current_is_nocb_kthread(struct rcu_data *rdp)
+{
+	/* Race on early boot between thread creation and assignment */
+	if (!rdp->nocb_cb_kthread || !rdp->nocb_gp_kthread)
+		return true;
+
+	if (current == rdp->nocb_cb_kthread || current == rdp->nocb_gp_kthread)
+		if (in_task())
+			return true;
+	return false;
+}
+
+static inline bool rcu_running_nocb_timer(struct rcu_data *rdp)
+{
+	return (timer_curr_running(&rdp->nocb_timer) && !in_irq());
+}
+#else
+static inline int rcu_lockdep_is_held_nocb(struct rcu_data *rdp)
+{
+	return 0;
+}
+
+static inline bool rcu_current_is_nocb_kthread(struct rcu_data *rdp)
+{
+	return false;
+}
+
+static inline bool rcu_running_nocb_timer(struct rcu_data *rdp)
+{
+	return false;
+}
+
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
+static bool rcu_rdp_is_offloaded(struct rcu_data *rdp)
+{
+	/*
+	 * In order to read the offloaded state of an rdp is a safe
+	 * and stable way and prevent from its value to be changed
+	 * under us, we must either hold the barrier mutex, the cpu
+	 * hotplug lock (read or write) or the nocb lock. Local
+	 * non-preemptible reads are also safe. NOCB kthreads and
+	 * timers have their own means of synchronization against the
+	 * offloaded state updaters.
+	 */
+	RCU_LOCKDEP_WARN(
+		!(lockdep_is_held(&rcu_state.barrier_mutex) ||
+		  (IS_ENABLED(CONFIG_HOTPLUG_CPU) && lockdep_is_cpus_held()) ||
+		  rcu_lockdep_is_held_nocb(rdp) ||
+		  (rdp == this_cpu_ptr(&rcu_data) &&
+		   !(IS_ENABLED(CONFIG_PREEMPT_COUNT) && preemptible())) ||
+		  rcu_current_is_nocb_kthread(rdp) ||
+		  rcu_running_nocb_timer(rdp)),
+		"Unsafe read of RCU_NOCB offloaded state"
+	);
+
+	return rcu_segcblist_is_offloaded(&rdp->cblist);
+}
+
 /*
  * Check the RCU kernel configuration parameters and print informative
  * messages about anything out of the ordinary.
@@ -1257,7 +1319,7 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 {
 	*nextevt = KTIME_MAX;
 	return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist) &&
-	       !rcu_segcblist_is_offloaded(&this_cpu_ptr(&rcu_data)->cblist);
+		!rcu_rdp_is_offloaded(this_cpu_ptr(&rcu_data));
 }
 
 /*
@@ -1352,7 +1414,7 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 
 	/* If no non-offloaded callbacks, RCU doesn't need the CPU. */
 	if (rcu_segcblist_empty(&rdp->cblist) ||
-	    rcu_segcblist_is_offloaded(&this_cpu_ptr(&rcu_data)->cblist)) {
+	    rcu_rdp_is_offloaded(rdp)) {
 		*nextevt = KTIME_MAX;
 		return 0;
 	}
@@ -1388,7 +1450,7 @@ static void rcu_prepare_for_idle(void)
 	int tne;
 
 	lockdep_assert_irqs_disabled();
-	if (rcu_segcblist_is_offloaded(&rdp->cblist))
+	if (rcu_rdp_is_offloaded(rdp))
 		return;
 
 	/* Handle nohz enablement switches conservatively. */
@@ -1429,7 +1491,7 @@ static void rcu_cleanup_after_idle(void)
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
 	lockdep_assert_irqs_disabled();
-	if (rcu_segcblist_is_offloaded(&rdp->cblist))
+	if (rcu_rdp_is_offloaded(rdp))
 		return;
 	if (rcu_try_advance_all_cbs())
 		invoke_rcu_core();
@@ -1560,7 +1622,7 @@ static void rcu_nocb_bypass_unlock(struct rcu_data *rdp)
 static void rcu_nocb_lock(struct rcu_data *rdp)
 {
 	lockdep_assert_irqs_disabled();
-	if (!rcu_segcblist_is_offloaded(&rdp->cblist))
+	if (!rcu_rdp_is_offloaded(rdp))
 		return;
 	raw_spin_lock(&rdp->nocb_lock);
 }
@@ -1571,7 +1633,7 @@ static void rcu_nocb_lock(struct rcu_data *rdp)
  */
 static void rcu_nocb_unlock(struct rcu_data *rdp)
 {
-	if (rcu_segcblist_is_offloaded(&rdp->cblist)) {
+	if (rcu_rdp_is_offloaded(rdp)) {
 		lockdep_assert_irqs_disabled();
 		raw_spin_unlock(&rdp->nocb_lock);
 	}
@@ -1584,7 +1646,7 @@ static void rcu_nocb_unlock(struct rcu_data *rdp)
 static void rcu_nocb_unlock_irqrestore(struct rcu_data *rdp,
 				       unsigned long flags)
 {
-	if (rcu_segcblist_is_offloaded(&rdp->cblist)) {
+	if (rcu_rdp_is_offloaded(rdp)) {
 		lockdep_assert_irqs_disabled();
 		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 	} else {
@@ -1596,7 +1658,7 @@ static void rcu_nocb_unlock_irqrestore(struct rcu_data *rdp,
 static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp)
 {
 	lockdep_assert_irqs_disabled();
-	if (rcu_segcblist_is_offloaded(&rdp->cblist))
+	if (rcu_rdp_is_offloaded(rdp))
 		lockdep_assert_held(&rdp->nocb_lock);
 }
 
@@ -1690,7 +1752,7 @@ static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 {
 	struct rcu_cblist rcl;
 
-	WARN_ON_ONCE(!rcu_segcblist_is_offloaded(&rdp->cblist));
+	WARN_ON_ONCE(!rcu_rdp_is_offloaded(rdp));
 	rcu_lockdep_assert_cblist_protected(rdp);
 	lockdep_assert_held(&rdp->nocb_bypass_lock);
 	if (rhp && !rcu_cblist_n_cbs(&rdp->nocb_bypass)) {
@@ -1718,7 +1780,7 @@ static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 				  unsigned long j)
 {
-	if (!rcu_segcblist_is_offloaded(&rdp->cblist))
+	if (!rcu_rdp_is_offloaded(rdp))
 		return true;
 	rcu_lockdep_assert_cblist_protected(rdp);
 	rcu_nocb_bypass_lock(rdp);
@@ -1732,7 +1794,7 @@ static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 static void rcu_nocb_try_flush_bypass(struct rcu_data *rdp, unsigned long j)
 {
 	rcu_lockdep_assert_cblist_protected(rdp);
-	if (!rcu_segcblist_is_offloaded(&rdp->cblist) ||
+	if (!rcu_rdp_is_offloaded(rdp) ||
 	    !rcu_nocb_bypass_trylock(rdp))
 		return;
 	WARN_ON_ONCE(!rcu_nocb_do_flush_bypass(rdp, NULL, j));
@@ -1764,7 +1826,7 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 	unsigned long j = jiffies;
 	long ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
 
-	if (!rcu_segcblist_is_offloaded(&rdp->cblist)) {
+	if (!rcu_rdp_is_offloaded(rdp)) {
 		*was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist);
 		return false; /* Not offloaded, no bypassing. */
 	}
@@ -2397,7 +2459,7 @@ int rcu_nocb_cpu_deoffload(int cpu)
 	}
 	mutex_lock(&rcu_state.barrier_mutex);
 	cpus_read_lock();
-	if (rcu_segcblist_is_offloaded(&rdp->cblist)) {
+	if (rcu_rdp_is_offloaded(rdp)) {
 		if (cpu_online(cpu))
 			ret = work_on_cpu(cpu, rcu_nocb_rdp_deoffload, rdp);
 		else
@@ -2472,7 +2534,7 @@ int rcu_nocb_cpu_offload(int cpu)
 
 	mutex_lock(&rcu_state.barrier_mutex);
 	cpus_read_lock();
-	if (!rcu_segcblist_is_offloaded(&rdp->cblist)) {
+	if (!rcu_rdp_is_offloaded(rdp)) {
 		if (cpu_online(cpu))
 			ret = work_on_cpu(cpu, rcu_nocb_rdp_offload, rdp);
 		else