Merge branch 'urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/urgent

Pull two RCU fixes from Paul E. McKenney:

" - Complete the work of commit dd56af42bd82 (rcu: Eliminate deadlock
    between CPU hotplug and expedited grace periods), which was
    intended to allow synchronize_sched_expedited() to be safely
    used when holding locks acquired by CPU-hotplug notifiers.
    This commit makes the put_online_cpus() avoid the deadlock
    instead of just handling the get_online_cpus().

  - Complete the work of commit 35ce7f29a44a (rcu: Create rcuo
    kthreads only for onlined CPUs), which was intended to allow
    RCU to avoid allocating unneeded kthreads on systems where the
    firmware says that there are more CPUs than are really present.
    This commit makes rcu_barrier() aware of the mismatch, so that
    it doesn't hang waiting for non-existent CPUs. "

Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/trace/events/rcu.h

@@ -660,18 +660,18 @@ TRACE_EVENT(rcu_torture_read,
 /*
  * Tracepoint for _rcu_barrier() execution.  The string "s" describes
  * the _rcu_barrier phase:
- *	"Begin": rcu_barrier_callback() started.
- *	"Check": rcu_barrier_callback() checking for piggybacking.
- *	"EarlyExit": rcu_barrier_callback() piggybacked, thus early exit.
- *	"Inc1": rcu_barrier_callback() piggyback check counter incremented.
- *	"Offline": rcu_barrier_callback() found offline CPU
- *	"OnlineNoCB": rcu_barrier_callback() found online no-CBs CPU.
- *	"OnlineQ": rcu_barrier_callback() found online CPU with callbacks.
- *	"OnlineNQ": rcu_barrier_callback() found online CPU, no callbacks.
+ *	"Begin": _rcu_barrier() started.
+ *	"Check": _rcu_barrier() checking for piggybacking.
+ *	"EarlyExit": _rcu_barrier() piggybacked, thus early exit.
+ *	"Inc1": _rcu_barrier() piggyback check counter incremented.
+ *	"OfflineNoCB": _rcu_barrier() found callback on never-online CPU
+ *	"OnlineNoCB": _rcu_barrier() found online no-CBs CPU.
+ *	"OnlineQ": _rcu_barrier() found online CPU with callbacks.
+ *	"OnlineNQ": _rcu_barrier() found online CPU, no callbacks.
  *	"IRQ": An rcu_barrier_callback() callback posted on remote CPU.
  *	"CB": An rcu_barrier_callback() invoked a callback, not the last.
  *	"LastCB": An rcu_barrier_callback() invoked the last callback.
- *	"Inc2": rcu_barrier_callback() piggyback check counter incremented.
+ *	"Inc2": _rcu_barrier() piggyback check counter incremented.
  * The "cpu" argument is the CPU or -1 if meaningless, the "cnt" argument
  * is the count of remaining callbacks, and "done" is the piggybacking count.
  */

kernel/cpu.c

@@ -64,6 +64,8 @@ static struct {
 	 * an ongoing cpu hotplug operation.
 	 */
 	int refcount;
+	/* And allows lockless put_online_cpus(). */
+	atomic_t puts_pending;
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map dep_map;
@@ -113,7 +115,11 @@ void put_online_cpus(void)
 {
 	if (cpu_hotplug.active_writer == current)
 		return;
-	mutex_lock(&cpu_hotplug.lock);
+	if (!mutex_trylock(&cpu_hotplug.lock)) {
+		atomic_inc(&cpu_hotplug.puts_pending);
+		cpuhp_lock_release();
+		return;
+	}
 
 	if (WARN_ON(!cpu_hotplug.refcount))
 		cpu_hotplug.refcount++; /* try to fix things up */
@@ -155,6 +161,12 @@ void cpu_hotplug_begin(void)
 	cpuhp_lock_acquire();
 	for (;;) {
 		mutex_lock(&cpu_hotplug.lock);
+		if (atomic_read(&cpu_hotplug.puts_pending)) {
+			int delta;
+
+			delta = atomic_xchg(&cpu_hotplug.puts_pending, 0);
+			cpu_hotplug.refcount -= delta;
+		}
 		if (likely(!cpu_hotplug.refcount))
 			break;
 		__set_current_state(TASK_UNINTERRUPTIBLE);

kernel/rcu/tree.c

@@ -3299,11 +3299,16 @@ static void _rcu_barrier(struct rcu_state *rsp)
 			continue;
 		rdp = per_cpu_ptr(rsp->rda, cpu);
 		if (rcu_is_nocb_cpu(cpu)) {
-			_rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
-					   rsp->n_barrier_done);
-			atomic_inc(&rsp->barrier_cpu_count);
-			__call_rcu(&rdp->barrier_head, rcu_barrier_callback,
-				   rsp, cpu, 0);
+			if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) {
+				_rcu_barrier_trace(rsp, "OfflineNoCB", cpu,
+						   rsp->n_barrier_done);
+			} else {
+				_rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
+						   rsp->n_barrier_done);
+				atomic_inc(&rsp->barrier_cpu_count);
+				__call_rcu(&rdp->barrier_head,
+					   rcu_barrier_callback, rsp, cpu, 0);
+			}
 		} else if (ACCESS_ONCE(rdp->qlen)) {
 			_rcu_barrier_trace(rsp, "OnlineQ", cpu,
 					   rsp->n_barrier_done);

kernel/rcu/tree.h

@@ -587,6 +587,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
 static void print_cpu_stall_info_end(void);
 static void zero_cpu_stall_ticks(struct rcu_data *rdp);
 static void increment_cpu_stall_ticks(void);
+static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu);
 static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
 static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
 static void rcu_init_one_nocb(struct rcu_node *rnp);

kernel/rcu/tree_plugin.h

@@ -2049,6 +2049,33 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force)
 	}
 }
 
+/*
+ * Does the specified CPU need an RCU callback for the specified flavor
+ * of rcu_barrier()?
+ */
+static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
+{
+	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+	struct rcu_head *rhp;
+
+	/* No-CBs CPUs might have callbacks on any of three lists. */
+	rhp = ACCESS_ONCE(rdp->nocb_head);
+	if (!rhp)
+		rhp = ACCESS_ONCE(rdp->nocb_gp_head);
+	if (!rhp)
+		rhp = ACCESS_ONCE(rdp->nocb_follower_head);
+
+	/* Having no rcuo kthread but CBs after scheduler starts is bad! */
+	if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp) {
+		/* RCU callback enqueued before CPU first came online??? */
+		pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n",
+		       cpu, rhp->func);
+		WARN_ON_ONCE(1);
+	}
+
+	return !!rhp;
+}
+
 /*
  * Enqueue the specified string of rcu_head structures onto the specified
  * CPU's no-CBs lists.  The CPU is specified by rdp, the head of the
@@ -2642,6 +2669,12 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
 
 #else /* #ifdef CONFIG_RCU_NOCB_CPU */
 
+static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
+{
+	WARN_ON_ONCE(1); /* Should be dead code. */
+	return false;
+}
+
 static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 {
 }