Merge branch 'rcu-tasks.2014.09.10a' into HEAD

rcu-tasks.2014.09.10a: Add RCU-tasks flavor of RCU.

1 files changed, 312 insertions, 1 deletions

diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index ea8ea7b16e11..3ef8ba58694e 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -47,6 +47,8 @@
 #include <linux/hardirq.h>
 #include <linux/delay.h>
 #include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/tick.h>
 
 #define CREATE_TRACE_POINTS
 
@@ -91,7 +93,7 @@ void __rcu_read_unlock(void)
 		barrier();  /* critical section before exit code. */
 		t->rcu_read_lock_nesting = INT_MIN;
 		barrier();  /* assign before ->rcu_read_unlock_special load */
-		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
+		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special.s)))
 			rcu_read_unlock_special(t);
 		barrier();  /* ->rcu_read_unlock_special load before assign */
 		t->rcu_read_lock_nesting = 0;
@@ -379,3 +381,312 @@ static int __init check_cpu_stall_init(void)
 early_initcall(check_cpu_stall_init);
 
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
+
+#ifdef CONFIG_TASKS_RCU
+
+/*
+ * Simple variant of RCU whose quiescent states are voluntary context switch,
+ * user-space execution, and idle.  As such, grace periods can take one good
+ * long time.  There are no read-side primitives similar to rcu_read_lock()
+ * and rcu_read_unlock() because this implementation is intended to get
+ * the system into a safe state for some of the manipulations involved in
+ * tracing and the like.  Finally, this implementation does not support
+ * high call_rcu_tasks() rates from multiple CPUs.  If this is required,
+ * per-CPU callback lists will be needed.
+ */
+
+/* Global list of callbacks and associated lock. */
+static struct rcu_head *rcu_tasks_cbs_head;
+static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
+static DECLARE_WAIT_QUEUE_HEAD(rcu_tasks_cbs_wq);
+static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock);
+
+/* Track exiting tasks in order to allow them to be waited for. */
+DEFINE_SRCU(tasks_rcu_exit_srcu);
+
+/* Control stall timeouts.  Disable with <= 0, otherwise jiffies till stall. */
+static int rcu_task_stall_timeout __read_mostly = HZ * 60 * 10;
+module_param(rcu_task_stall_timeout, int, 0644);
+
+static void rcu_spawn_tasks_kthread(void);
+
+/*
+ * Post an RCU-tasks callback.  First call must be from process context
+ * after the scheduler if fully operational.
+ */
+void call_rcu_tasks(struct rcu_head *rhp, void (*func)(struct rcu_head *rhp))
+{
+	unsigned long flags;
+	bool needwake;
+
+	rhp->next = NULL;
+	rhp->func = func;
+	raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
+	needwake = !rcu_tasks_cbs_head;
+	*rcu_tasks_cbs_tail = rhp;
+	rcu_tasks_cbs_tail = &rhp->next;
+	raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
+	if (needwake) {
+		rcu_spawn_tasks_kthread();
+		wake_up(&rcu_tasks_cbs_wq);
+	}
+}
+EXPORT_SYMBOL_GPL(call_rcu_tasks);
+
+/**
+ * synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full rcu-tasks
+ * grace period has elapsed, in other words after all currently
+ * executing rcu-tasks read-side critical sections have elapsed.  These
+ * read-side critical sections are delimited by calls to schedule(),
+ * cond_resched_rcu_qs(), idle execution, userspace execution, calls
+ * to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
+ *
+ * This is a very specialized primitive, intended only for a few uses in
+ * tracing and other situations requiring manipulation of function
+ * preambles and profiling hooks.  The synchronize_rcu_tasks() function
+ * is not (yet) intended for heavy use from multiple CPUs.
+ *
+ * Note that this guarantee implies further memory-ordering guarantees.
+ * On systems with more than one CPU, when synchronize_rcu_tasks() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since the
+ * end of its last RCU-tasks read-side critical section whose beginning
+ * preceded the call to synchronize_rcu_tasks().  In addition, each CPU
+ * having an RCU-tasks read-side critical section that extends beyond
+ * the return from synchronize_rcu_tasks() is guaranteed to have executed
+ * a full memory barrier after the beginning of synchronize_rcu_tasks()
+ * and before the beginning of that RCU-tasks read-side critical section.
+ * Note that these guarantees include CPUs that are offline, idle, or
+ * executing in user mode, as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked synchronize_rcu_tasks(), which returned
+ * to its caller on CPU B, then both CPU A and CPU B are guaranteed
+ * to have executed a full memory barrier during the execution of
+ * synchronize_rcu_tasks() -- even if CPU A and CPU B are the same CPU
+ * (but again only if the system has more than one CPU).
+ */
+void synchronize_rcu_tasks(void)
+{
+	/* Complain if the scheduler has not started.  */
+	rcu_lockdep_assert(!rcu_scheduler_active,
+			   "synchronize_rcu_tasks called too soon");
+
+	/* Wait for the grace period. */
+	wait_rcu_gp(call_rcu_tasks);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_tasks);
+
+/**
+ * rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks.
+ *
+ * Although the current implementation is guaranteed to wait, it is not
+ * obligated to, for example, if there are no pending callbacks.
+ */
+void rcu_barrier_tasks(void)
+{
+	/* There is only one callback queue, so this is easy.  ;-) */
+	synchronize_rcu_tasks();
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
+
+/* See if tasks are still holding out, complain if so. */
+static void check_holdout_task(struct task_struct *t,
+			       bool needreport, bool *firstreport)
+{
+	int cpu;
+
+	if (!ACCESS_ONCE(t->rcu_tasks_holdout) ||
+	    t->rcu_tasks_nvcsw != ACCESS_ONCE(t->nvcsw) ||
+	    !ACCESS_ONCE(t->on_rq) ||
+	    (IS_ENABLED(CONFIG_NO_HZ_FULL) &&
+	     !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
+		ACCESS_ONCE(t->rcu_tasks_holdout) = false;
+		list_del_init(&t->rcu_tasks_holdout_list);
+		put_task_struct(t);
+		return;
+	}
+	if (!needreport)
+		return;
+	if (*firstreport) {
+		pr_err("INFO: rcu_tasks detected stalls on tasks:\n");
+		*firstreport = false;
+	}
+	cpu = task_cpu(t);
+	pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n",
+		 t, ".I"[is_idle_task(t)],
+		 "N."[cpu < 0 || !tick_nohz_full_cpu(cpu)],
+		 t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout,
+		 t->rcu_tasks_idle_cpu, cpu);
+	sched_show_task(t);
+}
+
+/* RCU-tasks kthread that detects grace periods and invokes callbacks. */
+static int __noreturn rcu_tasks_kthread(void *arg)
+{
+	unsigned long flags;
+	struct task_struct *g, *t;
+	unsigned long lastreport;
+	struct rcu_head *list;
+	struct rcu_head *next;
+	LIST_HEAD(rcu_tasks_holdouts);
+
+	/* FIXME: Add housekeeping affinity. */
+
+	/*
+	 * Each pass through the following loop makes one check for
+	 * newly arrived callbacks, and, if there are some, waits for
+	 * one RCU-tasks grace period and then invokes the callbacks.
+	 * This loop is terminated by the system going down.  ;-)
+	 */
+	for (;;) {
+
+		/* Pick up any new callbacks. */
+		raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
+		list = rcu_tasks_cbs_head;
+		rcu_tasks_cbs_head = NULL;
+		rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
+		raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
+
+		/* If there were none, wait a bit and start over. */
+		if (!list) {
+			wait_event_interruptible(rcu_tasks_cbs_wq,
+						 rcu_tasks_cbs_head);
+			if (!rcu_tasks_cbs_head) {
+				WARN_ON(signal_pending(current));
+				schedule_timeout_interruptible(HZ/10);
+			}
+			continue;
+		}
+
+		/*
+		 * Wait for all pre-existing t->on_rq and t->nvcsw
+		 * transitions to complete.  Invoking synchronize_sched()
+		 * suffices because all these transitions occur with
+		 * interrupts disabled.  Without this synchronize_sched(),
+		 * a read-side critical section that started before the
+		 * grace period might be incorrectly seen as having started
+		 * after the grace period.
+		 *
+		 * This synchronize_sched() also dispenses with the
+		 * need for a memory barrier on the first store to
+		 * ->rcu_tasks_holdout, as it forces the store to happen
+		 * after the beginning of the grace period.
+		 */
+		synchronize_sched();
+
+		/*
+		 * There were callbacks, so we need to wait for an
+		 * RCU-tasks grace period.  Start off by scanning
+		 * the task list for tasks that are not already
+		 * voluntarily blocked.  Mark these tasks and make
+		 * a list of them in rcu_tasks_holdouts.
+		 */
+		rcu_read_lock();
+		for_each_process_thread(g, t) {
+			if (t != current && ACCESS_ONCE(t->on_rq) &&
+			    !is_idle_task(t)) {
+				get_task_struct(t);
+				t->rcu_tasks_nvcsw = ACCESS_ONCE(t->nvcsw);
+				ACCESS_ONCE(t->rcu_tasks_holdout) = true;
+				list_add(&t->rcu_tasks_holdout_list,
+					 &rcu_tasks_holdouts);
+			}
+		}
+		rcu_read_unlock();
+
+		/*
+		 * Wait for tasks that are in the process of exiting.
+		 * This does only part of the job, ensuring that all
+		 * tasks that were previously exiting reach the point
+		 * where they have disabled preemption, allowing the
+		 * later synchronize_sched() to finish the job.
+		 */
+		synchronize_srcu(&tasks_rcu_exit_srcu);
+
+		/*
+		 * Each pass through the following loop scans the list
+		 * of holdout tasks, removing any that are no longer
+		 * holdouts.  When the list is empty, we are done.
+		 */
+		lastreport = jiffies;
+		while (!list_empty(&rcu_tasks_holdouts)) {
+			bool firstreport;
+			bool needreport;
+			int rtst;
+			struct task_struct *t1;
+
+			schedule_timeout_interruptible(HZ);
+			rtst = ACCESS_ONCE(rcu_task_stall_timeout);
+			needreport = rtst > 0 &&
+				     time_after(jiffies, lastreport + rtst);
+			if (needreport)
+				lastreport = jiffies;
+			firstreport = true;
+			WARN_ON(signal_pending(current));
+			list_for_each_entry_safe(t, t1, &rcu_tasks_holdouts,
+						rcu_tasks_holdout_list) {
+				check_holdout_task(t, needreport, &firstreport);
+				cond_resched();
+			}
+		}
+
+		/*
+		 * Because ->on_rq and ->nvcsw are not guaranteed
+		 * to have a full memory barriers prior to them in the
+		 * schedule() path, memory reordering on other CPUs could
+		 * cause their RCU-tasks read-side critical sections to
+		 * extend past the end of the grace period.  However,
+		 * because these ->nvcsw updates are carried out with
+		 * interrupts disabled, we can use synchronize_sched()
+		 * to force the needed ordering on all such CPUs.
+		 *
+		 * This synchronize_sched() also confines all
+		 * ->rcu_tasks_holdout accesses to be within the grace
+		 * period, avoiding the need for memory barriers for
+		 * ->rcu_tasks_holdout accesses.
+		 *
+		 * In addition, this synchronize_sched() waits for exiting
+		 * tasks to complete their final preempt_disable() region
+		 * of execution, cleaning up after the synchronize_srcu()
+		 * above.
+		 */
+		synchronize_sched();
+
+		/* Invoke the callbacks. */
+		while (list) {
+			next = list->next;
+			local_bh_disable();
+			list->func(list);
+			local_bh_enable();
+			list = next;
+			cond_resched();
+		}
+		schedule_timeout_uninterruptible(HZ/10);
+	}
+}
+
+/* Spawn rcu_tasks_kthread() at first call to call_rcu_tasks(). */
+static void rcu_spawn_tasks_kthread(void)
+{
+	static DEFINE_MUTEX(rcu_tasks_kthread_mutex);
+	static struct task_struct *rcu_tasks_kthread_ptr;
+	struct task_struct *t;
+
+	if (ACCESS_ONCE(rcu_tasks_kthread_ptr)) {
+		smp_mb(); /* Ensure caller sees full kthread. */
+		return;
+	}
+	mutex_lock(&rcu_tasks_kthread_mutex);
+	if (rcu_tasks_kthread_ptr) {
+		mutex_unlock(&rcu_tasks_kthread_mutex);
+		return;
+	}
+	t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
+	BUG_ON(IS_ERR(t));
+	smp_mb(); /* Ensure others see full kthread. */
+	ACCESS_ONCE(rcu_tasks_kthread_ptr) = t;
+	mutex_unlock(&rcu_tasks_kthread_mutex);
+}
+
+#endif /* #ifdef CONFIG_TASKS_RCU */