rcu: Add call_rcu_tasks()

This commit adds a new RCU-tasks flavor of RCU, which provides
call_rcu_tasks().  This RCU flavor's quiescent states are voluntary
context switch (not preemption!) and userspace execution (not the idle
loop -- use some sort of schedule_on_each_cpu() if you need to handle the
idle tasks.  Note that unlike other RCU flavors, these quiescent states
occur in tasks, not necessarily CPUs.  Includes fixes from Steven Rostedt.

This RCU flavor is assumed to have very infrequent latency-tolerant
updaters.  This assumption permits significant simplifications, including
a single global callback list protected by a single global lock, along
with a single task-private linked list containing all tasks that have not
yet passed through a quiescent state.  If experience shows this assumption
to be incorrect, the required additional complexity will be added.

Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

3 files changed, 57 insertions, 11 deletions

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 2bb4c4f3531a..dffd9258ee60 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -117,6 +117,14 @@ extern struct group_info init_groups;
 #else
 #define INIT_TASK_RCU_PREEMPT(tsk)
 #endif
+#ifdef CONFIG_TASKS_RCU
+#define INIT_TASK_RCU_TASKS(tsk)					\
+	.rcu_tasks_holdout = false,					\
+	.rcu_tasks_holdout_list =					\
+		LIST_HEAD_INIT(tsk.rcu_tasks_holdout_list),
+#else
+#define INIT_TASK_RCU_TASKS(tsk)
+#endif
 
 extern struct cred init_cred;
 
@@ -224,6 +232,7 @@ extern struct task_group root_task_group;
 	INIT_FTRACE_GRAPH						\
 	INIT_TRACE_RECURSION						\
 	INIT_TASK_RCU_PREEMPT(tsk)					\
+	INIT_TASK_RCU_TASKS(tsk)					\
 	INIT_CPUSET_SEQ(tsk)						\
 	INIT_RT_MUTEXES(tsk)						\
 	INIT_VTIME(tsk)							\
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index d231aa17b1d7..3432063f4c87 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -197,6 +197,26 @@ void call_rcu_sched(struct rcu_head *head,
 
 void synchronize_sched(void);
 
+/**
+ * call_rcu_tasks() - Queue an RCU for invocation task-based grace period
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed. call_rcu_tasks() assumes
+ * that the read-side critical sections end at a voluntary context
+ * switch (not a preemption!), entry into idle, or transition to usermode
+ * execution.  As such, there are no read-side primitives analogous to
+ * rcu_read_lock() and rcu_read_unlock() because this primitive is intended
+ * to determine that all tasks have passed through a safe state, not so
+ * much for data-strcuture synchronization.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
+ */
+void call_rcu_tasks(struct rcu_head *head, void (*func)(struct rcu_head *head));
+
 #ifdef CONFIG_PREEMPT_RCU
 
 void __rcu_read_lock(void);
@@ -294,6 +314,22 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev,
 		rcu_irq_exit(); \
 	} while (0)
 
+/*
+ * Note a voluntary context switch for RCU-tasks benefit.  This is a
+ * macro rather than an inline function to avoid #include hell.
+ */
+#ifdef CONFIG_TASKS_RCU
+#define rcu_note_voluntary_context_switch(t) \
+	do { \
+		preempt_disable(); /* Exclude synchronize_sched(); */ \
+		if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \
+			ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \
+		preempt_enable(); \
+	} while (0)
+#else /* #ifdef CONFIG_TASKS_RCU */
+#define rcu_note_voluntary_context_switch(t)	do { } while (0)
+#endif /* #else #ifdef CONFIG_TASKS_RCU */
+
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP)
 bool __rcu_is_watching(void);
 #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5c2c885ee52b..eaacac4ae77d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1270,6 +1270,11 @@ struct task_struct {
 #ifdef CONFIG_TREE_PREEMPT_RCU
 	struct rcu_node *rcu_blocked_node;
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+#ifdef CONFIG_TASKS_RCU
+	unsigned long rcu_tasks_nvcsw;
+	bool rcu_tasks_holdout;
+	struct list_head rcu_tasks_holdout_list;
+#endif /* #ifdef CONFIG_TASKS_RCU */
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
 	struct sched_info sched_info;
@@ -2000,28 +2005,24 @@ extern void task_clear_jobctl_pending(struct task_struct *task,
 				      unsigned int mask);
 
 #ifdef CONFIG_PREEMPT_RCU
-
 #define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
 #define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
 
 static inline void rcu_copy_process(struct task_struct *p)
 {
+#ifdef CONFIG_PREEMPT_RCU
 	p->rcu_read_lock_nesting = 0;
 	p->rcu_read_unlock_special = 0;
-#ifdef CONFIG_TREE_PREEMPT_RCU
 	p->rcu_blocked_node = NULL;
-#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 	INIT_LIST_HEAD(&p->rcu_node_entry);
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
+#ifdef CONFIG_TASKS_RCU
+	p->rcu_tasks_holdout = false;
+	INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
+#endif /* #ifdef CONFIG_TASKS_RCU */
 }
 
-#else
-
-static inline void rcu_copy_process(struct task_struct *p)
-{
-}
-
-#endif
-
 static inline void tsk_restore_flags(struct task_struct *task,
 				unsigned long orig_flags, unsigned long flags)
 {