Merge remote-tracking branch 'rcu/rcu/next'

9 files changed, 104 insertions, 24 deletions

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index a2f6707e9fc0..0e849715e5be 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -126,17 +126,11 @@ extern struct group_info init_groups;
 #endif
 
 #ifdef CONFIG_PREEMPT_RCU
-#define INIT_TASK_RCU_TREE_PREEMPT()					\
-	.rcu_blocked_node = NULL,
-#else
-#define INIT_TASK_RCU_TREE_PREEMPT(tsk)
-#endif
-#ifdef CONFIG_PREEMPT_RCU
 #define INIT_TASK_RCU_PREEMPT(tsk)					\
 	.rcu_read_lock_nesting = 0,					\
 	.rcu_read_unlock_special.s = 0,					\
 	.rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry),		\
-	INIT_TASK_RCU_TREE_PREEMPT()
+	.rcu_blocked_node = NULL,
 #else
 #define INIT_TASK_RCU_PREEMPT(tsk)
 #endif
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index f816fc72b51e..96f1baf62ab8 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -58,8 +58,6 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func);
 void call_rcu_bh(struct rcu_head *head, rcu_callback_t func);
 void call_rcu_sched(struct rcu_head *head, rcu_callback_t func);
 void synchronize_sched(void);
-void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func);
-void synchronize_rcu_tasks(void);
 void rcu_barrier_tasks(void);
 
 #ifdef CONFIG_PREEMPT_RCU
@@ -105,11 +103,13 @@ static inline int rcu_preempt_depth(void)
 
 /* Internal to kernel */
 void rcu_init(void);
+extern int rcu_scheduler_active __read_mostly;
 void rcu_sched_qs(void);
 void rcu_bh_qs(void);
 void rcu_check_callbacks(int user);
 void rcu_report_dead(unsigned int cpu);
 void rcu_cpu_starting(unsigned int cpu);
+void rcutree_migrate_callbacks(int cpu);
 
 #ifdef CONFIG_RCU_STALL_COMMON
 void rcu_sysrq_start(void);
@@ -164,8 +164,6 @@ static inline void rcu_init_nohz(void) { }
  * macro rather than an inline function to avoid #include hell.
  */
 #ifdef CONFIG_TASKS_RCU
-#define TASKS_RCU(x) x
-extern struct srcu_struct tasks_rcu_exit_srcu;
 #define rcu_note_voluntary_context_switch_lite(t) \
 	do { \
 		if (READ_ONCE((t)->rcu_tasks_holdout)) \
@@ -176,10 +174,17 @@ extern struct srcu_struct tasks_rcu_exit_srcu;
 		rcu_all_qs(); \
 		rcu_note_voluntary_context_switch_lite(t); \
 	} while (0)
+void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func);
+void synchronize_rcu_tasks(void);
+void exit_tasks_rcu_start(void);
+void exit_tasks_rcu_finish(void);
 #else /* #ifdef CONFIG_TASKS_RCU */
-#define TASKS_RCU(x) do { } while (0)
 #define rcu_note_voluntary_context_switch_lite(t)	do { } while (0)
 #define rcu_note_voluntary_context_switch(t)		rcu_all_qs()
+#define call_rcu_tasks call_rcu_sched
+#define synchronize_rcu_tasks synchronize_sched
+static inline void exit_tasks_rcu_start(void) { }
+static inline void exit_tasks_rcu_finish(void) { }
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
 
 /**
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 5becbbccb998..b3dbf9502fd0 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -116,13 +116,11 @@ static inline void rcu_irq_exit_irqson(void) { }
 static inline void rcu_irq_enter_irqson(void) { }
 static inline void rcu_irq_exit(void) { }
 static inline void exit_rcu(void) { }
-
-#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU)
-extern int rcu_scheduler_active __read_mostly;
+#ifdef CONFIG_SRCU
 void rcu_scheduler_starting(void);
-#else /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
+#else /* #ifndef CONFIG_SRCU */
 static inline void rcu_scheduler_starting(void) { }
-#endif /* #else #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
+#endif /* #else #ifndef CONFIG_SRCU */
 static inline void rcu_end_inkernel_boot(void) { }
 static inline bool rcu_is_watching(void) { return true; }
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8337e2db0bb2..0db4870b477c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -589,9 +589,10 @@ struct task_struct {
 
 #ifdef CONFIG_TASKS_RCU
 	unsigned long			rcu_tasks_nvcsw;
-	bool				rcu_tasks_holdout;
-	struct list_head		rcu_tasks_holdout_list;
+	u8				rcu_tasks_holdout;
+	u8				rcu_tasks_idx;
 	int				rcu_tasks_idle_cpu;
+	struct list_head		rcu_tasks_holdout_list;
 #endif /* #ifdef CONFIG_TASKS_RCU */
 
 	struct sched_info		sched_info;
@@ -1522,10 +1523,11 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
  * cond_resched_lock() will drop the spinlock before scheduling,
  * cond_resched_softirq() will enable bhs before scheduling.
  */
+void rcu_all_qs(void);
 #ifndef CONFIG_PREEMPT
 extern int _cond_resched(void);
 #else
-static inline int _cond_resched(void) { return 0; }
+static inline int _cond_resched(void) { rcu_all_qs(); return 0; }
 #endif
 
 #define cond_resched() ({			\
diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h
index cfbfc540cafc..261471f407a5 100644
--- a/include/linux/srcutiny.h
+++ b/include/linux/srcutiny.h
@@ -87,4 +87,17 @@ static inline void srcu_barrier(struct srcu_struct *sp)
 	synchronize_srcu(sp);
 }
 
+/* Defined here to avoid size increase for non-torture kernels. */
+static inline void srcu_torture_stats_print(struct srcu_struct *sp,
+					    char *tt, char *tf)
+{
+	int idx;
+
+	idx = READ_ONCE(sp->srcu_idx) & 0x1;
+	pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n",
+		 tt, tf, idx,
+		 READ_ONCE(sp->srcu_lock_nesting[!idx]),
+		 READ_ONCE(sp->srcu_lock_nesting[idx]));
+}
+
 #endif
diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 42973f787e7e..a949f4f9e4d7 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -104,8 +104,6 @@ struct srcu_struct {
 #define SRCU_STATE_SCAN1	1
 #define SRCU_STATE_SCAN2	2
 
-void process_srcu(struct work_struct *work);
-
 #define __SRCU_STRUCT_INIT(name)					\
 	{								\
 		.sda = &name##_srcu_data,				\
@@ -141,5 +139,6 @@ void process_srcu(struct work_struct *work);
 
 void synchronize_srcu_expedited(struct srcu_struct *sp);
 void srcu_barrier(struct srcu_struct *sp);
+void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf);
 
 #endif
diff --git a/include/linux/swait.h b/include/linux/swait.h
index c1f9c62a8a50..4a4e180d0a35 100644
--- a/include/linux/swait.h
+++ b/include/linux/swait.h
@@ -169,4 +169,59 @@ do {									\
 	__ret;								\
 })
 
+#define __swait_event_idle(wq, condition)				\
+	(void)___swait_event(wq, condition, TASK_IDLE, 0, schedule())
+
+/**
+ * swait_event_idle - wait without system load contribution
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ *
+ * The process is put to sleep (TASK_IDLE) until the @condition evaluates to
+ * true. The @condition is checked each time the waitqueue @wq is woken up.
+ *
+ * This function is mostly used when a kthread or workqueue waits for some
+ * condition and doesn't want to contribute to system load. Signals are
+ * ignored.
+ */
+#define swait_event_idle(wq, condition)					\
+do {									\
+	if (condition)							\
+		break;							\
+	__swait_event_idle(wq, condition);				\
+} while (0)
+
+#define __swait_event_idle_timeout(wq, condition, timeout)		\
+	___swait_event(wq, ___wait_cond_timeout(condition),		\
+		       TASK_IDLE, timeout,				\
+		       __ret = schedule_timeout(__ret))
+
+/**
+ * swait_event_idle_timeout - wait up to timeout without load contribution
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @timeout: timeout at which we'll give up in jiffies
+ *
+ * The process is put to sleep (TASK_IDLE) until the @condition evaluates to
+ * true. The @condition is checked each time the waitqueue @wq is woken up.
+ *
+ * This function is mostly used when a kthread or workqueue waits for some
+ * condition and doesn't want to contribute to system load. Signals are
+ * ignored.
+ *
+ * Returns:
+ * 0 if the @condition evaluated to %false after the @timeout elapsed,
+ * 1 if the @condition evaluated to %true after the @timeout elapsed,
+ * or the remaining jiffies (at least 1) if the @condition evaluated
+ * to %true before the @timeout elapsed.
+ */
+#define swait_event_idle_timeout(wq, condition, timeout)		\
+({									\
+	long __ret = timeout;						\
+	if (!___wait_cond_timeout(condition))				\
+		__ret = __swait_event_idle_timeout(wq,			\
+						   condition, timeout);	\
+	__ret;								\
+})
+
 #endif /* _LINUX_SWAIT_H */
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 91dc089d65b7..e91ae1f2290d 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -703,6 +703,7 @@ TRACE_EVENT(rcu_batch_end,
  * at the beginning and end of the read, respectively.  Note that the
  * callback address can be NULL.
  */
+#define RCUTORTURENAME_LEN 8
 TRACE_EVENT(rcu_torture_read,
 
 	TP_PROTO(const char *rcutorturename, struct rcu_head *rhp,
@@ -711,7 +712,7 @@ TRACE_EVENT(rcu_torture_read,
 	TP_ARGS(rcutorturename, rhp, secs, c_old, c),
 
 	TP_STRUCT__entry(
-		__field(const char *, rcutorturename)
+		__field(char, rcutorturename[RCUTORTURENAME_LEN])
 		__field(struct rcu_head *, rhp)
 		__field(unsigned long, secs)
 		__field(unsigned long, c_old)
@@ -719,7 +720,9 @@ TRACE_EVENT(rcu_torture_read,
 	),
 
 	TP_fast_assign(
-		__entry->rcutorturename = rcutorturename;
+		strncpy(__entry->rcutorturename, rcutorturename,
+			RCUTORTURENAME_LEN);
+		__entry->rcutorturename[RCUTORTURENAME_LEN - 1] = 0;
 		__entry->rhp = rhp;
 		__entry->secs = secs;
 		__entry->c_old = c_old;
diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h
index e0b108bd2624..ba36d8a6be61 100644
--- a/include/uapi/linux/membarrier.h
+++ b/include/uapi/linux/membarrier.h
@@ -40,6 +40,16 @@
  *                          (non-running threads are de facto in such a
  *                          state). This covers threads from all processes
  *                          running on the system. This command returns 0.
+ * @MEMBARRIER_CMD_SHARED_EXPEDITED:  Execute a memory barrier on all
+ *			    running threads, but in an expedited fashion.
+ *                          Upon return from system call, the caller thread
+ *                          is ensured that all running threads have passed
+ *                          through a state where all memory accesses to
+ *                          user-space addresses match program order between
+ *                          entry to and return from the system call
+ *                          (non-running threads are de facto in such a
+ *                          state). This covers threads from all processes
+ *                          running on the system. This command returns 0.
  *
  * Command to be passed to the membarrier system call. The commands need to
  * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to
@@ -48,6 +58,7 @@
 enum membarrier_cmd {
 	MEMBARRIER_CMD_QUERY = 0,
 	MEMBARRIER_CMD_SHARED = (1 << 0),
+	MEMBARRIER_CMD_SHARED_EXPEDITED = (2 << 0),
 };
 
 #endif /* _UAPI_LINUX_MEMBARRIER_H */