Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU updates from Ingo Molnad:
 "The main RCU related changes in this cycle were:

   - Removal of spin_unlock_wait()
   - SRCU updates
   - RCU torture-test updates
   - RCU Documentation updates
   - Extend the sys_membarrier() ABI with the MEMBARRIER_CMD_PRIVATE_EXPEDITED variant
   - Miscellaneous RCU fixes
   - CPU-hotplug fixes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (63 commits)
  arch: Remove spin_unlock_wait() arch-specific definitions
  locking: Remove spin_unlock_wait() generic definitions
  drivers/ata: Replace spin_unlock_wait() with lock/unlock pair
  ipc: Replace spin_unlock_wait() with lock/unlock pair
  exit: Replace spin_unlock_wait() with lock/unlock pair
  completion: Replace spin_unlock_wait() with lock/unlock pair
  doc: Set down RCU's scheduling-clock-interrupt needs
  doc: No longer allowed to use rcu_dereference on non-pointers
  doc: Add RCU files to docbook-generation files
  doc: Update memory-barriers.txt for read-to-write dependencies
  doc: Update RCU documentation
  membarrier: Provide expedited private command
  rcu: Remove exports from rcu_idle_exit() and rcu_idle_enter()
  rcu: Add warning to rcu_idle_enter() for irqs enabled
  rcu: Make rcu_idle_enter() rely on callers disabling irqs
  rcu: Add assertions verifying blocked-tasks list
  rcu/tracing: Set disable_rcu_irq_enter on rcu_eqs_exit()
  rcu: Add TPS() protection for _rcu_barrier_trace strings
  rcu: Use idle versions of swait to make idle-hack clear
  swait: Add idle variants which don't contribute to load average
  ...

12 files changed, 112 insertions, 76 deletions

diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 9f0681bf1e87..66260777d644 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -22,17 +22,6 @@
 #include <asm-generic/qspinlock_types.h>
 
 /**
- * queued_spin_unlock_wait - wait until the _current_ lock holder releases the lock
- * @lock : Pointer to queued spinlock structure
- *
- * There is a very slight possibility of live-lock if the lockers keep coming
- * and the waiter is just unfortunate enough to not see any unlock state.
- */
-#ifndef queued_spin_unlock_wait
-extern void queued_spin_unlock_wait(struct qspinlock *lock);
-#endif
-
-/**
  * queued_spin_is_locked - is the spinlock locked?
  * @lock: Pointer to queued spinlock structure
  * Return: 1 if it is locked, 0 otherwise
@@ -41,8 +30,6 @@ extern void queued_spin_unlock_wait(struct qspinlock *lock);
 static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
 {
 	/*
-	 * See queued_spin_unlock_wait().
-	 *
 	 * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL
 	 * isn't immediately observable.
 	 */
@@ -135,6 +122,5 @@ static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 #define arch_spin_trylock(l)		queued_spin_trylock(l)
 #define arch_spin_unlock(l)		queued_spin_unlock(l)
 #define arch_spin_lock_flags(l, f)	queued_spin_lock(l)
-#define arch_spin_unlock_wait(l)	queued_spin_unlock_wait(l)
 
 #endif /* __ASM_GENERIC_QSPINLOCK_H */
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 c05ac5f5aa03..b57c7bedb534 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;
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index d9510e8522d4..ef018a6e4985 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -130,12 +130,6 @@ do {								\
 #define smp_mb__before_spinlock()	smp_wmb()
 #endif
 
-/**
- * raw_spin_unlock_wait - wait until the spinlock gets unlocked
- * @lock: the spinlock in question.
- */
-#define raw_spin_unlock_wait(lock)	arch_spin_unlock_wait(&(lock)->raw_lock)
-
 #ifdef CONFIG_DEBUG_SPINLOCK
  extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock);
 #define do_raw_spin_lock_flags(lock, flags) do_raw_spin_lock(lock)
@@ -369,31 +363,6 @@ static __always_inline int spin_trylock_irq(spinlock_t *lock)
 	raw_spin_trylock_irqsave(spinlock_check(lock), flags); \
 })
 
-/**
- * spin_unlock_wait - Interpose between successive critical sections
- * @lock: the spinlock whose critical sections are to be interposed.
- *
- * Semantically this is equivalent to a spin_lock() immediately
- * followed by a spin_unlock().  However, most architectures have
- * more efficient implementations in which the spin_unlock_wait()
- * cannot block concurrent lock acquisition, and in some cases
- * where spin_unlock_wait() does not write to the lock variable.
- * Nevertheless, spin_unlock_wait() can have high overhead, so if
- * you feel the need to use it, please check to see if there is
- * a better way to get your job done.
- *
- * The ordering guarantees provided by spin_unlock_wait() are:
- *
- * 1.  All accesses preceding the spin_unlock_wait() happen before
- *     any accesses in later critical sections for this same lock.
- * 2.  All accesses following the spin_unlock_wait() happen after
- *     any accesses in earlier critical sections for this same lock.
- */
-static __always_inline void spin_unlock_wait(spinlock_t *lock)
-{
-	raw_spin_unlock_wait(&lock->rlock);
-}
-
 static __always_inline int spin_is_locked(spinlock_t *lock)
 {
 	return raw_spin_is_locked(&lock->rlock);
diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h
index 0d9848de677d..612fb530af41 100644
--- a/include/linux/spinlock_up.h
+++ b/include/linux/spinlock_up.h
@@ -26,11 +26,6 @@
 #ifdef CONFIG_DEBUG_SPINLOCK
 #define arch_spin_is_locked(x)		((x)->slock == 0)
 
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
-	smp_cond_load_acquire(&lock->slock, VAL);
-}
-
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	lock->slock = 0;
@@ -73,7 +68,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 #else /* DEBUG_SPINLOCK */
 #define arch_spin_is_locked(lock)	((void)(lock), 0)
-#define arch_spin_unlock_wait(lock)	do { barrier(); (void)(lock); } while (0)
 /* for sched/core.c and kernel_lock.c: */
 # define arch_spin_lock(lock)		do { barrier(); (void)(lock); } while (0)
 # define arch_spin_lock_flags(lock, flags)	do { barrier(); (void)(lock); } while (0)
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..6d47b3249d8a 100644
--- a/include/uapi/linux/membarrier.h
+++ b/include/uapi/linux/membarrier.h
@@ -40,14 +40,33 @@
  *                          (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_PRIVATE_EXPEDITED:
+ *                          Execute a memory barrier on each running
+ *                          thread belonging to the same process as the current
+ *                          thread. Upon return from system call, the
+ *                          caller thread is ensured that all its running
+ *                          threads siblings 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 only covers threads from the
+ *                          same processes as the caller thread. This
+ *                          command returns 0. The "expedited" commands
+ *                          complete faster than the non-expedited ones,
+ *                          they never block, but have the downside of
+ *                          causing extra overhead.
  *
  * 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
  * the value 0.
  */
 enum membarrier_cmd {
-	MEMBARRIER_CMD_QUERY = 0,
-	MEMBARRIER_CMD_SHARED = (1 << 0),
+	MEMBARRIER_CMD_QUERY			= 0,
+	MEMBARRIER_CMD_SHARED			= (1 << 0),
+	/* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */
+	/* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */
+	MEMBARRIER_CMD_PRIVATE_EXPEDITED	= (1 << 3),
 };
 
 #endif /* _UAPI_LINUX_MEMBARRIER_H */