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

13 files changed, 123 insertions, 642 deletions

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 55ee9ee814f8..219f82f3ec1a 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -17,11 +17,7 @@
 # define __release(x)	__context__(x,-1)
 # define __cond_lock(x,c)	((c) ? ({ __acquire(x); 1; }) : 0)
 # define __percpu	__attribute__((noderef, address_space(3)))
-#ifdef CONFIG_SPARSE_RCU_POINTER
 # define __rcu		__attribute__((noderef, address_space(4)))
-#else /* CONFIG_SPARSE_RCU_POINTER */
-# define __rcu
-#endif /* CONFIG_SPARSE_RCU_POINTER */
 # define __private	__attribute__((noderef))
 extern void __chk_user_ptr(const volatile void __user *);
 extern void __chk_io_ptr(const volatile void __iomem *);
diff --git a/include/linux/rcu_node_tree.h b/include/linux/rcu_node_tree.h
index 4b766b61e1a0..426cee67f0e2 100644
--- a/include/linux/rcu_node_tree.h
+++ b/include/linux/rcu_node_tree.h
@@ -7,6 +7,10 @@
  * unlimited scalability while maintaining a constant level of contention
  * on the root node.
  *
+ * This seemingly RCU-private file must be available to SRCU users
+ * because the size of the TREE SRCU srcu_struct structure depends
+ * on these definitions.
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h
index ba4d2621d9ca..c3ad00e63556 100644
--- a/include/linux/rcu_segcblist.h
+++ b/include/linux/rcu_segcblist.h
@@ -1,6 +1,10 @@
 /*
  * RCU segmented callback lists
  *
+ * This seemingly RCU-private file must be available to SRCU users
+ * because the size of the TREE SRCU srcu_struct structure depends
+ * on these definitions.
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index e1e5d002fdb9..ce9d21923d75 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -34,104 +34,15 @@
 #define __LINUX_RCUPDATE_H
 
 #include <linux/types.h>
-#include <linux/cache.h>
-#include <linux/spinlock.h>
-#include <linux/threads.h>
-#include <linux/cpumask.h>
-#include <linux/seqlock.h>
-#include <linux/lockdep.h>
-#include <linux/debugobjects.h>
-#include <linux/bug.h>
 #include <linux/compiler.h>
-#include <linux/ktime.h>
+#include <linux/atomic.h>
 #include <linux/irqflags.h>
+#include <linux/preempt.h>
+#include <linux/bottom_half.h>
+#include <linux/lockdep.h>
+#include <asm/processor.h>
+#include <linux/cpumask.h>
 
-#include <asm/barrier.h>
-
-#ifndef CONFIG_TINY_RCU
-extern int rcu_expedited; /* for sysctl */
-extern int rcu_normal;    /* also for sysctl */
-#endif /* #ifndef CONFIG_TINY_RCU */
-
-#ifdef CONFIG_TINY_RCU
-/* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */
-static inline bool rcu_gp_is_normal(void)  /* Internal RCU use. */
-{
-	return true;
-}
-static inline bool rcu_gp_is_expedited(void)  /* Internal RCU use. */
-{
-	return false;
-}
-
-static inline void rcu_expedite_gp(void)
-{
-}
-
-static inline void rcu_unexpedite_gp(void)
-{
-}
-#else /* #ifdef CONFIG_TINY_RCU */
-bool rcu_gp_is_normal(void);     /* Internal RCU use. */
-bool rcu_gp_is_expedited(void);  /* Internal RCU use. */
-void rcu_expedite_gp(void);
-void rcu_unexpedite_gp(void);
-#endif /* #else #ifdef CONFIG_TINY_RCU */
-
-enum rcutorture_type {
-	RCU_FLAVOR,
-	RCU_BH_FLAVOR,
-	RCU_SCHED_FLAVOR,
-	RCU_TASKS_FLAVOR,
-	SRCU_FLAVOR,
-	INVALID_RCU_FLAVOR
-};
-
-#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
-void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
-			    unsigned long *gpnum, unsigned long *completed);
-void rcutorture_record_test_transition(void);
-void rcutorture_record_progress(unsigned long vernum);
-void do_trace_rcu_torture_read(const char *rcutorturename,
-			       struct rcu_head *rhp,
-			       unsigned long secs,
-			       unsigned long c_old,
-			       unsigned long c);
-bool rcu_irq_enter_disabled(void);
-#else
-static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
-					  int *flags,
-					  unsigned long *gpnum,
-					  unsigned long *completed)
-{
-	*flags = 0;
-	*gpnum = 0;
-	*completed = 0;
-}
-static inline void rcutorture_record_test_transition(void)
-{
-}
-static inline void rcutorture_record_progress(unsigned long vernum)
-{
-}
-static inline bool rcu_irq_enter_disabled(void)
-{
-	return false;
-}
-#ifdef CONFIG_RCU_TRACE
-void do_trace_rcu_torture_read(const char *rcutorturename,
-			       struct rcu_head *rhp,
-			       unsigned long secs,
-			       unsigned long c_old,
-			       unsigned long c);
-#else
-#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
-	do { } while (0)
-#endif
-#endif
-
-#define UINT_CMP_GE(a, b)	(UINT_MAX / 2 >= (a) - (b))
-#define UINT_CMP_LT(a, b)	(UINT_MAX / 2 < (a) - (b))
 #define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
 #define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))
 #define ulong2long(a)		(*(long *)(&(a)))
@@ -139,117 +50,14 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 /* Exported common interfaces */
 
 #ifdef CONFIG_PREEMPT_RCU
-
-/**
- * call_rcu() - Queue an RCU callback for invocation after a 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 pre-existing RCU read-side
- * critical sections have completed.  However, the callback function
- * might well execute concurrently with RCU read-side critical sections
- * that started after call_rcu() was invoked.  RCU read-side critical
- * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
- * and may be nested.
- *
- * Note that all CPUs must agree that the grace period extended beyond
- * all pre-existing RCU read-side critical section.  On systems with more
- * than one CPU, this means that when "func()" is invoked, each CPU is
- * guaranteed to have executed a full memory barrier since the end of its
- * last RCU read-side critical section whose beginning preceded the call
- * to call_rcu().  It also means that each CPU executing an RCU read-side
- * critical section that continues beyond the start of "func()" must have
- * executed a memory barrier after the call_rcu() but before the beginning
- * of that RCU 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 call_rcu() and CPU B invoked the
- * resulting RCU callback function "func()", then both CPU A and CPU B are
- * guaranteed to execute a full memory barrier during the time interval
- * between the call to call_rcu() and the invocation of "func()" -- even
- * if CPU A and CPU B are the same CPU (but again only if the system has
- * more than one CPU).
- */
-void call_rcu(struct rcu_head *head,
-	      rcu_callback_t func);
-
+void call_rcu(struct rcu_head *head, rcu_callback_t func);
 #else /* #ifdef CONFIG_PREEMPT_RCU */
-
-/* In classic RCU, call_rcu() is just call_rcu_sched(). */
 #define	call_rcu	call_rcu_sched
-
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
-/**
- * call_rcu_bh() - Queue an RCU for invocation after a quicker 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_bh() assumes
- * that the read-side critical sections end on completion of a softirq
- * handler. This means that read-side critical sections in process
- * context must not be interrupted by softirqs. This interface is to be
- * used when most of the read-side critical sections are in softirq context.
- * RCU read-side critical sections are delimited by :
- *  - rcu_read_lock() and  rcu_read_unlock(), if in interrupt context.
- *  OR
- *  - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
- *  These may be nested.
- *
- * See the description of call_rcu() for more detailed information on
- * memory ordering guarantees.
- */
-void call_rcu_bh(struct rcu_head *head,
-		 rcu_callback_t func);
-
-/**
- * call_rcu_sched() - Queue an RCU for invocation after sched 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_sched() assumes
- * that the read-side critical sections end on enabling of preemption
- * or on voluntary preemption.
- * RCU read-side critical sections are delimited by :
- *  - rcu_read_lock_sched() and  rcu_read_unlock_sched(),
- *  OR
- *  anything that disables preemption.
- *  These may be nested.
- *
- * See the description of call_rcu() for more detailed information on
- * memory ordering guarantees.
- */
-void call_rcu_sched(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);
-
-/**
- * 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, rcu_callback_t func);
-void synchronize_rcu_tasks(void);
 void rcu_barrier_tasks(void);
 
 #ifdef CONFIG_PREEMPT_RCU
@@ -301,22 +109,12 @@ void rcu_check_callbacks(int user);
 void rcu_report_dead(unsigned int cpu);
 void rcu_cpu_starting(unsigned int cpu);
 
-#ifndef CONFIG_TINY_RCU
-void rcu_end_inkernel_boot(void);
-#else /* #ifndef CONFIG_TINY_RCU */
-static inline void rcu_end_inkernel_boot(void) { }
-#endif /* #ifndef CONFIG_TINY_RCU */
-
 #ifdef CONFIG_RCU_STALL_COMMON
 void rcu_sysrq_start(void);
 void rcu_sysrq_end(void);
 #else /* #ifdef CONFIG_RCU_STALL_COMMON */
-static inline void rcu_sysrq_start(void)
-{
-}
-static inline void rcu_sysrq_end(void)
-{
-}
+static inline void rcu_sysrq_start(void) { }
+static inline void rcu_sysrq_end(void) { }
 #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */
 
 #ifdef CONFIG_NO_HZ_FULL
@@ -330,9 +128,7 @@ static inline void rcu_user_exit(void) { }
 #ifdef CONFIG_RCU_NOCB_CPU
 void rcu_init_nohz(void);
 #else /* #ifdef CONFIG_RCU_NOCB_CPU */
-static inline void rcu_init_nohz(void)
-{
-}
+static inline void rcu_init_nohz(void) { }
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
 
 /**
@@ -366,8 +162,6 @@ 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)) \
@@ -378,10 +172,17 @@ 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 */
 
 /**
@@ -397,10 +198,6 @@ do { \
 		rcu_note_voluntary_context_switch(current); \
 } while (0)
 
-#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) */
-
 /*
  * Infrastructure to implement the synchronize_() primitives in
  * TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
@@ -414,10 +211,6 @@ bool __rcu_is_watching(void);
 #error "Unknown RCU implementation specified to kernel configuration"
 #endif
 
-#define RCU_SCHEDULER_INACTIVE	0
-#define RCU_SCHEDULER_INIT	1
-#define RCU_SCHEDULER_RUNNING	2
-
 /*
  * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic
  * initialization and destruction of rcu_head on the stack. rcu_head structures
@@ -430,30 +223,16 @@ void destroy_rcu_head(struct rcu_head *head);
 void init_rcu_head_on_stack(struct rcu_head *head);
 void destroy_rcu_head_on_stack(struct rcu_head *head);
 #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-static inline void init_rcu_head(struct rcu_head *head)
-{
-}
-
-static inline void destroy_rcu_head(struct rcu_head *head)
-{
-}
-
-static inline void init_rcu_head_on_stack(struct rcu_head *head)
-{
-}
-
-static inline void destroy_rcu_head_on_stack(struct rcu_head *head)
-{
-}
+static inline void init_rcu_head(struct rcu_head *head) { }
+static inline void destroy_rcu_head(struct rcu_head *head) { }
+static inline void init_rcu_head_on_stack(struct rcu_head *head) { }
+static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
 #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU)
 bool rcu_lockdep_current_cpu_online(void);
 #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
-static inline bool rcu_lockdep_current_cpu_online(void)
-{
-	return true;
-}
+static inline bool rcu_lockdep_current_cpu_online(void) { return true; }
 #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -473,18 +252,8 @@ extern struct lockdep_map rcu_bh_lock_map;
 extern struct lockdep_map rcu_sched_lock_map;
 extern struct lockdep_map rcu_callback_map;
 int debug_lockdep_rcu_enabled(void);
-
 int rcu_read_lock_held(void);
 int rcu_read_lock_bh_held(void);
-
-/**
- * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
- *
- * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
- * RCU-sched read-side critical section.  In absence of
- * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
- * critical section unless it can prove otherwise.
- */
 int rcu_read_lock_sched_held(void);
 
 #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
@@ -531,9 +300,7 @@ static inline void rcu_preempt_sleep_check(void)
 			 "Illegal context switch in RCU read-side critical section");
 }
 #else /* #ifdef CONFIG_PROVE_RCU */
-static inline void rcu_preempt_sleep_check(void)
-{
-}
+static inline void rcu_preempt_sleep_check(void) { }
 #endif /* #else #ifdef CONFIG_PROVE_RCU */
 
 #define rcu_sleep_check()						\
@@ -1084,52 +851,6 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 #define kfree_rcu(ptr, rcu_head)					\
 	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
 
-#ifdef CONFIG_TINY_RCU
-static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
-{
-	*nextevt = KTIME_MAX;
-	return 0;
-}
-#endif /* #ifdef CONFIG_TINY_RCU */
-
-#if defined(CONFIG_RCU_NOCB_CPU_ALL)
-static inline bool rcu_is_nocb_cpu(int cpu) { return true; }
-#elif defined(CONFIG_RCU_NOCB_CPU)
-bool rcu_is_nocb_cpu(int cpu);
-#else
-static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
-#endif
-
-
-/* Only for use by adaptive-ticks code. */
-#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
-bool rcu_sys_is_idle(void);
-void rcu_sysidle_force_exit(void);
-#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
-
-static inline bool rcu_sys_is_idle(void)
-{
-	return false;
-}
-
-static inline void rcu_sysidle_force_exit(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
-
-
-/*
- * Dump the ftrace buffer, but only one time per callsite per boot.
- */
-#define rcu_ftrace_dump(oops_dump_mode) \
-do { \
-	static atomic_t ___rfd_beenhere = ATOMIC_INIT(0); \
-	\
-	if (!atomic_read(&___rfd_beenhere) && \
-	    !atomic_xchg(&___rfd_beenhere, 1)) \
-		ftrace_dump(oops_dump_mode); \
-} while (0)
 
 /*
  * Place this after a lock-acquisition primitive to guarantee that
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 74d9c3a1feee..5becbbccb998 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -25,7 +25,7 @@
 #ifndef __LINUX_TINY_H
 #define __LINUX_TINY_H
 
-#include <linux/cache.h>
+#include <linux/ktime.h>
 
 struct rcu_dynticks;
 static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
@@ -33,10 +33,8 @@ static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
 	return 0;
 }
 
-static inline bool rcu_eqs_special_set(int cpu)
-{
-	return false;  /* Never flag non-existent other CPUs! */
-}
+/* Never flag non-existent other CPUs! */
+static inline bool rcu_eqs_special_set(int cpu) { return false; }
 
 static inline unsigned long get_state_synchronize_rcu(void)
 {
@@ -98,159 +96,38 @@ static inline void kfree_call_rcu(struct rcu_head *head,
 		rcu_note_voluntary_context_switch_lite(current); \
 	} while (0)
 
-/*
- * Take advantage of the fact that there is only one CPU, which
- * allows us to ignore virtualization-based context switches.
- */
-static inline void rcu_virt_note_context_switch(int cpu)
-{
-}
-
-/*
- * Return the number of grace periods started.
- */
-static inline unsigned long rcu_batches_started(void)
-{
-	return 0;
-}
-
-/*
- * Return the number of bottom-half grace periods started.
- */
-static inline unsigned long rcu_batches_started_bh(void)
-{
-	return 0;
-}
-
-/*
- * Return the number of sched grace periods started.
- */
-static inline unsigned long rcu_batches_started_sched(void)
-{
-	return 0;
-}
-
-/*
- * Return the number of grace periods completed.
- */
-static inline unsigned long rcu_batches_completed(void)
-{
-	return 0;
-}
-
-/*
- * Return the number of bottom-half grace periods completed.
- */
-static inline unsigned long rcu_batches_completed_bh(void)
-{
-	return 0;
-}
-
-/*
- * Return the number of sched grace periods completed.
- */
-static inline unsigned long rcu_batches_completed_sched(void)
+static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 {
+	*nextevt = KTIME_MAX;
 	return 0;
 }
 
 /*
- * Return the number of expedited grace periods completed.
- */
-static inline unsigned long rcu_exp_batches_completed(void)
-{
-	return 0;
-}
-
-/*
- * Return the number of expedited sched grace periods completed.
+ * Take advantage of the fact that there is only one CPU, which
+ * allows us to ignore virtualization-based context switches.
  */
-static inline unsigned long rcu_exp_batches_completed_sched(void)
-{
-	return 0;
-}
-
-static inline void rcu_force_quiescent_state(void)
-{
-}
-
-static inline void rcu_bh_force_quiescent_state(void)
-{
-}
-
-static inline void rcu_sched_force_quiescent_state(void)
-{
-}
-
-static inline void show_rcu_gp_kthreads(void)
-{
-}
-
-static inline void rcu_cpu_stall_reset(void)
-{
-}
-
-static inline void rcu_idle_enter(void)
-{
-}
-
-static inline void rcu_idle_exit(void)
-{
-}
-
-static inline void rcu_irq_enter(void)
-{
-}
-
-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)
-{
-}
+static inline void rcu_virt_note_context_switch(int cpu) { }
+static inline void rcu_cpu_stall_reset(void) { }
+static inline void rcu_idle_enter(void) { }
+static inline void rcu_idle_exit(void) { }
+static inline void rcu_irq_enter(void) { }
+static inline bool rcu_irq_enter_disabled(void) { return false; }
+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;
 void rcu_scheduler_starting(void);
 #else /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
-static inline void rcu_scheduler_starting(void)
-{
-}
+static inline void rcu_scheduler_starting(void) { }
 #endif /* #else #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
+static inline void rcu_end_inkernel_boot(void) { }
+static inline bool rcu_is_watching(void) { return true; }
 
-#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
-
-static inline bool rcu_is_watching(void)
-{
-	return __rcu_is_watching();
-}
-
-#else /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
-
-static inline bool rcu_is_watching(void)
-{
-	return true;
-}
-
-#endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
-
-static inline void rcu_request_urgent_qs_task(struct task_struct *t)
-{
-}
-
-static inline void rcu_all_qs(void)
-{
-	barrier(); /* Avoid RCU read-side critical sections leaking across. */
-}
+/* Avoid RCU read-side critical sections leaking across. */
+static inline void rcu_all_qs(void) { barrier(); }
 
 /* RCUtree hotplug events */
 #define rcutree_prepare_cpu      NULL
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 0bacb6b2af69..37d6fd3b7ff8 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -79,37 +79,20 @@ void cond_synchronize_rcu(unsigned long oldstate);
 unsigned long get_state_synchronize_sched(void);
 void cond_synchronize_sched(unsigned long oldstate);
 
-extern unsigned long rcutorture_testseq;
-extern unsigned long rcutorture_vernum;
-unsigned long rcu_batches_started(void);
-unsigned long rcu_batches_started_bh(void);
-unsigned long rcu_batches_started_sched(void);
-unsigned long rcu_batches_completed(void);
-unsigned long rcu_batches_completed_bh(void);
-unsigned long rcu_batches_completed_sched(void);
-unsigned long rcu_exp_batches_completed(void);
-unsigned long rcu_exp_batches_completed_sched(void);
-void show_rcu_gp_kthreads(void);
-
-void rcu_force_quiescent_state(void);
-void rcu_bh_force_quiescent_state(void);
-void rcu_sched_force_quiescent_state(void);
-
 void rcu_idle_enter(void);
 void rcu_idle_exit(void);
 void rcu_irq_enter(void);
 void rcu_irq_exit(void);
 void rcu_irq_enter_irqson(void);
 void rcu_irq_exit_irqson(void);
+bool rcu_irq_enter_disabled(void);
 
 void exit_rcu(void);
 
 void rcu_scheduler_starting(void);
 extern int rcu_scheduler_active __read_mostly;
-
+void rcu_end_inkernel_boot(void);
 bool rcu_is_watching(void);
-void rcu_request_urgent_qs_task(struct task_struct *t);
-
 void rcu_all_qs(void);
 
 /* RCUtree hotplug events */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2b69fc650201..a093771e40c7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -546,9 +546,10 @@ 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;
@@ -1472,10 +1473,11 @@ 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/spinlock.h b/include/linux/spinlock.h
index 59248dcc6ef3..d9510e8522d4 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -369,6 +369,26 @@ 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);
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 167ad8831aaf..d5fbf028cf56 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -60,32 +60,15 @@ int init_srcu_struct(struct srcu_struct *sp);
 #include <linux/srcutiny.h>
 #elif defined(CONFIG_TREE_SRCU)
 #include <linux/srcutree.h>
-#elif defined(CONFIG_CLASSIC_SRCU)
-#include <linux/srcuclassic.h>
-#else
+#elif defined(CONFIG_SRCU)
 #error "Unknown SRCU implementation specified to kernel configuration"
+#else
+/* Dummy definition for things like notifiers.  Actual use gets link error. */
+struct srcu_struct { };
 #endif
 
-/**
- * call_srcu() - Queue a callback for invocation after an SRCU grace period
- * @sp: srcu_struct in queue the callback
- * @head: structure to be used for queueing the SRCU callback.
- * @func: function to be invoked after the SRCU grace period
- *
- * The callback function will be invoked some time after a full SRCU
- * grace period elapses, in other words after all pre-existing SRCU
- * read-side critical sections have completed.  However, the callback
- * function might well execute concurrently with other SRCU read-side
- * critical sections that started after call_srcu() was invoked.  SRCU
- * read-side critical sections are delimited by srcu_read_lock() and
- * srcu_read_unlock(), and may be nested.
- *
- * The callback will be invoked from process context, but must nevertheless
- * be fast and must not block.
- */
 void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
 		void (*func)(struct rcu_head *head));
-
 void cleanup_srcu_struct(struct srcu_struct *sp);
 int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
 void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
diff --git a/include/linux/srcuclassic.h b/include/linux/srcuclassic.h
deleted file mode 100644
index 5753f7322262..000000000000
--- a/include/linux/srcuclassic.h
+++ /dev/null
@@ -1,115 +0,0 @@
-/*
- * Sleepable Read-Copy Update mechanism for mutual exclusion,
- *	classic v4.11 variant.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, you can access it online at
- * http://www.gnu.org/licenses/gpl-2.0.html.
- *
- * Copyright (C) IBM Corporation, 2017
- *
- * Author: Paul McKenney <paulmck@us.ibm.com>
- */
-
-#ifndef _LINUX_SRCU_CLASSIC_H
-#define _LINUX_SRCU_CLASSIC_H
-
-struct srcu_array {
-	unsigned long lock_count[2];
-	unsigned long unlock_count[2];
-};
-
-struct rcu_batch {
-	struct rcu_head *head, **tail;
-};
-
-#define RCU_BATCH_INIT(name) { NULL, &(name.head) }
-
-struct srcu_struct {
-	unsigned long completed;
-	struct srcu_array __percpu *per_cpu_ref;
-	spinlock_t queue_lock; /* protect ->batch_queue, ->running */
-	bool running;
-	/* callbacks just queued */
-	struct rcu_batch batch_queue;
-	/* callbacks try to do the first check_zero */
-	struct rcu_batch batch_check0;
-	/* callbacks done with the first check_zero and the flip */
-	struct rcu_batch batch_check1;
-	struct rcu_batch batch_done;
-	struct delayed_work work;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map dep_map;
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
-};
-
-void process_srcu(struct work_struct *work);
-
-#define __SRCU_STRUCT_INIT(name)					\
-	{								\
-		.completed = -300,					\
-		.per_cpu_ref = &name##_srcu_array,			\
-		.queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock),	\
-		.running = false,					\
-		.batch_queue = RCU_BATCH_INIT(name.batch_queue),	\
-		.batch_check0 = RCU_BATCH_INIT(name.batch_check0),	\
-		.batch_check1 = RCU_BATCH_INIT(name.batch_check1),	\
-		.batch_done = RCU_BATCH_INIT(name.batch_done),		\
-		.work = __DELAYED_WORK_INITIALIZER(name.work, process_srcu, 0),\
-		__SRCU_DEP_MAP_INIT(name)				\
-	}
-
-/*
- * Define and initialize a srcu struct at build time.
- * Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it.
- *
- * Note that although DEFINE_STATIC_SRCU() hides the name from other
- * files, the per-CPU variable rules nevertheless require that the
- * chosen name be globally unique.  These rules also prohibit use of
- * DEFINE_STATIC_SRCU() within a function.  If these rules are too
- * restrictive, declare the srcu_struct manually.  For example, in
- * each file:
- *
- *	static struct srcu_struct my_srcu;
- *
- * Then, before the first use of each my_srcu, manually initialize it:
- *
- *	init_srcu_struct(&my_srcu);
- *
- * See include/linux/percpu-defs.h for the rules on per-CPU variables.
- */
-#define __DEFINE_SRCU(name, is_static)					\
-	static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\
-	is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
-#define DEFINE_SRCU(name)		__DEFINE_SRCU(name, /* not static */)
-#define DEFINE_STATIC_SRCU(name)	__DEFINE_SRCU(name, static)
-
-void synchronize_srcu_expedited(struct srcu_struct *sp);
-void srcu_barrier(struct srcu_struct *sp);
-unsigned long srcu_batches_completed(struct srcu_struct *sp);
-
-static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
-					   struct srcu_struct *sp, int *flags,
-					   unsigned long *gpnum,
-					   unsigned long *completed)
-{
-	if (test_type != SRCU_FLAVOR)
-		return;
-	*flags = 0;
-	*completed = sp->completed;
-	*gpnum = *completed;
-	if (sp->batch_queue.head || sp->batch_check0.head || sp->batch_check0.head)
-		(*gpnum)++;
-}
-
-#endif
diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h
index 42311ee0334f..7e36cec3c4b4 100644
--- a/include/linux/srcutiny.h
+++ b/include/linux/srcutiny.h
@@ -27,15 +27,14 @@
 #include <linux/swait.h>
 
 struct srcu_struct {
-	int srcu_lock_nesting[2];	/* srcu_read_lock() nesting depth. */
+	short srcu_lock_nesting[2];	/* srcu_read_lock() nesting depth. */
+	short srcu_idx;			/* Current reader array element. */
+	u8 srcu_gp_running;		/* GP workqueue running? */
+	u8 srcu_gp_waiting;		/* GP waiting for readers? */
 	struct swait_queue_head srcu_wq;
 					/* Last srcu_read_unlock() wakes GP. */
-	unsigned long srcu_gp_seq;	/* GP seq # for callback tagging. */
-	struct rcu_segcblist srcu_cblist;
-					/* Pending SRCU callbacks. */
-	int srcu_idx;			/* Current reader array element. */
-	bool srcu_gp_running;		/* GP workqueue running? */
-	bool srcu_gp_waiting;		/* GP waiting for readers? */
+	struct rcu_head *srcu_cb_head;	/* Pending callbacks: Head. */
+	struct rcu_head **srcu_cb_tail;	/* Pending callbacks: Tail. */
 	struct work_struct srcu_work;	/* For driving grace periods. */
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map dep_map;
@@ -47,7 +46,7 @@ void srcu_drive_gp(struct work_struct *wp);
 #define __SRCU_STRUCT_INIT(name)					\
 {									\
 	.srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq),	\
-	.srcu_cblist = RCU_SEGCBLIST_INITIALIZER(name.srcu_cblist),	\
+	.srcu_cb_tail = &name.srcu_cb_head,				\
 	.srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp),	\
 	__SRCU_DEP_MAP_INIT(name)					\
 }
@@ -63,6 +62,20 @@ void srcu_drive_gp(struct work_struct *wp);
 
 void synchronize_srcu(struct srcu_struct *sp);
 
+/*
+ * Counts the new reader in the appropriate per-CPU element of the
+ * srcu_struct.  Must be called from process context.
+ * Returns an index that must be passed to the matching srcu_read_unlock().
+ */
+static inline int __srcu_read_lock(struct srcu_struct *sp)
+{
+	int idx;
+
+	idx = READ_ONCE(sp->srcu_idx);
+	WRITE_ONCE(sp->srcu_lock_nesting[idx], sp->srcu_lock_nesting[idx] + 1);
+	return idx;
+}
+
 static inline void synchronize_srcu_expedited(struct srcu_struct *sp)
 {
 	synchronize_srcu(sp);
@@ -73,21 +86,17 @@ static inline void srcu_barrier(struct srcu_struct *sp)
 	synchronize_srcu(sp);
 }
 
-static inline unsigned long srcu_batches_completed(struct srcu_struct *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)
 {
-	return 0;
-}
+	int idx;
 
-static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
-					   struct srcu_struct *sp, int *flags,
-					   unsigned long *gpnum,
-					   unsigned long *completed)
-{
-	if (test_type != SRCU_FLAVOR)
-		return;
-	*flags = 0;
-	*completed = sp->srcu_gp_seq;
-	*gpnum = *completed;
+	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 32e86d85fd11..7886356bdc84 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -40,7 +40,7 @@ struct srcu_data {
 	unsigned long srcu_unlock_count[2];	/* Unlocks per CPU. */
 
 	/* Update-side state. */
-	spinlock_t lock ____cacheline_internodealigned_in_smp;
+	raw_spinlock_t __private lock ____cacheline_internodealigned_in_smp;
 	struct rcu_segcblist srcu_cblist;	/* List of callbacks.*/
 	unsigned long srcu_gp_seq_needed;	/* Furthest future GP needed. */
 	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
@@ -58,7 +58,7 @@ struct srcu_data {
  * Node in SRCU combining tree, similar in function to rcu_data.
  */
 struct srcu_node {
-	spinlock_t lock;
+	raw_spinlock_t __private lock;
 	unsigned long srcu_have_cbs[4];		/* GP seq for children */
 						/*  having CBs, but only */
 						/*  is > ->srcu_gq_seq. */
@@ -78,7 +78,7 @@ struct srcu_struct {
 	struct srcu_node *level[RCU_NUM_LVLS + 1];
 						/* First node at each level. */
 	struct mutex srcu_cb_mutex;		/* Serialize CB preparation. */
-	spinlock_t gp_lock;			/* protect ->srcu_cblist */
+	raw_spinlock_t __private lock;		/* Protect counters */
 	struct mutex srcu_gp_mutex;		/* Serialize GP work. */
 	unsigned int srcu_idx;			/* Current rdr array element. */
 	unsigned long srcu_gp_seq;		/* Grace-period seq #. */
@@ -109,7 +109,7 @@ void process_srcu(struct work_struct *work);
 #define __SRCU_STRUCT_INIT(name)					\
 	{								\
 		.sda = &name##_srcu_data,				\
-		.gp_lock = __SPIN_LOCK_UNLOCKED(name.gp_lock),		\
+		.lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock),		\
 		.srcu_gp_seq_needed = 0 - 1,				\
 		__SRCU_DEP_MAP_INIT(name)				\
 	}
@@ -141,10 +141,6 @@ void process_srcu(struct work_struct *work);
 
 void synchronize_srcu_expedited(struct srcu_struct *sp);
 void srcu_barrier(struct srcu_struct *sp);
-unsigned long srcu_batches_completed(struct srcu_struct *sp);
-
-void srcutorture_get_gp_data(enum rcutorture_type test_type,
-			     struct srcu_struct *sp, int *flags,
-			     unsigned long *gpnum, unsigned long *completed);
+void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf);
 
 #endif
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index e3facb356838..91dc089d65b7 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -742,6 +742,7 @@ TRACE_EVENT(rcu_torture_read,
  *	"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.
+ *	"IRQNQ": An rcu_barrier_callback() callback found no callbacks.
  *	"CB": An rcu_barrier_callback() invoked a callback, not the last.
  *	"LastCB": An rcu_barrier_callback() invoked the last callback.
  *	"Inc2": _rcu_barrier() piggyback check counter incremented.