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
  ...

26 files changed, 573 insertions, 798 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 4cb8e8b23c6e..9c323a6daa46 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -108,7 +108,6 @@ obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
 obj-$(CONFIG_JUMP_LABEL) += jump_label.o
 obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o
 obj-$(CONFIG_TORTURE_TEST) += torture.o
-obj-$(CONFIG_MEMBARRIER) += membarrier.o
 
 obj-$(CONFIG_HAS_IOMEM) += memremap.o
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index eee033134262..bfbd649ccdc8 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -650,6 +650,7 @@ static int takedown_cpu(unsigned int cpu)
 	__cpu_die(cpu);
 
 	tick_cleanup_dead_cpu(cpu);
+	rcutree_migrate_callbacks(cpu);
 	return 0;
 }
 
diff --git a/kernel/exit.c b/kernel/exit.c
index c5548faa9f37..f9ef3ecc78c1 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -764,7 +764,6 @@ void __noreturn do_exit(long code)
 {
 	struct task_struct *tsk = current;
 	int group_dead;
-	TASKS_RCU(int tasks_rcu_i);
 
 	profile_task_exit(tsk);
 	kcov_task_exit(tsk);
@@ -819,7 +818,8 @@ void __noreturn do_exit(long code)
 	 * Ensure that we must observe the pi_state in exit_mm() ->
 	 * mm_release() -> exit_pi_state_list().
 	 */
-	raw_spin_unlock_wait(&tsk->pi_lock);
+	raw_spin_lock_irq(&tsk->pi_lock);
+	raw_spin_unlock_irq(&tsk->pi_lock);
 
 	if (unlikely(in_atomic())) {
 		pr_info("note: %s[%d] exited with preempt_count %d\n",
@@ -881,9 +881,7 @@ void __noreturn do_exit(long code)
 	 */
 	flush_ptrace_hw_breakpoint(tsk);
 
-	TASKS_RCU(preempt_disable());
-	TASKS_RCU(tasks_rcu_i = __srcu_read_lock(&tasks_rcu_exit_srcu));
-	TASKS_RCU(preempt_enable());
+	exit_tasks_rcu_start();
 	exit_notify(tsk, group_dead);
 	proc_exit_connector(tsk);
 	mpol_put_task_policy(tsk);
@@ -918,7 +916,7 @@ void __noreturn do_exit(long code)
 	if (tsk->nr_dirtied)
 		__this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied);
 	exit_rcu();
-	TASKS_RCU(__srcu_read_unlock(&tasks_rcu_exit_srcu, tasks_rcu_i));
+	exit_tasks_rcu_finish();
 
 	do_task_dead();
 }
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index fd24153e8a48..294294c71ba4 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -268,123 +268,6 @@ static __always_inline u32  __pv_wait_head_or_lock(struct qspinlock *lock,
 #define queued_spin_lock_slowpath	native_queued_spin_lock_slowpath
 #endif
 
-/*
- * Various notes on spin_is_locked() and spin_unlock_wait(), which are
- * 'interesting' functions:
- *
- * PROBLEM: some architectures have an interesting issue with atomic ACQUIRE
- * operations in that the ACQUIRE applies to the LOAD _not_ the STORE (ARM64,
- * PPC). Also qspinlock has a similar issue per construction, the setting of
- * the locked byte can be unordered acquiring the lock proper.
- *
- * This gets to be 'interesting' in the following cases, where the /should/s
- * end up false because of this issue.
- *
- *
- * CASE 1:
- *
- * So the spin_is_locked() correctness issue comes from something like:
- *
- *   CPU0				CPU1
- *
- *   global_lock();			local_lock(i)
- *     spin_lock(&G)			  spin_lock(&L[i])
- *     for (i)				  if (!spin_is_locked(&G)) {
- *       spin_unlock_wait(&L[i]);	    smp_acquire__after_ctrl_dep();
- *					    return;
- *					  }
- *					  // deal with fail
- *
- * Where it is important CPU1 sees G locked or CPU0 sees L[i] locked such
- * that there is exclusion between the two critical sections.
- *
- * The load from spin_is_locked(&G) /should/ be constrained by the ACQUIRE from
- * spin_lock(&L[i]), and similarly the load(s) from spin_unlock_wait(&L[i])
- * /should/ be constrained by the ACQUIRE from spin_lock(&G).
- *
- * Similarly, later stuff is constrained by the ACQUIRE from CTRL+RMB.
- *
- *
- * CASE 2:
- *
- * For spin_unlock_wait() there is a second correctness issue, namely:
- *
- *   CPU0				CPU1
- *
- *   flag = set;
- *   smp_mb();				spin_lock(&l)
- *   spin_unlock_wait(&l);		if (!flag)
- *					  // add to lockless list
- *					spin_unlock(&l);
- *   // iterate lockless list
- *
- * Which wants to ensure that CPU1 will stop adding bits to the list and CPU0
- * will observe the last entry on the list (if spin_unlock_wait() had ACQUIRE
- * semantics etc..)
- *
- * Where flag /should/ be ordered against the locked store of l.
- */
-
-/*
- * queued_spin_lock_slowpath() can (load-)ACQUIRE the lock before
- * issuing an _unordered_ store to set _Q_LOCKED_VAL.
- *
- * This means that the store can be delayed, but no later than the
- * store-release from the unlock. This means that simply observing
- * _Q_LOCKED_VAL is not sufficient to determine if the lock is acquired.
- *
- * There are two paths that can issue the unordered store:
- *
- *  (1) clear_pending_set_locked():	*,1,0 -> *,0,1
- *
- *  (2) set_locked():			t,0,0 -> t,0,1 ; t != 0
- *      atomic_cmpxchg_relaxed():	t,0,0 -> 0,0,1
- *
- * However, in both cases we have other !0 state we've set before to queue
- * ourseves:
- *
- * For (1) we have the atomic_cmpxchg_acquire() that set _Q_PENDING_VAL, our
- * load is constrained by that ACQUIRE to not pass before that, and thus must
- * observe the store.
- *
- * For (2) we have a more intersting scenario. We enqueue ourselves using
- * xchg_tail(), which ends up being a RELEASE. This in itself is not
- * sufficient, however that is followed by an smp_cond_acquire() on the same
- * word, giving a RELEASE->ACQUIRE ordering. This again constrains our load and
- * guarantees we must observe that store.
- *
- * Therefore both cases have other !0 state that is observable before the
- * unordered locked byte store comes through. This means we can use that to
- * wait for the lock store, and then wait for an unlock.
- */
-#ifndef queued_spin_unlock_wait
-void queued_spin_unlock_wait(struct qspinlock *lock)
-{
-	u32 val;
-
-	for (;;) {
-		val = atomic_read(&lock->val);
-
-		if (!val) /* not locked, we're done */
-			goto done;
-
-		if (val & _Q_LOCKED_MASK) /* locked, go wait for unlock */
-			break;
-
-		/* not locked, but pending, wait until we observe the lock */
-		cpu_relax();
-	}
-
-	/* any unlock is good */
-	while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
-		cpu_relax();
-
-done:
-	smp_acquire__after_ctrl_dep();
-}
-EXPORT_SYMBOL(queued_spin_unlock_wait);
-#endif
-
 #endif /* _GEN_PV_LOCK_SLOWPATH */
 
 /**
diff --git a/kernel/membarrier.c b/kernel/membarrier.c
deleted file mode 100644
index 9f9284f37f8d..000000000000
--- a/kernel/membarrier.c
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * Copyright (C) 2010, 2015 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
- *
- * membarrier system call
- *
- * 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.
- */
-
-#include <linux/syscalls.h>
-#include <linux/membarrier.h>
-#include <linux/tick.h>
-
-/*
- * Bitmask made from a "or" of all commands within enum membarrier_cmd,
- * except MEMBARRIER_CMD_QUERY.
- */
-#define MEMBARRIER_CMD_BITMASK	(MEMBARRIER_CMD_SHARED)
-
-/**
- * sys_membarrier - issue memory barriers on a set of threads
- * @cmd:   Takes command values defined in enum membarrier_cmd.
- * @flags: Currently needs to be 0. For future extensions.
- *
- * If this system call is not implemented, -ENOSYS is returned. If the
- * command specified does not exist, or if the command argument is invalid,
- * this system call returns -EINVAL. For a given command, with flags argument
- * set to 0, this system call is guaranteed to always return the same value
- * until reboot.
- *
- * All memory accesses performed in program order from each targeted thread
- * is guaranteed to be ordered with respect to sys_membarrier(). If we use
- * the semantic "barrier()" to represent a compiler barrier forcing memory
- * accesses to be performed in program order across the barrier, and
- * smp_mb() to represent explicit memory barriers forcing full memory
- * ordering across the barrier, we have the following ordering table for
- * each pair of barrier(), sys_membarrier() and smp_mb():
- *
- * The pair ordering is detailed as (O: ordered, X: not ordered):
- *
- *                        barrier()   smp_mb() sys_membarrier()
- *        barrier()          X           X            O
- *        smp_mb()           X           O            O
- *        sys_membarrier()   O           O            O
- */
-SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
-{
-	/* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */
-	if (tick_nohz_full_enabled())
-		return -ENOSYS;
-	if (unlikely(flags))
-		return -EINVAL;
-	switch (cmd) {
-	case MEMBARRIER_CMD_QUERY:
-		return MEMBARRIER_CMD_BITMASK;
-	case MEMBARRIER_CMD_SHARED:
-		if (num_online_cpus() > 1)
-			synchronize_sched();
-		return 0;
-	default:
-		return -EINVAL;
-	}
-}
diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index be90c945063f..9210379c0353 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -69,8 +69,7 @@ config TREE_SRCU
 	  This option selects the full-fledged version of SRCU.
 
 config TASKS_RCU
-	bool
-	default n
+	def_bool PREEMPT
 	select SRCU
 	help
 	  This option enables a task-based RCU implementation that uses
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 808b8c85f626..e4b43fef89f5 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -356,22 +356,10 @@ do {									\
 
 #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)
-{
-}
+static inline bool rcu_gp_is_normal(void) { return true; }
+static inline bool rcu_gp_is_expedited(void) { 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. */
@@ -419,12 +407,8 @@ static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
 	*gpnum = 0;
 	*completed = 0;
 }
-static inline void rcutorture_record_test_transition(void)
-{
-}
-static inline void rcutorture_record_progress(unsigned long vernum)
-{
-}
+static inline void rcutorture_record_test_transition(void) { }
+static inline void rcutorture_record_progress(unsigned long vernum) { }
 #ifdef CONFIG_RCU_TRACE
 void do_trace_rcu_torture_read(const char *rcutorturename,
 			       struct rcu_head *rhp,
@@ -460,92 +444,20 @@ void srcutorture_get_gp_data(enum rcutorture_type test_type,
 #endif
 
 #ifdef CONFIG_TINY_RCU
-
-/*
- * 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)
-{
-	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.
- */
-static inline unsigned long rcu_exp_batches_completed_sched(void)
-{
-	return 0;
-}
-
-static inline unsigned long srcu_batches_completed(struct srcu_struct *sp)
-{
-	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 unsigned long rcu_batches_started(void) { return 0; }
+static inline unsigned long rcu_batches_started_bh(void) { return 0; }
+static inline unsigned long rcu_batches_started_sched(void) { return 0; }
+static inline unsigned long rcu_batches_completed(void) { return 0; }
+static inline unsigned long rcu_batches_completed_bh(void) { return 0; }
+static inline unsigned long rcu_batches_completed_sched(void) { return 0; }
+static inline unsigned long rcu_exp_batches_completed(void) { return 0; }
+static inline unsigned long rcu_exp_batches_completed_sched(void) { return 0; }
+static inline unsigned long
+srcu_batches_completed(struct srcu_struct *sp) { 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) { }
 #else /* #ifdef CONFIG_TINY_RCU */
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 2b62a38b080f..7649fcd2c4c7 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -36,24 +36,6 @@ void rcu_cblist_init(struct rcu_cblist *rclp)
 }
 
 /*
- * Debug function to actually count the number of callbacks.
- * If the number exceeds the limit specified, return -1.
- */
-long rcu_cblist_count_cbs(struct rcu_cblist *rclp, long lim)
-{
-	int cnt = 0;
-	struct rcu_head **rhpp = &rclp->head;
-
-	for (;;) {
-		if (!*rhpp)
-			return cnt;
-		if (++cnt > lim)
-			return -1;
-		rhpp = &(*rhpp)->next;
-	}
-}
-
-/*
  * Dequeue the oldest rcu_head structure from the specified callback
  * list.  This function assumes that the callback is non-lazy, but
  * the caller can later invoke rcu_cblist_dequeued_lazy() if it
@@ -103,17 +85,6 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp)
 }
 
 /*
- * Is the specified segment of the specified rcu_segcblist structure
- * empty of callbacks?
- */
-bool rcu_segcblist_segempty(struct rcu_segcblist *rsclp, int seg)
-{
-	if (seg == RCU_DONE_TAIL)
-		return &rsclp->head == rsclp->tails[RCU_DONE_TAIL];
-	return rsclp->tails[seg - 1] == rsclp->tails[seg];
-}
-
-/*
  * Does the specified rcu_segcblist structure contain callbacks that
  * are ready to be invoked?
  */
@@ -134,50 +105,6 @@ bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp)
 }
 
 /*
- * Dequeue and return the first ready-to-invoke callback.  If there
- * are no ready-to-invoke callbacks, return NULL.  Disables interrupts
- * to avoid interference.  Does not protect from interference from other
- * CPUs or tasks.
- */
-struct rcu_head *rcu_segcblist_dequeue(struct rcu_segcblist *rsclp)
-{
-	unsigned long flags;
-	int i;
-	struct rcu_head *rhp;
-
-	local_irq_save(flags);
-	if (!rcu_segcblist_ready_cbs(rsclp)) {
-		local_irq_restore(flags);
-		return NULL;
-	}
-	rhp = rsclp->head;
-	BUG_ON(!rhp);
-	rsclp->head = rhp->next;
-	for (i = RCU_DONE_TAIL; i < RCU_CBLIST_NSEGS; i++) {
-		if (rsclp->tails[i] != &rhp->next)
-			break;
-		rsclp->tails[i] = &rsclp->head;
-	}
-	smp_mb(); /* Dequeue before decrement for rcu_barrier(). */
-	WRITE_ONCE(rsclp->len, rsclp->len - 1);
-	local_irq_restore(flags);
-	return rhp;
-}
-
-/*
- * Account for the fact that a previously dequeued callback turned out
- * to be marked as lazy.
- */
-void rcu_segcblist_dequeued_lazy(struct rcu_segcblist *rsclp)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	rsclp->len_lazy--;
-	local_irq_restore(flags);
-}
-
-/*
  * Return a pointer to the first callback in the specified rcu_segcblist
  * structure.  This is useful for diagnostics.
  */
@@ -203,17 +130,6 @@ struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp)
 }
 
 /*
- * Does the specified rcu_segcblist structure contain callbacks that
- * have not yet been processed beyond having been posted, that is,
- * does it contain callbacks in its last segment?
- */
-bool rcu_segcblist_new_cbs(struct rcu_segcblist *rsclp)
-{
-	return rcu_segcblist_is_enabled(rsclp) &&
-	       !rcu_segcblist_restempty(rsclp, RCU_NEXT_READY_TAIL);
-}
-
-/*
  * Enqueue the specified callback onto the specified rcu_segcblist
  * structure, updating accounting as needed.  Note that the ->len
  * field may be accessed locklessly, hence the WRITE_ONCE().
@@ -503,3 +419,27 @@ bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
 			return true;
 	return false;
 }
+
+/*
+ * Merge the source rcu_segcblist structure into the destination
+ * rcu_segcblist structure, then initialize the source.  Any pending
+ * callbacks from the source get to start over.  It is best to
+ * advance and accelerate both the destination and the source
+ * before merging.
+ */
+void rcu_segcblist_merge(struct rcu_segcblist *dst_rsclp,
+			 struct rcu_segcblist *src_rsclp)
+{
+	struct rcu_cblist donecbs;
+	struct rcu_cblist pendcbs;
+
+	rcu_cblist_init(&donecbs);
+	rcu_cblist_init(&pendcbs);
+	rcu_segcblist_extract_count(src_rsclp, &donecbs);
+	rcu_segcblist_extract_done_cbs(src_rsclp, &donecbs);
+	rcu_segcblist_extract_pend_cbs(src_rsclp, &pendcbs);
+	rcu_segcblist_insert_count(dst_rsclp, &donecbs);
+	rcu_segcblist_insert_done_cbs(dst_rsclp, &donecbs);
+	rcu_segcblist_insert_pend_cbs(dst_rsclp, &pendcbs);
+	rcu_segcblist_init(src_rsclp);
+}
diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
index 6e36e36478cd..581c12b63544 100644
--- a/kernel/rcu/rcu_segcblist.h
+++ b/kernel/rcu/rcu_segcblist.h
@@ -31,29 +31,7 @@ static inline void rcu_cblist_dequeued_lazy(struct rcu_cblist *rclp)
 	rclp->len_lazy--;
 }
 
-/*
- * Interim function to return rcu_cblist head pointer.  Longer term, the
- * rcu_cblist will be used more pervasively, removing the need for this
- * function.
- */
-static inline struct rcu_head *rcu_cblist_head(struct rcu_cblist *rclp)
-{
-	return rclp->head;
-}
-
-/*
- * Interim function to return rcu_cblist head pointer.  Longer term, the
- * rcu_cblist will be used more pervasively, removing the need for this
- * function.
- */
-static inline struct rcu_head **rcu_cblist_tail(struct rcu_cblist *rclp)
-{
-	WARN_ON_ONCE(!rclp->head);
-	return rclp->tail;
-}
-
 void rcu_cblist_init(struct rcu_cblist *rclp);
-long rcu_cblist_count_cbs(struct rcu_cblist *rclp, long lim);
 struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp);
 
 /*
@@ -134,14 +112,10 @@ static inline struct rcu_head **rcu_segcblist_tail(struct rcu_segcblist *rsclp)
 
 void rcu_segcblist_init(struct rcu_segcblist *rsclp);
 void rcu_segcblist_disable(struct rcu_segcblist *rsclp);
-bool rcu_segcblist_segempty(struct rcu_segcblist *rsclp, int seg);
 bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp);
 bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp);
-struct rcu_head *rcu_segcblist_dequeue(struct rcu_segcblist *rsclp);
-void rcu_segcblist_dequeued_lazy(struct rcu_segcblist *rsclp);
 struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp);
 struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp);
-bool rcu_segcblist_new_cbs(struct rcu_segcblist *rsclp);
 void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
 			   struct rcu_head *rhp, bool lazy);
 bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
@@ -162,3 +136,5 @@ void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq);
 bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq);
 bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
 				    unsigned long seq);
+void rcu_segcblist_merge(struct rcu_segcblist *dst_rsclp,
+			 struct rcu_segcblist *src_rsclp);
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 3cc18110b612..1f87a02c3399 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -317,8 +317,6 @@ static struct rcu_perf_ops sched_ops = {
 	.name		= "sched"
 };
 
-#ifdef CONFIG_TASKS_RCU
-
 /*
  * Definitions for RCU-tasks perf testing.
  */
@@ -346,24 +344,11 @@ static struct rcu_perf_ops tasks_ops = {
 	.name		= "tasks"
 };
 
-#define RCUPERF_TASKS_OPS &tasks_ops,
-
 static bool __maybe_unused torturing_tasks(void)
 {
 	return cur_ops == &tasks_ops;
 }
 
-#else /* #ifdef CONFIG_TASKS_RCU */
-
-#define RCUPERF_TASKS_OPS
-
-static bool __maybe_unused torturing_tasks(void)
-{
-	return false;
-}
-
-#endif /* #else #ifdef CONFIG_TASKS_RCU */
-
 /*
  * If performance tests complete, wait for shutdown to commence.
  */
@@ -658,7 +643,7 @@ rcu_perf_init(void)
 	int firsterr = 0;
 	static struct rcu_perf_ops *perf_ops[] = {
 		&rcu_ops, &rcu_bh_ops, &srcu_ops, &srcud_ops, &sched_ops,
-		RCUPERF_TASKS_OPS
+		&tasks_ops,
 	};
 
 	if (!torture_init_begin(perf_type, verbose, &perf_runnable))
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index b8f7f8ce8575..45f2ffbc1e78 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -199,7 +199,8 @@ MODULE_PARM_DESC(torture_runnable, "Start rcutorture at boot");
 static u64 notrace rcu_trace_clock_local(void)
 {
 	u64 ts = trace_clock_local();
-	unsigned long __maybe_unused ts_rem = do_div(ts, NSEC_PER_USEC);
+
+	(void)do_div(ts, NSEC_PER_USEC);
 	return ts;
 }
 #else /* #ifdef CONFIG_RCU_TRACE */
@@ -496,7 +497,7 @@ static struct rcu_torture_ops rcu_busted_ops = {
 	.fqs		= NULL,
 	.stats		= NULL,
 	.irq_capable	= 1,
-	.name		= "rcu_busted"
+	.name		= "busted"
 };
 
 /*
@@ -522,7 +523,7 @@ static void srcu_read_delay(struct torture_random_state *rrsp)
 
 	delay = torture_random(rrsp) %
 		(nrealreaders * 2 * longdelay * uspertick);
-	if (!delay)
+	if (!delay && in_task())
 		schedule_timeout_interruptible(longdelay);
 	else
 		rcu_read_delay(rrsp);
@@ -561,44 +562,7 @@ static void srcu_torture_barrier(void)
 
 static void srcu_torture_stats(void)
 {
-	int __maybe_unused cpu;
-	int idx;
-
-#ifdef CONFIG_TREE_SRCU
-	idx = srcu_ctlp->srcu_idx & 0x1;
-	pr_alert("%s%s Tree SRCU per-CPU(idx=%d):",
-		 torture_type, TORTURE_FLAG, idx);
-	for_each_possible_cpu(cpu) {
-		unsigned long l0, l1;
-		unsigned long u0, u1;
-		long c0, c1;
-		struct srcu_data *counts;
-
-		counts = per_cpu_ptr(srcu_ctlp->sda, cpu);
-		u0 = counts->srcu_unlock_count[!idx];
-		u1 = counts->srcu_unlock_count[idx];
-
-		/*
-		 * Make sure that a lock is always counted if the corresponding
-		 * unlock is counted.
-		 */
-		smp_rmb();
-
-		l0 = counts->srcu_lock_count[!idx];
-		l1 = counts->srcu_lock_count[idx];
-
-		c0 = l0 - u0;
-		c1 = l1 - u1;
-		pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
-	}
-	pr_cont("\n");
-#elif defined(CONFIG_TINY_SRCU)
-	idx = READ_ONCE(srcu_ctlp->srcu_idx) & 0x1;
-	pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n",
-		 torture_type, TORTURE_FLAG, idx,
-		 READ_ONCE(srcu_ctlp->srcu_lock_nesting[!idx]),
-		 READ_ONCE(srcu_ctlp->srcu_lock_nesting[idx]));
-#endif
+	srcu_torture_stats_print(srcu_ctlp, torture_type, TORTURE_FLAG);
 }
 
 static void srcu_torture_synchronize_expedited(void)
@@ -620,6 +584,7 @@ static struct rcu_torture_ops srcu_ops = {
 	.call		= srcu_torture_call,
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
+	.irq_capable	= 1,
 	.name		= "srcu"
 };
 
@@ -652,6 +617,7 @@ static struct rcu_torture_ops srcud_ops = {
 	.call		= srcu_torture_call,
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
+	.irq_capable	= 1,
 	.name		= "srcud"
 };
 
@@ -696,8 +662,6 @@ static struct rcu_torture_ops sched_ops = {
 	.name		= "sched"
 };
 
-#ifdef CONFIG_TASKS_RCU
-
 /*
  * Definitions for RCU-tasks torture testing.
  */
@@ -735,24 +699,11 @@ static struct rcu_torture_ops tasks_ops = {
 	.name		= "tasks"
 };
 
-#define RCUTORTURE_TASKS_OPS &tasks_ops,
-
 static bool __maybe_unused torturing_tasks(void)
 {
 	return cur_ops == &tasks_ops;
 }
 
-#else /* #ifdef CONFIG_TASKS_RCU */
-
-#define RCUTORTURE_TASKS_OPS
-
-static bool __maybe_unused torturing_tasks(void)
-{
-	return false;
-}
-
-#endif /* #else #ifdef CONFIG_TASKS_RCU */
-
 /*
  * RCU torture priority-boost testing.  Runs one real-time thread per
  * CPU for moderate bursts, repeatedly registering RCU callbacks and
@@ -1114,6 +1065,11 @@ rcu_torture_fakewriter(void *arg)
 	return 0;
 }
 
+static void rcu_torture_timer_cb(struct rcu_head *rhp)
+{
+	kfree(rhp);
+}
+
 /*
  * RCU torture reader from timer handler.  Dereferences rcu_torture_current,
  * incrementing the corresponding element of the pipeline array.  The
@@ -1176,6 +1132,14 @@ static void rcu_torture_timer(unsigned long unused)
 	__this_cpu_inc(rcu_torture_batch[completed]);
 	preempt_enable();
 	cur_ops->readunlock(idx);
+
+	/* Test call_rcu() invocation from interrupt handler. */
+	if (cur_ops->call) {
+		struct rcu_head *rhp = kmalloc(sizeof(*rhp), GFP_NOWAIT);
+
+		if (rhp)
+			cur_ops->call(rhp, rcu_torture_timer_cb);
+	}
 }
 
 /*
@@ -1354,11 +1318,12 @@ rcu_torture_stats_print(void)
 		srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
 					&flags, &gpnum, &completed);
 		wtp = READ_ONCE(writer_task);
-		pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx\n",
+		pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx cpu %d\n",
 			 rcu_torture_writer_state_getname(),
 			 rcu_torture_writer_state,
 			 gpnum, completed, flags,
-			 wtp == NULL ? ~0UL : wtp->state);
+			 wtp == NULL ? ~0UL : wtp->state,
+			 wtp == NULL ? -1 : (int)task_cpu(wtp));
 		show_rcu_gp_kthreads();
 		rcu_ftrace_dump(DUMP_ALL);
 	}
@@ -1749,7 +1714,7 @@ rcu_torture_init(void)
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] = {
 		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
-		&sched_ops, RCUTORTURE_TASKS_OPS
+		&sched_ops, &tasks_ops,
 	};
 
 	if (!torture_init_begin(torture_type, verbose, &torture_runnable))
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 1a1c1047d2ed..76ac5f50b2c7 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -33,6 +33,8 @@
 #include "rcu_segcblist.h"</