Merge branch 'rcu/next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/rcu

Pull RCU updates from Paul E. McKenney:

  * Update RCU documentation.

  * Miscellaneous fixes.

  * Maintainership changes.

  * Torture-test updates.

  * Callback-offloading changes.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

10 files changed, 450 insertions, 155 deletions

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index bfda2726ca45..ff1a6de62f17 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -99,6 +99,10 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 
 void kfree(const void *);
 
+/*
+ * Reclaim the specified callback, either by invoking it (non-lazy case)
+ * or freeing it directly (lazy case).  Return true if lazy, false otherwise.
+ */
 static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
 {
 	unsigned long offset = (unsigned long)head->func;
@@ -108,12 +112,12 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
 		RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset));
 		kfree((void *)head - offset);
 		rcu_lock_release(&rcu_callback_map);
-		return 1;
+		return true;
 	} else {
 		RCU_TRACE(trace_rcu_invoke_callback(rn, head));
 		head->func(head);
 		rcu_lock_release(&rcu_callback_map);
-		return 0;
+		return false;
 	}
 }
 
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index c639556f3fa0..e037f3eb2f7b 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -298,9 +298,9 @@ int __srcu_read_lock(struct srcu_struct *sp)
 
 	idx = ACCESS_ONCE(sp->completed) & 0x1;
 	preempt_disable();
-	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) += 1;
+	__this_cpu_inc(sp->per_cpu_ref->c[idx]);
 	smp_mb(); /* B */  /* Avoid leaking the critical section. */
-	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->seq[idx]) += 1;
+	__this_cpu_inc(sp->per_cpu_ref->seq[idx]);
 	preempt_enable();
 	return idx;
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f1ba77363fbb..1b70cb6fbe3c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -206,6 +206,70 @@ void rcu_bh_qs(int cpu)
 	rdp->passed_quiesce = 1;
 }
 
+static DEFINE_PER_CPU(int, rcu_sched_qs_mask);
+
+static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
+	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
+	.dynticks = ATOMIC_INIT(1),
+#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
+	.dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE,
+	.dynticks_idle = ATOMIC_INIT(1),
+#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+};
+
+/*
+ * Let the RCU core know that this CPU has gone through the scheduler,
+ * which is a quiescent state.  This is called when the need for a
+ * quiescent state is urgent, so we burn an atomic operation and full
+ * memory barriers to let the RCU core know about it, regardless of what
+ * this CPU might (or might not) do in the near future.
+ *
+ * We inform the RCU core by emulating a zero-duration dyntick-idle
+ * period, which we in turn do by incrementing the ->dynticks counter
+ * by two.
+ */
+static void rcu_momentary_dyntick_idle(void)
+{
+	unsigned long flags;
+	struct rcu_data *rdp;
+	struct rcu_dynticks *rdtp;
+	int resched_mask;
+	struct rcu_state *rsp;
+
+	local_irq_save(flags);
+
+	/*
+	 * Yes, we can lose flag-setting operations.  This is OK, because
+	 * the flag will be set again after some delay.
+	 */
+	resched_mask = raw_cpu_read(rcu_sched_qs_mask);
+	raw_cpu_write(rcu_sched_qs_mask, 0);
+
+	/* Find the flavor that needs a quiescent state. */
+	for_each_rcu_flavor(rsp) {
+		rdp = raw_cpu_ptr(rsp->rda);
+		if (!(resched_mask & rsp->flavor_mask))
+			continue;
+		smp_mb(); /* rcu_sched_qs_mask before cond_resched_completed. */
+		if (ACCESS_ONCE(rdp->mynode->completed) !=
+		    ACCESS_ONCE(rdp->cond_resched_completed))
+			continue;
+
+		/*
+		 * Pretend to be momentarily idle for the quiescent state.
+		 * This allows the grace-period kthread to record the
+		 * quiescent state, with no need for this CPU to do anything
+		 * further.
+		 */
+		rdtp = this_cpu_ptr(&rcu_dynticks);
+		smp_mb__before_atomic(); /* Earlier stuff before QS. */
+		atomic_add(2, &rdtp->dynticks);  /* QS. */
+		smp_mb__after_atomic(); /* Later stuff after QS. */
+		break;
+	}
+	local_irq_restore(flags);
+}
+
 /*
  * Note a context switch.  This is a quiescent state for RCU-sched,
  * and requires special handling for preemptible RCU.
@@ -216,19 +280,12 @@ void rcu_note_context_switch(int cpu)
 	trace_rcu_utilization(TPS("Start context switch"));
 	rcu_sched_qs(cpu);
 	rcu_preempt_note_context_switch(cpu);
+	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
+		rcu_momentary_dyntick_idle();
 	trace_rcu_utilization(TPS("End context switch"));
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 
-static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
-	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
-	.dynticks = ATOMIC_INIT(1),
-#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
-	.dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE,
-	.dynticks_idle = ATOMIC_INIT(1),
-#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
-};
-
 static long blimit = 10;	/* Maximum callbacks per rcu_do_batch. */
 static long qhimark = 10000;	/* If this many pending, ignore blimit. */
 static long qlowmark = 100;	/* Once only this many pending, use blimit. */
@@ -243,6 +300,13 @@ static ulong jiffies_till_next_fqs = ULONG_MAX;
 module_param(jiffies_till_first_fqs, ulong, 0644);
 module_param(jiffies_till_next_fqs, ulong, 0644);
 
+/*
+ * How long the grace period must be before we start recruiting
+ * quiescent-state help from rcu_note_context_switch().
+ */
+static ulong jiffies_till_sched_qs = HZ / 20;
+module_param(jiffies_till_sched_qs, ulong, 0644);
+
 static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 				  struct rcu_data *rdp);
 static void force_qs_rnp(struct rcu_state *rsp,
@@ -853,6 +917,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 				    bool *isidle, unsigned long *maxj)
 {
 	unsigned int curr;
+	int *rcrmp;
 	unsigned int snap;
 
 	curr = (unsigned int)atomic_add_return(0, &rdp->dynticks->dynticks);
@@ -893,27 +958,43 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 	}
 
 	/*
-	 * There is a possibility that a CPU in adaptive-ticks state
-	 * might run in the kernel with the scheduling-clock tick disabled
-	 * for an extended time period.  Invoke rcu_kick_nohz_cpu() to
-	 * force the CPU to restart the scheduling-clock tick in this
-	 * CPU is in this state.
-	 */
-	rcu_kick_nohz_cpu(rdp->cpu);
-
-	/*
-	 * Alternatively, the CPU might be running in the kernel
-	 * for an extended period of time without a quiescent state.
-	 * Attempt to force the CPU through the scheduler to gain the
-	 * needed quiescent state, but only if the grace period has gone
-	 * on for an uncommonly long time.  If there are many stuck CPUs,
-	 * we will beat on the first one until it gets unstuck, then move
-	 * to the next.  Only do this for the primary flavor of RCU.
+	 * A CPU running for an extended time within the kernel can
+	 * delay RCU grace periods.  When the CPU is in NO_HZ_FULL mode,
+	 * even context-switching back and forth between a pair of
+	 * in-kernel CPU-bound tasks cannot advance grace periods.
+	 * So if the grace period is old enough, make the CPU pay attention.
+	 * Note that the unsynchronized assignments to the per-CPU
+	 * rcu_sched_qs_mask variable are safe.  Yes, setting of
+	 * bits can be lost, but they will be set again on the next
+	 * force-quiescent-state pass.  So lost bit sets do not result
+	 * in incorrect behavior, merely in a grace period lasting
+	 * a few jiffies longer than it might otherwise.  Because
+	 * there are at most four threads involved, and because the
+	 * updates are only once every few jiffies, the probability of
+	 * lossage (and thus of slight grace-period extension) is
+	 * quite low.
+	 *
+	 * Note that if the jiffies_till_sched_qs boot/sysfs parameter
+	 * is set too high, we override with half of the RCU CPU stall
+	 * warning delay.
 	 */
-	if (rdp->rsp == rcu_state_p &&
+	rcrmp = &per_cpu(rcu_sched_qs_mask, rdp->cpu);
+	if (ULONG_CMP_GE(jiffies,
+			 rdp->rsp->gp_start + jiffies_till_sched_qs) ||
 	    ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
-		rdp->rsp->jiffies_resched += 5;
-		resched_cpu(rdp->cpu);
+		if (!(ACCESS_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
+			ACCESS_ONCE(rdp->cond_resched_completed) =
+				ACCESS_ONCE(rdp->mynode->completed);
+			smp_mb(); /* ->cond_resched_completed before *rcrmp. */
+			ACCESS_ONCE(*rcrmp) =
+				ACCESS_ONCE(*rcrmp) + rdp->rsp->flavor_mask;
+			resched_cpu(rdp->cpu);  /* Force CPU into scheduler. */
+			rdp->rsp->jiffies_resched += 5; /* Enable beating. */
+		} else if (ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
+			/* Time to beat on that CPU again! */
+			resched_cpu(rdp->cpu);  /* Force CPU into scheduler. */
+			rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */
+		}
 	}
 
 	return 0;
@@ -932,10 +1013,7 @@ static void record_gp_stall_check_time(struct rcu_state *rsp)
 }
 
 /*
- * Dump stacks of all tasks running on stalled CPUs.  This is a fallback
- * for architectures that do not implement trigger_all_cpu_backtrace().
- * The NMI-triggered stack traces are more accurate because they are
- * printed by the target CPU.
+ * Dump stacks of all tasks running on stalled CPUs.
  */
 static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
 {
@@ -1013,7 +1091,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	       (long)rsp->gpnum, (long)rsp->completed, totqlen);
 	if (ndetected == 0)
 		pr_err("INFO: Stall ended before state dump start\n");
-	else if (!trigger_all_cpu_backtrace())
+	else
 		rcu_dump_cpu_stacks(rsp);
 
 	/* Complain about tasks blocking the grace period. */
@@ -1044,8 +1122,7 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n",
 		jiffies - rsp->gp_start,
 		(long)rsp->gpnum, (long)rsp->completed, totqlen);
-	if (!trigger_all_cpu_backtrace())
-		dump_stack();
+	rcu_dump_cpu_stacks(rsp);
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	if (ULONG_CMP_GE(jiffies, ACCESS_ONCE(rsp->jiffies_stall)))
@@ -1224,10 +1301,16 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 	 * believe that a grace period is in progress, then we must wait
 	 * for the one following, which is in "c".  Because our request
 	 * will be noticed at the end of the current grace period, we don't
-	 * need to explicitly start one.
+	 * need to explicitly start one.  We only do the lockless check
+	 * of rnp_root's fields if the current rcu_node structure thinks
+	 * there is no grace period in flight, and because we hold rnp->lock,
+	 * the only possible change is when rnp_root's two fields are
+	 * equal, in which case rnp_root->gpnum might be concurrently
+	 * incremented.  But that is OK, as it will just result in our
+	 * doing some extra useless work.
 	 */
 	if (rnp->gpnum != rnp->completed ||
-	    ACCESS_ONCE(rnp->gpnum) != ACCESS_ONCE(rnp->completed)) {
+	    ACCESS_ONCE(rnp_root->gpnum) != ACCESS_ONCE(rnp_root->completed)) {
 		rnp->need_future_gp[c & 0x1]++;
 		trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf"));
 		goto out;
@@ -1564,11 +1647,6 @@ static int rcu_gp_init(struct rcu_state *rsp)
 					    rnp->level, rnp->grplo,
 					    rnp->grphi, rnp->qsmask);
 		raw_spin_unlock_irq(&rnp->lock);
-#ifdef CONFIG_PROVE_RCU_DELAY
-		if ((prandom_u32() % (rcu_num_nodes + 1)) == 0 &&
-		    system_state == SYSTEM_RUNNING)
-			udelay(200);
-#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
 		cond_resched();
 	}
 
@@ -2266,7 +2344,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 	}
 	smp_mb(); /* List handling before counting for rcu_barrier(). */
 	rdp->qlen_lazy -= count_lazy;
-	ACCESS_ONCE(rdp->qlen) -= count;
+	ACCESS_ONCE(rdp->qlen) = rdp->qlen - count;
 	rdp->n_cbs_invoked += count;
 
 	/* Reinstate batch limit if we have worked down the excess. */
@@ -2404,14 +2482,14 @@ static void force_quiescent_state(struct rcu_state *rsp)
 	struct rcu_node *rnp_old = NULL;
 
 	/* Funnel through hierarchy to reduce memory contention. */
-	rnp = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode;
+	rnp = __this_cpu_read(rsp->rda->mynode);
 	for (; rnp != NULL; rnp = rnp->parent) {
 		ret = (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) ||
 		      !raw_spin_trylock(&rnp->fqslock);
 		if (rnp_old != NULL)
 			raw_spin_unlock(&rnp_old->fqslock);
 		if (ret) {
-			ACCESS_ONCE(rsp->n_force_qs_lh)++;
+			rsp->n_force_qs_lh++;
 			return;
 		}
 		rnp_old = rnp;
@@ -2423,7 +2501,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
 	smp_mb__after_unlock_lock();
 	raw_spin_unlock(&rnp_old->fqslock);
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
-		ACCESS_ONCE(rsp->n_force_qs_lh)++;
+		rsp->n_force_qs_lh++;
 		raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
 		return;  /* Someone beat us to it. */
 	}
@@ -2581,7 +2659,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	unsigned long flags;
 	struct rcu_data *rdp;
 
-	WARN_ON_ONCE((unsigned long)head & 0x3); /* Misaligned rcu_head! */
+	WARN_ON_ONCE((unsigned long)head & 0x1); /* Misaligned rcu_head! */
 	if (debug_rcu_head_queue(head)) {
 		/* Probable double call_rcu(), so leak the callback. */
 		ACCESS_ONCE(head->func) = rcu_leak_callback;
@@ -2612,7 +2690,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 		local_irq_restore(flags);
 		return;
 	}
-	ACCESS_ONCE(rdp->qlen)++;
+	ACCESS_ONCE(rdp->qlen) = rdp->qlen + 1;
 	if (lazy)
 		rdp->qlen_lazy++;
 	else
@@ -3176,7 +3254,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
 	 * ACCESS_ONCE() to prevent the compiler from speculating
 	 * the increment to precede the early-exit check.
 	 */
-	ACCESS_ONCE(rsp->n_barrier_done)++;
+	ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1;
 	WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1);
 	_rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done);
 	smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */
@@ -3226,7 +3304,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
 
 	/* Increment ->n_barrier_done to prevent duplicate work. */
 	smp_mb(); /* Keep increment after above mechanism. */
-	ACCESS_ONCE(rsp->n_barrier_done)++;
+	ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1;
 	WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0);
 	_rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done);
 	smp_mb(); /* Keep increment before caller's subsequent code. */
@@ -3483,14 +3561,17 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
 static void __init rcu_init_one(struct rcu_state *rsp,
 		struct rcu_data __percpu *rda)
 {
-	static char *buf[] = { "rcu_node_0",
-			       "rcu_node_1",
-			       "rcu_node_2",
-			       "rcu_node_3" };  /* Match MAX_RCU_LVLS */
-	static char *fqs[] = { "rcu_node_fqs_0",
-			       "rcu_node_fqs_1",
-			       "rcu_node_fqs_2",
-			       "rcu_node_fqs_3" };  /* Match MAX_RCU_LVLS */
+	static const char * const buf[] = {
+		"rcu_node_0",
+		"rcu_node_1",
+		"rcu_node_2",
+		"rcu_node_3" };  /* Match MAX_RCU_LVLS */
+	static const char * const fqs[] = {
+		"rcu_node_fqs_0",
+		"rcu_node_fqs_1",
+		"rcu_node_fqs_2",
+		"rcu_node_fqs_3" };  /* Match MAX_RCU_LVLS */
+	static u8 fl_mask = 0x1;
 	int cpustride = 1;
 	int i;
 	int j;
@@ -3509,6 +3590,8 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 	for (i = 1; i < rcu_num_lvls; i++)
 		rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1];
 	rcu_init_levelspread(rsp);
+	rsp->flavor_mask = fl_mask;
+	fl_mask <<= 1;
 
 	/* Initialize the elements themselves, starting from the leaves. */
 
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index bf2c1e669691..71e64c718f75 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -172,6 +172,14 @@ struct rcu_node {
 				/*  queued on this rcu_node structure that */
 				/*  are blocking the current grace period, */
 				/*  there can be no such task. */
+	struct completion boost_completion;
+				/* Used to ensure that the rt_mutex used */
+				/*  to carry out the boosting is fully */
+				/*  released with no future boostee accesses */
+				/*  before that rt_mutex is re-initialized. */
+	struct rt_mutex boost_mtx;
+				/* Used only for the priority-boosting */
+				/*  side effect, not as a lock. */
 	unsigned long boost_time;
 				/* When to start boosting (jiffies). */
 	struct task_struct *boost_kthread_task;
@@ -307,6 +315,9 @@ struct rcu_data {
 	/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
 	unsigned long dynticks_fqs;	/* Kicked due to dynticks idle. */
 	unsigned long offline_fqs;	/* Kicked due to being offline. */
+	unsigned long cond_resched_completed;
+					/* Grace period that needs help */
+					/*  from cond_resched(). */
 
 	/* 5) __rcu_pending() statistics. */
 	unsigned long n_rcu_pending;	/* rcu_pending() calls since boot. */
@@ -331,11 +342,29 @@ struct rcu_data {
 	struct rcu_head **nocb_tail;
 	atomic_long_t nocb_q_count;	/* # CBs waiting for kthread */
 	atomic_long_t nocb_q_count_lazy; /*  (approximate). */
+	struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */
+	struct rcu_head **nocb_follower_tail;
+	atomic_long_t nocb_follower_count; /* # CBs ready to invoke. */
+	atomic_long_t nocb_follower_count_lazy; /*  (approximate). */
 	int nocb_p_count;		/* # CBs being invoked by kthread */
 	int nocb_p_count_lazy;		/*  (approximate). */
 	wait_queue_head_t nocb_wq;	/* For nocb kthreads to sleep on. */
 	struct task_struct *nocb_kthread;
 	bool nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
+
+	/* The following fields are used by the leader, hence own cacheline. */
+	struct rcu_head *nocb_gp_head ____cacheline_internodealigned_in_smp;
+					/* CBs waiting for GP. */
+	struct rcu_head **nocb_gp_tail;
+	long nocb_gp_count;
+	long nocb_gp_count_lazy;
+	bool nocb_leader_wake;		/* Is the nocb leader thread awake? */
+	struct rcu_data *nocb_next_follower;
+					/* Next follower in wakeup chain. */
+
+	/* The following fields are used by the follower, hence new cachline. */
+	struct rcu_data *nocb_leader ____cacheline_internodealigned_in_smp;
+					/* Leader CPU takes GP-end wakeups. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
 	/* 8) RCU CPU stall data. */
@@ -392,6 +421,7 @@ struct rcu_state {
 	struct rcu_node *level[RCU_NUM_LVLS];	/* Hierarchy levels. */
 	u32 levelcnt[MAX_RCU_LVLS + 1];		/* # nodes in each level. */
 	u8 levelspread[RCU_NUM_LVLS];		/* kids/node in each level. */
+	u8 flavor_mask;				/* bit in flavor mask. */
 	struct rcu_data __percpu *rda;		/* pointer of percu rcu_data. */
 	void (*call)(struct rcu_head *head,	/* call_rcu() flavor. */
 		     void (*func)(struct rcu_head *head));
@@ -563,7 +593,7 @@ static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
 static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
 static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
 static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
-static void rcu_kick_nohz_cpu(int cpu);
+static void __maybe_unused rcu_kick_nohz_cpu(int cpu);
 static bool init_nocb_callback_list(struct rcu_data *rdp);
 static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq);
 static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq);
@@ -583,8 +613,14 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
 /* Sum up queue lengths for tracing. */
 static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
 {
-	*ql = atomic_long_read(&rdp->nocb_q_count) + rdp->nocb_p_count;
-	*qll = atomic_long_read(&rdp->nocb_q_count_lazy) + rdp->nocb_p_count_lazy;
+	*ql = atomic_long_read(&rdp->nocb_q_count) +
+	      rdp->nocb_p_count +
+	      atomic_long_read(&rdp->nocb_follower_count) +
+	      rdp->nocb_p_count + rdp->nocb_gp_count;
+	*qll = atomic_long_read(&rdp->nocb_q_count_lazy) +
+	       rdp->nocb_p_count_lazy +
+	       atomic_long_read(&rdp->nocb_follower_count_lazy) +
+	       rdp->nocb_p_count_lazy + rdp->nocb_gp_count_lazy;
 }
 #else /* #ifdef CONFIG_RCU_NOCB_CPU */
 static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index cbc2c45265e2..00dc411e9676 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -33,6 +33,7 @@
 #define RCU_KTHREAD_PRIO 1
 
 #ifdef CONFIG_RCU_BOOST
+#include "../locking/rtmutex_common.h"
 #define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO
 #else
 #define RCU_BOOST_PRIO RCU_KTHREAD_PRIO
@@ -336,7 +337,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 	unsigned long flags;
 	struct list_head *np;
 #ifdef CONFIG_RCU_BOOST
-	struct rt_mutex *rbmp = NULL;
+	bool drop_boost_mutex = false;
 #endif /* #ifdef CONFIG_RCU_BOOST */
 	struct rcu_node *rnp;
 	int special;
@@ -398,11 +399,8 @@ void rcu_read_unlock_special(struct task_struct *t)
 #ifdef CONFIG_RCU_BOOST
 		if (&t->rcu_node_entry == rnp->boost_tasks)
 			rnp->boost_tasks = np;
-		/* Snapshot/clear ->rcu_boost_mutex with rcu_node lock held. */
-		if (t->rcu_boost_mutex) {
-			rbmp = t->rcu_boost_mutex;
-			t->rcu_boost_mutex = NULL;
-		}
+		/* Snapshot ->boost_mtx ownership with rcu_node lock held. */
+		drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
 #endif /* #ifdef CONFIG_RCU_BOOST */
 
 		/*
@@ -427,8 +425,10 @@ void rcu_read_unlock_special(struct task_struct *t)
 
 #ifdef CONFIG_RCU_BOOST
 		/* Unboost if we were boosted. */
-		if (rbmp)
-			rt_mutex_unlock(rbmp);
+		if (drop_boost_mutex) {
+			rt_mutex_unlock(&rnp->boost_mtx);
+			complete(&rnp->boost_completion);
+		}
 #endif /* #ifdef CONFIG_RCU_BOOST */
 
 		/*
@@ -988,6 +988,7 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 
 /* Because preemptible RCU does not exist, no quieting of tasks. */
 static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
+	__releases(rnp->lock)
 {
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
@@ -1149,7 +1150,6 @@ static void rcu_wake_cond(struct task_struct *t, int status)
 static int rcu_boost(struct rcu_node *rnp)
 {
 	unsigned long flags;
-	struct rt_mutex mtx;
 	struct task_struct *t;
 	struct list_head *tb;
 
@@ -1200,11 +1200,15 @@ static int rcu_boost(struct rcu_node *rnp)
 	 * section.
 	 */
 	t = container_of(tb, struct task_struct, rcu_node_entry);
-	rt_mutex_init_proxy_locked(&mtx, t);
-	t->rcu_boost_mutex = &mtx;
+	rt_mutex_init_proxy_locked(&rnp->boost_mtx, t);
+	init_completion(&rnp->boost_completion);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	rt_mutex_lock(&mtx);  /* Side effect: boosts task t's priority. */
-	rt_mutex_unlock(&mtx);  /* Keep lockdep happy. */
+	/* Lock only for side effect: boosts task t's priority. */
+	rt_mutex_lock(&rnp->boost_mtx);
+	rt_mutex_unlock(&rnp->boost_mtx);  /* Then keep lockdep happy. */
+
+	/* Wait for boostee to be done w/boost_mtx before reinitializing. */
+	wait_for_completion(&rnp->boost_completion);
 
 	return ACCESS_ONCE(rnp->exp_tasks) != NULL ||
 	       ACCESS_ONCE(rnp->boost_tasks) != NULL;
@@ -1256,6 +1260,7 @@ static int rcu_boost_kthread(void *arg)
  * about it going away.
  */
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
+	__releases(rnp->lock)
 {
 	struct task_struct *t;
 
@@ -1491,6 +1496,7 @@ static void rcu_prepare_kthreads(int cpu)
 #else /* #ifdef CONFIG_RCU_BOOST */
 
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
+	__releases(rnp->lock)
 {
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
@@ -2060,6 +2066,22 @@ bool rcu_is_nocb_cpu(int cpu)
 #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 
 /*
+ * Kick the leader kthread for this NOCB group.
+ */
+static void wake_nocb_leader(struct rcu_data *rdp, bool force)
+{
+	struct rcu_data *rdp_leader = rdp->nocb_leader;
+
+	if (!ACCESS_ONCE(rdp_leader->nocb_kthread))
+		return;
+	if (!ACCESS_ONCE(rdp_leader->nocb_leader_wake) || force) {
+		/* Prior xchg orders against prior callback enqueue. */
+		ACCESS_ONCE(rdp_leader->nocb_leader_wake) = true;
+		wake_up(&rdp_leader->nocb_wq);
+	}
+}
+
+/*
  * Enqueue the specified string of rcu_head structures onto the specified
  * CPU's no-CBs lists.  The CPU is specified by rdp, the head of the
  * string by rhp, and the tail of the string by rhtp.  The non-lazy/lazy
@@ -2093,7 +2115,8 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 	len = atomic_long_read(&rdp->nocb_q_count);
 	if (old_rhpp == &rdp->nocb_head) {
 		if (!irqs_disabled_flags(flags)) {
-			wake_up(&rdp->nocb_wq); /* ... if queue was empty ... */
+			/* ... if queue was empty ... */
+			wake_nocb_leader(rdp, false);
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    TPS("WakeEmpty"));
 		} else {
@@ -2103,7 +2126,8 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 		}
 		rdp->qlen_last_fqs_check = 0;
 	} else if (len > rdp->qlen_last_fqs_check + qhimark) {
-		wake_up_process(t); /* ... or if many callbacks queued. */
+		/* ... or if many callbacks queued. */
+		wake_nocb_leader(rdp, true);
 		rdp->qlen_last_fqs_check = LONG_MAX / 2;
 		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeOvf"));
 	} else {
@@ -2213,13 +2237,150 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 }
 
 /*
+ * Leaders come here to wait for additional callbacks to show up.
+ * This function does not return until callbacks appear.
+ */
+static void nocb_leader_wait(struct rcu_data *my_rdp)
+{
+	bool firsttime = true;
+	bool gotcbs;
+	struct rcu_data *rdp;
+	struct rcu_head **tail;
+
+wait_again:
+
+	/* Wait for callbacks to appear. */
+	if (!rcu_nocb_poll) {
+		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep");
+		wait_event_interruptible(my_rdp->nocb_wq,
+					 ACCESS_ONCE(my_rdp->nocb_leader_wake));
+		/* Memory barrier handled by smp_mb() calls below and repoll. */
+	} else if (firsttime) {
+		firsttime = false; /* Don't drown trace log with "Poll"! */
+		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Poll");
+	}
+
+	/*
+	 * Each pass through the following loop checks a follower for CBs.
+	 * We are our own first follower.  Any CBs found are moved to
+	 * nocb_gp_head, where they await a grace period.
+	 */
+	gotcbs = false;
+	for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
+		rdp->nocb_gp_head = ACCESS_ONCE(rdp->nocb_head);
+		if (!rdp->nocb_gp_head)
+			continue;  /* No CBs here, try next follower. */
+
+		/* Move callbacks to wait-for-GP list, which is empty. */
+		ACCESS_ONCE(rdp->nocb_head) = NULL;
+		rdp->nocb_gp_tail = xchg(&rdp->nocb_tail, &rdp->nocb_head);
+		rdp->nocb_gp_count = atomic_long_xchg(&rdp->nocb_q_count, 0);
+		rdp->nocb_gp_count_lazy =
+			atomic_long_xchg(&rdp->nocb_q_count_lazy, 0);
+		gotcbs = true;
+	}
+
+	/*
+	 * If there were no callbacks, sleep a bit, rescan after a
+	 * memory barrier, and go retry.
+	 */
+	if (unlikely(!gotcbs)) {
+		if (!rcu_nocb_poll)
+			trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu,
+					    "WokeEmpty");
+		flush_signals(current);
+		schedule_timeout_interruptible(1);
+
+		/* Rescan in case we were a victim of memory ordering. */
+		my_rdp->nocb_leader_wake = false;
+		smp_mb();  /* Ensure _wake false before scan. */
+		for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower)
+			if (ACCESS_ONCE(rdp->nocb_head)) {
+				/* Found CB, so short-circuit next wait. */
+				my_rdp->nocb_leader_wake = true;
+				break;
+			}
+		goto wait_again;
+	}
+
+	/* Wait for one grace period. */
+	rcu_nocb_wait_gp(my_rdp);
+
+	/*
+	 * We left ->nocb_leader_wake set to reduce cache thrashing.
+	 * We clear it now, but recheck for new callbacks while
+	 * traversing our follower list.
+	 */
+	my_rdp->nocb_leader_wake = false;
+	smp_mb(); /* Ensure _wake false before scan of ->nocb_head. */
+
+	/* Each pass through the following loop wakes a follower, if needed. */
+	for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
+		if (ACCESS_ONCE(rdp->nocb_head))
+			my_rdp->nocb_leader_wake = true; /* No need to wait. */
+		if (!rdp->nocb_gp_head)
+			continue; /* No CBs, so no need to wake follower. */
+
+		/* Append callbacks to follower's "done" list. */
+		tail = xchg(&rdp->nocb_follower_tail, rdp->nocb_gp_tail);
+		*tail = rdp->nocb_gp_head;
+		atomic_long_add(rdp->nocb_gp_count, &rdp->nocb_follower_count);
+		atomic_long_add(rdp->nocb_gp_count_lazy,
+				&rdp->nocb_follower_count_lazy);
+		if (rdp != my_rdp && tail == &rdp->nocb_follower_head) {
+			/*
+			 * List was empty, wake up the follower.
+			 * Memory barriers supplied by atomic_long_add().
+			 */
+			wake_up(&rdp->nocb_wq);
+		}
+	}
+
+	/* If we (the leader) don't have CBs, go wait some more. */
+	if (!my_rdp->nocb_follower_head)
+		goto wait_again;
+}
+
+/*
+ * Followers come here to wait for additional callbacks to show up.
+ * This function does not return until callbacks appear.
+ */
+static void nocb_follower_wait(struct rcu_data *rdp)
+{
+	bool firsttime = true;
+
+	for (;;) {
+		if (!rcu_nocb_poll) {
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    "FollowerSleep");
+			wait_event_interruptible(rdp->nocb_wq,
+						 ACCESS_ONCE(rdp->nocb_follower_head));
+		} else if (firsttime) {
+			/* Don't drown trace log with "Poll"! */
+			firsttime = false;
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "Poll");
+		}
+		if (smp_load_acquire(&rdp->nocb_follower_head)) {
+			/* ^^^ Ensure CB invocation follows _head test. */
+			return;
+		}
+		if (!rcu_nocb_poll)
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    "WokeEmpty");
+		flush_signals(current);
+		schedule_timeout_interruptible(1);
+	}
+}
+
+/*
  * Per-rcu_data kthread, but only for no-CBs CPUs.  Each kthread invokes
- * callbacks queued by the corresponding no-CBs CPU.
+ * callbacks queued by the corresponding no-CBs CPU, however, there is
+ * an optional leader-follower relationship so that the grace-period
+ * kthreads don't have to do quite so many wakeups.
  */
 static int rcu_nocb_kthread(void *arg)
 {
 	int c, cl;
-	bool firsttime = 1;
 	struct rcu_head *list;
 	struct rcu_head *next;
 	struct rcu_head **tail;
@@ -2227,41 +2388,22 @@ static int rcu_nocb_kthread(void *arg)
 
 	/* Each pass through this loop invokes one batch of callbacks */
 	for (;;) {
-		/* If not polling, wait for next batch of callbacks. */
-		if (!rcu_nocb_poll) {
-			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
-					    TPS("Sleep"));
-			wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head);
-			/* Memory barrier provide by xchg() below. */
-		} else if (firsttime) {
-			firsttime = 0;
-			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
-					    TPS("Poll"));
-		}
-		list = ACCESS_ONCE(rdp->nocb_head);
-		if (!list) {
-			if (!rcu_nocb_poll)
-				trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
-						    TPS("WokeEmpty"));
-			schedule_timeout_interruptible(1);
-			flush_signals(current);
-			continue;
-		}
-		firsttime = 1;
-		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
-				    TPS("WokeNonEmpty"));
-
-		/*
-		 * Extract queued callbacks, update counts, and wait
-		 * for a grace period to elapse.
-		 */
-		ACCESS_ONCE(rdp->nocb_head) = NULL;
-		tail = xchg(&rdp->nocb_tail, &rdp->nocb_head);
-		c = atomic_long_xchg(&rdp->nocb_q_count, 0);
-		cl = atomic_long_xchg(&rdp->nocb_q_count_lazy, 0);
-		ACCESS_ONCE(rdp->nocb_p_count) += c;
-		ACCESS_ONCE(rdp->nocb_p_count_lazy) += cl;
-		rcu_nocb_wait_gp(rdp);
+		/* Wait for callbacks. */
+		if (rdp->nocb_leader == rdp)
+			nocb_leader_wait(rdp);
+		else
+			nocb_follower_wait(rdp);
+
+		/* Pull the ready-to-invoke callbacks onto local list. */
+		list = ACCESS_ONCE(rdp->nocb_follower_head);
+		BUG_ON(!list);
+		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "WokeNonEmpty");
+		ACCESS_ONCE(rdp->nocb_follower_head) = NULL;
+		tail = xchg(&rdp->nocb_follower_tail, &rdp->nocb_follower_head);
+		c = atomic_long_xchg(&rdp->nocb_follower_count, 0);
+		cl = atomic_long_xchg(&rdp->nocb_follower_count_lazy, 0);
+		rdp->nocb_p_count += c;
+		rdp->nocb_p_count_lazy += cl;
 
 		/* Each pass through the following loop invokes a callback. */
 		trace_rcu_batch_start(rdp->rsp->name, cl, c, -1);
@@ -2305,7 +2447,7 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
 	if (!rcu_nocb_need_deferred_wakeup(rdp))
 		return;
 	ACCESS_ONCE(rdp->nocb_defer_wakeup) = false;
-	wake_up(&rdp->nocb_wq);
+	wake_nocb_leader(rdp, false);
 	trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty"));
 }
 
@@ -2314,19 +2456,57 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
 	rdp->nocb_tail = &rdp->nocb_head;
 	init_waitqueue_head(&rdp->nocb_wq);
+	rdp->nocb_follower_tail = &rdp->nocb_follower_head;
 }
 
-/* Create a kthread for each RCU flavor for each no-CBs CPU. */
+/* How many follower CPU IDs per leader?  Default of -1 for sqrt(nr_cpu_ids). */
+static int rcu_nocb_leader_stride = -1;
+module_param(rcu_nocb_leader_stride, int, 0444);
+
+/*
+ * Create a kthread for each RCU flavor for each no-CBs CPU.
+ * Also initialize leader-follower relationships.
+ */
 static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
 {
 	int cpu;
+	int ls = rcu_nocb_leader_stride;
+	int nl = 0;  /* Next leader. */
 	struct rcu_data *rdp;
+	struct rcu_data *rdp_leader = NULL;  /* Suppress misguided gcc warn. */
+	struct rcu_data *rdp_prev = NULL;
 	struct task_struct *t;
 
 	if (rcu_nocb_mask == NULL)
 		return;
+#if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL)
+	if (tick_nohz_full_running)
+		cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
+#endif /* #if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) */
+	if (ls == -1) {
+		ls = int_sqrt(nr_cpu_ids);
+		rcu_nocb_leader_stride = ls;
+	}
+
+	/*
+	 * Each pass through this loop sets up one rcu_data structure and
+	 * spawns one rcu_nocb_kthread().
+	 */
 	for_each_cpu(cpu, rcu_nocb_mask) {
 		rdp = per_cpu_ptr(rsp->rda, cpu);
+		if (rdp->cpu >= nl) {
+			/* New leader, set up for followers & next leader. */
+			nl = DIV_ROUND_UP(rdp->cpu + 1, ls) * ls;
+			rdp->nocb_leader = rdp;
+			rdp_leader = rdp;
+		} else {
+			/* Another follower, link to previous leader. */
+			rdp->nocb_leader = rdp_leader;
+			rdp_prev->nocb_next_follower = rdp;
+		}
+		rdp_prev = rdp;
+
+		/* Spawn the kthread for this CPU. */
 		t = kthread_run(rcu_nocb_kthread, rdp,
 				"rcuo%c/%d", rsp->abbr, cpu);
 		BUG_ON(IS_ERR(t));
@@ -2404,7 +2584,7 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
  * if an adaptive-ticks CPU is failing to respond to the current grace
  * period and has not be idle from an RCU perspective, kick it.
  */
-static void rcu_kick_nohz_cpu(int cpu)
+static void __maybe_unused rcu_kick_nohz_cpu(int cpu)
 {
 #ifdef CONFIG_NO_HZ_FULL
 	if (tick_nohz_full_cpu(cpu))
@@ -2843,12 +3023,16 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
  */
 static void rcu_bind_gp_kthread(void)
 {
-#ifdef CONFIG_NO_HZ_FULL
-	int cpu = ACCESS_ONCE(tick_do_timer_cpu);
+	int __maybe_unused cpu;
 
-	if (cpu < 0 || cpu >= nr_cpu_ids)
+	if (!tick_nohz_full_enabled())
 		return;
-	if (raw_smp_processor_id() != cpu)
+#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
+	cpu = tick_do_timer_cpu;
+	if (cpu >= 0 && cpu < nr_cpu_ids && raw_smp_processor_id() != cpu)
 		set_cpus_allowed_ptr(current, cpumask_of(cpu));
-#endif /* #ifdef CONFIG_NO_HZ_FULL */
+#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+	if (!is_housekeeping_cpu(raw_smp_processor_id()))
+		housekeeping_affine(current);
+#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 }
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index a2aeb4df0f60..4056d7992a6c 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -90,9 +90,6 @@ void __rcu_read_unlock(void)
 	} else {
 		barrier();  /* critical section before exit code. */
 		t->rcu_read_lock_nesting = INT_MIN;
-#ifdef CONFIG_PROVE_RCU_DELAY
-		udelay(10); /* Make preemption more probable. */
-#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
 		barrier();  /* assign before ->rcu_read_unlock_special load */
 		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
 			rcu_read_unlock_special(t);
@@ -200,12 +197,12 @@ void wait_rcu_gp(call_rcu_func_t crf)
 EXPORT_SYMBOL_GPL(wait_rcu_gp);
 
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
-static inline void debug_init_rcu_head(struct rcu_head *head)
+void init_rcu_head(struct rcu_head *head)
 {
 	debug_object_init(head, &rcuhead_debug_descr);
 }
 
-static inline void debug_rcu_head_free(struct rcu_head *head)
+void destroy_rcu_head(struct rcu_head *head)
 {
 	debug_object_free(head, &rcuhead_debug_descr);
 }
@@ -350,21 +347,3 @@ static int __init check_cpu_stall_init(void)
 early_initcall(check_cpu_stall_init);
 
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
-
-/*
- * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings.
- */
-
-DEFINE_PER_CPU(int, rcu_cond_resched_count);
-
-/*
- * Report a set of RCU quiescent states, for use by cond_resched()
- * and friends.  Out of line due to being called infrequently.
- */
-void rcu_resched(void)
-{
-	preempt_disable();
-	__this_cpu_write(rcu_cond_resched_count, 0);
-	rcu_note_context_switch(smp_processor_id());
-	preempt_enable();
-}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3bdf01b494fe..bc1638b33449 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4147,7 +4147,6 @@ static void __cond_resched(void)
 
 int __sched _cond_resched(void)
 {
-	rcu_cond_resched();
 	if (should_resched()) {
 		__cond_resched();
 		return 1;
@@ -4166,18 +4165,15 @@ EXPORT_SYMBOL(_cond_resched);
  */
 int __cond_resched_lock(spinlock_t *lock)
 {
-	bool need_rcu_resched = rcu_should_resched();
 	int resched = should_resched();
 	int ret = 0;
 
 	lockdep_assert_held(lock);
 
-	if (spin_needbreak(lock) || resched || need_rcu_resched) {
+	if (spin_needbreak(lock) || resched) {
 		spin_unlock(lock);
 		if (resched)
 			__cond_resched();
-		else if (unlikely(need_rcu_resched))
-			rcu_resched();
 		else
 			cpu_relax();
 		ret = 1;
@@ -4191,7 +4187,6 @@ int __sched __cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
 
-	rcu_cond_resched();  /* BH disabled OK, just recording QSes. */
 	if (should_resched()) {
 		local_bh_enable();
 		__cond_resched();
diff --git a/kernel/signal.c b/kernel/signal.c
index a4077e90f19f..40b76e351e64 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1263,6 +1263,10 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
 	struct sighand_struct *sighand;
 
 	for (;;) {
+		/*
+		 * Disable interrupts early to avoid deadlocks.
+		 * See rcu_read_unlock() comment header for details.
+		 */
 		local_irq_save(*flags);
 		rcu_read_lock();
 		sighand = rcu_dereference(tsk->sighand);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 6558b7ac112d..f784d83e29f1 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -154,6 +154,7 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 
 #ifdef CONFIG_NO_HZ_FULL
 cpumask_var_t tick_nohz_full_mask;
+cpumask_var_t housekeeping_mask;
 bool tick_nohz_full_running;
 
 static bool can_stop_full_tick(void)
@@ -281,6 +282,7 @@ static int __init tick_nohz_full_setup(char *str)
 	int cpu;
 
 	alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
+	alloc_bootmem_cpumask_var(&housekeeping_mask);
 	if (cpulist_parse(str, tick_nohz_full_mask) < 0) {
 		pr_warning("NOHZ: Incorrect nohz_full cpumask\n");
 		return 1;
@@ -291,6 +293,8 @@ static int __init tick_nohz_full_setup(char *str)
 		pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu);
 		cpumask_clear_cpu(cpu, tick_nohz_full_mask);
 	}
+	cpumask_andnot(housekeeping_mask,
+		       cpu_possible_mask, tick_nohz_full_mask);
 	tick_nohz_full_running = true;
 
 	return 1;
@@ -332,9 +336,15 @@ static int tick_nohz_init_all(void)
 		pr_err("NO_HZ: Can't allocate full dynticks cpumask\n");
 		return err;
 	}
+	if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) {
+		pr_err("NO_HZ: Can't allocate not-full dynticks cpumask\n");
+		return err;
+	}
 	err = 0;
 	cpumask_setall(tick_nohz_full_mask);
 	cpumask_clear_cpu(smp_processor_id(), tick_nohz_full_mask);
+	cpumask_clear(housekeeping_mask);
+	cpumask_set_cpu(smp_processor_id(), housekeeping_mask);
 	tick_nohz_full_running = true;
 #endif
 	return err;
diff --git a/kernel/torture.c b/kernel/torture.c
index 40bb511cca48..d600af21f022 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -708,7 +708,7 @@ int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m,
 	int ret = 0;
 
 	VERBOSE_TOROUT_STRING(m);
-	*tp = kthread_run(fn, arg, s);
+	*tp = kthread_run(fn, arg, "%s", s);
 	if (IS_ERR(*tp)) {
 		ret = PTR_ERR(*tp);
 		VERBOSE_TOROUT_ERRSTRING(f);