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

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

   - Dynamic tick (nohz) updates, perhaps most notably changes to force
     the tick on when needed due to lengthy in-kernel execution on CPUs
     on which RCU is waiting.

   - Linux-kernel memory consistency model updates.

   - Replace rcu_swap_protected() with rcu_prepace_pointer().

   - Torture-test updates.

   - Documentation updates.

   - Miscellaneous fixes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (51 commits)
  security/safesetid: Replace rcu_swap_protected() with rcu_replace_pointer()
  net/sched: Replace rcu_swap_protected() with rcu_replace_pointer()
  net/netfilter: Replace rcu_swap_protected() with rcu_replace_pointer()
  net/core: Replace rcu_swap_protected() with rcu_replace_pointer()
  bpf/cgroup: Replace rcu_swap_protected() with rcu_replace_pointer()
  fs/afs: Replace rcu_swap_protected() with rcu_replace_pointer()
  drivers/scsi: Replace rcu_swap_protected() with rcu_replace_pointer()
  drm/i915: Replace rcu_swap_protected() with rcu_replace_pointer()
  x86/kvm/pmu: Replace rcu_swap_protected() with rcu_replace_pointer()
  rcu: Upgrade rcu_swap_protected() to rcu_replace_pointer()
  rcu: Suppress levelspread uninitialized messages
  rcu: Fix uninitialized variable in nocb_gp_wait()
  rcu: Update descriptions for rcu_future_grace_period tracepoint
  rcu: Update descriptions for rcu_nocb_wake tracepoint
  rcu: Remove obsolete descriptions for rcu_barrier tracepoint
  rcu: Ensure that ->rcu_urgent_qs is set before resched IPI
  workqueue: Convert for_each_wq to use built-in list check
  rcu: Several rcu_segcblist functions can be static
  rcu: Remove unused function hlist_bl_del_init_rcu()
  Documentation: Rename rcu_node_context_switch() to rcu_note_context_switch()
  ...

12 files changed, 113 insertions, 67 deletions

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index a3eaf08e7dd3..9f90d3c92bda 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -180,8 +180,8 @@ static void activate_effective_progs(struct cgroup *cgrp,
 				     enum bpf_attach_type type,
 				     struct bpf_prog_array *old_array)
 {
-	rcu_swap_protected(cgrp->bpf.effective[type], old_array,
-			   lockdep_is_held(&cgroup_mutex));
+	old_array = rcu_replace_pointer(cgrp->bpf.effective[type], old_array,
+					lockdep_is_held(&cgroup_mutex));
 	/* free prog array after grace period, since __cgroup_bpf_run_*()
 	 * might be still walking the array
 	 */
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index c513031cd7e3..99475a66c94f 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -16,7 +16,6 @@
 #include <linux/kthread.h>
 #include <linux/sched/rt.h>
 #include <linux/spinlock.h>
-#include <linux/rwlock.h>
 #include <linux/mutex.h>
 #include <linux/rwsem.h>
 #include <linux/smp.h>
@@ -889,16 +888,16 @@ static int __init lock_torture_init(void)
 		cxt.nrealwriters_stress = 2 * num_online_cpus();
 
 #ifdef CONFIG_DEBUG_MUTEXES
-	if (strncmp(torture_type, "mutex", 5) == 0)
+	if (str_has_prefix(torture_type, "mutex"))
 		cxt.debug_lock = true;
 #endif
 #ifdef CONFIG_DEBUG_RT_MUTEXES
-	if (strncmp(torture_type, "rtmutex", 7) == 0)
+	if (str_has_prefix(torture_type, "rtmutex"))
 		cxt.debug_lock = true;
 #endif
 #ifdef CONFIG_DEBUG_SPINLOCK
-	if ((strncmp(torture_type, "spin", 4) == 0) ||
-	    (strncmp(torture_type, "rw_lock", 7) == 0))
+	if ((str_has_prefix(torture_type, "spin")) ||
+	    (str_has_prefix(torture_type, "rw_lock")))
 		cxt.debug_lock = true;
 #endif
 
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 8fd4f82c9b3d..ab504fbc76ca 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -299,6 +299,8 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
 {
 	int i;
 
+	for (i = 0; i < RCU_NUM_LVLS; i++)
+		levelspread[i] = INT_MIN;
 	if (rcu_fanout_exact) {
 		levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
 		for (i = rcu_num_lvls - 2; i >= 0; i--)
@@ -455,7 +457,6 @@ enum rcutorture_type {
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
 void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 			    unsigned long *gp_seq);
-void rcutorture_record_progress(unsigned long vernum);
 void do_trace_rcu_torture_read(const char *rcutorturename,
 			       struct rcu_head *rhp,
 			       unsigned long secs,
@@ -468,7 +469,6 @@ static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
 	*flags = 0;
 	*gp_seq = 0;
 }
-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,
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 495c58ce1640..cbc87b804db9 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -88,7 +88,7 @@ struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp)
 }
 
 /* Set the length of an rcu_segcblist structure. */
-void rcu_segcblist_set_len(struct rcu_segcblist *rsclp, long v)
+static void rcu_segcblist_set_len(struct rcu_segcblist *rsclp, long v)
 {
 #ifdef CONFIG_RCU_NOCB_CPU
 	atomic_long_set(&rsclp->len, v);
@@ -104,7 +104,7 @@ void rcu_segcblist_set_len(struct rcu_segcblist *rsclp, long v)
  * This increase is fully ordered with respect to the callers accesses
  * both before and after.
  */
-void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v)
+static void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v)
 {
 #ifdef CONFIG_RCU_NOCB_CPU
 	smp_mb__before_atomic(); /* Up to the caller! */
@@ -134,7 +134,7 @@ void rcu_segcblist_inc_len(struct rcu_segcblist *rsclp)
  * with the actual number of callbacks on the structure.  This exchange is
  * fully ordered with respect to the callers accesses both before and after.
  */
-long rcu_segcblist_xchg_len(struct rcu_segcblist *rsclp, long v)
+static long rcu_segcblist_xchg_len(struct rcu_segcblist *rsclp, long v)
 {
 #ifdef CONFIG_RCU_NOCB_CPU
 	return atomic_long_xchg(&rsclp->len, v);
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 5a879d073c1c..5f884d560384 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -109,15 +109,6 @@ static unsigned long b_rcu_perf_writer_started;
 static unsigned long b_rcu_perf_writer_finished;
 static DEFINE_PER_CPU(atomic_t, n_async_inflight);
 
-static int rcu_perf_writer_state;
-#define RTWS_INIT		0
-#define RTWS_ASYNC		1
-#define RTWS_BARRIER		2
-#define RTWS_EXP_SYNC		3
-#define RTWS_SYNC		4
-#define RTWS_IDLE		5
-#define RTWS_STOPPING		6
-
 #define MAX_MEAS 10000
 #define MIN_MEAS 100
 
@@ -404,25 +395,20 @@ retry:
 			if (!rhp)
 				rhp = kmalloc(sizeof(*rhp), GFP_KERNEL);
 			if (rhp && atomic_read(this_cpu_ptr(&n_async_inflight)) < gp_async_max) {
-				rcu_perf_writer_state = RTWS_ASYNC;
 				atomic_inc(this_cpu_ptr(&n_async_inflight));
 				cur_ops->async(rhp, rcu_perf_async_cb);
 				rhp = NULL;
 			} else if (!kthread_should_stop()) {
-				rcu_perf_writer_state = RTWS_BARRIER;
 				cur_ops->gp_barrier();
 				goto retry;
 			} else {
 				kfree(rhp); /* Because we are stopping. */
 			}
 		} else if (gp_exp) {
-			rcu_perf_writer_state = RTWS_EXP_SYNC;
 			cur_ops->exp_sync();
 		} else {
-			rcu_perf_writer_state = RTWS_SYNC;
 			cur_ops->sync();
 		}
-		rcu_perf_writer_state = RTWS_IDLE;
 		t = ktime_get_mono_fast_ns();
 		*wdp = t - *wdp;
 		i_max = i;
@@ -463,10 +449,8 @@ retry:
 		rcu_perf_wait_shutdown();
 	} while (!torture_must_stop());
 	if (gp_async) {
-		rcu_perf_writer_state = RTWS_BARRIER;
 		cur_ops->gp_barrier();
 	}
-	rcu_perf_writer_state = RTWS_STOPPING;
 	writer_n_durations[me] = i_max;
 	torture_kthread_stopping("rcu_perf_writer");
 	return 0;
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 3c9feca1eab1..dee043feb71f 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -44,6 +44,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/sysctl.h>
 #include <linux/oom.h>
+#include <linux/tick.h>
 
 #include "rcu.h"
 
@@ -1363,15 +1364,15 @@ rcu_torture_reader(void *arg)
 	set_user_nice(current, MAX_NICE);
 	if (irqreader && cur_ops->irq_capable)
 		timer_setup_on_stack(&t, rcu_torture_timer, 0);
-
+	tick_dep_set_task(current, TICK_DEP_BIT_RCU);
 	do {
 		if (irqreader && cur_ops->irq_capable) {
 			if (!timer_pending(&t))
 				mod_timer(&t, jiffies + 1);
 		}
-		if (!rcu_torture_one_read(&rand))
+		if (!rcu_torture_one_read(&rand) && !torture_must_stop())
 			schedule_timeout_interruptible(HZ);
-		if (time_after(jiffies, lastsleep)) {
+		if (time_after(jiffies, lastsleep) && !torture_must_stop()) {
 			schedule_timeout_interruptible(1);
 			lastsleep = jiffies + 10;
 		}
@@ -1383,6 +1384,7 @@ rcu_torture_reader(void *arg)
 		del_timer_sync(&t);
 		destroy_timer_on_stack(&t);
 	}
+	tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
 	torture_kthread_stopping("rcu_torture_reader");
 	return 0;
 }
@@ -1442,15 +1444,18 @@ rcu_torture_stats_print(void)
 		n_rcu_torture_barrier_error);
 
 	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
-	if (atomic_read(&n_rcu_torture_mberror) != 0 ||
-	    n_rcu_torture_barrier_error != 0 ||
-	    n_rcu_torture_boost_ktrerror != 0 ||
-	    n_rcu_torture_boost_rterror != 0 ||
-	    n_rcu_torture_boost_failure != 0 ||
+	if (atomic_read(&n_rcu_torture_mberror) ||
+	    n_rcu_torture_barrier_error || n_rcu_torture_boost_ktrerror ||
+	    n_rcu_torture_boost_rterror || n_rcu_torture_boost_failure ||
 	    i > 1) {
 		pr_cont("%s", "!!! ");
 		atomic_inc(&n_rcu_torture_error);
-		WARN_ON_ONCE(1);
+		WARN_ON_ONCE(atomic_read(&n_rcu_torture_mberror));
+		WARN_ON_ONCE(n_rcu_torture_barrier_error);  // rcu_barrier()
+		WARN_ON_ONCE(n_rcu_torture_boost_ktrerror); // no boost kthread
+		WARN_ON_ONCE(n_rcu_torture_boost_rterror); // can't set RT prio
+		WARN_ON_ONCE(n_rcu_torture_boost_failure); // RCU boost failed
+		WARN_ON_ONCE(i > 1); // Too-short grace period
 	}
 	pr_cont("Reader Pipe: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
@@ -1729,10 +1734,10 @@ static void rcu_torture_fwd_prog_cond_resched(unsigned long iter)
 		// Real call_rcu() floods hit userspace, so emulate that.
 		if (need_resched() || (iter & 0xfff))
 			schedule();
-	} else {
-		// No userspace emulation: CB invocation throttles call_rcu()
-		cond_resched();
+		return;
 	}
+	// No userspace emulation: CB invocation throttles call_rcu()
+	cond_resched();
 }
 
 /*
@@ -1759,6 +1764,11 @@ static unsigned long rcu_torture_fwd_prog_cbfree(void)
 		kfree(rfcp);
 		freed++;
 		rcu_torture_fwd_prog_cond_resched(freed);
+		if (tick_nohz_full_enabled()) {
+			local_irq_save(flags);
+			rcu_momentary_dyntick_idle();
+			local_irq_restore(flags);
+		}
 	}
 	return freed;
 }
@@ -1803,7 +1813,7 @@ static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries)
 		udelay(10);
 		cur_ops->readunlock(idx);
 		if (!fwd_progress_need_resched || need_resched())
-			rcu_torture_fwd_prog_cond_resched(1);
+			cond_resched();
 	}
 	(*tested_tries)++;
 	if (!time_before(jiffies, stopat) &&
@@ -1833,6 +1843,7 @@ static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries)
 static void rcu_torture_fwd_prog_cr(void)
 {
 	unsigned long cver;
+	unsigned long flags;
 	unsigned long gps;
 	int i;
 	long n_launders;
@@ -1865,6 +1876,7 @@ static void rcu_torture_fwd_prog_cr(void)
 	cver = READ_ONCE(rcu_torture_current_version);
 	gps = cur_ops->get_gp_seq();
 	rcu_launder_gp_seq_start = gps;
+	tick_dep_set_task(current, TICK_DEP_BIT_RCU);
 	while (time_before(jiffies, stopat) &&
 	       !shutdown_time_arrived() &&
 	       !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
@@ -1891,6 +1903,11 @@ static void rcu_torture_fwd_prog_cr(void)
 		}
 		cur_ops->call(&rfcp->rh, rcu_torture_fwd_cb_cr);
 		rcu_torture_fwd_prog_cond_resched(n_launders + n_max_cbs);
+		if (tick_nohz_full_enabled()) {
+			local_irq_save(flags);
+			rcu_momentary_dyntick_idle();
+			local_irq_restore(flags);
+		}
 	}
 	stoppedat = jiffies;
 	n_launders_cb_snap = READ_ONCE(n_launders_cb);
@@ -1911,6 +1928,7 @@ static void rcu_torture_fwd_prog_cr(void)
 		rcu_torture_fwd_cb_hist();
 	}
 	schedule_timeout_uninterruptible(HZ); /* Let CBs drain. */
+	tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
 	WRITE_ONCE(rcu_fwd_cb_nodelay, false);
 }
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 81105141b6a8..1694a6b57ad8 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -364,7 +364,7 @@ bool rcu_eqs_special_set(int cpu)
  *
  * The caller must have disabled interrupts and must not be idle.
  */
-static void __maybe_unused rcu_momentary_dyntick_idle(void)
+void rcu_momentary_dyntick_idle(void)
 {
 	int special;
 
@@ -375,6 +375,7 @@ static void __maybe_unused rcu_momentary_dyntick_idle(void)
 	WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
 	rcu_preempt_deferred_qs(current);
 }
+EXPORT_SYMBOL_GPL(rcu_momentary_dyntick_idle);
 
 /**
  * rcu_is_cpu_rrupt_from_idle - see if interrupted from idle
@@ -496,7 +497,7 @@ module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next
 module_param(rcu_kick_kthreads, bool, 0644);
 
 static void force_qs_rnp(int (*f)(struct rcu_data *rdp));
-static int rcu_pending(void);
+static int rcu_pending(int user);
 
 /*
  * Return the number of RCU GPs completed thus far for debug & stats.
@@ -824,6 +825,11 @@ static __always_inline void rcu_nmi_enter_common(bool irq)
 			rcu_cleanup_after_idle();
 
 		incby = 1;
+	} else if (tick_nohz_full_cpu(rdp->cpu) &&
+		   rdp->dynticks_nmi_nesting == DYNTICK_IRQ_NONIDLE &&
+		   READ_ONCE(rdp->rcu_urgent_qs) && !rdp->rcu_forced_tick) {
+		rdp->rcu_forced_tick = true;
+		tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
 	}
 	trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
 			  rdp->dynticks_nmi_nesting,
@@ -885,6 +891,21 @@ void rcu_irq_enter_irqson(void)
 	local_irq_restore(flags);
 }
 
+/*
+ * If any sort of urgency was applied to the current CPU (for example,
+ * the scheduler-clock interrupt was enabled on a nohz_full CPU) in order
+ * to get to a quiescent state, disable it.
+ */
+static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
+{
+	WRITE_ONCE(rdp->rcu_urgent_qs, false);
+	WRITE_ONCE(rdp->rcu_need_heavy_qs, false);
+	if (tick_nohz_full_cpu(rdp->cpu) && rdp->rcu_forced_tick) {
+		tick_dep_clear_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
+		rdp->rcu_forced_tick = false;
+	}
+}
+
 /**
  * rcu_is_watching - see if RCU thinks that the current CPU is not idle
  *
@@ -1073,6 +1094,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	if (tick_nohz_full_cpu(rdp->cpu) &&
 		   time_after(jiffies,
 			      READ_ONCE(rdp->last_fqs_resched) + jtsq * 3)) {
+		WRITE_ONCE(*ruqp, true);
 		resched_cpu(rdp->cpu);
 		WRITE_ONCE(rdp->last_fqs_resched, jiffies);
 	}
@@ -1968,7 +1990,6 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
 		return;
 	}
 	mask = rdp->grpmask;
-	rdp->core_needs_qs = false;
 	if ((rnp->qsmask & mask) == 0) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	} else {
@@ -1979,6 +2000,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
 		if (!offloaded)
 			needwake = rcu_accelerate_cbs(rnp, rdp);
 
+		rcu_disable_urgency_upon_qs(rdp);
 		rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
 		/* ^^^ Released rnp->lock */
 		if (needwake)
@@ -2101,6 +2123,9 @@ int rcutree_dead_cpu(unsigned int cpu)
 	rcu_boost_kthread_setaffinity(rnp, -1);
 	/* Do any needed no-CB deferred wakeups from this CPU. */
 	do_nocb_deferred_wakeup(per_cpu_ptr(&rcu_data, cpu));
+
+	// Stop-machine done, so allow nohz_full to disable tick.
+	tick_dep_clear(TICK_DEP_BIT_RCU);
 	return 0;
 }
 
@@ -2151,6 +2176,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	rcu_nocb_unlock_irqrestore(rdp, flags);
 
 	/* Invoke callbacks. */
+	tick_dep_set_task(current, TICK_DEP_BIT_RCU);
 	rhp = rcu_cblist_dequeue(&rcl);
 	for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) {
 		debug_rcu_head_unqueue(rhp);
@@ -2217,6 +2243,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	/* Re-invoke RCU core processing if there are callbacks remaining. */
 	if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist))
 		invoke_rcu_core();
+	tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
 }
 
 /*
@@ -2241,7 +2268,7 @@ void rcu_sched_clock_irq(int user)
 		__this_cpu_write(rcu_data.rcu_urgent_qs, false);
 	}
 	rcu_flavor_sched_clock_irq(user);
-	if (rcu_pending())
+	if (rcu_pending(user))
 		invoke_rcu_core();
 
 	trace_rcu_utilization(TPS("End scheduler-tick"));
@@ -2259,6 +2286,7 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
 	int cpu;
 	unsigned long flags;
 	unsigned long mask;
+	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 
 	rcu_for_each_leaf_node(rnp) {
@@ -2283,8 +2311,11 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
 			unsigned long bit = leaf_node_cpu_bit(rnp, cpu);
 			if ((rnp->qsmask & bit) != 0) {
-				if (f(per_cpu_ptr(&rcu_data, cpu)))
+				rdp = per_cpu_ptr(&rcu_data, cpu);
+				if (f(rdp)) {
 					mask |= bit;
+					rcu_disable_urgency_upon_qs(rdp);
+				}
 			}
 		}
 		if (mask != 0) {
@@ -2312,7 +2343,7 @@ void rcu_force_quiescent_state(void)
 	rnp = __this_cpu_read(rcu_data.mynode);
 	for (; rnp != NULL; rnp = rnp->parent) {
 		ret = (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) ||
-		      !raw_spin_trylock(&rnp->fqslock);
+		       !raw_spin_trylock(&rnp->fqslock);
 		if (rnp_old != NULL)
 			raw_spin_unlock(&rnp_old->fqslock);
 		if (ret)
@@ -2786,8 +2817,9 @@ EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
  * CPU-local state are performed first.  However, we must check for CPU
  * stalls first, else we might not get a chance.
  */
-static int rcu_pending(void)
+static int rcu_pending(int user)
 {
+	bool gp_in_progress;
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;
 
@@ -2798,12 +2830,13 @@ static int rcu_pending(void)
 	if (rcu_nocb_need_deferred_wakeup(rdp))
 		return 1;
 
-	/* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */
-	if (rcu_nohz_full_cpu())
+	/* Is this a nohz_full CPU in userspace or idle?  (Ignore RCU if so.) */
+	if ((user || rcu_is_cpu_rrupt_from_idle()) && rcu_nohz_full_cpu())
 		return 0;
 
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
-	if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm)
+	gp_in_progress = rcu_gp_in_progress();
+	if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm && gp_in_progress)
 		return 1;
 
 	/* Does this CPU have callbacks ready to invoke? */
@@ -2811,8 +2844,7 @@ static int rcu_pending(void)
 		return 1;
 
 	/* Has RCU gone idle with this CPU needing another grace period? */
-	if (!rcu_gp_in_progress() &&
-	    rcu_segcblist_is_enabled(&rdp->cblist) &&
+	if (!gp_in_progress && rcu_segcblist_is_enabled(&rdp->cblist) &&
 	    (!IS_ENABLED(CONFIG_RCU_NOCB_CPU) ||
 	     !rcu_segcblist_is_offloaded(&rdp->cblist)) &&
 	    !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
@@ -2845,7 +2877,7 @@ static void rcu_barrier_callback(struct rcu_head *rhp)
 {
 	if (atomic_dec_and_test(&rcu_state.barrier_cpu_count)) {
 		rcu_barrier_trace(TPS("LastCB"), -1,
-				   rcu_state.barrier_sequence);
+				  rcu_state.barrier_sequence);
 		complete(&rcu_state.barrier_completion);
 	} else {
 		rcu_barrier_trace(TPS("CB"), -1, rcu_state.barrier_sequence);
@@ -2869,7 +2901,7 @@ static void rcu_barrier_func(void *unused)
 	} else {
 		debug_rcu_head_unqueue(&rdp->barrier_head);
 		rcu_barrier_trace(TPS("IRQNQ"), -1,
-				   rcu_state.barrier_sequence);
+				  rcu_state.barrier_sequence);
 	}
 	rcu_nocb_unlock(rdp);
 }
@@ -2896,7 +2928,7 @@ void rcu_barrier(void)
 	/* Did someone else do our work for us? */
 	if (rcu_seq_done(&rcu_state.barrier_sequence, s)) {
 		rcu_barrier_trace(TPS("EarlyExit"), -1,
-				   rcu_state.barrier_sequence);
+				  rcu_state.barrier_sequence);
 		smp_mb(); /* caller's subsequent code after above check. */
 		mutex_unlock(&rcu_state.barrier_mutex);
 		return;
@@ -2928,11 +2960,11 @@ void rcu_barrier(void)
 			continue;
 		if (rcu_segcblist_n_cbs(&rdp->cblist)) {
 			rcu_barrier_trace(TPS("OnlineQ"), cpu,
-					   rcu_state.barrier_sequence);
+					  rcu_state.barrier_sequence);
 			smp_call_function_single(cpu, rcu_barrier_func, NULL, 1);
 		} else {
 			rcu_barrier_trace(TPS("OnlineNQ"), cpu,
-					   rcu_state.barrier_sequence);
+					  rcu_state.barrier_sequence);
 		}
 	}
 	put_online_cpus();
@@ -3083,6 +3115,9 @@ int rcutree_online_cpu(unsigned int cpu)
 		return 0; /* Too early in boot for scheduler work. */
 	sync_sched_exp_online_cleanup(cpu);
 	rcutree_affinity_setting(cpu, -1);
+
+	// Stop-machine done, so allow nohz_full to disable tick.
+	tick_dep_clear(TICK_DEP_BIT_RCU);
 	return 0;
 }
 
@@ -3103,6 +3138,9 @@ int rcutree_offline_cpu(unsigned int cpu)
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 
 	rcutree_affinity_setting(cpu, cpu);
+
+	// nohz_full CPUs need the tick for stop-machine to work quickly
+	tick_dep_set(TICK_DEP_BIT_RCU);
 	return 0;
 }
 
@@ -3148,6 +3186,7 @@ void rcu_cpu_starting(unsigned int cpu)
 	rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq);
 	rdp->rcu_onl_gp_flags = READ_ONCE(rcu_state.gp_flags);
 	if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
+		rcu_disable_urgency_upon_qs(rdp);
 		/* Report QS -after- changing ->qsmaskinitnext! */
 		rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
 	} else {
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index c612f306fe89..055c31781d3a 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -181,6 +181,7 @@ struct rcu_data {
 	atomic_t dynticks;		/* Even value for idle, else odd. */
 	bool rcu_need_heavy_qs;		/* GP old, so heavy quiescent state! */
 	bool rcu_urgent_qs;		/* GP old need light quiescent state. */
+	bool rcu_forced_tick;		/* Forced tick to provide QS. */
 #ifdef CONFIG_RCU_FAST_NO_HZ
 	bool all_lazy;			/* All CPU's CBs lazy at idle start? */
 	unsigned long last_accelerate;	/* Last jiffy CBs were accelerated. */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 2defc7fe74c3..fa08d55f7040 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1946,7 +1946,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 	int __maybe_unused cpu = my_rdp->cpu;
 	unsigned long cur_gp_seq;
 	unsigned long flags;
-	bool gotcbs;
+	bool gotcbs = false;
 	unsigned long j = jiffies;
 	bool needwait_gp = false; // This prevents actual uninitialized use.
 	bool needwake;
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 998d50ee2d9b..1fe34a9fabc2 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -235,6 +235,7 @@ static int multi_cpu_stop(void *data)
 			 */
 			touch_nmi_watchdog();
 		}
+		rcu_momentary_dyntick_idle();
 	} while (curstate != MULTI_STOP_EXIT);
 
 	local_irq_restore(flags);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index c2748232f607..8b192e67aabc 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -172,6 +172,7 @@ 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;
 bool tick_nohz_full_running;
+EXPORT_SYMBOL_GPL(tick_nohz_full_running);
 static atomic_t tick_dep_mask;
 
 static bool check_tick_dependency(atomic_t *dep)
@@ -198,6 +199,11 @@ static bool check_tick_dependency(atomic_t *dep)
 		return true;
 	}
 
+	if (val & TICK_DEP_MASK_RCU) {
+		trace_tick_stop(0, TICK_DEP_MASK_RCU);
+		return true;
+	}
+
 	return false;
 }
 
@@ -324,6 +330,7 @@ void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit)
 		preempt_enable();
 	}
 }
+EXPORT_SYMBOL_GPL(tick_nohz_dep_set_cpu);
 
 void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
 {
@@ -331,6 +338,7 @@ void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
 
 	atomic_andnot(BIT(bit), &ts->tick_dep_mask);
 }
+EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu);
 
 /*
  * Set a per-task tick dependency. Posix CPU timers need this in order to elapse
@@ -344,11 +352,13 @@ void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit)
 	 */
 	tick_nohz_dep_set_all(&tsk->tick_dep_mask, bit);
 }
+EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task);
 
 void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit)
 {
 	atomic_andnot(BIT(bit), &tsk->tick_dep_mask);
 }
+EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_task);
 
 /*
  * Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse
@@ -397,6 +407,7 @@ void __init tick_nohz_full_setup(cpumask_var_t cpumask)
 	cpumask_copy(tick_nohz_full_mask, cpumask);
 	tick_nohz_full_running = true;
 }
+EXPORT_SYMBOL_GPL(tick_nohz_full_setup);
 
 static int tick_nohz_cpu_down(unsigned int cpu)
 {
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 914b845ad4ff..bc88fd939f4e 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -365,11 +365,6 @@ static void show_pwq(struct pool_workqueue *pwq);
 			 !lockdep_is_held(&wq_pool_mutex),		\
 			 "RCU or wq_pool_mutex should be held")
 
-#define assert_rcu_or_wq_mutex(wq)					\
-	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
-			 !lockdep_is_held(&wq->mutex),			\
-			 "RCU or wq->mutex should be held")
-
 #define assert_rcu_or_wq_mutex_or_pool_mutex(wq)			\
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
 			 !lockdep_is_held(&wq->mutex) &&		\
@@ -427,9 +422,7 @@ static void show_pwq(struct pool_workqueue *pwq);
  */
 #define for_each_pwq(pwq, wq)						\
 	list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node,		\
-				lockdep_is_held(&wq->mutex))		\
-		if (({ assert_rcu_or_wq_mutex(wq); false; })) { }	\
-		else
+				 lockdep_is_held(&(wq->mutex)))
 
 #ifdef CONFIG_DEBUG_OBJECTS_WORK