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

13 files changed, 333 insertions, 188 deletions

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 7c38f8f3d97b..844cd04bb453 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4412,13 +4412,13 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
 #endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */
 	/* Note: the following can be executed concurrently, so be careful. */
 	printk("\n");
-	printk("===============================\n");
-	printk("[ INFO: suspicious RCU usage. ]\n");
+	pr_err("===============================\n");
+	pr_err("suspicious RCU usage. ]\n");
 	print_kernel_ident();
-	printk("-------------------------------\n");
-	printk("%s:%d %s!\n", file, line, s);
-	printk("\nother info that might help us debug this:\n\n");
-	printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
+	pr_err("-------------------------------\n");
+	pr_err("%s:%d %s!\n", file, line, s);
+	pr_err("\nother info that might help us debug this:\n\n");
+	pr_err("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
 	       !rcu_lockdep_current_cpu_online()
 			? "RCU used illegally from offline CPU!\n"
 			: !rcu_is_watching()
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index f8c5af52a131..d3de04b12f8c 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -780,6 +780,10 @@ static void lock_torture_cleanup(void)
 	else
 		lock_torture_print_module_parms(cxt.cur_ops,
 						"End of test: SUCCESS");
+
+	kfree(cxt.lwsa);
+	kfree(cxt.lrsa);
+
 end:
 	torture_cleanup_end();
 }
@@ -924,6 +928,8 @@ static int __init lock_torture_init(void)
 				       GFP_KERNEL);
 		if (reader_tasks == NULL) {
 			VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory");
+			kfree(writer_tasks);
+			writer_tasks = NULL;
 			firsterr = -ENOMEM;
 			goto unwind;
 		}
diff --git a/kernel/membarrier.c b/kernel/membarrier.c
index 536c727a56e9..9f9284f37f8d 100644
--- a/kernel/membarrier.c
+++ b/kernel/membarrier.c
@@ -16,6 +16,7 @@
 
 #include <linux/syscalls.h>
 #include <linux/membarrier.h>
+#include <linux/tick.h>
 
 /*
  * Bitmask made from a "or" of all commands within enum membarrier_cmd,
@@ -51,6 +52,9 @@
  */
 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) {
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 87c51225ceec..6e4fd7680c70 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -564,10 +564,24 @@ static void srcu_torture_stats(void)
 	pr_alert("%s%s 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_struct_array* counts =
+			per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu);
 
-		c0 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[!idx];
-		c1 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[idx];
+		u0 = counts->unlock_count[!idx];
+		u1 = counts->unlock_count[idx];
+
+		/* Make sure that a lock is always counted if the corresponding
+		   unlock is counted. */
+		smp_rmb();
+
+		l0 = counts->lock_count[!idx];
+		l1 = counts->lock_count[idx];
+
+		c0 = (long)(l0 - u0);
+		c1 = (long)(l1 - u1);
 		pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
 	}
 	pr_cont("\n");
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index 9b9cdd549caa..2c9265035154 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -141,34 +141,38 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 /*
- * Returns approximate total of the readers' ->seq[] values for the
+ * Returns approximate total of the readers' ->lock_count[] values for the
  * rank of per-CPU counters specified by idx.
  */
-static unsigned long srcu_readers_seq_idx(struct srcu_struct *sp, int idx)
+static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx)
 {
 	int cpu;
 	unsigned long sum = 0;
 	unsigned long t;
 
 	for_each_possible_cpu(cpu) {
-		t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]);
+		struct srcu_struct_array* cpu_counts =
+			per_cpu_ptr(sp->per_cpu_ref, cpu);
+		t = READ_ONCE(cpu_counts->lock_count[idx]);
 		sum += t;
 	}
 	return sum;
 }
 
 /*
- * Returns approximate number of readers active on the specified rank
- * of the per-CPU ->c[] counters.
+ * Returns approximate total of the readers' ->unlock_count[] values for the
+ * rank of per-CPU counters specified by idx.
  */
-static unsigned long srcu_readers_active_idx(struct srcu_struct *sp, int idx)
+static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx)
 {
 	int cpu;
 	unsigned long sum = 0;
 	unsigned long t;
 
 	for_each_possible_cpu(cpu) {
-		t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]);
+		struct srcu_struct_array* cpu_counts =
+			per_cpu_ptr(sp->per_cpu_ref, cpu);
+		t = READ_ONCE(cpu_counts->unlock_count[idx]);
 		sum += t;
 	}
 	return sum;
@@ -176,79 +180,43 @@ static unsigned long srcu_readers_active_idx(struct srcu_struct *sp, int idx)
 
 /*
  * Return true if the number of pre-existing readers is determined to
- * be stably zero.  An example unstable zero can occur if the call
- * to srcu_readers_active_idx() misses an __srcu_read_lock() increment,
- * but due to task migration, sees the corresponding __srcu_read_unlock()
- * decrement.  This can happen because srcu_readers_active_idx() takes
- * time to sum the array, and might in fact be interrupted or preempted
- * partway through the summation.
+ * be zero.
  */
 static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
 {
-	unsigned long seq;
+	unsigned long unlocks;
 
-	seq = srcu_readers_seq_idx(sp, idx);
+	unlocks = srcu_readers_unlock_idx(sp, idx);
 
 	/*
-	 * The following smp_mb() A pairs with the smp_mb() B located in
-	 * __srcu_read_lock().  This pairing ensures that if an
-	 * __srcu_read_lock() increments its counter after the summation
-	 * in srcu_readers_active_idx(), then the corresponding SRCU read-side
-	 * critical section will see any changes made prior to the start
-	 * of the current SRCU grace period.
+	 * Make sure that a lock is always counted if the corresponding unlock
+	 * is counted. Needs to be a smp_mb() as the read side may contain a
+	 * read from a variable that is written to before the synchronize_srcu()
+	 * in the write side. In this case smp_mb()s A and B act like the store
+	 * buffering pattern.
 	 *
-	 * Also, if the above call to srcu_readers_seq_idx() saw the
-	 * increment of ->seq[], then the call to srcu_readers_active_idx()
-	 * must see the increment of ->c[].
+	 * This smp_mb() also pairs with smp_mb() C to prevent writes after the
+	 * synchronize_srcu() from being executed before the grace period ends.
 	 */
 	smp_mb(); /* A */
 
 	/*
-	 * Note that srcu_readers_active_idx() can incorrectly return
-	 * zero even though there is a pre-existing reader throughout.
-	 * To see this, suppose that task A is in a very long SRCU
-	 * read-side critical section that started on CPU 0, and that
-	 * no other reader exists, so that the sum of the counters
-	 * is equal to one.  Then suppose that task B starts executing
-	 * srcu_readers_active_idx(), summing up to CPU 1, and then that
-	 * task C starts reading on CPU 0, so that its increment is not
-	 * summed, but finishes reading on CPU 2, so that its decrement
-	 * -is- summed.  Then when task B completes its sum, it will
-	 * incorrectly get zero, despite the fact that task A has been
-	 * in its SRCU read-side critical section the whole time.
+	 * If the locks are the same as the unlocks, then there must of have
+	 * been no readers on this index at some time in between. This does not
+	 * mean that there are no more readers, as one could have read the
+	 * current index but have incremented the lock counter yet.
 	 *
-	 * We therefore do a validation step should srcu_readers_active_idx()
-	 * return zero.
+	 * Note that there can be at most NR_CPUS worth of readers using the old
+	 * index that haven't incremented ->lock_count[] yet.  Therefore, the
+	 * sum of the ->lock_count[]s cannot increment enough times to overflow
+	 * and end up equal the sum of the ->unlock_count[]s, as long as there
+	 * are at most ULONG_MAX - NR_CPUS readers at a time.  (Yes, this does
+	 * mean that systems having more than a billion or so CPUs need to be
+	 * 64-bit systems.)  Therefore, the only way that the return values of
+	 * the two calls to srcu_readers_(un)lock_idx() can be equal is if there
+	 * are no active readers using this index.
 	 */
-	if (srcu_readers_active_idx(sp, idx) != 0)
-		return false;
-
-	/*
-	 * The remainder of this function is the validation step.
-	 * The following smp_mb() D pairs with the smp_mb() C in
-	 * __srcu_read_unlock().  If the __srcu_read_unlock() was seen
-	 * by srcu_readers_active_idx() above, then any destructive
-	 * operation performed after the grace period will happen after
-	 * the corresponding SRCU read-side critical section.
-	 *
-	 * Note that there can be at most NR_CPUS worth of readers using
-	 * the old index, which is not enough to overflow even a 32-bit
-	 * integer.  (Yes, this does mean that systems having more than
-	 * a billion or so CPUs need to be 64-bit systems.)  Therefore,
-	 * the sum of the ->seq[] counters cannot possibly overflow.
-	 * Therefore, the only way that the return values of the two
-	 * calls to srcu_readers_seq_idx() can be equal is if there were
-	 * no increments of the corresponding rank of ->seq[] counts
-	 * in the interim.  But the missed-increment scenario laid out
-	 * above includes an increment of the ->seq[] counter by
-	 * the corresponding __srcu_read_lock().  Therefore, if this
-	 * scenario occurs, the return values from the two calls to
-	 * srcu_readers_seq_idx() will differ, and thus the validation
-	 * step below suffices.
-	 */
-	smp_mb(); /* D */
-
-	return srcu_readers_seq_idx(sp, idx) == seq;
+	return srcu_readers_lock_idx(sp, idx) == unlocks;
 }
 
 /**
@@ -266,8 +234,12 @@ static bool srcu_readers_active(struct srcu_struct *sp)
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]);
-		sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]);
+		struct srcu_struct_array* cpu_counts =
+			per_cpu_ptr(sp->per_cpu_ref, cpu);
+		sum += READ_ONCE(cpu_counts->lock_count[0]);
+		sum += READ_ONCE(cpu_counts->lock_count[1]);
+		sum -= READ_ONCE(cpu_counts->unlock_count[0]);
+		sum -= READ_ONCE(cpu_counts->unlock_count[1]);
 	}
 	return sum;
 }
@@ -298,9 +270,8 @@ int __srcu_read_lock(struct srcu_struct *sp)
 	int idx;
 
 	idx = READ_ONCE(sp->completed) & 0x1;
-	__this_cpu_inc(sp->per_cpu_ref->c[idx]);
+	__this_cpu_inc(sp->per_cpu_ref->lock_count[idx]);
 	smp_mb(); /* B */  /* Avoid leaking the critical section. */
-	__this_cpu_inc(sp->per_cpu_ref->seq[idx]);
 	return idx;
 }
 EXPORT_SYMBOL_GPL(__srcu_read_lock);
@@ -314,7 +285,7 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock);
 void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 {
 	smp_mb(); /* C */  /* Avoid leaking the critical section. */
-	this_cpu_dec(sp->per_cpu_ref->c[idx]);
+	this_cpu_inc(sp->per_cpu_ref->unlock_count[idx]);
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
@@ -349,7 +320,7 @@ static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount)
 
 /*
  * Increment the ->completed counter so that future SRCU readers will
- * use the other rank of the ->c[] and ->seq[] arrays.  This allows
+ * use the other rank of the ->(un)lock_count[] arrays.  This allows
  * us to wait for pre-existing readers in a starvation-free manner.
  */
 static void srcu_flip(struct srcu_struct *sp)
@@ -392,6 +363,7 @@ void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
 	head->next = NULL;
 	head->func = func;
 	spin_lock_irqsave(&sp->queue_lock, flags);
+	smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */
 	rcu_batch_queue(&sp->batch_queue, head);
 	if (!sp->running) {
 		sp->running = true;
@@ -425,6 +397,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
 	head->next = NULL;
 	head->func = wakeme_after_rcu;
 	spin_lock_irq(&sp->queue_lock);
+	smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */
 	if (!sp->running) {
 		/* steal the processing owner */
 		sp->running = true;
@@ -446,6 +419,8 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
 
 	if (!done)
 		wait_for_completion(&rcu.completion);
+
+	smp_mb(); /* Caller's later accesses after GP. */
 }
 
 /**
@@ -620,6 +595,7 @@ static void srcu_invoke_callbacks(struct srcu_struct *sp)
 	int i;
 	struct rcu_head *head;
 
+	smp_mb(); /* Callback accesses after GP. */
 	for (i = 0; i < SRCU_CALLBACK_BATCH; i++) {
 		head = rcu_batch_dequeue(&sp->batch_done);
 		if (!head)
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 1898559e6b60..905b8dba89f2 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -41,8 +41,6 @@
 
 /* Forward declarations for tiny_plugin.h. */
 struct rcu_ctrlblk;
-static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp);
-static void rcu_process_callbacks(struct softirq_action *unused);
 static void __call_rcu(struct rcu_head *head,
 		       rcu_callback_t func,
 		       struct rcu_ctrlblk *rcp);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 96c52e43f7ca..b56e2dc31ba5 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -269,15 +269,170 @@ void rcu_bh_qs(void)
 
 static DEFINE_PER_CPU(int, rcu_sched_qs_mask);
 
+/*
+ * Steal a bit from the bottom of ->dynticks for idle entry/exit
+ * control.  Initially this is for TLB flushing.
+ */
+#define RCU_DYNTICK_CTRL_MASK 0x1
+#define RCU_DYNTICK_CTRL_CTR  (RCU_DYNTICK_CTRL_MASK + 1)
+#ifndef rcu_eqs_special_exit
+#define rcu_eqs_special_exit() do { } while (0)
+#endif
+
 static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
-	.dynticks = ATOMIC_INIT(1),
+	.dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR),
 #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 */
 };
 
+/*
+ * Record entry into an extended quiescent state.  This is only to be
+ * called when not already in an extended quiescent state.
+ */
+static void rcu_dynticks_eqs_enter(void)
+{
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	int seq;
+
+	/*
+	 * CPUs seeing atomic_inc_return() must see prior RCU read-side
+	 * critical sections, and we also must force ordering with the
+	 * next idle sojourn.
+	 */
+	seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
+	/* Better be in an extended quiescent state! */
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     (seq & RCU_DYNTICK_CTRL_CTR));
+	/* Better not have special action (TLB flush) pending! */
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     (seq & RCU_DYNTICK_CTRL_MASK));
+}
+
+/*
+ * Record exit from an extended quiescent state.  This is only to be
+ * called from an extended quiescent state.
+ */
+static void rcu_dynticks_eqs_exit(void)
+{
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	int seq;
+
+	/*
+	 * CPUs seeing atomic_inc_return() must see prior idle sojourns,
+	 * and we also must force ordering with the next RCU read-side
+	 * critical section.
+	 */
+	seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     !(seq & RCU_DYNTICK_CTRL_CTR));
+	if (seq & RCU_DYNTICK_CTRL_MASK) {
+		rcu_eqs_special_exit();
+		/* Prefer duplicate flushes to losing a flush. */
+		smp_mb__before_atomic(); /* NMI safety. */
+		atomic_and(~RCU_DYNTICK_CTRL_MASK, &rdtp->dynticks);
+	}
+}
+
+/*
+ * Reset the current CPU's ->dynticks counter to indicate that the
+ * newly onlined CPU is no longer in an extended quiescent state.
+ * This will either leave the counter unchanged, or increment it
+ * to the next non-quiescent value.
+ *
+ * The non-atomic test/increment sequence works because the upper bits
+ * of the ->dynticks counter are manipulated only by the corresponding CPU,
+ * or when the corresponding CPU is offline.
+ */
+static void rcu_dynticks_eqs_online(void)
+{
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+
+	if (atomic_read(&rdtp->dynticks) & RCU_DYNTICK_CTRL_CTR)
+		return;
+	atomic_add(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
+}
+
+/*
+ * Is the current CPU in an extended quiescent state?
+ *
+ * No ordering, as we are sampling CPU-local information.
+ */
+bool rcu_dynticks_curr_cpu_in_eqs(void)
+{
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+
+	return !(atomic_read(&rdtp->dynticks) & RCU_DYNTICK_CTRL_CTR);
+}
+
+/*
+ * Snapshot the ->dynticks counter with full ordering so as to allow
+ * stable comparison of this counter with past and future snapshots.
+ */
+int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
+{
+	int snap = atomic_add_return(0, &rdtp->dynticks);
+
+	return snap & ~RCU_DYNTICK_CTRL_MASK;
+}
+
+/*
+ * Return true if the snapshot returned from rcu_dynticks_snap()
+ * indicates that RCU is in an extended quiescent state.
+ */
+static bool rcu_dynticks_in_eqs(int snap)
+{
+	return !(snap & RCU_DYNTICK_CTRL_CTR);
+}
+
+/*
+ * Return true if the CPU corresponding to the specified rcu_dynticks
+ * structure has spent some time in an extended quiescent state since
+ * rcu_dynticks_snap() returned the specified snapshot.
+ */
+static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap)
+{
+	return snap != rcu_dynticks_snap(rdtp);
+}
+
+/*
+ * Do a double-increment of the ->dynticks counter to emulate a
+ * momentary idle-CPU quiescent state.
+ */
+static void rcu_dynticks_momentary_idle(void)
+{
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	int special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR,
+					&rdtp->dynticks);
+
+	/* It is illegal to call this from idle state. */
+	WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
+}
+
+/*
+ * Set the special (bottom) bit of the specified CPU so that it
+ * will take special action (such as flushing its TLB) on the
+ * next exit from an extended quiescent state.  Returns true if
+ * the bit was successfully set, or false if the CPU was not in
+ * an extended quiescent state.
+ */
+bool rcu_eqs_special_set(int cpu)
+{
+	int old;
+	int new;
+	struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+	do {
+		old = atomic_read(&rdtp->dynticks);
+		if (old & RCU_DYNTICK_CTRL_CTR)
+			return false;
+		new = old | RCU_DYNTICK_CTRL_MASK;
+	} while (atomic_cmpxchg(&rdtp->dynticks, old, new) != old);
+	return true;
+}
+
 DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
 EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr);
 
@@ -297,7 +452,6 @@ EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr);
 static void rcu_momentary_dyntick_idle(void)
 {
 	struct rcu_data *rdp;
-	struct rcu_dynticks *rdtp;
 	int resched_mask;
 	struct rcu_state *rsp;
 
@@ -324,10 +478,7 @@ static void rcu_momentary_dyntick_idle(void)
 		 * 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. */
+		rcu_dynticks_momentary_idle();
 		break;
 	}
 }
@@ -670,7 +821,7 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
 {
 	struct rcu_state *rsp;
 	struct rcu_data *rdp;
-	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	struct rcu_dynticks __maybe_unused *rdtp = this_cpu_ptr(&rcu_dynticks);
 
 	trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
 	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
@@ -689,12 +840,7 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
 		do_nocb_deferred_wakeup(rdp);
 	}
 	rcu_prepare_for_idle();
-	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
-	smp_mb__before_atomic();  /* See above. */
-	atomic_inc(&rdtp->dynticks);
-	smp_mb__after_atomic();  /* Force ordering with next sojourn. */
-	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
-		     atomic_read(&rdtp->dynticks) & 0x1);
+	rcu_dynticks_eqs_enter();
 	rcu_dynticks_task_enter();
 
 	/*
@@ -823,15 +969,10 @@ void rcu_irq_exit_irqson(void)
  */
 static void rcu_eqs_exit_common(long long oldval, int user)
 {
-	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	struct rcu_dynticks __maybe_unused *rdtp = this_cpu_ptr(&rcu_dynticks);
 
 	rcu_dynticks_task_exit();
-	smp_mb__before_atomic();  /* Force ordering w/previous sojourn. */
-	atomic_inc(&rdtp->dynticks);
-	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
-	smp_mb__after_atomic();  /* See above. */
-	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
-		     !(atomic_read(&rdtp->dynticks) & 0x1));
+	rcu_dynticks_eqs_exit();
 	rcu_cleanup_after_idle();
 	trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting);
 	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
@@ -977,12 +1118,8 @@ void rcu_nmi_enter(void)
 	 * to be in the outermost NMI handler that interrupted an RCU-idle
 	 * period (observation due to Andy Lutomirski).
 	 */
-	if (!(atomic_read(&rdtp->dynticks) & 0x1)) {
-		smp_mb__before_atomic();  /* Force delay from prior write. */
-		atomic_inc(&rdtp->dynticks);
-		/* atomic_inc() before later RCU read-side crit sects */
-		smp_mb__after_atomic();  /* See above. */
-		WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+	if (rcu_dynticks_curr_cpu_in_eqs()) {
+		rcu_dynticks_eqs_exit();
 		incby = 1;
 	}
 	rdtp->dynticks_nmi_nesting += incby;
@@ -1007,7 +1144,7 @@ void rcu_nmi_exit(void)
 	 * to us!)
 	 */
 	WARN_ON_ONCE(rdtp->dynticks_nmi_nesting <= 0);
-	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+	WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs());
 
 	/*
 	 * If the nesting level is not 1, the CPU wasn't RCU-idle, so
@@ -1020,11 +1157,7 @@ void rcu_nmi_exit(void)
 
 	/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
 	rdtp->dynticks_nmi_nesting = 0;
-	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
-	smp_mb__before_atomic();  /* See above. */
-	atomic_inc(&rdtp->dynticks);
-	smp_mb__after_atomic();  /* Force delay to next write. */
-	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+	rcu_dynticks_eqs_enter();
 }
 
 /**
@@ -1037,7 +1170,7 @@ void rcu_nmi_exit(void)
  */
 bool notrace __rcu_is_watching(void)
 {
-	return atomic_read(this_cpu_ptr(&rcu_dynticks.dynticks)) & 0x1;
+	return !rcu_dynticks_curr_cpu_in_eqs();
 }
 
 /**
@@ -1120,9 +1253,9 @@ static int rcu_is_cpu_rrupt_from_idle(void)
 static int dyntick_save_progress_counter(struct rcu_data *rdp,
 					 bool *isidle, unsigned long *maxj)
 {
-	rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
+	rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks);
 	rcu_sysidle_check_cpu(rdp, isidle, maxj);
-	if ((rdp->dynticks_snap & 0x1) == 0) {
+	if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) {
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
 		if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4,
 				 rdp->mynode->gpnum))
@@ -1141,12 +1274,8 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp,
 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);
-	snap = (unsigned int)rdp->dynticks_snap;
+	struct rcu_node *rnp;
 
 	/*
 	 * If the CPU passed through or entered a dynticks idle phase with
@@ -1156,27 +1285,27 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 	 * read-side critical section that started before the beginning
 	 * of the current RCU grace period.
 	 */
-	if ((curr & 0x1) == 0 || UINT_CMP_GE(curr, snap + 2)) {
+	if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) {
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
 		rdp->dynticks_fqs++;
 		return 1;
 	}
 
 	/*
-	 * Check for the CPU being offline, but only if the grace period
-	 * is old enough.  We don't need to worry about the CPU changing
-	 * state: If we see it offline even once, it has been through a
-	 * quiescent state.
-	 *
-	 * The reason for insisting that the grace period be at least
-	 * one jiffy old is that CPUs that are not quite online and that
-	 * have just gone offline can still execute RCU read-side critical
-	 * sections.
+	 * Has this CPU encountered a cond_resched_rcu_qs() since the
+	 * beginning of the grace period?  For this to be the case,
+	 * the CPU has to have noticed the current grace period.  This
+	 * might not be the case for nohz_full CPUs looping in the kernel.
 	 */
-	if (ULONG_CMP_GE(rdp->rsp->gp_start + 2, jiffies))
-		return 0;  /* Grace period is not old enough. */
-	barrier();
-	if (cpu_is_offline(rdp->cpu)) {
+	rnp = rdp->mynode;
+	if (READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_qs_ctr, rdp->cpu) &&
+	    READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) {
+		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc"));
+		return 1;
+	}
+
+	/* Check for the CPU being offline. */
+	if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) {
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl"));
 		rdp->offline_fqs++;
 		return 1;
@@ -1217,11 +1346,12 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 		rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */
 	}
 
-	/* And if it has been a really long time, kick the CPU as well. */
-	if (ULONG_CMP_GE(jiffies,
-			 rdp->rsp->gp_start + 2 * jiffies_till_sched_qs) ||
-	    ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs))
-		resched_cpu(rdp->cpu);  /* Force CPU into scheduler. */
+	/*
+	 * If more than halfway to RCU CPU stall-warning time, do
+	 * a resched_cpu() to try to loosen things up a bit.
+	 */
+	if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2)
+		resched_cpu(rdp->cpu);
 
 	return 0;
 }
@@ -1274,7 +1404,10 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
 }
 
 /*
- * Dump stacks of all tasks running on stalled CPUs.
+ * Dump stacks of all tasks running on stalled CPUs.  First try using
+ * NMIs, but fall back to manual remote stack tracing on architectures
+ * that don't support NMI-based stack dumps.  The NMI-triggered stack
+ * traces are more accurate because they are printed by the target CPU.
  */
 static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
 {
@@ -1284,11 +1417,10 @@ static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
 
 	rcu_for_each_leaf_node(rsp, rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
-		if (rnp->qsmask != 0) {
-			for_each_leaf_node_possible_cpu(rnp, cpu)
-				if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
+		for_each_leaf_node_possible_cpu(rnp, cpu)
+			if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
+				if (!trigger_single_cpu_backtrace(cpu))
 					dump_cpu_task(cpu);
-		}
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
 }
@@ -1376,6 +1508,9 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	       (long)rsp->gpnum, (long)rsp->completed, totqlen);
 	if (ndetected) {
 		rcu_dump_cpu_stacks(rsp);
+
+		/* Complain about tasks blocking the grace period. */
+		rcu_print_detail_task_stall(rsp);
 	} else {
 		if (READ_ONCE(rsp->gpnum) != gpnum ||
 		    READ_ONCE(rsp->completed) == gpnum) {
@@ -1392,9 +1527,6 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 		}
 	}
 
-	/* Complain about tasks blocking the grace period. */
-	rcu_print_detail_task_stall(rsp);
-
 	rcu_check_gp_kthread_starvation(rsp);
 
 	panic_on_rcu_stall();
@@ -2464,10 +2596,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 
 	rnp = rdp->mynode;
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	if ((rdp->cpu_no_qs.b.norm &&
-	     rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) ||
-	    rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum ||
-	    rdp->gpwrap) {
+	if (rdp->cpu_no_qs.b.norm || rdp->gpnum != rnp->gpnum ||
+	    rnp->completed == rnp->gpnum || rdp->gpwrap) {
 
 		/*
 		 * The grace period in which this quiescent state was
@@ -2522,8 +2652,7 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
 	 * Was there a quiescent state since the beginning of the grace
 	 * period? If no, then exit and wait for the next call.
 	 */
-	if (rdp->cpu_no_qs.b.norm &&
-	    rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr))
+	if (rdp->cpu_no_qs.b.norm)
 		return;
 
 	/*
@@ -3287,6 +3416,18 @@ void synchronize_sched(void)
 EXPORT_SYMBOL_GPL(synchronize_sched);
 
 /**
+ * rcu_sched_trivial_gp - Are RCU-sched grace periods trivially zero cost?
+ *
+ * Returns true if RCU-sched grace periods are currently zero cost, which
+ * they are if there is only one CPU.  Note that unless you take steps to
+ * prevent it, the number of CPUs might change at any time.
+ */
+bool rcu_sched_trivial_gp(void)
+{
+	return rcu_blocking_is_gp();
+}
+
+/**
  * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
  *
  * Control will return to the caller some time after a full rcu_bh grace
@@ -3314,6 +3455,18 @@ void synchronize_rcu_bh(void)
 EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
 
 /**
+ * rcu_bh_trivial_gp - Are RCU-bh grace periods trivially zero cost?
+ *
+ * Returns true if RCU-bh grace periods are currently zero cost, which
+ * they are if there is only one CPU.  Note that unless you take steps to
+ * prevent it, the number of CPUs might change at any time.
+ */
+bool rcu_bh_trivial_gp(void)
+{
+	return rcu_blocking_is_gp();
+}
+
+/**
  * get_state_synchronize_rcu - Snapshot current RCU state
  *
  * Returns a cookie that is used by a later call to cond_synchronize_rcu()
@@ -3477,9 +3630,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	    rdp->core_needs_qs && rdp->cpu_no_qs.b.norm &&
 	    rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) {
 		rdp->n_rp_core_needs_qs++;
-	} else if (rdp->core_needs_qs &&
-		   (!rdp->cpu_no_qs.b.norm ||
-		    rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) {
+	} else if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm) {
 		rdp->n_rp_report_qs++;
 		return 1;
 	}
@@ -3745,7 +3896,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu);
 	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
 	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE);
-	WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
+	WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks)));
 	rdp->cpu = cpu;
 	rdp->rsp = rsp;
 	rcu_boot_init_nocb_percpu_data(rdp);
@@ -3762,7 +3913,6 @@ static void
 rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 {
 	unsigned long flags;
-	unsigned long mask;
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
@@ -3775,8 +3925,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 		init_callback_list(rdp);  /* Re-enable callbacks on this CPU. */
 	rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 	rcu_sysidle_init_percpu_data(rdp->dynticks);
-	atomic_set(&rdp->dynticks->dynticks,
-		   (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1);
+	rcu_dynticks_eqs_online();
 	raw_spin_unlock_rcu_node(rnp);		/* irqs remain disabled. */
 
 	/*
@@ -3785,7 +3934,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	 * of the next grace period.
 	 */
 	rnp = rdp->mynode;
-	mask = rdp->grpmask;
 	raw_spin_lock_rcu_node(rnp);		/* irqs already disabled. */
 	if (!rdp->beenonline)
 		WRITE_ONCE(rsp->ncpus, READ_ONCE(rsp->ncpus) + 1);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index fe98dd24adf8..c0a4bf8f1ed0 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -595,6 +595,9 @@ extern struct rcu_state rcu_bh_state;
 extern struct rcu_state rcu_preempt_state;
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
 
+int rcu_dynticks_snap(struct rcu_dynticks *rdtp);
+bool rcu_eqs_special_set(int cpu);
+
 #ifdef CONFIG_RCU_BOOST
 DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
 DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu);
@@ -688,18 +691,6 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
 #endif /* #ifdef CONFIG_RCU_TRACE */
 
 /*
- * Place this after a lock-acquisition primitive to guarantee that
- * an UNLOCK+LOCK pair act as a full barrier.  This guarantee applies
- * if the UNLOCK and LOCK are executed by the same CPU or if the
- * UNLOCK and LOCK operate on the same lock variable.
- */
-#ifdef CONFIG_PPC
-#define smp_mb__after_unlock_lock()	smp_mb()  /* Full ordering for lock. */
-#else /* #ifdef CONFIG_PPC */
-#define smp_mb__after_unlock_lock()	do { } while (0)
-#endif /* #else #ifdef CONFIG_PPC */
-
-/*
  * Wrappers for the rcu_node::lock acquire and release.
  *
  * Because the rcu_nodes form a tree, the tree traversal locking will observe
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index d3053e99fdb6..a3a8756670d1 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -356,12 +356,11 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 		mask_ofl_test = 0;
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
 			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
-			struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
 
 			rdp->exp_dynticks_snap =
-				atomic_add_return(0, &rdtp->dynticks);
+				rcu_dynticks_snap(rdp->dynticks);
 			if (raw_smp_processor_id() == cpu ||
-			    !(rdp->exp_dynticks_snap & 0x1) ||
+			    rcu_dynticks_in_eqs(rdp->exp_dynticks_snap) ||
 			    !(rnp->qsmaskinitnext & rdp->grpmask))
 				mask_ofl_test |= rdp->grpmask;
 		}
@@ -380,13 +379,12 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
 			unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
 			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
-			struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
 
 			if (!(mask_ofl_ipi & mask))
 				continue;
 retry_ipi:
-			if (atomic_add_return(0, &rdtp->dynticks) !=
-			    rdp->exp_dynticks_snap) {
+			if (rcu_dynticks_in_eqs_since(rdp->dynticks,
+						      rdp->exp_dynticks_snap)) {
 				mask_ofl_test |= mask;
 				continue;
 			}
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 85c5a883c6e3..69c6eb27c37f 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -680,6 +680,17 @@ void synchronize_rcu(void)
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
 /**
+ * rcu_trivial_gp - Are RCU grace periods trivially zero cost?
+ *
+ * Returns true if RCU grace periods are currently zero cost, which
+ * they are during boot.
+ */
+bool rcu_trivial_gp(void)
+{
+	return !rcu_scheduler_active;
+}
+
+/**
  * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete.
  *
  * Note that this primitive does not necessarily wait for an RCU grace period
@@ -1643,7 +1654,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 	       "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
 	       "N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)],
 	       ticks_value, ticks_title,
-	       atomic_read(&rdtp->dynticks) & 0xfff,
+	       rcu_dynticks_snap(rdtp) & 0xfff,
 	       rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting,
 	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
 	       READ_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart,
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index b1f28972872c..b833cd0a29e8 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -124,7 +124,7 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu),
 		   rdp->core_needs_qs);
 	seq_printf(m, " dt=%d/%llx/%d df=%lu",
-		   atomic_read(&rdp->dynticks->dynticks),
+		   rcu_dynticks_snap(rdp->dynticks),
 		   rdp->dynticks->dynticks_nesting,
 		   rdp->dynticks->dynticks_nmi_nesting,
 		   rdp->dynticks_fqs);
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index f19271dce0a9..587c8373f8d8 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -129,8 +129,7 @@ bool rcu_gp_is_normal(void)
 }
 EXPORT_SYMBOL_GPL(rcu_gp_is_normal);
 
-static atomic_t rcu_expedited_nesting =
-	ATOMIC_INIT(IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT) ? 1 : 0);
+static atomic_t rcu_expedited_nesting = ATOMIC_INIT(1);
 
 /*
  * Should normal grace-period primitives be expedited?  Intended for
@@ -178,8 +177,7 @@ EXPORT_SYMBOL_GPL(rcu_unexpedite_gp);
  */
 void rcu_end_inkernel_boot(void)
 {
-	if (IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT))
-		rcu_unexpedite_gp();
+	rcu_unexpedite_gp();
 	if (rcu_normal_after_boot)
 		WRITE_ONCE(rcu_normal, 1);
 }
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 966556ebdbb3..1480faa40497 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4907,6 +4907,7 @@ int __sched _cond_resched(void)
 		preempt_schedule_common();
 		return 1;
 	}
+	rcu_all_qs();
 	return 0;
 }
 EXPORT_SYMBOL(_cond_resched);