Merge branches 'doc.2017.01.15b', 'dyntick.2017.01.23a', 'fixes.2017.01.23a', 'srcu.2017.01.25a' and 'torture.2017.01.15b' into HEAD

doc.2017.01.15b: Documentation updates
dyntick.2017.01.23a: Dyntick tracking consolidation
fixes.2017.01.23a: Miscellaneous fixes
srcu.2017.01.25a: SRCU rewrite, fixes, and verification
torture.2017.01.15b: Torture-test updates

Documentation/RCU/trace.txt

@@ -237,7 +237,7 @@ o	"ktl" is the low-order 16 bits (in hexadecimal) of the count of
 
 The output of "cat rcu/rcu_preempt/rcuexp" looks as follows:
 
-s=21872 wd1=0 wd2=0 wd3=5 n=0 enq=0 sc=21872
+s=21872 wd1=0 wd2=0 wd3=5 enq=0 sc=21872
 
 These fields are as follows:
 
@@ -249,9 +249,6 @@ o	"wd1", "wd2", and "wd3" are the number of times that an attempt
 	completed an expedited grace period that satisfies the attempted
 	request.  "Our work is done."
 
-o	"n" is number of times that a concurrent CPU-hotplug operation
-	forced a fallback to a normal grace period.
-
 o	"enq" is the number of quiescent states still outstanding.
 
 o	"sc" is the number of times that the attempt to start a

include/linux/llist.h

@@ -3,28 +3,33 @@
 /*
  * Lock-less NULL terminated single linked list
  *
- * If there are multiple producers and multiple consumers, llist_add
- * can be used in producers and llist_del_all can be used in
- * consumers.  They can work simultaneously without lock.  But
- * llist_del_first can not be used here.  Because llist_del_first
- * depends on list->first->next does not changed if list->first is not
- * changed during its operation, but llist_del_first, llist_add,
- * llist_add (or llist_del_all, llist_add, llist_add) sequence in
- * another consumer may violate that.
+ * Cases where locking is not needed:
+ * If there are multiple producers and multiple consumers, llist_add can be
+ * used in producers and llist_del_all can be used in consumers simultaneously
+ * without locking. Also a single consumer can use llist_del_first while
+ * multiple producers simultaneously use llist_add, without any locking.
  *
- * If there are multiple producers and one consumer, llist_add can be
- * used in producers and llist_del_all or llist_del_first can be used
- * in the consumer.
+ * Cases where locking is needed:
+ * If we have multiple consumers with llist_del_first used in one consumer, and
+ * llist_del_first or llist_del_all used in other consumers, then a lock is
+ * needed.  This is because llist_del_first depends on list->first->next not
+ * changing, but without lock protection, there's no way to be sure about that
+ * if a preemption happens in the middle of the delete operation and on being
+ * preempted back, the list->first is the same as before causing the cmpxchg in
+ * llist_del_first to succeed. For example, while a llist_del_first operation
+ * is in progress in one consumer, then a llist_del_first, llist_add,
+ * llist_add (or llist_del_all, llist_add, llist_add) sequence in another
+ * consumer may cause violations.
  *
- * This can be summarized as follow:
+ * This can be summarized as follows:
  *
  *           |   add    | del_first |  del_all
  * add       |    -     |     -     |     -
  * del_first |          |     L     |     L
  * del_all   |          |           |     -
  *
- * Where "-" stands for no lock is needed, while "L" stands for lock
- * is needed.
+ * Where, a particular row's operation can happen concurrently with a column's
+ * operation, with "-" being no lock needed, while "L" being lock is needed.
  *
  * The list entries deleted via llist_del_all can be traversed with
  * traversing function such as llist_for_each etc.  But the list

include/linux/rcupdate.h

@@ -1161,5 +1161,17 @@ do { \
 		ftrace_dump(oops_dump_mode); \
 } while (0)
 
+/*
+ * Place this after a lock-acquisition primitive to guarantee that
+ * an UNLOCK+LOCK pair acts 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 */
+
 
 #endif /* __LINUX_RCUPDATE_H */

include/linux/rcutiny.h

@@ -27,6 +27,12 @@
 
 #include <linux/cache.h>
 
+struct rcu_dynticks;
+static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
+{
+	return 0;
+}
+
 static inline unsigned long get_state_synchronize_rcu(void)
 {
 	return 0;

include/linux/srcu.h

@@ -33,9 +33,9 @@
 #include <linux/rcupdate.h>
 #include <linux/workqueue.h>
 
-struct srcu_struct_array {
-	unsigned long c[2];
-	unsigned long seq[2];
+struct srcu_array {
+	unsigned long lock_count[2];
+	unsigned long unlock_count[2];
 };
 
 struct rcu_batch {
@@ -46,7 +46,7 @@ struct rcu_batch {
 
 struct srcu_struct {
 	unsigned long completed;
-	struct srcu_struct_array __percpu *per_cpu_ref;
+	struct srcu_array __percpu *per_cpu_ref;
 	spinlock_t queue_lock; /* protect ->batch_queue, ->running */
 	bool running;
 	/* callbacks just queued */
@@ -118,7 +118,7 @@ void process_srcu(struct work_struct *work);
  * See include/linux/percpu-defs.h for the rules on per-CPU variables.
  */
 #define __DEFINE_SRCU(name, is_static)					\
-	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
+	static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\
 	is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
 #define DEFINE_SRCU(name)		__DEFINE_SRCU(name, /* not static */)
 #define DEFINE_STATIC_SRCU(name)	__DEFINE_SRCU(name, static)

include/trace/events/rcu.h

@@ -385,11 +385,11 @@ TRACE_EVENT(rcu_quiescent_state_report,
 
 /*
  * Tracepoint for quiescent states detected by force_quiescent_state().
- * These trace events include the type of RCU, the grace-period number
- * that was blocked by the CPU, the CPU itself, and the type of quiescent
- * state, which can be "dti" for dyntick-idle mode, "ofl" for CPU offline,
- * or "kick" when kicking a CPU that has been in dyntick-idle mode for
- * too long.
+ * These trace events include the type of RCU, the grace-period number that
+ * was blocked by the CPU, the CPU itself, and the type of quiescent state,
+ * which can be "dti" for dyntick-idle mode, "ofl" for CPU offline, "kick"
+ * when kicking a CPU that has been in dyntick-idle mode for too long, or
+ * "rqc" if the CPU got a quiescent state via its rcu_qs_ctr.
  */
 TRACE_EVENT(rcu_fqs,
 

init/Kconfig

@@ -529,7 +529,6 @@ config SRCU
 config TASKS_RCU
 	bool
 	default n
-	depends on !UML
 	select SRCU
 	help
 	  This option enables a task-based RCU implementation that uses
@@ -781,19 +780,6 @@ config RCU_NOCB_CPU_ALL
 
 endchoice
 
-config RCU_EXPEDITE_BOOT
-	bool
-	default n
-	help
-	  This option enables expedited grace periods at boot time,
-	  as if rcu_expedite_gp() had been invoked early in boot.
-	  The corresponding rcu_unexpedite_gp() is invoked from
-	  rcu_end_inkernel_boot(), which is intended to be invoked
-	  at the end of the kernel-only boot sequence, just before
-	  init is exec'ed.
-
-	  Accept the default if unsure.
-
 endmenu # "RCU Subsystem"
 
 config BUILD_BIN2C

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("[ 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()

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;
 		}

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) {

kernel/rcu/rcutorture.c

@@ -564,10 +564,25 @@ 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_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 = l0 - u0;
+		c1 = l1 - u1;
 		pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
 	}
 	pr_cont("\n");

kernel/rcu/srcu.c

@@ -106,7 +106,7 @@ static int init_srcu_struct_fields(struct srcu_struct *sp)
 	rcu_batch_init(&sp->batch_check1);
 	rcu_batch_init(&sp->batch_done);
 	INIT_DELAYED_WORK(&sp->work, process_srcu);
-	sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array);
+	sp->per_cpu_ref = alloc_percpu(struct srcu_array);
 	return sp->per_cpu_ref ? 0 : -ENOMEM;
 }
 
@@ -141,114 +141,77 @@ 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]);
-		sum += t;
+		struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu);
+
+		sum += READ_ONCE(cpuc->lock_count[idx]);
 	}
 	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]);
-		sum += t;
+		struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu);
+
+		sum += READ_ONCE(cpuc->unlock_count[idx]);
 	}
 	return sum;
 }
 
 /*
  * 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 accesses 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 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 not have incremented the lock counter yet.
 	 *
-	 * We therefore do a validation step should srcu_readers_active_idx()
-	 * return zero.
+	 * Possible bug: There is no guarantee that there haven't been ULONG_MAX
+	 * increments of ->lock_count[] since the unlocks were counted, meaning
+	 * that this could return true even if there are still active readers.
+	 * Since there are no memory barriers around srcu_flip(), the CPU is not
+	 * required to increment ->completed before running
+	 * srcu_readers_unlock_idx(), which means that there could be an
+	 * arbitrarily large number of critical sections that execute after
+	 * srcu_readers_unlock_idx() but use the old value of ->completed.
 	 */
-	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 +229,12 @@ 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_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu);
+
+		sum += READ_ONCE(cpuc->lock_count[0]);
+		sum += READ_ONCE(cpuc->lock_count[1]);
+		sum -= READ_ONCE(cpuc->unlock_count[0]);
+		sum -= READ_ONCE(cpuc->unlock_count[1]);
 	}
 	return sum;
 }
@@ -298,9 +265,8 @@ 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 +280,7 @@ 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);
 
@@ -349,12 +315,21 @@ 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)
 {
-	sp->completed++;
+	WRITE_ONCE(sp->completed, sp->completed + 1);
+
+	/*
+	 * Ensure that if the updater misses an __srcu_read_unlock()
+	 * increment, that task's next __srcu_read_lock() will see the
+	 * above counter update.  Note that both this memory barrier
+	 * and the one in srcu_readers_active_idx_check() provide the
+	 * guarantee for __srcu_read_lock().
+	 */
+	smp_mb(); /* D */  /* Pairs with C. */
 }
 
 /*
@@ -392,6 +367,7 @@ 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 +401,7 @@ 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;
@@ -444,8 +421,11 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
 		spin_unlock_irq(&sp->queue_lock);
 	}
 
-	if (!done)
+	if (!done) {
 		wait_for_completion(&rcu.completion);
+		smp_mb(); /* Caller's later accesses after GP. */
+	}
+
 }
 
 /**
@@ -613,7 +593,8 @@ static void srcu_advance_batches(struct srcu_struct *sp, int trycount)
 /*
  * Invoke a limited number of SRCU callbacks that have passed through
  * their grace period.  If there are more to do, SRCU will reschedule
- * the workqueue.
+ * the workqueue.  Note that needed memory barriers have been executed
+ * in this task's context by srcu_readers_active_idx_check().
  */
 static void srcu_invoke_callbacks(struct srcu_struct *sp)
 {

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);

kernel/rcu/tree.c

@@ -281,6 +281,116 @@ static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 #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 special;
+
+	/*
+	 * CPUs seeing atomic_inc_return() must see prior RCU read-side
+	 * critical sections, and we also must force ordering with the
+	 * next idle sojourn.
+	 */
+	special = atomic_inc_return(&rdtp->dynticks);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && special & 0x1);
+}
+
+/*
+ * 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 special;
+
+	/*
+	 * CPUs seeing atomic_inc_return() must see prior idle sojourns,
+	 * and we also must force ordering with the next RCU read-side
+	 * critical section.
+	 */
+	special = atomic_inc_return(&rdtp->dynticks);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(special & 0x1));
+}
+
+/*
+ * 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) & 0x1)
+		return;
+	atomic_add(0x1, &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) & 0x1);
+}
+
+/*
+ * 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;
+}
+
+/*
+ * 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 & 0x1);
+}
+
+/*
+ * 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, &rdtp->dynticks);
+
+	/* It is illegal to call this from idle state. */
+	WARN_ON_ONCE(!(special & 0x1));
+}
+
 DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
 EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr);
 
@@ -300,7 +410,6 @@ 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;
 
@@ -327,10 +436,7 @@ 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;
 	}
 }
@@ -611,7 +717,7 @@ static int
 cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
 {
 	return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL] &&
-	       rdp->nxttail[RCU_DONE_TAIL] != NULL;
+	       rdp->nxttail[RCU_NEXT_TAIL] != NULL;
 }
 
 /*
@@ -673,7 +779,7 @@ 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);
+	RCU_TRACE(struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);)
 
 	trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
 	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
@@ -692,12 +798,7 @@ 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();
 
 	/*
@@ -826,15 +927,10 @@ 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);
+	RCU_TRACE(struct rcu_dynticks *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) &&
@@ -980,12 +1076,8 @@ 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;
@@ -1010,7 +1102,7 @@ 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
@@ -1023,11 +1115,7 @@ 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();
 }
 
 /**
@@ -1040,7 +1128,7 @@ 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();
 }
 
 /**
@@ -1123,9 +1211,9 @@ 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))
@@ -1144,12 +1232,10 @@ 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;
+	unsigned long jtsq;
 	int *rcrmp;
-	unsigned int snap;
-
-	curr = (unsigned int)atomic_add_return(0, &rdp->dynticks->dynticks);
-	snap = (unsigned int)rdp->dynticks_snap;
+	unsigned long rjtsc;
+	struct rcu_node *rnp;
 
 	/*
 	 * If the CPU passed through or entered a dynticks idle phase with
@@ -1159,27 +1245,39 @@ 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;
 	}
 
+	/* Compute and saturate jiffies_till_sched_qs. */
+	jtsq = jiffies_till_sched_qs;
+	rjtsc = rcu_jiffies_till_stall_check();
+	if (jtsq > rjtsc / 2) {
+		WRITE_ONCE(jiffies_till_sched_qs, rjtsc);
+		jtsq = rjtsc / 2;
+	} else if (jtsq < 1) {
+		WRITE_ONCE(jiffies_till_sched_qs, 1);
+		jtsq = 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 (time_after(jiffies, rdp->rsp->gp_start + jtsq) &&
+	    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;
@@ -1207,9 +1305,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 	 * warning delay.
 	 */
 	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)) {
+	if (time_after(jiffies, rdp->rsp->gp_start + jtsq) ||
+	    time_after(jiffies, rdp->rsp->jiffies_resched)) {
 		if (!(READ_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
 			WRITE_ONCE(rdp->cond_resched_completed,
 				   READ_ONCE(rdp->mynode->completed));
@@ -1220,11 +1317,12 @@ 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;
 }
@@ -1277,7 +1375,10 @@ 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)
 {
@@ -1287,11 +1388,10 @@ 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);
 	}
 }
@@ -1379,6 +1479,9 @@ 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) {
@@ -1395,9 +1498,6 @@ 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();
@@ -2467,10 +2567,8 @@ 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
@@ -2525,8 +2623,7 @@ 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;
 
 	/*
@@ -3480,9 +3577,7 @@ 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;
 	}
@@ -3748,7 +3843,7 @@ 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);
@@ -3765,7 +3860,6 @@ 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);
 
@@ -3778,8 +3872,7 @@ 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. */
 
 	/*
@@ -3788,7 +3881,6 @@ 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);
@@ -3872,7 +3964,7 @@ void rcu_cpu_starting(unsigned int cpu)
 	struct rcu_state *rsp;
 
 	for_each_rcu_flavor(rsp) {
-		rdp = this_cpu_ptr(rsp->rda);
+		rdp = per_cpu_ptr(rsp->rda, cpu);
 		rnp = rdp->mynode;
 		mask = rdp->grpmask;
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);

kernel/rcu/tree.h

@@ -521,7 +521,6 @@ struct rcu_state {
 	struct mutex exp_mutex;			/* Serialize expedited GP. */
 	struct mutex exp_wake_mutex;		/* Serialize wakeup. */
 	unsigned long expedited_sequence;	/* Take a ticket. */
-	atomic_long_t expedited_normal;		/* # fallbacks to normal. */
 	atomic_t expedited_need_qs;		/* # CPUs left to check in. */
 	struct swait_queue_head expedited_wq;	/* Wait for check-ins. */
 	int ncpus_snap;				/* # CPUs seen last time. */
@@ -595,6 +594,8 @@ 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);
+
 #ifdef CONFIG_RCU_BOOST
 DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
 DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu);
@@ -687,18 +688,6 @@ 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.
  *

kernel/rcu/tree_exp.h

@@ -20,16 +20,26 @@
  * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
  */
 
-/* Wrapper functions for expedited grace periods.  */
+/*
+ * Record the start of an expedited grace period.
+ */
 static void rcu_exp_gp_seq_start(struct rcu_state *rsp)
 {
 	rcu_seq_start(&rsp->expedited_sequence);
 }
+
+/*
+ * Record the end of an expedited grace period.
+ */
 static void rcu_exp_gp_seq_end(struct rcu_state *rsp)
 {
 	rcu_seq_end(&rsp->expedited_sequence);
 	smp_mb(); /* Ensure that consecutive grace periods serialize. */
 }
+
+/*
+ * Take a snapshot of the expedited-grace-period counter.
+ */
 static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp)
 {
 	unsigned long s;
@@ -39,6 +49,12 @@ static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp)
 	trace_rcu_exp_grace_period(rsp->name, s, TPS("snap"));
 	return s;
 }
+
+/*
+ * Given a counter snapshot from rcu_exp_gp_seq_snap(), return true
+ * if a full expedited grace period has elapsed since that snapshot
+ * was taken.
+ */
 static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s)
 {
 	return rcu_seq_done(&rsp->expedited_sequence, s);
@@ -356,12 +372,11 @@ 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 +395,12 @@ 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;
 			}
@@ -623,6 +637,11 @@ void synchronize_sched_expedited(void)
 {
 	struct rcu_state *rsp = &rcu_sched_state;
 
+	RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
+			 lock_is_held(&rcu_lock_map) ||
+			 lock_is_held(&rcu_sched_lock_map),
+			 "Illegal synchronize_sched_expedited() in RCU read-side critical section");
+
 	/* If only one CPU, this is automatically a grace period. */
 	if (rcu_blocking_is_gp())
 		return;
@@ -692,6 +711,11 @@ void synchronize_rcu_expedited(void)
 {
 	struct rcu_state *rsp = rcu_state_p;
 
+	RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
+			 lock_is_held(&rcu_lock_map) ||
+			 lock_is_held(&rcu_sched_lock_map),
+			 "Illegal synchronize_rcu_expedited() in RCU read-side critical section");
+
 	if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
 		return;
 	_synchronize_rcu_expedited(rsp, sync_rcu_exp_handler);

kernel/rcu/tree_plugin.h

@@ -1643,7 +1643,7 @@ 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,
@@ -2366,8 +2366,9 @@ static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp)
 	}
 
 	/*
-	 * Each pass through this loop sets up one rcu_data structure and
-	 * spawns one rcu_nocb_kthread().
+	 * Each pass through this loop sets up one rcu_data structure.
+	 * Should the corresponding CPU come online in the future, then
+	 * we will spawn the needed set of rcu_nocb_kthread() kthreads.
 	 */
 	for_each_cpu(cpu, rcu_nocb_mask) {
 		rdp = per_cpu_ptr(rsp->rda, cpu);

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);
@@ -194,9 +194,8 @@ static int show_rcuexp(struct seq_file *m, void *v)
 		s2 += atomic_long_read(&rdp->exp_workdone2);
 		s3 += atomic_long_read(&rdp->exp_workdone3);
 	}
-	seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n",
+	seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu enq=%d sc=%lu\n",
 		   rsp->expedited_sequence, s0, s1, s2, s3,
-		   atomic_long_read(&rsp->expedited_normal),
 		   atomic_read(&rsp->expedited_need_qs),
 		   rsp->expedited_sequence / 2);
 	return 0;

kernel/rcu/update.c

@@ -132,8 +132,7 @@ 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
@@ -182,8 +181,7 @@ 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);
 }

lib/Kconfig.debug

@@ -1450,6 +1450,7 @@ config RCU_CPU_STALL_TIMEOUT
 config RCU_TRACE
 	bool "Enable tracing for RCU"
 	depends on DEBUG_KERNEL
+	default y if TREE_RCU
 	select TRACE_CLOCK
 	help
 	  This option provides tracing in RCU which presents stats