Merge branches 'barrier.2012.05.09a', 'fixes.2012.04.26a', 'inline.2012.05.02b' and 'srcu.2012.05.07b' into HEAD

barrier:  Reduce the amount of disturbance by rcu_barrier() to the rest of
    	the system.  This branch also includes improvements to
    	RCU_FAST_NO_HZ, which are included here due to conflicts.
fixes:  Miscellaneous fixes.
inline:  Remaining changes from an abortive attempt to inline
    	preemptible RCU's __rcu_read_lock().  These are (1) making
    	exit_rcu() avoid unnecessary work and (2) avoiding having
    	preemptible RCU record a blocked thread when the scheduler
    	declines to do a context switch.
srcu:	Lai Jiangshan's algorithmic implementation of SRCU, including
    	call_srcu().

Documentation/RCU/torture.txt

@@ -47,6 +47,16 @@ irqreader	Says to invoke RCU readers from irq level.  This is currently
 		permit this.  (Or, more accurately, variants of RCU that do
 		-not- permit this know to ignore this variable.)
 
+n_barrier_cbs	If this is nonzero, RCU barrier testing will be conducted,
+		in which case n_barrier_cbs specifies the number of
+		RCU callbacks (and corresponding kthreads) to use for
+		this testing.  The value cannot be negative.  If you
+		specify this to be non-zero when torture_type indicates a
+		synchronous RCU implementation (one for which a member of
+		the synchronize_rcu() rather than the call_rcu() family is
+		used -- see the documentation for torture_type below), an
+		error will be reported and no testing will be carried out.
+
 nfakewriters	This is the number of RCU fake writer threads to run.  Fake
 		writer threads repeatedly use the synchronous "wait for
 		current readers" function of the interface selected by
@@ -188,7 +198,7 @@ OUTPUT
 The statistics output is as follows:
 
 	rcu-torture:--- Start of test: nreaders=16 nfakewriters=4 stat_interval=30 verbose=0 test_no_idle_hz=1 shuffle_interval=3 stutter=5 irqreader=1 fqs_duration=0 fqs_holdoff=0 fqs_stutter=3 test_boost=1/0 test_boost_interval=7 test_boost_duration=4
-	rcu-torture: rtc:           (null) ver: 155441 tfle: 0 rta: 155441 rtaf: 8884 rtf: 155440 rtmbe: 0 rtbke: 0 rtbre: 0 rtbf: 0 rtb: 0 nt: 3055767
+	rcu-torture: rtc:           (null) ver: 155441 tfle: 0 rta: 155441 rtaf: 8884 rtf: 155440 rtmbe: 0 rtbe: 0 rtbke: 0 rtbre: 0 rtbf: 0 rtb: 0 nt: 3055767
 	rcu-torture: Reader Pipe:  727860534 34213 0 0 0 0 0 0 0 0 0
 	rcu-torture: Reader Batch:  727877838 17003 0 0 0 0 0 0 0 0 0
 	rcu-torture: Free-Block Circulation:  155440 155440 155440 155440 155440 155440 155440 155440 155440 155440 0
@@ -230,6 +240,9 @@ o	"rtmbe": A non-zero value indicates that rcutorture believes that
 	rcu_assign_pointer() and rcu_dereference() are not working
 	correctly.  This value should be zero.
 
+o	"rtbe": A non-zero value indicates that one of the rcu_barrier()
+	family of functions is not working correctly.
+
 o	"rtbke": rcutorture was unable to create the real-time kthreads
 	used to force RCU priority inversion.  This value should be zero.
 

Documentation/kernel-parameters.txt

@@ -2330,18 +2330,100 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	ramdisk_size=	[RAM] Sizes of RAM disks in kilobytes
 			See Documentation/blockdev/ramdisk.txt.
 
-	rcupdate.blimit=	[KNL,BOOT]
+	rcutree.blimit=	[KNL,BOOT]
 			Set maximum number of finished RCU callbacks to process
 			in one batch.
 
-	rcupdate.qhimark=	[KNL,BOOT]
+	rcutree.qhimark=	[KNL,BOOT]
 			Set threshold of queued
 			RCU callbacks over which batch limiting is disabled.
 
-	rcupdate.qlowmark=	[KNL,BOOT]
+	rcutree.qlowmark=	[KNL,BOOT]
 			Set threshold of queued RCU callbacks below which
 			batch limiting is re-enabled.
 
+	rcutree.rcu_cpu_stall_suppress=	[KNL,BOOT]
+			Suppress RCU CPU stall warning messages.
+
+	rcutree.rcu_cpu_stall_timeout= [KNL,BOOT]
+			Set timeout for RCU CPU stall warning messages.
+
+	rcutorture.fqs_duration= [KNL,BOOT]
+			Set duration of force_quiescent_state bursts.
+
+	rcutorture.fqs_holdoff= [KNL,BOOT]
+			Set holdoff time within force_quiescent_state bursts.
+
+	rcutorture.fqs_stutter= [KNL,BOOT]
+			Set wait time between force_quiescent_state bursts.
+
+	rcutorture.irqreader= [KNL,BOOT]
+			Test RCU readers from irq handlers.
+
+	rcutorture.n_barrier_cbs= [KNL,BOOT]
+			Set callbacks/threads for rcu_barrier() testing.
+
+	rcutorture.nfakewriters= [KNL,BOOT]
+			Set number of concurrent RCU writers.  These just
+			stress RCU, they don't participate in the actual
+			test, hence the "fake".
+
+	rcutorture.nreaders= [KNL,BOOT]
+			Set number of RCU readers.
+
+	rcutorture.onoff_holdoff= [KNL,BOOT]
+			Set time (s) after boot for CPU-hotplug testing.
+
+	rcutorture.onoff_interval= [KNL,BOOT]
+			Set time (s) between CPU-hotplug operations, or
+			zero to disable CPU-hotplug testing.
+
+	rcutorture.shuffle_interval= [KNL,BOOT]
+			Set task-shuffle interval (s).  Shuffling tasks
+			allows some CPUs to go into dyntick-idle mode
+			during the rcutorture test.
+
+	rcutorture.shutdown_secs= [KNL,BOOT]
+			Set time (s) after boot system shutdown.  This
+			is useful for hands-off automated testing.
+
+	rcutorture.stall_cpu= [KNL,BOOT]
+			Duration of CPU stall (s) to test RCU CPU stall
+			warnings, zero to disable.
+
+	rcutorture.stall_cpu_holdoff= [KNL,BOOT]
+			Time to wait (s) after boot before inducing stall.
+
+	rcutorture.stat_interval= [KNL,BOOT]
+			Time (s) between statistics printk()s.
+
+	rcutorture.stutter= [KNL,BOOT]
+			Time (s) to stutter testing, for example, specifying
+			five seconds causes the test to run for five seconds,
+			wait for five seconds, and so on.  This tests RCU's
+			ability to transition abruptly to and from idle.
+
+	rcutorture.test_boost= [KNL,BOOT]
+			Test RCU priority boosting?  0=no, 1=maybe, 2=yes.
+			"Maybe" means test if the RCU implementation
+			under test support RCU priority boosting.
+
+	rcutorture.test_boost_duration= [KNL,BOOT]
+			Duration (s) of each individual boost test.
+
+	rcutorture.test_boost_interval= [KNL,BOOT]
+			Interval (s) between each boost test.
+
+	rcutorture.test_no_idle_hz= [KNL,BOOT]
+			Test RCU's dyntick-idle handling.  See also the
+			rcutorture.shuffle_interval parameter.
+
+	rcutorture.torture_type= [KNL,BOOT]
+			Specify the RCU implementation to test.
+
+	rcutorture.verbose= [KNL,BOOT]
+			Enable additional printk() statements.
+
 	rdinit=		[KNL]
 			Format: <full_path>
 			Run specified binary instead of /init from the ramdisk,

MAINTAINERS

@@ -5607,14 +5607,13 @@ F:	net/rds/
 READ-COPY UPDATE (RCU)
 M:	Dipankar Sarma <dipankar@in.ibm.com>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
-W:	http://www.rdrop.com/users/paulmck/rclock/
+W:	http://www.rdrop.com/users/paulmck/RCU/
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	Documentation/RCU/
+X:	Documentation/RCU/torture.txt
 F:	include/linux/rcu*
-F:	include/linux/srcu*
 F:	kernel/rcu*
-F:	kernel/srcu*
 X:	kernel/rcutorture.c
 
 REAL TIME CLOCK (RTC) SUBSYSTEM
@@ -6131,6 +6130,15 @@ S:	Maintained
 F:	include/linux/sl?b*.h
 F:	mm/sl?b.c
 
+SLEEPABLE READ-COPY UPDATE (SRCU)
+M:	Lai Jiangshan <laijs@cn.fujitsu.com>
+M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
+W:	http://www.rdrop.com/users/paulmck/RCU/
+S:	Supported
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+F:	include/linux/srcu*
+F:	kernel/srcu*
+
 SMC91x ETHERNET DRIVER
 M:	Nicolas Pitre <nico@fluxnic.net>
 S:	Odd Fixes

arch/um/drivers/mconsole_kern.c

@@ -705,6 +705,7 @@ static void stack_proc(void *arg)
 	struct task_struct *from = current, *to = arg;
 
 	to->thread.saved_task = from;
+	rcu_switch_from(from);
 	switch_to(from, to, from);
 }
 

include/linux/rculist.h

@@ -30,6 +30,7 @@
  * This is only for internal list manipulation where we know
  * the prev/next entries already!
  */
+#ifndef CONFIG_DEBUG_LIST
 static inline void __list_add_rcu(struct list_head *new,
 		struct list_head *prev, struct list_head *next)
 {
@@ -38,6 +39,10 @@ static inline void __list_add_rcu(struct list_head *new,
 	rcu_assign_pointer(list_next_rcu(prev), new);
 	next->prev = new;
 }
+#else
+extern void __list_add_rcu(struct list_head *new,
+		struct list_head *prev, struct list_head *next);
+#endif
 
 /**
  * list_add_rcu - add a new entry to rcu-protected list
@@ -108,7 +113,7 @@ static inline void list_add_tail_rcu(struct list_head *new,
  */
 static inline void list_del_rcu(struct list_head *entry)
 {
-	__list_del(entry->prev, entry->next);
+	__list_del_entry(entry);
 	entry->prev = LIST_POISON2;
 }
 
@@ -228,18 +233,43 @@ static inline void list_splice_init_rcu(struct list_head *list,
 	})
 
 /**
- * list_first_entry_rcu - get the first element from a list
+ * Where are list_empty_rcu() and list_first_entry_rcu()?
+ *
+ * Implementing those functions following their counterparts list_empty() and
+ * list_first_entry() is not advisable because they lead to subtle race
+ * conditions as the following snippet shows:
+ *
+ * if (!list_empty_rcu(mylist)) {
+ *	struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member);
+ *	do_something(bar);
+ * }
+ *
+ * The list may not be empty when list_empty_rcu checks it, but it may be when
+ * list_first_entry_rcu rereads the ->next pointer.
+ *
+ * Rereading the ->next pointer is not a problem for list_empty() and
+ * list_first_entry() because they would be protected by a lock that blocks
+ * writers.
+ *
+ * See list_first_or_null_rcu for an alternative.
+ */
+
+/**
+ * list_first_or_null_rcu - get the first element from a list
  * @ptr:        the list head to take the element from.
  * @type:       the type of the struct this is embedded in.
  * @member:     the name of the list_struct within the struct.
  *
- * Note, that list is expected to be not empty.
+ * Note that if the list is empty, it returns NULL.
  *
  * This primitive may safely run concurrently with the _rcu list-mutation
  * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
  */
-#define list_first_entry_rcu(ptr, type, member) \
+#define list_first_or_null_rcu(ptr, type, member) \
-	list_entry_rcu((ptr)->next, type, member)
+	({struct list_head *__ptr = (ptr); \
+	  struct list_head __rcu *__next = list_next_rcu(__ptr); \
+	  likely(__ptr != __next) ? container_of(__next, type, member) : NULL; \
+	})
 
 /**
  * list_for_each_entry_rcu	-	iterate over rcu list of given type

include/linux/rcupdate.h

@@ -184,12 +184,14 @@ static inline int rcu_preempt_depth(void)
 /* Internal to kernel */
 extern void rcu_sched_qs(int cpu);
 extern void rcu_bh_qs(int cpu);
+extern void rcu_preempt_note_context_switch(void);
 extern void rcu_check_callbacks(int cpu, int user);
 struct notifier_block;
 extern void rcu_idle_enter(void);
 extern void rcu_idle_exit(void);
 extern void rcu_irq_enter(void);
 extern void rcu_irq_exit(void);
+extern void exit_rcu(void);
 
 /**
  * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers
@@ -922,6 +924,21 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset)
 	kfree_call_rcu(head, (rcu_callback)offset);
 }
 
+/*
+ * Does the specified offset indicate that the corresponding rcu_head
+ * structure can be handled by kfree_rcu()?
+ */
+#define __is_kfree_rcu_offset(offset) ((offset) < 4096)
+
+/*
+ * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain.
+ */
+#define __kfree_rcu(head, offset) \
+	do { \
+		BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \
+		call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \
+	} while (0)
+
 /**
  * kfree_rcu() - kfree an object after a grace period.
  * @ptr:	pointer to kfree
@@ -944,6 +961,9 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset)
  *
  * Note that the allowable offset might decrease in the future, for example,
  * to allow something like kmem_cache_free_rcu().
+ *
+ * The BUILD_BUG_ON check must not involve any function calls, hence the
+ * checks are done in macros here.
  */
 #define kfree_rcu(ptr, rcu_head)					\
 	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))

include/linux/rcutiny.h

@@ -87,14 +87,6 @@ static inline void kfree_call_rcu(struct rcu_head *head,
 
 #ifdef CONFIG_TINY_RCU
 
-static inline void rcu_preempt_note_context_switch(void)
-{
-}
-
-static inline void exit_rcu(void)
-{
-}
-
 static inline int rcu_needs_cpu(int cpu)
 {
 	return 0;
@@ -102,8 +94,6 @@ static inline int rcu_needs_cpu(int cpu)
 
 #else /* #ifdef CONFIG_TINY_RCU */
 
-void rcu_preempt_note_context_switch(void);
-extern void exit_rcu(void);
 int rcu_preempt_needs_cpu(void);
 
 static inline int rcu_needs_cpu(int cpu)
@@ -116,7 +106,6 @@ static inline int rcu_needs_cpu(int cpu)
 static inline void rcu_note_context_switch(int cpu)
 {
 	rcu_sched_qs(cpu);
-	rcu_preempt_note_context_switch();
 }
 
 /*

include/linux/rcutree.h

@@ -45,18 +45,6 @@ static inline void rcu_virt_note_context_switch(int cpu)
 	rcu_note_context_switch(cpu);
 }
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
-
-extern void exit_rcu(void);
-
-#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-
-static inline void exit_rcu(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
-
 extern void synchronize_rcu_bh(void);
 extern void synchronize_sched_expedited(void);
 extern void synchronize_rcu_expedited(void);
@@ -98,13 +86,6 @@ extern void rcu_force_quiescent_state(void);
 extern void rcu_bh_force_quiescent_state(void);
 extern void rcu_sched_force_quiescent_state(void);
 
-/* A context switch is a grace period for RCU-sched and RCU-bh. */
-static inline int rcu_blocking_is_gp(void)
-{
-	might_sleep();  /* Check for RCU read-side critical section. */
-	return num_online_cpus() == 1;
-}
-
 extern void rcu_scheduler_starting(void);
 extern int rcu_scheduler_active __read_mostly;
 

include/linux/sched.h

@@ -1905,12 +1905,22 @@ static inline void rcu_copy_process(struct task_struct *p)
 	INIT_LIST_HEAD(&p->rcu_node_entry);
 }
 
+static inline void rcu_switch_from(struct task_struct *prev)
+{
+	if (prev->rcu_read_lock_nesting != 0)
+		rcu_preempt_note_context_switch();
+}
+
 #else
 
 static inline void rcu_copy_process(struct task_struct *p)
 {
 }
 
+static inline void rcu_switch_from(struct task_struct *prev)
+{
+}
+
 #endif
 
 #ifdef CONFIG_SMP

include/linux/srcu.h

@@ -29,26 +29,35 @@
 
 #include <linux/mutex.h>
 #include <linux/rcupdate.h>
+#include <linux/workqueue.h>
 
 struct srcu_struct_array {
-	int c[2];
+	unsigned long c[2];
+	unsigned long seq[2];
+};
+
+struct rcu_batch {
+	struct rcu_head *head, **tail;
 };
 
 struct srcu_struct {
-	int completed;
+	unsigned completed;
 	struct srcu_struct_array __percpu *per_cpu_ref;
-	struct mutex mutex;
+	spinlock_t queue_lock; /* protect ->batch_queue, ->running */
+	bool running;
+	/* callbacks just queued */
+	struct rcu_batch batch_queue;
+	/* callbacks try to do the first check_zero */
+	struct rcu_batch batch_check0;
+	/* callbacks done with the first check_zero and the flip */
+	struct rcu_batch batch_check1;
+	struct rcu_batch batch_done;
+	struct delayed_work work;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map dep_map;
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 };
 
-#ifndef CONFIG_PREEMPT
-#define srcu_barrier() barrier()
-#else /* #ifndef CONFIG_PREEMPT */
-#define srcu_barrier()
-#endif /* #else #ifndef CONFIG_PREEMPT */
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 int __init_srcu_struct(struct srcu_struct *sp, const char *name,
@@ -67,12 +76,33 @@ int init_srcu_struct(struct srcu_struct *sp);
 
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
+/**
+ * call_srcu() - Queue a callback for invocation after an SRCU grace period
+ * @sp: srcu_struct in queue the callback
+ * @head: structure to be used for queueing the SRCU callback.
+ * @func: function to be invoked after the SRCU grace period
+ *
+ * The callback function will be invoked some time after a full SRCU
+ * grace period elapses, in other words after all pre-existing SRCU
+ * read-side critical sections have completed.  However, the callback
+ * function might well execute concurrently with other SRCU read-side
+ * critical sections that started after call_srcu() was invoked.  SRCU
+ * read-side critical sections are delimited by srcu_read_lock() and
+ * srcu_read_unlock(), and may be nested.
+ *
+ * The callback will be invoked from process context, but must nevertheless
+ * be fast and must not block.
+ */
+void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
+		void (*func)(struct rcu_head *head));
+
 void cleanup_srcu_struct(struct srcu_struct *sp);
 int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
 void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
 void synchronize_srcu(struct srcu_struct *sp);
 void synchronize_srcu_expedited(struct srcu_struct *sp);
 long srcu_batches_completed(struct srcu_struct *sp);
+void srcu_barrier(struct srcu_struct *sp);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 

init/Kconfig

@@ -458,6 +458,33 @@ config RCU_FANOUT
 	  Select a specific number if testing RCU itself.
 	  Take the default if unsure.
 
+config RCU_FANOUT_LEAF
+	int "Tree-based hierarchical RCU leaf-level fanout value"
+	range 2 RCU_FANOUT if 64BIT
+	range 2 RCU_FANOUT if !64BIT
+	depends on TREE_RCU || TREE_PREEMPT_RCU
+	default 16
+	help
+	  This option controls the leaf-level fanout of hierarchical
+	  implementations of RCU, and allows trading off cache misses
+	  against lock contention.  Systems that synchronize their
+	  scheduling-clock interrupts for energy-efficiency reasons will
+	  want the default because the smaller leaf-level fanout keeps
+	  lock contention levels acceptably low.  Very large systems
+	  (hundreds or thousands of CPUs) will instead want to set this
+	  value to the maximum value possible in order to reduce the
+	  number of cache misses incurred during RCU's grace-period
+	  initialization.  These systems tend to run CPU-bound, and thus
+	  are not helped by synchronized interrupts, and thus tend to
+	  skew them, which reduces lock contention enough that large
+	  leaf-level fanouts work well.
+
+	  Select a specific number if testing RCU itself.
+
+	  Select the maximum permissible value for large systems.
+
+	  Take the default if unsure.
+
 config RCU_FANOUT_EXACT
 	bool "Disable tree-based hierarchical RCU auto-balancing"
 	depends on TREE_RCU || TREE_PREEMPT_RCU
@@ -515,10 +542,25 @@ config RCU_BOOST_PRIO
 	depends on RCU_BOOST
 	default 1
 	help
-	  This option specifies the real-time priority to which preempted
+	  This option specifies the real-time priority to which long-term
-	  RCU readers are to be boosted.  If you are working with CPU-bound
+	  preempted RCU readers are to be boosted.  If you are working
-	  real-time applications, you should specify a priority higher then
+	  with a real-time application that has one or more CPU-bound
-	  the highest-priority CPU-bound application.
+	  threads running at a real-time priority level, you should set
+	  RCU_BOOST_PRIO to a priority higher then the highest-priority
+	  real-time CPU-bound thread.  The default RCU_BOOST_PRIO value
+	  of 1 is appropriate in the common case, which is real-time
+	  applications that do not have any CPU-bound threads.
+
+	  Some real-time applications might not have a single real-time
+	  thread that saturates a given CPU, but instead might have
+	  multiple real-time threads that, taken together, fully utilize
+	  that CPU.  In this case, you should set RCU_BOOST_PRIO to
+	  a priority higher than the lowest-priority thread that is
+	  conspiring to prevent the CPU from running any non-real-time
+	  tasks.  For example, if one thread at priority 10 and another
+	  thread at priority 5 are between themselves fully consuming
+	  the CPU time on a given CPU, then RCU_BOOST_PRIO should be
+	  set to priority 6 or higher.
 
 	  Specify the real-time priority, or take the default if unsure.
 

kernel/rcupdate.c

@@ -51,6 +51,34 @@
 
 #include "rcu.h"
 
+#ifdef CONFIG_PREEMPT_RCU
+
+/*
+ * Check for a task exiting while in a preemptible-RCU read-side
+ * critical section, clean up if so.  No need to issue warnings,
+ * as debug_check_no_locks_held() already does this if lockdep
+ * is enabled.
+ */
+void exit_rcu(void)
+{
+	struct task_struct *t = current;
+
+	if (likely(list_empty(&current->rcu_node_entry)))
+		return;
+	t->rcu_read_lock_nesting = 1;
+	barrier();
+	t->rcu_read_unlock_special = RCU_READ_UNLOCK_BLOCKED;
+	__rcu_read_unlock();
+}
+
+#else /* #ifdef CONFIG_PREEMPT_RCU */
+
+void exit_rcu(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key rcu_lock_key;
 struct lockdep_map rcu_lock_map =

kernel/rcutiny_plugin.h

@@ -851,22 +851,6 @@ int rcu_preempt_needs_cpu(void)
 	return rcu_preempt_ctrlblk.rcb.rcucblist != NULL;
 }
 
-/*
- * Check for a task exiting while in a preemptible -RCU read-side
- * critical section, clean up if so.  No need to issue warnings,
- * as debug_check_no_locks_held() already does this if lockdep
- * is enabled.
- */
-void exit_rcu(void)
-{
-	struct task_struct *t = current;
-
-	if (t->rcu_read_lock_nesting == 0)
-		return;
-	t->rcu_read_lock_nesting = 1;
-	__rcu_read_unlock();
-}
-
 #else /* #ifdef CONFIG_TINY_PREEMPT_RCU */
 
 #ifdef CONFIG_RCU_TRACE

kernel/rcutorture.c

@@ -64,6 +64,7 @@ static int irqreader = 1;	/* RCU readers from irq (timers). */
 static int fqs_duration;	/* Duration of bursts (us), 0 to disable. */
 static int fqs_holdoff;		/* Hold time within burst (us). */
 static int fqs_stutter = 3;	/* Wait time between bursts (s). */
+static int n_barrier_cbs;	/* Number of callbacks to test RCU barriers. */
 static int onoff_interval;	/* Wait time between CPU hotplugs, 0=disable. */
 static int onoff_holdoff;	/* Seconds after boot before CPU hotplugs. */
 static int shutdown_secs;	/* Shutdown time (s).  <=0 for no shutdown. */
@@ -96,6 +97,8 @@ module_param(fqs_holdoff, int, 0444);
 MODULE_PARM_DESC(fqs_holdoff, "Holdoff time within fqs bursts (us)");
 module_param(fqs_stutter, int, 0444);
 MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)");
+module_param(n_barrier_cbs, int, 0444);
+MODULE_PARM_DESC(n_barrier_cbs, "# of callbacks/kthreads for barrier testing");
 module_param(onoff_interval, int, 0444);
 MODULE_PARM_DESC(onoff_interval, "Time between CPU hotplugs (s), 0=disable");
 module_param(onoff_holdoff, int, 0444);
@@ -139,6 +142,8 @@ static struct task_struct *shutdown_task;
 static struct task_struct *onoff_task;
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 static struct task_struct *stall_task;
+static struct task_struct **barrier_cbs_tasks;
+static struct task_struct *barrier_task;
 
 #define RCU_TORTURE_PIPE_LEN 10
 
@@ -164,6 +169,7 @@ static atomic_t n_rcu_torture_alloc_fail;
 static atomic_t n_rcu_torture_free;
 static atomic_t n_rcu_torture_mberror;
 static atomic_t n_rcu_torture_error;
+static long n_rcu_torture_barrier_error;
 static long n_rcu_torture_boost_ktrerror;
 static long n_rcu_torture_boost_rterror;
 static long n_rcu_torture_boost_failure;
@@ -173,6 +179,8 @@ static long n_offline_attempts;
 static long n_offline_successes;
 static long n_online_attempts;
 static long n_online_successes;
+static long n_barrier_attempts;
+static long n_barrier_successes;
 static struct list_head rcu_torture_removed;
 static cpumask_var_t shuffle_tmp_mask;
 
@@ -197,6 +205,10 @@ static unsigned long shutdown_time;	/* jiffies to system shutdown. */
 static unsigned long boost_starttime;	/* jiffies of next boost test start. */
 DEFINE_MUTEX(boost_mutex);		/* protect setting boost_starttime */
 					/*  and boost task create/destroy. */
+static atomic_t barrier_cbs_count;	/* Barrier callbacks registered. */
+static atomic_t barrier_cbs_invoked;	/* Barrier callbacks invoked. */
+static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */
+static DECLARE_WAIT_QUEUE_HEAD(barrier_wq);
 
 /* Mediate rmmod and system shutdown.  Concurrent rmmod & shutdown illegal! */
 
@@ -327,6 +339,7 @@ struct rcu_torture_ops {
 	int (*completed)(void);
 	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
+	void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
 	void (*cb_barrier)(void);
 	void (*fqs)(void);
 	int (*stats)(char *page);
@@ -417,6 +430,7 @@ static struct rcu_torture_ops rcu_ops = {
 	.completed	= rcu_torture_completed,
 	.deferred_free	= rcu_torture_deferred_free,
 	.sync		= synchronize_rcu,
+	.call		= call_rcu,
 	.cb_barrier	= rcu_barrier,
 	.fqs		= rcu_force_quiescent_state,
 	.stats		= NULL,
@@ -460,6 +474,7 @@ static struct rcu_torture_ops rcu_sync_ops = {
 	.completed	= rcu_torture_completed,
 	.deferred_free	= rcu_sync_torture_deferred_free,
 	.sync		= synchronize_rcu,
+	.call		= NULL,
 	.cb_barrier	= NULL,
 	.fqs		= rcu_force_quiescent_state,
 	.stats		= NULL,
@@ -477,6 +492,7 @@ static struct rcu_torture_ops rcu_expedited_ops = {
 	.completed	= rcu_no_completed,
 	.deferred_free	= rcu_sync_torture_deferred_free,
 	.sync		= synchronize_rcu_expedited,
+	.call		= NULL,
 	.cb_barrier	= NULL,
 	.fqs		= rcu_force_quiescent_state,
 	.stats		= NULL,
@@ -519,6 +535,7 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.completed	= rcu_bh_torture_completed,
 	.deferred_free	= rcu_bh_torture_deferred_free,
 	.sync		= synchronize_rcu_bh,
+	.call		= call_rcu_bh,
 	.cb_barrier	= rcu_barrier_bh,
 	.fqs		= rcu_bh_force_quiescent_state,
 	.stats		= NULL,
@@ -535,6 +552,7 @@ static struct rcu_torture_ops rcu_bh_sync_ops = {
 	.completed	= rcu_bh_torture_completed,
 	.deferred_free	= rcu_sync_torture_deferred_free,
 	.sync		= synchronize_rcu_bh,
+	.call		= NULL,
 	.cb_barrier	= NULL,
 	.fqs		= rcu_bh_force_quiescent_state,
 	.stats		= NULL,
@@ -551,6 +569,7 @@ static struct rcu_torture_ops rcu_bh_expedited_ops = {
 	.completed	= rcu_bh_torture_completed,
 	.deferred_free	= rcu_sync_torture_deferred_free,
 	.sync		= synchronize_rcu_bh_expedited,
+	.call		= NULL,
 	.cb_barrier	= NULL,
 	.fqs		= rcu_bh_force_quiescent_state,
 	.stats		= NULL,
@@ -606,6 +625,11 @@ static int srcu_torture_completed(void)
 	return srcu_batches_completed(&srcu_ctl);
 }
 
+static void srcu_torture_deferred_free(struct rcu_torture *rp)
+{
+	call_srcu(&srcu_ctl, &rp->rtort_rcu, rcu_torture_cb);
+}
+
 static void srcu_torture_synchronize(void)
 {
 	synchronize_srcu(&srcu_ctl);
@@ -620,7 +644,7 @@ static int srcu_torture_stats(char *page)
 	cnt += sprintf(&page[cnt], "%s%s per-CPU(idx=%d):",
 		       torture_type, TORTURE_FLAG, idx);
 	for_each_possible_cpu(cpu) {
-		cnt += sprintf(&page[cnt], " %d(%d,%d)", cpu,
+		cnt += sprintf(&page[cnt], " %d(%lu,%lu)", cpu,
 			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx],
 			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]);
 	}
@@ -635,13 +659,29 @@ static struct rcu_torture_ops srcu_ops = {
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock,
 	.completed	= srcu_torture_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
+	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
+	.call		= NULL,
 	.cb_barrier	= NULL,
 	.stats		= srcu_torture_stats,
 	.name		= "srcu"
 };
 
+static struct rcu_torture_ops srcu_sync_ops = {
+	.init		= srcu_torture_init,
+	.cleanup	= srcu_torture_cleanup,
+	.readlock	= srcu_torture_read_lock,
+	.read_delay	= srcu_read_delay,
+	.readunlock	= srcu_torture_read_unlock,
+	.completed	= srcu_torture_completed,
+	.deferred_free	= rcu_sync_torture_deferred_free,
+	.sync		= srcu_torture_synchronize,
+	.call		= NULL,
+	.cb_barrier	= NULL,
+	.stats		= srcu_torture_stats,
+	.name		= "srcu_sync"
+};
+
 static int srcu_torture_read_lock_raw(void) __acquires(&srcu_ctl)
 {
 	return srcu_read_lock_raw(&srcu_ctl);
@@ -659,13 +699,29 @@ static struct rcu_torture_ops srcu_raw_ops = {
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock_raw,
 	.completed	= srcu_torture_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
+	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
+	.call		= NULL,
 	.cb_barrier	= NULL,
 	.stats		= srcu_torture_stats,
 	.name		= "srcu_raw"
 };
 
+static struct rcu_torture_ops srcu_raw_sync_ops = {
+	.init		= srcu_torture_init,
+	.cleanup	= srcu_torture_cleanup,
+	.readlock	= srcu_torture_read_lock_raw,
+	.read_delay	= srcu_read_delay,
+	.readunlock	= srcu_torture_read_unlock_raw,
+	.completed	= srcu_torture_completed,
+	.deferred_free	= rcu_sync_torture_deferred_free,
+	.sync		= srcu_torture_synchronize,
+	.call		= NULL,
+	.cb_barrier	= NULL,
+	.stats		= srcu_torture_stats,
+	.name		= "srcu_raw_sync"
+};
+
 static void srcu_torture_synchronize_expedited(void)
 {
 	synchronize_srcu_expedited(&srcu_ctl);
@@ -680,6 +736,7 @@ static struct rcu_torture_ops srcu_expedited_ops = {
 	.completed	= srcu_torture_completed,
 	.deferred_free	= rcu_sync_torture_deferred_free,
 	.sync		= srcu_torture_synchronize_expedited,
+	.call		= NULL,
 	.cb_barrier	= NULL,
 	.stats		= srcu_torture_stats,
 	.name		= "srcu_expedited"
@@ -1129,7 +1186,8 @@ rcu_torture_printk(char *page)
 		       "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d "
 		       "rtmbe: %d rtbke: %ld rtbre: %ld "
 		       "rtbf: %ld rtb: %ld nt: %ld "
-		       "onoff: %ld/%ld:%ld/%ld",
+		       "onoff: %ld/%ld:%ld/%ld "
+		       "barrier: %ld/%ld:%ld",
 		       rcu_torture_current,
 		       rcu_torture_current_version,
 		       list_empty(&rcu_torture_freelist),
@@ -1145,14 +1203,17 @@ rcu_torture_printk(char *page)
 		       n_online_successes,
 		       n_online_attempts,
 		       n_offline_successes,
-		       n_offline_attempts);
+		       n_offline_attempts,
+		       n_barrier_successes,
+		       n_barrier_attempts,
+		       n_rcu_torture_barrier_error);
+	cnt += sprintf(&page[cnt], "\n%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)
+	    n_rcu_torture_boost_failure != 0 ||
-		cnt += sprintf(&page[cnt], " !!!");
+	    i > 1) {
-	cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
-	if (i > 1) {
 		cnt += sprintf(&page[cnt], "!!! ");
 		atomic_inc(&n_rcu_torture_error);
 		WARN_ON_ONCE(1);
@@ -1337,6 +1398,7 @@ static void rcutorture_booster_cleanup(int cpu)
 
 	/* This must be outside of the mutex, otherwise deadlock! */
 	kthread_stop(t);
+	boost_tasks[cpu] = NULL;
 }
 
 static int rcutorture_booster_init(int cpu)
@@ -1484,13 +1546,15 @@ static void rcu_torture_onoff_cleanup(void)
 		return;
 	VERBOSE_PRINTK_STRING("Stopping rcu_torture_onoff task");
 	kthread_stop(onoff_task);
+	onoff_task = NULL;
 }
 
 #else /* #ifdef CONFIG_HOTPLUG_CPU */
 
-static void
+static int
 rcu_torture_onoff_init(void)
 {
+	return 0;
 }
 
 static void rcu_torture_onoff_cleanup(void)
@@ -1554,6 +1618,152 @@ static void rcu_torture_stall_cleanup(void)
 		return;
 	VERBOSE_PRINTK_STRING("Stopping rcu_torture_stall_task.");
 	kthread_stop(stall_task);
+	stall_task = NULL;
+}
+
+/* Callback function for RCU barrier testing. */
+void rcu_torture_barrier_cbf(struct rcu_head *rcu)
+{
+	atomic_inc(&barrier_cbs_invoked);
+}
+
+/* kthread function to register callbacks used to test RCU barriers. */
+static int rcu_torture_barrier_cbs(void *arg)
+{
+	long myid = (long)arg;
+	struct rcu_head rcu;
+
+	init_rcu_head_on_stack(&rcu);
+	VERBOSE_PRINTK_STRING("rcu_torture_barrier_cbs task started");
+	set_user_nice(current, 19);
+	do {
+		wait_event(barrier_cbs_wq[myid],
+			   atomic_read(&barrier_cbs_count) == n_barrier_cbs ||
+			   kthread_should_stop() ||
+			   fullstop != FULLSTOP_DONTSTOP);
+		if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
+			break;
+		cur_ops->call(&rcu, rcu_torture_barrier_cbf);
+		if (atomic_dec_and_test(&barrier_cbs_count))
+			wake_up(&barrier_wq);
+	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
+	VERBOSE_PRINTK_STRING("rcu_torture_barrier_cbs task stopping");
+	rcutorture_shutdown_absorb("rcu_torture_barrier_cbs");
+	while (!kthread_should_stop())
+		schedule_timeout_interruptible(1);
+	cur_ops->cb_barrier();
+	destroy_rcu_head_on_stack(&rcu);
+	return 0;
+}
+
+/* kthread function to drive and coordinate RCU barrier testing. */
+static int rcu_torture_barrier(void *arg)
+{
+	int i;
+
+	VERBOSE_PRINTK_STRING("rcu_torture_barrier task starting");
+	do {
+		atomic_set(&barrier_cbs_invoked, 0);
+		atomic_set(&barrier_cbs_count, n_barrier_cbs);
+		/* wake_up() path contains the required barriers. */
+		for (i = 0; i < n_barrier_cbs; i++)
+			wake_up(&barrier_cbs_wq[i]);
+		wait_event(barrier_wq,
+			   atomic_read(&barrier_cbs_count) == 0 ||
+			   kthread_should_stop() ||
+			   fullstop != FULLSTOP_DONTSTOP);
+		if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
+			break;
+		n_barrier_attempts++;
+		cur_ops->cb_barrier();
+		if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) {
+			n_rcu_torture_barrier_error++;
+			WARN_ON_ONCE(1);
+		}
+		n_barrier_successes++;
+		schedule_timeout_interruptible(HZ / 10);
+	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
+	VERBOSE_PRINTK_STRING("rcu_torture_barrier task stopping");
+	rcutorture_shutdown_absorb("rcu_torture_barrier_cbs");
+	while (!kthread_should_stop())
+		schedule_timeout_interruptible(1);
+	return 0;
+}
+
+/* Initialize RCU barrier testing. */
+static int rcu_torture_barrier_init(void)
+{
+	int i;
+	int ret;
+
+	if (n_barrier_cbs == 0)
+		return 0;
+	if (cur_ops->call == NULL || cur_ops->cb_barrier == NULL) {
+		printk(KERN_ALERT "%s" TORTURE_FLAG
+		       " Call or barrier ops missing for %s,\n",
+		       torture_type, cur_ops->name);
+		printk(KERN_ALERT "%s" TORTURE_FLAG
+		       " RCU barrier testing omitted from run.\n",
+		       torture_type);
+		return 0;
+	}
+	atomic_set(&barrier_cbs_count, 0);
+	atomic_set(&barrier_cbs_invoked, 0);
+	barrier_cbs_tasks =
+		kzalloc(n_barrier_cbs * sizeof(barrier_cbs_tasks[0]),
+			GFP_KERNEL);
+	barrier_cbs_wq =
+		kzalloc(n_barrier_cbs * sizeof(barrier_cbs_wq[0]),
+			GFP_KERNEL);
+	if (barrier_cbs_tasks == NULL || barrier_cbs_wq == 0)
+		return -ENOMEM;
+	for (i = 0; i < n_barrier_cbs; i++) {
+		init_waitqueue_head(&barrier_cbs_wq[i]);
+		barrier_cbs_tasks[i] = kthread_run(rcu_torture_barrier_cbs,
+						   (void *)(long)i,
+						   "rcu_torture_barrier_cbs");
+		if (IS_ERR(barrier_cbs_tasks[i])) {
+			ret = PTR_ERR(barrier_cbs_tasks[i]);
+			VERBOSE_PRINTK_ERRSTRING("Failed to create rcu_torture_barrier_cbs");
+			barrier_cbs_tasks[i] = NULL;
+			return ret;
+		}
+	}
+	barrier_task = kthread_run(rcu_torture_barrier, NULL,
+				   "rcu_torture_barrier");
+	if (IS_ERR(barrier_task)) {
+		ret = PTR_ERR(barrier_task);
+		VERBOSE_PRINTK_ERRSTRING("Failed to create rcu_torture_barrier");
+		barrier_task = NULL;
+	}
+	return 0;
+}
+
+/* Clean up after RCU barrier testing. */
+static void rcu_torture_barrier_cleanup(void)
+{
+	int i;
+
+	if (barrier_task != NULL) {
+		VERBOSE_PRINTK_STRING("Stopping rcu_torture_barrier task");
+		kthread_stop(barrier_task);
+		barrier_task = NULL;
+	}
+	if (barrier_cbs_tasks != NULL) {
+		for (i = 0; i < n_barrier_cbs; i++) {
+			if (barrier_cbs_tasks[i] != NULL) {
+				VERBOSE_PRINTK_STRING("Stopping rcu_torture_barrier_cbs task");
+				kthread_stop(barrier_cbs_tasks[i]);
+				barrier_cbs_tasks[i] = NULL;
+			}
+		}
+		kfree(barrier_cbs_tasks);
+		barrier_cbs_tasks = NULL;
+	}
+	if (barrier_cbs_wq != NULL) {
+		kfree(barrier_cbs_wq);
+		barrier_cbs_wq = NULL;
+	}
 }
 
 static int rcutorture_cpu_notify(struct notifier_block *self,
@@ -1598,6 +1808,7 @@ rcu_torture_cleanup(void)
 	fullstop = FULLSTOP_RMMOD;
 	mutex_unlock(&fullstop_mutex);
 	unregister_reboot_notifier(&rcutorture_shutdown_nb);
+	rcu_torture_barrier_cleanup();
 	rcu_torture_stall_cleanup();
 	if (stutter_task) {
 		VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task");
@@ -1665,6 +1876,7 @@ rcu_torture_cleanup(void)
 		VERBOSE_PRINTK_STRING("Stopping rcu_torture_shutdown task");
 		kthread_stop(shutdown_task);
 	}
+	shutdown_task = NULL;
 	rcu_torture_onoff_cleanup();
 
 	/* Wait for all RCU callbacks to fire.  */
@@ -1676,7 +1888,7 @@ rcu_torture_cleanup(void)
 
 	if (cur_ops->cleanup)
 		cur_ops->cleanup();
-	if (atomic_read(&n_rcu_torture_error))
+	if (atomic_read(&n_rcu_torture_error) || n_rcu_torture_barrier_error)
 		rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE");
 	else if (n_online_successes != n_online_attempts ||
 		 n_offline_successes != n_offline_attempts)
@@ -1692,10 +1904,12 @@ rcu_torture_init(void)
 	int i;
 	int cpu;
 	int firsterr = 0;
+	int retval;
 	static struct rcu_torture_ops *torture_ops[] =
 		{ &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops,
 		  &rcu_bh_ops, &rcu_bh_sync_ops, &rcu_bh_expedited_ops,
-		  &srcu_ops, &srcu_raw_ops, &srcu_expedited_ops,
+		  &srcu_ops, &srcu_sync_ops, &srcu_raw_ops,
+		  &srcu_raw_sync_ops, &srcu_expedited_ops,
 		  &sched_ops, &sched_sync_ops, &sched_expedited_ops, };
 
 	mutex_lock(&fullstop_mutex);
@@ -1749,6 +1963,7 @@ rcu_torture_init(void)
 	atomic_set(&n_rcu_torture_free, 0);
 	atomic_set(&n_rcu_torture_mberror, 0);
 	atomic_set(&n_rcu_torture_error, 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;
@@ -1872,7 +2087,6 @@ rcu_torture_init(void)
 		test_boost_duration = 2;
 	if ((test_boost == 1 && cur_ops->can_boost) ||
 	    test_boost == 2) {
-		int retval;
 
 		boost_starttime = jiffies + test_boost_interval * HZ;
 		register_cpu_notifier(&rcutorture_cpu_nb);
@@ -1897,9 +2111,22 @@ rcu_torture_init(void)
 			goto unwind;
 		}
 	}
-	rcu_torture_onoff_init();
+	i = rcu_torture_onoff_init();
+	if (i != 0) {
+		firsterr = i;
+		goto unwind;
+	}
 	register_reboot_notifier(&rcutorture_shutdown_nb);
-	rcu_torture_stall_init();
+	i = rcu_torture_stall_init();
+	if (i != 0) {
+		firsterr = i;
+		goto unwind;
+	}
+	retval = rcu_torture_barrier_init();
+	if (retval != 0) {
+		firsterr = retval;
+		goto unwind;
+	}
 	rcutorture_record_test_transition();
 	mutex_unlock(&fullstop_mutex);
 	return 0;

kernel/rcutree.c

@@ -201,7 +201,6 @@ void rcu_note_context_switch(int cpu)
 {
 	trace_rcu_utilization("Start context switch");
 	rcu_sched_qs(cpu);
-	rcu_preempt_note_context_switch(cpu);
 	trace_rcu_utilization("End context switch");
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
@@ -1953,6 +1952,38 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 }
 EXPORT_SYMBOL_GPL(call_rcu_bh);
 
+/*
+ * Because a context switch is a grace period for RCU-sched and RCU-bh,
+ * any blocking grace-period wait automatically implies a grace period
+ * if there is only one CPU online at any point time during execution
+ * of either synchronize_sched() or synchronize_rcu_bh().  It is OK to
+ * occasionally incorrectly indicate that there are multiple CPUs online
+ * when there was in fact only one the whole time, as this just adds
+ * some overhead: RCU still operates correctly.
+ *
+ * Of course, sampling num_online_cpus() with preemption enabled can
+ * give erroneous results if there are concurrent CPU-hotplug operations.
+ * For example, given a demonic sequence of preemptions in num_online_cpus()
+ * and CPU-hotplug operations, there could be two or more CPUs online at
+ * all times, but num_online_cpus() might well return one (or even zero).
+ *
+ * However, all such demonic sequences require at least one CPU-offline
+ * operation.  Furthermore, rcu_blocking_is_gp() giving the wrong answer
+ * is only a problem if there is an RCU read-side critical section executing
+ * throughout.  But RCU-sched and RCU-bh read-side critical sections
+ * disable either preemption or bh, which prevents a CPU from going offline.
+ * Therefore, the only way that rcu_blocking_is_gp() can incorrectly return
+ * that there is only one CPU when in fact there was more than one throughout
+ * is when there were no RCU readers in the system.  If there are no
+ * RCU readers, the grace period by definition can be of zero length,
+ * regardless of the number of online CPUs.
+ */
+static inline int rcu_blocking_is_gp(void)
+{
+	might_sleep();  /* Check for RCU read-side critical section. */
+	return num_online_cpus() <= 1;
+}
+
 /**
  * synchronize_sched - wait until an rcu-sched grace period has elapsed.
  *
@@ -2543,7 +2574,7 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
 
 	for (i = NUM_RCU_LVLS - 1; i > 0; i--)
 		rsp->levelspread[i] = CONFIG_RCU_FANOUT;
-	rsp->levelspread[0] = RCU_FANOUT_LEAF;
+	rsp->levelspread[0] = CONFIG_RCU_FANOUT_LEAF;
 }
 #else /* #ifdef CONFIG_RCU_FANOUT_EXACT */
 static void __init rcu_init_levelspread(struct rcu_state *rsp)

kernel/rcutree.h

@@ -29,18 +29,14 @@
 #include <linux/seqlock.h>
 
 /*
- * Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT.
+ * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
+ * CONFIG_RCU_FANOUT_LEAF.
  * In theory, it should be possible to add more levels straightforwardly.
  * In practice, this did work well going from three levels to four.
  * Of course, your mileage may vary.
  */
 #define MAX_RCU_LVLS 4
-#if CONFIG_RCU_FANOUT > 16
+#define RCU_FANOUT_1	      (CONFIG_RCU_FANOUT_LEAF)
-#define RCU_FANOUT_LEAF       16
-#else /* #if CONFIG_RCU_FANOUT > 16 */
-#define RCU_FANOUT_LEAF       (CONFIG_RCU_FANOUT)
-#endif /* #else #if CONFIG_RCU_FANOUT > 16 */
-#define RCU_FANOUT_1	      (RCU_FANOUT_LEAF)
 #define RCU_FANOUT_2	      (RCU_FANOUT_1 * CONFIG_RCU_FANOUT)
 #define RCU_FANOUT_3	      (RCU_FANOUT_2 * CONFIG_RCU_FANOUT)
 #define RCU_FANOUT_4	      (RCU_FANOUT_3 * CONFIG_RCU_FANOUT)
@@ -434,7 +430,6 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work);
 /* Forward declarations for rcutree_plugin.h */
 static void rcu_bootup_announce(void);
 long rcu_batches_completed(void);
-static void rcu_preempt_note_context_switch(int cpu);
 static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,

kernel/rcutree_plugin.h

@@ -153,7 +153,7 @@ static void rcu_preempt_qs(int cpu)
  *
  * Caller must disable preemption.
  */
-static void rcu_preempt_note_context_switch(int cpu)
+void rcu_preempt_note_context_switch(void)
 {
 	struct task_struct *t = current;
 	unsigned long flags;
@@ -164,7 +164,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
 
 		/* Possibly blocking in an RCU read-side critical section. */
-		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
+		rdp = __this_cpu_ptr(rcu_preempt_state.rda);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
@@ -228,7 +228,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 	 * means that we continue to block the current grace period.
 	 */
 	local_irq_save(flags);
-	rcu_preempt_qs(cpu);
+	rcu_preempt_qs(smp_processor_id());
 	local_irq_restore(flags);
 }
 
@@ -969,22 +969,6 @@ static void __init __rcu_init_preempt(void)
 	rcu_init_one(&rcu_preempt_state, &rcu_preempt_data);
 }
 
-/*
- * Check for a task exiting while in a preemptible-RCU read-side
- * critical section, clean up if so.  No need to issue warnings,
- * as debug_check_no_locks_held() already does this if lockdep
- * is enabled.
- */
-void exit_rcu(void)
-{
-	struct task_struct *t = current;
-
-	if (t->rcu_read_lock_nesting == 0)
-		return;
-	t->rcu_read_lock_nesting = 1;
-	__rcu_read_unlock();
-}
-
 #else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
 static struct rcu_state *rcu_state = &rcu_sched_state;
@@ -1017,14 +1001,6 @@ void rcu_force_quiescent_state(void)
 }
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
-/*
- * Because preemptible RCU does not exist, we never have to check for
- * CPUs being in quiescent states.
- */
-static void rcu_preempt_note_context_switch(int cpu)
-{
-}
-
 /*
  * Because preemptible RCU does not exist, there are never any preempted
  * RCU readers.

kernel/sched/core.c

@@ -2083,6 +2083,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 #endif
 
 	/* Here we just switch the register state and the stack. */
+	rcu_switch_from(prev);
 	switch_to(prev, next, prev);
 
 	barrier();

kernel/srcu.c

@@ -34,10 +34,77 @@
 #include <linux/delay.h>
 #include <linux/srcu.h>
 
+/*
+ * Initialize an rcu_batch structure to empty.
+ */
+static inline void rcu_batch_init(struct rcu_batch *b)
+{
+	b->head = NULL;
+	b->tail = &b->head;
+}
+
+/*
+ * Enqueue a callback onto the tail of the specified rcu_batch structure.
+ */
+static inline void rcu_batch_queue(struct rcu_batch *b, struct rcu_head *head)
+{
+	*b->tail = head;
+	b->tail = &head->next;
+}
+
+/*
+ * Is the specified rcu_batch structure empty?
+ */
+static inline bool rcu_batch_empty(struct rcu_batch *b)
+{
+	return b->tail == &b->head;
+}
+
+/*
+ * Remove the callback at the head of the specified rcu_batch structure
+ * and return a pointer to it, or return NULL if the structure is empty.
+ */
+static inline struct rcu_head *rcu_batch_dequeue(struct rcu_batch *b)
+{
+	struct rcu_head *head;
+
+	if (rcu_batch_empty(b))
+		return NULL;
+
+	head = b->head;
+	b->head = head->next;
+	if (b->tail == &head->next)
+		rcu_batch_init(b);
+
+	return head;
+}
+
+/*
+ * Move all callbacks from the rcu_batch structure specified by "from" to
+ * the structure specified by "to".
+ */
+static inline void rcu_batch_move(struct rcu_batch *to, struct rcu_batch *from)
+{
+	if (!rcu_batch_empty(from)) {
+		*to->tail = from->head;
+		to->tail = from->tail;
+		rcu_batch_init(from);
+	}
+}
+
+/* single-thread state-machine */
+static void process_srcu(struct work_struct *work);
+
 static int init_srcu_struct_fields(struct srcu_struct *sp)
 {
 	sp->completed = 0;
-	mutex_init(&sp->mutex);
+	spin_lock_init(&sp->queue_lock);
+	sp->running = false;
+	rcu_batch_init(&sp->batch_queue);
+	rcu_batch_init(&sp->batch_check0);
+	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);
 	return sp->per_cpu_ref ? 0 : -ENOMEM;
 }
@@ -73,21 +140,116 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 /*
- * srcu_readers_active_idx -- returns approximate number of readers
+ * Returns approximate total of the readers' ->seq[] values for the
- *	active on the specified rank of per-CPU counters.
+ * rank of per-CPU counters specified by idx.
  */
-
+static unsigned long srcu_readers_seq_idx(struct srcu_struct *sp, int idx)
-static int srcu_readers_active_idx(struct srcu_struct *sp, int idx)
 {
 	int cpu;
-	int sum;
+	unsigned long sum = 0;
+	unsigned long t;
 
-	sum = 0;
+	for_each_possible_cpu(cpu) {
-	for_each_possible_cpu(cpu)
+		t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]);
-		sum += per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx];
+		sum += t;
+	}
 	return sum;
 }
 
+/*
+ * Returns approximate number of readers active on the specified rank
+ * of the per-CPU ->c[] counters.
+ */
+static unsigned long srcu_readers_active_idx(struct srcu_struct *sp, int idx)
+{
+	int cpu;
+	unsigned long sum = 0;
+	unsigned long t;
+
+	for_each_possible_cpu(cpu) {
+		t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]);
+		sum += t;
+	}
+	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.
+ */
+static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
+{
+	unsigned long seq;
+
+	seq = srcu_readers_seq_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.
+	 *
+	 * 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[].
+	 */
+	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.
+	 *
+	 * We therefore do a validation step should srcu_readers_active_idx()
+	 * return zero.
+	 */
+	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;
+}
+
 /**
  * srcu_readers_active - returns approximate number of readers.
  * @sp: which srcu_struct to count active readers (holding srcu_read_lock).
@@ -98,7 +260,14 @@ static int srcu_readers_active_idx(struct srcu_struct *sp, int idx)
  */
 static int srcu_readers_active(struct srcu_struct *sp)
 {
-	return srcu_readers_active_idx(sp, 0) + srcu_readers_active_idx(sp, 1);
+	int cpu;
+	unsigned long sum = 0;
+
+	for_each_possible_cpu(cpu) {
+		sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]);
+		sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]);
+	}
+	return sum;
 }
 
 /**
@@ -131,10 +300,11 @@ int __srcu_read_lock(struct srcu_struct *sp)
 	int idx;
 
 	preempt_disable();
-	idx = sp->completed & 0x1;
+	idx = rcu_dereference_index_check(sp->completed,
-	barrier();  /* ensure compiler looks -once- at sp->completed. */
+					  rcu_read_lock_sched_held()) & 0x1;
-	per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]++;
+	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) += 1;
-	srcu_barrier();  /* ensure compiler won't misorder critical section. */
+	smp_mb(); /* B */  /* Avoid leaking the critical section. */
+	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->seq[idx]) += 1;
 	preempt_enable();
 	return idx;
 }
@@ -149,8 +319,8 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock);
 void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 {
 	preempt_disable();
-	srcu_barrier();  /* ensure compiler won't misorder critical section. */
+	smp_mb(); /* C */  /* Avoid leaking the critical section. */
-	per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]--;
+	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) -= 1;
 	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
@@ -163,14 +333,86 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock);
  * we repeatedly block for 1-millisecond time periods.  This approach
  * has done well in testing, so there is no need for a config parameter.
  */
-#define SYNCHRONIZE_SRCU_READER_DELAY 10
+#define SRCU_RETRY_CHECK_DELAY		5
+#define SYNCHRONIZE_SRCU_TRYCOUNT	2
+#define SYNCHRONIZE_SRCU_EXP_TRYCOUNT	12
+
+/*
+ * @@@ Wait until all pre-existing readers complete.  Such readers
+ * will have used the index specified by "idx".
+ * the caller should ensures the ->completed is not changed while checking
+ * and idx = (->completed & 1) ^ 1
+ */
+static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount)
+{
+	for (;;) {
+		if (srcu_readers_active_idx_check(sp, idx))
+			return true;
+		if (--trycount <= 0)
+			return false;
+		udelay(SRCU_RETRY_CHECK_DELAY);
+	}
+}
+
+/*
+ * Increment the ->completed counter so that future SRCU readers will
+ * use the other rank of the ->c[] and ->seq[] 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++;
+}
+
+/*
+ * Enqueue an SRCU callback on the specified srcu_struct structure,
+ * initiating grace-period processing if it is not already running.
+ */
+void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
+		void (*func)(struct rcu_head *head))
+{
+	unsigned long flags;
+
+	head->next = NULL;
+	head->func = func;
+	spin_lock_irqsave(&sp->queue_lock, flags);
+	rcu_batch_queue(&sp->batch_queue, head);
+	if (!sp->running) {
+		sp->running = true;
+		queue_delayed_work(system_nrt_wq, &sp->work, 0);
+	}
+	spin_unlock_irqrestore(&sp->queue_lock, flags);
+}
+EXPORT_SYMBOL_GPL(call_srcu);
+
+struct rcu_synchronize {
+	struct rcu_head head;
+	struct completion completion;
+};
+
+/*
+ * Awaken the corresponding synchronize_srcu() instance now that a
+ * grace period has elapsed.
+ */
+static void wakeme_after_rcu(struct rcu_head *head)
+{
+	struct rcu_synchronize *rcu;
+
+	rcu = container_of(head, struct rcu_synchronize, head);
+	complete(&rcu->completion);
+}
+
+static void srcu_advance_batches(struct srcu_struct *sp, int trycount);
+static void srcu_reschedule(struct srcu_struct *sp);
 
 /*
  * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
  */
-static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
+static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
 {
-	int idx;
+	struct rcu_synchronize rcu;
+	struct rcu_head *head = &rcu.head;
+	bool done = false;
 
 	rcu_lockdep_assert(!lock_is_held(&sp->dep_map) &&
 			   !lock_is_held(&rcu_bh_lock_map) &&
@@ -178,91 +420,32 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
 			   !lock_is_held(&rcu_sched_lock_map),
 			   "Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section");
 
-	idx = sp->completed;
+	init_completion(&rcu.completion);
-	mutex_lock(&sp->mutex);
 
-	/*
+	head->next = NULL;
-	 * Check to see if someone else did the work for us while we were
+	head->func = wakeme_after_rcu;
-	 * waiting to acquire the lock.  We need -two- advances of
+	spin_lock_irq(&sp->queue_lock);
-	 * the counter, not just one.  If there was but one, we might have
+	if (!sp->running) {
-	 * shown up -after- our helper's first synchronize_sched(), thus
+		/* steal the processing owner */
-	 * having failed to prevent CPU-reordering races with concurrent
+		sp->running = true;
-	 * srcu_read_unlock()s on other CPUs (see comment below).  So we
+		rcu_batch_queue(&sp->batch_check0, head);
-	 * either (1) wait for two or (2) supply the second ourselves.
+		spin_unlock_irq(&sp->queue_lock);
-	 */
 
-	if ((sp->completed - idx) >= 2) {
+		srcu_advance_batches(sp, trycount);
-		mutex_unlock(&sp->mutex);
+		if (!rcu_batch_empty(&sp->batch_done)) {
-		return;
+			BUG_ON(sp->batch_done.head != head);
+			rcu_batch_dequeue(&sp->batch_done);
+			done = true;
+		}
+		/* give the processing owner to work_struct */
+		srcu_reschedule(sp);
+	} else {
+		rcu_batch_queue(&sp->batch_queue, head);
+		spin_unlock_irq(&sp->queue_lock);
 	}
 
-	sync_func();  /* Force memory barrier on all CPUs. */
+	if (!done)
-
+		wait_for_completion(&rcu.completion);
-	/*
-	 * The preceding synchronize_sched() ensures that any CPU that
-	 * sees the new value of sp->completed will also see any preceding
-	 * changes to data structures made by this CPU.  This prevents
-	 * some other CPU from reordering the accesses in its SRCU
-	 * read-side critical section to precede the corresponding
-	 * srcu_read_lock() -- ensuring that such references will in
-	 * fact be protected.
-	 *
-	 * So it is now safe to do the flip.
-	 */
-
-	idx = sp->completed & 0x1;
-	sp->completed++;
-
-	sync_func();  /* Force memory barrier on all CPUs. */
-
-	/*
-	 * At this point, because of the preceding synchronize_sched(),
-	 * all srcu_read_lock() calls using the old counters have completed.
-	 * Their corresponding critical sections might well be still
-	 * executing, but the srcu_read_lock() primitives themselves
-	 * will have finished executing.  We initially give readers
-	 * an arbitrarily chosen 10 microseconds to get out of their
-	 * SRCU read-side critical sections, then loop waiting 1/HZ
-	 * seconds per iteration.  The 10-microsecond value has done
-	 * very well in testing.
-	 */
-
-	if (srcu_readers_active_idx(sp, idx))
-		udelay(SYNCHRONIZE_SRCU_READER_DELAY);
-	while (srcu_readers_active_idx(sp, idx))
-		schedule_timeout_interruptible(1);
-
-	sync_func();  /* Force memory barrier on all CPUs. */
-
-	/*
-	 * The preceding synchronize_sched() forces all srcu_read_unlock()
-	 * primitives that were executing concurrently with the preceding
-	 * for_each_possible_cpu() loop to have completed by this point.
-	 * More importantly, it also forces the corresponding SRCU read-side
-	 * critical sections to have also completed, and the corresponding
-	 * references to SRCU-protected data items to be dropped.
-	 *
-	 * Note:
-	 *
-	 *	Despite what you might think at first glance, the
-	 *	preceding synchronize_sched() -must- be within the
-	 *	critical section ended by the following mutex_unlock().
-	 *	Otherwise, a task taking the early exit can race
-	 *	with a srcu_read_unlock(), which might have executed
-	 *	just before the preceding srcu_readers_active() check,
-	 *	and whose CPU might have reordered the srcu_read_unlock()
-	 *	with the preceding critical section.  In this case, there
-	 *	is nothing preventing the synchronize_sched() task that is
-	 *	taking the early exit from freeing a data structure that
-	 *	is still being referenced (out of order) by the task
-	 *	doing the srcu_read_unlock().
-	 *
-	 *	Alternatively, the comparison with "2" on the early exit
-	 *	could be changed to "3", but this increases synchronize_srcu()
-	 *	latency for bulk loads.  So the current code is preferred.
-	 */
-
-	mutex_unlock(&sp->mutex);
 }
 
 /**
@@ -281,7 +464,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
  */
 void synchronize_srcu(struct srcu_struct *sp)
 {
-	__synchronize_srcu(sp, synchronize_sched);
+	__synchronize_srcu(sp, SYNCHRONIZE_SRCU_TRYCOUNT);
 }
 EXPORT_SYMBOL_GPL(synchronize_srcu);
 
@@ -289,18 +472,11 @@ EXPORT_SYMBOL_GPL(synchronize_srcu);
  * synchronize_srcu_expedited - Brute-force SRCU grace period
  * @sp: srcu_struct with which to synchronize.
  *
- * Wait for an SRCU grace period to elapse, but use a "big hammer"
+ * Wait for an SRCU grace period to elapse, but be more aggressive about
- * approach to force the grace period to end quickly.  This consumes
+ * spinning rather than blocking when waiting.
- * significant time on all CPUs and is unfriendly to real-time workloads,
- * so is thus not recommended for any sort of common-case code.  In fact,
- * if you are using synchronize_srcu_expedited() in a loop, please
- * restructure your code to batch your updates, and then use a single
- * synchronize_srcu() instead.
  *
  * Note that it is illegal to call this function while holding any lock
- * that is acquired by a CPU-hotplug notifier.  And yes, it is also illegal
+ * that is acquired by a CPU-hotplug notifier.  It is also illegal to call
- * to call this function from a CPU-hotplug notifier.  Failing to observe
- * these restriction will result in deadlock.  It is also illegal to call
  * synchronize_srcu_expedited() from the corresponding SRCU read-side
  * critical section; doing so will result in deadlock.  However, it is
  * perfectly legal to call synchronize_srcu_expedited() on one srcu_struct
@@ -309,10 +485,19 @@ EXPORT_SYMBOL_GPL(synchronize_srcu);
  */
 void synchronize_srcu_expedited(struct srcu_struct *sp)
 {
-	__synchronize_srcu(sp, synchronize_sched_expedited);
+	__synchronize_srcu(sp, SYNCHRONIZE_SRCU_EXP_TRYCOUNT);
 }
 EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
 
+/**
+ * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
+ */
+void srcu_barrier(struct srcu_struct *sp)
+{
+	synchronize_srcu(sp);
+}
+EXPORT_SYMBOL_GPL(srcu_barrier);
+
 /**
  * srcu_batches_completed - return batches completed.
  * @sp: srcu_struct on which to report batch completion.
@@ -320,9 +505,146 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
  * Report the number of batches, correlated with, but not necessarily
  * precisely the same as, the number of grace periods that have elapsed.
  */
-
 long srcu_batches_completed(struct srcu_struct *sp)
 {
 	return sp->completed;
 }
 EXPORT_SYMBOL_GPL(srcu_batches_completed);
+
+#define SRCU_CALLBACK_BATCH	10
+#define SRCU_INTERVAL		1
+
+/*
+ * Move any new SRCU callbacks to the first stage of the SRCU grace
+ * period pipeline.
+ */
+static void srcu_collect_new(struct srcu_struct *sp)
+{
+	if (!rcu_batch_empty(&sp->batch_queue)) {
+		spin_lock_irq(&sp->queue_lock);
+		rcu_batch_move(&sp->batch_check0, &sp->batch_queue);
+		spin_unlock_irq(&sp->queue_lock);
+	}
+}
+
+/*
+ * Core SRCU state machine.  Advance callbacks from ->batch_check0 to
+ * ->batch_check1 and then to ->batch_done as readers drain.
+ */
+static void srcu_advance_batches(struct srcu_struct *sp, int trycount)
+{
+	int idx = 1 ^ (sp->completed & 1);
+
+	/*
+	 * Because readers might be delayed for an extended period after
+	 * fetching ->completed for their index, at any point in time there
+	 * might well be readers using both idx=0 and idx=1.  We therefore
+	 * need to wait for readers to clear from both index values before
+	 * invoking a callback.
+	 */
+
+	if (rcu_batch_empty(&sp->batch_check0) &&
+	    rcu_batch_empty(&sp->batch_check1))
+		return; /* no callbacks need to be advanced */
+
+	if (!try_check_zero(sp, idx, trycount))
+		return; /* failed to advance, will try after SRCU_INTERVAL */
+
+	/*
+	 * The callbacks in ->batch_check1 have already done with their
+	 * first zero check and flip back when they were enqueued on
+	 * ->batch_check0 in a previous invocation of srcu_advance_batches().
+	 * (Presumably try_check_zero() returned false during that
+	 * invocation, leaving the callbacks stranded on ->batch_check1.)
+	 * They are therefore ready to invoke, so move them to ->batch_done.
+	 */
+	rcu_batch_move(&sp->batch_done, &sp->batch_check1);
+
+	if (rcu_batch_empty(&sp->batch_check0))
+		return; /* no callbacks need to be advanced */
+	srcu_flip(sp);
+
+	/*
+	 * The callbacks in ->batch_check0 just finished their
+	 * first check zero and flip, so move them to ->batch_check1
+	 * for future checking on the other idx.
+	 */
+	rcu_batch_move(&sp->batch_check1, &sp->batch_check0);
+
+	/*
+	 * SRCU read-side critical sections are normally short, so check
+	 * at least twice in quick succession after a flip.
+	 */
+	trycount = trycount < 2 ? 2 : trycount;
+	if (!try_check_zero(sp, idx^1, trycount))
+		return; /* failed to advance, will try after SRCU_INTERVAL */
+
+	/*
+	 * The callbacks in ->batch_check1 have now waited for all
+	 * pre-existing readers using both idx values.  They are therefore
+	 * ready to invoke, so move them to ->batch_done.
+	 */
+	rcu_batch_move(&sp->batch_done, &sp->batch_check1);
+}
+
+/*
+ * 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.
+ */
+static void srcu_invoke_callbacks(struct srcu_struct *sp)
+{
+	int i;
+	struct rcu_head *head;
+
+	for (i = 0; i < SRCU_CALLBACK_BATCH; i++) {
+		head = rcu_batch_dequeue(&sp->batch_done);
+		if (!head)
+			break;
+		local_bh_disable();
+		head->func(head);
+		local_bh_enable();
+	}
+}
+
+/*
+ * Finished one round of SRCU grace period.  Start another if there are
+ * more SRCU callbacks queued, otherwise put SRCU into not-running state.
+ */
+static void srcu_reschedule(struct srcu_struct *sp)
+{
+	bool pending = true;
+
+	if (rcu_batch_empty(&sp->batch_done) &&
+	    rcu_batch_empty(&sp->batch_check1) &&
+	    rcu_batch_empty(&sp->batch_check0) &&
+	    rcu_batch_empty(&sp->batch_queue)) {
+		spin_lock_irq(&sp->queue_lock);
+		if (rcu_batch_empty(&sp->batch_done) &&
+		    rcu_batch_empty(&sp->batch_check1) &&
+		    rcu_batch_empty(&sp->batch_check0) &&
+		    rcu_batch_empty(&sp->batch_queue)) {
+			sp->running = false;
+			pending = false;
+		}
+		spin_unlock_irq(&sp->queue_lock);
+	}
+
+	if (pending)
+		queue_delayed_work(system_nrt_wq, &sp->work, SRCU_INTERVAL);
+}
+
+/*
+ * This is the work-queue function that handles SRCU grace periods.
+ */
+static void process_srcu(struct work_struct *work)
+{
+	struct srcu_struct *sp;
+
+	sp = container_of(work, struct srcu_struct, work.work);
+
+	srcu_collect_new(sp);
+	srcu_advance_batches(sp, 1);
+	srcu_invoke_callbacks(sp);
+	srcu_reschedule(sp);
+}

kernel/timer.c

@@ -861,7 +861,13 @@ EXPORT_SYMBOL(mod_timer);
  *
  * mod_timer_pinned() is a way to update the expire field of an
  * active timer (if the timer is inactive it will be activated)
- * and not allow the timer to be migrated to a different CPU.
+ * and to ensure that the timer is scheduled on the current CPU.
+ *
+ * Note that this does not prevent the timer from being migrated
+ * when the current CPU goes offline.  If this is a problem for
+ * you, use CPU-hotplug notifiers to handle it correctly, for
+ * example, cancelling the timer when the corresponding CPU goes
+ * offline.
  *
  * mod_timer_pinned(timer, expires) is equivalent to:
  *

lib/list_debug.c

@@ -10,6 +10,7 @@
 #include <linux/list.h>
 #include <linux/bug.h>
 #include <linux/kernel.h>
+#include <linux/rculist.h>
 
 /*
  * Insert a new entry between two known consecutive entries.
@@ -75,3 +76,24 @@ void list_del(struct list_head *entry)
 	entry->prev = LIST_POISON2;
 }
 EXPORT_SYMBOL(list_del);
+
+/*
+ * RCU variants.
+ */
+void __list_add_rcu(struct list_head *new,
+		    struct list_head *prev, struct list_head *next)
+{
+	WARN(next->prev != prev,
+		"list_add_rcu corruption. next->prev should be "
+		"prev (%p), but was %p. (next=%p).\n",
+		prev, next->prev, next);
+	WARN(prev->next != next,
+		"list_add_rcu corruption. prev->next should be "
+		"next (%p), but was %p. (prev=%p).\n",
+		next, prev->next, prev);
+	new->next = next;
+	new->prev = prev;
+	rcu_assign_pointer(list_next_rcu(prev), new);
+	next->prev = new;
+}
+EXPORT_SYMBOL(__list_add_rcu);