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

Pull RCU changes from Ingo Molnar:
 "This is the v3.5 RCU tree from Paul E.  McKenney:

 1) A set of improvements and fixes to the RCU_FAST_NO_HZ feature (with
    more on the way for 3.6).  Posted to LKML:
       https://lkml.org/lkml/2012/4/23/324 (commits 1-3 and 5),
       https://lkml.org/lkml/2012/4/16/611 (commit 4),
       https://lkml.org/lkml/2012/4/30/390 (commit 6), and
       https://lkml.org/lkml/2012/5/4/410 (commit 7, combined with
       the other commits for the convenience of the tester).

 2) Changes to make rcu_barrier() avoid disrupting execution of CPUs
    that have no RCU callbacks.  Posted to LKML:
       https://lkml.org/lkml/2012/4/23/322.

 3) A couple of commits that improve the efficiency of the interaction
    between preemptible RCU and the scheduler, these two being all that
    survived an abortive attempt to allow preemptible RCU's
    __rcu_read_lock() to be inlined.  The full set was posted to LKML at
    https://lkml.org/lkml/2012/4/14/143, and the first and third patches
    of that set remain.

 4) Lai Jiangshan's algorithmic implementation of SRCU, which includes
    call_srcu() and srcu_barrier().  A major feature of this new
    implementation is that synchronize_srcu() no longer disturbs the
    execution of other CPUs.  This work is based on earlier
    implementations by Peter Zijlstra and Paul E.  McKenney.  Posted to
    LKML: https://lkml.org/lkml/2012/2/22/82.

 5) A number of miscellaneous bug fixes and improvements which were
    posted to LKML at: https://lkml.org/lkml/2012/4/23/353 with
    subsequent updates posted to LKML."

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
  rcu: Make rcu_barrier() less disruptive
  rcu: Explicitly initialize RCU_FAST_NO_HZ per-CPU variables
  rcu: Make RCU_FAST_NO_HZ handle timer migration
  rcu: Update RCU maintainership
  rcu: Make exit_rcu() more precise and consolidate
  rcu: Move PREEMPT_RCU preemption to switch_to() invocation
  rcu: Ensure that RCU_FAST_NO_HZ timers expire on correct CPU
  rcu: Add rcutorture test for call_srcu()
  rcu: Implement per-domain single-threaded call_srcu() state machine
  rcu: Use single value to handle expedited SRCU grace periods
  rcu: Improve srcu_readers_active_idx()'s cache locality
  rcu: Remove unused srcu_barrier()
  rcu: Implement a variant of Peter's SRCU algorithm
  rcu: Improve SRCU's wait_idx() comments
  rcu: Flip ->completed only once per SRCU grace period
  rcu: Increment upper bit only for srcu_read_lock()
  rcu: Remove fast check path from __synchronize_srcu()
  rcu: Direct algorithmic SRCU implementation
  rcu: Introduce rcutorture testing for rcu_barrier()
  timer: Fix mod_timer_pinned() header comment
  ...

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

@@ -2333,18 +2333,100 @@ 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

@@ -5598,14 +5598,13 @@ 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
@@ -6122,6 +6121,15 @@ 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) \
-	list_entry_rcu((ptr)->next, type, member)
+#define list_first_or_null_rcu(ptr, 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
 

include/trace/events/rcu.h

@@ -292,6 +292,8 @@ TRACE_EVENT(rcu_dyntick,
  *	"More callbacks": Still more callbacks, try again to clear them out.
  *	"Callbacks drained": All callbacks processed, off to dyntick idle!
  *	"Timer": Timer fired to cause CPU to continue processing callbacks.
+ *	"Demigrate": Timer fired on wrong CPU, woke up correct CPU.
+ *	"Cleanup after idle": Idle exited, timer canceled.
  */
 TRACE_EVENT(rcu_prep_idle,
 

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
-	  RCU readers are to be boosted.  If you are working with CPU-bound
-	  real-time applications, you should specify a priority higher then
-	  the highest-priority CPU-bound application.
+	  This option specifies the real-time priority to which long-term
+	  preempted RCU readers are to be boosted.  If you are working
+	  with a real-time application that has one or more CPU-bound
+	  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/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_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_1	      (CONFIG_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)
@@ -371,6 +367,17 @@ struct rcu_state {
 
 	raw_spinlock_t onofflock;		/* exclude on/offline and */
 						/*  starting new GP. */
+	struct rcu_head *orphan_nxtlist;	/* Orphaned callbacks that */
+						/*  need a grace period. */
+	struct rcu_head **orphan_nxttail;	/* Tail of above. */
+	struct rcu_head *orphan_donelist;	/* Orphaned callbacks that */
+						/*  are ready to invoke. */
+	struct rcu_head **orphan_donetail;	/* Tail of above. */
+	long qlen_lazy;				/* Number of lazy callbacks. */
+	long qlen;				/* Total number of callbacks. */
+	struct task_struct *rcu_barrier_in_progress;
+						/* Task doing rcu_barrier(), */
+						/*  or NULL if no barrier. */
 	raw_spinlock_t fqslock;			/* Only one task forcing */
 						/*  quiescent states. */
 	unsigned long jiffies_force_qs;		/* Time at which to invoke */
@@ -423,7 +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,
@@ -471,6 +477,7 @@ static void __cpuinit rcu_prepare_kthreads(int cpu);
 static void rcu_prepare_for_idle_init(int cpu);
 static void rcu_cleanup_after_idle(int cpu);
 static void rcu_prepare_for_idle(int cpu);
+static void rcu_idle_count_callbacks_posted(void);
 static void print_cpu_stall_info_begin(void);
 static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
 static void print_cpu_stall_info_end(void);

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.
@@ -1938,6 +1914,14 @@ static void rcu_prepare_for_idle(int cpu)
 {
 }
 
+/*
+ * Don't bother keeping a running count of the number of RCU callbacks
+ * posted because CONFIG_RCU_FAST_NO_HZ=n.
+ */
+static void rcu_idle_count_callbacks_posted(void)
+{
+}
+
 #else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */
 
 /*
@@ -1978,11 +1962,20 @@ static void rcu_prepare_for_idle(int cpu)
 #define RCU_IDLE_GP_DELAY 6		/* Roughly one grace period. */
 #define RCU_IDLE_LAZY_GP_DELAY (6 * HZ)	/* Roughly six seconds. */
 
+/* Loop counter for rcu_prepare_for_idle(). */
 static DEFINE_PER_CPU(int, rcu_dyntick_drain);
+/* If rcu_dyntick_holdoff==jiffies, don't try to enter dyntick-idle mode. */
 static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
-static DEFINE_PER_CPU(struct hrtimer, rcu_idle_gp_timer);
-static ktime_t rcu_idle_gp_wait;	/* If some non-lazy callbacks. */
-static ktime_t rcu_idle_lazy_gp_wait;	/* If only lazy callbacks. */
+/* Timer to awaken the CPU if it enters dyntick-idle mode with callbacks. */
+static DEFINE_PER_CPU(struct timer_list, rcu_idle_gp_timer);
+/* Scheduled expiry time for rcu_idle_gp_timer to allow reposting. */
+static DEFINE_PER_CPU(unsigned long, rcu_idle_gp_timer_expires);
+/* Enable special processing on first attempt to enter dyntick-idle mode. */
+static DEFINE_PER_CPU(bool, rcu_idle_first_pass);
+/* Running count of non-lazy callbacks posted, never decremented. */
+static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted);
+/* Snapshot of rcu_nonlazy_posted to detect meaningful exits from idle. */
+static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted_snap);
 
 /*
  * Allow the CPU to enter dyntick-idle mode if either: (1) There are no
@@ -1995,6 +1988,8 @@ static ktime_t rcu_idle_lazy_gp_wait;	/* If only lazy callbacks. */
  */
 int rcu_needs_cpu(int cpu)
 {
+	/* Flag a new idle sojourn to the idle-entry state machine. */
+	per_cpu(rcu_idle_first_pass, cpu) = 1;
 	/* If no callbacks, RCU doesn't need the CPU. */
 	if (!rcu_cpu_has_callbacks(cpu))
 		return 0;
@@ -2044,17 +2039,35 @@ static bool rcu_cpu_has_nonlazy_callbacks(int cpu)
 	       rcu_preempt_cpu_has_nonlazy_callbacks(cpu);
 }
 
+/*
+ * Handler for smp_call_function_single().  The only point of this
+ * handler is to wake the CPU up, so the handler does only tracing.
+ */
+void rcu_idle_demigrate(void *unused)
+{
+	trace_rcu_prep_idle("Demigrate");
+}
+
 /*
  * Timer handler used to force CPU to start pushing its remaining RCU
  * callbacks in the case where it entered dyntick-idle mode with callbacks
  * pending.  The hander doesn't really need to do anything because the
  * real work is done upon re-entry to idle, or by the next scheduling-clock
  * interrupt should idle not be re-entered.
+ *
+ * One special case: the timer gets migrated without awakening the CPU
+ * on which the timer was scheduled on.  In this case, we must wake up
+ * that CPU.  We do so with smp_call_function_single().
  */
-static enum hrtimer_restart rcu_idle_gp_timer_func(struct hrtimer *hrtp)
+static void rcu_idle_gp_timer_func(unsigned long cpu_in)
 {
+	int cpu = (int)cpu_in;
+
 	trace_rcu_prep_idle("Timer");
-	return HRTIMER_NORESTART;
+	if (cpu != smp_processor_id())
+		smp_call_function_single(cpu, rcu_idle_demigrate, NULL, 0);
+	else
+		WARN_ON_ONCE(1); /* Getting here can hang the system... */
 }
 
 /*
@@ -2062,19 +2075,11 @@ static enum hrtimer_restart rcu_idle_gp_timer_func(struct hrtimer *hrtp)
  */
 static void rcu_prepare_for_idle_init(int cpu)
 {
-	static int firsttime = 1;
-	struct hrtimer *hrtp = &per_cpu(rcu_idle_gp_timer, cpu);
-
-	hrtimer_init(hrtp, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hrtp->function = rcu_idle_gp_timer_func;
-	if (firsttime) {
-		unsigned int upj = jiffies_to_usecs(RCU_IDLE_GP_DELAY);
-
-		rcu_idle_gp_wait = ns_to_ktime(upj * (u64)1000);
-		upj = jiffies_to_usecs(RCU_IDLE_LAZY_GP_DELAY);
-		rcu_idle_lazy_gp_wait = ns_to_ktime(upj * (u64)1000);
-		firsttime = 0;
-	}
+	per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
+	setup_timer(&per_cpu(rcu_idle_gp_timer, cpu),
+		    rcu_idle_gp_timer_func, cpu);
+	per_cpu(rcu_idle_gp_timer_expires, cpu) = jiffies - 1;
+	per_cpu(rcu_idle_first_pass, cpu) = 1;
 }
 
 /*
@@ -2084,7 +2089,8 @@ static void rcu_prepare_for_idle_init(int cpu)
  */
 static void rcu_cleanup_after_idle(int cpu)
 {
-	hrtimer_cancel(&per_cpu(rcu_idle_gp_timer, cpu));
+	del_timer(&per_cpu(rcu_idle_gp_timer, cpu));
+	trace_rcu_prep_idle("Cleanup after idle");
 }
 
 /*
@@ -2108,6 +2114,29 @@ static void rcu_cleanup_after_idle(int cpu)
  */
 static void rcu_prepare_for_idle(int cpu)
 {
+	struct timer_list *tp;
+
+	/*
+	 * If this is an idle re-entry, for example, due to use of
+	 * RCU_NONIDLE() or the new idle-loop tracing API within the idle
+	 * loop, then don't take any state-machine actions, unless the
+	 * momentary exit from idle queued additional non-lazy callbacks.
+	 * Instead, repost the rcu_idle_gp_timer if this CPU has callbacks
+	 * pending.
+	 */
+	if (!per_cpu(rcu_idle_first_pass, cpu) &&
+	    (per_cpu(rcu_nonlazy_posted, cpu) ==
+	     per_cpu(rcu_nonlazy_posted_snap, cpu))) {
+		if (rcu_cpu_has_callbacks(cpu)) {
+			tp = &per_cpu(rcu_idle_gp_timer, cpu);
+			mod_timer_pinned(tp, per_cpu(rcu_idle_gp_timer_expires, cpu));
+		}
+		return;
+	}
+	per_cpu(rcu_idle_first_pass, cpu) = 0;
+	per_cpu(rcu_nonlazy_posted_snap, cpu) =
+		per_cpu(rcu_nonlazy_posted, cpu) - 1;
+
 	/*
 	 * If there are no callbacks on this CPU, enter dyntick-idle mode.
 	 * Also reset state to avoid prejudicing later attempts.
@@ -2140,11 +2169,15 @@ static void rcu_prepare_for_idle(int cpu)
 		per_cpu(rcu_dyntick_drain, cpu) = 0;
 		per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
 		if (rcu_cpu_has_nonlazy_callbacks(cpu))
-			hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu),
-				      rcu_idle_gp_wait, HRTIMER_MODE_REL);
+			per_cpu(rcu_idle_gp_timer_expires, cpu) =
+					   jiffies + RCU_IDLE_GP_DELAY;
 		else
-			hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu),
-				      rcu_idle_lazy_gp_wait, HRTIMER_MODE_REL);
+			per_cpu(rcu_idle_gp_timer_expires, cpu) =
+					   jiffies + RCU_IDLE_LAZY_GP_DELAY;
+		tp = &per_cpu(rcu_idle_gp_timer, cpu);
+		mod_timer_pinned(tp, per_cpu(rcu_idle_gp_timer_expires, cpu));
+		per_cpu(rcu_nonlazy_posted_snap, cpu) =
+			per_cpu(rcu_nonlazy_posted, cpu);
 		return; /* Nothing more to do immediately. */
 	} else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) {
 		/* We have hit the limit, so time to give up. */
@@ -2184,6 +2217,19 @@ static void rcu_prepare_for_idle(int cpu)
 		trace_rcu_prep_idle("Callbacks drained");
 }
 
+/*
+ * Keep a running count of the number of non-lazy callbacks posted
+ * on this CPU.  This running counter (which is never decremented) allows
+ * rcu_prepare_for_idle() to detect when something out of the idle loop
+ * posts a callback, even if an equal number of callbacks are invoked.
+ * Of course, callbacks should only be posted from within a trace event
+ * designed to be called from idle or from within RCU_NONIDLE().
+ */
+static void rcu_idle_count_callbacks_posted(void)
+{
+	__this_cpu_add(rcu_nonlazy_posted, 1);
+}
+
 #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
 
 #ifdef CONFIG_RCU_CPU_STALL_INFO
@@ -2192,14 +2238,12 @@ static void rcu_prepare_for_idle(int cpu)
 
 static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
 {
-	struct hrtimer *hrtp = &per_cpu(rcu_idle_gp_timer, cpu);
+	struct timer_list *tltp = &per_cpu(rcu_idle_gp_timer, cpu);
 
-	sprintf(cp, "drain=%d %c timer=%lld",
+	sprintf(cp, "drain=%d %c timer=%lu",
 		per_cpu(rcu_dyntick_drain, cpu),
 		per_cpu(rcu_dyntick_holdoff, cpu) == jiffies ? 'H' : '.',
-		hrtimer_active(hrtp)
-			? ktime_to_us(hrtimer_get_remaining(hrtp))
-			: -1);
+		timer_pending(tltp) ? tltp->expires - jiffies : -1);
 }
 
 #else /* #ifdef CONFIG_RCU_FAST_NO_HZ */

kernel/rcutree_trace.c

@@ -271,13 +271,13 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 
 	gpnum = rsp->gpnum;
 	seq_printf(m, "c=%lu g=%lu s=%d jfq=%ld j=%x "
-		      "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n",
+		      "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n",
 		   rsp->completed, gpnum, rsp->fqs_state,
 		   (long)(rsp->jiffies_force_qs - jiffies),
 		   (int)(jiffies & 0xffff),
 		   rsp->n_force_qs, rsp->n_force_qs_ngp,
 		   rsp->n_force_qs - rsp->n_force_qs_ngp,
-		   rsp->n_force_qs_lh);
+		   rsp->n_force_qs_lh, rsp->qlen_lazy, rsp->qlen);
 	for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) {
 		if (rnp->level != level) {
 			seq_puts(m, "\n");

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/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);