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

Pull RCU update from Ingo Molnar:
 "The major features of this tree are:

     1. A first version of no-callbacks CPUs.  This version prohibits
        offlining CPU 0, but only when enabled via CONFIG_RCU_NOCB_CPU=y.
        Relaxing this constraint is in progress, but not yet ready
        for prime time.  These commits were posted to LKML at
        https://lkml.org/lkml/2012/10/30/724.

     2. Changes to SRCU that allows statically initialized srcu_struct
        structures.  These commits were posted to LKML at
        https://lkml.org/lkml/2012/10/30/296.

     3. Restructuring of RCU's debugfs output.  These commits were posted
        to LKML at https://lkml.org/lkml/2012/10/30/341.

     4. Additional CPU-hotplug/RCU improvements, posted to LKML at
        https://lkml.org/lkml/2012/10/30/327.
        Note that the commit eliminating __stop_machine() was judged to
        be too-high of risk, so is deferred to 3.9.

     5. Changes to RCU's idle interface, most notably a new module
        parameter that redirects normal grace-period operations to
        their expedited equivalents.  These were posted to LKML at
        https://lkml.org/lkml/2012/10/30/739.

     6. Additional diagnostics for RCU's CPU stall warning facility,
        posted to LKML at https://lkml.org/lkml/2012/10/30/315.
        The most notable change reduces the
        default RCU CPU stall-warning time from 60 seconds to 21 seconds,
        so that it once again happens sooner than the softlockup timeout.

     7. Documentation updates, which were posted to LKML at
        https://lkml.org/lkml/2012/10/30/280.
        A couple of late-breaking changes were posted at
        https://lkml.org/lkml/2012/11/16/634 and
        https://lkml.org/lkml/2012/11/16/547.

     8. Miscellaneous fixes, which were posted to LKML at
        https://lkml.org/lkml/2012/10/30/309.

     9. Finally, a fix for an lockdep-RCU splat was posted to LKML
        at https://lkml.org/lkml/2012/11/7/486."

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (49 commits)
  context_tracking: New context tracking susbsystem
  sched: Mark RCU reader in sched_show_task()
  rcu: Separate accounting of callbacks from callback-free CPUs
  rcu: Add callback-free CPUs
  rcu: Add documentation for the new rcuexp debugfs trace file
  rcu: Update documentation for TREE_RCU debugfs tracing
  rcu: Reduce default RCU CPU stall warning timeout
  rcu: Fix TINY_RCU rcu_is_cpu_rrupt_from_idle check
  rcu: Clarify memory-ordering properties of grace-period primitives
  rcu: Add new rcutorture module parameters to start/end test messages
  rcu: Remove list_for_each_continue_rcu()
  rcu: Fix batch-limit size problem
  rcu: Add tracing for synchronize_sched_expedited()
  rcu: Remove old debugfs interfaces and also RCU flavor name
  rcu: split 'rcuhier' to each flavor
  rcu: split 'rcugp' to each flavor
  rcu: split 'rcuboost' to each flavor
  rcu: split 'rcubarrier' to each flavor
  rcu: Fix tracing formatting
  rcu: Remove the interface "rcudata.csv"
  ...

Documentation/RCU/RTFP.txt

@@ -186,7 +186,7 @@ Bibtex Entries
 
 @article{Kung80
 ,author="H. T. Kung and Q. Lehman"
-,title="Concurrent Maintenance of Binary Search Trees"
+,title="Concurrent Manipulation of Binary Search Trees"
 ,Year="1980"
 ,Month="September"
 ,journal="ACM Transactions on Database Systems"

Documentation/RCU/checklist.txt

@@ -271,15 +271,14 @@ over a rather long period of time, but improvements are always welcome!
 	The same cautions apply to call_rcu_bh() and call_rcu_sched().
 
 9.	All RCU list-traversal primitives, which include
-	rcu_dereference(), list_for_each_entry_rcu(),
-	list_for_each_continue_rcu(), and list_for_each_safe_rcu(),
-	must be either within an RCU read-side critical section or
-	must be protected by appropriate update-side locks.  RCU
-	read-side critical sections are delimited by rcu_read_lock()
-	and rcu_read_unlock(), or by similar primitives such as
-	rcu_read_lock_bh() and rcu_read_unlock_bh(), in which case
-	the matching rcu_dereference() primitive must be used in order
-	to keep lockdep happy, in this case, rcu_dereference_bh().
+	rcu_dereference(), list_for_each_entry_rcu(), and
+	list_for_each_safe_rcu(), must be either within an RCU read-side
+	critical section or must be protected by appropriate update-side
+	locks.	RCU read-side critical sections are delimited by
+	rcu_read_lock() and rcu_read_unlock(), or by similar primitives
+	such as rcu_read_lock_bh() and rcu_read_unlock_bh(), in which
+	case the matching rcu_dereference() primitive must be used in
+	order to keep lockdep happy, in this case, rcu_dereference_bh().
 
 	The reason that it is permissible to use RCU list-traversal
 	primitives when the update-side lock is held is that doing so

Documentation/RCU/listRCU.txt

@@ -205,7 +205,7 @@ RCU ("read-copy update") its name.  The RCU code is as follows:
 				audit_copy_rule(&ne->rule, &e->rule);
 				ne->rule.action = newaction;
 				ne->rule.file_count = newfield_count;
-				list_replace_rcu(e, ne);
+				list_replace_rcu(&e->list, &ne->list);
 				call_rcu(&e->rcu, audit_free_rule);
 				return 0;
 			}

Documentation/RCU/rcuref.txt

@@ -20,7 +20,7 @@ release_referenced()			delete()
 {					{
     ...					    write_lock(&list_lock);
     atomic_dec(&el->rc, relfunc)	    ...
-    ...					    delete_element
+    ...					    remove_element
 }					    write_unlock(&list_lock);
  					    ...
 					    if (atomic_dec_and_test(&el->rc))
@@ -52,7 +52,7 @@ release_referenced()			delete()
 {					{
     ...					    spin_lock(&list_lock);
     if (atomic_dec_and_test(&el->rc))       ...
-        call_rcu(&el->head, el_free);       delete_element
+        call_rcu(&el->head, el_free);       remove_element
     ...                                     spin_unlock(&list_lock);
 } 					    ...
 					    if (atomic_dec_and_test(&el->rc))
@@ -64,3 +64,60 @@ Sometimes, a reference to the element needs to be obtained in the
 update (write) stream.  In such cases, atomic_inc_not_zero() might be
 overkill, since we hold the update-side spinlock.  One might instead
 use atomic_inc() in such cases.
+
+It is not always convenient to deal with "FAIL" in the
+search_and_reference() code path.  In such cases, the
+atomic_dec_and_test() may be moved from delete() to el_free()
+as follows:
+
+1.					2.
+add()					search_and_reference()
+{					{
+    alloc_object			    rcu_read_lock();
+    ...					    search_for_element
+    atomic_set(&el->rc, 1);		    atomic_inc(&el->rc);
+    spin_lock(&list_lock);		    ...
+
+    add_element				    rcu_read_unlock();
+    ...					}
+    spin_unlock(&list_lock);		4.
+}					delete()
+3.					{
+release_referenced()			    spin_lock(&list_lock);
+{					    ...
+    ...					    remove_element
+    if (atomic_dec_and_test(&el->rc))       spin_unlock(&list_lock);
+        kfree(el);			    ...
+    ...                                     call_rcu(&el->head, el_free);
+} 					    ...
+5.					}
+void el_free(struct rcu_head *rhp)
+{
+    release_referenced();
+}
+
+The key point is that the initial reference added by add() is not removed
+until after a grace period has elapsed following removal.  This means that
+search_and_reference() cannot find this element, which means that the value
+of el->rc cannot increase.  Thus, once it reaches zero, there are no
+readers that can or ever will be able to reference the element.  The
+element can therefore safely be freed.  This in turn guarantees that if
+any reader finds the element, that reader may safely acquire a reference
+without checking the value of the reference counter.
+
+In cases where delete() can sleep, synchronize_rcu() can be called from
+delete(), so that el_free() can be subsumed into delete as follows:
+
+4.
+delete()
+{
+    spin_lock(&list_lock);
+    ...
+    remove_element
+    spin_unlock(&list_lock);
+    ...
+    synchronize_rcu();
+    if (atomic_dec_and_test(&el->rc))
+    	kfree(el);
+    ...
+}

Documentation/RCU/whatisRCU.txt

@@ -499,6 +499,8 @@ The foo_reclaim() function might appear as follows:
 	{
 		struct foo *fp = container_of(rp, struct foo, rcu);
 
+		foo_cleanup(fp->a);
+
 		kfree(fp);
 	}
 
@@ -521,6 +523,12 @@ o	Use call_rcu() -after- removing a data element from an
 	read-side critical sections that might be referencing that
 	data item.
 
+If the callback for call_rcu() is not doing anything more than calling
+kfree() on the structure, you can use kfree_rcu() instead of call_rcu()
+to avoid having to write your own callback:
+
+	kfree_rcu(old_fp, rcu);
+
 Again, see checklist.txt for additional rules governing the use of RCU.
 
 
@@ -773,8 +781,8 @@ a single atomic update, converting to RCU will require special care.
 
 Also, the presence of synchronize_rcu() means that the RCU version of
 delete() can now block.  If this is a problem, there is a callback-based
-mechanism that never blocks, namely call_rcu(), that can be used in
-place of synchronize_rcu().
+mechanism that never blocks, namely call_rcu() or kfree_rcu(), that can
+be used in place of synchronize_rcu().
 
 
 7.  FULL LIST OF RCU APIs
@@ -789,9 +797,7 @@ RCU list traversal:
 	list_for_each_entry_rcu
 	hlist_for_each_entry_rcu
 	hlist_nulls_for_each_entry_rcu
-
-	list_for_each_continue_rcu	(to be deprecated in favor of new
-					 list_for_each_entry_continue_rcu)
+	list_for_each_entry_continue_rcu
 
 RCU pointer/list update:
 
@@ -813,6 +819,7 @@ RCU:	Critical sections	Grace period		Barrier
 	rcu_read_unlock		synchronize_rcu
 	rcu_dereference		synchronize_rcu_expedited
 				call_rcu
+				kfree_rcu
 
 
 bh:	Critical sections	Grace period		Barrier

Documentation/kernel-parameters.txt

@@ -2394,6 +2394,27 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	ramdisk_size=	[RAM] Sizes of RAM disks in kilobytes
 			See Documentation/blockdev/ramdisk.txt.
 
+	rcu_nocbs=	[KNL,BOOT]
+			In kernels built with CONFIG_RCU_NOCB_CPU=y, set
+			the specified list of CPUs to be no-callback CPUs.
+			Invocation of these CPUs' RCU callbacks will
+			be offloaded to "rcuoN" kthreads created for
+			that purpose.  This reduces OS jitter on the
+			offloaded CPUs, which can be useful for HPC and
+			real-time workloads.  It can also improve energy
+			efficiency for asymmetric multiprocessors.
+
+	rcu_nocbs_poll	[KNL,BOOT]
+			Rather than requiring that offloaded CPUs
+			(specified by rcu_nocbs= above) explicitly
+			awaken the corresponding "rcuoN" kthreads,
+			make these kthreads poll for callbacks.
+			This improves the real-time response for the
+			offloaded CPUs by relieving them of the need to
+			wake up the corresponding kthread, but degrades
+			energy efficiency by requiring that the kthreads
+			periodically wake up to do the polling.
+
 	rcutree.blimit=	[KNL,BOOT]
 			Set maximum number of finished RCU callbacks to process
 			in one batch.

Documentation/memory-barriers.txt

@@ -251,12 +251,13 @@ And there are a number of things that _must_ or _must_not_ be assumed:
 
      And for:
 
-	*A = X; Y = *A;
+	*A = X; *(A + 4) = Y;
 
-     we may get either of:
+     we may get any of:
 
-	STORE *A = X; Y = LOAD *A;
-	STORE *A = Y = X;
+	STORE *A = X; STORE *(A + 4) = Y;
+	STORE *(A + 4) = Y; STORE *A = X;
+	STORE {*A, *(A + 4) } = {X, Y};
 
 
 =========================

arch/Kconfig

@@ -300,15 +300,16 @@ config SECCOMP_FILTER
 
 	  See Documentation/prctl/seccomp_filter.txt for details.
 
-config HAVE_RCU_USER_QS
+config HAVE_CONTEXT_TRACKING
 	bool
 	help
-	  Provide kernel entry/exit hooks necessary for userspace
-	  RCU extended quiescent state. Syscalls need to be wrapped inside
-	  rcu_user_exit()-rcu_user_enter() through the slow path using
-	  TIF_NOHZ flag. Exceptions handlers must be wrapped as well. Irqs
-	  are already protected inside rcu_irq_enter/rcu_irq_exit() but
-	  preemption or signal handling on irq exit still need to be protected.
+	  Provide kernel/user boundaries probes necessary for subsystems
+	  that need it, such as userspace RCU extended quiescent state.
+	  Syscalls need to be wrapped inside user_exit()-user_enter() through
+	  the slow path using TIF_NOHZ flag. Exceptions handlers must be
+	  wrapped as well. Irqs are already protected inside
+	  rcu_irq_enter/rcu_irq_exit() but preemption or signal handling on
+	  irq exit still need to be protected.
 
 config HAVE_VIRT_CPU_ACCOUNTING
 	bool

arch/um/drivers/mconsole_kern.c

@@ -648,7 +648,7 @@ static void stack_proc(void *arg)
 	struct task_struct *from = current, *to = arg;
 
 	to->thread.saved_task = from;
-	rcu_switch(from, to);
+	rcu_user_hooks_switch(from, to);
 	switch_to(from, to, from);
 }
 

arch/x86/Kconfig

@@ -106,7 +106,7 @@ config X86
 	select KTIME_SCALAR if X86_32
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
-	select HAVE_RCU_USER_QS if X86_64
+	select HAVE_CONTEXT_TRACKING if X86_64
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select GENERIC_KERNEL_THREAD
 	select GENERIC_KERNEL_EXECVE

arch/x86/include/asm/rcu.h → arch/x86/include/asm/context_tracking.h

-#ifndef _ASM_X86_RCU_H
-#define _ASM_X86_RCU_H
+#ifndef _ASM_X86_CONTEXT_TRACKING_H
+#define _ASM_X86_CONTEXT_TRACKING_H
 
 #ifndef __ASSEMBLY__
-
-#include <linux/rcupdate.h>
+#include <linux/context_tracking.h>
 #include <asm/ptrace.h>
 
 static inline void exception_enter(struct pt_regs *regs)
 {
-	rcu_user_exit();
+	user_exit();
 }
 
 static inline void exception_exit(struct pt_regs *regs)
 {
-#ifdef CONFIG_RCU_USER_QS
+#ifdef CONFIG_CONTEXT_TRACKING
 	if (user_mode(regs))
-		rcu_user_enter();
+		user_enter();
 #endif
 }
 
 #else /* __ASSEMBLY__ */
 
-#ifdef CONFIG_RCU_USER_QS
+#ifdef CONFIG_CONTEXT_TRACKING
 # define SCHEDULE_USER call schedule_user
 #else
 # define SCHEDULE_USER call schedule

arch/x86/kernel/entry_64.S

@@ -56,7 +56,7 @@
 #include <asm/ftrace.h>
 #include <asm/percpu.h>
 #include <asm/asm.h>
-#include <asm/rcu.h>
+#include <asm/context_tracking.h>
 #include <asm/smap.h>
 #include <linux/err.h>
 

arch/x86/kernel/ptrace.c

@@ -23,6 +23,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/rcupdate.h>
 #include <linux/module.h>
+#include <linux/context_tracking.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -1491,7 +1492,7 @@ long syscall_trace_enter(struct pt_regs *regs)
 {
 	long ret = 0;
 
-	rcu_user_exit();
+	user_exit();
 
 	/*
 	 * If we stepped into a sysenter/syscall insn, it trapped in
@@ -1546,7 +1547,7 @@ void syscall_trace_leave(struct pt_regs *regs)
 	 * or do_notify_resume(), in which case we can be in RCU
 	 * user mode.
 	 */
-	rcu_user_exit();
+	user_exit();
 
 	audit_syscall_exit(regs);
 
@@ -1564,5 +1565,5 @@ void syscall_trace_leave(struct pt_regs *regs)
 	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, step);
 
-	rcu_user_enter();
+	user_enter();
 }

arch/x86/kernel/signal.c

@@ -22,6 +22,7 @@
 #include <linux/uaccess.h>
 #include <linux/user-return-notifier.h>
 #include <linux/uprobes.h>
+#include <linux/context_tracking.h>
 
 #include <asm/processor.h>
 #include <asm/ucontext.h>
@@ -816,7 +817,7 @@ static void do_signal(struct pt_regs *regs)
 void
 do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 {
-	rcu_user_exit();
+	user_exit();
 
 #ifdef CONFIG_X86_MCE
 	/* notify userspace of pending MCEs */
@@ -838,7 +839,7 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 	if (thread_info_flags & _TIF_USER_RETURN_NOTIFY)
 		fire_user_return_notifiers();
 
-	rcu_user_enter();
+	user_enter();
 }
 
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where)

arch/x86/kernel/traps.c

@@ -55,7 +55,7 @@
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
 #include <asm/mce.h>
-#include <asm/rcu.h>
+#include <asm/context_tracking.h>
 
 #include <asm/mach_traps.h>
 

arch/x86/mm/fault.c

@@ -18,7 +18,7 @@
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
 #include <asm/kmemcheck.h>		/* kmemcheck_*(), ...		*/
 #include <asm/fixmap.h>			/* VSYSCALL_START		*/
-#include <asm/rcu.h>			/* exception_enter(), ...	*/
+#include <asm/context_tracking.h>	/* exception_enter(), ...	*/
 
 /*
  * Page fault error code bits:

include/linux/context_tracking.h

+#ifndef _LINUX_CONTEXT_TRACKING_H
+#define _LINUX_CONTEXT_TRACKING_H
+
+#ifdef CONFIG_CONTEXT_TRACKING
+#include <linux/sched.h>
+
+extern void user_enter(void);
+extern void user_exit(void);
+extern void context_tracking_task_switch(struct task_struct *prev,
+					 struct task_struct *next);
+#else
+static inline void user_enter(void) { }
+static inline void user_exit(void) { }
+static inline void context_tracking_task_switch(struct task_struct *prev,
+						struct task_struct *next) { }
+#endif /* !CONFIG_CONTEXT_TRACKING */
+
+#endif

include/linux/rculist.h

@@ -286,23 +286,6 @@ static inline void list_splice_init_rcu(struct list_head *list,
 		&pos->member != (head); \
 		pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
 
-
-/**
- * list_for_each_continue_rcu
- * @pos:	the &struct list_head to use as a loop cursor.
- * @head:	the head for your list.
- *
- * Iterate over an rcu-protected list, continuing after current point.
- *
- * This list-traversal primitive may safely run concurrently with
- * the _rcu list-mutation primitives such as list_add_rcu()
- * as long as the traversal is guarded by rcu_read_lock().
- */
-#define list_for_each_continue_rcu(pos, head) \
-	for ((pos) = rcu_dereference_raw(list_next_rcu(pos)); \
-		(pos) != (head); \
-		(pos) = rcu_dereference_raw(list_next_rcu(pos)))
-
 /**
  * list_for_each_entry_continue_rcu - continue iteration over list of given type
  * @pos:	the type * to use as a loop cursor.

include/linux/rcupdate.h

@@ -90,6 +90,25 @@ extern void do_trace_rcu_torture_read(char *rcutorturename,
  * that started after call_rcu() was invoked.  RCU read-side critical
  * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
  * and may be nested.
+ *
+ * Note that all CPUs must agree that the grace period extended beyond
+ * all pre-existing RCU read-side critical section.  On systems with more
+ * than one CPU, this means that when "func()" is invoked, each CPU is
+ * guaranteed to have executed a full memory barrier since the end of its
+ * last RCU read-side critical section whose beginning preceded the call
+ * to call_rcu().  It also means that each CPU executing an RCU read-side
+ * critical section that continues beyond the start of "func()" must have
+ * executed a memory barrier after the call_rcu() but before the beginning
+ * of that RCU read-side critical section.  Note that these guarantees
+ * include CPUs that are offline, idle, or executing in user mode, as
+ * well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * resulting RCU callback function "func()", then both CPU A and CPU B are
+ * guaranteed to execute a full memory barrier during the time interval
+ * between the call to call_rcu() and the invocation of "func()" -- even
+ * if CPU A and CPU B are the same CPU (but again only if the system has
+ * more than one CPU).
  */
 extern void call_rcu(struct rcu_head *head,
 			      void (*func)(struct rcu_head *head));
@@ -118,6 +137,9 @@ extern void call_rcu(struct rcu_head *head,
  *  OR
  *  - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
  *  These may be nested.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
  */
 extern void call_rcu_bh(struct rcu_head *head,
 			void (*func)(struct rcu_head *head));
@@ -137,6 +159,9 @@ extern void call_rcu_bh(struct rcu_head *head,
  *  OR
  *  anything that disables preemption.
  *  These may be nested.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
  */
 extern void call_rcu_sched(struct rcu_head *head,
 			   void (*func)(struct rcu_head *rcu));
@@ -197,13 +222,13 @@ extern void rcu_user_enter(void);
 extern void rcu_user_exit(void);
 extern void rcu_user_enter_after_irq(void);
 extern void rcu_user_exit_after_irq(void);
-extern void rcu_user_hooks_switch(struct task_struct *prev,
-				  struct task_struct *next);
 #else
 static inline void rcu_user_enter(void) { }
 static inline void rcu_user_exit(void) { }
 static inline void rcu_user_enter_after_irq(void) { }
 static inline void rcu_user_exit_after_irq(void) { }
+static inline void rcu_user_hooks_switch(struct task_struct *prev,
+					 struct task_struct *next) { }
 #endif /* CONFIG_RCU_USER_QS */
 
 extern void exit_rcu(void);

include/linux/sched.h

@@ -109,6 +109,8 @@ extern void update_cpu_load_nohz(void);
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
+extern void dump_cpu_task(int cpu);
+
 struct seq_file;
 struct cfs_rq;
 struct task_group;
@@ -1845,14 +1847,6 @@ static inline void rcu_copy_process(struct task_struct *p)
 
 #endif
 
-static inline void rcu_switch(struct task_struct *prev,
-			      struct task_struct *next)
-{
-#ifdef CONFIG_RCU_USER_QS
-	rcu_user_hooks_switch(prev, next);
-#endif
-}
-
 static inline void tsk_restore_flags(struct task_struct *task,
 				unsigned long orig_flags, unsigned long flags)
 {

include/linux/srcu.h

@@ -16,8 +16,10 @@
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2006
+ * Copyright (C) Fujitsu, 2012
  *
  * Author: Paul McKenney <paulmck@us.ibm.com>
+ *	   Lai Jiangshan <laijs@cn.fujitsu.com>
  *
  * For detailed explanation of Read-Copy Update mechanism see -
  * 		Documentation/RCU/ *.txt
@@ -40,6 +42,8 @@ struct rcu_batch {
 	struct rcu_head *head, **tail;
 };
 
+#define RCU_BATCH_INIT(name) { NULL, &(name.head) }
+
 struct srcu_struct {
 	unsigned completed;
 	struct srcu_struct_array __percpu *per_cpu_ref;
@@ -70,12 +74,42 @@ int __init_srcu_struct(struct srcu_struct *sp, const char *name,
 	__init_srcu_struct((sp), #sp, &__srcu_key); \
 })
 
+#define __SRCU_DEP_MAP_INIT(srcu_name)	.dep_map = { .name = #srcu_name },
 #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 int init_srcu_struct(struct srcu_struct *sp);
 
+#define __SRCU_DEP_MAP_INIT(srcu_name)
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
+void process_srcu(struct work_struct *work);
+
+#define __SRCU_STRUCT_INIT(name)					\
+	{								\
+		.completed = -300,					\
+		.per_cpu_ref = &name##_srcu_array,			\
+		.queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock),	\
+		.running = false,					\
+		.batch_queue = RCU_BATCH_INIT(name.batch_queue),	\
+		.batch_check0 = RCU_BATCH_INIT(name.batch_check0),	\
+		.batch_check1 = RCU_BATCH_INIT(name.batch_check1),	\
+		.batch_done = RCU_BATCH_INIT(name.batch_done),		\
+		.work = __DELAYED_WORK_INITIALIZER(name.work, process_srcu, 0),\
+		__SRCU_DEP_MAP_INIT(name)				\
+	}
+
+/*
+ * define and init a srcu struct at build time.
+ * dont't call init_srcu_struct() nor cleanup_srcu_struct() on it.
+ */
+#define DEFINE_SRCU(name)						\
+	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
+	struct srcu_struct name = __SRCU_STRUCT_INIT(name);
+
+#define DEFINE_STATIC_SRCU(name)					\
+	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
+	static struct srcu_struct name = __SRCU_STRUCT_INIT(name);
+
 /**
  * call_srcu() - Queue a callback for invocation after an SRCU grace period
  * @sp: srcu_struct in queue the callback

include/trace/events/rcu.h

@@ -549,6 +549,7 @@ TRACE_EVENT(rcu_torture_read,
  *	"EarlyExit": rcu_barrier_callback() piggybacked, thus early exit.
  *	"Inc1": rcu_barrier_callback() piggyback check counter incremented.
  *	"Offline": rcu_barrier_callback() found offline CPU
+ *	"OnlineNoCB": rcu_barrier_callback() found online no-CBs CPU.
  *	"OnlineQ": rcu_barrier_callback() found online CPU with callbacks.
  *	"OnlineNQ": rcu_barrier_callback() found online CPU, no callbacks.
  *	"IRQ": An rcu_barrier_callback() callback posted on remote CPU.

init/Kconfig

@@ -486,35 +486,35 @@ config PREEMPT_RCU
 	  This option enables preemptible-RCU code that is common between
 	  the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
 
+config CONTEXT_TRACKING
+       bool
+
 config RCU_USER_QS
 	bool "Consider userspace as in RCU extended quiescent state"
-	depends on HAVE_RCU_USER_QS && SMP
+	depends on HAVE_CONTEXT_TRACKING && SMP
+	select CONTEXT_TRACKING
 	help
 	  This option sets hooks on kernel / userspace boundaries and
 	  puts RCU in extended quiescent state when the CPU runs in
 	  userspace. It means that when a CPU runs in userspace, it is
 	  excluded from the global RCU state machine and thus doesn't
-	  to keep the timer tick on for RCU.
+	  try to keep the timer tick on for RCU.
 
 	  Unless you want to hack and help the development of the full
-	  tickless feature, you shouldn't enable this option. It adds
-	  unnecessary overhead.
+	  dynticks mode, you shouldn't enable this option.  It also
+	  adds unnecessary overhead.
 
 	  If unsure say N
 
-config RCU_USER_QS_FORCE
-	bool "Force userspace extended QS by default"
-	depends on RCU_USER_QS
+config CONTEXT_TRACKING_FORCE
+	bool "Force context tracking"
+	depends on CONTEXT_TRACKING
 	help
-	  Set the hooks in user/kernel boundaries by default in order to
-	  test this feature that treats userspace as an extended quiescent
-	  state until we have a real user like a full adaptive nohz option.
-
-	  Unless you want to hack and help the development of the full
-	  tickless feature, you shouldn't enable this option. It adds
-	  unnecessary overhead.
-
-	  If unsure say N
+	  Probe on user/kernel boundaries by default in order to
+	  test the features that rely on it such as userspace RCU extended
+	  quiescent states.
+	  This test is there for debugging until we have a real user like the
+	  full dynticks mode.
 
 config RCU_FANOUT
 	int "Tree-based hierarchical RCU fanout value"
@@ -582,14 +582,13 @@ config RCU_FAST_NO_HZ
 	depends on NO_HZ && SMP
 	default n
 	help
-	  This option causes RCU to attempt to accelerate grace periods
-	  in order to allow CPUs to enter dynticks-idle state more
-	  quickly.  On the other hand, this option increases the overhead
-	  of the dynticks-idle checking, particularly on systems with
-	  large numbers of CPUs.
+	  This option causes RCU to attempt to accelerate grace periods in
+	  order to allow CPUs to enter dynticks-idle state more quickly.
+	  On the other hand, this option increases the overhead of the
+	  dynticks-idle checking, thus degrading scheduling latency.
 
-	  Say Y if energy efficiency is critically important, particularly
-	  	if you have relatively few CPUs.
+	  Say Y if energy efficiency is critically important, and you don't
+	  	care about real-time response.
 
 	  Say N if you are unsure.
 
@@ -655,6 +654,28 @@ config RCU_BOOST_DELAY
 
 	  Accept the default if unsure.
 
+config RCU_NOCB_CPU
+	bool "Offload RCU callback processing from boot-selected CPUs"
+	depends on TREE_RCU || TREE_PREEMPT_RCU
+	default n
+	help
+	  Use this option to reduce OS jitter for aggressive HPC or
+	  real-time workloads.	It can also be used to offload RCU
+	  callback invocation to energy-efficient CPUs in battery-powered
+	  asymmetric multiprocessors.
+
+	  This option offloads callback invocation from the set of
+	  CPUs specified at boot time by the rcu_nocbs parameter.
+	  For each such CPU, a kthread ("rcuoN") will be created to
+	  invoke callbacks, where the "N" is the CPU being offloaded.
+	  Nothing prevents this kthread from running on the specified
+	  CPUs, but (1) the kthreads may be preempted between each
+	  callback, and (2) affinity or cgroups can be used to force
+	  the kthreads to run on whatever set of CPUs is desired.
+
+	  Say Y here if you want reduced OS jitter on selected CPUs.
+	  Say N here if you are unsure.
+
 endmenu # "RCU Subsystem"
 
 config IKCONFIG

kernel/Makefile

@@ -110,6 +110,7 @@ obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
 obj-$(CONFIG_PADATA) += padata.o
 obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
 obj-$(CONFIG_JUMP_LABEL) += jump_label.o
+obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o
 
 $(obj)/configs.o: $(obj)/config_data.h
 

kernel/context_tracking.c

+#include <linux/context_tracking.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+
+struct context_tracking {
+	/*
+	 * When active is false, hooks are not set to
+	 * minimize overhead: TIF flags are cleared
+	 * and calls to user_enter/exit are ignored. This
+	 * may be further optimized using static keys.
+	 */
+	bool active;
+	enum {
+		IN_KERNEL = 0,
+		IN_USER,
+	} state;
+};
+
+static DEFINE_PER_CPU(struct context_tracking, context_tracking) = {
+#ifdef CONFIG_CONTEXT_TRACKING_FORCE
+	.active = true,
+#endif
+};
+
+void user_enter(void)
+{
+	unsigned long flags;
+
+	/*
+	 * Some contexts may involve an exception occuring in an irq,
+	 * leading to that nesting:
+	 * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
+	 * This would mess up the dyntick_nesting count though. And rcu_irq_*()
+	 * helpers are enough to protect RCU uses inside the exception. So
+	 * just return immediately if we detect we are in an IRQ.
+	 */
+	if (in_interrupt())
+		return;
+
+	WARN_ON_ONCE(!current->mm);
+
+	local_irq_save(flags);
+	if (__this_cpu_read(context_tracking.active) &&
+	    __this_cpu_read(context_tracking.state) != IN_USER) {
+		__this_cpu_write(context_tracking.state, IN_USER);
+		rcu_user_enter();
+	}
+	local_irq_restore(flags);
+}
+
+void user_exit(void)
+{
+	unsigned long flags;
+
+	/*
+	 * Some contexts may involve an exception occuring in an irq,
+	 * leading to that nesting:
+	 * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
+	 * This would mess up the dyntick_nesting count though. And rcu_irq_*()
+	 * helpers are enough to protect RCU uses inside the exception. So
+	 * just return immediately if we detect we are in an IRQ.
+	 */
+	if (in_interrupt())
+		return;
+
+	local_irq_save(flags);
+	if (__this_cpu_read(context_tracking.state) == IN_USER) {
+		__this_cpu_write(context_tracking.state, IN_KERNEL);
+		rcu_user_exit();
+	}
+	local_irq_restore(flags);
+}
+
+void context_tracking_task_switch(struct task_struct *prev,
+			     struct task_struct *next)
+{
+	if (__this_cpu_read(context_tracking.active)) {
+		clear_tsk_thread_flag(prev, TIF_NOHZ);
+		set_tsk_thread_flag(next, TIF_NOHZ);
+	}
+}

kernel/ksysfs.c

@@ -140,6 +140,23 @@ static ssize_t fscaps_show(struct kobject *kobj,
 }
 KERNEL_ATTR_RO(fscaps);
 
+int rcu_expedited;
+static ssize_t rcu_expedited_show(struct kobject *kobj,
+				  struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", rcu_expedited);
+}
+static ssize_t rcu_expedited_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t count)
+{
+	if (kstrtoint(buf, 0, &rcu_expedited))
+		return -EINVAL;
+
+	return count;
+}
+KERNEL_ATTR_RW(rcu_expedited);
+
 /*
  * Make /sys/kernel/notes give the raw contents of our kernel .notes section.
  */
@@ -179,6 +196,7 @@ static struct attribute * kernel_attrs[] = {
 	&kexec_crash_size_attr.attr,
 	&vmcoreinfo_attr.attr,
 #endif
+	&rcu_expedited_attr.attr,
 	NULL
 };
 

kernel/rcu.h

@@ -109,4 +109,6 @@ static inline bool __rcu_reclaim(char *rn, struct rcu_head *head)
 	}
 }
 
+extern int rcu_expedited;
+
 #endif /* __LINUX_RCU_H */

kernel/rcupdate.c

@@ -46,12 +46,15 @@
 #include <linux/export.h>
 #include <linux/hardirq.h>
 #include <linux/delay.h>
+#include <linux/module.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/rcu.h>
 
 #include "rcu.h"
 
+module_param(rcu_expedited, int, 0);
+
 #ifdef CONFIG_PREEMPT_RCU
 
 /*

kernel/rcutiny.c

@@ -195,7 +195,7 @@ EXPORT_SYMBOL(rcu_is_cpu_idle);
  */
 int rcu_is_cpu_rrupt_from_idle(void)
 {
-	return rcu_dynticks_nesting <= 0;
+	return rcu_dynticks_nesting <= 1;
 }
 
 /*

kernel/rcutiny_plugin.h

@@ -706,7 +706,10 @@ void synchronize_rcu(void)
 		return;
 
 	/* Once we get past the fastpath checks, same code as rcu_barrier(). */
-	rcu_barrier();
+	if (rcu_expedited)
+		synchronize_rcu_expedited();
+	else
+		rcu_barrier();
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 

kernel/rcutorture.c

@@ -339,7 +339,6 @@ rcu_stutter_wait(char *title)
 
 struct rcu_torture_ops {
 	void (*init)(void);
-	void (*cleanup)(void);
 	int (*readlock)(void);
 	void (*read_delay)(struct rcu_random_state *rrsp);
 	void (*readunlock)(int idx);
@@ -431,7 +430,6 @@ static void rcu_torture_deferred_free(struct rcu_torture *p)
 
 static struct rcu_torture_ops rcu_ops = {
 	.init		= NULL,
-	.cleanup	= NULL,
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,
 	.readunlock	= rcu_torture_read_unlock,
@@ -475,7 +473,6 @@ static void rcu_sync_torture_init(void)
 
 static struct rcu_torture_ops rcu_sync_ops = {
 	.init		= rcu_sync_torture_init,
-	.cleanup	= NULL,
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,
 	.readunlock	= rcu_torture_read_unlock,
@@ -493,7 +490,6 @@ static struct rcu_torture_ops rcu_sync_ops = {
 
 static struct rcu_torture_ops rcu_expedited_ops = {
 	.init		= rcu_sync_torture_init,
-	.cleanup	= NULL,
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_torture_read_unlock,
@@ -536,7 +532,6 @@ static void rcu_bh_torture_deferred_free(struct rcu_torture *p)
 
 static struct rcu_torture_ops rcu_bh_ops = {
 	.init		= NULL,
-	.cleanup	= NULL,
 	.readlock	= rcu_bh_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_bh_torture_read_unlock,
@@ -553,7 +548,6 @@ static struct rcu_torture_ops rcu_bh_ops = {
 
 static struct rcu_torture_ops rcu_bh_sync_ops = {
 	.init		= rcu_sync_torture_init,
-	.cleanup	= NULL,
 	.readlock	= rcu_bh_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_bh_torture_read_unlock,
@@ -570,7 +564,6 @@ static struct rcu_torture_ops rcu_bh_sync_ops = {
 
 static struct rcu_torture_ops rcu_bh_expedited_ops = {
 	.init		= rcu_sync_torture_init,
-	.cleanup	= NULL,
 	.readlock	= rcu_bh_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_bh_torture_read_unlock,
@@ -589,19 +582,7 @@ static struct rcu_torture_ops rcu_bh_expedited_ops = {
  * Definitions for srcu torture testing.
  */
 
-static struct srcu_struct srcu_ctl;
-
-static void srcu_torture_init(void)
-{
-	init_srcu_struct(&srcu_ctl);
-	rcu_sync_torture_init();
-}
-
-static void srcu_torture_cleanup(void)
-{
-	synchronize_srcu(&srcu_ctl);
-	cleanup_srcu_struct(&srcu_ctl);
-}
+DEFINE_STATIC_SRCU(srcu_ctl);
 
 static int srcu_torture_read_lock(void) __acquires(&srcu_ctl)
 {
@@ -672,8 +653,7 @@ static int srcu_torture_stats(char *page)
 }
 
 static struct rcu_torture_ops srcu_ops = {
-	.init		= srcu_torture_init,
-	.cleanup	= srcu_torture_cleanup,
+	.init		= rcu_sync_torture_init,
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock,
@@ -687,8 +667,7 @@ static struct rcu_torture_ops srcu_ops = {
 };
 
 static struct rcu_torture_ops srcu_sync_ops = {
-	.init		= srcu_torture_init,
-	.cleanup	= srcu_torture_cleanup,
+	.init		= rcu_sync_torture_init,
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock,
@@ -712,8 +691,7 @@ static void srcu_torture_read_unlock_raw(int idx) __releases(&srcu_ctl)
 }
 
 static struct rcu_torture_ops srcu_raw_ops = {
-	.init		= srcu_torture_init,
-	.cleanup	= srcu_torture_cleanup,
+	.init		= rcu_sync_torture_init,
 	.readlock	= srcu_torture_read_lock_raw,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock_raw,
@@ -727,8 +705,7 @@ static struct rcu_torture_ops srcu_raw_ops = {
 };
 
 static struct rcu_torture_ops srcu_raw_sync_ops = {
-	.init		= srcu_torture_init,
-	.cleanup	= srcu_torture_cleanup,
+	.init		= rcu_sync_torture_init,
 	.readlock	= srcu_torture_read_lock_raw,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock_raw,
@@ -747,8 +724,7 @@ static void srcu_torture_synchronize_expedited(void)
 }
 
 static struct rcu_torture_ops srcu_expedited_ops = {
-	.init		= srcu_torture_init,
-	.cleanup	= srcu_torture_cleanup,
+	.init		= rcu_sync_torture_init,
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock,
@@ -783,7 +759,6 @@ static void rcu_sched_torture_deferred_free(struct rcu_torture *p)
 
 static struct rcu_torture_ops sched_ops = {
 	.init		= rcu_sync_torture_init,
-	.cleanup	= NULL,
 	.readlock	= sched_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= sched_torture_read_unlock,
@@ -799,7 +774,6 @@ static struct rcu_torture_ops sched_ops = {
 
 static struct rcu_torture_ops sched_sync_ops = {
 	.init		= rcu_sync_torture_init,
-	.cleanup	= NULL,
 	.readlock	= sched_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= sched_torture_read_unlock,
@@ -814,7 +788,6 @@ static struct rcu_torture_ops sched_sync_ops = {
 
 static struct rcu_torture_ops sched_expedited_ops = {
 	.init		= rcu_sync_torture_init,
-	.cleanup	= NULL,
 	.readlock	= sched_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= sched_torture_read_unlock,
@@ -1396,12 +1369,16 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, char *tag)
 		 "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d "
 		 "test_boost=%d/%d test_boost_interval=%d "
 		 "test_boost_duration=%d shutdown_secs=%d "
+		 "stall_cpu=%d stall_cpu_holdoff=%d "
+		 "n_barrier_cbs=%d "
 		 "onoff_interval=%d onoff_holdoff=%d\n",
 		 torture_type, tag, nrealreaders, nfakewriters,
 		 stat_interval, verbose, test_no_idle_hz, shuffle_interval,
 		 stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
 		 test_boost, cur_ops->can_boost,
 		 test_boost_interval, test_boost_duration, shutdown_secs,
+		 stall_cpu, stall_cpu_holdoff,
+		 n_barrier_cbs,
 		 onoff_interval, onoff_holdoff);
 }
 
@@ -1502,6 +1479,7 @@ rcu_torture_onoff(void *arg)
 	unsigned long delta;
 	int maxcpu = -1;
 	DEFINE_RCU_RANDOM(rand);
+	int ret;
 	unsigned long starttime;
 
 	VERBOSE_PRINTK_STRING("rcu_torture_onoff task started");
@@ -1522,7 +1500,13 @@ rcu_torture_onoff(void *arg)
 					 torture_type, cpu);
 			starttime = jiffies;
 			n_offline_attempts++;
-			if (cpu_down(cpu) == 0) {
+			ret = cpu_down(cpu);
+			if (ret) {
+				if (verbose)
+					pr_alert("%s" TORTURE_FLAG
+						 "rcu_torture_onoff task: offline %d failed: errno %d\n",
+						 torture_type, cpu, ret);
+			} else {
 				if (verbose)
 					pr_alert("%s" TORTURE_FLAG
 						 "rcu_torture_onoff task: offlined %d\n",
@@ -1936,8 +1920,6 @@ rcu_torture_cleanup(void)
 
 	rcu_torture_stats_print();  /* -After- the stats thread is stopped! */
 
-	if (cur_ops->cleanup)
-		cur_ops->cleanup();
 	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 ||

kernel/rcutree.h

@@ -287,6 +287,7 @@ struct rcu_data {
 	long		qlen_last_fqs_check;
 					/* qlen at last check for QS forcing */
 	unsigned long	n_cbs_invoked;	/* count of RCU cbs invoked. */
+	unsigned long	n_nocbs_invoked; /* count of no-CBs RCU cbs invoked. */
 	unsigned long   n_cbs_orphaned; /* RCU cbs orphaned by dying CPU */
 	unsigned long   n_cbs_adopted;  /* RCU cbs adopted from dying CPU */
 	unsigned long	n_force_qs_snap;
@@ -317,6 +318,18 @@ struct rcu_data {
 	struct rcu_head oom_head;
 #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
 
+	/* 7) Callback offloading. */
+#ifdef CONFIG_RCU_NOCB_CPU
+	struct rcu_head *nocb_head;	/* CBs waiting for kthread. */
+	struct rcu_head **nocb_tail;
+	atomic_long_t nocb_q_count;	/* # CBs waiting for kthread */
+	atomic_long_t nocb_q_count_lazy; /*  (approximate). */
+	int nocb_p_count;		/* # CBs being invoked by kthread */
+	int nocb_p_count_lazy;		/*  (approximate). */
+	wait_queue_head_t nocb_wq;	/* For nocb kthreads to sleep on. */
+	struct task_struct *nocb_kthread;
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
+
 	int cpu;
 	struct rcu_state *rsp;
 };
@@ -369,6 +382,12 @@ struct rcu_state {
 	struct rcu_data __percpu *rda;		/* pointer of percu rcu_data. */
 	void (*call)(struct rcu_head *head,	/* call_rcu() flavor. */
 		     void (*func)(struct rcu_head *head));
+#ifdef CONFIG_RCU_NOCB_CPU
+	void (*call_remote)(struct rcu_head *head,
+		     void (*func)(struct rcu_head *head));
+						/* call_rcu() flavor, but for */
+						/*  placing on remote CPU. */
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
 	/* The following fields are guarded by the root rcu_node's lock. */
 
@@ -383,9 +402,8 @@ struct rcu_state {
 
 	/* End of fields guarded by root rcu_node's lock. */
 
-	raw_spinlock_t onofflock ____cacheline_internodealigned_in_smp;
-						/* exclude on/offline and */
-						/*  starting new GP. */
+	raw_spinlock_t orphan_lock ____cacheline_internodealigned_in_smp;
+						/* Protect following fields. */
 	struct rcu_head *orphan_nxtlist;	/* Orphaned callbacks that */
 						/*  need a grace period. */
 	struct rcu_head **orphan_nxttail;	/* Tail of above. */
@@ -394,7 +412,7 @@ struct rcu_state {
 	struct rcu_head **orphan_donetail;	/* Tail of above. */
 	long qlen_lazy;				/* Number of lazy callbacks. */
 	long qlen;				/* Total number of callbacks. */
-	/* End of fields guarded by onofflock. */
+	/* End of fields guarded by orphan_lock. */
 
 	struct mutex onoff_mutex;		/* Coordinate hotplug & GPs. */
 
@@ -405,6 +423,18 @@ struct rcu_state {
 						/*  _rcu_barrier(). */
 	/* End of fields guarded by barrier_mutex. */
 
+	atomic_long_t expedited_start;		/* Starting ticket. */
+	atomic_long_t expedited_done;		/* Done ticket. */
+	atomic_long_t expedited_wrap;		/* # near-wrap incidents. */
+	atomic_long_t expedited_tryfail;	/* # acquisition failures. */
+	atomic_long_t expedited_workdone1;	/* # done by others #1. */
+	atomic_long_t expedited_workdone2;	/* # done by others #2. */
+	atomic_long_t expedited_normal;		/* # fallbacks to normal. */
+	atomic_long_t expedited_stoppedcpus;	/* # successful stop_cpus. */
+	atomic_long_t expedited_done_tries;	/* # tries to update _done. */
+	atomic_long_t expedited_done_lost;	/* # times beaten to _done. */
+	atomic_long_t expedited_done_exit;	/* # times exited _done loop. */
+
 	unsigned long jiffies_force_qs;		/* Time at which to invoke */
 						/*  force_quiescent_state(). */
 	unsigned long n_force_qs;		/* Number of calls to */
@@ -428,6 +458,8 @@ struct rcu_state {
 #define RCU_GP_FLAG_FQS  0x2	/* Need grace-period quiescent-state forcing. */
 
 extern struct list_head rcu_struct_flavors;
+
+/* Sequence through rcu_state structures for each RCU flavor. */
 #define for_each_rcu_flavor(rsp) \
 	list_for_each_entry((rsp), &rcu_struct_flavors, flavors)
 
@@ -504,5 +536,32 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
 static void print_cpu_stall_info_end(void);
 static void zero_cpu_stall_ticks(struct rcu_data *rdp);
 static void increment_cpu_stall_ticks(void);
+static bool is_nocb_cpu(int cpu);
+static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
+			    bool lazy);
+static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
+				      struct rcu_data *rdp);
+static bool nocb_cpu_expendable(int cpu);
+static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
+static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
+static void init_nocb_callback_list(struct rcu_data *rdp);
+static void __init rcu_init_nocb(void);
 
 #endif /* #ifndef RCU_TREE_NONCORE */
+
+#ifdef CONFIG_RCU_TRACE
+#ifdef CONFIG_RCU_NOCB_CPU
+/* Sum up queue lengths for tracing. */
+static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
+{
+	*ql = atomic_long_read(&rdp->nocb_q_count) + rdp->nocb_p_count;
+	*qll = atomic_long_read(&rdp->nocb_q_count_lazy) + rdp->nocb_p_count_lazy;
+}
+#else /* #ifdef CONFIG_RCU_NOCB_CPU */
+static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
+{
+	*ql = 0;
+	*qll = 0;
+}
+#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
+#endif /* #ifdef CONFIG_RCU_TRACE */

kernel/sched/core.c

@@ -72,6 +72,7 @@
 #include <linux/slab.h>
 #include <linux/init_task.h>
 #include <linux/binfmts.h>
+#include <linux/context_tracking.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
@@ -1886,8 +1887,8 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
 #endif
 
+	context_tracking_task_switch(prev, next);
 	/* Here we just switch the register state and the stack. */
-	rcu_switch(prev, next);
 	switch_to(prev, next, prev);
 
 	barrier();
@@ -2911,7 +2912,7 @@ asmlinkage void __sched schedule(void)
 }
 EXPORT_SYMBOL(schedule);
 
-#ifdef CONFIG_RCU_USER_QS
+#ifdef CONFIG_CONTEXT_TRACKING
 asmlinkage void __sched schedule_user(void)
 {
 	/*
@@ -2920,9 +2921,9 @@ asmlinkage void __sched schedule_user(void)
 	 * we haven't yet exited the RCU idle mode. Do it here manually until
 	 * we find a better solution.
 	 */
-	rcu_user_exit();
+	user_exit();
 	schedule();
-	rcu_user_enter();
+	user_enter();
 }
 #endif
 
@@ -3027,7 +3028,7 @@ asmlinkage void __sched preempt_schedule_irq(void)
 	/* Catch callers which need to be fixed */
 	BUG_ON(ti->preempt_count || !irqs_disabled());
 
-	rcu_user_exit();
+	user_exit();
 	do {
 		add_preempt_count(PREEMPT_ACTIVE);
 		local_irq_enable();
@@ -4474,6 +4475,7 @@ static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
 void sched_show_task(struct task_struct *p)
 {
 	unsigned long free = 0;
+	int ppid;
 	unsigned state;
 
 	state = p->state ? __ffs(p->state) + 1 : 0;
@@ -4493,8 +4495,11 @@ void sched_show_task(struct task_struct *p)
 #ifdef CONFIG_DEBUG_STACK_USAGE
 	free = stack_not_used(p);
 #endif
+	rcu_read_lock();
+	ppid = task_pid_nr(rcu_dereference(p->real_parent));
+	rcu_read_unlock();
 	printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
-		task_pid_nr(p), task_pid_nr(rcu_dereference(p->real_parent)),
+		task_pid_nr(p), ppid,
 		(unsigned long)task_thread_info(p)->flags);
 
 	show_stack(p, NULL);
@@ -8076,3 +8081,9 @@ struct cgroup_subsys cpuacct_subsys = {
 	.base_cftypes = files,
 };
 #endif	/* CONFIG_CGROUP_CPUACCT */
+
+void dump_cpu_task(int cpu)
+{
+	pr_info("Task dump for CPU %d:\n", cpu);
+	sched_show_task(cpu_curr(cpu));
+}

kernel/srcu.c

@@ -16,8 +16,10 @@
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
  * Copyright (C) IBM Corporation, 2006
+ * Copyright (C) Fujitsu, 2012
  *
  * Author: Paul McKenney <paulmck@us.ibm.com>
+ *	   Lai Jiangshan <laijs@cn.fujitsu.com>
  *
  * For detailed explanation of Read-Copy Update mechanism see -
  * 		Documentation/RCU/ *.txt
@@ -34,6 +36,10 @@
 #include <linux/delay.h>
 #include <linux/srcu.h>
 
+#include <trace/events/rcu.h>
+
+#include "rcu.h"
+
 /*
  * Initialize an rcu_batch structure to empty.
  */
@@ -92,9 +98,6 @@ static inline void rcu_batch_move(struct rcu_batch *to, struct rcu_batch *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;
@@ -464,7 +467,9 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
  */
 void synchronize_srcu(struct srcu_struct *sp)
 {
-	__synchronize_srcu(sp, SYNCHRONIZE_SRCU_TRYCOUNT);
+	__synchronize_srcu(sp, rcu_expedited
+			   ? SYNCHRONIZE_SRCU_EXP_TRYCOUNT
+			   : SYNCHRONIZE_SRCU_TRYCOUNT);
 }
 EXPORT_SYMBOL_GPL(synchronize_srcu);
 
@@ -637,7 +642,7 @@ static void srcu_reschedule(struct srcu_struct *sp)
 /*
  * This is the work-queue function that handles SRCU grace periods.
  */
-static void process_srcu(struct work_struct *work)
+void process_srcu(struct work_struct *work)
 {
 	struct srcu_struct *sp;
 
@@ -648,3 +653,4 @@ static void process_srcu(struct work_struct *work)
 	srcu_invoke_callbacks(sp);
 	srcu_reschedule(sp);
 }
+EXPORT_SYMBOL_GPL(process_srcu);

lib/Kconfig.debug

@@ -972,7 +972,7 @@ config RCU_CPU_STALL_TIMEOUT
 	int "RCU CPU stall timeout in seconds"
 	depends on TREE_RCU || TREE_PREEMPT_RCU
 	range 3 300
-	default 60
+	default 21
 	help
 	  If a given RCU grace period extends more than the specified
 	  number of seconds, a CPU stall warning is printed.  If the