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"
  ...

6 files changed, 82 insertions, 27 deletions

diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
new file mode 100644
index 000000000000..e24339ccb7f0
--- /dev/null
+++ b/include/linux/context_tracking.h
@@ -0,0 +1,18 @@
+#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
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index e0f0fab20415..c92dd28eaa6c 100644
--- a/include/linux/rculist.h
+++ b/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.
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 7c968e4f929e..275aa3f1062d 100644
--- a/include/linux/rcupdate.h
+++ b/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);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3e387df065fc..29116b853ece 100644
--- a/include/linux/sched.h
+++ b/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)
 {
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 55a5c52cbb25..6eb691b08358 100644
--- a/include/linux/srcu.h
+++ b/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
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 5bde94d8585b..d4f559b1ec34 100644
--- a/include/trace/events/rcu.h
+++ b/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.