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

Pull RCU changes for v3.4 from Ingo Molnar.  The major features of this
series are:

 - making RCU more aggressive about entering dyntick-idle mode in order
   to improve energy efficiency

 - converting a few more call_rcu()s to kfree_rcu()s

 - applying a number of rcutree fixes and cleanups to rcutiny

 - removing CONFIG_SMP #ifdefs from treercu

 - allowing RCU CPU stall times to be set via sysfs

 - adding CPU-stall capability to rcutorture

 - adding more RCU-abuse diagnostics

 - updating documentation

 - fixing yet more issues located by the still-ongoing top-to-bottom
   inspection of RCU, this time with a special focus on the CPU-hotplug
   code path.

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits)
  rcu: Stop spurious warnings from synchronize_sched_expedited
  rcu: Hold off RCU_FAST_NO_HZ after timer posted
  rcu: Eliminate softirq-mediated RCU_FAST_NO_HZ idle-entry loop
  rcu: Add RCU_NONIDLE() for idle-loop RCU read-side critical sections
  rcu: Allow nesting of rcu_idle_enter() and rcu_idle_exit()
  rcu: Remove redundant check for rcu_head misalignment
  PTR_ERR should be called before its argument is cleared.
  rcu: Convert WARN_ON_ONCE() in rcu_lock_acquire() to lockdep
  rcu: Trace only after NULL-pointer check
  rcu: Call out dangers of expedited RCU primitives
  rcu: Rework detection of use of RCU by offline CPUs
  lockdep: Add CPU-idle/offline warning to lockdep-RCU splat
  rcu: No interrupt disabling for rcu_prepare_for_idle()
  rcu: Move synchronize_sched_expedited() to rcutree.c
  rcu: Check for illegal use of RCU from offlined CPUs
  rcu: Update stall-warning documentation
  rcu: Add CPU-stall capability to rcutorture
  rcu: Make documentation give more realistic rcutorture duration
  rcutorture: Permit holding off CPU-hotplug operations during boot
  rcu: Print scheduling-clock information on RCU CPU stall-warning messages
  ...

6 files changed, 156 insertions, 37 deletions

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 81c04f4348ec..937217425c47 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -190,6 +190,33 @@ extern void rcu_idle_exit(void);
 extern void rcu_irq_enter(void);
 extern void rcu_irq_exit(void);
 
+/**
+ * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers
+ * @a: Code that RCU needs to pay attention to.
+ *
+ * RCU, RCU-bh, and RCU-sched read-side critical sections are forbidden
+ * in the inner idle loop, that is, between the rcu_idle_enter() and
+ * the rcu_idle_exit() -- RCU will happily ignore any such read-side
+ * critical sections.  However, things like powertop need tracepoints
+ * in the inner idle loop.
+ *
+ * This macro provides the way out:  RCU_NONIDLE(do_something_with_RCU())
+ * will tell RCU that it needs to pay attending, invoke its argument
+ * (in this example, a call to the do_something_with_RCU() function),
+ * and then tell RCU to go back to ignoring this CPU.  It is permissible
+ * to nest RCU_NONIDLE() wrappers, but the nesting level is currently
+ * quite limited.  If deeper nesting is required, it will be necessary
+ * to adjust DYNTICK_TASK_NESTING_VALUE accordingly.
+ *
+ * This macro may be used from process-level code only.
+ */
+#define RCU_NONIDLE(a) \
+        do { \
+                rcu_idle_exit(); \
+                do { a; } while (0); \
+                rcu_idle_enter(); \
+        } while (0)
+
 /*
  * Infrastructure to implement the synchronize_() primitives in
  * TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
@@ -226,6 +253,15 @@ static inline void destroy_rcu_head_on_stack(struct rcu_head *head)
 }
 #endif  /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
+#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU)
+bool rcu_lockdep_current_cpu_online(void);
+#else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
+static inline bool rcu_lockdep_current_cpu_online(void)
+{
+        return 1;
+}
+#endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 #ifdef CONFIG_PROVE_RCU
@@ -239,13 +275,11 @@ static inline int rcu_is_cpu_idle(void)
 
 static inline void rcu_lock_acquire(struct lockdep_map *map)
 {
-        WARN_ON_ONCE(rcu_is_cpu_idle());
         lock_acquire(map, 0, 0, 2, 1, NULL, _THIS_IP_);
 }
 
 static inline void rcu_lock_release(struct lockdep_map *map)
 {
-        WARN_ON_ONCE(rcu_is_cpu_idle());
         lock_release(map, 1, _THIS_IP_);
 }
 
@@ -270,6 +304,9 @@ extern int debug_lockdep_rcu_enabled(void);
  * occur in the same context, for example, it is illegal to invoke
  * rcu_read_unlock() in process context if the matching rcu_read_lock()
  * was invoked from within an irq handler.
+ *
+ * Note that rcu_read_lock() is disallowed if the CPU is either idle or
+ * offline from an RCU perspective, so check for those as well.
  */
 static inline int rcu_read_lock_held(void)
 {
@@ -277,6 +314,8 @@ static inline int rcu_read_lock_held(void)
                 return 1;
         if (rcu_is_cpu_idle())
                 return 0;
+        if (!rcu_lockdep_current_cpu_online())
+                return 0;
         return lock_is_held(&rcu_lock_map);
 }
 
@@ -313,6 +352,9 @@ extern int rcu_read_lock_bh_held(void);
  * notice an extended quiescent state to other CPUs that started a grace
  * period. Otherwise we would delay any grace period as long as we run in
  * the idle task.
+ *
+ * Similarly, we avoid claiming an SRCU read lock held if the current
+ * CPU is offline.
  */
 #ifdef CONFIG_PREEMPT_COUNT
 static inline int rcu_read_lock_sched_held(void)
@@ -323,6 +365,8 @@ static inline int rcu_read_lock_sched_held(void)
                 return 1;
         if (rcu_is_cpu_idle())
                 return 0;
+        if (!rcu_lockdep_current_cpu_online())
+                return 0;
         if (debug_locks)
                 lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
         return lockdep_opinion || preempt_count() != 0 || irqs_disabled();
@@ -381,8 +425,22 @@ extern int rcu_my_thread_group_empty(void);
                 }                                                       \
         } while (0)
 
+#if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU)
+static inline void rcu_preempt_sleep_check(void)
+{
+        rcu_lockdep_assert(!lock_is_held(&rcu_lock_map),
+                           "Illegal context switch in RCU read-side "
+                           "critical section");
+}
+#else /* #ifdef CONFIG_PROVE_RCU */
+static inline void rcu_preempt_sleep_check(void)
+{
+}
+#endif /* #else #ifdef CONFIG_PROVE_RCU */
+
 #define rcu_sleep_check()                                               \
         do {                                                            \
+                rcu_preempt_sleep_check();                              \
                 rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map),     \
                                    "Illegal context switch in RCU-bh"   \
                                    " read-side critical section");      \
@@ -470,6 +528,13 @@ extern int rcu_my_thread_group_empty(void);
  * NULL.  Although rcu_access_pointer() may also be used in cases where
  * update-side locks prevent the value of the pointer from changing, you
  * should instead use rcu_dereference_protected() for this use case.
+ *
+ * It is also permissible to use rcu_access_pointer() when read-side
+ * access to the pointer was removed at least one grace period ago, as
+ * is the case in the context of the RCU callback that is freeing up
+ * the data, or after a synchronize_rcu() returns.  This can be useful
+ * when tearing down multi-linked structures after a grace period
+ * has elapsed.
  */
 #define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu)
 
@@ -659,6 +724,8 @@ static inline void rcu_read_lock(void)
         __rcu_read_lock();
         __acquire(RCU);
         rcu_lock_acquire(&rcu_lock_map);
+        rcu_lockdep_assert(!rcu_is_cpu_idle(),
+                           "rcu_read_lock() used illegally while idle");
 }
 
 /*
@@ -678,6 +745,8 @@ static inline void rcu_read_lock(void)
  */
 static inline void rcu_read_unlock(void)
 {
+        rcu_lockdep_assert(!rcu_is_cpu_idle(),
+                           "rcu_read_unlock() used illegally while idle");
         rcu_lock_release(&rcu_lock_map);
         __release(RCU);
         __rcu_read_unlock();
@@ -705,6 +774,8 @@ static inline void rcu_read_lock_bh(void)
         local_bh_disable();
         __acquire(RCU_BH);
         rcu_lock_acquire(&rcu_bh_lock_map);
+        rcu_lockdep_assert(!rcu_is_cpu_idle(),
+                           "rcu_read_lock_bh() used illegally while idle");
 }
 
 /*
@@ -714,6 +785,8 @@ static inline void rcu_read_lock_bh(void)
  */
 static inline void rcu_read_unlock_bh(void)
 {
+        rcu_lockdep_assert(!rcu_is_cpu_idle(),
+                           "rcu_read_unlock_bh() used illegally while idle");
         rcu_lock_release(&rcu_bh_lock_map);
         __release(RCU_BH);
         local_bh_enable();
@@ -737,6 +810,8 @@ static inline void rcu_read_lock_sched(void)
         preempt_disable();
         __acquire(RCU_SCHED);
         rcu_lock_acquire(&rcu_sched_lock_map);
+        rcu_lockdep_assert(!rcu_is_cpu_idle(),
+                           "rcu_read_lock_sched() used illegally while idle");
 }
 
 /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */
@@ -753,6 +828,8 @@ static inline notrace void rcu_read_lock_sched_notrace(void)
  */
 static inline void rcu_read_unlock_sched(void)
 {
+        rcu_lockdep_assert(!rcu_is_cpu_idle(),
+                           "rcu_read_unlock_sched() used illegally while idle");
         rcu_lock_release(&rcu_sched_lock_map);
         __release(RCU_SCHED);
         preempt_enable();
@@ -841,7 +918,7 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset)
         /* See the kfree_rcu() header comment. */
         BUILD_BUG_ON(!__is_kfree_rcu_offset(offset));
 
-        call_rcu(head, (rcu_callback)offset);
+        kfree_call_rcu(head, (rcu_callback)offset);
 }
 
 /**
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 00b7a5e493d2..e93df77176d1 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -27,13 +27,9 @@
 
 #include <linux/cache.h>
 
-#ifdef CONFIG_RCU_BOOST
 static inline void rcu_init(void)
 {
 }
-#else /* #ifdef CONFIG_RCU_BOOST */
-void rcu_init(void);
-#endif /* #else #ifdef CONFIG_RCU_BOOST */
 
 static inline void rcu_barrier_bh(void)
 {
@@ -83,6 +79,12 @@ static inline void synchronize_sched_expedited(void)
         synchronize_sched();
 }
 
+static inline void kfree_call_rcu(struct rcu_head *head,
+                                  void (*func)(struct rcu_head *rcu))
+{
+        call_rcu(head, func);
+}
+
 #ifdef CONFIG_TINY_RCU
 
 static inline void rcu_preempt_note_context_switch(void)
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 67458468f1a8..e8ee5dd0854c 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -61,6 +61,24 @@ extern void synchronize_rcu_bh(void);
 extern void synchronize_sched_expedited(void);
 extern void synchronize_rcu_expedited(void);
 
+void kfree_call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
+
+/**
+ * synchronize_rcu_bh_expedited - Brute-force RCU-bh grace period
+ *
+ * Wait for an RCU-bh grace period to elapse, but use a "big hammer"
+ * approach to force the grace period to end quickly.  This consumes
+ * significant time on all CPUs and is unfriendly to real-time workloads,
+ * so is thus not recommended for any sort of common-case code.  In fact,
+ * if you are using synchronize_rcu_bh_expedited() in a loop, please
+ * restructure your code to batch your updates, and then use a single
+ * synchronize_rcu_bh() instead.
+ *
+ * Note that it is illegal to call this function while holding any lock
+ * that is acquired by a CPU-hotplug notifier.  And yes, it is also illegal
+ * to call this function from a CPU-hotplug notifier.  Failing to observe
+ * these restriction will result in deadlock.
+ */
 static inline void synchronize_rcu_bh_expedited(void)
 {
         synchronize_sched_expedited();
@@ -83,6 +101,7 @@ 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;
 }
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0657368bd78f..f58889b8a608 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1863,8 +1863,7 @@ extern void task_clear_jobctl_pending(struct task_struct *task,
 #ifdef CONFIG_PREEMPT_RCU
 
 #define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
-#define RCU_READ_UNLOCK_BOOSTED (1 << 1) /* boosted while in RCU read-side. */
-#define RCU_READ_UNLOCK_NEED_QS (1 << 2) /* RCU core needs CPU response. */
+#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
 
 static inline void rcu_copy_process(struct task_struct *p)
 {
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index e1b005918bbb..d3d5fa54f25e 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -99,15 +99,18 @@ long srcu_batches_completed(struct srcu_struct *sp);
  * power mode. This way we can notice an extended quiescent state to
  * other CPUs that started a grace period. Otherwise we would delay any
  * grace period as long as we run in the idle task.
+ *
+ * Similarly, we avoid claiming an SRCU read lock held if the current
+ * CPU is offline.
  */
 static inline int srcu_read_lock_held(struct srcu_struct *sp)
 {
-        if (rcu_is_cpu_idle())
-                return 0;
-
         if (!debug_lockdep_rcu_enabled())
                 return 1;
-
+        if (rcu_is_cpu_idle())
+                return 0;
+        if (!rcu_lockdep_current_cpu_online())
+                return 0;
         return lock_is_held(&sp->dep_map);
 }
 
@@ -169,6 +172,8 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp)
         int retval = __srcu_read_lock(sp);
 
         rcu_lock_acquire(&(sp)->dep_map);
+        rcu_lockdep_assert(!rcu_is_cpu_idle(),
+                           "srcu_read_lock() used illegally while idle");
         return retval;
 }
 
@@ -182,6 +187,8 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp)
 static inline void srcu_read_unlock(struct srcu_struct *sp, int idx)
         __releases(sp)
 {
+        rcu_lockdep_assert(!rcu_is_cpu_idle(),
+                           "srcu_read_unlock() used illegally while idle");
         rcu_lock_release(&(sp)->dep_map);
         __srcu_read_unlock(sp, idx);
 }
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index d2d88bed891b..337099783f37 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -313,19 +313,22 @@ TRACE_EVENT(rcu_prep_idle,
 /*
  * Tracepoint for the registration of a single RCU callback function.
  * The first argument is the type of RCU, the second argument is
- * a pointer to the RCU callback itself, and the third element is the
- * new RCU callback queue length for the current CPU.
+ * a pointer to the RCU callback itself, the third element is the
+ * number of lazy callbacks queued, and the fourth element is the
+ * total number of callbacks queued.
  */
 TRACE_EVENT(rcu_callback,
 
-        TP_PROTO(char *rcuname, struct rcu_head *rhp, long qlen),
+        TP_PROTO(char *rcuname, struct rcu_head *rhp, long qlen_lazy,
+                 long qlen),
 
-        TP_ARGS(rcuname, rhp, qlen),
+        TP_ARGS(rcuname, rhp, qlen_lazy, qlen),
 
         TP_STRUCT__entry(
                 __field(char *, rcuname)
                 __field(void *, rhp)
                 __field(void *, func)
+                __field(long, qlen_lazy)
                 __field(long, qlen)
         ),
 
@@ -333,11 +336,13 @@ TRACE_EVENT(rcu_callback,
                 __entry->rcuname = rcuname;
                 __entry->rhp = rhp;
                 __entry->func = rhp->func;
+                __entry->qlen_lazy = qlen_lazy;
                 __entry->qlen = qlen;
         ),
 
-        TP_printk("%s rhp=%p func=%pf %ld",
-                  __entry->rcuname, __entry->rhp, __entry->func, __entry->qlen)
+        TP_printk("%s rhp=%p func=%pf %ld/%ld",
+                  __entry->rcuname, __entry->rhp, __entry->func,
+                  __entry->qlen_lazy, __entry->qlen)
 );
 
 /*
@@ -345,20 +350,21 @@ TRACE_EVENT(rcu_callback,
  * kfree() form.  The first argument is the RCU type, the second argument
  * is a pointer to the RCU callback, the third argument is the offset
  * of the callback within the enclosing RCU-protected data structure,
- * and the fourth argument is the new RCU callback queue length for the
- * current CPU.
+ * the fourth argument is the number of lazy callbacks queued, and the
+ * fifth argument is the total number of callbacks queued.
  */
 TRACE_EVENT(rcu_kfree_callback,
 
         TP_PROTO(char *rcuname, struct rcu_head *rhp, unsigned long offset,
-                 long qlen),
+                 long qlen_lazy, long qlen),
 
-        TP_ARGS(rcuname, rhp, offset, qlen),
+        TP_ARGS(rcuname, rhp, offset, qlen_lazy, qlen),
 
         TP_STRUCT__entry(
                 __field(char *, rcuname)
                 __field(void *, rhp)
                 __field(unsigned long, offset)
+                __field(long, qlen_lazy)
                 __field(long, qlen)
         ),
 
@@ -366,41 +372,45 @@ TRACE_EVENT(rcu_kfree_callback,
                 __entry->rcuname = rcuname;
                 __entry->rhp = rhp;
                 __entry->offset = offset;
+                __entry->qlen_lazy = qlen_lazy;
                 __entry->qlen = qlen;
         ),
 
-        TP_printk("%s rhp=%p func=%ld %ld",
+        TP_printk("%s rhp=%p func=%ld %ld/%ld",
                   __entry->rcuname, __entry->rhp, __entry->offset,
-                  __entry->qlen)
+                  __entry->qlen_lazy, __entry->qlen)
 );
 
 /*
  * Tracepoint for marking the beginning rcu_do_batch, performed to start
  * RCU callback invocation.  The first argument is the RCU flavor,
- * the second is the total number of callbacks (including those that
- * are not yet ready to be invoked), and the third argument is the
- * current RCU-callback batch limit.
+ * the second is the number of lazy callbacks queued, the third is
+ * the total number of callbacks queued, and the fourth argument is
+ * the current RCU-callback batch limit.
  */
 TRACE_EVENT(rcu_batch_start,
 
-        TP_PROTO(char *rcuname, long qlen, int blimit),
+        TP_PROTO(char *rcuname, long qlen_lazy, long qlen, int blimit),
 
-        TP_ARGS(rcuname, qlen, blimit),
+        TP_ARGS(rcuname, qlen_lazy, qlen, blimit),
 
         TP_STRUCT__entry(
                 __field(char *, rcuname)
+                __field(long, qlen_lazy)
                 __field(long, qlen)
                 __field(int, blimit)
         ),
 
         TP_fast_assign(
                 __entry->rcuname = rcuname;
+                __entry->qlen_lazy = qlen_lazy;
                 __entry->qlen = qlen;
                 __entry->blimit = blimit;
         ),
 
-        TP_printk("%s CBs=%ld bl=%d",
-                  __entry->rcuname, __entry->qlen, __entry->blimit)
+        TP_printk("%s CBs=%ld/%ld bl=%d",
+                  __entry->rcuname, __entry->qlen_lazy, __entry->qlen,
+                  __entry->blimit)
 );
 
 /*
@@ -531,16 +541,21 @@ TRACE_EVENT(rcu_torture_read,
 #else /* #ifdef CONFIG_RCU_TRACE */
 
 #define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0)
-#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, qsmask) do { } while (0)
+#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \
+                                    qsmask) do { } while (0)
 #define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0)
 #define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0)
-#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks) do { } while (0)
+#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \
+                                         grplo, grphi, gp_tasks) do { } \
+        while (0)
 #define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0)
 #define trace_rcu_dyntick(polarity, oldnesting, newnesting) do { } while (0)
 #define trace_rcu_prep_idle(reason) do { } while (0)
-#define trace_rcu_callback(rcuname, rhp, qlen) do { } while (0)
-#define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen) do { } while (0)
-#define trace_rcu_batch_start(rcuname, qlen, blimit) do { } while (0)
+#define trace_rcu_callback(rcuname, rhp, qlen_lazy, qlen) do { } while (0)
+#define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen_lazy, qlen) \
+        do { } while (0)
+#define trace_rcu_batch_start(rcuname, qlen_lazy, qlen, blimit) \
+        do { } while (0)
 #define trace_rcu_invoke_callback(rcuname, rhp) do { } while (0)
 #define trace_rcu_invoke_kfree_callback(rcuname, rhp, offset) do { } while (0)
 #define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \