18 files changed, 218 insertions, 61 deletions

diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 081147da0564..fbe89e17124e 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -319,13 +319,6 @@ static inline void __clocksource_updatefreq_khz(struct clocksource *cs, u32 khz)
         __clocksource_updatefreq_scale(cs, 1000, khz);
 }
 
-static inline void
-clocksource_calc_mult_shift(struct clocksource *cs, u32 freq, u32 minsec)
-{
-        return clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
-                                      NSEC_PER_SEC, minsec);
-}
-
 #ifdef CONFIG_GENERIC_TIME_VSYSCALL
 extern void
 update_vsyscall(struct timespec *ts, struct timespec *wtm,
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index dd478fc8f9f5..5f3f3be5af09 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -144,12 +144,14 @@ struct event_filter;
 enum trace_reg {
         TRACE_REG_REGISTER,
         TRACE_REG_UNREGISTER,
+#ifdef CONFIG_PERF_EVENTS
         TRACE_REG_PERF_REGISTER,
         TRACE_REG_PERF_UNREGISTER,
         TRACE_REG_PERF_OPEN,
         TRACE_REG_PERF_CLOSE,
         TRACE_REG_PERF_ADD,
         TRACE_REG_PERF_DEL,
+#endif
 };
 
 struct ftrace_event_call;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index fe23ee768589..e61d3192448e 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -596,6 +596,7 @@ extern char *disk_name (struct gendisk *hd, int partno, char *buf);
 
 extern int disk_expand_part_tbl(struct gendisk *disk, int target);
 extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev);
+extern int invalidate_partitions(struct gendisk *disk, struct block_device *bdev);
 extern struct hd_struct * __must_check add_partition(struct gendisk *disk,
                                                      int partno, sector_t start,
                                                      sector_t len, int flags,
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 9c66b1ada9d7..f994d51f70f2 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -149,7 +149,7 @@ extern struct cred init_cred;
         },                                                              \
         .rt             = {                                             \
                 .run_list       = LIST_HEAD_INIT(tsk.rt.run_list),      \
-                .time_slice     = HZ,                                   \
+                .time_slice     = RR_TIMESLICE,                         \
                 .nr_cpus_allowed = NR_CPUS,                             \
         },                                                              \
         .tasks          = LIST_HEAD_INIT(tsk.tasks),                    \
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index 119773eebe31..1a3018063034 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -6,8 +6,11 @@
 #include <linux/workqueue.h>
 
 enum {
-        ICQ_IOPRIO_CHANGED,
-        ICQ_CGROUP_CHANGED,
+        ICQ_IOPRIO_CHANGED      = 1 << 0,
+        ICQ_CGROUP_CHANGED      = 1 << 1,
+        ICQ_EXITED              = 1 << 2,
+
+        ICQ_CHANGED_MASK        = ICQ_IOPRIO_CHANGED | ICQ_CGROUP_CHANGED,
 };
 
 /*
@@ -88,7 +91,7 @@ struct io_cq {
                 struct rcu_head         __rcu_head;
         };
 
-        unsigned long           changed;
+        unsigned int            flags;
 };
 
 /*
@@ -139,6 +142,7 @@ struct io_context *get_task_io_context(struct task_struct *task,
                                        gfp_t gfp_flags, int node);
 void ioc_ioprio_changed(struct io_context *ioc, int ioprio);
 void ioc_cgroup_changed(struct io_context *ioc);
+unsigned int icq_get_changed(struct io_cq *icq);
 #else
 struct io_context;
 static inline void put_io_context(struct io_context *ioc) { }
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index e8343422240a..5582c7985567 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -85,6 +85,19 @@
 }                                                       \
 )
 
+/*
+ * Multiplies an integer by a fraction, while avoiding unnecessary
+ * overflow or loss of precision.
+ */
+#define mult_frac(x, numer, denom)(                     \
+{                                                       \
+        typeof(x) quot = (x) / (denom);                 \
+        typeof(x) rem  = (x) % (denom);                 \
+        (quot * (numer)) + ((rem * (numer)) / (denom)); \
+}                                                       \
+)
+
+
 #define _RET_IP_                (unsigned long)__builtin_return_address(0)
 #define _THIS_IP_  ({ __label__ __here; __here: (unsigned long)&&__here; })
 
@@ -414,16 +427,10 @@ extern int __must_check hex2bin(u8 *dst, const char *src, size_t count);
  * Most likely, you want to use tracing_on/tracing_off.
  */
 #ifdef CONFIG_RING_BUFFER
-void tracing_on(void);
-void tracing_off(void);
 /* trace_off_permanent stops recording with no way to bring it back */
 void tracing_off_permanent(void);
-int tracing_is_on(void);
 #else
-static inline void tracing_on(void) { }
-static inline void tracing_off(void) { }
 static inline void tracing_off_permanent(void) { }
-static inline int tracing_is_on(void) { return 0; }
 #endif
 
 enum ftrace_dump_mode {
@@ -433,6 +440,10 @@ enum ftrace_dump_mode {
 };
 
 #ifdef CONFIG_TRACING
+void tracing_on(void);
+void tracing_off(void);
+int tracing_is_on(void);
+
 extern void tracing_start(void);
 extern void tracing_stop(void);
 extern void ftrace_off_permanent(void);
@@ -517,6 +528,11 @@ static inline void tracing_start(void) { }
 static inline void tracing_stop(void) { }
 static inline void ftrace_off_permanent(void) { }
 static inline void trace_dump_stack(void) { }
+
+static inline void tracing_on(void) { }
+static inline void tracing_off(void) { }
+static inline int tracing_is_on(void) { return 0; }
+
 static inline int
 trace_printk(const char *fmt, ...)
 {
diff --git a/include/linux/math64.h b/include/linux/math64.h
index 23fcdfcba81b..b8ba85544721 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -6,6 +6,8 @@
 
 #if BITS_PER_LONG == 64
 
+#define div64_long(x,y) div64_s64((x),(y))
+
 /**
  * div_u64_rem - unsigned 64bit divide with 32bit divisor with remainder
  *
@@ -45,6 +47,8 @@ static inline s64 div64_s64(s64 dividend, s64 divisor)
 
 #elif BITS_PER_LONG == 32
 
+#define div64_long(x,y) div_s64((x),(y))
+
 #ifndef div_u64_rem
 static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
 {
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 58969b2a8a82..5a710b9c578e 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -48,12 +48,14 @@ do { \
         barrier(); \
 } while (0)
 
-#define preempt_enable_no_resched() \
+#define sched_preempt_enable_no_resched() \
 do { \
         barrier(); \
         dec_preempt_count(); \
 } while (0)
 
+#define preempt_enable_no_resched()     sched_preempt_enable_no_resched()
+
 #define preempt_enable() \
 do { \
         preempt_enable_no_resched(); \
@@ -92,6 +94,7 @@ do { \
 #else /* !CONFIG_PREEMPT_COUNT */
 
 #define preempt_disable()               do { } while (0)
+#define sched_preempt_enable_no_resched()       do { } while (0)
 #define preempt_enable_no_resched()     do { } while (0)
 #define preempt_enable()                do { } while (0)
 
diff --git a/include/linux/printk.h b/include/linux/printk.h
index f0e22f75143f..1f77a4174ee0 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -101,6 +101,11 @@ asmlinkage __printf(1, 2) __cold
 int printk(const char *fmt, ...);
 
 /*
+ * Special printk facility for scheduler use only, _DO_NOT_USE_ !
+ */
+__printf(1, 2) __cold int printk_sched(const char *fmt, ...);
+
+/*
  * Please don't use printk_ratelimit(), because it shares ratelimiting state
  * with all other unrelated printk_ratelimit() callsites.  Instead use
  * printk_ratelimited() or plain old __ratelimit().
@@ -127,6 +132,11 @@ int printk(const char *s, ...)
 {
         return 0;
 }
+static inline __printf(1, 2) __cold
+int printk_sched(const char *s, ...)
+{
+        return 0;
+}
 static inline int printk_ratelimit(void)
 {
         return 0;
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/ring_buffer.h b/include/linux/ring_buffer.h
index 67be0376d8e3..7be2e88f23fd 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -151,6 +151,9 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu);
 
 void ring_buffer_record_disable(struct ring_buffer *buffer);
 void ring_buffer_record_enable(struct ring_buffer *buffer);
+void ring_buffer_record_off(struct ring_buffer *buffer);
+void ring_buffer_record_on(struct ring_buffer *buffer);
+int ring_buffer_record_is_on(struct ring_buffer *buffer);
 void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu);
 void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0657368bd78f..e074e1e54f85 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -361,6 +361,7 @@ extern signed long schedule_timeout_interruptible(signed long timeout);
 extern signed long schedule_timeout_killable(signed long timeout);
 extern signed long schedule_timeout_uninterruptible(signed long timeout);
 asmlinkage void schedule(void);
+extern void schedule_preempt_disabled(void);
 extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner);
 
 struct nsproxy;
@@ -905,6 +906,7 @@ struct sched_group_power {
          * single CPU.
          */
         unsigned int power, power_orig;
+        unsigned long next_update;
         /*
          * Number of busy cpus in this group.
          */
@@ -1052,6 +1054,8 @@ static inline int test_sd_parent(struct sched_domain *sd, int flag)
 unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
 unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);
 
+bool cpus_share_cache(int this_cpu, int that_cpu);
+
 #else /* CONFIG_SMP */
 
 struct sched_domain_attr;
@@ -1061,6 +1065,12 @@ partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
                         struct sched_domain_attr *dattr_new)
 {
 }
+
+static inline bool cpus_share_cache(int this_cpu, int that_cpu)
+{
+        return true;
+}
+
 #endif  /* !CONFIG_SMP */
 
 
@@ -1225,6 +1235,12 @@ struct sched_rt_entity {
 #endif
 };
 
+/*
+ * default timeslice is 100 msecs (used only for SCHED_RR tasks).
+ * Timeslices get refilled after they expire.
+ */
+#define RR_TIMESLICE            (100 * HZ / 1000)
+
 struct rcu_node;
 
 enum perf_event_task_context {
@@ -1319,6 +1335,11 @@ struct task_struct {
         unsigned sched_reset_on_fork:1;
         unsigned sched_contributes_to_load:1;
 
+#ifdef CONFIG_GENERIC_HARDIRQS
+        /* IRQ handler threads */
+        unsigned irq_thread:1;
+#endif
+
         pid_t pid;
         pid_t tgid;
 
@@ -1427,11 +1448,6 @@ struct task_struct {
  * mempolicy */
         spinlock_t alloc_lock;
 
-#ifdef CONFIG_GENERIC_HARDIRQS
-        /* IRQ handler threads */
-        struct irqaction *irqaction;
-#endif
-
         /* Protection of the PI data structures: */
         raw_spinlock_t pi_lock;
 
@@ -1863,8 +1879,7 @@ 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)
 {
@@ -2048,7 +2063,7 @@ extern void sched_autogroup_fork(struct signal_struct *sig);
 extern void sched_autogroup_exit(struct signal_struct *sig);
 #ifdef CONFIG_PROC_FS
 extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m);
-extern int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice);
+extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice);
 #endif
 #else
 static inline void sched_autogroup_create_attach(struct task_struct *p) { }
@@ -2065,12 +2080,20 @@ extern unsigned int sysctl_sched_cfs_bandwidth_slice;
 extern int rt_mutex_getprio(struct task_struct *p);
 extern void rt_mutex_setprio(struct task_struct *p, int prio);
 extern void rt_mutex_adjust_pi(struct task_struct *p);
+static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
+{
+        return tsk->pi_blocked_on != NULL;
+}
 #else
 static inline int rt_mutex_getprio(struct task_struct *p)
 {
         return p->normal_prio;
 }
 # define rt_mutex_adjust_pi(p)          do { } while (0)
+static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
+{
+        return false;
+}
 #endif
 
 extern bool yield_to(struct task_struct *p, bool preempt);
@@ -2389,12 +2412,15 @@ static inline void task_unlock(struct task_struct *p)
 extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
                                                         unsigned long *flags);
 
-#define lock_task_sighand(tsk, flags)                                   \
-({      struct sighand_struct *__ss;                                    \
-        __cond_lock(&(tsk)->sighand->siglock,                           \
-                    (__ss = __lock_task_sighand(tsk, flags)));          \
-        __ss;                                                           \
-})                                                                      \
+static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
+                                                       unsigned long *flags)
+{
+        struct sighand_struct *ret;
+
+        ret = __lock_task_sighand(tsk, flags);
+        (void)__cond_lock(&tsk->sighand->siglock, ret);
+        return ret;
+}
 
 static inline void unlock_task_sighand(struct task_struct *tsk,
                                                 unsigned long *flags)
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/linux/timex.h b/include/linux/timex.h
index aa60fe7b6ed6..b75e1864ed19 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -234,23 +234,9 @@ struct timex {
 extern unsigned long tick_usec;         /* USER_HZ period (usec) */
 extern unsigned long tick_nsec;         /* ACTHZ          period (nsec) */
 
-/*
- * phase-lock loop variables
- */
-extern int time_status;         /* clock synchronization status bits */
-
 extern void ntp_init(void);
 extern void ntp_clear(void);
 
-/**
- * ntp_synced - Returns 1 if the NTP status is not UNSYNC
- *
- */
-static inline int ntp_synced(void)
-{
-        return !(time_status & STA_UNSYNC);
-}
-
 /* Required to safely shift negative values */
 #define shift_right(x, s) ({    \
         __typeof__(x) __x = (x);        \
@@ -264,10 +250,9 @@ static inline int ntp_synced(void)
 #define NTP_INTERVAL_LENGTH (NSEC_PER_SEC/NTP_INTERVAL_FREQ)
 
 /* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */
-extern u64 tick_length;
+extern u64 ntp_tick_length(void);
 
 extern void second_overflow(void);
-extern void update_ntp_one_tick(void);
 extern int do_adjtimex(struct timex *);
 extern void hardpps(const struct timespec *, const struct timespec *);
 
diff --git a/include/linux/wait.h b/include/linux/wait.h
index a9ce45e8501c..7d9a9e990ce6 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -157,7 +157,7 @@ void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr,
                         void *key);
-void __wake_up_locked(wait_queue_head_t *q, unsigned int mode);
+void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_bit(wait_queue_head_t *, void *, int);
 int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned);
@@ -170,7 +170,8 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 #define wake_up(x)                      __wake_up(x, TASK_NORMAL, 1, NULL)
 #define wake_up_nr(x, nr)               __wake_up(x, TASK_NORMAL, nr, NULL)
 #define wake_up_all(x)                  __wake_up(x, TASK_NORMAL, 0, NULL)
-#define wake_up_locked(x)               __wake_up_locked((x), TASK_NORMAL)
+#define wake_up_locked(x)               __wake_up_locked((x), TASK_NORMAL, 1)
+#define wake_up_all_locked(x)           __wake_up_locked((x), TASK_NORMAL, 0)
 
 #define wake_up_interruptible(x)        __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL)
 #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL)
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index eb8b9f15f2e0..af155450cabb 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -289,12 +289,16 @@ enum {
  *
  * system_freezable_wq is equivalent to system_wq except that it's
  * freezable.
+ *
+ * system_nrt_freezable_wq is equivalent to system_nrt_wq except that
+ * it's freezable.
  */
 extern struct workqueue_struct *system_wq;
 extern struct workqueue_struct *system_long_wq;
 extern struct workqueue_struct *system_nrt_wq;
 extern struct workqueue_struct *system_unbound_wq;
 extern struct workqueue_struct *system_freezable_wq;
+extern struct workqueue_struct *system_nrt_freezable_wq;
 
 extern struct workqueue_struct *
 __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,