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

Pull locking updates from Ingo Molnar:
 "The main changes in this cycle were:

   - a big round of FUTEX_UNLOCK_PI improvements, fixes, cleanups and
     general restructuring

   - lockdep updates such as new checks for lock_downgrade()

   - introduce the new atomic_try_cmpxchg() locking API and use it to
     optimize refcount code generation

   - ... plus misc fixes, updates and cleanups"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (38 commits)
  MAINTAINERS: Add FUTEX SUBSYSTEM
  futex: Clarify mark_wake_futex memory barrier usage
  futex: Fix small (and harmless looking) inconsistencies
  futex: Avoid freeing an active timer
  rtmutex: Plug preempt count leak in rt_mutex_futex_unlock()
  rtmutex: Fix more prio comparisons
  rtmutex: Fix PI chain order integrity
  sched,tracing: Update trace_sched_pi_setprio()
  sched/rtmutex: Refactor rt_mutex_setprio()
  rtmutex: Clean up
  sched/deadline/rtmutex: Dont miss the dl_runtime/dl_period update
  sched/rtmutex/deadline: Fix a PI crash for deadline tasks
  rtmutex: Deboost before waking up the top waiter
  locking/ww-mutex: Limit stress test to 2 seconds
  locking/atomic: Fix atomic_try_cmpxchg() semantics
  lockdep: Fix per-cpu static objects
  futex: Drop hb->lock before enqueueing on the rtmutex
  futex: Futex_unlock_pi() determinism
  futex: Rework futex_lock_pi() to use rt_mutex_*_proxy_lock()
  futex,rt_mutex: Restructure rt_mutex_finish_proxy_lock()
  ...

10 files changed, 107 insertions, 22 deletions

diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index e71835bf60a9..c56be7410130 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -423,6 +423,29 @@
 #endif
 #endif /* atomic_cmpxchg_relaxed */
 
+#ifndef atomic_try_cmpxchg
+
+#define __atomic_try_cmpxchg(type, _p, _po, _n)				\
+({									\
+	typeof(_po) __po = (_po);					\
+	typeof(*(_po)) __r, __o = *__po;				\
+	__r = atomic_cmpxchg##type((_p), __o, (_n));			\
+	if (unlikely(__r != __o))					\
+		*__po = __r;						\
+	likely(__r == __o);						\
+})
+
+#define atomic_try_cmpxchg(_p, _po, _n)		__atomic_try_cmpxchg(, _p, _po, _n)
+#define atomic_try_cmpxchg_relaxed(_p, _po, _n)	__atomic_try_cmpxchg(_relaxed, _p, _po, _n)
+#define atomic_try_cmpxchg_acquire(_p, _po, _n)	__atomic_try_cmpxchg(_acquire, _p, _po, _n)
+#define atomic_try_cmpxchg_release(_p, _po, _n)	__atomic_try_cmpxchg(_release, _p, _po, _n)
+
+#else /* atomic_try_cmpxchg */
+#define atomic_try_cmpxchg_relaxed	atomic_try_cmpxchg
+#define atomic_try_cmpxchg_acquire	atomic_try_cmpxchg
+#define atomic_try_cmpxchg_release	atomic_try_cmpxchg
+#endif /* atomic_try_cmpxchg */
+
 /* cmpxchg_relaxed */
 #ifndef cmpxchg_relaxed
 #define  cmpxchg_relaxed		cmpxchg
@@ -996,6 +1019,29 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #endif
 #endif /* atomic64_cmpxchg_relaxed */
 
+#ifndef atomic64_try_cmpxchg
+
+#define __atomic64_try_cmpxchg(type, _p, _po, _n)			\
+({									\
+	typeof(_po) __po = (_po);					\
+	typeof(*(_po)) __r, __o = *__po;				\
+	__r = atomic64_cmpxchg##type((_p), __o, (_n));			\
+	if (unlikely(__r != __o))					\
+		*__po = __r;						\
+	likely(__r == __o);						\
+})
+
+#define atomic64_try_cmpxchg(_p, _po, _n)		__atomic64_try_cmpxchg(, _p, _po, _n)
+#define atomic64_try_cmpxchg_relaxed(_p, _po, _n)	__atomic64_try_cmpxchg(_relaxed, _p, _po, _n)
+#define atomic64_try_cmpxchg_acquire(_p, _po, _n)	__atomic64_try_cmpxchg(_acquire, _p, _po, _n)
+#define atomic64_try_cmpxchg_release(_p, _po, _n)	__atomic64_try_cmpxchg(_release, _p, _po, _n)
+
+#else /* atomic64_try_cmpxchg */
+#define atomic64_try_cmpxchg_relaxed	atomic64_try_cmpxchg
+#define atomic64_try_cmpxchg_acquire	atomic64_try_cmpxchg
+#define atomic64_try_cmpxchg_release	atomic64_try_cmpxchg
+#endif /* atomic64_try_cmpxchg */
+
 #ifndef atomic64_andnot
 static inline void atomic64_andnot(long long i, atomic64_t *v)
 {
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 91d9049f0039..2c487e0879d5 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -181,6 +181,7 @@ extern struct cred init_cred;
 #ifdef CONFIG_RT_MUTEXES
 # define INIT_RT_MUTEXES(tsk)						\
 	.pi_waiters = RB_ROOT,						\
+	.pi_top_task = NULL,						\
 	.pi_waiters_leftmost = NULL,
 #else
 # define INIT_RT_MUTEXES(tsk)
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 1e327bb80838..fffe49f188e6 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -361,6 +361,8 @@ static inline void lock_set_subclass(struct lockdep_map *lock,
 	lock_set_class(lock, lock->name, lock->key, subclass, ip);
 }
 
+extern void lock_downgrade(struct lockdep_map *lock, unsigned long ip);
+
 extern void lockdep_set_current_reclaim_state(gfp_t gfp_mask);
 extern void lockdep_clear_current_reclaim_state(void);
 extern void lockdep_trace_alloc(gfp_t mask);
@@ -411,6 +413,7 @@ static inline void lockdep_on(void)
 
 # define lock_acquire(l, s, t, r, c, n, i)	do { } while (0)
 # define lock_release(l, n, i)			do { } while (0)
+# define lock_downgrade(l, i)			do { } while (0)
 # define lock_set_class(l, n, k, s, i)		do { } while (0)
 # define lock_set_subclass(l, s, i)		do { } while (0)
 # define lockdep_set_current_reclaim_state(g)	do { } while (0)
diff --git a/include/linux/module.h b/include/linux/module.h
index 0297c5cd7cdf..9ad68561d8c2 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -493,6 +493,7 @@ static inline int module_is_live(struct module *mod)
 struct module *__module_text_address(unsigned long addr);
 struct module *__module_address(unsigned long addr);
 bool is_module_address(unsigned long addr);
+bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr);
 bool is_module_percpu_address(unsigned long addr);
 bool is_module_text_address(unsigned long addr);
 
@@ -660,6 +661,11 @@ static inline bool is_module_percpu_address(unsigned long addr)
 	return false;
 }
 
+static inline bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr)
+{
+	return false;
+}
+
 static inline bool is_module_text_address(unsigned long addr)
 {
 	return false;
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 56939d3f6e53..491b3f5a5f8a 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -110,6 +110,7 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size,
 #endif
 
 extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align);
+extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr);
 extern bool is_kernel_percpu_address(unsigned long addr);
 
 #if !defined(CONFIG_SMP) || !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index 0023fee4bbbc..b34aa649d204 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -6,17 +6,36 @@
 #include <linux/spinlock.h>
 #include <linux/kernel.h>
 
+/**
+ * refcount_t - variant of atomic_t specialized for reference counts
+ * @refs: atomic_t counter field
+ *
+ * The counter saturates at UINT_MAX and will not move once
+ * there. This avoids wrapping the counter and causing 'spurious'
+ * use-after-free bugs.
+ */
 typedef struct refcount_struct {
 	atomic_t refs;
 } refcount_t;
 
 #define REFCOUNT_INIT(n)	{ .refs = ATOMIC_INIT(n), }
 
+/**
+ * refcount_set - set a refcount's value
+ * @r: the refcount
+ * @n: value to which the refcount will be set
+ */
 static inline void refcount_set(refcount_t *r, unsigned int n)
 {
 	atomic_set(&r->refs, n);
 }
 
+/**
+ * refcount_read - get a refcount's value
+ * @r: the refcount
+ *
+ * Return: the refcount's value
+ */
 static inline unsigned int refcount_read(const refcount_t *r)
 {
 	return atomic_read(&r->refs);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b9a421f1f76f..ba080e586dae 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -779,6 +779,8 @@ struct task_struct {
 	/* PI waiters blocked on a rt_mutex held by this task: */
 	struct rb_root			pi_waiters;
 	struct rb_node			*pi_waiters_leftmost;
+	/* Updated under owner's pi_lock and rq lock */
+	struct task_struct		*pi_top_task;
 	/* Deadlock detection and priority inheritance handling: */
 	struct rt_mutex_waiter		*pi_blocked_on;
 #endif
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index 3bd668414f61..f93329aba31a 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -18,27 +18,20 @@ static inline int rt_task(struct task_struct *p)
 }
 
 #ifdef CONFIG_RT_MUTEXES
-extern int rt_mutex_getprio(struct task_struct *p);
-extern void rt_mutex_setprio(struct task_struct *p, int prio);
-extern int rt_mutex_get_effective_prio(struct task_struct *task, int newprio);
-extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task);
+/*
+ * Must hold either p->pi_lock or task_rq(p)->lock.
+ */
+static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p)
+{
+	return p->pi_top_task;
+}
+extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task);
 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;
-}
-
-static inline int rt_mutex_get_effective_prio(struct task_struct *task,
-					      int newprio)
-{
-	return newprio;
-}
-
 static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
 {
 	return NULL;
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 8e0cb7a0f836..68123c1fe549 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -120,6 +120,13 @@ extern unsigned int setup_max_cpus;
 extern void __init setup_nr_cpu_ids(void);
 extern void __init smp_init(void);
 
+extern int __boot_cpu_id;
+
+static inline int get_boot_cpu_id(void)
+{
+	return __boot_cpu_id;
+}
+
 #else /* !SMP */
 
 static inline void smp_send_stop(void) { }
@@ -158,6 +165,11 @@ static inline void smp_init(void) { up_late_init(); }
 static inline void smp_init(void) { }
 #endif
 
+static inline int get_boot_cpu_id(void)
+{
+	return 0;
+}
+
 #endif /* !SMP */
 
 /*
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 9e3ef6c99e4b..ae1409ffe99a 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -70,7 +70,7 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
 	TP_fast_assign(
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
+		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
 		__entry->success	= 1; /* rudiment, kill when possible */
 		__entry->target_cpu	= task_cpu(p);
 	),
@@ -147,6 +147,7 @@ TRACE_EVENT(sched_switch,
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
 		__entry->next_pid	= next->pid;
 		__entry->next_prio	= next->prio;
+		/* XXX SCHED_DEADLINE */
 	),
 
 	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d",
@@ -181,7 +182,7 @@ TRACE_EVENT(sched_migrate_task,
 	TP_fast_assign(
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
+		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
 		__entry->orig_cpu	= task_cpu(p);
 		__entry->dest_cpu	= dest_cpu;
 	),
@@ -206,7 +207,7 @@ DECLARE_EVENT_CLASS(sched_process_template,
 	TP_fast_assign(
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
+		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
 	),
 
 	TP_printk("comm=%s pid=%d prio=%d",
@@ -253,7 +254,7 @@ TRACE_EVENT(sched_process_wait,
 	TP_fast_assign(
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 		__entry->pid		= pid_nr(pid);
-		__entry->prio		= current->prio;
+		__entry->prio		= current->prio; /* XXX SCHED_DEADLINE */
 	),
 
 	TP_printk("comm=%s pid=%d prio=%d",
@@ -413,9 +414,9 @@ DEFINE_EVENT(sched_stat_runtime, sched_stat_runtime,
  */
 TRACE_EVENT(sched_pi_setprio,
 
-	TP_PROTO(struct task_struct *tsk, int newprio),
+	TP_PROTO(struct task_struct *tsk, struct task_struct *pi_task),
 
-	TP_ARGS(tsk, newprio),
+	TP_ARGS(tsk, pi_task),
 
 	TP_STRUCT__entry(
 		__array( char,	comm,	TASK_COMM_LEN	)
@@ -428,7 +429,8 @@ TRACE_EVENT(sched_pi_setprio,
 		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
 		__entry->pid		= tsk->pid;
 		__entry->oldprio	= tsk->prio;
-		__entry->newprio	= newprio;
+		__entry->newprio	= pi_task ? pi_task->prio : tsk->prio;
+		/* XXX SCHED_DEADLINE bits missing */
 	),
 
 	TP_printk("comm=%s pid=%d oldprio=%d newprio=%d",