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

Pull core locking changes from Ingo Molnar:
 "The biggest changes:

   - add lockdep support for seqcount/seqlocks structures, this
     unearthed both bugs and required extra annotation.

   - move the various kernel locking primitives to the new
     kernel/locking/ directory"

* 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (21 commits)
  block: Use u64_stats_init() to initialize seqcounts
  locking/lockdep: Mark __lockdep_count_forward_deps() as static
  lockdep/proc: Fix lock-time avg computation
  locking/doc: Update references to kernel/mutex.c
  ipv6: Fix possible ipv6 seqlock deadlock
  cpuset: Fix potential deadlock w/ set_mems_allowed
  seqcount: Add lockdep functionality to seqcount/seqlock structures
  net: Explicitly initialize u64_stats_sync structures for lockdep
  locking: Move the percpu-rwsem code to kernel/locking/
  locking: Move the lglocks code to kernel/locking/
  locking: Move the rwsem code to kernel/locking/
  locking: Move the rtmutex code to kernel/locking/
  locking: Move the semaphore core to kernel/locking/
  locking: Move the spinlock code to kernel/locking/
  locking: Move the lockdep code to kernel/locking/
  locking: Move the mutex code to kernel/locking/
  hung_task debugging: Add tracepoint to report the hang
  x86/locking/kconfig: Update paravirt spinlock Kconfig description
  lockstat: Report avg wait and hold times
  lockdep, x86/alternatives: Drop ancient lockdep fixup message
  ...

8 files changed, 114 insertions, 15 deletions

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index cc1b01cf2035..3fe661fe96d1 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -110,10 +110,14 @@ static inline bool put_mems_allowed(unsigned int seq)
 
 static inline void set_mems_allowed(nodemask_t nodemask)
 {
+	unsigned long flags;
+
 	task_lock(current);
+	local_irq_save(flags);
 	write_seqcount_begin(&current->mems_allowed_seq);
 	current->mems_allowed = nodemask;
 	write_seqcount_end(&current->mems_allowed_seq);
+	local_irq_restore(flags);
 	task_unlock(current);
 }
 
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 5cd0f0949927..b0ed422e4e4a 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -32,10 +32,10 @@ extern struct fs_struct init_fs;
 #endif
 
 #ifdef CONFIG_CPUSETS
-#define INIT_CPUSET_SEQ							\
-	.mems_allowed_seq = SEQCNT_ZERO,
+#define INIT_CPUSET_SEQ(tsk)							\
+	.mems_allowed_seq = SEQCNT_ZERO(tsk.mems_allowed_seq),
 #else
-#define INIT_CPUSET_SEQ
+#define INIT_CPUSET_SEQ(tsk)
 #endif
 
 #define INIT_SIGNALS(sig) {						\
@@ -220,7 +220,7 @@ extern struct task_group root_task_group;
 	INIT_FTRACE_GRAPH						\
 	INIT_TRACE_RECURSION						\
 	INIT_TASK_RCU_PREEMPT(tsk)					\
-	INIT_CPUSET_SEQ							\
+	INIT_CPUSET_SEQ(tsk)						\
 	INIT_VTIME(tsk)							\
 }
 
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index cfc2f119779a..92b1bfc5da60 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -497,6 +497,10 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 #define rwlock_acquire_read(l, s, t, i)		lock_acquire_shared_recursive(l, s, t, NULL, i)
 #define rwlock_release(l, n, i)			lock_release(l, n, i)
 
+#define seqcount_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
+#define seqcount_acquire_read(l, s, t, i)	lock_acquire_shared_recursive(l, s, t, NULL, i)
+#define seqcount_release(l, n, i)		lock_release(l, n, i)
+
 #define mutex_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
 #define mutex_acquire_nest(l, s, t, n, i)	lock_acquire_exclusive(l, s, t, n, i)
 #define mutex_release(l, n, i)			lock_release(l, n, i)
@@ -504,11 +508,11 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 #define rwsem_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
 #define rwsem_acquire_nest(l, s, t, n, i)	lock_acquire_exclusive(l, s, t, n, i)
 #define rwsem_acquire_read(l, s, t, i)		lock_acquire_shared(l, s, t, NULL, i)
-# define rwsem_release(l, n, i)			lock_release(l, n, i)
+#define rwsem_release(l, n, i)			lock_release(l, n, i)
 
 #define lock_map_acquire(l)			lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_)
 #define lock_map_acquire_read(l)		lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_)
-# define lock_map_release(l)			lock_release(l, 1, _THIS_IP_)
+#define lock_map_release(l)			lock_release(l, 1, _THIS_IP_)
 
 #ifdef CONFIG_PROVE_LOCKING
 # define might_lock(lock) 						\
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index bab49da8a0f0..d3181936c138 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -131,7 +131,7 @@ static inline int mutex_is_locked(struct mutex *lock)
 }
 
 /*
- * See kernel/mutex.c for detailed documentation of these APIs.
+ * See kernel/locking/mutex.c for detailed documentation of these APIs.
  * Also see Documentation/mutex-design.txt.
  */
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 10d16c4fbe89..41467f8ff8ec 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -2,8 +2,8 @@
 #define _SCHED_SYSCTL_H
 
 #ifdef CONFIG_DETECT_HUNG_TASK
+extern int	     sysctl_hung_task_check_count;
 extern unsigned int  sysctl_hung_task_panic;
-extern unsigned long sysctl_hung_task_check_count;
 extern unsigned long sysctl_hung_task_timeout_secs;
 extern unsigned long sysctl_hung_task_warnings;
 extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 21a209336e79..1e8a8b6e837d 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -34,6 +34,7 @@
 
 #include <linux/spinlock.h>
 #include <linux/preempt.h>
+#include <linux/lockdep.h>
 #include <asm/processor.h>
 
 /*
@@ -44,10 +45,50 @@
  */
 typedef struct seqcount {
 	unsigned sequence;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map dep_map;
+#endif
 } seqcount_t;
 
-#define SEQCNT_ZERO { 0 }
-#define seqcount_init(x)	do { *(x) = (seqcount_t) SEQCNT_ZERO; } while (0)
+static inline void __seqcount_init(seqcount_t *s, const char *name,
+					  struct lock_class_key *key)
+{
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	lockdep_init_map(&s->dep_map, name, key, 0);
+	s->sequence = 0;
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define SEQCOUNT_DEP_MAP_INIT(lockname) \
+		.dep_map = { .name = #lockname } \
+
+# define seqcount_init(s)				\
+	do {						\
+		static struct lock_class_key __key;	\
+		__seqcount_init((s), #s, &__key);	\
+	} while (0)
+
+static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
+{
+	seqcount_t *l = (seqcount_t *)s;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	seqcount_acquire_read(&l->dep_map, 0, 0, _RET_IP_);
+	seqcount_release(&l->dep_map, 1, _RET_IP_);
+	local_irq_restore(flags);
+}
+
+#else
+# define SEQCOUNT_DEP_MAP_INIT(lockname)
+# define seqcount_init(s) __seqcount_init(s, NULL, NULL)
+# define seqcount_lockdep_reader_access(x)
+#endif
+
+#define SEQCNT_ZERO(lockname) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(lockname)}
+
 
 /**
  * __read_seqcount_begin - begin a seq-read critical section (without barrier)
@@ -76,6 +117,22 @@ repeat:
 }
 
 /**
+ * read_seqcount_begin_no_lockdep - start seq-read critical section w/o lockdep
+ * @s: pointer to seqcount_t
+ * Returns: count to be passed to read_seqcount_retry
+ *
+ * read_seqcount_begin_no_lockdep opens a read critical section of the given
+ * seqcount, but without any lockdep checking. Validity of the critical
+ * section is tested by checking read_seqcount_retry function.
+ */
+static inline unsigned read_seqcount_begin_no_lockdep(const seqcount_t *s)
+{
+	unsigned ret = __read_seqcount_begin(s);
+	smp_rmb();
+	return ret;
+}
+
+/**
  * read_seqcount_begin - begin a seq-read critical section
  * @s: pointer to seqcount_t
  * Returns: count to be passed to read_seqcount_retry
@@ -86,9 +143,8 @@ repeat:
  */
 static inline unsigned read_seqcount_begin(const seqcount_t *s)
 {
-	unsigned ret = __read_seqcount_begin(s);
-	smp_rmb();
-	return ret;
+	seqcount_lockdep_reader_access(s);
+	return read_seqcount_begin_no_lockdep(s);
 }
 
 /**
@@ -108,6 +164,8 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s)
 static inline unsigned raw_seqcount_begin(const seqcount_t *s)
 {
 	unsigned ret = ACCESS_ONCE(s->sequence);
+
+	seqcount_lockdep_reader_access(s);
 	smp_rmb();
 	return ret & ~1;
 }
@@ -152,14 +210,21 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
  * Sequence counter only version assumes that callers are using their
  * own mutexing.
  */
-static inline void write_seqcount_begin(seqcount_t *s)
+static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass)
 {
 	s->sequence++;
 	smp_wmb();
+	seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
+}
+
+static inline void write_seqcount_begin(seqcount_t *s)
+{
+	write_seqcount_begin_nested(s, 0);
 }
 
 static inline void write_seqcount_end(seqcount_t *s)
 {
+	seqcount_release(&s->dep_map, 1, _RET_IP_);
 	smp_wmb();
 	s->sequence++;
 }
@@ -188,7 +253,7 @@ typedef struct {
  */
 #define __SEQLOCK_UNLOCKED(lockname)			\
 	{						\
-		.seqcount = SEQCNT_ZERO,		\
+		.seqcount = SEQCNT_ZERO(lockname),	\
 		.lock =	__SPIN_LOCK_UNLOCKED(lockname)	\
 	}
 
diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h
index 8da8c4e87da3..7bfabd20204c 100644
--- a/include/linux/u64_stats_sync.h
+++ b/include/linux/u64_stats_sync.h
@@ -67,6 +67,13 @@ struct u64_stats_sync {
 #endif
 };
 
+
+#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
+# define u64_stats_init(syncp)	seqcount_init(syncp.seq)
+#else
+# define u64_stats_init(syncp)	do { } while (0)
+#endif
+
 static inline void u64_stats_update_begin(struct u64_stats_sync *syncp)
 {
 #if BITS_PER_LONG==32 && defined(CONFIG_SMP)
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 613381bcde40..04c308413a5d 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -424,6 +424,25 @@ TRACE_EVENT(sched_pi_setprio,
 			__entry->oldprio, __entry->newprio)
 );
 
+#ifdef CONFIG_DETECT_HUNG_TASK
+TRACE_EVENT(sched_process_hang,
+	TP_PROTO(struct task_struct *tsk),
+	TP_ARGS(tsk),
+
+	TP_STRUCT__entry(
+		__array( char,	comm,	TASK_COMM_LEN	)
+		__field( pid_t,	pid			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid = tsk->pid;
+	),
+
+	TP_printk("comm=%s pid=%d", __entry->comm, __entry->pid)
+);
+#endif /* CONFIG_DETECT_HUNG_TASK */
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */