Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (44 commits)
  rcu: Fix accelerated GPs for last non-dynticked CPU
  rcu: Make non-RCU_PROVE_LOCKING rcu_read_lock_sched_held() understand boot
  rcu: Fix accelerated grace periods for last non-dynticked CPU
  rcu: Export rcu_scheduler_active
  rcu: Make rcu_read_lock_sched_held() take boot time into account
  rcu: Make lockdep_rcu_dereference() message less alarmist
  sched, cgroups: Fix module export
  rcu: Add RCU_CPU_STALL_VERBOSE to dump detailed per-task information
  rcu: Fix rcutorture mod_timer argument to delay one jiffy
  rcu: Fix deadlock in TREE_PREEMPT_RCU CPU stall detection
  rcu: Convert to raw_spinlocks
  rcu: Stop overflowing signed integers
  rcu: Use canonical URL for Mathieu's dissertation
  rcu: Accelerate grace period if last non-dynticked CPU
  rcu: Fix citation of Mathieu's dissertation
  rcu: Documentation update for CONFIG_PROVE_RCU
  security: Apply lockdep-based checking to rcu_dereference() uses
  idr: Apply lockdep-based diagnostics to rcu_dereference() uses
  radix-tree: Disable RCU lockdep checking in radix tree
  vfs: Abstract rcu_dereference_check for files-fdtable use
  ...

include/linux/cgroup.h

@@ -28,6 +28,7 @@ struct css_id;
 extern int cgroup_init_early(void);
 extern int cgroup_init(void);
 extern void cgroup_lock(void);
+extern int cgroup_lock_is_held(void);
 extern bool cgroup_lock_live_group(struct cgroup *cgrp);
 extern void cgroup_unlock(void);
 extern void cgroup_fork(struct task_struct *p);
@@ -486,7 +487,9 @@ static inline struct cgroup_subsys_state *cgroup_subsys_state(
 static inline struct cgroup_subsys_state *task_subsys_state(
 	struct task_struct *task, int subsys_id)
 {
-	return rcu_dereference(task->cgroups->subsys[subsys_id]);
+	return rcu_dereference_check(task->cgroups->subsys[subsys_id],
+				     rcu_read_lock_held() ||
+				     cgroup_lock_is_held());
 }
 
 static inline struct cgroup* task_cgroup(struct task_struct *task,

include/linux/cpumask.h

@@ -143,6 +143,8 @@ static inline unsigned int cpumask_any_but(const struct cpumask *mask,
 
 #define for_each_cpu(cpu, mask)			\
 	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
+#define for_each_cpu_not(cpu, mask)		\
+	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
 #define for_each_cpu_and(cpu, mask, and)	\
 	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)and)
 #else
@@ -202,6 +204,18 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
 		(cpu) = cpumask_next((cpu), (mask)),	\
 		(cpu) < nr_cpu_ids;)
 
+/**
+ * for_each_cpu_not - iterate over every cpu in a complemented mask
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask: the cpumask pointer
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu_not(cpu, mask)				\
+	for ((cpu) = -1;					\
+		(cpu) = cpumask_next_zero((cpu), (mask)),	\
+		(cpu) < nr_cpu_ids;)
+
 /**
  * for_each_cpu_and - iterate over every cpu in both masks
  * @cpu: the (optionally unsigned) integer iterator

include/linux/cred.h

@@ -280,7 +280,7 @@ static inline void put_cred(const struct cred *_cred)
  * task or by holding tasklist_lock to prevent it from being unlinked.
  */
 #define __task_cred(task) \
-	((const struct cred *)(rcu_dereference((task)->real_cred)))
+	((const struct cred *)(rcu_dereference_check((task)->real_cred, rcu_read_lock_held() || lockdep_is_held(&tasklist_lock))))
 
 /**
  * get_task_cred - Get another task's objective credentials

include/linux/fdtable.h

@@ -57,7 +57,14 @@ struct files_struct {
 	struct file * fd_array[NR_OPEN_DEFAULT];
 };
 
-#define files_fdtable(files) (rcu_dereference((files)->fdt))
+#define rcu_dereference_check_fdtable(files, fdtfd) \
+	(rcu_dereference_check((fdtfd), \
+			       rcu_read_lock_held() || \
+			       lockdep_is_held(&(files)->file_lock) || \
+			       atomic_read(&(files)->count) == 1))
+
+#define files_fdtable(files) \
+		(rcu_dereference_check_fdtable((files), (files)->fdt))
 
 struct file_operations;
 struct vfsmount;
@@ -78,7 +85,7 @@ static inline struct file * fcheck_files(struct files_struct *files, unsigned in
 	struct fdtable *fdt = files_fdtable(files);
 
 	if (fd < fdt->max_fds)
-		file = rcu_dereference(fdt->fd[fd]);
+		file = rcu_dereference_check_fdtable(files, fdt->fd[fd]);
 	return file;
 }
 

include/linux/lockdep.h

@@ -534,4 +534,8 @@ do {									\
 # define might_lock_read(lock) do { } while (0)
 #endif
 
+#ifdef CONFIG_PROVE_RCU
+extern void lockdep_rcu_dereference(const char *file, const int line);
+#endif
+
 #endif /* __LINUX_LOCKDEP_H */

include/linux/rculist.h

@@ -208,7 +208,7 @@ static inline void list_splice_init_rcu(struct list_head *list,
  * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
  */
 #define list_entry_rcu(ptr, type, member) \
-	container_of(rcu_dereference(ptr), type, member)
+	container_of(rcu_dereference_raw(ptr), type, member)
 
 /**
  * list_first_entry_rcu - get the first element from a list
@@ -225,9 +225,9 @@ static inline void list_splice_init_rcu(struct list_head *list,
 	list_entry_rcu((ptr)->next, type, member)
 
 #define __list_for_each_rcu(pos, head) \
-	for (pos = rcu_dereference((head)->next); \
+	for (pos = rcu_dereference_raw((head)->next); \
 		pos != (head); \
-		pos = rcu_dereference(pos->next))
+		pos = rcu_dereference_raw(pos->next))
 
 /**
  * list_for_each_entry_rcu	-	iterate over rcu list of given type
@@ -257,9 +257,9 @@ static inline void list_splice_init_rcu(struct list_head *list,
  * as long as the traversal is guarded by rcu_read_lock().
  */
 #define list_for_each_continue_rcu(pos, head) \
-	for ((pos) = rcu_dereference((pos)->next); \
+	for ((pos) = rcu_dereference_raw((pos)->next); \
 		prefetch((pos)->next), (pos) != (head); \
-		(pos) = rcu_dereference((pos)->next))
+		(pos) = rcu_dereference_raw((pos)->next))
 
 /**
  * list_for_each_entry_continue_rcu - continue iteration over list of given type
@@ -418,10 +418,10 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
  * as long as the traversal is guarded by rcu_read_lock().
  */
 #define hlist_for_each_entry_rcu(tpos, pos, head, member)		 \
-	for (pos = rcu_dereference((head)->first);			 \
+	for (pos = rcu_dereference_raw((head)->first);			 \
 		pos && ({ prefetch(pos->next); 1; }) &&			 \
 		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \
-		pos = rcu_dereference(pos->next))
+		pos = rcu_dereference_raw(pos->next))
 
 #endif	/* __KERNEL__ */
 #endif

include/linux/rculist_nulls.h

@@ -101,10 +101,10 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
  *
  */
 #define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \
-	for (pos = rcu_dereference((head)->first);			 \
+	for (pos = rcu_dereference_raw((head)->first);			 \
 		(!is_a_nulls(pos)) &&			\
 		({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \
-		pos = rcu_dereference(pos->next))
+		pos = rcu_dereference_raw(pos->next))
 
 #endif
 #endif

include/linux/rcupdate.h

@@ -62,6 +62,8 @@ extern int sched_expedited_torture_stats(char *page);
 
 /* Internal to kernel */
 extern void rcu_init(void);
+extern int rcu_scheduler_active;
+extern void rcu_scheduler_starting(void);
 
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
 #include <linux/rcutree.h>
@@ -78,14 +80,120 @@ extern void rcu_init(void);
 } while (0)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
+
 extern struct lockdep_map rcu_lock_map;
-# define rcu_read_acquire()	\
-			lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
+# define rcu_read_acquire() \
+		lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
 # define rcu_read_release()	lock_release(&rcu_lock_map, 1, _THIS_IP_)
-#else
-# define rcu_read_acquire()	do { } while (0)
-# define rcu_read_release()	do { } while (0)
-#endif
+
+extern struct lockdep_map rcu_bh_lock_map;
+# define rcu_read_acquire_bh() \
+		lock_acquire(&rcu_bh_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
+# define rcu_read_release_bh()	lock_release(&rcu_bh_lock_map, 1, _THIS_IP_)
+
+extern struct lockdep_map rcu_sched_lock_map;
+# define rcu_read_acquire_sched() \
+		lock_acquire(&rcu_sched_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
+# define rcu_read_release_sched() \
+		lock_release(&rcu_sched_lock_map, 1, _THIS_IP_)
+
+/**
+ * rcu_read_lock_held - might we be in RCU read-side critical section?
+ *
+ * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
+ * an RCU read-side critical section.  In absence of CONFIG_PROVE_LOCKING,
+ * this assumes we are in an RCU read-side critical section unless it can
+ * prove otherwise.
+ */
+static inline int rcu_read_lock_held(void)
+{
+	if (debug_locks)
+		return lock_is_held(&rcu_lock_map);
+	return 1;
+}
+
+/**
+ * rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section?
+ *
+ * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
+ * an RCU-bh read-side critical section.  In absence of CONFIG_PROVE_LOCKING,
+ * this assumes we are in an RCU-bh read-side critical section unless it can
+ * prove otherwise.
+ */
+static inline int rcu_read_lock_bh_held(void)
+{
+	if (debug_locks)
+		return lock_is_held(&rcu_bh_lock_map);
+	return 1;
+}
+
+/**
+ * rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section?
+ *
+ * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in an
+ * RCU-sched read-side critical section.  In absence of CONFIG_PROVE_LOCKING,
+ * this assumes we are in an RCU-sched read-side critical section unless it
+ * can prove otherwise.  Note that disabling of preemption (including
+ * disabling irqs) counts as an RCU-sched read-side critical section.
+ */
+static inline int rcu_read_lock_sched_held(void)
+{
+	int lockdep_opinion = 0;
+
+	if (debug_locks)
+		lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
+	return lockdep_opinion || preempt_count() != 0 || !rcu_scheduler_active;
+}
+
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+# define rcu_read_acquire()		do { } while (0)
+# define rcu_read_release()		do { } while (0)
+# define rcu_read_acquire_bh()		do { } while (0)
+# define rcu_read_release_bh()		do { } while (0)
+# define rcu_read_acquire_sched()	do { } while (0)
+# define rcu_read_release_sched()	do { } while (0)
+
+static inline int rcu_read_lock_held(void)
+{
+	return 1;
+}
+
+static inline int rcu_read_lock_bh_held(void)
+{
+	return 1;
+}
+
+static inline int rcu_read_lock_sched_held(void)
+{
+	return preempt_count() != 0 || !rcu_scheduler_active;
+}
+
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+#ifdef CONFIG_PROVE_RCU
+
+/**
+ * rcu_dereference_check - rcu_dereference with debug checking
+ *
+ * Do an rcu_dereference(), but check that the context is correct.
+ * For example, rcu_dereference_check(gp, rcu_read_lock_held()) to
+ * ensure that the rcu_dereference_check() executes within an RCU
+ * read-side critical section.  It is also possible to check for
+ * locks being held, for example, by using lockdep_is_held().
+ */
+#define rcu_dereference_check(p, c) \
+	({ \
+		if (debug_locks && !(c)) \
+			lockdep_rcu_dereference(__FILE__, __LINE__); \
+		rcu_dereference_raw(p); \
+	})
+
+#else /* #ifdef CONFIG_PROVE_RCU */
+
+#define rcu_dereference_check(p, c)	rcu_dereference_raw(p)
+
+#endif /* #else #ifdef CONFIG_PROVE_RCU */
 
 /**
  * rcu_read_lock - mark the beginning of an RCU read-side critical section.
@@ -160,7 +268,7 @@ static inline void rcu_read_lock_bh(void)
 {
 	__rcu_read_lock_bh();
 	__acquire(RCU_BH);
-	rcu_read_acquire();
+	rcu_read_acquire_bh();
 }
 
 /*
@@ -170,7 +278,7 @@ static inline void rcu_read_lock_bh(void)
  */
 static inline void rcu_read_unlock_bh(void)
 {
-	rcu_read_release();
+	rcu_read_release_bh();
 	__release(RCU_BH);
 	__rcu_read_unlock_bh();
 }
@@ -188,7 +296,7 @@ static inline void rcu_read_lock_sched(void)
 {
 	preempt_disable();
 	__acquire(RCU_SCHED);
-	rcu_read_acquire();
+	rcu_read_acquire_sched();
 }
 
 /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */
@@ -205,7 +313,7 @@ static inline notrace void rcu_read_lock_sched_notrace(void)
  */
 static inline void rcu_read_unlock_sched(void)
 {
-	rcu_read_release();
+	rcu_read_release_sched();
 	__release(RCU_SCHED);
 	preempt_enable();
 }
@@ -219,21 +327,48 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 
 
 /**
- * rcu_dereference - fetch an RCU-protected pointer in an
- * RCU read-side critical section.  This pointer may later
- * be safely dereferenced.
+ * rcu_dereference_raw - fetch an RCU-protected pointer
+ *
+ * The caller must be within some flavor of RCU read-side critical
+ * section, or must be otherwise preventing the pointer from changing,
+ * for example, by holding an appropriate lock.  This pointer may later
+ * be safely dereferenced.  It is the caller's responsibility to have
+ * done the right thing, as this primitive does no checking of any kind.
  *
  * Inserts memory barriers on architectures that require them
  * (currently only the Alpha), and, more importantly, documents
  * exactly which pointers are protected by RCU.
  */
-
-#define rcu_dereference(p)     ({ \
+#define rcu_dereference_raw(p)	({ \
 				typeof(p) _________p1 = ACCESS_ONCE(p); \
 				smp_read_barrier_depends(); \
 				(_________p1); \
 				})
 
+/**
+ * rcu_dereference - fetch an RCU-protected pointer, checking for RCU
+ *
+ * Makes rcu_dereference_check() do the dirty work.
+ */
+#define rcu_dereference(p) \
+	rcu_dereference_check(p, rcu_read_lock_held())
+
+/**
+ * rcu_dereference_bh - fetch an RCU-protected pointer, checking for RCU-bh
+ *
+ * Makes rcu_dereference_check() do the dirty work.
+ */
+#define rcu_dereference_bh(p) \
+		rcu_dereference_check(p, rcu_read_lock_bh_held())
+
+/**
+ * rcu_dereference_sched - fetch RCU-protected pointer, checking for RCU-sched
+ *
+ * Makes rcu_dereference_check() do the dirty work.
+ */
+#define rcu_dereference_sched(p) \
+		rcu_dereference_check(p, rcu_read_lock_sched_held())
+
 /**
  * rcu_assign_pointer - assign (publicize) a pointer to a newly
  * initialized structure that will be dereferenced by RCU read-side

include/linux/rcutiny.h

@@ -62,6 +62,18 @@ static inline long rcu_batches_completed_bh(void)
 
 extern int rcu_expedited_torture_stats(char *page);
 
+static inline void rcu_force_quiescent_state(void)
+{
+}
+
+static inline void rcu_bh_force_quiescent_state(void)
+{
+}
+
+static inline void rcu_sched_force_quiescent_state(void)
+{
+}
+
 #define synchronize_rcu synchronize_sched
 
 static inline void synchronize_rcu_expedited(void)
@@ -93,10 +105,6 @@ static inline void rcu_exit_nohz(void)
 
 #endif /* #else #ifdef CONFIG_NO_HZ */
 
-static inline void rcu_scheduler_starting(void)
-{
-}
-
 static inline void exit_rcu(void)
 {
 }

include/linux/rcutree.h

@@ -35,7 +35,6 @@ struct notifier_block;
 extern void rcu_sched_qs(int cpu);
 extern void rcu_bh_qs(int cpu);
 extern int rcu_needs_cpu(int cpu);
-extern void rcu_scheduler_starting(void);
 extern int rcu_expedited_torture_stats(char *page);
 
 #ifdef CONFIG_TREE_PREEMPT_RCU
@@ -99,6 +98,9 @@ extern void rcu_check_callbacks(int cpu, int user);
 extern long rcu_batches_completed(void);
 extern long rcu_batches_completed_bh(void);
 extern long rcu_batches_completed_sched(void);
+extern void rcu_force_quiescent_state(void);
+extern void rcu_bh_force_quiescent_state(void);
+extern void rcu_sched_force_quiescent_state(void);
 
 #ifdef CONFIG_NO_HZ
 void rcu_enter_nohz(void);

include/linux/rtnetlink.h

@@ -735,6 +735,9 @@ extern void rtnl_lock(void);
 extern void rtnl_unlock(void);
 extern int rtnl_trylock(void);
 extern int rtnl_is_locked(void);
+#ifdef CONFIG_PROVE_LOCKING
+extern int lockdep_rtnl_is_held(void);
+#endif /* #ifdef CONFIG_PROVE_LOCKING */
 
 extern void rtnetlink_init(void);
 extern void __rtnl_unlock(void);

include/linux/srcu.h

@@ -35,6 +35,9 @@ struct srcu_struct {
 	int completed;
 	struct srcu_struct_array *per_cpu_ref;
 	struct mutex mutex;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map dep_map;
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 };
 
 #ifndef CONFIG_PREEMPT
@@ -43,12 +46,100 @@ struct srcu_struct {
 #define srcu_barrier()
 #endif /* #else #ifndef CONFIG_PREEMPT */
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+int __init_srcu_struct(struct srcu_struct *sp, const char *name,
+		       struct lock_class_key *key);
+
+#define init_srcu_struct(sp) \
+({ \
+	static struct lock_class_key __srcu_key; \
+	\
+	__init_srcu_struct((sp), #sp, &__srcu_key); \
+})
+
+# define srcu_read_acquire(sp) \
+		lock_acquire(&(sp)->dep_map, 0, 0, 2, 1, NULL, _THIS_IP_)
+# define srcu_read_release(sp) \
+		lock_release(&(sp)->dep_map, 1, _THIS_IP_)
+
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
 int init_srcu_struct(struct srcu_struct *sp);
+
+# define srcu_read_acquire(sp)  do { } while (0)
+# define srcu_read_release(sp)  do { } while (0)
+
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
 void cleanup_srcu_struct(struct srcu_struct *sp);
-int srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
-void srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
+int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
+void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
 void synchronize_srcu(struct srcu_struct *sp);
 void synchronize_srcu_expedited(struct srcu_struct *sp);
 long srcu_batches_completed(struct srcu_struct *sp);
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+/**
+ * srcu_read_lock_held - might we be in SRCU read-side critical section?
+ *
+ * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
+ * an SRCU read-side critical section.  In absence of CONFIG_PROVE_LOCKING,
+ * this assumes we are in an SRCU read-side critical section unless it can
+ * prove otherwise.
+ */
+static inline int srcu_read_lock_held(struct srcu_struct *sp)
+{
+	if (debug_locks)
+		return lock_is_held(&sp->dep_map);
+	return 1;
+}
+
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+static inline int srcu_read_lock_held(struct srcu_struct *sp)
+{
+	return 1;
+}
+
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+/**
+ * srcu_dereference - fetch SRCU-protected pointer with checking
+ *
+ * Makes rcu_dereference_check() do the dirty work.
+ */
+#define srcu_dereference(p, sp) \
+		rcu_dereference_check(p, srcu_read_lock_held(sp))
+
+/**
+ * srcu_read_lock - register a new reader for an SRCU-protected structure.
+ * @sp: srcu_struct in which to register the new reader.
+ *
+ * Enter an SRCU read-side critical section.  Note that SRCU read-side
+ * critical sections may be nested.
+ */
+static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp)
+{
+	int retval = __srcu_read_lock(sp);
+
+	srcu_read_acquire(sp);
+	return retval;
+}
+
+/**
+ * srcu_read_unlock - unregister a old reader from an SRCU-protected structure.
+ * @sp: srcu_struct in which to unregister the old reader.
+ * @idx: return value from corresponding srcu_read_lock().
+ *
+ * Exit an SRCU read-side critical section.
+ */
+static inline void srcu_read_unlock(struct srcu_struct *sp, int idx)
+	__releases(sp)
+{
+	srcu_read_release(sp);
+	__srcu_read_unlock(sp, idx);
+}
+
 #endif