15 files changed, 366 insertions, 146 deletions

diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index 8dee32007500..0540ca27a446 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -291,7 +291,7 @@ handle_t *journal_start(journal_t *journal, int nblocks)
                 goto out;
         }
 
-        lock_acquire(&handle->h_lockdep_map, 0, 0, 0, 2, _THIS_IP_);
+        lock_map_acquire(&handle->h_lockdep_map);
 
 out:
         return handle;
@@ -1448,7 +1448,7 @@ int journal_stop(handle_t *handle)
                 spin_unlock(&journal->j_state_lock);
         }
 
-        lock_release(&handle->h_lockdep_map, 1, _THIS_IP_);
+        lock_map_release(&handle->h_lockdep_map);
 
         jbd_free_handle(handle);
         return err;
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 4f7cadbb19fa..e5d540588fa9 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -301,7 +301,7 @@ handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
                 goto out;
         }
 
-        lock_acquire(&handle->h_lockdep_map, 0, 0, 0, 2, _THIS_IP_);
+        lock_map_acquire(&handle->h_lockdep_map);
 out:
         return handle;
 }
@@ -1279,7 +1279,7 @@ int jbd2_journal_stop(handle_t *handle)
                 spin_unlock(&journal->j_state_lock);
         }
 
-        lock_release(&handle->h_lockdep_map, 1, _THIS_IP_);
+        lock_map_release(&handle->h_lockdep_map);
 
         jbd2_free_handle(handle);
         return err;
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 2486eb4edbf1..331e5f1c2d8e 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -89,6 +89,7 @@ struct lock_class {
 
         struct lockdep_subclass_key     *key;
         unsigned int                    subclass;
+        unsigned int                    dep_gen_id;
 
         /*
          * IRQ/softirq usage tracking bits:
@@ -189,6 +190,14 @@ struct lock_chain {
         u64                             chain_key;
 };
 
+#define MAX_LOCKDEP_KEYS_BITS           13
+/*
+ * Subtract one because we offset hlock->class_idx by 1 in order
+ * to make 0 mean no class. This avoids overflowing the class_idx
+ * bitfield and hitting the BUG in hlock_class().
+ */
+#define MAX_LOCKDEP_KEYS                ((1UL << MAX_LOCKDEP_KEYS_BITS) - 1)
+
 struct held_lock {
         /*
          * One-way hash of the dependency chain up to this point. We
@@ -205,14 +214,14 @@ struct held_lock {
          * with zero), here we store the previous hash value:
          */
         u64                             prev_chain_key;
-        struct lock_class               *class;
         unsigned long                   acquire_ip;
         struct lockdep_map              *instance;
-
+        struct lockdep_map              *nest_lock;
 #ifdef CONFIG_LOCK_STAT
         u64                             waittime_stamp;
         u64                             holdtime_stamp;
 #endif
+        unsigned int                    class_idx:MAX_LOCKDEP_KEYS_BITS;
         /*
          * The lock-stack is unified in that the lock chains of interrupt
          * contexts nest ontop of process context chains, but we 'separate'
@@ -226,11 +235,11 @@ struct held_lock {
          * The following field is used to detect when we cross into an
          * interrupt context:
          */
-        int                             irq_context;
-        int                             trylock;
-        int                             read;
-        int                             check;
-        int                             hardirqs_off;
+        unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */
+        unsigned int trylock:1;
+        unsigned int read:2;        /* see lock_acquire() comment */
+        unsigned int check:2;       /* see lock_acquire() comment */
+        unsigned int hardirqs_off:1;
 };
 
 /*
@@ -294,11 +303,15 @@ extern void lockdep_init_map(struct lockdep_map *lock, const char *name,
  *   2: full validation
  */
 extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
-                         int trylock, int read, int check, unsigned long ip);
+                         int trylock, int read, int check,
+                         struct lockdep_map *nest_lock, unsigned long ip);
 
 extern void lock_release(struct lockdep_map *lock, int nested,
                          unsigned long ip);
 
+extern void lock_set_subclass(struct lockdep_map *lock, unsigned int subclass,
+                              unsigned long ip);
+
 # define INIT_LOCKDEP                           .lockdep_recursion = 0,
 
 #define lockdep_depth(tsk)      (debug_locks ? (tsk)->lockdep_depth : 0)
@@ -313,8 +326,9 @@ static inline void lockdep_on(void)
 {
 }
 
-# define lock_acquire(l, s, t, r, c, i)         do { } while (0)
+# define lock_acquire(l, s, t, r, c, n, i)      do { } while (0)
 # define lock_release(l, n, i)                  do { } while (0)
+# define lock_set_subclass(l, s, i)             do { } while (0)
 # define lockdep_init()                         do { } while (0)
 # define lockdep_info()                         do { } while (0)
 # define lockdep_init_map(lock, name, key, sub) do { (void)(key); } while (0)
@@ -400,9 +414,11 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # ifdef CONFIG_PROVE_LOCKING
-#  define spin_acquire(l, s, t, i)              lock_acquire(l, s, t, 0, 2, i)
+#  define spin_acquire(l, s, t, i)              lock_acquire(l, s, t, 0, 2, NULL, i)
+#  define spin_acquire_nest(l, s, t, n, i)      lock_acquire(l, s, t, 0, 2, n, i)
 # else
-#  define spin_acquire(l, s, t, i)              lock_acquire(l, s, t, 0, 1, i)
+#  define spin_acquire(l, s, t, i)              lock_acquire(l, s, t, 0, 1, NULL, i)
+#  define spin_acquire_nest(l, s, t, n, i)      lock_acquire(l, s, t, 0, 1, NULL, i)
 # endif
 # define spin_release(l, n, i)                  lock_release(l, n, i)
 #else
@@ -412,11 +428,11 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # ifdef CONFIG_PROVE_LOCKING
-#  define rwlock_acquire(l, s, t, i)            lock_acquire(l, s, t, 0, 2, i)
-#  define rwlock_acquire_read(l, s, t, i)       lock_acquire(l, s, t, 2, 2, i)
+#  define rwlock_acquire(l, s, t, i)            lock_acquire(l, s, t, 0, 2, NULL, i)
+#  define rwlock_acquire_read(l, s, t, i)       lock_acquire(l, s, t, 2, 2, NULL, i)
 # else
-#  define rwlock_acquire(l, s, t, i)            lock_acquire(l, s, t, 0, 1, i)
-#  define rwlock_acquire_read(l, s, t, i)       lock_acquire(l, s, t, 2, 1, i)
+#  define rwlock_acquire(l, s, t, i)            lock_acquire(l, s, t, 0, 1, NULL, i)
+#  define rwlock_acquire_read(l, s, t, i)       lock_acquire(l, s, t, 2, 1, NULL, i)
 # endif
 # define rwlock_release(l, n, i)                lock_release(l, n, i)
 #else
@@ -427,9 +443,9 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # ifdef CONFIG_PROVE_LOCKING
-#  define mutex_acquire(l, s, t, i)             lock_acquire(l, s, t, 0, 2, i)
+#  define mutex_acquire(l, s, t, i)             lock_acquire(l, s, t, 0, 2, NULL, i)
 # else
-#  define mutex_acquire(l, s, t, i)             lock_acquire(l, s, t, 0, 1, i)
+#  define mutex_acquire(l, s, t, i)             lock_acquire(l, s, t, 0, 1, NULL, i)
 # endif
 # define mutex_release(l, n, i)                 lock_release(l, n, i)
 #else
@@ -439,11 +455,11 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # ifdef CONFIG_PROVE_LOCKING
-#  define rwsem_acquire(l, s, t, i)             lock_acquire(l, s, t, 0, 2, i)
-#  define rwsem_acquire_read(l, s, t, i)        lock_acquire(l, s, t, 1, 2, i)
+#  define rwsem_acquire(l, s, t, i)             lock_acquire(l, s, t, 0, 2, NULL, i)
+#  define rwsem_acquire_read(l, s, t, i)        lock_acquire(l, s, t, 1, 2, NULL, i)
 # else
-#  define rwsem_acquire(l, s, t, i)             lock_acquire(l, s, t, 0, 1, i)
-#  define rwsem_acquire_read(l, s, t, i)        lock_acquire(l, s, t, 1, 1, i)
+#  define rwsem_acquire(l, s, t, i)             lock_acquire(l, s, t, 0, 1, NULL, i)
+#  define rwsem_acquire_read(l, s, t, i)        lock_acquire(l, s, t, 1, 1, NULL, i)
 # endif
 # define rwsem_release(l, n, i)                 lock_release(l, n, i)
 #else
@@ -452,4 +468,16 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 # define rwsem_release(l, n, i)                 do { } while (0)
 #endif
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# ifdef CONFIG_PROVE_LOCKING
+#  define lock_map_acquire(l)           lock_acquire(l, 0, 0, 0, 2, NULL, _THIS_IP_)
+# else
+#  define lock_map_acquire(l)           lock_acquire(l, 0, 0, 0, 1, NULL, _THIS_IP_)
+# endif
+# define lock_map_release(l)                    lock_release(l, 1, _THIS_IP_)
+#else
+# define lock_map_acquire(l)                    do { } while (0)
+# define lock_map_release(l)                    do { } while (0)
+#endif
+
 #endif /* __LINUX_LOCKDEP_H */
diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h
index 8c774905dcfe..4ab843622727 100644
--- a/include/linux/rcuclassic.h
+++ b/include/linux/rcuclassic.h
@@ -117,7 +117,7 @@ extern int rcu_needs_cpu(int cpu);
 #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, _THIS_IP_)
+                        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)
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 61e5610ad165..e0c0fccced46 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -183,8 +183,14 @@ do {								\
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define spin_lock_nested(lock, subclass) _spin_lock_nested(lock, subclass)
+# define spin_lock_nest_lock(lock, nest_lock)                           \
+         do {                                                           \
+                 typecheck(struct lockdep_map *, &(nest_lock)->dep_map);\
+                 _spin_lock_nest_lock(lock, &(nest_lock)->dep_map);     \
+         } while (0)
 #else
 # define spin_lock_nested(lock, subclass) _spin_lock(lock)
+# define spin_lock_nest_lock(lock, nest_lock) _spin_lock(lock)
 #endif
 
 #define write_lock(lock)                _write_lock(lock)
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index 8a2307ce7296..d79845d034b5 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -22,6 +22,8 @@ int in_lock_functions(unsigned long addr);
 void __lockfunc _spin_lock(spinlock_t *lock)            __acquires(lock);
 void __lockfunc _spin_lock_nested(spinlock_t *lock, int subclass)
                                                         __acquires(lock);
+void __lockfunc _spin_lock_nest_lock(spinlock_t *lock, struct lockdep_map *map)
+                                                        __acquires(lock);
 void __lockfunc _read_lock(rwlock_t *lock)              __acquires(lock);
 void __lockfunc _write_lock(rwlock_t *lock)             __acquires(lock);
 void __lockfunc _spin_lock_bh(spinlock_t *lock)         __acquires(lock);
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index d38a64362973..1aa91fd6b06e 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -124,6 +124,15 @@ static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES];
 unsigned long nr_lock_classes;
 static struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
 
+static inline struct lock_class *hlock_class(struct held_lock *hlock)
+{
+        if (!hlock->class_idx) {
+                DEBUG_LOCKS_WARN_ON(1);
+                return NULL;
+        }
+        return lock_classes + hlock->class_idx - 1;
+}
+
 #ifdef CONFIG_LOCK_STAT
 static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
 
@@ -222,7 +231,7 @@ static void lock_release_holdtime(struct held_lock *hlock)
 
         holdtime = sched_clock() - hlock->holdtime_stamp;
 
-        stats = get_lock_stats(hlock->class);
+        stats = get_lock_stats(hlock_class(hlock));
         if (hlock->read)
                 lock_time_inc(&stats->read_holdtime, holdtime);
         else
@@ -372,6 +381,19 @@ unsigned int nr_process_chains;
 unsigned int max_lockdep_depth;
 unsigned int max_recursion_depth;
 
+static unsigned int lockdep_dependency_gen_id;
+
+static bool lockdep_dependency_visit(struct lock_class *source,
+                                     unsigned int depth)
+{
+        if (!depth)
+                lockdep_dependency_gen_id++;
+        if (source->dep_gen_id == lockdep_dependency_gen_id)
+                return true;
+        source->dep_gen_id = lockdep_dependency_gen_id;
+        return false;
+}
+
 #ifdef CONFIG_DEBUG_LOCKDEP
 /*
  * We cannot printk in early bootup code. Not even early_printk()
@@ -505,7 +527,7 @@ static void print_lockdep_cache(struct lockdep_map *lock)
 
 static void print_lock(struct held_lock *hlock)
 {
-        print_lock_name(hlock->class);
+        print_lock_name(hlock_class(hlock));
         printk(", at: ");
         print_ip_sym(hlock->acquire_ip);
 }
@@ -558,6 +580,9 @@ static void print_lock_dependencies(struct lock_class *class, int depth)
 {
         struct lock_list *entry;
 
+        if (lockdep_dependency_visit(class, depth))
+                return;
+
         if (DEBUG_LOCKS_WARN_ON(depth >= 20))
                 return;
 
@@ -932,7 +957,7 @@ static noinline int print_circular_bug_tail(void)
         if (debug_locks_silent)
                 return 0;
 
-        this.class = check_source->class;
+        this.class = hlock_class(check_source);
         if (!save_trace(&this.trace))
                 return 0;
 
@@ -959,6 +984,67 @@ static int noinline print_infinite_recursion_bug(void)
         return 0;
 }
 
+unsigned long __lockdep_count_forward_deps(struct lock_class *class,
+                                           unsigned int depth)
+{
+        struct lock_list *entry;
+        unsigned long ret = 1;
+
+        if (lockdep_dependency_visit(class, depth))
+                return 0;
+
+        /*
+         * Recurse this class's dependency list:
+         */
+        list_for_each_entry(entry, &class->locks_after, entry)
+                ret += __lockdep_count_forward_deps(entry->class, depth + 1);
+
+        return ret;
+}
+
+unsigned long lockdep_count_forward_deps(struct lock_class *class)
+{
+        unsigned long ret, flags;
+
+        local_irq_save(flags);
+        __raw_spin_lock(&lockdep_lock);
+        ret = __lockdep_count_forward_deps(class, 0);
+        __raw_spin_unlock(&lockdep_lock);
+        local_irq_restore(flags);
+
+        return ret;
+}
+
+unsigned long __lockdep_count_backward_deps(struct lock_class *class,
+                                            unsigned int depth)
+{
+        struct lock_list *entry;
+        unsigned long ret = 1;
+
+        if (lockdep_dependency_visit(class, depth))
+                return 0;
+        /*
+         * Recurse this class's dependency list:
+         */
+        list_for_each_entry(entry, &class->locks_before, entry)
+                ret += __lockdep_count_backward_deps(entry->class, depth + 1);
+
+        return ret;
+}
+
+unsigned long lockdep_count_backward_deps(struct lock_class *class)
+{
+        unsigned long ret, flags;
+
+        local_irq_save(flags);
+        __raw_spin_lock(&lockdep_lock);
+        ret = __lockdep_count_backward_deps(class, 0);
+        __raw_spin_unlock(&lockdep_lock);
+        local_irq_restore(flags);
+
+        return ret;
+}
+
 /*
  * Prove that the dependency graph starting at <entry> can not
  * lead to <target>. Print an error and return 0 if it does.
@@ -968,6 +1054,9 @@ check_noncircular(struct lock_class *source, unsigned int depth)
 {
         struct lock_list *entry;
 
+        if (lockdep_dependency_visit(source, depth))
+                return 1;
+
         debug_atomic_inc(&nr_cyclic_check_recursions);
         if (depth > max_recursion_depth)
                 max_recursion_depth = depth;
@@ -977,7 +1066,7 @@ check_noncircular(struct lock_class *source, unsigned int depth)
          * Check this lock's dependency list:
          */
         list_for_each_entry(entry, &source->locks_after, entry) {
-                if (entry->class == check_target->class)
+                if (entry->class == hlock_class(check_target))
                         return print_circular_bug_header(entry, depth+1);
                 debug_atomic_inc(&nr_cyclic_checks);
                 if (!check_noncircular(entry->class, depth+1))
@@ -1011,6 +1100,9 @@ find_usage_forwards(struct lock_class *source, unsigned int depth)
         struct lock_list *entry;
         int ret;
 
+        if (lockdep_dependency_visit(source, depth))
+                return 1;
+
         if (depth > max_recursion_depth)
                 max_recursion_depth = depth;
         if (depth >= RECURSION_LIMIT)
@@ -1050,6 +1142,9 @@ find_usage_backwards(struct lock_class *source, unsigned int depth)
         struct lock_list *entry;
         int ret;
 
+        if (lockdep_dependency_visit(source, depth))
+                return 1;
+
         if (!__raw_spin_is_locked(&lockdep_lock))
                 return DEBUG_LOCKS_WARN_ON(1);
 
@@ -1064,6 +1159,11 @@ find_usage_backwards(struct lock_class *source, unsigned int depth)
                 return 2;
         }
 
+        if (!source && debug_locks_off_graph_unlock()) {
+                WARN_ON(1);
+                return 0;
+        }
+
         /*
          * Check this lock's dependency list:
          */
@@ -1103,9 +1203,9 @@ print_bad_irq_dependency(struct task_struct *curr,
         printk("\nand this task is already holding:\n");
         print_lock(prev);
         printk("which would create a new lock dependency:\n");
-        print_lock_name(prev->class);
+        print_lock_name(hlock_class(prev));
         printk(" ->");
-        print_lock_name(next->class);
+        print_lock_name(hlock_class(next));
         printk("\n");
 
         printk("\nbut this new dependency connects a %s-irq-safe lock:\n",
@@ -1146,12 +1246,12 @@ check_usage(struct task_struct *curr, struct held_lock *prev,
 
         find_usage_bit = bit_backwards;
         /* fills in <backwards_match> */
-        ret = find_usage_backwards(prev->class, 0);
+        ret = find_usage_backwards(hlock_class(prev), 0);
         if (!ret || ret == 1)
                 return ret;
 
         find_usage_bit = bit_forwards;
-        ret = find_usage_forwards(next->class, 0);
+        ret = find_usage_forwards(hlock_class(next), 0);
         if (!ret || ret == 1)
                 return ret;
         /* ret == 2 */
@@ -1272,18 +1372,32 @@ check_deadlock(struct task_struct *curr, struct held_lock *next,
                struct lockdep_map *next_instance, int read)
 {
         struct held_lock *prev;
+        struct held_lock *nest = NULL;
         int i;
 
         for (i = 0; i < curr->lockdep_depth; i++) {
                 prev = curr->held_locks + i;
-                if (prev->class != next->class)
+
+                if (prev->instance == next->nest_lock)
+                        nest = prev;
+
+                if (hlock_class(prev) != hlock_class(next))
                         continue;
+
                 /*
                  * Allow read-after-read recursion of the same
                  * lock class (i.e. read_lock(lock)+read_lock(lock)):
                  */
                 if ((read == 2) && prev->read)
                         return 2;
+
+                /*
+                 * We're holding the nest_lock, which serializes this lock's
+                 * nesting behaviour.
+                 */
+                if (nest)
+                        return 2;
+
                 return print_deadlock_bug(curr, prev, next);
         }
         return 1;
@@ -1329,7 +1443,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
          */
         check_source = next;
         check_target = prev;
-        if (!(check_noncircular(next->class, 0)))
+        if (!(check_noncircular(hlock_class(next), 0)))
                 return print_circular_bug_tail();
 
         if (!check_prev_add_irq(curr, prev, next))
@@ -1353,8 +1467,8 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
          *  chains - the second one will be new, but L1 already has
          *  L2 added to its dependency list, due to the first chain.)
          */
-        list_for_each_entry(entry, &prev->class->locks_after, entry) {
-                if (entry->class == next->class) {
+        list_for_each_entry(entry, &hlock_class(prev)->locks_after, entry) {
+                if (entry->class == hlock_class(next)) {
                         if (distance == 1)
                                 entry->distance = 1;
                         return 2;
@@ -1365,26 +1479,28 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
          * Ok, all validations passed, add the new lock
          * to the previous lock's dependency list:
          */
-        ret = add_lock_to_list(prev->class, next->class,
-                               &prev->class->locks_after, next->acquire_ip, distance);
+        ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
+                               &hlock_class(prev)->locks_after,
+                               next->acquire_ip, distance);
 
         if (!ret)
                 return 0;
 
-        ret = add_lock_to_list(next->class, prev->class,
-                               &next->class->locks_before, next->acquire_ip, distance);
+        ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
+                               &hlock_class(next)->locks_before,
+                               next->acquire_ip, distance);
         if (!ret)
                 return 0;
 
         /*
          * Debugging printouts:
          */
-        if (verbose(prev->class) || verbose(next->class)) {
+        if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) {
                 graph_unlock();
                 printk("\n new dependency: ");
-                print_lock_name(prev->class);
+                print_lock_name(hlock_class(prev));
                 printk(" => ");
-                print_lock_name(next->class);
+                print_lock_name(hlock_class(next));
                 printk("\n");
                 dump_stack();
                 return graph_lock();
@@ -1481,7 +1597,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
                                      struct held_lock *hlock,
                                      u64 chain_key)
 {
-        struct lock_class *class = hlock->class;
+        struct lock_class *class = hlock_class(hlock);
         struct list_head *hash_head = chainhashentry(chain_key);
         struct lock_chain *chain;
         struct held_lock *hlock_curr, *hlock_next;
@@ -1554,7 +1670,7 @@ cache_hit:
         if (likely(cn + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) {
                 chain->base = cn;
                 for (j = 0; j < chain->depth - 1; j++, i++) {
-                        int lock_id = curr->held_locks[i].class - lock_classes;
+                        int lock_id = curr->held_locks[i].class_idx - 1;
                         chain_hlocks[chain->base + j] = lock_id;
                 }
                 chain_hlocks[chain->base + j] = class - lock_classes;
@@ -1650,7 +1766,7 @@ static void check_chain_key(struct task_struct *curr)
                         WARN_ON(1);
                         return;
                 }
-                id = hlock->class - lock_classes;
+                id = hlock->class_idx - 1;
                 if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS))
                         return;
 
@@ -1695,7 +1811,7 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this,
         print_lock(this);
 
         printk("{%s} state was registered at:\n", usage_str[prev_bit]);
-        print_stack_trace(this->class->usage_traces + prev_bit, 1);
+        print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1);
 
         print_irqtrace_events(curr);
         printk("\nother info that might help us debug this:\n");
@@ -1714,7 +1830,7 @@ static inline int
 valid_state(struct task_struct *curr, struct held_lock *this,
             enum lock_usage_bit new_bit, enum lock_usage_bit bad_bit)
 {
-        if (unlikely(this->class->usage_mask & (1 << bad_bit)))
+        if (unlikely(hlock_class(this)->usage_mask & (1 << bad_bit)))
                 return print_usage_bug(curr, this, bad_bit, new_bit);
         return 1;
 }
@@ -1753,7 +1869,7 @@ print_irq_inversion_bug(struct task_struct *curr, struct lock_class *other,
         lockdep_print_held_locks(curr);
 
         printk("\nthe first lock's dependencies:\n");
-        print_lock_dependencies(this->class, 0);
+        print_lock_dependencies(hlock_class(this), 0);
 
         printk("\nthe second lock's dependencies:\n");
         print_lock_dependencies(other, 0);
@@ -1776,7 +1892,7 @@ check_usage_forwards(struct task_struct *curr, struct held_lock *this,
 
         find_usage_bit = bit;
         /* fills in <forwards_match> */
-        ret = find_usage_forwards(this->class, 0);
+        ret = find_usage_forwards(hlock_class(this), 0);
         if (!ret || ret == 1)
                 return ret;
 
@@ -1795,7 +1911,7 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 
         find_usage_bit = bit;
         /* fills in <backwards_match> */
-        ret = find_usage_backwards(this->class, 0);
+        ret = find_usage_backwards(hlock_class(this), 0);
         if (!ret || ret == 1)
                 return ret;
 
@@ -1861,7 +1977,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                 LOCK_ENABLED_HARDIRQS_READ, "hard-read"))
                         return 0;
 #endif
-                if (hardirq_verbose(this->class))
+                if (hardirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_USED_IN_SOFTIRQ:
@@ -1886,7 +2002,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                 LOCK_ENABLED_SOFTIRQS_READ, "soft-read"))
                         return 0;
 #endif
-                if (softirq_verbose(this->class))
+                if (softirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_USED_IN_HARDIRQ_READ:
@@ -1899,7 +2015,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                 if (!check_usage_forwards(curr, this,
                                           LOCK_ENABLED_HARDIRQS, "hard"))
                         return 0;
-                if (hardirq_verbose(this->class))
+                if (hardirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_USED_IN_SOFTIRQ_READ:
@@ -1912,7 +2028,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                 if (!check_usage_forwards(curr, this,
                                           LOCK_ENABLED_SOFTIRQS, "soft"))
                         return 0;
-                if (softirq_verbose(this->class))
+                if (softirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_ENABLED_HARDIRQS:
@@ -1938,7 +2054,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                    LOCK_USED_IN_HARDIRQ_READ, "hard-read"))
                         return 0;
 #endif
-                if (hardirq_verbose(this->class))
+                if (hardirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_ENABLED_SOFTIRQS:
@@ -1964,7 +2080,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                    LOCK_USED_IN_SOFTIRQ_READ, "soft-read"))
                         return 0;
 #endif
-                if (softirq_verbose(this->class))
+                if (softirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_ENABLED_HARDIRQS_READ:
@@ -1979,7 +2095,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                            LOCK_USED_IN_HARDIRQ, "hard"))
                         return 0;
 #endif
-                if (hardirq_verbose(this->class))
+                if (hardirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         case LOCK_ENABLED_SOFTIRQS_READ:
@@ -1994,7 +2110,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
                                            LOCK_USED_IN_SOFTIRQ, "soft"))
                         return 0;
 #endif
-                if (softirq_verbose(this->class))
+                if (softirq_verbose(hlock_class(this)))
                         ret = 2;
                 break;
         default:
@@ -2310,7 +2426,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
          * If already set then do not dirty the cacheline,
          * nor do any checks:
          */
-        if (likely(this->class->usage_mask & new_mask))
+        if (likely(hlock_class(this)->usage_mask & new_mask))
                 return 1;
 
         if (!graph_lock())
@@ -2318,14 +2434,14 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
         /*
          * Make sure we didnt race:
          */
-        if (unlikely(this->class->usage_mask & new_mask)) {
+        if (unlikely(hlock_class(this)->usage_mask & new_mask)) {
                 graph_unlock();
                 return 1;
         }
 
-        this->class->usage_mask |= new_mask;
+        hlock_class(this)->usage_mask |= new_mask;
 
-        if (!save_trace(this->class->usage_traces + new_bit))
+        if (!save_trace(hlock_class(this)->usage_traces + new_bit))
                 return 0;
 
         switch (new_bit) {
@@ -2405,7 +2521,7 @@ EXPORT_SYMBOL_GPL(lockdep_init_map);
  */
 static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
                           int trylock, int read, int check, int hardirqs_off,
-                          unsigned long ip)
+                          struct lockdep_map *nest_lock, unsigned long ip)
 {
         struct task_struct *curr = current;
         struct lock_class *class = NULL;
@@ -2459,10 +2575,12 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
                 return 0;
 
         hlock = curr->held_locks + depth;
-
-        hlock->class = class;
+        if (DEBUG_LOCKS_WARN_ON(!class))
+                return 0;
+        hlock->class_idx = class - lock_classes + 1;
         hlock->acquire_ip = ip;
         hlock->instance = lock;
+        hlock->nest_lock = nest_lock;
         hlock->trylock = trylock;
         hlock->read = read;
         hlock->check = check;
@@ -2574,6 +2692,55 @@ static int check_unlock(struct task_struct *curr, struct lockdep_map *lock,
         return 1;
 }
 
+static int
+__lock_set_subclass(struct lockdep_map *lock,
+                    unsigned int subclass, unsigned long ip)
+{
+        struct task_struct *curr = current;
+        struct held_lock *hlock, *prev_hlock;
+        struct lock_class *class;
+        unsigned int depth;
+        int i;
+
+        depth = curr->lockdep_depth;
+        if (DEBUG_LOCKS_WARN_ON(!depth))
+                return 0;
+
+        prev_hlock = NULL;
+        for (i = depth-1; i >= 0; i--) {
+                hlock = curr->held_locks + i;
+                /*
+                 * We must not cross into another context:
+                 */
+                if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
+                        break;
+                if (hlock->instance == lock)
+                        goto found_it;
+                prev_hlock = hlock;
+        }
+        return print_unlock_inbalance_bug(curr, lock, ip);
+
+found_it:
+        class = register_lock_class(lock, subclass, 0);
+        hlock->class_idx = class - lock_classes + 1;
+
+        curr->lockdep_depth = i;
+        curr->curr_chain_key = hlock->prev_chain_key;
+
+        for (; i < depth; i++) {
+                hlock = curr->held_locks + i;
+                if (!__lock_acquire(hlock->instance,
+                        hlock_class(hlock)->subclass, hlock->trylock,
+                                hlock->read, hlock->check, hlock->hardirqs_off,
+                                hlock->nest_lock, hlock->acquire_ip))
+                        return 0;
+        }
+
+        if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth))
+                return 0;
+        return 1;
+}
+
 /*
  * Remove the lock to the list of currently held locks in a
  * potentially non-nested (out of order) manner. This is a
@@ -2624,9 +2791,9 @@ found_it:
         for (i++; i < depth; i++) {
                 hlock = curr->held_locks + i;
                 if (!__lock_acquire(hlock->instance,
-                        hlock->class->subclass, hlock->trylock,
+                        hlock_class(hlock)->subclass, hlock->trylock,
                                 hlock->read, hlock->check, hlock->hardirqs_off,
-                                hlock->acquire_ip))
+                                hlock->nest_lock, hlock->acquire_ip))
                         return 0;
         }
 
@@ -2669,7 +2836,7 @@ static int lock_release_nested(struct task_struct *curr,
 
 #ifdef CONFIG_DEBUG_LOCKDEP
         hlock->prev_chain_key = 0;
-        hlock->class = NULL;
+        hlock->class_idx = 0;
         hlock->acquire_ip = 0;
         hlock->irq_context = 0;
 #endif
@@ -2738,18 +2905,36 @@ static void check_flags(unsigned long flags)
 #endif
 }
 
+void
+lock_set_subclass(struct lockdep_map *lock,
+                  unsigned int subclass, unsigned long ip)
+{
+        unsigned long flags;
+
+        if (unlikely(current->lockdep_recursion))
+                return;
+
+        raw_local_irq_save(flags);
+        current->lockdep_recursion = 1;
+        check_flags(flags);
+        if (__lock_set_subclass(lock, subclass, ip))
+                check_chain_key(current);
+        current->lockdep_recursion = 0;
+        raw_local_irq_restore(flags);
+}
+
+EXPORT_SYMBOL_GPL(lock_set_subclass);
+
 /*
  * We are not always called with irqs disabled - do that here,
  * and also avoid lockdep recursion:
  */
 void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
-                          int trylock, int read, int check, unsigned long ip)
+                          int trylock, int read, int check,
+                          struct lockdep_map *nest_lock, unsigned long ip)
 {
         unsigned long flags;
 
-        if (unlikely(!lock_stat && !prove_locking))
-                return;
-
         if (unlikely(current->lockdep_recursion))
                 return;
 
@@ -2758,7 +2943,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 
         current->lockdep_recursion = 1;
         __lock_acquire(lock, subclass, trylock, read, check,
-                       irqs_disabled_flags(flags), ip);
+                       irqs_disabled_flags(flags), nest_lock, ip);
         current->lockdep_recursion = 0;
         raw_local_irq_restore(flags);
 }
@@ -2770,9 +2955,6 @@ void lock_release(struct lockdep_map *lock, int nested,
 {
         unsigned long flags;
 
-        if (unlikely(!lock_stat && !prove_locking))
-                return;
-
         if (unlikely(current->lockdep_recursion))
                 return;
 
@@ -2845,9 +3027,9 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 found_it:
         hlock->waittime_stamp = sched_clock();
 
-        point = lock_contention_point(hlock->class, ip);
+        point = lock_contention_point(hlock_class(hlock), ip);
 
-        stats = get_lock_stats(hlock->class);
+        stats = get_lock_stats(hlock_class(hlock));
         if (point < ARRAY_SIZE(stats->contention_point))
                 stats->contention_point[i]++;
         if (lock->cpu != smp_processor_id())
@@ -2893,7 +3075,7 @@ found_it:
                 hlock->holdtime_stamp = now;
         }
 
-        stats = get_lock_stats(hlock->class);
+        stats = get_lock_stats(hlock_class(hlock));
         if (waittime) {
                 if (hlock->read)
                         lock_time_inc(&stats->read_waittime, waittime);
@@ -2988,6 +3170,7 @@ static void zap_class(struct lock_class *class)
         list_del_rcu(&class->hash_entry);
         list_del_rcu(&class->lock_entry);
 
+        class->key = NULL;
 }
 
 static inline int within(const void *addr, void *start, unsigned long size)
diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h
index c3600a091a28..55db193d366d 100644
--- a/kernel/lockdep_internals.h
+++ b/kernel/lockdep_internals.h
@@ -17,9 +17,6 @@
  */
 #define MAX_LOCKDEP_ENTRIES     8192UL
 
-#define MAX_LOCKDEP_KEYS_BITS   11
-#define MAX_LOCKDEP_KEYS        (1UL << MAX_LOCKDEP_KEYS_BITS)
-
 #define MAX_LOCKDEP_CHAINS_BITS 14
 #define MAX_LOCKDEP_CHAINS      (1UL << MAX_LOCKDEP_CHAINS_BITS)
 
@@ -53,6 +50,9 @@ extern unsigned int nr_process_chains;
 extern unsigned int max_lockdep_depth;
 extern unsigned int max_recursion_depth;
 
+extern unsigned long lockdep_count_forward_deps(struct lock_class *);
+extern unsigned long lockdep_count_backward_deps(struct lock_class *);
+
 #ifdef CONFIG_DEBUG_LOCKDEP
 /*
  * Various lockdep statistics:
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index 9b0e940e2545..fa19aee604c2 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -63,34 +63,6 @@ static void l_stop(struct seq_file *m, void *v)
 {
 }
 
-static unsigned long count_forward_deps(struct lock_class *class)
-{
-        struct lock_list *entry;
-        unsigned long ret = 1;
-
-        /*
-         * Recurse this class's dependency list:
-         */
-        list_for_each_entry(entry, &class->locks_after, entry)
-                ret += count_forward_deps(entry->class);
-
-        return ret;
-}
-
-static unsigned long count_backward_deps(struct lock_class *class)
-{
-        struct lock_list *entry;
-        unsigned long ret = 1;
-
-        /*
-         * Recurse this class's dependency list:
-         */
-        list_for_each_entry(entry, &class->locks_before, entry)
-                ret += count_backward_deps(entry->class);
-
-        return ret;
-}
-
 static void print_name(struct seq_file *m, struct lock_class *class)
 {
         char str[128];
@@ -124,10 +96,10 @@ static int l_show(struct seq_file *m, void *v)
 #ifdef CONFIG_DEBUG_LOCKDEP
         seq_printf(m, " OPS:%8ld", class->ops);
 #endif
-        nr_forward_deps = count_forward_deps(class);
+        nr_forward_deps = lockdep_count_forward_deps(class);
         seq_printf(m, " FD:%5ld", nr_forward_deps);
 
-        nr_backward_deps = count_backward_deps(class);
+        nr_backward_deps = lockdep_count_backward_deps(class);
         seq_printf(m, " BD:%5ld", nr_backward_deps);
 
         get_usage_chars(class, &c1, &c2, &c3, &c4);
@@ -229,6 +201,9 @@ static int lc_show(struct seq_file *m, void *v)
 
         for (i = 0; i < chain->depth; i++) {
                 class = lock_chain_get_class(chain, i);
+                if (!class->key)
+                        continue;
+
                 seq_printf(m, "[%p] ", class->key);
                 print_name(m, class);
                 seq_puts(m, "\n");
@@ -350,7 +325,7 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
                 if (class->usage_mask & LOCKF_ENABLED_HARDIRQS_READ)
                         nr_hardirq_read_unsafe++;
 
-                sum_forward_deps += count_forward_deps(class);
+                sum_forward_deps += lockdep_count_forward_deps(class);
         }
 #ifdef CONFIG_DEBUG_LOCKDEP
         DEBUG_LOCKS_WARN_ON(debug_atomic_read(&nr_unused_locks) != nr_unused);
diff --git a/kernel/sched.c b/kernel/sched.c
index 04160d277e7a..ace566bdfc68 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -600,7 +600,6 @@ struct rq {
         /* BKL stats */
         unsigned int bkl_count;
 #endif
-        struct lock_class_key rq_lock_key;
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
@@ -2759,10 +2758,10 @@ static void double_rq_lock(struct rq *rq1, struct rq *rq2)
         } else {
                 if (rq1 < rq2) {
                         spin_lock(&rq1->lock);
-                        spin_lock(&rq2->lock);
+                        spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
                 } else {
                         spin_lock(&rq2->lock);
-                        spin_lock(&rq1->lock);
+                        spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
                 }
         }
         update_rq_clock(rq1);
@@ -2805,14 +2804,21 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
                 if (busiest < this_rq) {
                         spin_unlock(&this_rq->lock);
                         spin_lock(&busiest->lock);
-                        spin_lock(&this_rq->lock);
+                        spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
                         ret = 1;
                 } else
-                        spin_lock(&busiest->lock);
+                        spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
         }
         return ret;
 }
 
+static void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
+        __releases(busiest->lock)
+{
+        spin_unlock(&busiest->lock);
+        lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
+}
+
 /*
  * If dest_cpu is allowed for this process, migrate the task to it.
  * This is accomplished by forcing the cpu_allowed mask to only
@@ -3637,7 +3643,7 @@ redo:
                 ld_moved = move_tasks(this_rq, this_cpu, busiest,
                                         imbalance, sd, CPU_NEWLY_IDLE,
                                         &all_pinned);
-                spin_unlock(&busiest->lock);
+                double_unlock_balance(this_rq, busiest);
 
                 if (unlikely(all_pinned)) {
                         cpu_clear(cpu_of(busiest), *cpus);
@@ -3752,7 +3758,7 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
                 else
                         schedstat_inc(sd, alb_failed);
         }
-        spin_unlock(&target_rq->lock);
+        double_unlock_balance(busiest_rq, target_rq);
 }
 
 #ifdef CONFIG_NO_HZ
@@ -8000,7 +8006,6 @@ void __init sched_init(void)
 
                 rq = cpu_rq(i);
                 spin_lock_init(&rq->lock);
-                lockdep_set_class(&rq->lock, &rq->rq_lock_key);
                 rq->nr_running = 0;
                 init_cfs_rq(&rq->cfs, rq);
                 init_rt_rq(&rq->rt, rq);
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 908c04f9dad0..6163e4cf885b 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -861,6 +861,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 #define RT_MAX_TRIES 3
 
 static int double_lock_balance(struct rq *this_rq, struct rq *busiest);
+static void double_unlock_balance(struct rq *this_rq, struct rq *busiest);
+
 static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep);
 
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
@@ -1022,7 +1024,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
                         break;
 
                 /* try again */
-                spin_unlock(&lowest_rq->lock);
+                double_unlock_balance(rq, lowest_rq);
                 lowest_rq = NULL;
         }
 
@@ -1091,7 +1093,7 @@ static int push_rt_task(struct rq *rq)
 
         resched_task(lowest_rq->curr);
 
-        spin_unlock(&lowest_rq->lock);
+        double_unlock_balance(rq, lowest_rq);
 
         ret = 1;
 out:
@@ -1197,7 +1199,7 @@ static int pull_rt_task(struct rq *this_rq)
 
                 }
  skip:
-                spin_unlock(&src_rq->lock);
+                double_unlock_balance(this_rq, src_rq);
         }
 
         return ret;
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index a1fb54c93cdd..44baeea94ab9 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -292,6 +292,7 @@ void __lockfunc _spin_lock_nested(spinlock_t *lock, int subclass)
 }
 
 EXPORT_SYMBOL(_spin_lock_nested);
+
 unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclass)
 {
         unsigned long flags;
@@ -314,6 +315,16 @@ unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclas
 
 EXPORT_SYMBOL(_spin_lock_irqsave_nested);
 
+void __lockfunc _spin_lock_nest_lock(spinlock_t *lock,
+                                     struct lockdep_map *nest_lock)
+{
+        preempt_disable();
+        spin_acquire_nest(&lock->dep_map, 0, 0, nest_lock, _RET_IP_);
+        LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+}
+
+EXPORT_SYMBOL(_spin_lock_nest_lock);
+
 #endif
 
 void __lockfunc _spin_unlock(spinlock_t *lock)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 4a26a1382df0..4048e92aa04f 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -290,11 +290,11 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq)
 
                 BUG_ON(get_wq_data(work) != cwq);
                 work_clear_pending(work);
-                lock_acquire(&cwq->wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
-                lock_acquire(&lockdep_map, 0, 0, 0, 2, _THIS_IP_);
+                lock_map_acquire(&cwq->wq->lockdep_map);
+                lock_map_acquire(&lockdep_map);
                 f(work);
-                lock_release(&lockdep_map, 1, _THIS_IP_);
-                lock_release(&cwq->wq->lockdep_map, 1, _THIS_IP_);
+                lock_map_release(&lockdep_map);
+                lock_map_release(&cwq->wq->lockdep_map);
 
                 if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
                         printk(KERN_ERR "BUG: workqueue leaked lock or atomic: "
@@ -413,8 +413,8 @@ void flush_workqueue(struct workqueue_struct *wq)
         int cpu;
 
         might_sleep();
-        lock_acquire(&wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
-        lock_release(&wq->lockdep_map, 1, _THIS_IP_);
+        lock_map_acquire(&wq->lockdep_map);
+        lock_map_release(&wq->lockdep_map);
         for_each_cpu_mask_nr(cpu, *cpu_map)
                 flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu));
 }
@@ -441,8 +441,8 @@ int flush_work(struct work_struct *work)
         if (!cwq)
                 return 0;
 
-        lock_acquire(&cwq->wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
-        lock_release(&cwq->wq->lockdep_map, 1, _THIS_IP_);
+        lock_map_acquire(&cwq->wq->lockdep_map);
+        lock_map_release(&cwq->wq->lockdep_map);
 
         prev = NULL;
         spin_lock_irq(&cwq->lock);
@@ -536,8 +536,8 @@ static void wait_on_work(struct work_struct *work)
 
         might_sleep();
 
-        lock_acquire(&work->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
-        lock_release(&work->lockdep_map, 1, _THIS_IP_);
+        lock_map_acquire(&work->lockdep_map);
+        lock_map_release(&work->lockdep_map);
 
         cwq = get_wq_data(work);
         if (!cwq)
@@ -872,8 +872,8 @@ static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
         if (cwq->thread == NULL)
                 return;
 
-        lock_acquire(&cwq->wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
-        lock_release(&cwq->wq->lockdep_map, 1, _THIS_IP_);
+        lock_map_acquire(&cwq->wq->lockdep_map);
+        lock_map_release(&cwq->wq->lockdep_map);
 
         flush_cpu_workqueue(cwq);
         /*
diff --git a/lib/debug_locks.c b/lib/debug_locks.c
index 0ef01d14727c..0218b4693dd8 100644
--- a/lib/debug_locks.c
+++ b/lib/debug_locks.c
@@ -8,6 +8,7 @@
  *
  *  Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  */
+#include <linux/kernel.h>
 #include <linux/rwsem.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
@@ -37,6 +38,7 @@ int debug_locks_off(void)
 {
         if (xchg(&debug_locks, 0)) {
                 if (!debug_locks_silent) {
+                        oops_in_progress = 1;
                         console_verbose();
                         return 1;
                 }
diff --git a/mm/mmap.c b/mm/mmap.c
index 971d0eda754a..339cf5c4d5d8 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2273,14 +2273,14 @@ int install_special_mapping(struct mm_struct *mm,
 
 static DEFINE_MUTEX(mm_all_locks_mutex);
 
-static void vm_lock_anon_vma(struct anon_vma *anon_vma)
+static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma)
 {
         if (!test_bit(0, (unsigned long *) &anon_vma->head.next)) {
                 /*
                  * The LSB of head.next can't change from under us
                  * because we hold the mm_all_locks_mutex.
                  */
-                spin_lock(&anon_vma->lock);
+                spin_lock_nest_lock(&anon_vma->lock, &mm->mmap_sem);
                 /*
                  * We can safely modify head.next after taking the
                  * anon_vma->lock. If some other vma in this mm shares
@@ -2296,7 +2296,7 @@ static void vm_lock_anon_vma(struct anon_vma *anon_vma)
         }
 }
 
-static void vm_lock_mapping(struct address_space *mapping)
+static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
 {
         if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) {
                 /*
@@ -2310,7 +2310,7 @@ static void vm_lock_mapping(struct address_space *mapping)
                  */
                 if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags))
                         BUG();
-                spin_lock(&mapping->i_mmap_lock);
+                spin_lock_nest_lock(&mapping->i_mmap_lock, &mm->mmap_sem);
         }
 }
 
@@ -2358,11 +2358,17 @@ int mm_take_all_locks(struct mm_struct *mm)
         for (vma = mm->mmap; vma; vma = vma->vm_next) {
                 if (signal_pending(current))
                         goto out_unlock;
-                if (vma->anon_vma)
-                        vm_lock_anon_vma(vma->anon_vma);
                 if (vma->vm_file && vma->vm_file->f_mapping)
-                        vm_lock_mapping(vma->vm_file->f_mapping);
+                        vm_lock_mapping(mm, vma->vm_file->f_mapping);
+        }
+
+        for (vma = mm->mmap; vma; vma = vma->vm_next) {
+                if (signal_pending(current))
+                        goto out_unlock;
+                if (vma->anon_vma)
+                        vm_lock_anon_vma(mm, vma->anon_vma);
         }
+
         ret = 0;
 
 out_unlock: