Merge branch 'core/locking' into core/urgent

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;

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;

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 */

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)

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)

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);

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:

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);

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);

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;

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)

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);
 	/*

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;
 		}

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: