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
  ...

28 files changed, 1107 insertions, 32 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index a4d1aa8da9b..09a9c94f42b 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -7,22 +7,19 @@ obj-y     = fork.o exec_domain.o panic.o \
 	    sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \
 	    signal.o sys.o kmod.o workqueue.o pid.o task_work.o \
 	    extable.o params.o posix-timers.o \
-	    kthread.o sys_ni.o posix-cpu-timers.o mutex.o \
-	    hrtimer.o rwsem.o nsproxy.o semaphore.o \
+	    kthread.o sys_ni.o posix-cpu-timers.o \
+	    hrtimer.o nsproxy.o \
 	    notifier.o ksysfs.o cred.o reboot.o \
-	    async.o range.o groups.o lglock.o smpboot.o
+	    async.o range.o groups.o smpboot.o
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files
-CFLAGS_REMOVE_lockdep.o = -pg
-CFLAGS_REMOVE_lockdep_proc.o = -pg
-CFLAGS_REMOVE_mutex-debug.o = -pg
-CFLAGS_REMOVE_rtmutex-debug.o = -pg
 CFLAGS_REMOVE_cgroup-debug.o = -pg
 CFLAGS_REMOVE_irq_work.o = -pg
 endif
 
 obj-y += sched/
+obj-y += locking/
 obj-y += power/
 obj-y += printk/
 obj-y += cpu/
@@ -34,26 +31,15 @@ obj-$(CONFIG_FREEZER) += freezer.o
 obj-$(CONFIG_PROFILING) += profile.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
 obj-y += time/
-obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
-obj-$(CONFIG_LOCKDEP) += lockdep.o
-ifeq ($(CONFIG_PROC_FS),y)
-obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
-endif
 obj-$(CONFIG_FUTEX) += futex.o
 ifeq ($(CONFIG_COMPAT),y)
 obj-$(CONFIG_FUTEX) += futex_compat.o
 endif
-obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
-obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
-obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
 obj-$(CONFIG_SMP) += smp.o
 ifneq ($(CONFIG_SMP),y)
 obj-y += up.o
 endif
-obj-$(CONFIG_SMP) += spinlock.o
-obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
-obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
 obj-$(CONFIG_UID16) += uid16.o
 obj-$(CONFIG_MODULES) += module.o
 obj-$(CONFIG_MODULE_SIG) += module_signing.o modsign_pubkey.o modsign_certificate.o
diff --git a/kernel/futex.c b/kernel/futex.c
index c3a1a55a521..80ba086f021 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -66,7 +66,7 @@
 
 #include <asm/futex.h>
 
-#include "rtmutex_common.h"
+#include "locking/rtmutex_common.h"
 
 int __read_mostly futex_cmpxchg_enabled;
 
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 3e97fb126e6..8807061ca00 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -16,11 +16,12 @@
 #include <linux/export.h>
 #include <linux/sysctl.h>
 #include <linux/utsname.h>
+#include <trace/events/sched.h>
 
 /*
  * The number of tasks checked:
  */
-unsigned long __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
+int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
 
 /*
  * Limit number of tasks checked in a batch.
@@ -92,6 +93,9 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 		t->last_switch_count = switch_count;
 		return;
 	}
+
+	trace_sched_process_hang(t);
+
 	if (!sysctl_hung_task_warnings)
 		return;
 	sysctl_hung_task_warnings--;
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
new file mode 100644
index 00000000000..baab8e5e7f6
--- /dev/null
+++ b/kernel/locking/Makefile
@@ -0,0 +1,25 @@
+
+obj-y += mutex.o semaphore.o rwsem.o lglock.o
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_lockdep.o = -pg
+CFLAGS_REMOVE_lockdep_proc.o = -pg
+CFLAGS_REMOVE_mutex-debug.o = -pg
+CFLAGS_REMOVE_rtmutex-debug.o = -pg
+endif
+
+obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
+obj-$(CONFIG_LOCKDEP) += lockdep.o
+ifeq ($(CONFIG_PROC_FS),y)
+obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
+endif
+obj-$(CONFIG_SMP) += spinlock.o
+obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
+obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
+obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
+obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
+obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
+obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
+obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
+obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
+obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o
diff --git a/kernel/lglock.c b/kernel/locking/lglock.c
index 86ae2aebf00..86ae2aebf00 100644
--- a/kernel/lglock.c
+++ b/kernel/locking/lglock.c
diff --git a/kernel/lockdep.c b/kernel/locking/lockdep.c
index 4e8e14c34e4..576ba756a32 100644
--- a/kernel/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1232,7 +1232,7 @@ static int noop_count(struct lock_list *entry, void *data)
 	return 0;
 }
 
-unsigned long __lockdep_count_forward_deps(struct lock_list *this)
+static unsigned long __lockdep_count_forward_deps(struct lock_list *this)
 {
 	unsigned long  count = 0;
 	struct lock_list *uninitialized_var(target_entry);
@@ -1258,7 +1258,7 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class)
 	return ret;
 }
 
-unsigned long __lockdep_count_backward_deps(struct lock_list *this)
+static unsigned long __lockdep_count_backward_deps(struct lock_list *this)
 {
 	unsigned long  count = 0;
 	struct lock_list *uninitialized_var(target_entry);
diff --git a/kernel/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index 4f560cfedc8..4f560cfedc8 100644
--- a/kernel/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
diff --git a/kernel/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index b2c71c5873e..ef43ac4bafb 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -421,6 +421,7 @@ static void seq_lock_time(struct seq_file *m, struct lock_time *lt)
 	seq_time(m, lt->min);
 	seq_time(m, lt->max);
 	seq_time(m, lt->total);
+	seq_time(m, lt->nr ? div_s64(lt->total, lt->nr) : 0);
 }
 
 static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
@@ -518,20 +519,20 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
 	}
 	if (i) {
 		seq_puts(m, "\n");
-		seq_line(m, '.', 0, 40 + 1 + 10 * (14 + 1));
+		seq_line(m, '.', 0, 40 + 1 + 12 * (14 + 1));
 		seq_puts(m, "\n");
 	}
 }
 
 static void seq_header(struct seq_file *m)
 {
-	seq_printf(m, "lock_stat version 0.3\n");
+	seq_puts(m, "lock_stat version 0.4\n");
 
 	if (unlikely(!debug_locks))
 		seq_printf(m, "*WARNING* lock debugging disabled!! - possibly due to a lockdep warning\n");
 
-	seq_line(m, '-', 0, 40 + 1 + 10 * (14 + 1));
-	seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s "
+	seq_line(m, '-', 0, 40 + 1 + 12 * (14 + 1));
+	seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s %14s %14s "
 			"%14s %14s\n",
 			"class name",
 			"con-bounces",
@@ -539,12 +540,14 @@ static void seq_header(struct seq_file *m)
 			"waittime-min",
 			"waittime-max",
 			"waittime-total",
+			"waittime-avg",
 			"acq-bounces",
 			"acquisitions",
 			"holdtime-min",
 			"holdtime-max",
-			"holdtime-total");
-	seq_line(m, '-', 0, 40 + 1 + 10 * (14 + 1));
+			"holdtime-total",
+			"holdtime-avg");
+	seq_line(m, '-', 0, 40 + 1 + 12 * (14 + 1));
 	seq_printf(m, "\n");
 }
 
diff --git a/kernel/lockdep_states.h b/kernel/locking/lockdep_states.h
index 995b0cc2b84..995b0cc2b84 100644
--- a/kernel/lockdep_states.h
+++ b/kernel/locking/lockdep_states.h
diff --git a/kernel/mutex-debug.c b/kernel/locking/mutex-debug.c
index 7e3443fe1f4..7e3443fe1f4 100644
--- a/kernel/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
diff --git a/kernel/mutex-debug.h b/kernel/locking/mutex-debug.h
index 0799fd3e4cf..0799fd3e4cf 100644
--- a/kernel/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
diff --git a/kernel/mutex.c b/kernel/locking/mutex.c
index d24105b1b79..4dd6e4c219d 100644
--- a/kernel/mutex.c
+++ b/kernel/locking/mutex.c
@@ -1,5 +1,5 @@
 /*
- * kernel/mutex.c
+ * kernel/locking/mutex.c
  *
  * Mutexes: blocking mutual exclusion locks
  *
diff --git a/kernel/mutex.h b/kernel/locking/mutex.h
index 4115fbf83b1..4115fbf83b1 100644
--- a/kernel/mutex.h
+++ b/kernel/locking/mutex.h
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
new file mode 100644
index 00000000000..652a8ee8efe
--- /dev/null
+++ b/kernel/locking/percpu-rwsem.c
@@ -0,0 +1,165 @@
+#include <linux/atomic.h>
+#include <linux/rwsem.h>
+#include <linux/percpu.h>
+#include <linux/wait.h>
+#include <linux/lockdep.h>
+#include <linux/percpu-rwsem.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/errno.h>
+
+int __percpu_init_rwsem(struct percpu_rw_semaphore *brw,
+			const char *name, struct lock_class_key *rwsem_key)
+{
+	brw->fast_read_ctr = alloc_percpu(int);
+	if (unlikely(!brw->fast_read_ctr))
+		return -ENOMEM;
+
+	/* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */
+	__init_rwsem(&brw->rw_sem, name, rwsem_key);
+	atomic_set(&brw->write_ctr, 0);
+	atomic_set(&brw->slow_read_ctr, 0);
+	init_waitqueue_head(&brw->write_waitq);
+	return 0;
+}
+
+void percpu_free_rwsem(struct percpu_rw_semaphore *brw)
+{
+	free_percpu(brw->fast_read_ctr);
+	brw->fast_read_ctr = NULL; /* catch use after free bugs */
+}
+
+/*
+ * This is the fast-path for down_read/up_read, it only needs to ensure
+ * there is no pending writer (atomic_read(write_ctr) == 0) and inc/dec the
+ * fast per-cpu counter. The writer uses synchronize_sched_expedited() to
+ * serialize with the preempt-disabled section below.
+ *
+ * The nontrivial part is that we should guarantee acquire/release semantics
+ * in case when
+ *
+ *	R_W: down_write() comes after up_read(), the writer should see all
+ *	     changes done by the reader
+ * or
+ *	W_R: down_read() comes after up_write(), the reader should see all
+ *	     changes done by the writer
+ *
+ * If this helper fails the callers rely on the normal rw_semaphore and
+ * atomic_dec_and_test(), so in this case we have the necessary barriers.
+ *
+ * But if it succeeds we do not have any barriers, atomic_read(write_ctr) or
+ * __this_cpu_add() below can be reordered with any LOAD/STORE done by the
+ * reader inside the critical section. See the comments in down_write and
+ * up_write below.
+ */
+static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val)
+{
+	bool success = false;
+
+	preempt_disable();
+	if (likely(!atomic_read(&brw->write_ctr))) {
+		__this_cpu_add(*brw->fast_read_ctr, val);
+		success = true;
+	}
+	preempt_enable();
+
+	return success;
+}
+
+/*
+ * Like the normal down_read() this is not recursive, the writer can
+ * come after the first percpu_down_read() and create the deadlock.
+ *
+ * Note: returns with lock_is_held(brw->rw_sem) == T for lockdep,
+ * percpu_up_read() does rwsem_release(). This pairs with the usage
+ * of ->rw_sem in percpu_down/up_write().
+ */
+void percpu_down_read(struct percpu_rw_semaphore *brw)
+{
+	might_sleep();
+	if (likely(update_fast_ctr(brw, +1))) {
+		rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 0, _RET_IP_);
+		return;
+	}
+
+	down_read(&brw->rw_sem);
+	atomic_inc(&brw->slow_read_ctr);
+	/* avoid up_read()->rwsem_release() */
+	__up_read(&brw->rw_sem);
+}
+
+void percpu_up_read(struct percpu_rw_semaphore *brw)
+{
+	rwsem_release(&brw->rw_sem.dep_map, 1, _RET_IP_);
+
+	if (likely(update_fast_ctr(brw, -1)))
+		return;
+
+	/* false-positive is possible but harmless */
+	if (atomic_dec_and_test(&brw->slow_read_ctr))
+		wake_up_all(&brw->write_waitq);
+}
+
+static int clear_fast_ctr(struct percpu_rw_semaphore *brw)
+{
+	unsigned int sum = 0;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		sum += per_cpu(*brw->fast_read_ctr, cpu);
+		per_cpu(*brw->fast_read_ctr, cpu) = 0;
+	}
+
+	return sum;
+}
+
+/*
+ * A writer increments ->write_ctr to force the readers to switch to the
+ * slow mode, note the atomic_read() check in update_fast_ctr().
+ *
+ * After that the readers can only inc/dec the slow ->slow_read_ctr counter,
+ * ->fast_read_ctr is stable. Once the writer moves its sum into the slow
+ * counter it represents the number of active readers.
+ *
+ * Finally the writer takes ->rw_sem for writing and blocks the new readers,
+ * then waits until the slow counter becomes zero.
+ */
+void percpu_down_write(struct percpu_rw_semaphore *brw)
+{
+	/* tell update_fast_ctr() there is a pending writer */
+	atomic_inc(&brw->write_ctr);
+	/*
+	 * 1. Ensures that write_ctr != 0 is visible to any down_read/up_read
+	 *    so that update_fast_ctr() can't succeed.
+	 *
+	 * 2. Ensures we see the result of every previous this_cpu_add() in
+	 *    update_fast_ctr().
+	 *
+	 * 3. Ensures that if any reader has exited its critical section via
+	 *    fast-path, it executes a full memory barrier before we return.
+	 *    See R_W case in the comment above update_fast_ctr().
+	 */
+	synchronize_sched_expedited();
+
+	/* exclude other writers, and block the new readers completely */
+	down_write(&brw->rw_sem);
+
+	/* nobody can use fast_read_ctr, move its sum into slow_read_ctr */
+	atomic_add(clear_fast_ctr(brw), &brw->slow_read_ctr);
+
+	/* wait for all readers to complete their percpu_up_read() */
+	wait_event(brw->write_waitq, !atomic_read(&brw->slow_read_ctr));
+}
+
+void percpu_up_write(struct percpu_rw_semaphore *brw)
+{
+	/* release the lock, but the readers can't use the fast-path */
+	up_write(&brw->rw_sem);
+	/*
+	 * Insert the barrier before the next fast-path in down_read,
+	 * see W_R case in the comment above update_fast_ctr().
+	 */
+	synchronize_sched_expedited();
+	/* the last writer unblocks update_fast_ctr() */
+	atomic_dec(&brw->write_ctr);
+}
diff --git a/kernel/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index 13b243a323f..13b243a323f 100644
--- a/kernel/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
diff --git a/kernel/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h
index 14193d596d7..14193d596d7 100644
--- a/kernel/rtmutex-debug.h
+++ b/kernel/locking/rtmutex-debug.h
diff --git a/kernel/rtmutex-tester.c b/kernel/locking/rtmutex-tester.c
index 1d96dd0d93c..1d96dd0d93c 100644
--- a/kernel/rtmutex-tester.c
+++ b/kernel/locking/rtmutex-tester.c
diff --git a/kernel/rtmutex.c b/kernel/locking/rtmutex.c
index 0dd6aec1cb6..0dd6aec1cb6 100644
--- a/kernel/rtmutex.c
+++ b/kernel/locking/rtmutex.c
diff --git a/kernel/rtmutex.h b/kernel/locking/rtmutex.h
index a1a1dd06421..a1a1dd06421 100644
--- a/kernel/rtmutex.h
+++ b/kernel/locking/rtmutex.h
diff --git a/kernel/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 53a66c85261..53a66c85261 100644
--- a/kernel/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
new file mode 100644
index 00000000000..9be8a914497
--- /dev/null
+++ b/kernel/locking/rwsem-spinlock.c
@@ -0,0 +1,296 @@
+/* rwsem-spinlock.c: R/W semaphores: contention handling functions for
+ * generic spinlock implementation
+ *
+ * Copyright (c) 2001   David Howells (dhowells@redhat.com).
+ * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
+ * - Derived also from comments by Linus
+ */
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/export.h>
+
+enum rwsem_waiter_type {
+	RWSEM_WAITING_FOR_WRITE,
+	RWSEM_WAITING_FOR_READ
+};
+
+struct rwsem_waiter {
+	struct list_head list;
+	struct task_struct *task;
+	enum rwsem_waiter_type type;
+};
+
+int rwsem_is_locked(struct rw_semaphore *sem)
+{
+	int ret = 1;
+	unsigned long flags;
+
+	if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
+		ret = (sem->activity != 0);
+		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(rwsem_is_locked);
+
+/*
+ * initialise the semaphore
+ */
+void __init_rwsem(struct rw_semaphore *sem, const char *name,
+		  struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held semaphore:
+	 */
+	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+	lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
+	sem->activity = 0;
+	raw_spin_lock_init(&sem->wait_lock);
+	INIT_LIST_HEAD(&sem->wait_list);
+}
+EXPORT_SYMBOL(__init_rwsem);
+
+/*
+ * handle the lock release when processes blocked on it that can now run
+ * - if we come here, then:
+ *   - the 'active count' _reached_ zero
+ *   - the 'waiting count' is non-zero
+ * - the spinlock must be held by the caller
+ * - woken process blocks are discarded from the list after having task zeroed
+ * - writers are only woken if wakewrite is non-zero
+ */
+static inline struct rw_semaphore *
+__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
+{
+	struct rwsem_waiter *waiter;
+	struct task_struct *tsk;
+	int woken;
+
+	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+
+	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
+		if (wakewrite)
+			/* Wake up a writer. Note that we do not grant it the
+			 * lock - it will have to acquire it when it runs. */
+			wake_up_process(waiter->task);
+		goto out;
+	}
+
+	/* grant an infinite number of read locks to the front of the queue */
+	woken = 0;
+	do {
+		struct list_head *next = waiter->list.next;
+
+		list_del(&waiter->list);
+		tsk = waiter->task;
+		smp_mb();
+		waiter->task = NULL;
+		wake_up_process(tsk);
+		put_task_struct(tsk);
+		woken++;
+		if (next == &sem->wait_list)
+			break;
+		waiter = list_entry(next, struct rwsem_waiter, list);
+	} while (waiter->type != RWSEM_WAITING_FOR_WRITE);
+
+	sem->activity += woken;
+
+ out:
+	return sem;
+}
+
+/*
+ * wake a single writer
+ */
+static inline struct rw_semaphore *
+__rwsem_wake_one_writer(struct rw_semaphore *sem)
+{
+	struct rwsem_waiter *waiter;
+
+	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+	wake_up_process(waiter->task);
+
+	return sem;
+}
+
+/*
+ * get a read lock on the semaphore
+ */
+void __sched __down_read(struct rw_semaphore *sem)
+{
+	struct rwsem_waiter waiter;
+	struct task_struct *tsk;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+		/* granted */
+		sem->activity++;
+		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+		goto out;
+	}
+
+	tsk = current;
+	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+
+	/* set up my own style of waitqueue */
+	waiter.task = tsk;
+	waiter.type = RWSEM_WAITING_FOR_READ;
+	get_task_struct(tsk);
+
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* we don't need to touch the semaphore struct anymore */
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	/* wait to be given the lock */
+	for (;;) {
+		if (!waiter.task)
+			break;
+		schedule();
+		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+	}
+
+	tsk->state = TASK_RUNNING;
+ out:
+	;
+}
+
+/*
+ * trylock for reading -- returns 1 if successful, 0 if contention
+ */
+int __down_read_trylock(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+	int ret = 0;
+
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+		/* granted */
+		sem->activity++;
+		ret = 1;
+	}
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return ret;
+}
+
+/*
+ * get a write lock on the semaphore
+ */
+void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
+{
+	struct rwsem_waiter waiter;
+	struct task_struct *tsk;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	/* set up my own style of waitqueue */
+	tsk = current;
+	waiter.task = tsk;
+	waiter.type = RWSEM_WAITING_FOR_WRITE;
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* wait for someone to release the lock */
+	for (;;) {
+		/*
+		 * That is the key to support write lock stealing: allows the
+		 * task already on CPU to get the lock soon rather than put
+		 * itself into sleep and waiting for system woke it or someone
+		 * else in the head of the wait list up.
+		 */
+		if (sem->activity == 0)
+			break;
+		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+		schedule();
+		raw_spin_lock_irqsave(&sem->wait_lock, flags);
+	}
+	/* got the lock */
+	sem->activity = -1;
+	list_del(&waiter.list);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+}
+
+void __sched __down_write(struct rw_semaphore *sem)
+{
+	__down_write_nested(sem, 0);
+}
+
+/*
+ * trylock for writing -- returns 1 if successful, 0 if contention
+ */
+int __down_write_trylock(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+	int ret = 0;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	if (sem->activity == 0) {
+		/* got the lock */
+		sem->activity = -1;
+		ret = 1;
+	}
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return ret;
+}
+
+/*
+ * release a read lock on the semaphore
+ */
+void __up_read(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	if (--sem->activity == 0 && !list_empty(&sem->wait_list))
+		sem = __rwsem_wake_one_writer(sem);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+}
+
+/*
+ * release a write lock on the semaphore
+ */
+void __up_write(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	sem->activity = 0;
+	if (!list_empty(&sem->wait_list))
+		sem = __rwsem_do_wake(sem, 1);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+}
+
+/*
+ * downgrade a write lock into a read lock
+ * - just wake up any readers at the front of the queue
+ */
+void __downgrade_write(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	sem->activity = 1;
+	if (!list_empty(&sem->wait_list))
+		sem = __rwsem_do_wake(sem, 0);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+}
+
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
new file mode 100644
index 00000000000..19c5fa95e0b
--- /dev/null
+++ b/kernel/locking/rwsem-xadd.c
@@ -0,0 +1,293 @@
+/* rwsem.c: R/W semaphores: contention handling functions
+ *
+ * Written by David Howells (dhowells@redhat.com).
+ * Derived from arch/i386/kernel/semaphore.c
+ *
+ * Writer lock-stealing by Alex Shi <alex.shi@intel.com>
+ * and Michel Lespinasse <walken@google.com>
+ */
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/export.h>
+
+/*
+ * Initialize an rwsem:
+ */
+void __init_rwsem(struct rw_semaphore *sem, const char *name,
+		  struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held semaphore:
+	 */
+	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+	lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
+	sem->count = RWSEM_UNLOCKED_VALUE;
+	raw_spin_lock_init(&sem->wait_lock);
+	INIT_LIST_HEAD(&sem->wait_list);
+}
+
+EXPORT_SYMBOL(__init_rwsem);
+
+enum rwsem_waiter_type {
+	RWSEM_WAITING_FOR_WRITE,
+	RWSEM_WAITING_FOR_READ
+};
+
+struct rwsem_waiter {
+	struct list_head list;
+	struct task_struct *task;
+	enum rwsem_waiter_type type;
+};
+
+enum rwsem_wake_type {
+	RWSEM_WAKE_ANY,		/* Wake whatever's at head of wait list */
+	RWSEM_WAKE_READERS,	/* Wake readers only */
+	RWSEM_WAKE_READ_OWNED	/* Waker thread holds the read lock */
+};
+
+/*
+ * handle the lock release when processes blocked on it that can now run
+ * - if we come here from up_xxxx(), then:
+ *   - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed)
+ *   - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so)
+ * - there must be someone on the queue
+ * - the spinlock must be held by the caller
+ * - woken process blocks are discarded from the list after having task zeroed
+ * - writers are only woken if downgrading is false
+ */
+static struct rw_semaphore *
+__rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
+{
+	struct rwsem_waiter *waiter;
+	struct task_struct *tsk;
+	struct list_head *next;
+	long oldcount, woken, loop, adjustment;
+
+	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
+		if (wake_type == RWSEM_WAKE_ANY)
+			/* Wake writer at the front of the queue, but do not
+			 * grant it the lock yet as we want other writers
+			 * to be able to steal it.  Readers, on the other hand,
+			 * will block as they will notice the queued writer.
+			 */
+			wake_up_process(waiter->task);
+		goto out;
+	}
+
+	/* Writers might steal the lock before we grant it to the next reader.
+	 * We prefer to do the first reader grant before counting readers
+	 * so we can bail out early if a writer stole the lock.
+	 */
+	adjustment = 0;
+	if (wake_type != RWSEM_WAKE_READ_OWNED) {
+		adjustment = RWSEM_ACTIVE_READ_BIAS;
+ try_reader_grant:
+		oldcount = rwsem_atomic_update(adjustment, sem) - adjustment;
+		if (unlikely(oldcount < RWSEM_WAITING_BIAS)) {
+			/* A writer stole the lock. Undo our reader grant. */
+			if (rwsem_atomic_update(-adjustment, sem) &
+						RWSEM_ACTIVE_MASK)
+				goto out;
+			/* Last active locker left. Retry waking readers. */
+			goto try_reader_grant;
+		}
+	}
+
+	/* Grant an infinite number of read locks to the readers at the front
+	 * of the queue.  Note we increment the 'active part' of the count by
+	 * the number of readers before waking any processes up.
+	 */
+	woken = 0;
+	do {
+		woken++;
+
+		if (waiter->list.next == &sem->wait_list)
+			break;
+
+		waiter = list_entry(waiter->list.next,
+					struct rwsem_waiter, list);
+
+	} while (waiter->type != RWSEM_WAITING_FOR_WRITE);
+
+	adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
+	if (waiter->type != RWSEM_WAITING_FOR_WRITE)
+		/* hit end of list above */
+		adjustment -= RWSEM_WAITING_BIAS;
+
+	if (adjustment)
+		rwsem_atomic_add(adjustment, sem);
+
+	next = sem->wait_list.next;
+	loop = woken;
+	do {
+		waiter = list_entry(next, struct rwsem_waiter, list);
+		next = waiter->list.next;
+		tsk = waiter->task;
+		smp_mb();
+		waiter->task = NULL;
+		wake_up_process(tsk);
+		put_task_struct(tsk);
+	} while (--loop);
+
+	sem->wait_list.next = next;
+	next->prev = &sem->wait_list;
+
+ out:
+	return sem;
+}
+
+/*
+ * wait for the read lock to be granted
+ */
+struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
+{
+	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
+	struct rwsem_waiter waiter;
+	struct task_struct *tsk = current;
+
+	/* set up my own style of waitqueue */
+	waiter.task = tsk;
+	waiter.type = RWSEM_WAITING_FOR_READ;
+	get_task_struct(tsk);
+
+	raw_spin_lock_irq(&sem->wait_lock);
+	if (list_empty(&sem->wait_list))
+		adjustment += RWSEM_WAITING_BIAS;
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* we're now waiting on the lock, but no longer actively locking */
+	count = rwsem_atomic_update(adjustment, sem);
+
+	/* If there are no active locks, wake the front queued process(es).
+	 *
+	 * If there are no writers and we are first in the queue,
+	 * wake our own waiter to join the existing active readers !
+	 */
+	if (count == RWSEM_WAITING_BIAS ||
+	    (count > RWSEM_WAITING_BIAS &&
+	     adjustment != -RWSEM_ACTIVE_READ_BIAS))
+		sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+
+	raw_spin_unlock_irq(&sem->wait_lock);
+
+	/* wait to be given the lock */
+	while (true) {
+		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+		if (!waiter.task)
+			break;
+		schedule();
+	}
+
+	tsk->state = TASK_RUNNING;
+
+	return sem;
+}
+
+/*
+ * wait until we successfully acquire the write lock
+ */
+struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
+{
+	long count, adjustment = -RWSEM_ACTIVE_WRITE_BIAS;
+	struct rwsem_waiter waiter;
+	struct task_struct *tsk = current;
+
+	/* set up my own style of waitqueue */
+	waiter.task = tsk;
+	waiter.type = RWSEM_WAITING_FOR_WRITE;
+
+	raw_spin_lock_irq(&sem->wait_lock);
+	if (list_empty(&sem->wait_list))
+		adjustment += RWSEM_WAITING_BIAS;
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* we're now waiting on the lock, but no longer actively locking */
+	count = rwsem_atomic_update(adjustment, sem);
+
+	/* If there were already threads queued before us and there are no
+	 * active writers, the lock must be read owned; so we try to wake
+	 * any read locks that were queued ahead of us. */
+	if (count > RWSEM_WAITING_BIAS &&
+	    adjustment == -RWSEM_ACTIVE_WRITE_BIAS)
+		sem = __rwsem_do_wake(sem, RWSEM_WAKE_READERS);
+
+	/* wait until we successfully acquire the lock */
+	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+	while (true) {
+		if (!(count & RWSEM_ACTIVE_MASK)) {
+			/* Try acquiring the write lock. */
+			count = RWSEM_ACTIVE_WRITE_BIAS;
+			if (!list_is_singular(&sem->wait_list))
+				count += RWSEM_WAITING_BIAS;
+
+			if (sem->count == RWSEM_WAITING_BIAS &&
+			    cmpxchg(&sem->count, RWSEM_WAITING_BIAS, count) ==
+							RWSEM_WAITING_BIAS)
+				break;
+		}
+
+		raw_spin_unlock_irq(&sem->wait_lock);
+
+		/* Block until there are no active lockers. */
+		do {
+			schedule();
+			set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+		} while ((count = sem->count) & RWSEM_ACTIVE_MASK);
+
+		raw_spin_lock_irq(&sem->wait_lock);
+	}
+
+	list_del(&waiter.list);
+	raw_spin_unlock_irq(&sem->wait_lock);
+	tsk->state = TASK_RUNNING;
+
+	return sem;
+}
+
+/*
+ * handle waking up a waiter on the semaphore
+ * - up_read/up_write has decremented the active part of count if we come here
+ */
+struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	/* do nothing if list empty */
+	if (!list_empty(&sem->wait_list))
+		sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return sem;
+}
+
+/*
+ * downgrade a write lock into a read lock
+ * - caller incremented waiting part of count and discovered it still negative
+ * - just wake up any readers at the front of the queue
+ */
+struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	/* do nothing if list empty */
+	if (!list_empty(&sem->wait_list))
+		sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return sem;
+}
+
+EXPORT_SYMBOL(rwsem_down_read_failed);
+EXPORT_SYMBOL(rwsem_down_write_failed);
+EXPORT_SYMBOL(rwsem_wake);
+EXPORT_SYMBOL(rwsem_downgrade_wake);
diff --git a/kernel/rwsem.c b/kernel/locking/rwsem.c
index cfff1435bdf..cfff1435bdf 100644
--- a/kernel/rwsem.c
+++ b/kernel/locking/rwsem.c
diff --git a/kernel/semaphore.c b/kernel/locking/semaphore.c
index 6815171a4ff..6815171a4ff 100644
--- a/kernel/semaphore.c
+++ b/kernel/locking/semaphore.c
diff --git a/kernel/spinlock.c b/kernel/locking/spinlock.c
index 4b082b5cac9..4b082b5cac9 100644
--- a/kernel/spinlock.c
+++ b/kernel/locking/spinlock.c
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
new file mode 100644
index 00000000000..0374a596cff
--- /dev/null
+++ b/kernel/locking/spinlock_debug.c
@@ -0,0 +1,302 @@
+/*
+ * Copyright 2005, Red Hat, Inc., Ingo Molnar
+ * Released under the General Public License (GPL).
+ *
+ * This file contains the spinlock/rwlock implementations for
+ * DEBUG_SPINLOCK.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/nmi.h>
+#include <linux/interrupt.h>
+#include <linux/debug_locks.h>
+#include <linux/delay.h>
+#include <linux/export.h>
+
+void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
+			  struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+#endif
+	lock->raw_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+	lock->magic = SPINLOCK_MAGIC;
+	lock->owner = SPINLOCK_OWNER_INIT;
+	lock->owner_cpu = -1;
+}
+
+EXPORT_SYMBOL(__raw_spin_lock_init);
+
+void __rwlock_init(rwlock_t *lock, const char *name,
+		   struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+#endif
+	lock->raw_lock = (arch_rwlock_t) __ARCH_RW_LOCK_UNLOCKED;
+	lock->magic = RWLOCK_MAGIC;
+	lock->owner = SPINLOCK_OWNER_INIT;
+	lock->owner_cpu = -1;
+}
+
+EXPORT_SYMBOL(__rwlock_init);
+
+static void spin_dump(raw_spinlock_t *lock, const char *msg)
+{
+	struct task_struct *owner = NULL;
+
+	if (lock->owner && lock->owner != SPINLOCK_OWNER_INIT)
+		owner = lock->owner;
+	printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n",
+		msg, raw_smp_processor_id(),
+		current->comm, task_pid_nr(current));
+	printk(KERN_EMERG " lock: %pS, .magic: %08x, .owner: %s/%d, "
+			".owner_cpu: %d\n",
+		lock, lock->magic,
+		owner ? owner->comm : "<none>",
+		owner ? task_pid_nr(owner) : -1,
+		lock->owner_cpu);
+	dump_stack();
+}
+
+static void spin_bug(raw_spinlock_t *lock, const char *msg)
+{
+	if (!debug_locks_off())
+		return;
+
+	spin_dump(lock, msg);
+}
+
+#define SPIN_BUG_ON(cond, lock, msg) if (unlikely(cond)) spin_bug(lock, msg)
+
+static inline void
+debug_spin_lock_before(raw_spinlock_t *lock)
+{
+	SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic");
+	SPIN_BUG_ON(lock->owner == current, lock, "recursion");
+	SPIN_BUG_ON(lock->owner_cpu == raw_smp_processor_id(),
+							lock, "cpu recursion");
+}
+
+static inline void debug_spin_lock_after(raw_spinlock_t *lock)
+{
+	lock->owner_cpu = raw_smp_processor_id();
+	lock->owner = current;
+}
+
+static inline void debug_spin_unlock(raw_spinlock_t *lock)
+{
+	SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic");
+	SPIN_BUG_ON(!raw_spin_is_locked(lock), lock, "already unlocked");
+	SPIN_BUG_ON(lock->owner != current, lock, "wrong owner");
+	SPIN_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
+							lock, "wrong CPU");
+	lock->owner = SPINLOCK_OWNER_INIT;
+	lock->owner_cpu = -1;
+}
+
+static void __spin_lock_debug(raw_spinlock_t *lock)
+{
+	u64 i;
+	u64 loops = loops_per_jiffy * HZ;
+
+	for (i = 0; i < loops; i++) {
+		if (arch_spin_trylock(&lock->raw_lock))
+			return;
+		__delay(1);
+	}
+	/* lockup suspected: */
+	spin_dump(lock, "lockup suspected");
+#ifdef CONFIG_SMP
+	trigger_all_cpu_backtrace();
+#endif
+
+	/*
+	 * The trylock above was causing a livelock.  Give the lower level arch
+	 * specific lock code a chance to acquire the lock. We have already
+	 * printed a warning/backtrace at this point. The non-debug arch
+	 * specific code might actually succeed in acquiring the lock.  If it is
+	 * not successful, the end-result is the same - there is no forward
+	 * progress.
+	 */
+	arch_spin_lock(&lock->raw_lock);
+}
+
+void do_raw_spin_lock(raw_spinlock_t *lock)
+{
+	debug_spin_lock_before(lock);
+	if (unlikely(!arch_spin_trylock(&lock->raw_lock)))
+		__spin_lock_debug(lock);
+	debug_spin_lock_after(lock);
+}
+
+int do_raw_spin_trylock(raw_spinlock_t *lock)
+{
+	int ret = arch_spin_trylock(&lock->raw_lock);
+
+	if (ret)
+		debug_spin_lock_after(lock);
+#ifndef CONFIG_SMP
+	/*
+	 * Must not happen on UP:
+	 */
+	SPIN_BUG_ON(!ret, lock, "trylock failure on UP");
+#endif
+	return ret;
+}
+
+void do_raw_spin_unlock(raw_spinlock_t *lock)
+{
+	debug_spin_unlock(lock);
+	arch_spin_unlock(&lock->raw_lock);
+}
+
+static void rwlock_bug(rwlock_t *lock, const char *msg)
+{
+	if (!debug_locks_off())
+		return;
+
+	printk(KERN_EMERG "BUG: rwlock %s on CPU#%d, %s/%d, %p\n",
+		msg, raw_smp_processor_id(), current->comm,
+		task_pid_nr(current), lock);
+	dump_stack();
+}
+
+#define RWLOCK_BUG_ON(cond, lock, msg) if (unlikely(cond)) rwlock_bug(lock, msg)
+
+#if 0		/* __write_lock_debug() can lock up - maybe this can too? */
+static void __read_lock_debug(rwlock_t *lock)
+{
+	u64 i;
+	u64 loops = loops_per_jiffy * HZ;
+	int print_once = 1;
+
+	for (;;) {
+		for (i = 0; i < loops; i++) {
+			if (arch_read_trylock(&lock->raw_lock))
+				return;
+			__delay(1);
+		}
+		/* lockup suspected: */
+		if (print_once) {
+			print_once = 0;
+			printk(KERN_EMERG "BUG: read-lock lockup on CPU#%d, "
+					"%s/%d, %p\n",
+				raw_smp_processor_id(), current->comm,
+				current->pid, lock);
+			dump_stack();
+		}
+	}
+}
+#endif
+
+void do_raw_read_lock(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	arch_read_lock(&lock->raw_lock);
+}
+
+int do_raw_read_trylock(rwlock_t *lock)
+{
+	int ret = arch_read_trylock(&lock->raw_lock);
+
+#ifndef CONFIG_SMP
+	/*
+	 * Must not happen on UP:
+	 */
+	RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP");
+#endif
+	return ret;
+}
+
+void do_raw_read_unlock(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	arch_read_unlock(&lock->raw_lock);
+}
+
+static inline void debug_write_lock_before(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	RWLOCK_BUG_ON(lock->owner == current, lock, "recursion");
+	RWLOCK_BUG_ON(lock->owner_cpu == raw_smp_processor_id(),
+							lock, "cpu recursion");
+}
+
+static inline void debug_write_lock_after(rwlock_t *lock)
+{
+	lock->owner_cpu = raw_smp_processor_id();
+	lock->owner = current;
+}
+
+static inline void debug_write_unlock(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	RWLOCK_BUG_ON(lock->owner != current, lock, "wrong owner");
+	RWLOCK_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
+							lock, "wrong CPU");
+	lock->owner = SPINLOCK_OWNER_INIT;
+	lock->owner_cpu = -1;
+}
+
+#if 0		/* This can cause lockups */
+static void __write_lock_debug(rwlock_t *lock)
+{
+	u64 i;
+	u64 loops = loops_per_jiffy * HZ;
+	int print_once = 1;
+
+	for (;;) {
+		for (i = 0; i < loops; i++) {
+			if (arch_write_trylock(&lock->raw_lock))
+				return;
+			__delay(1);
+		}
+		/* lockup suspected: */
+		if (print_once) {
+			print_once = 0;
+			printk(KERN_EMERG "BUG: write-lock lockup on CPU#%d, "
+					"%s/%d, %p\n",
+				raw_smp_processor_id(), current->comm,
+				current->pid, lock);
+			dump_stack();
+		}
+	}
+}
+#endif
+
+void do_raw_write_lock(rwlock_t *lock)
+{
+	debug_write_lock_before(lock);
+	arch_write_lock(&lock->raw_lock);
+	debug_write_lock_after(lock);
+}
+
+int do_raw_write_trylock(rwlock_t *lock)
+{
+	int ret = arch_write_trylock(&lock->raw_lock);
+
+	if (ret)
+		debug_write_lock_after(lock);
+#ifndef CONFIG_SMP
+	/*
+	 * Must not happen on UP:
+	 */
+	RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP");
+#endif
+	return ret;
+}
+
+void do_raw_write_unlock(rwlock_t *lock)
+{
+	debug_write_unlock(lock);
+	arch_write_unlock(&lock->raw_lock);
+}
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 3822ac0c4b2..6abb03dff5c 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1133,7 +1133,7 @@ void exit_rcu(void)
 
 #ifdef CONFIG_RCU_BOOST
 
-#include "../rtmutex_common.h"
+#include "../locking/rtmutex_common.h"
 
 #ifdef CONFIG_RCU_TRACE
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index d37d9dd8f46..34a604726d0 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -969,9 +969,10 @@ static struct ctl_table kern_table[] = {
 	{
 		.procname	= "hung_task_check_count",
 		.data		= &sysctl_hung_task_check_count,
-		.maxlen		= sizeof(unsigned long),
+		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_doulongvec_minmax,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
 	},
 	{
 		.procname	= "hung_task_timeout_secs",