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

Pull scheduler updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Add the SYSTEM_SCHEDULING bootup state to move various scheduler
     debug checks earlier into the bootup. This turns silent and
     sporadically deadly bugs into nice, deterministic splats. Fix some
     of the splats that triggered. (Thomas Gleixner)

   - A round of restructuring and refactoring of the load-balancing and
     topology code (Peter Zijlstra)

   - Another round of consolidating ~20 of incremental scheduler code
     history: this time in terms of wait-queue nomenclature. (I didn't
     get much feedback on these renaming patches, and we can still
     easily change any names I might have misplaced, so if anyone hates
     a new name, please holler and I'll fix it.) (Ingo Molnar)

   - sched/numa improvements, fixes and updates (Rik van Riel)

   - Another round of x86/tsc scheduler clock code improvements, in hope
     of making it more robust (Peter Zijlstra)

   - Improve NOHZ behavior (Frederic Weisbecker)

   - Deadline scheduler improvements and fixes (Luca Abeni, Daniel
     Bristot de Oliveira)

   - Simplify and optimize the topology setup code (Lauro Ramos
     Venancio)

   - Debloat and decouple scheduler code some more (Nicolas Pitre)

   - Simplify code by making better use of llist primitives (Byungchul
     Park)

   - ... plus other fixes and improvements"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (103 commits)
  sched/cputime: Refactor the cputime_adjust() code
  sched/debug: Expose the number of RT/DL tasks that can migrate
  sched/numa: Hide numa_wake_affine() from UP build
  sched/fair: Remove effective_load()
  sched/numa: Implement NUMA node level wake_affine()
  sched/fair: Simplify wake_affine() for the single socket case
  sched/numa: Override part of migrate_degrades_locality() when idle balancing
  sched/rt: Move RT related code from sched/core.c to sched/rt.c
  sched/deadline: Move DL related code from sched/core.c to sched/deadline.c
  sched/cpuset: Only offer CONFIG_CPUSETS if SMP is enabled
  sched/fair: Spare idle load balancing on nohz_full CPUs
  nohz: Move idle balancer registration to the idle path
  sched/loadavg: Generalize "_idle" naming to "_nohz"
  sched/core: Drop the unused try_get_task_struct() helper function
  sched/fair: WARN() and refuse to set buddy when !se->on_rq
  sched/debug: Fix SCHED_WARN_ON() to return a value on !CONFIG_SCHED_DEBUG as well
  sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming
  sched/wait: Move bit_wait_table[] and related functionality from sched/core.c to sched/wait_bit.c
  sched/wait: Split out the wait_bit*() APIs from <linux/wait.h> into <linux/wait_bit.h>
  sched/wait: Re-adjust macro line continuation backslashes in <linux/wait.h>
  ...

22 files changed, 731 insertions, 656 deletions

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 23d32ff0b462..14542308d25b 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -33,7 +33,7 @@ struct blk_mq_hw_ctx {
 	struct blk_mq_ctx	**ctxs;
 	unsigned int		nr_ctx;
 
-	wait_queue_t		dispatch_wait;
+	wait_queue_entry_t		dispatch_wait;
 	atomic_t		wait_index;
 
 	struct blk_mq_tags	*tags;
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index f2b10d9ebd04..81490456c242 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -96,6 +96,7 @@ struct clocksource {
 	void (*suspend)(struct clocksource *cs);
 	void (*resume)(struct clocksource *cs);
 	void (*mark_unstable)(struct clocksource *cs);
+	void (*tick_stable)(struct clocksource *cs);
 
 	/* private: */
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 2404ad238c0b..4bf4479a3a80 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -236,6 +236,23 @@ unsigned int cpumask_local_spread(unsigned int i, int node);
 		(cpu) = cpumask_next_zero((cpu), (mask)),	\
 		(cpu) < nr_cpu_ids;)
 
+extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap);
+
+/**
+ * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask: the cpumask poiter
+ * @start: the start location
+ *
+ * The implementation does not assume any bit in @mask is set (including @start).
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu_wrap(cpu, mask, start)					\
+	for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false);	\
+	     (cpu) < nr_cpumask_bits;						\
+	     (cpu) = cpumask_next_wrap((cpu), (mask), (start), true))
+
 /**
  * for_each_cpu_and - iterate over every cpu in both masks
  * @cpu: the (optionally unsigned) integer iterator
@@ -276,6 +293,12 @@ static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
 	set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
+static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+{
+	__set_bit(cpumask_check(cpu), cpumask_bits(dstp));
+}
+
+
 /**
  * cpumask_clear_cpu - clear a cpu in a cpumask
  * @cpu: cpu number (< nr_cpu_ids)
@@ -286,6 +309,11 @@ static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp)
 	clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
+static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
+{
+	__clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
+}
+
 /**
  * cpumask_test_cpu - test for a cpu in a cpumask
  * @cpu: cpu number (< nr_cpu_ids)
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index ff0b981f078e..9e4befd95bc7 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -37,7 +37,7 @@ struct eventfd_ctx *eventfd_ctx_fdget(int fd);
 struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
 __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n);
 ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, __u64 *cnt);
-int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_t *wait,
+int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt);
 
 #else /* CONFIG_EVENTFD */
@@ -73,7 +73,7 @@ static inline ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait,
 }
 
 static inline int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx,
-						wait_queue_t *wait, __u64 *cnt)
+						wait_queue_entry_t *wait, __u64 *cnt)
 {
 	return -ENOSYS;
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 65adbddb3163..771fe1131467 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2,7 +2,7 @@
 #define _LINUX_FS_H
 
 #include <linux/linkage.h>
-#include <linux/wait.h>
+#include <linux/wait_bit.h>
 #include <linux/kdev_t.h>
 #include <linux/dcache.h>
 #include <linux/path.h>
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 13bc08aba704..1c91f26e2996 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -490,9 +490,13 @@ extern int root_mountflags;
 
 extern bool early_boot_irqs_disabled;
 
-/* Values used for system_state */
+/*
+ * Values used for system_state. Ordering of the states must not be changed
+ * as code checks for <, <=, >, >= STATE.
+ */
 extern enum system_states {
 	SYSTEM_BOOTING,
+	SYSTEM_SCHEDULING,
 	SYSTEM_RUNNING,
 	SYSTEM_HALT,
 	SYSTEM_POWER_OFF,
diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h
index 0c1de05098c8..76c2fbc59f35 100644
--- a/include/linux/kvm_irqfd.h
+++ b/include/linux/kvm_irqfd.h
@@ -46,7 +46,7 @@ struct kvm_kernel_irqfd_resampler {
 struct kvm_kernel_irqfd {
 	/* Used for MSI fast-path */
 	struct kvm *kvm;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	/* Update side is protected by irqfds.lock */
 	struct kvm_kernel_irq_routing_entry irq_entry;
 	seqcount_t irq_entry_sc;
diff --git a/include/linux/llist.h b/include/linux/llist.h
index 171baa90f6f6..d11738110a7a 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -110,6 +110,25 @@ static inline void init_llist_head(struct llist_head *list)
 	for ((pos) = (node); pos; (pos) = (pos)->next)
 
 /**
+ * llist_for_each_safe - iterate over some deleted entries of a lock-less list
+ *			 safe against removal of list entry
+ * @pos:	the &struct llist_node to use as a loop cursor
+ * @n:		another &struct llist_node to use as temporary storage
+ * @node:	the first entry of deleted list entries
+ *
+ * In general, some entries of the lock-less list can be traversed
+ * safely only after being deleted from list, so start with an entry
+ * instead of list head.
+ *
+ * If being used on entries deleted from lock-less list directly, the
+ * traverse order is from the newest to the oldest added entry.  If
+ * you want to traverse from the oldest to the newest, you must
+ * reverse the order by yourself before traversing.
+ */
+#define llist_for_each_safe(pos, n, node)			\
+	for ((pos) = (node); (pos) && ((n) = (pos)->next, true); (pos) = (n))
+
+/**
  * llist_for_each_entry - iterate over some deleted entries of lock-less list of given type
  * @pos:	the type * to use as a loop cursor.
  * @node:	the fist entry of deleted list entries.
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 316a19f6b635..e7bbd9d4dc6c 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -524,7 +524,7 @@ void page_endio(struct page *page, bool is_write, int err);
 /*
  * Add an arbitrary waiter to a page's wait queue
  */
-extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter);
+extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter);
 
 /*
  * Fault everything in given userspace address range in.
diff --git a/include/linux/poll.h b/include/linux/poll.h
index 75ffc5729e4c..2889f09a1c60 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -75,7 +75,7 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
 struct poll_table_entry {
 	struct file *filp;
 	unsigned long key;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	wait_queue_head_t *wait_address;
 };
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2b69fc650201..1f0f427e0292 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -421,7 +421,8 @@ struct sched_dl_entity {
 	u64				dl_runtime;	/* Maximum runtime for each instance	*/
 	u64				dl_deadline;	/* Relative deadline of each instance	*/
 	u64				dl_period;	/* Separation of two instances (period) */
-	u64				dl_bw;		/* dl_runtime / dl_deadline		*/
+	u64				dl_bw;		/* dl_runtime / dl_period		*/
+	u64				dl_density;	/* dl_runtime / dl_deadline		*/
 
 	/*
 	 * Actual scheduling parameters. Initialized with the values above,
@@ -445,16 +446,33 @@ struct sched_dl_entity {
 	 *
 	 * @dl_yielded tells if task gave up the CPU before consuming
 	 * all its available runtime during the last job.
+	 *
+	 * @dl_non_contending tells if the task is inactive while still
+	 * contributing to the active utilization. In other words, it
+	 * indicates if the inactive timer has been armed and its handler
+	 * has not been executed yet. This flag is useful to avoid race
+	 * conditions between the inactive timer handler and the wakeup
+	 * code.
 	 */
 	int				dl_throttled;
 	int				dl_boosted;
 	int				dl_yielded;
+	int				dl_non_contending;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
 	 * own bandwidth to be enforced, thus we need one timer per task.
 	 */
 	struct hrtimer			dl_timer;
+
+	/*
+	 * Inactive timer, responsible for decreasing the active utilization
+	 * at the "0-lag time". When a -deadline task blocks, it contributes
+	 * to GRUB's active utilization until the "0-lag time", hence a
+	 * timer is needed to decrease the active utilization at the correct
+	 * time.
+	 */
+	struct hrtimer inactive_timer;
 };
 
 union rcu_special {
@@ -1096,8 +1114,6 @@ static inline struct pid *task_session(struct task_struct *task)
  *                     current.
  * task_xid_nr_ns()  : id seen from the ns specified;
  *
- * set_task_vxid()   : assigns a virtual id to a task;
- *
  * see also pid_nr() etc in include/linux/pid.h
  */
 pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns);
diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h
index 34fe92ce1ebd..a55600ffdf4b 100644
--- a/include/linux/sched/clock.h
+++ b/include/linux/sched/clock.h
@@ -23,10 +23,6 @@ extern u64 sched_clock_cpu(int cpu);
 extern void sched_clock_init(void);
 
 #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-static inline void sched_clock_init_late(void)
-{
-}
-
 static inline void sched_clock_tick(void)
 {
 }
@@ -39,7 +35,7 @@ static inline void sched_clock_idle_sleep_event(void)
 {
 }
 
-static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
+static inline void sched_clock_idle_wakeup_event(void)
 {
 }
 
@@ -53,7 +49,6 @@ static inline u64 local_clock(void)
 	return sched_clock();
 }
 #else
-extern void sched_clock_init_late(void);
 extern int sched_clock_stable(void);
 extern void clear_sched_clock_stable(void);
 
@@ -63,10 +58,10 @@ extern void clear_sched_clock_stable(void);
  */
 extern u64 __sched_clock_offset;
 
-
 extern void sched_clock_tick(void);
+extern void sched_clock_tick_stable(void);
 extern void sched_clock_idle_sleep_event(void);
-extern void sched_clock_idle_wakeup_event(u64 delta_ns);
+extern void sched_clock_idle_wakeup_event(void);
 
 /*
  * As outlined in clock.c, provides a fast, high resolution, nanosecond
diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h
index 4995b717500b..7d3f75db23e5 100644
--- a/include/linux/sched/nohz.h
+++ b/include/linux/sched/nohz.h
@@ -23,11 +23,11 @@ static inline void set_cpu_sd_state_idle(void) { }
 #endif
 
 #ifdef CONFIG_NO_HZ_COMMON
-void calc_load_enter_idle(void);
-void calc_load_exit_idle(void);
+void calc_load_nohz_start(void);
+void calc_load_nohz_stop(void);
 #else
-static inline void calc_load_enter_idle(void) { }
-static inline void calc_load_exit_idle(void) { }
+static inline void calc_load_nohz_start(void) { }
+static inline void calc_load_nohz_stop(void) { }
 #endif /* CONFIG_NO_HZ_COMMON */
 
 #if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP)
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index a978d7189cfd..f0f065c5afcf 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -95,8 +95,6 @@ static inline void put_task_struct(struct task_struct *t)
 }
 
 struct task_struct *task_rcu_dereference(struct task_struct **ptask);
-struct task_struct *try_get_task_struct(struct task_struct **ptask);
-
 
 #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
 extern int arch_task_struct_size __read_mostly;
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 7ba040c797ec..9d7529ffc4ce 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -13,7 +13,7 @@
 #include <linux/ktime.h>
 #include <linux/sunrpc/types.h>
 #include <linux/spinlock.h>
-#include <linux/wait.h>
+#include <linux/wait_bit.h>
 #include <linux/workqueue.h>
 #include <linux/sunrpc/xdr.h>
 
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index edf9b2cad277..f57076b958b7 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -183,7 +183,7 @@ struct virqfd {
 	void			(*thread)(void *, void *);
 	void			*data;
 	struct work_struct	inject;
-	wait_queue_t		wait;
+	wait_queue_entry_t		wait;
 	poll_table		pt;
 	struct work_struct	shutdown;
 	struct virqfd		**pvirqfd;
diff --git a/include/linux/wait.h b/include/linux/wait.h
index db076ca7f11d..b289c96151ee 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -10,38 +10,30 @@
 #include <asm/current.h>
 #include <uapi/linux/wait.h>
 
-typedef struct __wait_queue wait_queue_t;
-typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key);
-int default_wake_function(wait_queue_t *wait, unsigned mode, int flags, void *key);
+typedef struct wait_queue_entry wait_queue_entry_t;
 
-/* __wait_queue::flags */
+typedef int (*wait_queue_func_t)(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key);
+int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key);
+
+/* wait_queue_entry::flags */
 #define WQ_FLAG_EXCLUSIVE	0x01
 #define WQ_FLAG_WOKEN		0x02
 
-struct __wait_queue {
+/*
+ * A single wait-queue entry structure:
+ */
+struct wait_queue_entry {
 	unsigned int		flags;
 	void			*private;
 	wait_queue_func_t	func;
-	struct list_head	task_list;
-};
-
-struct wait_bit_key {
-	void			*flags;
-	int			bit_nr;
-#define WAIT_ATOMIC_T_BIT_NR	-1
-	unsigned long		timeout;
+	struct list_head	entry;
 };
 
-struct wait_bit_queue {
-	struct wait_bit_key	key;
-	wait_queue_t		wait;
-};
-
-struct __wait_queue_head {
+struct wait_queue_head {
 	spinlock_t		lock;
-	struct list_head	task_list;
+	struct list_head	head;
 };
-typedef struct __wait_queue_head wait_queue_head_t;
+typedef struct wait_queue_head wait_queue_head_t;
 
 struct task_struct;
 
@@ -49,82 +41,76 @@ struct task_struct;
  * Macros for declaration and initialisaton of the datatypes
  */
 
-#define __WAITQUEUE_INITIALIZER(name, tsk) {				\
-	.private	= tsk,						\
-	.func		= default_wake_function,			\
-	.task_list	= { NULL, NULL } }
+#define __WAITQUEUE_INITIALIZER(name, tsk) {					\
+	.private	= tsk,							\
+	.func		= default_wake_function,				\
+	.entry		= { NULL, NULL } }
 
-#define DECLARE_WAITQUEUE(name, tsk)					\
-	wait_queue_t name = __WAITQUEUE_INITIALIZER(name, tsk)
+#define DECLARE_WAITQUEUE(name, tsk)						\
+	struct wait_queue_entry name = __WAITQUEUE_INITIALIZER(name, tsk)
 
-#define __WAIT_QUEUE_HEAD_INITIALIZER(name) {				\
-	.lock		= __SPIN_LOCK_UNLOCKED(name.lock),		\
-	.task_list	= { &(name).task_list, &(name).task_list } }
+#define __WAIT_QUEUE_HEAD_INITIALIZER(name) {					\
+	.lock		= __SPIN_LOCK_UNLOCKED(name.lock),			\
+	.head		= { &(name).head, &(name).head } }
 
 #define DECLARE_WAIT_QUEUE_HEAD(name) \
-	wait_queue_head_t name = __WAIT_QUEUE_HEAD_INITIALIZER(name)
-
-#define __WAIT_BIT_KEY_INITIALIZER(word, bit)				\
-	{ .flags = word, .bit_nr = bit, }
+	struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name)
 
-#define __WAIT_ATOMIC_T_KEY_INITIALIZER(p)				\
-	{ .flags = p, .bit_nr = WAIT_ATOMIC_T_BIT_NR, }
+extern void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *);
 
-extern void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *);
-
-#define init_waitqueue_head(q)				\
-	do {						\
-		static struct lock_class_key __key;	\
-							\
-		__init_waitqueue_head((q), #q, &__key);	\
+#define init_waitqueue_head(wq_head)						\
+	do {									\
+		static struct lock_class_key __key;				\
+										\
+		__init_waitqueue_head((wq_head), #wq_head, &__key);		\
 	} while (0)
 
 #ifdef CONFIG_LOCKDEP
 # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \
 	({ init_waitqueue_head(&name); name; })
 # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) \
-	wait_queue_head_t name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name)
+	struct wait_queue_head name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name)
 #else
 # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) DECLARE_WAIT_QUEUE_HEAD(name)
 #endif
 
-static inline void init_waitqueue_entry(wait_queue_t *q, struct task_struct *p)
+static inline void init_waitqueue_entry(struct wait_queue_entry *wq_entry, struct task_struct *p)
 {
-	q->flags	= 0;
-	q->private	= p;
-	q->func		= default_wake_function;
+	wq_entry->flags		= 0;
+	wq_entry->private	= p;
+	wq_entry->func		= default_wake_function;
 }
 
 static inline void
-init_waitqueue_func_entry(wait_queue_t *q, wait_queue_func_t func)
+init_waitqueue_func_entry(struct wait_queue_entry *wq_entry, wait_queue_func_t func)
 {
-	q->flags	= 0;
-	q->private	= NULL;
-	q->func		= func;
+	wq_entry->flags		= 0;
+	wq_entry->private	= NULL;
+	wq_entry->func		= func;
 }
 
 /**
  * waitqueue_active -- locklessly test for waiters on the queue
- * @q: the waitqueue to test for waiters
+ * @wq_head: the waitqueue to test for waiters
  *
  * returns true if the wait list is not empty
  *
  * NOTE: this function is lockless and requires care, incorrect usage _will_
  * lead to sporadic and non-obvious failure.
  *
- * Use either while holding wait_queue_head_t::lock or when used for wakeups
+ * Use either while holding wait_queue_head::lock or when used for wakeups
  * with an extra smp_mb() like:
  *
  *      CPU0 - waker                    CPU1 - waiter
  *
  *                                      for (;;) {
- *      @cond = true;                     prepare_to_wait(&wq, &wait, state);
+ *      @cond = true;                     prepare_to_wait(&wq_head, &wait, state);
  *      smp_mb();                         // smp_mb() from set_current_state()
- *      if (waitqueue_active(wq))         if (@cond)
- *        wake_up(wq);                      break;
+ *      if (waitqueue_active(wq_head))         if (@cond)
+ *        wake_up(wq_head);                      break;
  *                                        schedule();
  *                                      }
- *                                      finish_wait(&wq, &wait);
+ *                                      finish_wait(&wq_head, &wait);
  *
  * Because without the explicit smp_mb() it's possible for the
  * waitqueue_active() load to get hoisted over the @cond store such that we'll
@@ -133,20 +119,20 @@ init_waitqueue_func_entry(wait_queue_t *q, wait_queue_func_t func)
  * Also note that this 'optimization' trades a spin_lock() for an smp_mb(),
  * which (when the lock is uncontended) are of roughly equal cost.
  */
-static inline int waitqueue_active(wait_queue_head_t *q)
+static inline int waitqueue_active(struct wait_queue_head *wq_head)
 {
-	return !list_empty(&q->task_list);
+	return !list_empty(&wq_head->head);
 }
 
 /**
  * wq_has_sleeper - check if there are any waiting processes
- * @wq: wait queue head
+ * @wq_head: wait queue head
  *
- * Returns true if wq has waiting processes
+ * Returns true if wq_head has waiting processes
  *
  * Please refer to the comment for waitqueue_active.
  */
-static inline bool wq_has_sleeper(wait_queue_head_t *wq)
+static inline bool wq_has_sleeper(struct wait_queue_head *wq_head)
 {
 	/*
 	 * We need to be sure we are in sync with the
@@ -156,63 +142,51 @@ static inline bool wq_has_sleeper(wait_queue_head_t *wq)
 	 * waiting side.
 	 */
 	smp_mb();
-	return waitqueue_active(wq);
+	return waitqueue_active(wq_head);
 }
 
-extern void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait);
-extern void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait);
-extern void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait);
+extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
+extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
+extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 
-static inline void __add_wait_queue(wait_queue_head_t *head, wait_queue_t *new)
+static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
-	list_add(&new->task_list, &head->task_list);
+	list_add(&wq_entry->entry, &wq_head->head);
 }
 
 /*
  * Used for wake-one threads:
  */
 static inline void
-__add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
+__add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
-	wait->flags |= WQ_FLAG_EXCLUSIVE;
-	__add_wait_queue(q, wait);
+	wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
+	__add_wait_queue(wq_head, wq_entry);
 }
 
-static inline void __add_wait_queue_tail(wait_queue_head_t *head,
-					 wait_queue_t *new)
+static inline void __add_wait_queue_entry_tail(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
-	list_add_tail(&new->task_list, &head->task_list);
+	list_add_tail(&wq_entry->entry, &wq_head->head);
 }
 
 static inline void
-__add_wait_queue_tail_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
+__add_wait_queue_entry_tail_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
-	wait->flags |= WQ_FLAG_EXCLUSIVE;
-	__add_wait_queue_tail(q, wait);
+	wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
+	__add_wait_queue_entry_tail(wq_head, wq_entry);
 }
 
 static inline void
-__remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old)
+__remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
-	list_del(&old->task_list);
+	list_del(&wq_entry->entry);
 }
 
-typedef int wait_bit_action_f(struct wait_bit_key *, int mode);
-void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
-void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
-void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr);
-void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
-void __wake_up_bit(wait_queue_head_t *, void *, int);
-int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned);
-int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned);
-void wake_up_bit(void *, int);
-void wake_up_atomic_t(atomic_t *);
-int out_of_line_wait_on_bit(void *, int, wait_bit_action_f *, unsigned);
-int out_of_line_wait_on_bit_timeout(void *, int, wait_bit_action_f *, unsigned, unsigned long);
-int out_of_line_wait_on_bit_lock(void *, int, wait_bit_action_f *, unsigned);
-int out_of_line_wait_on_atomic_t(atomic_t *, int (*)(atomic_t *), unsigned);
-wait_queue_head_t *bit_waitqueue(void *, int);
+void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key);
+void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key);
+void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key);
+void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr);
+void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr);
 
 #define wake_up(x)			__wake_up(x, TASK_NORMAL, 1, NULL)
 #define wake_up_nr(x, nr)		__wake_up(x, TASK_NORMAL, nr, NULL)
@@ -228,28 +202,28 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 /*
  * Wakeup macros to be used to report events to the targets.
  */
-#define wake_up_poll(x, m)						\
+#define wake_up_poll(x, m)							\
 	__wake_up(x, TASK_NORMAL, 1, (void *) (m))
-#define wake_up_locked_poll(x, m)					\
+#define wake_up_locked_poll(x, m)						\
 	__wake_up_locked_key((x), TASK_NORMAL, (void *) (m))
-#define wake_up_interruptible_poll(x, m)				\
+#define wake_up_interruptible_poll(x, m)					\
 	__wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m))
-#define wake_up_interruptible_sync_poll(x, m)				\
+#define wake_up_interruptible_sync_poll(x, m)					\
 	__wake_up_sync_key((x), TASK_INTERRUPTIBLE, 1, (void *) (m))
 
-#define ___wait_cond_timeout(condition)					\
-({									\
-	bool __cond = (condition);					\
-	if (__cond && !__ret)						\
-		__ret = 1;						\
-	__cond || !__ret;						\
+#define ___wait_cond_timeout(condition)						\
+({										\
+	bool __cond = (condition);						\
+	if (__cond && !__ret)							\
+		__ret = 1;							\
+	__cond || !__ret;							\
 })
 
-#define ___wait_is_interruptible(state)					\
-	(!__builtin_constant_p(state) ||				\
-		state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE)	\
+#define ___wait_is_interruptible(state)						\
+	(!__builtin_constant_p(state) ||					\
+		state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE)		\
 
-extern void init_wait_entry(wait_queue_t *__wait, int flags);
+extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags);
 
 /*
  * The below macro ___wait_event() has an explicit shadow of the __ret
@@ -263,108 +237,108 @@ extern void init_wait_entry(wait_queue_t *__wait, int flags);
  * otherwise.
  */
 
-#define ___wait_event(wq, condition, state, exclusive, ret, cmd)	\
-({									\
-	__label__ __out;						\
-	wait_queue_t __wait;						\
-	long __ret = ret;	/* explicit shadow */			\
-									\
-	init_wait_entry(&__wait, exclusive ? WQ_FLAG_EXCLUSIVE : 0);	\
-	for (;;) {							\
-		long __int = prepare_to_wait_event(&wq, &__wait, state);\
-									\
-		if (condition)						\
-			break;						\
-									\
-		if (___wait_is_interruptible(state) && __int) {		\
-			__ret = __int;					\
-			goto __out;					\
-		}							\
-									\
-		cmd;							\
-	}								\
-	finish_wait(&wq, &__wait);					\
-__out:	__ret;								\
+#define ___wait_event(wq_head, condition, state, exclusive, ret, cmd)		\
+({										\
+	__label__ __out;							\
+	struct wait_queue_entry __wq_entry;					\
+	long __ret = ret;	/* explicit shadow */				\
+										\
+	init_wait_entry(&__wq_entry, exclusive ? WQ_FLAG_EXCLUSIVE : 0);	\
+	for (;;) {								\
+		long __int = prepare_to_wait_event(&wq_head, &__wq_entry, state);\
+										\
+		if (condition)							\
+			break;							\
+										\
+		if (___wait_is_interruptible(state) && __int) {			\
+			__ret = __int;						\
+			goto __out;						\
+		}								\
+										\
+		cmd;								\
+	}									\
+	finish_wait(&wq_head, &__wq_entry);					\
+__out:	__ret;									\
 })
 
-#define __wait_event(wq, condition)					\
-	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
+#define __wait_event(wq_head, condition)					\
+	(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
 			    schedule())
 
 /**
  * wait_event - sleep until a condition gets true
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  *
  * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
  * @condition evaluates to true. The @condition is checked each time
- * the waitqueue @wq is woken up.
+ * the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
  */
-#define wait_event(wq, condition)					\
-do {									\
-	might_sleep();							\
-	if (condition)							\
-		break;							\
-	__wait_event(wq, condition);					\
+#define wait_event(wq_head, condition)						\
+do {										\
+	might_sleep();								\
+	if (condition)								\
+		break;								\
+	__wait_event(wq_head, condition);					\
 } while (0)
 
-#define __io_wait_event(wq, condition)					\
-	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
+#define __io_wait_event(wq_head, condition)					\
+	(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
 			    io_schedule())
 
 /*
  * io_wait_event() -- like wait_event() but with io_schedule()
  */
-#define io_wait_event(wq, condition)					\
-do {									\
-	might_sleep();							\
-	if (condition)							\
-		break;							\
-	__io_wait_event(wq, condition);					\
+#define io_wait_event(wq_head, condition)					\
+do {										\
+	might_sleep();								\
+	if (condition)								\
+		break;								\
+	__io_wait_event(wq_head, condition);					\
 } while (0)
 
-#define __wait_event_freezable(wq, condition)				\
-	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
+#define __wait_event_freezable(wq_head, condition)				\
+	___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0,		\
 			    schedule(); try_to_freeze())
 
 /**
  * wait_event_freezable - sleep (or freeze) until a condition gets true
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  *
  * The process is put to sleep (TASK_INTERRUPTIBLE -- so as not to contribute
  * to system load) until the @condition evaluates to true. The
- * @condition is checked each time the waitqueue @wq is woken up.
+ * @condition is checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
  */
-#define wait_event_freezable(wq, condition)				\
-({									\
-	int __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_freezable(wq, condition);		\
-	__ret;								\
+#define wait_event_freezable(wq_head, condition)				\
+({										\
+	int __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_freezable(wq_head, condition);		\
+	__ret;									\
 })
 
-#define __wait_event_timeout(wq, condition, timeout)			\
-	___wait_event(wq, ___wait_cond_timeout(condition),		\
-		      TASK_UNINTERRUPTIBLE, 0, timeout,			\
+#define __wait_event_timeout(wq_head, condition, timeout)			\
+	___wait_event(wq_head, ___wait_cond_timeout(condition),			\
+		      TASK_UNINTERRUPTIBLE, 0, timeout,				\
 		      __ret = schedule_timeout(__ret))
 
 /**
  * wait_event_timeout - sleep until a condition gets true or a timeout elapses
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @timeout: timeout, in jiffies
  *
  * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
  * @condition evaluates to true. The @condition is checked each time
- * the waitqueue @wq is woken up.
+ * the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
@@ -375,83 +349,83 @@ do {									\
  * or the remaining jiffies (at least 1) if the @condition evaluated
  * to %true before the @timeout elapsed.
  */
-#define wait_event_timeout(wq, condition, timeout)			\
-({									\
-	long __ret = timeout;						\
-	might_sleep();							\
-	if (!___wait_cond_timeout(condition))				\
-		__ret = __wait_event_timeout(wq, condition, timeout);	\
-	__ret;								\
+#define wait_event_timeout(wq_head, condition, timeout)				\
+({										\
+	long __ret = timeout;							\
+	might_sleep();								\
+	if (!___wait_cond_timeout(condition))					\
+		__ret = __wait_event_timeout(wq_head, condition, timeout);	\
+	__ret;									\
 })
 
-#define __wait_event_freezable_timeout(wq, condition, timeout)		\
-	___wait_event(wq, ___wait_cond_timeout(condition),		\
-		      TASK_INTERRUPTIBLE, 0, timeout,			\
+#define __wait_event_freezable_timeout(wq_head, condition, timeout)		\
+	___wait_event(wq_head, ___wait_cond_timeout(condition),			\
+		      TASK_INTERRUPTIBLE, 0, timeout,				\
 		      __ret = schedule_timeout(__ret); try_to_freeze())
 
 /*
  * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid
  * increasing load and is freezable.
  */
-#define wait_event_freezable_timeout(wq, condition, timeout)		\
-({									\
-	long __ret = timeout;						\
-	might_sleep();							\
-	if (!___wait_cond_timeout(condition))				\
-		__ret = __wait_event_freezable_timeout(wq, condition, timeout);	\
-	__ret;								\
+#define wait_event_freezable_timeout(wq_head, condition, timeout)		\
+({										\
+	long __ret = timeout;							\
+	might_sleep();								\
+	if (!___wait_cond_timeout(condition))					\
+		__ret = __wait_event_freezable_timeout(wq_head, condition, timeout); \
+	__ret;									\
 })
 
-#define __wait_event_exclusive_cmd(wq, condition, cmd1, cmd2)		\
-	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 1, 0,	\
+#define __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2)		\
+	(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 1, 0,	\
 			    cmd1; schedule(); cmd2)
 /*
  * Just like wait_event_cmd(), except it sets exclusive flag
  */
-#define wait_event_exclusive_cmd(wq, condition, cmd1, cmd2)		\
-do {									\
-	if (condition)							\
-		break;							\
-	__wait_event_exclusive_cmd(wq, condition, cmd1, cmd2);		\
+#define wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2)		\
+do {										\
+	if (condition)								\
+		break;								\
+	__wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2);		\
 } while (0)
 
-#define __wait_event_cmd(wq, condition, cmd1, cmd2)			\
-	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
+#define __wait_event_cmd(wq_head, condition, cmd1, cmd2)			\
+	(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
 			    cmd1; schedule(); cmd2)
 
 /**
  * wait_event_cmd - sleep until a condition gets true
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @cmd1: the command will be executed before sleep
  * @cmd2: the command will be executed after sleep
  *
  * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
  * @condition evaluates to true. The @condition is checked each time
- * the waitqueue @wq is woken up.
+ * the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
  */
-#define wait_event_cmd(wq, condition, cmd1, cmd2)			\
-do {									\
-	if (condition)							\
-		break;							\
-	__wait_event_cmd(wq, condition, cmd1, cmd2);			\
+#define wait_event_cmd(wq_head, condition, cmd1, cmd2)				\
+do {										\
+	if (condition)								\
+		break;								\
+	__wait_event_cmd(wq_head, condition, cmd1, cmd2);			\
 } while (0)
 
-#define __wait_event_interruptible(wq, condition)			\
-	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
+#define __wait_event_interruptible(wq_head, condition)				\
+	___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0,		\
 		      schedule())
 
 /**
  * wait_event_interruptible - sleep until a condition gets true
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  *
  * The process is put to sleep (TASK_INTERRUPTIBLE) until the
  * @condition evaluates to true or a signal is received.
- * The @condition is checked each time the waitqueue @wq is woken up.
+ * The @condition is checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
@@ -459,29 +433,29 @@ do {									\
  * The function will return -ERESTARTSYS if it was interrupted by a
  * signal and 0 if @condition evaluated to true.
  */
-#define wait_event_interruptible(wq, condition)				\
-({									\
-	int __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_interruptible(wq, condition);	\
-	__ret;								\
+#define wait_event_interruptible(wq_head, condition)				\
+({										\
+	int __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_interruptible(wq_head, condition);		\
+	__ret;									\
 })
 
-#define __wait_event_interruptible_timeout(wq, condition, timeout)	\
-	___wait_event(wq, ___wait_cond_timeout(condition),		\
-		      TASK_INTERRUPTIBLE, 0, timeout,			\
+#define __wait_event_interruptible_timeout(wq_head, condition, timeout)		\
+	___wait_event(wq_head, ___wait_cond_timeout(condition),			\
+		      TASK_INTERRUPTIBLE, 0, timeout,				\
 		      __ret = schedule_timeout(__ret))
 
 /**
  * wait_event_interruptible_timeout - sleep until a condition gets true or a timeout elapses
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @timeout: timeout, in jiffies
  *
  * The process is put to sleep (TASK_INTERRUPTIBLE) until the
  * @condition evaluates to true or a signal is received.
- * The @condition is checked each time the waitqueue @wq is woken up.
+ * The @condition is checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
@@ -493,50 +467,49 @@ do {									\
  * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was
  * interrupted by a signal.
  */
-#define wait_event_interruptible_timeout(wq, condition, timeout)	\
-({									\
-	long __ret = timeout;						\
-	might_sleep();							\
-	if (!___wait_cond_timeout(condition))				\
-		__ret = __wait_event_interruptible_timeout(wq,		\
-						condition, timeout);	\
-	__ret;								\
+#define wait_event_interruptible_timeout(wq_head, condition, timeout)		\
+({										\
+	long __ret = timeout;							\
+	might_sleep();								\
+	if (!___wait_cond_timeout(condition))					\
+		__ret = __wait_event_interruptible_timeout(wq_head,		\
+						condition, timeout);		\
+	__ret;									\
 })
 
-#define __wait_event_hrtimeout(wq, condition, timeout, state)		\
-({									\
-	int __ret = 0;							\
-	struct hrtimer_sleeper __t;					\
-									\
-	hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC,		\
-			      HRTIMER_MODE_REL);			\
-	hrtimer_init_sleeper(&__t, current);				\
-	if ((timeout) != KTIME_MAX)				\
-		hrtimer_start_range_ns(&__t.timer, timeout,		\
-				       current->timer_slack_ns,		\
-				       HRTIMER_MODE_REL);		\
-									\
-	__ret = ___wait_event(wq, condition, state, 0, 0,		\
-		if (!__t.task) {					\
-			__ret = -ETIME;					\
-			break;						\
-		}							\
-		schedule());						\
-									\
-	hrtimer_cancel(&__t.timer);					\
-	destroy_hrtimer_on_stack(&__t.timer);				\
-	__ret;								\
+#define __wait_event_hrtimeout(wq_head, condition, timeout, state)		\
+({										\
+	int __ret = 0;								\
+	struct hrtimer_sleeper __t;						\
+										\
+	hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);	\
+	hrtimer_init_sleeper(&__t, current);					\
+	if ((timeout) != KTIME_MAX)						\
+		hrtimer_start_range_ns(&__t.timer, timeout,			\
+				       current->timer_slack_ns,			\
+				       HRTIMER_MODE_REL);			\
+										\
+	__ret = ___wait_event(wq_head, condition, state, 0, 0,			\
+		if (!__t.task) {						\
+			__ret = -ETIME;						\
+			break;							\
+		}								\
+		schedule());							\
+										\
+	hrtimer_cancel(&__t.timer);						\
+	destroy_hrtimer_on_stack(&__t.timer);					\
+	__ret;									\
 })
 
 /**
  * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @timeout: timeout, as a ktime_t
  *
  * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
  * @condition evaluates to true or a signal is received.
- * The @condition is checked each time the waitqueue @wq is woken up.
+ * The @condition is checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
@@ -544,25 +517,25 @@ do {									\
  * The function returns 0 if @condition became true, or -ETIME if the timeout
  * elapsed.
  */
-#define wait_event_hrtimeout(wq, condition, timeout)			\
-({									\
-	int __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_hrtimeout(wq, condition, timeout,	\
-					       TASK_UNINTERRUPTIBLE);	\
-	__ret;								\
+#define wait_event_hrtimeout(wq_head, condition, timeout)			\
+({										\
+	int __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_hrtimeout(wq_head, condition, timeout,	\
+					       TASK_UNINTERRUPTIBLE);		\
+	__ret;									\
 })
 
 /**
  * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @timeout: timeout, as a ktime_t
  *
  * The process is put to sleep (TASK_INTERRUPTIBLE) until the
  * @condition evaluates to true or a signal is received.
- * The @condition is checked each time the waitqueue @wq is woken up.
+ * The @condition is checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
@@ -570,73 +543,73 @@ do {									\
  * The function returns 0 if @condition became true, -ERESTARTSYS if it was
  * interrupted by a signal, or -ETIME if the timeout elapsed.
  */
-#define wait_event_interruptible_hrtimeout(wq, condition, timeout)	\
-({									\
-	long __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_hrtimeout(wq, condition, timeout,	\
-					       TASK_INTERRUPTIBLE);	\
-	__ret;								\
+#define wait_event_interruptible_hrtimeout(wq, condition, timeout)		\
+({										\
+	long __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_hrtimeout(wq, condition, timeout,		\
+					       TASK_INTERRUPTIBLE);		\
+	__ret;									\
 })
 
-#define __wait_event_interruptible_exclusive(wq, condition)		\
-	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0,		\
+#define __wait_event_interruptible_exclusive(wq, condition)			\
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0,			\
 		      schedule())
 
-#define wait_event_interruptible_exclusive(wq, condition)		\
-({									\
-	int __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_interruptible_exclusive(wq, condition);\
-	__ret;								\
+#define wait_event_interruptible_exclusive(wq, condition)			\
+({										\
+	int __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_interruptible_exclusive(wq, condition);	\
+	__ret;									\
 })
 
-#define __wait_event_killable_exclusive(wq, condition)			\
-	___wait_event(wq, condition, TASK_KILLABLE, 1, 0,		\
+#define __wait_event_killable_exclusive(wq, condition)				\
+	___wait_event(wq, condition, TASK_KILLABLE, 1, 0,			\
 		      schedule())
 
-#define wait_event_killable_exclusive(wq, condition)			\
-({									\
-	int __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_killable_exclusive(wq, condition);	\
-	__ret;								\
+#define wait_event_killable_exclusive(wq, condition)				\
+({										\
+	int __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_killable_exclusive(wq, condition);		\
+	__ret;									\
 })
 
 
-#define __wait_event_freezable_exclusive(wq, condition)			\
-	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0,		\
+#define __wait_event_freezable_exclusive(wq, condition)				\
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0,			\
 			schedule(); try_to_freeze())
 
-#define wait_event_freezable_exclusive(wq, condition)			\
-({									\
-	int __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_freezable_exclusive(wq, condition);\
-	__ret;								\
+#define wait_event_freezable_exclusive(wq, condition)				\
+({										\
+	int __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_freezable_exclusive(wq, condition);	\
+	__ret;									\
 })
 
-extern int do_wait_intr(wait_queue_head_t *, wait_queue_t *);
-extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *);
-
-#define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \
-({									\
-	int __ret;							\
-	DEFINE_WAIT(__wait);						\
-	if (exclusive)							\
-		__wait.flags |= WQ_FLAG_EXCLUSIVE;			\
-	do {								\
-		__ret = fn(&(wq), &__wait);				\
-		if (__ret)						\
-			break;						\
-	} while (!(condition));						\
-	__remove_wait_queue(&(wq), &__wait);				\
-	__set_current_state(TASK_RUNNING);				\
-	__ret;								\
+extern int do_wait_intr(wait_queue_head_t *, wait_queue_entry_t *);
+extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *);
+
+#define __wait_event_interruptible_locked(wq, condition, exclusive, fn)		\
+({										\
+	int __ret;								\
+	DEFINE_WAIT(__wait);							\
+	if (exclusive)								\
+		__wait.flags |= WQ_FLAG_EXCLUSIVE;				\
+	do {									\
+		__ret = fn(&(wq), &__wait);					\
+		if (__ret)							\
+			break;							\
+	} while (!(condition));							\
+	__remove_wait_queue(&(wq), &__wait);					\
+	__set_current_state(TASK_RUNNING);					\
+	__ret;									\
 })
 
 
@@ -663,8 +636,8 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *);
  * The function will return -ERESTARTSYS if it was interrupted by a
  * signal and 0 if @condition evaluated to true.
  */
-#define wait_event_interruptible_locked(wq, condition)			\
-	((condition)							\
+#define wait_event_interruptible_locked(wq, condition)				\
+	((condition)								\
 	 ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr))
 
 /**
@@ -690,8 +663,8 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *);
  * The function will return -ERESTARTSYS if it was interrupted by a
  * signal and 0 if @condition evaluated to true.
  */
-#define wait_event_interruptible_locked_irq(wq, condition)		\
-	((condition)							\
+#define wait_event_interruptible_locked_irq(wq, condition)			\
+	((condition)								\
 	 ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq))
 
 /**
@@ -721,8 +694,8 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *);
  * The function will return -ERESTARTSYS if it was interrupted by a
  * signal and 0 if @condition evaluated to true.
  */
-#define wait_event_interruptible_exclusive_locked(wq, condition)	\
-	((condition)							\
+#define wait_event_interruptible_exclusive_locked(wq, condition)		\
+	((condition)								\
 	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr))
 
 /**
@@ -752,12 +725,12 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *);
  * The function will return -ERESTARTSYS if it was interrupted by a
  * signal and 0 if @condition evaluated to true.
  */
-#define wait_event_interruptible_exclusive_locked_irq(wq, condition)	\
-	((condition)							\
+#define wait_event_interruptible_exclusive_locked_irq(wq, condition)		\
+	((condition)								\
 	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq))
 
 
-#define __wait_event_killable(wq, condition)				\
+#define __wait_event_killable(wq, condition)					\
 	___wait_event(wq, condition, TASK_KILLABLE, 0, 0, schedule())
 
 /**
@@ -775,21 +748,21 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *);
  * The function will return -ERESTARTSYS if it was interrupted by a
  * signal and 0 if @condition evaluated to true.
  */
-#define wait_event_killable(wq, condition)				\
-({									\
-	int __ret = 0;							\
-	might_sleep();							\
-	if (!(condition))						\
-		__ret = __wait_event_killable(wq, condition);		\
-	__ret;								\
+#define wait_event_killable(wq_head, condition)					\
+({										\
+	int __ret = 0;								\
+	might_sleep();								\
+	if (!(condition))							\
+		__ret = __wait_event_killable(wq_head, condition);		\
+	__ret;									\
 })
 
 
-#define __wait_event_lock_irq(wq, condition, lock, cmd)			\
-	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
-			    spin_unlock_irq(&lock);			\
-			    cmd;					\
-			    schedule();					\
+#define __wait_event_lock_irq(wq_head, condition, lock, cmd)			\
+	(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
+			    spin_unlock_irq(&lock);				\
+			    cmd;						\
+			    schedule();						\
 			    spin_lock_irq(&lock))
 
 /**
@@ -797,7 +770,7 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *);
  *			     condition is checked under the lock. This
  *			     is expected to be called with the lock
  *			     taken.
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @lock: a locked spinlock_t, which will be released before cmd
  *	  and schedule() and reacquired afterwards.
@@ -806,7 +779,7 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *);
  *
  * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
  * @condition evaluates to true. The @condition is checked each time
- * the waitqueue @wq is woken up.
+ * the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
@@ -815,11 +788,11 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_t *);
  * dropped before invoking the cmd and going to sleep and is reacquired
  * afterwards.
  */
-#define wait_event_lock_irq_cmd(wq, condition, lock, cmd)		\
-do {									\
-	if (condition)							\
-		break;							\
-	__wait_event_lock_irq(wq, condition, lock, cmd);		\
+#define wait_event_lock_irq_cmd(wq_head, condition, lock, cmd)			\
+do {										\
+	if (condition)								\
+		break;								\
+	__wait_event_lock_irq(wq_head, condition, lock, cmd);			\
 } while (0)
 
 /**
@@ -827,14 +800,14 @@ do {									\
  *			 condition is checked under the lock. This
  *			 is expected to be called with the lock
  *			 taken.
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @lock: a locked spinlock_t, which will be released before schedule()
  *	  and reacquired afterwards.
  *
  * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
  * @condition evaluates to true. The @condition is checked each time
- * the waitqueue @wq is woken up.
+ * the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
@@ -842,26 +815,26 @@ do {									\
  * This is supposed to be called while holding the lock. The lock is
  * dropped before going to sleep and is reacquired afterwards.
  */
-#define wait_event_lock_irq(wq, condition, lock)			\
-do {									\
-	if (condition)							\
-		break;							\
-	__wait_event_lock_irq(wq, condition, lock, );			\
+#define wait_event_lock_irq(wq_head, condition, lock)				\
+do {										\
+	if (condition)								\
+		break;								\
+	__wait_event_lock_irq(wq_head, condition, lock, );			\
 } while (0)
 
 
-#define __wait_event_interruptible_lock_irq(wq, condition, lock, cmd)	\
-	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
-		      spin_unlock_irq(&lock);				\
-		      cmd;						\
-		      schedule();					\
+#define __wait_event_interruptible_lock_irq(wq_head, condition, lock, cmd)	\
+	___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0,		\
+		      spin_unlock_irq(&lock);					\
+		      cmd;							\
+		      schedule();						\
 		      spin_lock_irq(&lock))
 
 /**
  * wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true.
  *		The condition is checked under the lock. This is expected to
  *		be called with the lock taken.
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @lock: a locked spinlock_t, which will be released before cmd and
  *	  schedule() and reacquired afterwards.
@@ -870,7 +843,7 @@ do {									\
  *
  * The process is put to sleep (TASK_INTERRUPTIBLE) until the
  * @condition evaluates to true or a signal is received. The @condition is
- * checked each time the waitqueue @wq is woken up.
+ * checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
@@ -882,27 +855,27 @@ do {									\
  * The macro will return -ERESTARTSYS if it was interrupted by a signal
  * and 0 if @condition evaluated to true.
  */
-#define wait_event_interruptible_lock_irq_cmd(wq, condition, lock, cmd)	\
-({									\
-	int __ret = 0;							\
-	if (!(condition))						\
-		__ret = __wait_event_interruptible_lock_irq(wq,		\
-						condition, lock, cmd);	\
-	__ret;								\
+#define wait_event_interruptible_lock_irq_cmd(wq_head, condition, lock, cmd)	\
+({										\
+	int __ret = 0;								\
+	if (!(condition))							\
+		__ret = __wait_event_interruptible_lock_irq(wq_head,		\
+						condition, lock, cmd);		\
+	__ret;									\
 })
 
 /**
  * wait_event_interruptible_lock_irq - sleep until a condition gets true.
  *		The condition is checked under the lock. This is expected
  *		to be called with the lock taken.
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @lock: a locked spinlock_t, which will be released before schedule()
  *	  and reacquired afterwards.
  *
  * The process is put to sleep (TASK_INTERRUPTIBLE) until the
  * @condition evaluates to true or signal is received. The @condition is
- * checked each time the waitqueue @wq is woken up.
+ * checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
@@ -913,28 +886,28 @@ do {									\
  * The macro will return -ERESTARTSYS if it was interrupted by a signal
  * and 0 if @condition evaluated to true.
  */
-#define wait_event_interruptible_lock_irq(wq, condition, lock)		\
-({									\
-	int __ret = 0;							\
-	if (!(condition))						\
-		__ret = __wait_event_interruptible_lock_irq(wq,		\
-						condition, lock,);	\
-	__ret;								\
+#define wait_event_interruptible_lock_irq(wq_head, condition, lock)		\
+({										\
+	int __ret = 0;								\
+	if (!(condition))							\
+		__ret = __wait_event_interruptible_lock_irq(wq_head,		\
+						condition, lock,);		\
+	__ret;									\
 })
 
-#define __wait_event_interruptible_lock_irq_timeout(wq, condition,	\
-						    lock, timeout)	\
-	___wait_event(wq, ___wait_cond_timeout(condition),		\
-		      TASK_INTERRUPTIBLE, 0, timeout,			\
-		      spin_unlock_irq(&lock);				\
-		      __ret = schedule_timeout(__ret);			\
+#define __wait_event_interruptible_lock_irq_timeout(wq_head, condition,		\
+						    lock, timeout)		\
+	___wait_event(wq_head, ___wait_cond_timeout(condition),			\
+		      TASK_INTERRUPTIBLE, 0, timeout,				\
+		      spin_unlock_irq(&lock);					\
+		      __ret = schedule_timeout(__ret);				\
 		      spin_lock_irq(&lock));
 
 /**
  * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets
  *		true or a timeout elapses. The condition is checked under
  *		the lock. This is expected to be called with the lock taken.
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @lock: a locked spinlock_t, which will be released before schedule()
  *	  and reacquired afterwards.
@@ -942,7 +915,7 @@ do {									\
  *
  * The process is put to sleep (TASK_INTERRUPTIBLE) until the
  * @condition evaluates to true or signal is received. The @condition is
- * checked each time the waitqueue @wq is woken up.
+ * checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
@@ -954,263 +927,42 @@ do {									\
  * was interrupted by a signal, and the remaining jiffies otherwise
  * if the condition evaluated to true before the timeout elapsed.
  */
-#define wait_event_interruptible_lock_irq_timeout(wq, condition, lock,	\
-						  timeout)		\
-({									\
-	long __ret = timeout;						\
-	if (!___wait_cond_timeout(condition))				\
-		__ret = __wait_event_interruptible_lock_irq_timeout(	\
-					wq, condition, lock, timeout);	\
-	__ret;								\
+#define wait_event_interruptible_lock_irq_timeout(wq_head, condition, lock,	\
+						  timeout)			\
+({										\
+	long __ret = timeout;							\
+	if (!___wait_cond_timeout(condition))					\
+		__ret = __wait_event_interruptible_lock_irq_timeout(		\
+					wq_head, condition, lock, timeout);	\
+	__ret;									\
 })
 
 /*
  * Waitqueues which are removed from the waitqueue_head at wakeup time
  */
-void prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state);
-void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state);
-long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state);
-void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
-long wait_woken(wait_queue_t *wait, unsigned mode, long timeout);
-int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
-int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
-int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
-
-#define DEFINE_WAIT_FUNC(name, function)				\
-	wait_queue_t name = {						\
-		.private	= current,				\
-		.func		= function,				\
-		.task_list	= LIST_HEAD_INIT((name).task_list),	\
+void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
+void prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
+long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
+void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
+long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout);
+int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key);
+int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key);
+
+#define DEFINE_WAIT_FUNC(name, function)					\
+	struct wait_queue_entry name = {					\
+		.private	= current,					\
+		.func		= function,					\
+		.entry		= LIST_HEAD_INIT((name).entry),			\
 	}
 
 #define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function)
 
-#define DEFINE_WAIT_BIT(name, word, bit)				\
-	struct wait_bit_queue name = {					\
-		.key = __WAIT_BIT_KEY_INITIALIZER(word, bit),		\
-		.wait	= {						\
-			.private	= current,			\
-			.func		= wake_bit_function,		\
-			.task_list	=				\
-				LIST_HEAD_INIT((name).wait.task_list),	\
-		},							\
-	}
-
-#define init_wait(wait)							\
-	do {								\
-		(wait)->private = current;				\
-		(wait)->func = autoremove_wake_function;		\
-		INIT_LIST_HEAD(&(wait)->task_list);			\
-		(wait)->flags = 0;					\
+#define init_wait(wait)								\
+	do {									\
+		(wait)->private = current;					\
+		(wait)->func = autoremove_wake_function;			\
+		INIT_LIST_HEAD(&(wait)->entry);					\
+		(wait)->flags = 0;						\
 	} while (0)
 
-
-extern int bit_wait(struct wait_bit_key *, int);
-extern int bit_wait_io(struct wait_bit_key *, int);
-extern int bit_wait_timeout(struct wait_bit_key *, int);
-extern int bit_wait_io_timeout(struct wait_bit_key *, int);
-
-/**
- * wait_on_bit - wait for a bit to be cleared
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- * @mode: the task state to sleep in
- *
- * There is a standard hashed waitqueue table for generic use. This
- * is the part of the hashtable's accessor API that waits on a bit.
- * For instance, if one were to have waiters on a bitflag, one would
- * call wait_on_bit() in threads waiting for the bit to clear.
- * One uses wait_on_bit() where one is waiting for the bit to clear,
- * but has no intention of setting it.
- * Returned value will be zero if the bit was cleared, or non-zero
- * if the process received a signal and the mode permitted wakeup
- * on that signal.
- */
-static inline int
-wait_on_bit(unsigned long *word, int bit, unsigned mode)
-{
-	might_sleep();
-	if (!test_bit(bit, word))
-		return 0;
-	return out_of_line_wait_on_bit(word, bit,
-				       bit_wait,
-				       mode);
-}
-
-/**
- * wait_on_bit_io - wait for a bit to be cleared
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- * @mode: the task state to sleep in
- *
- * Use the standard hashed waitqueue table to wait for a bit
- * to be cleared.  This is similar to wait_on_bit(), but calls
- * io_schedule() instead of schedule() for the actual waiting.
- *
- * Returned value will be zero if the bit was cleared, or non-zero
- * if the process received a signal and the mode permitted wakeup
- * on that signal.
- */
-static inline int
-wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
-{
-	might_sleep();
-	if (!test_bit(bit, word))
-		return 0;
-	return out_of_line_wait_on_bit(word, bit,
-				       bit_wait_io,
-				       mode);
-}
-
-/**
- * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- * @mode: the task state to sleep in
- * @timeout: timeout, in jiffies
- *
- * Use the standard hashed waitqueue table to wait for a bit
- * to be cleared. This is similar to wait_on_bit(), except also takes a
- * timeout parameter.
- *
- * Returned value will be zero if the bit was cleared before the
- * @timeout elapsed, or non-zero if the @timeout elapsed or process
- * received a signal and the mode permitted wakeup on that signal.
- */
-static inline int
-wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode,
-		    unsigned long timeout)
-{
-	might_sleep();
-	if (!test_bit(bit, word))
-		return 0;
-	return out_of_line_wait_on_bit_timeout(word, bit,
-					       bit_wait_timeout,
-					       mode, timeout);
-}
-
-/**
- * wait_on_bit_action - wait for a bit to be cleared
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- * @action: the function used to sleep, which may take special actions
- * @mode: the task state to sleep in
- *
- * Use the standard hashed waitqueue table to wait for a bit
- * to be cleared, and allow the waiting action to be specified.
- * This is like wait_on_bit() but allows fine control of how the waiting
- * is done.
- *
- * Returned value will be zero if the bit was cleared, or non-zero
- * if the process received a signal and the mode permitted wakeup
- * on that signal.
- */
-static inline int
-wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action,
-		   unsigned mode)
-{
-	might_sleep();
-	if (!test_bit(bit, word))
-		return 0;
-	return out_of_line_wait_on_bit(word, bit, action, mode);
-}
-
-/**
- * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- * @mode: the task state to sleep in
- *
- * There is a standard hashed waitqueue table for generic use. This
- * is the part of the hashtable's accessor API that waits on a bit
- * when one intends to set it, for instance, trying to lock bitflags.
- * For instance, if one were to have waiters trying to set bitflag
- * and waiting for it to clear before setting it, one would call
- * wait_on_bit() in threads waiting to be able to set the bit.
- * One uses wait_on_bit_lock() where one is waiting for the bit to
- * clear with the intention of setting it, and when done, clearing it.
- *
- * Returns zero if the bit was (eventually) found to be clear and was
- * set.  Returns non-zero if a signal was delivered to the process and
- * the @mode allows that signal to wake the process.
- */
-static inline int
-wait_on_bit_lock(unsigned long *word, int bit, unsigned mode)
-{
-	might_sleep();
-	if (!test_and_set_bit(bit, word))
-		return 0;
-	return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode);
-}
-
-/**
- * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- * @mode: the task state to sleep in
- *
- * Use the standard hashed waitqueue table to wait for a bit
- * to be cleared and then to atomically set it.  This is similar
- * to wait_on_bit(), but calls io_schedule() instead of schedule()
- * for the actual waiting.
- *
- * Returns zero if the bit was (eventually) found to be clear and was
- * set.  Returns non-zero if a signal was delivered to the process and
- * the @mode allows that signal to wake the process.
- */
-static inline int
-wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode)
-{
-	might_sleep();
-	if (!test_and_set_bit(bit, word))
-		return 0;
-	return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode);
-}
-
-/**
- * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- * @action: the function used to sleep, which may take special actions
- * @mode: the task state to sleep in
- *
- * Use the standard hashed waitqueue table to wait for a bit
- * to be cleared and then to set it, and allow the waiting action
- * to be specified.
- * This is like wait_on_bit() but allows fine control of how the waiting
- * is done.
- *
- * Returns zero if the bit was (eventually) found to be clear and was
- * set.  Returns non-zero if a signal was delivered to the process and
- * the @mode allows that signal to wake the process.
- */
-static inline int
-wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action,
-			unsigned mode)
-{
-	might_sleep();
-	if (!test_and_set_bit(bit, word))
-		return 0;
-	return out_of_line_wait_on_bit_lock(word, bit, action, mode);
-}
-
-/**
- * wait_on_atomic_t - Wait for an atomic_t to become 0
- * @val: The atomic value being waited on, a kernel virtual address
- * @action: the function used to sleep, which may take special actions
- * @mode: the task state to sleep in
- *
- * Wait for an atomic_t to become 0.  We abuse the bit-wait waitqueue table for
- * the purpose of getting a waitqueue, but we set the key to a bit number
- * outside of the target 'word'.
- */
-static inline
-int wait_on_atomic_t(atomic_t *val, int (*action)(atomic_t *), unsigned mode)
-{
-	might_sleep();
-	if (atomic_read(val) == 0)
-		return 0;
-	return out_of_line_wait_on_atomic_t(val, action, mode);
-}
-
 #endif /* _LINUX_WAIT_H */
diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h
new file mode 100644
index 000000000000..12b26660d7e9
--- /dev/null
+++ b/include/linux/wait_bit.h
@@ -0,0 +1,261 @@
+#ifndef _LINUX_WAIT_BIT_H
+#define _LINUX_WAIT_BIT_H
+
+/*
+ * Linux wait-bit related types and methods:
+ */
+#include <linux/wait.h>
+
+struct wait_bit_key {
+	void			*flags;
+	int			bit_nr;
+#define WAIT_ATOMIC_T_BIT_NR	-1
+	unsigned long		timeout;
+};
+
+struct wait_bit_queue_entry {
+	struct wait_bit_key	key;
+	struct wait_queue_entry	wq_entry;
+};
+
+#define __WAIT_BIT_KEY_INITIALIZER(word, bit)					\
+	{ .flags = word, .bit_nr = bit, }
+
+#define __WAIT_ATOMIC_T_KEY_INITIALIZER(p)					\
+	{ .flags = p, .bit_nr = WAIT_ATOMIC_T_BIT_NR, }
+
+typedef int wait_bit_action_f(struct wait_bit_key *key, int mode);
+void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit);
+int __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode);
+int __wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode);
+void wake_up_bit(void *word, int bit);
+void wake_up_atomic_t(atomic_t *p);
+int out_of_line_wait_on_bit(void *word, int, wait_bit_action_f *action, unsigned int mode);
+int out_of_line_wait_on_bit_timeout(void *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout);
+int out_of_line_wait_on_bit_lock(void *word, int, wait_bit_action_f *action, unsigned int mode);
+int out_of_line_wait_on_atomic_t(atomic_t *p, int (*)(atomic_t *), unsigned int mode);
+struct wait_queue_head *bit_waitqueue(void *word, int bit);
+extern void __init wait_bit_init(void);
+
+int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key);
+
+#define DEFINE_WAIT_BIT(name, word, bit)					\
+	struct wait_bit_queue_entry name = {					\
+		.key = __WAIT_BIT_KEY_INITIALIZER(word, bit),			\
+		.wq_entry = {							\
+			.private	= current,				\
+			.func		= wake_bit_function,			\
+			.entry		=					\
+				LIST_HEAD_INIT((name).wq_entry.entry),		\
+		},								\
+	}
+
+extern int bit_wait(struct wait_bit_key *key, int bit);
+extern int bit_wait_io(struct wait_bit_key *key, int bit);
+extern int bit_wait_timeout(struct wait_bit_key *key, int bit);
+extern int bit_wait_io_timeout(struct wait_bit_key *key, int bit);
+
+/**
+ * wait_on_bit - wait for a bit to be cleared
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ *
+ * There is a standard hashed waitqueue table for generic use. This
+ * is the part of the hashtable's accessor API that waits on a bit.
+ * For instance, if one were to have waiters on a bitflag, one would
+ * call wait_on_bit() in threads waiting for the bit to clear.
+ * One uses wait_on_bit() where one is waiting for the bit to clear,
+ * but has no intention of setting it.
+ * Returned value will be zero if the bit was cleared, or non-zero
+ * if the process received a signal and the mode permitted wakeup
+ * on that signal.
+ */
+static inline int
+wait_on_bit(unsigned long *word, int bit, unsigned mode)
+{
+	might_sleep();
+	if (!test_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit(word, bit,
+				       bit_wait,
+				       mode);
+}
+
+/**
+ * wait_on_bit_io - wait for a bit to be cleared
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared.  This is similar to wait_on_bit(), but calls
+ * io_schedule() instead of schedule() for the actual waiting.
+ *
+ * Returned value will be zero if the bit was cleared, or non-zero
+ * if the process received a signal and the mode permitted wakeup
+ * on that signal.
+ */
+static inline int
+wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
+{
+	might_sleep();
+	if (!test_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit(word, bit,
+				       bit_wait_io,
+				       mode);
+}
+
+/**
+ * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ * @timeout: timeout, in jiffies
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared. This is similar to wait_on_bit(), except also takes a
+ * timeout parameter.
+ *
+ * Returned value will be zero if the bit was cleared before the
+ * @timeout elapsed, or non-zero if the @timeout elapsed or process
+ * received a signal and the mode permitted wakeup on that signal.
+ */
+static inline int
+wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode,
+		    unsigned long timeout)
+{
+	might_sleep();
+	if (!test_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit_timeout(word, bit,
+					       bit_wait_timeout,
+					       mode, timeout);
+}
+
+/**
+ * wait_on_bit_action - wait for a bit to be cleared
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @action: the function used to sleep, which may take special actions
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared, and allow the waiting action to be specified.
+ * This is like wait_on_bit() but allows fine control of how the waiting
+ * is done.
+ *
+ * Returned value will be zero if the bit was cleared, or non-zero
+ * if the process received a signal and the mode permitted wakeup
+ * on that signal.
+ */
+static inline int
+wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action,
+		   unsigned mode)
+{
+	might_sleep();
+	if (!test_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit(word, bit, action, mode);
+}
+
+/**
+ * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ *
+ * There is a standard hashed waitqueue table for generic use. This
+ * is the part of the hashtable's accessor API that waits on a bit
+ * when one intends to set it, for instance, trying to lock bitflags.
+ * For instance, if one were to have waiters trying to set bitflag
+ * and waiting for it to clear before setting it, one would call
+ * wait_on_bit() in threads waiting to be able to set the bit.
+ * One uses wait_on_bit_lock() where one is waiting for the bit to
+ * clear with the intention of setting it, and when done, clearing it.
+ *
+ * Returns zero if the bit was (eventually) found to be clear and was
+ * set.  Returns non-zero if a signal was delivered to the process and
+ * the @mode allows that signal to wake the process.
+ */
+static inline int
+wait_on_bit_lock(unsigned long *word, int bit, unsigned mode)
+{
+	might_sleep();
+	if (!test_and_set_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode);
+}
+
+/**
+ * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared and then to atomically set it.  This is similar
+ * to wait_on_bit(), but calls io_schedule() instead of schedule()
+ * for the actual waiting.
+ *
+ * Returns zero if the bit was (eventually) found to be clear and was
+ * set.  Returns non-zero if a signal was delivered to the process and
+ * the @mode allows that signal to wake the process.
+ */
+static inline int
+wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode)
+{
+	might_sleep();
+	if (!test_and_set_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode);
+}
+
+/**
+ * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @action: the function used to sleep, which may take special actions
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared and then to set it, and allow the waiting action
+ * to be specified.
+ * This is like wait_on_bit() but allows fine control of how the waiting
+ * is done.
+ *
+ * Returns zero if the bit was (eventually) found to be clear and was
+ * set.  Returns non-zero if a signal was delivered to the process and
+ * the @mode allows that signal to wake the process.
+ */
+static inline int
+wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action,
+			unsigned mode)
+{
+	might_sleep();
+	if (!test_and_set_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit_lock(word, bit, action, mode);
+}
+
+/**
+ * wait_on_atomic_t - Wait for an atomic_t to become 0
+ * @val: The atomic value being waited on, a kernel virtual address
+ * @action: the function used to sleep, which may take special actions
+ * @mode: the task state to sleep in
+ *
+ * Wait for an atomic_t to become 0.  We abuse the bit-wait waitqueue table for
+ * the purpose of getting a waitqueue, but we set the key to a bit number
+ * outside of the target 'word'.
+ */
+static inline
+int wait_on_atomic_t(atomic_t *val, int (*action)(atomic_t *), unsigned mode)
+{
+	might_sleep();
+	if (atomic_read(val) == 0)
+		return 0;
+	return out_of_line_wait_on_atomic_t(val, action, mode);
+}
+
+#endif /* _LINUX_WAIT_BIT_H */
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index fd60eccb59a6..75e612a45824 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -62,7 +62,7 @@ struct unix_sock {
 #define UNIX_GC_CANDIDATE	0
 #define UNIX_GC_MAYBE_CYCLE	1
 	struct socket_wq	peer_wq;
-	wait_queue_t		peer_wake;
+	wait_queue_entry_t		peer_wake;
 };
 
 static inline struct unix_sock *unix_sk(const struct sock *sk)
diff --git a/include/uapi/linux/auto_fs.h b/include/uapi/linux/auto_fs.h
index aa63451ef20a..1953f8d6063b 100644
--- a/include/uapi/linux/auto_fs.h
+++ b/include/uapi/linux/auto_fs.h
@@ -26,7 +26,7 @@
 #define AUTOFS_MIN_PROTO_VERSION	AUTOFS_PROTO_VERSION
 
 /*
- * The wait_queue_token (autofs_wqt_t) is part of a structure which is passed
+ * The wait_queue_entry_token (autofs_wqt_t) is part of a structure which is passed
  * back to the kernel via ioctl from userspace. On architectures where 32- and
  * 64-bit userspace binaries can be executed it's important that the size of
  * autofs_wqt_t stays constant between 32- and 64-bit Linux kernels so that we
@@ -49,7 +49,7 @@ struct autofs_packet_hdr {
 
 struct autofs_packet_missing {
 	struct autofs_packet_hdr hdr;
-	autofs_wqt_t wait_queue_token;
+	autofs_wqt_t wait_queue_entry_token;
 	int len;
 	char name[NAME_MAX+1];
 };	
diff --git a/include/uapi/linux/auto_fs4.h b/include/uapi/linux/auto_fs4.h
index 7c6da423d54e..65b72d0222e7 100644
--- a/include/uapi/linux/auto_fs4.h
+++ b/include/uapi/linux/auto_fs4.h
@@ -108,7 +108,7 @@ enum autofs_notify {
 /* v4 multi expire (via pipe) */
 struct autofs_packet_expire_multi {
 	struct autofs_packet_hdr hdr;
-	autofs_wqt_t wait_queue_token;
+	autofs_wqt_t wait_queue_entry_token;
 	int len;
 	char name[NAME_MAX+1];
 };
@@ -123,7 +123,7 @@ union autofs_packet_union {
 /* autofs v5 common packet struct */
 struct autofs_v5_packet {
 	struct autofs_packet_hdr hdr;
-	autofs_wqt_t wait_queue_token;
+	autofs_wqt_t wait_queue_entry_token;
 	__u32 dev;
 	__u64 ino;
 	__u32 uid;
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 5f0fe019a720..e2a6c7b3510b 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -47,5 +47,6 @@
  * For the sched_{set,get}attr() calls
  */
 #define SCHED_FLAG_RESET_ON_FORK	0x01
+#define SCHED_FLAG_RECLAIM		0x02
 
 #endif /* _UAPI_LINUX_SCHED_H */