sched/wait: Split out the wait_bit*() APIs from <linux/wait.h> into <linux/wait_bit.h>

The wait_bit*() types and APIs are mixed into wait.h, but they
are a pretty orthogonal extension of wait-queues.

Furthermore, only about 50 kernel files use these APIs, while
over 1000 use the regular wait-queue functionality.

So clean up the main wait.h by moving the wait-bit functionality
out of it, into a separate .h and .c file:

  include/linux/wait_bit.h  for types and APIs
  kernel/sched/wait_bit.c   for the implementation

Update all header dependencies.

This reduces the size of wait.h rather significantly, by about 30%.

Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

fs/cachefiles/internal.h

@@ -18,7 +18,7 @@
 
 #include <linux/fscache-cache.h>
 #include <linux/timer.h>
-#include <linux/wait.h>
+#include <linux/wait_bit.h>
 #include <linux/cred.h>
 #include <linux/workqueue.h>
 #include <linux/security.h>

fs/cifs/inode.c

@@ -24,6 +24,7 @@
 #include <linux/pagemap.h>
 #include <linux/freezer.h>
 #include <linux/sched/signal.h>
+#include <linux/wait_bit.h>
 
 #include <asm/div64.h>
 #include "cifsfs.h"

fs/nfs/internal.h

@@ -7,6 +7,7 @@
 #include <linux/security.h>
 #include <linux/crc32.h>
 #include <linux/nfs_page.h>
+#include <linux/wait_bit.h>
 
 #define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
 

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>

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>
 

include/linux/wait_bit.h

+#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);
+
+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,			\
+			.task_list	=					\
+				LIST_HEAD_INIT((name).wq_entry.task_list),	\
+		},								\
+	}
+
+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 */

kernel/sched/Makefile

@@ -17,7 +17,7 @@ endif
 
 obj-y += core.o loadavg.o clock.o cputime.o
 obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
-obj-y += wait.o swait.o completion.o idle.o
+obj-y += wait.o wait_bit.o swait.o completion.o idle.o
 obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o

kernel/sched/wait.c

@@ -390,260 +390,3 @@ int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sy
 	return default_wake_function(wq_entry, mode, sync, key);
 }
 EXPORT_SYMBOL(woken_wake_function);
-
-int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *arg)
-{
-	struct wait_bit_key *key = arg;
-	struct wait_bit_queue_entry *wait_bit = container_of(wq_entry, struct wait_bit_queue_entry, wq_entry);
-
-	if (wait_bit->key.flags != key->flags ||
-			wait_bit->key.bit_nr != key->bit_nr ||
-			test_bit(key->bit_nr, key->flags))
-		return 0;
-	else
-		return autoremove_wake_function(wq_entry, mode, sync, key);
-}
-EXPORT_SYMBOL(wake_bit_function);
-
-/*
- * To allow interruptible waiting and asynchronous (i.e. nonblocking)
- * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are
- * permitted return codes. Nonzero return codes halt waiting and return.
- */
-int __sched
-__wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry,
-	      wait_bit_action_f *action, unsigned mode)
-{
-	int ret = 0;
-
-	do {
-		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
-		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
-			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
-	finish_wait(wq_head, &wbq_entry->wq_entry);
-	return ret;
-}
-EXPORT_SYMBOL(__wait_on_bit);
-
-int __sched out_of_line_wait_on_bit(void *word, int bit,
-				    wait_bit_action_f *action, unsigned mode)
-{
-	struct wait_queue_head *wq_head = bit_waitqueue(word, bit);
-	DEFINE_WAIT_BIT(wq_entry, word, bit);
-
-	return __wait_on_bit(wq_head, &wq_entry, action, mode);
-}
-EXPORT_SYMBOL(out_of_line_wait_on_bit);
-
-int __sched out_of_line_wait_on_bit_timeout(
-	void *word, int bit, wait_bit_action_f *action,
-	unsigned mode, unsigned long timeout)
-{
-	struct wait_queue_head *wq_head = bit_waitqueue(word, bit);
-	DEFINE_WAIT_BIT(wq_entry, word, bit);
-
-	wq_entry.key.timeout = jiffies + timeout;
-	return __wait_on_bit(wq_head, &wq_entry, action, mode);
-}
-EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout);
-
-int __sched
-__wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry,
-			wait_bit_action_f *action, unsigned mode)
-{
-	int ret = 0;
-
-	for (;;) {
-		prepare_to_wait_exclusive(wq_head, &wbq_entry->wq_entry, mode);
-		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) {
-			ret = action(&wbq_entry->key, mode);
-			/*
-			 * See the comment in prepare_to_wait_event().
-			 * finish_wait() does not necessarily takes wwq_head->lock,
-			 * but test_and_set_bit() implies mb() which pairs with
-			 * smp_mb__after_atomic() before wake_up_page().
-			 */
-			if (ret)
-				finish_wait(wq_head, &wbq_entry->wq_entry);
-		}
-		if (!test_and_set_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) {
-			if (!ret)
-				finish_wait(wq_head, &wbq_entry->wq_entry);
-			return 0;
-		} else if (ret) {
-			return ret;
-		}
-	}
-}
-EXPORT_SYMBOL(__wait_on_bit_lock);
-
-int __sched out_of_line_wait_on_bit_lock(void *word, int bit,
-					 wait_bit_action_f *action, unsigned mode)
-{
-	struct wait_queue_head *wq_head = bit_waitqueue(word, bit);
-	DEFINE_WAIT_BIT(wq_entry, word, bit);
-
-	return __wait_on_bit_lock(wq_head, &wq_entry, action, mode);
-}
-EXPORT_SYMBOL(out_of_line_wait_on_bit_lock);
-
-void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit)
-{
-	struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit);
-	if (waitqueue_active(wq_head))
-		__wake_up(wq_head, TASK_NORMAL, 1, &key);
-}
-EXPORT_SYMBOL(__wake_up_bit);
-
-/**
- * wake_up_bit - wake up a waiter on a bit
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- *
- * There is a standard hashed waitqueue table for generic use. This
- * is the part of the hashtable's accessor API that wakes up waiters
- * on a bit. For instance, if one were to have waiters on a bitflag,
- * one would call wake_up_bit() after clearing the bit.
- *
- * In order for this to function properly, as it uses waitqueue_active()
- * internally, some kind of memory barrier must be done prior to calling
- * this. Typically, this will be smp_mb__after_atomic(), but in some
- * cases where bitflags are manipulated non-atomically under a lock, one
- * may need to use a less regular barrier, such fs/inode.c's smp_mb(),
- * because spin_unlock() does not guarantee a memory barrier.
- */
-void wake_up_bit(void *word, int bit)
-{
-	__wake_up_bit(bit_waitqueue(word, bit), word, bit);
-}
-EXPORT_SYMBOL(wake_up_bit);
-
-/*
- * Manipulate the atomic_t address to produce a better bit waitqueue table hash
- * index (we're keying off bit -1, but that would produce a horrible hash
- * value).
- */
-static inline wait_queue_head_t *atomic_t_waitqueue(atomic_t *p)
-{
-	if (BITS_PER_LONG == 64) {
-		unsigned long q = (unsigned long)p;
-		return bit_waitqueue((void *)(q & ~1), q & 1);
-	}
-	return bit_waitqueue(p, 0);
-}
-
-static int wake_atomic_t_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync,
-				  void *arg)
-{
-	struct wait_bit_key *key = arg;
-	struct wait_bit_queue_entry *wait_bit = container_of(wq_entry, struct wait_bit_queue_entry, wq_entry);
-	atomic_t *val = key->flags;
-
-	if (wait_bit->key.flags != key->flags ||
-	    wait_bit->key.bit_nr != key->bit_nr ||
-	    atomic_read(val) != 0)
-		return 0;
-	return autoremove_wake_function(wq_entry, mode, sync, key);
-}
-
-/*
- * To allow interruptible waiting and asynchronous (i.e. nonblocking) waiting,
- * the actions of __wait_on_atomic_t() are permitted return codes.  Nonzero
- * return codes halt waiting and return.
- */
-static __sched
-int __wait_on_atomic_t(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry,
-		       int (*action)(atomic_t *), unsigned mode)
-{
-	atomic_t *val;
-	int ret = 0;
-
-	do {
-		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
-		val = wbq_entry->key.flags;
-		if (atomic_read(val) == 0)
-			break;
-		ret = (*action)(val);
-	} while (!ret && atomic_read(val) != 0);
-	finish_wait(wq_head, &wbq_entry->wq_entry);
-	return ret;
-}
-
-#define DEFINE_WAIT_ATOMIC_T(name, p)					\
-	struct wait_bit_queue_entry name = {				\
-		.key = __WAIT_ATOMIC_T_KEY_INITIALIZER(p),		\
-		.wq_entry = {						\
-			.private	= current,			\
-			.func		= wake_atomic_t_function,	\
-			.task_list	=				\
-				LIST_HEAD_INIT((name).wq_entry.task_list), \
-		},							\
-	}
-
-__sched int out_of_line_wait_on_atomic_t(atomic_t *p, int (*action)(atomic_t *),
-					 unsigned mode)
-{
-	struct wait_queue_head *wq_head = atomic_t_waitqueue(p);
-	DEFINE_WAIT_ATOMIC_T(wq_entry, p);
-
-	return __wait_on_atomic_t(wq_head, &wq_entry, action, mode);
-}
-EXPORT_SYMBOL(out_of_line_wait_on_atomic_t);
-
-/**
- * wake_up_atomic_t - Wake up a waiter on a atomic_t
- * @p: The atomic_t being waited on, a kernel virtual address
- *
- * Wake up anyone waiting for the atomic_t to go to zero.
- *
- * Abuse the bit-waker function and its waitqueue hash table set (the atomic_t
- * check is done by the waiter's wake function, not the by the waker itself).
- */
-void wake_up_atomic_t(atomic_t *p)
-{
-	__wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR);
-}
-EXPORT_SYMBOL(wake_up_atomic_t);
-
-__sched int bit_wait(struct wait_bit_key *word, int mode)
-{
-	schedule();
-	if (signal_pending_state(mode, current))
-		return -EINTR;
-	return 0;
-}
-EXPORT_SYMBOL(bit_wait);
-
-__sched int bit_wait_io(struct wait_bit_key *word, int mode)
-{
-	io_schedule();
-	if (signal_pending_state(mode, current))
-		return -EINTR;
-	return 0;
-}
-EXPORT_SYMBOL(bit_wait_io);
-
-__sched int bit_wait_timeout(struct wait_bit_key *word, int mode)
-{
-	unsigned long now = READ_ONCE(jiffies);
-	if (time_after_eq(now, word->timeout))
-		return -EAGAIN;
-	schedule_timeout(word->timeout - now);
-	if (signal_pending_state(mode, current))
-		return -EINTR;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(bit_wait_timeout);
-
-__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode)
-{
-	unsigned long now = READ_ONCE(jiffies);
-	if (time_after_eq(now, word->timeout))
-		return -EAGAIN;
-	io_schedule_timeout(word->timeout - now);
-	if (signal_pending_state(mode, current))
-		return -EINTR;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(bit_wait_io_timeout);

kernel/sched/wait_bit.c

+/*
+ * The implementation of the wait_bit*() and related waiting APIs:
+ */
+#include <linux/wait_bit.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
+
+int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *arg)
+{
+	struct wait_bit_key *key = arg;
+	struct wait_bit_queue_entry *wait_bit = container_of(wq_entry, struct wait_bit_queue_entry, wq_entry);
+
+	if (wait_bit->key.flags != key->flags ||
+			wait_bit->key.bit_nr != key->bit_nr ||
+			test_bit(key->bit_nr, key->flags))
+		return 0;
+	else
+		return autoremove_wake_function(wq_entry, mode, sync, key);
+}
+EXPORT_SYMBOL(wake_bit_function);
+
+/*
+ * To allow interruptible waiting and asynchronous (i.e. nonblocking)
+ * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are
+ * permitted return codes. Nonzero return codes halt waiting and return.
+ */
+int __sched
+__wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry,
+	      wait_bit_action_f *action, unsigned mode)
+{
+	int ret = 0;
+
+	do {
+		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
+		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
+			ret = (*action)(&wbq_entry->key, mode);
+	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	finish_wait(wq_head, &wbq_entry->wq_entry);
+	return ret;
+}
+EXPORT_SYMBOL(__wait_on_bit);
+
+int __sched out_of_line_wait_on_bit(void *word, int bit,
+				    wait_bit_action_f *action, unsigned mode)
+{
+	struct wait_queue_head *wq_head = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wq_entry, word, bit);
+
+	return __wait_on_bit(wq_head, &wq_entry, action, mode);
+}
+EXPORT_SYMBOL(out_of_line_wait_on_bit);
+
+int __sched out_of_line_wait_on_bit_timeout(
+	void *word, int bit, wait_bit_action_f *action,
+	unsigned mode, unsigned long timeout)
+{
+	struct wait_queue_head *wq_head = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wq_entry, word, bit);
+
+	wq_entry.key.timeout = jiffies + timeout;
+	return __wait_on_bit(wq_head, &wq_entry, action, mode);
+}
+EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout);
+
+int __sched
+__wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry,
+			wait_bit_action_f *action, unsigned mode)
+{
+	int ret = 0;
+
+	for (;;) {
+		prepare_to_wait_exclusive(wq_head, &wbq_entry->wq_entry, mode);
+		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) {
+			ret = action(&wbq_entry->key, mode);
+			/*
+			 * See the comment in prepare_to_wait_event().
+			 * finish_wait() does not necessarily takes wwq_head->lock,
+			 * but test_and_set_bit() implies mb() which pairs with
+			 * smp_mb__after_atomic() before wake_up_page().
+			 */
+			if (ret)
+				finish_wait(wq_head, &wbq_entry->wq_entry);
+		}
+		if (!test_and_set_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) {
+			if (!ret)
+				finish_wait(wq_head, &wbq_entry->wq_entry);
+			return 0;
+		} else if (ret) {
+			return ret;
+		}
+	}
+}
+EXPORT_SYMBOL(__wait_on_bit_lock);
+
+int __sched out_of_line_wait_on_bit_lock(void *word, int bit,
+					 wait_bit_action_f *action, unsigned mode)
+{
+	struct wait_queue_head *wq_head = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wq_entry, word, bit);
+
+	return __wait_on_bit_lock(wq_head, &wq_entry, action, mode);
+}
+EXPORT_SYMBOL(out_of_line_wait_on_bit_lock);
+
+void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit)
+{
+	struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit);
+	if (waitqueue_active(wq_head))
+		__wake_up(wq_head, TASK_NORMAL, 1, &key);
+}
+EXPORT_SYMBOL(__wake_up_bit);
+
+/**
+ * wake_up_bit - wake up a waiter on a bit
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ *
+ * There is a standard hashed waitqueue table for generic use. This
+ * is the part of the hashtable's accessor API that wakes up waiters
+ * on a bit. For instance, if one were to have waiters on a bitflag,
+ * one would call wake_up_bit() after clearing the bit.
+ *
+ * In order for this to function properly, as it uses waitqueue_active()
+ * internally, some kind of memory barrier must be done prior to calling
+ * this. Typically, this will be smp_mb__after_atomic(), but in some
+ * cases where bitflags are manipulated non-atomically under a lock, one
+ * may need to use a less regular barrier, such fs/inode.c's smp_mb(),
+ * because spin_unlock() does not guarantee a memory barrier.
+ */
+void wake_up_bit(void *word, int bit)
+{
+	__wake_up_bit(bit_waitqueue(word, bit), word, bit);
+}
+EXPORT_SYMBOL(wake_up_bit);
+
+/*
+ * Manipulate the atomic_t address to produce a better bit waitqueue table hash
+ * index (we're keying off bit -1, but that would produce a horrible hash
+ * value).
+ */
+static inline wait_queue_head_t *atomic_t_waitqueue(atomic_t *p)
+{
+	if (BITS_PER_LONG == 64) {
+		unsigned long q = (unsigned long)p;
+		return bit_waitqueue((void *)(q & ~1), q & 1);
+	}
+	return bit_waitqueue(p, 0);
+}
+
+static int wake_atomic_t_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync,
+				  void *arg)
+{
+	struct wait_bit_key *key = arg;
+	struct wait_bit_queue_entry *wait_bit = container_of(wq_entry, struct wait_bit_queue_entry, wq_entry);
+	atomic_t *val = key->flags;
+
+	if (wait_bit->key.flags != key->flags ||
+	    wait_bit->key.bit_nr != key->bit_nr ||
+	    atomic_read(val) != 0)
+		return 0;
+	return autoremove_wake_function(wq_entry, mode, sync, key);
+}
+
+/*
+ * To allow interruptible waiting and asynchronous (i.e. nonblocking) waiting,
+ * the actions of __wait_on_atomic_t() are permitted return codes.  Nonzero
+ * return codes halt waiting and return.
+ */
+static __sched
+int __wait_on_atomic_t(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry,
+		       int (*action)(atomic_t *), unsigned mode)
+{
+	atomic_t *val;
+	int ret = 0;
+
+	do {
+		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
+		val = wbq_entry->key.flags;
+		if (atomic_read(val) == 0)
+			break;
+		ret = (*action)(val);
+	} while (!ret && atomic_read(val) != 0);
+	finish_wait(wq_head, &wbq_entry->wq_entry);
+	return ret;
+}
+
+#define DEFINE_WAIT_ATOMIC_T(name, p)					\
+	struct wait_bit_queue_entry name = {				\
+		.key = __WAIT_ATOMIC_T_KEY_INITIALIZER(p),		\
+		.wq_entry = {						\
+			.private	= current,			\
+			.func		= wake_atomic_t_function,	\
+			.task_list	=				\
+				LIST_HEAD_INIT((name).wq_entry.task_list), \
+		},							\
+	}
+
+__sched int out_of_line_wait_on_atomic_t(atomic_t *p, int (*action)(atomic_t *),
+					 unsigned mode)
+{
+	struct wait_queue_head *wq_head = atomic_t_waitqueue(p);
+	DEFINE_WAIT_ATOMIC_T(wq_entry, p);
+
+	return __wait_on_atomic_t(wq_head, &wq_entry, action, mode);
+}
+EXPORT_SYMBOL(out_of_line_wait_on_atomic_t);
+
+/**
+ * wake_up_atomic_t - Wake up a waiter on a atomic_t
+ * @p: The atomic_t being waited on, a kernel virtual address
+ *
+ * Wake up anyone waiting for the atomic_t to go to zero.
+ *
+ * Abuse the bit-waker function and its waitqueue hash table set (the atomic_t
+ * check is done by the waiter's wake function, not the by the waker itself).
+ */
+void wake_up_atomic_t(atomic_t *p)
+{
+	__wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR);
+}
+EXPORT_SYMBOL(wake_up_atomic_t);
+
+__sched int bit_wait(struct wait_bit_key *word, int mode)
+{
+	schedule();
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL(bit_wait);
+
+__sched int bit_wait_io(struct wait_bit_key *word, int mode)
+{
+	io_schedule();
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL(bit_wait_io);
+
+__sched int bit_wait_timeout(struct wait_bit_key *word, int mode)
+{
+	unsigned long now = READ_ONCE(jiffies);
+	if (time_after_eq(now, word->timeout))
+		return -EAGAIN;
+	schedule_timeout(word->timeout - now);
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bit_wait_timeout);
+
+__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode)
+{
+	unsigned long now = READ_ONCE(jiffies);
+	if (time_after_eq(now, word->timeout))
+		return -EAGAIN;
+	io_schedule_timeout(word->timeout - now);
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bit_wait_io_timeout);

security/keys/internal.h

@@ -13,6 +13,7 @@
 #define _INTERNAL_H
 
 #include <linux/sched.h>
+#include <linux/wait_bit.h>
 #include <linux/cred.h>
 #include <linux/key-type.h>
 #include <linux/task_work.h>