/*
   *  Fast Userspace Mutexes (which I call "Futexes!").
   *  (C) Rusty Russell, IBM 2002
   *
   *  Generalized futexes, futex requeueing, misc fixes by Ingo Molnar
   *  (C) Copyright 2003 Red Hat Inc, All Rights Reserved
   *
   *  Removed page pinning, fix privately mapped COW pages and other cleanups
   *  (C) Copyright 2003, 2004 Jamie Lokier
   *

   *  Robust futex support started by Ingo Molnar
   *  (C) Copyright 2006 Red Hat Inc, All Rights Reserved
   *  Thanks to Thomas Gleixner for suggestions, analysis and fixes.
   *

   *  PI-futex support started by Ingo Molnar and Thomas Gleixner
   *  Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
   *  Copyright (C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
   *

   *  PRIVATE futexes by Eric Dumazet
   *  Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com>
   *

   *  Requeue-PI support by Darren Hart <dvhltc@us.ibm.com>
   *  Copyright (C) IBM Corporation, 2009
   *  Thanks to Thomas Gleixner for conceptual design and careful reviews.
   *

   *  Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly
   *  enough at me, Linus for the original (flawed) idea, Matthew
   *  Kirkwood for proof-of-concept implementation.
   *
   *  "The futexes are also cursed."
   *  "But they come in a choice of three flavours!"
   *
   *  This program is free software; you can redistribute it and/or modify
   *  it under the terms of the GNU General Public License as published by
   *  the Free Software Foundation; either version 2 of the License, or
   *  (at your option) any later version.
   *
   *  This program is distributed in the hope that it will be useful,
   *  but WITHOUT ANY WARRANTY; without even the implied warranty of
   *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   *  GNU General Public License for more details.
   *
   *  You should have received a copy of the GNU General Public License
   *  along with this program; if not, write to the Free Software
   *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
   */
  #include <linux/slab.h>
  #include <linux/poll.h>
  #include <linux/fs.h>
  #include <linux/file.h>
  #include <linux/jhash.h>
  #include <linux/init.h>
  #include <linux/futex.h>
  #include <linux/mount.h>
  #include <linux/pagemap.h>
  #include <linux/syscalls.h>

  #include <linux/signal.h>

  #include <linux/export.h>

  #include <linux/magic.h>

  #include <linux/pid.h>
  #include <linux/nsproxy.h>

  #include <linux/ptrace.h>

  #include <linux/sched/rt.h>

  #include <linux/hugetlb.h>

  #include <linux/freezer.h>

  #include <linux/bootmem.h>

  #include <asm/futex.h>

  #include "locking/rtmutex_common.h"

  /*

   * READ this before attempting to hack on futexes!
   *
   * Basic futex operation and ordering guarantees
   * =============================================

   *
   * The waiter reads the futex value in user space and calls
   * futex_wait(). This function computes the hash bucket and acquires
   * the hash bucket lock. After that it reads the futex user space value

   * again and verifies that the data has not changed. If it has not changed
   * it enqueues itself into the hash bucket, releases the hash bucket lock
   * and schedules.

   *
   * The waker side modifies the user space value of the futex and calls

   * futex_wake(). This function computes the hash bucket and acquires the
   * hash bucket lock. Then it looks for waiters on that futex in the hash
   * bucket and wakes them.

   *

   * In futex wake up scenarios where no tasks are blocked on a futex, taking
   * the hb spinlock can be avoided and simply return. In order for this
   * optimization to work, ordering guarantees must exist so that the waiter
   * being added to the list is acknowledged when the list is concurrently being
   * checked by the waker, avoiding scenarios like the following:

   *
   * CPU 0                               CPU 1
   * val = *futex;
   * sys_futex(WAIT, futex, val);
   *   futex_wait(futex, val);
   *   uval = *futex;
   *                                     *futex = newval;
   *                                     sys_futex(WAKE, futex);
   *                                       futex_wake(futex);
   *                                       if (queue_empty())
   *                                         return;
   *   if (uval == val)
   *      lock(hash_bucket(futex));
   *      queue();
   *     unlock(hash_bucket(futex));
   *     schedule();
   *
   * This would cause the waiter on CPU 0 to wait forever because it
   * missed the transition of the user space value from val to newval
   * and the waker did not find the waiter in the hash bucket queue.

   *

   * The correct serialization ensures that a waiter either observes
   * the changed user space value before blocking or is woken by a
   * concurrent waker:
   *
   * CPU 0                                 CPU 1

   * val = *futex;
   * sys_futex(WAIT, futex, val);
   *   futex_wait(futex, val);

   *

   *   waiters++; (a)

   *   mb(); (A) <-- paired with -.
   *                              |
   *   lock(hash_bucket(futex));  |
   *                              |
   *   uval = *futex;             |
   *                              |        *futex = newval;
   *                              |        sys_futex(WAKE, futex);
   *                              |          futex_wake(futex);
   *                              |
   *                              `------->  mb(); (B)

   *   if (uval == val)

   *     queue();

   *     unlock(hash_bucket(futex));

   *     schedule();                         if (waiters)
   *                                           lock(hash_bucket(futex));

   *   else                                    wake_waiters(futex);
   *     waiters--; (b)                        unlock(hash_bucket(futex));

   *

   * Where (A) orders the waiters increment and the futex value read through
   * atomic operations (see hb_waiters_inc) and where (B) orders the write
   * to futex and the waiters read -- this is done by the barriers in
   * get_futex_key_refs(), through either ihold or atomic_inc, depending on the
   * futex type.

   *
   * This yields the following case (where X:=waiters, Y:=futex):
   *
   *	X = Y = 0
   *
   *	w[X]=1		w[Y]=1
   *	MB		MB
   *	r[Y]=y		r[X]=x
   *
   * Which guarantees that x==0 && y==0 is impossible; which translates back into
   * the guarantee that we cannot both miss the futex variable change and the
   * enqueue.

   *
   * Note that a new waiter is accounted for in (a) even when it is possible that
   * the wait call can return error, in which case we backtrack from it in (b).
   * Refer to the comment in queue_lock().
   *
   * Similarly, in order to account for waiters being requeued on another
   * address we always increment the waiters for the destination bucket before
   * acquiring the lock. It then decrements them again  after releasing it -
   * the code that actually moves the futex(es) between hash buckets (requeue_futex)
   * will do the additional required waiter count housekeeping. This is done for
   * double_lock_hb() and double_unlock_hb(), respectively.

   */

  #ifndef CONFIG_HAVE_FUTEX_CMPXCHG

  int __read_mostly futex_cmpxchg_enabled;

  #endif

  /*

   * Futex flags used to encode options to functions and preserve them across
   * restarts.
   */
  #define FLAGS_SHARED		0x01
  #define FLAGS_CLOCKRT		0x02
  #define FLAGS_HAS_TIMEOUT	0x04
  
  /*

   * Priority Inheritance state:
   */
  struct futex_pi_state {
  	/*
  	 * list of 'owned' pi_state instances - these have to be
  	 * cleaned up in do_exit() if the task exits prematurely:
  	 */
  	struct list_head list;
  
  	/*
  	 * The PI object:
  	 */
  	struct rt_mutex pi_mutex;
  
  	struct task_struct *owner;
  	atomic_t refcount;
  
  	union futex_key key;
  };

  /**
   * struct futex_q - The hashed futex queue entry, one per waiting task

   * @list:		priority-sorted list of tasks waiting on this futex

   * @task:		the task waiting on the futex
   * @lock_ptr:		the hash bucket lock
   * @key:		the key the futex is hashed on
   * @pi_state:		optional priority inheritance state
   * @rt_waiter:		rt_waiter storage for use with requeue_pi
   * @requeue_pi_key:	the requeue_pi target futex key
   * @bitset:		bitset for the optional bitmasked wakeup
   *
   * We use this hashed waitqueue, instead of a normal wait_queue_t, so

   * we can wake only the relevant ones (hashed queues may be shared).
   *
   * A futex_q has a woken state, just like tasks have TASK_RUNNING.

   * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0.

   * The order of wakeup is always to make the first condition true, then

   * the second.
   *
   * PI futexes are typically woken before they are removed from the hash list via
   * the rt_mutex code. See unqueue_me_pi().

   */
  struct futex_q {

  	struct plist_node list;

  	struct task_struct *task;

  	spinlock_t *lock_ptr;

  	union futex_key key;

  	struct futex_pi_state *pi_state;

  	struct rt_mutex_waiter *rt_waiter;

  	union futex_key *requeue_pi_key;

  	u32 bitset;

  };

  static const struct futex_q futex_q_init = {
  	/* list gets initialized in queue_me()*/
  	.key = FUTEX_KEY_INIT,
  	.bitset = FUTEX_BITSET_MATCH_ANY
  };

  /*

   * Hash buckets are shared by all the futex_keys that hash to the same
   * location.  Each key may have multiple futex_q structures, one for each task
   * waiting on a futex.

   */
  struct futex_hash_bucket {

  	atomic_t waiters;

  	spinlock_t lock;
  	struct plist_head chain;

  } ____cacheline_aligned_in_smp;

  static unsigned long __read_mostly futex_hashsize;
  
  static struct futex_hash_bucket *futex_queues;

  static inline void futex_get_mm(union futex_key *key)
  {
  	atomic_inc(&key->private.mm->mm_count);
  	/*
  	 * Ensure futex_get_mm() implies a full barrier such that
  	 * get_futex_key() implies a full barrier. This is relied upon
  	 * as full barrier (B), see the ordering comment above.
  	 */
  	smp_mb__after_atomic_inc();
  }

  /*
   * Reflects a new waiter being added to the waitqueue.
   */
  static inline void hb_waiters_inc(struct futex_hash_bucket *hb)

  {
  #ifdef CONFIG_SMP

  	atomic_inc(&hb->waiters);

  	/*

  	 * Full barrier (A), see the ordering comment above.

  	 */

  	smp_mb__after_atomic_inc();
  #endif
  }
  
  /*
   * Reflects a waiter being removed from the waitqueue by wakeup
   * paths.
   */
  static inline void hb_waiters_dec(struct futex_hash_bucket *hb)
  {
  #ifdef CONFIG_SMP
  	atomic_dec(&hb->waiters);
  #endif
  }

  static inline int hb_waiters_pending(struct futex_hash_bucket *hb)
  {
  #ifdef CONFIG_SMP
  	return atomic_read(&hb->waiters);

  #else

  	return 1;

  #endif
  }

  /*
   * We hash on the keys returned from get_futex_key (see below).
   */
  static struct futex_hash_bucket *hash_futex(union futex_key *key)
  {
  	u32 hash = jhash2((u32*)&key->both.word,
  			  (sizeof(key->both.word)+sizeof(key->both.ptr))/4,
  			  key->both.offset);

  	return &futex_queues[hash & (futex_hashsize - 1)];

  }
  
  /*
   * Return 1 if two futex_keys are equal, 0 otherwise.
   */
  static inline int match_futex(union futex_key *key1, union futex_key *key2)
  {

  	return (key1 && key2
  		&& key1->both.word == key2->both.word

  		&& key1->both.ptr == key2->both.ptr
  		&& key1->both.offset == key2->both.offset);
  }

  /*
   * Take a reference to the resource addressed by a key.
   * Can be called while holding spinlocks.
   *
   */
  static void get_futex_key_refs(union futex_key *key)
  {
  	if (!key->both.ptr)
  		return;
  
  	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
  	case FUT_OFF_INODE:

  		ihold(key->shared.inode); /* implies MB (B) */

  		break;
  	case FUT_OFF_MMSHARED:

  		futex_get_mm(key); /* implies MB (B) */

  		break;
  	}
  }
  
  /*
   * Drop a reference to the resource addressed by a key.
   * The hash bucket spinlock must not be held.
   */
  static void drop_futex_key_refs(union futex_key *key)
  {

  	if (!key->both.ptr) {
  		/* If we're here then we tried to put a key we failed to get */
  		WARN_ON_ONCE(1);

  		return;

  	}

  
  	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
  	case FUT_OFF_INODE:
  		iput(key->shared.inode);
  		break;
  	case FUT_OFF_MMSHARED:
  		mmdrop(key->private.mm);
  		break;
  	}
  }

  /**

   * get_futex_key() - Get parameters which are the keys for a futex
   * @uaddr:	virtual address of the futex
   * @fshared:	0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
   * @key:	address where result is stored.

   * @rw:		mapping needs to be read/write (values: VERIFY_READ,
   *              VERIFY_WRITE)

   *

   * Return: a negative error code or 0
   *

   * The key words are stored in *key on success.

   *

   * For shared mappings, it's (page->index, file_inode(vma->vm_file),

   * offset_within_page).  For private mappings, it's (uaddr, current->mm).
   * We can usually work out the index without swapping in the page.
   *

   * lock_page() might sleep, the caller should not hold a spinlock.

   */

  static int

  get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)

  {

  	unsigned long address = (unsigned long)uaddr;

  	struct mm_struct *mm = current->mm;

  	struct page *page, *page_head;

  	int err, ro = 0;

  
  	/*
  	 * The futex address must be "naturally" aligned.
  	 */

  	key->both.offset = address % PAGE_SIZE;

  	if (unlikely((address % sizeof(u32)) != 0))

  		return -EINVAL;

  	address -= key->both.offset;

  	if (unlikely(!access_ok(rw, uaddr, sizeof(u32))))
  		return -EFAULT;

  	/*

  	 * PROCESS_PRIVATE futexes are fast.
  	 * As the mm cannot disappear under us and the 'key' only needs
  	 * virtual address, we dont even have to find the underlying vma.
  	 * Note : We do have to check 'uaddr' is a valid user address,
  	 *        but access_ok() should be faster than find_vma()
  	 */
  	if (!fshared) {

  		key->private.mm = mm;
  		key->private.address = address;

  		get_futex_key_refs(key);  /* implies MB (B) */

  		return 0;
  	}

  again:

  	err = get_user_pages_fast(address, 1, 1, &page);

  	/*
  	 * If write access is not required (eg. FUTEX_WAIT), try
  	 * and get read-only access.
  	 */
  	if (err == -EFAULT && rw == VERIFY_READ) {
  		err = get_user_pages_fast(address, 1, 0, &page);
  		ro = 1;
  	}

  	if (err < 0)
  		return err;

  	else
  		err = 0;

  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
  	page_head = page;
  	if (unlikely(PageTail(page))) {

  		put_page(page);

  		/* serialize against __split_huge_page_splitting() */
  		local_irq_disable();

  		if (likely(__get_user_pages_fast(address, 1, !ro, &page) == 1)) {

  			page_head = compound_head(page);
  			/*
  			 * page_head is valid pointer but we must pin
  			 * it before taking the PG_lock and/or
  			 * PG_compound_lock. The moment we re-enable
  			 * irqs __split_huge_page_splitting() can
  			 * return and the head page can be freed from
  			 * under us. We can't take the PG_lock and/or
  			 * PG_compound_lock on a page that could be
  			 * freed from under us.
  			 */
  			if (page != page_head) {
  				get_page(page_head);
  				put_page(page);
  			}
  			local_irq_enable();
  		} else {
  			local_irq_enable();
  			goto again;
  		}
  	}
  #else
  	page_head = compound_head(page);
  	if (page != page_head) {
  		get_page(page_head);
  		put_page(page);
  	}
  #endif
  
  	lock_page(page_head);

  
  	/*
  	 * If page_head->mapping is NULL, then it cannot be a PageAnon
  	 * page; but it might be the ZERO_PAGE or in the gate area or
  	 * in a special mapping (all cases which we are happy to fail);
  	 * or it may have been a good file page when get_user_pages_fast
  	 * found it, but truncated or holepunched or subjected to
  	 * invalidate_complete_page2 before we got the page lock (also
  	 * cases which we are happy to fail).  And we hold a reference,
  	 * so refcount care in invalidate_complete_page's remove_mapping
  	 * prevents drop_caches from setting mapping to NULL beneath us.
  	 *
  	 * The case we do have to guard against is when memory pressure made
  	 * shmem_writepage move it from filecache to swapcache beneath us:
  	 * an unlikely race, but we do need to retry for page_head->mapping.
  	 */

  	if (!page_head->mapping) {

  		int shmem_swizzled = PageSwapCache(page_head);

  		unlock_page(page_head);
  		put_page(page_head);

  		if (shmem_swizzled)
  			goto again;
  		return -EFAULT;

  	}

  
  	/*
  	 * Private mappings are handled in a simple way.
  	 *
  	 * NOTE: When userspace waits on a MAP_SHARED mapping, even if
  	 * it's a read-only handle, it's expected that futexes attach to

  	 * the object not the particular process.

  	 */

  	if (PageAnon(page_head)) {

  		/*
  		 * A RO anonymous page will never change and thus doesn't make
  		 * sense for futex operations.
  		 */
  		if (ro) {
  			err = -EFAULT;
  			goto out;
  		}

  		key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */

  		key->private.mm = mm;

  		key->private.address = address;

  	} else {
  		key->both.offset |= FUT_OFF_INODE; /* inode-based key */

  		key->shared.inode = page_head->mapping->host;

  		key->shared.pgoff = basepage_index(page);

  	}

  	get_futex_key_refs(key); /* implies MB (B) */

  out:

  	unlock_page(page_head);
  	put_page(page_head);

  	return err;

  }

  static inline void put_futex_key(union futex_key *key)

  {

  	drop_futex_key_refs(key);

  }

  /**
   * fault_in_user_writeable() - Fault in user address and verify RW access

   * @uaddr:	pointer to faulting user space address
   *
   * Slow path to fixup the fault we just took in the atomic write
   * access to @uaddr.
   *

   * We have no generic implementation of a non-destructive write to the

   * user address. We know that we faulted in the atomic pagefault
   * disabled section so we can as well avoid the #PF overhead by
   * calling get_user_pages() right away.
   */
  static int fault_in_user_writeable(u32 __user *uaddr)
  {

  	struct mm_struct *mm = current->mm;
  	int ret;
  
  	down_read(&mm->mmap_sem);

  	ret = fixup_user_fault(current, mm, (unsigned long)uaddr,
  			       FAULT_FLAG_WRITE);

  	up_read(&mm->mmap_sem);

  	return ret < 0 ? ret : 0;
  }

  /**
   * futex_top_waiter() - Return the highest priority waiter on a futex

   * @hb:		the hash bucket the futex_q's reside in
   * @key:	the futex key (to distinguish it from other futex futex_q's)

   *
   * Must be called with the hb lock held.
   */
  static struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb,
  					union futex_key *key)
  {
  	struct futex_q *this;
  
  	plist_for_each_entry(this, &hb->chain, list) {
  		if (match_futex(&this->key, key))
  			return this;
  	}
  	return NULL;
  }

  static int cmpxchg_futex_value_locked(u32 *curval, u32 __user *uaddr,
  				      u32 uval, u32 newval)

  {

  	int ret;

  
  	pagefault_disable();

  	ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval);

  	pagefault_enable();

  	return ret;

  }
  
  static int get_futex_value_locked(u32 *dest, u32 __user *from)

  {
  	int ret;

  	pagefault_disable();

  	ret = __copy_from_user_inatomic(dest, from, sizeof(u32));

  	pagefault_enable();

  
  	return ret ? -EFAULT : 0;
  }

  
  /*
   * PI code:
   */
  static int refill_pi_state_cache(void)
  {
  	struct futex_pi_state *pi_state;
  
  	if (likely(current->pi_state_cache))
  		return 0;

  	pi_state = kzalloc(sizeof(*pi_state), GFP_KERNEL);

  
  	if (!pi_state)
  		return -ENOMEM;

  	INIT_LIST_HEAD(&pi_state->list);
  	/* pi_mutex gets initialized later */
  	pi_state->owner = NULL;
  	atomic_set(&pi_state->refcount, 1);

  	pi_state->key = FUTEX_KEY_INIT;

  
  	current->pi_state_cache = pi_state;
  
  	return 0;
  }
  
  static struct futex_pi_state * alloc_pi_state(void)
  {
  	struct futex_pi_state *pi_state = current->pi_state_cache;
  
  	WARN_ON(!pi_state);
  	current->pi_state_cache = NULL;
  
  	return pi_state;
  }
  
  static void free_pi_state(struct futex_pi_state *pi_state)
  {
  	if (!atomic_dec_and_test(&pi_state->refcount))
  		return;
  
  	/*
  	 * If pi_state->owner is NULL, the owner is most probably dying
  	 * and has cleaned up the pi_state already
  	 */
  	if (pi_state->owner) {

  		raw_spin_lock_irq(&pi_state->owner->pi_lock);

  		list_del_init(&pi_state->list);

  		raw_spin_unlock_irq(&pi_state->owner->pi_lock);

  
  		rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner);
  	}
  
  	if (current->pi_state_cache)
  		kfree(pi_state);
  	else {
  		/*
  		 * pi_state->list is already empty.
  		 * clear pi_state->owner.
  		 * refcount is at 0 - put it back to 1.
  		 */
  		pi_state->owner = NULL;
  		atomic_set(&pi_state->refcount, 1);
  		current->pi_state_cache = pi_state;
  	}
  }
  
  /*
   * Look up the task based on what TID userspace gave us.
   * We dont trust it.
   */
  static struct task_struct * futex_find_get_task(pid_t pid)
  {
  	struct task_struct *p;

  	rcu_read_lock();

  	p = find_task_by_vpid(pid);

  	if (p)
  		get_task_struct(p);

  	rcu_read_unlock();

  
  	return p;
  }
  
  /*
   * This task is holding PI mutexes at exit time => bad.
   * Kernel cleans up PI-state, but userspace is likely hosed.
   * (Robust-futex cleanup is separate and might save the day for userspace.)
   */
  void exit_pi_state_list(struct task_struct *curr)
  {

  	struct list_head *next, *head = &curr->pi_state_list;
  	struct futex_pi_state *pi_state;

  	struct futex_hash_bucket *hb;

  	union futex_key key = FUTEX_KEY_INIT;

  	if (!futex_cmpxchg_enabled)
  		return;

  	/*
  	 * We are a ZOMBIE and nobody can enqueue itself on
  	 * pi_state_list anymore, but we have to be careful

  	 * versus waiters unqueueing themselves:

  	 */

  	raw_spin_lock_irq(&curr->pi_lock);

  	while (!list_empty(head)) {
  
  		next = head->next;
  		pi_state = list_entry(next, struct futex_pi_state, list);
  		key = pi_state->key;

  		hb = hash_futex(&key);

  		raw_spin_unlock_irq(&curr->pi_lock);

  		spin_lock(&hb->lock);

  		raw_spin_lock_irq(&curr->pi_lock);

  		/*
  		 * We dropped the pi-lock, so re-check whether this
  		 * task still owns the PI-state:
  		 */

  		if (head->next != next) {
  			spin_unlock(&hb->lock);
  			continue;
  		}

  		WARN_ON(pi_state->owner != curr);

  		WARN_ON(list_empty(&pi_state->list));
  		list_del_init(&pi_state->list);

  		pi_state->owner = NULL;

  		raw_spin_unlock_irq(&curr->pi_lock);

  
  		rt_mutex_unlock(&pi_state->pi_mutex);
  
  		spin_unlock(&hb->lock);

  		raw_spin_lock_irq(&curr->pi_lock);

  	}

  	raw_spin_unlock_irq(&curr->pi_lock);

  }

  /*
   * We need to check the following states:
   *
   *      Waiter | pi_state | pi->owner | uTID      | uODIED | ?
   *
   * [1]  NULL   | ---      | ---       | 0         | 0/1    | Valid
   * [2]  NULL   | ---      | ---       | >0        | 0/1    | Valid
   *
   * [3]  Found  | NULL     | --        | Any       | 0/1    | Invalid
   *
   * [4]  Found  | Found    | NULL      | 0         | 1      | Valid
   * [5]  Found  | Found    | NULL      | >0        | 1      | Invalid
   *
   * [6]  Found  | Found    | task      | 0         | 1      | Valid
   *
   * [7]  Found  | Found    | NULL      | Any       | 0      | Invalid
   *
   * [8]  Found  | Found    | task      | ==taskTID | 0/1    | Valid
   * [9]  Found  | Found    | task      | 0         | 0      | Invalid
   * [10] Found  | Found    | task      | !=taskTID | 0/1    | Invalid
   *
   * [1]	Indicates that the kernel can acquire the futex atomically. We
   *	came came here due to a stale FUTEX_WAITERS/FUTEX_OWNER_DIED bit.
   *
   * [2]	Valid, if TID does not belong to a kernel thread. If no matching
   *      thread is found then it indicates that the owner TID has died.
   *
   * [3]	Invalid. The waiter is queued on a non PI futex
   *
   * [4]	Valid state after exit_robust_list(), which sets the user space
   *	value to FUTEX_WAITERS | FUTEX_OWNER_DIED.
   *
   * [5]	The user space value got manipulated between exit_robust_list()
   *	and exit_pi_state_list()
   *
   * [6]	Valid state after exit_pi_state_list() which sets the new owner in
   *	the pi_state but cannot access the user space value.
   *
   * [7]	pi_state->owner can only be NULL when the OWNER_DIED bit is set.
   *
   * [8]	Owner and user space value match
   *
   * [9]	There is no transient state which sets the user space TID to 0
   *	except exit_robust_list(), but this is indicated by the
   *	FUTEX_OWNER_DIED bit. See [4]
   *
   * [10] There is no transient state which leaves owner and user space
   *	TID out of sync.
   */

  static int

  lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,

  		union futex_key *key, struct futex_pi_state **ps)

  {
  	struct futex_pi_state *pi_state = NULL;
  	struct futex_q *this, *next;

  	struct task_struct *p;

  	pid_t pid = uval & FUTEX_TID_MASK;

  	plist_for_each_entry_safe(this, next, &hb->chain, list) {

  		if (match_futex(&this->key, key)) {

  			/*

  			 * Sanity check the waiter before increasing
  			 * the refcount and attaching to it.

  			 */
  			pi_state = this->pi_state;

  			/*

  			 * Userspace might have messed up non-PI and
  			 * PI futexes [3]

  			 */
  			if (unlikely(!pi_state))
  				return -EINVAL;

  			WARN_ON(!atomic_read(&pi_state->refcount));

  
  			/*

  			 * Handle the owner died case:

  			 */

  			if (uval & FUTEX_OWNER_DIED) {

  				/*

  				 * exit_pi_state_list sets owner to NULL and
  				 * wakes the topmost waiter. The task which
  				 * acquires the pi_state->rt_mutex will fixup
  				 * owner.

  				 */

  				if (!pi_state->owner) {
  					/*
  					 * No pi state owner, but the user
  					 * space TID is not 0. Inconsistent
  					 * state. [5]
  					 */
  					if (pid)
  						return -EINVAL;
  					/*
  					 * Take a ref on the state and
  					 * return. [4]
  					 */
  					goto out_state;
  				}
  
  				/*
  				 * If TID is 0, then either the dying owner
  				 * has not yet executed exit_pi_state_list()
  				 * or some waiter acquired the rtmutex in the
  				 * pi state, but did not yet fixup the TID in
  				 * user space.
  				 *
  				 * Take a ref on the state and return. [6]
  				 */
  				if (!pid)
  					goto out_state;
  			} else {
  				/*
  				 * If the owner died bit is not set,
  				 * then the pi_state must have an
  				 * owner. [7]
  				 */
  				if (!pi_state->owner)

  					return -EINVAL;
  			}

  			/*

  			 * Bail out if user space manipulated the
  			 * futex value. If pi state exists then the
  			 * owner TID must be the same as the user
  			 * space TID. [9/10]

  			 */

  			if (pid != task_pid_vnr(pi_state->owner))
  				return -EINVAL;

  		out_state:

  			atomic_inc(&pi_state->refcount);

  			*ps = pi_state;

  			return 0;
  		}
  	}
  
  	/*

  	 * We are the first waiter - try to look up the real owner and attach

  	 * the new pi_state to it, but bail out when TID = 0 [1]

  	 */

  	if (!pid)

  		return -ESRCH;

  	p = futex_find_get_task(pid);

  	if (!p)
  		return -ESRCH;

  	if (!p->mm) {
  		put_task_struct(p);
  		return -EPERM;
  	}

  	/*
  	 * We need to look at the task state flags to figure out,
  	 * whether the task is exiting. To protect against the do_exit
  	 * change of the task flags, we do this protected by
  	 * p->pi_lock:
  	 */

  	raw_spin_lock_irq(&p->pi_lock);

  	if (unlikely(p->flags & PF_EXITING)) {
  		/*
  		 * The task is on the way out. When PF_EXITPIDONE is
  		 * set, we know that the task has finished the
  		 * cleanup:
  		 */
  		int ret = (p->flags & PF_EXITPIDONE) ? -ESRCH : -EAGAIN;

  		raw_spin_unlock_irq(&p->pi_lock);

  		put_task_struct(p);
  		return ret;
  	}

  	/*
  	 * No existing pi state. First waiter. [2]
  	 */

  	pi_state = alloc_pi_state();
  
  	/*
  	 * Initialize the pi_mutex in locked state and make 'p'
  	 * the owner of it:
  	 */
  	rt_mutex_init_proxy_locked(&pi_state->pi_mutex, p);
  
  	/* Store the key for possible exit cleanups: */

  	pi_state->key = *key;

  	WARN_ON(!list_empty(&pi_state->list));

  	list_add(&pi_state->list, &p->pi_state_list);
  	pi_state->owner = p;

  	raw_spin_unlock_irq(&p->pi_lock);

  
  	put_task_struct(p);

  	*ps = pi_state;

  
  	return 0;
  }

  /**

   * futex_lock_pi_atomic() - Atomic work required to acquire a pi aware futex

   * @uaddr:		the pi futex user address
   * @hb:			the pi futex hash bucket
   * @key:		the futex key associated with uaddr and hb
   * @ps:			the pi_state pointer where we store the result of the
   *			lookup
   * @task:		the task to perform the atomic lock work for.  This will
   *			be "current" except in the case of requeue pi.
   * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)

   *

   * Return:
   *  0 - ready to wait;
   *  1 - acquired the lock;

   * <0 - error
   *
   * The hb->lock and futex_key refs shall be held by the caller.
   */
  static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
  				union futex_key *key,
  				struct futex_pi_state **ps,

  				struct task_struct *task, int set_waiters)

  {

  	int lock_taken, ret, force_take = 0;

  	u32 uval, newval, curval, vpid = task_pid_vnr(task);

  
  retry:
  	ret = lock_taken = 0;
  
  	/*
  	 * To avoid races, we attempt to take the lock here again
  	 * (by doing a 0 -> TID atomic cmpxchg), while holding all
  	 * the locks. It will most likely not succeed.
  	 */

  	newval = vpid;

  	if (set_waiters)
  		newval |= FUTEX_WAITERS;

  	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval)))

  		return -EFAULT;
  
  	/*
  	 * Detect deadlocks.
  	 */

  	if ((unlikely((curval & FUTEX_TID_MASK) == vpid)))

  		return -EDEADLK;
  
  	/*

  	 * Surprise - we got the lock, but we do not trust user space at all.

  	 */

  	if (unlikely(!curval)) {
  		/*
  		 * We verify whether there is kernel state for this
  		 * futex. If not, we can safely assume, that the 0 ->
  		 * TID transition is correct. If state exists, we do
  		 * not bother to fixup the user space state as it was
  		 * corrupted already.
  		 */
  		return futex_top_waiter(hb, key) ? -EINVAL : 1;
  	}

  
  	uval = curval;
  
  	/*
  	 * Set the FUTEX_WAITERS flag, so the owner will know it has someone
  	 * to wake at the next unlock.
  	 */
  	newval = curval | FUTEX_WAITERS;
  
  	/*

  	 * Should we force take the futex? See below.

  	 */

  	if (unlikely(force_take)) {
  		/*
  		 * Keep the OWNER_DIED and the WAITERS bit and set the
  		 * new TID value.
  		 */

  		newval = (curval & ~FUTEX_TID_MASK) | vpid;

  		force_take = 0;

  		lock_taken = 1;
  	}

  	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))

  		return -EFAULT;
  	if (unlikely(curval != uval))
  		goto retry;
  
  	/*

  	 * We took the lock due to forced take over.

  	 */
  	if (unlikely(lock_taken))
  		return 1;
  
  	/*
  	 * We dont have the lock. Look up the PI state (or create it if
  	 * we are the first waiter):
  	 */

  	ret = lookup_pi_state(uval, hb, key, ps);

  
  	if (unlikely(ret)) {
  		switch (ret) {
  		case -ESRCH:
  			/*

  			 * We failed to find an owner for this
  			 * futex. So we have no pi_state to block
  			 * on. This can happen in two cases:
  			 *
  			 * 1) The owner died
  			 * 2) A stale FUTEX_WAITERS bit
  			 *
  			 * Re-read the futex value.

  			 */
  			if (get_futex_value_locked(&curval, uaddr))
  				return -EFAULT;
  
  			/*

  			 * If the owner died or we have a stale
  			 * WAITERS bit the owner TID in the user space
  			 * futex is 0.

  			 */

  			if (!(curval & FUTEX_TID_MASK)) {
  				force_take = 1;

  				goto retry;
  			}
  		default:
  			break;
  		}
  	}
  
  	return ret;
  }

  /**
   * __unqueue_futex() - Remove the futex_q from its futex_hash_bucket
   * @q:	The futex_q to unqueue
   *
   * The q->lock_ptr must not be NULL and must be held by the caller.
   */
  static void __unqueue_futex(struct futex_q *q)
  {
  	struct futex_hash_bucket *hb;

  	if (WARN_ON_SMP(!q->lock_ptr || !spin_is_locked(q->lock_ptr))
  	    || WARN_ON(plist_node_empty(&q->list)))

  		return;
  
  	hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
  	plist_del(&q->list, &hb->chain);

  	hb_waiters_dec(hb);

  }

  /*

   * The hash bucket lock must be held when this is called.
   * Afterwards, the futex_q must not be accessed.
   */
  static void wake_futex(struct futex_q *q)
  {

  	struct task_struct *p = q->task;

  	if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex
  "))
  		return;

  	/*

  	 * We set q->lock_ptr = NULL _before_ we wake up the task. If

  	 * a non-futex wake up happens on another CPU then the task
  	 * might exit and p would dereference a non-existing task

  	 * struct. Prevent this by holding a reference on p across the
  	 * wake up.

  	 */

  	get_task_struct(p);

  	__unqueue_futex(q);

  	/*

  	 * The waiting task can free the futex_q as soon as
  	 * q->lock_ptr = NULL is written, without taking any locks. A
  	 * memory barrier is required here to prevent the following
  	 * store to lock_ptr from getting ahead of the plist_del.

  	 */

  	smp_wmb();

  	q->lock_ptr = NULL;

  
  	wake_up_state(p, TASK_NORMAL);
  	put_task_struct(p);

  }

  static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
  {
  	struct task_struct *new_owner;
  	struct futex_pi_state *pi_state = this->pi_state;

  	u32 uninitialized_var(curval), newval;

  	int ret = 0;

  
  	if (!pi_state)
  		return -EINVAL;

  	/*
  	 * If current does not own the pi_state then the futex is
  	 * inconsistent and user space fiddled with the futex value.
  	 */
  	if (pi_state->owner != current)
  		return -EINVAL;

  	raw_spin_lock(&pi_state->pi_mutex.wait_lock);

  	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
  
  	/*

  	 * It is possible that the next waiter (the one that brought
  	 * this owner to the kernel) timed out and is no longer
  	 * waiting on the lock.

  	 */
  	if (!new_owner)
  		new_owner = this->task;
  
  	/*

  	 * We pass it to the next owner. The WAITERS bit is always
  	 * kept enabled while there is PI state around. We cleanup the
  	 * owner died bit, because we are the owner.

  	 */

  	newval = FUTEX_WAITERS | task_pid_vnr(new_owner);

  	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
  		ret = -EFAULT;
  	else if (curval != uval)
  		ret = -EINVAL;
  	if (ret) {
  		raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
  		return ret;

  	}

  	raw_spin_lock_irq(&pi_state->owner->pi_lock);

  	WARN_ON(list_empty(&pi_state->list));
  	list_del_init(&pi_state->list);

  	raw_spin_unlock_irq(&pi_state->owner->pi_lock);

  	raw_spin_lock_irq(&new_owner->pi_lock);

  	WARN_ON(!list_empty(&pi_state->list));

  	list_add(&pi_state->list, &new_owner->pi_state_list);
  	pi_state->owner = new_owner;

  	raw_spin_unlock_irq(&new_owner->pi_lock);

  	raw_spin_unlock(&pi_state->pi_mutex.wait_lock);

  	rt_mutex_unlock(&pi_state->pi_mutex);
  
  	return 0;
  }
  
  static int unlock_futex_pi(u32 __user *uaddr, u32 uval)
  {

  	u32 uninitialized_var(oldval);

  
  	/*
  	 * There is no waiter, so we unlock the futex. The owner died
  	 * bit has not to be preserved here. We are the owner:
  	 */

  	if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0))
  		return -EFAULT;

  	if (oldval != uval)
  		return -EAGAIN;
  
  	return 0;
  }

  /*

   * Express the locking dependencies for lockdep:
   */
  static inline void
  double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
  {
  	if (hb1 <= hb2) {
  		spin_lock(&hb1->lock);
  		if (hb1 < hb2)
  			spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING);
  	} else { /* hb1 > hb2 */
  		spin_lock(&hb2->lock);
  		spin_lock_nested(&hb1->lock, SINGLE_DEPTH_NESTING);
  	}
  }

  static inline void
  double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
  {

  	spin_unlock(&hb1->lock);

  	if (hb1 != hb2)
  		spin_unlock(&hb2->lock);

  }

  /*

   * Wake up waiters matching bitset queued on this futex (uaddr).

   */

  static int
  futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)

  {

  	struct futex_hash_bucket *hb;

  	struct futex_q *this, *next;

  	union futex_key key = FUTEX_KEY_INIT;

  	int ret;

  	if (!bitset)
  		return -EINVAL;

  	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_READ);

  	if (unlikely(ret != 0))
  		goto out;

  	hb = hash_futex(&key);

  
  	/* Make sure we really have tasks to wakeup */
  	if (!hb_waiters_pending(hb))
  		goto out_put_key;

  	spin_lock(&hb->lock);

  	plist_for_each_entry_safe(this, next, &hb->chain, list) {

  		if (match_futex (&this->key, &key)) {

  			if (this->pi_state || this->rt_waiter) {

  				ret = -EINVAL;
  				break;
  			}

  
  			/* Check if one of the bits is set in both bitsets */
  			if (!(this->bitset & bitset))
  				continue;

  			wake_futex(this);
  			if (++ret >= nr_wake)
  				break;
  		}
  	}

  	spin_unlock(&hb->lock);

  out_put_key:

  	put_futex_key(&key);

  out:

  	return ret;
  }
  
  /*

   * Wake up all waiters hashed on the physical page that is mapped
   * to this virtual address:
   */

  static int

  futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,

  	      int nr_wake, int nr_wake2, int op)

  {

  	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;

  	struct futex_hash_bucket *hb1, *hb2;

  	struct futex_q *this, *next;

  	int ret, op_ret;

  retry:

  	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);

  	if (unlikely(ret != 0))
  		goto out;

  	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);

  	if (unlikely(ret != 0))

  		goto out_put_key1;

  	hb1 = hash_futex(&key1);
  	hb2 = hash_futex(&key2);

  retry_private:

  	double_lock_hb(hb1, hb2);

  	op_ret = futex_atomic_op_inuser(op, uaddr2);

  	if (unlikely(op_ret < 0)) {

  		double_unlock_hb(hb1, hb2);

  #ifndef CONFIG_MMU

  		/*
  		 * we don't get EFAULT from MMU faults if we don't have an MMU,
  		 * but we might get them from range checking
  		 */

  		ret = op_ret;

  		goto out_put_keys;

  #endif

  		if (unlikely(op_ret != -EFAULT)) {
  			ret = op_ret;

  			goto out_put_keys;

  		}

  		ret = fault_in_user_writeable(uaddr2);

  		if (ret)

  			goto out_put_keys;

  		if (!(flags & FLAGS_SHARED))

  			goto retry_private;

  		put_futex_key(&key2);
  		put_futex_key(&key1);

  		goto retry;

  	}

  	plist_for_each_entry_safe(this, next, &hb1->chain, list) {

  		if (match_futex (&this->key, &key1)) {

  			if (this->pi_state || this->rt_waiter) {
  				ret = -EINVAL;
  				goto out_unlock;
  			}

  			wake_futex(this);
  			if (++ret >= nr_wake)
  				break;
  		}
  	}
  
  	if (op_ret > 0) {

  		op_ret = 0;

  		plist_for_each_entry_safe(this, next, &hb2->chain, list) {

  			if (match_futex (&this->key, &key2)) {

  				if (this->pi_state || this->rt_waiter) {
  					ret = -EINVAL;
  					goto out_unlock;
  				}

  				wake_futex(this);
  				if (++op_ret >= nr_wake2)
  					break;
  			}
  		}
  		ret += op_ret;
  	}

  out_unlock:

  	double_unlock_hb(hb1, hb2);

  out_put_keys:

  	put_futex_key(&key2);

  out_put_key1:

  	put_futex_key(&key1);

  out:

  	return ret;
  }

  /**
   * requeue_futex() - Requeue a futex_q from one hb to another
   * @q:		the futex_q to requeue
   * @hb1:	the source hash_bucket
   * @hb2:	the target hash_bucket
   * @key2:	the new key for the requeued futex_q
   */
  static inline
  void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
  		   struct futex_hash_bucket *hb2, union futex_key *key2)
  {
  
  	/*
  	 * If key1 and key2 hash to the same bucket, no need to
  	 * requeue.
  	 */
  	if (likely(&hb1->chain != &hb2->chain)) {
  		plist_del(&q->list, &hb1->chain);

  		hb_waiters_dec(hb1);

  		plist_add(&q->list, &hb2->chain);

  		hb_waiters_inc(hb2);

  		q->lock_ptr = &hb2->lock;

  	}
  	get_futex_key_refs(key2);
  	q->key = *key2;
  }

  /**
   * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue

   * @q:		the futex_q
   * @key:	the key of the requeue target futex
   * @hb:		the hash_bucket of the requeue target futex

   *
   * During futex_requeue, with requeue_pi=1, it is possible to acquire the
   * target futex if it is uncontended or via a lock steal.  Set the futex_q key
   * to the requeue target futex so the waiter can detect the wakeup on the right
   * futex, but remove it from the hb and NULL the rt_waiter so it can detect

   * atomic lock acquisition.  Set the q->lock_ptr to the requeue target hb->lock
   * to protect access to the pi_state to fixup the owner later.  Must be called
   * with both q->lock_ptr and hb->lock held.

   */
  static inline

  void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
  			   struct futex_hash_bucket *hb)

  {

  	get_futex_key_refs(key);
  	q->key = *key;

  	__unqueue_futex(q);

  
  	WARN_ON(!q->rt_waiter);
  	q->rt_waiter = NULL;

  	q->lock_ptr = &hb->lock;

  	wake_up_state(q->task, TASK_NORMAL);

  }
  
  /**
   * futex_proxy_trylock_atomic() - Attempt an atomic lock for the top waiter

   * @pifutex:		the user address of the to futex
   * @hb1:		the from futex hash bucket, must be locked by the caller
   * @hb2:		the to futex hash bucket, must be locked by the caller
   * @key1:		the from futex key
   * @key2:		the to futex key
   * @ps:			address to store the pi_state pointer
   * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)

   *
   * Try and get the lock on behalf of the top waiter if we can do it atomically.

   * Wake the top waiter if we succeed.  If the caller specified set_waiters,
   * then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit.
   * hb1 and hb2 must be held by the caller.

   *

   * Return:
   *  0 - failed to acquire the lock atomically;

   * >0 - acquired the lock, return value is vpid of the top_waiter

   * <0 - error
   */
  static int futex_proxy_trylock_atomic(u32 __user *pifutex,
  				 struct futex_hash_bucket *hb1,
  				 struct futex_hash_bucket *hb2,
  				 union futex_key *key1, union futex_key *key2,

  				 struct futex_pi_state **ps, int set_waiters)

  {

  	struct futex_q *top_waiter = NULL;

  	u32 curval;

  	int ret, vpid;

  
  	if (get_futex_value_locked(&curval, pifutex))
  		return -EFAULT;

  	/*
  	 * Find the top_waiter and determine if there are additional waiters.
  	 * If the caller intends to requeue more than 1 waiter to pifutex,
  	 * force futex_lock_pi_atomic() to set the FUTEX_WAITERS bit now,
  	 * as we have means to handle the possible fault.  If not, don't set
  	 * the bit unecessarily as it will force the subsequent unlock to enter
  	 * the kernel.
  	 */

  	top_waiter = futex_top_waiter(hb1, key1);
  
  	/* There are no waiters, nothing for us to do. */
  	if (!top_waiter)
  		return 0;

  	/* Ensure we requeue to the expected futex. */
  	if (!match_futex(top_waiter->requeue_pi_key, key2))
  		return -EINVAL;

  	/*

  	 * Try to take the lock for top_waiter.  Set the FUTEX_WAITERS bit in
  	 * the contended case or if set_waiters is 1.  The pi_state is returned
  	 * in ps in contended cases.

  	 */

  	vpid = task_pid_vnr(top_waiter->task);

  	ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
  				   set_waiters);

  	if (ret == 1) {

  		requeue_pi_wake_futex(top_waiter, key2, hb2);

  		return vpid;
  	}

  	return ret;
  }
  
  /**
   * futex_requeue() - Requeue waiters from uaddr1 to uaddr2

   * @uaddr1:	source futex user address

   * @flags:	futex flags (FLAGS_SHARED, etc.)

   * @uaddr2:	target futex user address
   * @nr_wake:	number of waiters to wake (must be 1 for requeue_pi)
   * @nr_requeue:	number of waiters to requeue (0-INT_MAX)
   * @cmpval:	@uaddr1 expected value (or %NULL)
   * @requeue_pi:	if we are attempting to requeue from a non-pi futex to a

   *		pi futex (pi to pi requeue is not supported)

   *
   * Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire
   * uaddr2 atomically on behalf of the top waiter.
   *

   * Return:
   * >=0 - on success, the number of tasks requeued or woken;

   *  <0 - on error

   */

  static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
  			 u32 __user *uaddr2, int nr_wake, int nr_requeue,
  			 u32 *cmpval, int requeue_pi)

  {

  	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;

  	int drop_count = 0, task_count = 0, ret;
  	struct futex_pi_state *pi_state = NULL;

  	struct futex_hash_bucket *hb1, *hb2;

  	struct futex_q *this, *next;

  
  	if (requeue_pi) {
  		/*

  		 * Requeue PI only works on two distinct uaddrs. This
  		 * check is only valid for private futexes. See below.
  		 */
  		if (uaddr1 == uaddr2)
  			return -EINVAL;
  
  		/*

  		 * requeue_pi requires a pi_state, try to allocate it now
  		 * without any locks in case it fails.
  		 */
  		if (refill_pi_state_cache())
  			return -ENOMEM;
  		/*
  		 * requeue_pi must wake as many tasks as it can, up to nr_wake
  		 * + nr_requeue, since it acquires the rt_mutex prior to
  		 * returning to userspace, so as to not leave the rt_mutex with
  		 * waiters and no owner.  However, second and third wake-ups
  		 * cannot be predicted as they involve race conditions with the
  		 * first wake and a fault while looking up the pi_state.  Both
  		 * pthread_cond_signal() and pthread_cond_broadcast() should
  		 * use nr_wake=1.
  		 */
  		if (nr_wake != 1)
  			return -EINVAL;
  	}

  retry:

  	if (pi_state != NULL) {
  		/*
  		 * We will have to lookup the pi_state again, so free this one
  		 * to keep the accounting correct.
  		 */
  		free_pi_state(pi_state);
  		pi_state = NULL;
  	}

  	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);

  	if (unlikely(ret != 0))
  		goto out;

  	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2,
  			    requeue_pi ? VERIFY_WRITE : VERIFY_READ);

  	if (unlikely(ret != 0))

  		goto out_put_key1;

  	/*
  	 * The check above which compares uaddrs is not sufficient for
  	 * shared futexes. We need to compare the keys:
  	 */
  	if (requeue_pi && match_futex(&key1, &key2)) {
  		ret = -EINVAL;
  		goto out_put_keys;
  	}

  	hb1 = hash_futex(&key1);
  	hb2 = hash_futex(&key2);

  retry_private:

  	hb_waiters_inc(hb2);

  	double_lock_hb(hb1, hb2);

  	if (likely(cmpval != NULL)) {
  		u32 curval;

  		ret = get_futex_value_locked(&curval, uaddr1);

  
  		if (unlikely(ret)) {

  			double_unlock_hb(hb1, hb2);

  			hb_waiters_dec(hb2);

  			ret = get_user(curval, uaddr1);

  			if (ret)
  				goto out_put_keys;

  			if (!(flags & FLAGS_SHARED))

  				goto retry_private;

  			put_futex_key(&key2);
  			put_futex_key(&key1);

  			goto retry;

  		}

  		if (curval != *cmpval) {

  			ret = -EAGAIN;
  			goto out_unlock;
  		}
  	}

  	if (requeue_pi && (task_count - nr_wake < nr_requeue)) {

  		/*
  		 * Attempt to acquire uaddr2 and wake the top waiter. If we
  		 * intend to requeue waiters, force setting the FUTEX_WAITERS
  		 * bit.  We force this here where we are able to easily handle
  		 * faults rather in the requeue loop below.
  		 */

  		ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1,

  						 &key2, &pi_state, nr_requeue);

  
  		/*
  		 * At this point the top_waiter has either taken uaddr2 or is
  		 * waiting on it.  If the former, then the pi_state will not
  		 * exist yet, look it up one more time to ensure we have a

  		 * reference to it. If the lock was taken, ret contains the
  		 * vpid of the top waiter task.

  		 */

  		if (ret > 0) {

  			WARN_ON(pi_state);

  			drop_count++;

  			task_count++;

  			/*
  			 * If we acquired the lock, then the user
  			 * space value of uaddr2 should be vpid. It
  			 * cannot be changed by the top waiter as it
  			 * is blocked on hb2 lock if it tries to do
  			 * so. If something fiddled with it behind our
  			 * back the pi state lookup might unearth
  			 * it. So we rather use the known value than
  			 * rereading and handing potential crap to
  			 * lookup_pi_state.
  			 */

  			ret = lookup_pi_state(ret, hb2, &key2, &pi_state);

  		}
  
  		switch (ret) {
  		case 0:
  			break;
  		case -EFAULT:
  			double_unlock_hb(hb1, hb2);

  			hb_waiters_dec(hb2);

  			put_futex_key(&key2);
  			put_futex_key(&key1);

  			ret = fault_in_user_writeable(uaddr2);

  			if (!ret)
  				goto retry;
  			goto out;
  		case -EAGAIN:
  			/* The owner was exiting, try again. */
  			double_unlock_hb(hb1, hb2);

  			hb_waiters_dec(hb2);

  			put_futex_key(&key2);
  			put_futex_key(&key1);

  			cond_resched();
  			goto retry;
  		default:
  			goto out_unlock;
  		}
  	}

  	plist_for_each_entry_safe(this, next, &hb1->chain, list) {

  		if (task_count - nr_wake >= nr_requeue)
  			break;
  
  		if (!match_futex(&this->key, &key1))

  			continue;

  		/*
  		 * FUTEX_WAIT_REQEUE_PI and FUTEX_CMP_REQUEUE_PI should always
  		 * be paired with each other and no other futex ops.

  		 *
  		 * We should never be requeueing a futex_q with a pi_state,
  		 * which is awaiting a futex_unlock_pi().

  		 */
  		if ((requeue_pi && !this->rt_waiter) ||

  		    (!requeue_pi && this->rt_waiter) ||
  		    this->pi_state) {

  			ret = -EINVAL;
  			break;
  		}

  
  		/*
  		 * Wake nr_wake waiters.  For requeue_pi, if we acquired the
  		 * lock, we already woke the top_waiter.  If not, it will be
  		 * woken by futex_unlock_pi().
  		 */
  		if (++task_count <= nr_wake && !requeue_pi) {

  			wake_futex(this);

  			continue;
  		}

  		/* Ensure we requeue to the expected futex for requeue_pi. */
  		if (requeue_pi && !match_futex(this->requeue_pi_key, &key2)) {
  			ret = -EINVAL;
  			break;
  		}

  		/*
  		 * Requeue nr_requeue waiters and possibly one more in the case
  		 * of requeue_pi if we couldn't acquire the lock atomically.
  		 */
  		if (requeue_pi) {
  			/* Prepare the waiter to take the rt_mutex. */
  			atomic_inc(&pi_state->refcount);
  			this->pi_state = pi_state;
  			ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
  							this->rt_waiter,
  							this->task, 1);
  			if (ret == 1) {
  				/* We got the lock. */

  				requeue_pi_wake_futex(this, &key2, hb2);

  				drop_count++;

  				continue;
  			} else if (ret) {
  				/* -EDEADLK */
  				this->pi_state = NULL;
  				free_pi_state(pi_state);
  				goto out_unlock;
  			}

  		}

  		requeue_futex(this, hb1, hb2, &key2);
  		drop_count++;

  	}
  
  out_unlock:

  	double_unlock_hb(hb1, hb2);

  	hb_waiters_dec(hb2);

  	/*
  	 * drop_futex_key_refs() must be called outside the spinlocks. During
  	 * the requeue we moved futex_q's from the hash bucket at key1 to the
  	 * one at key2 and updated their key pointer.  We no longer need to
  	 * hold the references to key1.
  	 */

  	while (--drop_count >= 0)

  		drop_futex_key_refs(&key1);

  out_put_keys:

  	put_futex_key(&key2);

  out_put_key1:

  	put_futex_key(&key1);

  out:

  	if (pi_state != NULL)
  		free_pi_state(pi_state);
  	return ret ? ret : task_count;

  }
  
  /* The key must be already stored in q->key. */

  static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)

  	__acquires(&hb->lock)

  {

  	struct futex_hash_bucket *hb;

  	hb = hash_futex(&q->key);

  
  	/*
  	 * Increment the counter before taking the lock so that
  	 * a potential waker won't miss a to-be-slept task that is
  	 * waiting for the spinlock. This is safe as all queue_lock()
  	 * users end up calling queue_me(). Similarly, for housekeeping,
  	 * decrement the counter at queue_unlock() when some error has
  	 * occurred and we don't end up adding the task to the list.
  	 */
  	hb_waiters_inc(hb);

  	q->lock_ptr = &hb->lock;

  	spin_lock(&hb->lock); /* implies MB (A) */

  	return hb;

  }

  static inline void

  queue_unlock(struct futex_hash_bucket *hb)

  	__releases(&hb->lock)

  {
  	spin_unlock(&hb->lock);

  	hb_waiters_dec(hb);

  }
  
  /**
   * queue_me() - Enqueue the futex_q on the futex_hash_bucket
   * @q:	The futex_q to enqueue
   * @hb:	The destination hash bucket
   *
   * The hb->lock must be held by the caller, and is released here. A call to
   * queue_me() is typically paired with exactly one call to unqueue_me().  The
   * exceptions involve the PI related operations, which may use unqueue_me_pi()
   * or nothing if the unqueue is done as part of the wake process and the unqueue
   * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
   * an example).
   */

  static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)

  	__releases(&hb->lock)