1 files changed, 92 insertions, 68 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index 248dd119a86e..fb65e822fc41 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -89,36 +89,36 @@ struct futex_pi_state {
         union futex_key key;
 };
 
-/*
- * We use this hashed waitqueue instead of a normal wait_queue_t, so
+/**
+ * struct futex_q - The hashed futex queue entry, one per waiting task
+ * @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 wakup is always to make the first condition true, then
- * wake up q->waiter, then make the second condition true.
+ * 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;
-        /* Waiter reference */
-        struct task_struct *task;
 
-        /* Which hash list lock to use: */
+        struct task_struct *task;
         spinlock_t *lock_ptr;
-
-        /* Key which the futex is hashed on: */
         union futex_key key;
-
-        /* Optional priority inheritance state: */
         struct futex_pi_state *pi_state;
-
-        /* rt_waiter storage for requeue_pi: */
         struct rt_mutex_waiter *rt_waiter;
-
-        /* The expected requeue pi target futex key: */
         union futex_key *requeue_pi_key;
-
-        /* Bitset for the optional bitmasked wakeup */
         u32 bitset;
 };
 
@@ -150,7 +150,8 @@ static struct futex_hash_bucket *hash_futex(union futex_key *key)
  */
 static inline int match_futex(union futex_key *key1, union futex_key *key2)
 {
-        return (key1->both.word == key2->both.word
+        return (key1 && key2
+                && key1->both.word == key2->both.word
                 && key1->both.ptr == key2->both.ptr
                 && key1->both.offset == key2->both.offset);
 }
@@ -198,11 +199,12 @@ static void drop_futex_key_refs(union futex_key *key)
 }
 
 /**
- * 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)
+ * 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)
  *
  * Returns a negative error code or 0
  * The key words are stored in *key on success.
@@ -288,8 +290,8 @@ void put_futex_key(int fshared, union futex_key *key)
         drop_futex_key_refs(key);
 }
 
-/*
- * fault_in_user_writeable - fault in user address and verify RW access
+/**
+ * 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
@@ -309,8 +311,8 @@ static int fault_in_user_writeable(u32 __user *uaddr)
 
 /**
  * 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)
+ * @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.
  */
@@ -588,7 +590,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 }
 
 /**
- * futex_lock_pi_atomic() - atomic work required to acquire a pi aware futex
+ * 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
@@ -915,8 +917,8 @@ retry:
         hb1 = hash_futex(&key1);
         hb2 = hash_futex(&key2);
 
-        double_lock_hb(hb1, hb2);
 retry_private:
+        double_lock_hb(hb1, hb2);
         op_ret = futex_atomic_op_inuser(op, uaddr2);
         if (unlikely(op_ret < 0)) {
 
@@ -1011,9 +1013,9 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
 
 /**
  * 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
+ * @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
@@ -1027,7 +1029,6 @@ static inline
 void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
                            struct futex_hash_bucket *hb)
 {
-        drop_futex_key_refs(&q->key);
         get_futex_key_refs(key);
         q->key = *key;
 
@@ -1225,6 +1226,7 @@ retry_private:
                  */
                 if (ret == 1) {
                         WARN_ON(pi_state);
+                        drop_count++;
                         task_count++;
                         ret = get_futex_value_locked(&curval2, uaddr2);
                         if (!ret)
@@ -1303,6 +1305,7 @@ retry_private:
                         if (ret == 1) {
                                 /* We got the lock. */
                                 requeue_pi_wake_futex(this, &key2, hb2);
+                                drop_count++;
                                 continue;
                         } else if (ret) {
                                 /* -EDEADLK */
@@ -1350,6 +1353,25 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
         return hb;
 }
 
+static inline void
+queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
+{
+        spin_unlock(&hb->lock);
+        drop_futex_key_refs(&q->key);
+}
+
+/**
+ * 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)
 {
         int prio;
@@ -1373,19 +1395,17 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
         spin_unlock(&hb->lock);
 }
 
-static inline void
-queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
-{
-        spin_unlock(&hb->lock);
-        drop_futex_key_refs(&q->key);
-}
-
-/*
- * queue_me and unqueue_me must be called as a pair, each
- * exactly once.  They are called with the hashed spinlock held.
+/**
+ * unqueue_me() - Remove the futex_q from its futex_hash_bucket
+ * @q:  The futex_q to unqueue
+ *
+ * The q->lock_ptr must not be held by the caller. A call to unqueue_me() must
+ * be paired with exactly one earlier call to queue_me().
+ *
+ * Returns:
+ *   1 - if the futex_q was still queued (and we removed unqueued it)
+ *   0 - if the futex_q was already removed by the waking thread
  */
-
-/* Return 1 if we were still queued (ie. 0 means we were woken) */
 static int unqueue_me(struct futex_q *q)
 {
         spinlock_t *lock_ptr;
@@ -1638,17 +1658,14 @@ out:
 static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
                                 struct hrtimer_sleeper *timeout)
 {
-        queue_me(q, hb);
-
         /*
-         * There might have been scheduling since the queue_me(), as we
-         * cannot hold a spinlock across the get_user() in case it
-         * faults, and we cannot just set TASK_INTERRUPTIBLE state when
-         * queueing ourselves into the futex hash. This code thus has to
-         * rely on the futex_wake() code removing us from hash when it
-         * wakes us up.
+         * The task state is guaranteed to be set before another task can
+         * wake it. set_current_state() is implemented using set_mb() and
+         * queue_me() calls spin_unlock() upon completion, both serializing
+         * access to the hash list and forcing another memory barrier.
          */
         set_current_state(TASK_INTERRUPTIBLE);
+        queue_me(q, hb);
 
         /* Arm the timer */
         if (timeout) {
@@ -1658,8 +1675,8 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
         }
 
         /*
-         * !plist_node_empty() is safe here without any lock.
-         * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
+         * If we have been removed from the hash list, then another task
+         * has tried to wake us, and we can skip the call to schedule().
          */
         if (likely(!plist_node_empty(&q->list))) {
                 /*
@@ -1776,6 +1793,7 @@ static int futex_wait(u32 __user *uaddr, int fshared,
                                              current->timer_slack_ns);
         }
 
+retry:
         /* Prepare to wait on uaddr. */
         ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
         if (ret)
@@ -1793,9 +1811,14 @@ static int futex_wait(u32 __user *uaddr, int fshared,
                 goto out_put_key;
 
         /*
-         * We expect signal_pending(current), but another thread may
-         * have handled it for us already.
+         * We expect signal_pending(current), but we might be the
+         * victim of a spurious wakeup as well.
          */
+        if (!signal_pending(current)) {
+                put_futex_key(fshared, &q.key);
+                goto retry;
+        }
+
         ret = -ERESTARTSYS;
         if (!abs_time)
                 goto out_put_key;
@@ -2102,11 +2125,12 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
                  * Unqueue the futex_q and determine which it was.
                  */
                 plist_del(&q->list, &q->list.plist);
-                drop_futex_key_refs(&q->key);
 
+                /* Handle spurious wakeups gracefully */
+                ret = -EWOULDBLOCK;
                 if (timeout && !timeout->task)
                         ret = -ETIMEDOUT;
-                else
+                else if (signal_pending(current))
                         ret = -ERESTARTNOINTR;
         }
         return ret;
@@ -2114,12 +2138,12 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
 
 /**
  * futex_wait_requeue_pi() - Wait on uaddr and take uaddr2
- * @uaddr:      the futex we initialyl wait on (non-pi)
+ * @uaddr:      the futex we initially wait on (non-pi)
  * @fshared:    whether the futexes are shared (1) or not (0).  They must be
  *              the same type, no requeueing from private to shared, etc.
  * @val:        the expected value of uaddr
  * @abs_time:   absolute timeout
- * @bitset:     32 bit wakeup bitset set by userspace, defaults to all.
+ * @bitset:     32 bit wakeup bitset set by userspace, defaults to all
  * @clockrt:    whether to use CLOCK_REALTIME (1) or CLOCK_MONOTONIC (0)
  * @uaddr2:     the pi futex we will take prior to returning to user-space
  *
@@ -2246,7 +2270,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
                 res = fixup_owner(uaddr2, fshared, &q, !ret);
                 /*
                  * If fixup_owner() returned an error, proprogate that.  If it
-                 * acquired the lock, clear our -ETIMEDOUT or -EINTR.
+                 * acquired the lock, clear -ETIMEDOUT or -EINTR.
                  */
                 if (res)
                         ret = (res < 0) ? res : 0;
@@ -2302,9 +2326,9 @@ out:
  */
 
 /**
- * sys_set_robust_list - set the robust-futex list head of a task
- * @head: pointer to the list-head
- * @len: length of the list-head, as userspace expects
+ * sys_set_robust_list() - Set the robust-futex list head of a task
+ * @head:       pointer to the list-head
+ * @len:        length of the list-head, as userspace expects
  */
 SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head,
                 size_t, len)
@@ -2323,10 +2347,10 @@ SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head,
 }
 
 /**
- * sys_get_robust_list - get the robust-futex list head of a task
- * @pid: pid of the process [zero for current task]
- * @head_ptr: pointer to a list-head pointer, the kernel fills it in
- * @len_ptr: pointer to a length field, the kernel fills in the header size
+ * sys_get_robust_list() - Get the robust-futex list head of a task
+ * @pid:        pid of the process [zero for current task]
+ * @head_ptr:   pointer to a list-head pointer, the kernel fills it in
+ * @len_ptr:    pointer to a length field, the kernel fills in the header size
  */
 SYSCALL_DEFINE3(get_robust_list, int, pid,
                 struct robust_list_head __user * __user *, head_ptr,