3 files changed, 63 insertions, 11 deletions

diff --git a/include/linux/wait.h b/include/linux/wait.h
index ef609f842fac..a210ede73b56 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -132,6 +132,8 @@ static inline void __remove_wait_queue(wait_queue_head_t *head,
         list_del(&old->task_list);
 }
 
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+                        int nr_exclusive, int sync, void *key);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 extern void __wake_up_locked(wait_queue_head_t *q, unsigned int mode);
 extern void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
@@ -333,16 +335,19 @@ do {									\
         for (;;) {                                                      \
                 prepare_to_wait_exclusive(&wq, &__wait,                 \
                                         TASK_INTERRUPTIBLE);            \
-                if (condition)                                          \
+                if (condition) {                                        \
+                        finish_wait(&wq, &__wait);                      \
                         break;                                          \
+                }                                                       \
                 if (!signal_pending(current)) {                         \
                         schedule();                                     \
                         continue;                                       \
                 }                                                       \
                 ret = -ERESTARTSYS;                                     \
+                abort_exclusive_wait(&wq, &__wait,                      \
+                                TASK_INTERRUPTIBLE, NULL);              \
                 break;                                                  \
         }                                                               \
-        finish_wait(&wq, &__wait);                                      \
 } while (0)
 
 #define wait_event_interruptible_exclusive(wq, condition)               \
@@ -431,6 +436,8 @@ extern long interruptible_sleep_on_timeout(wait_queue_head_t *q,
 void prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
+void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
+                        unsigned int mode, void *key);
 int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 242d0d47a70d..8ee437a5ec1d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4697,8 +4697,8 @@ EXPORT_SYMBOL(default_wake_function);
  * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
-static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
-                             int nr_exclusive, int sync, void *key)
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+                        int nr_exclusive, int sync, void *key)
 {
         wait_queue_t *curr, *next;
 
diff --git a/kernel/wait.c b/kernel/wait.c
index cd87131f2fc2..42a2dbc181c8 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -91,6 +91,15 @@ prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
 }
 EXPORT_SYMBOL(prepare_to_wait_exclusive);
 
+/*
+ * finish_wait - clean up after waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ */
 void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
 {
         unsigned long flags;
@@ -117,6 +126,39 @@ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
 }
 EXPORT_SYMBOL(finish_wait);
 
+/*
+ * abort_exclusive_wait - abort exclusive waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ * @state: runstate of the waiter to be woken
+ * @key: key to identify a wait bit queue or %NULL
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ *
+ * Wakes up the next waiter if the caller is concurrently
+ * woken up through the queue.
+ *
+ * This prevents waiter starvation where an exclusive waiter
+ * aborts and is woken up concurrently and noone wakes up
+ * the next waiter.
+ */
+void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
+                        unsigned int mode, void *key)
+{
+        unsigned long flags;
+
+        __set_current_state(TASK_RUNNING);
+        spin_lock_irqsave(&q->lock, flags);
+        if (!list_empty(&wait->task_list))
+                list_del_init(&wait->task_list);
+        else if (waitqueue_active(q))
+                __wake_up_common(q, mode, 1, 0, key);
+        spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(abort_exclusive_wait);
+
 int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
 {
         int ret = default_wake_function(wait, mode, sync, key);
@@ -177,17 +219,20 @@ int __sched
 __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
                         int (*action)(void *), unsigned mode)
 {
-        int ret = 0;
-
         do {
+                int ret;
+
                 prepare_to_wait_exclusive(wq, &q->wait, mode);
-                if (test_bit(q->key.bit_nr, q->key.flags)) {
-                        if ((ret = (*action)(q->key.flags)))
-                                break;
-                }
+                if (!test_bit(q->key.bit_nr, q->key.flags))
+                        continue;
+                ret = action(q->key.flags);
+                if (!ret)
+                        continue;
+                abort_exclusive_wait(wq, &q->wait, mode, &q->key);
+                return ret;
         } while (test_and_set_bit(q->key.bit_nr, q->key.flags));
         finish_wait(wq, &q->wait);
-        return ret;
+        return 0;
 }
 EXPORT_SYMBOL(__wait_on_bit_lock);