Merge branch 'locking/urgent' into locking/core

Reason: Required to add more rtmutex robustness changes on top of
those already in mainline.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

3 files changed, 218 insertions, 35 deletions

diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h
index 14193d596d78..ab29b6a22669 100644
--- a/kernel/locking/rtmutex-debug.h
+++ b/kernel/locking/rtmutex-debug.h
@@ -31,3 +31,8 @@ static inline int debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
 {
         return (waiter != NULL);
 }
+
+static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
+{
+        debug_rt_mutex_print_deadlock(w);
+}
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index a620d4d08ca6..fc605941b9b8 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -83,6 +83,47 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
                 owner = *p;
         } while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner);
 }
+
+/*
+ * Safe fastpath aware unlock:
+ * 1) Clear the waiters bit
+ * 2) Drop lock->wait_lock
+ * 3) Try to unlock the lock with cmpxchg
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+        __releases(lock->wait_lock)
+{
+        struct task_struct *owner = rt_mutex_owner(lock);
+
+        clear_rt_mutex_waiters(lock);
+        raw_spin_unlock(&lock->wait_lock);
+        /*
+         * If a new waiter comes in between the unlock and the cmpxchg
+         * we have two situations:
+         *
+         * unlock(wait_lock);
+         *                                      lock(wait_lock);
+         * cmpxchg(p, owner, 0) == owner
+         *                                      mark_rt_mutex_waiters(lock);
+         *                                      acquire(lock);
+         * or:
+         *
+         * unlock(wait_lock);
+         *                                      lock(wait_lock);
+         *                                      mark_rt_mutex_waiters(lock);
+         *
+         * cmpxchg(p, owner, 0) != owner
+         *                                      enqueue_waiter();
+         *                                      unlock(wait_lock);
+         * lock(wait_lock);
+         * wake waiter();
+         * unlock(wait_lock);
+         *                                      lock(wait_lock);
+         *                                      acquire(lock);
+         */
+        return rt_mutex_cmpxchg(lock, owner, NULL);
+}
+
 #else
 # define rt_mutex_cmpxchg(l,c,n)        (0)
 static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
@@ -90,6 +131,17 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
         lock->owner = (struct task_struct *)
                         ((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS);
 }
+
+/*
+ * Simple slow path only version: lock->owner is protected by lock->wait_lock.
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+        __releases(lock->wait_lock)
+{
+        lock->owner = NULL;
+        raw_spin_unlock(&lock->wait_lock);
+        return true;
+}
 #endif
 
 static inline int
@@ -260,27 +312,36 @@ static void rt_mutex_adjust_prio(struct task_struct *task)
  */
 int max_lock_depth = 1024;
 
+static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
+{
+        return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
+}
+
 /*
  * Adjust the priority chain. Also used for deadlock detection.
  * Decreases task's usage by one - may thus free the task.
  *
- * @task: the task owning the mutex (owner) for which a chain walk is probably
- *        needed
+ * @task:       the task owning the mutex (owner) for which a chain walk is
+ *              probably needed
  * @deadlock_detect: do we have to carry out deadlock detection?
- * @orig_lock: the mutex (can be NULL if we are walking the chain to recheck
- *             things for a task that has just got its priority adjusted, and
- *             is waiting on a mutex)
+ * @orig_lock:  the mutex (can be NULL if we are walking the chain to recheck
+ *              things for a task that has just got its priority adjusted, and
+ *              is waiting on a mutex)
+ * @next_lock:  the mutex on which the owner of @orig_lock was blocked before
+ *              we dropped its pi_lock. Is never dereferenced, only used for
+ *              comparison to detect lock chain changes.
  * @orig_waiter: rt_mutex_waiter struct for the task that has just donated
- *               its priority to the mutex owner (can be NULL in the case
- *               depicted above or if the top waiter is gone away and we are
- *               actually deboosting the owner)
- * @top_task: the current top waiter
+ *              its priority to the mutex owner (can be NULL in the case
+ *              depicted above or if the top waiter is gone away and we are
+ *              actually deboosting the owner)
+ * @top_task:   the current top waiter
  *
  * Returns 0 or -EDEADLK.
  */
 static int rt_mutex_adjust_prio_chain(struct task_struct *task,
                                       int deadlock_detect,
                                       struct rt_mutex *orig_lock,
+                                      struct rt_mutex *next_lock,
                                       struct rt_mutex_waiter *orig_waiter,
                                       struct task_struct *top_task)
 {
@@ -314,7 +375,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
                 }
                 put_task_struct(task);
 
-                return deadlock_detect ? -EDEADLK : 0;
+                return -EDEADLK;
         }
  retry:
         /*
@@ -339,6 +400,18 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
                 goto out_unlock_pi;
 
         /*
+         * We dropped all locks after taking a refcount on @task, so
+         * the task might have moved on in the lock chain or even left
+         * the chain completely and blocks now on an unrelated lock or
+         * on @orig_lock.
+         *
+         * We stored the lock on which @task was blocked in @next_lock,
+         * so we can detect the chain change.
+         */
+        if (next_lock != waiter->lock)
+                goto out_unlock_pi;
+
+        /*
          * Drop out, when the task has no waiters. Note,
          * top_waiter can be NULL, when we are in the deboosting
          * mode!
@@ -377,7 +450,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
         if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
                 debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
                 raw_spin_unlock(&lock->wait_lock);
-                ret = deadlock_detect ? -EDEADLK : 0;
+                ret = -EDEADLK;
                 goto out_unlock_pi;
         }
 
@@ -422,11 +495,26 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
                 __rt_mutex_adjust_prio(task);
         }
 
+        /*
+         * Check whether the task which owns the current lock is pi
+         * blocked itself. If yes we store a pointer to the lock for
+         * the lock chain change detection above. After we dropped
+         * task->pi_lock next_lock cannot be dereferenced anymore.