[rlc-9/5.14.0-687.17.1.el9_8] Multiple patches tested (11 commits)

fs/eventpoll.c

@@ -225,6 +225,9 @@ struct eventpoll {
 	 */
 	refcount_t refcount;
 
+	/* used to defer freeing past ep_get_upwards_depth_proc() RCU walk */
+	struct rcu_head rcu;
+
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	/* used to track busy poll napi_id */
 	unsigned int napi_id;
@@ -708,41 +711,54 @@ static void ep_free(struct eventpoll *ep)
 	mutex_destroy(&ep->mtx);
 	free_uid(ep->user);
 	wakeup_source_unregister(ep->ws);
-	kfree(ep);
+	/* ep_get_upwards_depth_proc() may still hold epi->ep under RCU */
+	kfree_rcu(ep, rcu);
 }
 
 /*
- * Removes a "struct epitem" from the eventpoll RB tree and deallocates
- * all the associated resources. Must be called with "mtx" held.
- * If the dying flag is set, do the removal only if force is true.
- * This prevents ep_clear_and_put() from dropping all the ep references
- * while running concurrently with eventpoll_release_file().
- * Returns true if the eventpoll can be disposed.
+ * The ffd.file pointer may be in the process of being torn down due to
+ * being closed, but we may not have finished eventpoll_release() yet.
+ *
+ * Normally, even with the atomic_long_inc_not_zero, the file may have
+ * been free'd and then gotten re-allocated to something else (since
+ * files are not RCU-delayed, they are SLAB_TYPESAFE_BY_RCU).
+ *
+ * But for epoll, users hold the ep->mtx mutex, and as such any file in
+ * the process of being free'd will block in eventpoll_release_file()
+ * and thus the underlying file allocation will not be free'd, and the
+ * file re-use cannot happen.
+ *
+ * For the same reason we can avoid a rcu_read_lock() around the
+ * operation - 'ffd.file' cannot go away even if the refcount has
+ * reached zero (but we must still not call out to ->poll() functions
+ * etc).
  */
-static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
+static struct file *epi_fget(const struct epitem *epi)
 {
-	struct file *file = epi->ffd.file;
-	struct epitems_head *to_free;
-	struct hlist_head *head;
+	struct file *file;
 
-	lockdep_assert_irqs_enabled();
+	file = epi->ffd.file;
+	if (!atomic_long_inc_not_zero(&file->f_count))
+		file = NULL;
+	return file;
+}
 
-	/*
-	 * Removes poll wait queue hooks.
-	 */
-	ep_unregister_pollwait(ep, epi);
+/*
+ * Called with &file->f_lock held,
+ * returns with it released
+ */
+static void ep_remove_file(struct eventpoll *ep, struct epitem *epi,
+			     struct file *file)
+{
+	struct epitems_head *to_free = NULL;
+	struct hlist_head *head = file->f_ep;
 
-	/* Remove the current item from the list of epoll hooks */
-	spin_lock(&file->f_lock);
-	if (epi->dying && !force) {
-		spin_unlock(&file->f_lock);
-		return false;
-	}
+	lockdep_assert_held(&ep->mtx);
+	lockdep_assert_held(&file->f_lock);
 
-	to_free = NULL;
-	head = file->f_ep;
-	if (head->first == &epi->fllink && !epi->fllink.next) {
-		file->f_ep = NULL;
+	if (hlist_is_singular_node(&epi->fllink, head)) {
+		/* See eventpoll_release() for details. */
+		WRITE_ONCE(file->f_ep, NULL);
 		if (!is_file_epoll(file)) {
 			struct epitems_head *v;
 			v = container_of(head, struct epitems_head, epitems);
@@ -753,6 +769,11 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
 	hlist_del_rcu(&epi->fllink);
 	spin_unlock(&file->f_lock);
 	free_ephead(to_free);
+}
+
+static bool ep_remove_epi(struct eventpoll *ep, struct epitem *epi)
+{
+	lockdep_assert_held(&ep->mtx);
 
 	rb_erase_cached(&epi->rbn, &ep->rbr);
 
@@ -778,9 +799,31 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
 /*
  * ep_remove variant for callers owing an additional reference to the ep
  */
-static void ep_remove_safe(struct eventpoll *ep, struct epitem *epi)
+static void ep_remove(struct eventpoll *ep, struct epitem *epi)
 {
-	if (__ep_remove(ep, epi, false))
+	struct file *file __free(fput) = NULL;
+
+	lockdep_assert_irqs_enabled();
+	lockdep_assert_held(&ep->mtx);
+
+	ep_unregister_pollwait(ep, epi);
+
+	/* cheap sync with eventpoll_release_file() */
+	if (unlikely(READ_ONCE(epi->dying)))
+		return;
+
+	/*
+	 * If we manage to grab a reference it means we're not in
+	 * eventpoll_release_file() and aren't going to be.
+	 */
+	file = epi_fget(epi);
+	if (!file)
+		return;
+
+	spin_lock(&file->f_lock);
+	ep_remove_file(ep, epi, file);
+
+	if (ep_remove_epi(ep, epi))
 		WARN_ON_ONCE(ep_refcount_dec_and_test(ep));
 }
 
@@ -807,7 +850,7 @@ static void ep_clear_and_put(struct eventpoll *ep)
 
 	/*
 	 * Walks through the whole tree and try to free each "struct epitem".
-	 * Note that ep_remove_safe() will not remove the epitem in case of a
+	 * Note that ep_remove() will not remove the epitem in case of a
 	 * racing eventpoll_release_file(); the latter will do the removal.
 	 * At this point we are sure no poll callbacks will be lingering around.
 	 * Since we still own a reference to the eventpoll struct, the loop can't
@@ -816,7 +859,7 @@ static void ep_clear_and_put(struct eventpoll *ep)
 	for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = next) {
 		next = rb_next(rbp);
 		epi = rb_entry(rbp, struct epitem, rbn);
-		ep_remove_safe(ep, epi);
+		ep_remove(ep, epi);
 		cond_resched();
 	}
 
@@ -875,34 +918,6 @@ static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int dep
 	return res;
 }
 
-/*
- * The ffd.file pointer may be in the process of being torn down due to
- * being closed, but we may not have finished eventpoll_release() yet.
- *
- * Normally, even with the atomic_long_inc_not_zero, the file may have
- * been free'd and then gotten re-allocated to something else (since
- * files are not RCU-delayed, they are SLAB_TYPESAFE_BY_RCU).
- *
- * But for epoll, users hold the ep->mtx mutex, and as such any file in
- * the process of being free'd will block in eventpoll_release_file()
- * and thus the underlying file allocation will not be free'd, and the
- * file re-use cannot happen.
- *
- * For the same reason we can avoid a rcu_read_lock() around the
- * operation - 'ffd.file' cannot go away even if the refcount has
- * reached zero (but we must still not call out to ->poll() functions
- * etc).
- */
-static struct file *epi_fget(const struct epitem *epi)
-{
-	struct file *file;
-
-	file = epi->ffd.file;
-	if (!atomic_long_inc_not_zero(&file->f_count))
-		file = NULL;
-	return file;
-}
-
 /*
  * Differs from ep_eventpoll_poll() in that internal callers already have
  * the ep->mtx so we need to start from depth=1, such that mutex_lock_nested()
@@ -989,7 +1004,7 @@ void eventpoll_release_file(struct file *file)
 	spin_lock(&file->f_lock);
 	if (file->f_ep && file->f_ep->first) {
 		epi = hlist_entry(file->f_ep->first, struct epitem, fllink);
-		epi->dying = true;
+		WRITE_ONCE(epi->dying, true);
 		spin_unlock(&file->f_lock);
 
 		/*
@@ -998,7 +1013,13 @@ void eventpoll_release_file(struct file *file)
 		 */
 		ep = epi->ep;
 		mutex_lock(&ep->mtx);
-		dispose = __ep_remove(ep, epi, true);
+
+		ep_unregister_pollwait(ep, epi);
+
+		spin_lock(&file->f_lock);
+		ep_remove_file(ep, epi, file);
+		dispose = ep_remove_epi(ep, epi);
+
 		mutex_unlock(&ep->mtx);
 
 		if (dispose && ep_refcount_dec_and_test(ep))
@@ -1505,7 +1526,8 @@ static int attach_epitem(struct file *file, struct epitem *epi)
 			spin_unlock(&file->f_lock);
 			goto allocate;
 		}
-		file->f_ep = head;
+		/* See eventpoll_release() for details. */
+		WRITE_ONCE(file->f_ep, head);
 		to_free = NULL;
 	}
 	hlist_add_head_rcu(&epi->fllink, file->f_ep);
@@ -1571,21 +1593,21 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 		mutex_unlock(&tep->mtx);
 
 	/*
-	 * ep_remove_safe() calls in the later error paths can't lead to
+	 * ep_remove() calls in the later error paths can't lead to
 	 * ep_free() as the ep file itself still holds an ep reference.
 	 */
 	ep_get(ep);
 
 	/* now check if we've created too many backpaths */
 	if (unlikely(full_check && reverse_path_check())) {
-		ep_remove_safe(ep, epi);
+		ep_remove(ep, epi);
 		return -EINVAL;
 	}
 
 	if (epi->event.events & EPOLLWAKEUP) {
 		error = ep_create_wakeup_source(epi);
 		if (error) {
-			ep_remove_safe(ep, epi);
+			ep_remove(ep, epi);
 			return error;
 		}
 	}
@@ -1609,7 +1631,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 	 * high memory pressure.
 	 */
 	if (unlikely(!epq.epi)) {
-		ep_remove_safe(ep, epi);
+		ep_remove(ep, epi);
 		return -ENOMEM;
 	}
 
@@ -2262,7 +2284,7 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
 			 * The eventpoll itself is still alive: the refcount
 			 * can't go to zero here.
 			 */
-			ep_remove_safe(ep, epi);
+			ep_remove(ep, epi);
 			error = 0;
 		} else {
 			error = -ENOENT;

include/linux/eventpoll.h

@@ -42,7 +42,7 @@ static inline void eventpoll_release(struct file *file)
 	 * because the file in on the way to be removed and nobody ( but
 	 * eventpoll ) has still a reference to this file.
 	 */
-	if (likely(!file->f_ep))
+	if (likely(!READ_ONCE(file->f_ep)))
 		return;
 
 	/*

kernel/locking/rtmutex.c

@@ -1534,20 +1534,26 @@ static bool rtmutex_spin_on_owner(struct rt_mutex_base *lock,
  *
  * Must be called with lock->wait_lock held and interrupts disabled. It must
  * have just failed to try_to_take_rt_mutex().
+ *
+ * When invoked from rt_mutex_start_proxy_lock() waiter::task != current !
  */
 static void __sched remove_waiter(struct rt_mutex_base *lock,
 				  struct rt_mutex_waiter *waiter)
 {
 	bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);
+	struct task_struct *waiter_task = waiter->task;
 	struct rt_mutex_base *next_lock;
 
 	lockdep_assert_held(&lock->wait_lock);
 
-	raw_spin_lock(&current->pi_lock);
-	rt_mutex_dequeue(lock, waiter);
-	current->pi_blocked_on = NULL;
-	raw_spin_unlock(&current->pi_lock);
+	if (!waiter_task) /* never enqueued */
+		return;
+
+	scoped_guard(raw_spinlock, &waiter_task->pi_lock) {
+		rt_mutex_dequeue(lock, waiter);
+		waiter_task->pi_blocked_on = NULL;
+	}
 
 	/*
 	 * Only update priority if the waiter was the highest priority
@@ -1583,7 +1589,7 @@ static void __sched remove_waiter(struct rt_mutex_base *lock,
 	raw_spin_unlock_irq(&lock->wait_lock);
 
 	rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock,
-				   next_lock, NULL, current);
+				   next_lock, NULL, waiter_task);
 
 	raw_spin_lock_irq(&lock->wait_lock);
 }

kernel/locking/rtmutex_api.c

@@ -347,7 +347,7 @@ int __sched rt_mutex_start_proxy_lock(struct rt_mutex_base *lock,
 
 	raw_spin_lock_irq(&lock->wait_lock);
 	ret = __rt_mutex_start_proxy_lock(lock, waiter, task, &wake_q);
-	if (unlikely(ret))
+	if (unlikely(ret < 0))
 		remove_waiter(lock, waiter);
 	preempt_disable();
 	raw_spin_unlock_irq(&lock->wait_lock);