From 3419b23a919698f75944d3e0d97eb1d9c51e4bb6 Mon Sep 17 00:00:00 2001 From: Davide Libenzi Date: Sun, 25 Jun 2006 05:48:14 -0700 Subject: [PATCH] [PATCH] epoll: use unlocked wqueue operations A few days ago Arjan signaled a lockdep red flag on epoll locks, and precisely between the epoll's device structure lock (->lock) and the wait queue head lock (->lock). Like I explained in another email, and directly to Arjan, this can't happen in reality because of the explicit check at eventpoll.c:592, that does not allow to drop an epoll fd inside the same epoll fd. Since lockdep is working on per-structure locks, it will never be able to know of policies enforced in other parts of the code. It was decided time ago of having the ability to drop epoll fds inside other epoll fds, that triggers a very trick wakeup operations (due to possibly reentrant callback-driven wakeups) handled by the ep_poll_safewake() function. While looking again at the code though, I noticed that all the operations done on the epoll's main structure wait queue head (->wq) are already protected by the epoll lock (->lock), so that locked-style functions can be used to manipulate the ->wq member. This makes both a lock-acquire save, and lockdep happy. Running totalmess on my dual opteron for a while did not reveal any problem so far: http://www.xmailserver.org/totalmess.c Signed-off-by: Davide Libenzi Cc: Arjan van de Ven Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/eventpoll.c | 17 ++++++++++------- include/linux/eventpoll.h | 2 +- 2 files changed, 11 insertions(+), 8 deletions(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 08e7e6a555c..9c677bbd0b0 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1,6 +1,6 @@ /* * fs/eventpoll.c ( Efficent event polling implementation ) - * Copyright (C) 2001,...,2003 Davide Libenzi + * Copyright (C) 2001,...,2006 Davide Libenzi * * 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 @@ -1004,7 +1004,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) - wake_up(&ep->wq); + __wake_up_locked(&ep->wq, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE); if (waitqueue_active(&ep->poll_wait)) pwake++; } @@ -1083,7 +1083,8 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) - wake_up(&ep->wq); + __wake_up_locked(&ep->wq, TASK_UNINTERRUPTIBLE | + TASK_INTERRUPTIBLE); if (waitqueue_active(&ep->poll_wait)) pwake++; } @@ -1260,7 +1261,8 @@ is_linked: * wait list. */ if (waitqueue_active(&ep->wq)) - wake_up(&ep->wq); + __wake_up_locked(&ep->wq, TASK_UNINTERRUPTIBLE | + TASK_INTERRUPTIBLE); if (waitqueue_active(&ep->poll_wait)) pwake++; @@ -1444,7 +1446,8 @@ static void ep_reinject_items(struct eventpoll *ep, struct list_head *txlist) * wait list. */ if (waitqueue_active(&ep->wq)) - wake_up(&ep->wq); + __wake_up_locked(&ep->wq, TASK_UNINTERRUPTIBLE | + TASK_INTERRUPTIBLE); if (waitqueue_active(&ep->poll_wait)) pwake++; } @@ -1516,7 +1519,7 @@ retry: * ep_poll_callback() when events will become available. */ init_waitqueue_entry(&wait, current); - add_wait_queue(&ep->wq, &wait); + __add_wait_queue(&ep->wq, &wait); for (;;) { /* @@ -1536,7 +1539,7 @@ retry: jtimeout = schedule_timeout(jtimeout); write_lock_irqsave(&ep->lock, flags); } - remove_wait_queue(&ep->wq, &wait); + __remove_wait_queue(&ep->wq, &wait); set_current_state(TASK_RUNNING); } diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 1e4bdfcf83a..84cfa8bbdc3 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -1,6 +1,6 @@ /* * include/linux/eventpoll.h ( Efficent event polling implementation ) - * Copyright (C) 2001,...,2003 Davide Libenzi + * Copyright (C) 2001,...,2006 Davide Libenzi * * 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 -- 2.41.1