Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753376AbdLNPZN (ORCPT ); Thu, 14 Dec 2017 10:25:13 -0500 Received: from bombadil.infradead.org ([65.50.211.133]:36641 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753065AbdLNPZJ (ORCPT ); Thu, 14 Dec 2017 10:25:09 -0500 From: Christoph Hellwig To: Ingo Molnar , Peter Zijlstra Cc: Andrew Morton , Al Viro , Andrea Arcangeli , Mike Rapoport , Jason Baron , linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org Subject: [PATCH 1/3] epoll: use the waitqueue lock to protect ep->wq Date: Thu, 14 Dec 2017 16:23:42 +0100 Message-Id: <20171214152344.6880-2-hch@lst.de> X-Mailer: git-send-email 2.14.2 In-Reply-To: <20171214152344.6880-1-hch@lst.de> References: <20171214152344.6880-1-hch@lst.de> X-SRS-Rewrite: SMTP reverse-path rewritten from by bombadil.infradead.org. See http://www.infradead.org/rpr.html Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 9727 Lines: 260 The epoll code currently uses the unlocked waitqueue helpers for managing ep->wq, but instead of holding the waitqueue lock around these calls, it uses its own ep->lock spinlock. Given that the waitqueue is not exposed to the rest of the kernel this actually works ok at the moment, but prevents the epoll locking rules from being enforced using lockdep. Remove ep->lock and use the waitqueue lock to not only reduce the size of struct eventpoll but also to make sure we can assert locking invariants in the waitqueue code. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Baron --- fs/eventpoll.c | 65 ++++++++++++++++++++++++++-------------------------------- 1 file changed, 29 insertions(+), 36 deletions(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index afd548ebc328..d32617582432 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -50,10 +50,10 @@ * * 1) epmutex (mutex) * 2) ep->mtx (mutex) - * 3) ep->lock (spinlock) + * 3) ep->wq.lock (spinlock) * * The acquire order is the one listed above, from 1 to 3. - * We need a spinlock (ep->lock) because we manipulate objects + * We need a spinlock (ep->wq.lock) because we manipulate objects * from inside the poll callback, that might be triggered from * a wake_up() that in turn might be called from IRQ context. * So we can't sleep inside the poll callback and hence we need @@ -85,7 +85,7 @@ * of epoll file descriptors, we use the current recursion depth as * the lockdep subkey. * It is possible to drop the "ep->mtx" and to use the global - * mutex "epmutex" (together with "ep->lock") to have it working, + * mutex "epmutex" (together with "ep->wq.lock") to have it working, * but having "ep->mtx" will make the interface more scalable. * Events that require holding "epmutex" are very rare, while for * normal operations the epoll private "ep->mtx" will guarantee @@ -182,11 +182,10 @@ struct epitem { * This structure is stored inside the "private_data" member of the file * structure and represents the main data structure for the eventpoll * interface. + * + * Access to it is protected by the lock inside wq. */ struct eventpoll { - /* Protect the access to this structure */ - spinlock_t lock; - /* * This mutex is used to ensure that files are not removed * while epoll is using them. This is held during the event @@ -210,7 +209,7 @@ struct eventpoll { /* * This is a single linked list that chains all the "struct epitem" that * happened while transferring ready events to userspace w/out - * holding ->lock. + * holding ->wq.lock. */ struct epitem *ovflist; @@ -686,17 +685,17 @@ static int ep_scan_ready_list(struct eventpoll *ep, * because we want the "sproc" callback to be able to do it * in a lockless way. */ - spin_lock_irqsave(&ep->lock, flags); + spin_lock_irqsave(&ep->wq.lock, flags); list_splice_init(&ep->rdllist, &txlist); ep->ovflist = NULL; - spin_unlock_irqrestore(&ep->lock, flags); + spin_unlock_irqrestore(&ep->wq.lock, flags); /* * Now call the callback function. */ error = (*sproc)(ep, &txlist, priv); - spin_lock_irqsave(&ep->lock, flags); + spin_lock_irqsave(&ep->wq.lock, flags); /* * During the time we spent inside the "sproc" callback, some * other events might have been queued by the poll callback. @@ -738,7 +737,7 @@ static int ep_scan_ready_list(struct eventpoll *ep, if (waitqueue_active(&ep->poll_wait)) pwake++; } - spin_unlock_irqrestore(&ep->lock, flags); + spin_unlock_irqrestore(&ep->wq.lock, flags); if (!ep_locked) mutex_unlock(&ep->mtx); @@ -766,12 +765,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) struct file *file = epi->ffd.file; /* - * Removes poll wait queue hooks. We _have_ to do this without holding - * the "ep->lock" otherwise a deadlock might occur. This because of the - * sequence of the lock acquisition. Here we do "ep->lock" then the wait - * queue head lock when unregistering the wait queue. The wakeup callback - * will run by holding the wait queue head lock and will call our callback - * that will try to get "ep->lock". + * Removes poll wait queue hooks. */ ep_unregister_pollwait(ep, epi); @@ -782,10 +776,10 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) rb_erase_cached(&epi->rbn, &ep->rbr); - spin_lock_irqsave(&ep->lock, flags); + spin_lock_irqsave(&ep->wq.lock, flags); if (ep_is_linked(&epi->rdllink)) list_del_init(&epi->rdllink); - spin_unlock_irqrestore(&ep->lock, flags); + spin_unlock_irqrestore(&ep->wq.lock, flags); wakeup_source_unregister(ep_wakeup_source(epi)); /* @@ -835,7 +829,7 @@ static void ep_free(struct eventpoll *ep) * Walks through the whole tree by freeing each "struct epitem". At this * point we are sure no poll callbacks will be lingering around, and also by * holding "epmutex" we can be sure that no file cleanup code will hit - * us during this operation. So we can avoid the lock on "ep->lock". + * us during this operation. So we can avoid the lock on "ep->wq.lock". * We do not need to lock ep->mtx, either, we only do it to prevent * a lockdep warning. */ @@ -1015,7 +1009,6 @@ static int ep_alloc(struct eventpoll **pep) if (unlikely(!ep)) goto free_uid; - spin_lock_init(&ep->lock); mutex_init(&ep->mtx); init_waitqueue_head(&ep->wq); init_waitqueue_head(&ep->poll_wait); @@ -1119,7 +1112,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v struct eventpoll *ep = epi->ep; int ewake = 0; - spin_lock_irqsave(&ep->lock, flags); + spin_lock_irqsave(&ep->wq.lock, flags); ep_set_busy_poll_napi_id(epi); @@ -1196,7 +1189,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v pwake++; out_unlock: - spin_unlock_irqrestore(&ep->lock, flags); + spin_unlock_irqrestore(&ep->wq.lock, flags); /* We have to call this outside the lock */ if (pwake) @@ -1480,7 +1473,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, goto error_remove_epi; /* We have to drop the new item inside our item list to keep track of it */ - spin_lock_irqsave(&ep->lock, flags); + spin_lock_irqsave(&ep->wq.lock, flags); /* record NAPI ID of new item if present */ ep_set_busy_poll_napi_id(epi); @@ -1497,7 +1490,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, pwake++; } - spin_unlock_irqrestore(&ep->lock, flags); + spin_unlock_irqrestore(&ep->wq.lock, flags); atomic_long_inc(&ep->user->epoll_watches); @@ -1523,10 +1516,10 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, * list, since that is used/cleaned only inside a section bound by "mtx". * And ep_insert() is called with "mtx" held. */ - spin_lock_irqsave(&ep->lock, flags); + spin_lock_irqsave(&ep->wq.lock, flags); if (ep_is_linked(&epi->rdllink)) list_del_init(&epi->rdllink); - spin_unlock_irqrestore(&ep->lock, flags); + spin_unlock_irqrestore(&ep->wq.lock, flags); wakeup_source_unregister(ep_wakeup_source(epi)); @@ -1568,9 +1561,9 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even * 1) Flush epi changes above to other CPUs. This ensures * we do not miss events from ep_poll_callback if an * event occurs immediately after we call f_op->poll(). - * We need this because we did not take ep->lock while + * We need this because we did not take ep->wq.lock while * changing epi above (but ep_poll_callback does take - * ep->lock). + * ep->wq.lock). * * 2) We also need to ensure we do not miss _past_ events * when calling f_op->poll(). This barrier also @@ -1593,7 +1586,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even * list, push it inside. */ if (revents & event->events) { - spin_lock_irq(&ep->lock); + spin_lock_irq(&ep->wq.lock); if (!ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); @@ -1604,7 +1597,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even if (waitqueue_active(&ep->poll_wait)) pwake++; } - spin_unlock_irq(&ep->lock); + spin_unlock_irq(&ep->wq.lock); } /* We have to call this outside the lock */ @@ -1754,7 +1747,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, * caller specified a non blocking operation. */ timed_out = 1; - spin_lock_irqsave(&ep->lock, flags); + spin_lock_irqsave(&ep->wq.lock, flags); goto check_events; } @@ -1763,7 +1756,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, if (!ep_events_available(ep)) ep_busy_loop(ep, timed_out); - spin_lock_irqsave(&ep->lock, flags); + spin_lock_irqsave(&ep->wq.lock, flags); if (!ep_events_available(ep)) { /* @@ -1805,11 +1798,11 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, break; } - spin_unlock_irqrestore(&ep->lock, flags); + spin_unlock_irqrestore(&ep->wq.lock, flags); if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) timed_out = 1; - spin_lock_irqsave(&ep->lock, flags); + spin_lock_irqsave(&ep->wq.lock, flags); } __remove_wait_queue(&ep->wq, &wait); @@ -1819,7 +1812,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, /* Is it worth to try to dig for events ? */ eavail = ep_events_available(ep); - spin_unlock_irqrestore(&ep->lock, flags); + spin_unlock_irqrestore(&ep->wq.lock, flags); /* * Try to transfer events to user space. In case we get 0 events and -- 2.14.2