Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S935360AbXHGUtz (ORCPT ); Tue, 7 Aug 2007 16:49:55 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S935292AbXHGUr3 (ORCPT ); Tue, 7 Aug 2007 16:47:29 -0400 Received: from pentafluge.infradead.org ([213.146.154.40]:51408 "EHLO pentafluge.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S935289AbXHGUr1 (ORCPT ); Tue, 7 Aug 2007 16:47:27 -0400 Date: Tue, 7 Aug 2007 13:43:49 -0700 From: Greg KH To: linux-kernel@vger.kernel.org, stable@kernel.org Cc: Justin Forbes , Zwane Mwaikambo , "Theodore Ts'o" , Randy Dunlap , Dave Jones , Chuck Wolber , Chris Wedgwood , Michael Krufky , Chuck Ebbert , Domenico Andreoli , torvalds@linux-foundation.org, akpm@linux-foundation.org, alan@lxorguk.ukuu.org.uk, bunk@stusta.de, Ranko Zivojnovic , "David S. Miller" Subject: [2.6.22.2 review 11/84] gen estimator deadlock fix Message-ID: <20070807204349.GL23028@kroah.com> References: <20070807204034.882009319@mini.kroah.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline; filename="gen-estimator-deadlock-fix.patch" In-Reply-To: <20070807204157.GA23028@kroah.com> User-Agent: Mutt/1.5.15 (2007-04-06) X-Bad-Reply: References and In-Reply-To but no 'Re:' in Subject. Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6094 Lines: 217 From: Ranko Zivojnovic [NET]: gen_estimator deadlock fix -Fixes ABBA deadlock noted by Patrick McHardy : > There is at least one ABBA deadlock, est_timer() does: > read_lock(&est_lock) > spin_lock(e->stats_lock) (which is dev->queue_lock) > > and qdisc_destroy calls htb_destroy under dev->queue_lock, which > calls htb_destroy_class, then gen_kill_estimator and this > write_locks est_lock. To fix the ABBA deadlock the rate estimators are now kept on an rcu list. -The est_lock changes the use from protecting the list to protecting the update to the 'bstat' pointer in order to avoid NULL dereferencing. -The 'interval' member of the gen_estimator structure removed as it is not needed. Signed-off-by: Ranko Zivojnovic Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/gen_estimator.c | 81 ++++++++++++++++++++++++++++------------------- 1 file changed, 49 insertions(+), 32 deletions(-) --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -79,27 +79,27 @@ struct gen_estimator { - struct gen_estimator *next; + struct list_head list; struct gnet_stats_basic *bstats; struct gnet_stats_rate_est *rate_est; spinlock_t *stats_lock; - unsigned interval; int ewma_log; u64 last_bytes; u32 last_packets; u32 avpps; u32 avbps; + struct rcu_head e_rcu; }; struct gen_estimator_head { struct timer_list timer; - struct gen_estimator *list; + struct list_head list; }; static struct gen_estimator_head elist[EST_MAX_INTERVAL+1]; -/* Estimator array lock */ +/* Protects against NULL dereference */ static DEFINE_RWLOCK(est_lock); static void est_timer(unsigned long arg) @@ -107,13 +107,17 @@ static void est_timer(unsigned long arg) int idx = (int)arg; struct gen_estimator *e; - read_lock(&est_lock); - for (e = elist[idx].list; e; e = e->next) { + rcu_read_lock(); + list_for_each_entry_rcu(e, &elist[idx].list, list) { u64 nbytes; u32 npackets; u32 rate; spin_lock(e->stats_lock); + read_lock(&est_lock); + if (e->bstats == NULL) + goto skip; + nbytes = e->bstats->bytes; npackets = e->bstats->packets; rate = (nbytes - e->last_bytes)<<(7 - idx); @@ -125,12 +129,14 @@ static void est_timer(unsigned long arg) e->last_packets = npackets; e->avpps += ((long)rate - (long)e->avpps) >> e->ewma_log; e->rate_est->pps = (e->avpps+0x1FF)>>10; +skip: + read_unlock(&est_lock); spin_unlock(e->stats_lock); } - if (elist[idx].list != NULL) + if (!list_empty(&elist[idx].list)) mod_timer(&elist[idx].timer, jiffies + ((HZ<interval = parm->interval + 2; + idx = parm->interval + 2; est->bstats = bstats; est->rate_est = rate_est; est->stats_lock = stats_lock; @@ -174,20 +185,25 @@ int gen_new_estimator(struct gnet_stats_ est->last_packets = bstats->packets; est->avpps = rate_est->pps<<10; - est->next = elist[est->interval].list; - if (est->next == NULL) { - init_timer(&elist[est->interval].timer); - elist[est->interval].timer.data = est->interval; - elist[est->interval].timer.expires = jiffies + ((HZ<interval)/4); - elist[est->interval].timer.function = est_timer; - add_timer(&elist[est->interval].timer); + if (!elist[idx].timer.function) { + INIT_LIST_HEAD(&elist[idx].list); + setup_timer(&elist[idx].timer, est_timer, idx); } - write_lock_bh(&est_lock); - elist[est->interval].list = est; - write_unlock_bh(&est_lock); + + if (list_empty(&elist[idx].list)) + mod_timer(&elist[idx].timer, jiffies + ((HZ<list, &elist[idx].list); return 0; } +static void __gen_kill_estimator(struct rcu_head *head) +{ + struct gen_estimator *e = container_of(head, + struct gen_estimator, e_rcu); + kfree(e); +} + /** * gen_kill_estimator - remove a rate estimator * @bstats: basic statistics @@ -195,31 +211,32 @@ int gen_new_estimator(struct gnet_stats_ * * Removes the rate estimator specified by &bstats and &rate_est * and deletes the timer. + * + * NOTE: Called under rtnl_mutex */ void gen_kill_estimator(struct gnet_stats_basic *bstats, struct gnet_stats_rate_est *rate_est) { int idx; - struct gen_estimator *est, **pest; + struct gen_estimator *e, *n; for (idx=0; idx <= EST_MAX_INTERVAL; idx++) { - int killed = 0; - pest = &elist[idx].list; - while ((est=*pest) != NULL) { - if (est->rate_est != rate_est || est->bstats != bstats) { - pest = &est->next; + + /* Skip non initialized indexes */ + if (!elist[idx].timer.function) + continue; + + list_for_each_entry_safe(e, n, &elist[idx].list, list) { + if (e->rate_est != rate_est || e->bstats != bstats) continue; - } write_lock_bh(&est_lock); - *pest = est->next; + e->bstats = NULL; write_unlock_bh(&est_lock); - kfree(est); - killed++; + list_del_rcu(&e->list); + call_rcu(&e->e_rcu, __gen_kill_estimator); } - if (killed && elist[idx].list == NULL) - del_timer(&elist[idx].timer); } } -- - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/