From a9312ae89324438b0edc554eb36c3ec6bf927d04 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 17 Aug 2008 21:51:03 -0700 Subject: pkt_sched: Add 'deactivated' state. This new state lets dev_deactivate() mark a qdisc as having been deactivated. dev_queue_xmit() and ing_filter() check for this bit and do not try to process the qdisc if the bit is set. dev_deactivate() polls the qdisc after setting the bit, waiting for both __QDISC_STATE_RUNNING and __QDISC_STATE_SCHED to clear. This isn't perfect yet, but subsequent changesets will make it so. This part is just one piece of the puzzle. Signed-off-by: David S. Miller --- net/sched/sch_generic.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net/sched/sch_generic.c') diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 4685746..ff1c455 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -597,6 +597,9 @@ static void transition_one_qdisc(struct net_device *dev, struct Qdisc *new_qdisc = dev_queue->qdisc_sleeping; int *need_watchdog_p = _need_watchdog; + if (!(new_qdisc->flags & TCQ_F_BUILTIN)) + clear_bit(__QDISC_STATE_DEACTIVATED, &new_qdisc->state); + rcu_assign_pointer(dev_queue->qdisc, new_qdisc); if (need_watchdog_p && new_qdisc != &noqueue_qdisc) *need_watchdog_p = 1; @@ -640,6 +643,9 @@ static void dev_deactivate_queue(struct net_device *dev, if (qdisc) { spin_lock_bh(qdisc_lock(qdisc)); + if (!(qdisc->flags & TCQ_F_BUILTIN)) + set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state); + dev_queue->qdisc = qdisc_default; qdisc_reset(qdisc); -- cgit v1.1 From 4335cd2da1e8986fa8aff21a91144d986cb0a5fc Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 17 Aug 2008 21:58:07 -0700 Subject: pkt_sched: Simplify dev_deactivate() polling loop. The condition under which the previous qdisc has no more references after we've attached &noop_qdisc is that both RUNNING and SCHED are both seen clear while holding the root lock. So just make specifically that check in the polling loop, instead of this overly complex "check without then check with lock held" sequence. Signed-off-by: David S. Miller --- net/sched/sch_generic.c | 31 +++++-------------------------- 1 file changed, 5 insertions(+), 26 deletions(-) (limited to 'net/sched/sch_generic.c') diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index ff1c455..30b76ae 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -653,7 +653,7 @@ static void dev_deactivate_queue(struct net_device *dev, } } -static bool some_qdisc_is_busy(struct net_device *dev, int lock) +static bool some_qdisc_is_busy(struct net_device *dev) { unsigned int i; @@ -667,14 +667,12 @@ static bool some_qdisc_is_busy(struct net_device *dev, int lock) q = dev_queue->qdisc_sleeping; root_lock = qdisc_lock(q); - if (lock) - spin_lock_bh(root_lock); + spin_lock_bh(root_lock); val = (test_bit(__QDISC_STATE_RUNNING, &q->state) || test_bit(__QDISC_STATE_SCHED, &q->state)); - if (lock) - spin_unlock_bh(root_lock); + spin_unlock_bh(root_lock); if (val) return true; @@ -684,8 +682,6 @@ static bool some_qdisc_is_busy(struct net_device *dev, int lock) void dev_deactivate(struct net_device *dev) { - bool running; - netdev_for_each_tx_queue(dev, dev_deactivate_queue, &noop_qdisc); dev_deactivate_queue(dev, &dev->rx_queue, &noop_qdisc); @@ -695,25 +691,8 @@ void dev_deactivate(struct net_device *dev) synchronize_rcu(); /* Wait for outstanding qdisc_run calls. */ - do { - while (some_qdisc_is_busy(dev, 0)) - yield(); - - /* - * Double-check inside queue lock to ensure that all effects - * of the queue run are visible when we return. - */ - running = some_qdisc_is_busy(dev, 1); - - /* - * The running flag should never be set at this point because - * we've already set dev->qdisc to noop_qdisc *inside* the same - * pair of spin locks. That is, if any qdisc_run starts after - * our initial test it should see the noop_qdisc and then - * clear the RUNNING bit before dropping the queue lock. So - * if it is set here then we've found a bug. - */ - } while (WARN_ON_ONCE(running)); + while (some_qdisc_is_busy(dev)) + yield(); } static void dev_init_scheduler_queue(struct net_device *dev, -- cgit v1.1 From 1e0d5a5747772182d1bb2525d8153da640fdfb58 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 17 Aug 2008 22:31:26 -0700 Subject: pkt_sched: No longer destroy qdiscs from RCU. We can now kill them synchronously with all of the previous dev_deactivate() cures. This makes netdev destruction and shutdown saner as the qdiscs hold references to the device. Signed-off-by: David S. Miller --- net/sched/sch_generic.c | 27 +++++++++------------------ 1 file changed, 9 insertions(+), 18 deletions(-) (limited to 'net/sched/sch_generic.c') diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 30b76ae..6f96b7b 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -518,14 +518,19 @@ void qdisc_reset(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_reset); -/* this is the rcu callback function to clean up a qdisc when there - * are no further references to it */ +/* Under qdisc_lock(qdisc) and BH! */ -static void __qdisc_destroy(struct rcu_head *head) +void qdisc_destroy(struct Qdisc *qdisc) { - struct Qdisc *qdisc = container_of(head, struct Qdisc, q_rcu); const struct Qdisc_ops *ops = qdisc->ops; + if (qdisc->flags & TCQ_F_BUILTIN || + !atomic_dec_and_test(&qdisc->refcnt)) + return; + + if (qdisc->parent) + list_del(&qdisc->list); + #ifdef CONFIG_NET_SCHED qdisc_put_stab(qdisc->stab); #endif @@ -542,20 +547,6 @@ static void __qdisc_destroy(struct rcu_head *head) kfree((char *) qdisc - qdisc->padded); } - -/* Under qdisc_lock(qdisc) and BH! */ - -void qdisc_destroy(struct Qdisc *qdisc) -{ - if (qdisc->flags & TCQ_F_BUILTIN || - !atomic_dec_and_test(&qdisc->refcnt)) - return; - - if (qdisc->parent) - list_del(&qdisc->list); - - call_rcu(&qdisc->q_rcu, __qdisc_destroy); -} EXPORT_SYMBOL(qdisc_destroy); static bool dev_all_qdisc_sleeping_noop(struct net_device *dev) -- cgit v1.1 From 4d8863a29c4755a0461cd31b6865026187d6c43a Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 18 Aug 2008 21:03:15 -0700 Subject: pkt_sched: Don't hold qdisc lock over qdisc_destroy(). Based upon reports by Denys Fedoryshchenko, and feedback and help from Jarek Poplawski and Herbert Xu. We always either: 1) Never made an external reference to this qdisc. or 2) Did a dev_deactivate() which purged all asynchronous references. So do not lock the qdisc when we call qdisc_destroy(), it's illegal anyways as when we drop the lock this is free'd memory. Signed-off-by: David S. Miller --- net/sched/sch_generic.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'net/sched/sch_generic.c') diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 6f96b7b..c3ed4d4 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -518,8 +518,6 @@ void qdisc_reset(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_reset); -/* Under qdisc_lock(qdisc) and BH! */ - void qdisc_destroy(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; @@ -712,14 +710,10 @@ static void shutdown_scheduler_queue(struct net_device *dev, struct Qdisc *qdisc_default = _qdisc_default; if (qdisc) { - spinlock_t *root_lock = qdisc_lock(qdisc); - dev_queue->qdisc = qdisc_default; dev_queue->qdisc_sleeping = qdisc_default; - spin_lock_bh(root_lock); qdisc_destroy(qdisc); - spin_unlock_bh(root_lock); } } -- cgit v1.1 From f6e0b239a2657ea8cb67f0d83d0bfdbfd19a481b Mon Sep 17 00:00:00 2001 From: Jarek Poplawski Date: Fri, 22 Aug 2008 03:24:05 -0700 Subject: pkt_sched: Fix qdisc list locking Since some qdiscs call qdisc_tree_decrease_qlen() (so qdisc_lookup()) without rtnl_lock(), adding and deleting from a qdisc list needs additional locking. This patch adds global spinlock qdisc_list_lock and wrapper functions for modifying the list. It is considered as a temporary solution until hfsc_dequeue(), netem_dequeue() and tbf_dequeue() (or qdisc_tree_decrease_qlen()) are redone. With feedback from Herbert Xu and David S. Miller. Signed-off-by: Jarek Poplawski Acked-by: Herbert Xu Signed-off-by: David S. Miller --- net/sched/sch_generic.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'net/sched/sch_generic.c') diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index c3ed4d4..5f0ade7 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -526,10 +526,9 @@ void qdisc_destroy(struct Qdisc *qdisc) !atomic_dec_and_test(&qdisc->refcnt)) return; - if (qdisc->parent) - list_del(&qdisc->list); - #ifdef CONFIG_NET_SCHED + qdisc_list_del(qdisc); + qdisc_put_stab(qdisc->stab); #endif gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est); -- cgit v1.1