From b26b0d1e8b1de83bbce81c8d119260ac91031ebd Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 12 Sep 2014 20:04:52 -0700 Subject: [PATCH 01/12] net: qdisc: use rcu prefix and silence sparse warnings Add __rcu notation to qdisc handling by doing this we can make smatch output more legible. And anyways some of the cases should be using rcu_dereference() see qdisc_all_tx_empty(), qdisc_tx_chainging(), and so on. Also *wake_queue() API is commonly called from driver timer routines without rcu lock or rtnl lock. So I added rcu_read_lock() blocks around netif_wake_subqueue and netif_tx_wake_queue. Signed-off-by: John Fastabend Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 29 +++------------------- include/net/sch_generic.h | 21 +++++++++++----- net/core/dev.c | 51 +++++++++++++++++++++++++++++++++++++-- net/sched/sch_generic.c | 4 +-- net/sched/sch_mqprio.c | 6 +++-- net/sched/sch_teql.c | 13 ++++++---- 6 files changed, 82 insertions(+), 42 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ba72f6baae1a..ae721f53739e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -543,7 +543,7 @@ struct netdev_queue { * read mostly part */ struct net_device *dev; - struct Qdisc *qdisc; + struct Qdisc __rcu *qdisc; struct Qdisc *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; @@ -2356,12 +2356,7 @@ static inline void input_queue_tail_incr_save(struct softnet_data *sd, DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); void __netif_schedule(struct Qdisc *q); - -static inline void netif_schedule_queue(struct netdev_queue *txq) -{ - if (!(txq->state & QUEUE_STATE_ANY_XOFF)) - __netif_schedule(txq->qdisc); -} +void netif_schedule_queue(struct netdev_queue *txq); static inline void netif_tx_schedule_all(struct net_device *dev) { @@ -2397,11 +2392,7 @@ static inline void netif_tx_start_all_queues(struct net_device *dev) } } -static inline void netif_tx_wake_queue(struct netdev_queue *dev_queue) -{ - if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) - __netif_schedule(dev_queue->qdisc); -} +void netif_tx_wake_queue(struct netdev_queue *dev_queue); /** * netif_wake_queue - restart transmit @@ -2673,19 +2664,7 @@ static inline bool netif_subqueue_stopped(const struct net_device *dev, return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb)); } -/** - * netif_wake_subqueue - allow sending packets on subqueue - * @dev: network device - * @queue_index: sub queue index - * - * Resume individual transmit queue of a device with multiple transmit queues. - */ -static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) -{ - struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); - if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state)) - __netif_schedule(txq->qdisc); -} +void netif_wake_subqueue(struct net_device *dev, u16 queue_index); #ifdef CONFIG_XPS int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index a3cfb8ebeb53..56838ab29b42 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -259,7 +259,9 @@ static inline spinlock_t *qdisc_lock(struct Qdisc *qdisc) static inline struct Qdisc *qdisc_root(const struct Qdisc *qdisc) { - return qdisc->dev_queue->qdisc; + struct Qdisc *q = rcu_dereference_rtnl(qdisc->dev_queue->qdisc); + + return q; } static inline struct Qdisc *qdisc_root_sleeping(const struct Qdisc *qdisc) @@ -384,7 +386,7 @@ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) struct Qdisc *qdisc; for (; i < dev->num_tx_queues; i++) { - qdisc = netdev_get_tx_queue(dev, i)->qdisc; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc); if (qdisc) { spin_lock_bh(qdisc_lock(qdisc)); qdisc_reset(qdisc); @@ -402,13 +404,18 @@ static inline void qdisc_reset_all_tx(struct net_device *dev) static inline bool qdisc_all_tx_empty(const struct net_device *dev) { unsigned int i; + + rcu_read_lock(); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - const struct Qdisc *q = txq->qdisc; + const struct Qdisc *q = rcu_dereference(txq->qdisc); - if (q->q.qlen) + if (q->q.qlen) { + rcu_read_unlock(); return false; + } } + rcu_read_unlock(); return true; } @@ -416,9 +423,10 @@ static inline bool qdisc_all_tx_empty(const struct net_device *dev) static inline bool qdisc_tx_changing(const struct net_device *dev) { unsigned int i; + for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - if (txq->qdisc != txq->qdisc_sleeping) + if (rcu_access_pointer(txq->qdisc) != txq->qdisc_sleeping) return true; } return false; @@ -428,9 +436,10 @@ static inline bool qdisc_tx_changing(const struct net_device *dev) static inline bool qdisc_tx_is_noop(const struct net_device *dev) { unsigned int i; + for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - if (txq->qdisc != &noop_qdisc) + if (rcu_access_pointer(txq->qdisc) != &noop_qdisc) return false; } return true; diff --git a/net/core/dev.c b/net/core/dev.c index 3c6a967e5830..b3d6dbc0c696 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2177,6 +2177,53 @@ static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb) return (struct dev_kfree_skb_cb *)skb->cb; } +void netif_schedule_queue(struct netdev_queue *txq) +{ + rcu_read_lock(); + if (!(txq->state & QUEUE_STATE_ANY_XOFF)) { + struct Qdisc *q = rcu_dereference(txq->qdisc); + + __netif_schedule(q); + } + rcu_read_unlock(); +} +EXPORT_SYMBOL(netif_schedule_queue); + +/** + * netif_wake_subqueue - allow sending packets on subqueue + * @dev: network device + * @queue_index: sub queue index + * + * Resume individual transmit queue of a device with multiple transmit queues. + */ +void netif_wake_subqueue(struct net_device *dev, u16 queue_index) +{ + struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); + + if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state)) { + struct Qdisc *q; + + rcu_read_lock(); + q = rcu_dereference(txq->qdisc); + __netif_schedule(q); + rcu_read_unlock(); + } +} +EXPORT_SYMBOL(netif_wake_subqueue); + +void netif_tx_wake_queue(struct netdev_queue *dev_queue) +{ + if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) { + struct Qdisc *q; + + rcu_read_lock(); + q = rcu_dereference(dev_queue->qdisc); + __netif_schedule(q); + rcu_read_unlock(); + } +} +EXPORT_SYMBOL(netif_tx_wake_queue); + void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason) { unsigned long flags; @@ -3432,7 +3479,7 @@ static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq) skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl); skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS); - q = rxq->qdisc; + q = rcu_dereference(rxq->qdisc); if (q != &noop_qdisc) { spin_lock(qdisc_lock(q)); if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) @@ -3449,7 +3496,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, { struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue); - if (!rxq || rxq->qdisc == &noop_qdisc) + if (!rxq || rcu_access_pointer(rxq->qdisc) == &noop_qdisc) goto out; if (*pt_prev) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 19696ebe9ebc..346ef85617d3 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -783,7 +783,7 @@ static void dev_deactivate_queue(struct net_device *dev, struct Qdisc *qdisc_default = _qdisc_default; struct Qdisc *qdisc; - qdisc = dev_queue->qdisc; + qdisc = rtnl_dereference(dev_queue->qdisc); if (qdisc) { spin_lock_bh(qdisc_lock(qdisc)); @@ -876,7 +876,7 @@ static void dev_init_scheduler_queue(struct net_device *dev, { struct Qdisc *qdisc = _qdisc; - dev_queue->qdisc = qdisc; + rcu_assign_pointer(dev_queue->qdisc, qdisc); dev_queue->qdisc_sleeping = qdisc; } diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 6749e2f540d0..37e7d25d21f1 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -231,7 +231,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) memset(&sch->qstats, 0, sizeof(sch->qstats)); for (i = 0; i < dev->num_tx_queues; i++) { - qdisc = netdev_get_tx_queue(dev, i)->qdisc; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc); spin_lock_bh(qdisc_lock(qdisc)); sch->q.qlen += qdisc->q.qlen; sch->bstats.bytes += qdisc->bstats.bytes; @@ -340,7 +340,9 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, spin_unlock_bh(d->lock); for (i = tc.offset; i < tc.offset + tc.count; i++) { - qdisc = netdev_get_tx_queue(dev, i)->qdisc; + struct netdev_queue *q = netdev_get_tx_queue(dev, i); + + qdisc = rtnl_dereference(q->qdisc); spin_lock_bh(qdisc_lock(qdisc)); bstats.bytes += qdisc->bstats.bytes; bstats.packets += qdisc->bstats.packets; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index aaa8d03ed054..5cd291bd00e4 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -96,11 +96,14 @@ teql_dequeue(struct Qdisc *sch) struct teql_sched_data *dat = qdisc_priv(sch); struct netdev_queue *dat_queue; struct sk_buff *skb; + struct Qdisc *q; skb = __skb_dequeue(&dat->q); dat_queue = netdev_get_tx_queue(dat->m->dev, 0); + q = rcu_dereference_bh(dat_queue->qdisc); + if (skb == NULL) { - struct net_device *m = qdisc_dev(dat_queue->qdisc); + struct net_device *m = qdisc_dev(q); if (m) { dat->m->slaves = sch; netif_wake_queue(m); @@ -108,7 +111,7 @@ teql_dequeue(struct Qdisc *sch) } else { qdisc_bstats_update(sch, skb); } - sch->q.qlen = dat->q.qlen + dat_queue->qdisc->q.qlen; + sch->q.qlen = dat->q.qlen + q->q.qlen; return skb; } @@ -157,9 +160,9 @@ teql_destroy(struct Qdisc *sch) txq = netdev_get_tx_queue(master->dev, 0); master->slaves = NULL; - root_lock = qdisc_root_sleeping_lock(txq->qdisc); + root_lock = qdisc_root_sleeping_lock(rtnl_dereference(txq->qdisc)); spin_lock_bh(root_lock); - qdisc_reset(txq->qdisc); + qdisc_reset(rtnl_dereference(txq->qdisc)); spin_unlock_bh(root_lock); } } @@ -266,7 +269,7 @@ static inline int teql_resolve(struct sk_buff *skb, struct dst_entry *dst = skb_dst(skb); int res; - if (txq->qdisc == &noop_qdisc) + if (rcu_access_pointer(txq->qdisc) == &noop_qdisc) return -ENODEV; if (!dev->header_ops || !dst) From 80a735f7b952b8bd7028cfffba2105a38c1a9f0c Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 12 Sep 2014 20:05:27 -0700 Subject: [PATCH 02/12] net: rcu-ify tcf_proto rcu'ify tcf_proto this allows calling tc_classify() without holding any locks. Updaters are protected by RTNL. This patch prepares the core net_sched infrastracture for running the classifier/action chains without holding the qdisc lock however it does nothing to ensure cls_xxx and act_xxx types also work without locking. Additional patches are required to address the fall out. Signed-off-by: John Fastabend Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sch_generic.h | 9 +++++---- net/sched/cls_api.c | 30 +++++++++++++++--------------- net/sched/sch_api.c | 10 +++++----- net/sched/sch_atm.c | 20 +++++++++++--------- net/sched/sch_cbq.c | 11 +++++++---- net/sched/sch_choke.c | 15 +++++++++------ net/sched/sch_drr.c | 9 ++++++--- net/sched/sch_dsmark.c | 9 +++++---- net/sched/sch_fq_codel.c | 11 +++++++---- net/sched/sch_hfsc.c | 8 ++++---- net/sched/sch_htb.c | 15 ++++++++------- net/sched/sch_ingress.c | 8 +++++--- net/sched/sch_multiq.c | 8 +++++--- net/sched/sch_prio.c | 11 +++++++---- net/sched/sch_qfq.c | 9 ++++++--- net/sched/sch_sfb.c | 15 +++++++++------ net/sched/sch_sfq.c | 11 +++++++---- 17 files changed, 121 insertions(+), 88 deletions(-) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 56838ab29b42..1e89b9ad3a4c 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -143,7 +143,7 @@ struct Qdisc_class_ops { void (*walk)(struct Qdisc *, struct qdisc_walker * arg); /* Filter manipulation */ - struct tcf_proto ** (*tcf_chain)(struct Qdisc *, unsigned long); + struct tcf_proto __rcu ** (*tcf_chain)(struct Qdisc *, unsigned long); unsigned long (*bind_tcf)(struct Qdisc *, unsigned long, u32 classid); void (*unbind_tcf)(struct Qdisc *, unsigned long); @@ -212,8 +212,8 @@ struct tcf_proto_ops { struct tcf_proto { /* Fast access part */ - struct tcf_proto *next; - void *root; + struct tcf_proto __rcu *next; + void __rcu *root; int (*classify)(struct sk_buff *, const struct tcf_proto *, struct tcf_result *); @@ -225,6 +225,7 @@ struct tcf_proto { struct Qdisc *q; void *data; const struct tcf_proto_ops *ops; + struct rcu_head rcu; }; struct qdisc_skb_cb { @@ -378,7 +379,7 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab); void tcf_destroy(struct tcf_proto *tp); -void tcf_destroy_chain(struct tcf_proto **fl); +void tcf_destroy_chain(struct tcf_proto __rcu **fl); /* Reset all TX qdiscs greater then index of a device. */ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index c28b0d327b12..e547efdaba9d 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -117,7 +117,6 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n) { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; - spinlock_t *root_lock; struct tcmsg *t; u32 protocol; u32 prio; @@ -125,7 +124,8 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n) u32 parent; struct net_device *dev; struct Qdisc *q; - struct tcf_proto **back, **chain; + struct tcf_proto __rcu **back; + struct tcf_proto __rcu **chain; struct tcf_proto *tp; const struct tcf_proto_ops *tp_ops; const struct Qdisc_class_ops *cops; @@ -197,7 +197,9 @@ replay: goto errout; /* Check the chain for existence of proto-tcf with this priority */ - for (back = chain; (tp = *back) != NULL; back = &tp->next) { + for (back = chain; + (tp = rtnl_dereference(*back)) != NULL; + back = &tp->next) { if (tp->prio >= prio) { if (tp->prio == prio) { if (!nprio || @@ -209,8 +211,6 @@ replay: } } - root_lock = qdisc_root_sleeping_lock(q); - if (tp == NULL) { /* Proto-tcf does not exist, create new one */ @@ -259,7 +259,8 @@ replay: } tp->ops = tp_ops; tp->protocol = protocol; - tp->prio = nprio ? : TC_H_MAJ(tcf_auto_prio(*back)); + tp->prio = nprio ? : + TC_H_MAJ(tcf_auto_prio(rtnl_dereference(*back))); tp->q = q; tp->classify = tp_ops->classify; tp->classid = parent; @@ -280,9 +281,9 @@ replay: if (fh == 0) { if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) { - spin_lock_bh(root_lock); - *back = tp->next; - spin_unlock_bh(root_lock); + struct tcf_proto *next = rtnl_dereference(tp->next); + + RCU_INIT_POINTER(*back, next); tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER); tcf_destroy(tp); @@ -322,10 +323,8 @@ replay: n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE); if (err == 0) { if (tp_created) { - spin_lock_bh(root_lock); - tp->next = *back; - *back = tp; - spin_unlock_bh(root_lock); + RCU_INIT_POINTER(tp->next, rtnl_dereference(*back)); + rcu_assign_pointer(*back, tp); } tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER); } else { @@ -420,7 +419,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) int s_t; struct net_device *dev; struct Qdisc *q; - struct tcf_proto *tp, **chain; + struct tcf_proto *tp, __rcu **chain; struct tcmsg *tcm = nlmsg_data(cb->nlh); unsigned long cl = 0; const struct Qdisc_class_ops *cops; @@ -454,7 +453,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) s_t = cb->args[0]; - for (tp = *chain, t = 0; tp; tp = tp->next, t++) { + for (tp = rtnl_dereference(*chain), t = 0; + tp; tp = rtnl_dereference(tp->next), t++) { if (t < s_t) continue; if (TC_H_MAJ(tcm->tcm_info) && diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 58bed7599db7..ca6248345937 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1781,7 +1781,7 @@ int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp, __be16 protocol = skb->protocol; int err; - for (; tp; tp = tp->next) { + for (; tp; tp = rcu_dereference_bh(tp->next)) { if (tp->protocol != protocol && tp->protocol != htons(ETH_P_ALL)) continue; @@ -1833,15 +1833,15 @@ void tcf_destroy(struct tcf_proto *tp) { tp->ops->destroy(tp); module_put(tp->ops->owner); - kfree(tp); + kfree_rcu(tp, rcu); } -void tcf_destroy_chain(struct tcf_proto **fl) +void tcf_destroy_chain(struct tcf_proto __rcu **fl) { struct tcf_proto *tp; - while ((tp = *fl) != NULL) { - *fl = tp->next; + while ((tp = rtnl_dereference(*fl)) != NULL) { + RCU_INIT_POINTER(*fl, tp->next); tcf_destroy(tp); } } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 8449b337f9e3..c398f9c3dbdd 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -41,7 +41,7 @@ struct atm_flow_data { struct Qdisc *q; /* FIFO, TBF, etc. */ - struct tcf_proto *filter_list; + struct tcf_proto __rcu *filter_list; struct atm_vcc *vcc; /* VCC; NULL if VCC is closed */ void (*old_pop)(struct atm_vcc *vcc, struct sk_buff *skb); /* chaining */ @@ -273,7 +273,7 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, error = -ENOBUFS; goto err_out; } - flow->filter_list = NULL; + RCU_INIT_POINTER(flow->filter_list, NULL); flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); if (!flow->q) flow->q = &noop_qdisc; @@ -311,7 +311,7 @@ static int atm_tc_delete(struct Qdisc *sch, unsigned long arg) pr_debug("atm_tc_delete(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); if (list_empty(&flow->list)) return -EINVAL; - if (flow->filter_list || flow == &p->link) + if (rcu_access_pointer(flow->filter_list) || flow == &p->link) return -EBUSY; /* * Reference count must be 2: one for "keepalive" (set at class @@ -345,7 +345,8 @@ static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker) } } -static struct tcf_proto **atm_tc_find_tcf(struct Qdisc *sch, unsigned long cl) +static struct tcf_proto __rcu **atm_tc_find_tcf(struct Qdisc *sch, + unsigned long cl) { struct atm_qdisc_data *p = qdisc_priv(sch); struct atm_flow_data *flow = (struct atm_flow_data *)cl; @@ -369,11 +370,12 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch) flow = NULL; if (TC_H_MAJ(skb->priority) != sch->handle || !(flow = (struct atm_flow_data *)atm_tc_get(sch, skb->priority))) { + struct tcf_proto *fl; + list_for_each_entry(flow, &p->flows, list) { - if (flow->filter_list) { - result = tc_classify_compat(skb, - flow->filter_list, - &res); + fl = rcu_dereference_bh(flow->filter_list); + if (fl) { + result = tc_classify_compat(skb, fl, &res); if (result < 0) continue; flow = (struct atm_flow_data *)res.class; @@ -544,7 +546,7 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) if (!p->link.q) p->link.q = &noop_qdisc; pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); - p->link.filter_list = NULL; + RCU_INIT_POINTER(p->link.filter_list, NULL); p->link.vcc = NULL; p->link.sock = NULL; p->link.classid = sch->handle; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 762a04bb8f6d..a3244a800501 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -133,7 +133,7 @@ struct cbq_class { struct gnet_stats_rate_est64 rate_est; struct tc_cbq_xstats xstats; - struct tcf_proto *filter_list; + struct tcf_proto __rcu *filter_list; int refcnt; int filters; @@ -221,6 +221,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) struct cbq_class **defmap; struct cbq_class *cl = NULL; u32 prio = skb->priority; + struct tcf_proto *fl; struct tcf_result res; /* @@ -235,11 +236,12 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) int result = 0; defmap = head->defaults; + fl = rcu_dereference_bh(head->filter_list); /* * Step 2+n. Apply classifier. */ - if (!head->filter_list || - (result = tc_classify_compat(skb, head->filter_list, &res)) < 0) + result = tc_classify_compat(skb, fl, &res); + if (!fl || result < 0) goto fallback; cl = (void *)res.class; @@ -1954,7 +1956,8 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg) return 0; } -static struct tcf_proto **cbq_find_tcf(struct Qdisc *sch, unsigned long arg) +static struct tcf_proto __rcu **cbq_find_tcf(struct Qdisc *sch, + unsigned long arg) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl = (struct cbq_class *)arg; diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index ed30e436128b..74813e6b6ff6 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -57,7 +57,7 @@ struct choke_sched_data { /* Variables */ struct red_vars vars; - struct tcf_proto *filter_list; + struct tcf_proto __rcu *filter_list; struct { u32 prob_drop; /* Early probability drops */ u32 prob_mark; /* Early probability marks */ @@ -193,9 +193,11 @@ static bool choke_classify(struct sk_buff *skb, { struct choke_sched_data *q = qdisc_priv(sch); struct tcf_result res; + struct tcf_proto *fl; int result; - result = tc_classify(skb, q->filter_list, &res); + fl = rcu_dereference_bh(q->filter_list); + result = tc_classify(skb, fl, &res); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { @@ -249,7 +251,7 @@ static bool choke_match_random(const struct choke_sched_data *q, return false; oskb = choke_peek_random(q, pidx); - if (q->filter_list) + if (rcu_access_pointer(q->filter_list)) return choke_get_classid(nskb) == choke_get_classid(oskb); return choke_match_flow(oskb, nskb); @@ -257,11 +259,11 @@ static bool choke_match_random(const struct choke_sched_data *q, static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch) { + int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; struct choke_sched_data *q = qdisc_priv(sch); const struct red_parms *p = &q->parms; - int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - if (q->filter_list) { + if (rcu_access_pointer(q->filter_list)) { /* If using external classifiers, get result and record it. */ if (!choke_classify(skb, sch, &ret)) goto other_drop; /* Packet was eaten by filter */ @@ -554,7 +556,8 @@ static unsigned long choke_bind(struct Qdisc *sch, unsigned long parent, return 0; } -static struct tcf_proto **choke_find_tcf(struct Qdisc *sch, unsigned long cl) +static struct tcf_proto __rcu **choke_find_tcf(struct Qdisc *sch, + unsigned long cl) { struct choke_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 7bbbfe112192..d8b5ccfd248a 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -35,7 +35,7 @@ struct drr_class { struct drr_sched { struct list_head active; - struct tcf_proto *filter_list; + struct tcf_proto __rcu *filter_list; struct Qdisc_class_hash clhash; }; @@ -184,7 +184,8 @@ static void drr_put_class(struct Qdisc *sch, unsigned long arg) drr_destroy_class(sch, cl); } -static struct tcf_proto **drr_tcf_chain(struct Qdisc *sch, unsigned long cl) +static struct tcf_proto __rcu **drr_tcf_chain(struct Qdisc *sch, + unsigned long cl) { struct drr_sched *q = qdisc_priv(sch); @@ -319,6 +320,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl; struct tcf_result res; + struct tcf_proto *fl; int result; if (TC_H_MAJ(skb->priority ^ sch->handle) == 0) { @@ -328,7 +330,8 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, } *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tc_classify(skb, q->filter_list, &res); + fl = rcu_dereference_bh(q->filter_list); + result = tc_classify(skb, fl, &res); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 49d6ef338b55..485e456c8139 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -37,7 +37,7 @@ struct dsmark_qdisc_data { struct Qdisc *q; - struct tcf_proto *filter_list; + struct tcf_proto __rcu *filter_list; u8 *mask; /* "owns" the array */ u8 *value; u16 indices; @@ -186,8 +186,8 @@ ignore: } } -static inline struct tcf_proto **dsmark_find_tcf(struct Qdisc *sch, - unsigned long cl) +static inline struct tcf_proto __rcu **dsmark_find_tcf(struct Qdisc *sch, + unsigned long cl) { struct dsmark_qdisc_data *p = qdisc_priv(sch); return &p->filter_list; @@ -229,7 +229,8 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch) skb->tc_index = TC_H_MIN(skb->priority); else { struct tcf_result res; - int result = tc_classify(skb, p->filter_list, &res); + struct tcf_proto *fl = rcu_dereference_bh(p->filter_list); + int result = tc_classify(skb, fl, &res); pr_debug("result %d class 0x%04x\n", result, res.classid); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index cc56c8bb9bed..105cf5557630 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -52,7 +52,7 @@ struct fq_codel_flow { }; /* please try to keep this structure <= 64 bytes */ struct fq_codel_sched_data { - struct tcf_proto *filter_list; /* optional external classifier */ + struct tcf_proto __rcu *filter_list; /* optional external classifier */ struct fq_codel_flow *flows; /* Flows table [flows_cnt] */ u32 *backlogs; /* backlog table [flows_cnt] */ u32 flows_cnt; /* number of flows */ @@ -85,6 +85,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) { struct fq_codel_sched_data *q = qdisc_priv(sch); + struct tcf_proto *filter; struct tcf_result res; int result; @@ -93,11 +94,12 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch, TC_H_MIN(skb->priority) <= q->flows_cnt) return TC_H_MIN(skb->priority); - if (!q->filter_list) + filter = rcu_dereference(q->filter_list); + if (!filter) return fq_codel_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tc_classify(skb, q->filter_list, &res); + result = tc_classify(skb, filter, &res); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { @@ -496,7 +498,8 @@ static void fq_codel_put(struct Qdisc *q, unsigned long cl) { } -static struct tcf_proto **fq_codel_find_tcf(struct Qdisc *sch, unsigned long cl) +static struct tcf_proto __rcu **fq_codel_find_tcf(struct Qdisc *sch, + unsigned long cl) { struct fq_codel_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index ec8aeaac1dd7..04b0de4c68b5 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -116,7 +116,7 @@ struct hfsc_class { struct gnet_stats_queue qstats; struct gnet_stats_rate_est64 rate_est; unsigned int level; /* class level in hierarchy */ - struct tcf_proto *filter_list; /* filter list */ + struct tcf_proto __rcu *filter_list; /* filter list */ unsigned int filter_cnt; /* filter count */ struct hfsc_sched *sched; /* scheduler data */ @@ -1161,7 +1161,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; head = &q->root; - tcf = q->root.filter_list; + tcf = rcu_dereference_bh(q->root.filter_list); while (tcf && (result = tc_classify(skb, tcf, &res)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { @@ -1185,7 +1185,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) return cl; /* hit leaf class */ /* apply inner filter chain */ - tcf = cl->filter_list; + tcf = rcu_dereference_bh(cl->filter_list); head = cl; } @@ -1285,7 +1285,7 @@ hfsc_unbind_tcf(struct Qdisc *sch, unsigned long arg) cl->filter_cnt--; } -static struct tcf_proto ** +static struct tcf_proto __rcu ** hfsc_tcf_chain(struct Qdisc *sch, unsigned long arg) { struct hfsc_sched *q = qdisc_priv(sch); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index aea942ce6008..6d16b9b81c28 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -103,7 +103,7 @@ struct htb_class { u32 prio; /* these two are used only by leaves... */ int quantum; /* but stored for parent-to-leaf return */ - struct tcf_proto *filter_list; /* class attached filters */ + struct tcf_proto __rcu *filter_list; /* class attached filters */ int filter_cnt; int refcnt; /* usage count of this class */ @@ -153,7 +153,7 @@ struct htb_sched { int rate2quantum; /* quant = rate / rate2quantum */ /* filters for qdisc itself */ - struct tcf_proto *filter_list; + struct tcf_proto __rcu *filter_list; #define HTB_WARN_TOOMANYEVENTS 0x1 unsigned int warned; /* only one warning */ @@ -223,9 +223,9 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, if (cl->level == 0) return cl; /* Start with inner filter chain if a non-leaf class is selected */ - tcf = cl->filter_list; + tcf = rcu_dereference_bh(cl->filter_list); } else { - tcf = q->filter_list; + tcf = rcu_dereference_bh(q->filter_list); } *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; @@ -251,7 +251,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, return cl; /* we hit leaf; return it */ /* we have got inner class; apply inner filter chain */ - tcf = cl->filter_list; + tcf = rcu_dereference_bh(cl->filter_list); } /* classification failed; try to use default class */ cl = htb_find(TC_H_MAKE(TC_H_MAJ(sch->handle), q->defcls), sch); @@ -1519,11 +1519,12 @@ failure: return err; } -static struct tcf_proto **htb_find_tcf(struct Qdisc *sch, unsigned long arg) +static struct tcf_proto __rcu **htb_find_tcf(struct Qdisc *sch, + unsigned long arg) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)arg; - struct tcf_proto **fl = cl ? &cl->filter_list : &q->filter_list; + struct tcf_proto __rcu **fl = cl ? &cl->filter_list : &q->filter_list; return fl; } diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 62871c14e1f9..b351125f3849 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -17,7 +17,7 @@ struct ingress_qdisc_data { - struct tcf_proto *filter_list; + struct tcf_proto __rcu *filter_list; }; /* ------------------------- Class/flow operations ------------------------- */ @@ -46,7 +46,8 @@ static void ingress_walk(struct Qdisc *sch, struct qdisc_walker *walker) { } -static struct tcf_proto **ingress_find_tcf(struct Qdisc *sch, unsigned long cl) +static struct tcf_proto __rcu **ingress_find_tcf(struct Qdisc *sch, + unsigned long cl) { struct ingress_qdisc_data *p = qdisc_priv(sch); @@ -59,9 +60,10 @@ static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct ingress_qdisc_data *p = qdisc_priv(sch); struct tcf_result res; + struct tcf_proto *fl = rcu_dereference_bh(p->filter_list); int result; - result = tc_classify(skb, p->filter_list, &res); + result = tc_classify(skb, fl, &res); qdisc_bstats_update(sch, skb); switch (result) { diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index afb050a735fa..c0466c1840f3 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -31,7 +31,7 @@ struct multiq_sched_data { u16 bands; u16 max_bands; u16 curband; - struct tcf_proto *filter_list; + struct tcf_proto __rcu *filter_list; struct Qdisc **queues; }; @@ -42,10 +42,11 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) struct multiq_sched_data *q = qdisc_priv(sch); u32 band; struct tcf_result res; + struct tcf_proto *fl = rcu_dereference_bh(q->filter_list); int err; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - err = tc_classify(skb, q->filter_list, &res); + err = tc_classify(skb, fl, &res); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: @@ -388,7 +389,8 @@ static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg) } } -static struct tcf_proto **multiq_find_tcf(struct Qdisc *sch, unsigned long cl) +static struct tcf_proto __rcu **multiq_find_tcf(struct Qdisc *sch, + unsigned long cl) { struct multiq_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 79359b69ad8d..03ef99e52a5c 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -24,7 +24,7 @@ struct prio_sched_data { int bands; - struct tcf_proto *filter_list; + struct tcf_proto __rcu *filter_list; u8 prio2band[TC_PRIO_MAX+1]; struct Qdisc *queues[TCQ_PRIO_BANDS]; }; @@ -36,11 +36,13 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) struct prio_sched_data *q = qdisc_priv(sch); u32 band = skb->priority; struct tcf_result res; + struct tcf_proto *fl; int err; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; if (TC_H_MAJ(skb->priority) != sch->handle) { - err = tc_classify(skb, q->filter_list, &res); + fl = rcu_dereference_bh(q->filter_list); + err = tc_classify(skb, fl, &res); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: @@ -50,7 +52,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) return NULL; } #endif - if (!q->filter_list || err < 0) { + if (!fl || err < 0) { if (TC_H_MAJ(band)) band = 0; return q->queues[q->prio2band[band & TC_PRIO_MAX]]; @@ -351,7 +353,8 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg) } } -static struct tcf_proto **prio_find_tcf(struct Qdisc *sch, unsigned long cl) +static struct tcf_proto __rcu **prio_find_tcf(struct Qdisc *sch, + unsigned long cl) { struct prio_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 8056fb4e618a..602ea01a4ddd 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -181,7 +181,7 @@ struct qfq_group { }; struct qfq_sched { - struct tcf_proto *filter_list; + struct tcf_proto __rcu *filter_list; struct Qdisc_class_hash clhash; u64 oldV, V; /* Precise virtual times. */ @@ -576,7 +576,8 @@ static void qfq_put_class(struct Qdisc *sch, unsigned long arg) qfq_destroy_class(sch, cl); } -static struct tcf_proto **qfq_tcf_chain(struct Qdisc *sch, unsigned long cl) +static struct tcf_proto __rcu **qfq_tcf_chain(struct Qdisc *sch, + unsigned long cl) { struct qfq_sched *q = qdisc_priv(sch); @@ -704,6 +705,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch, struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl; struct tcf_result res; + struct tcf_proto *fl; int result; if (TC_H_MAJ(skb->priority ^ sch->handle) == 0) { @@ -714,7 +716,8 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch, } *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tc_classify(skb, q->filter_list, &res); + fl = rcu_dereference_bh(q->filter_list); + result = tc_classify(skb, fl, &res); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 9b0f7093d970..1562fb2b3f46 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -55,7 +55,7 @@ struct sfb_bins { struct sfb_sched_data { struct Qdisc *qdisc; - struct tcf_proto *filter_list; + struct tcf_proto __rcu *filter_list; unsigned long rehash_interval; unsigned long warmup_time; /* double buffering warmup time in jiffies */ u32 max; @@ -253,13 +253,13 @@ static bool sfb_rate_limit(struct sk_buff *skb, struct sfb_sched_data *q) return false; } -static bool sfb_classify(struct sk_buff *skb, struct sfb_sched_data *q, +static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl, int *qerr, u32 *salt) { struct tcf_result res; int result; - result = tc_classify(skb, q->filter_list, &res); + result = tc_classify(skb, fl, &res); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { @@ -281,6 +281,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch) struct sfb_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; + struct tcf_proto *fl; int i; u32 p_min = ~0; u32 minqlen = ~0; @@ -306,9 +307,10 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch) } } - if (q->filter_list) { + fl = rcu_dereference_bh(q->filter_list); + if (fl) { /* If using external classifiers, get result and record it. */ - if (!sfb_classify(skb, q, &ret, &salt)) + if (!sfb_classify(skb, fl, &ret, &salt)) goto other_drop; keys.src = salt; keys.dst = 0; @@ -660,7 +662,8 @@ static void sfb_walk(struct Qdisc *sch, struct qdisc_walker *walker) } } -static struct tcf_proto **sfb_find_tcf(struct Qdisc *sch, unsigned long cl) +static struct tcf_proto __rcu **sfb_find_tcf(struct Qdisc *sch, + unsigned long cl) { struct sfb_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 211db9017c35..80c36bd54abc 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -125,7 +125,7 @@ struct sfq_sched_data { u8 cur_depth; /* depth of longest slot */ u8 flags; unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */ - struct tcf_proto *filter_list; + struct tcf_proto __rcu *filter_list; sfq_index *ht; /* Hash table ('divisor' slots) */ struct sfq_slot *slots; /* Flows table ('maxflows' entries) */ @@ -187,6 +187,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, { struct sfq_sched_data *q = qdisc_priv(sch); struct tcf_result res; + struct tcf_proto *fl; int result; if (TC_H_MAJ(skb->priority) == sch->handle && @@ -194,13 +195,14 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, TC_H_MIN(skb->priority) <= q->divisor) return TC_H_MIN(skb->priority); - if (!q->filter_list) { + fl = rcu_dereference_bh(q->filter_list); + if (!fl) { skb_flow_dissect(skb, &sfq_skb_cb(skb)->keys); return sfq_hash(q, skb) + 1; } *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tc_classify(skb, q->filter_list, &res); + result = tc_classify(skb, fl, &res); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { @@ -836,7 +838,8 @@ static void sfq_put(struct Qdisc *q, unsigned long cl) { } -static struct tcf_proto **sfq_find_tcf(struct Qdisc *sch, unsigned long cl) +static struct tcf_proto __rcu **sfq_find_tcf(struct Qdisc *sch, + unsigned long cl) { struct sfq_sched_data *q = qdisc_priv(sch); From c8b9affec519d27ce202a7ed22617eecbd96f127 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 12 Sep 2014 20:05:59 -0700 Subject: [PATCH 03/12] net: sched: cls_basic use RCU Enable basic classifier for RCU. Dereferencing tp->root may look a bit strange here but it is needed by my accounting because it is allocated at init time and needs to be kfree'd at destroy time. However because it may be referenced in the classify() path we must wait an RCU grace period before free'ing it. We use kfree_rcu() and rcu_ APIs to enforce this. This pattern is used in all the classifiers. Also the hgenerator can be incremented without concern because it is always incremented under RTNL. Signed-off-by: John Fastabend Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/cls_basic.c | 80 ++++++++++++++++++++++++------------------- 1 file changed, 45 insertions(+), 35 deletions(-) diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 0ae1813e3e90..1937298d6775 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -24,6 +24,7 @@ struct basic_head { u32 hgenerator; struct list_head flist; + struct rcu_head rcu; }; struct basic_filter { @@ -31,17 +32,19 @@ struct basic_filter { struct tcf_exts exts; struct tcf_ematch_tree ematches; struct tcf_result res; + struct tcf_proto *tp; struct list_head link; + struct rcu_head rcu; }; static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { int r; - struct basic_head *head = tp->root; + struct basic_head *head = rcu_dereference_bh(tp->root); struct basic_filter *f; - list_for_each_entry(f, &head->flist, link) { + list_for_each_entry_rcu(f, &head->flist, link) { if (!tcf_em_tree_match(skb, &f->ematches, NULL)) continue; *res = f->res; @@ -56,7 +59,7 @@ static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, static unsigned long basic_get(struct tcf_proto *tp, u32 handle) { unsigned long l = 0UL; - struct basic_head *head = tp->root; + struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f; if (head == NULL) @@ -81,12 +84,15 @@ static int basic_init(struct tcf_proto *tp) if (head == NULL) return -ENOBUFS; INIT_LIST_HEAD(&head->flist); - tp->root = head; + rcu_assign_pointer(tp->root, head); return 0; } -static void basic_delete_filter(struct tcf_proto *tp, struct basic_filter *f) +static void basic_delete_filter(struct rcu_head *head) { + struct basic_filter *f = container_of(head, struct basic_filter, rcu); + struct tcf_proto *tp = f->tp; + tcf_unbind_filter(tp, &f->res); tcf_exts_destroy(tp, &f->exts); tcf_em_tree_destroy(tp, &f->ematches); @@ -95,27 +101,26 @@ static void basic_delete_filter(struct tcf_proto *tp, struct basic_filter *f) static void basic_destroy(struct tcf_proto *tp) { - struct basic_head *head = tp->root; + struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f, *n; list_for_each_entry_safe(f, n, &head->flist, link) { - list_del(&f->link); - basic_delete_filter(tp, f); + list_del_rcu(&f->link); + call_rcu(&f->rcu, basic_delete_filter); } - kfree(head); + RCU_INIT_POINTER(tp->root, NULL); + kfree_rcu(head, rcu); } static int basic_delete(struct tcf_proto *tp, unsigned long arg) { - struct basic_head *head = tp->root; + struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *t, *f = (struct basic_filter *) arg; list_for_each_entry(t, &head->flist, link) if (t == f) { - tcf_tree_lock(tp); - list_del(&t->link); - tcf_tree_unlock(tp); - basic_delete_filter(tp, t); + list_del_rcu(&t->link); + call_rcu(&t->rcu, basic_delete_filter); return 0; } @@ -152,6 +157,7 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp, tcf_exts_change(tp, &f->exts, &e); tcf_em_tree_change(tp, &f->ematches, &t); + f->tp = tp; return 0; errout: @@ -164,9 +170,10 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, struct nlattr **tca, unsigned long *arg, bool ovr) { int err; - struct basic_head *head = tp->root; + struct basic_head *head = rtnl_dereference(tp->root); struct nlattr *tb[TCA_BASIC_MAX + 1]; - struct basic_filter *f = (struct basic_filter *) *arg; + struct basic_filter *fold = (struct basic_filter *) *arg; + struct basic_filter *fnew; if (tca[TCA_OPTIONS] == NULL) return -EINVAL; @@ -176,22 +183,23 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, if (err < 0) return err; - if (f != NULL) { - if (handle && f->handle != handle) + if (fold != NULL) { + if (handle && fold->handle != handle) return -EINVAL; - return basic_set_parms(net, tp, f, base, tb, tca[TCA_RATE], ovr); } err = -ENOBUFS; - f = kzalloc(sizeof(*f), GFP_KERNEL); - if (f == NULL) + fnew = kzalloc(sizeof(*fnew), GFP_KERNEL); + if (fnew == NULL) goto errout; - tcf_exts_init(&f->exts, TCA_BASIC_ACT, TCA_BASIC_POLICE); + tcf_exts_init(&fnew->exts, TCA_BASIC_ACT, TCA_BASIC_POLICE); err = -EINVAL; - if (handle) - f->handle = handle; - else { + if (handle) { + fnew->handle = handle; + } else if (fold) { + fnew->handle = fold->handle; + } else { unsigned int i = 0x80000000; do { if (++head->hgenerator == 0x7FFFFFFF) @@ -203,29 +211,31 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, goto errout; } - f->handle = head->hgenerator; + fnew->handle = head->hgenerator; } - err = basic_set_parms(net, tp, f, base, tb, tca[TCA_RATE], ovr); + err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], ovr); if (err < 0) goto errout; - tcf_tree_lock(tp); - list_add(&f->link, &head->flist); - tcf_tree_unlock(tp); - *arg = (unsigned long) f; + *arg = (unsigned long)fnew; + + if (fold) { + list_replace_rcu(&fold->link, &fnew->link); + call_rcu(&fold->rcu, basic_delete_filter); + } else { + list_add_rcu(&fnew->link, &head->flist); + } return 0; errout: - if (*arg == 0UL && f) - kfree(f); - + kfree(fnew); return err; } static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct basic_head *head = tp->root; + struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f; list_for_each_entry(f, &head->flist, link) { From c7953ef23042b7c4fc2be5ecdd216aacff6df5eb Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 12 Sep 2014 20:06:26 -0700 Subject: [PATCH 04/12] net: sched: cls_cgroup use RCU Make cgroup classifier safe for RCU. Also drops the calls in the classify routine that were doing a rcu_read_lock()/rcu_read_unlock(). If the rcu_read_lock() isn't held entering this routine we have issues with deleting the classifier chain so remove the unnecessary rcu_read_lock()/rcu_read_unlock() pair noting all paths AFAIK hold rcu_read_lock. If there is a case where classify is called without the rcu read lock then an rcu splat will occur and we can correct it. Signed-off-by: John Fastabend Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/cls_cgroup.c | 67 ++++++++++++++++++++++++++---------------- 1 file changed, 41 insertions(+), 26 deletions(-) diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index cacf01bd04f0..3b7548759998 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -22,17 +22,17 @@ struct cls_cgroup_head { u32 handle; struct tcf_exts exts; struct tcf_ematch_tree ematches; + struct tcf_proto *tp; + struct rcu_head rcu; }; static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct cls_cgroup_head *head = tp->root; + struct cls_cgroup_head *head = rcu_dereference_bh(tp->root); u32 classid; - rcu_read_lock(); classid = task_cls_state(current)->classid; - rcu_read_unlock(); /* * Due to the nature of the classifier it is required to ignore all @@ -80,13 +80,25 @@ static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = { [TCA_CGROUP_EMATCHES] = { .type = NLA_NESTED }, }; +static void cls_cgroup_destroy_rcu(struct rcu_head *root) +{ + struct cls_cgroup_head *head = container_of(root, + struct cls_cgroup_head, + rcu); + + tcf_exts_destroy(head->tp, &head->exts); + tcf_em_tree_destroy(head->tp, &head->ematches); + kfree(head); +} + static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, unsigned long *arg, bool ovr) { struct nlattr *tb[TCA_CGROUP_MAX + 1]; - struct cls_cgroup_head *head = tp->root; + struct cls_cgroup_head *head = rtnl_dereference(tp->root); + struct cls_cgroup_head *new; struct tcf_ematch_tree t; struct tcf_exts e; int err; @@ -94,25 +106,24 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, if (!tca[TCA_OPTIONS]) return -EINVAL; - if (head == NULL) { - if (!handle) - return -EINVAL; + if (!head && !handle) + return -EINVAL; - head = kzalloc(sizeof(*head), GFP_KERNEL); - if (head == NULL) - return -ENOBUFS; - - tcf_exts_init(&head->exts, TCA_CGROUP_ACT, TCA_CGROUP_POLICE); - head->handle = handle; - - tcf_tree_lock(tp); - tp->root = head; - tcf_tree_unlock(tp); - } - - if (handle != head->handle) + if (head && handle != head->handle) return -ENOENT; + new = kzalloc(sizeof(*head), GFP_KERNEL); + if (!new) + return -ENOBUFS; + + if (head) { + new->handle = head->handle; + } else { + tcf_exts_init(&new->exts, TCA_CGROUP_ACT, TCA_CGROUP_POLICE); + new->handle = handle; + } + + new->tp = tp; err = nla_parse_nested(tb, TCA_CGROUP_MAX, tca[TCA_OPTIONS], cgroup_policy); if (err < 0) @@ -127,20 +138,24 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, if (err < 0) return err; - tcf_exts_change(tp, &head->exts, &e); - tcf_em_tree_change(tp, &head->ematches, &t); + tcf_exts_change(tp, &new->exts, &e); + tcf_em_tree_change(tp, &new->ematches, &t); + rcu_assign_pointer(tp->root, new); + if (head) + call_rcu(&head->rcu, cls_cgroup_destroy_rcu); return 0; } static void cls_cgroup_destroy(struct tcf_proto *tp) { - struct cls_cgroup_head *head = tp->root; + struct cls_cgroup_head *head = rtnl_dereference(tp->root); if (head) { tcf_exts_destroy(tp, &head->exts); tcf_em_tree_destroy(tp, &head->ematches); - kfree(head); + RCU_INIT_POINTER(tp->root, NULL); + kfree_rcu(head, rcu); } } @@ -151,7 +166,7 @@ static int cls_cgroup_delete(struct tcf_proto *tp, unsigned long arg) static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct cls_cgroup_head *head = tp->root; + struct cls_cgroup_head *head = rtnl_dereference(tp->root); if (arg->count < arg->skip) goto skip; @@ -167,7 +182,7 @@ skip: static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct cls_cgroup_head *head = tp->root; + struct cls_cgroup_head *head = rtnl_dereference(tp->root); unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; From ad7a97ae7aef6227456c7a90bf3b3522d25f3171 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 12 Sep 2014 20:06:55 -0700 Subject: [PATCH 05/12] net: sched: cls_flow use RCU Signed-off-by: John Fastabend Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/cls_flow.c | 145 +++++++++++++++++++++++++------------------ 1 file changed, 84 insertions(+), 61 deletions(-) diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 35be16f7c192..95736fa479f3 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -34,12 +34,14 @@ struct flow_head { struct list_head filters; + struct rcu_head rcu; }; struct flow_filter { struct list_head list; struct tcf_exts exts; struct tcf_ematch_tree ematches; + struct tcf_proto *tp; struct timer_list perturb_timer; u32 perturb_period; u32 handle; @@ -54,6 +56,7 @@ struct flow_filter { u32 divisor; u32 baseclass; u32 hashrnd; + struct rcu_head rcu; }; static inline u32 addr_fold(void *addr) @@ -276,14 +279,14 @@ static u32 flow_key_get(struct sk_buff *skb, int key, struct flow_keys *flow) static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct flow_head *head = tp->root; + struct flow_head *head = rcu_dereference_bh(tp->root); struct flow_filter *f; u32 keymask; u32 classid; unsigned int n, key; int r; - list_for_each_entry(f, &head->filters, list) { + list_for_each_entry_rcu(f, &head->filters, list) { u32 keys[FLOW_KEY_MAX + 1]; struct flow_keys flow_keys; @@ -346,13 +349,23 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = { [TCA_FLOW_PERTURB] = { .type = NLA_U32 }, }; +static void flow_destroy_filter(struct rcu_head *head) +{ + struct flow_filter *f = container_of(head, struct flow_filter, rcu); + + del_timer_sync(&f->perturb_timer); + tcf_exts_destroy(f->tp, &f->exts); + tcf_em_tree_destroy(f->tp, &f->ematches); + kfree(f); +} + static int flow_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, unsigned long *arg, bool ovr) { - struct flow_head *head = tp->root; - struct flow_filter *f; + struct flow_head *head = rtnl_dereference(tp->root); + struct flow_filter *fold, *fnew; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_FLOW_MAX + 1]; struct tcf_exts e; @@ -401,20 +414,42 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto err1; - f = (struct flow_filter *)*arg; - if (f != NULL) { + err = -ENOBUFS; + fnew = kzalloc(sizeof(*fnew), GFP_KERNEL); + if (!fnew) + goto err2; + + fold = (struct flow_filter *)*arg; + if (fold) { err = -EINVAL; - if (f->handle != handle && handle) + if (fold->handle != handle && handle) goto err2; - mode = f->mode; + /* Copy fold into fnew */ + fnew->handle = fold->handle; + fnew->keymask = fold->keymask; + fnew->tp = fold->tp; + + fnew->handle = fold->handle; + fnew->nkeys = fold->nkeys; + fnew->keymask = fold->keymask; + fnew->mode = fold->mode; + fnew->mask = fold->mask; + fnew->xor = fold->xor; + fnew->rshift = fold->rshift; + fnew->addend = fold->addend; + fnew->divisor = fold->divisor; + fnew->baseclass = fold->baseclass; + fnew->hashrnd = fold->hashrnd; + + mode = fold->mode; if (tb[TCA_FLOW_MODE]) mode = nla_get_u32(tb[TCA_FLOW_MODE]); if (mode != FLOW_MODE_HASH && nkeys > 1) goto err2; if (mode == FLOW_MODE_HASH) - perturb_period = f->perturb_period; + perturb_period = fold->perturb_period; if (tb[TCA_FLOW_PERTURB]) { if (mode != FLOW_MODE_HASH) goto err2; @@ -444,83 +479,70 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, if (TC_H_MIN(baseclass) == 0) baseclass = TC_H_MAKE(baseclass, 1); - err = -ENOBUFS; - f = kzalloc(sizeof(*f), GFP_KERNEL); - if (f == NULL) - goto err2; - - f->handle = handle; - f->mask = ~0U; - tcf_exts_init(&f->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE); - - get_random_bytes(&f->hashrnd, 4); - f->perturb_timer.function = flow_perturbation; - f->perturb_timer.data = (unsigned long)f; - init_timer_deferrable(&f->perturb_timer); + fnew->handle = handle; + fnew->mask = ~0U; + fnew->tp = tp; + get_random_bytes(&fnew->hashrnd, 4); + tcf_exts_init(&fnew->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE); } - tcf_exts_change(tp, &f->exts, &e); - tcf_em_tree_change(tp, &f->ematches, &t); + fnew->perturb_timer.function = flow_perturbation; + fnew->perturb_timer.data = (unsigned long)fnew; + init_timer_deferrable(&fnew->perturb_timer); - tcf_tree_lock(tp); + tcf_exts_change(tp, &fnew->exts, &e); + tcf_em_tree_change(tp, &fnew->ematches, &t); if (tb[TCA_FLOW_KEYS]) { - f->keymask = keymask; - f->nkeys = nkeys; + fnew->keymask = keymask; + fnew->nkeys = nkeys; } - f->mode = mode; + fnew->mode = mode; if (tb[TCA_FLOW_MASK]) - f->mask = nla_get_u32(tb[TCA_FLOW_MASK]); + fnew->mask = nla_get_u32(tb[TCA_FLOW_MASK]); if (tb[TCA_FLOW_XOR]) - f->xor = nla_get_u32(tb[TCA_FLOW_XOR]); + fnew->xor = nla_get_u32(tb[TCA_FLOW_XOR]); if (tb[TCA_FLOW_RSHIFT]) - f->rshift = nla_get_u32(tb[TCA_FLOW_RSHIFT]); + fnew->rshift = nla_get_u32(tb[TCA_FLOW_RSHIFT]); if (tb[TCA_FLOW_ADDEND]) - f->addend = nla_get_u32(tb[TCA_FLOW_ADDEND]); + fnew->addend = nla_get_u32(tb[TCA_FLOW_ADDEND]); if (tb[TCA_FLOW_DIVISOR]) - f->divisor = nla_get_u32(tb[TCA_FLOW_DIVISOR]); + fnew->divisor = nla_get_u32(tb[TCA_FLOW_DIVISOR]); if (baseclass) - f->baseclass = baseclass; + fnew->baseclass = baseclass; - f->perturb_period = perturb_period; - del_timer(&f->perturb_timer); + fnew->perturb_period = perturb_period; if (perturb_period) - mod_timer(&f->perturb_timer, jiffies + perturb_period); + mod_timer(&fnew->perturb_timer, jiffies + perturb_period); if (*arg == 0) - list_add_tail(&f->list, &head->filters); + list_add_tail_rcu(&fnew->list, &head->filters); + else + list_replace_rcu(&fnew->list, &fold->list); - tcf_tree_unlock(tp); + *arg = (unsigned long)fnew; - *arg = (unsigned long)f; + if (fold) + call_rcu(&fold->rcu, flow_destroy_filter); return 0; err2: tcf_em_tree_destroy(tp, &t); + kfree(fnew); err1: tcf_exts_destroy(tp, &e); return err; } -static void flow_destroy_filter(struct tcf_proto *tp, struct flow_filter *f) -{ - del_timer_sync(&f->perturb_timer); - tcf_exts_destroy(tp, &f->exts); - tcf_em_tree_destroy(tp, &f->ematches); - kfree(f); -} - static int flow_delete(struct tcf_proto *tp, unsigned long arg) { struct flow_filter *f = (struct flow_filter *)arg; - tcf_tree_lock(tp); - list_del(&f->list); - tcf_tree_unlock(tp); - flow_destroy_filter(tp, f); + list_del_rcu(&f->list); + call_rcu(&f->rcu, flow_destroy_filter); return 0; } @@ -532,28 +554,29 @@ static int flow_init(struct tcf_proto *tp) if (head == NULL) return -ENOBUFS; INIT_LIST_HEAD(&head->filters); - tp->root = head; + rcu_assign_pointer(tp->root, head); return 0; } static void flow_destroy(struct tcf_proto *tp) { - struct flow_head *head = tp->root; + struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f, *next; list_for_each_entry_safe(f, next, &head->filters, list) { - list_del(&f->list); - flow_destroy_filter(tp, f); + list_del_rcu(&f->list); + call_rcu(&f->rcu, flow_destroy_filter); } - kfree(head); + RCU_INIT_POINTER(tp->root, NULL); + kfree_rcu(head, rcu); } static unsigned long flow_get(struct tcf_proto *tp, u32 handle) { - struct flow_head *head = tp->root; + struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f; - list_for_each_entry(f, &head->filters, list) + list_for_each_entry_rcu(f, &head->filters, list) if (f->handle == handle) return (unsigned long)f; return 0; @@ -626,10 +649,10 @@ nla_put_failure: static void flow_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct flow_head *head = tp->root; + struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f; - list_for_each_entry(f, &head->filters, list) { + list_for_each_entry_rcu(f, &head->filters, list) { if (arg->count < arg->skip) goto skip; if (arg->fn(tp, (unsigned long)f, arg) < 0) { From 1f31fea5a69089a40561548ff5931bc5e4e79b61 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 12 Sep 2014 20:07:22 -0700 Subject: [PATCH 06/12] net: sched: fw use RCU RCU'ify fw classifier. Signed-off-by: John Fastabend Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/cls_fw.c | 111 +++++++++++++++++++++++++++++++-------------- 1 file changed, 77 insertions(+), 34 deletions(-) diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 861b03ccfed0..006b45a67fdd 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -33,17 +33,20 @@ struct fw_head { u32 mask; - struct fw_filter *ht[HTSIZE]; + struct fw_filter __rcu *ht[HTSIZE]; + struct rcu_head rcu; }; struct fw_filter { - struct fw_filter *next; + struct fw_filter __rcu *next; u32 id; struct tcf_result res; #ifdef CONFIG_NET_CLS_IND int ifindex; #endif /* CONFIG_NET_CLS_IND */ struct tcf_exts exts; + struct tcf_proto *tp; + struct rcu_head rcu; }; static u32 fw_hash(u32 handle) @@ -56,14 +59,16 @@ static u32 fw_hash(u32 handle) static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct fw_head *head = tp->root; + struct fw_head *head = rcu_dereference_bh(tp->root); struct fw_filter *f; int r; u32 id = skb->mark; if (head != NULL) { id &= head->mask; - for (f = head->ht[fw_hash(id)]; f; f = f->next) { + + for (f = rcu_dereference_bh(head->ht[fw_hash(id)]); f; + f = rcu_dereference_bh(f->next)) { if (f->id == id) { *res = f->res; #ifdef CONFIG_NET_CLS_IND @@ -92,13 +97,14 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, static unsigned long fw_get(struct tcf_proto *tp, u32 handle) { - struct fw_head *head = tp->root; + struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f; if (head == NULL) return 0; - for (f = head->ht[fw_hash(handle)]; f; f = f->next) { + f = rtnl_dereference(head->ht[fw_hash(handle)]); + for (; f; f = rtnl_dereference(f->next)) { if (f->id == handle) return (unsigned long)f; } @@ -114,8 +120,11 @@ static int fw_init(struct tcf_proto *tp) return 0; } -static void fw_delete_filter(struct tcf_proto *tp, struct fw_filter *f) +static void fw_delete_filter(struct rcu_head *head) { + struct fw_filter *f = container_of(head, struct fw_filter, rcu); + struct tcf_proto *tp = f->tp; + tcf_unbind_filter(tp, &f->res); tcf_exts_destroy(tp, &f->exts); kfree(f); @@ -123,7 +132,7 @@ static void fw_delete_filter(struct tcf_proto *tp, struct fw_filter *f) static void fw_destroy(struct tcf_proto *tp) { - struct fw_head *head = tp->root; + struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f; int h; @@ -131,29 +140,33 @@ static void fw_destroy(struct tcf_proto *tp) return; for (h = 0; h < HTSIZE; h++) { - while ((f = head->ht[h]) != NULL) { - head->ht[h] = f->next; - fw_delete_filter(tp, f); + while ((f = rtnl_dereference(head->ht[h])) != NULL) { + RCU_INIT_POINTER(head->ht[h], + rtnl_dereference(f->next)); + call_rcu(&f->rcu, fw_delete_filter); } } - kfree(head); + RCU_INIT_POINTER(tp->root, NULL); + kfree_rcu(head, rcu); } static int fw_delete(struct tcf_proto *tp, unsigned long arg) { - struct fw_head *head = tp->root; + struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f = (struct fw_filter *)arg; - struct fw_filter **fp; + struct fw_filter __rcu **fp; + struct fw_filter *pfp; if (head == NULL || f == NULL) goto out; - for (fp = &head->ht[fw_hash(f->id)]; *fp; fp = &(*fp)->next) { - if (*fp == f) { - tcf_tree_lock(tp); - *fp = f->next; - tcf_tree_unlock(tp); - fw_delete_filter(tp, f); + fp = &head->ht[fw_hash(f->id)]; + + for (pfp = rtnl_dereference(*fp); pfp; + fp = &pfp->next, pfp = rtnl_dereference(*fp)) { + if (pfp == f) { + RCU_INIT_POINTER(*fp, rtnl_dereference(f->next)); + call_rcu(&f->rcu, fw_delete_filter); return 0; } } @@ -171,7 +184,7 @@ static int fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, struct nlattr **tb, struct nlattr **tca, unsigned long base, bool ovr) { - struct fw_head *head = tp->root; + struct fw_head *head = rtnl_dereference(tp->root); struct tcf_exts e; u32 mask; int err; @@ -220,7 +233,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, struct nlattr **tca, unsigned long *arg, bool ovr) { - struct fw_head *head = tp->root; + struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f = (struct fw_filter *) *arg; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_FW_MAX + 1]; @@ -233,10 +246,42 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, if (err < 0) return err; - if (f != NULL) { + if (f) { + struct fw_filter *pfp, *fnew; + struct fw_filter __rcu **fp; + if (f->id != handle && handle) return -EINVAL; - return fw_change_attrs(net, tp, f, tb, tca, base, ovr); + + fnew = kzalloc(sizeof(struct fw_filter), GFP_KERNEL); + if (!fnew) + return -ENOBUFS; + + fnew->id = f->id; + fnew->res = f->res; +#ifdef CONFIG_NET_CLS_IND + fnew->ifindex = f->ifindex; +#endif /* CONFIG_NET_CLS_IND */ + fnew->tp = f->tp; + + err = fw_change_attrs(net, tp, fnew, tb, tca, base, ovr); + if (err < 0) { + kfree(fnew); + return err; + } + + fp = &head->ht[fw_hash(fnew->id)]; + for (pfp = rtnl_dereference(*fp); pfp; + fp = &pfp->next, pfp = rtnl_dereference(*fp)) + if (pfp == f) + break; + + RCU_INIT_POINTER(fnew->next, rtnl_dereference(pfp->next)); + rcu_assign_pointer(*fp, fnew); + call_rcu(&f->rcu, fw_delete_filter); + + *arg = (unsigned long)fnew; + return err; } if (!handle) @@ -252,9 +297,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, return -ENOBUFS; head->mask = mask; - tcf_tree_lock(tp); - tp->root = head; - tcf_tree_unlock(tp); + rcu_assign_pointer(tp->root, head); } f = kzalloc(sizeof(struct fw_filter), GFP_KERNEL); @@ -263,15 +306,14 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, tcf_exts_init(&f->exts, TCA_FW_ACT, TCA_FW_POLICE); f->id = handle; + f->tp = tp; err = fw_change_attrs(net, tp, f, tb, tca, base, ovr); if (err < 0) goto errout; - f->next = head->ht[fw_hash(handle)]; - tcf_tree_lock(tp); - head->ht[fw_hash(handle)] = f; - tcf_tree_unlock(tp); + RCU_INIT_POINTER(f->next, head->ht[fw_hash(handle)]); + rcu_assign_pointer(head->ht[fw_hash(handle)], f); *arg = (unsigned long)f; return 0; @@ -283,7 +325,7 @@ errout: static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct fw_head *head = tp->root; + struct fw_head *head = rtnl_dereference(tp->root); int h; if (head == NULL) @@ -295,7 +337,8 @@ static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) for (h = 0; h < HTSIZE; h++) { struct fw_filter *f; - for (f = head->ht[h]; f; f = f->next) { + for (f = rtnl_dereference(head->ht[h]); f; + f = rtnl_dereference(f->next)) { if (arg->count < arg->skip) { arg->count++; continue; @@ -312,7 +355,7 @@ static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) static int fw_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct fw_head *head = tp->root; + struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f = (struct fw_filter *)fh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; From cc91210cd2f6832db1a174269627d97b7d4f2c80 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 12 Sep 2014 20:07:50 -0700 Subject: [PATCH 07/12] net: sched: RCU cls_route RCUify the route classifier. For now however spinlock's are used to protect fastmap cache. The issue here is the fastmap may be read by one CPU while the cache is being updated by another. An array of pointers could be one possible solution. Signed-off-by: John Fastabend Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/cls_route.c | 226 ++++++++++++++++++++++++------------------ 1 file changed, 132 insertions(+), 94 deletions(-) diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index dd9fc2523c76..ba96deacf27c 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -29,25 +29,26 @@ * are mutually exclusive. * 3. "to TAG from ANY" has higher priority, than "to ANY from XXX" */ - struct route4_fastmap { - struct route4_filter *filter; - u32 id; - int iif; + struct route4_filter *filter; + u32 id; + int iif; }; struct route4_head { - struct route4_fastmap fastmap[16]; - struct route4_bucket *table[256 + 1]; + struct route4_fastmap fastmap[16]; + struct route4_bucket __rcu *table[256 + 1]; + struct rcu_head rcu; }; struct route4_bucket { /* 16 FROM buckets + 16 IIF buckets + 1 wildcard bucket */ - struct route4_filter *ht[16 + 16 + 1]; + struct route4_filter __rcu *ht[16 + 16 + 1]; + struct rcu_head rcu; }; struct route4_filter { - struct route4_filter *next; + struct route4_filter __rcu *next; u32 id; int iif; @@ -55,6 +56,8 @@ struct route4_filter { struct tcf_exts exts; u32 handle; struct route4_bucket *bkt; + struct tcf_proto *tp; + struct rcu_head rcu; }; #define ROUTE4_FAILURE ((struct route4_filter *)(-1L)) @@ -64,14 +67,13 @@ static inline int route4_fastmap_hash(u32 id, int iif) return id & 0xF; } +static DEFINE_SPINLOCK(fastmap_lock); static void -route4_reset_fastmap(struct Qdisc *q, struct route4_head *head, u32 id) +route4_reset_fastmap(struct route4_head *head) { - spinlock_t *root_lock = qdisc_root_sleeping_lock(q); - - spin_lock_bh(root_lock); + spin_lock_bh(&fastmap_lock); memset(head->fastmap, 0, sizeof(head->fastmap)); - spin_unlock_bh(root_lock); + spin_unlock_bh(&fastmap_lock); } static void @@ -80,9 +82,12 @@ route4_set_fastmap(struct route4_head *head, u32 id, int iif, { int h = route4_fastmap_hash(id, iif); + /* fastmap updates must look atomic to aling id, iff, filter */ + spin_lock_bh(&fastmap_lock); head->fastmap[h].id = id; head->fastmap[h].iif = iif; head->fastmap[h].filter = f; + spin_unlock_bh(&fastmap_lock); } static inline int route4_hash_to(u32 id) @@ -123,7 +128,7 @@ static inline int route4_hash_wild(void) static int route4_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct route4_head *head = tp->root; + struct route4_head *head = rcu_dereference_bh(tp->root); struct dst_entry *dst; struct route4_bucket *b; struct route4_filter *f; @@ -141,32 +146,43 @@ static int route4_classify(struct sk_buff *skb, const struct tcf_proto *tp, iif = inet_iif(skb); h = route4_fastmap_hash(id, iif); + + spin_lock(&fastmap_lock); if (id == head->fastmap[h].id && iif == head->fastmap[h].iif && (f = head->fastmap[h].filter) != NULL) { - if (f == ROUTE4_FAILURE) + if (f == ROUTE4_FAILURE) { + spin_unlock(&fastmap_lock); goto failure; + } *res = f->res; + spin_unlock(&fastmap_lock); return 0; } + spin_unlock(&fastmap_lock); h = route4_hash_to(id); restart: - b = head->table[h]; + b = rcu_dereference_bh(head->table[h]); if (b) { - for (f = b->ht[route4_hash_from(id)]; f; f = f->next) + for (f = rcu_dereference_bh(b->ht[route4_hash_from(id)]); + f; + f = rcu_dereference_bh(f->next)) if (f->id == id) ROUTE4_APPLY_RESULT(); - for (f = b->ht[route4_hash_iif(iif)]; f; f = f->next) + for (f = rcu_dereference_bh(b->ht[route4_hash_iif(iif)]); + f; + f = rcu_dereference_bh(f->next)) if (f->iif == iif) ROUTE4_APPLY_RESULT(); - for (f = b->ht[route4_hash_wild()]; f; f = f->next) + for (f = rcu_dereference_bh(b->ht[route4_hash_wild()]); + f; + f = rcu_dereference_bh(f->next)) ROUTE4_APPLY_RESULT(); - } if (h < 256) { h = 256; @@ -213,7 +229,7 @@ static inline u32 from_hash(u32 id) static unsigned long route4_get(struct tcf_proto *tp, u32 handle) { - struct route4_head *head = tp->root; + struct route4_head *head = rtnl_dereference(tp->root); struct route4_bucket *b; struct route4_filter *f; unsigned int h1, h2; @@ -229,9 +245,11 @@ static unsigned long route4_get(struct tcf_proto *tp, u32 handle) if (h2 > 32) return 0; - b = head->table[h1]; + b = rtnl_dereference(head->table[h1]); if (b) { - for (f = b->ht[h2]; f; f = f->next) + for (f = rtnl_dereference(b->ht[h2]); + f; + f = rtnl_dereference(f->next)) if (f->handle == handle) return (unsigned long)f; } @@ -248,8 +266,11 @@ static int route4_init(struct tcf_proto *tp) } static void -route4_delete_filter(struct tcf_proto *tp, struct route4_filter *f) +route4_delete_filter(struct rcu_head *head) { + struct route4_filter *f = container_of(head, struct route4_filter, rcu); + struct tcf_proto *tp = f->tp; + tcf_unbind_filter(tp, &f->res); tcf_exts_destroy(tp, &f->exts); kfree(f); @@ -257,7 +278,7 @@ route4_delete_filter(struct tcf_proto *tp, struct route4_filter *f) static void route4_destroy(struct tcf_proto *tp) { - struct route4_head *head = tp->root; + struct route4_head *head = rtnl_dereference(tp->root); int h1, h2; if (head == NULL) @@ -266,28 +287,35 @@ static void route4_destroy(struct tcf_proto *tp) for (h1 = 0; h1 <= 256; h1++) { struct route4_bucket *b; - b = head->table[h1]; + b = rtnl_dereference(head->table[h1]); if (b) { for (h2 = 0; h2 <= 32; h2++) { struct route4_filter *f; - while ((f = b->ht[h2]) != NULL) { - b->ht[h2] = f->next; - route4_delete_filter(tp, f); + while ((f = rtnl_dereference(b->ht[h2])) != NULL) { + struct route4_filter *next; + + next = rtnl_dereference(f->next); + RCU_INIT_POINTER(b->ht[h2], next); + call_rcu(&f->rcu, route4_delete_filter); } } - kfree(b); + RCU_INIT_POINTER(head->table[h1], NULL); + kfree_rcu(b, rcu); } } - kfree(head); + RCU_INIT_POINTER(tp->root, NULL); + kfree_rcu(head, rcu); } static int route4_delete(struct tcf_proto *tp, unsigned long arg) { - struct route4_head *head = tp->root; - struct route4_filter **fp, *f = (struct route4_filter *)arg; - unsigned int h = 0; + struct route4_head *head = rtnl_dereference(tp->root); + struct route4_filter *f = (struct route4_filter *)arg; + struct route4_filter __rcu **fp; + struct route4_filter *nf; struct route4_bucket *b; + unsigned int h = 0; int i; if (!head || !f) @@ -296,27 +324,35 @@ static int route4_delete(struct tcf_proto *tp, unsigned long arg) h = f->handle; b = f->bkt; - for (fp = &b->ht[from_hash(h >> 16)]; *fp; fp = &(*fp)->next) { - if (*fp == f) { - tcf_tree_lock(tp); - *fp = f->next; - tcf_tree_unlock(tp); + fp = &b->ht[from_hash(h >> 16)]; + for (nf = rtnl_dereference(*fp); nf; + fp = &nf->next, nf = rtnl_dereference(*fp)) { + if (nf == f) { + /* unlink it */ + RCU_INIT_POINTER(*fp, rtnl_dereference(f->next)); - route4_reset_fastmap(tp->q, head, f->id); - route4_delete_filter(tp, f); + /* Remove any fastmap lookups that might ref filter + * notice we unlink'd the filter so we can't get it + * back in the fastmap. + */ + route4_reset_fastmap(head); - /* Strip tree */ + /* Delete it */ + call_rcu(&f->rcu, route4_delete_filter); - for (i = 0; i <= 32; i++) - if (b->ht[i]) + /* Strip RTNL protected tree */ + for (i = 0; i <= 32; i++) { + struct route4_filter *rt; + + rt = rtnl_dereference(b->ht[i]); + if (rt) return 0; + } /* OK, session has no flows */ - tcf_tree_lock(tp); - head->table[to_hash(h)] = NULL; - tcf_tree_unlock(tp); + RCU_INIT_POINTER(head->table[to_hash(h)], NULL); + kfree_rcu(b, rcu); - kfree(b); return 0; } } @@ -380,26 +416,25 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, } h1 = to_hash(nhandle); - b = head->table[h1]; + b = rtnl_dereference(head->table[h1]); if (!b) { err = -ENOBUFS; b = kzalloc(sizeof(struct route4_bucket), GFP_KERNEL); if (b == NULL) goto errout; - tcf_tree_lock(tp); - head->table[h1] = b; - tcf_tree_unlock(tp); + rcu_assign_pointer(head->table[h1], b); } else { unsigned int h2 = from_hash(nhandle >> 16); err = -EEXIST; - for (fp = b->ht[h2]; fp; fp = fp->next) + for (fp = rtnl_dereference(b->ht[h2]); + fp; + fp = rtnl_dereference(fp->next)) if (fp->handle == f->handle) goto errout; } - tcf_tree_lock(tp); if (tb[TCA_ROUTE4_TO]) f->id = to; @@ -410,7 +445,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, f->handle = nhandle; f->bkt = b; - tcf_tree_unlock(tp); + f->tp = tp; if (tb[TCA_ROUTE4_CLASSID]) { f->res.classid = nla_get_u32(tb[TCA_ROUTE4_CLASSID]); @@ -431,14 +466,15 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, struct nlattr **tca, unsigned long *arg, bool ovr) { - struct route4_head *head = tp->root; - struct route4_filter *f, *f1, **fp; + struct route4_head *head = rtnl_dereference(tp->root); + struct route4_filter __rcu **fp; + struct route4_filter *fold, *f1, *pfp, *f = NULL; struct route4_bucket *b; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_ROUTE4_MAX + 1]; unsigned int h, th; - u32 old_handle = 0; int err; + bool new = true; if (opt == NULL) return handle ? -EINVAL : 0; @@ -447,70 +483,70 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (err < 0) return err; - f = (struct route4_filter *)*arg; - if (f) { - if (f->handle != handle && handle) + fold = (struct route4_filter *)*arg; + if (fold && handle && fold->handle != handle) return -EINVAL; - if (f->bkt) - old_handle = f->handle; - - err = route4_set_parms(net, tp, base, f, handle, head, tb, - tca[TCA_RATE], 0, ovr); - if (err < 0) - return err; - - goto reinsert; - } - err = -ENOBUFS; if (head == NULL) { head = kzalloc(sizeof(struct route4_head), GFP_KERNEL); if (head == NULL) goto errout; - - tcf_tree_lock(tp); - tp->root = head; - tcf_tree_unlock(tp); + rcu_assign_pointer(tp->root, head); } f = kzalloc(sizeof(struct route4_filter), GFP_KERNEL); - if (f == NULL) + if (!f) goto errout; tcf_exts_init(&f->exts, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE); + if (fold) { + f->id = fold->id; + f->iif = fold->iif; + f->res = fold->res; + f->handle = fold->handle; + + f->tp = fold->tp; + f->bkt = fold->bkt; + new = false; + } + err = route4_set_parms(net, tp, base, f, handle, head, tb, - tca[TCA_RATE], 1, ovr); + tca[TCA_RATE], new, ovr); if (err < 0) goto errout; -reinsert: h = from_hash(f->handle >> 16); - for (fp = &f->bkt->ht[h]; (f1 = *fp) != NULL; fp = &f1->next) + fp = &f->bkt->ht[h]; + for (pfp = rtnl_dereference(*fp); + (f1 = rtnl_dereference(*fp)) != NULL; + fp = &f1->next) if (f->handle < f1->handle) break; - f->next = f1; - tcf_tree_lock(tp); - *fp = f; + rcu_assign_pointer(f->next, f1); + rcu_assign_pointer(*fp, f); - if (old_handle && f->handle != old_handle) { - th = to_hash(old_handle); - h = from_hash(old_handle >> 16); - b = head->table[th]; + if (fold && fold->handle && f->handle != fold->handle) { + th = to_hash(fold->handle); + h = from_hash(fold->handle >> 16); + b = rtnl_dereference(head->table[th]); if (b) { - for (fp = &b->ht[h]; *fp; fp = &(*fp)->next) { - if (*fp == f) { + fp = &b->ht[h]; + for (pfp = rtnl_dereference(*fp); pfp; + fp = &pfp->next, pfp = rtnl_dereference(*fp)) { + if (pfp == f) { *fp = f->next; break; } } } } - tcf_tree_unlock(tp); - route4_reset_fastmap(tp->q, head, f->id); + route4_reset_fastmap(head); *arg = (unsigned long)f; + if (fold) + call_rcu(&fold->rcu, route4_delete_filter); return 0; errout: @@ -520,7 +556,7 @@ errout: static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct route4_head *head = tp->root; + struct route4_head *head = rtnl_dereference(tp->root); unsigned int h, h1; if (head == NULL) @@ -530,13 +566,15 @@ static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) return; for (h = 0; h <= 256; h++) { - struct route4_bucket *b = head->table[h]; + struct route4_bucket *b = rtnl_dereference(head->table[h]); if (b) { for (h1 = 0; h1 <= 32; h1++) { struct route4_filter *f; - for (f = b->ht[h1]; f; f = f->next) { + for (f = rtnl_dereference(b->ht[h1]); + f; + f = rtnl_dereference(f->next)) { if (arg->count < arg->skip) { arg->count++; continue; From 8332904aa971ed4547514f57c8b3780ad4f0f949 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 12 Sep 2014 20:08:20 -0700 Subject: [PATCH 08/12] net: sched: RCU cls_tcindex Make cls_tcindex RCU safe. This patch addds a new RCU routine rcu_dereference_bh_rtnl() to check caller either holds the rcu read lock or RTNL. This is needed to handle the case where tcindex_lookup() is being called in both cases. Signed-off-by: John Fastabend Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 10 ++ net/sched/cls_tcindex.c | 250 +++++++++++++++++++++++--------------- 2 files changed, 165 insertions(+), 95 deletions(-) diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 167bae7bdfa4..6cacbce1a06c 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -46,6 +46,16 @@ static inline int lockdep_rtnl_is_held(void) #define rcu_dereference_rtnl(p) \ rcu_dereference_check(p, lockdep_rtnl_is_held()) +/** + * rcu_dereference_bh_rtnl - rcu_dereference_bh with debug checking + * @p: The pointer to read, prior to dereference + * + * Do an rcu_dereference_bh(p), but check caller either holds rcu_read_lock_bh() + * or RTNL. Note : Please prefer rtnl_dereference() or rcu_dereference_bh() + */ +#define rcu_dereference_bh_rtnl(p) \ + rcu_dereference_bh_check(p, lockdep_rtnl_is_held()) + /** * rtnl_dereference - fetch RCU pointer when updates are prevented by RTNL * @p: The pointer to read, prior to dereferencing diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 3e9f76413b3b..a9f4279fbd69 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -32,19 +32,21 @@ struct tcindex_filter_result { struct tcindex_filter { u16 key; struct tcindex_filter_result result; - struct tcindex_filter *next; + struct tcindex_filter __rcu *next; + struct rcu_head rcu; }; struct tcindex_data { struct tcindex_filter_result *perfect; /* perfect hash; NULL if none */ - struct tcindex_filter **h; /* imperfect hash; only used if !perfect; - NULL if unused */ + struct tcindex_filter __rcu **h; /* imperfect hash; */ + struct tcf_proto *tp; u16 mask; /* AND key with mask */ - int shift; /* shift ANDed key to the right */ - int hash; /* hash table size; 0 if undefined */ - int alloc_hash; /* allocated size */ - int fall_through; /* 0: only classify if explicit match */ + u32 shift; /* shift ANDed key to the right */ + u32 hash; /* hash table size; 0 if undefined */ + u32 alloc_hash; /* allocated size */ + u32 fall_through; /* 0: only classify if explicit match */ + struct rcu_head rcu; }; static inline int @@ -56,13 +58,18 @@ tcindex_filter_is_set(struct tcindex_filter_result *r) static struct tcindex_filter_result * tcindex_lookup(struct tcindex_data *p, u16 key) { - struct tcindex_filter *f; + if (p->perfect) { + struct tcindex_filter_result *f = p->perfect + key; - if (p->perfect) - return tcindex_filter_is_set(p->perfect + key) ? - p->perfect + key : NULL; - else if (p->h) { - for (f = p->h[key % p->hash]; f; f = f->next) + return tcindex_filter_is_set(f) ? f : NULL; + } else if (p->h) { + struct tcindex_filter __rcu **fp; + struct tcindex_filter *f; + + fp = &p->h[key % p->hash]; + for (f = rcu_dereference_bh_rtnl(*fp); + f; + fp = &f->next, f = rcu_dereference_bh_rtnl(*fp)) if (f->key == key) return &f->result; } @@ -74,7 +81,7 @@ tcindex_lookup(struct tcindex_data *p, u16 key) static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct tcindex_data *p = tp->root; + struct tcindex_data *p = rcu_dereference(tp->root); struct tcindex_filter_result *f; int key = (skb->tc_index & p->mask) >> p->shift; @@ -99,7 +106,7 @@ static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, static unsigned long tcindex_get(struct tcf_proto *tp, u32 handle) { - struct tcindex_data *p = tp->root; + struct tcindex_data *p = rtnl_dereference(tp->root); struct tcindex_filter_result *r; pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle); @@ -129,49 +136,59 @@ static int tcindex_init(struct tcf_proto *tp) p->hash = DEFAULT_HASH_SIZE; p->fall_through = 1; - tp->root = p; + rcu_assign_pointer(tp->root, p); return 0; } - static int -__tcindex_delete(struct tcf_proto *tp, unsigned long arg, int lock) +tcindex_delete(struct tcf_proto *tp, unsigned long arg) { - struct tcindex_data *p = tp->root; + struct tcindex_data *p = rtnl_dereference(tp->root); struct tcindex_filter_result *r = (struct tcindex_filter_result *) arg; + struct tcindex_filter __rcu **walk; struct tcindex_filter *f = NULL; - pr_debug("tcindex_delete(tp %p,arg 0x%lx),p %p,f %p\n", tp, arg, p, f); + pr_debug("tcindex_delete(tp %p,arg 0x%lx),p %p\n", tp, arg, p); if (p->perfect) { if (!r->res.class) return -ENOENT; } else { int i; - struct tcindex_filter **walk = NULL; - for (i = 0; i < p->hash; i++) - for (walk = p->h+i; *walk; walk = &(*walk)->next) - if (&(*walk)->result == r) + for (i = 0; i < p->hash; i++) { + walk = p->h + i; + for (f = rtnl_dereference(*walk); f; + walk = &f->next, f = rtnl_dereference(*walk)) { + if (&f->result == r) goto found; + } + } return -ENOENT; found: - f = *walk; - if (lock) - tcf_tree_lock(tp); - *walk = f->next; - if (lock) - tcf_tree_unlock(tp); + rcu_assign_pointer(*walk, rtnl_dereference(f->next)); } tcf_unbind_filter(tp, &r->res); tcf_exts_destroy(tp, &r->exts); - kfree(f); + if (f) + kfree_rcu(f, rcu); return 0; } -static int tcindex_delete(struct tcf_proto *tp, unsigned long arg) +static int tcindex_destroy_element(struct tcf_proto *tp, + unsigned long arg, + struct tcf_walker *walker) { - return __tcindex_delete(tp, arg, 1); + return tcindex_delete(tp, arg); +} + +static void __tcindex_destroy(struct rcu_head *head) +{ + struct tcindex_data *p = container_of(head, struct tcindex_data, rcu); + + kfree(p->perfect); + kfree(p->h); + kfree(p); } static inline int @@ -194,6 +211,14 @@ static void tcindex_filter_result_init(struct tcindex_filter_result *r) tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); } +static void __tcindex_partial_destroy(struct rcu_head *head) +{ + struct tcindex_data *p = container_of(head, struct tcindex_data, rcu); + + kfree(p->perfect); + kfree(p); +} + static int tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, u32 handle, struct tcindex_data *p, @@ -203,7 +228,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, int err, balloc = 0; struct tcindex_filter_result new_filter_result, *old_r = r; struct tcindex_filter_result cr; - struct tcindex_data cp; + struct tcindex_data *cp, *oldp; struct tcindex_filter *f = NULL; /* make gcc behave */ struct tcf_exts e; @@ -212,84 +237,118 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, if (err < 0) return err; - memcpy(&cp, p, sizeof(cp)); - tcindex_filter_result_init(&new_filter_result); + /* tcindex_data attributes must look atomic to classifier/lookup so + * allocate new tcindex data and RCU assign it onto root. Keeping + * perfect hash and hash pointers from old data. + */ + cp = kzalloc(sizeof(cp), GFP_KERNEL); + if (!cp) + return -ENOMEM; + + cp->mask = p->mask; + cp->shift = p->shift; + cp->hash = p->hash; + cp->alloc_hash = p->alloc_hash; + cp->fall_through = p->fall_through; + cp->tp = tp; + + if (p->perfect) { + cp->perfect = kmemdup(p->perfect, + sizeof(*r) * cp->hash, GFP_KERNEL); + if (!cp->perfect) + goto errout; + } + cp->h = p->h; + + memset(&new_filter_result, 0, sizeof(new_filter_result)); + tcf_exts_init(&new_filter_result.exts, + TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); tcindex_filter_result_init(&cr); if (old_r) cr.res = r->res; if (tb[TCA_TCINDEX_HASH]) - cp.hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); + cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); if (tb[TCA_TCINDEX_MASK]) - cp.mask = nla_get_u16(tb[TCA_TCINDEX_MASK]); + cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]); if (tb[TCA_TCINDEX_SHIFT]) - cp.shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]); + cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]); err = -EBUSY; + /* Hash already allocated, make sure that we still meet the * requirements for the allocated hash. */ - if (cp.perfect) { - if (!valid_perfect_hash(&cp) || - cp.hash > cp.alloc_hash) + if (cp->perfect) { + if (!valid_perfect_hash(cp) || + cp->hash > cp->alloc_hash) goto errout; - } else if (cp.h && cp.hash != cp.alloc_hash) + } else if (cp->h && cp->hash != cp->alloc_hash) { goto errout; + } err = -EINVAL; if (tb[TCA_TCINDEX_FALL_THROUGH]) - cp.fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]); + cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]); - if (!cp.hash) { + if (!cp->hash) { /* Hash not specified, use perfect hash if the upper limit * of the hashing index is below the threshold. */ - if ((cp.mask >> cp.shift) < PERFECT_HASH_THRESHOLD) - cp.hash = (cp.mask >> cp.shift) + 1; + if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD) + cp->hash = (cp->mask >> cp->shift) + 1; else - cp.hash = DEFAULT_HASH_SIZE; + cp->hash = DEFAULT_HASH_SIZE; } - if (!cp.perfect && !cp.h) - cp.alloc_hash = cp.hash; + if (!cp->perfect && cp->h) + cp->alloc_hash = cp->hash; /* Note: this could be as restrictive as if (handle & ~(mask >> shift)) * but then, we'd fail handles that may become valid after some future * mask change. While this is extremely unlikely to ever matter, * the check below is safer (and also more backwards-compatible). */ - if (cp.perfect || valid_perfect_hash(&cp)) - if (handle >= cp.alloc_hash) + if (cp->perfect || valid_perfect_hash(cp)) + if (handle >= cp->alloc_hash) goto errout; err = -ENOMEM; - if (!cp.perfect && !cp.h) { - if (valid_perfect_hash(&cp)) { + if (!cp->perfect && !cp->h) { + if (valid_perfect_hash(cp)) { int i; - cp.perfect = kcalloc(cp.hash, sizeof(*r), GFP_KERNEL); - if (!cp.perfect) + cp->perfect = kcalloc(cp->hash, sizeof(*r), GFP_KERNEL); + if (!cp->perfect) goto errout; - for (i = 0; i < cp.hash; i++) - tcf_exts_init(&cp.perfect[i].exts, TCA_TCINDEX_ACT, + for (i = 0; i < cp->hash; i++) + tcf_exts_init(&cp->perfect[i].exts, + TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); balloc = 1; } else { - cp.h = kcalloc(cp.hash, sizeof(f), GFP_KERNEL); - if (!cp.h) + struct tcindex_filter __rcu **hash; + + hash = kcalloc(cp->hash, + sizeof(struct tcindex_filter *), + GFP_KERNEL); + + if (!hash) goto errout; + + cp->h = hash; balloc = 2; } } - if (cp.perfect) - r = cp.perfect + handle; + if (cp->perfect) + r = cp->perfect + handle; else - r = tcindex_lookup(&cp, handle) ? : &new_filter_result; + r = tcindex_lookup(cp, handle) ? : &new_filter_result; if (r == &new_filter_result) { f = kzalloc(sizeof(*f), GFP_KERNEL); @@ -307,33 +366,41 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, else tcf_exts_change(tp, &cr.exts, &e); - tcf_tree_lock(tp); if (old_r && old_r != r) tcindex_filter_result_init(old_r); - memcpy(p, &cp, sizeof(cp)); + oldp = p; r->res = cr.res; + rcu_assign_pointer(tp->root, cp); if (r == &new_filter_result) { - struct tcindex_filter **fp; + struct tcindex_filter *nfp; + struct tcindex_filter __rcu **fp; f->key = handle; f->result = new_filter_result; f->next = NULL; - for (fp = p->h+(handle % p->hash); *fp; fp = &(*fp)->next) - /* nothing */; - *fp = f; - } - tcf_tree_unlock(tp); + fp = p->h + (handle % p->hash); + for (nfp = rtnl_dereference(*fp); + nfp; + fp = &nfp->next, nfp = rtnl_dereference(*fp)) + ; /* nothing */ + + rcu_assign_pointer(*fp, f); + } + + if (oldp) + call_rcu(&oldp->rcu, __tcindex_partial_destroy); return 0; errout_alloc: if (balloc == 1) - kfree(cp.perfect); + kfree(cp->perfect); else if (balloc == 2) - kfree(cp.h); + kfree(cp->h); errout: + kfree(cp); tcf_exts_destroy(tp, &e); return err; } @@ -345,7 +412,7 @@ tcindex_change(struct net *net, struct sk_buff *in_skb, { struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_TCINDEX_MAX + 1]; - struct tcindex_data *p = tp->root; + struct tcindex_data *p = rtnl_dereference(tp->root); struct tcindex_filter_result *r = (struct tcindex_filter_result *) *arg; int err; @@ -364,10 +431,9 @@ tcindex_change(struct net *net, struct sk_buff *in_skb, tca[TCA_RATE], ovr); } - static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) { - struct tcindex_data *p = tp->root; + struct tcindex_data *p = rtnl_dereference(tp->root); struct tcindex_filter *f, *next; int i; @@ -390,8 +456,8 @@ static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) if (!p->h) return; for (i = 0; i < p->hash; i++) { - for (f = p->h[i]; f; f = next) { - next = f->next; + for (f = rtnl_dereference(p->h[i]); f; f = next) { + next = rtnl_dereference(f->next); if (walker->count >= walker->skip) { if (walker->fn(tp, (unsigned long) &f->result, walker) < 0) { @@ -404,17 +470,9 @@ static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) } } - -static int tcindex_destroy_element(struct tcf_proto *tp, - unsigned long arg, struct tcf_walker *walker) -{ - return __tcindex_delete(tp, arg, 0); -} - - static void tcindex_destroy(struct tcf_proto *tp) { - struct tcindex_data *p = tp->root; + struct tcindex_data *p = rtnl_dereference(tp->root); struct tcf_walker walker; pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); @@ -422,17 +480,16 @@ static void tcindex_destroy(struct tcf_proto *tp) walker.skip = 0; walker.fn = tcindex_destroy_element; tcindex_walk(tp, &walker); - kfree(p->perfect); - kfree(p->h); - kfree(p); - tp->root = NULL; + + RCU_INIT_POINTER(tp->root, NULL); + call_rcu(&p->rcu, __tcindex_destroy); } static int tcindex_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct tcindex_data *p = tp->root; + struct tcindex_data *p = rtnl_dereference(tp->root); struct tcindex_filter_result *r = (struct tcindex_filter_result *) fh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; @@ -455,15 +512,18 @@ static int tcindex_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, nla_nest_end(skb, nest); } else { if (p->perfect) { - t->tcm_handle = r-p->perfect; + t->tcm_handle = r - p->perfect; } else { struct tcindex_filter *f; + struct tcindex_filter __rcu **fp; int i; t->tcm_handle = 0; for (i = 0; !t->tcm_handle && i < p->hash; i++) { - for (f = p->h[i]; !t->tcm_handle && f; - f = f->next) { + fp = &p->h[i]; + for (f = rtnl_dereference(*fp); + !t->tcm_handle && f; + fp = &f->next, f = rtnl_dereference(*fp)) { if (&f->result == r) t->tcm_handle = f->key; } From f4f640502dfbe9b658f9008ee614932bb463d541 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 12 Sep 2014 20:08:47 -0700 Subject: [PATCH 09/12] net: sched: make cls_u32 per cpu This uses per cpu counters in cls_u32 in preparation to convert over to rcu. Signed-off-by: John Fastabend Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/cls_u32.c | 75 +++++++++++++++++++++++++++++++++++---------- 1 file changed, 59 insertions(+), 16 deletions(-) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 70c0be8d0121..f3227d73a7ae 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -55,10 +55,12 @@ struct tc_u_knode { struct tcf_result res; struct tc_u_hnode *ht_down; #ifdef CONFIG_CLS_U32_PERF - struct tc_u32_pcnt *pf; + struct tc_u32_pcnt __percpu *pf; #endif #ifdef CONFIG_CLS_U32_MARK - struct tc_u32_mark mark; + u32 val; + u32 mask; + u32 __percpu *pcpu_success; #endif struct tc_u32_sel sel; }; @@ -115,16 +117,16 @@ next_knode: struct tc_u32_key *key = n->sel.keys; #ifdef CONFIG_CLS_U32_PERF - n->pf->rcnt += 1; + __this_cpu_inc(n->pf->rcnt); j = 0; #endif #ifdef CONFIG_CLS_U32_MARK - if ((skb->mark & n->mark.mask) != n->mark.val) { + if ((skb->mark & n->mask) != n->val) { n = n->next; goto next_knode; } else { - n->mark.success++; + __this_cpu_inc(*n->pcpu_success); } #endif @@ -143,7 +145,7 @@ next_knode: goto next_knode; } #ifdef CONFIG_CLS_U32_PERF - n->pf->kcnts[j] += 1; + __this_cpu_inc(n->pf->kcnts[j]); j++; #endif } @@ -159,7 +161,7 @@ check_terminal: } #endif #ifdef CONFIG_CLS_U32_PERF - n->pf->rhit += 1; + __this_cpu_inc(n->pf->rhit); #endif r = tcf_exts_exec(skb, &n->exts, res); if (r < 0) { @@ -342,7 +344,7 @@ static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n) if (n->ht_down) n->ht_down->refcnt--; #ifdef CONFIG_CLS_U32_PERF - kfree(n->pf); + free_percpu(n->pf); #endif kfree(n); return 0; @@ -564,6 +566,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, struct nlattr *tb[TCA_U32_MAX + 1]; u32 htid; int err; +#ifdef CONFIG_CLS_U32_PERF + size_t size; +#endif if (opt == NULL) return handle ? -EINVAL : 0; @@ -642,8 +647,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -ENOBUFS; #ifdef CONFIG_CLS_U32_PERF - n->pf = kzalloc(sizeof(struct tc_u32_pcnt) + s->nkeys*sizeof(u64), GFP_KERNEL); - if (n->pf == NULL) { + size = sizeof(struct tc_u32_pcnt) + s->nkeys * sizeof(u64); + n->pf = __alloc_percpu(size, __alignof__(struct tc_u32_pcnt)); + if (!n->pf) { kfree(n); return -ENOBUFS; } @@ -656,12 +662,14 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE); #ifdef CONFIG_CLS_U32_MARK + n->pcpu_success = alloc_percpu(u32); + if (tb[TCA_U32_MARK]) { struct tc_u32_mark *mark; mark = nla_data(tb[TCA_U32_MARK]); - memcpy(&n->mark, mark, sizeof(struct tc_u32_mark)); - n->mark.success = 0; + n->val = mark->val; + n->mask = mark->mask; } #endif @@ -745,6 +753,11 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, if (nla_put_u32(skb, TCA_U32_DIVISOR, divisor)) goto nla_put_failure; } else { +#ifdef CONFIG_CLS_U32_PERF + struct tc_u32_pcnt *gpf; +#endif + int cpu; + if (nla_put(skb, TCA_U32_SEL, sizeof(n->sel) + n->sel.nkeys*sizeof(struct tc_u32_key), &n->sel)) @@ -762,9 +775,20 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, goto nla_put_failure; #ifdef CONFIG_CLS_U32_MARK - if ((n->mark.val || n->mark.mask) && - nla_put(skb, TCA_U32_MARK, sizeof(n->mark), &n->mark)) - goto nla_put_failure; + if ((n->val || n->mask)) { + struct tc_u32_mark mark = {.val = n->val, + .mask = n->mask, + .success = 0}; + + for_each_possible_cpu(cpu) { + __u32 cnt = *per_cpu_ptr(n->pcpu_success, cpu); + + mark.success += cnt; + } + + if (nla_put(skb, TCA_U32_MARK, sizeof(mark), &mark)) + goto nla_put_failure; + } #endif if (tcf_exts_dump(skb, &n->exts) < 0) @@ -779,10 +803,29 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, } #endif #ifdef CONFIG_CLS_U32_PERF + gpf = kzalloc(sizeof(struct tc_u32_pcnt) + + n->sel.nkeys * sizeof(u64), + GFP_KERNEL); + if (!gpf) + goto nla_put_failure; + + for_each_possible_cpu(cpu) { + int i; + struct tc_u32_pcnt *pf = per_cpu_ptr(n->pf, cpu); + + gpf->rcnt += pf->rcnt; + gpf->rhit += pf->rhit; + for (i = 0; i < n->sel.nkeys; i++) + gpf->kcnts[i] += pf->kcnts[i]; + } + if (nla_put(skb, TCA_U32_PCNT, sizeof(struct tc_u32_pcnt) + n->sel.nkeys*sizeof(u64), - n->pf)) + gpf)) { + kfree(gpf); goto nla_put_failure; + } + kfree(gpf); #endif } From 8f787cd1cc1ea51cde3bba82bd0a63b343f88a32 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 12 Sep 2014 20:09:16 -0700 Subject: [PATCH 10/12] net: sched: make cls_u32 lockless Make cls_u32 classifier safe to run without holding lock. This patch converts statistics that are kept in read section u32_classify into per cpu counters. This patch was tested with a tight u32 filter add/delete loop while generating traffic with pktgen. By running pktgen on vlan devices created on top of a physical device we can hit the qdisc layer correctly. For ingress qdisc's a loopback cable was used. for i in {1..100}; do q=`echo $i%8|bc`; echo -n "u32 tos: iteration $i on queue $q"; tc filter add dev p3p2 parent $p prio $i u32 match ip tos 0x10 0xff \ action skbedit queue_mapping $q; sleep 1; tc filter del dev p3p2 prio $i; echo -n "u32 tos hash table: iteration $i on queue $q"; tc filter add dev p3p2 parent $p protocol ip prio $i handle 628: u32 divisor 1 tc filter add dev p3p2 parent $p protocol ip prio $i u32 \ match ip protocol 17 0xff link 628: offset at 0 mask 0xf00 shift 6 plus 0 tc filter add dev p3p2 parent $p protocol ip prio $i u32 \ ht 628:0 match ip tos 0x10 0xff action skbedit queue_mapping $q sleep 2; tc filter del dev p3p2 prio $i sleep 1; done Signed-off-by: John Fastabend Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/cls_u32.c | 183 ++++++++++++++++++++++++++------------------ 1 file changed, 110 insertions(+), 73 deletions(-) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index f3227d73a7ae..5ed5ac4361b1 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include @@ -44,16 +45,16 @@ #include struct tc_u_knode { - struct tc_u_knode *next; + struct tc_u_knode __rcu *next; u32 handle; - struct tc_u_hnode *ht_up; + struct tc_u_hnode __rcu *ht_up; struct tcf_exts exts; #ifdef CONFIG_NET_CLS_IND int ifindex; #endif u8 fshift; struct tcf_result res; - struct tc_u_hnode *ht_down; + struct tc_u_hnode __rcu *ht_down; #ifdef CONFIG_CLS_U32_PERF struct tc_u32_pcnt __percpu *pf; #endif @@ -62,24 +63,28 @@ struct tc_u_knode { u32 mask; u32 __percpu *pcpu_success; #endif + struct tcf_proto *tp; struct tc_u32_sel sel; + struct rcu_head rcu; }; struct tc_u_hnode { - struct tc_u_hnode *next; + struct tc_u_hnode __rcu *next; u32 handle; u32 prio; struct tc_u_common *tp_c; int refcnt; unsigned int divisor; - struct tc_u_knode *ht[1]; + struct tc_u_knode __rcu *ht[1]; + struct rcu_head rcu; }; struct tc_u_common { - struct tc_u_hnode *hlist; + struct tc_u_hnode __rcu *hlist; struct Qdisc *q; int refcnt; u32 hgenerator; + struct rcu_head rcu; }; static inline unsigned int u32_hash_fold(__be32 key, @@ -98,7 +103,7 @@ static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct unsigned int off; } stack[TC_U32_MAXDEPTH]; - struct tc_u_hnode *ht = tp->root; + struct tc_u_hnode *ht = rcu_dereference_bh(tp->root); unsigned int off = skb_network_offset(skb); struct tc_u_knode *n; int sdepth = 0; @@ -110,7 +115,7 @@ static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct int i, r; next_ht: - n = ht->ht[sel]; + n = rcu_dereference_bh(ht->ht[sel]); next_knode: if (n) { @@ -123,7 +128,7 @@ next_knode: #ifdef CONFIG_CLS_U32_MARK if ((skb->mark & n->mask) != n->val) { - n = n->next; + n = rcu_dereference_bh(n->next); goto next_knode; } else { __this_cpu_inc(*n->pcpu_success); @@ -141,7 +146,7 @@ next_knode: if (!data) goto out; if ((*data ^ key->val) & key->mask) { - n = n->next; + n = rcu_dereference_bh(n->next); goto next_knode; } #ifdef CONFIG_CLS_U32_PERF @@ -149,14 +154,16 @@ next_knode: j++; #endif } - if (n->ht_down == NULL) { + + ht = rcu_dereference_bh(n->ht_down); + if (!ht) { check_terminal: if (n->sel.flags & TC_U32_TERMINAL) { *res = n->res; #ifdef CONFIG_NET_CLS_IND if (!tcf_match_indev(skb, n->ifindex)) { - n = n->next; + n = rcu_dereference_bh(n->next); goto next_knode; } #endif @@ -165,13 +172,13 @@ check_terminal: #endif r = tcf_exts_exec(skb, &n->exts, res); if (r < 0) { - n = n->next; + n = rcu_dereference_bh(n->next); goto next_knode; } return r; } - n = n->next; + n = rcu_dereference_bh(n->next); goto next_knode; } @@ -182,7 +189,7 @@ check_terminal: stack[sdepth].off = off; sdepth++; - ht = n->ht_down; + ht = rcu_dereference_bh(n->ht_down); sel = 0; if (ht->divisor) { __be32 *data, hdata; @@ -224,7 +231,7 @@ check_terminal: /* POP */ if (sdepth--) { n = stack[sdepth].knode; - ht = n->ht_up; + ht = rcu_dereference_bh(n->ht_up); off = stack[sdepth].off; goto check_terminal; } @@ -241,7 +248,9 @@ u32_lookup_ht(struct tc_u_common *tp_c, u32 handle) { struct tc_u_hnode *ht; - for (ht = tp_c->hlist; ht; ht = ht->next) + for (ht = rtnl_dereference(tp_c->hlist); + ht; + ht = rtnl_dereference(ht->next)) if (ht->handle == handle) break; @@ -258,7 +267,9 @@ u32_lookup_key(struct tc_u_hnode *ht, u32 handle) if (sel > ht->divisor) goto out; - for (n = ht->ht[sel]; n; n = n->next) + for (n = rtnl_dereference(ht->ht[sel]); + n; + n = rtnl_dereference(n->next)) if (n->handle == handle) break; out: @@ -272,7 +283,7 @@ static unsigned long u32_get(struct tcf_proto *tp, u32 handle) struct tc_u_common *tp_c = tp->data; if (TC_U32_HTID(handle) == TC_U32_ROOT) - ht = tp->root; + ht = rtnl_dereference(tp->root); else ht = u32_lookup_ht(tp_c, TC_U32_HTID(handle)); @@ -293,6 +304,9 @@ static u32 gen_new_htid(struct tc_u_common *tp_c) { int i = 0x800; + /* hgenerator only used inside rtnl lock it is safe to increment + * without read _copy_ update semantics + */ do { if (++tp_c->hgenerator == 0x7FF) tp_c->hgenerator = 1; @@ -328,11 +342,11 @@ static int u32_init(struct tcf_proto *tp) } tp_c->refcnt++; - root_ht->next = tp_c->hlist; - tp_c->hlist = root_ht; + RCU_INIT_POINTER(root_ht->next, tp_c->hlist); + rcu_assign_pointer(tp_c->hlist, root_ht); root_ht->tp_c = tp_c; - tp->root = root_ht; + rcu_assign_pointer(tp->root, root_ht); tp->data = tp_c; return 0; } @@ -350,19 +364,27 @@ static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n) return 0; } +static void u32_delete_key_rcu(struct rcu_head *rcu) +{ + struct tc_u_knode *key = container_of(rcu, struct tc_u_knode, rcu); + + u32_destroy_key(key->tp, key); +} + static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) { - struct tc_u_knode **kp; + struct tc_u_knode __rcu **kp; + struct tc_u_knode *pkp; struct tc_u_hnode *ht = key->ht_up; if (ht) { - for (kp = &ht->ht[TC_U32_HASH(key->handle)]; *kp; kp = &(*kp)->next) { - if (*kp == key) { - tcf_tree_lock(tp); - *kp = key->next; - tcf_tree_unlock(tp); + kp = &ht->ht[TC_U32_HASH(key->handle)]; + for (pkp = rtnl_dereference(*kp); pkp; + kp = &pkp->next, pkp = rtnl_dereference(*kp)) { + if (pkp == key) { + RCU_INIT_POINTER(*kp, key->next); - u32_destroy_key(tp, key); + call_rcu(&key->rcu, u32_delete_key_rcu); return 0; } } @@ -371,16 +393,16 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) return 0; } -static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) +static void u32_clear_hnode(struct tc_u_hnode *ht) { struct tc_u_knode *n; unsigned int h; for (h = 0; h <= ht->divisor; h++) { - while ((n = ht->ht[h]) != NULL) { - ht->ht[h] = n->next; - - u32_destroy_key(tp, n); + while ((n = rtnl_dereference(ht->ht[h])) != NULL) { + RCU_INIT_POINTER(ht->ht[h], + rtnl_dereference(n->next)); + call_rcu(&n->rcu, u32_delete_key_rcu); } } } @@ -388,28 +410,31 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) { struct tc_u_common *tp_c = tp->data; - struct tc_u_hnode **hn; + struct tc_u_hnode __rcu **hn; + struct tc_u_hnode *phn; WARN_ON(ht->refcnt); - u32_clear_hnode(tp, ht); + u32_clear_hnode(ht); - for (hn = &tp_c->hlist; *hn; hn = &(*hn)->next) { - if (*hn == ht) { - *hn = ht->next; - kfree(ht); + hn = &tp_c->hlist; + for (phn = rtnl_dereference(*hn); + phn; + hn = &phn->next, phn = rtnl_dereference(*hn)) { + if (phn == ht) { + RCU_INIT_POINTER(*hn, ht->next); + kfree_rcu(ht, rcu); return 0; } } - WARN_ON(1); return -ENOENT; } static void u32_destroy(struct tcf_proto *tp) { struct tc_u_common *tp_c = tp->data; - struct tc_u_hnode *root_ht = tp->root; + struct tc_u_hnode *root_ht = rtnl_dereference(tp->root); WARN_ON(root_ht == NULL); @@ -421,17 +446,16 @@ static void u32_destroy(struct tcf_proto *tp) tp->q->u32_node = NULL; - for (ht = tp_c->hlist; ht; ht = ht->next) { + for (ht = rtnl_dereference(tp_c->hlist); + ht; + ht = rtnl_dereference(ht->next)) { ht->refcnt--; - u32_clear_hnode(tp, ht); + u32_clear_hnode(ht); } - while ((ht = tp_c->hlist) != NULL) { - tp_c->hlist = ht->next; - - WARN_ON(ht->refcnt != 0); - - kfree(ht); + while ((ht = rtnl_dereference(tp_c->hlist)) != NULL) { + RCU_INIT_POINTER(tp_c->hlist, ht->next); + kfree_rcu(ht, rcu); } kfree(tp_c); @@ -443,6 +467,7 @@ static void u32_destroy(struct tcf_proto *tp) static int u32_delete(struct tcf_proto *tp, unsigned long arg) { struct tc_u_hnode *ht = (struct tc_u_hnode *)arg; + struct tc_u_hnode *root_ht = rtnl_dereference(tp->root); if (ht == NULL) return 0; @@ -450,7 +475,7 @@ static int u32_delete(struct tcf_proto *tp, unsigned long arg) if (TC_U32_KEY(ht->handle)) return u32_delete_key(tp, (struct tc_u_knode *)ht); - if (tp->root == ht) + if (root_ht == ht) return -EINVAL; if (ht->refcnt == 1) { @@ -473,7 +498,9 @@ static u32 gen_new_kid(struct tc_u_hnode *ht, u32 handle) if (!bitmap) return handle | 0xFFF; - for (n = ht->ht[TC_U32_HASH(handle)]; n; n = n->next) + for (n = rtnl_dereference(ht->ht[TC_U32_HASH(handle)]); + n; + n = rtnl_dereference(n->next)) set_bit(TC_U32_NODE(n->handle), bitmap); i = find_next_zero_bit(bitmap, NR_U32_NODE, 0x800); @@ -523,10 +550,8 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, ht_down->refcnt++; } - tcf_tree_lock(tp); - ht_old = n->ht_down; - n->ht_down = ht_down; - tcf_tree_unlock(tp); + ht_old = rtnl_dereference(n->ht_down); + rcu_assign_pointer(n->ht_down, ht_down); if (ht_old) ht_old->refcnt--; @@ -606,8 +631,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, ht->divisor = divisor; ht->handle = handle; ht->prio = tp->prio; - ht->next = tp_c->hlist; - tp_c->hlist = ht; + RCU_INIT_POINTER(ht->next, tp_c->hlist); + rcu_assign_pointer(tp_c->hlist, ht); *arg = (unsigned long)ht; return 0; } @@ -615,7 +640,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (tb[TCA_U32_HASH]) { htid = nla_get_u32(tb[TCA_U32_HASH]); if (TC_U32_HTID(htid) == TC_U32_ROOT) { - ht = tp->root; + ht = rtnl_dereference(tp->root); htid = ht->handle; } else { ht = u32_lookup_ht(tp->data, TC_U32_HTID(htid)); @@ -623,7 +648,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -EINVAL; } } else { - ht = tp->root; + ht = rtnl_dereference(tp->root); htid = ht->handle; } @@ -660,6 +685,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, n->handle = handle; n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0; tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE); + n->tp = tp; #ifdef CONFIG_CLS_U32_MARK n->pcpu_success = alloc_percpu(u32); @@ -675,21 +701,23 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE], ovr); if (err == 0) { - struct tc_u_knode **ins; - for (ins = &ht->ht[TC_U32_HASH(handle)]; *ins; ins = &(*ins)->next) - if (TC_U32_NODE(handle) < TC_U32_NODE((*ins)->handle)) + struct tc_u_knode __rcu **ins; + struct tc_u_knode *pins; + + ins = &ht->ht[TC_U32_HASH(handle)]; + for (pins = rtnl_dereference(*ins); pins; + ins = &pins->next, pins = rtnl_dereference(*ins)) + if (TC_U32_NODE(handle) < TC_U32_NODE(pins->handle)) break; - n->next = *ins; - tcf_tree_lock(tp); - *ins = n; - tcf_tree_unlock(tp); + RCU_INIT_POINTER(n->next, pins); + rcu_assign_pointer(*ins, n); *arg = (unsigned long)n; return 0; } #ifdef CONFIG_CLS_U32_PERF - kfree(n->pf); + free_percpu(n->pf); #endif kfree(n); return err; @@ -705,7 +733,9 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) if (arg->stop) return; - for (ht = tp_c->hlist; ht; ht = ht->next) { + for (ht = rtnl_dereference(tp_c->hlist); + ht; + ht = rtnl_dereference(ht->next)) { if (ht->prio != tp->prio) continue; if (arg->count >= arg->skip) { @@ -716,7 +746,9 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) } arg->count++; for (h = 0; h <= ht->divisor; h++) { - for (n = ht->ht[h]; n; n = n->next) { + for (n = rtnl_dereference(ht->ht[h]); + n; + n = rtnl_dereference(n->next)) { if (arg->count < arg->skip) { arg->count++; continue; @@ -735,6 +767,7 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct tc_u_knode *n = (struct tc_u_knode *)fh; + struct tc_u_hnode *ht_up, *ht_down; struct nlattr *nest; if (n == NULL) @@ -762,7 +795,9 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, sizeof(n->sel) + n->sel.nkeys*sizeof(struct tc_u32_key), &n->sel)) goto nla_put_failure; - if (n->ht_up) { + + ht_up = rtnl_dereference(n->ht_up); + if (ht_up) { u32 htid = n->handle & 0xFFFFF000; if (nla_put_u32(skb, TCA_U32_HASH, htid)) goto nla_put_failure; @@ -770,8 +805,10 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, if (n->res.classid && nla_put_u32(skb, TCA_U32_CLASSID, n->res.classid)) goto nla_put_failure; - if (n->ht_down && - nla_put_u32(skb, TCA_U32_LINK, n->ht_down->handle)) + + ht_down = rtnl_dereference(n->ht_down); + if (ht_down && + nla_put_u32(skb, TCA_U32_LINK, ht_down->handle)) goto nla_put_failure; #ifdef CONFIG_CLS_U32_MARK From 8b21e2307f2601fd3baaddb3e22f1a25e6719695 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 12 Sep 2014 20:09:49 -0700 Subject: [PATCH 11/12] net: sched: rcu'ify cls_rsvp Signed-off-by: John Fastabend Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/cls_rsvp.h | 160 ++++++++++++++++++++++++------------------- 1 file changed, 90 insertions(+), 70 deletions(-) diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 1020e233a5d6..b044c208b133 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -70,31 +70,34 @@ struct rsvp_head { u32 tmap[256/32]; u32 hgenerator; u8 tgenerator; - struct rsvp_session *ht[256]; + struct rsvp_session __rcu *ht[256]; + struct rcu_head rcu; }; struct rsvp_session { - struct rsvp_session *next; - __be32 dst[RSVP_DST_LEN]; - struct tc_rsvp_gpi dpi; - u8 protocol; - u8 tunnelid; + struct rsvp_session __rcu *next; + __be32 dst[RSVP_DST_LEN]; + struct tc_rsvp_gpi dpi; + u8 protocol; + u8 tunnelid; /* 16 (src,sport) hash slots, and one wildcard source slot */ - struct rsvp_filter *ht[16 + 1]; + struct rsvp_filter __rcu *ht[16 + 1]; + struct rcu_head rcu; }; struct rsvp_filter { - struct rsvp_filter *next; - __be32 src[RSVP_DST_LEN]; - struct tc_rsvp_gpi spi; - u8 tunnelhdr; + struct rsvp_filter __rcu *next; + __be32 src[RSVP_DST_LEN]; + struct tc_rsvp_gpi spi; + u8 tunnelhdr; - struct tcf_result res; - struct tcf_exts exts; + struct tcf_result res; + struct tcf_exts exts; - u32 handle; - struct rsvp_session *sess; + u32 handle; + struct rsvp_session *sess; + struct rcu_head rcu; }; static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) @@ -128,7 +131,7 @@ static inline unsigned int hash_src(__be32 *src) static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct rsvp_session **sht = ((struct rsvp_head *)tp->root)->ht; + struct rsvp_head *head = rcu_dereference_bh(tp->root); struct rsvp_session *s; struct rsvp_filter *f; unsigned int h1, h2; @@ -169,7 +172,8 @@ restart: h1 = hash_dst(dst, protocol, tunnelid); h2 = hash_src(src); - for (s = sht[h1]; s; s = s->next) { + for (s = rcu_dereference_bh(head->ht[h1]); s; + s = rcu_dereference_bh(s->next)) { if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN - 1] && protocol == s->protocol && !(s->dpi.mask & @@ -181,7 +185,8 @@ restart: #endif tunnelid == s->tunnelid) { - for (f = s->ht[h2]; f; f = f->next) { + for (f = rcu_dereference_bh(s->ht[h2]); f; + f = rcu_dereference_bh(f->next)) { if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN - 1] && !(f->spi.mask & (*(u32 *)(xprt + f->spi.offset) ^ f->spi.key)) #if RSVP_DST_LEN == 4 @@ -205,7 +210,8 @@ matched: } /* And wildcard bucket... */ - for (f = s->ht[16]; f; f = f->next) { + for (f = rcu_dereference_bh(s->ht[16]); f; + f = rcu_dereference_bh(f->next)) { *res = f->res; RSVP_APPLY_RESULT(); goto matched; @@ -218,7 +224,7 @@ matched: static unsigned long rsvp_get(struct tcf_proto *tp, u32 handle) { - struct rsvp_session **sht = ((struct rsvp_head *)tp->root)->ht; + struct rsvp_head *head = rtnl_dereference(tp->root); struct rsvp_session *s; struct rsvp_filter *f; unsigned int h1 = handle & 0xFF; @@ -227,8 +233,10 @@ static unsigned long rsvp_get(struct tcf_proto *tp, u32 handle) if (h2 > 16) return 0; - for (s = sht[h1]; s; s = s->next) { - for (f = s->ht[h2]; f; f = f->next) { + for (s = rtnl_dereference(head->ht[h1]); s; + s = rtnl_dereference(s->next)) { + for (f = rtnl_dereference(s->ht[h2]); f; + f = rtnl_dereference(f->next)) { if (f->handle == handle) return (unsigned long)f; } @@ -246,7 +254,7 @@ static int rsvp_init(struct tcf_proto *tp) data = kzalloc(sizeof(struct rsvp_head), GFP_KERNEL); if (data) { - tp->root = data; + rcu_assign_pointer(tp->root, data); return 0; } return -ENOBUFS; @@ -257,53 +265,54 @@ rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) { tcf_unbind_filter(tp, &f->res); tcf_exts_destroy(tp, &f->exts); - kfree(f); + kfree_rcu(f, rcu); } static void rsvp_destroy(struct tcf_proto *tp) { - struct rsvp_head *data = xchg(&tp->root, NULL); - struct rsvp_session **sht; + struct rsvp_head *data = rtnl_dereference(tp->root); int h1, h2; if (data == NULL) return; - sht = data->ht; + RCU_INIT_POINTER(tp->root, NULL); for (h1 = 0; h1 < 256; h1++) { struct rsvp_session *s; - while ((s = sht[h1]) != NULL) { - sht[h1] = s->next; + while ((s = rtnl_dereference(data->ht[h1])) != NULL) { + RCU_INIT_POINTER(data->ht[h1], s->next); for (h2 = 0; h2 <= 16; h2++) { struct rsvp_filter *f; - while ((f = s->ht[h2]) != NULL) { - s->ht[h2] = f->next; + while ((f = rtnl_dereference(s->ht[h2])) != NULL) { + rcu_assign_pointer(s->ht[h2], f->next); rsvp_delete_filter(tp, f); } } - kfree(s); + kfree_rcu(s, rcu); } } - kfree(data); + kfree_rcu(data, rcu); } static int rsvp_delete(struct tcf_proto *tp, unsigned long arg) { - struct rsvp_filter **fp, *f = (struct rsvp_filter *)arg; + struct rsvp_head *head = rtnl_dereference(tp->root); + struct rsvp_filter *nfp, *f = (struct rsvp_filter *)arg; + struct rsvp_filter __rcu **fp; unsigned int h = f->handle; - struct rsvp_session **sp; - struct rsvp_session *s = f->sess; + struct rsvp_session __rcu **sp; + struct rsvp_session *nsp, *s = f->sess; int i; - for (fp = &s->ht[(h >> 8) & 0xFF]; *fp; fp = &(*fp)->next) { - if (*fp == f) { - tcf_tree_lock(tp); - *fp = f->next; - tcf_tree_unlock(tp); + fp = &s->ht[(h >> 8) & 0xFF]; + for (nfp = rtnl_dereference(*fp); nfp; + fp = &nfp->next, nfp = rtnl_dereference(*fp)) { + if (nfp == f) { + RCU_INIT_POINTER(*fp, f->next); rsvp_delete_filter(tp, f); /* Strip tree */ @@ -313,14 +322,12 @@ static int rsvp_delete(struct tcf_proto *tp, unsigned long arg) return 0; /* OK, session has no flows */ - for (sp = &((struct rsvp_head *)tp->root)->ht[h & 0xFF]; - *sp; sp = &(*sp)->next) { - if (*sp == s) { - tcf_tree_lock(tp); - *sp = s->next; - tcf_tree_unlock(tp); - - kfree(s); + sp = &head->ht[h & 0xFF]; + for (nsp = rtnl_dereference(*sp); nsp; + sp = &nsp->next, nsp = rtnl_dereference(*sp)) { + if (nsp == s) { + RCU_INIT_POINTER(*sp, s->next); + kfree_rcu(s, rcu); return 0; } } @@ -333,7 +340,7 @@ static int rsvp_delete(struct tcf_proto *tp, unsigned long arg) static unsigned int gen_handle(struct tcf_proto *tp, unsigned salt) { - struct rsvp_head *data = tp->root; + struct rsvp_head *data = rtnl_dereference(tp->root); int i = 0xFFFF; while (i-- > 0) { @@ -361,7 +368,7 @@ static int tunnel_bts(struct rsvp_head *data) static void tunnel_recycle(struct rsvp_head *data) { - struct rsvp_session **sht = data->ht; + struct rsvp_session __rcu **sht = data->ht; u32 tmap[256/32]; int h1, h2; @@ -369,11 +376,13 @@ static void tunnel_recycle(struct rsvp_head *data) for (h1 = 0; h1 < 256; h1++) { struct rsvp_session *s; - for (s = sht[h1]; s; s = s->next) { + for (s = rtnl_dereference(sht[h1]); s; + s = rtnl_dereference(s->next)) { for (h2 = 0; h2 <= 16; h2++) { struct rsvp_filter *f; - for (f = s->ht[h2]; f; f = f->next) { + for (f = rtnl_dereference(s->ht[h2]); f; + f = rtnl_dereference(f->next)) { if (f->tunnelhdr == 0) continue; data->tgenerator = f->res.classid; @@ -417,9 +426,11 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, struct nlattr **tca, unsigned long *arg, bool ovr) { - struct rsvp_head *data = tp->root; - struct rsvp_filter *f, **fp; - struct rsvp_session *s, **sp; + struct rsvp_head *data = rtnl_dereference(tp->root); + struct rsvp_filter *f, *nfp; + struct rsvp_filter __rcu **fp; + struct rsvp_session *nsp, *s; + struct rsvp_session __rcu **sp; struct tc_rsvp_pinfo *pinfo = NULL; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_RSVP_MAX + 1]; @@ -499,7 +510,9 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, goto errout; } - for (sp = &data->ht[h1]; (s = *sp) != NULL; sp = &s->next) { + for (sp = &data->ht[h1]; + (s = rtnl_dereference(*sp)) != NULL; + sp = &s->next) { if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] && pinfo && pinfo->protocol == s->protocol && memcmp(&pinfo->dpi, &s->dpi, sizeof(s->dpi)) == 0 && @@ -521,12 +534,16 @@ insert: tcf_exts_change(tp, &f->exts, &e); - for (fp = &s->ht[h2]; *fp; fp = &(*fp)->next) - if (((*fp)->spi.mask & f->spi.mask) != f->spi.mask) + fp = &s->ht[h2]; + for (nfp = rtnl_dereference(*fp); nfp; + fp = &nfp->next, nfp = rtnl_dereference(*fp)) { + __u32 mask = nfp->spi.mask & f->spi.mask; + + if (mask != f->spi.mask) break; - f->next = *fp; - wmb(); - *fp = f; + } + RCU_INIT_POINTER(f->next, nfp); + rcu_assign_pointer(*fp, f); *arg = (unsigned long)f; return 0; @@ -546,13 +563,14 @@ insert: s->protocol = pinfo->protocol; s->tunnelid = pinfo->tunnelid; } - for (sp = &data->ht[h1]; *sp; sp = &(*sp)->next) { - if (((*sp)->dpi.mask&s->dpi.mask) != s->dpi.mask) + sp = &data->ht[h1]; + for (nsp = rtnl_dereference(*sp); nsp; + sp = &nsp->next, nsp = rtnl_dereference(*sp)) { + if ((nsp->dpi.mask & s->dpi.mask) != s->dpi.mask) break; } - s->next = *sp; - wmb(); - *sp = s; + RCU_INIT_POINTER(s->next, nsp); + rcu_assign_pointer(*sp, s); goto insert; @@ -565,7 +583,7 @@ errout2: static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct rsvp_head *head = tp->root; + struct rsvp_head *head = rtnl_dereference(tp->root); unsigned int h, h1; if (arg->stop) @@ -574,11 +592,13 @@ static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) for (h = 0; h < 256; h++) { struct rsvp_session *s; - for (s = head->ht[h]; s; s = s->next) { + for (s = rtnl_dereference(head->ht[h]); s; + s = rtnl_dereference(s->next)) { for (h1 = 0; h1 <= 16; h1++) { struct rsvp_filter *f; - for (f = s->ht[h1]; f; f = f->next) { + for (f = rtnl_dereference(s->ht[h1]); f; + f = rtnl_dereference(f->next)) { if (arg->count < arg->skip) { arg->count++; continue; From d355ab09594118b8dfb3d78dbda72fff634a934b Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 12 Sep 2014 20:10:24 -0700 Subject: [PATCH 12/12] net: sched: rcu'ify cls_bpf This patch makes the cls_bpf classifier RCU safe. The tcf_lock was being used to protect a list of cls_bpf_prog now this list is RCU safe and updates occur with rcu_replace. Signed-off-by: John Fastabend Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/cls_bpf.c | 94 ++++++++++++++++++++++----------------------- 1 file changed, 47 insertions(+), 47 deletions(-) diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 0e30d58149da..6a7386e6e5a8 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -27,6 +27,7 @@ MODULE_DESCRIPTION("TC BPF based classifier"); struct cls_bpf_head { struct list_head plist; u32 hgen; + struct rcu_head rcu; }; struct cls_bpf_prog { @@ -37,6 +38,8 @@ struct cls_bpf_prog { struct list_head link; u32 handle; u16 bpf_len; + struct tcf_proto *tp; + struct rcu_head rcu; }; static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { @@ -49,11 +52,11 @@ static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct cls_bpf_head *head = tp->root; + struct cls_bpf_head *head = rcu_dereference(tp->root); struct cls_bpf_prog *prog; int ret; - list_for_each_entry(prog, &head->plist, link) { + list_for_each_entry_rcu(prog, &head->plist, link) { int filter_res = BPF_PROG_RUN(prog->filter, skb); if (filter_res == 0) @@ -81,8 +84,8 @@ static int cls_bpf_init(struct tcf_proto *tp) if (head == NULL) return -ENOBUFS; - INIT_LIST_HEAD(&head->plist); - tp->root = head; + INIT_LIST_HEAD_RCU(&head->plist); + rcu_assign_pointer(tp->root, head); return 0; } @@ -98,18 +101,22 @@ static void cls_bpf_delete_prog(struct tcf_proto *tp, struct cls_bpf_prog *prog) kfree(prog); } +static void __cls_bpf_delete_prog(struct rcu_head *rcu) +{ + struct cls_bpf_prog *prog = container_of(rcu, struct cls_bpf_prog, rcu); + + cls_bpf_delete_prog(prog->tp, prog); +} + static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg) { - struct cls_bpf_head *head = tp->root; + struct cls_bpf_head *head = rtnl_dereference(tp->root); struct cls_bpf_prog *prog, *todel = (struct cls_bpf_prog *) arg; list_for_each_entry(prog, &head->plist, link) { if (prog == todel) { - tcf_tree_lock(tp); - list_del(&prog->link); - tcf_tree_unlock(tp); - - cls_bpf_delete_prog(tp, prog); + list_del_rcu(&prog->link); + call_rcu(&prog->rcu, __cls_bpf_delete_prog); return 0; } } @@ -119,27 +126,28 @@ static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg) static void cls_bpf_destroy(struct tcf_proto *tp) { - struct cls_bpf_head *head = tp->root; + struct cls_bpf_head *head = rtnl_dereference(tp->root); struct cls_bpf_prog *prog, *tmp; list_for_each_entry_safe(prog, tmp, &head->plist, link) { - list_del(&prog->link); - cls_bpf_delete_prog(tp, prog); + list_del_rcu(&prog->link); + call_rcu(&prog->rcu, __cls_bpf_delete_prog); } - kfree(head); + RCU_INIT_POINTER(tp->root, NULL); + kfree_rcu(head, rcu); } static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle) { - struct cls_bpf_head *head = tp->root; + struct cls_bpf_head *head = rtnl_dereference(tp->root); struct cls_bpf_prog *prog; unsigned long ret = 0UL; if (head == NULL) return 0UL; - list_for_each_entry(prog, &head->plist, link) { + list_for_each_entry_rcu(prog, &head->plist, link) { if (prog->handle == handle) { ret = (unsigned long) prog; break; @@ -158,10 +166,10 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, unsigned long base, struct nlattr **tb, struct nlattr *est, bool ovr) { - struct sock_filter *bpf_ops, *bpf_old; + struct sock_filter *bpf_ops; struct tcf_exts exts; struct sock_fprog_kern tmp; - struct bpf_prog *fp, *fp_old; + struct bpf_prog *fp; u16 bpf_size, bpf_len; u32 classid; int ret; @@ -197,26 +205,15 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, if (ret) goto errout_free; - tcf_tree_lock(tp); - fp_old = prog->filter; - bpf_old = prog->bpf_ops; - prog->bpf_len = bpf_len; prog->bpf_ops = bpf_ops; prog->filter = fp; prog->res.classid = classid; - tcf_tree_unlock(tp); tcf_bind_filter(tp, &prog->res, base); tcf_exts_change(tp, &prog->exts, &exts); - if (fp_old) - bpf_prog_destroy(fp_old); - if (bpf_old) - kfree(bpf_old); - return 0; - errout_free: kfree(bpf_ops); errout: @@ -244,9 +241,10 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, u32 handle, struct nlattr **tca, unsigned long *arg, bool ovr) { - struct cls_bpf_head *head = tp->root; - struct cls_bpf_prog *prog = (struct cls_bpf_prog *) *arg; + struct cls_bpf_head *head = rtnl_dereference(tp->root); + struct cls_bpf_prog *oldprog = (struct cls_bpf_prog *) *arg; struct nlattr *tb[TCA_BPF_MAX + 1]; + struct cls_bpf_prog *prog; int ret; if (tca[TCA_OPTIONS] == NULL) @@ -256,18 +254,19 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, if (ret < 0) return ret; - if (prog != NULL) { - if (handle && prog->handle != handle) - return -EINVAL; - return cls_bpf_modify_existing(net, tp, prog, base, tb, - tca[TCA_RATE], ovr); - } - prog = kzalloc(sizeof(*prog), GFP_KERNEL); - if (prog == NULL) + if (!prog) return -ENOBUFS; tcf_exts_init(&prog->exts, TCA_BPF_ACT, TCA_BPF_POLICE); + + if (oldprog) { + if (handle && oldprog->handle != handle) { + ret = -EINVAL; + goto errout; + } + } + if (handle == 0) prog->handle = cls_bpf_grab_new_handle(tp, head); else @@ -281,16 +280,17 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, if (ret < 0) goto errout; - tcf_tree_lock(tp); - list_add(&prog->link, &head->plist); - tcf_tree_unlock(tp); + if (oldprog) { + list_replace_rcu(&prog->link, &oldprog->link); + call_rcu(&oldprog->rcu, __cls_bpf_delete_prog); + } else { + list_add_rcu(&prog->link, &head->plist); + } *arg = (unsigned long) prog; - return 0; errout: - if (*arg == 0UL && prog) - kfree(prog); + kfree(prog); return ret; } @@ -339,10 +339,10 @@ nla_put_failure: static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct cls_bpf_head *head = tp->root; + struct cls_bpf_head *head = rtnl_dereference(tp->root); struct cls_bpf_prog *prog; - list_for_each_entry(prog, &head->plist, link) { + list_for_each_entry_rcu(prog, &head->plist, link) { if (arg->count < arg->skip) goto skip; if (arg->fn(tp, (unsigned long) prog, arg) < 0) {