diff options
Diffstat (limited to 'net/sched')
51 files changed, 2769 insertions, 1069 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig index e95741388311..1b9afdee5ba9 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -194,6 +194,17 @@ config NET_SCH_ETF To compile this code as a module, choose M here: the module will be called sch_etf. +config NET_SCH_TAPRIO + tristate "Time Aware Priority (taprio) Scheduler" + help + Say Y here if you want to use the Time Aware Priority (taprio) packet + scheduling algorithm. + + See the top of <file:net/sched/sch_taprio.c> for more details. + + To compile this code as a module, choose M here: the + module will be called sch_taprio. + config NET_SCH_GRED tristate "Generic Random Early Detection (GRED)" ---help--- diff --git a/net/sched/Makefile b/net/sched/Makefile index f0403f49edcb..8a40431d7b5c 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -57,6 +57,7 @@ obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o +obj-$(CONFIG_NET_SCH_TAPRIO) += sch_taprio.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index e12f8ef7baa4..d4b8355737d8 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -21,8 +21,6 @@ #include <linux/kmod.h> #include <linux/err.h> #include <linux/module.h> -#include <linux/rhashtable.h> -#include <linux/list.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/sch_generic.h> @@ -81,6 +79,7 @@ static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie, static void free_tcf(struct tc_action *p) { free_percpu(p->cpu_bstats); + free_percpu(p->cpu_bstats_hw); free_percpu(p->cpu_qstats); tcf_set_action_cookie(&p->act_cookie, NULL); @@ -103,11 +102,11 @@ static int __tcf_action_put(struct tc_action *p, bool bind) { struct tcf_idrinfo *idrinfo = p->idrinfo; - if (refcount_dec_and_lock(&p->tcfa_refcnt, &idrinfo->lock)) { + if (refcount_dec_and_mutex_lock(&p->tcfa_refcnt, &idrinfo->lock)) { if (bind) atomic_dec(&p->tcfa_bindcnt); idr_remove(&idrinfo->action_idr, p->tcfa_index); - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); tcf_action_cleanup(p); return 1; @@ -199,7 +198,7 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, struct tc_action *p; unsigned long id = 1; - spin_lock(&idrinfo->lock); + mutex_lock(&idrinfo->lock); s_i = cb->args[0]; @@ -234,7 +233,7 @@ done: if (index >= 0) cb->args[0] = index + 1; - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); if (n_i) { if (act_flags & TCA_FLAG_LARGE_DUMP_ON) cb->args[1] = n_i; @@ -246,6 +245,20 @@ nla_put_failure: goto done; } +static int tcf_idr_release_unsafe(struct tc_action *p) +{ + if (atomic_read(&p->tcfa_bindcnt) > 0) + return -EPERM; + + if (refcount_dec_and_test(&p->tcfa_refcnt)) { + idr_remove(&p->idrinfo->action_idr, p->tcfa_index); + tcf_action_cleanup(p); + return ACT_P_DELETED; + } + + return 0; +} + static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, const struct tc_action_ops *ops) { @@ -262,15 +275,19 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, if (nla_put_string(skb, TCA_KIND, ops->kind)) goto nla_put_failure; + mutex_lock(&idrinfo->lock); idr_for_each_entry_ul(idr, p, id) { - ret = __tcf_idr_release(p, false, true); + ret = tcf_idr_release_unsafe(p); if (ret == ACT_P_DELETED) { module_put(ops->owner); n_i++; } else if (ret < 0) { + mutex_unlock(&idrinfo->lock); goto nla_put_failure; } } + mutex_unlock(&idrinfo->lock); + if (nla_put_u32(skb, TCA_FCNT, n_i)) goto nla_put_failure; nla_nest_end(skb, nest); @@ -305,13 +322,13 @@ int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index) struct tcf_idrinfo *idrinfo = tn->idrinfo; struct tc_action *p; - spin_lock(&idrinfo->lock); + mutex_lock(&idrinfo->lock); p = idr_find(&idrinfo->action_idr, index); if (IS_ERR(p)) p = NULL; else if (p) refcount_inc(&p->tcfa_refcnt); - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); if (p) { *a = p; @@ -326,10 +343,10 @@ static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index) struct tc_action *p; int ret = 0; - spin_lock(&idrinfo->lock); + mutex_lock(&idrinfo->lock); p = idr_find(&idrinfo->action_idr, index); if (!p) { - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); return -ENOENT; } @@ -339,7 +356,7 @@ static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index) WARN_ON(p != idr_remove(&idrinfo->action_idr, p->tcfa_index)); - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); tcf_action_cleanup(p); module_put(owner); @@ -350,7 +367,7 @@ static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index) ret = -EPERM; } - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); return ret; } @@ -372,9 +389,12 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); if (!p->cpu_bstats) goto err1; + p->cpu_bstats_hw = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); + if (!p->cpu_bstats_hw) + goto err2; p->cpu_qstats = alloc_percpu(struct gnet_stats_queue); if (!p->cpu_qstats) - goto err2; + goto err3; } spin_lock_init(&p->tcfa_lock); p->tcfa_index = index; @@ -386,15 +406,17 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, &p->tcfa_rate_est, &p->tcfa_lock, NULL, est); if (err) - goto err3; + goto err4; } p->idrinfo = idrinfo; p->ops = ops; *a = p; return 0; -err3: +err4: free_percpu(p->cpu_qstats); +err3: + free_percpu(p->cpu_bstats_hw); err2: free_percpu(p->cpu_bstats); err1: @@ -407,10 +429,10 @@ void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a) { struct tcf_idrinfo *idrinfo = tn->idrinfo; - spin_lock(&idrinfo->lock); + mutex_lock(&idrinfo->lock); /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */ WARN_ON(!IS_ERR(idr_replace(&idrinfo->action_idr, a, a->tcfa_index))); - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); } EXPORT_SYMBOL(tcf_idr_insert); @@ -420,10 +442,10 @@ void tcf_idr_cleanup(struct tc_action_net *tn, u32 index) { struct tcf_idrinfo *idrinfo = tn->idrinfo; - spin_lock(&idrinfo->lock); + mutex_lock(&idrinfo->lock); /* Remove ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */ WARN_ON(!IS_ERR(idr_remove(&idrinfo->action_idr, index))); - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); } EXPORT_SYMBOL(tcf_idr_cleanup); @@ -441,14 +463,14 @@ int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, int ret; again: - spin_lock(&idrinfo->lock); + mutex_lock(&idrinfo->lock); if (*index) { p = idr_find(&idrinfo->action_idr, *index); if (IS_ERR(p)) { /* This means that another process allocated * index but did not assign the pointer yet. */ - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); goto again; } @@ -461,7 +483,7 @@ again: } else { *a = NULL; ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index, - *index, GFP_ATOMIC); + *index, GFP_KERNEL); if (!ret) idr_replace(&idrinfo->action_idr, ERR_PTR(-EBUSY), *index); @@ -470,12 +492,12 @@ again: *index = 1; *a = NULL; ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index, - UINT_MAX, GFP_ATOMIC); + UINT_MAX, GFP_KERNEL); if (!ret) idr_replace(&idrinfo->action_idr, ERR_PTR(-EBUSY), *index); } - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); return ret; } EXPORT_SYMBOL(tcf_idr_check_alloc); @@ -979,6 +1001,8 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p, goto errout; if (gnet_stats_copy_basic(NULL, &d, p->cpu_bstats, &p->tcfa_bstats) < 0 || + gnet_stats_copy_basic_hw(NULL, &d, p->cpu_bstats_hw, + &p->tcfa_bstats_hw) < 0 || gnet_stats_copy_rate_est(&d, &p->tcfa_rate_est) < 0 || gnet_stats_copy_queue(&d, p->cpu_qstats, &p->tcfa_qstats, @@ -1073,12 +1097,14 @@ static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla, err = -EINVAL; ops = tc_lookup_action(tb[TCA_ACT_KIND]); if (!ops) { /* could happen in batch of actions */ - NL_SET_ERR_MSG(extack, "Specified TC action not found"); + NL_SET_ERR_MSG(extack, "Specified TC action kind not found"); goto err_out; } err = -ENOENT; - if (ops->lookup(net, &a, index, extack) == 0) + if (ops->lookup(net, &a, index) == 0) { + NL_SET_ERR_MSG(extack, "TC action with specified index not found"); goto err_mod; + } module_put(ops->owner); return a; @@ -1424,7 +1450,7 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) u32 act_count = 0; ret = nlmsg_parse(cb->nlh, sizeof(struct tcamsg), tb, TCA_ROOT_MAX, - tcaa_policy, NULL); + tcaa_policy, cb->extack); if (ret < 0) return ret; @@ -1494,227 +1520,8 @@ out_module_put: return skb->len; } -struct tcf_action_net { - struct rhashtable egdev_ht; -}; - -static unsigned int tcf_action_net_id; - -struct tcf_action_egdev_cb { - struct list_head list; - tc_setup_cb_t *cb; - void *cb_priv; -}; - -struct tcf_action_egdev { - struct rhash_head ht_node; - const struct net_device *dev; - unsigned int refcnt; - struct list_head cb_list; -}; - -static const struct rhashtable_params tcf_action_egdev_ht_params = { - .key_offset = offsetof(struct tcf_action_egdev, dev), - .head_offset = offsetof(struct tcf_action_egdev, ht_node), - .key_len = sizeof(const struct net_device *), -}; - -static struct tcf_action_egdev * -tcf_action_egdev_lookup(const struct net_device *dev) -{ - struct net *net = dev_net(dev); - struct tcf_action_net *tan = net_generic(net, tcf_action_net_id); - - return rhashtable_lookup_fast(&tan->egdev_ht, &dev, - tcf_action_egdev_ht_params); -} - -static struct tcf_action_egdev * -tcf_action_egdev_get(const struct net_device *dev) -{ - struct tcf_action_egdev *egdev; - struct tcf_action_net *tan; - - egdev = tcf_action_egdev_lookup(dev); - if (egdev) - goto inc_ref; - - egdev = kzalloc(sizeof(*egdev), GFP_KERNEL); - if (!egdev) - return NULL; - INIT_LIST_HEAD(&egdev->cb_list); - egdev->dev = dev; - tan = net_generic(dev_net(dev), tcf_action_net_id); - rhashtable_insert_fast(&tan->egdev_ht, &egdev->ht_node, - tcf_action_egdev_ht_params); - -inc_ref: - egdev->refcnt++; - return egdev; -} - -static void tcf_action_egdev_put(struct tcf_action_egdev *egdev) -{ - struct tcf_action_net *tan; - - if (--egdev->refcnt) - return; - tan = net_generic(dev_net(egdev->dev), tcf_action_net_id); - rhashtable_remove_fast(&tan->egdev_ht, &egdev->ht_node, - tcf_action_egdev_ht_params); - kfree(egdev); -} - -static struct tcf_action_egdev_cb * -tcf_action_egdev_cb_lookup(struct tcf_action_egdev *egdev, - tc_setup_cb_t *cb, void *cb_priv) -{ - struct tcf_action_egdev_cb *egdev_cb; - - list_for_each_entry(egdev_cb, &egdev->cb_list, list) - if (egdev_cb->cb == cb && egdev_cb->cb_priv == cb_priv) - return egdev_cb; - return NULL; -} - -static int tcf_action_egdev_cb_call(struct tcf_action_egdev *egdev, - enum tc_setup_type type, - void *type_data, bool err_stop) -{ - struct tcf_action_egdev_cb *egdev_cb; - int ok_count = 0; - int err; - - list_for_each_entry(egdev_cb, &egdev->cb_list, list) { - err = egdev_cb->cb(type, type_data, egdev_cb->cb_priv); - if (err) { - if (err_stop) - return err; - } else { - ok_count++; - } - } - return ok_count; -} - -static int tcf_action_egdev_cb_add(struct tcf_action_egdev *egdev, - tc_setup_cb_t *cb, void *cb_priv) -{ - struct tcf_action_egdev_cb *egdev_cb; - - egdev_cb = tcf_action_egdev_cb_lookup(egdev, cb, cb_priv); - if (WARN_ON(egdev_cb)) - return -EEXIST; - egdev_cb = kzalloc(sizeof(*egdev_cb), GFP_KERNEL); - if (!egdev_cb) - return -ENOMEM; - egdev_cb->cb = cb; - egdev_cb->cb_priv = cb_priv; - list_add(&egdev_cb->list, &egdev->cb_list); - return 0; -} - -static void tcf_action_egdev_cb_del(struct tcf_action_egdev *egdev, - tc_setup_cb_t *cb, void *cb_priv) -{ - struct tcf_action_egdev_cb *egdev_cb; - - egdev_cb = tcf_action_egdev_cb_lookup(egdev, cb, cb_priv); - if (WARN_ON(!egdev_cb)) - return; - list_del(&egdev_cb->list); - kfree(egdev_cb); -} - -static int __tc_setup_cb_egdev_register(const struct net_device *dev, - tc_setup_cb_t *cb, void *cb_priv) -{ - struct tcf_action_egdev *egdev = tcf_action_egdev_get(dev); - int err; - - if (!egdev) - return -ENOMEM; - err = tcf_action_egdev_cb_add(egdev, cb, cb_priv); - if (err) - goto err_cb_add; - return 0; - -err_cb_add: - tcf_action_egdev_put(egdev); - return err; -} -int tc_setup_cb_egdev_register(const struct net_device *dev, - tc_setup_cb_t *cb, void *cb_priv) -{ - int err; - - rtnl_lock(); - err = __tc_setup_cb_egdev_register(dev, cb, cb_priv); - rtnl_unlock(); - return err; -} -EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_register); - -static void __tc_setup_cb_egdev_unregister(const struct net_device *dev, - tc_setup_cb_t *cb, void *cb_priv) -{ - struct tcf_action_egdev *egdev = tcf_action_egdev_lookup(dev); - - if (WARN_ON(!egdev)) - return; - tcf_action_egdev_cb_del(egdev, cb, cb_priv); - tcf_action_egdev_put(egdev); -} -void tc_setup_cb_egdev_unregister(const struct net_device *dev, - tc_setup_cb_t *cb, void *cb_priv) -{ - rtnl_lock(); - __tc_setup_cb_egdev_unregister(dev, cb, cb_priv); - rtnl_unlock(); -} -EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_unregister); - -int tc_setup_cb_egdev_call(const struct net_device *dev, - enum tc_setup_type type, void *type_data, - bool err_stop) -{ - struct tcf_action_egdev *egdev = tcf_action_egdev_lookup(dev); - - if (!egdev) - return 0; - return tcf_action_egdev_cb_call(egdev, type, type_data, err_stop); -} -EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_call); - -static __net_init int tcf_action_net_init(struct net *net) -{ - struct tcf_action_net *tan = net_generic(net, tcf_action_net_id); - - return rhashtable_init(&tan->egdev_ht, &tcf_action_egdev_ht_params); -} - -static void __net_exit tcf_action_net_exit(struct net *net) -{ - struct tcf_action_net *tan = net_generic(net, tcf_action_net_id); - - rhashtable_destroy(&tan->egdev_ht); -} - -static struct pernet_operations tcf_action_net_ops = { - .init = tcf_action_net_init, - .exit = tcf_action_net_exit, - .id = &tcf_action_net_id, - .size = sizeof(struct tcf_action_net), -}; - static int __init tc_action_init(void) { - int err; - - err = register_pernet_subsys(&tcf_action_net_ops); - if (err) - return err; - rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETACTION, tc_ctl_action, tc_dump_action, diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 0c68bc9cf0b4..c7633843e223 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -387,8 +387,7 @@ static int tcf_bpf_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, bpf_net_id); diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 6f0f273f1139..8475913f2070 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -143,8 +143,10 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, return -EEXIST; } /* replacing action and zone */ + spin_lock_bh(&ci->tcf_lock); ci->tcf_action = parm->action; ci->zone = parm->zone; + spin_unlock_bh(&ci->tcf_lock); ret = 0; } @@ -156,16 +158,16 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a, { unsigned char *b = skb_tail_pointer(skb); struct tcf_connmark_info *ci = to_connmark(a); - struct tc_connmark opt = { .index = ci->tcf_index, .refcnt = refcount_read(&ci->tcf_refcnt) - ref, .bindcnt = atomic_read(&ci->tcf_bindcnt) - bind, - .action = ci->tcf_action, - .zone = ci->zone, }; struct tcf_t t; + spin_lock_bh(&ci->tcf_lock); + opt.action = ci->tcf_action; + opt.zone = ci->zone; if (nla_put(skb, TCA_CONNMARK_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -173,9 +175,12 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put_64bit(skb, TCA_CONNMARK_TM, sizeof(t), &t, TCA_CONNMARK_PAD)) goto nla_put_failure; + spin_unlock_bh(&ci->tcf_lock); return skb->len; + nla_put_failure: + spin_unlock_bh(&ci->tcf_lock); nlmsg_trim(skb, b); return -1; } @@ -190,8 +195,7 @@ static int tcf_connmark_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, connmark_net_id); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index b8a67ae3105a..3dc25b7806d7 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -646,8 +646,7 @@ static int tcf_csum_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, csum_net_id); diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index cd1d9bd32ef9..b61c20ebb314 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -88,6 +88,11 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, p_parm = nla_data(tb[TCA_GACT_PROB]); if (p_parm->ptype >= MAX_RAND) return -EINVAL; + if (TC_ACT_EXT_CMP(p_parm->paction, TC_ACT_GOTO_CHAIN)) { + NL_SET_ERR_MSG(extack, + "goto chain not allowed on fallback"); + return -EINVAL; + } } #endif @@ -157,7 +162,7 @@ static int tcf_gact_act(struct sk_buff *skb, const struct tc_action *a, } static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets, - u64 lastuse) + u64 lastuse, bool hw) { struct tcf_gact *gact = to_gact(a); int action = READ_ONCE(gact->tcf_action); @@ -168,6 +173,10 @@ static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets, if (action == TC_ACT_SHOT) this_cpu_ptr(gact->common.cpu_qstats)->drops += packets; + if (hw) + _bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats_hw), + bytes, packets); + tm->lastuse = max_t(u64, tm->lastuse, lastuse); } @@ -222,8 +231,7 @@ static int tcf_gact_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, gact_net_id); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 06a3d4801878..30b63fa23ee2 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -855,8 +855,7 @@ static int tcf_ife_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, ife_net_id); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 8525de811616..8af6c11d2482 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -329,8 +329,7 @@ static int tcf_ipt_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, ipt_net_id); @@ -379,8 +378,7 @@ static int tcf_xt_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, xt_net_id); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 8bf66d0a6800..c8cf4d10c435 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -258,7 +258,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, if (is_redirect) { skb2->tc_redirected = 1; skb2->tc_from_ingress = skb2->tc_at_ingress; - + if (skb2->tc_from_ingress) + skb2->tstamp = 0; /* let's the caller reinsert the packet, if possible */ if (use_reinsert) { res->ingress = want_ingress; @@ -283,12 +284,15 @@ out: } static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets, - u64 lastuse) + u64 lastuse, bool hw) { struct tcf_mirred *m = to_mirred(a); struct tcf_t *tm = &m->tcf_tm; _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); + if (hw) + _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw), + bytes, packets); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } @@ -338,8 +342,7 @@ static int tcf_mirred_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, mirred_net_id); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 4313aa102440..c5c1e23add77 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -256,28 +256,31 @@ static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a, unsigned char *b = skb_tail_pointer(skb); struct tcf_nat *p = to_tcf_nat(a); struct tc_nat opt = { - .old_addr = p->old_addr, - .new_addr = p->new_addr, - .mask = p->mask, - .flags = p->flags, - .index = p->tcf_index, - .action = p->tcf_action, .refcnt = refcount_read(&p->tcf_refcnt) - ref, .bindcnt = atomic_read(&p->tcf_bindcnt) - bind, }; struct tcf_t t; + spin_lock_bh(&p->tcf_lock); + opt.old_addr = p->old_addr; + opt.new_addr = p->new_addr; + opt.mask = p->mask; + opt.flags = p->flags; + opt.action = p->tcf_action; + if (nla_put(skb, TCA_NAT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_NAT_TM, sizeof(t), &t, TCA_NAT_PAD)) goto nla_put_failure; + spin_unlock_bh(&p->tcf_lock); return skb->len; nla_put_failure: + spin_unlock_bh(&p->tcf_lock); nlmsg_trim(skb, b); return -1; } @@ -292,8 +295,7 @@ static int tcf_nat_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, nat_net_id); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index ad99a99f11f6..2b372a06b432 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -201,7 +201,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, goto out_release; } } else { - return err; + ret = err; + goto out_free; } p = to_pedit(*a); @@ -460,8 +461,7 @@ static int tcf_pedit_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, pedit_net_id); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 5d8bfa878477..ec8ec55e0fe8 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -22,20 +22,27 @@ #include <net/act_api.h> #include <net/netlink.h> -struct tcf_police { - struct tc_action common; +struct tcf_police_params { int tcfp_result; u32 tcfp_ewma_rate; s64 tcfp_burst; u32 tcfp_mtu; - s64 tcfp_toks; - s64 tcfp_ptoks; s64 tcfp_mtu_ptoks; - s64 tcfp_t_c; struct psched_ratecfg rate; bool rate_present; struct psched_ratecfg peak; bool peak_present; + struct rcu_head rcu; +}; + +struct tcf_police { + struct tc_action common; + struct tcf_police_params __rcu *params; + + spinlock_t tcfp_lock ____cacheline_aligned_in_smp; + s64 tcfp_toks; + s64 tcfp_ptoks; + s64 tcfp_t_c; }; #define to_police(pc) ((struct tcf_police *)pc) @@ -78,14 +85,14 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, int ovr, int bind, bool rtnl_held, struct netlink_ext_ack *extack) { - int ret = 0, err; + int ret = 0, tcfp_result = TC_ACT_OK, err, size; struct nlattr *tb[TCA_POLICE_MAX + 1]; struct tc_police *parm; struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; struct tc_action_net *tn = net_generic(net, police_net_id); + struct tcf_police_params *new; bool exists = false; - int size; if (nla == NULL) return -EINVAL; @@ -110,12 +117,13 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, parm->index, NULL, a, - &act_police_ops, bind, false); + &act_police_ops, bind, true); if (ret) { tcf_idr_cleanup(tn, parm->index); return ret; } ret = ACT_P_CREATED; + spin_lock_init(&(to_police(*a)->tcfp_lock)); } else if (!ovr) { tcf_idr_release(*a, bind); return -EEXIST; @@ -137,7 +145,8 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, } if (est) { - err = gen_replace_estimator(&police->tcf_bstats, NULL, + err = gen_replace_estimator(&police->tcf_bstats, + police->common.cpu_bstats, &police->tcf_rate_est, &police->tcf_lock, NULL, est); @@ -150,50 +159,71 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, goto failure; } - spin_lock_bh(&police->tcf_lock); + if (tb[TCA_POLICE_RESULT]) { + tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); + if (TC_ACT_EXT_CMP(tcfp_result, TC_ACT_GOTO_CHAIN)) { + NL_SET_ERR_MSG(extack, + "goto chain not allowed on fallback"); + err = -EINVAL; + goto failure; + } + } + + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (unlikely(!new)) { + err = -ENOMEM; + goto failure; + } + /* No failure allowed after this point */ - police->tcfp_mtu = parm->mtu; - if (police->tcfp_mtu == 0) { - police->tcfp_mtu = ~0; + new->tcfp_result = tcfp_result; + new->tcfp_mtu = parm->mtu; + if (!new->tcfp_mtu) { + new->tcfp_mtu = ~0; if (R_tab) - police->tcfp_mtu = 255 << R_tab->rate.cell_log; + new->tcfp_mtu = 255 << R_tab->rate.cell_log; } if (R_tab) { - police->rate_present = true; - psched_ratecfg_precompute(&police->rate, &R_tab->rate, 0); + new->rate_present = true; + psched_ratecfg_precompute(&new->rate, &R_tab->rate, 0); qdisc_put_rtab(R_tab); } else { - police->rate_present = false; + new->rate_present = false; } if (P_tab) { - police->peak_present = true; - psched_ratecfg_precompute(&police->peak, &P_tab->rate, 0); + new->peak_present = true; + psched_ratecfg_precompute(&new->peak, &P_tab->rate, 0); qdisc_put_rtab(P_tab); } else { - police->peak_present = false; + new->peak_present = false; } - if (tb[TCA_POLICE_RESULT]) - police->tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); - police->tcfp_burst = PSCHED_TICKS2NS(parm->burst); - police->tcfp_toks = police->tcfp_burst; - if (police->peak_present) { - police->tcfp_mtu_ptoks = (s64) psched_l2t_ns(&police->peak, - police->tcfp_mtu); - police->tcfp_ptoks = police->tcfp_mtu_ptoks; - } - police->tcf_action = parm->action; + new->tcfp_burst = PSCHED_TICKS2NS(parm->burst); + if (new->peak_present) + new->tcfp_mtu_ptoks = (s64)psched_l2t_ns(&new->peak, + new->tcfp_mtu); if (tb[TCA_POLICE_AVRATE]) - police->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]); + new->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]); + spin_lock_bh(&police->tcf_lock); + spin_lock_bh(&police->tcfp_lock); + police->tcfp_t_c = ktime_get_ns(); + police->tcfp_toks = new->tcfp_burst; + if (new->peak_present) + police->tcfp_ptoks = new->tcfp_mtu_ptoks; + spin_unlock_bh(&police->tcfp_lock); + police->tcf_action = parm->action; + rcu_swap_protected(police->params, + new, + lockdep_is_held(&police->tcf_lock)); spin_unlock_bh(&police->tcf_lock); - if (ret != ACT_P_CREATED) - return ret; - police->tcfp_t_c = ktime_get_ns(); - tcf_idr_insert(tn, *a); + if (new) + kfree_rcu(new, rcu); + if (ret == ACT_P_CREATED) + tcf_idr_insert(tn, *a); return ret; failure: @@ -207,64 +237,72 @@ static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_police *police = to_police(a); - s64 now; - s64 toks; - s64 ptoks = 0; + struct tcf_police_params *p; + s64 now, toks, ptoks = 0; + int ret; - spin_lock(&police->tcf_lock); - - bstats_update(&police->tcf_bstats, skb); tcf_lastuse_update(&police->tcf_tm); + bstats_cpu_update(this_cpu_ptr(police->common.cpu_bstats), skb); + + ret = READ_ONCE(police->tcf_action); + p = rcu_dereference_bh(police->params); - if (police->tcfp_ewma_rate) { + if (p->tcfp_ewma_rate) { struct gnet_stats_rate_est64 sample; if (!gen_estimator_read(&police->tcf_rate_est, &sample) || - sample.bps >= police->tcfp_ewma_rate) { - police->tcf_qstats.overlimits++; - if (police->tcf_action == TC_ACT_SHOT) - police->tcf_qstats.drops++; - spin_unlock(&police->tcf_lock); - return police->tcf_action; - } + sample.bps >= p->tcfp_ewma_rate) + goto inc_overlimits; } - if (qdisc_pkt_len(skb) <= police->tcfp_mtu) { - if (!police->rate_present) { - spin_unlock(&police->tcf_lock); - return police->tcfp_result; + if (qdisc_pkt_len(skb) <= p->tcfp_mtu) { + if (!p->rate_present) { + ret = p->tcfp_result; + goto end; } now = ktime_get_ns(); - toks = min_t(s64, now - police->tcfp_t_c, - police->tcfp_burst); - if (police->peak_present) { + spin_lock_bh(&police->tcfp_lock); + toks = min_t(s64, now - police->tcfp_t_c, p->tcfp_burst); + if (p->peak_present) { ptoks = toks + police->tcfp_ptoks; - if (ptoks > police->tcfp_mtu_ptoks) - ptoks = police->tcfp_mtu_ptoks; - ptoks -= (s64) psched_l2t_ns(&police->peak, - qdisc_pkt_len(skb)); + if (ptoks > p->tcfp_mtu_ptoks) + ptoks = p->tcfp_mtu_ptoks; + ptoks -= (s64)psched_l2t_ns(&p->peak, + qdisc_pkt_len(skb)); } toks += police->tcfp_toks; - if (toks > police->tcfp_burst) - toks = police->tcfp_burst; - toks -= (s64) psched_l2t_ns(&police->rate, qdisc_pkt_len(skb)); + if (toks > p->tcfp_burst) + toks = p->tcfp_burst; + toks -= (s64)psched_l2t_ns(&p->rate, qdisc_pkt_len(skb)); if ((toks|ptoks) >= 0) { police->tcfp_t_c = now; police->tcfp_toks = toks; police->tcfp_ptoks = ptoks; - if (police->tcfp_result == TC_ACT_SHOT) - police->tcf_qstats.drops++; - spin_unlock(&police->tcf_lock); - return police->tcfp_result; + spin_unlock_bh(&police->tcfp_lock); + ret = p->tcfp_result; + goto inc_drops; } + spin_unlock_bh(&police->tcfp_lock); } - police->tcf_qstats.overlimits++; - if (police->tcf_action == TC_ACT_SHOT) - police->tcf_qstats.drops++; - spin_unlock(&police->tcf_lock); - return police->tcf_action; +inc_overlimits: + qstats_overlimit_inc(this_cpu_ptr(police->common.cpu_qstats)); +inc_drops: + if (ret == TC_ACT_SHOT) + qstats_drop_inc(this_cpu_ptr(police->common.cpu_qstats)); +end: + return ret; +} + +static void tcf_police_cleanup(struct tc_action *a) +{ + struct tcf_police *police = to_police(a); + struct tcf_police_params *p; + + p = rcu_dereference_protected(police->params, 1); + if (p) + kfree_rcu(p, rcu); } static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, @@ -272,6 +310,7 @@ static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, { unsigned char *b = skb_tail_pointer(skb); struct tcf_police *police = to_police(a); + struct tcf_police_params *p; struct tc_police opt = { .index = police->tcf_index, .refcnt = refcount_read(&police->tcf_refcnt) - ref, @@ -281,19 +320,21 @@ static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, spin_lock_bh(&police->tcf_lock); opt.action = police->tcf_action; - opt.mtu = police->tcfp_mtu; - opt.burst = PSCHED_NS2TICKS(police->tcfp_burst); - if (police->rate_present) - psched_ratecfg_getrate(&opt.rate, &police->rate); - if (police->peak_present) - psched_ratecfg_getrate(&opt.peakrate, &police->peak); + p = rcu_dereference_protected(police->params, + lockdep_is_held(&police->tcf_lock)); + opt.mtu = p->tcfp_mtu; + opt.burst = PSCHED_NS2TICKS(p->tcfp_burst); + if (p->rate_present) + psched_ratecfg_getrate(&opt.rate, &p->rate); + if (p->peak_present) + psched_ratecfg_getrate(&opt.peakrate, &p->peak); if (nla_put(skb, TCA_POLICE_TBF, sizeof(opt), &opt)) goto nla_put_failure; - if (police->tcfp_result && - nla_put_u32(skb, TCA_POLICE_RESULT, police->tcfp_result)) + if (p->tcfp_result && + nla_put_u32(skb, TCA_POLICE_RESULT, p->tcfp_result)) goto nla_put_failure; - if (police->tcfp_ewma_rate && - nla_put_u32(skb, TCA_POLICE_AVRATE, police->tcfp_ewma_rate)) + if (p->tcfp_ewma_rate && + nla_put_u32(skb, TCA_POLICE_AVRATE, p->tcfp_ewma_rate)) goto nla_put_failure; t.install = jiffies_to_clock_t(jiffies - police->tcf_tm.install); @@ -312,8 +353,7 @@ nla_put_failure: return -1; } -static int tcf_police_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_police_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, police_net_id); @@ -333,6 +373,7 @@ static struct tc_action_ops act_police_ops = { .init = tcf_police_init, .walk = tcf_police_walker, .lookup = tcf_police_search, + .cleanup = tcf_police_cleanup, .size = sizeof(struct tcf_police), }; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 6b67aa13d2dd..1a0c682fd734 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -224,8 +224,7 @@ static int tcf_sample_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, sample_net_id); diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 52400d49f81f..902957beceb3 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -188,8 +188,7 @@ static int tcf_simp_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, simp_net_id); diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 73e44ce2a883..64dba3708fce 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -99,7 +99,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); - struct tcf_skbedit_params *params_old, *params_new; + struct tcf_skbedit_params *params_new; struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; struct tc_skbedit *parm; struct tcf_skbedit *d; @@ -187,8 +187,6 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, } } - ASSERT_RTNL(); - params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { if (ret == ACT_P_CREATED) @@ -210,11 +208,13 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, if (flags & SKBEDIT_F_MASK) params_new->mask = *mask; + spin_lock_bh(&d->tcf_lock); d->tcf_action = parm->action; - params_old = rtnl_dereference(d->params); - rcu_assign_pointer(d->params, params_new); - if (params_old) - kfree_rcu(params_old, rcu); + rcu_swap_protected(d->params, params_new, + lockdep_is_held(&d->tcf_lock)); + spin_unlock_bh(&d->tcf_lock); + if (params_new) + kfree_rcu(params_new, rcu); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); @@ -231,12 +231,14 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, .index = d->tcf_index, .refcnt = refcount_read(&d->tcf_refcnt) - ref, .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, - .action = d->tcf_action, }; u64 pure_flags = 0; struct tcf_t t; - params = rtnl_dereference(d->params); + spin_lock_bh(&d->tcf_lock); + params = rcu_dereference_protected(d->params, + lockdep_is_held(&d->tcf_lock)); + opt.action = d->tcf_action; if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -264,9 +266,12 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD)) goto nla_put_failure; + spin_unlock_bh(&d->tcf_lock); + return skb->len; nla_put_failure: + spin_unlock_bh(&d->tcf_lock); nlmsg_trim(skb, b); return -1; } @@ -291,8 +296,7 @@ static int tcf_skbedit_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 588077fafd6c..59710a183bd3 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -251,8 +251,7 @@ static int tcf_skbmod_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 681f6f04e7da..c3b90fadaff6 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -210,9 +210,9 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, struct tcf_tunnel_key *t; bool exists = false; __be16 dst_port = 0; + __be64 key_id = 0; int opts_len = 0; - __be64 key_id; - __be16 flags; + __be16 flags = 0; u8 tos, ttl; int ret = 0; int err; @@ -246,15 +246,15 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, case TCA_TUNNEL_KEY_ACT_RELEASE: break; case TCA_TUNNEL_KEY_ACT_SET: - if (!tb[TCA_TUNNEL_KEY_ENC_KEY_ID]) { - NL_SET_ERR_MSG(extack, "Missing tunnel key id"); - ret = -EINVAL; - goto err_out; - } + if (tb[TCA_TUNNEL_KEY_ENC_KEY_ID]) { + __be32 key32; - key_id = key32_to_tunnel_id(nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID])); + key32 = nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID]); + key_id = key32_to_tunnel_id(key32); + flags = TUNNEL_KEY; + } - flags = TUNNEL_KEY | TUNNEL_CSUM; + flags |= TUNNEL_CSUM; if (tb[TCA_TUNNEL_KEY_NO_CSUM] && nla_get_u8(tb[TCA_TUNNEL_KEY_NO_CSUM])) flags &= ~TUNNEL_CSUM; @@ -508,10 +508,13 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, struct ip_tunnel_key *key = &info->key; __be32 key_id = tunnel_id_to_key32(key->tun_id); - if (nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id) || + if (((key->tun_flags & TUNNEL_KEY) && + nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id)) || tunnel_key_dump_addresses(skb, ¶ms->tcft_enc_metadata->u.tun_info) || - nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst) || + (key->tp_dst && + nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, + key->tp_dst)) || nla_put_u8(skb, TCA_TUNNEL_KEY_NO_CSUM, !(key->tun_flags & TUNNEL_CSUM)) || tunnel_key_opts_dump(skb, info)) @@ -548,8 +551,7 @@ static int tunnel_key_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 033d273afe50..93fdaf707313 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -63,7 +63,7 @@ static int tcf_vlan_act(struct sk_buff *skb, const struct tc_action *a, /* extract existing tag (and guarantee no hw-accel tag) */ if (skb_vlan_tag_present(skb)) { tci = skb_vlan_tag_get(skb); - skb->vlan_tci = 0; + __vlan_hwaccel_clear_tag(skb); } else { /* in-payload vlan tag, pop it */ err = __skb_vlan_pop(skb, &tci); @@ -288,8 +288,7 @@ static int tcf_vlan_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, vlan_net_id); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 70f144ac5e1d..8ce2a0507970 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -25,6 +25,7 @@ #include <linux/kmod.h> #include <linux/slab.h> #include <linux/idr.h> +#include <linux/rhashtable.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> @@ -242,8 +243,8 @@ static void tcf_chain_destroy(struct tcf_chain *chain) if (!chain->index) block->chain0.chain = NULL; kfree(chain); - if (list_empty(&block->chain_list) && block->refcnt == 0) - kfree(block); + if (list_empty(&block->chain_list) && !refcount_read(&block->refcnt)) + kfree_rcu(block, rcu); } static void tcf_chain_hold(struct tcf_chain *chain) @@ -365,6 +366,245 @@ static void tcf_chain_flush(struct tcf_chain *chain) } } +static struct tcf_block *tc_dev_ingress_block(struct net_device *dev) +{ + const struct Qdisc_class_ops *cops; + struct Qdisc *qdisc; + + if (!dev_ingress_queue(dev)) + return NULL; + + qdisc = dev_ingress_queue(dev)->qdisc_sleeping; + if (!qdisc) + return NULL; + + cops = qdisc->ops->cl_ops; + if (!cops) + return NULL; + + if (!cops->tcf_block) + return NULL; + + return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL); +} + +static struct rhashtable indr_setup_block_ht; + +struct tc_indr_block_dev { + struct rhash_head ht_node; + struct net_device *dev; + unsigned int refcnt; + struct list_head cb_list; + struct tcf_block *block; +}; + +struct tc_indr_block_cb { + struct list_head list; + void *cb_priv; + tc_indr_block_bind_cb_t *cb; + void *cb_ident; +}; + +static const struct rhashtable_params tc_indr_setup_block_ht_params = { + .key_offset = offsetof(struct tc_indr_block_dev, dev), + .head_offset = offsetof(struct tc_indr_block_dev, ht_node), + .key_len = sizeof(struct net_device *), +}; + +static struct tc_indr_block_dev * +tc_indr_block_dev_lookup(struct net_device *dev) +{ + return rhashtable_lookup_fast(&indr_setup_block_ht, &dev, + tc_indr_setup_block_ht_params); +} + +static struct tc_indr_block_dev *tc_indr_block_dev_get(struct net_device *dev) +{ + struct tc_indr_block_dev *indr_dev; + + indr_dev = tc_indr_block_dev_lookup(dev); + if (indr_dev) + goto inc_ref; + + indr_dev = kzalloc(sizeof(*indr_dev), GFP_KERNEL); + if (!indr_dev) + return NULL; + + INIT_LIST_HEAD(&indr_dev->cb_list); + indr_dev->dev = dev; + indr_dev->block = tc_dev_ingress_block(dev); + if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node, + tc_indr_setup_block_ht_params)) { + kfree(indr_dev); + return NULL; + } + +inc_ref: + indr_dev->refcnt++; + return indr_dev; +} + +static void tc_indr_block_dev_put(struct tc_indr_block_dev *indr_dev) +{ + if (--indr_dev->refcnt) + return; + + rhashtable_remove_fast(&indr_setup_block_ht, &indr_dev->ht_node, + tc_indr_setup_block_ht_params); + kfree(indr_dev); +} + +static struct tc_indr_block_cb * +tc_indr_block_cb_lookup(struct tc_indr_block_dev *indr_dev, + tc_indr_block_bind_cb_t *cb, void *cb_ident) +{ + struct tc_indr_block_cb *indr_block_cb; + + list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) + if (indr_block_cb->cb == cb && + indr_block_cb->cb_ident == cb_ident) + return indr_block_cb; + return NULL; +} + +static struct tc_indr_block_cb * +tc_indr_block_cb_add(struct tc_indr_block_dev *indr_dev, void *cb_priv, + tc_indr_block_bind_cb_t *cb, void *cb_ident) +{ + struct tc_indr_block_cb *indr_block_cb; + + indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident); + if (indr_block_cb) + return ERR_PTR(-EEXIST); + + indr_block_cb = kzalloc(sizeof(*indr_block_cb), GFP_KERNEL); + if (!indr_block_cb) + return ERR_PTR(-ENOMEM); + + indr_block_cb->cb_priv = cb_priv; + indr_block_cb->cb = cb; + indr_block_cb->cb_ident = cb_ident; + list_add(&indr_block_cb->list, &indr_dev->cb_list); + + return indr_block_cb; +} + +static void tc_indr_block_cb_del(struct tc_indr_block_cb *indr_block_cb) +{ + list_del(&indr_block_cb->list); + kfree(indr_block_cb); +} + +static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev, + struct tc_indr_block_cb *indr_block_cb, + enum tc_block_command command) +{ + struct tc_block_offload bo = { + .command = command, + .binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS, + .block = indr_dev->block, + }; + + if (!indr_dev->block) + return; + + indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, + &bo); +} + +int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, + tc_indr_block_bind_cb_t *cb, void *cb_ident) +{ + struct tc_indr_block_cb *indr_block_cb; + struct tc_indr_block_dev *indr_dev; + int err; + + indr_dev = tc_indr_block_dev_get(dev); + if (!indr_dev) + return -ENOMEM; + + indr_block_cb = tc_indr_block_cb_add(indr_dev, cb_priv, cb, cb_ident); + err = PTR_ERR_OR_ZERO(indr_block_cb); + if (err) + goto err_dev_put; + + tc_indr_block_ing_cmd(indr_dev, indr_block_cb, TC_BLOCK_BIND); + return 0; + +err_dev_put: + tc_indr_block_dev_put(indr_dev); + return err; +} +EXPORT_SYMBOL_GPL(__tc_indr_block_cb_register); + +int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, + tc_indr_block_bind_cb_t *cb, void *cb_ident) +{ + int err; + + rtnl_lock(); + err = __tc_indr_block_cb_register(dev, cb_priv, cb, cb_ident); + rtnl_unlock(); + + return err; +} +EXPORT_SYMBOL_GPL(tc_indr_block_cb_register); + +void __tc_indr_block_cb_unregister(struct net_device *dev, + tc_indr_block_bind_cb_t *cb, void *cb_ident) +{ + struct tc_indr_block_cb *indr_block_cb; + struct tc_indr_block_dev *indr_dev; + + indr_dev = tc_indr_block_dev_lookup(dev); + if (!indr_dev) + return; + + indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident); + if (!indr_block_cb) + return; + + /* Send unbind message if required to free any block cbs. */ + tc_indr_block_ing_cmd(indr_dev, indr_block_cb, TC_BLOCK_UNBIND); + tc_indr_block_cb_del(indr_block_cb); + tc_indr_block_dev_put(indr_dev); +} +EXPORT_SYMBOL_GPL(__tc_indr_block_cb_unregister); + +void tc_indr_block_cb_unregister(struct net_device *dev, + tc_indr_block_bind_cb_t *cb, void *cb_ident) +{ + rtnl_lock(); + __tc_indr_block_cb_unregister(dev, cb, cb_ident); + rtnl_unlock(); +} +EXPORT_SYMBOL_GPL(tc_indr_block_cb_unregister); + +static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev, + struct tcf_block_ext_info *ei, + enum tc_block_command command, + struct netlink_ext_ack *extack) +{ + struct tc_indr_block_cb *indr_block_cb; + struct tc_indr_block_dev *indr_dev; + struct tc_block_offload bo = { + .command = command, + .binder_type = ei->binder_type, + .block = block, + .extack = extack, + }; + + indr_dev = tc_indr_block_dev_lookup(dev); + if (!indr_dev) + return; + + indr_dev->block = command == TC_BLOCK_BIND ? block : NULL; + + list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) + indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, + &bo); +} + static bool tcf_block_offload_in_use(struct tcf_block *block) { return block->offloadcnt; @@ -406,12 +646,17 @@ static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND, extack); if (err == -EOPNOTSUPP) goto no_offload_dev_inc; - return err; + if (err) + return err; + + tc_indr_block_call(block, dev, ei, TC_BLOCK_BIND, extack); + return 0; no_offload_dev_inc: if (tcf_block_offload_in_use(block)) return -EOPNOTSUPP; block->nooffloaddevcnt++; + tc_indr_block_call(block, dev, ei, TC_BLOCK_BIND, extack); return 0; } @@ -421,6 +666,8 @@ static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q, struct net_device *dev = q->dev_queue->dev; int err; + tc_indr_block_call(block, dev, ei, TC_BLOCK_UNBIND, NULL); + if (!dev->netdev_ops->ndo_setup_tc) goto no_offload_dev_dec; err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND, NULL); @@ -475,6 +722,7 @@ tcf_chain0_head_change_cb_del(struct tcf_block *block, } struct tcf_net { + spinlock_t idr_lock; /* Protects idr */ struct idr idr; }; @@ -484,16 +732,25 @@ static int tcf_block_insert(struct tcf_block *block, struct net *net, struct netlink_ext_ack *extack) { struct tcf_net *tn = net_generic(net, tcf_net_id); + int err; + + idr_preload(GFP_KERNEL); + spin_lock(&tn->idr_lock); + err = idr_alloc_u32(&tn->idr, block, &block->index, block->index, + GFP_NOWAIT); + spin_unlock(&tn->idr_lock); + idr_preload_end(); - return idr_alloc_u32(&tn->idr, block, &block->index, block->index, - GFP_KERNEL); + return err; } static void tcf_block_remove(struct tcf_block *block, struct net *net) { struct tcf_net *tn = net_generic(net, tcf_net_id); + spin_lock(&tn->idr_lock); idr_remove(&tn->idr, block->index); + spin_unlock(&tn->idr_lock); } static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, @@ -512,7 +769,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, INIT_LIST_HEAD(&block->owner_list); INIT_LIST_HEAD(&block->chain0.filter_chain_list); - block->refcnt = 1; + refcount_set(&block->refcnt, 1); block->net = net; block->index = block_index; @@ -529,6 +786,78 @@ static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index) return idr_find(&tn->idr, block_index); } +static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index) +{ + struct tcf_block *block; + + rcu_read_lock(); + block = tcf_block_lookup(net, block_index); + if (block && !refcount_inc_not_zero(&block->refcnt)) + block = NULL; + rcu_read_unlock(); + + return block; +} + +static void tcf_block_flush_all_chains(struct tcf_block *block) +{ + struct tcf_chain *chain; + + /* Hold a refcnt for all chains, so that they don't disappear + * while we are iterating. + */ + list_for_each_entry(chain, &block->chain_list, list) + tcf_chain_hold(chain); + + list_for_each_entry(chain, &block->chain_list, list) + tcf_chain_flush(chain); +} + +static void tcf_block_put_all_chains(struct tcf_block *block) +{ + struct tcf_chain *chain, *tmp; + + /* At this point, all the chains should have refcnt >= 1. */ + list_for_each_entry_safe(chain, tmp, &block->chain_list, list) { + tcf_chain_put_explicitly_created(chain); + tcf_chain_put(chain); + } +} + +static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei) +{ + if (refcount_dec_and_test(&block->refcnt)) { + /* Flushing/putting all chains will cause the block to be + * deallocated when last chain is freed. However, if chain_list + * is empty, block has to be manually deallocated. After block + * reference counter reached 0, it is no longer possible to + * increment it or add new chains to block. + */ + bool free_block = list_empty(&block->chain_list); + + if (tcf_block_shared(block)) + tcf_block_remove(block, block->net); + if (!free_block) + tcf_block_flush_all_chains(block); + + if (q) + tcf_block_offload_unbind(block, q, ei); + + if (free_block) + kfree_rcu(block, rcu); + else + tcf_block_put_all_chains(block); + } else if (q) { + tcf_block_offload_unbind(block, q, ei); + } +} + +static void tcf_block_refcnt_put(struct tcf_block *block) +{ + __tcf_block_put(block, NULL, NULL); +} + /* Find tcf block. * Set q, parent, cl when appropriate. */ @@ -539,9 +868,10 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, struct netlink_ext_ack *extack) { struct tcf_block *block; + int err = 0; if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) { - block = tcf_block_lookup(net, block_index); + block = tcf_block_refcnt_get(net, block_index); if (!block) { NL_SET_ERR_MSG(extack, "Block of given index was not found"); return ERR_PTR(-EINVAL); @@ -550,55 +880,106 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, const struct Qdisc_class_ops *cops; struct net_device *dev; + rcu_read_lock(); + /* Find link */ - dev = __dev_get_by_index(net, ifindex); - if (!dev) + dev = dev_get_by_index_rcu(net, ifindex); + if (!dev) { + rcu_read_unlock(); return ERR_PTR(-ENODEV); + } /* Find qdisc */ if (!*parent) { *q = dev->qdisc; *parent = (*q)->handle; } else { - *q = qdisc_lookup(dev, TC_H_MAJ(*parent)); + *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent)); if (!*q) { NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); - return ERR_PTR(-EINVAL); + err = -EINVAL; + goto errout_rcu; } } + *q = qdisc_refcount_inc_nz(*q); + if (!*q) { + NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); + err = -EINVAL; + goto errout_rcu; + } + /* Is it classful? */ cops = (*q)->ops->cl_ops; if (!cops) { NL_SET_ERR_MSG(extack, "Qdisc not classful"); - return ERR_PTR(-EINVAL); + err = -EINVAL; + goto errout_rcu; } if (!cops->tcf_block) { NL_SET_ERR_MSG(extack, "Class doesn't support blocks"); - return ERR_PTR(-EOPNOTSUPP); + err = -EOPNOTSUPP; + goto errout_rcu; } + /* At this point we know that qdisc is not noop_qdisc, + * which means that qdisc holds a reference to net_device + * and we hold a reference to qdisc, so it is safe to release + * rcu read lock. + */ + rcu_read_unlock(); + /* Do we search for filter, attached to class? */ if (TC_H_MIN(*parent)) { *cl = cops->find(*q, *parent); if (*cl == 0) { NL_SET_ERR_MSG(extack, "Specified class doesn't exist"); - return ERR_PTR(-ENOENT); + err = -ENOENT; + goto errout_qdisc; } } /* And the last stroke */ block = cops->tcf_block(*q, *cl, extack); - if (!block) - return ERR_PTR(-EINVAL); + if (!block) { + err = -EINVAL; + goto errout_qdisc; + } if (tcf_block_shared(block)) { NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters"); - return ERR_PTR(-EOPNOTSUPP); + err = -EOPNOTSUPP; + goto errout_qdisc; } + + /* Always take reference to block in order to support execution + * of rules update path of cls API without rtnl lock. Caller + * must release block when it is finished using it. 'if' block + * of this conditional obtain reference to block by calling + * tcf_block_refcnt_get(). + */ + refcount_inc(&block->refcnt); } return block; + +errout_rcu: + rcu_read_unlock(); +errout_qdisc: + if (*q) { + qdisc_put(*q); + *q = NULL; + } + return ERR_PTR(err); +} + +static void tcf_block_release(struct Qdisc *q, struct tcf_block *block) +{ + if (!IS_ERR_OR_NULL(block)) + tcf_block_refcnt_put(block); + + if (q) + qdisc_put(q); } struct tcf_block_owner_item { @@ -666,21 +1047,16 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, { struct net *net = qdisc_net(q); struct tcf_block *block = NULL; - bool created = false; int err; - if (ei->block_index) { + if (ei->block_index) /* block_index not 0 means the shared block is requested */ - block = tcf_block_lookup(net, ei->block_index); - if (block) - block->refcnt++; - } + block = tcf_block_refcnt_get(net, ei->block_index); if (!block) { block = tcf_block_create(net, q, ei->block_index, extack); if (IS_ERR(block)) return PTR_ERR(block); - created = true; if (tcf_block_shared(block)) { err = tcf_block_insert(block, net, extack); if (err) @@ -710,14 +1086,8 @@ err_block_offload_bind: err_chain0_head_change_cb_add: tcf_block_owner_del(block, q, ei->binder_type); err_block_owner_add: - if (created) { - if (tcf_block_shared(block)) - tcf_block_remove(block, net); err_block_insert: - kfree(block); - } else { - block->refcnt--; - } + tcf_block_refcnt_put(block); return err; } EXPORT_SYMBOL(tcf_block_get_ext); @@ -749,42 +1119,12 @@ EXPORT_SYMBOL(tcf_block_get); void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, struct tcf_block_ext_info *ei) { - struct tcf_chain *chain, *tmp; - if (!block) return; tcf_chain0_head_change_cb_del(block, ei); tcf_block_owner_del(block, q, ei->binder_type); - if (block->refcnt == 1) { - if (tcf_block_shared(block)) - tcf_block_remove(block, block->net); - - /* Hold a refcnt for all chains, so that they don't disappear - * while we are iterating. - */ - list_for_each_entry(chain, &block->chain_list, list) - tcf_chain_hold(chain); - - list_for_each_entry(chain, &block->chain_list, list) - tcf_chain_flush(chain); - } - - tcf_block_offload_unbind(block, q, ei); - - if (block->refcnt == 1) { - /* At this point, all the chains should have refcnt >= 1. */ - list_for_each_entry_safe(chain, tmp, &block->chain_list, list) { - tcf_chain_put_explicitly_created(chain); - tcf_chain_put(chain); - } - - block->refcnt--; - if (list_empty(&block->chain_list)) - kfree(block); - } else { - block->refcnt--; - } + __tcf_block_put(block, q, ei); } EXPORT_SYMBOL(tcf_block_put_ext); @@ -930,29 +1270,6 @@ void tcf_block_cb_unregister(struct tcf_block *block, } EXPORT_SYMBOL(tcf_block_cb_unregister); -static int tcf_block_cb_call(struct tcf_block *block, enum tc_setup_type type, - void *type_data, bool err_stop) -{ - struct tcf_block_cb *block_cb; - int ok_count = 0; - int err; - - /* Make sure all netdevs sharing this block are offload-capable. */ - if (block->nooffloaddevcnt && err_stop) - return -EOPNOTSUPP; - - list_for_each_entry(block_cb, &block->cb_list, list) { - err = block_cb->cb(type, type_data, block_cb->cb_priv); - if (err) { - if (err_stop) - return err; - } else { - ok_count++; - } - } - return ok_count; -} - /* Main classifier routine: scans classifier chain attached * to this qdisc, (optionally) tests for protocol and asks * specific classifiers. @@ -1334,6 +1651,7 @@ replay: errout: if (chain) tcf_chain_put(chain); + tcf_block_release(q, block); if (err == -EAGAIN) /* Replay the request. */ goto replay; @@ -1455,6 +1773,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, errout: if (chain) tcf_chain_put(chain); + tcf_block_release(q, block); return err; } @@ -1540,6 +1859,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, errout: if (chain) tcf_chain_put(chain); + tcf_block_release(q, block); return err; } @@ -1633,12 +1953,13 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (nlmsg_len(cb->nlh) < sizeof(*tcm)) return skb->len; - err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL); + err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, + cb->extack); if (err) return err; if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) { - block = tcf_block_lookup(net, tcm->tcm_block_index); + block = tcf_block_refcnt_get(net, tcm->tcm_block_index); if (!block) goto out; /* If we work with block index, q is NULL and parent value @@ -1697,6 +2018,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) } } + if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) + tcf_block_refcnt_put(block); cb->args[0] = index; out: @@ -1856,7 +2179,8 @@ replay: chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; if (chain_index > TC_ACT_EXT_VAL_MASK) { NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); - return -EINVAL; + err = -EINVAL; + goto errout_block; } chain = tcf_chain_lookup(block, chain_index); if (n->nlmsg_type == RTM_NEWCHAIN) { @@ -1868,23 +2192,27 @@ replay: tcf_chain_hold(chain); } else { NL_SET_ERR_MSG(extack, "Filter chain already exists"); - return -EEXIST; + err = -EEXIST; + goto errout_block; } } else { if (!(n->nlmsg_flags & NLM_F_CREATE)) { NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain"); - return -ENOENT; + err = -ENOENT; + goto errout_block; } chain = tcf_chain_create(block, chain_index); if (!chain) { NL_SET_ERR_MSG(extack, "Failed to create filter chain"); - return -ENOMEM; + err = -ENOMEM; + goto errout_block; } } } else { if (!chain || tcf_chain_held_by_acts_only(chain)) { NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); - return -EINVAL; + err = -EINVAL; + goto errout_block; } tcf_chain_hold(chain); } @@ -1928,6 +2256,8 @@ replay: errout: tcf_chain_put(chain); +errout_block: + tcf_block_release(q, block); if (err == -EAGAIN) /* Replay the request. */ goto replay; @@ -1952,12 +2282,12 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, - NULL); + cb->extack); if (err) return err; if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) { - block = tcf_block_lookup(net, tcm->tcm_block_index); + block = tcf_block_refcnt_get(net, tcm->tcm_block_index); if (!block) goto out; /* If we work with block index, q is NULL and parent value @@ -2024,6 +2354,8 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) index++; } + if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) + tcf_block_refcnt_put(block); cb->args[0] = index; out: @@ -2160,54 +2492,26 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts) } EXPORT_SYMBOL(tcf_exts_dump_stats); -static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts, - enum tc_setup_type type, - void *type_data, bool err_stop) +int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, + void *type_data, bool err_stop) { + struct tcf_block_cb *block_cb; int ok_count = 0; -#ifdef CONFIG_NET_CLS_ACT - const struct tc_action *a; - struct net_device *dev; - int i, ret; + int err; - if (!tcf_exts_has_actions(exts)) - return 0; + /* Make sure all netdevs sharing this block are offload-capable. */ + if (block->nooffloaddevcnt && err_stop) + return -EOPNOTSUPP; - for (i = 0; i < exts->nr_actions; i++) { - a = exts->actions[i]; - if (!a->ops->get_dev) - continue; - dev = a->ops->get_dev(a); - if (!dev) - continue; - ret = tc_setup_cb_egdev_call(dev, type, type_data, err_stop); - a->ops->put_dev(dev); - if (ret < 0) - return ret; - ok_count += ret; + list_for_each_entry(block_cb, &block->cb_list, list) { + err = block_cb->cb(type, type_data, block_cb->cb_priv); + if (err) { + if (err_stop) + return err; + } else { + ok_count++; + } } -#endif - return ok_count; -} - -int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts, - enum tc_setup_type type, void *type_data, bool err_stop) -{ - int ok_count; - int ret; - - ret = tcf_block_cb_call(block, type, type_data, err_stop); - if (ret < 0) - return ret; - ok_count = ret; - - if (!exts || ok_count) - return ok_count; - ret = tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop); - if (ret < 0) - return ret; - ok_count += ret; - return ok_count; } EXPORT_SYMBOL(tc_setup_cb_call); @@ -2216,6 +2520,7 @@ static __net_init int tcf_net_init(struct net *net) { struct tcf_net *tn = net_generic(net, tcf_net_id); + spin_lock_init(&tn->idr_lock); idr_init(&tn->idr); return 0; } @@ -2246,6 +2551,11 @@ static int __init tc_filter_init(void) if (err) goto err_register_pernet_subsys; + err = rhashtable_init(&indr_setup_block_ht, + &tc_indr_setup_block_ht_params); + if (err) + goto err_rhash_setup_block_ht; + rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter, @@ -2257,6 +2567,8 @@ static int __init tc_filter_init(void) return 0; +err_rhash_setup_block_ht: + unregister_pernet_subsys(&tcf_net_ops); err_register_pernet_subsys: destroy_workqueue(tc_filter_wq); return err; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index fa6fe2fe0f32..a95cb240a606 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -169,7 +169,7 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, if (oldprog) tcf_block_offload_dec(block, &oldprog->gen_flags); - err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, skip_sw); + err = tc_setup_cb_call(block, TC_SETUP_CLSBPF, &cls_bpf, skip_sw); if (prog) { if (err < 0) { cls_bpf_offload_cmd(tp, oldprog, prog, extack); @@ -234,7 +234,7 @@ static void cls_bpf_offload_update_stats(struct tcf_proto *tp, cls_bpf.name = prog->bpf_name; cls_bpf.exts_integrated = prog->exts_integrated; - tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, false); + tc_setup_cb_call(block, TC_SETUP_CLSBPF, &cls_bpf, false); } static int cls_bpf_init(struct tcf_proto *tp) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 6fd9bdd93796..dad04e710493 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -55,6 +55,8 @@ struct fl_flow_key { struct flow_dissector_key_ip ip; struct flow_dissector_key_ip enc_ip; struct flow_dissector_key_enc_opts enc_opts; + struct flow_dissector_key_ports tp_min; + struct flow_dissector_key_ports tp_max; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct fl_flow_mask_range { @@ -65,6 +67,7 @@ struct fl_flow_mask_range { struct fl_flow_mask { struct fl_flow_key key; struct fl_flow_mask_range range; + u32 flags; struct rhash_head ht_node; struct rhashtable ht; struct rhashtable_params filter_ht_params; @@ -98,7 +101,7 @@ struct cls_fl_filter { struct list_head list; u32 handle; u32 flags; - unsigned int in_hw_count; + u32 in_hw_count; struct rcu_work rwork; struct net_device *hw_dev; }; @@ -179,13 +182,89 @@ static void fl_clear_masked_range(struct fl_flow_key *key, memset(fl_key_get_start(key, mask), 0, fl_mask_range(mask)); } -static struct cls_fl_filter *fl_lookup(struct fl_flow_mask *mask, - struct fl_flow_key *mkey) +static bool fl_range_port_dst_cmp(struct cls_fl_filter *filter, + struct fl_flow_key *key, + struct fl_flow_key *mkey) +{ + __be16 min_mask, max_mask, min_val, max_val; + + min_mask = htons(filter->mask->key.tp_min.dst); + max_mask = htons(filter->mask->key.tp_max.dst); + min_val = htons(filter->key.tp_min.dst); + max_val = htons(filter->key.tp_max.dst); + + if (min_mask && max_mask) { + if (htons(key->tp.dst) < min_val || + htons(key->tp.dst) > max_val) + return false; + + /* skb does not have min and max values */ + mkey->tp_min.dst = filter->mkey.tp_min.dst; + mkey->tp_max.dst = filter->mkey.tp_max.dst; + } + return true; +} + +static bool fl_range_port_src_cmp(struct cls_fl_filter *filter, + struct fl_flow_key *key, + struct fl_flow_key *mkey) +{ + __be16 min_mask, max_mask, min_val, max_val; + + min_mask = htons(filter->mask->key.tp_min.src); + max_mask = htons(filter->mask->key.tp_max.src); + min_val = htons(filter->key.tp_min.src); + max_val = htons(filter->key.tp_max.src); + + if (min_mask && max_mask) { + if (htons(key->tp.src) < min_val || + htons(key->tp.src) > max_val) + return false; + + /* skb does not have min and max values */ + mkey->tp_min.src = filter->mkey.tp_min.src; + mkey->tp_max.src = filter->mkey.tp_max.src; + } + return true; +} + +static struct cls_fl_filter *__fl_lookup(struct fl_flow_mask *mask, + struct fl_flow_key *mkey) { return rhashtable_lookup_fast(&mask->ht, fl_key_get_start(mkey, mask), mask->filter_ht_params); } +static struct cls_fl_filter *fl_lookup_range(struct fl_flow_mask *mask, + struct fl_flow_key *mkey, + struct fl_flow_key *key) +{ + struct cls_fl_filter *filter, *f; + + list_for_each_entry_rcu(filter, &mask->filters, list) { + if (!fl_range_port_dst_cmp(filter, key, mkey)) + continue; + + if (!fl_range_port_src_cmp(filter, key, mkey)) + continue; + + f = __fl_lookup(mask, mkey); + if (f) + return f; + } + return NULL; +} + +static struct cls_fl_filter *fl_lookup(struct fl_flow_mask *mask, + struct fl_flow_key *mkey, + struct fl_flow_key *key) +{ + if ((mask->flags & TCA_FLOWER_MASK_FLAGS_RANGE)) + return fl_lookup_range(mask, mkey, key); + + return __fl_lookup(mask, mkey); +} + static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { @@ -208,7 +287,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, fl_set_masked_key(&skb_mkey, &skb_key, mask); - f = fl_lookup(mask, &skb_mkey); + f = fl_lookup(mask, &skb_mkey, &skb_key); if (f && !tc_skip_sw(f->flags)) { *res = f->res; return tcf_exts_exec(skb, &f->exts, res); @@ -289,8 +368,7 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f, cls_flower.command = TC_CLSFLOWER_DESTROY; cls_flower.cookie = (unsigned long) f; - tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER, - &cls_flower, false); + tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); tcf_block_offload_dec(block, &f->flags); } @@ -312,8 +390,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, cls_flower.exts = &f->exts; cls_flower.classid = f->res.classid; - err = tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER, - &cls_flower, skip_sw); + err = tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, skip_sw); if (err < 0) { fl_hw_destroy_filter(tp, f, NULL); return err; @@ -339,8 +416,7 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) cls_flower.exts = &f->exts; cls_flower.classid = f->res.classid; - tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER, - &cls_flower, false); + tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); } static bool __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, @@ -514,6 +590,31 @@ static void fl_set_key_val(struct nlattr **tb, memcpy(mask, nla_data(tb[mask_type]), len); } +static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key, + struct fl_flow_key *mask) +{ + fl_set_key_val(tb, &key->tp_min.dst, + TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_min.dst, + TCA_FLOWER_UNSPEC, sizeof(key->tp_min.dst)); + fl_set_key_val(tb, &key->tp_max.dst, + TCA_FLOWER_KEY_PORT_DST_MAX, &mask->tp_max.dst, + TCA_FLOWER_UNSPEC, sizeof(key->tp_max.dst)); + fl_set_key_val(tb, &key->tp_min.src, + TCA_FLOWER_KEY_PORT_SRC_MIN, &mask->tp_min.src, + TCA_FLOWER_UNSPEC, sizeof(key->tp_min.src)); + fl_set_key_val(tb, &key->tp_max.src, + TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_max.src, + TCA_FLOWER_UNSPEC, sizeof(key->tp_max.src)); + + if ((mask->tp_min.dst && mask->tp_max.dst && + htons(key->tp_max.dst) <= htons(key->tp_min.dst)) || + (mask->tp_min.src && mask->tp_max.src && + htons(key->tp_max.src) <= htons(key->tp_min.src))) + return -EINVAL; + + return 0; +} + static int fl_set_key_mpls(struct nlattr **tb, struct flow_dissector_key_mpls *key_val, struct flow_dissector_key_mpls *key_mask) @@ -709,11 +810,23 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, struct netlink_ext_ack *extack) { const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL; - int option_len, key_depth, msk_depth = 0; + int err, option_len, key_depth, msk_depth = 0; + + err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS], + TCA_FLOWER_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]); if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) { + err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK], + TCA_FLOWER_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; + nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); } @@ -909,6 +1022,14 @@ static int fl_set_key(struct net *net, struct nlattr **tb, sizeof(key->arp.tha)); } + if (key->basic.ip_proto == IPPROTO_TCP || + key->basic.ip_proto == IPPROTO_UDP || + key->basic.ip_proto == IPPROTO_SCTP) { + ret = fl_set_key_port_range(tb, key, mask); + if (ret) + return ret; + } + if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] || tb[TCA_FLOWER_KEY_ENC_IPV4_DST]) { key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; @@ -993,7 +1114,7 @@ static int fl_init_mask_hashtable(struct fl_flow_mask *mask) } #define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member) -#define FL_KEY_MEMBER_SIZE(member) (sizeof(((struct fl_flow_key *) 0)->member)) +#define FL_KEY_MEMBER_SIZE(member) FIELD_SIZEOF(struct fl_flow_key, member) #define FL_KEY_IS_MASKED(mask, member) \ memchr_inv(((char *)mask) + FL_KEY_MEMBER_OFFSET(member), \ @@ -1026,8 +1147,9 @@ static void fl_init_dissector(struct flow_dissector *dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6); - FL_KEY_SET_IF_MASKED(mask, keys, cnt, - FLOW_DISSECTOR_KEY_PORTS, tp); + if (FL_KEY_IS_MASKED(mask, tp) || + FL_KEY_IS_MASKED(mask, tp_min) || FL_KEY_IS_MASKED(mask, tp_max)) + FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_PORTS, tp); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_IP, ip); FL_KEY_SET_IF_MASKED(mask, keys, cnt, @@ -1074,6 +1196,10 @@ static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head, fl_mask_copy(newmask, mask); + if ((newmask->key.tp_min.dst && newmask->key.tp_max.dst) || + (newmask->key.tp_min.src && newmask->key.tp_max.src)) + newmask->flags |= TCA_FLOWER_MASK_FLAGS_RANGE; + err = fl_init_mask_hashtable(newmask); if (err) goto errout_free; @@ -1226,18 +1352,16 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (err) goto errout_idr; - if (!tc_skip_sw(fnew->flags)) { - if (!fold && fl_lookup(fnew->mask, &fnew->mkey)) { - err = -EEXIST; - goto errout_mask; - } - - err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node, - fnew->mask->filter_ht_params); - if (err) - goto errout_mask; + if (!fold && __fl_lookup(fnew->mask, &fnew->mkey)) { + err = -EEXIST; + goto errout_mask; } + err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node, + fnew->mask->filter_ht_params); + if (err) + goto errout_mask; + if (!tc_skip_hw(fnew->flags)) { err = fl_hw_replace_filter(tp, fnew, extack); if (err) @@ -1248,10 +1372,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, fnew->flags |= TCA_CLS_FLAGS_NOT_IN_HW; if (fold) { - if (!tc_skip_sw(fold->flags)) - rhashtable_remove_fast(&fold->mask->ht, - &fold->ht_node, - fold->mask->filter_ht_params); + rhashtable_remove_fast(&fold->mask->ht, + &fold->ht_node, + fold->mask->filter_ht_params); if (!tc_skip_hw(fold->flags)) fl_hw_destroy_filter(tp, fold, NULL); } @@ -1291,9 +1414,8 @@ static int fl_delete(struct tcf_proto *tp, void *arg, bool *last, struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f = arg; - if (!tc_skip_sw(f->flags)) - rhashtable_remove_fast(&f->mask->ht, &f->ht_node, - f->mask->filter_ht_params); + rhashtable_remove_fast(&f->mask->ht, &f->ht_node, + f->mask->filter_ht_params); __fl_delete(tp, f, extack); *last = list_empty(&head->masks); return 0; @@ -1376,8 +1498,7 @@ static void fl_hw_create_tmplt(struct tcf_chain *chain, /* We don't care if driver (any of them) fails to handle this * call. It serves just as a hint for it. */ - tc_setup_cb_call(block, NULL, TC_SETUP_CLSFLOWER, - &cls_flower, false); + tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); } static void fl_hw_destroy_tmplt(struct tcf_chain *chain, @@ -1390,8 +1511,7 @@ static void fl_hw_destroy_tmplt(struct tcf_chain *chain, cls_flower.command = TC_CLSFLOWER_TMPLT_DESTROY; cls_flower.cookie = (unsigned long) tmplt; - tc_setup_cb_call(block, NULL, TC_SETUP_CLSFLOWER, - &cls_flower, false); + tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); } static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain, @@ -1464,6 +1584,26 @@ static int fl_dump_key_val(struct sk_buff *skb, return 0; } +static int fl_dump_key_port_range(struct sk_buff *skb, struct fl_flow_key *key, + struct fl_flow_key *mask) +{ + if (fl_dump_key_val(skb, &key->tp_min.dst, TCA_FLOWER_KEY_PORT_DST_MIN, + &mask->tp_min.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp_min.dst)) || + fl_dump_key_val(skb, &key->tp_max.dst, TCA_FLOWER_KEY_PORT_DST_MAX, + &mask->tp_max.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp_max.dst)) || + fl_dump_key_val(skb, &key->tp_min.src, TCA_FLOWER_KEY_PORT_SRC_MIN, + &mask->tp_min.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp_min.src)) || + fl_dump_key_val(skb, &key->tp_max.src, TCA_FLOWER_KEY_PORT_SRC_MAX, + &mask->tp_max.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp_max.src))) + return -1; + + return 0; +} + static int fl_dump_key_mpls(struct sk_buff *skb, struct flow_dissector_key_mpls *mpls_key, struct flow_dissector_key_mpls *mpls_mask) @@ -1800,6 +1940,12 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, sizeof(key->arp.tha)))) goto nla_put_failure; + if ((key->basic.ip_proto == IPPROTO_TCP || + key->basic.ip_proto == IPPROTO_UDP || + key->basic.ip_proto == IPPROTO_SCTP) && + fl_dump_key_port_range(skb, key, mask)) + goto nla_put_failure; + if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS && (fl_dump_key_val(skb, &key->enc_ipv4.src, TCA_FLOWER_KEY_ENC_IPV4_SRC, &mask->enc_ipv4.src, @@ -1880,6 +2026,9 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, if (f->flags && nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags)) goto nla_put_failure; + if (nla_put_u32(skb, TCA_FLOWER_IN_HW_COUNT, f->in_hw_count)) + goto nla_put_failure; + if (tcf_exts_dump(skb, &f->exts)) goto nla_put_failure; diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 856fa79d4ffd..0e408ee9dcec 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -71,7 +71,7 @@ static void mall_destroy_hw_filter(struct tcf_proto *tp, cls_mall.command = TC_CLSMATCHALL_DESTROY; cls_mall.cookie = cookie; - tc_setup_cb_call(block, NULL, TC_SETUP_CLSMATCHALL, &cls_mall, false); + tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, false); tcf_block_offload_dec(block, &head->flags); } @@ -90,8 +90,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, cls_mall.exts = &head->exts; cls_mall.cookie = cookie; - err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSMATCHALL, - &cls_mall, skip_sw); + err = tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, skip_sw); if (err < 0) { mall_destroy_hw_filter(tp, head, cookie, NULL); return err; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index b2c3406a2cf2..dcea21004604 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -68,7 +68,6 @@ struct tc_u_knode { u32 mask; u32 __percpu *pcpu_success; #endif - struct tcf_proto *tp; struct rcu_work rwork; /* The 'sel' field MUST be the last field in structure to allow for * tc_u32_keys allocated at end of structure. @@ -80,10 +79,10 @@ struct tc_u_hnode { struct tc_u_hnode __rcu *next; u32 handle; u32 prio; - struct tc_u_common *tp_c; int refcnt; unsigned int divisor; struct idr handle_idr; + bool is_root; struct rcu_head rcu; u32 flags; /* The 'ht' field MUST be the last field in structure to allow for @@ -98,7 +97,7 @@ struct tc_u_common { int refcnt; struct idr handle_idr; struct hlist_node hnode; - struct rcu_head rcu; + long knodes; }; static inline unsigned int u32_hash_fold(__be32 key, @@ -344,19 +343,16 @@ static void *tc_u_common_ptr(const struct tcf_proto *tp) return block->q; } -static unsigned int tc_u_hash(const struct tcf_proto *tp) +static struct hlist_head *tc_u_hash(void *key) { - return hash_ptr(tc_u_common_ptr(tp), U32_HASH_SHIFT); + return tc_u_common_hash + hash_ptr(key, U32_HASH_SHIFT); } -static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp) +static struct tc_u_common *tc_u_common_find(void *key) { struct tc_u_common *tc; - unsigned int h; - - h = tc_u_hash(tp); - hlist_for_each_entry(tc, &tc_u_common_hash[h], hnode) { - if (tc->ptr == tc_u_common_ptr(tp)) + hlist_for_each_entry(tc, tc_u_hash(key), hnode) { + if (tc->ptr == key) return tc; } return NULL; @@ -365,10 +361,8 @@ static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp) static int u32_init(struct tcf_proto *tp) { struct tc_u_hnode *root_ht; - struct tc_u_common *tp_c; - unsigned int h; - - tp_c = tc_u_common_find(tp); + void *key = tc_u_common_ptr(tp); + struct tc_u_common *tp_c = tc_u_common_find(key); root_ht = kzalloc(sizeof(*root_ht), GFP_KERNEL); if (root_ht == NULL) @@ -377,6 +371,7 @@ static int u32_init(struct tcf_proto *tp) root_ht->refcnt++; root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : 0x80000000; root_ht->prio = tp->prio; + root_ht->is_root = true; idr_init(&root_ht->handle_idr); if (tp_c == NULL) { @@ -385,18 +380,16 @@ static int u32_init(struct tcf_proto *tp) kfree(root_ht); return -ENOBUFS; } - tp_c->ptr = tc_u_common_ptr(tp); + tp_c->ptr = key; INIT_HLIST_NODE(&tp_c->hnode); idr_init(&tp_c->handle_idr); - h = tc_u_hash(tp); - hlist_add_head(&tp_c->hnode, &tc_u_common_hash[h]); + hlist_add_head(&tp_c->hnode, tc_u_hash(key)); } tp_c->refcnt++; RCU_INIT_POINTER(root_ht->next, tp_c->hlist); rcu_assign_pointer(tp_c->hlist, root_ht); - root_ht->tp_c = tp_c; root_ht->refcnt++; rcu_assign_pointer(tp->root, root_ht); @@ -404,8 +397,7 @@ static int u32_init(struct tcf_proto *tp) return 0; } -static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n, - bool free_pf) +static int u32_destroy_key(struct tc_u_knode *n, bool free_pf) { struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); @@ -439,7 +431,7 @@ static void u32_delete_key_work(struct work_struct *work) struct tc_u_knode, rwork); rtnl_lock(); - u32_destroy_key(key->tp, key, false); + u32_destroy_key(key, false); rtnl_unlock(); } @@ -456,12 +448,13 @@ static void u32_delete_key_freepf_work(struct work_struct *work) struct tc_u_knode, rwork); rtnl_lock(); - u32_destroy_key(key->tp, key, true); + u32_destroy_key(key, true); rtnl_unlock(); } static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) { + struct tc_u_common *tp_c = tp->data; struct tc_u_knode __rcu **kp; struct tc_u_knode *pkp; struct tc_u_hnode *ht = rtnl_dereference(key->ht_up); @@ -472,6 +465,7 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) kp = &pkp->next, pkp = rtnl_dereference(*kp)) { if (pkp == key) { RCU_INIT_POINTER(*kp, key->next); + tp_c->knodes--; tcf_unbind_filter(tp, &key->res); idr_remove(&ht->handle_idr, key->handle); @@ -497,7 +491,7 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, cls_u32.hnode.handle = h->handle; cls_u32.hnode.prio = h->prio; - tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, false); + tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, false); } static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, @@ -515,7 +509,7 @@ static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, cls_u32.hnode.handle = h->handle; cls_u32.hnode.prio = h->prio; - err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw); + err = tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, skip_sw); if (err < 0) { u32_clear_hw_hnode(tp, h, NULL); return err; @@ -539,7 +533,7 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, cls_u32.command = TC_CLSU32_DELETE_KNODE; cls_u32.knode.handle = n->handle; - tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, false); + tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, false); tcf_block_offload_dec(block, &n->flags); } @@ -564,11 +558,12 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, cls_u32.knode.mask = 0; #endif cls_u32.knode.sel = &n->sel; + cls_u32.knode.res = &n->res; cls_u32.knode.exts = &n->exts; if (n->ht_down) cls_u32.knode.link_handle = ht->handle; - err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw); + err = tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, skip_sw); if (err < 0) { u32_remove_hw_knode(tp, n, NULL); return err; @@ -586,6 +581,7 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, struct netlink_ext_ack *extack) { + struct tc_u_common *tp_c = tp->data; struct tc_u_knode *n; unsigned int h; @@ -593,13 +589,14 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, while ((n = rtnl_dereference(ht->ht[h])) != NULL) { RCU_INIT_POINTER(ht->ht[h], rtnl_dereference(n->next)); + tp_c->knodes--; tcf_unbind_filter(tp, &n->res); u32_remove_hw_knode(tp, n, extack); idr_remove(&ht->handle_idr, n->handle); if (tcf_exts_get_net(&n->exts)) tcf_queue_work(&n->rwork, u32_delete_key_freepf_work); else - u32_destroy_key(n->tp, n, true); + u32_destroy_key(n, true); } } } @@ -632,17 +629,6 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, return -ENOENT; } -static bool ht_empty(struct tc_u_hnode *ht) -{ - unsigned int h; - - for (h = 0; h <= ht->divisor; h++) - if (rcu_access_pointer(ht->ht[h])) - return false; - - return true; -} - static void u32_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; @@ -680,20 +666,16 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, struct netlink_ext_ack *extack) { struct tc_u_hnode *ht = arg; - struct tc_u_hnode *root_ht = rtnl_dereference(tp->root); struct tc_u_common *tp_c = tp->data; int ret = 0; - if (ht == NULL) - goto out; - if (TC_U32_KEY(ht->handle)) { u32_remove_hw_knode(tp, (struct tc_u_knode *)ht, extack); ret = u32_delete_key(tp, (struct tc_u_knode *)ht); goto out; } - if (root_ht == ht) { + if (ht->is_root) { NL_SET_ERR_MSG_MOD(extack, "Not allowed to delete root node"); return -EINVAL; } @@ -706,38 +688,7 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, } out: - *last = true; - if (root_ht) { - if (root_ht->refcnt > 2) { - *last = false; - goto ret; - } - if (root_ht->refcnt == 2) { - if (!ht_empty(root_ht)) { - *last = false; - goto ret; - } - } - } - - if (tp_c->refcnt > 1) { - *last = false; - goto ret; - } - - if (tp_c->refcnt == 1) { - struct tc_u_hnode *ht; - - for (ht = rtnl_dereference(tp_c->hlist); - ht; - ht = rtnl_dereference(ht->next)) - if (!ht_empty(ht)) { - *last = false; - break; - } - } - -ret: + *last = tp_c->refcnt == 1 && tp_c->knodes == 0; return ret; } @@ -768,7 +719,7 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { }; static int u32_set_parms(struct net *net, struct tcf_proto *tp, - unsigned long base, struct tc_u_hnode *ht, + unsigned long base, struct tc_u_knode *n, struct nlattr **tb, struct nlattr *est, bool ovr, struct netlink_ext_ack *extack) @@ -789,12 +740,16 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, } if (handle) { - ht_down = u32_lookup_ht(ht->tp_c, handle); + ht_down = u32_lookup_ht(tp->data, handle); if (!ht_down) { NL_SET_ERR_MSG_MOD(extack, "Link hash table not found"); return -EINVAL; } + if (ht_down->is_root) { + NL_SET_ERR_MSG_MOD(extack, "Not linking to root node"); + return -EINVAL; + } ht_down->refcnt++; } @@ -891,7 +846,6 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, /* Similarly success statistics must be moved as pointers */ new->pcpu_success = n->pcpu_success; #endif - new->tp = tp; memcpy(&new->sel, s, sizeof(*s) + s->nkeys*sizeof(struct tc_u32_key)); if (tcf_exts_init(&new->exts, TCA_U32_ACT, TCA_U32_POLICE)) { @@ -960,18 +914,17 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (!new) return -ENOMEM; - err = u32_set_parms(net, tp, base, - rtnl_dereference(n->ht_up), new, tb, + err = u32_set_parms(net, tp, base, new, tb, tca[TCA_RATE], ovr, extack); if (err) { - u32_destroy_key(tp, new, false); + u32_destroy_key(new, false); return err; } err = u32_replace_hw_knode(tp, new, flags, extack); if (err) { - u32_destroy_key(tp, new, false); + u32_destroy_key(new, false); return err; } @@ -988,7 +941,11 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (tb[TCA_U32_DIVISOR]) { unsigned int divisor = nla_get_u32(tb[TCA_U32_DIVISOR]); - if (--divisor > 0x100) { + if (!is_power_of_2(divisor)) { + NL_SET_ERR_MSG_MOD(extack, "Divisor is not a power of 2"); + return -EINVAL; + } + if (divisor-- > 0x100) { NL_SET_ERR_MSG_MOD(extack, "Exceeded maximum 256 hash buckets"); return -EINVAL; } @@ -1013,7 +970,6 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return err; } } - ht->tp_c = tp_c; ht->refcnt = 1; ht->divisor = divisor; ht->handle = handle; @@ -1103,7 +1059,6 @@ 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; n->flags = flags; - n->tp = tp; err = tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE); if (err < 0) @@ -1125,7 +1080,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, } #endif - err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE], ovr, + err = u32_set_parms(net, tp, base, n, tb, tca[TCA_RATE], ovr, extack); if (err == 0) { struct tc_u_knode __rcu **ins; @@ -1146,6 +1101,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, RCU_INIT_POINTER(n->next, pins); rcu_assign_pointer(*ins, n); + tp_c->knodes++; *arg = n; return 0; } @@ -1251,6 +1207,7 @@ static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n, cls_u32.knode.mask = 0; #endif cls_u32.knode.sel = &n->sel; + cls_u32.knode.res = &n->res; cls_u32.knode.exts = &n->exts; if (n->ht_down) cls_u32.knode.link_handle = ht->handle; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 3dc0acf54245..7e4d1ccf4c87 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -27,7 +27,6 @@ #include <linux/kmod.h> #include <linux/list.h> #include <linux/hrtimer.h> -#include <linux/lockdep.h> #include <linux/slab.h> #include <linux/hashtable.h> @@ -315,10 +314,27 @@ out: return q; } +struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle) +{ + struct netdev_queue *nq; + struct Qdisc *q; + + if (!handle) + return NULL; + q = qdisc_match_from_root(dev->qdisc, handle); + if (q) + goto out; + + nq = dev_ingress_queue_rcu(dev); + if (nq) + q = qdisc_match_from_root(nq->qdisc_sleeping, handle); +out: + return q; +} + static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) { unsigned long cl; - struct Qdisc *leaf; const struct Qdisc_class_ops *cops = p->ops->cl_ops; if (cops == NULL) @@ -327,8 +343,7 @@ static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) if (cl == 0) return NULL; - leaf = cops->leaf(p, cl); - return leaf; + return cops->leaf(p, cl); } /* Find queueing discipline by name */ @@ -523,7 +538,7 @@ void qdisc_put_stab(struct qdisc_size_table *tab) if (--tab->refcnt == 0) { list_del(&tab->list); - call_rcu_bh(&tab->rcu, stab_kfree_rcu); + call_rcu(&tab->rcu, stab_kfree_rcu); } } EXPORT_SYMBOL(qdisc_put_stab); @@ -793,6 +808,71 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n, } EXPORT_SYMBOL(qdisc_tree_reduce_backlog); +int qdisc_offload_dump_helper(struct Qdisc *sch, enum tc_setup_type type, + void *type_data) +{ + struct net_device *dev = qdisc_dev(sch); + int err; + + sch->flags &= ~TCQ_F_OFFLOADED; + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return 0; + + err = dev->netdev_ops->ndo_setup_tc(dev, type, type_data); + if (err == -EOPNOTSUPP) + return 0; + + if (!err) + sch->flags |= TCQ_F_OFFLOADED; + + return err; +} +EXPORT_SYMBOL(qdisc_offload_dump_helper); + +void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch, + struct Qdisc *new, struct Qdisc *old, + enum tc_setup_type type, void *type_data, + struct netlink_ext_ack *extack) +{ + bool any_qdisc_is_offloaded; + int err; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + err = dev->netdev_ops->ndo_setup_tc(dev, type, type_data); + + /* Don't report error if the graft is part of destroy operation. */ + if (!err || !new || new == &noop_qdisc) + return; + + /* Don't report error if the parent, the old child and the new + * one are not offloaded. + */ + any_qdisc_is_offloaded = new->flags & TCQ_F_OFFLOADED; + any_qdisc_is_offloaded |= sch && sch->flags & TCQ_F_OFFLOADED; + any_qdisc_is_offloaded |= old && old->flags & TCQ_F_OFFLOADED; + + if (any_qdisc_is_offloaded) + NL_SET_ERR_MSG(extack, "Offloading graft operation failed."); +} +EXPORT_SYMBOL(qdisc_offload_graft_helper); + +static void qdisc_offload_graft_root(struct net_device *dev, + struct Qdisc *new, struct Qdisc *old, + struct netlink_ext_ack *extack) +{ + struct tc_root_qopt_offload graft_offload = { + .command = TC_ROOT_GRAFT, + .handle = new ? new->handle : 0, + .ingress = (new && new->flags & TCQ_F_INGRESS) || + (old && old->flags & TCQ_F_INGRESS), + }; + + qdisc_offload_graft_helper(dev, NULL, new, old, + TC_SETUP_ROOT_QDISC, &graft_offload, extack); +} + static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, u32 portid, u32 seq, u16 flags, int event) { @@ -921,7 +1001,7 @@ static void notify_and_destroy(struct net *net, struct sk_buff *skb, qdisc_notify(net, skb, n, clid, old, new); if (old) - qdisc_destroy(old); + qdisc_put(old); } /* Graft qdisc "new" to class "classid" of qdisc "parent" or @@ -940,7 +1020,6 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, { struct Qdisc *q = old; struct net *net = dev_net(dev); - int err = 0; if (parent == NULL) { unsigned int i, num_q, ingress; @@ -960,6 +1039,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, if (dev->flags & IFF_UP) dev_deactivate(dev); + qdisc_offload_graft_root(dev, new, old, extack); + if (new && new->ops->attach) goto skip; @@ -974,7 +1055,7 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, qdisc_refcount_inc(new); if (!ingress) - qdisc_destroy(old); + qdisc_put(old); } skip: @@ -995,28 +1076,29 @@ skip: dev_activate(dev); } else { const struct Qdisc_class_ops *cops = parent->ops->cl_ops; + unsigned long cl; + int err; /* Only support running class lockless if parent is lockless */ if (new && (new->flags & TCQ_F_NOLOCK) && parent && !(parent->flags & TCQ_F_NOLOCK)) new->flags &= ~TCQ_F_NOLOCK; - err = -EOPNOTSUPP; - if (cops && cops->graft) { - unsigned long cl = cops->find(parent, classid); + if (!cops || !cops->graft) + return -EOPNOTSUPP; - if (cl) { - err = cops->graft(parent, cl, new, &old, - extack); - } else { - NL_SET_ERR_MSG(extack, "Specified class not found"); - err = -ENOENT; - } + cl = cops->find(parent, classid); + if (!cl) { + NL_SET_ERR_MSG(extack, "Specified class not found"); + return -ENOENT; } - if (!err) - notify_and_destroy(net, skb, n, classid, old, new); + + err = cops->graft(parent, cl, new, &old, extack); + if (err) + return err; + notify_and_destroy(net, skb, n, classid, old, new); } - return err; + return 0; } static int qdisc_block_indexes_set(struct Qdisc *sch, struct nlattr **tca, @@ -1053,10 +1135,6 @@ static int qdisc_block_indexes_set(struct Qdisc *sch, struct nlattr **tca, return 0; } -/* lockdep annotation is needed for ingress; egress gets it only for name */ -static struct lock_class_key qdisc_tx_lock; -static struct lock_class_key qdisc_rx_lock; - /* Allocate and initialize new qdisc. @@ -1121,7 +1199,6 @@ static struct Qdisc *qdisc_create(struct net_device *dev, if (handle == TC_H_INGRESS) { sch->flags |= TCQ_F_INGRESS; handle = TC_H_MAKE(TC_H_INGRESS, 0); - lockdep_set_class(qdisc_lock(sch), &qdisc_rx_lock); } else { if (handle == 0) { handle = qdisc_alloc_handle(dev); @@ -1129,7 +1206,6 @@ static struct Qdisc *qdisc_create(struct net_device *dev, if (handle == 0) goto err_out3; } - lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock); if (!netif_is_multiqueue(dev)) sch->flags |= TCQ_F_ONETXQUEUE; } @@ -1309,7 +1385,6 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = { [TCA_KIND] = { .type = NLA_STRING }, - [TCA_OPTIONS] = { .type = NLA_NESTED }, [TCA_RATE] = { .type = NLA_BINARY, .len = sizeof(struct tc_estimator) }, [TCA_STAB] = { .type = NLA_NESTED }, @@ -1582,7 +1657,7 @@ graft: err = qdisc_graft(dev, p, skb, n, clid, q, NULL, extack); if (err) { if (q) - qdisc_destroy(q); + qdisc_put(q); return err; } @@ -1660,7 +1735,7 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) ASSERT_RTNL(); err = nlmsg_parse(nlh, sizeof(struct tcmsg), tca, TCA_MAX, - rtm_tca_policy, NULL); + rtm_tca_policy, cb->extack); if (err < 0) return err; diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index cd49afca9617..d714d3747bcb 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -150,7 +150,7 @@ static void atm_tc_put(struct Qdisc *sch, unsigned long cl) pr_debug("atm_tc_put: destroying\n"); list_del_init(&flow->list); pr_debug("atm_tc_put: qdisc %p\n", flow->q); - qdisc_destroy(flow->q); + qdisc_put(flow->q); tcf_block_put(flow->block); if (flow->sock) { pr_debug("atm_tc_put: f_count %ld\n", diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 793016d722ec..b910cd5c56f7 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -812,7 +812,7 @@ static struct sk_buff *dequeue_head(struct cake_flow *flow) if (skb) { flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); } return skb; @@ -1252,7 +1252,7 @@ found: else flow->head = elig_ack->next; - elig_ack->next = NULL; + skb_mark_not_on_list(elig_ack); return elig_ack; } @@ -1675,7 +1675,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, while (segs) { nskb = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; cobalt_set_enqueue_time(segs, now); get_cobalt_cb(segs)->adjusted_len = cake_overhead(q, diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index f42025d53cfe..4dc05409e3fb 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1418,7 +1418,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) WARN_ON(cl->filters); tcf_block_put(cl->block); - qdisc_destroy(cl->q); + qdisc_put(cl->q); qdisc_put_rtab(cl->R_tab); gen_kill_estimator(&cl->rate_est); if (cl != &q->link) diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index e26a24017faa..e689e11b6d0f 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -379,7 +379,7 @@ static void cbs_destroy(struct Qdisc *sch) cbs_disable_offload(dev, q); if (q->qdisc) - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); } static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index e0b0cf8a9939..cdebaed0f8cf 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -134,7 +134,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to replace estimator"); - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); kfree(cl); return err; } @@ -153,7 +153,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, static void drr_destroy_class(struct Qdisc *sch, struct drr_class *cl) { gen_kill_estimator(&cl->rate_est); - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); kfree(cl); } diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 049714c57075..f6f480784bc6 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -412,7 +412,7 @@ static void dsmark_destroy(struct Qdisc *sch) pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); tcf_block_put(p->block); - qdisc_destroy(p->q); + qdisc_put(p->q); if (p->mv != p->embedded) kfree(p->mv); } diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c index 1538d6fa8165..1150f22983df 100644 --- a/net/sched/sch_etf.c +++ b/net/sched/sch_etf.c @@ -30,7 +30,7 @@ struct etf_sched_data { int queue; s32 delta; /* in ns */ ktime_t last; /* The txtime of the last skb sent to the netdevice. */ - struct rb_root head; + struct rb_root_cached head; struct qdisc_watchdog watchdog; ktime_t (*get_time)(void); }; @@ -104,7 +104,7 @@ static struct sk_buff *etf_peek_timesortedlist(struct Qdisc *sch) struct etf_sched_data *q = qdisc_priv(sch); struct rb_node *p; - p = rb_first(&q->head); + p = rb_first_cached(&q->head); if (!p) return NULL; @@ -117,8 +117,10 @@ static void reset_watchdog(struct Qdisc *sch) struct sk_buff *skb = etf_peek_timesortedlist(sch); ktime_t next; - if (!skb) + if (!skb) { + qdisc_watchdog_cancel(&q->watchdog); return; + } next = ktime_sub_ns(skb->tstamp, q->delta); qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next)); @@ -154,8 +156,9 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch, struct sk_buff **to_free) { struct etf_sched_data *q = qdisc_priv(sch); - struct rb_node **p = &q->head.rb_node, *parent = NULL; + struct rb_node **p = &q->head.rb_root.rb_node, *parent = NULL; ktime_t txtime = nskb->tstamp; + bool leftmost = true; if (!is_packet_valid(sch, nskb)) { report_sock_error(nskb, EINVAL, @@ -168,13 +171,15 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch, parent = *p; skb = rb_to_skb(parent); - if (ktime_after(txtime, skb->tstamp)) + if (ktime_after(txtime, skb->tstamp)) { p = &parent->rb_right; - else + leftmost = false; + } else { p = &parent->rb_left; + } } rb_link_node(&nskb->rbnode, parent, p); - rb_insert_color(&nskb->rbnode, &q->head); + rb_insert_color_cached(&nskb->rbnode, &q->head, leftmost); qdisc_qstats_backlog_inc(sch, nskb); sch->q.qlen++; @@ -185,12 +190,42 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch, return NET_XMIT_SUCCESS; } -static void timesortedlist_erase(struct Qdisc *sch, struct sk_buff *skb, - bool drop) +static void timesortedlist_drop(struct Qdisc *sch, struct sk_buff *skb, + ktime_t now) +{ + struct etf_sched_data *q = qdisc_priv(sch); + struct sk_buff *to_free = NULL; + struct sk_buff *tmp = NULL; + + skb_rbtree_walk_from_safe(skb, tmp) { + if (ktime_after(skb->tstamp, now)) + break; + + rb_erase_cached(&skb->rbnode, &q->head); + + /* The rbnode field in the skb re-uses these fields, now that + * we are done with the rbnode, reset them. + */ + skb->next = NULL; + skb->prev = NULL; + skb->dev = qdisc_dev(sch); + + report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED); + + qdisc_qstats_backlog_dec(sch, skb); + qdisc_drop(skb, sch, &to_free); + qdisc_qstats_overlimit(sch); + sch->q.qlen--; + } + + kfree_skb_list(to_free); +} + +static void timesortedlist_remove(struct Qdisc *sch, struct sk_buff *skb) { struct etf_sched_data *q = qdisc_priv(sch); - rb_erase(&skb->rbnode, &q->head); + rb_erase_cached(&skb->rbnode, &q->head); /* The rbnode field in the skb re-uses these fields, now that * we are done with the rbnode, reset them. @@ -201,19 +236,9 @@ static void timesortedlist_erase(struct Qdisc *sch, struct sk_buff *skb, qdisc_qstats_backlog_dec(sch, skb); - if (drop) { - struct sk_buff *to_free = NULL; + qdisc_bstats_update(sch, skb); - report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED); - - qdisc_drop(skb, sch, &to_free); - kfree_skb_list(to_free); - qdisc_qstats_overlimit(sch); - } else { - qdisc_bstats_update(sch, skb); - - q->last = skb->tstamp; - } + q->last = skb->tstamp; sch->q.qlen--; } @@ -232,7 +257,7 @@ static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch) /* Drop if packet has expired while in queue. */ if (ktime_before(skb->tstamp, now)) { - timesortedlist_erase(sch, skb, true); + timesortedlist_drop(sch, skb, now); skb = NULL; goto out; } @@ -241,7 +266,7 @@ static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch) * txtime from deadline to (now + delta). */ if (q->deadline_mode) { - timesortedlist_erase(sch, skb, false); + timesortedlist_remove(sch, skb); skb->tstamp = now; goto out; } @@ -250,7 +275,7 @@ static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch) /* Dequeue only if now is within the [txtime - delta, txtime] range. */ if (ktime_after(now, next)) - timesortedlist_erase(sch, skb, false); + timesortedlist_remove(sch, skb); else skb = NULL; @@ -386,14 +411,14 @@ static int etf_init(struct Qdisc *sch, struct nlattr *opt, static void timesortedlist_clear(struct Qdisc *sch) { struct etf_sched_data *q = qdisc_priv(sch); - struct rb_node *p = rb_first(&q->head); + struct rb_node *p = rb_first_cached(&q->head); while (p) { struct sk_buff *skb = rb_to_skb(p); p = rb_next(p); - rb_erase(&skb->rbnode, &q->head); + rb_erase_cached(&skb->rbnode, &q->head); rtnl_kfree_skbs(skb, skb); sch->q.qlen--; } diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 24893d3b5d22..3809c9bf8896 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -177,7 +177,7 @@ struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, if (q) { err = fifo_set_limit(q, limit); if (err < 0) { - qdisc_destroy(q); + qdisc_put(q); q = NULL; } } diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 4808713c73b9..1a662f2bb7bb 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -92,8 +92,9 @@ struct fq_sched_data { u32 quantum; u32 initial_quantum; u32 flow_refill_delay; - u32 flow_max_rate; /* optional max rate per flow */ u32 flow_plimit; /* max packets per flow */ + unsigned long flow_max_rate; /* optional max rate per flow */ + u64 ce_threshold; u32 orphan_mask; /* mask for orphaned skb */ u32 low_rate_threshold; struct rb_root *fq_root; @@ -106,8 +107,8 @@ struct fq_sched_data { u64 stat_gc_flows; u64 stat_internal_packets; - u64 stat_tcp_retrans; u64 stat_throttled; + u64 stat_ce_mark; u64 stat_flows_plimit; u64 stat_pkts_too_long; u64 stat_allocation_errors; @@ -319,7 +320,7 @@ static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow) if (skb) { flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); flow->qlen--; qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; @@ -327,62 +328,17 @@ static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow) return skb; } -/* We might add in the future detection of retransmits - * For the time being, just return false - */ -static bool skb_is_retransmit(struct sk_buff *skb) -{ - return false; -} - -/* add skb to flow queue - * flow queue is a linked list, kind of FIFO, except for TCP retransmits - * We special case tcp retransmits to be transmitted before other packets. - * We rely on fact that TCP retransmits are unlikely, so we do not waste - * a separate queue or a pointer. - * head-> [retrans pkt 1] - * [retrans pkt 2] - * [ normal pkt 1] - * [ normal pkt 2] - * [ normal pkt 3] - * tail-> [ normal pkt 4] - */ static void flow_queue_add(struct fq_flow *flow, struct sk_buff *skb) { - struct sk_buff *prev, *head = flow->head; + struct sk_buff *head = flow->head; skb->next = NULL; - if (!head) { + if (!head) flow->head = skb; - flow->tail = skb; - return; - } - if (likely(!skb_is_retransmit(skb))) { + else flow->tail->next = skb; - flow->tail = skb; - return; - } - /* This skb is a tcp retransmit, - * find the last retrans packet in the queue - */ - prev = NULL; - while (skb_is_retransmit(head)) { - prev = head; - head = head->next; - if (!head) - break; - } - if (!prev) { /* no rtx packet in queue, become the new head */ - skb->next = flow->head; - flow->head = skb; - } else { - if (prev == flow->tail) - flow->tail = skb; - else - skb->next = prev->next; - prev->next = skb; - } + flow->tail = skb; } static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, @@ -401,8 +357,6 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, } f->qlen++; - if (skb_is_retransmit(skb)) - q->stat_tcp_retrans++; qdisc_qstats_backlog_inc(sch, skb); if (fq_flow_is_detached(f)) { struct sock *sk = skb->sk; @@ -460,15 +414,21 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now) static struct sk_buff *fq_dequeue(struct Qdisc *sch) { struct fq_sched_data *q = qdisc_priv(sch); - u64 now = ktime_get_ns(); struct fq_flow_head *head; struct sk_buff *skb; struct fq_flow *f; - u32 rate, plen; + unsigned long rate; + u32 plen; + u64 now; + + if (!sch->q.qlen) + return NULL; skb = fq_dequeue_head(sch, &q->internal); if (skb) goto out; + + now = ktime_get_ns(); fq_check_throttled(q, now); begin: head = &q->new_flows; @@ -491,11 +451,21 @@ begin: } skb = f->head; - if (unlikely(skb && now < f->time_next_packet && - !skb_is_tcp_pure_ack(skb))) { - head->first = f->next; - fq_flow_set_throttled(q, f); - goto begin; + if (skb) { + u64 time_next_packet = max_t(u64, ktime_to_ns(skb->tstamp), + f->time_next_packet); + + if (now < time_next_packet) { + head->first = f->next; + f->time_next_packet = time_next_packet; + fq_flow_set_throttled(q, f); + goto begin; + } + if (time_next_packet && + (s64)(now - time_next_packet - q->ce_threshold) > 0) { + INET_ECN_set_ce(skb); + q->stat_ce_mark++; + } } skb = fq_dequeue_head(sch, f); @@ -511,32 +481,35 @@ begin: goto begin; } prefetch(&skb->end); - f->credit -= qdisc_pkt_len(skb); + plen = qdisc_pkt_len(skb); + f->credit -= plen; if (!q->rate_enable) goto out; - /* Do not pace locally generated ack packets */ - if (skb_is_tcp_pure_ack(skb)) - goto out; - rate = q->flow_max_rate; - if (skb->sk) - rate = min(skb->sk->sk_pacing_rate, rate); - - if (rate <= q->low_rate_threshold) { - f->credit = 0; - plen = qdisc_pkt_len(skb); - } else { - plen = max(qdisc_pkt_len(skb), q->quantum); - if (f->credit > 0) - goto out; + + /* If EDT time was provided for this skb, we need to + * update f->time_next_packet only if this qdisc enforces + * a flow max rate. + */ + if (!skb->tstamp) { + if (skb->sk) + rate = min(skb->sk->sk_pacing_rate, rate); + + if (rate <= q->low_rate_threshold) { + f->credit = 0; + } else { + plen = max(plen, q->quantum); + if (f->credit > 0) + goto out; + } } - if (rate != ~0U) { + if (rate != ~0UL) { u64 len = (u64)plen * NSEC_PER_SEC; if (likely(rate)) - do_div(len, rate); + len = div64_ul(len, rate); /* Since socket rate can change later, * clamp the delay to 1 second. * Really, providers of too big packets should be fixed ! @@ -696,6 +669,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { [TCA_FQ_BUCKETS_LOG] = { .type = NLA_U32 }, [TCA_FQ_FLOW_REFILL_DELAY] = { .type = NLA_U32 }, [TCA_FQ_LOW_RATE_THRESHOLD] = { .type = NLA_U32 }, + [TCA_FQ_CE_THRESHOLD] = { .type = NLA_U32 }, }; static int fq_change(struct Qdisc *sch, struct nlattr *opt, @@ -748,9 +722,11 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, pr_warn_ratelimited("sch_fq: defrate %u ignored.\n", nla_get_u32(tb[TCA_FQ_FLOW_DEFAULT_RATE])); - if (tb[TCA_FQ_FLOW_MAX_RATE]) - q->flow_max_rate = nla_get_u32(tb[TCA_FQ_FLOW_MAX_RATE]); + if (tb[TCA_FQ_FLOW_MAX_RATE]) { + u32 rate = nla_get_u32(tb[TCA_FQ_FLOW_MAX_RATE]); + q->flow_max_rate = (rate == ~0U) ? ~0UL : rate; + } if (tb[TCA_FQ_LOW_RATE_THRESHOLD]) q->low_rate_threshold = nla_get_u32(tb[TCA_FQ_LOW_RATE_THRESHOLD]); @@ -773,6 +749,10 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_FQ_ORPHAN_MASK]) q->orphan_mask = nla_get_u32(tb[TCA_FQ_ORPHAN_MASK]); + if (tb[TCA_FQ_CE_THRESHOLD]) + q->ce_threshold = (u64)NSEC_PER_USEC * + nla_get_u32(tb[TCA_FQ_CE_THRESHOLD]); + if (!err) { sch_tree_unlock(sch); err = fq_resize(sch, fq_log); @@ -813,7 +793,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt, q->quantum = 2 * psched_mtu(qdisc_dev(sch)); q->initial_quantum = 10 * psched_mtu(qdisc_dev(sch)); q->flow_refill_delay = msecs_to_jiffies(40); - q->flow_max_rate = ~0U; + q->flow_max_rate = ~0UL; q->time_next_delayed_flow = ~0ULL; q->rate_enable = 1; q->new_flows.first = NULL; @@ -823,7 +803,11 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt, q->fq_trees_log = ilog2(1024); q->orphan_mask = 1024 - 1; q->low_rate_threshold = 550000 / 8; - qdisc_watchdog_init(&q->watchdog, sch); + + /* Default ce_threshold of 4294 seconds */ + q->ce_threshold = (u64)NSEC_PER_USEC * ~0U; + + qdisc_watchdog_init_clockid(&q->watchdog, sch, CLOCK_MONOTONIC); if (opt) err = fq_change(sch, opt, extack); @@ -836,6 +820,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt, static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) { struct fq_sched_data *q = qdisc_priv(sch); + u64 ce_threshold = q->ce_threshold; struct nlattr *opts; opts = nla_nest_start(skb, TCA_OPTIONS); @@ -844,17 +829,21 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) /* TCA_FQ_FLOW_DEFAULT_RATE is not used anymore */ + do_div(ce_threshold, NSEC_PER_USEC); + if (nla_put_u32(skb, TCA_FQ_PLIMIT, sch->limit) || nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT, q->flow_plimit) || nla_put_u32(skb, TCA_FQ_QUANTUM, q->quantum) || nla_put_u32(skb, TCA_FQ_INITIAL_QUANTUM, q->initial_quantum) || nla_put_u32(skb, TCA_FQ_RATE_ENABLE, q->rate_enable) || - nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, q->flow_max_rate) || + nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, + min_t(unsigned long, q->flow_max_rate, ~0U)) || nla_put_u32(skb, TCA_FQ_FLOW_REFILL_DELAY, jiffies_to_usecs(q->flow_refill_delay)) || nla_put_u32(skb, TCA_FQ_ORPHAN_MASK, q->orphan_mask) || nla_put_u32(skb, TCA_FQ_LOW_RATE_THRESHOLD, q->low_rate_threshold) || + nla_put_u32(skb, TCA_FQ_CE_THRESHOLD, (u32)ce_threshold) || nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log)) goto nla_put_failure; @@ -873,7 +862,7 @@ static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) st.gc_flows = q->stat_gc_flows; st.highprio_packets = q->stat_internal_packets; - st.tcp_retrans = q->stat_tcp_retrans; + st.tcp_retrans = 0; st.throttled = q->stat_throttled; st.flows_plimit = q->stat_flows_plimit; st.pkts_too_long = q->stat_pkts_too_long; @@ -884,6 +873,7 @@ static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) st.throttled_flows = q->throttled_flows; st.unthrottle_latency_ns = min_t(unsigned long, q->unthrottle_latency_ns, ~0U); + st.ce_mark = q->stat_ce_mark; sch_tree_unlock(sch); return gnet_stats_copy_app(d, &st, sizeof(st)); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 6c0a9d5dbf94..cd04d40c30b6 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -124,7 +124,7 @@ static inline struct sk_buff *dequeue_head(struct fq_codel_flow *flow) struct sk_buff *skb = flow->head; flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); return skb; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 69078c82963e..66ba2ce2320f 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -184,7 +184,7 @@ static void try_bulk_dequeue_skb(struct Qdisc *q, skb = nskb; (*packets)++; /* GSO counts as one pkt */ } - skb->next = NULL; + skb_mark_not_on_list(skb); } /* This variant of try_bulk_dequeue_skb() makes sure @@ -210,7 +210,7 @@ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, skb = nskb; } while (++cnt < 8); (*packets) += cnt; - skb->next = NULL; + skb_mark_not_on_list(skb); } /* Note that dequeue_skb can possibly return a SKB list (via skb->next). @@ -572,6 +572,18 @@ struct Qdisc noop_qdisc = { .dev_queue = &noop_netdev_queue, .running = SEQCNT_ZERO(noop_qdisc.running), .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), + .gso_skb = { + .next = (struct sk_buff *)&noop_qdisc.gso_skb, + .prev = (struct sk_buff *)&noop_qdisc.gso_skb, + .qlen = 0, + .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.gso_skb.lock), + }, + .skb_bad_txq = { + .next = (struct sk_buff *)&noop_qdisc.skb_bad_txq, + .prev = (struct sk_buff *)&noop_qdisc.skb_bad_txq, + .qlen = 0, + .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.skb_bad_txq.lock), + }, }; EXPORT_SYMBOL(noop_qdisc); @@ -901,7 +913,7 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, if (!ops->init || ops->init(sch, NULL, extack) == 0) return sch; - qdisc_destroy(sch); + qdisc_put(sch); return NULL; } EXPORT_SYMBOL(qdisc_create_dflt); @@ -941,15 +953,18 @@ void qdisc_free(struct Qdisc *qdisc) kfree((char *) qdisc - qdisc->padded); } -void qdisc_destroy(struct Qdisc *qdisc) +static void qdisc_free_cb(struct rcu_head *head) +{ + struct Qdisc *q = container_of(head, struct Qdisc, rcu); + + qdisc_free(q); +} + +static void qdisc_destroy(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; struct sk_buff *skb, *tmp; - if (qdisc->flags & TCQ_F_BUILTIN || - !refcount_dec_and_test(&qdisc->refcnt)) - return; - #ifdef CONFIG_NET_SCHED qdisc_hash_del(qdisc); @@ -974,9 +989,34 @@ void qdisc_destroy(struct Qdisc *qdisc) kfree_skb_list(skb); } - qdisc_free(qdisc); + call_rcu(&qdisc->rcu, qdisc_free_cb); +} + +void qdisc_put(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN || + !refcount_dec_and_test(&qdisc->refcnt)) + return; + + qdisc_destroy(qdisc); +} +EXPORT_SYMBOL(qdisc_put); + +/* Version of qdisc_put() that is called with rtnl mutex unlocked. + * Intended to be used as optimization, this function only takes rtnl lock if + * qdisc reference counter reached zero. + */ + +void qdisc_put_unlocked(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN || + !refcount_dec_and_rtnl_lock(&qdisc->refcnt)) + return; + + qdisc_destroy(qdisc); + rtnl_unlock(); } -EXPORT_SYMBOL(qdisc_destroy); +EXPORT_SYMBOL(qdisc_put_unlocked); /* Attach toplevel qdisc to device queue. */ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, @@ -1245,8 +1285,6 @@ static void dev_init_scheduler_queue(struct net_device *dev, rcu_assign_pointer(dev_queue->qdisc, qdisc); dev_queue->qdisc_sleeping = qdisc; - __skb_queue_head_init(&qdisc->gso_skb); - __skb_queue_head_init(&qdisc->skb_bad_txq); } void dev_init_scheduler(struct net_device *dev) @@ -1270,7 +1308,7 @@ static void shutdown_scheduler_queue(struct net_device *dev, rcu_assign_pointer(dev_queue->qdisc, qdisc_default); dev_queue->qdisc_sleeping = qdisc_default; - qdisc_destroy(qdisc); + qdisc_put(qdisc); } } @@ -1279,7 +1317,7 @@ void dev_shutdown(struct net_device *dev) netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); if (dev_ingress_queue(dev)) shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); - qdisc_destroy(dev->qdisc); + qdisc_put(dev->qdisc); dev->qdisc = &noop_qdisc; WARN_ON(timer_pending(&dev->watchdog_timer)); @@ -1334,7 +1372,7 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, if (!tp_head) { RCU_INIT_POINTER(*miniqp->p_miniq, NULL); /* Wait for flying RCU callback before it is freed. */ - rcu_barrier_bh(); + rcu_barrier(); return; } @@ -1342,10 +1380,10 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, &miniqp->miniq1 : &miniqp->miniq2; /* We need to make sure that readers won't see the miniq - * we are about to modify. So wait until previous call_rcu_bh callback + * we are about to modify. So wait until previous call_rcu callback * is done. */ - rcu_barrier_bh(); + rcu_barrier(); miniq->filter_list = tp_head; rcu_assign_pointer(*miniqp->p_miniq, miniq); @@ -1354,7 +1392,7 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, * block potential new user of miniq_old until all readers * are not seeing it. */ - call_rcu_bh(&miniq_old->rcu, mini_qdisc_rcu_func); + call_rcu(&miniq_old->rcu, mini_qdisc_rcu_func); } EXPORT_SYMBOL(mini_qdisc_pair_swap); diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index cbe4831f46f4..234afbf9115b 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -23,19 +23,23 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/skbuff.h> +#include <net/pkt_cls.h> #include <net/pkt_sched.h> #include <net/red.h> #define GRED_DEF_PRIO (MAX_DPs / 2) #define GRED_VQ_MASK (MAX_DPs - 1) +#define GRED_VQ_RED_FLAGS (TC_RED_ECN | TC_RED_HARDDROP) + struct gred_sched_data; struct gred_sched; struct gred_sched_data { u32 limit; /* HARD maximal queue length */ u32 DP; /* the drop parameters */ - u32 bytesin; /* bytes seen on virtualQ so far*/ + u32 red_flags; /* virtualQ version of red_flags */ + u64 bytesin; /* bytes seen on virtualQ so far*/ u32 packetsin; /* packets seen on virtualQ so far*/ u32 backlog; /* bytes on the virtualQ */ u8 prio; /* the prio of this vq */ @@ -139,14 +143,27 @@ static inline void gred_store_wred_set(struct gred_sched *table, table->wred_set.qidlestart = q->vars.qidlestart; } -static inline int gred_use_ecn(struct gred_sched *t) +static int gred_use_ecn(struct gred_sched_data *q) +{ + return q->red_flags & TC_RED_ECN; +} + +static int gred_use_harddrop(struct gred_sched_data *q) { - return t->red_flags & TC_RED_ECN; + return q->red_flags & TC_RED_HARDDROP; } -static inline int gred_use_harddrop(struct gred_sched *t) +static bool gred_per_vq_red_flags_used(struct gred_sched *table) { - return t->red_flags & TC_RED_HARDDROP; + unsigned int i; + + /* Local per-vq flags couldn't have been set unless global are 0 */ + if (table->red_flags) + return false; + for (i = 0; i < MAX_DPs; i++) + if (table->tab[i] && table->tab[i]->red_flags) + return true; + return false; } static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch, @@ -212,7 +229,7 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch, case RED_PROB_MARK: qdisc_qstats_overlimit(sch); - if (!gred_use_ecn(t) || !INET_ECN_set_ce(skb)) { + if (!gred_use_ecn(q) || !INET_ECN_set_ce(skb)) { q->stats.prob_drop++; goto congestion_drop; } @@ -222,7 +239,7 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch, case RED_HARD_MARK: qdisc_qstats_overlimit(sch); - if (gred_use_harddrop(t) || !gred_use_ecn(t) || + if (gred_use_harddrop(q) || !gred_use_ecn(q) || !INET_ECN_set_ce(skb)) { q->stats.forced_drop++; goto congestion_drop; @@ -295,15 +312,103 @@ static void gred_reset(struct Qdisc *sch) } } +static void gred_offload(struct Qdisc *sch, enum tc_gred_command command) +{ + struct gred_sched *table = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_gred_qopt_offload opt = { + .command = command, + .handle = sch->handle, + .parent = sch->parent, + }; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + if (command == TC_GRED_REPLACE) { + unsigned int i; + + opt.set.grio_on = gred_rio_mode(table); + opt.set.wred_on = gred_wred_mode(table); + opt.set.dp_cnt = table->DPs; + opt.set.dp_def = table->def; + + for (i = 0; i < table->DPs; i++) { + struct gred_sched_data *q = table->tab[i]; + + if (!q) + continue; + opt.set.tab[i].present = true; + opt.set.tab[i].limit = q->limit; + opt.set.tab[i].prio = q->prio; + opt.set.tab[i].min = q->parms.qth_min >> q->parms.Wlog; + opt.set.tab[i].max = q->parms.qth_max >> q->parms.Wlog; + opt.set.tab[i].is_ecn = gred_use_ecn(q); + opt.set.tab[i].is_harddrop = gred_use_harddrop(q); + opt.set.tab[i].probability = q->parms.max_P; + opt.set.tab[i].backlog = &q->backlog; + } + opt.set.qstats = &sch->qstats; + } + + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_GRED, &opt); +} + +static int gred_offload_dump_stats(struct Qdisc *sch) +{ + struct gred_sched *table = qdisc_priv(sch); + struct tc_gred_qopt_offload *hw_stats; + unsigned int i; + int ret; + + hw_stats = kzalloc(sizeof(*hw_stats), GFP_KERNEL); + if (!hw_stats) + return -ENOMEM; + + hw_stats->command = TC_GRED_STATS; + hw_stats->handle = sch->handle; + hw_stats->parent = sch->parent; + + for (i = 0; i < MAX_DPs; i++) + if (table->tab[i]) + hw_stats->stats.xstats[i] = &table->tab[i]->stats; + + ret = qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_GRED, hw_stats); + /* Even if driver returns failure adjust the stats - in case offload + * ended but driver still wants to adjust the values. + */ + for (i = 0; i < MAX_DPs; i++) { + if (!table->tab[i]) + continue; + table->tab[i]->packetsin += hw_stats->stats.bstats[i].packets; + table->tab[i]->bytesin += hw_stats->stats.bstats[i].bytes; + table->tab[i]->backlog += hw_stats->stats.qstats[i].backlog; + + _bstats_update(&sch->bstats, + hw_stats->stats.bstats[i].bytes, + hw_stats->stats.bstats[i].packets); + sch->qstats.qlen += hw_stats->stats.qstats[i].qlen; + sch->qstats.backlog += hw_stats->stats.qstats[i].backlog; + sch->qstats.drops += hw_stats->stats.qstats[i].drops; + sch->qstats.requeues += hw_stats->stats.qstats[i].requeues; + sch->qstats.overlimits += hw_stats->stats.qstats[i].overlimits; + } + + kfree(hw_stats); + return ret; +} + static inline void gred_destroy_vq(struct gred_sched_data *q) { kfree(q); } -static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps) +static int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps, + struct netlink_ext_ack *extack) { struct gred_sched *table = qdisc_priv(sch); struct tc_gred_sopt *sopt; + bool red_flags_changed; int i; if (!dps) @@ -311,13 +416,28 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps) sopt = nla_data(dps); - if (sopt->DPs > MAX_DPs || sopt->DPs == 0 || - sopt->def_DP >= sopt->DPs) + if (sopt->DPs > MAX_DPs) { + NL_SET_ERR_MSG_MOD(extack, "number of virtual queues too high"); + return -EINVAL; + } + if (sopt->DPs == 0) { + NL_SET_ERR_MSG_MOD(extack, + "number of virtual queues can't be 0"); + return -EINVAL; + } + if (sopt->def_DP >= sopt->DPs) { + NL_SET_ERR_MSG_MOD(extack, "default virtual queue above virtual queue count"); return -EINVAL; + } + if (sopt->flags && gred_per_vq_red_flags_used(table)) { + NL_SET_ERR_MSG_MOD(extack, "can't set per-Qdisc RED flags when per-virtual queue flags are used"); + return -EINVAL; + } sch_tree_lock(sch); table->DPs = sopt->DPs; table->def = sopt->def_DP; + red_flags_changed = table->red_flags != sopt->flags; table->red_flags = sopt->flags; /* @@ -337,6 +457,12 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps) gred_disable_wred_mode(table); } + if (red_flags_changed) + for (i = 0; i < table->DPs; i++) + if (table->tab[i]) + table->tab[i]->red_flags = + table->red_flags & GRED_VQ_RED_FLAGS; + for (i = table->DPs; i < MAX_DPs; i++) { if (table->tab[i]) { pr_warn("GRED: Warning: Destroying shadowed VQ 0x%x\n", @@ -346,25 +472,30 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps) } } + gred_offload(sch, TC_GRED_REPLACE); return 0; } static inline int gred_change_vq(struct Qdisc *sch, int dp, struct tc_gred_qopt *ctl, int prio, u8 *stab, u32 max_P, - struct gred_sched_data **prealloc) + struct gred_sched_data **prealloc, + struct netlink_ext_ack *extack) { struct gred_sched *table = qdisc_priv(sch); struct gred_sched_data *q = table->tab[dp]; - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) { + NL_SET_ERR_MSG_MOD(extack, "invalid RED parameters"); return -EINVAL; + } if (!q) { table->tab[dp] = q = *prealloc; *prealloc = NULL; if (!q) return -ENOMEM; + q->red_flags = table->red_flags & GRED_VQ_RED_FLAGS; } q->DP = dp; @@ -384,14 +515,127 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp, return 0; } +static const struct nla_policy gred_vq_policy[TCA_GRED_VQ_MAX + 1] = { + [TCA_GRED_VQ_DP] = { .type = NLA_U32 }, + [TCA_GRED_VQ_FLAGS] = { .type = NLA_U32 }, +}; + +static const struct nla_policy gred_vqe_policy[TCA_GRED_VQ_ENTRY_MAX + 1] = { + [TCA_GRED_VQ_ENTRY] = { .type = NLA_NESTED }, +}; + static const struct nla_policy gred_policy[TCA_GRED_MAX + 1] = { [TCA_GRED_PARMS] = { .len = sizeof(struct tc_gred_qopt) }, [TCA_GRED_STAB] = { .len = 256 }, [TCA_GRED_DPS] = { .len = sizeof(struct tc_gred_sopt) }, [TCA_GRED_MAX_P] = { .type = NLA_U32 }, [TCA_GRED_LIMIT] = { .type = NLA_U32 }, + [TCA_GRED_VQ_LIST] = { .type = NLA_NESTED }, }; +static void gred_vq_apply(struct gred_sched *table, const struct nlattr *entry) +{ + struct nlattr *tb[TCA_GRED_VQ_MAX + 1]; + u32 dp; + + nla_parse_nested(tb, TCA_GRED_VQ_MAX, entry, gred_vq_policy, NULL); + + dp = nla_get_u32(tb[TCA_GRED_VQ_DP]); + + if (tb[TCA_GRED_VQ_FLAGS]) + table->tab[dp]->red_flags = nla_get_u32(tb[TCA_GRED_VQ_FLAGS]); +} + +static void gred_vqs_apply(struct gred_sched *table, struct nlattr *vqs) +{ + const struct nlattr *attr; + int rem; + + nla_for_each_nested(attr, vqs, rem) { + switch (nla_type(attr)) { + case TCA_GRED_VQ_ENTRY: + gred_vq_apply(table, attr); + break; + } + } +} + +static int gred_vq_validate(struct gred_sched *table, u32 cdp, + const struct nlattr *entry, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_GRED_VQ_MAX + 1]; + int err; + u32 dp; + + err = nla_parse_nested(tb, TCA_GRED_VQ_MAX, entry, gred_vq_policy, + extack); + if (err < 0) + return err; + + if (!tb[TCA_GRED_VQ_DP]) { + NL_SET_ERR_MSG_MOD(extack, "Virtual queue with no index specified"); + return -EINVAL; + } + dp = nla_get_u32(tb[TCA_GRED_VQ_DP]); + if (dp >= table->DPs) { + NL_SET_ERR_MSG_MOD(extack, "Virtual queue with index out of bounds"); + return -EINVAL; + } + if (dp != cdp && !table->tab[dp]) { + NL_SET_ERR_MSG_MOD(extack, "Virtual queue not yet instantiated"); + return -EINVAL; + } + + if (tb[TCA_GRED_VQ_FLAGS]) { + u32 red_flags = nla_get_u32(tb[TCA_GRED_VQ_FLAGS]); + + if (table->red_flags && table->red_flags != red_flags) { + NL_SET_ERR_MSG_MOD(extack, "can't change per-virtual queue RED flags when per-Qdisc flags are used"); + return -EINVAL; + } + if (red_flags & ~GRED_VQ_RED_FLAGS) { + NL_SET_ERR_MSG_MOD(extack, + "invalid RED flags specified"); + return -EINVAL; + } + } + + return 0; +} + +static int gred_vqs_validate(struct gred_sched *table, u32 cdp, + struct nlattr *vqs, struct netlink_ext_ack *extack) +{ + const struct nlattr *attr; + int rem, err; + + err = nla_validate_nested(vqs, TCA_GRED_VQ_ENTRY_MAX, + gred_vqe_policy, extack); + if (err < 0) + return err; + + nla_for_each_nested(attr, vqs, rem) { + switch (nla_type(attr)) { + case TCA_GRED_VQ_ENTRY: + err = gred_vq_validate(table, cdp, attr, extack); + if (err) + return err; + break; + default: + NL_SET_ERR_MSG_MOD(extack, "GRED_VQ_LIST can contain only entry attributes"); + return -EINVAL; + } + } + + if (rem > 0) { + NL_SET_ERR_MSG_MOD(extack, "Trailing data after parsing virtual queue list"); + return -EINVAL; + } + + return 0; +} + static int gred_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -406,29 +650,39 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt, if (opt == NULL) return -EINVAL; - err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy, NULL); + err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy, extack); if (err < 0) return err; if (tb[TCA_GRED_PARMS] == NULL && tb[TCA_GRED_STAB] == NULL) { if (tb[TCA_GRED_LIMIT] != NULL) sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]); - return gred_change_table_def(sch, opt); + return gred_change_table_def(sch, tb[TCA_GRED_DPS], extack); } if (tb[TCA_GRED_PARMS] == NULL || tb[TCA_GRED_STAB] == NULL || - tb[TCA_GRED_LIMIT] != NULL) + tb[TCA_GRED_LIMIT] != NULL) { + NL_SET_ERR_MSG_MOD(extack, "can't configure Qdisc and virtual queue at the same time"); return -EINVAL; + } max_P = tb[TCA_GRED_MAX_P] ? nla_get_u32(tb[TCA_GRED_MAX_P]) : 0; - err = -EINVAL; ctl = nla_data(tb[TCA_GRED_PARMS]); stab = nla_data(tb[TCA_GRED_STAB]); - if (ctl->DP >= table->DPs) - goto errout; + if (ctl->DP >= table->DPs) { + NL_SET_ERR_MSG_MOD(extack, "virtual queue index above virtual queue count"); + return -EINVAL; + } + + if (tb[TCA_GRED_VQ_LIST]) { + err = gred_vqs_validate(table, ctl->DP, tb[TCA_GRED_VQ_LIST], + extack); + if (err) + return err; + } if (gred_rio_mode(table)) { if (ctl->prio == 0) { @@ -448,9 +702,13 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt, prealloc = kzalloc(sizeof(*prealloc), GFP_KERNEL); sch_tree_lock(sch); - err = gred_change_vq(sch, ctl->DP, ctl, prio, stab, max_P, &prealloc); + err = gred_change_vq(sch, ctl->DP, ctl, prio, stab, max_P, &prealloc, + extack); if (err < 0) - goto errout_locked; + goto err_unlock_free; + + if (tb[TCA_GRED_VQ_LIST]) + gred_vqs_apply(table, tb[TCA_GRED_VQ_LIST]); if (gred_rio_mode(table)) { gred_disable_wred_mode(table); @@ -458,12 +716,15 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt, gred_enable_wred_mode(table); } - err = 0; + sch_tree_unlock(sch); + kfree(prealloc); + + gred_offload(sch, TC_GRED_REPLACE); + return 0; -errout_locked: +err_unlock_free: sch_tree_unlock(sch); kfree(prealloc); -errout: return err; } @@ -476,12 +737,15 @@ static int gred_init(struct Qdisc *sch, struct nlattr *opt, if (!opt) return -EINVAL; - err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy, NULL); + err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy, extack); if (err < 0) return err; - if (tb[TCA_GRED_PARMS] || tb[TCA_GRED_STAB]) + if (tb[TCA_GRED_PARMS] || tb[TCA_GRED_STAB]) { + NL_SET_ERR_MSG_MOD(extack, + "virtual queue configuration can't be specified at initialization time"); return -EINVAL; + } if (tb[TCA_GRED_LIMIT]) sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]); @@ -489,13 +753,13 @@ static int gred_init(struct Qdisc *sch, struct nlattr *opt, sch->limit = qdisc_dev(sch)->tx_queue_len * psched_mtu(qdisc_dev(sch)); - return gred_change_table_def(sch, tb[TCA_GRED_DPS]); + return gred_change_table_def(sch, tb[TCA_GRED_DPS], extack); } static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) { struct gred_sched *table = qdisc_priv(sch); - struct nlattr *parms, *opts = NULL; + struct nlattr *parms, *vqs, *opts = NULL; int i; u32 max_p[MAX_DPs]; struct tc_gred_sopt sopt = { @@ -505,6 +769,9 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) .flags = table->red_flags, }; + if (gred_offload_dump_stats(sch)) + goto nla_put_failure; + opts = nla_nest_start(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; @@ -522,6 +789,7 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put_u32(skb, TCA_GRED_LIMIT, sch->limit)) goto nla_put_failure; + /* Old style all-in-one dump of VQs */ parms = nla_nest_start(skb, TCA_GRED_PARMS); if (parms == NULL) goto nla_put_failure; @@ -572,6 +840,58 @@ append_opt: nla_nest_end(skb, parms); + /* Dump the VQs again, in more structured way */ + vqs = nla_nest_start(skb, TCA_GRED_VQ_LIST); + if (!vqs) + goto nla_put_failure; + + for (i = 0; i < MAX_DPs; i++) { + struct gred_sched_data *q = table->tab[i]; + struct nlattr *vq; + + if (!q) + continue; + + vq = nla_nest_start(skb, TCA_GRED_VQ_ENTRY); + if (!vq) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_GRED_VQ_DP, q->DP)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_GRED_VQ_FLAGS, q->red_flags)) + goto nla_put_failure; + + /* Stats */ + if (nla_put_u64_64bit(skb, TCA_GRED_VQ_STAT_BYTES, q->bytesin, + TCA_GRED_VQ_PAD)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PACKETS, q->packetsin)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_VQ_STAT_BACKLOG, + gred_backlog(table, q, sch))) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PROB_DROP, + q->stats.prob_drop)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PROB_MARK, + q->stats.prob_mark)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_VQ_STAT_FORCED_DROP, + q->stats.forced_drop)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_VQ_STAT_FORCED_MARK, + q->stats.forced_mark)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_VQ_STAT_PDROP, q->stats.pdrop)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_GRED_VQ_STAT_OTHER, q->stats.other)) + goto nla_put_failure; + + nla_nest_end(skb, vq); + } + nla_nest_end(skb, vqs); + return nla_nest_end(skb, opts); nla_put_failure: @@ -588,6 +908,7 @@ static void gred_destroy(struct Qdisc *sch) if (table->tab[i]) gred_destroy_vq(table->tab[i]); } + gred_offload(sch, TC_GRED_DESTROY); } static struct Qdisc_ops gred_qdisc_ops __read_mostly = { diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 3278a76f6861..b18ec1f6de60 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1092,7 +1092,7 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl) struct hfsc_sched *q = qdisc_priv(sch); tcf_block_put(cl->block); - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); gen_kill_estimator(&cl->rate_est); if (cl != &q->root) kfree(cl); diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index c3a8388dcdf6..9d6a47697406 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -330,7 +330,7 @@ static struct sk_buff *dequeue_head(struct wdrr_bucket *bucket) struct sk_buff *skb = bucket->head; bucket->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); return skb; } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 43c4bfe625a9..58b449490757 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -132,7 +132,7 @@ struct htb_class { struct htb_class_inner { struct htb_prio clprio[TC_HTB_NUMPRIO]; } inner; - } un; + }; s64 pq_key; int prio_activity; /* for which prios are we active */ @@ -411,13 +411,13 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) int prio = ffz(~m); m &= ~(1 << prio); - if (p->un.inner.clprio[prio].feed.rb_node) + if (p->inner.clprio[prio].feed.rb_node) /* parent already has its feed in use so that * reset bit in mask as parent is already ok */ mask &= ~(1 << prio); - htb_add_to_id_tree(&p->un.inner.clprio[prio].feed, cl, prio); + htb_add_to_id_tree(&p->inner.clprio[prio].feed, cl, prio); } p->prio_activity |= mask; cl = p; @@ -447,19 +447,19 @@ static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl) int prio = ffz(~m); m &= ~(1 << prio); - if (p->un.inner.clprio[prio].ptr == cl->node + prio) { + if (p->inner.clprio[prio].ptr == cl->node + prio) { /* we are removing child which is pointed to from * parent feed - forget the pointer but remember * classid */ - p->un.inner.clprio[prio].last_ptr_id = cl->common.classid; - p->un.inner.clprio[prio].ptr = NULL; + p->inner.clprio[prio].last_ptr_id = cl->common.classid; + p->inner.clprio[prio].ptr = NULL; } htb_safe_rb_erase(cl->node + prio, - &p->un.inner.clprio[prio].feed); + &p->inner.clprio[prio].feed); - if (!p->un.inner.clprio[prio].feed.rb_node) + if (!p->inner.clprio[prio].feed.rb_node) mask |= 1 << prio; } @@ -555,7 +555,7 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) */ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) { - WARN_ON(cl->level || !cl->un.leaf.q || !cl->un.leaf.q->q.qlen); + WARN_ON(cl->level || !cl->leaf.q || !cl->leaf.q->q.qlen); if (!cl->prio_activity) { cl->prio_activity = 1 << cl->prio; @@ -577,22 +577,6 @@ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl) cl->prio_activity = 0; } -static void htb_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, - struct qdisc_skb_head *qh) -{ - struct sk_buff *last = qh->tail; - - if (last) { - skb->next = NULL; - last->next = skb; - qh->tail = skb; - } else { - qh->tail = skb; - qh->head = skb; - } - qh->qlen++; -} - static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { @@ -603,7 +587,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (cl == HTB_DIRECT) { /* enqueue to helper queue */ if (q->direct_queue.qlen < q->direct_qlen) { - htb_enqueue_tail(skb, sch, &q->direct_queue); + __qdisc_enqueue_tail(skb, &q->direct_queue); q->direct_pkts++; } else { return qdisc_drop(skb, sch, to_free); @@ -615,7 +599,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, __qdisc_drop(skb, to_free); return ret; #endif - } else if ((ret = qdisc_enqueue(skb, cl->un.leaf.q, + } else if ((ret = qdisc_enqueue(skb, cl->leaf.q, to_free)) != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) { qdisc_qstats_drop(sch); @@ -823,7 +807,7 @@ static struct htb_class *htb_lookup_leaf(struct htb_prio *hprio, const int prio) cl = rb_entry(*sp->pptr, struct htb_class, node[prio]); if (!cl->level) return cl; - clp = &cl->un.inner.clprio[prio]; + clp = &cl->inner.clprio[prio]; (++sp)->root = clp->feed.rb_node; sp->pptr = &clp->ptr; sp->pid = &clp->last_ptr_id; @@ -857,7 +841,7 @@ next: * graft operation on the leaf since last dequeue; * simply deactivate and skip such class */ - if (unlikely(cl->un.leaf.q->q.qlen == 0)) { + if (unlikely(cl->leaf.q->q.qlen == 0)) { struct htb_class *next; htb_deactivate(q, cl); @@ -873,12 +857,12 @@ next: goto next; } - skb = cl->un.leaf.q->dequeue(cl->un.leaf.q); + skb = cl->leaf.q->dequeue(cl->leaf.q); if (likely(skb != NULL)) break; - qdisc_warn_nonwc("htb", cl->un.leaf.q); - htb_next_rb_node(level ? &cl->parent->un.inner.clprio[prio].ptr: + qdisc_warn_nonwc("htb", cl->leaf.q); + htb_next_rb_node(level ? &cl->parent->inner.clprio[prio].ptr: &q->hlevel[0].hprio[prio].ptr); cl = htb_lookup_leaf(hprio, prio); @@ -886,16 +870,16 @@ next: if (likely(skb != NULL)) { bstats_update(&cl->bstats, skb); - cl->un.leaf.deficit[level] -= qdisc_pkt_len(skb); - if (cl->un.leaf.deficit[level] < 0) { - cl->un.leaf.deficit[level] += cl->quantum; - htb_next_rb_node(level ? &cl->parent->un.inner.clprio[prio].ptr : + cl->leaf.deficit[level] -= qdisc_pkt_len(skb); + if (cl->leaf.deficit[level] < 0) { + cl->leaf.deficit[level] += cl->quantum; + htb_next_rb_node(level ? &cl->parent->inner.clprio[prio].ptr : &q->hlevel[0].hprio[prio].ptr); } /* this used to be after charge_class but this constelation * gives us slightly better performance */ - if (!cl->un.leaf.q->q.qlen) + if (!cl->leaf.q->q.qlen) htb_deactivate(q, cl); htb_charge_class(q, cl, level, skb); } @@ -972,10 +956,10 @@ static void htb_reset(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (cl->level) - memset(&cl->un.inner, 0, sizeof(cl->un.inner)); + memset(&cl->inner, 0, sizeof(cl->inner)); else { - if (cl->un.leaf.q) - qdisc_reset(cl->un.leaf.q); + if (cl->leaf.q) + qdisc_reset(cl->leaf.q); } cl->prio_activity = 0; cl->cmode = HTB_CAN_SEND; @@ -1098,8 +1082,8 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, */ tcm->tcm_parent = cl->parent ? cl->parent->common.classid : TC_H_ROOT; tcm->tcm_handle = cl->common.classid; - if (!cl->level && cl->un.leaf.q) - tcm->tcm_info = cl->un.leaf.q->handle; + if (!cl->level && cl->leaf.q) + tcm->tcm_info = cl->leaf.q->handle; nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) @@ -1142,9 +1126,9 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) }; __u32 qlen = 0; - if (!cl->level && cl->un.leaf.q) { - qlen = cl->un.leaf.q->q.qlen; - qs.backlog = cl->un.leaf.q->qstats.backlog; + if (!cl->level && cl->leaf.q) { + qlen = cl->leaf.q->q.qlen; + qs.backlog = cl->leaf.q->qstats.backlog; } cl->xstats.tokens = clamp_t(s64, PSCHED_NS2TICKS(cl->tokens), INT_MIN, INT_MAX); @@ -1172,14 +1156,14 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, cl->common.classid, extack)) == NULL) return -ENOBUFS; - *old = qdisc_replace(sch, new, &cl->un.leaf.q); + *old = qdisc_replace(sch, new, &cl->leaf.q); return 0; } static struct Qdisc *htb_leaf(struct Qdisc *sch, unsigned long arg) { struct htb_class *cl = (struct htb_class *)arg; - return !cl->level ? cl->un.leaf.q : NULL; + return !cl->level ? cl->leaf.q : NULL; } static void htb_qlen_notify(struct Qdisc *sch, unsigned long arg) @@ -1205,15 +1189,15 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, { struct htb_class *parent = cl->parent; - WARN_ON(cl->level || !cl->un.leaf.q || cl->prio_activity); + WARN_ON(cl->level || !cl->leaf.q || cl->prio_activity); if (parent->cmode != HTB_CAN_SEND) htb_safe_rb_erase(&parent->pq_node, &q->hlevel[parent->level].wait_pq); parent->level = 0; - memset(&parent->un.inner, 0, sizeof(parent->un.inner)); - parent->un.leaf.q = new_q ? new_q : &noop_qdisc; + memset(&parent->inner, 0, sizeof(parent->inner)); + parent->leaf.q = new_q ? new_q : &noop_qdisc; parent->tokens = parent->buffer; parent->ctokens = parent->cbuffer; parent->t_c = ktime_get_ns(); @@ -1223,8 +1207,8 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) { if (!cl->level) { - WARN_ON(!cl->un.leaf.q); - qdisc_destroy(cl->un.leaf.q); + WARN_ON(!cl->leaf.q); + qdisc_put(cl->leaf.q); } gen_kill_estimator(&cl->rate_est); tcf_block_put(cl->block); @@ -1286,11 +1270,11 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) sch_tree_lock(sch); if (!cl->level) { - unsigned int qlen = cl->un.leaf.q->q.qlen; - unsigned int backlog = cl->un.leaf.q->qstats.backlog; + unsigned int qlen = cl->leaf.q->q.qlen; + unsigned int backlog = cl->leaf.q->qstats.backlog; - qdisc_reset(cl->un.leaf.q); - qdisc_tree_reduce_backlog(cl->un.leaf.q, qlen, backlog); + qdisc_reset(cl->leaf.q); + qdisc_tree_reduce_backlog(cl->leaf.q, qlen, backlog); } /* delete from hash and active; remainder in destroy_class */ @@ -1419,13 +1403,13 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, classid, NULL); sch_tree_lock(sch); if (parent && !parent->level) { - unsigned int qlen = parent->un.leaf.q->q.qlen; - unsigned int backlog = parent->un.leaf.q->qstats.backlog; + unsigned int qlen = parent->leaf.q->q.qlen; + unsigned int backlog = parent->leaf.q->qstats.backlog; /* turn parent into inner node */ - qdisc_reset(parent->un.leaf.q); - qdisc_tree_reduce_backlog(parent->un.leaf.q, qlen, backlog); - qdisc_destroy(parent->un.leaf.q); + qdisc_reset(parent->leaf.q); + qdisc_tree_reduce_backlog(parent->leaf.q, qlen, backlog); + qdisc_put(parent->leaf.q); if (parent->prio_activity) htb_deactivate(q, parent); @@ -1436,10 +1420,10 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, } parent->level = (parent->parent ? parent->parent->level : TC_HTB_MAXDEPTH) - 1; - memset(&parent->un.inner, 0, sizeof(parent->un.inner)); + memset(&parent->inner, 0, sizeof(parent->inner)); } /* leaf (we) needs elementary qdisc */ - cl->un.leaf.q = new_q ? new_q : &noop_qdisc; + cl->leaf.q = new_q ? new_q : &noop_qdisc; cl->common.classid = classid; cl->parent = parent; @@ -1455,8 +1439,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, qdisc_class_hash_insert(&q->clhash, &cl->common); if (parent) parent->children++; - if (cl->un.leaf.q != &noop_qdisc) - qdisc_hash_add(cl->un.leaf.q, true); + if (cl->leaf.q != &noop_qdisc) + qdisc_hash_add(cl->leaf.q, true); } else { if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, @@ -1478,7 +1462,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64); /* it used to be a nasty bug here, we have to check that node - * is really leaf before changing cl->un.leaf ! + * is really leaf before changing cl->leaf ! */ if (!cl->level) { u64 quantum = cl->rate.rate_bytes_ps; diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index d6b8ae4ed7a3..203659bc3906 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -38,9 +38,8 @@ static int mq_offload(struct Qdisc *sch, enum tc_mq_command cmd) return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQ, &opt); } -static void mq_offload_stats(struct Qdisc *sch) +static int mq_offload_stats(struct Qdisc *sch) { - struct net_device *dev = qdisc_dev(sch); struct tc_mq_qopt_offload opt = { .command = TC_MQ_STATS, .handle = sch->handle, @@ -50,8 +49,7 @@ static void mq_offload_stats(struct Qdisc *sch) }, }; - if (tc_can_offload(dev) && dev->netdev_ops->ndo_setup_tc) - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQ, &opt); + return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_MQ, &opt); } static void mq_destroy(struct Qdisc *sch) @@ -65,7 +63,7 @@ static void mq_destroy(struct Qdisc *sch) if (!priv->qdiscs) return; for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++) - qdisc_destroy(priv->qdiscs[ntx]); + qdisc_put(priv->qdiscs[ntx]); kfree(priv->qdiscs); } @@ -119,7 +117,7 @@ static void mq_attach(struct Qdisc *sch) qdisc = priv->qdiscs[ntx]; old = dev_graft_qdisc(qdisc->dev_queue, qdisc); if (old) - qdisc_destroy(old); + qdisc_put(old); #ifdef CONFIG_NET_SCHED if (ntx < dev->real_num_tx_queues) qdisc_hash_add(qdisc, false); @@ -171,9 +169,8 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) spin_unlock_bh(qdisc_lock(qdisc)); } - mq_offload_stats(sch); - return 0; + return mq_offload_stats(sch); } static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl) @@ -196,6 +193,7 @@ static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); + struct tc_mq_qopt_offload graft_offload; struct net_device *dev = qdisc_dev(sch); if (dev->flags & IFF_UP) @@ -206,6 +204,14 @@ static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; if (dev->flags & IFF_UP) dev_activate(dev); + + graft_offload.handle = sch->handle; + graft_offload.graft_params.queue = cl - 1; + graft_offload.graft_params.child_handle = new ? new->handle : 0; + graft_offload.command = TC_MQ_GRAFT; + + qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, *old, + TC_SETUP_QDISC_MQ, &graft_offload, extack); return 0; } diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 0e9d761cdd80..d364e63c396d 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -40,7 +40,7 @@ static void mqprio_destroy(struct Qdisc *sch) for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++) - qdisc_destroy(priv->qdiscs[ntx]); + qdisc_put(priv->qdiscs[ntx]); kfree(priv->qdiscs); } @@ -300,7 +300,7 @@ static void mqprio_attach(struct Qdisc *sch) qdisc = priv->qdiscs[ntx]; old = dev_graft_qdisc(qdisc->dev_queue, qdisc); if (old) - qdisc_destroy(old); + qdisc_put(old); if (ntx < dev->real_num_tx_queues) qdisc_hash_add(qdisc, false); } diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 1da7ea8de0ad..7410ce4d0321 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -175,7 +175,7 @@ multiq_destroy(struct Qdisc *sch) tcf_block_put(q->block); for (band = 0; band < q->bands; band++) - qdisc_destroy(q->queues[band]); + qdisc_put(q->queues[band]); kfree(q->queues); } @@ -204,7 +204,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, q->queues[i] = &noop_qdisc; qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog); - qdisc_destroy(child); + qdisc_put(child); } } @@ -228,7 +228,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog); - qdisc_destroy(old); + qdisc_put(old); } sch_tree_unlock(sch); } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index ad18a2052416..75046ec72144 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -77,6 +77,10 @@ struct netem_sched_data { /* internal t(ime)fifo qdisc uses t_root and sch->limit */ struct rb_root t_root; + /* a linear queue; reduces rbtree rebalancing when jitter is low */ + struct sk_buff *t_head; + struct sk_buff *t_tail; + /* optional qdisc for classful handling (NULL at netem init) */ struct Qdisc *qdisc; @@ -369,26 +373,39 @@ static void tfifo_reset(struct Qdisc *sch) rb_erase(&skb->rbnode, &q->t_root); rtnl_kfree_skbs(skb, skb); } + + rtnl_kfree_skbs(q->t_head, q->t_tail); + q->t_head = NULL; + q->t_tail = NULL; } static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); u64 tnext = netem_skb_cb(nskb)->time_to_send; - struct rb_node **p = &q->t_root.rb_node, *parent = NULL; - - while (*p) { - struct sk_buff *skb; - parent = *p; - skb = rb_to_skb(parent); - if (tnext >= netem_skb_cb(skb)->time_to_send) - p = &parent->rb_right; + if (!q->t_tail || tnext >= netem_skb_cb(q->t_tail)->time_to_send) { + if (q->t_tail) + q->t_tail->next = nskb; else - p = &parent->rb_left; + q->t_head = nskb; + q->t_tail = nskb; + } else { + struct rb_node **p = &q->t_root.rb_node, *parent = NULL; + + while (*p) { + struct sk_buff *skb; + + parent = *p; + skb = rb_to_skb(parent); + if (tnext >= netem_skb_cb(skb)->time_to_send) + p = &parent->rb_right; + else + p = &parent->rb_left; + } + rb_link_node(&nskb->rbnode, parent, p); + rb_insert_color(&nskb->rbnode, &q->t_root); } - rb_link_node(&nskb->rbnode, parent, p); - rb_insert_color(&nskb->rbnode, &q->t_root); sch->q.qlen++; } @@ -412,16 +429,6 @@ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch, return segs; } -static void netem_enqueue_skb_head(struct qdisc_skb_head *qh, struct sk_buff *skb) -{ - skb->next = qh->head; - - if (!qh->head) - qh->tail = skb; - qh->head = skb; - qh->qlen++; -} - /* * Insert one skb into qdisc. * Note: parent depends on return value to account for queue length. @@ -441,6 +448,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, int count = 1; int rc = NET_XMIT_SUCCESS; + /* Do not fool qdisc_drop_all() */ + skb->prev = NULL; + /* Random duplication */ if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor)) ++count; @@ -540,9 +550,16 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, t_skb = skb_rb_last(&q->t_root); t_last = netem_skb_cb(t_skb); if (!last || - t_last->time_to_send > last->time_to_send) { + t_last->time_to_send > last->time_to_send) + last = t_last; + } + if (q->t_tail) { + struct netem_skb_cb *t_last = + netem_skb_cb(q->t_tail); + + if (!last || + t_last->time_to_send > last->time_to_send) last = t_last; - } } if (last) { @@ -570,7 +587,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, cb->time_to_send = ktime_get_ns(); q->counter = 0; - netem_enqueue_skb_head(&sch->q, skb); + __qdisc_enqueue_head(skb, &sch->q); sch->qstats.requeues++; } @@ -578,7 +595,7 @@ finish_segs: if (segs) { while (segs) { skb2 = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; last_len = segs->len; rc = qdisc_enqueue(segs, sch, to_free); @@ -621,11 +638,38 @@ static void get_slot_next(struct netem_sched_data *q, u64 now) q->slot.bytes_left = q->slot_config.max_bytes; } +static struct sk_buff *netem_peek(struct netem_sched_data *q) +{ + struct sk_buff *skb = skb_rb_first(&q->t_root); + u64 t1, t2; + + if (!skb) + return q->t_head; + if (!q->t_head) + return skb; + + t1 = netem_skb_cb(skb)->time_to_send; + t2 = netem_skb_cb(q->t_head)->time_to_send; + if (t1 < t2) + return skb; + return q->t_head; +} + +static void netem_erase_head(struct netem_sched_data *q, struct sk_buff *skb) +{ + if (skb == q->t_head) { + q->t_head = skb->next; + if (!q->t_head) + q->t_tail = NULL; + } else { + rb_erase(&skb->rbnode, &q->t_root); + } +} + static struct sk_buff *netem_dequeue(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; - struct rb_node *p; tfifo_dequeue: skb = __qdisc_dequeue_head(&sch->q); @@ -635,20 +679,18 @@ deliver: qdisc_bstats_update(sch, skb); return skb; } - p = rb_first(&q->t_root); - if (p) { + skb = netem_peek(q); + if (skb) { u64 time_to_send; u64 now = ktime_get_ns(); - skb = rb_to_skb(p); - /* if more time remaining? */ time_to_send = netem_skb_cb(skb)->time_to_send; if (q->slot.slot_next && q->slot.slot_next < time_to_send) get_slot_next(q, now); - if (time_to_send <= now && q->slot.slot_next <= now) { - rb_erase(p, &q->t_root); + if (time_to_send <= now && q->slot.slot_next <= now) { + netem_erase_head(q, skb); sch->q.qlen--; qdisc_qstats_backlog_dec(sch, skb); skb->next = NULL; @@ -658,15 +700,6 @@ deliver: */ skb->dev = qdisc_dev(sch); -#ifdef CONFIG_NET_CLS_ACT - /* - * If it's at ingress let's pretend the delay is - * from the network (tstamp will be updated). - */ - if (skb->tc_redirected && skb->tc_from_ingress) - skb->tstamp = 0; -#endif - if (q->slot.slot_next) { q->slot.packets_left--; q->slot.bytes_left -= qdisc_pkt_len(skb); @@ -1032,7 +1065,7 @@ static void netem_destroy(struct Qdisc *sch) qdisc_watchdog_cancel(&q->watchdog); if (q->qdisc) - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); dist_free(q->delay_dist); dist_free(q->slot_dist); } diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 18d30bb86881..d1429371592f 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -110,8 +110,8 @@ static bool drop_early(struct Qdisc *sch, u32 packet_size) /* If current delay is less than half of target, and * if drop prob is low already, disable early_drop */ - if ((q->vars.qdelay < q->params.target / 2) - && (q->vars.prob < MAX_PROB / 5)) + if ((q->vars.qdelay < q->params.target / 2) && + (q->vars.prob < MAX_PROB / 5)) return false; /* If we have fewer than 2 mtu-sized packets, disable drop_early, @@ -209,7 +209,8 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt, /* tupdate is in jiffies */ if (tb[TCA_PIE_TUPDATE]) - q->params.tupdate = usecs_to_jiffies(nla_get_u32(tb[TCA_PIE_TUPDATE])); + q->params.tupdate = + usecs_to_jiffies(nla_get_u32(tb[TCA_PIE_TUPDATE])); if (tb[TCA_PIE_LIMIT]) { u32 limit = nla_get_u32(tb[TCA_PIE_LIMIT]); @@ -247,7 +248,6 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt, static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb) { - struct pie_sched_data *q = qdisc_priv(sch); int qlen = sch->qstats.backlog; /* current queue size in bytes */ @@ -294,9 +294,9 @@ static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb) * dq_count to 0 to re-enter the if block when the next * packet is dequeued */ - if (qlen < QUEUE_THRESHOLD) + if (qlen < QUEUE_THRESHOLD) { q->vars.dq_count = DQCOUNT_INVALID; - else { + } else { q->vars.dq_count = 0; q->vars.dq_tstamp = psched_get_time(); } @@ -370,7 +370,7 @@ static void calculate_probability(struct Qdisc *sch) oldprob = q->vars.prob; /* to ensure we increase probability in steps of no more than 2% */ - if (delta > (s32) (MAX_PROB / (100 / 2)) && + if (delta > (s32)(MAX_PROB / (100 / 2)) && q->vars.prob >= MAX_PROB / 10) delta = (MAX_PROB / 100) * 2; @@ -405,7 +405,7 @@ static void calculate_probability(struct Qdisc *sch) * delay is 0 for 2 consecutive Tupdate periods. */ - if ((qdelay == 0) && (qdelay_old == 0) && update_prob) + if (qdelay == 0 && qdelay_old == 0 && update_prob) q->vars.prob = (q->vars.prob * 98) / 100; q->vars.qdelay = qdelay; @@ -419,8 +419,8 @@ static void calculate_probability(struct Qdisc *sch) */ if ((q->vars.qdelay < q->params.target / 2) && (q->vars.qdelay_old < q->params.target / 2) && - (q->vars.prob == 0) && - (q->vars.avg_dq_rate > 0)) + q->vars.prob == 0 && + q->vars.avg_dq_rate > 0) pie_vars_init(&q->vars); } @@ -437,7 +437,6 @@ static void pie_timer(struct timer_list *t) if (q->params.tupdate) mod_timer(&q->adapt_timer, jiffies + q->params.tupdate); spin_unlock(root_lock); - } static int pie_init(struct Qdisc *sch, struct nlattr *opt, @@ -469,15 +468,16 @@ static int pie_dump(struct Qdisc *sch, struct sk_buff *skb) struct nlattr *opts; opts = nla_nest_start(skb, TCA_OPTIONS); - if (opts == NULL) + if (!opts) goto nla_put_failure; /* convert target from pschedtime to us */ if (nla_put_u32(skb, TCA_PIE_TARGET, - ((u32) PSCHED_TICKS2NS(q->params.target)) / + ((u32)PSCHED_TICKS2NS(q->params.target)) / NSEC_PER_USEC) || nla_put_u32(skb, TCA_PIE_LIMIT, sch->limit) || - nla_put_u32(skb, TCA_PIE_TUPDATE, jiffies_to_usecs(q->params.tupdate)) || + nla_put_u32(skb, TCA_PIE_TUPDATE, + jiffies_to_usecs(q->params.tupdate)) || nla_put_u32(skb, TCA_PIE_ALPHA, q->params.alpha) || nla_put_u32(skb, TCA_PIE_BETA, q->params.beta) || nla_put_u32(skb, TCA_PIE_ECN, q->params.ecn) || @@ -489,7 +489,6 @@ static int pie_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_failure: nla_nest_cancel(skb, opts); return -1; - } static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) @@ -497,7 +496,7 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) struct pie_sched_data *q = qdisc_priv(sch); struct tc_pie_xstats st = { .prob = q->vars.prob, - .delay = ((u32) PSCHED_TICKS2NS(q->vars.qdelay)) / + .delay = ((u32)PSCHED_TICKS2NS(q->vars.qdelay)) / NSEC_PER_USEC, /* unscale and return dq_rate in bytes per sec */ .avg_dq_rate = q->vars.avg_dq_rate * @@ -514,8 +513,7 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) static struct sk_buff *pie_qdisc_dequeue(struct Qdisc *sch) { - struct sk_buff *skb; - skb = qdisc_dequeue_head(sch); + struct sk_buff *skb = qdisc_dequeue_head(sch); if (!skb) return NULL; @@ -527,6 +525,7 @@ static struct sk_buff *pie_qdisc_dequeue(struct Qdisc *sch) static void pie_reset(struct Qdisc *sch) { struct pie_sched_data *q = qdisc_priv(sch); + qdisc_reset_queue(sch); pie_vars_init(&q->vars); } @@ -534,6 +533,7 @@ static void pie_reset(struct Qdisc *sch) static void pie_destroy(struct Qdisc *sch) { struct pie_sched_data *q = qdisc_priv(sch); + q->params.tupdate = 0; del_timer_sync(&q->adapt_timer); } diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 222e53d3d27a..cdf68706e40f 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -175,7 +175,7 @@ prio_destroy(struct Qdisc *sch) tcf_block_put(q->block); prio_offload(sch, NULL); for (prio = 0; prio < q->bands; prio++) - qdisc_destroy(q->queues[prio]); + qdisc_put(q->queues[prio]); } static int prio_tune(struct Qdisc *sch, struct nlattr *opt, @@ -205,7 +205,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt, extack); if (!queues[i]) { while (i > oldbands) - qdisc_destroy(queues[--i]); + qdisc_put(queues[--i]); return -ENOMEM; } } @@ -220,7 +220,6 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt, qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog); - qdisc_destroy(child); } for (i = oldbands; i < q->bands; i++) { @@ -230,6 +229,9 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt, } sch_tree_unlock(sch); + + for (i = q->bands; i < oldbands; i++) + qdisc_put(q->queues[i]); return 0; } @@ -251,7 +253,6 @@ static int prio_init(struct Qdisc *sch, struct nlattr *opt, static int prio_dump_offload(struct Qdisc *sch) { - struct net_device *dev = qdisc_dev(sch); struct tc_prio_qopt_offload hw_stats = { .command = TC_PRIO_STATS, .handle = sch->handle, @@ -263,21 +264,8 @@ static int prio_dump_offload(struct Qdisc *sch) }, }, }; - int err; - - sch->flags &= ~TCQ_F_OFFLOADED; - if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) - return 0; - - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_PRIO, - &hw_stats); - if (err == -EOPNOTSUPP) - return 0; - if (!err) - sch->flags |= TCQ_F_OFFLOADED; - - return err; + return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_PRIO, &hw_stats); } static int prio_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -309,43 +297,22 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, { struct prio_sched_data *q = qdisc_priv(sch); struct tc_prio_qopt_offload graft_offload; - struct net_device *dev = qdisc_dev(sch); unsigned long band = arg - 1; - bool any_qdisc_is_offloaded; - int err; if (new == NULL) new = &noop_qdisc; *old = qdisc_replace(sch, new, &q->queues[band]); - if (!tc_can_offload(dev)) - return 0; - graft_offload.handle = sch->handle; graft_offload.parent = sch->parent; graft_offload.graft_params.band = band; graft_offload.graft_params.child_handle = new->handle; graft_offload.command = TC_PRIO_GRAFT; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_PRIO, - &graft_offload); - - /* Don't report error if the graft is part of destroy operation. */ - if (err && new != &noop_qdisc) { - /* Don't report error if the parent, the old child and the new - * one are not offloaded. - */ - any_qdisc_is_offloaded = sch->flags & TCQ_F_OFFLOADED; - any_qdisc_is_offloaded |= new->flags & TCQ_F_OFFLOADED; - if (*old) - any_qdisc_is_offloaded |= (*old)->flags & - TCQ_F_OFFLOADED; - - if (any_qdisc_is_offloaded) - NL_SET_ERR_MSG(extack, "Offloading graft operation failed."); - } - + qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, *old, + TC_SETUP_QDISC_PRIO, &graft_offload, + extack); return 0; } diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index bb1a9c11fc54..dc37c4ead439 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -526,7 +526,7 @@ set_change_agg: return 0; destroy_class: - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); kfree(cl); return err; } @@ -537,7 +537,7 @@ static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl) qfq_rm_from_agg(q, cl); gen_kill_estimator(&cl->rate_est); - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); kfree(cl); } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 56c181c3feeb..9df9942340ea 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -166,7 +166,9 @@ static int red_offload(struct Qdisc *sch, bool enable) opt.set.min = q->parms.qth_min >> q->parms.Wlog; opt.set.max = q->parms.qth_max >> q->parms.Wlog; opt.set.probability = q->parms.max_P; + opt.set.limit = q->limit; opt.set.is_ecn = red_use_ecn(q); + opt.set.is_harddrop = red_use_harddrop(q); opt.set.qstats = &sch->qstats; } else { opt.command = TC_RED_DESTROY; @@ -181,7 +183,7 @@ static void red_destroy(struct Qdisc *sch) del_timer_sync(&q->adapt_timer); red_offload(sch, false); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); } static const struct nla_policy red_policy[TCA_RED_MAX + 1] = { @@ -193,10 +195,10 @@ static const struct nla_policy red_policy[TCA_RED_MAX + 1] = { static int red_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + struct Qdisc *old_child = NULL, *child = NULL; struct red_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_RED_MAX + 1]; struct tc_red_qopt *ctl; - struct Qdisc *child = NULL; int err; u32 max_P; @@ -233,7 +235,7 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt, if (child) { qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, q->qdisc->qstats.backlog); - qdisc_destroy(q->qdisc); + old_child = q->qdisc; q->qdisc = child; } @@ -252,7 +254,11 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt, red_start_of_idle_period(&q->vars); sch_tree_unlock(sch); + red_offload(sch, true); + + if (old_child) + qdisc_put(old_child); return 0; } @@ -279,9 +285,8 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt, return red_change(sch, opt, extack); } -static int red_dump_offload_stats(struct Qdisc *sch, struct tc_red_qopt *opt) +static int red_dump_offload_stats(struct Qdisc *sch) { - struct net_device *dev = qdisc_dev(sch); struct tc_red_qopt_offload hw_stats = { .command = TC_RED_STATS, .handle = sch->handle, @@ -291,22 +296,8 @@ static int red_dump_offload_stats(struct Qdisc *sch, struct tc_red_qopt *opt) .stats.qstats = &sch->qstats, }, }; - int err; - - sch->flags &= ~TCQ_F_OFFLOADED; - - if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) - return 0; - - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, - &hw_stats); - if (err == -EOPNOTSUPP) - return 0; - if (!err) - sch->flags |= TCQ_F_OFFLOADED; - - return err; + return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_RED, &hw_stats); } static int red_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -324,7 +315,7 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) }; int err; - err = red_dump_offload_stats(sch, &opt); + err = red_dump_offload_stats(sch); if (err) goto nla_put_failure; @@ -377,6 +368,21 @@ static int red_dump_class(struct Qdisc *sch, unsigned long cl, return 0; } +static void red_graft_offload(struct Qdisc *sch, + struct Qdisc *new, struct Qdisc *old, + struct netlink_ext_ack *extack) +{ + struct tc_red_qopt_offload graft_offload = { + .handle = sch->handle, + .parent = sch->parent, + .child_handle = new->handle, + .command = TC_RED_GRAFT, + }; + + qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, old, + TC_SETUP_QDISC_RED, &graft_offload, extack); +} + static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { @@ -386,6 +392,8 @@ static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, new = &noop_qdisc; *old = qdisc_replace(sch, new, &q->qdisc); + + red_graft_offload(sch, new, *old, extack); return 0; } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 7cbdad8419b7..bab506b01a32 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -469,7 +469,7 @@ static void sfb_destroy(struct Qdisc *sch) struct sfb_sched_data *q = qdisc_priv(sch); tcf_block_put(q->block); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); } static const struct nla_policy sfb_policy[TCA_SFB_MAX + 1] = { @@ -523,7 +523,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, q->qdisc->qstats.backlog); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); q->qdisc = child; q->rehash_interval = msecs_to_jiffies(ctl->rehash_interval); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c new file mode 100644 index 000000000000..206e4dbed12f --- /dev/null +++ b/net/sched/sch_taprio.c @@ -0,0 +1,962 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* net/sched/sch_taprio.c Time Aware Priority Scheduler + * + * Authors: Vinicius Costa Gomes <vinicius.gomes@intel.com> + * + */ + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/list.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <linux/module.h> +#include <linux/spinlock.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> +#include <net/pkt_cls.h> +#include <net/sch_generic.h> + +#define TAPRIO_ALL_GATES_OPEN -1 + +struct sched_entry { + struct list_head list; + + /* The instant that this entry "closes" and the next one + * should open, the qdisc will make some effort so that no + * packet leaves after this time. + */ + ktime_t close_time; + atomic_t budget; + int index; + u32 gate_mask; + u32 interval; + u8 command; +}; + +struct taprio_sched { + struct Qdisc **qdiscs; + struct Qdisc *root; + s64 base_time; + int clockid; + int picos_per_byte; /* Using picoseconds because for 10Gbps+ + * speeds it's sub-nanoseconds per byte + */ + size_t num_entries; + + /* Protects the update side of the RCU protected current_entry */ + spinlock_t current_entry_lock; + struct sched_entry __rcu *current_entry; + struct list_head entries; + ktime_t (*get_time)(void); + struct hrtimer advance_timer; +}; + +static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct Qdisc *child; + int queue; + + queue = skb_get_queue_mapping(skb); + + child = q->qdiscs[queue]; + if (unlikely(!child)) + return qdisc_drop(skb, sch, to_free); + + qdisc_qstats_backlog_inc(sch, skb); + sch->q.qlen++; + + return qdisc_enqueue(skb, child, to_free); +} + +static struct sk_buff *taprio_peek(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sched_entry *entry; + struct sk_buff *skb; + u32 gate_mask; + int i; + + rcu_read_lock(); + entry = rcu_dereference(q->current_entry); + gate_mask = entry ? entry->gate_mask : -1; + rcu_read_unlock(); + + if (!gate_mask) + return NULL; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct Qdisc *child = q->qdiscs[i]; + int prio; + u8 tc; + + if (unlikely(!child)) + continue; + + skb = child->ops->peek(child); + if (!skb) + continue; + + prio = skb->priority; + tc = netdev_get_prio_tc_map(dev, prio); + + if (!(gate_mask & BIT(tc))) + return NULL; + + return skb; + } + + return NULL; +} + +static inline int length_to_duration(struct taprio_sched *q, int len) +{ + return (len * q->picos_per_byte) / 1000; +} + +static struct sk_buff *taprio_dequeue(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sched_entry *entry; + struct sk_buff *skb; + u32 gate_mask; + int i; + + rcu_read_lock(); + entry = rcu_dereference(q->current_entry); + /* if there's no entry, it means that the schedule didn't + * start yet, so force all gates to be open, this is in + * accordance to IEEE 802.1Qbv-2015 Section 8.6.9.4.5 + * "AdminGateSates" + */ + gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; + rcu_read_unlock(); + + if (!gate_mask) + return NULL; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct Qdisc *child = q->qdiscs[i]; + ktime_t guard; + int prio; + int len; + u8 tc; + + if (unlikely(!child)) + continue; + + skb = child->ops->peek(child); + if (!skb) + continue; + + prio = skb->priority; + tc = netdev_get_prio_tc_map(dev, prio); + + if (!(gate_mask & BIT(tc))) + continue; + + len = qdisc_pkt_len(skb); + guard = ktime_add_ns(q->get_time(), + length_to_duration(q, len)); + + /* In the case that there's no gate entry, there's no + * guard band ... + */ + if (gate_mask != TAPRIO_ALL_GATES_OPEN && + ktime_after(guard, entry->close_time)) + return NULL; + + /* ... and no budget. */ + if (gate_mask != TAPRIO_ALL_GATES_OPEN && + atomic_sub_return(len, &entry->budget) < 0) + return NULL; + + skb = child->ops->dequeue(child); + if (unlikely(!skb)) + return NULL; + + qdisc_bstats_update(sch, skb); + qdisc_qstats_backlog_dec(sch, skb); + sch->q.qlen--; + + return skb; + } + + return NULL; +} + +static bool should_restart_cycle(const struct taprio_sched *q, + const struct sched_entry *entry) +{ + WARN_ON(!entry); + + return list_is_last(&entry->list, &q->entries); +} + +static enum hrtimer_restart advance_sched(struct hrtimer *timer) +{ + struct taprio_sched *q = container_of(timer, struct taprio_sched, + advance_timer); + struct sched_entry *entry, *next; + struct Qdisc *sch = q->root; + ktime_t close_time; + + spin_lock(&q->current_entry_lock); + entry = rcu_dereference_protected(q->current_entry, + lockdep_is_held(&q->current_entry_lock)); + + /* This is the case that it's the first time that the schedule + * runs, so it only happens once per schedule. The first entry + * is pre-calculated during the schedule initialization. + */ + if (unlikely(!entry)) { + next = list_first_entry(&q->entries, struct sched_entry, + list); + close_time = next->close_time; + goto first_run; + } + + if (should_restart_cycle(q, entry)) + next = list_first_entry(&q->entries, struct sched_entry, + list); + else + next = list_next_entry(entry, list); + + close_time = ktime_add_ns(entry->close_time, next->interval); + + next->close_time = close_time; + atomic_set(&next->budget, + (next->interval * 1000) / q->picos_per_byte); + +first_run: + rcu_assign_pointer(q->current_entry, next); + spin_unlock(&q->current_entry_lock); + + hrtimer_set_expires(&q->advance_timer, close_time); + + rcu_read_lock(); + __netif_schedule(sch); + rcu_read_unlock(); + + return HRTIMER_RESTART; +} + +static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { + [TCA_TAPRIO_SCHED_ENTRY_INDEX] = { .type = NLA_U32 }, + [TCA_TAPRIO_SCHED_ENTRY_CMD] = { .type = NLA_U8 }, + [TCA_TAPRIO_SCHED_ENTRY_GATE_MASK] = { .type = NLA_U32 }, + [TCA_TAPRIO_SCHED_ENTRY_INTERVAL] = { .type = NLA_U32 }, +}; + +static const struct nla_policy entry_list_policy[TCA_TAPRIO_SCHED_MAX + 1] = { + [TCA_TAPRIO_SCHED_ENTRY] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { + [TCA_TAPRIO_ATTR_PRIOMAP] = { + .len = sizeof(struct tc_mqprio_qopt) + }, + [TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST] = { .type = NLA_NESTED }, + [TCA_TAPRIO_ATTR_SCHED_BASE_TIME] = { .type = NLA_S64 }, + [TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] = { .type = NLA_NESTED }, + [TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 }, +}; + +static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, + struct netlink_ext_ack *extack) +{ + u32 interval = 0; + + if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD]) + entry->command = nla_get_u8( + tb[TCA_TAPRIO_SCHED_ENTRY_CMD]); + + if (tb[TCA_TAPRIO_SCHED_ENTRY_GATE_MASK]) + entry->gate_mask = nla_get_u32( + tb[TCA_TAPRIO_SCHED_ENTRY_GATE_MASK]); + + if (tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]) + interval = nla_get_u32( + tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]); + + if (interval == 0) { + NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry"); + return -EINVAL; + } + + entry->interval = interval; + + return 0; +} + +static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry, + int index, struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; + int err; + + err = nla_parse_nested(tb, TCA_TAPRIO_SCHED_ENTRY_MAX, n, + entry_policy, NULL); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Could not parse nested entry"); + return -EINVAL; + } + + entry->index = index; + + return fill_sched_entry(tb, entry, extack); +} + +/* Returns the number of entries in case of success */ +static int parse_sched_single_entry(struct nlattr *n, + struct taprio_sched *q, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb_entry[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; + struct nlattr *tb_list[TCA_TAPRIO_SCHED_MAX + 1] = { }; + struct sched_entry *entry; + bool found = false; + u32 index; + int err; + + err = nla_parse_nested(tb_list, TCA_TAPRIO_SCHED_MAX, + n, entry_list_policy, NULL); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Could not parse nested entry"); + return -EINVAL; + } + + if (!tb_list[TCA_TAPRIO_SCHED_ENTRY]) { + NL_SET_ERR_MSG(extack, "Single-entry must include an entry"); + return -EINVAL; + } + + err = nla_parse_nested(tb_entry, TCA_TAPRIO_SCHED_ENTRY_MAX, + tb_list[TCA_TAPRIO_SCHED_ENTRY], + entry_policy, NULL); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Could not parse nested entry"); + return -EINVAL; + } + + if (!tb_entry[TCA_TAPRIO_SCHED_ENTRY_INDEX]) { + NL_SET_ERR_MSG(extack, "Entry must specify an index\n"); + return -EINVAL; + } + + index = nla_get_u32(tb_entry[TCA_TAPRIO_SCHED_ENTRY_INDEX]); + if (index >= q->num_entries) { + NL_SET_ERR_MSG(extack, "Index for single entry exceeds number of entries in schedule"); + return -EINVAL; + } + + list_for_each_entry(entry, &q->entries, list) { + if (entry->index == index) { + found = true; + break; + } + } + + if (!found) { + NL_SET_ERR_MSG(extack, "Could not find entry"); + return -ENOENT; + } + + err = fill_sched_entry(tb_entry, entry, extack); + if (err < 0) + return err; + + return q->num_entries; +} + +static int parse_sched_list(struct nlattr *list, + struct taprio_sched *q, + struct netlink_ext_ack *extack) +{ + struct nlattr *n; + int err, rem; + int i = 0; + + if (!list) + return -EINVAL; + + nla_for_each_nested(n, list, rem) { + struct sched_entry *entry; + + if (nla_type(n) != TCA_TAPRIO_SCHED_ENTRY) { + NL_SET_ERR_MSG(extack, "Attribute is not of type 'entry'"); + continue; + } + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + NL_SET_ERR_MSG(extack, "Not enough memory for entry"); + return -ENOMEM; + } + + err = parse_sched_entry(n, entry, i, extack); + if (err < 0) { + kfree(entry); + return err; + } + + list_add_tail(&entry->list, &q->entries); + i++; + } + + q->num_entries = i; + + return i; +} + +/* Returns the number of entries in case of success */ +static int parse_taprio_opt(struct nlattr **tb, struct taprio_sched *q, + struct netlink_ext_ack *extack) +{ + int err = 0; + int clockid; + + if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST] && + tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY]) + return -EINVAL; + + if (tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] && q->num_entries == 0) + return -EINVAL; + + if (q->clockid == -1 && !tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) + return -EINVAL; + + if (tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]) + q->base_time = nla_get_s64( + tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]); + + if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { + clockid = nla_get_s32(tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]); + + /* We only support static clockids and we don't allow + * for it to be modified after the first init. + */ + if (clockid < 0 || (q->clockid != -1 && q->clockid != clockid)) + return -EINVAL; + + q->clockid = clockid; + } + + if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST]) + err = parse_sched_list( + tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], q, extack); + else if (tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY]) + err = parse_sched_single_entry( + tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY], q, extack); + + /* parse_sched_* return the number of entries in the schedule, + * a schedule with zero entries is an error. + */ + if (err == 0) { + NL_SET_ERR_MSG(extack, "The schedule should contain at least one entry"); + return -EINVAL; + } + + return err; +} + +static int taprio_parse_mqprio_opt(struct net_device *dev, + struct tc_mqprio_qopt *qopt, + struct netlink_ext_ack *extack) +{ + int i, j; + + if (!qopt) { + NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary"); + return -EINVAL; + } + + /* Verify num_tc is not out of max range */ + if (qopt->num_tc > TC_MAX_QUEUE) { + NL_SET_ERR_MSG(extack, "Number of traffic classes is outside valid range"); + return -EINVAL; + } + + /* taprio imposes that traffic classes map 1:n to tx queues */ + if (qopt->num_tc > dev->num_tx_queues) { + NL_SET_ERR_MSG(extack, "Number of traffic classes is greater than number of HW queues"); + return -EINVAL; + } + + /* Verify priority mapping uses valid tcs */ + for (i = 0; i < TC_BITMASK + 1; i++) { + if (qopt->prio_tc_map[i] >= qopt->num_tc) { + NL_SET_ERR_MSG(extack, "Invalid traffic class in priority to traffic class mapping"); + return -EINVAL; + } + } + + for (i = 0; i < qopt->num_tc; i++) { + unsigned int last = qopt->offset[i] + qopt->count[i]; + + /* Verify the queue count is in tx range being equal to the + * real_num_tx_queues indicates the last queue is in use. + */ + if (qopt->offset[i] >= dev->num_tx_queues || + !qopt->count[i] || + last > dev->real_num_tx_queues) { + NL_SET_ERR_MSG(extack, "Invalid queue in traffic class to queue mapping"); + return -EINVAL; + } + + /* Verify that the offset and counts do not overlap */ + for (j = i + 1; j < qopt->num_tc; j++) { + if (last > qopt->offset[j]) { + NL_SET_ERR_MSG(extack, "Detected overlap in the traffic class to queue mapping"); + return -EINVAL; + } + } + } + + return 0; +} + +static ktime_t taprio_get_start_time(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct sched_entry *entry; + ktime_t now, base, cycle; + s64 n; + + base = ns_to_ktime(q->base_time); + cycle = 0; + + /* Calculate the cycle_time, by summing all the intervals. + */ + list_for_each_entry(entry, &q->entries, list) + cycle = ktime_add_ns(cycle, entry->interval); + + if (!cycle) + return base; + + now = q->get_time(); + + if (ktime_after(base, now)) + return base; + + /* Schedule the start time for the beginning of the next + * cycle. + */ + n = div64_s64(ktime_sub_ns(now, base), cycle); + + return ktime_add_ns(base, (n + 1) * cycle); +} + +static void taprio_start_sched(struct Qdisc *sch, ktime_t start) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct sched_entry *first; + unsigned long flags; + + spin_lock_irqsave(&q->current_entry_lock, flags); + + first = list_first_entry(&q->entries, struct sched_entry, + list); + + first->close_time = ktime_add_ns(start, first->interval); + atomic_set(&first->budget, + (first->interval * 1000) / q->picos_per_byte); + rcu_assign_pointer(q->current_entry, NULL); + + spin_unlock_irqrestore(&q->current_entry_lock, flags); + + hrtimer_start(&q->advance_timer, start, HRTIMER_MODE_ABS); +} + +static int taprio_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_TAPRIO_ATTR_MAX + 1] = { }; + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_mqprio_qopt *mqprio = NULL; + struct ethtool_link_ksettings ecmd; + int i, err, size; + s64 link_speed; + ktime_t start; + + err = nla_parse_nested(tb, TCA_TAPRIO_ATTR_MAX, opt, + taprio_policy, extack); + if (err < 0) + return err; + + err = -EINVAL; + if (tb[TCA_TAPRIO_ATTR_PRIOMAP]) + mqprio = nla_data(tb[TCA_TAPRIO_ATTR_PRIOMAP]); + + err = taprio_parse_mqprio_opt(dev, mqprio, extack); + if (err < 0) + return err; + + /* A schedule with less than one entry is an error */ + size = parse_taprio_opt(tb, q, extack); + if (size < 0) + return size; + + hrtimer_init(&q->advance_timer, q->clockid, HRTIMER_MODE_ABS); + q->advance_timer.function = advance_sched; + + switch (q->clockid) { + case CLOCK_REALTIME: + q->get_time = ktime_get_real; + break; + case CLOCK_MONOTONIC: + q->get_time = ktime_get; + break; + case CLOCK_BOOTTIME: + q->get_time = ktime_get_boottime; + break; + case CLOCK_TAI: + q->get_time = ktime_get_clocktai; + break; + default: + return -ENOTSUPP; + } + + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *dev_queue; + struct Qdisc *qdisc; + + dev_queue = netdev_get_tx_queue(dev, i); + qdisc = qdisc_create_dflt(dev_queue, + &pfifo_qdisc_ops, + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(i + 1)), + extack); + if (!qdisc) + return -ENOMEM; + + if (i < dev->real_num_tx_queues) + qdisc_hash_add(qdisc, false); + + q->qdiscs[i] = qdisc; + } + + if (mqprio) { + netdev_set_num_tc(dev, mqprio->num_tc); + for (i = 0; i < mqprio->num_tc; i++) + netdev_set_tc_queue(dev, i, + mqprio->count[i], + mqprio->offset[i]); + + /* Always use supplied priority mappings */ + for (i = 0; i < TC_BITMASK + 1; i++) + netdev_set_prio_tc_map(dev, i, + mqprio->prio_tc_map[i]); + } + + if (!__ethtool_get_link_ksettings(dev, &ecmd)) + link_speed = ecmd.base.speed; + else + link_speed = SPEED_1000; + + q->picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8, + link_speed * 1000 * 1000); + + start = taprio_get_start_time(sch); + if (!start) + return 0; + + taprio_start_sched(sch, start); + + return 0; +} + +static void taprio_destroy(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sched_entry *entry, *n; + unsigned int i; + + hrtimer_cancel(&q->advance_timer); + + if (q->qdiscs) { + for (i = 0; i < dev->num_tx_queues && q->qdiscs[i]; i++) + qdisc_put(q->qdiscs[i]); + + kfree(q->qdiscs); + } + q->qdiscs = NULL; + + netdev_set_num_tc(dev, 0); + + list_for_each_entry_safe(entry, n, &q->entries, list) { + list_del(&entry->list); + kfree(entry); + } +} + +static int taprio_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + + INIT_LIST_HEAD(&q->entries); + spin_lock_init(&q->current_entry_lock); + + /* We may overwrite the configuration later */ + hrtimer_init(&q->advance_timer, CLOCK_TAI, HRTIMER_MODE_ABS); + + q->root = sch; + + /* We only support static clockids. Use an invalid value as default + * and get the valid one on taprio_change(). + */ + q->clockid = -1; + + if (sch->parent != TC_H_ROOT) + return -EOPNOTSUPP; + + if (!netif_is_multiqueue(dev)) + return -EOPNOTSUPP; + + /* pre-allocate qdisc, attachment can't fail */ + q->qdiscs = kcalloc(dev->num_tx_queues, + sizeof(q->qdiscs[0]), + GFP_KERNEL); + + if (!q->qdiscs) + return -ENOMEM; + + if (!opt) + return -EINVAL; + + return taprio_change(sch, opt, extack); +} + +static struct netdev_queue *taprio_queue_get(struct Qdisc *sch, + unsigned long cl) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned long ntx = cl - 1; + + if (ntx >= dev->num_tx_queues) + return NULL; + + return netdev_get_tx_queue(dev, ntx); +} + +static int taprio_graft(struct Qdisc *sch, unsigned long cl, + struct Qdisc *new, struct Qdisc **old, + struct netlink_ext_ack *extack) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); + + if (!dev_queue) + return -EINVAL; + + if (dev->flags & IFF_UP) + dev_deactivate(dev); + + *old = q->qdiscs[cl - 1]; + q->qdiscs[cl - 1] = new; + + if (new) + new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + + if (dev->flags & IFF_UP) + dev_activate(dev); + + return 0; +} + +static int dump_entry(struct sk_buff *msg, + const struct sched_entry *entry) +{ + struct nlattr *item; + + item = nla_nest_start(msg, TCA_TAPRIO_SCHED_ENTRY); + if (!item) + return -ENOSPC; + + if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_INDEX, entry->index)) + goto nla_put_failure; + + if (nla_put_u8(msg, TCA_TAPRIO_SCHED_ENTRY_CMD, entry->command)) + goto nla_put_failure; + + if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_GATE_MASK, + entry->gate_mask)) + goto nla_put_failure; + + if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_INTERVAL, + entry->interval)) + goto nla_put_failure; + + return nla_nest_end(msg, item); + +nla_put_failure: + nla_nest_cancel(msg, item); + return -1; +} + +static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_mqprio_qopt opt = { 0 }; + struct nlattr *nest, *entry_list; + struct sched_entry *entry; + unsigned int i; + + opt.num_tc = netdev_get_num_tc(dev); + memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); + + for (i = 0; i < netdev_get_num_tc(dev); i++) { + opt.count[i] = dev->tc_to_txq[i].count; + opt.offset[i] = dev->tc_to_txq[i].offset; + } + + nest = nla_nest_start(skb, TCA_OPTIONS); + if (!nest) + return -ENOSPC; + + if (nla_put(skb, TCA_TAPRIO_ATTR_PRIOMAP, sizeof(opt), &opt)) + goto options_error; + + if (nla_put_s64(skb, TCA_TAPRIO_ATTR_SCHED_BASE_TIME, + q->base_time, TCA_TAPRIO_PAD)) + goto options_error; + + if (nla_put_s32(skb, TCA_TAPRIO_ATTR_SCHED_CLOCKID, q->clockid)) + goto options_error; + + entry_list = nla_nest_start(skb, TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST); + if (!entry_list) + goto options_error; + + list_for_each_entry(entry, &q->entries, list) { + if (dump_entry(skb, entry) < 0) + goto options_error; + } + + nla_nest_end(skb, entry_list); + + return nla_nest_end(skb, nest); + +options_error: + nla_nest_cancel(skb, nest); + return -1; +} + +static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl) +{ + struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); + + if (!dev_queue) + return NULL; + + return dev_queue->qdisc_sleeping; +} + +static unsigned long taprio_find(struct Qdisc *sch, u32 classid) +{ + unsigned int ntx = TC_H_MIN(classid); + + if (!taprio_queue_get(sch, ntx)) + return 0; + return ntx; +} + +static int taprio_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); + + tcm->tcm_parent = TC_H_ROOT; + tcm->tcm_handle |= TC_H_MIN(cl); + tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + + return 0; +} + +static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, + struct gnet_dump *d) + __releases(d->lock) + __acquires(d->lock) +{ + struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); + + sch = dev_queue->qdisc_sleeping; + if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 || + gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0) + return -1; + return 0; +} + +static void taprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned long ntx; + + if (arg->stop) + return; + + arg->count = arg->skip; + for (ntx = arg->skip; ntx < dev->num_tx_queues; ntx++) { + if (arg->fn(sch, ntx + 1, arg) < 0) { + arg->stop = 1; + break; + } + arg->count++; + } +} + +static struct netdev_queue *taprio_select_queue(struct Qdisc *sch, + struct tcmsg *tcm) +{ + return taprio_queue_get(sch, TC_H_MIN(tcm->tcm_parent)); +} + +static const struct Qdisc_class_ops taprio_class_ops = { + .graft = taprio_graft, + .leaf = taprio_leaf, + .find = taprio_find, + .walk = taprio_walk, + .dump = taprio_dump_class, + .dump_stats = taprio_dump_class_stats, + .select_queue = taprio_select_queue, +}; + +static struct Qdisc_ops taprio_qdisc_ops __read_mostly = { + .cl_ops = &taprio_class_ops, + .id = "taprio", + .priv_size = sizeof(struct taprio_sched), + .init = taprio_init, + .destroy = taprio_destroy, + .peek = taprio_peek, + .dequeue = taprio_dequeue, + .enqueue = taprio_enqueue, + .dump = taprio_dump, + .owner = THIS_MODULE, +}; + +static int __init taprio_module_init(void) +{ + return register_qdisc(&taprio_qdisc_ops); +} + +static void __exit taprio_module_exit(void) +{ + unregister_qdisc(&taprio_qdisc_ops); +} + +module_init(taprio_module_init); +module_exit(taprio_module_exit); +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 6f74a426f159..942dcca09cf2 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -162,7 +162,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, nb = 0; while (segs) { nskb = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; len += segs->len; ret = qdisc_enqueue(segs, q->qdisc, to_free); @@ -392,7 +392,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt, if (child) { qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, q->qdisc->qstats.backlog); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); q->qdisc = child; } q->limit = qopt->limit; @@ -438,7 +438,7 @@ static void tbf_destroy(struct Qdisc *sch) struct tbf_sched_data *q = qdisc_priv(sch); qdisc_watchdog_cancel(&q->watchdog); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); } static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb) |
