diff options
Diffstat (limited to 'net/sched')
41 files changed, 1867 insertions, 534 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig index e70ed26485a2..c03d86a7775e 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -172,6 +172,17 @@ config NET_SCH_TBF To compile this code as a module, choose M here: the module will be called sch_tbf. +config NET_SCH_CBS + tristate "Credit Based Shaper (CBS)" + ---help--- + Say Y here if you want to use the Credit Based Shaper (CBS) packet + scheduling algorithm. + + See the top of <file:net/sched/sch_cbs.c> for more details. + + To compile this code as a module, choose M here: the + module will be called sch_cbs. + config NET_SCH_GRED tristate "Generic Random Early Detection (GRED)" ---help--- diff --git a/net/sched/Makefile b/net/sched/Makefile index 9e43a4721ef8..5b635447e3f8 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -53,6 +53,7 @@ obj-$(CONFIG_NET_SCH_FQ_CODEL) += sch_fq_codel.o obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o 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_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 8f2c63514956..4d33a50a8a6d 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -21,6 +21,8 @@ #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> @@ -1251,8 +1253,227 @@ 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 c0c707eb2c96..5ef8ce8c83d4 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -49,11 +49,11 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, filter = rcu_dereference(prog->filter); if (at_ingress) { __skb_push(skb, skb->mac_len); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); filter_res = BPF_PROG_RUN(filter, skb); __skb_pull(skb, skb->mac_len); } else { - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); filter_res = BPF_PROG_RUN(filter, skb); } rcu_read_unlock(); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 8ccd35825b6b..3007cb1310ea 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -248,6 +248,22 @@ static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len) return ret; } +#ifdef CONFIG_MODULES +static const char *ife_meta_id2name(u32 metaid) +{ + switch (metaid) { + case IFE_META_SKBMARK: + return "skbmark"; + case IFE_META_PRIO: + return "skbprio"; + case IFE_META_TCINDEX: + return "tcindex"; + default: + return "unknown"; + } +} +#endif + /* called when adding new meta information * under ife->tcf_lock for existing action */ @@ -263,7 +279,7 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, if (exists) spin_unlock_bh(&ife->tcf_lock); rtnl_unlock(); - request_module("ifemeta%u", metaid); + request_module("ife-meta-%s", ife_meta_id2name(metaid)); rtnl_lock(); if (exists) spin_lock_bh(&ife->tcf_lock); @@ -392,10 +408,14 @@ static void _tcf_ife_cleanup(struct tc_action *a, int bind) static void tcf_ife_cleanup(struct tc_action *a, int bind) { struct tcf_ife_info *ife = to_ife(a); + struct tcf_ife_params *p; spin_lock_bh(&ife->tcf_lock); _tcf_ife_cleanup(a, bind); spin_unlock_bh(&ife->tcf_lock); + + p = rcu_dereference_protected(ife->params, 1); + kfree_rcu(p, rcu); } /* under ife->tcf_lock for existing action */ @@ -432,6 +452,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, ife_net_id); struct nlattr *tb[TCA_IFE_MAX + 1]; struct nlattr *tb2[IFE_META_MAX + 1]; + struct tcf_ife_params *p, *p_old; struct tcf_ife_info *ife; u16 ife_type = ETH_P_IFE; struct tc_ife *parm; @@ -450,24 +471,41 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_IFE_PARMS]); + /* IFE_DECODE is 0 and indicates the opposite of IFE_ENCODE because + * they cannot run as the same time. Check on all other values which + * are not supported right now. + */ + if (parm->flags & ~IFE_ENCODE) + return -EINVAL; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + exists = tcf_idr_check(tn, parm->index, a, bind); - if (exists && bind) + if (exists && bind) { + kfree(p); return 0; + } if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops, - bind, false); - if (ret) + bind, true); + if (ret) { + kfree(p); return ret; + } ret = ACT_P_CREATED; } else { tcf_idr_release(*a, bind); - if (!ovr) + if (!ovr) { + kfree(p); return -EEXIST; + } } ife = to_ife(*a); - ife->flags = parm->flags; + p->flags = parm->flags; if (parm->flags & IFE_ENCODE) { if (tb[TCA_IFE_TYPE]) @@ -478,24 +516,25 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, saddr = nla_data(tb[TCA_IFE_SMAC]); } - if (exists) - spin_lock_bh(&ife->tcf_lock); ife->tcf_action = parm->action; if (parm->flags & IFE_ENCODE) { if (daddr) - ether_addr_copy(ife->eth_dst, daddr); + ether_addr_copy(p->eth_dst, daddr); else - eth_zero_addr(ife->eth_dst); + eth_zero_addr(p->eth_dst); if (saddr) - ether_addr_copy(ife->eth_src, saddr); + ether_addr_copy(p->eth_src, saddr); else - eth_zero_addr(ife->eth_src); + eth_zero_addr(p->eth_src); - ife->eth_type = ife_type; + p->eth_type = ife_type; } + if (exists) + spin_lock_bh(&ife->tcf_lock); + if (ret == ACT_P_CREATED) INIT_LIST_HEAD(&ife->metalist); @@ -511,6 +550,7 @@ metadata_parse_err: if (exists) spin_unlock_bh(&ife->tcf_lock); + kfree(p); return err; } @@ -531,6 +571,7 @@ metadata_parse_err: if (exists) spin_unlock_bh(&ife->tcf_lock); + kfree(p); return err; } } @@ -538,6 +579,11 @@ metadata_parse_err: if (exists) spin_unlock_bh(&ife->tcf_lock); + p_old = rtnl_dereference(ife->params); + rcu_assign_pointer(ife->params, p); + if (p_old) + kfree_rcu(p_old, rcu); + if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); @@ -549,12 +595,13 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, { unsigned char *b = skb_tail_pointer(skb); struct tcf_ife_info *ife = to_ife(a); + struct tcf_ife_params *p = rtnl_dereference(ife->params); struct tc_ife opt = { .index = ife->tcf_index, .refcnt = ife->tcf_refcnt - ref, .bindcnt = ife->tcf_bindcnt - bind, .action = ife->tcf_action, - .flags = ife->flags, + .flags = p->flags, }; struct tcf_t t; @@ -565,17 +612,17 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, if (nla_put_64bit(skb, TCA_IFE_TM, sizeof(t), &t, TCA_IFE_PAD)) goto nla_put_failure; - if (!is_zero_ether_addr(ife->eth_dst)) { - if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, ife->eth_dst)) + if (!is_zero_ether_addr(p->eth_dst)) { + if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, p->eth_dst)) goto nla_put_failure; } - if (!is_zero_ether_addr(ife->eth_src)) { - if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, ife->eth_src)) + if (!is_zero_ether_addr(p->eth_src)) { + if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, p->eth_src)) goto nla_put_failure; } - if (nla_put(skb, TCA_IFE_TYPE, 2, &ife->eth_type)) + if (nla_put(skb, TCA_IFE_TYPE, 2, &p->eth_type)) goto nla_put_failure; if (dump_metalist(skb, ife)) { @@ -617,19 +664,15 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u8 *tlv_data; u16 metalen; - spin_lock(&ife->tcf_lock); - bstats_update(&ife->tcf_bstats, skb); + bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); - spin_unlock(&ife->tcf_lock); if (skb_at_tc_ingress(skb)) skb_push(skb, skb->dev->hard_header_len); tlv_data = ife_decode(skb, &metalen); if (unlikely(!tlv_data)) { - spin_lock(&ife->tcf_lock); - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -647,14 +690,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, */ pr_info_ratelimited("Unknown metaid %d dlen %d\n", mtype, dlen); - ife->tcf_qstats.overlimits++; + qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats)); } } if (WARN_ON(tlv_data != ifehdr_end)) { - spin_lock(&ife->tcf_lock); - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -683,7 +724,7 @@ static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife) } static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) + struct tcf_result *res, struct tcf_ife_params *p) { struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; @@ -706,23 +747,20 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, exceed_mtu = true; } - spin_lock(&ife->tcf_lock); - bstats_update(&ife->tcf_bstats, skb); + bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); if (!metalen) { /* no metadata to send */ /* abuse overlimits to count when we allow packet * with no metadata */ - ife->tcf_qstats.overlimits++; - spin_unlock(&ife->tcf_lock); + qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats)); return action; } /* could be stupid policy setup or mtu config * so lets be conservative.. */ if ((action == TC_ACT_SHOT) || exceed_mtu) { - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -731,6 +769,8 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, ife_meta = ife_encode(skb, metalen); + spin_lock(&ife->tcf_lock); + /* XXX: we dont have a clever way of telling encode to * not repeat some of the computations that are done by * ops->presence_check... @@ -742,25 +782,24 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, } if (err < 0) { /* too corrupt to keep around if overwritten */ - ife->tcf_qstats.drops++; spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } skboff += err; } + spin_unlock(&ife->tcf_lock); oethh = (struct ethhdr *)skb->data; - if (!is_zero_ether_addr(ife->eth_src)) - ether_addr_copy(oethh->h_source, ife->eth_src); - if (!is_zero_ether_addr(ife->eth_dst)) - ether_addr_copy(oethh->h_dest, ife->eth_dst); - oethh->h_proto = htons(ife->eth_type); + if (!is_zero_ether_addr(p->eth_src)) + ether_addr_copy(oethh->h_source, p->eth_src); + if (!is_zero_ether_addr(p->eth_dst)) + ether_addr_copy(oethh->h_dest, p->eth_dst); + oethh->h_proto = htons(p->eth_type); if (skb_at_tc_ingress(skb)) skb_pull(skb, skb->dev->hard_header_len); - spin_unlock(&ife->tcf_lock); - return action; } @@ -768,21 +807,19 @@ static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_ife_info *ife = to_ife(a); + struct tcf_ife_params *p; + int ret; + + rcu_read_lock(); + p = rcu_dereference(ife->params); + if (p->flags & IFE_ENCODE) { + ret = tcf_ife_encode(skb, a, res, p); + rcu_read_unlock(); + return ret; + } + rcu_read_unlock(); - if (ife->flags & IFE_ENCODE) - return tcf_ife_encode(skb, a, res); - - if (!(ife->flags & IFE_ENCODE)) - return tcf_ife_decode(skb, a, res); - - pr_info_ratelimited("unknown failure(policy neither de/encode\n"); - spin_lock(&ife->tcf_lock); - bstats_update(&ife->tcf_bstats, skb); - tcf_lastuse_update(&ife->tcf_tm); - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); - - return TC_ACT_SHOT; + return tcf_ife_decode(skb, a, res); } static int tcf_ife_walker(struct net *net, struct sk_buff *skb, diff --git a/net/sched/act_meta_mark.c b/net/sched/act_meta_mark.c index 82892170ce4f..1e3f10e5da99 100644 --- a/net/sched/act_meta_mark.c +++ b/net/sched/act_meta_mark.c @@ -76,4 +76,4 @@ module_exit(ifemark_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2015)"); MODULE_DESCRIPTION("Inter-FE skb mark metadata module"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_IFE_META(IFE_META_SKBMARK); +MODULE_ALIAS_IFE_META("skbmark"); diff --git a/net/sched/act_meta_skbprio.c b/net/sched/act_meta_skbprio.c index 26bf4d86030b..4033f9fc4d4a 100644 --- a/net/sched/act_meta_skbprio.c +++ b/net/sched/act_meta_skbprio.c @@ -73,4 +73,4 @@ module_exit(ifeprio_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2015)"); MODULE_DESCRIPTION("Inter-FE skb prio metadata action"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_IFE_META(IFE_META_PRIO); +MODULE_ALIAS_IFE_META("skbprio"); diff --git a/net/sched/act_meta_skbtcindex.c b/net/sched/act_meta_skbtcindex.c index 3b35774ce890..2ea1f26c9e96 100644 --- a/net/sched/act_meta_skbtcindex.c +++ b/net/sched/act_meta_skbtcindex.c @@ -76,4 +76,4 @@ module_exit(ifetc_index_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2016)"); MODULE_DESCRIPTION("Inter-FE skb tc_index metadata module"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_IFE_META(IFE_META_SKBTCINDEX); +MODULE_ALIAS_IFE_META("tcindex"); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 416627c66f08..8b3e59388480 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -140,6 +140,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, m->tcfm_eaction = parm->eaction; if (dev != NULL) { m->tcfm_ifindex = parm->ifindex; + m->net = net; if (ret != ACT_P_CREATED) dev_put(rcu_dereference_protected(m->tcfm_dev, 1)); dev_hold(dev); @@ -313,15 +314,11 @@ static struct notifier_block mirred_device_notifier = { .notifier_call = mirred_device_event, }; -static int tcf_mirred_device(const struct tc_action *a, struct net *net, - struct net_device **mirred_dev) +static struct net_device *tcf_mirred_get_dev(const struct tc_action *a) { - int ifindex = tcf_mirred_ifindex(a); + struct tcf_mirred *m = to_mirred(a); - *mirred_dev = __dev_get_by_index(net, ifindex); - if (!*mirred_dev) - return -EINVAL; - return 0; + return __dev_get_by_index(m->net, m->tcfm_ifindex); } static struct tc_action_ops act_mirred_ops = { @@ -336,7 +333,7 @@ static struct tc_action_ops act_mirred_ops = { .walk = tcf_mirred_walker, .lookup = tcf_mirred_search, .size = sizeof(struct tcf_mirred), - .get_dev = tcf_mirred_device, + .get_dev = tcf_mirred_get_dev, }; static __net_init int mirred_init_net(struct net *net) diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 16eb067a8d8f..97f717a13ad5 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -26,14 +26,13 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_vlan *v = to_vlan(a); + struct tcf_vlan_params *p; int action; int err; u16 tci; - spin_lock(&v->tcf_lock); tcf_lastuse_update(&v->tcf_tm); - bstats_update(&v->tcf_bstats, skb); - action = v->tcf_action; + bstats_cpu_update(this_cpu_ptr(v->common.cpu_bstats), skb); /* Ensure 'data' points at mac_header prior calling vlan manipulating * functions. @@ -41,15 +40,21 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, if (skb_at_tc_ingress(skb)) skb_push_rcsum(skb, skb->mac_len); - switch (v->tcfv_action) { + rcu_read_lock(); + + action = READ_ONCE(v->tcf_action); + + p = rcu_dereference(v->vlan_p); + + switch (p->tcfv_action) { case TCA_VLAN_ACT_POP: err = skb_vlan_pop(skb); if (err) goto drop; break; case TCA_VLAN_ACT_PUSH: - err = skb_vlan_push(skb, v->tcfv_push_proto, v->tcfv_push_vid | - (v->tcfv_push_prio << VLAN_PRIO_SHIFT)); + err = skb_vlan_push(skb, p->tcfv_push_proto, p->tcfv_push_vid | + (p->tcfv_push_prio << VLAN_PRIO_SHIFT)); if (err) goto drop; break; @@ -68,14 +73,14 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, goto drop; } /* replace the vid */ - tci = (tci & ~VLAN_VID_MASK) | v->tcfv_push_vid; + tci = (tci & ~VLAN_VID_MASK) | p->tcfv_push_vid; /* replace prio bits, if tcfv_push_prio specified */ - if (v->tcfv_push_prio) { + if (p->tcfv_push_prio) { tci &= ~VLAN_PRIO_MASK; - tci |= v->tcfv_push_prio << VLAN_PRIO_SHIFT; + tci |= p->tcfv_push_prio << VLAN_PRIO_SHIFT; } /* put updated tci as hwaccel tag */ - __vlan_hwaccel_put_tag(skb, v->tcfv_push_proto, tci); + __vlan_hwaccel_put_tag(skb, p->tcfv_push_proto, tci); break; default: BUG(); @@ -85,12 +90,13 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, drop: action = TC_ACT_SHOT; - v->tcf_qstats.drops++; + qstats_drop_inc(this_cpu_ptr(v->common.cpu_qstats)); + unlock: + rcu_read_unlock(); if (skb_at_tc_ingress(skb)) skb_pull_rcsum(skb, skb->mac_len); - spin_unlock(&v->tcf_lock); return action; } @@ -107,6 +113,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, { struct tc_action_net *tn = net_generic(net, vlan_net_id); struct nlattr *tb[TCA_VLAN_MAX + 1]; + struct tcf_vlan_params *p, *p_old; struct tc_vlan *parm; struct tcf_vlan *v; int action; @@ -172,7 +179,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, - &act_vlan_ops, bind, false); + &act_vlan_ops, bind, true); if (ret) return ret; @@ -185,46 +192,67 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, v = to_vlan(*a); - spin_lock_bh(&v->tcf_lock); - - v->tcfv_action = action; - v->tcfv_push_vid = push_vid; - v->tcfv_push_prio = push_prio; - v->tcfv_push_proto = push_proto; + ASSERT_RTNL(); + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) { + if (ovr) + tcf_idr_release(*a, bind); + return -ENOMEM; + } v->tcf_action = parm->action; - spin_unlock_bh(&v->tcf_lock); + p_old = rtnl_dereference(v->vlan_p); + + p->tcfv_action = action; + p->tcfv_push_vid = push_vid; + p->tcfv_push_prio = push_prio; + p->tcfv_push_proto = push_proto; + + rcu_assign_pointer(v->vlan_p, p); + + if (p_old) + kfree_rcu(p_old, rcu); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); return ret; } +static void tcf_vlan_cleanup(struct tc_action *a, int bind) +{ + struct tcf_vlan *v = to_vlan(a); + struct tcf_vlan_params *p; + + p = rcu_dereference_protected(v->vlan_p, 1); + kfree_rcu(p, rcu); +} + static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_vlan *v = to_vlan(a); + struct tcf_vlan_params *p = rtnl_dereference(v->vlan_p); struct tc_vlan opt = { .index = v->tcf_index, .refcnt = v->tcf_refcnt - ref, .bindcnt = v->tcf_bindcnt - bind, .action = v->tcf_action, - .v_action = v->tcfv_action, + .v_action = p->tcfv_action, }; struct tcf_t t; if (nla_put(skb, TCA_VLAN_PARMS, sizeof(opt), &opt)) goto nla_put_failure; - if ((v->tcfv_action == TCA_VLAN_ACT_PUSH || - v->tcfv_action == TCA_VLAN_ACT_MODIFY) && - (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, v->tcfv_push_vid) || + if ((p->tcfv_action == TCA_VLAN_ACT_PUSH || + p->tcfv_action == TCA_VLAN_ACT_MODIFY) && + (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, p->tcfv_push_vid) || nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, - v->tcfv_push_proto) || + p->tcfv_push_proto) || (nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY, - v->tcfv_push_prio)))) + p->tcfv_push_prio)))) goto nla_put_failure; tcf_tm_dump(&t, &v->tcf_tm); @@ -260,6 +288,7 @@ static struct tc_action_ops act_vlan_ops = { .act = tcf_vlan, .dump = tcf_vlan_dump, .init = tcf_vlan_init, + .cleanup = tcf_vlan_cleanup, .walk = tcf_vlan_walker, .lookup = tcf_vlan_search, .size = sizeof(struct tcf_vlan), diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index ecbb019efcbd..ab255b421781 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -195,12 +195,19 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block, return chain; } +static void tcf_chain_head_change(struct tcf_chain *chain, + struct tcf_proto *tp_head) +{ + if (chain->chain_head_change) + chain->chain_head_change(tp_head, + chain->chain_head_change_priv); +} + static void tcf_chain_flush(struct tcf_chain *chain) { struct tcf_proto *tp; - if (chain->p_filter_chain) - RCU_INIT_POINTER(*chain->p_filter_chain, NULL); + tcf_chain_head_change(chain, NULL); while ((tp = rtnl_dereference(chain->filter_chain)) != NULL) { RCU_INIT_POINTER(chain->filter_chain, tp->next); tcf_chain_put(chain); @@ -242,15 +249,35 @@ void tcf_chain_put(struct tcf_chain *chain) } EXPORT_SYMBOL(tcf_chain_put); -static void -tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain, - struct tcf_proto __rcu **p_filter_chain) +static void tcf_block_offload_cmd(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei, + enum tc_block_command command) { - chain->p_filter_chain = p_filter_chain; + struct net_device *dev = q->dev_queue->dev; + struct tc_block_offload bo = {}; + + if (!dev->netdev_ops->ndo_setup_tc) + return; + bo.command = command; + bo.binder_type = ei->binder_type; + bo.block = block; + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); } -int tcf_block_get(struct tcf_block **p_block, - struct tcf_proto __rcu **p_filter_chain) +static void tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei) +{ + tcf_block_offload_cmd(block, q, ei, TC_BLOCK_BIND); +} + +static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei) +{ + tcf_block_offload_cmd(block, q, ei, TC_BLOCK_UNBIND); +} + +int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, + struct tcf_block_ext_info *ei) { struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL); struct tcf_chain *chain; @@ -259,13 +286,20 @@ int tcf_block_get(struct tcf_block **p_block, if (!block) return -ENOMEM; INIT_LIST_HEAD(&block->chain_list); + INIT_LIST_HEAD(&block->cb_list); + /* Create chain 0 by default, it has to be always present. */ chain = tcf_chain_create(block, 0); if (!chain) { err = -ENOMEM; goto err_chain_create; } - tcf_chain_filter_chain_ptr_set(chain, p_filter_chain); + WARN_ON(!ei->chain_head_change); + chain->chain_head_change = ei->chain_head_change; + chain->chain_head_change_priv = ei->chain_head_change_priv; + block->net = qdisc_net(q); + block->q = q; + tcf_block_offload_bind(block, q, ei); *p_block = block; return 0; @@ -273,6 +307,26 @@ err_chain_create: kfree(block); return err; } +EXPORT_SYMBOL(tcf_block_get_ext); + +static void tcf_chain_head_change_dflt(struct tcf_proto *tp_head, void *priv) +{ + struct tcf_proto __rcu **p_filter_chain = priv; + + rcu_assign_pointer(*p_filter_chain, tp_head); +} + +int tcf_block_get(struct tcf_block **p_block, + struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q) +{ + struct tcf_block_ext_info ei = { + .chain_head_change = tcf_chain_head_change_dflt, + .chain_head_change_priv = p_filter_chain, + }; + + WARN_ON(!p_filter_chain); + return tcf_block_get_ext(p_block, q, &ei); +} EXPORT_SYMBOL(tcf_block_get); static void tcf_block_put_final(struct work_struct *work) @@ -292,25 +346,140 @@ static void tcf_block_put_final(struct work_struct *work) * actions should be all removed after flushing. However, filters are now * destroyed in tc filter workqueue with RTNL lock, they can not race here. */ -void tcf_block_put(struct tcf_block *block) +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; - list_for_each_entry_safe(chain, tmp, &block->chain_list, list) tcf_chain_flush(chain); + tcf_block_offload_unbind(block, q, ei); + INIT_WORK(&block->work, tcf_block_put_final); - /* Wait for RCU callbacks to release the reference count and make - * sure their works have been queued before this. + /* Wait for existing RCU callbacks to cool down, make sure their works + * have been queued before this. We can not flush pending works here + * because we are holding the RTNL lock. */ rcu_barrier(); tcf_queue_work(&block->work); } +EXPORT_SYMBOL(tcf_block_put_ext); + +void tcf_block_put(struct tcf_block *block) +{ + struct tcf_block_ext_info ei = {0, }; + + if (!block) + return; + tcf_block_put_ext(block, block->q, &ei); +} + EXPORT_SYMBOL(tcf_block_put); +struct tcf_block_cb { + struct list_head list; + tc_setup_cb_t *cb; + void *cb_ident; + void *cb_priv; + unsigned int refcnt; +}; + +void *tcf_block_cb_priv(struct tcf_block_cb *block_cb) +{ + return block_cb->cb_priv; +} +EXPORT_SYMBOL(tcf_block_cb_priv); + +struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block, + tc_setup_cb_t *cb, void *cb_ident) +{ struct tcf_block_cb *block_cb; + + list_for_each_entry(block_cb, &block->cb_list, list) + if (block_cb->cb == cb && block_cb->cb_ident == cb_ident) + return block_cb; + return NULL; +} +EXPORT_SYMBOL(tcf_block_cb_lookup); + +void tcf_block_cb_incref(struct tcf_block_cb *block_cb) +{ + block_cb->refcnt++; +} +EXPORT_SYMBOL(tcf_block_cb_incref); + +unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb) +{ + return --block_cb->refcnt; +} +EXPORT_SYMBOL(tcf_block_cb_decref); + +struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, + tc_setup_cb_t *cb, void *cb_ident, + void *cb_priv) +{ + struct tcf_block_cb *block_cb; + + block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL); + if (!block_cb) + return NULL; + block_cb->cb = cb; + block_cb->cb_ident = cb_ident; + block_cb->cb_priv = cb_priv; + list_add(&block_cb->list, &block->cb_list); + return block_cb; +} +EXPORT_SYMBOL(__tcf_block_cb_register); + +int tcf_block_cb_register(struct tcf_block *block, + tc_setup_cb_t *cb, void *cb_ident, + void *cb_priv) +{ + struct tcf_block_cb *block_cb; + + block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv); + return block_cb ? 0 : -ENOMEM; +} +EXPORT_SYMBOL(tcf_block_cb_register); + +void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb) +{ + list_del(&block_cb->list); + kfree(block_cb); +} +EXPORT_SYMBOL(__tcf_block_cb_unregister); + +void tcf_block_cb_unregister(struct tcf_block *block, + tc_setup_cb_t *cb, void *cb_ident) +{ + struct tcf_block_cb *block_cb; + + block_cb = tcf_block_cb_lookup(block, cb, cb_ident); + if (!block_cb) + return; + __tcf_block_cb_unregister(block_cb); +} +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; + + 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. @@ -379,9 +548,8 @@ static void tcf_chain_tp_insert(struct tcf_chain *chain, struct tcf_chain_info *chain_info, struct tcf_proto *tp) { - if (chain->p_filter_chain && - *chain_info->pprev == chain->filter_chain) - rcu_assign_pointer(*chain->p_filter_chain, tp); + if (*chain_info->pprev == chain->filter_chain) + tcf_chain_head_change(chain, tp); RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info)); rcu_assign_pointer(*chain_info->pprev, tp); tcf_chain_hold(chain); @@ -393,8 +561,8 @@ static void tcf_chain_tp_remove(struct tcf_chain *chain, { struct tcf_proto *next = rtnl_dereference(chain_info->next); - if (chain->p_filter_chain && tp == chain->filter_chain) - RCU_INIT_POINTER(*chain->p_filter_chain, next); + if (tp == chain->filter_chain) + tcf_chain_head_change(chain, next); RCU_INIT_POINTER(*chain_info->pprev, next); tcf_chain_put(chain); } @@ -427,8 +595,8 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, } static int tcf_fill_node(struct net *net, struct sk_buff *skb, - struct tcf_proto *tp, void *fh, u32 portid, - u32 seq, u16 flags, int event) + struct tcf_proto *tp, struct Qdisc *q, u32 parent, + void *fh, u32 portid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -441,8 +609,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, tcm->tcm_family = AF_UNSPEC; tcm->tcm__pad1 = 0; tcm->tcm__pad2 = 0; - tcm->tcm_ifindex = qdisc_dev(tp->q)->ifindex; - tcm->tcm_parent = tp->classid; + tcm->tcm_ifindex = qdisc_dev(q)->ifindex; + tcm->tcm_parent = parent; tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol); if (nla_put_string(skb, TCA_KIND, tp->ops->kind)) goto nla_put_failure; @@ -465,6 +633,7 @@ nla_put_failure: static int tfilter_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, + struct Qdisc *q, u32 parent, void *fh, int event, bool unicast) { struct sk_buff *skb; @@ -474,7 +643,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, + if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq, n->nlmsg_flags, event) <= 0) { kfree_skb(skb); return -EINVAL; @@ -489,6 +658,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, + struct Qdisc *q, u32 parent, void *fh, bool unicast, bool *last) { struct sk_buff *skb; @@ -499,7 +669,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, + if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER) <= 0) { kfree_skb(skb); return -EINVAL; @@ -519,6 +689,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, } static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, + struct Qdisc *q, u32 parent, struct nlmsghdr *n, struct tcf_chain *chain, int event) { @@ -526,7 +697,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, for (tp = rtnl_dereference(chain->filter_chain); tp; tp = rtnl_dereference(tp->next)) - tfilter_notify(net, oskb, n, tp, 0, event, false); + tfilter_notify(net, oskb, n, tp, q, parent, 0, event, false); } /* Add/change/delete/get a filter node */ @@ -645,7 +816,8 @@ replay: } if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) { - tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER); + tfilter_notify_chain(net, skb, q, parent, n, + chain, RTM_DELTFILTER); tcf_chain_flush(chain); err = 0; goto errout; @@ -692,7 +864,7 @@ replay: if (!fh) { if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) { tcf_chain_tp_remove(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, fh, + tfilter_notify(net, skb, n, tp, q, parent, fh, RTM_DELTFILTER, false); tcf_proto_destroy(tp); err = 0; @@ -717,8 +889,8 @@ replay: } break; case RTM_DELTFILTER: - err = tfilter_del_notify(net, skb, n, tp, fh, false, - &last); + err = tfilter_del_notify(net, skb, n, tp, q, parent, + fh, false, &last); if (err) goto errout; if (last) { @@ -727,7 +899,7 @@ replay: } goto errout; case RTM_GETTFILTER: - err = tfilter_notify(net, skb, n, tp, fh, + err = tfilter_notify(net, skb, n, tp, q, parent, fh, RTM_NEWTFILTER, true); goto errout; default: @@ -741,7 +913,8 @@ replay: if (err == 0) { if (tp_created) tcf_chain_tp_insert(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER, false); + tfilter_notify(net, skb, n, tp, q, parent, fh, + RTM_NEWTFILTER, false); } else { if (tp_created) tcf_proto_destroy(tp); @@ -760,6 +933,8 @@ struct tcf_dump_args { struct tcf_walker w; struct sk_buff *skb; struct netlink_callback *cb; + struct Qdisc *q; + u32 parent; }; static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) @@ -767,13 +942,14 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) struct tcf_dump_args *a = (void *)arg; struct net *net = sock_net(a->skb->sk); - return tcf_fill_node(net, a->skb, tp, n, NETLINK_CB(a->cb->skb).portid, + return tcf_fill_node(net, a->skb, tp, a->q, a->parent, + n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER); } -static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, - struct netlink_callback *cb, +static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, + struct sk_buff *skb, struct netlink_callback *cb, long index_start, long *p_index) { struct net *net = sock_net(skb->sk); @@ -795,7 +971,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (cb->args[1] == 0) { - if (tcf_fill_node(net, skb, tp, 0, + if (tcf_fill_node(net, skb, tp, q, parent, 0, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER) <= 0) @@ -808,6 +984,8 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, arg.w.fn = tcf_node_dump; arg.skb = skb; arg.cb = cb; + arg.q = q; + arg.parent = parent; arg.w.stop = 0; arg.w.skip = cb->args[1] - 1; arg.w.count = 0; @@ -833,6 +1011,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) const struct Qdisc_class_ops *cops; long index_start; long index; + u32 parent; int err; if (nlmsg_len(cb->nlh) < sizeof(*tcm)) @@ -846,10 +1025,13 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (!dev) return skb->len; - if (!tcm->tcm_parent) + parent = tcm->tcm_parent; + if (!parent) { q = dev->qdisc; - else + parent = q->handle; + } else { q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); + } if (!q) goto out; cops = q->ops->cl_ops; @@ -873,7 +1055,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (tca[TCA_CHAIN] && nla_get_u32(tca[TCA_CHAIN]) != chain->index) continue; - if (!tcf_chain_dump(chain, skb, cb, index_start, &index)) + if (!tcf_chain_dump(chain, q, parent, skb, cb, + index_start, &index)) break; } @@ -1015,29 +1198,56 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts) } EXPORT_SYMBOL(tcf_exts_dump_stats); -int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts, - struct net_device **hw_dev) +static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts, + enum tc_setup_type type, + void *type_data, bool err_stop) { + int ok_count = 0; #ifdef CONFIG_NET_CLS_ACT const struct tc_action *a; - LIST_HEAD(actions); + struct net_device *dev; + int i, ret; if (!tcf_exts_has_actions(exts)) - return -EINVAL; + return 0; - tcf_exts_to_list(exts, &actions); - list_for_each_entry(a, &actions, list) { - if (a->ops->get_dev) { - a->ops->get_dev(a, dev_net(dev), hw_dev); - break; - } + 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); + if (ret < 0) + return ret; + ok_count += ret; } - if (*hw_dev) - return 0; #endif - return -EOPNOTSUPP; + 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) + 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(tcf_exts_get_dev); +EXPORT_SYMBOL(tc_setup_cb_call); static int __init tc_filter_init(void) { diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index e43c56d5b96a..5f169ded347e 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -17,13 +17,14 @@ #include <linux/errno.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> +#include <linux/idr.h> #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> struct basic_head { - u32 hgenerator; struct list_head flist; + struct idr handle_idr; struct rcu_head rcu; }; @@ -81,6 +82,7 @@ static int basic_init(struct tcf_proto *tp) if (head == NULL) return -ENOBUFS; INIT_LIST_HEAD(&head->flist); + idr_init(&head->handle_idr); rcu_assign_pointer(tp->root, head); return 0; } @@ -118,11 +120,13 @@ static void basic_destroy(struct tcf_proto *tp) list_for_each_entry_safe(f, n, &head->flist, link) { list_del_rcu(&f->link); tcf_unbind_filter(tp, &f->res); + idr_remove_ext(&head->handle_idr, f->handle); if (tcf_exts_get_net(&f->exts)) call_rcu(&f->rcu, basic_delete_filter); else __basic_delete_filter(f); } + idr_destroy(&head->handle_idr); kfree_rcu(head, rcu); } @@ -133,6 +137,7 @@ static int basic_delete(struct tcf_proto *tp, void *arg, bool *last) list_del_rcu(&f->link); tcf_unbind_filter(tp, &f->res); + idr_remove_ext(&head->handle_idr, f->handle); tcf_exts_get_net(&f->exts); call_rcu(&f->rcu, basic_delete_filter); *last = list_empty(&head->flist); @@ -177,6 +182,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, struct nlattr *tb[TCA_BASIC_MAX + 1]; struct basic_filter *fold = (struct basic_filter *) *arg; struct basic_filter *fnew; + unsigned long idr_index; if (tca[TCA_OPTIONS] == NULL) return -EINVAL; @@ -199,33 +205,33 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout; - err = -EINVAL; if (handle) { fnew->handle = handle; - } else if (fold) { - fnew->handle = fold->handle; + if (!fold) { + err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index, + handle, handle + 1, GFP_KERNEL); + if (err) + goto errout; + } } else { - unsigned int i = 0x80000000; - do { - if (++head->hgenerator == 0x7FFFFFFF) - head->hgenerator = 1; - } while (--i > 0 && basic_get(tp, head->hgenerator)); - - if (i <= 0) { - pr_err("Insufficient number of handles\n"); + err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index, + 1, 0x7FFFFFFF, GFP_KERNEL); + if (err) goto errout; - } - - fnew->handle = head->hgenerator; + fnew->handle = idr_index; } err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], ovr); - if (err < 0) + if (err < 0) { + if (!fold) + idr_remove_ext(&head->handle_idr, fnew->handle); goto errout; + } *arg = fnew; if (fold) { + idr_replace_ext(&head->handle_idr, fnew, fnew->handle); list_replace_rcu(&fold->link, &fnew->link); tcf_unbind_filter(tp, &fold->res); tcf_exts_get_net(&fold->exts); diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 990eb4d91d54..fb680dafac5a 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -17,6 +17,7 @@ #include <linux/skbuff.h> #include <linux/filter.h> #include <linux/bpf.h> +#include <linux/idr.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> @@ -32,7 +33,7 @@ MODULE_DESCRIPTION("TC BPF based classifier"); struct cls_bpf_head { struct list_head plist; - u32 hgen; + struct idr handle_idr; struct rcu_head rcu; }; @@ -102,11 +103,11 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, } else if (at_ingress) { /* It is safe to push/pull even if skb_shared() */ __skb_push(skb, skb->mac_len); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); filter_res = BPF_PROG_RUN(prog->filter, skb); __skb_pull(skb, skb->mac_len); } else { - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); filter_res = BPF_PROG_RUN(prog->filter, skb); } @@ -149,7 +150,9 @@ static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog) static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, enum tc_clsbpf_command cmd) { - struct net_device *dev = tp->q->dev_queue->dev; + bool addorrep = cmd == TC_CLSBPF_ADD || cmd == TC_CLSBPF_REPLACE; + struct tcf_block *block = tp->chain->block; + bool skip_sw = tc_skip_sw(prog->gen_flags); struct tc_cls_bpf_offload cls_bpf = {}; int err; @@ -161,17 +164,25 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, cls_bpf.exts_integrated = prog->exts_integrated; cls_bpf.gen_flags = prog->gen_flags; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSBPF, &cls_bpf); - if (!err && (cmd == TC_CLSBPF_ADD || cmd == TC_CLSBPF_REPLACE)) - prog->gen_flags |= TCA_CLS_FLAGS_IN_HW; + err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, skip_sw); + if (addorrep) { + if (err < 0) { + cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_DESTROY); + return err; + } else if (err > 0) { + prog->gen_flags |= TCA_CLS_FLAGS_IN_HW; + } + } + + if (addorrep && skip_sw && !(prog->gen_flags & TCA_CLS_FLAGS_IN_HW)) + return -EINVAL; - return err; + return 0; } static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, struct cls_bpf_prog *oldprog) { - struct net_device *dev = tp->q->dev_queue->dev; struct cls_bpf_prog *obj = prog; enum tc_clsbpf_command cmd; bool skip_sw; @@ -181,7 +192,7 @@ static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, (oldprog && tc_skip_sw(oldprog->gen_flags)); if (oldprog && oldprog->offloaded) { - if (tc_should_offload(dev, prog->gen_flags)) { + if (!tc_skip_hw(prog->gen_flags)) { cmd = TC_CLSBPF_REPLACE; } else if (!tc_skip_sw(prog->gen_flags)) { obj = oldprog; @@ -190,14 +201,14 @@ static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, return -EINVAL; } } else { - if (!tc_should_offload(dev, prog->gen_flags)) + if (tc_skip_hw(prog->gen_flags)) return skip_sw ? -EINVAL : 0; cmd = TC_CLSBPF_ADD; } ret = cls_bpf_offload_cmd(tp, obj, cmd); if (ret) - return skip_sw ? ret : 0; + return ret; obj->offloaded = true; if (oldprog) @@ -241,6 +252,7 @@ static int cls_bpf_init(struct tcf_proto *tp) return -ENOBUFS; INIT_LIST_HEAD_RCU(&head->plist); + idr_init(&head->handle_idr); rcu_assign_pointer(tp->root, head); return 0; @@ -280,6 +292,9 @@ static void cls_bpf_delete_prog_rcu(struct rcu_head *rcu) static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog) { + struct cls_bpf_head *head = rtnl_dereference(tp->root); + + idr_remove_ext(&head->handle_idr, prog->handle); cls_bpf_stop_offload(tp, prog); list_del_rcu(&prog->link); tcf_unbind_filter(tp, &prog->res); @@ -306,6 +321,7 @@ static void cls_bpf_destroy(struct tcf_proto *tp) list_for_each_entry_safe(prog, tmp, &head->plist, link) __cls_bpf_delete(tp, prog); + idr_destroy(&head->handle_idr); kfree_rcu(head, rcu); } @@ -362,7 +378,7 @@ static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog) } static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, - const struct tcf_proto *tp) + u32 gen_flags, const struct tcf_proto *tp) { struct bpf_prog *fp; char *name = NULL; @@ -370,7 +386,11 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, bpf_fd = nla_get_u32(tb[TCA_BPF_FD]); - fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_CLS); + if (gen_flags & TCA_CLS_FLAGS_SKIP_SW) + fp = bpf_prog_get_type_dev(bpf_fd, BPF_PROG_TYPE_SCHED_CLS, + qdisc_dev(tp->q)); + else + fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_CLS); if (IS_ERR(fp)) return PTR_ERR(fp); @@ -428,7 +448,7 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, prog->gen_flags = gen_flags; ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : - cls_bpf_prog_from_efd(tb, prog, tp); + cls_bpf_prog_from_efd(tb, prog, gen_flags, tp); if (ret < 0) return ret; @@ -440,27 +460,6 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, return 0; } -static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp, - struct cls_bpf_head *head) -{ - unsigned int i = 0x80000000; - u32 handle; - - do { - if (++head->hgen == 0x7FFFFFFF) - head->hgen = 1; - } while (--i > 0 && cls_bpf_get(tp, head->hgen)); - - if (unlikely(i == 0)) { - pr_err("Insufficient number of handles\n"); - handle = 0; - } else { - handle = head->hgen; - } - - return handle; -} - static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -470,6 +469,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct cls_bpf_prog *oldprog = *arg; struct nlattr *tb[TCA_BPF_MAX + 1]; struct cls_bpf_prog *prog; + unsigned long idr_index; int ret; if (tca[TCA_OPTIONS] == NULL) @@ -495,21 +495,30 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, } } - if (handle == 0) - prog->handle = cls_bpf_grab_new_handle(tp, head); - else + if (handle == 0) { + ret = idr_alloc_ext(&head->handle_idr, prog, &idr_index, + 1, 0x7FFFFFFF, GFP_KERNEL); + if (ret) + goto errout; + prog->handle = idr_index; + } else { + if (!oldprog) { + ret = idr_alloc_ext(&head->handle_idr, prog, &idr_index, + handle, handle + 1, GFP_KERNEL); + if (ret) + goto errout; + } prog->handle = handle; - if (prog->handle == 0) { - ret = -EINVAL; - goto errout; } ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], ovr); if (ret < 0) - goto errout; + goto errout_idr; ret = cls_bpf_offload(tp, prog, oldprog); if (ret) { + if (!oldprog) + idr_remove_ext(&head->handle_idr, prog->handle); __cls_bpf_delete_prog(prog); return ret; } @@ -518,6 +527,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, prog->gen_flags |= TCA_CLS_FLAGS_NOT_IN_HW; if (oldprog) { + idr_replace_ext(&head->handle_idr, prog, handle); list_replace_rcu(&oldprog->link, &prog->link); tcf_unbind_filter(tp, &oldprog->res); tcf_exts_get_net(&oldprog->exts); @@ -529,6 +539,9 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, *arg = prog; return 0; +errout_idr: + if (!oldprog) + idr_remove_ext(&head->handle_idr, prog->handle); errout: tcf_exts_destroy(&prog->exts); kfree(prog); diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 85f765cff697..25c2a888e1f0 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -348,9 +348,9 @@ static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp, return -1; } -static void flow_perturbation(unsigned long arg) +static void flow_perturbation(struct timer_list *t) { - struct flow_filter *f = (struct flow_filter *)arg; + struct flow_filter *f = from_timer(f, t, perturb_timer); get_random_bytes(&f->hashrnd, 4); if (f->perturb_period) @@ -510,8 +510,11 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, perturb_period = nla_get_u32(tb[TCA_FLOW_PERTURB]) * HZ; } - if (TC_H_MAJ(baseclass) == 0) - baseclass = TC_H_MAKE(tp->q->handle, baseclass); + if (TC_H_MAJ(baseclass) == 0) { + struct Qdisc *q = tcf_block_q(tp->chain->block); + + baseclass = TC_H_MAKE(q->handle, baseclass); + } if (TC_H_MIN(baseclass) == 0) baseclass = TC_H_MAKE(baseclass, 1); @@ -521,8 +524,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, get_random_bytes(&fnew->hashrnd, 4); } - setup_deferrable_timer(&fnew->perturb_timer, flow_perturbation, - (unsigned long)fnew); + timer_setup(&fnew->perturb_timer, flow_perturbation, TIMER_DEFERRABLE); netif_keep_dst(qdisc_dev(tp->q)); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 7a838d1c1c00..543a3e875d05 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -155,37 +155,12 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct cls_fl_filter *f; struct fl_flow_key skb_key; struct fl_flow_key skb_mkey; - struct ip_tunnel_info *info; if (!atomic_read(&head->ht.nelems)) return -1; fl_clear_masked_range(&skb_key, &head->mask); - info = skb_tunnel_info(skb); - if (info) { - struct ip_tunnel_key *key = &info->key; - - switch (ip_tunnel_info_af(info)) { - case AF_INET: - skb_key.enc_control.addr_type = - FLOW_DISSECTOR_KEY_IPV4_ADDRS; - skb_key.enc_ipv4.src = key->u.ipv4.src; - skb_key.enc_ipv4.dst = key->u.ipv4.dst; - break; - case AF_INET6: - skb_key.enc_control.addr_type = - FLOW_DISSECTOR_KEY_IPV6_ADDRS; - skb_key.enc_ipv6.src = key->u.ipv6.src; - skb_key.enc_ipv6.dst = key->u.ipv6.dst; - break; - } - - skb_key.enc_key_id.keyid = tunnel_id_to_key32(key->tun_id); - skb_key.enc_tp.src = key->tp_src; - skb_key.enc_tp.dst = key->tp_dst; - } - skb_key.indev_ifindex = skb->skb_iif; /* skb_flow_dissect() does not set n_proto in case an unknown protocol, * so do it rather here. @@ -245,17 +220,14 @@ static void fl_destroy_filter(struct rcu_head *head) static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f) { struct tc_cls_flower_offload cls_flower = {}; - struct net_device *dev = f->hw_dev; - - if (!tc_can_offload(dev)) - return; + struct tcf_block *block = tp->chain->block; tc_cls_common_offload_init(&cls_flower.common, tp); cls_flower.command = TC_CLSFLOWER_DESTROY; cls_flower.cookie = (unsigned long) f; - cls_flower.egress_dev = f->hw_dev != tp->q->dev_queue->dev; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, &cls_flower); + tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER, + &cls_flower, false); } static int fl_hw_replace_filter(struct tcf_proto *tp, @@ -263,22 +235,11 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, struct fl_flow_key *mask, struct cls_fl_filter *f) { - struct net_device *dev = tp->q->dev_queue->dev; struct tc_cls_flower_offload cls_flower = {}; + struct tcf_block *block = tp->chain->block; + bool skip_sw = tc_skip_sw(f->flags); int err; - if (!tc_can_offload(dev)) { - if (tcf_exts_get_dev(dev, &f->exts, &f->hw_dev) || - (f->hw_dev && !tc_can_offload(f->hw_dev))) { - f->hw_dev = dev; - return tc_skip_sw(f->flags) ? -EINVAL : 0; - } - dev = f->hw_dev; - cls_flower.egress_dev = true; - } else { - f->hw_dev = dev; - } - tc_cls_common_offload_init(&cls_flower.common, tp); cls_flower.command = TC_CLSFLOWER_REPLACE; cls_flower.cookie = (unsigned long) f; @@ -286,33 +247,36 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, cls_flower.mask = mask; cls_flower.key = &f->mkey; cls_flower.exts = &f->exts; + cls_flower.classid = f->res.classid; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, - &cls_flower); - if (!err) + err = tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER, + &cls_flower, skip_sw); + if (err < 0) { + fl_hw_destroy_filter(tp, f); + return err; + } else if (err > 0) { f->flags |= TCA_CLS_FLAGS_IN_HW; + } + + if (skip_sw && !(f->flags & TCA_CLS_FLAGS_IN_HW)) + return -EINVAL; - if (tc_skip_sw(f->flags)) - return err; return 0; } static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) { struct tc_cls_flower_offload cls_flower = {}; - struct net_device *dev = f->hw_dev; - - if (!tc_can_offload(dev)) - return; + struct tcf_block *block = tp->chain->block; tc_cls_common_offload_init(&cls_flower.common, tp); cls_flower.command = TC_CLSFLOWER_STATS; cls_flower.cookie = (unsigned long) f; cls_flower.exts = &f->exts; - cls_flower.egress_dev = f->hw_dev != tp->q->dev_queue->dev; + cls_flower.classid = f->res.classid; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, - &cls_flower); + tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER, + &cls_flower, false); } static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f) diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 7f45e5ab8afc..20f0de1a960a 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -28,6 +28,7 @@ #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> +#include <net/sch_generic.h> #define HTSIZE 256 @@ -86,9 +87,11 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, } } } else { + struct Qdisc *q = tcf_block_q(tp->chain->block); + /* Old method: classify the packet using its skb mark. */ if (id && (TC_H_MAJ(id) == 0 || - !(TC_H_MAJ(id ^ tp->q->handle)))) { + !(TC_H_MAJ(id ^ q->handle)))) { res->classid = id; res->class = 0; return 0; diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 3684153cd8a9..66d4e0099158 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -69,12 +69,27 @@ static void mall_destroy_rcu(struct rcu_head *rcu) tcf_queue_work(&head->work); } +static void mall_destroy_hw_filter(struct tcf_proto *tp, + struct cls_mall_head *head, + unsigned long cookie) +{ + struct tc_cls_matchall_offload cls_mall = {}; + struct tcf_block *block = tp->chain->block; + + tc_cls_common_offload_init(&cls_mall.common, tp); + cls_mall.command = TC_CLSMATCHALL_DESTROY; + cls_mall.cookie = cookie; + + tc_setup_cb_call(block, NULL, TC_SETUP_CLSMATCHALL, &cls_mall, false); +} + static int mall_replace_hw_filter(struct tcf_proto *tp, struct cls_mall_head *head, unsigned long cookie) { - struct net_device *dev = tp->q->dev_queue->dev; struct tc_cls_matchall_offload cls_mall = {}; + struct tcf_block *block = tp->chain->block; + bool skip_sw = tc_skip_sw(head->flags); int err; tc_cls_common_offload_init(&cls_mall.common, tp); @@ -82,37 +97,29 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, cls_mall.exts = &head->exts; cls_mall.cookie = cookie; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSMATCHALL, - &cls_mall); - if (!err) + err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSMATCHALL, + &cls_mall, skip_sw); + if (err < 0) { + mall_destroy_hw_filter(tp, head, cookie); + return err; + } else if (err > 0) { head->flags |= TCA_CLS_FLAGS_IN_HW; + } - return err; -} - -static void mall_destroy_hw_filter(struct tcf_proto *tp, - struct cls_mall_head *head, - unsigned long cookie) -{ - struct net_device *dev = tp->q->dev_queue->dev; - struct tc_cls_matchall_offload cls_mall = {}; - - tc_cls_common_offload_init(&cls_mall.common, tp); - cls_mall.command = TC_CLSMATCHALL_DESTROY; - cls_mall.cookie = cookie; + if (skip_sw && !(head->flags & TCA_CLS_FLAGS_IN_HW)) + return -EINVAL; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSMATCHALL, &cls_mall); + return 0; } static void mall_destroy(struct tcf_proto *tp) { struct cls_mall_head *head = rtnl_dereference(tp->root); - struct net_device *dev = tp->q->dev_queue->dev; if (!head) return; - if (tc_should_offload(dev, head->flags)) + if (!tc_skip_hw(head->flags)) mall_destroy_hw_filter(tp, head, (unsigned long) head); if (tcf_exts_get_net(&head->exts)) @@ -155,7 +162,6 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, void **arg, bool ovr) { struct cls_mall_head *head = rtnl_dereference(tp->root); - struct net_device *dev = tp->q->dev_queue->dev; struct nlattr *tb[TCA_MATCHALL_MAX + 1]; struct cls_mall_head *new; u32 flags = 0; @@ -195,14 +201,10 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, if (err) goto err_set_parms; - if (tc_should_offload(dev, flags)) { + if (!tc_skip_hw(new->flags)) { err = mall_replace_hw_filter(tp, new, (unsigned long) new); - if (err) { - if (tc_skip_sw(flags)) - goto err_replace_hw_filter; - else - err = 0; - } + if (err) + goto err_replace_hw_filter; } if (!tc_in_hw(new->flags)) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index a76937ee0b2d..67467ae24c97 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -13,6 +13,7 @@ #include <net/act_api.h> #include <net/netlink.h> #include <net/pkt_cls.h> +#include <net/sch_generic.h> /* * Passing parameters to the root seems to be done more awkwardly than really @@ -96,9 +97,11 @@ static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, f = tcindex_lookup(p, key); if (!f) { + struct Qdisc *q = tcf_block_q(tp->chain->block); + if (!p->fall_through) return -1; - res->classid = TC_H_MAKE(TC_H_MAJ(tp->q->handle), key); + res->classid = TC_H_MAKE(TC_H_MAJ(q->handle), key); res->class = 0; pr_debug("alg 0x%x\n", res->classid); return 0; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index b58eccb21f03..ac152b4f4247 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -46,6 +46,7 @@ #include <net/act_api.h> #include <net/pkt_cls.h> #include <linux/netdevice.h> +#include <linux/idr.h> struct tc_u_knode { struct tc_u_knode __rcu *next; @@ -85,6 +86,7 @@ struct tc_u_hnode { struct tc_u_common *tp_c; int refcnt; unsigned int divisor; + struct idr handle_idr; struct rcu_head rcu; /* The 'ht' field MUST be the last field in structure to allow for * more entries allocated at end of structure. @@ -94,9 +96,9 @@ struct tc_u_hnode { struct tc_u_common { struct tc_u_hnode __rcu *hlist; - struct Qdisc *q; + struct tcf_block *block; int refcnt; - u32 hgenerator; + struct idr handle_idr; struct hlist_node hnode; struct rcu_head rcu; }; @@ -314,19 +316,19 @@ static void *u32_get(struct tcf_proto *tp, u32 handle) return u32_lookup_key(ht, handle); } -static u32 gen_new_htid(struct tc_u_common *tp_c) +static u32 gen_new_htid(struct tc_u_common *tp_c, struct tc_u_hnode *ptr) { - int i = 0x800; + unsigned long idr_index; + int err; - /* hgenerator only used inside rtnl lock it is safe to increment + /* This is only used inside rtnl lock it is safe to increment * without read _copy_ update semantics */ - do { - if (++tp_c->hgenerator == 0x7FF) - tp_c->hgenerator = 1; - } while (--i > 0 && u32_lookup_ht(tp_c, (tp_c->hgenerator|0x800)<<20)); - - return i > 0 ? (tp_c->hgenerator|0x800)<<20 : 0; + err = idr_alloc_ext(&tp_c->handle_idr, ptr, &idr_index, + 1, 0x7FF, GFP_KERNEL); + if (err) + return 0; + return (u32)(idr_index | 0x800) << 20; } static struct hlist_head *tc_u_common_hash; @@ -336,11 +338,7 @@ static struct hlist_head *tc_u_common_hash; static unsigned int tc_u_hash(const struct tcf_proto *tp) { - struct net_device *dev = tp->q->dev_queue->dev; - u32 qhandle = tp->q->handle; - int ifindex = dev->ifindex; - - return hash_64((u64)ifindex << 32 | qhandle, U32_HASH_SHIFT); + return hash_ptr(tp->chain->block, U32_HASH_SHIFT); } static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp) @@ -350,7 +348,7 @@ static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp) h = tc_u_hash(tp); hlist_for_each_entry(tc, &tc_u_common_hash[h], hnode) { - if (tc->q == tp->q) + if (tc->block == tp->chain->block) return tc; } return NULL; @@ -369,8 +367,9 @@ static int u32_init(struct tcf_proto *tp) return -ENOBUFS; root_ht->refcnt++; - root_ht->handle = tp_c ? gen_new_htid(tp_c) : 0x80000000; + root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : 0x80000000; root_ht->prio = tp->prio; + idr_init(&root_ht->handle_idr); if (tp_c == NULL) { tp_c = kzalloc(sizeof(*tp_c), GFP_KERNEL); @@ -378,8 +377,9 @@ static int u32_init(struct tcf_proto *tp) kfree(root_ht); return -ENOBUFS; } - tp_c->q = tp->q; + tp_c->block = tp->chain->block; 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]); @@ -487,71 +487,69 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) return 0; } -static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) +static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) { - struct net_device *dev = tp->q->dev_queue->dev; + struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; - if (!tc_should_offload(dev, 0)) - return; - tc_cls_common_offload_init(&cls_u32.common, tp); - cls_u32.command = TC_CLSU32_DELETE_KNODE; - cls_u32.knode.handle = handle; + cls_u32.command = TC_CLSU32_DELETE_HNODE; + cls_u32.hnode.divisor = h->divisor; + cls_u32.hnode.handle = h->handle; + cls_u32.hnode.prio = h->prio; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32); + tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, false); } static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, u32 flags) { - struct net_device *dev = tp->q->dev_queue->dev; + struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; + bool skip_sw = tc_skip_sw(flags); + bool offloaded = false; int err; - if (!tc_should_offload(dev, flags)) - return tc_skip_sw(flags) ? -EINVAL : 0; - tc_cls_common_offload_init(&cls_u32.common, tp); cls_u32.command = TC_CLSU32_NEW_HNODE; cls_u32.hnode.divisor = h->divisor; cls_u32.hnode.handle = h->handle; cls_u32.hnode.prio = h->prio; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32); - if (tc_skip_sw(flags)) + err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw); + if (err < 0) { + u32_clear_hw_hnode(tp, h); return err; + } else if (err > 0) { + offloaded = true; + } + + if (skip_sw && !offloaded) + return -EINVAL; return 0; } -static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) +static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) { - struct net_device *dev = tp->q->dev_queue->dev; + struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; - if (!tc_should_offload(dev, 0)) - return; - tc_cls_common_offload_init(&cls_u32.common, tp); - cls_u32.command = TC_CLSU32_DELETE_HNODE; - cls_u32.hnode.divisor = h->divisor; - cls_u32.hnode.handle = h->handle; - cls_u32.hnode.prio = h->prio; + cls_u32.command = TC_CLSU32_DELETE_KNODE; + cls_u32.knode.handle = handle; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32); + tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, false); } static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, u32 flags) { - struct net_device *dev = tp->q->dev_queue->dev; + struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; + bool skip_sw = tc_skip_sw(flags); int err; - if (!tc_should_offload(dev, flags)) - return tc_skip_sw(flags) ? -EINVAL : 0; - tc_cls_common_offload_init(&cls_u32.common, tp); cls_u32.command = TC_CLSU32_REPLACE_KNODE; cls_u32.knode.handle = n->handle; @@ -568,13 +566,16 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, if (n->ht_down) cls_u32.knode.link_handle = n->ht_down->handle; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32); - - if (!err) + err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw); + if (err < 0) { + u32_remove_hw_knode(tp, n->handle); + return err; + } else if (err > 0) { n->flags |= TCA_CLS_FLAGS_IN_HW; + } - if (tc_skip_sw(flags)) - return err; + if (skip_sw && !(n->flags & TCA_CLS_FLAGS_IN_HW)) + return -EINVAL; return 0; } @@ -590,6 +591,7 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) rtnl_dereference(n->next)); tcf_unbind_filter(tp, &n->res); u32_remove_hw_knode(tp, n->handle); + idr_remove_ext(&ht->handle_idr, n->handle); if (tcf_exts_get_net(&n->exts)) call_rcu(&n->rcu, u32_delete_key_freepf_rcu); else @@ -614,6 +616,8 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) hn = &phn->next, phn = rtnl_dereference(*hn)) { if (phn == ht) { u32_clear_hw_hnode(tp, ht); + idr_destroy(&ht->handle_idr); + idr_remove_ext(&tp_c->handle_idr, ht->handle); RCU_INIT_POINTER(*hn, ht->next); kfree_rcu(ht, rcu); return 0; @@ -661,6 +665,7 @@ static void u32_destroy(struct tcf_proto *tp) kfree_rcu(ht, rcu); } + idr_destroy(&tp_c->handle_idr); kfree(tp_c); } @@ -729,27 +734,21 @@ ret: return ret; } -#define NR_U32_NODE (1<<12) -static u32 gen_new_kid(struct tc_u_hnode *ht, u32 handle) +static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid) { - struct tc_u_knode *n; - unsigned long i; - unsigned long *bitmap = kzalloc(BITS_TO_LONGS(NR_U32_NODE) * sizeof(unsigned long), - GFP_KERNEL); - if (!bitmap) - return handle | 0xFFF; - - for (n = rtnl_dereference(ht->ht[TC_U32_HASH(handle)]); - n; - n = rtnl_dereference(n->next)) - set_bit(TC_U32_NODE(n->handle), bitmap); - - i = find_next_zero_bit(bitmap, NR_U32_NODE, 0x800); - if (i >= NR_U32_NODE) - i = find_next_zero_bit(bitmap, NR_U32_NODE, 1); + unsigned long idr_index; + u32 start = htid | 0x800; + u32 max = htid | 0xFFF; + u32 min = htid; + + if (idr_alloc_ext(&ht->handle_idr, NULL, &idr_index, + start, max + 1, GFP_KERNEL)) { + if (idr_alloc_ext(&ht->handle_idr, NULL, &idr_index, + min + 1, max + 1, GFP_KERNEL)) + return max; + } - kfree(bitmap); - return handle | (i >= NR_U32_NODE ? 0xFFF : i); + return (u32)idr_index; } static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { @@ -834,6 +833,7 @@ static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c, if (pins->handle == n->handle) break; + idr_replace_ext(&ht->handle_idr, n, n->handle); RCU_INIT_POINTER(n->next, pins->next); rcu_assign_pointer(*ins, n); } @@ -966,22 +966,33 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -EINVAL; if (TC_U32_KEY(handle)) return -EINVAL; - if (handle == 0) { - handle = gen_new_htid(tp->data); - if (handle == 0) - return -ENOMEM; - } ht = kzalloc(sizeof(*ht) + divisor*sizeof(void *), GFP_KERNEL); if (ht == NULL) return -ENOBUFS; + if (handle == 0) { + handle = gen_new_htid(tp->data, ht); + if (handle == 0) { + kfree(ht); + return -ENOMEM; + } + } else { + err = idr_alloc_ext(&tp_c->handle_idr, ht, NULL, + handle, handle + 1, GFP_KERNEL); + if (err) { + kfree(ht); + return err; + } + } ht->tp_c = tp_c; ht->refcnt = 1; ht->divisor = divisor; ht->handle = handle; ht->prio = tp->prio; + idr_init(&ht->handle_idr); err = u32_replace_hw_hnode(tp, ht, flags); if (err) { + idr_remove_ext(&tp_c->handle_idr, handle); kfree(ht); return err; } @@ -1015,24 +1026,33 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (TC_U32_HTID(handle) && TC_U32_HTID(handle^htid)) return -EINVAL; handle = htid | TC_U32_NODE(handle); + err = idr_alloc_ext(&ht->handle_idr, NULL, NULL, + handle, handle + 1, + GFP_KERNEL); + if (err) + return err; } else handle = gen_new_kid(ht, htid); - if (tb[TCA_U32_SEL] == NULL) - return -EINVAL; + if (tb[TCA_U32_SEL] == NULL) { + err = -EINVAL; + goto erridr; + } s = nla_data(tb[TCA_U32_SEL]); n = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), GFP_KERNEL); - if (n == NULL) - return -ENOBUFS; + if (n == NULL) { + err = -ENOBUFS; + goto erridr; + } #ifdef CONFIG_CLS_U32_PERF size = sizeof(struct tc_u32_pcnt) + s->nkeys * sizeof(u64); n->pf = __alloc_percpu(size, __alignof__(struct tc_u32_pcnt)); if (!n->pf) { - kfree(n); - return -ENOBUFS; + err = -ENOBUFS; + goto errfree; } #endif @@ -1095,9 +1115,12 @@ errhw: errout: tcf_exts_destroy(&n->exts); #ifdef CONFIG_CLS_U32_PERF +errfree: free_percpu(n->pf); #endif kfree(n); +erridr: + idr_remove_ext(&ht->handle_idr, handle); return err; } diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 03b677bc0700..1331a4c2d8ff 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -178,7 +178,7 @@ static int tcf_em_validate(struct tcf_proto *tp, struct tcf_ematch_hdr *em_hdr = nla_data(nla); int data_len = nla_len(nla) - sizeof(*em_hdr); void *data = (void *) em_hdr + sizeof(*em_hdr); - struct net *net = dev_net(qdisc_dev(tp->q)); + struct net *net = tp->chain->block->net; if (!TCF_EM_REL_VALID(em_hdr->flags)) goto errout; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 22bc6fc48311..b6c4f536876b 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1502,7 +1502,6 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) int s_idx, s_q_idx; struct net_device *dev; const struct nlmsghdr *nlh = cb->nlh; - struct tcmsg *tcm = nlmsg_data(nlh); struct nlattr *tca[TCA_MAX + 1]; int err; @@ -1512,7 +1511,7 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; ASSERT_RTNL(); - err = nlmsg_parse(nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL); + err = nlmsg_parse(nlh, sizeof(struct tcmsg), tca, TCA_MAX, NULL, NULL); if (err < 0) return err; @@ -1664,9 +1663,11 @@ static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg) struct tcf_bind_args *a = (void *)arg; if (tp->ops->bind_class) { - tcf_tree_lock(tp); + struct Qdisc *q = tcf_block_q(tp->chain->block); + + sch_tree_lock(q); tp->ops->bind_class(n, a->classid, a->cl); - tcf_tree_unlock(tp); + sch_tree_unlock(q); } return 0; } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index c5fcdf1a58a0..2dbd249c0b2f 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -281,7 +281,7 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, goto err_out; } - error = tcf_block_get(&flow->block, &flow->filter_list); + error = tcf_block_get(&flow->block, &flow->filter_list, sch); if (error) { kfree(flow); goto err_out; @@ -546,7 +546,7 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) p->link.q = &noop_qdisc; pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); - err = tcf_block_get(&p->link.block, &p->link.filter_list); + err = tcf_block_get(&p->link.block, &p->link.filter_list, sch); if (err) return err; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index dcef97fa8047..6361be7881f1 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -255,6 +255,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return NULL; case TC_ACT_RECLASSIFY: @@ -1566,7 +1567,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (cl == NULL) goto failure; - err = tcf_block_get(&cl->block, &cl->filter_list); + err = tcf_block_get(&cl->block, &cl->filter_list, sch); if (err) { kfree(cl); return err; diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c new file mode 100644 index 000000000000..7a72980c1509 --- /dev/null +++ b/net/sched/sch_cbs.c @@ -0,0 +1,373 @@ +/* + * net/sched/sch_cbs.c Credit Based Shaper + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Vinicius Costa Gomes <vinicius.gomes@intel.com> + * + */ + +/* Credit Based Shaper (CBS) + * ========================= + * + * This is a simple rate-limiting shaper aimed at TSN applications on + * systems with known traffic workloads. + * + * Its algorithm is defined by the IEEE 802.1Q-2014 Specification, + * Section 8.6.8.2, and explained in more detail in the Annex L of the + * same specification. + * + * There are four tunables to be considered: + * + * 'idleslope': Idleslope is the rate of credits that is + * accumulated (in kilobits per second) when there is at least + * one packet waiting for transmission. Packets are transmitted + * when the current value of credits is equal or greater than + * zero. When there is no packet to be transmitted the amount of + * credits is set to zero. This is the main tunable of the CBS + * algorithm. + * + * 'sendslope': + * Sendslope is the rate of credits that is depleted (it should be a + * negative number of kilobits per second) when a transmission is + * ocurring. It can be calculated as follows, (IEEE 802.1Q-2014 Section + * 8.6.8.2 item g): + * + * sendslope = idleslope - port_transmit_rate + * + * 'hicredit': Hicredit defines the maximum amount of credits (in + * bytes) that can be accumulated. Hicredit depends on the + * characteristics of interfering traffic, + * 'max_interference_size' is the maximum size of any burst of + * traffic that can delay the transmission of a frame that is + * available for transmission for this traffic class, (IEEE + * 802.1Q-2014 Annex L, Equation L-3): + * + * hicredit = max_interference_size * (idleslope / port_transmit_rate) + * + * 'locredit': Locredit is the minimum amount of credits that can + * be reached. It is a function of the traffic flowing through + * this qdisc (IEEE 802.1Q-2014 Annex L, Equation L-2): + * + * locredit = max_frame_size * (sendslope / port_transmit_rate) + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <net/netlink.h> +#include <net/sch_generic.h> +#include <net/pkt_sched.h> + +#define BYTES_PER_KBIT (1000LL / 8) + +struct cbs_sched_data { + bool offload; + int queue; + s64 port_rate; /* in bytes/s */ + s64 last; /* timestamp in ns */ + s64 credits; /* in bytes */ + s32 locredit; /* in bytes */ + s32 hicredit; /* in bytes */ + s64 sendslope; /* in bytes/s */ + s64 idleslope; /* in bytes/s */ + struct qdisc_watchdog watchdog; + int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch); + struct sk_buff *(*dequeue)(struct Qdisc *sch); +}; + +static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch) +{ + return qdisc_enqueue_tail(skb, sch); +} + +static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + if (sch->q.qlen == 0 && q->credits > 0) { + /* We need to stop accumulating credits when there's + * no enqueued packets and q->credits is positive. + */ + q->credits = 0; + q->last = ktime_get_ns(); + } + + return qdisc_enqueue_tail(skb, sch); +} + +static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + return q->enqueue(skb, sch); +} + +/* timediff is in ns, slope is in bytes/s */ +static s64 timediff_to_credits(s64 timediff, s64 slope) +{ + return div64_s64(timediff * slope, NSEC_PER_SEC); +} + +static s64 delay_from_credits(s64 credits, s64 slope) +{ + if (unlikely(slope == 0)) + return S64_MAX; + + return div64_s64(-credits * NSEC_PER_SEC, slope); +} + +static s64 credits_from_len(unsigned int len, s64 slope, s64 port_rate) +{ + if (unlikely(port_rate == 0)) + return S64_MAX; + + return div64_s64(len * slope, port_rate); +} + +static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + s64 now = ktime_get_ns(); + struct sk_buff *skb; + s64 credits; + int len; + + if (q->credits < 0) { + credits = timediff_to_credits(now - q->last, q->idleslope); + + credits = q->credits + credits; + q->credits = min_t(s64, credits, q->hicredit); + + if (q->credits < 0) { + s64 delay; + + delay = delay_from_credits(q->credits, q->idleslope); + qdisc_watchdog_schedule_ns(&q->watchdog, now + delay); + + q->last = now; + + return NULL; + } + } + + skb = qdisc_dequeue_head(sch); + if (!skb) + return NULL; + + len = qdisc_pkt_len(skb); + + /* As sendslope is a negative number, this will decrease the + * amount of q->credits. + */ + credits = credits_from_len(len, q->sendslope, q->port_rate); + credits += q->credits; + + q->credits = max_t(s64, credits, q->locredit); + q->last = now; + + return skb; +} + +static struct sk_buff *cbs_dequeue_offload(struct Qdisc *sch) +{ + return qdisc_dequeue_head(sch); +} + +static struct sk_buff *cbs_dequeue(struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + return q->dequeue(sch); +} + +static const struct nla_policy cbs_policy[TCA_CBS_MAX + 1] = { + [TCA_CBS_PARMS] = { .len = sizeof(struct tc_cbs_qopt) }, +}; + +static void cbs_disable_offload(struct net_device *dev, + struct cbs_sched_data *q) +{ + struct tc_cbs_qopt_offload cbs = { }; + const struct net_device_ops *ops; + int err; + + if (!q->offload) + return; + + q->enqueue = cbs_enqueue_soft; + q->dequeue = cbs_dequeue_soft; + + ops = dev->netdev_ops; + if (!ops->ndo_setup_tc) + return; + + cbs.queue = q->queue; + cbs.enable = 0; + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_CBS, &cbs); + if (err < 0) + pr_warn("Couldn't disable CBS offload for queue %d\n", + cbs.queue); +} + +static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q, + const struct tc_cbs_qopt *opt) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct tc_cbs_qopt_offload cbs = { }; + int err; + + if (!ops->ndo_setup_tc) + return -EOPNOTSUPP; + + cbs.queue = q->queue; + + cbs.enable = 1; + cbs.hicredit = opt->hicredit; + cbs.locredit = opt->locredit; + cbs.idleslope = opt->idleslope; + cbs.sendslope = opt->sendslope; + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_CBS, &cbs); + if (err < 0) + return err; + + q->enqueue = cbs_enqueue_offload; + q->dequeue = cbs_dequeue_offload; + + return 0; +} + +static int cbs_change(struct Qdisc *sch, struct nlattr *opt) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct nlattr *tb[TCA_CBS_MAX + 1]; + struct tc_cbs_qopt *qopt; + int err; + + err = nla_parse_nested(tb, TCA_CBS_MAX, opt, cbs_policy, NULL); + if (err < 0) + return err; + + if (!tb[TCA_CBS_PARMS]) + return -EINVAL; + + qopt = nla_data(tb[TCA_CBS_PARMS]); + + if (!qopt->offload) { + struct ethtool_link_ksettings ecmd; + s64 link_speed; + + if (!__ethtool_get_link_ksettings(dev, &ecmd)) + link_speed = ecmd.base.speed; + else + link_speed = SPEED_1000; + + q->port_rate = link_speed * 1000 * BYTES_PER_KBIT; + + cbs_disable_offload(dev, q); + } else { + err = cbs_enable_offload(dev, q, qopt); + if (err < 0) + return err; + } + + /* Everything went OK, save the parameters used. */ + q->hicredit = qopt->hicredit; + q->locredit = qopt->locredit; + q->idleslope = qopt->idleslope * BYTES_PER_KBIT; + q->sendslope = qopt->sendslope * BYTES_PER_KBIT; + q->offload = qopt->offload; + + return 0; +} + +static int cbs_init(struct Qdisc *sch, struct nlattr *opt) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + + if (!opt) + return -EINVAL; + + q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0); + + q->enqueue = cbs_enqueue_soft; + q->dequeue = cbs_dequeue_soft; + + qdisc_watchdog_init(&q->watchdog, sch); + + return cbs_change(sch, opt); +} + +static void cbs_destroy(struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + + qdisc_watchdog_cancel(&q->watchdog); + + cbs_disable_offload(dev, q); +} + +static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct tc_cbs_qopt opt = { }; + struct nlattr *nest; + + nest = nla_nest_start(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + + opt.hicredit = q->hicredit; + opt.locredit = q->locredit; + opt.sendslope = div64_s64(q->sendslope, BYTES_PER_KBIT); + opt.idleslope = div64_s64(q->idleslope, BYTES_PER_KBIT); + opt.offload = q->offload; + + if (nla_put(skb, TCA_CBS_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + return nla_nest_end(skb, nest); + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + +static struct Qdisc_ops cbs_qdisc_ops __read_mostly = { + .id = "cbs", + .priv_size = sizeof(struct cbs_sched_data), + .enqueue = cbs_enqueue, + .dequeue = cbs_dequeue, + .peek = qdisc_peek_dequeued, + .init = cbs_init, + .reset = qdisc_reset_queue, + .destroy = cbs_destroy, + .change = cbs_change, + .dump = cbs_dump, + .owner = THIS_MODULE, +}; + +static int __init cbs_module_init(void) +{ + return register_qdisc(&cbs_qdisc_ops); +} + +static void __exit cbs_module_exit(void) +{ + unregister_qdisc(&cbs_qdisc_ops); +} +module_init(cbs_module_init) +module_exit(cbs_module_exit) +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 2d0e8d4bdc29..5bbcef3dcd8c 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -321,6 +321,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return NULL; } @@ -412,7 +413,7 @@ static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt) struct drr_sched *q = qdisc_priv(sch); int err; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; err = qdisc_class_hash_init(&q->clhash); diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 2836c80c7aa5..fb4fb71c68cf 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -344,7 +344,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) goto errout; - err = tcf_block_get(&p->block, &p->filter_list); + err = tcf_block_get(&p->block, &p->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index de3b57ceca7b..0305d791ea94 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -105,6 +105,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return 0; } @@ -481,7 +482,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) return err; } - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index bf8c81e07c70..3839cbbdc32b 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -288,9 +288,9 @@ unsigned long dev_trans_start(struct net_device *dev) } EXPORT_SYMBOL(dev_trans_start); -static void dev_watchdog(unsigned long arg) +static void dev_watchdog(struct timer_list *t) { - struct net_device *dev = (struct net_device *)arg; + struct net_device *dev = from_timer(dev, t, watchdog_timer); netif_tx_lock(dev); if (!qdisc_tx_is_noop(dev)) { @@ -603,8 +603,14 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, struct Qdisc *sch; unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size; int err = -ENOBUFS; - struct net_device *dev = dev_queue->dev; + struct net_device *dev; + + if (!dev_queue) { + err = -EINVAL; + goto errout; + } + dev = dev_queue->dev; p = kzalloc_node(size, GFP_KERNEL, netdev_queue_numa_node_read(dev_queue)); @@ -689,10 +695,8 @@ void qdisc_reset(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_reset); -static void qdisc_rcu_free(struct rcu_head *head) +static void qdisc_free(struct Qdisc *qdisc) { - struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head); - if (qdisc_is_percpu_stats(qdisc)) { free_percpu(qdisc->cpu_bstats); free_percpu(qdisc->cpu_qstats); @@ -725,11 +729,7 @@ void qdisc_destroy(struct Qdisc *qdisc) kfree_skb_list(qdisc->gso_skb); kfree_skb(qdisc->skb_bad_txq); - /* - * gen_estimator est_timer() might access qdisc->q.lock, - * wait a RCU grace period before freeing qdisc. - */ - call_rcu(&qdisc->rcu_head, qdisc_rcu_free); + qdisc_free(qdisc); } EXPORT_SYMBOL(qdisc_destroy); @@ -960,7 +960,7 @@ void dev_init_scheduler(struct net_device *dev) if (dev_ingress_queue(dev)) dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); - setup_timer(&dev->watchdog_timer, dev_watchdog, (unsigned long)dev); + timer_setup(&dev->watchdog_timer, dev_watchdog, 0); } static void shutdown_scheduler_queue(struct net_device *dev, @@ -1024,3 +1024,49 @@ void psched_ratecfg_precompute(struct psched_ratecfg *r, } } EXPORT_SYMBOL(psched_ratecfg_precompute); + +static void mini_qdisc_rcu_func(struct rcu_head *head) +{ +} + +void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, + struct tcf_proto *tp_head) +{ + struct mini_Qdisc *miniq_old = rtnl_dereference(*miniqp->p_miniq); + struct mini_Qdisc *miniq; + + if (!tp_head) { + RCU_INIT_POINTER(*miniqp->p_miniq, NULL); + return; + } + + miniq = !miniq_old || miniq_old == &miniqp->miniq2 ? + &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 + * is done. + */ + rcu_barrier_bh(); + miniq->filter_list = tp_head; + rcu_assign_pointer(*miniqp->p_miniq, miniq); + + if (miniq_old) + /* This is counterpart of the rcu barrier above. We need to + * block potential new user of miniq_old until all readers + * are not seeing it. + */ + call_rcu_bh(&miniq_old->rcu, mini_qdisc_rcu_func); +} +EXPORT_SYMBOL(mini_qdisc_pair_swap); + +void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, + struct mini_Qdisc __rcu **p_miniq) +{ + miniqp->miniq1.cpu_bstats = qdisc->cpu_bstats; + miniqp->miniq1.cpu_qstats = qdisc->cpu_qstats; + miniqp->miniq2.cpu_bstats = qdisc->cpu_bstats; + miniqp->miniq2.cpu_qstats = qdisc->cpu_qstats; + miniqp->p_miniq = p_miniq; +} +EXPORT_SYMBOL(mini_qdisc_pair_init); diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 3f88b75488b0..d04068a97d81 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1033,7 +1033,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; - err = tcf_block_get(&cl->block, &cl->filter_list); + err = tcf_block_get(&cl->block, &cl->filter_list, sch); if (err) { kfree(cl); return err; @@ -1144,6 +1144,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return NULL; } @@ -1405,7 +1406,7 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) return err; q->eligible = RB_ROOT; - err = tcf_block_get(&q->root.block, &q->root.filter_list); + err = tcf_block_get(&q->root.block, &q->root.filter_list, sch); if (err) return err; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 7e148376ba52..fa0380730ff0 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -142,6 +142,7 @@ struct htb_class { struct rb_node node[TC_HTB_NUMPRIO]; /* node for self or feed tree */ unsigned int drops ____cacheline_aligned_in_smp; + unsigned int overlimits; }; struct htb_level { @@ -243,6 +244,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return NULL; } @@ -533,6 +535,9 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) if (new_mode == cl->cmode) return; + if (new_mode == HTB_CANT_SEND) + cl->overlimits++; + if (cl->prio_activity) { /* not necessary: speed optimization */ if (cl->cmode != HTB_CANT_SEND) htb_deactivate_prios(q, cl); @@ -1026,7 +1031,7 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; @@ -1143,6 +1148,7 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) struct htb_class *cl = (struct htb_class *)arg; struct gnet_stats_queue qs = { .drops = cl->drops, + .overlimits = cl->overlimits, }; __u32 qlen = 0; @@ -1388,7 +1394,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!cl) goto failure; - err = tcf_block_get(&cl->block, &cl->filter_list); + err = tcf_block_get(&cl->block, &cl->filter_list, sch); if (err) { kfree(cl); goto failure; diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 44de4ee51ce9..5ecc38f35d47 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -20,6 +20,8 @@ struct ingress_sched_data { struct tcf_block *block; + struct tcf_block_ext_info block_info; + struct mini_Qdisc_pair miniqp; }; static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg) @@ -53,13 +55,26 @@ static struct tcf_block *ingress_tcf_block(struct Qdisc *sch, unsigned long cl) return q->block; } +static void clsact_chain_head_change(struct tcf_proto *tp_head, void *priv) +{ + struct mini_Qdisc_pair *miniqp = priv; + + mini_qdisc_pair_swap(miniqp, tp_head); +} + static int ingress_init(struct Qdisc *sch, struct nlattr *opt) { struct ingress_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); int err; - err = tcf_block_get(&q->block, &dev->ingress_cl_list); + mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress); + + q->block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + q->block_info.chain_head_change = clsact_chain_head_change; + q->block_info.chain_head_change_priv = &q->miniqp; + + err = tcf_block_get_ext(&q->block, sch, &q->block_info); if (err) return err; @@ -73,7 +88,7 @@ static void ingress_destroy(struct Qdisc *sch) { struct ingress_sched_data *q = qdisc_priv(sch); - tcf_block_put(q->block); + tcf_block_put_ext(q->block, sch, &q->block_info); net_dec_ingress_queue(); } @@ -114,6 +129,10 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { struct clsact_sched_data { struct tcf_block *ingress_block; struct tcf_block *egress_block; + struct tcf_block_ext_info ingress_block_info; + struct tcf_block_ext_info egress_block_info; + struct mini_Qdisc_pair miniqp_ingress; + struct mini_Qdisc_pair miniqp_egress; }; static unsigned long clsact_find(struct Qdisc *sch, u32 classid) @@ -153,13 +172,25 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) struct net_device *dev = qdisc_dev(sch); int err; - err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list); + mini_qdisc_pair_init(&q->miniqp_ingress, sch, &dev->miniq_ingress); + + q->ingress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + q->ingress_block_info.chain_head_change = clsact_chain_head_change; + q->ingress_block_info.chain_head_change_priv = &q->miniqp_ingress; + + err = tcf_block_get_ext(&q->ingress_block, sch, &q->ingress_block_info); if (err) return err; - err = tcf_block_get(&q->egress_block, &dev->egress_cl_list); + mini_qdisc_pair_init(&q->miniqp_egress, sch, &dev->miniq_egress); + + q->egress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS; + q->egress_block_info.chain_head_change = clsact_chain_head_change; + q->egress_block_info.chain_head_change_priv = &q->miniqp_egress; + + err = tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info); if (err) - return err; + goto err_egress_block_get; net_inc_ingress_queue(); net_inc_egress_queue(); @@ -167,14 +198,18 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) sch->flags |= TCQ_F_CPUSTATS; return 0; + +err_egress_block_get: + tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info); + return err; } static void clsact_destroy(struct Qdisc *sch) { struct clsact_sched_data *q = qdisc_priv(sch); - tcf_block_put(q->egress_block); - tcf_block_put(q->ingress_block); + tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info); + tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info); net_dec_ingress_queue(); net_dec_egress_queue(); diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index f3a3e507422b..213b586a06a0 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -130,15 +130,7 @@ static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl) static struct netdev_queue *mq_select_queue(struct Qdisc *sch, struct tcmsg *tcm) { - unsigned int ntx = TC_H_MIN(tcm->tcm_parent); - struct netdev_queue *dev_queue = mq_queue_get(sch, ntx); - - if (!dev_queue) { - struct net_device *dev = qdisc_dev(sch); - - return netdev_get_tx_queue(dev, 0); - } - return dev_queue; + return mq_queue_get(sch, TC_H_MIN(tcm->tcm_parent)); } static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 6bcdfe6e7b63..b85885a9d8a1 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -18,10 +18,16 @@ #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/sch_generic.h> +#include <net/pkt_cls.h> struct mqprio_sched { struct Qdisc **qdiscs; + u16 mode; + u16 shaper; int hw_offload; + u32 flags; + u64 min_rate[TC_QOPT_MAX_QUEUE]; + u64 max_rate[TC_QOPT_MAX_QUEUE]; }; static void mqprio_destroy(struct Qdisc *sch) @@ -39,9 +45,18 @@ static void mqprio_destroy(struct Qdisc *sch) } if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) { - struct tc_mqprio_qopt mqprio = {}; - - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, &mqprio); + struct tc_mqprio_qopt_offload mqprio = { { 0 } }; + + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + case TC_MQPRIO_MODE_CHANNEL: + dev->netdev_ops->ndo_setup_tc(dev, + TC_SETUP_QDISC_MQPRIO, + &mqprio); + break; + default: + return; + } } else { netdev_set_num_tc(dev, 0); } @@ -97,6 +112,26 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) return 0; } +static const struct nla_policy mqprio_policy[TCA_MQPRIO_MAX + 1] = { + [TCA_MQPRIO_MODE] = { .len = sizeof(u16) }, + [TCA_MQPRIO_SHAPER] = { .len = sizeof(u16) }, + [TCA_MQPRIO_MIN_RATE64] = { .type = NLA_NESTED }, + [TCA_MQPRIO_MAX_RATE64] = { .type = NLA_NESTED }, +}; + +static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, + const struct nla_policy *policy, int len) +{ + int nested_len = nla_len(nla) - NLA_ALIGN(len); + + if (nested_len >= nla_attr_size(0)) + return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len), + nested_len, policy, NULL); + + memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); + return 0; +} + static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) { struct net_device *dev = qdisc_dev(sch); @@ -105,6 +140,10 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) struct Qdisc *qdisc; int i, err = -EOPNOTSUPP; struct tc_mqprio_qopt *qopt = NULL; + struct nlattr *tb[TCA_MQPRIO_MAX + 1]; + struct nlattr *attr; + int rem; + int len; BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE); BUILD_BUG_ON(TC_BITMASK != TC_QOPT_BITMASK); @@ -115,6 +154,10 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) if (!netif_is_multiqueue(dev)) return -EOPNOTSUPP; + /* make certain can allocate enough classids to handle queues */ + if (dev->num_tx_queues >= TC_H_MIN_PRIORITY) + return -ENOMEM; + if (!opt || nla_len(opt) < sizeof(*qopt)) return -EINVAL; @@ -122,6 +165,59 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) if (mqprio_parse_opt(dev, qopt)) return -EINVAL; + len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt)); + if (len > 0) { + err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy, + sizeof(*qopt)); + if (err < 0) + return err; + + if (!qopt->hw) + return -EINVAL; + + if (tb[TCA_MQPRIO_MODE]) { + priv->flags |= TC_MQPRIO_F_MODE; + priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]); + } + + if (tb[TCA_MQPRIO_SHAPER]) { + priv->flags |= TC_MQPRIO_F_SHAPER; + priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]); + } + + if (tb[TCA_MQPRIO_MIN_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->min_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MIN_RATE; + } + + if (tb[TCA_MQPRIO_MAX_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->max_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MAX_RATE; + } + } + /* pre-allocate qdisc, attachment can't fail */ priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]), GFP_KERNEL); @@ -146,14 +242,36 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) * supplied and verified mapping */ if (qopt->hw) { - struct tc_mqprio_qopt mqprio = *qopt; + struct tc_mqprio_qopt_offload mqprio = {.qopt = *qopt}; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + if (priv->shaper != TC_MQPRIO_SHAPER_DCB) + return -EINVAL; + break; + case TC_MQPRIO_MODE_CHANNEL: + mqprio.flags = priv->flags; + if (priv->flags & TC_MQPRIO_F_MODE) + mqprio.mode = priv->mode; + if (priv->flags & TC_MQPRIO_F_SHAPER) + mqprio.shaper = priv->shaper; + if (priv->flags & TC_MQPRIO_F_MIN_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.min_rate[i] = priv->min_rate[i]; + if (priv->flags & TC_MQPRIO_F_MAX_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.max_rate[i] = priv->max_rate[i]; + break; + default: + return -EINVAL; + } + err = dev->netdev_ops->ndo_setup_tc(dev, + TC_SETUP_QDISC_MQPRIO, &mqprio); if (err) return err; - priv->hw_offload = mqprio.hw; + priv->hw_offload = mqprio.qopt.hw; } else { netdev_set_num_tc(dev, qopt->num_tc); for (i = 0; i < qopt->num_tc; i++) @@ -193,7 +311,7 @@ static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch, unsigned long cl) { struct net_device *dev = qdisc_dev(sch); - unsigned long ntx = cl - 1 - netdev_get_num_tc(dev); + unsigned long ntx = cl - 1; if (ntx >= dev->num_tx_queues) return NULL; @@ -223,11 +341,51 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, return 0; } +static int dump_rates(struct mqprio_sched *priv, + struct tc_mqprio_qopt *opt, struct sk_buff *skb) +{ + struct nlattr *nest; + int i; + + if (priv->flags & TC_MQPRIO_F_MIN_RATE) { + nest = nla_nest_start(skb, TCA_MQPRIO_MIN_RATE64); + if (!nest) + goto nla_put_failure; + + for (i = 0; i < opt->num_tc; i++) { + if (nla_put(skb, TCA_MQPRIO_MIN_RATE64, + sizeof(priv->min_rate[i]), + &priv->min_rate[i])) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } + + if (priv->flags & TC_MQPRIO_F_MAX_RATE) { + nest = nla_nest_start(skb, TCA_MQPRIO_MAX_RATE64); + if (!nest) + goto nla_put_failure; + + for (i = 0; i < opt->num_tc; i++) { + if (nla_put(skb, TCA_MQPRIO_MAX_RATE64, + sizeof(priv->max_rate[i]), + &priv->max_rate[i])) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) { struct net_device *dev = qdisc_dev(sch); struct mqprio_sched *priv = qdisc_priv(sch); - unsigned char *b = skb_tail_pointer(skb); + struct nlattr *nla = (struct nlattr *)skb_tail_pointer(skb); struct tc_mqprio_qopt opt = { 0 }; struct Qdisc *qdisc; unsigned int i; @@ -258,12 +416,25 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) opt.offset[i] = dev->tc_to_txq[i].offset; } - if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) + if (nla_put(skb, TCA_OPTIONS, NLA_ALIGN(sizeof(opt)), &opt)) + goto nla_put_failure; + + if ((priv->flags & TC_MQPRIO_F_MODE) && + nla_put_u16(skb, TCA_MQPRIO_MODE, priv->mode)) goto nla_put_failure; - return skb->len; + if ((priv->flags & TC_MQPRIO_F_SHAPER) && + nla_put_u16(skb, TCA_MQPRIO_SHAPER, priv->shaper)) + goto nla_put_failure; + + if ((priv->flags & TC_MQPRIO_F_MIN_RATE || + priv->flags & TC_MQPRIO_F_MAX_RATE) && + (dump_rates(priv, &opt, skb) != 0)) + goto nla_put_failure; + + return nla_nest_end(skb, nla); nla_put_failure: - nlmsg_trim(skb, b); + nlmsg_trim(skb, nla); return -1; } @@ -282,38 +453,35 @@ static unsigned long mqprio_find(struct Qdisc *sch, u32 classid) struct net_device *dev = qdisc_dev(sch); unsigned int ntx = TC_H_MIN(classid); - if (ntx > dev->num_tx_queues + netdev_get_num_tc(dev)) - return 0; - return ntx; + /* There are essentially two regions here that have valid classid + * values. The first region will have a classid value of 1 through + * num_tx_queues. All of these are backed by actual Qdiscs. + */ + if (ntx < TC_H_MIN_PRIORITY) + return (ntx <= dev->num_tx_queues) ? ntx : 0; + + /* The second region represents the hardware traffic classes. These + * are represented by classid values of TC_H_MIN_PRIORITY through + * TC_H_MIN_PRIORITY + netdev_get_num_tc - 1 + */ + return ((ntx - TC_H_MIN_PRIORITY) < netdev_get_num_tc(dev)) ? ntx : 0; } static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { - struct net_device *dev = qdisc_dev(sch); + if (cl < TC_H_MIN_PRIORITY) { + struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); + struct net_device *dev = qdisc_dev(sch); + int tc = netdev_txq_to_tc(dev, cl - 1); - if (cl <= netdev_get_num_tc(dev)) { + tcm->tcm_parent = (tc < 0) ? 0 : + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(tc + TC_H_MIN_PRIORITY)); + tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + } else { tcm->tcm_parent = TC_H_ROOT; tcm->tcm_info = 0; - } else { - int i; - struct netdev_queue *dev_queue; - - dev_queue = mqprio_queue_get(sch, cl); - tcm->tcm_parent = 0; - for (i = 0; i < netdev_get_num_tc(dev); i++) { - struct netdev_tc_txq tc = dev->tc_to_txq[i]; - int q_idx = cl - netdev_get_num_tc(dev); - - if (q_idx > tc.offset && - q_idx <= tc.offset + tc.count) { - tcm->tcm_parent = - TC_H_MAKE(TC_H_MAJ(sch->handle), - TC_H_MIN(i + 1)); - break; - } - } - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; } tcm->tcm_handle |= TC_H_MIN(cl); return 0; @@ -324,15 +492,14 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, __releases(d->lock) __acquires(d->lock) { - struct net_device *dev = qdisc_dev(sch); - - if (cl <= netdev_get_num_tc(dev)) { + if (cl >= TC_H_MIN_PRIORITY) { int i; __u32 qlen = 0; struct Qdisc *qdisc; struct gnet_stats_queue qstats = {0}; struct gnet_stats_basic_packed bstats = {0}; - struct netdev_tc_txq tc = dev->tc_to_txq[cl - 1]; + struct net_device *dev = qdisc_dev(sch); + struct netdev_tc_txq tc = dev->tc_to_txq[cl & TC_BITMASK]; /* Drop lock here it will be reclaimed before touching * statistics this is required because the d->lock we @@ -385,17 +552,36 @@ static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) /* Walk hierarchy with a virtual class per tc */ arg->count = arg->skip; - for (ntx = arg->skip; - ntx < dev->num_tx_queues + netdev_get_num_tc(dev); - ntx++) { + for (ntx = arg->skip; ntx < netdev_get_num_tc(dev); ntx++) { + if (arg->fn(sch, ntx + TC_H_MIN_PRIORITY, arg) < 0) { + arg->stop = 1; + return; + } + arg->count++; + } + + /* Pad the values and skip over unused traffic classes */ + if (ntx < TC_MAX_QUEUE) { + arg->count = TC_MAX_QUEUE; + ntx = TC_MAX_QUEUE; + } + + /* Reset offset, sort out remaining per-queue qdiscs */ + for (ntx -= TC_MAX_QUEUE; ntx < dev->num_tx_queues; ntx++) { if (arg->fn(sch, ntx + 1, arg) < 0) { arg->stop = 1; - break; + return; } arg->count++; } } +static struct netdev_queue *mqprio_select_queue(struct Qdisc *sch, + struct tcmsg *tcm) +{ + return mqprio_queue_get(sch, TC_H_MIN(tcm->tcm_parent)); +} + static const struct Qdisc_class_ops mqprio_class_ops = { .graft = mqprio_graft, .leaf = mqprio_leaf, @@ -403,6 +589,7 @@ static const struct Qdisc_class_ops mqprio_class_ops = { .walk = mqprio_walk, .dump = mqprio_dump_class, .dump_stats = mqprio_dump_class_stats, + .select_queue = mqprio_select_queue, }; static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = { diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index ff4fc3e0facd..012216386c0b 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -54,6 +54,7 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return NULL; } @@ -245,7 +246,7 @@ static int multiq_init(struct Qdisc *sch, struct nlattr *opt) if (opt == NULL) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index b1266e75ca43..dd70924cbcdf 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -77,8 +77,8 @@ struct netem_sched_data { struct qdisc_watchdog watchdog; - psched_tdiff_t latency; - psched_tdiff_t jitter; + s64 latency; + s64 jitter; u32 loss; u32 ecn; @@ -135,6 +135,13 @@ struct netem_sched_data { u32 a5; /* p23 used only in 4-states */ } clg; + struct tc_netem_slot slot_config; + struct slotstate { + u64 slot_next; + s32 packets_left; + s32 bytes_left; + } slot; + }; /* Time stamp put into socket buffer control block @@ -145,16 +152,9 @@ struct netem_sched_data { * we save skb->tstamp value in skb->cb[] before destroying it. */ struct netem_skb_cb { - psched_time_t time_to_send; - ktime_t tstamp_save; + u64 time_to_send; }; - -static struct sk_buff *netem_rb_to_skb(struct rb_node *rb) -{ - return rb_entry(rb, struct sk_buff, rbnode); -} - static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) { /* we assume we can use skb next/prev/tstamp as storage for rb_node */ @@ -312,11 +312,11 @@ static bool loss_event(struct netem_sched_data *q) * std deviation sigma. Uses table lookup to approximate the desired * distribution, and a uniformly-distributed pseudo-random source. */ -static psched_tdiff_t tabledist(psched_tdiff_t mu, psched_tdiff_t sigma, - struct crndstate *state, - const struct disttable *dist) +static s64 tabledist(s64 mu, s32 sigma, + struct crndstate *state, + const struct disttable *dist) { - psched_tdiff_t x; + s64 x; long t; u32 rnd; @@ -327,7 +327,7 @@ static psched_tdiff_t tabledist(psched_tdiff_t mu, psched_tdiff_t sigma, /* default uniform distribution */ if (dist == NULL) - return (rnd % (2*sigma)) - sigma + mu; + return (rnd % (2 * sigma)) - sigma + mu; t = dist->table[rnd % dist->size]; x = (sigma % NETEM_DIST_SCALE) * t; @@ -339,10 +339,8 @@ static psched_tdiff_t tabledist(psched_tdiff_t mu, psched_tdiff_t sigma, return x / NETEM_DIST_SCALE + (sigma / NETEM_DIST_SCALE) * t + mu; } -static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sched_data *q) +static u64 packet_time_ns(u64 len, const struct netem_sched_data *q) { - u64 ticks; - len += q->packet_overhead; if (q->cell_size) { @@ -353,21 +351,19 @@ static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sche len = cells * (q->cell_size + q->cell_overhead); } - ticks = (u64)len * NSEC_PER_SEC; - - do_div(ticks, q->rate); - return PSCHED_NS2TICKS(ticks); + return div64_u64(len * NSEC_PER_SEC, q->rate); } static void tfifo_reset(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); - struct rb_node *p; + struct rb_node *p = rb_first(&q->t_root); - while ((p = rb_first(&q->t_root))) { - struct sk_buff *skb = netem_rb_to_skb(p); + while (p) { + struct sk_buff *skb = rb_to_skb(p); - rb_erase(p, &q->t_root); + p = rb_next(p); + rb_erase(&skb->rbnode, &q->t_root); rtnl_kfree_skbs(skb, skb); } } @@ -375,14 +371,14 @@ static void tfifo_reset(struct Qdisc *sch) static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); - psched_time_t tnext = netem_skb_cb(nskb)->time_to_send; + 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 = netem_rb_to_skb(parent); + skb = rb_to_skb(parent); if (tnext >= netem_skb_cb(skb)->time_to_send) p = &parent->rb_right; else @@ -521,13 +517,13 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (q->gap == 0 || /* not doing reordering */ q->counter < q->gap - 1 || /* inside last reordering gap */ q->reorder < get_crandom(&q->reorder_cor)) { - psched_time_t now; - psched_tdiff_t delay; + u64 now; + s64 delay; delay = tabledist(q->latency, q->jitter, &q->delay_cor, q->delay_dist); - now = psched_get_time(); + now = ktime_get_ns(); if (q->rate) { struct netem_skb_cb *last = NULL; @@ -538,7 +534,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff *t_skb; struct netem_skb_cb *t_last; - t_skb = netem_rb_to_skb(rb_last(&q->t_root)); + 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) { @@ -553,15 +549,14 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, * from delay. */ delay -= last->time_to_send - now; - delay = max_t(psched_tdiff_t, 0, delay); + delay = max_t(s64, 0, delay); now = last->time_to_send; } - delay += packet_len_2_sched_time(qdisc_pkt_len(skb), q); + delay += packet_time_ns(qdisc_pkt_len(skb), q); } cb->time_to_send = now + delay; - cb->tstamp_save = skb->tstamp; ++q->counter; tfifo_enqueue(skb, sch); } else { @@ -569,7 +564,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, * Do re-ordering by putting one out of N packets at the front * of the queue. */ - cb->time_to_send = psched_get_time(); + cb->time_to_send = ktime_get_ns(); q->counter = 0; netem_enqueue_skb_head(&sch->q, skb); @@ -600,6 +595,20 @@ finish_segs: return NET_XMIT_SUCCESS; } +/* Delay the next round with a new future slot with a + * correct number of bytes and packets. + */ + +static void get_slot_next(struct netem_sched_data *q, u64 now) +{ + q->slot.slot_next = now + q->slot_config.min_delay + + (prandom_u32() * + (q->slot_config.max_delay - + q->slot_config.min_delay) >> 32); + q->slot.packets_left = q->slot_config.max_packets; + q->slot.bytes_left = q->slot_config.max_bytes; +} + static struct sk_buff *netem_dequeue(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); @@ -616,20 +625,26 @@ deliver: } p = rb_first(&q->t_root); if (p) { - psched_time_t time_to_send; + u64 time_to_send; + u64 now = ktime_get_ns(); - skb = netem_rb_to_skb(p); + skb = rb_to_skb(p); /* if more time remaining? */ time_to_send = netem_skb_cb(skb)->time_to_send; - if (time_to_send <= psched_get_time()) { - rb_erase(p, &q->t_root); + 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); sch->q.qlen--; qdisc_qstats_backlog_dec(sch, skb); skb->next = NULL; skb->prev = NULL; - skb->tstamp = netem_skb_cb(skb)->tstamp_save; + /* skb->dev shares skb->rbnode area, + * we need to restore its value. + */ + skb->dev = qdisc_dev(sch); #ifdef CONFIG_NET_CLS_ACT /* @@ -640,6 +655,14 @@ deliver: skb->tstamp = 0; #endif + if (q->slot.slot_next) { + q->slot.packets_left--; + q->slot.bytes_left -= qdisc_pkt_len(skb); + if (q->slot.packets_left <= 0 || + q->slot.bytes_left <= 0) + get_slot_next(q, now); + } + if (q->qdisc) { unsigned int pkt_len = qdisc_pkt_len(skb); struct sk_buff *to_free = NULL; @@ -663,7 +686,10 @@ deliver: if (skb) goto deliver; } - qdisc_watchdog_schedule(&q->watchdog, time_to_send); + + qdisc_watchdog_schedule_ns(&q->watchdog, + max(time_to_send, + q->slot.slot_next)); } if (q->qdisc) { @@ -694,6 +720,7 @@ static void dist_free(struct disttable *d) * Distribution data is a variable size payload containing * signed 16 bit values. */ + static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) { struct netem_sched_data *q = qdisc_priv(sch); @@ -724,6 +751,23 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) return 0; } +static void get_slot(struct netem_sched_data *q, const struct nlattr *attr) +{ + const struct tc_netem_slot *c = nla_data(attr); + + q->slot_config = *c; + if (q->slot_config.max_packets == 0) + q->slot_config.max_packets = INT_MAX; + if (q->slot_config.max_bytes == 0) + q->slot_config.max_bytes = INT_MAX; + q->slot.packets_left = q->slot_config.max_packets; + q->slot.bytes_left = q->slot_config.max_bytes; + if (q->slot_config.min_delay | q->slot_config.max_delay) + q->slot.slot_next = ktime_get_ns(); + else + q->slot.slot_next = 0; +} + static void get_correlation(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_corr *c = nla_data(attr); @@ -825,6 +869,9 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = { [TCA_NETEM_LOSS] = { .type = NLA_NESTED }, [TCA_NETEM_ECN] = { .type = NLA_U32 }, [TCA_NETEM_RATE64] = { .type = NLA_U64 }, + [TCA_NETEM_LATENCY64] = { .type = NLA_S64 }, + [TCA_NETEM_JITTER64] = { .type = NLA_S64 }, + [TCA_NETEM_SLOT] = { .len = sizeof(struct tc_netem_slot) }, }; static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, @@ -892,8 +939,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) sch->limit = qopt->limit; - q->latency = qopt->latency; - q->jitter = qopt->jitter; + q->latency = PSCHED_TICKS2NS(qopt->latency); + q->jitter = PSCHED_TICKS2NS(qopt->jitter); q->limit = qopt->limit; q->gap = qopt->gap; q->counter = 0; @@ -922,9 +969,18 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) q->rate = max_t(u64, q->rate, nla_get_u64(tb[TCA_NETEM_RATE64])); + if (tb[TCA_NETEM_LATENCY64]) + q->latency = nla_get_s64(tb[TCA_NETEM_LATENCY64]); + + if (tb[TCA_NETEM_JITTER64]) + q->jitter = nla_get_s64(tb[TCA_NETEM_JITTER64]); + if (tb[TCA_NETEM_ECN]) q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]); + if (tb[TCA_NETEM_SLOT]) + get_slot(q, tb[TCA_NETEM_SLOT]); + return ret; } @@ -1014,9 +1070,12 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) struct tc_netem_reorder reorder; struct tc_netem_corrupt corrupt; struct tc_netem_rate rate; + struct tc_netem_slot slot; - qopt.latency = q->latency; - qopt.jitter = q->jitter; + qopt.latency = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->latency), + UINT_MAX); + qopt.jitter = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->jitter), + UINT_MAX); qopt.limit = q->limit; qopt.loss = q->loss; qopt.gap = q->gap; @@ -1024,6 +1083,12 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt)) goto nla_put_failure; + if (nla_put(skb, TCA_NETEM_LATENCY64, sizeof(q->latency), &q->latency)) + goto nla_put_failure; + + if (nla_put(skb, TCA_NETEM_JITTER64, sizeof(q->jitter), &q->jitter)) + goto nla_put_failure; + cor.delay_corr = q->delay_cor.rho; cor.loss_corr = q->loss_cor.rho; cor.dup_corr = q->dup_cor.rho; @@ -1060,6 +1125,16 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) if (dump_loss_model(q, skb) != 0) goto nla_put_failure; + if (q->slot_config.min_delay | q->slot_config.max_delay) { + slot = q->slot_config; + if (slot.max_packets == INT_MAX) + slot.max_packets = 0; + if (slot.max_bytes == INT_MAX) + slot.max_bytes = 0; + if (nla_put(skb, TCA_NETEM_SLOT, sizeof(slot), &slot)) + goto nla_put_failure; + } + return nla_nest_end(skb, nla); nla_put_failure: diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 6c2791d6102d..776c694c77c7 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -74,6 +74,7 @@ struct pie_sched_data { struct pie_vars vars; struct pie_stats stats; struct timer_list adapt_timer; + struct Qdisc *sch; }; static void pie_params_init(struct pie_params *params) @@ -422,10 +423,10 @@ static void calculate_probability(struct Qdisc *sch) pie_vars_init(&q->vars); } -static void pie_timer(unsigned long arg) +static void pie_timer(struct timer_list *t) { - struct Qdisc *sch = (struct Qdisc *)arg; - struct pie_sched_data *q = qdisc_priv(sch); + struct pie_sched_data *q = from_timer(q, t, adapt_timer); + struct Qdisc *sch = q->sch; spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -446,7 +447,8 @@ static int pie_init(struct Qdisc *sch, struct nlattr *opt) pie_vars_init(&q->vars); sch->limit = q->params.limit; - setup_timer(&q->adapt_timer, pie_timer, (unsigned long)sch); + q->sch = sch; + timer_setup(&q->adapt_timer, pie_timer, 0); if (opt) { int err = pie_change(sch, opt); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 2dd6c68ae91e..2c79559a0d31 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -50,6 +50,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return NULL; } @@ -212,7 +213,7 @@ static int prio_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 6ddfd4991108..6962b37a3ad3 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -709,6 +709,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return NULL; } @@ -1419,7 +1420,7 @@ static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt) int i, j, err; u32 max_cl_shift, maxbudg_shift, max_classes; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 93b9d70a9b28..7f8ea9e297c3 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -19,6 +19,7 @@ #include <linux/kernel.h> #include <linux/skbuff.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <net/inet_ecn.h> #include <net/red.h> @@ -40,6 +41,7 @@ struct red_sched_data { u32 limit; /* HARD maximal queue length */ unsigned char flags; struct timer_list adapt_timer; + struct Qdisc *sch; struct red_parms parms; struct red_vars vars; struct red_stats stats; @@ -147,11 +149,37 @@ static void red_reset(struct Qdisc *sch) red_restart(&q->vars); } +static int red_offload(struct Qdisc *sch, bool enable) +{ + struct red_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_red_qopt_offload opt = { + .handle = sch->handle, + .parent = sch->parent, + }; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return -EOPNOTSUPP; + + if (enable) { + opt.command = TC_RED_REPLACE; + 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.is_ecn = red_use_ecn(q); + } else { + opt.command = TC_RED_DESTROY; + } + + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, &opt); +} + static void red_destroy(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); del_timer_sync(&q->adapt_timer); + red_offload(sch, false); qdisc_destroy(q->qdisc); } @@ -218,13 +246,14 @@ 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); return 0; } -static inline void red_adaptative_timer(unsigned long arg) +static inline void red_adaptative_timer(struct timer_list *t) { - struct Qdisc *sch = (struct Qdisc *)arg; - struct red_sched_data *q = qdisc_priv(sch); + struct red_sched_data *q = from_timer(q, t, adapt_timer); + struct Qdisc *sch = q->sch; spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -238,10 +267,40 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt) struct red_sched_data *q = qdisc_priv(sch); q->qdisc = &noop_qdisc; - setup_timer(&q->adapt_timer, red_adaptative_timer, (unsigned long)sch); + q->sch = sch; + timer_setup(&q->adapt_timer, red_adaptative_timer, 0); return red_change(sch, opt); } +static int red_dump_offload(struct Qdisc *sch, struct tc_red_qopt *opt) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_red_qopt_offload hw_stats = { + .command = TC_RED_STATS, + .handle = sch->handle, + .parent = sch->parent, + { + .stats.bstats = &sch->bstats, + .stats.qstats = &sch->qstats, + }, + }; + int err; + + opt->flags &= ~TC_RED_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) + opt->flags |= TC_RED_OFFLOADED; + + return err; +} + static int red_dump(struct Qdisc *sch, struct sk_buff *skb) { struct red_sched_data *q = qdisc_priv(sch); @@ -255,8 +314,13 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) .Plog = q->parms.Plog, .Scell_log = q->parms.Scell_log, }; + int err; sch->qstats.backlog = q->qdisc->qstats.backlog; + err = red_dump_offload(sch, &opt); + if (err) + goto nla_put_failure; + opts = nla_nest_start(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; @@ -273,6 +337,7 @@ nla_put_failure: static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct red_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); struct tc_red_xstats st = { .early = q->stats.prob_drop + q->stats.forced_drop, .pdrop = q->stats.pdrop, @@ -280,6 +345,26 @@ static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) .marked = q->stats.prob_mark + q->stats.forced_mark, }; + if (tc_can_offload(dev) && dev->netdev_ops->ndo_setup_tc) { + struct red_stats hw_stats = {0}; + struct tc_red_qopt_offload hw_stats_request = { + .command = TC_RED_XSTATS, + .handle = sch->handle, + .parent = sch->parent, + { + .xstats = &hw_stats, + }, + }; + if (!dev->netdev_ops->ndo_setup_tc(dev, + TC_SETUP_QDISC_RED, + &hw_stats_request)) { + st.early += hw_stats.prob_drop + hw_stats.forced_drop; + st.pdrop += hw_stats.pdrop; + st.other += hw_stats.other; + st.marked += hw_stats.prob_mark + hw_stats.forced_mark; + } + } + return gnet_stats_copy_app(d, &st, sizeof(st)); } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index cc39e170b4aa..0678debdd856 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -268,6 +268,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl, case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return false; } @@ -553,7 +554,7 @@ static int sfb_init(struct Qdisc *sch, struct nlattr *opt) struct sfb_sched_data *q = qdisc_priv(sch); int err; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 74ea863b8240..890f4a4564e7 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -145,6 +145,7 @@ struct sfq_sched_data { int perturb_period; unsigned int quantum; /* Allotment per round: MUST BE >= MTU */ struct timer_list perturb_timer; + struct Qdisc *sch; }; /* @@ -189,6 +190,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return 0; } @@ -604,10 +606,10 @@ drop: qdisc_tree_reduce_backlog(sch, dropped, drop_len); } -static void sfq_perturbation(unsigned long arg) +static void sfq_perturbation(struct timer_list *t) { - struct Qdisc *sch = (struct Qdisc *)arg; - struct sfq_sched_data *q = qdisc_priv(sch); + struct sfq_sched_data *q = from_timer(q, t, perturb_timer); + struct Qdisc *sch = q->sch; spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -722,10 +724,9 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) int i; int err; - setup_deferrable_timer(&q->perturb_timer, sfq_perturbation, - (unsigned long)sch); + timer_setup(&q->perturb_timer, sfq_perturbation, TIMER_DEFERRABLE); - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; |