diff options
Diffstat (limited to 'net/sched')
31 files changed, 866 insertions, 427 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 919847beec3..a1a8e29e5fc 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -295,6 +295,19 @@ config NET_SCH_HHF To compile this driver as a module, choose M here: the module will be called sch_hhf. +config NET_SCH_PIE + tristate "Proportional Integral controller Enhanced (PIE) scheduler" + help + Say Y here if you want to use the Proportional Integral controller + Enhanced scheduler packet scheduling algorithm. + For more information, please see + http://tools.ietf.org/html/draft-pan-tsvwg-pie-00 + + To compile this driver as a module, choose M here: the module + will be called sch_pie. + + If unsure, say N. + config NET_SCH_INGRESS tristate "Ingress Qdisc" depends on NET_CLS_ACT @@ -444,6 +457,7 @@ config NET_CLS_FLOW config NET_CLS_CGROUP tristate "Control Group Classifier" select NET_CLS + select CGROUP_NET_CLASSID depends on CGROUPS ---help--- Say Y here if you want to classify packets based on the control diff --git a/net/sched/Makefile b/net/sched/Makefile index 3442e5fbc4d..0a869a11f3e 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -41,6 +41,7 @@ obj-$(CONFIG_NET_SCH_CODEL) += sch_codel.o obj-$(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_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 8114fef308d..35f89e9ce49 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -126,9 +126,10 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a, for (i = 0; i < (hinfo->hmask + 1); i++) { head = &hinfo->htab[tcf_hash(i, hinfo->hmask)]; hlist_for_each_entry_safe(p, n, head, tcfc_head) { - if (ACT_P_DELETED == tcf_hash_release(p, 0, hinfo)) + if (ACT_P_DELETED == tcf_hash_release(p, 0, hinfo)) { module_put(a->ops->owner); - n_i++; + n_i++; + } } } if (nla_put_u32(skb, TCA_FCNT, n_i)) @@ -141,8 +142,8 @@ nla_put_failure: return -EINVAL; } -int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb, - int type, struct tc_action *a) +static int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb, + int type, struct tc_action *a) { struct tcf_hashinfo *hinfo = a->ops->hinfo; @@ -155,7 +156,6 @@ int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb, return -EINVAL; } } -EXPORT_SYMBOL(tcf_generic_walker); struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo) { @@ -173,21 +173,21 @@ struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo) } EXPORT_SYMBOL(tcf_hash_lookup); -u32 tcf_hash_new_index(u32 *idx_gen, struct tcf_hashinfo *hinfo) +u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo) { - u32 val = *idx_gen; + u32 val = hinfo->index; do { if (++val == 0) val = 1; } while (tcf_hash_lookup(val, hinfo)); - *idx_gen = val; + hinfo->index = val; return val; } EXPORT_SYMBOL(tcf_hash_new_index); -int tcf_hash_search(struct tc_action *a, u32 index) +static int tcf_hash_search(struct tc_action *a, u32 index) { struct tcf_hashinfo *hinfo = a->ops->hinfo; struct tcf_common *p = tcf_hash_lookup(index, hinfo); @@ -198,7 +198,6 @@ int tcf_hash_search(struct tc_action *a, u32 index) } return 0; } -EXPORT_SYMBOL(tcf_hash_search); struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, int bind, struct tcf_hashinfo *hinfo) @@ -216,7 +215,7 @@ EXPORT_SYMBOL(tcf_hash_check); struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, int size, int bind, - u32 *idx_gen, struct tcf_hashinfo *hinfo) + struct tcf_hashinfo *hinfo) { struct tcf_common *p = kzalloc(size, GFP_KERNEL); @@ -228,7 +227,7 @@ struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est, spin_lock_init(&p->tcfc_lock); INIT_HLIST_NODE(&p->tcfc_head); - p->tcfc_index = index ? index : tcf_hash_new_index(idx_gen, hinfo); + p->tcfc_index = index ? index : tcf_hash_new_index(hinfo); p->tcfc_tm.install = jiffies; p->tcfc_tm.lastuse = jiffies; if (est) { @@ -291,12 +290,12 @@ int tcf_unregister_action(struct tc_action_ops *act) int err = -ENOENT; write_lock(&act_mod_lock); - list_for_each_entry(a, &act_base, head) - if (a == act) + list_for_each_entry(a, &act_base, head) { + if (a == act) { + list_del(&act->head); + err = 0; break; - if (a) { - list_del(&act->head); - err = 0; + } } write_unlock(&act_mod_lock); return err; @@ -306,68 +305,41 @@ EXPORT_SYMBOL(tcf_unregister_action); /* lookup by name */ static struct tc_action_ops *tc_lookup_action_n(char *kind) { - struct tc_action_ops *a = NULL; + struct tc_action_ops *a, *res = NULL; if (kind) { read_lock(&act_mod_lock); list_for_each_entry(a, &act_base, head) { if (strcmp(kind, a->kind) == 0) { - if (!try_module_get(a->owner)) { - read_unlock(&act_mod_lock); - return NULL; - } + if (try_module_get(a->owner)) + res = a; break; } } read_unlock(&act_mod_lock); } - return a; + return res; } /* lookup by nlattr */ static struct tc_action_ops *tc_lookup_action(struct nlattr *kind) { - struct tc_action_ops *a = NULL; + struct tc_action_ops *a, *res = NULL; if (kind) { read_lock(&act_mod_lock); list_for_each_entry(a, &act_base, head) { if (nla_strcmp(kind, a->kind) == 0) { - if (!try_module_get(a->owner)) { - read_unlock(&act_mod_lock); - return NULL; - } + if (try_module_get(a->owner)) + res = a; break; } } read_unlock(&act_mod_lock); } - return a; + return res; } -#if 0 -/* lookup by id */ -static struct tc_action_ops *tc_lookup_action_id(u32 type) -{ - struct tc_action_ops *a = NULL; - - if (type) { - read_lock(&act_mod_lock); - for (a = act_base; a; a = a->next) { - if (a->type == type) { - if (!try_module_get(a->owner)) { - read_unlock(&act_mod_lock); - return NULL; - } - break; - } - } - read_unlock(&act_mod_lock); - } - return a; -} -#endif - int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions, struct tcf_result *res) { @@ -381,18 +353,16 @@ int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions, } list_for_each_entry(a, actions, list) { repeat: - if (a->ops) { - ret = a->ops->act(skb, a, res); - if (TC_MUNGED & skb->tc_verd) { - /* copied already, allow trampling */ - skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd); - skb->tc_verd = CLR_TC_MUNGED(skb->tc_verd); - } - if (ret == TC_ACT_REPEAT) - goto repeat; /* we need a ttl - JHS */ - if (ret != TC_ACT_PIPE) - goto exec_done; + ret = a->ops->act(skb, a, res); + if (TC_MUNGED & skb->tc_verd) { + /* copied already, allow trampling */ + skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd); + skb->tc_verd = CLR_TC_MUNGED(skb->tc_verd); } + if (ret == TC_ACT_REPEAT) + goto repeat; /* we need a ttl - JHS */ + if (ret != TC_ACT_PIPE) + goto exec_done; } exec_done: return ret; @@ -404,27 +374,16 @@ void tcf_action_destroy(struct list_head *actions, int bind) struct tc_action *a, *tmp; list_for_each_entry_safe(a, tmp, actions, list) { - if (a->ops) { - if (a->ops->cleanup(a, bind) == ACT_P_DELETED) - module_put(a->ops->owner); - list_del(&a->list); - kfree(a); - } else { - /*FIXME: Remove later - catch insertion bugs*/ - WARN(1, "tcf_action_destroy: BUG? destroying NULL ops\n"); - list_del(&a->list); - kfree(a); - } + if (a->ops->cleanup(a, bind) == ACT_P_DELETED) + module_put(a->ops->owner); + list_del(&a->list); + kfree(a); } } int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { - int err = -EINVAL; - - if (a->ops == NULL) - return err; return a->ops->dump(skb, a, bind, ref); } @@ -435,9 +394,6 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; - if (a->ops == NULL) - return err; - if (nla_put_string(skb, TCA_KIND, a->ops->kind)) goto nla_put_failure; if (tcf_action_copy_stats(skb, a, 0)) @@ -600,9 +556,9 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, { int err = 0; struct gnet_dump d; - struct tcf_act_hdr *h = a->priv; + struct tcf_common *p = a->priv; - if (h == NULL) + if (p == NULL) goto errout; /* compat_mode being true specifies a call that is supposed @@ -611,20 +567,20 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, if (compat_mode) { if (a->type == TCA_OLD_COMPAT) err = gnet_stats_start_copy_compat(skb, 0, - TCA_STATS, TCA_XSTATS, &h->tcf_lock, &d); + TCA_STATS, TCA_XSTATS, &p->tcfc_lock, &d); else return 0; } else err = gnet_stats_start_copy(skb, TCA_ACT_STATS, - &h->tcf_lock, &d); + &p->tcfc_lock, &d); if (err < 0) goto errout; - if (gnet_stats_copy_basic(&d, &h->tcf_bstats) < 0 || - gnet_stats_copy_rate_est(&d, &h->tcf_bstats, - &h->tcf_rate_est) < 0 || - gnet_stats_copy_queue(&d, &h->tcf_qstats) < 0) + if (gnet_stats_copy_basic(&d, &p->tcfc_bstats) < 0 || + gnet_stats_copy_rate_est(&d, &p->tcfc_bstats, + &p->tcfc_rate_est) < 0 || + gnet_stats_copy_queue(&d, &p->tcfc_qstats) < 0) goto errout; if (gnet_stats_finish_copy(&d) < 0) @@ -713,7 +669,7 @@ tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 portid) INIT_LIST_HEAD(&a->list); err = -EINVAL; a->ops = tc_lookup_action(tb[TCA_ACT_KIND]); - if (a->ops == NULL) + if (a->ops == NULL) /* could happen in batch of actions */ goto err_free; err = -ENOENT; if (a->ops->lookup(a, index) == 0) @@ -789,7 +745,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, err = -EINVAL; kind = tb[TCA_ACT_KIND]; a->ops = tc_lookup_action(kind); - if (a->ops == NULL) + if (a->ops == NULL) /*some idjot trying to flush unknown action */ goto err_out; nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0); @@ -833,6 +789,33 @@ noflush_out: } static int +tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, + u32 portid) +{ + int ret; + struct sk_buff *skb; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION, + 0, 1) <= 0) { + kfree_skb(skb); + return -EINVAL; + } + + /* now do the delete */ + tcf_action_destroy(actions, 0); + + ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); + if (ret > 0) + return 0; + return ret; +} + +static int tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, u32 portid, int event) { @@ -865,27 +848,9 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, if (event == RTM_GETACTION) ret = act_get_notify(net, portid, n, &actions, event); else { /* delete */ - struct sk_buff *skb; - - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) { - ret = -ENOBUFS; + ret = tcf_del_notify(net, n, &actions, portid); + if (ret) goto err; - } - - if (tca_get_fill(skb, &actions, portid, n->nlmsg_seq, 0, event, - 0, 1) <= 0) { - kfree_skb(skb); - ret = -EINVAL; - goto err; - } - - /* now do the delete */ - tcf_action_destroy(&actions, 0); - ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); - if (ret > 0) - return 0; return ret; } err: @@ -893,60 +858,36 @@ err: return ret; } -static int tcf_add_notify(struct net *net, struct list_head *actions, - u32 portid, u32 seq, int event, u16 flags) +static int +tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, + u32 portid) { - struct tcamsg *t; - struct nlmsghdr *nlh; struct sk_buff *skb; - struct nlattr *nest; - unsigned char *b; int err = 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; - b = skb_tail_pointer(skb); - - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*t), flags); - if (!nlh) - goto out_kfree_skb; - t = nlmsg_data(nlh); - t->tca_family = AF_UNSPEC; - t->tca__pad1 = 0; - t->tca__pad2 = 0; - - nest = nla_nest_start(skb, TCA_ACT_TAB); - if (nest == NULL) - goto out_kfree_skb; - - if (tcf_action_dump(skb, actions, 0, 0) < 0) - goto out_kfree_skb; - - nla_nest_end(skb, nest); - - nlh->nlmsg_len = skb_tail_pointer(skb) - b; - NETLINK_CB(skb).dst_group = RTNLGRP_TC; + if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, n->nlmsg_flags, + RTM_NEWACTION, 0, 0) <= 0) { + kfree_skb(skb); + return -EINVAL; + } - err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO); + err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); if (err > 0) err = 0; return err; - -out_kfree_skb: - kfree_skb(skb); - return -1; } - static int tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, u32 portid, int ovr) { int ret = 0; LIST_HEAD(actions); - u32 seq = n->nlmsg_seq; ret = tcf_action_init(net, nla, NULL, NULL, ovr, 0, &actions); if (ret) @@ -955,7 +896,7 @@ tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, /* dump then free all the actions after update; inserted policy * stays intact */ - ret = tcf_add_notify(net, &actions, portid, seq, RTM_NEWACTION, n->nlmsg_flags); + ret = tcf_add_notify(net, n, &actions, portid); cleanup_a(&actions); done: return ret; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 5d350c57af3..ee28e1ccbbd 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -37,7 +37,6 @@ #include <net/tc_act/tc_csum.h> #define CSUM_TAB_MASK 15 -static u32 csum_idx_gen; static struct tcf_hashinfo csum_hash_info; static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = { @@ -67,19 +66,19 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, pc = tcf_hash_check(parm->index, a, bind, &csum_hash_info); if (!pc) { pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, - &csum_idx_gen, &csum_hash_info); + &csum_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); - p = to_tcf_csum(pc); ret = ACT_P_CREATED; } else { - p = to_tcf_csum(pc); - if (!ovr) { - tcf_hash_release(pc, bind, &csum_hash_info); + if (bind)/* dont override defaults */ + return 0; + tcf_hash_release(pc, bind, &csum_hash_info); + if (!ovr) return -EEXIST; - } } + p = to_tcf_csum(pc); spin_lock_bh(&p->tcf_lock); p->tcf_action = parm->action; p->update_flags = parm->update_flags; @@ -586,7 +585,7 @@ MODULE_LICENSE("GPL"); static int __init csum_init_module(void) { - int err = tcf_hashinfo_init(&csum_hash_info, CSUM_TAB_MASK+1); + int err = tcf_hashinfo_init(&csum_hash_info, CSUM_TAB_MASK); if (err) return err; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 1e6e0e76524..f26e6b890cc 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -24,7 +24,6 @@ #include <net/tc_act/tc_gact.h> #define GACT_TAB_MASK 15 -static u32 gact_idx_gen; static struct tcf_hashinfo gact_hash_info; #ifdef CONFIG_GACT_PROB @@ -90,15 +89,16 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, pc = tcf_hash_check(parm->index, a, bind, &gact_hash_info); if (!pc) { pc = tcf_hash_create(parm->index, est, a, sizeof(*gact), - bind, &gact_idx_gen, &gact_hash_info); + bind, &gact_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); ret = ACT_P_CREATED; } else { - if (!ovr) { - tcf_hash_release(pc, bind, &gact_hash_info); + if (bind)/* dont override defaults */ + return 0; + tcf_hash_release(pc, bind, &gact_hash_info); + if (!ovr) return -EEXIST; - } } gact = to_gact(pc); @@ -208,7 +208,7 @@ MODULE_LICENSE("GPL"); static int __init gact_init_module(void) { - int err = tcf_hashinfo_init(&gact_hash_info, GACT_TAB_MASK+1); + int err = tcf_hashinfo_init(&gact_hash_info, GACT_TAB_MASK); if (err) return err; #ifdef CONFIG_GACT_PROB diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 8344380ebaf..484bd19601e 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -29,7 +29,6 @@ #define IPT_TAB_MASK 15 -static u32 ipt_idx_gen; static struct tcf_hashinfo ipt_hash_info; static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int hook) @@ -129,15 +128,17 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, pc = tcf_hash_check(index, a, bind, &ipt_hash_info); if (!pc) { pc = tcf_hash_create(index, est, a, sizeof(*ipt), bind, - &ipt_idx_gen, &ipt_hash_info); + &ipt_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); ret = ACT_P_CREATED; } else { - if (!ovr) { - tcf_ipt_release(to_ipt(pc), bind); + if (bind)/* dont override defaults */ + return 0; + tcf_ipt_release(to_ipt(pc), bind); + + if (!ovr) return -EEXIST; - } } ipt = to_ipt(pc); @@ -314,7 +315,7 @@ MODULE_ALIAS("act_xt"); static int __init ipt_init_module(void) { int ret1, ret2, err; - err = tcf_hashinfo_init(&ipt_hash_info, IPT_TAB_MASK+1); + err = tcf_hashinfo_init(&ipt_hash_info, IPT_TAB_MASK); if (err) return err; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 199fc9838af..5d05b573a62 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -30,7 +30,6 @@ #include <linux/if_arp.h> #define MIRRED_TAB_MASK 7 -static u32 mirred_idx_gen; static LIST_HEAD(mirred_list); static struct tcf_hashinfo mirred_hash_info; @@ -107,7 +106,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, if (dev == NULL) return -EINVAL; pc = tcf_hash_create(parm->index, est, a, sizeof(*m), bind, - &mirred_idx_gen, &mirred_hash_info); + &mirred_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); ret = ACT_P_CREATED; @@ -276,7 +275,7 @@ static int __init mirred_init_module(void) if (err) return err; - err = tcf_hashinfo_init(&mirred_hash_info, MIRRED_TAB_MASK+1); + err = tcf_hashinfo_init(&mirred_hash_info, MIRRED_TAB_MASK); if (err) { unregister_netdevice_notifier(&mirred_device_notifier); return err; @@ -287,9 +286,9 @@ static int __init mirred_init_module(void) static void __exit mirred_cleanup_module(void) { - unregister_netdevice_notifier(&mirred_device_notifier); - tcf_hashinfo_destroy(&mirred_hash_info); tcf_unregister_action(&act_mirred_ops); + tcf_hashinfo_destroy(&mirred_hash_info); + unregister_netdevice_notifier(&mirred_device_notifier); } module_init(mirred_init_module); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 409fe7181c5..a49fa23b49d 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -30,7 +30,6 @@ #define NAT_TAB_MASK 15 -static u32 nat_idx_gen; static struct tcf_hashinfo nat_hash_info; @@ -61,18 +60,18 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, pc = tcf_hash_check(parm->index, a, bind, &nat_hash_info); if (!pc) { pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, - &nat_idx_gen, &nat_hash_info); + &nat_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); - p = to_tcf_nat(pc); ret = ACT_P_CREATED; } else { - p = to_tcf_nat(pc); - if (!ovr) { - tcf_hash_release(pc, bind, &nat_hash_info); + if (bind) + return 0; + tcf_hash_release(pc, bind, &nat_hash_info); + if (!ovr) return -EEXIST; - } } + p = to_tcf_nat(pc); spin_lock_bh(&p->tcf_lock); p->old_addr = parm->old_addr; @@ -310,7 +309,7 @@ MODULE_LICENSE("GPL"); static int __init nat_init_module(void) { - int err = tcf_hashinfo_init(&nat_hash_info, NAT_TAB_MASK+1); + int err = tcf_hashinfo_init(&nat_hash_info, NAT_TAB_MASK); if (err) return err; return tcf_register_action(&act_nat_ops); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index aa5347c1b9f..f361e4e3c31 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -24,7 +24,6 @@ #include <net/tc_act/tc_pedit.h> #define PEDIT_TAB_MASK 15 -static u32 pedit_idx_gen; static struct tcf_hashinfo pedit_hash_info; @@ -63,7 +62,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (!parm->nkeys) return -EINVAL; pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, - &pedit_idx_gen, &pedit_hash_info); + &pedit_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); p = to_pedit(pc); @@ -78,10 +77,12 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, ret = ACT_P_CREATED; } else { p = to_pedit(pc); - if (!ovr) { - tcf_hash_release(pc, bind, &pedit_hash_info); + tcf_hash_release(pc, bind, &pedit_hash_info); + if (bind) + return 0; + if (!ovr) return -EEXIST; - } + if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) { keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) @@ -246,7 +247,7 @@ MODULE_LICENSE("GPL"); static int __init pedit_init_module(void) { - int err = tcf_hashinfo_init(&pedit_hash_info, PEDIT_TAB_MASK+1); + int err = tcf_hashinfo_init(&pedit_hash_info, PEDIT_TAB_MASK); if (err) return err; return tcf_register_action(&act_pedit_ops); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 7b23ab07c6c..a719fdff575 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -41,7 +41,6 @@ struct tcf_police { container_of(pc, struct tcf_police, common) #define POL_TAB_MASK 15 -static u32 police_idx_gen; static struct tcf_hashinfo police_hash_info; /* old policer structure from before tc actions */ @@ -162,10 +161,12 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla, if (bind) { police->tcf_bindcnt += 1; police->tcf_refcnt += 1; + return 0; } if (ovr) goto override; - return ret; + /* not replacing */ + return -EEXIST; } } @@ -249,7 +250,7 @@ override: police->tcfp_t_c = ktime_to_ns(ktime_get()); police->tcf_index = parm->index ? parm->index : - tcf_hash_new_index(&police_idx_gen, &police_hash_info); + tcf_hash_new_index(&police_hash_info); h = tcf_hash(police->tcf_index, POL_TAB_MASK); spin_lock_bh(&police_hash_info.lock); hlist_add_head(&police->tcf_head, &police_hash_info.htab[h]); @@ -396,7 +397,7 @@ static struct tc_action_ops act_police_ops = { static int __init police_init_module(void) { - int err = tcf_hashinfo_init(&police_hash_info, POL_TAB_MASK+1); + int err = tcf_hashinfo_init(&police_hash_info, POL_TAB_MASK); if (err) return err; err = tcf_register_action(&act_police_ops); diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 2d7a0eb11c6..f7d5406c1fe 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -25,7 +25,6 @@ #include <net/tc_act/tc_defact.h> #define SIMP_TAB_MASK 7 -static u32 simp_idx_gen; static struct tcf_hashinfo simp_hash_info; #define SIMP_MAX_DATA 32 @@ -118,7 +117,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, pc = tcf_hash_check(parm->index, a, bind, &simp_hash_info); if (!pc) { pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind, - &simp_idx_gen, &simp_hash_info); + &simp_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); @@ -135,10 +134,13 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, ret = ACT_P_CREATED; } else { d = to_defact(pc); - if (!ovr) { - tcf_simp_release(d, bind); + + if (bind) + return 0; + tcf_simp_release(d, bind); + if (!ovr) return -EEXIST; - } + reset_policy(d, defdata, parm); } @@ -203,7 +205,7 @@ MODULE_LICENSE("GPL"); static int __init simp_init_module(void) { int err, ret; - err = tcf_hashinfo_init(&simp_hash_info, SIMP_TAB_MASK+1); + err = tcf_hashinfo_init(&simp_hash_info, SIMP_TAB_MASK); if (err) return err; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 90ed04a83cf..74af4612706 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -28,7 +28,6 @@ #include <net/tc_act/tc_skbedit.h> #define SKBEDIT_TAB_MASK 15 -static u32 skbedit_idx_gen; static struct tcf_hashinfo skbedit_hash_info; static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, @@ -104,7 +103,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, pc = tcf_hash_check(parm->index, a, bind, &skbedit_hash_info); if (!pc) { pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind, - &skbedit_idx_gen, &skbedit_hash_info); + &skbedit_hash_info); if (IS_ERR(pc)) return PTR_ERR(pc); @@ -112,10 +111,11 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, ret = ACT_P_CREATED; } else { d = to_skbedit(pc); - if (!ovr) { - tcf_hash_release(pc, bind, &skbedit_hash_info); + if (bind) + return 0; + tcf_hash_release(pc, bind, &skbedit_hash_info); + if (!ovr) return -EEXIST; - } } spin_lock_bh(&d->tcf_lock); @@ -203,7 +203,7 @@ MODULE_LICENSE("GPL"); static int __init skbedit_init_module(void) { - int err = tcf_hashinfo_init(&skbedit_hash_info, SKBEDIT_TAB_MASK+1); + int err = tcf_hashinfo_init(&skbedit_hash_info, SKBEDIT_TAB_MASK); if (err) return err; return tcf_register_action(&act_skbedit_ops); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 6b085cf27a6..29a30a14c31 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -40,20 +40,20 @@ static DEFINE_RWLOCK(cls_mod_lock); static const struct tcf_proto_ops *tcf_proto_lookup_ops(struct nlattr *kind) { - const struct tcf_proto_ops *t = NULL; + const struct tcf_proto_ops *t, *res = NULL; if (kind) { read_lock(&cls_mod_lock); list_for_each_entry(t, &tcf_proto_base, head) { if (nla_strcmp(kind, t->kind) == 0) { - if (!try_module_get(t->owner)) - t = NULL; + if (try_module_get(t->owner)) + res = t; break; } } read_unlock(&cls_mod_lock); } - return t; + return res; } /* Register(unregister) new classifier type */ @@ -82,15 +82,13 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) int rc = -ENOENT; write_lock(&cls_mod_lock); - list_for_each_entry(t, &tcf_proto_base, head) - if (t == ops) + list_for_each_entry(t, &tcf_proto_base, head) { + if (t == ops) { + list_del(&t->head); + rc = 0; break; - - if (!t) - goto out; - list_del(&t->head); - rc = 0; -out: + } + } write_unlock(&cls_mod_lock); return rc; } @@ -342,7 +340,7 @@ errout: return err; } -static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp, +static int tcf_fill_node(struct net *net, struct sk_buff *skb, struct tcf_proto *tp, unsigned long fh, u32 portid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; @@ -364,7 +362,7 @@ static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp, tcm->tcm_handle = fh; if (RTM_DELTFILTER != event) { tcm->tcm_handle = 0; - if (tp->ops->dump && tp->ops->dump(tp, fh, skb, tcm) < 0) + if (tp->ops->dump && tp->ops->dump(net, tp, fh, skb, tcm) < 0) goto nla_put_failure; } nlh->nlmsg_len = skb_tail_pointer(skb) - b; @@ -387,7 +385,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(skb, tp, fh, portid, n->nlmsg_seq, 0, event) <= 0) { + if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, 0, event) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -406,8 +404,9 @@ static int tcf_node_dump(struct tcf_proto *tp, unsigned long n, struct tcf_walker *arg) { struct tcf_dump_args *a = (void *)arg; + struct net *net = sock_net(a->skb->sk); - return tcf_fill_node(a->skb, tp, n, NETLINK_CB(a->cb->skb).portid, + return tcf_fill_node(net, a->skb, tp, n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER); } @@ -465,7 +464,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (t > s_t) memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(cb->args[0])); if (cb->args[1] == 0) { - if (tcf_fill_node(skb, tp, 0, NETLINK_CB(cb->skb).portid, + if (tcf_fill_node(net, skb, tp, 0, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER) <= 0) break; @@ -579,7 +578,7 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts) } else if (exts->police) { struct tc_action *act = tcf_exts_first_act(exts); nest = nla_nest_start(skb, exts->police); - if (nest == NULL) + if (nest == NULL || !act) goto nla_put_failure; if (tcf_action_dump_old(skb, act, 0, 0) < 0) goto nla_put_failure; diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index b6552035d1f..e98ca99c202 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -38,7 +38,7 @@ static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { int r; - struct basic_head *head = (struct basic_head *) tp->root; + struct basic_head *head = tp->root; struct basic_filter *f; list_for_each_entry(f, &head->flist, link) { @@ -56,7 +56,7 @@ static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, static unsigned long basic_get(struct tcf_proto *tp, u32 handle) { unsigned long l = 0UL; - struct basic_head *head = (struct basic_head *) tp->root; + struct basic_head *head = tp->root; struct basic_filter *f; if (head == NULL) @@ -107,7 +107,7 @@ static void basic_destroy(struct tcf_proto *tp) static int basic_delete(struct tcf_proto *tp, unsigned long arg) { - struct basic_head *head = (struct basic_head *) tp->root; + struct basic_head *head = tp->root; struct basic_filter *t, *f = (struct basic_filter *) arg; list_for_each_entry(t, &head->flist, link) @@ -164,7 +164,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, struct nlattr **tca, unsigned long *arg) { int err; - struct basic_head *head = (struct basic_head *) tp->root; + struct basic_head *head = tp->root; struct nlattr *tb[TCA_BASIC_MAX + 1]; struct basic_filter *f = (struct basic_filter *) *arg; @@ -225,7 +225,7 @@ errout: static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct basic_head *head = (struct basic_head *) tp->root; + struct basic_head *head = tp->root; struct basic_filter *f; list_for_each_entry(f, &head->flist, link) { @@ -241,7 +241,7 @@ skip: } } -static int basic_dump(struct tcf_proto *tp, unsigned long fh, +static int basic_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct basic_filter *f = (struct basic_filter *) fh; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 00a5a585e5f..8e3cf49118e 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -295,7 +295,7 @@ errout: return ret; } -static int cls_bpf_dump(struct tcf_proto *tp, unsigned long fh, +static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *tm) { struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index f9d212583ea..8e2158ab551 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -11,109 +11,13 @@ #include <linux/module.h> #include <linux/slab.h> -#include <linux/types.h> -#include <linux/string.h> -#include <linux/errno.h> #include <linux/skbuff.h> -#include <linux/cgroup.h> #include <linux/rcupdate.h> -#include <linux/fdtable.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/sock.h> #include <net/cls_cgroup.h> -static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css) -{ - return css ? container_of(css, struct cgroup_cls_state, css) : NULL; -} - -static inline struct cgroup_cls_state *task_cls_state(struct task_struct *p) -{ - return css_cls_state(task_css(p, net_cls_subsys_id)); -} - -static struct cgroup_subsys_state * -cgrp_css_alloc(struct cgroup_subsys_state *parent_css) -{ - struct cgroup_cls_state *cs; - - cs = kzalloc(sizeof(*cs), GFP_KERNEL); - if (!cs) - return ERR_PTR(-ENOMEM); - return &cs->css; -} - -static int cgrp_css_online(struct cgroup_subsys_state *css) -{ - struct cgroup_cls_state *cs = css_cls_state(css); - struct cgroup_cls_state *parent = css_cls_state(css_parent(css)); - - if (parent) - cs->classid = parent->classid; - return 0; -} - -static void cgrp_css_free(struct cgroup_subsys_state *css) -{ - kfree(css_cls_state(css)); -} - -static int update_classid(const void *v, struct file *file, unsigned n) -{ - int err; - struct socket *sock = sock_from_file(file, &err); - if (sock) - sock->sk->sk_classid = (u32)(unsigned long)v; - return 0; -} - -static void cgrp_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) -{ - struct task_struct *p; - struct cgroup_cls_state *cs = css_cls_state(css); - void *v = (void *)(unsigned long)cs->classid; - - cgroup_taskset_for_each(p, css, tset) { - task_lock(p); - iterate_fd(p->files, 0, update_classid, v); - task_unlock(p); - } -} - -static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft) -{ - return css_cls_state(css)->classid; -} - -static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, - u64 value) -{ - css_cls_state(css)->classid = (u32) value; - return 0; -} - -static struct cftype ss_files[] = { - { - .name = "classid", - .read_u64 = read_classid, - .write_u64 = write_classid, - }, - { } /* terminate */ -}; - -struct cgroup_subsys net_cls_subsys = { - .name = "net_cls", - .css_alloc = cgrp_css_alloc, - .css_online = cgrp_css_online, - .css_free = cgrp_css_free, - .attach = cgrp_attach, - .subsys_id = net_cls_subsys_id, - .base_cftypes = ss_files, - .module = THIS_MODULE, -}; - struct cls_cgroup_head { u32 handle; struct tcf_exts exts; @@ -260,7 +164,7 @@ skip: arg->count++; } -static int cls_cgroup_dump(struct tcf_proto *tp, unsigned long fh, +static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct cls_cgroup_head *head = tp->root; @@ -305,25 +209,12 @@ static struct tcf_proto_ops cls_cgroup_ops __read_mostly = { static int __init init_cgroup_cls(void) { - int ret; - - ret = cgroup_load_subsys(&net_cls_subsys); - if (ret) - goto out; - - ret = register_tcf_proto_ops(&cls_cgroup_ops); - if (ret) - cgroup_unload_subsys(&net_cls_subsys); - -out: - return ret; + return register_tcf_proto_ops(&cls_cgroup_ops); } static void __exit exit_cgroup_cls(void) { unregister_tcf_proto_ops(&cls_cgroup_ops); - - cgroup_unload_subsys(&net_cls_subsys); } module_init(init_cgroup_cls); diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index dfd18a5c3e8..257029c5433 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -563,7 +563,7 @@ static void flow_put(struct tcf_proto *tp, unsigned long f) { } -static int flow_dump(struct tcf_proto *tp, unsigned long fh, +static int flow_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct flow_filter *f = (struct flow_filter *)fh; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 3f9cece1380..ed00e8c21ce 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -41,7 +41,7 @@ struct fw_filter { u32 id; struct tcf_result res; #ifdef CONFIG_NET_CLS_IND - char indev[IFNAMSIZ]; + int ifindex; #endif /* CONFIG_NET_CLS_IND */ struct tcf_exts exts; }; @@ -75,7 +75,7 @@ static inline int fw_hash(u32 handle) static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct fw_filter *f; int r; u32 id = skb->mark; @@ -86,7 +86,7 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, if (f->id == id) { *res = f->res; #ifdef CONFIG_NET_CLS_IND - if (!tcf_match_indev(skb, f->indev)) + if (!tcf_match_indev(skb, f->ifindex)) continue; #endif /* CONFIG_NET_CLS_IND */ r = tcf_exts_exec(skb, &f->exts, res); @@ -111,7 +111,7 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, static unsigned long fw_get(struct tcf_proto *tp, u32 handle) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct fw_filter *f; if (head == NULL) @@ -160,7 +160,7 @@ static void fw_destroy(struct tcf_proto *tp) static int fw_delete(struct tcf_proto *tp, unsigned long arg) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct fw_filter *f = (struct fw_filter *)arg; struct fw_filter **fp; @@ -190,7 +190,7 @@ static int fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, struct nlattr **tb, struct nlattr **tca, unsigned long base) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct tcf_exts e; u32 mask; int err; @@ -207,9 +207,11 @@ fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, #ifdef CONFIG_NET_CLS_IND if (tb[TCA_FW_INDEV]) { - err = tcf_change_indev(tp, f->indev, tb[TCA_FW_INDEV]); - if (err < 0) + int ret; + ret = tcf_change_indev(net, tb[TCA_FW_INDEV]); + if (ret < 0) goto errout; + f->ifindex = ret; } #endif /* CONFIG_NET_CLS_IND */ @@ -235,7 +237,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, struct nlattr **tca, unsigned long *arg) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct fw_filter *f = (struct fw_filter *) *arg; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_FW_MAX + 1]; @@ -298,7 +300,7 @@ errout: static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; int h; if (head == NULL) @@ -324,10 +326,10 @@ static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int fw_dump(struct tcf_proto *tp, unsigned long fh, +static int fw_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct fw_filter *f = (struct fw_filter *)fh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; @@ -348,9 +350,12 @@ static int fw_dump(struct tcf_proto *tp, unsigned long fh, nla_put_u32(skb, TCA_FW_CLASSID, f->res.classid)) goto nla_put_failure; #ifdef CONFIG_NET_CLS_IND - if (strlen(f->indev) && - nla_put_string(skb, TCA_FW_INDEV, f->indev)) - goto nla_put_failure; + if (f->ifindex) { + struct net_device *dev; + dev = __dev_get_by_index(net, f->ifindex); + if (dev && nla_put_string(skb, TCA_FW_INDEV, dev->name)) + goto nla_put_failure; + } #endif /* CONFIG_NET_CLS_IND */ if (head->mask != 0xFFFFFFFF && nla_put_u32(skb, TCA_FW_MASK, head->mask)) diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 2473953a594..1ad3068f2ce 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -123,7 +123,7 @@ static inline int route4_hash_wild(void) static int route4_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct route4_head *head = (struct route4_head *)tp->root; + struct route4_head *head = tp->root; struct dst_entry *dst; struct route4_bucket *b; struct route4_filter *f; @@ -213,7 +213,7 @@ static inline u32 from_hash(u32 id) static unsigned long route4_get(struct tcf_proto *tp, u32 handle) { - struct route4_head *head = (struct route4_head *)tp->root; + struct route4_head *head = tp->root; struct route4_bucket *b; struct route4_filter *f; unsigned int h1, h2; @@ -284,7 +284,7 @@ static void route4_destroy(struct tcf_proto *tp) static int route4_delete(struct tcf_proto *tp, unsigned long arg) { - struct route4_head *head = (struct route4_head *)tp->root; + struct route4_head *head = tp->root; struct route4_filter **fp, *f = (struct route4_filter *)arg; unsigned int h = 0; struct route4_bucket *b; @@ -551,7 +551,7 @@ static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int route4_dump(struct tcf_proto *tp, unsigned long fh, +static int route4_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct route4_filter *f = (struct route4_filter *)fh; diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 4f25c2ac825..19f8e5dfa8b 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -594,7 +594,7 @@ static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int rsvp_dump(struct tcf_proto *tp, unsigned long fh, +static int rsvp_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct rsvp_filter *f = (struct rsvp_filter *)fh; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index ffad18791c9..eed8404443d 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -24,9 +24,6 @@ #define DEFAULT_HASH_SIZE 64 /* optimized for diffserv */ -#define PRIV(tp) ((struct tcindex_data *) (tp)->root) - - struct tcindex_filter_result { struct tcf_exts exts; struct tcf_result res; @@ -77,7 +74,7 @@ tcindex_lookup(struct tcindex_data *p, u16 key) static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter_result *f; int key = (skb->tc_index & p->mask) >> p->shift; @@ -102,7 +99,7 @@ static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, static unsigned long tcindex_get(struct tcf_proto *tp, u32 handle) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter_result *r; pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle); @@ -140,7 +137,7 @@ static int tcindex_init(struct tcf_proto *tp) static int __tcindex_delete(struct tcf_proto *tp, unsigned long arg, int lock) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter_result *r = (struct tcindex_filter_result *) arg; struct tcindex_filter *f = NULL; @@ -338,7 +335,7 @@ tcindex_change(struct net *net, struct sk_buff *in_skb, { struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_TCINDEX_MAX + 1]; - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter_result *r = (struct tcindex_filter_result *) *arg; int err; @@ -360,7 +357,7 @@ tcindex_change(struct net *net, struct sk_buff *in_skb, static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter *f, *next; int i; @@ -407,7 +404,7 @@ static int tcindex_destroy_element(struct tcf_proto *tp, static void tcindex_destroy(struct tcf_proto *tp) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcf_walker walker; pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); @@ -422,10 +419,10 @@ static void tcindex_destroy(struct tcf_proto *tp) } -static int tcindex_dump(struct tcf_proto *tp, unsigned long fh, +static int tcindex_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter_result *r = (struct tcindex_filter_result *) fh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 20f2fb79c74..84c28daff84 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -48,7 +48,7 @@ struct tc_u_knode { struct tc_u_hnode *ht_up; struct tcf_exts exts; #ifdef CONFIG_NET_CLS_IND - char indev[IFNAMSIZ]; + int ifindex; #endif u8 fshift; struct tcf_result res; @@ -95,7 +95,7 @@ static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct unsigned int off; } stack[TC_U32_MAXDEPTH]; - struct tc_u_hnode *ht = (struct tc_u_hnode *)tp->root; + struct tc_u_hnode *ht = tp->root; unsigned int off = skb_network_offset(skb); struct tc_u_knode *n; int sdepth = 0; @@ -152,7 +152,7 @@ check_terminal: *res = n->res; #ifdef CONFIG_NET_CLS_IND - if (!tcf_match_indev(skb, n->indev)) { + if (!tcf_match_indev(skb, n->ifindex)) { n = n->next; goto next_knode; } @@ -527,9 +527,11 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, #ifdef CONFIG_NET_CLS_IND if (tb[TCA_U32_INDEV]) { - err = tcf_change_indev(tp, n->indev, tb[TCA_U32_INDEV]); - if (err < 0) + int ret; + ret = tcf_change_indev(net, tb[TCA_U32_INDEV]); + if (ret < 0) goto errout; + n->ifindex = ret; } #endif tcf_exts_change(tp, &n->exts, &e); @@ -712,7 +714,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int u32_dump(struct tcf_proto *tp, unsigned long fh, +static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct tc_u_knode *n = (struct tc_u_knode *)fh; @@ -760,9 +762,12 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh, goto nla_put_failure; #ifdef CONFIG_NET_CLS_IND - if (strlen(n->indev) && - nla_put_string(skb, TCA_U32_INDEV, n->indev)) - goto nla_put_failure; + if (n->ifindex) { + struct net_device *dev; + dev = __dev_get_by_index(net, n->ifindex); + if (dev && nla_put_string(skb, TCA_U32_INDEV, dev->name)) + goto nla_put_failure; + } #endif #ifdef CONFIG_CLS_U32_PERF if (nla_put(skb, TCA_U32_PCNT, diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index c31190e29b9..1313145e3b8 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -135,7 +135,7 @@ static DEFINE_RWLOCK(qdisc_mod_lock); static struct Qdisc_ops *qdisc_base; -/* Register/uregister queueing discipline */ +/* Register/unregister queueing discipline */ int register_qdisc(struct Qdisc_ops *qops) { diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index e2518333380..2f80d01d42a 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1060,8 +1060,8 @@ static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio) } if (cl->quantum <= 0 || cl->quantum > 32*qdisc_dev(cl->qdisc)->mtu) { - pr_warning("CBQ: class %08x has bad quantum==%ld, repaired.\n", - cl->common.classid, cl->quantum); + pr_warn("CBQ: class %08x has bad quantum==%ld, repaired.\n", + cl->common.classid, cl->quantum); cl->quantum = qdisc_dev(cl->qdisc)->mtu/2 + 1; } } diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 0952fd2684e..49d6ef338b5 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -57,8 +57,8 @@ static int dsmark_graft(struct Qdisc *sch, unsigned long arg, { struct dsmark_qdisc_data *p = qdisc_priv(sch); - pr_debug("dsmark_graft(sch %p,[qdisc %p],new %p,old %p)\n", - sch, p, new, old); + pr_debug("%s(sch %p,[qdisc %p],new %p,old %p)\n", + __func__, sch, p, new, old); if (new == NULL) { new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, @@ -85,8 +85,8 @@ static struct Qdisc *dsmark_leaf(struct Qdisc *sch, unsigned long arg) static unsigned long dsmark_get(struct Qdisc *sch, u32 classid) { - pr_debug("dsmark_get(sch %p,[qdisc %p],classid %x)\n", - sch, qdisc_priv(sch), classid); + pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", + __func__, sch, qdisc_priv(sch), classid); return TC_H_MIN(classid) + 1; } @@ -118,8 +118,8 @@ static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, int err = -EINVAL; u8 mask = 0; - pr_debug("dsmark_change(sch %p,[qdisc %p],classid %x,parent %x)," - "arg 0x%lx\n", sch, p, classid, parent, *arg); + pr_debug("%s(sch %p,[qdisc %p],classid %x,parent %x), arg 0x%lx\n", + __func__, sch, p, classid, parent, *arg); if (!dsmark_valid_index(p, *arg)) { err = -ENOENT; @@ -166,7 +166,8 @@ static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker) struct dsmark_qdisc_data *p = qdisc_priv(sch); int i; - pr_debug("dsmark_walk(sch %p,[qdisc %p],walker %p)\n", sch, p, walker); + pr_debug("%s(sch %p,[qdisc %p],walker %p)\n", + __func__, sch, p, walker); if (walker->stop) return; @@ -199,7 +200,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch) struct dsmark_qdisc_data *p = qdisc_priv(sch); int err; - pr_debug("dsmark_enqueue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); + pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p); if (p->set_tc_index) { switch (skb->protocol) { @@ -275,7 +276,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) struct sk_buff *skb; u32 index; - pr_debug("dsmark_dequeue(sch %p,[qdisc %p])\n", sch, p); + pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); skb = p->q->ops->dequeue(p->q); if (skb == NULL) @@ -303,8 +304,8 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) * and don't need yet another qdisc as a bypass. */ if (p->mask[index] != 0xff || p->value[index]) - pr_warning("dsmark_dequeue: unsupported protocol %d\n", - ntohs(skb->protocol)); + pr_warn("%s: unsupported protocol %d\n", + __func__, ntohs(skb->protocol)); break; } @@ -315,7 +316,7 @@ static struct sk_buff *dsmark_peek(struct Qdisc *sch) { struct dsmark_qdisc_data *p = qdisc_priv(sch); - pr_debug("dsmark_peek(sch %p,[qdisc %p])\n", sch, p); + pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); return p->q->ops->peek(p->q); } @@ -325,7 +326,7 @@ static unsigned int dsmark_drop(struct Qdisc *sch) struct dsmark_qdisc_data *p = qdisc_priv(sch); unsigned int len; - pr_debug("dsmark_reset(sch %p,[qdisc %p])\n", sch, p); + pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); if (p->q->ops->drop == NULL) return 0; @@ -346,7 +347,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) u16 indices; u8 *mask; - pr_debug("dsmark_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); + pr_debug("%s(sch %p,[qdisc %p],opt %p)\n", __func__, sch, p, opt); if (!opt) goto errout; @@ -384,7 +385,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) if (p->q == NULL) p->q = &noop_qdisc; - pr_debug("dsmark_init: qdisc %p\n", p->q); + pr_debug("%s: qdisc %p\n", __func__, p->q); err = 0; errout: @@ -395,7 +396,7 @@ static void dsmark_reset(struct Qdisc *sch) { struct dsmark_qdisc_data *p = qdisc_priv(sch); - pr_debug("dsmark_reset(sch %p,[qdisc %p])\n", sch, p); + pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); qdisc_reset(p->q); sch->q.qlen = 0; } @@ -404,7 +405,7 @@ static void dsmark_destroy(struct Qdisc *sch) { struct dsmark_qdisc_data *p = qdisc_priv(sch); - pr_debug("dsmark_destroy(sch %p,[qdisc %p])\n", sch, p); + pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); tcf_destroy_chain(&p->filter_list); qdisc_destroy(p->q); @@ -417,7 +418,7 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, struct dsmark_qdisc_data *p = qdisc_priv(sch); struct nlattr *opts = NULL; - pr_debug("dsmark_dump_class(sch %p,[qdisc %p],class %ld\n", sch, p, cl); + pr_debug("%s(sch %p,[qdisc %p],class %ld\n", __func__, sch, p, cl); if (!dsmark_valid_index(p, cl)) return -EINVAL; diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index d42234c0f13..12cbc09157f 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -370,8 +370,8 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps) for (i = table->DPs; i < MAX_DPs; i++) { if (table->tab[i]) { - pr_warning("GRED: Warning: Destroying " - "shadowed VQ 0x%x\n", i); + pr_warn("GRED: Warning: Destroying shadowed VQ 0x%x\n", + i); gred_destroy_vq(table->tab[i]); table->tab[i] = NULL; } diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 97aa33dbb90..1cf84a9e13a 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -574,18 +574,18 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt) q->hh_flows_limit = nla_get_u32(tb[TCA_HHF_HH_FLOWS_LIMIT]); if (tb[TCA_HHF_RESET_TIMEOUT]) { - u32 ms = nla_get_u32(tb[TCA_HHF_RESET_TIMEOUT]); + u32 us = nla_get_u32(tb[TCA_HHF_RESET_TIMEOUT]); - q->hhf_reset_timeout = msecs_to_jiffies(ms); + q->hhf_reset_timeout = usecs_to_jiffies(us); } if (tb[TCA_HHF_ADMIT_BYTES]) q->hhf_admit_bytes = nla_get_u32(tb[TCA_HHF_ADMIT_BYTES]); if (tb[TCA_HHF_EVICT_TIMEOUT]) { - u32 ms = nla_get_u32(tb[TCA_HHF_EVICT_TIMEOUT]); + u32 us = nla_get_u32(tb[TCA_HHF_EVICT_TIMEOUT]); - q->hhf_evict_timeout = msecs_to_jiffies(ms); + q->hhf_evict_timeout = usecs_to_jiffies(us); } qlen = sch->q.qlen; @@ -684,10 +684,10 @@ static int hhf_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u32(skb, TCA_HHF_QUANTUM, q->quantum) || nla_put_u32(skb, TCA_HHF_HH_FLOWS_LIMIT, q->hh_flows_limit) || nla_put_u32(skb, TCA_HHF_RESET_TIMEOUT, - jiffies_to_msecs(q->hhf_reset_timeout)) || + jiffies_to_usecs(q->hhf_reset_timeout)) || nla_put_u32(skb, TCA_HHF_ADMIT_BYTES, q->hhf_admit_bytes) || nla_put_u32(skb, TCA_HHF_EVICT_TIMEOUT, - jiffies_to_msecs(q->hhf_evict_timeout)) || + jiffies_to_usecs(q->hhf_evict_timeout)) || nla_put_u32(skb, TCA_HHF_NON_HH_WEIGHT, q->hhf_non_hh_weight)) goto nla_put_failure; @@ -711,7 +711,7 @@ static int hhf_dump_stats(struct Qdisc *sch, struct gnet_dump *d) return gnet_stats_copy_app(d, &st, sizeof(st)); } -struct Qdisc_ops hhf_qdisc_ops __read_mostly = { +static struct Qdisc_ops hhf_qdisc_ops __read_mostly = { .id = "hhf", .priv_size = sizeof(struct hhf_sched_data), @@ -727,7 +727,6 @@ struct Qdisc_ops hhf_qdisc_ops __read_mostly = { .dump_stats = hhf_dump_stats, .owner = THIS_MODULE, }; -EXPORT_SYMBOL(hhf_qdisc_ops); static int __init hhf_module_init(void) { diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 6b0e854b011..0db5a6eae87 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -712,7 +712,7 @@ static s64 htb_do_events(struct htb_sched *q, const int level, /* too much load - let's continue after a break for scheduling */ if (!(q->warned & HTB_WARN_TOOMANYEVENTS)) { - pr_warning("htb: too many events!\n"); + pr_warn("htb: too many events!\n"); q->warned |= HTB_WARN_TOOMANYEVENTS; } @@ -1276,9 +1276,10 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) struct Qdisc *new_q = NULL; int last_child = 0; - // TODO: why don't allow to delete subtree ? references ? does - // tc subsys quarantee us that in htb_destroy it holds no class - // refs so that we can remove children safely there ? + /* TODO: why don't allow to delete subtree ? references ? does + * tc subsys guarantee us that in htb_destroy it holds no class + * refs so that we can remove children safely there ? + */ if (cl->children || cl->filter_cnt) return -EBUSY; @@ -1488,15 +1489,13 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, cl->quantum = min_t(u64, quantum, INT_MAX); if (!hopt->quantum && cl->quantum < 1000) { - pr_warning( - "HTB: quantum of class %X is small. Consider r2q change.\n", - cl->common.classid); + pr_warn("HTB: quantum of class %X is small. Consider r2q change.\n", + cl->common.classid); cl->quantum = 1000; } if (!hopt->quantum && cl->quantum > 200000) { - pr_warning( - "HTB: quantum of class %X is big. Consider r2q change.\n", - cl->common.classid); + pr_warn("HTB: quantum of class %X is big. Consider r2q change.\n", + cl->common.classid); cl->quantum = 200000; } if (hopt->quantum) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index f3befd6b478..090a4e3ecd0 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -88,7 +88,7 @@ struct netem_sched_data { u32 duplicate; u32 reorder; u32 corrupt; - u32 rate; + u64 rate; s32 packet_overhead; u32 cell_size; u32 cell_size_reciprocal; @@ -495,7 +495,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) now = netem_skb_cb(last)->time_to_send; } - delay += packet_len_2_sched_time(skb->len, q); + delay += packet_len_2_sched_time(qdisc_pkt_len(skb), q); } cb->time_to_send = now + delay; @@ -782,6 +782,7 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = { [TCA_NETEM_RATE] = { .len = sizeof(struct tc_netem_rate) }, [TCA_NETEM_LOSS] = { .type = NLA_NESTED }, [TCA_NETEM_ECN] = { .type = NLA_U32 }, + [TCA_NETEM_RATE64] = { .type = NLA_U64 }, }; static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, @@ -852,6 +853,10 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_NETEM_RATE]) get_rate(sch, tb[TCA_NETEM_RATE]); + if (tb[TCA_NETEM_RATE64]) + q->rate = max_t(u64, q->rate, + nla_get_u64(tb[TCA_NETEM_RATE64])); + if (tb[TCA_NETEM_ECN]) q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]); @@ -974,7 +979,13 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt)) goto nla_put_failure; - rate.rate = q->rate; + if (q->rate >= (1ULL << 32)) { + if (nla_put_u64(skb, TCA_NETEM_RATE64, q->rate)) + goto nla_put_failure; + rate.rate = ~0U; + } else { + rate.rate = q->rate; + } rate.packet_overhead = q->packet_overhead; rate.cell_size = q->cell_size; rate.cell_overhead = q->cell_overhead; diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c new file mode 100644 index 00000000000..fe65340c8eb --- /dev/null +++ b/net/sched/sch_pie.c @@ -0,0 +1,555 @@ +/* Copyright (C) 2013 Cisco Systems, Inc, 2013. + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Author: Vijay Subramanian <vijaynsu@cisco.com> + * Author: Mythili Prabhu <mysuryan@cisco.com> + * + * ECN support is added by Naeem Khademi <naeemk@ifi.uio.no> + * University of Oslo, Norway. + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <net/pkt_sched.h> +#include <net/inet_ecn.h> + +#define QUEUE_THRESHOLD 10000 +#define DQCOUNT_INVALID -1 +#define MAX_PROB 0xffffffff +#define PIE_SCALE 8 + +/* parameters used */ +struct pie_params { + psched_time_t target; /* user specified target delay in pschedtime */ + u32 tupdate; /* timer frequency (in jiffies) */ + u32 limit; /* number of packets that can be enqueued */ + u32 alpha; /* alpha and beta are between -4 and 4 */ + u32 beta; /* and are used for shift relative to 1 */ + bool ecn; /* true if ecn is enabled */ + bool bytemode; /* to scale drop early prob based on pkt size */ +}; + +/* variables used */ +struct pie_vars { + u32 prob; /* probability but scaled by u32 limit. */ + psched_time_t burst_time; + psched_time_t qdelay; + psched_time_t qdelay_old; + u64 dq_count; /* measured in bytes */ + psched_time_t dq_tstamp; /* drain rate */ + u32 avg_dq_rate; /* bytes per pschedtime tick,scaled */ + u32 qlen_old; /* in bytes */ +}; + +/* statistics gathering */ +struct pie_stats { + u32 packets_in; /* total number of packets enqueued */ + u32 dropped; /* packets dropped due to pie_action */ + u32 overlimit; /* dropped due to lack of space in queue */ + u32 maxq; /* maximum queue size */ + u32 ecn_mark; /* packets marked with ECN */ +}; + +/* private data for the Qdisc */ +struct pie_sched_data { + struct pie_params params; + struct pie_vars vars; + struct pie_stats stats; + struct timer_list adapt_timer; +}; + +static void pie_params_init(struct pie_params *params) +{ + params->alpha = 2; + params->beta = 20; + params->tupdate = usecs_to_jiffies(30 * USEC_PER_MSEC); /* 30 ms */ + params->limit = 1000; /* default of 1000 packets */ + params->target = PSCHED_NS2TICKS(20 * NSEC_PER_MSEC); /* 20 ms */ + params->ecn = false; + params->bytemode = false; +} + +static void pie_vars_init(struct pie_vars *vars) +{ + vars->dq_count = DQCOUNT_INVALID; + vars->avg_dq_rate = 0; + /* default of 100 ms in pschedtime */ + vars->burst_time = PSCHED_NS2TICKS(100 * NSEC_PER_MSEC); +} + +static bool drop_early(struct Qdisc *sch, u32 packet_size) +{ + struct pie_sched_data *q = qdisc_priv(sch); + u32 rnd; + u32 local_prob = q->vars.prob; + u32 mtu = psched_mtu(qdisc_dev(sch)); + + /* If there is still burst allowance left skip random early drop */ + if (q->vars.burst_time > 0) + return false; + + /* If current delay is less than half of target, and + * if drop prob is low already, disable early_drop + */ + if ((q->vars.qdelay < q->params.target / 2) + && (q->vars.prob < MAX_PROB / 5)) + return false; + + /* If we have fewer than 2 mtu-sized packets, disable drop_early, + * similar to min_th in RED + */ + if (sch->qstats.backlog < 2 * mtu) + return false; + + /* If bytemode is turned on, use packet size to compute new + * probablity. Smaller packets will have lower drop prob in this case + */ + if (q->params.bytemode && packet_size <= mtu) + local_prob = (local_prob / mtu) * packet_size; + else + local_prob = q->vars.prob; + + rnd = net_random(); + if (rnd < local_prob) + return true; + + return false; +} + +static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + struct pie_sched_data *q = qdisc_priv(sch); + bool enqueue = false; + + if (unlikely(qdisc_qlen(sch) >= sch->limit)) { + q->stats.overlimit++; + goto out; + } + + if (!drop_early(sch, skb->len)) { + enqueue = true; + } else if (q->params.ecn && (q->vars.prob <= MAX_PROB / 10) && + INET_ECN_set_ce(skb)) { + /* If packet is ecn capable, mark it if drop probability + * is lower than 10%, else drop it. + */ + q->stats.ecn_mark++; + enqueue = true; + } + + /* we can enqueue the packet */ + if (enqueue) { + q->stats.packets_in++; + if (qdisc_qlen(sch) > q->stats.maxq) + q->stats.maxq = qdisc_qlen(sch); + + return qdisc_enqueue_tail(skb, sch); + } + +out: + q->stats.dropped++; + return qdisc_drop(skb, sch); +} + +static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = { + [TCA_PIE_TARGET] = {.type = NLA_U32}, + [TCA_PIE_LIMIT] = {.type = NLA_U32}, + [TCA_PIE_TUPDATE] = {.type = NLA_U32}, + [TCA_PIE_ALPHA] = {.type = NLA_U32}, + [TCA_PIE_BETA] = {.type = NLA_U32}, + [TCA_PIE_ECN] = {.type = NLA_U32}, + [TCA_PIE_BYTEMODE] = {.type = NLA_U32}, +}; + +static int pie_change(struct Qdisc *sch, struct nlattr *opt) +{ + struct pie_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_PIE_MAX + 1]; + unsigned int qlen; + int err; + + if (!opt) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_PIE_MAX, opt, pie_policy); + if (err < 0) + return err; + + sch_tree_lock(sch); + + /* convert from microseconds to pschedtime */ + if (tb[TCA_PIE_TARGET]) { + /* target is in us */ + u32 target = nla_get_u32(tb[TCA_PIE_TARGET]); + + /* convert to pschedtime */ + q->params.target = PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC); + } + + /* tupdate is in jiffies */ + if (tb[TCA_PIE_TUPDATE]) + q->params.tupdate = usecs_to_jiffies(nla_get_u32(tb[TCA_PIE_TUPDATE])); + + if (tb[TCA_PIE_LIMIT]) { + u32 limit = nla_get_u32(tb[TCA_PIE_LIMIT]); + + q->params.limit = limit; + sch->limit = limit; + } + + if (tb[TCA_PIE_ALPHA]) + q->params.alpha = nla_get_u32(tb[TCA_PIE_ALPHA]); + + if (tb[TCA_PIE_BETA]) + q->params.beta = nla_get_u32(tb[TCA_PIE_BETA]); + + if (tb[TCA_PIE_ECN]) + q->params.ecn = nla_get_u32(tb[TCA_PIE_ECN]); + + if (tb[TCA_PIE_BYTEMODE]) + q->params.bytemode = nla_get_u32(tb[TCA_PIE_BYTEMODE]); + + /* Drop excess packets if new limit is lower */ + qlen = sch->q.qlen; + while (sch->q.qlen > sch->limit) { + struct sk_buff *skb = __skb_dequeue(&sch->q); + + sch->qstats.backlog -= qdisc_pkt_len(skb); + qdisc_drop(skb, sch); + } + qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen); + + sch_tree_unlock(sch); + return 0; +} + +static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb) +{ + + struct pie_sched_data *q = qdisc_priv(sch); + int qlen = sch->qstats.backlog; /* current queue size in bytes */ + + /* If current queue is about 10 packets or more and dq_count is unset + * we have enough packets to calculate the drain rate. Save + * current time as dq_tstamp and start measurement cycle. + */ + if (qlen >= QUEUE_THRESHOLD && q->vars.dq_count == DQCOUNT_INVALID) { + q->vars.dq_tstamp = psched_get_time(); + q->vars.dq_count = 0; + } + + /* Calculate the average drain rate from this value. If queue length + * has receded to a small value viz., <= QUEUE_THRESHOLD bytes,reset + * the dq_count to -1 as we don't have enough packets to calculate the + * drain rate anymore The following if block is entered only when we + * have a substantial queue built up (QUEUE_THRESHOLD bytes or more) + * and we calculate the drain rate for the threshold here. dq_count is + * in bytes, time difference in psched_time, hence rate is in + * bytes/psched_time. + */ + if (q->vars.dq_count != DQCOUNT_INVALID) { + q->vars.dq_count += skb->len; + + if (q->vars.dq_count >= QUEUE_THRESHOLD) { + psched_time_t now = psched_get_time(); + u32 dtime = now - q->vars.dq_tstamp; + u32 count = q->vars.dq_count << PIE_SCALE; + + if (dtime == 0) + return; + + count = count / dtime; + + if (q->vars.avg_dq_rate == 0) + q->vars.avg_dq_rate = count; + else + q->vars.avg_dq_rate = + (q->vars.avg_dq_rate - + (q->vars.avg_dq_rate >> 3)) + (count >> 3); + + /* If the queue has receded below the threshold, we hold + * on to the last drain rate calculated, else we reset + * dq_count to 0 to re-enter the if block when the next + * packet is dequeued + */ + if (qlen < QUEUE_THRESHOLD) + q->vars.dq_count = DQCOUNT_INVALID; + else { + q->vars.dq_count = 0; + q->vars.dq_tstamp = psched_get_time(); + } + + if (q->vars.burst_time > 0) { + if (q->vars.burst_time > dtime) + q->vars.burst_time -= dtime; + else + q->vars.burst_time = 0; + } + } + } +} + +static void calculate_probability(struct Qdisc *sch) +{ + struct pie_sched_data *q = qdisc_priv(sch); + u32 qlen = sch->qstats.backlog; /* queue size in bytes */ + psched_time_t qdelay = 0; /* in pschedtime */ + psched_time_t qdelay_old = q->vars.qdelay; /* in pschedtime */ + s32 delta = 0; /* determines the change in probability */ + u32 oldprob; + u32 alpha, beta; + bool update_prob = true; + + q->vars.qdelay_old = q->vars.qdelay; + + if (q->vars.avg_dq_rate > 0) + qdelay = (qlen << PIE_SCALE) / q->vars.avg_dq_rate; + else + qdelay = 0; + + /* If qdelay is zero and qlen is not, it means qlen is very small, less + * than dequeue_rate, so we do not update probabilty in this round + */ + if (qdelay == 0 && qlen != 0) + update_prob = false; + + /* Add ranges for alpha and beta, more aggressive for high dropping + * mode and gentle steps for light dropping mode + * In light dropping mode, take gentle steps; in medium dropping mode, + * take medium steps; in high dropping mode, take big steps. + */ + if (q->vars.prob < MAX_PROB / 100) { + alpha = + (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 7; + beta = + (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 7; + } else if (q->vars.prob < MAX_PROB / 10) { + alpha = + (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 5; + beta = + (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 5; + } else { + alpha = + (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; + beta = + (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; + } + + /* alpha and beta should be between 0 and 32, in multiples of 1/16 */ + delta += alpha * ((qdelay - q->params.target)); + delta += beta * ((qdelay - qdelay_old)); + + oldprob = q->vars.prob; + + /* to ensure we increase probability in steps of no more than 2% */ + if (delta > (s32) (MAX_PROB / (100 / 2)) && + q->vars.prob >= MAX_PROB / 10) + delta = (MAX_PROB / 100) * 2; + + /* Non-linear drop: + * Tune drop probability to increase quickly for high delays(>= 250ms) + * 250ms is derived through experiments and provides error protection + */ + + if (qdelay > (PSCHED_NS2TICKS(250 * NSEC_PER_MSEC))) + delta += MAX_PROB / (100 / 2); + + q->vars.prob += delta; + + if (delta > 0) { + /* prevent overflow */ + if (q->vars.prob < oldprob) { + q->vars.prob = MAX_PROB; + /* Prevent normalization error. If probability is at + * maximum value already, we normalize it here, and + * skip the check to do a non-linear drop in the next + * section. + */ + update_prob = false; + } + } else { + /* prevent underflow */ + if (q->vars.prob > oldprob) + q->vars.prob = 0; + } + + /* Non-linear drop in probability: Reduce drop probability quickly if + * delay is 0 for 2 consecutive Tupdate periods. + */ + + if ((qdelay == 0) && (qdelay_old == 0) && update_prob) + q->vars.prob = (q->vars.prob * 98) / 100; + + q->vars.qdelay = qdelay; + q->vars.qlen_old = qlen; + + /* We restart the measurement cycle if the following conditions are met + * 1. If the delay has been low for 2 consecutive Tupdate periods + * 2. Calculated drop probability is zero + * 3. We have atleast one estimate for the avg_dq_rate ie., + * is a non-zero value + */ + if ((q->vars.qdelay < q->params.target / 2) && + (q->vars.qdelay_old < q->params.target / 2) && + (q->vars.prob == 0) && + (q->vars.avg_dq_rate > 0)) + pie_vars_init(&q->vars); +} + +static void pie_timer(unsigned long arg) +{ + struct Qdisc *sch = (struct Qdisc *)arg; + struct pie_sched_data *q = qdisc_priv(sch); + spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + + spin_lock(root_lock); + calculate_probability(sch); + + /* reset the timer to fire after 'tupdate'. tupdate is in jiffies. */ + if (q->params.tupdate) + mod_timer(&q->adapt_timer, jiffies + q->params.tupdate); + spin_unlock(root_lock); + +} + +static int pie_init(struct Qdisc *sch, struct nlattr *opt) +{ + struct pie_sched_data *q = qdisc_priv(sch); + + pie_params_init(&q->params); + pie_vars_init(&q->vars); + sch->limit = q->params.limit; + + setup_timer(&q->adapt_timer, pie_timer, (unsigned long)sch); + mod_timer(&q->adapt_timer, jiffies + HZ / 2); + + if (opt) { + int err = pie_change(sch, opt); + + if (err) + return err; + } + + return 0; +} + +static int pie_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct pie_sched_data *q = qdisc_priv(sch); + struct nlattr *opts; + + opts = nla_nest_start(skb, TCA_OPTIONS); + if (opts == NULL) + goto nla_put_failure; + + /* convert target from pschedtime to us */ + if (nla_put_u32(skb, TCA_PIE_TARGET, + ((u32) PSCHED_TICKS2NS(q->params.target)) / + NSEC_PER_USEC) || + nla_put_u32(skb, TCA_PIE_LIMIT, sch->limit) || + nla_put_u32(skb, TCA_PIE_TUPDATE, jiffies_to_usecs(q->params.tupdate)) || + nla_put_u32(skb, TCA_PIE_ALPHA, q->params.alpha) || + nla_put_u32(skb, TCA_PIE_BETA, q->params.beta) || + nla_put_u32(skb, TCA_PIE_ECN, q->params.ecn) || + nla_put_u32(skb, TCA_PIE_BYTEMODE, q->params.bytemode)) + goto nla_put_failure; + + return nla_nest_end(skb, opts); + +nla_put_failure: + nla_nest_cancel(skb, opts); + return -1; + +} + +static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct pie_sched_data *q = qdisc_priv(sch); + struct tc_pie_xstats st = { + .prob = q->vars.prob, + .delay = ((u32) PSCHED_TICKS2NS(q->vars.qdelay)) / + NSEC_PER_USEC, + /* unscale and return dq_rate in bytes per sec */ + .avg_dq_rate = q->vars.avg_dq_rate * + (PSCHED_TICKS_PER_SEC) >> PIE_SCALE, + .packets_in = q->stats.packets_in, + .overlimit = q->stats.overlimit, + .maxq = q->stats.maxq, + .dropped = q->stats.dropped, + .ecn_mark = q->stats.ecn_mark, + }; + + return gnet_stats_copy_app(d, &st, sizeof(st)); +} + +static struct sk_buff *pie_qdisc_dequeue(struct Qdisc *sch) +{ + struct sk_buff *skb; + skb = __qdisc_dequeue_head(sch, &sch->q); + + if (!skb) + return NULL; + + pie_process_dequeue(sch, skb); + return skb; +} + +static void pie_reset(struct Qdisc *sch) +{ + struct pie_sched_data *q = qdisc_priv(sch); + qdisc_reset_queue(sch); + pie_vars_init(&q->vars); +} + +static void pie_destroy(struct Qdisc *sch) +{ + struct pie_sched_data *q = qdisc_priv(sch); + q->params.tupdate = 0; + del_timer_sync(&q->adapt_timer); +} + +static struct Qdisc_ops pie_qdisc_ops __read_mostly = { + .id = "pie", + .priv_size = sizeof(struct pie_sched_data), + .enqueue = pie_qdisc_enqueue, + .dequeue = pie_qdisc_dequeue, + .peek = qdisc_peek_dequeued, + .init = pie_init, + .destroy = pie_destroy, + .reset = pie_reset, + .change = pie_change, + .dump = pie_dump, + .dump_stats = pie_dump_stats, + .owner = THIS_MODULE, +}; + +static int __init pie_module_init(void) +{ + return register_qdisc(&pie_qdisc_ops); +} + +static void __exit pie_module_exit(void) +{ + unregister_qdisc(&pie_qdisc_ops); +} + +module_init(pie_module_init); +module_exit(pie_module_exit); + +MODULE_DESCRIPTION("Proportional Integral controller Enhanced (PIE) scheduler"); +MODULE_AUTHOR("Vijay Subramanian"); +MODULE_AUTHOR("Mythili Prabhu"); +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 887e672f9d7..fbba5b0ec12 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -307,6 +307,8 @@ static const struct nla_policy tbf_policy[TCA_TBF_MAX + 1] = { [TCA_TBF_PTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE }, [TCA_TBF_RATE64] = { .type = NLA_U64 }, [TCA_TBF_PRATE64] = { .type = NLA_U64 }, + [TCA_TBF_BURST] = { .type = NLA_U32 }, + [TCA_TBF_PBURST] = { .type = NLA_U32 }, }; static int tbf_change(struct Qdisc *sch, struct nlattr *opt) @@ -358,7 +360,12 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) rate64 = nla_get_u64(tb[TCA_TBF_RATE64]); psched_ratecfg_precompute(&rate, &qopt->rate, rate64); - max_size = min_t(u64, psched_ns_t2l(&rate, buffer), ~0U); + if (tb[TCA_TBF_BURST]) { + max_size = nla_get_u32(tb[TCA_TBF_BURST]); + buffer = psched_l2t_ns(&rate, max_size); + } else { + max_size = min_t(u64, psched_ns_t2l(&rate, buffer), ~0U); + } if (qopt->peakrate.rate) { if (tb[TCA_TBF_PRATE64]) @@ -366,12 +373,18 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) psched_ratecfg_precompute(&peak, &qopt->peakrate, prate64); if (peak.rate_bytes_ps <= rate.rate_bytes_ps) { pr_warn_ratelimited("sch_tbf: peakrate %llu is lower than or equals to rate %llu !\n", - peak.rate_bytes_ps, rate.rate_bytes_ps); + peak.rate_bytes_ps, rate.rate_bytes_ps); err = -EINVAL; goto done; } - max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu)); + if (tb[TCA_TBF_PBURST]) { + u32 pburst = nla_get_u32(tb[TCA_TBF_PBURST]); + max_size = min_t(u32, max_size, pburst); + mtu = psched_l2t_ns(&peak, pburst); + } else { + max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu)); + } } if (max_size < psched_mtu(qdisc_dev(sch))) @@ -391,9 +404,15 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) q->qdisc = child; } q->limit = qopt->limit; - q->mtu = PSCHED_TICKS2NS(qopt->mtu); + if (tb[TCA_TBF_PBURST]) + q->mtu = mtu; + else + q->mtu = PSCHED_TICKS2NS(qopt->mtu); q->max_size = max_size; - q->buffer = PSCHED_TICKS2NS(qopt->buffer); + if (tb[TCA_TBF_BURST]) + q->buffer = buffer; + else + q->buffer = PSCHED_TICKS2NS(qopt->buffer); q->tokens = q->buffer; q->ptokens = q->mtu; |