diff options
Diffstat (limited to 'net/sched')
42 files changed, 985 insertions, 251 deletions
diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 2558f00f6b3e..90a31b15585f 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -88,7 +88,7 @@ struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action, struct tcf_chain *goto_chain) { a->tcfa_action = action; - rcu_swap_protected(a->goto_chain, goto_chain, 1); + goto_chain = rcu_replace_pointer(a->goto_chain, goto_chain, 1); return goto_chain; } EXPORT_SYMBOL(tcf_action_set_ctrlact); @@ -188,6 +188,8 @@ static size_t tcf_action_shared_attrs_size(const struct tc_action *act) + nla_total_size(0) /* TCA_ACT_STATS nested */ /* TCA_STATS_BASIC */ + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) + /* TCA_STATS_PKT64 */ + + nla_total_size_64bit(sizeof(u64)) /* TCA_STATS_QUEUE */ + nla_total_size_64bit(sizeof(struct gnet_stats_queue)) + nla_total_size(0) /* TCA_OPTIONS nested */ @@ -399,7 +401,7 @@ static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index) int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, - int bind, bool cpustats) + int bind, bool cpustats, u32 flags) { struct tc_action *p = kzalloc(ops->size, GFP_KERNEL); struct tcf_idrinfo *idrinfo = tn->idrinfo; @@ -427,6 +429,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, p->tcfa_tm.install = jiffies; p->tcfa_tm.lastuse = jiffies; p->tcfa_tm.firstuse = 0; + p->tcfa_flags = flags; if (est) { err = gen_new_estimator(&p->tcfa_bstats, p->cpu_bstats, &p->tcfa_rate_est, @@ -451,6 +454,17 @@ err1: } EXPORT_SYMBOL(tcf_idr_create); +int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index, + struct nlattr *est, struct tc_action **a, + const struct tc_action_ops *ops, int bind, + u32 flags) +{ + /* Set cpustats according to actions flags. */ + return tcf_idr_create(tn, index, est, a, ops, bind, + !(flags & TCA_ACT_FLAGS_NO_PERCPU_STATS), flags); +} +EXPORT_SYMBOL(tcf_idr_create_from_flags); + void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a) { struct tcf_idrinfo *idrinfo = tn->idrinfo; @@ -773,6 +787,14 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) } rcu_read_unlock(); + if (a->tcfa_flags) { + struct nla_bitfield32 flags = { a->tcfa_flags, + a->tcfa_flags, }; + + if (nla_put(skb, TCA_ACT_FLAGS, sizeof(flags), &flags)) + goto nla_put_failure; + } + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; @@ -831,13 +853,15 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) return c; } +static const u32 tca_act_flags_allowed = TCA_ACT_FLAGS_NO_PERCPU_STATS; static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = { - [TCA_ACT_KIND] = { .type = NLA_NUL_STRING, - .len = IFNAMSIZ - 1 }, + [TCA_ACT_KIND] = { .type = NLA_STRING }, [TCA_ACT_INDEX] = { .type = NLA_U32 }, [TCA_ACT_COOKIE] = { .type = NLA_BINARY, .len = TC_COOKIE_MAX_SIZE }, [TCA_ACT_OPTIONS] = { .type = NLA_NESTED }, + [TCA_ACT_FLAGS] = { .type = NLA_BITFIELD32, + .validation_data = &tca_act_flags_allowed }, }; struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, @@ -846,6 +870,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { + struct nla_bitfield32 flags = { 0, 0 }; struct tc_action *a; struct tc_action_ops *a_o; struct tc_cookie *cookie = NULL; @@ -865,8 +890,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, NL_SET_ERR_MSG(extack, "TC action kind must be specified"); goto err_out; } - nla_strlcpy(act_name, kind, IFNAMSIZ); - + if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) { + NL_SET_ERR_MSG(extack, "TC action name too long"); + goto err_out; + } if (tb[TCA_ACT_COOKIE]) { cookie = nla_memdup_cookie(tb); if (!cookie) { @@ -875,6 +902,8 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, goto err_out; } } + if (tb[TCA_ACT_FLAGS]) + flags = nla_get_bitfield32(tb[TCA_ACT_FLAGS]); } else { if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ) { NL_SET_ERR_MSG(extack, "TC action name too long"); @@ -913,10 +942,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, /* backward compatibility for policer */ if (name == NULL) err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind, - rtnl_held, tp, extack); + rtnl_held, tp, flags.value, extack); else err = a_o->init(net, nla, est, &a, ovr, bind, rtnl_held, - tp, extack); + tp, flags.value, extack); if (err < 0) goto err_mod; @@ -974,7 +1003,6 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, err = PTR_ERR(act); goto err; } - act->order = i; sz += tcf_action_fill_size(act); /* Start from index 0 */ actions[i - 1] = act; @@ -988,6 +1016,29 @@ err: return err; } +void tcf_action_update_stats(struct tc_action *a, u64 bytes, u32 packets, + bool drop, bool hw) +{ + if (a->cpu_bstats) { + _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); + + if (drop) + this_cpu_ptr(a->cpu_qstats)->drops += packets; + + if (hw) + _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw), + bytes, packets); + return; + } + + _bstats_update(&a->tcfa_bstats, bytes, packets); + if (drop) + a->tcfa_qstats.drops += packets; + if (hw) + _bstats_update(&a->tcfa_bstats_hw, bytes, packets); +} +EXPORT_SYMBOL(tcf_action_update_stats); + int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p, int compat_mode) { @@ -1352,11 +1403,16 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { size_t attr_size = 0; - int ret = 0; + int loop, ret; struct tc_action *actions[TCA_ACT_MAX_PRIO] = {}; - ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, actions, - &attr_size, true, extack); + for (loop = 0; loop < 10; loop++) { + ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, + actions, &attr_size, true, extack); + if (ret != -EAGAIN) + break; + } + if (ret < 0) return ret; ret = tcf_add_notify(net, n, actions, portid, attr_size, extack); @@ -1406,11 +1462,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, */ if (n->nlmsg_flags & NLM_F_REPLACE) ovr = 1; -replay: ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr, extack); - if (ret == -EAGAIN) - goto replay; break; case RTM_DELACTION: ret = tca_action_gd(net, tca[TCA_ACT_TAB], n, diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 04b7bd4ec751..46f47e58b3be 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -275,7 +275,8 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog, static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, int replace, int bind, bool rtnl_held, - struct tcf_proto *tp, struct netlink_ext_ack *extack) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, bpf_net_id); struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; @@ -303,7 +304,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, ret = tcf_idr_check_alloc(tn, &index, act, bind); if (!ret) { ret = tcf_idr_create(tn, index, est, act, - &act_bpf_ops, bind, true); + &act_bpf_ops, bind, true, 0); if (ret < 0) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 2b43cacf82af..43a243081e7d 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -94,7 +94,7 @@ static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = { static int tcf_connmark_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct tcf_proto *tp, + struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, connmark_net_id); @@ -121,7 +121,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, ret = tcf_idr_check_alloc(tn, &index, a, bind); if (!ret) { ret = tcf_idr_create(tn, index, est, a, - &act_connmark_ops, bind, false); + &act_connmark_ops, bind, false, 0); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index d3cfad88dc3a..cb8608f0a77a 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -43,7 +43,7 @@ static struct tc_action_ops act_csum_ops; static int tcf_csum_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, - struct netlink_ext_ack *extack) + u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, csum_net_id); struct tcf_csum_params *params_new; @@ -68,8 +68,8 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, index, est, a, - &act_csum_ops, bind, true); + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_csum_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -101,8 +101,8 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, spin_lock_bh(&p->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); - rcu_swap_protected(p->params, params_new, - lockdep_is_held(&p->tcf_lock)); + params_new = rcu_replace_pointer(p->params, params_new, + lockdep_is_held(&p->tcf_lock)); spin_unlock_bh(&p->tcf_lock); if (goto_ch) @@ -580,7 +580,7 @@ static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a, params = rcu_dereference_bh(p->params); tcf_lastuse_update(&p->tcf_tm); - bstats_cpu_update(this_cpu_ptr(p->common.cpu_bstats), skb); + tcf_action_update_bstats(&p->common, skb); action = READ_ONCE(p->tcf_action); if (unlikely(action == TC_ACT_SHOT)) @@ -624,7 +624,7 @@ out: return action; drop: - qstats_drop_inc(this_cpu_ptr(p->common.cpu_qstats)); + tcf_action_inc_drop_qstats(&p->common); action = TC_ACT_SHOT; goto out; } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index fcc46025e790..ae0de372b1c8 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -465,16 +465,15 @@ out_push: skb_push_rcsum(skb, nh_ofs); out: - bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), skb); + tcf_action_update_bstats(&c->common, skb); return retval; drop: - qstats_drop_inc(this_cpu_ptr(a->cpu_qstats)); + tcf_action_inc_drop_qstats(&c->common); return TC_ACT_SHOT; } static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = { - [TCA_CT_UNSPEC] = { .strict_start_type = TCA_CT_UNSPEC + 1 }, [TCA_CT_ACTION] = { .type = NLA_U16 }, [TCA_CT_PARMS] = { .type = NLA_EXACT_LEN, .len = sizeof(struct tc_ct) }, [TCA_CT_ZONE] = { .type = NLA_U16 }, @@ -656,7 +655,7 @@ static int tcf_ct_fill_params(struct net *net, static int tcf_ct_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int replace, int bind, bool rtnl_held, - struct tcf_proto *tp, + struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ct_net_id); @@ -688,8 +687,8 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, return err; if (!err) { - err = tcf_idr_create(tn, index, est, a, - &act_ct_ops, bind, true); + err = tcf_idr_create_from_flags(tn, index, est, a, + &act_ct_ops, bind, flags); if (err) { tcf_idr_cleanup(tn, index); return err; @@ -722,7 +721,8 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, spin_lock_bh(&c->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); - rcu_swap_protected(c->params, params, lockdep_is_held(&c->tcf_lock)); + params = rcu_replace_pointer(c->params, params, + lockdep_is_held(&c->tcf_lock)); spin_unlock_bh(&c->tcf_lock); if (goto_ch) @@ -905,11 +905,7 @@ static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets, { struct tcf_ct *c = to_ct(a); - _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); - - if (hw) - _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw), - bytes, packets); + tcf_action_update_stats(a, bytes, packets, false, hw); c->tcf_tm.lastuse = max_t(u64, c->tcf_tm.lastuse, lastuse); } diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 0dbcfd1dca7b..40038c321b4a 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -153,7 +153,7 @@ static const struct nla_policy ctinfo_policy[TCA_CTINFO_MAX + 1] = { static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct tcf_proto *tp, + struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ctinfo_net_id); @@ -210,7 +210,7 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { ret = tcf_idr_create(tn, index, est, a, - &act_ctinfo_ops, bind, false); + &act_ctinfo_ops, bind, false, 0); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -257,8 +257,8 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, spin_lock_bh(&ci->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, actparm->action, goto_ch); - rcu_swap_protected(ci->params, cp_new, - lockdep_is_held(&ci->tcf_lock)); + cp_new = rcu_replace_pointer(ci->params, cp_new, + lockdep_is_held(&ci->tcf_lock)); spin_unlock_bh(&ci->tcf_lock); if (goto_ch) diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 324f1d1f6d47..416065772719 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -53,7 +53,8 @@ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = { static int tcf_gact_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct tcf_proto *tp, struct netlink_ext_ack *extack) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, gact_net_id); struct nlattr *tb[TCA_GACT_MAX + 1]; @@ -98,8 +99,8 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, index, est, a, - &act_gact_ops, bind, true); + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_gact_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -161,9 +162,9 @@ static int tcf_gact_act(struct sk_buff *skb, const struct tc_action *a, action = gact_rand[ptype](gact); } #endif - bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), skb); + tcf_action_update_bstats(&gact->common, skb); if (action == TC_ACT_SHOT) - qstats_drop_inc(this_cpu_ptr(gact->common.cpu_qstats)); + tcf_action_inc_drop_qstats(&gact->common); tcf_lastuse_update(&gact->tcf_tm); @@ -177,15 +178,7 @@ static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets, int action = READ_ONCE(gact->tcf_action); struct tcf_t *tm = &gact->tcf_tm; - _bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), bytes, - packets); - if (action == TC_ACT_SHOT) - this_cpu_ptr(gact->common.cpu_qstats)->drops += packets; - - if (hw) - _bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats_hw), - bytes, packets); - + tcf_action_update_stats(a, bytes, packets, action == TC_ACT_SHOT, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 3a31e241c647..5e6379028fc3 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -465,7 +465,8 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, static int tcf_ife_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct tcf_proto *tp, struct netlink_ext_ack *extack) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ife_net_id); struct nlattr *tb[TCA_IFE_MAX + 1]; @@ -522,7 +523,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, est, a, &act_ife_ops, - bind, true); + bind, true, 0); if (ret) { tcf_idr_cleanup(tn, index); kfree(p); @@ -594,7 +595,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, spin_lock_bh(&ife->tcf_lock); /* protected by tcf_lock when modifying existing action */ goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); - rcu_swap_protected(ife->params, p, 1); + p = rcu_replace_pointer(ife->params, p, 1); if (exists) spin_unlock_bh(&ife->tcf_lock); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 214a03d405cf..400a2cfe8452 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -95,7 +95,7 @@ static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int ovr, int bind, - struct tcf_proto *tp) + struct tcf_proto *tp, u32 flags) { struct tc_action_net *tn = net_generic(net, id); struct nlattr *tb[TCA_IPT_MAX + 1]; @@ -144,7 +144,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, est, a, ops, bind, - false); + false, 0); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -205,19 +205,19 @@ err1: static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, - struct netlink_ext_ack *extack) + u32 flags, struct netlink_ext_ack *extack) { return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr, - bind, tp); + bind, tp, flags); } static int tcf_xt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool unlocked, struct tcf_proto *tp, - struct netlink_ext_ack *extack) + u32 flags, struct netlink_ext_ack *extack) { return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr, - bind, tp); + bind, tp, flags); } static int tcf_ipt_act(struct sk_buff *skb, const struct tc_action *a, diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 9ce073a05414..1e3eb3a97532 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -93,7 +93,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, - struct netlink_ext_ack *extack) + u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, mirred_net_id); struct nlattr *tb[TCA_MIRRED_MAX + 1]; @@ -148,8 +148,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist"); return -EINVAL; } - ret = tcf_idr_create(tn, index, est, a, - &act_mirred_ops, bind, true); + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_mirred_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -178,8 +178,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, goto put_chain; } mac_header_xmit = dev_is_mac_header_xmit(dev); - rcu_swap_protected(m->tcfm_dev, dev, - lockdep_is_held(&m->tcf_lock)); + dev = rcu_replace_pointer(m->tcfm_dev, dev, + lockdep_is_held(&m->tcf_lock)); if (dev) dev_put(dev); m->tcfm_mac_header_xmit = mac_header_xmit; @@ -231,7 +231,7 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, } tcf_lastuse_update(&m->tcf_tm); - bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); + tcf_action_update_bstats(&m->common, skb); m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit); m_eaction = READ_ONCE(m->tcfm_eaction); @@ -289,8 +289,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, /* let's the caller reinsert the packet, if possible */ if (use_reinsert) { res->ingress = want_ingress; - res->qstats = this_cpu_ptr(m->common.cpu_qstats); - skb_tc_reinsert(skb, res); + if (skb_tc_reinsert(skb, res)) + tcf_action_inc_overlimit_qstats(&m->common); __this_cpu_dec(mirred_rec_level); return TC_ACT_CONSUMED; } @@ -303,7 +303,7 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, if (err) { out: - qstats_overlimit_inc(this_cpu_ptr(m->common.cpu_qstats)); + tcf_action_inc_overlimit_qstats(&m->common); if (tcf_mirred_is_act_redirect(m_eaction)) retval = TC_ACT_SHOT; } @@ -318,10 +318,7 @@ static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets, struct tcf_mirred *m = to_mirred(a); struct tcf_t *tm = &m->tcf_tm; - _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); - if (hw) - _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw), - bytes, packets); + tcf_action_update_stats(a, bytes, packets, false, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } @@ -484,7 +481,11 @@ static int __init mirred_init_module(void) return err; pr_info("Mirror/redirect action on\n"); - return tcf_register_action(&act_mirred_ops, &mirred_net_ops); + err = tcf_register_action(&act_mirred_ops, &mirred_net_ops); + if (err) + unregister_netdevice_notifier(&mirred_device_notifier); + + return err; } static void __exit mirred_cleanup_module(void) diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index e168df0e008a..325eddcc6621 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -55,7 +55,7 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_mpls *m = to_mpls(a); struct tcf_mpls_params *p; __be32 new_lse; - int ret; + int ret, mac_len; tcf_lastuse_update(&m->tcf_tm); bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); @@ -63,8 +63,12 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, /* Ensure 'data' points at mac_header prior calling mpls manipulating * functions. */ - if (skb_at_tc_ingress(skb)) + if (skb_at_tc_ingress(skb)) { skb_push_rcsum(skb, skb->mac_len); + mac_len = skb->mac_len; + } else { + mac_len = skb_network_header(skb) - skb_mac_header(skb); + } ret = READ_ONCE(m->tcf_action); @@ -72,12 +76,12 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, switch (p->tcfm_action) { case TCA_MPLS_ACT_POP: - if (skb_mpls_pop(skb, p->tcfm_proto)) + if (skb_mpls_pop(skb, p->tcfm_proto, mac_len)) goto drop; break; case TCA_MPLS_ACT_PUSH: new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol)); - if (skb_mpls_push(skb, new_lse, p->tcfm_proto)) + if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len)) goto drop; break; case TCA_MPLS_ACT_MODIFY: @@ -115,7 +119,6 @@ static int valid_label(const struct nlattr *attr, } static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = { - [TCA_MPLS_UNSPEC] = { .strict_start_type = TCA_MPLS_UNSPEC + 1 }, [TCA_MPLS_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_mpls)), [TCA_MPLS_PROTO] = { .type = NLA_U16 }, [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_U32, valid_label), @@ -127,7 +130,8 @@ static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = { static int tcf_mpls_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct tcf_proto *tp, struct netlink_ext_ack *extack) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, mpls_net_id); struct nlattr *tb[TCA_MPLS_MAX + 1]; @@ -220,7 +224,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, est, a, - &act_mpls_ops, bind, true); + &act_mpls_ops, bind, true, 0); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -258,7 +262,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, spin_lock_bh(&m->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); - rcu_swap_protected(m->mpls_p, p, lockdep_is_held(&m->tcf_lock)); + p = rcu_replace_pointer(m->mpls_p, p, lockdep_is_held(&m->tcf_lock)); spin_unlock_bh(&m->tcf_lock); if (goto_ch) diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index ea4c5359e7df..855a6fa16a62 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -36,7 +36,7 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, - struct netlink_ext_ack *extack) + u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, nat_net_id); struct nlattr *tb[TCA_NAT_MAX + 1]; @@ -61,7 +61,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { ret = tcf_idr_create(tn, index, est, a, - &act_nat_ops, bind, false); + &act_nat_ops, bind, false, 0); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -206,9 +206,7 @@ static int tcf_nat_act(struct sk_buff *skb, const struct tc_action *a, icmph = (void *)(skb_network_header(skb) + ihl); - if ((icmph->type != ICMP_DEST_UNREACH) && - (icmph->type != ICMP_TIME_EXCEEDED) && - (icmph->type != ICMP_PARAMETERPROB)) + if (!icmp_is_err(icmph->type)) break; if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph) + diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index cdfaa79382a2..3ad718576304 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -43,7 +43,7 @@ static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla, int err = -EINVAL; int rem; - if (!nla || !n) + if (!nla) return NULL; keys_ex = kcalloc(n, sizeof(*k), GFP_KERNEL); @@ -137,7 +137,8 @@ nla_failure: static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct tcf_proto *tp, struct netlink_ext_ack *extack) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, pedit_net_id); struct nlattr *tb[TCA_PEDIT_MAX + 1]; @@ -170,6 +171,10 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, } parm = nla_data(pattr); + if (!parm->nkeys) { + NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); + return -EINVAL; + } ksize = parm->nkeys * sizeof(struct tc_pedit_key); if (nla_len(pattr) < sizeof(*parm) + ksize) { NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid"); @@ -183,14 +188,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - if (!parm->nkeys) { - tcf_idr_cleanup(tn, index); - NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); - ret = -EINVAL; - goto out_free; - } ret = tcf_idr_create(tn, index, est, a, - &act_pedit_ops, bind, false); + &act_pedit_ops, bind, false, 0); if (ret) { tcf_idr_cleanup(tn, index); goto out_free; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 89c04c52af3d..8b7a0ac96c51 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -47,7 +47,7 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { static int tcf_police_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct tcf_proto *tp, + struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { int ret = 0, tcfp_result = TC_ACT_OK, err, size; @@ -87,7 +87,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, NULL, a, - &act_police_ops, bind, true); + &act_police_ops, bind, true, 0); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -191,9 +191,9 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, police->tcfp_ptoks = new->tcfp_mtu_ptoks; spin_unlock_bh(&police->tcfp_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); - rcu_swap_protected(police->params, - new, - lockdep_is_held(&police->tcf_lock)); + new = rcu_replace_pointer(police->params, + new, + lockdep_is_held(&police->tcf_lock)); spin_unlock_bh(&police->tcf_lock); if (goto_ch) @@ -294,10 +294,7 @@ static void tcf_police_stats_update(struct tc_action *a, struct tcf_police *police = to_police(a); struct tcf_t *tm = &police->tcf_tm; - _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); - if (hw) - _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw), - bytes, packets); + tcf_action_update_stats(a, bytes, packets, false, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } @@ -345,10 +342,7 @@ static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, nla_put_u32(skb, TCA_POLICE_AVRATE, p->tcfp_ewma_rate)) goto nla_put_failure; - t.install = jiffies_to_clock_t(jiffies - police->tcf_tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - police->tcf_tm.lastuse); - t.firstuse = jiffies_to_clock_t(jiffies - police->tcf_tm.firstuse); - t.expires = jiffies_to_clock_t(police->tcf_tm.expires); + tcf_tm_dump(&t, &police->tcf_tm); if (nla_put_64bit(skb, TCA_POLICE_TM, sizeof(t), &t, TCA_POLICE_PAD)) goto nla_put_failure; spin_unlock_bh(&police->tcf_lock); diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 514456a0b9a8..ce948c1e24dc 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -36,7 +36,7 @@ static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = { static int tcf_sample_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, - struct netlink_ext_ack *extack) + u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, sample_net_id); struct nlattr *tb[TCA_SAMPLE_MAX + 1]; @@ -69,7 +69,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, est, a, - &act_sample_ops, bind, true); + &act_sample_ops, bind, true, 0); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -102,8 +102,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); s->rate = rate; s->psample_group_num = psample_group_num; - rcu_swap_protected(s->psample_group, psample_group, - lockdep_is_held(&s->tcf_lock)); + psample_group = rcu_replace_pointer(s->psample_group, psample_group, + lockdep_is_held(&s->tcf_lock)); if (tb[TCA_SAMPLE_TRUNC_SIZE]) { s->truncate = true; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 6120e56117ca..9813ca4006dd 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -35,7 +35,7 @@ static int tcf_simp_act(struct sk_buff *skb, const struct tc_action *a, * Example if this was the 3rd packet and the string was "hello" * then it would look like "hello_3" (without quotes) */ - pr_info("simple: %s_%d\n", + pr_info("simple: %s_%llu\n", (char *)d->tcfd_defdata, d->tcf_bstats.packets); spin_unlock(&d->tcf_lock); return d->tcf_action; @@ -86,7 +86,8 @@ static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = { static int tcf_simp_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct tcf_proto *tp, struct netlink_ext_ack *extack) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, simp_net_id); struct nlattr *tb[TCA_DEF_MAX + 1]; @@ -127,7 +128,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, est, a, - &act_simp_ops, bind, false); + &act_simp_ops, bind, false, 0); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 6a8d3337c577..e857424c387c 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -86,7 +86,7 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct tcf_proto *tp, + struct tcf_proto *tp, u32 act_flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); @@ -165,7 +165,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, est, a, - &act_skbedit_ops, bind, true); + &act_skbedit_ops, bind, true, 0); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -206,8 +206,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, spin_lock_bh(&d->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); - rcu_swap_protected(d->params, params_new, - lockdep_is_held(&d->tcf_lock)); + params_new = rcu_replace_pointer(d->params, params_new, + lockdep_is_held(&d->tcf_lock)); spin_unlock_bh(&d->tcf_lock); if (params_new) kfree_rcu(params_new, rcu); diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 888437f97ba6..39e6d94cfafb 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -79,7 +79,7 @@ static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = { static int tcf_skbmod_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct tcf_proto *tp, + struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); @@ -143,7 +143,7 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, index, est, a, - &act_skbmod_ops, bind, true); + &act_skbmod_ops, bind, true, 0); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 2f83a79f76aa..536c4bc31be6 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -10,6 +10,8 @@ #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <net/geneve.h> +#include <net/vxlan.h> +#include <net/erspan.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/dst.h> @@ -31,7 +33,7 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, params = rcu_dereference_bh(t->params); tcf_lastuse_update(&t->tcf_tm); - bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb); + tcf_action_update_bstats(&t->common, skb); action = READ_ONCE(t->tcf_action); switch (params->tcft_action) { @@ -53,7 +55,11 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, static const struct nla_policy enc_opts_policy[TCA_TUNNEL_KEY_ENC_OPTS_MAX + 1] = { + [TCA_TUNNEL_KEY_ENC_OPTS_UNSPEC] = { + .strict_start_type = TCA_TUNNEL_KEY_ENC_OPTS_VXLAN }, [TCA_TUNNEL_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED }, + [TCA_TUNNEL_KEY_ENC_OPTS_VXLAN] = { .type = NLA_NESTED }, + [TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN] = { .type = NLA_NESTED }, }; static const struct nla_policy @@ -64,6 +70,19 @@ geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = { .len = 128 }, }; +static const struct nla_policy +vxlan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1] = { + [TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP] = { .type = NLA_U32 }, +}; + +static const struct nla_policy +erspan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1] = { + [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER] = { .type = NLA_U8 }, + [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX] = { .type = NLA_U32 }, + [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR] = { .type = NLA_U8 }, + [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID] = { .type = NLA_U8 }, +}; + static int tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len, struct netlink_ext_ack *extack) @@ -116,10 +135,89 @@ tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len, return opt_len; } +static int +tunnel_key_copy_vxlan_opt(const struct nlattr *nla, void *dst, int dst_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1]; + int err; + + err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX, nla, + vxlan_opt_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key vxlan option gbp"); + return -EINVAL; + } + + if (dst) { + struct vxlan_metadata *md = dst; + + md->gbp = nla_get_u32(tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]); + } + + return sizeof(struct vxlan_metadata); +} + +static int +tunnel_key_copy_erspan_opt(const struct nlattr *nla, void *dst, int dst_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1]; + int err; + u8 ver; + + err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX, nla, + erspan_opt_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option ver"); + return -EINVAL; + } + + ver = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]); + if (ver == 1) { + if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option index"); + return -EINVAL; + } + } else if (ver == 2) { + if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR] || + !tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option dir or hwid"); + return -EINVAL; + } + } else { + NL_SET_ERR_MSG(extack, "Tunnel key erspan option ver is incorrect"); + return -EINVAL; + } + + if (dst) { + struct erspan_metadata *md = dst; + + md->version = ver; + if (ver == 1) { + nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX]; + md->u.index = nla_get_be32(nla); + } else { + nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR]; + md->u.md2.dir = nla_get_u8(nla); + nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID]; + set_hwid(&md->u.md2, nla_get_u8(nla)); + } + } + + return sizeof(struct erspan_metadata); +} + static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, int dst_len, struct netlink_ext_ack *extack) { - int err, rem, opt_len, len = nla_len(nla), opts_len = 0; + int err, rem, opt_len, len = nla_len(nla), opts_len = 0, type = 0; const struct nlattr *attr, *head = nla_data(nla); err = nla_validate_deprecated(head, len, TCA_TUNNEL_KEY_ENC_OPTS_MAX, @@ -130,15 +228,48 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, nla_for_each_attr(attr, head, len, rem) { switch (nla_type(attr)) { case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: + if (type && type != TUNNEL_GENEVE_OPT) { + NL_SET_ERR_MSG(extack, "Duplicate type for geneve options"); + return -EINVAL; + } opt_len = tunnel_key_copy_geneve_opt(attr, dst, dst_len, extack); if (opt_len < 0) return opt_len; opts_len += opt_len; + if (opts_len > IP_TUNNEL_OPTS_MAX) { + NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size"); + return -EINVAL; + } if (dst) { dst_len -= opt_len; dst += opt_len; } + type = TUNNEL_GENEVE_OPT; + break; + case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN: + if (type) { + NL_SET_ERR_MSG(extack, "Duplicate type for vxlan options"); + return -EINVAL; + } + opt_len = tunnel_key_copy_vxlan_opt(attr, dst, + dst_len, extack); + if (opt_len < 0) + return opt_len; + opts_len += opt_len; + type = TUNNEL_VXLAN_OPT; + break; + case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN: + if (type) { + NL_SET_ERR_MSG(extack, "Duplicate type for erspan options"); + return -EINVAL; + } + opt_len = tunnel_key_copy_erspan_opt(attr, dst, + dst_len, extack); + if (opt_len < 0) + return opt_len; + opts_len += opt_len; + type = TUNNEL_ERSPAN_OPT; break; } } @@ -175,6 +306,22 @@ static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info, #else return -EAFNOSUPPORT; #endif + case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN: +#if IS_ENABLED(CONFIG_INET) + info->key.tun_flags |= TUNNEL_VXLAN_OPT; + return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), + opts_len, extack); +#else + return -EAFNOSUPPORT; +#endif + case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN: +#if IS_ENABLED(CONFIG_INET) + info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), + opts_len, extack); +#else + return -EAFNOSUPPORT; +#endif default: NL_SET_ERR_MSG(extack, "Cannot set tunnel options for unknown tunnel type"); return -EINVAL; @@ -208,7 +355,7 @@ static void tunnel_key_release_params(struct tcf_tunnel_key_params *p) static int tunnel_key_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct tcf_proto *tp, + struct tcf_proto *tp, u32 act_flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); @@ -347,8 +494,9 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, } if (!exists) { - ret = tcf_idr_create(tn, index, est, a, - &act_tunnel_key_ops, bind, true); + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_tunnel_key_ops, bind, + act_flags); if (ret) { NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); goto release_tun_meta; @@ -381,8 +529,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, spin_lock_bh(&t->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); - rcu_swap_protected(t->params, params_new, - lockdep_is_held(&t->tcf_lock)); + params_new = rcu_replace_pointer(t->params, params_new, + lockdep_is_held(&t->tcf_lock)); spin_unlock_bh(&t->tcf_lock); tunnel_key_release_params(params_new); if (goto_ch) @@ -450,6 +598,56 @@ static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, return 0; } +static int tunnel_key_vxlan_opts_dump(struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + struct vxlan_metadata *md = (struct vxlan_metadata *)(info + 1); + struct nlattr *start; + + start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_VXLAN); + if (!start) + return -EMSGSIZE; + + if (nla_put_u32(skb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP, md->gbp)) { + nla_nest_cancel(skb, start); + return -EMSGSIZE; + } + + nla_nest_end(skb, start); + return 0; +} + +static int tunnel_key_erspan_opts_dump(struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + struct erspan_metadata *md = (struct erspan_metadata *)(info + 1); + struct nlattr *start; + + start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN); + if (!start) + return -EMSGSIZE; + + if (nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER, md->version)) + goto err; + + if (md->version == 1 && + nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX, md->u.index)) + goto err; + + if (md->version == 2 && + (nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR, + md->u.md2.dir) || + nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID, + get_hwid(&md->u.md2)))) + goto err; + + nla_nest_end(skb, start); + return 0; +err: + nla_nest_cancel(skb, start); + return -EMSGSIZE; +} + static int tunnel_key_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { @@ -467,6 +665,14 @@ static int tunnel_key_opts_dump(struct sk_buff *skb, err = tunnel_key_geneve_opts_dump(skb, info); if (err) goto err_out; + } else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) { + err = tunnel_key_vxlan_opts_dump(skb, info); + if (err) + goto err_out; + } else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) { + err = tunnel_key_erspan_opts_dump(skb, info); + if (err) + goto err_out; } else { err_out: nla_nest_cancel(skb, start); diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 08aaf719a70f..c91d3958fcbb 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -29,7 +29,7 @@ static int tcf_vlan_act(struct sk_buff *skb, const struct tc_action *a, u16 tci; tcf_lastuse_update(&v->tcf_tm); - bstats_cpu_update(this_cpu_ptr(v->common.cpu_bstats), skb); + tcf_action_update_bstats(&v->common, skb); /* Ensure 'data' points at mac_header prior calling vlan manipulating * functions. @@ -88,7 +88,7 @@ out: return action; drop: - qstats_drop_inc(this_cpu_ptr(v->common.cpu_qstats)); + tcf_action_inc_drop_qstats(&v->common); return TC_ACT_SHOT; } @@ -102,7 +102,8 @@ static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = { static int tcf_vlan_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct tcf_proto *tp, struct netlink_ext_ack *extack) + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, vlan_net_id); struct nlattr *tb[TCA_VLAN_MAX + 1]; @@ -188,8 +189,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, action = parm->v_action; if (!exists) { - ret = tcf_idr_create(tn, index, est, a, - &act_vlan_ops, bind, true); + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_vlan_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -220,7 +221,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, spin_lock_bh(&v->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); - rcu_swap_protected(v->vlan_p, p, lockdep_is_held(&v->tcf_lock)); + p = rcu_replace_pointer(v->vlan_p, p, lockdep_is_held(&v->tcf_lock)); spin_unlock_bh(&v->tcf_lock); if (goto_ch) @@ -307,10 +308,7 @@ static void tcf_vlan_stats_update(struct tc_action *a, u64 bytes, u32 packets, struct tcf_vlan *v = to_vlan(a); struct tcf_t *tm = &v->tcf_tm; - _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); - if (hw) - _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw), - bytes, packets); + tcf_action_update_stats(a, bytes, packets, false, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 64584a1df425..20d60b8fcb70 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -21,6 +21,7 @@ #include <linux/slab.h> #include <linux/idr.h> #include <linux/rhashtable.h> +#include <linux/jhash.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> @@ -47,6 +48,62 @@ static LIST_HEAD(tcf_proto_base); /* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK(cls_mod_lock); +static u32 destroy_obj_hashfn(const struct tcf_proto *tp) +{ + return jhash_3words(tp->chain->index, tp->prio, + (__force __u32)tp->protocol, 0); +} + +static void tcf_proto_signal_destroying(struct tcf_chain *chain, + struct tcf_proto *tp) +{ + struct tcf_block *block = chain->block; + + mutex_lock(&block->proto_destroy_lock); + hash_add_rcu(block->proto_destroy_ht, &tp->destroy_ht_node, + destroy_obj_hashfn(tp)); + mutex_unlock(&block->proto_destroy_lock); +} + +static bool tcf_proto_cmp(const struct tcf_proto *tp1, + const struct tcf_proto *tp2) +{ + return tp1->chain->index == tp2->chain->index && + tp1->prio == tp2->prio && + tp1->protocol == tp2->protocol; +} + +static bool tcf_proto_exists_destroying(struct tcf_chain *chain, + struct tcf_proto *tp) +{ + u32 hash = destroy_obj_hashfn(tp); + struct tcf_proto *iter; + bool found = false; + + rcu_read_lock(); + hash_for_each_possible_rcu(chain->block->proto_destroy_ht, iter, + destroy_ht_node, hash) { + if (tcf_proto_cmp(tp, iter)) { + found = true; + break; + } + } + rcu_read_unlock(); + + return found; +} + +static void +tcf_proto_signal_destroyed(struct tcf_chain *chain, struct tcf_proto *tp) +{ + struct tcf_block *block = chain->block; + + mutex_lock(&block->proto_destroy_lock); + if (hash_hashed(&tp->destroy_ht_node)) + hash_del_rcu(&tp->destroy_ht_node); + mutex_unlock(&block->proto_destroy_lock); +} + /* Find classifier type by string name */ static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind) @@ -162,11 +219,22 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) return TC_H_MAJ(first); } +static bool tcf_proto_check_kind(struct nlattr *kind, char *name) +{ + if (kind) + return nla_strlcpy(name, kind, IFNAMSIZ) >= IFNAMSIZ; + memset(name, 0, IFNAMSIZ); + return false; +} + static bool tcf_proto_is_unlocked(const char *kind) { const struct tcf_proto_ops *ops; bool ret; + if (strlen(kind) == 0) + return false; + ops = tcf_proto_lookup_ops(kind, false, NULL); /* On error return false to take rtnl lock. Proto lookup/create * functions will perform lookup again and properly handle errors. @@ -223,9 +291,11 @@ static void tcf_proto_get(struct tcf_proto *tp) static void tcf_chain_put(struct tcf_chain *chain); static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held, - struct netlink_ext_ack *extack) + bool sig_destroy, struct netlink_ext_ack *extack) { tp->ops->destroy(tp, rtnl_held, extack); + if (sig_destroy) + tcf_proto_signal_destroyed(tp->chain, tp); tcf_chain_put(tp->chain); module_put(tp->ops->owner); kfree_rcu(tp, rcu); @@ -235,7 +305,7 @@ static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { if (refcount_dec_and_test(&tp->refcnt)) - tcf_proto_destroy(tp, rtnl_held, extack); + tcf_proto_destroy(tp, rtnl_held, true, extack); } static int walker_check_empty(struct tcf_proto *tp, void *fh, @@ -359,6 +429,7 @@ static bool tcf_chain_detach(struct tcf_chain *chain) static void tcf_block_destroy(struct tcf_block *block) { mutex_destroy(&block->lock); + mutex_destroy(&block->proto_destroy_lock); kfree_rcu(block, rcu); } @@ -534,6 +605,12 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held) mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_dereference(chain->filter_chain, chain); + while (tp) { + tp_next = rcu_dereference_protected(tp->next, 1); + tcf_proto_signal_destroying(chain, tp); + tp = tp_next; + } + tp = tcf_chain_dereference(chain->filter_chain, chain); RCU_INIT_POINTER(chain->filter_chain, NULL); tcf_chain0_head_change(chain, NULL); chain->flushing = true; @@ -833,6 +910,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, return ERR_PTR(-ENOMEM); } mutex_init(&block->lock); + mutex_init(&block->proto_destroy_lock); init_rwsem(&block->cb_lock); flow_block_init(&block->flow_block); INIT_LIST_HEAD(&block->chain_list); @@ -1610,6 +1688,12 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain, mutex_lock(&chain->filter_chain_lock); + if (tcf_proto_exists_destroying(chain, tp_new)) { + mutex_unlock(&chain->filter_chain_lock); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); + return ERR_PTR(-EAGAIN); + } + tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, false); if (!tp) @@ -1617,10 +1701,10 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain, mutex_unlock(&chain->filter_chain_lock); if (tp) { - tcf_proto_destroy(tp_new, rtnl_held, NULL); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); tp_new = tp; } else if (err) { - tcf_proto_destroy(tp_new, rtnl_held, NULL); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); tp_new = ERR_PTR(err); } @@ -1658,6 +1742,7 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, return; } + tcf_proto_signal_destroying(chain, tp); next = tcf_chain_dereference(chain_info.next, chain); if (tp == chain->filter_chain) tcf_chain0_head_change(chain, next); @@ -1843,6 +1928,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; @@ -1899,13 +1985,19 @@ replay: if (err) return err; + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } + /* Take rtnl mutex if rtnl_held was set to true on previous iteration, * block is shared (no qdisc found), qdisc is not unlocked, classifier * type is not specified, classifier is not unlocked. */ if (rtnl_held || (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || - !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + !tcf_proto_is_unlocked(name)) { rtnl_held = true; rtnl_lock(); } @@ -2063,6 +2155,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; @@ -2102,13 +2195,18 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, if (err) return err; + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } /* Take rtnl mutex if flushing whole chain, block is shared (no qdisc * found), qdisc is not unlocked, classifier type is not specified, * classifier is not unlocked. */ if (!prio || (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || - !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + !tcf_proto_is_unlocked(name)) { rtnl_held = true; rtnl_lock(); } @@ -2164,6 +2262,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, err = -EINVAL; goto errout_locked; } else if (t->tcm_handle == 0) { + tcf_proto_signal_destroying(chain, tp); tcf_chain_tp_remove(chain, &chain_info, tp); mutex_unlock(&chain->filter_chain_lock); @@ -2216,6 +2315,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; @@ -2252,12 +2352,17 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, if (err) return err; + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } /* Take rtnl mutex if block is shared (no qdisc found), qdisc is not * unlocked, classifier type is not specified, classifier is not * unlocked. */ if ((q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || - !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + !tcf_proto_is_unlocked(name)) { rtnl_held = true; rtnl_lock(); } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index bf10bdaf5012..8229ed4a67be 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -162,16 +162,20 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, cls_bpf.name = obj->bpf_name; cls_bpf.exts_integrated = obj->exts_integrated; - if (oldprog) + if (oldprog && prog) err = tc_setup_cb_replace(block, tp, TC_SETUP_CLSBPF, &cls_bpf, skip_sw, &oldprog->gen_flags, &oldprog->in_hw_count, &prog->gen_flags, &prog->in_hw_count, true); - else + else if (prog) err = tc_setup_cb_add(block, tp, TC_SETUP_CLSBPF, &cls_bpf, skip_sw, &prog->gen_flags, &prog->in_hw_count, true); + else + err = tc_setup_cb_destroy(block, tp, TC_SETUP_CLSBPF, &cls_bpf, + skip_sw, &oldprog->gen_flags, + &oldprog->in_hw_count, true); if (prog && err) { cls_bpf_offload_cmd(tp, oldprog, prog, extack); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 74221e3351c3..c307ee1d6ca6 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -22,6 +22,8 @@ #include <net/ip.h> #include <net/flow_dissector.h> #include <net/geneve.h> +#include <net/vxlan.h> +#include <net/erspan.h> #include <net/dst.h> #include <net/dst_metadata.h> @@ -688,7 +690,11 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { static const struct nla_policy enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPTS_UNSPEC] = { + .strict_start_type = TCA_FLOWER_KEY_ENC_OPTS_VXLAN }, [TCA_FLOWER_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_OPTS_VXLAN] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_OPTS_ERSPAN] = { .type = NLA_NESTED }, }; static const struct nla_policy @@ -699,6 +705,19 @@ geneve_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1] = { .len = 128 }, }; +static const struct nla_policy +vxlan_opt_policy[TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP] = { .type = NLA_U32 }, +}; + +static const struct nla_policy +erspan_opt_policy[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID] = { .type = NLA_U8 }, +}; + static void fl_set_key_val(struct nlattr **tb, void *val, int val_type, void *mask, int mask_type, int len) @@ -928,6 +947,105 @@ static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key, return sizeof(struct geneve_opt) + data_len; } +static int fl_set_vxlan_opt(const struct nlattr *nla, struct fl_flow_key *key, + int depth, int option_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX + 1]; + struct vxlan_metadata *md; + int err; + + md = (struct vxlan_metadata *)&key->enc_opts.data[key->enc_opts.len]; + memset(md, 0xff, sizeof(*md)); + + if (!depth) + return sizeof(*md); + + if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_VXLAN) { + NL_SET_ERR_MSG(extack, "Non-vxlan option type for mask"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX, nla, + vxlan_opt_policy, extack); + if (err < 0) + return err; + + if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key vxlan option gbp"); + return -EINVAL; + } + + if (tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) + md->gbp = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]); + + return sizeof(*md); +} + +static int fl_set_erspan_opt(const struct nlattr *nla, struct fl_flow_key *key, + int depth, int option_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX + 1]; + struct erspan_metadata *md; + int err; + + md = (struct erspan_metadata *)&key->enc_opts.data[key->enc_opts.len]; + memset(md, 0xff, sizeof(*md)); + md->version = 1; + + if (!depth) + return sizeof(*md); + + if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_ERSPAN) { + NL_SET_ERR_MSG(extack, "Non-erspan option type for mask"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX, nla, + erspan_opt_policy, extack); + if (err < 0) + return err; + + if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option ver"); + return -EINVAL; + } + + if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER]) + md->version = nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER]); + + if (md->version == 1) { + if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) { + NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option index"); + return -EINVAL; + } + if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) { + nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]; + md->u.index = nla_get_be32(nla); + } + } else if (md->version == 2) { + if (!option_len && (!tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR] || + !tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID])) { + NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option dir or hwid"); + return -EINVAL; + } + if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR]) { + nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR]; + md->u.md2.dir = nla_get_u8(nla); + } + if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID]) { + nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID]; + set_hwid(&md->u.md2, nla_get_u8(nla)); + } + } else { + NL_SET_ERR_MSG(extack, "Tunnel key erspan option ver is incorrect"); + return -EINVAL; + } + + return sizeof(*md); +} + static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask, struct netlink_ext_ack *extack) @@ -958,6 +1076,11 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS]), key_depth) { switch (nla_type(nla_opt_key)) { case TCA_FLOWER_KEY_ENC_OPTS_GENEVE: + if (key->enc_opts.dst_opt_type && + key->enc_opts.dst_opt_type != TUNNEL_GENEVE_OPT) { + NL_SET_ERR_MSG(extack, "Duplicate type for geneve options"); + return -EINVAL; + } option_len = 0; key->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT; option_len = fl_set_geneve_opt(nla_opt_key, key, @@ -986,6 +1109,72 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, if (msk_depth) nla_opt_msk = nla_next(nla_opt_msk, &msk_depth); break; + case TCA_FLOWER_KEY_ENC_OPTS_VXLAN: + if (key->enc_opts.dst_opt_type) { + NL_SET_ERR_MSG(extack, "Duplicate type for vxlan options"); + return -EINVAL; + } + option_len = 0; + key->enc_opts.dst_opt_type = TUNNEL_VXLAN_OPT; + option_len = fl_set_vxlan_opt(nla_opt_key, key, + key_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + key->enc_opts.len += option_len; + /* At the same time we need to parse through the mask + * in order to verify exact and mask attribute lengths. + */ + mask->enc_opts.dst_opt_type = TUNNEL_VXLAN_OPT; + option_len = fl_set_vxlan_opt(nla_opt_msk, mask, + msk_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + mask->enc_opts.len += option_len; + if (key->enc_opts.len != mask->enc_opts.len) { + NL_SET_ERR_MSG(extack, "Key and mask miss aligned"); + return -EINVAL; + } + + if (msk_depth) + nla_opt_msk = nla_next(nla_opt_msk, &msk_depth); + break; + case TCA_FLOWER_KEY_ENC_OPTS_ERSPAN: + if (key->enc_opts.dst_opt_type) { + NL_SET_ERR_MSG(extack, "Duplicate type for erspan options"); + return -EINVAL; + } + option_len = 0; + key->enc_opts.dst_opt_type = TUNNEL_ERSPAN_OPT; + option_len = fl_set_erspan_opt(nla_opt_key, key, + key_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + key->enc_opts.len += option_len; + /* At the same time we need to parse through the mask + * in order to verify exact and mask attribute lengths. + */ + mask->enc_opts.dst_opt_type = TUNNEL_ERSPAN_OPT; + option_len = fl_set_erspan_opt(nla_opt_msk, mask, + msk_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + mask->enc_opts.len += option_len; + if (key->enc_opts.len != mask->enc_opts.len) { + NL_SET_ERR_MSG(extack, "Key and mask miss aligned"); + return -EINVAL; + } + + if (msk_depth) + nla_opt_msk = nla_next(nla_opt_msk, &msk_depth); + break; default: NL_SET_ERR_MSG(extack, "Unknown tunnel option type"); return -EINVAL; @@ -2135,6 +2324,61 @@ nla_put_failure: return -EMSGSIZE; } +static int fl_dump_key_vxlan_opt(struct sk_buff *skb, + struct flow_dissector_key_enc_opts *enc_opts) +{ + struct vxlan_metadata *md; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_VXLAN); + if (!nest) + goto nla_put_failure; + + md = (struct vxlan_metadata *)&enc_opts->data[0]; + if (nla_put_u32(skb, TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP, md->gbp)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int fl_dump_key_erspan_opt(struct sk_buff *skb, + struct flow_dissector_key_enc_opts *enc_opts) +{ + struct erspan_metadata *md; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_ERSPAN); + if (!nest) + goto nla_put_failure; + + md = (struct erspan_metadata *)&enc_opts->data[0]; + if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER, md->version)) + goto nla_put_failure; + + if (md->version == 1 && + nla_put_be32(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX, md->u.index)) + goto nla_put_failure; + + if (md->version == 2 && + (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR, + md->u.md2.dir) || + nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID, + get_hwid(&md->u.md2)))) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + static int fl_dump_key_ct(struct sk_buff *skb, struct flow_dissector_key_ct *key, struct flow_dissector_key_ct *mask) @@ -2188,6 +2432,16 @@ static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type, if (err) goto nla_put_failure; break; + case TUNNEL_VXLAN_OPT: + err = fl_dump_key_vxlan_opt(skb, enc_opts); + if (err) + goto nla_put_failure; + break; + case TUNNEL_ERSPAN_OPT: + err = fl_dump_key_erspan_opt(skb, enc_opts); + if (err) + goto nla_put_failure; + break; default: goto nla_put_failure; } diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 82bd14e7ac93..d99966a55c84 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -446,7 +446,7 @@ META_COLLECTOR(int_sk_wmem_queued) *err = -1; return; } - dst->value = sk->sk_wmem_queued; + dst->value = READ_ONCE(sk->sk_wmem_queued); } META_COLLECTOR(int_sk_fwd_alloc) @@ -521,7 +521,7 @@ META_COLLECTOR(int_sk_ack_bl) *err = -1; return; } - dst->value = sk->sk_ack_backlog; + dst->value = READ_ONCE(sk->sk_ack_backlog); } META_COLLECTOR(int_sk_max_ack_bl) @@ -532,7 +532,7 @@ META_COLLECTOR(int_sk_max_ack_bl) *err = -1; return; } - dst->value = sk->sk_max_ack_backlog; + dst->value = READ_ONCE(sk->sk_max_ack_backlog); } META_COLLECTOR(int_sk_prio) @@ -554,7 +554,7 @@ META_COLLECTOR(int_sk_rcvlowat) *err = -1; return; } - dst->value = sk->sk_rcvlowat; + dst->value = READ_ONCE(sk->sk_rcvlowat); } META_COLLECTOR(int_sk_rcvtimeo) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 81d58b280612..1047825d9f48 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1390,8 +1390,7 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) } const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = { - [TCA_KIND] = { .type = NLA_NUL_STRING, - .len = IFNAMSIZ - 1 }, + [TCA_KIND] = { .type = NLA_STRING }, [TCA_RATE] = { .type = NLA_BINARY, .len = sizeof(struct tc_estimator) }, [TCA_STAB] = { .type = NLA_NESTED }, diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 06c7a2da21bc..39b427dc7512 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1127,6 +1127,33 @@ static const struct nla_policy cbq_policy[TCA_CBQ_MAX + 1] = { [TCA_CBQ_POLICE] = { .len = sizeof(struct tc_cbq_police) }, }; +static int cbq_opt_parse(struct nlattr *tb[TCA_CBQ_MAX + 1], + struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + int err; + + if (!opt) { + NL_SET_ERR_MSG(extack, "CBQ options are required for this operation"); + return -EINVAL; + } + + err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, + cbq_policy, extack); + if (err < 0) + return err; + + if (tb[TCA_CBQ_WRROPT]) { + const struct tc_cbq_wrropt *wrr = nla_data(tb[TCA_CBQ_WRROPT]); + + if (wrr->priority > TC_CBQ_MAXPRIO) { + NL_SET_ERR_MSG(extack, "priority is bigger than TC_CBQ_MAXPRIO"); + err = -EINVAL; + } + } + return err; +} + static int cbq_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -1139,13 +1166,7 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt, hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); q->delay_timer.function = cbq_undelay; - if (!opt) { - NL_SET_ERR_MSG(extack, "CBQ options are required for this operation"); - return -EINVAL; - } - - err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, cbq_policy, - extack); + err = cbq_opt_parse(tb, opt, extack); if (err < 0) return err; @@ -1464,13 +1485,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t struct cbq_class *parent; struct qdisc_rate_table *rtab = NULL; - if (!opt) { - NL_SET_ERR_MSG(extack, "Mandatory qdisc options missing"); - return -EINVAL; - } - - err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, cbq_policy, - extack); + err = cbq_opt_parse(tb, opt, extack); if (err < 0) return err; diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index 1bef152c5721..b2905b03a432 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -306,7 +306,7 @@ static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q) if (err < 0) goto skip; - if (ecmd.base.speed != SPEED_UNKNOWN) + if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN) speed = ecmd.base.speed; skip: diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index bad1cbe59a56..05605b30bef3 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -361,6 +361,8 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt, goto errout; err = -EINVAL; + if (!tb[TCA_DSMARK_INDICES]) + goto errout; indices = nla_get_u16(tb[TCA_DSMARK_INDICES]); if (hweight32(indices) != 1) diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c index cebfb65d8556..b1da5589a0c6 100644 --- a/net/sched/sch_etf.c +++ b/net/sched/sch_etf.c @@ -177,7 +177,7 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch, parent = *p; skb = rb_to_skb(parent); - if (ktime_after(txtime, skb->tstamp)) { + if (ktime_compare(txtime, skb->tstamp) >= 0) { p = &parent->rb_right; leftmost = false; } else { diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 98dd87ce1510..b1c7e726ce5d 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -530,8 +530,7 @@ begin: fq_flow_set_throttled(q, f); goto begin; } - if (time_next_packet && - (s64)(now - time_next_packet - q->ce_threshold) > 0) { + if ((s64)(now - time_next_packet - q->ce_threshold) > 0) { INET_ECN_set_ce(skb); q->stat_ce_mark++; } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index c261c0a18868..968519ff36e9 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -14,7 +14,6 @@ #include <linux/errno.h> #include <linux/init.h> #include <linux/skbuff.h> -#include <linux/jhash.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/netlink.h> diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 17bd8f539bc7..5ab696efca95 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -382,13 +382,8 @@ void __qdisc_run(struct Qdisc *q) int packets; while (qdisc_restart(q, &packets)) { - /* - * Ordered by possible occurrence: Postpone processing if - * 1. we've exceeded packet quota - * 2. another process needs the CPU; - */ quota -= packets; - if (quota <= 0 || need_resched()) { + if (quota <= 0) { __netif_schedule(q); break; } @@ -657,7 +652,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) if (likely(skb)) { qdisc_update_stats_at_dequeue(qdisc, skb); } else { - qdisc->empty = true; + WRITE_ONCE(qdisc->empty, true); } return skb; @@ -799,9 +794,6 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = { }; EXPORT_SYMBOL(pfifo_fast_ops); -static struct lock_class_key qdisc_tx_busylock; -static struct lock_class_key qdisc_running_key; - struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack) @@ -854,17 +846,9 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, } spin_lock_init(&sch->busylock); - lockdep_set_class(&sch->busylock, - dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); - /* seqlock has the same scope of busylock, for NOLOCK qdisc */ spin_lock_init(&sch->seqlock); - lockdep_set_class(&sch->busylock, - dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); - seqcount_init(&sch->running); - lockdep_set_class(&sch->running, - dev->qdisc_running_key ?: &qdisc_running_key); sch->ops = ops; sch->flags = ops->static_flags; @@ -875,6 +859,12 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, dev_hold(dev); refcount_set(&sch->refcnt, 1); + if (sch != &noop_qdisc) { + lockdep_set_class(&sch->busylock, &dev->qdisc_tx_busylock_key); + lockdep_set_class(&sch->seqlock, &dev->qdisc_tx_busylock_key); + lockdep_set_class(&sch->running, &dev->qdisc_running_key); + } + return sch; errout1: kfree(p); @@ -1043,6 +1033,8 @@ static void attach_one_default_qdisc(struct net_device *dev, if (dev->priv_flags & IFF_NO_QUEUE) ops = &noqueue_qdisc_ops; + else if(dev->type == ARPHRD_CAN) + ops = &pfifo_fast_ops; qdisc = qdisc_create_dflt(dev_queue, ops, TC_H_ROOT, NULL); if (!qdisc) { @@ -1217,8 +1209,13 @@ void dev_deactivate_many(struct list_head *head) /* Wait for outstanding qdisc_run calls. */ list_for_each_entry(dev, head, close_list) { - while (some_qdisc_is_busy(dev)) - yield(); + while (some_qdisc_is_busy(dev)) { + /* wait_event() would avoid this sleep-loop but would + * require expensive checks in the fast paths of packet + * processing which isn't worth it. + */ + schedule_timeout_uninterruptible(1); + } /* The new qdisc is assigned at this point so we can safely * unwind stale skb lists and qdisc statistics */ diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 23cd1c873a2c..be35f03b657b 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -5,11 +5,11 @@ * Copyright (C) 2013 Nandita Dukkipati <nanditad@google.com> */ -#include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> +#include <linux/siphash.h> #include <net/pkt_sched.h> #include <net/sock.h> @@ -126,7 +126,7 @@ struct wdrr_bucket { struct hhf_sched_data { struct wdrr_bucket buckets[WDRR_BUCKET_CNT]; - u32 perturbation; /* hash perturbation */ + siphash_key_t perturbation; /* hash perturbation */ u32 quantum; /* psched_mtu(qdisc_dev(sch)); */ u32 drop_overlimit; /* number of times max qdisc packet * limit was hit @@ -264,7 +264,7 @@ static enum wdrr_bucket_idx hhf_classify(struct sk_buff *skb, struct Qdisc *sch) } /* Get hashed flow-id of the skb. */ - hash = skb_get_hash_perturb(skb, q->perturbation); + hash = skb_get_hash_perturb(skb, &q->perturbation); /* Check if this packet belongs to an already established HH flow. */ flow_pos = hash & HHF_BIT_MASK; @@ -582,7 +582,7 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt, sch->limit = 1000; q->quantum = psched_mtu(qdisc_dev(sch)); - q->perturbation = prandom_u32(); + get_random_bytes(&q->perturbation, sizeof(q->perturbation)); INIT_LIST_HEAD(&q->new_buckets); INIT_LIST_HEAD(&q->old_buckets); diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index 0d578333e967..278c0b2dc523 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -245,7 +245,8 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct netdev_queue *dev_queue = mq_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 || + if (gnet_stats_copy_basic(&sch->running, d, sch->cpu_bstats, + &sch->bstats) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; return 0; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 46980b8d66c5..0d0113a24962 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -557,8 +557,8 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &sch->bstats) < 0 || + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, + sch->cpu_bstats, &sch->bstats) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; } diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index b2b7fdb06fc6..1330ad224931 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -339,7 +339,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl, cl_q = q->queues[cl - 1]; if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl_q->bstats) < 0 || + d, cl_q->cpu_bstats, &cl_q->bstats) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 0e44039e729c..42e557d48e4e 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -509,6 +509,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) { qdisc_drop(skb, sch, to_free); + skb = NULL; goto finish_segs; } @@ -593,9 +594,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, finish_segs: if (segs) { unsigned int len, last_len; - int nb = 0; + int nb; - len = skb->len; + len = skb ? skb->len : 0; + nb = skb ? 1 : 0; while (segs) { skb2 = segs->next; @@ -612,7 +614,10 @@ finish_segs: } segs = skb2; } - qdisc_tree_reduce_backlog(sch, -nb, prev_len - len); + /* Parent qdiscs accounted for 1 skb of size @prev_len */ + qdisc_tree_reduce_backlog(sch, -(nb - 1), -(len - prev_len)); + } else if (!skb) { + return NET_XMIT_DROP; } return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index df98a887eb89..b0b0dc46af61 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -22,6 +22,7 @@ #define QUEUE_THRESHOLD 16384 #define DQCOUNT_INVALID -1 +#define DTIME_INVALID 0xffffffffffffffff #define MAX_PROB 0xffffffffffffffff #define PIE_SCALE 8 @@ -34,6 +35,7 @@ struct pie_params { 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 */ + u8 dq_rate_estimator; /* to calculate delay using Little's law */ }; /* variables used */ @@ -77,11 +79,34 @@ static void pie_params_init(struct pie_params *params) params->target = PSCHED_NS2TICKS(15 * NSEC_PER_MSEC); /* 15 ms */ params->ecn = false; params->bytemode = false; + params->dq_rate_estimator = false; +} + +/* private skb vars */ +struct pie_skb_cb { + psched_time_t enqueue_time; +}; + +static struct pie_skb_cb *get_pie_cb(const struct sk_buff *skb) +{ + qdisc_cb_private_validate(skb, sizeof(struct pie_skb_cb)); + return (struct pie_skb_cb *)qdisc_skb_cb(skb)->data; +} + +static psched_time_t pie_get_enqueue_time(const struct sk_buff *skb) +{ + return get_pie_cb(skb)->enqueue_time; +} + +static void pie_set_enqueue_time(struct sk_buff *skb) +{ + get_pie_cb(skb)->enqueue_time = psched_get_time(); } static void pie_vars_init(struct pie_vars *vars) { vars->dq_count = DQCOUNT_INVALID; + vars->dq_tstamp = DTIME_INVALID; vars->accu_prob = 0; vars->avg_dq_rate = 0; /* default of 150 ms in pschedtime */ @@ -172,6 +197,10 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* we can enqueue the packet */ if (enqueue) { + /* Set enqueue time only when dq_rate_estimator is disabled. */ + if (!q->params.dq_rate_estimator) + pie_set_enqueue_time(skb); + q->stats.packets_in++; if (qdisc_qlen(sch) > q->stats.maxq) q->stats.maxq = qdisc_qlen(sch); @@ -194,6 +223,7 @@ static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = { [TCA_PIE_BETA] = {.type = NLA_U32}, [TCA_PIE_ECN] = {.type = NLA_U32}, [TCA_PIE_BYTEMODE] = {.type = NLA_U32}, + [TCA_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32}, }; static int pie_change(struct Qdisc *sch, struct nlattr *opt, @@ -247,6 +277,10 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_PIE_BYTEMODE]) q->params.bytemode = nla_get_u32(tb[TCA_PIE_BYTEMODE]); + if (tb[TCA_PIE_DQ_RATE_ESTIMATOR]) + q->params.dq_rate_estimator = + nla_get_u32(tb[TCA_PIE_DQ_RATE_ESTIMATOR]); + /* Drop excess packets if new limit is lower */ qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { @@ -266,6 +300,28 @@ 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 */ + psched_time_t now = psched_get_time(); + u32 dtime = 0; + + /* If dq_rate_estimator is disabled, calculate qdelay using the + * packet timestamp. + */ + if (!q->params.dq_rate_estimator) { + q->vars.qdelay = now - pie_get_enqueue_time(skb); + + if (q->vars.dq_tstamp != DTIME_INVALID) + dtime = now - q->vars.dq_tstamp; + + q->vars.dq_tstamp = now; + + if (qlen == 0) + q->vars.qdelay = 0; + + if (dtime == 0) + return; + + goto burst_allowance_reduction; + } /* If current queue is about 10 packets or more and dq_count is unset * we have enough packets to calculate the drain rate. Save @@ -289,10 +345,10 @@ static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb) 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; + dtime = now - q->vars.dq_tstamp; + if (dtime == 0) return; @@ -317,14 +373,19 @@ static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb) 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; - } + goto burst_allowance_reduction; } } + + return; + +burst_allowance_reduction: + 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) @@ -332,19 +393,25 @@ 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 */ + psched_time_t qdelay_old = 0; /* in pschedtime */ s64 delta = 0; /* determines the change in probability */ u64 oldprob; u64 alpha, beta; u32 power; bool update_prob = true; - q->vars.qdelay_old = q->vars.qdelay; + if (q->params.dq_rate_estimator) { + qdelay_old = q->vars.qdelay; + 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 (q->vars.avg_dq_rate > 0) + qdelay = (qlen << PIE_SCALE) / q->vars.avg_dq_rate; + else + qdelay = 0; + } else { + qdelay = q->vars.qdelay; + qdelay_old = q->vars.qdelay_old; + } /* 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 @@ -430,14 +497,18 @@ static void calculate_probability(struct Qdisc *sch) /* 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 + * 3. If average dq_rate_estimator is enabled, 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) + (!q->params.dq_rate_estimator || q->vars.avg_dq_rate > 0)) { pie_vars_init(&q->vars); + } + + if (!q->params.dq_rate_estimator) + q->vars.qdelay_old = qdelay; } static void pie_timer(struct timer_list *t) @@ -497,7 +568,9 @@ static int pie_dump(struct Qdisc *sch, struct sk_buff *skb) 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)) + nla_put_u32(skb, TCA_PIE_BYTEMODE, q->params.bytemode) || + nla_put_u32(skb, TCA_PIE_DQ_RATE_ESTIMATOR, + q->params.dq_rate_estimator)) goto nla_put_failure; return nla_nest_end(skb, opts); @@ -514,9 +587,6 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) .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, @@ -524,6 +594,14 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) .ecn_mark = q->stats.ecn_mark, }; + /* avg_dq_rate is only valid if dq_rate_estimator is enabled */ + st.dq_rate_estimating = q->params.dq_rate_estimator; + + /* unscale and return dq_rate in bytes per sec */ + if (q->params.dq_rate_estimator) + st.avg_dq_rate = q->vars.avg_dq_rate * + (PSCHED_TICKS_PER_SEC) >> PIE_SCALE; + return gnet_stats_copy_app(d, &st, sizeof(st)); } diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 0f8fedb8809a..18b884cfdfe8 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -356,7 +356,7 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl, cl_q = q->queues[cl - 1]; if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl_q->bstats) < 0 || + d, cl_q->cpu_bstats, &cl_q->bstats) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index d448fe3068e5..4074c50ac3d7 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -18,7 +18,7 @@ #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/random.h> -#include <linux/jhash.h> +#include <linux/siphash.h> #include <net/ip.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> @@ -45,7 +45,7 @@ struct sfb_bucket { * (Section 4.4 of SFB reference : moving hash functions) */ struct sfb_bins { - u32 perturbation; /* jhash perturbation */ + siphash_key_t perturbation; /* siphash key */ struct sfb_bucket bins[SFB_LEVELS][SFB_NUMBUCKETS]; }; @@ -217,7 +217,8 @@ static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_da static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q) { - q->bins[slot].perturbation = prandom_u32(); + get_random_bytes(&q->bins[slot].perturbation, + sizeof(q->bins[slot].perturbation)); } static void sfb_swap_slot(struct sfb_sched_data *q) @@ -314,9 +315,9 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* If using external classifiers, get result and record it. */ if (!sfb_classify(skb, fl, &ret, &salt)) goto other_drop; - sfbhash = jhash_1word(salt, q->bins[slot].perturbation); + sfbhash = siphash_1u32(salt, &q->bins[slot].perturbation); } else { - sfbhash = skb_get_hash_perturb(skb, q->bins[slot].perturbation); + sfbhash = skb_get_hash_perturb(skb, &q->bins[slot].perturbation); } @@ -352,7 +353,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* Inelastic flow */ if (q->double_buffering) { sfbhash = skb_get_hash_perturb(skb, - q->bins[slot].perturbation); + &q->bins[slot].perturbation); if (!sfbhash) sfbhash = 1; sfb_skb_cb(skb)->hashes[slot] = sfbhash; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 68404a9d2ce4..c787d4d46017 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -14,7 +14,7 @@ #include <linux/errno.h> #include <linux/init.h> #include <linux/skbuff.h> -#include <linux/jhash.h> +#include <linux/siphash.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/netlink.h> @@ -117,7 +117,7 @@ struct sfq_sched_data { u8 headdrop; u8 maxdepth; /* limit of packets per flow */ - u32 perturbation; + siphash_key_t perturbation; u8 cur_depth; /* depth of longest slot */ u8 flags; unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */ @@ -157,7 +157,7 @@ static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index static unsigned int sfq_hash(const struct sfq_sched_data *q, const struct sk_buff *skb) { - return skb_get_hash_perturb(skb, q->perturbation) & (q->divisor - 1); + return skb_get_hash_perturb(skb, &q->perturbation) & (q->divisor - 1); } static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, @@ -607,9 +607,11 @@ static void sfq_perturbation(struct timer_list *t) 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)); + siphash_key_t nkey; + get_random_bytes(&nkey, sizeof(nkey)); spin_lock(root_lock); - q->perturbation = prandom_u32(); + q->perturbation = nkey; if (!q->filter_list && q->tail) sfq_rehash(sch); spin_unlock(root_lock); @@ -688,7 +690,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) del_timer(&q->perturb_timer); if (q->perturb_period) { mod_timer(&q->perturb_timer, jiffies + q->perturb_period); - q->perturbation = prandom_u32(); + get_random_bytes(&q->perturbation, sizeof(q->perturbation)); } sch_tree_unlock(sch); kfree(p); @@ -745,7 +747,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt, q->quantum = psched_mtu(qdisc_dev(sch)); q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum); q->perturb_period = 0; - q->perturbation = prandom_u32(); + get_random_bytes(&q->perturbation, sizeof(q->perturbation)); if (opt) { int err = sfq_change(sch, opt); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 2f7b34205c82..c609373c8661 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -922,7 +922,7 @@ static int taprio_parse_mqprio_opt(struct net_device *dev, } /* Verify priority mapping uses valid tcs */ - for (i = 0; i < TC_BITMASK + 1; i++) { + for (i = 0; i <= TC_BITMASK; i++) { if (qopt->prio_tc_map[i] >= qopt->num_tc) { NL_SET_ERR_MSG(extack, "Invalid traffic class in priority to traffic class mapping"); return -EINVAL; @@ -1044,12 +1044,11 @@ static void taprio_set_picos_per_byte(struct net_device *dev, if (err < 0) goto skip; - if (ecmd.base.speed != SPEED_UNKNOWN) + if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN) speed = ecmd.base.speed; skip: - picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8, - speed * 1000 * 1000); + picos_per_byte = (USEC_PER_SEC * 8) / speed; atomic64_set(&q->picos_per_byte, picos_per_byte); netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n", @@ -1153,7 +1152,7 @@ EXPORT_SYMBOL_GPL(taprio_offload_free); * offload state (PENDING, ACTIVE, INACTIVE) so it can be visible in dump(). * This is left as TODO. */ -void taprio_offload_config_changed(struct taprio_sched *q) +static void taprio_offload_config_changed(struct taprio_sched *q) { struct sched_gate_list *oper, *admin; @@ -1225,8 +1224,6 @@ static int taprio_enable_offload(struct net_device *dev, goto done; } - taprio_offload_config_changed(q); - done: taprio_offload_free(offload); @@ -1342,10 +1339,34 @@ static int taprio_parse_clockid(struct Qdisc *sch, struct nlattr **tb, NL_SET_ERR_MSG(extack, "Specifying a 'clockid' is mandatory"); goto out; } + + /* Everything went ok, return success. */ + err = 0; + out: return err; } +static int taprio_mqprio_cmp(const struct net_device *dev, + const struct tc_mqprio_qopt *mqprio) +{ + int i; + + if (!mqprio || mqprio->num_tc != dev->num_tc) + return -1; + + for (i = 0; i < mqprio->num_tc; i++) + if (dev->tc_to_txq[i].count != mqprio->count[i] || + dev->tc_to_txq[i].offset != mqprio->offset[i]) + return -1; + + for (i = 0; i <= TC_BITMASK; i++) + if (dev->prio_tc_map[i] != mqprio->prio_tc_map[i]) + return -1; + + return 0; +} + static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -1397,6 +1418,10 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, admin = rcu_dereference(q->admin_sched); rcu_read_unlock(); + /* no changes - no new mqprio settings */ + if (!taprio_mqprio_cmp(dev, mqprio)) + mqprio = NULL; + if (mqprio && (oper || admin)) { NL_SET_ERR_MSG(extack, "Changing the traffic mapping of a running schedule is not supported"); err = -ENOTSUPP; @@ -1454,7 +1479,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, mqprio->offset[i]); /* Always use supplied priority mappings */ - for (i = 0; i < TC_BITMASK + 1; i++) + for (i = 0; i <= TC_BITMASK; i++) netdev_set_prio_tc_map(dev, i, mqprio->prio_tc_map[i]); } @@ -1502,6 +1527,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, call_rcu(&admin->rcu, taprio_free_sched_cb); spin_unlock_irqrestore(&q->current_entry_lock, flags); + + if (FULL_OFFLOAD_IS_ENABLED(taprio_flags)) + taprio_offload_config_changed(q); } new_admin = NULL; |