diff options
Diffstat (limited to 'net/sched')
58 files changed, 4085 insertions, 1223 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig index afd2ba157a13..edde0e519438 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -324,7 +324,7 @@ config NET_SCH_CAKE tristate "Common Applications Kept Enhanced (CAKE)" help Say Y here if you want to use the Common Applications Kept Enhanced - (CAKE) queue management algorithm. + (CAKE) queue management algorithm. To compile this driver as a module, choose M here: the module will be called sch_cake. @@ -366,6 +366,19 @@ config NET_SCH_PIE If unsure, say N. +config NET_SCH_FQ_PIE + depends on NET_SCH_PIE + tristate "Flow Queue Proportional Integral controller Enhanced (FQ-PIE)" + help + Say Y here if you want to use the Flow Queue Proportional Integral + controller Enhanced (FQ-PIE) packet scheduling algorithm. + For more information, please see https://tools.ietf.org/html/rfc8033 + + To compile this driver as a module, choose M here: the module + will be called sch_fq_pie. + + If unsure, say N. + config NET_SCH_INGRESS tristate "Ingress/classifier-action Qdisc" depends on NET_CLS_ACT @@ -409,6 +422,23 @@ config NET_SCH_PLUG To compile this code as a module, choose M here: the module will be called sch_plug. +config NET_SCH_ETS + tristate "Enhanced transmission selection scheduler (ETS)" + help + The Enhanced Transmission Selection scheduler is a classful + queuing discipline that merges functionality of PRIO and DRR + qdiscs in one scheduler. ETS makes it easy to configure a set of + strict and bandwidth-sharing bands to implement the transmission + selection described in 802.1Qaz. + + Say Y here if you want to use the ETS packet scheduling + algorithm. + + To compile this driver as a module, choose M here: the module + will be called sch_ets. + + If unsure, say N. + menuconfig NET_SCH_DEFAULT bool "Allow override default queue discipline" ---help--- @@ -730,8 +760,8 @@ config NET_CLS_ACT config NET_ACT_POLICE tristate "Traffic Policing" - depends on NET_CLS_ACT - ---help--- + depends on NET_CLS_ACT + ---help--- Say Y here if you want to do traffic policing, i.e. strict bandwidth limiting. This action replaces the existing policing module. @@ -740,9 +770,9 @@ config NET_ACT_POLICE module will be called act_police. config NET_ACT_GACT - tristate "Generic actions" - depends on NET_CLS_ACT - ---help--- + tristate "Generic actions" + depends on NET_CLS_ACT + ---help--- Say Y here to take generic actions such as dropping and accepting packets. @@ -750,15 +780,15 @@ config NET_ACT_GACT module will be called act_gact. config GACT_PROB - bool "Probability support" - depends on NET_ACT_GACT - ---help--- + bool "Probability support" + depends on NET_ACT_GACT + ---help--- Say Y here to use the generic action randomly or deterministically. config NET_ACT_MIRRED - tristate "Redirecting and Mirroring" - depends on NET_CLS_ACT - ---help--- + tristate "Redirecting and Mirroring" + depends on NET_CLS_ACT + ---help--- Say Y here to allow packets to be mirrored or redirected to other devices. @@ -766,10 +796,10 @@ config NET_ACT_MIRRED module will be called act_mirred. config NET_ACT_SAMPLE - tristate "Traffic Sampling" - depends on NET_CLS_ACT - select PSAMPLE - ---help--- + tristate "Traffic Sampling" + depends on NET_CLS_ACT + select PSAMPLE + ---help--- Say Y here to allow packet sampling tc action. The packet sample action consists of statistically choosing packets and sampling them using the psample module. @@ -778,9 +808,9 @@ config NET_ACT_SAMPLE module will be called act_sample. config NET_ACT_IPT - tristate "IPtables targets" - depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES - ---help--- + tristate "IPtables targets" + depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES + ---help--- Say Y here to be able to invoke iptables targets after successful classification. @@ -788,9 +818,9 @@ config NET_ACT_IPT module will be called act_ipt. config NET_ACT_NAT - tristate "Stateless NAT" - depends on NET_CLS_ACT - ---help--- + tristate "Stateless NAT" + depends on NET_CLS_ACT + ---help--- Say Y here to do stateless NAT on IPv4 packets. You should use netfilter for NAT unless you know what you are doing. @@ -798,18 +828,18 @@ config NET_ACT_NAT module will be called act_nat. config NET_ACT_PEDIT - tristate "Packet Editing" - depends on NET_CLS_ACT - ---help--- + tristate "Packet Editing" + depends on NET_CLS_ACT + ---help--- Say Y here if you want to mangle the content of packets. To compile this code as a module, choose M here: the module will be called act_pedit. config NET_ACT_SIMP - tristate "Simple Example (Debug)" - depends on NET_CLS_ACT - ---help--- + tristate "Simple Example (Debug)" + depends on NET_CLS_ACT + ---help--- Say Y here to add a simple action for demonstration purposes. It is meant as an example and for debugging purposes. It will print a configured policy string followed by the packet count @@ -821,9 +851,9 @@ config NET_ACT_SIMP module will be called act_simple. config NET_ACT_SKBEDIT - tristate "SKB Editing" - depends on NET_CLS_ACT - ---help--- + tristate "SKB Editing" + depends on NET_CLS_ACT + ---help--- Say Y here to change skb priority or queue_mapping settings. If unsure, say N. @@ -832,10 +862,10 @@ config NET_ACT_SKBEDIT module will be called act_skbedit. config NET_ACT_CSUM - tristate "Checksum Updating" - depends on NET_CLS_ACT && INET - select LIBCRC32C - ---help--- + tristate "Checksum Updating" + depends on NET_CLS_ACT && INET + select LIBCRC32C + ---help--- Say Y here to update some common checksum after some direct packet alterations. @@ -854,9 +884,9 @@ config NET_ACT_MPLS module will be called act_mpls. config NET_ACT_VLAN - tristate "Vlan manipulation" - depends on NET_CLS_ACT - ---help--- + tristate "Vlan manipulation" + depends on NET_CLS_ACT + ---help--- Say Y here to push or pop vlan headers. If unsure, say N. @@ -865,9 +895,9 @@ config NET_ACT_VLAN module will be called act_vlan. config NET_ACT_BPF - tristate "BPF based action" - depends on NET_CLS_ACT - ---help--- + tristate "BPF based action" + depends on NET_CLS_ACT + ---help--- Say Y here to execute BPF code on packets. The BPF code will decide if the packet should be dropped or not. @@ -877,10 +907,10 @@ config NET_ACT_BPF module will be called act_bpf. config NET_ACT_CONNMARK - tristate "Netfilter Connection Mark Retriever" - depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES - depends on NF_CONNTRACK && NF_CONNTRACK_MARK - ---help--- + tristate "Netfilter Connection Mark Retriever" + depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES + depends on NF_CONNTRACK && NF_CONNTRACK_MARK + ---help--- Say Y here to allow retrieving of conn mark If unsure, say N. @@ -889,10 +919,10 @@ config NET_ACT_CONNMARK module will be called act_connmark. config NET_ACT_CTINFO - tristate "Netfilter Connection Mark Actions" - depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES - depends on NF_CONNTRACK && NF_CONNTRACK_MARK - help + tristate "Netfilter Connection Mark Actions" + depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES + depends on NF_CONNTRACK && NF_CONNTRACK_MARK + help Say Y here to allow transfer of a connmark stored information. Current actions transfer connmark stored DSCP into ipv4/v6 diffserv and/or to transfer connmark to packet @@ -906,21 +936,21 @@ config NET_ACT_CTINFO module will be called act_ctinfo. config NET_ACT_SKBMOD - tristate "skb data modification action" - depends on NET_CLS_ACT - ---help--- - Say Y here to allow modification of skb data + tristate "skb data modification action" + depends on NET_CLS_ACT + ---help--- + Say Y here to allow modification of skb data - If unsure, say N. + If unsure, say N. - To compile this code as a module, choose M here: the - module will be called act_skbmod. + To compile this code as a module, choose M here: the + module will be called act_skbmod. config NET_ACT_IFE - tristate "Inter-FE action based on IETF ForCES InterFE LFB" - depends on NET_CLS_ACT - select NET_IFE - ---help--- + tristate "Inter-FE action based on IETF ForCES InterFE LFB" + depends on NET_CLS_ACT + select NET_IFE + ---help--- Say Y here to allow for sourcing and terminating metadata For details refer to netdev01 paper: "Distributing Linux Traffic Control Classifier-Action Subsystem" @@ -930,9 +960,9 @@ config NET_ACT_IFE module will be called act_ife. config NET_ACT_TUNNEL_KEY - tristate "IP tunnel metadata manipulation" - depends on NET_CLS_ACT - ---help--- + tristate "IP tunnel metadata manipulation" + depends on NET_CLS_ACT + ---help--- Say Y here to set/release ip tunnel metadata. If unsure, say N. @@ -941,9 +971,9 @@ config NET_ACT_TUNNEL_KEY module will be called act_tunnel_key. config NET_ACT_CT - tristate "connection tracking tc action" - depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT - help + tristate "connection tracking tc action" + depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT + help Say Y here to allow sending the packets to conntrack module. If unsure, say N. @@ -952,16 +982,28 @@ config NET_ACT_CT module will be called act_ct. config NET_IFE_SKBMARK - tristate "Support to encoding decoding skb mark on IFE action" - depends on NET_ACT_IFE + tristate "Support to encoding decoding skb mark on IFE action" + depends on NET_ACT_IFE config NET_IFE_SKBPRIO - tristate "Support to encoding decoding skb prio on IFE action" - depends on NET_ACT_IFE + tristate "Support to encoding decoding skb prio on IFE action" + depends on NET_ACT_IFE config NET_IFE_SKBTCINDEX - tristate "Support to encoding decoding skb tcindex on IFE action" - depends on NET_ACT_IFE + tristate "Support to encoding decoding skb tcindex on IFE action" + depends on NET_ACT_IFE + +config NET_TC_SKB_EXT + bool "TC recirculation support" + depends on NET_CLS_ACT + select SKB_EXTENSIONS + + help + Say Y here to allow tc chain misses to continue in OvS datapath in + the correct recirc_id, and hardware chain misses to continue in + the correct chain in tc software datapath. + + Say N here if you won't be using tc<->ovs offload or tc chains offload. endif # NET_SCHED diff --git a/net/sched/Makefile b/net/sched/Makefile index 415d1e1f237e..31c367a6cd09 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -48,6 +48,7 @@ obj-$(CONFIG_NET_SCH_ATM) += sch_atm.o obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o +obj-$(CONFIG_NET_SCH_ETS) += sch_ets.o obj-$(CONFIG_NET_SCH_MQPRIO) += sch_mqprio.o obj-$(CONFIG_NET_SCH_SKBPRIO) += sch_skbprio.o obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o @@ -58,6 +59,7 @@ obj-$(CONFIG_NET_SCH_CAKE) += sch_cake.o obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o +obj-$(CONFIG_NET_SCH_FQ_PIE) += sch_fq_pie.o obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o obj-$(CONFIG_NET_SCH_TAPRIO) += sch_taprio.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 339712296164..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; @@ -831,12 +853,24 @@ 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_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, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, 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; @@ -846,8 +880,8 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, int err; if (name == NULL) { - err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, NULL, - extack); + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, + tcf_action_policy, extack); if (err < 0) goto err_out; err = -EINVAL; @@ -861,13 +895,6 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, goto err_out; } if (tb[TCA_ACT_COOKIE]) { - int cklen = nla_len(tb[TCA_ACT_COOKIE]); - - if (cklen > TC_COOKIE_MAX_SIZE) { - NL_SET_ERR_MSG(extack, "TC cookie size above the maximum"); - goto err_out; - } - cookie = nla_memdup_cookie(tb); if (!cookie) { NL_SET_ERR_MSG(extack, "No memory to generate TC 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) { @@ -1098,7 +1149,8 @@ static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla, int index; int err; - err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, NULL, extack); + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, + tcf_action_policy, extack); if (err < 0) goto err_out; @@ -1152,7 +1204,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, b = skb_tail_pointer(skb); - err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, NULL, extack); + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, + tcf_action_policy, extack); if (err < 0) goto err_out; @@ -1350,11 +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); @@ -1404,11 +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, @@ -1440,7 +1495,7 @@ static struct nlattr *find_dump_kind(struct nlattr **nla) if (tb[1] == NULL) return NULL; - if (nla_parse_nested_deprecated(tb2, TCA_ACT_MAX, tb[1], NULL, NULL) < 0) + if (nla_parse_nested_deprecated(tb2, TCA_ACT_MAX, tb[1], tcf_action_policy, NULL) < 0) return NULL; kind = tb2[TCA_ACT_KIND]; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index fd1f7e799e23..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; @@ -422,7 +423,7 @@ static __net_init int bpf_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, bpf_net_id); - return tc_action_net_init(tn, &act_bpf_ops); + return tc_action_net_init(net, tn, &act_bpf_ops); } static void __net_exit bpf_exit_net(struct list_head *net_list) diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 32ac04d77a45..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; @@ -231,7 +231,7 @@ static __net_init int connmark_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, connmark_net_id); - return tc_action_net_init(tn, &act_connmark_ops); + return tc_action_net_init(net, tn, &act_connmark_ops); } static void __net_exit connmark_exit_net(struct list_head *net_list) diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 9b9288267a54..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; } @@ -714,7 +714,7 @@ static __net_init int csum_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, csum_net_id); - return tc_action_net_init(tn, &act_csum_ops); + return tc_action_net_init(net, tn, &act_csum_ops); } static void __net_exit csum_exit_net(struct list_head *net_list) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 33a1a7406e87..f685c0d73708 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -24,12 +24,12 @@ #include <uapi/linux/tc_act/tc_ct.h> #include <net/tc_act/tc_ct.h> -#include <linux/netfilter/nf_nat.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> +#include <uapi/linux/netfilter/nf_nat.h> static struct tc_action_ops act_ct_ops; static unsigned int ct_net_id; @@ -312,7 +312,7 @@ static void tcf_ct_act_set_labels(struct nf_conn *ct, u32 *labels_m) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) - size_t labels_sz = FIELD_SIZEOF(struct tcf_ct_params, labels); + size_t labels_sz = sizeof_field(struct tcf_ct_params, labels); if (!memchr_inv(labels_m, 0, labels_sz)) return; @@ -329,6 +329,7 @@ static int tcf_ct_act_nat(struct sk_buff *skb, bool commit) { #if IS_ENABLED(CONFIG_NF_NAT) + int err; enum nf_nat_manip_type maniptype; if (!(ct_action & TCA_CT_ACT_NAT)) @@ -359,7 +360,17 @@ static int tcf_ct_act_nat(struct sk_buff *skb, return NF_ACCEPT; } - return ct_nat_execute(skb, ct, ctinfo, range, maniptype); + err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); + if (err == NF_ACCEPT && + ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC; + + err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); + } + return err; #else return NF_ACCEPT; #endif @@ -465,16 +476,15 @@ 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 +666,7 @@ 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 +698,8 @@ 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 +732,8 @@ 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 +916,7 @@ 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); } @@ -929,7 +936,7 @@ static struct tc_action_ops act_ct_ops = { static __net_init int ct_init_net(struct net *net) { - unsigned int n_bits = FIELD_SIZEOF(struct tcf_ct_params, labels) * 8; + unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8; struct tc_ct_action_net *tn = net_generic(net, ct_net_id); if (nf_connlabels_get(net, n_bits - 1)) { @@ -939,7 +946,7 @@ static __net_init int ct_init_net(struct net *net) tn->labels = true; } - return tc_action_net_init(&tn->tn, &act_ct_ops); + return tc_action_net_init(net, &tn->tn, &act_ct_ops); } static void __net_exit ct_exit_net(struct list_head *net_list) diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 06ef74b74911..19649623493b 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) @@ -360,6 +360,16 @@ static int tcf_ctinfo_search(struct net *net, struct tc_action **a, u32 index) return tcf_idr_search(tn, a, index); } +static void tcf_ctinfo_cleanup(struct tc_action *a) +{ + struct tcf_ctinfo *ci = to_ctinfo(a); + struct tcf_ctinfo_params *cp; + + cp = rcu_dereference_protected(ci->params, 1); + if (cp) + kfree_rcu(cp, rcu); +} + static struct tc_action_ops act_ctinfo_ops = { .kind = "ctinfo", .id = TCA_ID_CTINFO, @@ -367,6 +377,7 @@ static struct tc_action_ops act_ctinfo_ops = { .act = tcf_ctinfo_act, .dump = tcf_ctinfo_dump, .init = tcf_ctinfo_init, + .cleanup= tcf_ctinfo_cleanup, .walk = tcf_ctinfo_walker, .lookup = tcf_ctinfo_search, .size = sizeof(struct tcf_ctinfo), @@ -376,7 +387,7 @@ static __net_init int ctinfo_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, ctinfo_net_id); - return tc_action_net_init(tn, &act_ctinfo_ops); + return tc_action_net_init(net, tn, &act_ctinfo_ops); } static void __net_exit ctinfo_exit_net(struct list_head *net_list) diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 8f0140c6ca58..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); } @@ -278,7 +271,7 @@ static __net_init int gact_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, gact_net_id); - return tc_action_net_init(tn, &act_gact_ops); + return tc_action_net_init(net, tn, &act_gact_ops); } static void __net_exit gact_exit_net(struct list_head *net_list) diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 92ee853d43e6..c1fcd85719d6 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); @@ -536,6 +537,9 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } ife = to_ife(*a); + if (ret == ACT_P_CREATED) + INIT_LIST_HEAD(&ife->metalist); + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; @@ -565,10 +569,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, p->eth_type = ife_type; } - - if (ret == ACT_P_CREATED) - INIT_LIST_HEAD(&ife->metalist); - if (tb[TCA_IFE_METALST]) { err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, tb[TCA_IFE_METALST], NULL, @@ -594,7 +594,7 @@ 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); @@ -890,7 +890,7 @@ static __net_init int ife_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, ife_net_id); - return tc_action_net_init(tn, &act_ife_ops); + return tc_action_net_init(net, tn, &act_ife_ops); } static void __net_exit ife_exit_net(struct list_head *net_list) diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index ce2c30a591d2..400a2cfe8452 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -61,12 +61,13 @@ static int ipt_init_target(struct net *net, struct xt_entry_target *t, return 0; } -static void ipt_destroy_target(struct xt_entry_target *t) +static void ipt_destroy_target(struct xt_entry_target *t, struct net *net) { struct xt_tgdtor_param par = { .target = t->u.kernel.target, .targinfo = t->data, .family = NFPROTO_IPV4, + .net = net, }; if (par.target->destroy != NULL) par.target->destroy(&par); @@ -78,7 +79,7 @@ static void tcf_ipt_release(struct tc_action *a) struct tcf_ipt *ipt = to_ipt(a); if (ipt->tcfi_t) { - ipt_destroy_target(ipt->tcfi_t); + ipt_destroy_target(ipt->tcfi_t, a->idrinfo->net); kfree(ipt->tcfi_t); } kfree(ipt->tcfi_tname); @@ -94,7 +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]; @@ -143,7 +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; @@ -180,7 +181,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, spin_lock_bh(&ipt->tcf_lock); if (ret != ACT_P_CREATED) { - ipt_destroy_target(ipt->tcfi_t); + ipt_destroy_target(ipt->tcfi_t, net); kfree(ipt->tcfi_tname); kfree(ipt->tcfi_t); } @@ -204,19 +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, @@ -350,7 +351,7 @@ static __net_init int ipt_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, ipt_net_id); - return tc_action_net_init(tn, &act_ipt_ops); + return tc_action_net_init(net, tn, &act_ipt_ops); } static void __net_exit ipt_exit_net(struct list_head *net_list) @@ -399,7 +400,7 @@ static __net_init int xt_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, xt_net_id); - return tc_action_net_init(tn, &act_xt_ops); + return tc_action_net_init(net, tn, &act_xt_ops); } static void __net_exit xt_exit_net(struct list_head *net_list) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index be3f88dfc37e..1ad300e6dbc0 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; @@ -219,8 +219,10 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, bool use_reinsert; bool want_ingress; bool is_redirect; + bool expects_nh; int m_eaction; int mac_len; + bool at_nh; rec_level = __this_cpu_inc_return(mirred_rec_level); if (unlikely(rec_level > MIRRED_RECURSION_LIMIT)) { @@ -231,7 +233,7 @@ 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); @@ -261,19 +263,19 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, goto out; } - /* If action's target direction differs than filter's direction, - * and devices expect a mac header on xmit, then mac push/pull is - * needed. - */ want_ingress = tcf_mirred_act_wants_ingress(m_eaction); - if (skb_at_tc_ingress(skb) != want_ingress && m_mac_header_xmit) { - if (!skb_at_tc_ingress(skb)) { - /* caught at egress, act ingress: pull mac */ - mac_len = skb_network_header(skb) - skb_mac_header(skb); + + expects_nh = want_ingress || !m_mac_header_xmit; + at_nh = skb->data == skb_network_header(skb); + if (at_nh != expects_nh) { + mac_len = skb_at_tc_ingress(skb) ? skb->mac_len : + skb_network_header(skb) - skb_mac_header(skb); + if (expects_nh) { + /* target device/action expect data at nh */ skb_pull_rcsum(skb2, mac_len); } else { - /* caught at ingress, act egress: push mac */ - skb_push_rcsum(skb2, skb->mac_len); + /* target device/action expect data at mac */ + skb_push_rcsum(skb2, mac_len); } } @@ -289,8 +291,8 @@ 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 +305,7 @@ 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 +320,7 @@ 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); } @@ -408,25 +407,31 @@ static struct notifier_block mirred_device_notifier = { .notifier_call = mirred_device_event, }; -static struct net_device *tcf_mirred_get_dev(const struct tc_action *a) +static void tcf_mirred_dev_put(void *priv) +{ + struct net_device *dev = priv; + + dev_put(dev); +} + +static struct net_device * +tcf_mirred_get_dev(const struct tc_action *a, + tc_action_priv_destructor *destructor) { struct tcf_mirred *m = to_mirred(a); struct net_device *dev; rcu_read_lock(); dev = rcu_dereference(m->tcfm_dev); - if (dev) + if (dev) { dev_hold(dev); + *destructor = tcf_mirred_dev_put; + } rcu_read_unlock(); return dev; } -static void tcf_mirred_put_dev(struct net_device *dev) -{ - dev_put(dev); -} - static size_t tcf_mirred_get_fill_size(const struct tc_action *act) { return nla_total_size(sizeof(struct tc_mirred)); @@ -446,14 +451,13 @@ static struct tc_action_ops act_mirred_ops = { .get_fill_size = tcf_mirred_get_fill_size, .size = sizeof(struct tcf_mirred), .get_dev = tcf_mirred_get_dev, - .put_dev = tcf_mirred_put_dev, }; static __net_init int mirred_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, mirred_net_id); - return tc_action_net_init(tn, &act_mirred_ops); + return tc_action_net_init(net, tn, &act_mirred_ops); } static void __net_exit mirred_exit_net(struct list_head *net_list) @@ -479,7 +483,11 @@ 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 0f299e3b618c..be3f215cd027 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2019 Netronome Systems, Inc. */ +#include <linux/if_arp.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> @@ -55,7 +56,7 @@ 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 +64,12 @@ 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 +77,14 @@ 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, + skb->dev && skb->dev->type == ARPHRD_ETHER)) 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, + skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; break; case TCA_MPLS_ACT_MODIFY: @@ -115,7 +122,6 @@ 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 +133,8 @@ 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 +227,7 @@ 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 +265,7 @@ 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) @@ -375,7 +382,7 @@ static __net_init int mpls_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, mpls_net_id); - return tc_action_net_init(tn, &act_mpls_ops); + return tc_action_net_init(net, tn, &act_mpls_ops); } static void __net_exit mpls_exit_net(struct list_head *net_list) diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 7b858c11b1b5..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) + @@ -327,7 +325,7 @@ static __net_init int nat_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, nat_net_id); - return tc_action_net_init(tn, &act_nat_ops); + return tc_action_net_init(net, tn, &act_nat_ops); } static void __net_exit nat_exit_net(struct list_head *net_list) diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 17360c6faeaa..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; @@ -498,7 +497,7 @@ static __net_init int pedit_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, pedit_net_id); - return tc_action_net_init(tn, &act_pedit_ops); + return tc_action_net_init(net, tn, &act_pedit_ops); } static void __net_exit pedit_exit_net(struct list_head *net_list) diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 49cec3e64a4d..8b7a0ac96c51 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -40,12 +40,14 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { [TCA_POLICE_PEAKRATE] = { .len = TC_RTAB_SIZE }, [TCA_POLICE_AVRATE] = { .type = NLA_U32 }, [TCA_POLICE_RESULT] = { .type = NLA_U32 }, + [TCA_POLICE_RATE64] = { .type = NLA_U64 }, + [TCA_POLICE_PEAKRATE64] = { .type = NLA_U64 }, }; 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; @@ -58,6 +60,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, struct tcf_police_params *new; bool exists = false; u32 index; + u64 rate64, prate64; if (nla == NULL) return -EINVAL; @@ -84,7 +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; @@ -155,14 +158,18 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, } if (R_tab) { new->rate_present = true; - psched_ratecfg_precompute(&new->rate, &R_tab->rate, 0); + rate64 = tb[TCA_POLICE_RATE64] ? + nla_get_u64(tb[TCA_POLICE_RATE64]) : 0; + psched_ratecfg_precompute(&new->rate, &R_tab->rate, rate64); qdisc_put_rtab(R_tab); } else { new->rate_present = false; } if (P_tab) { new->peak_present = true; - psched_ratecfg_precompute(&new->peak, &P_tab->rate, 0); + prate64 = tb[TCA_POLICE_PEAKRATE64] ? + nla_get_u64(tb[TCA_POLICE_PEAKRATE64]) : 0; + psched_ratecfg_precompute(&new->peak, &P_tab->rate, prate64); qdisc_put_rtab(P_tab); } else { new->peak_present = false; @@ -184,9 +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) @@ -287,10 +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); } @@ -313,10 +317,22 @@ static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, lockdep_is_held(&police->tcf_lock)); opt.mtu = p->tcfp_mtu; opt.burst = PSCHED_NS2TICKS(p->tcfp_burst); - if (p->rate_present) + if (p->rate_present) { psched_ratecfg_getrate(&opt.rate, &p->rate); - if (p->peak_present) + if ((police->params->rate.rate_bytes_ps >= (1ULL << 32)) && + nla_put_u64_64bit(skb, TCA_POLICE_RATE64, + police->params->rate.rate_bytes_ps, + TCA_POLICE_PAD)) + goto nla_put_failure; + } + if (p->peak_present) { psched_ratecfg_getrate(&opt.peakrate, &p->peak); + if ((police->params->peak.rate_bytes_ps >= (1ULL << 32)) && + nla_put_u64_64bit(skb, TCA_POLICE_PEAKRATE64, + police->params->peak.rate_bytes_ps, + TCA_POLICE_PAD)) + goto nla_put_failure; + } if (nla_put(skb, TCA_POLICE_TBF, sizeof(opt), &opt)) goto nla_put_failure; if (p->tcfp_result && @@ -326,10 +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); @@ -371,7 +384,7 @@ static __net_init int police_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, police_net_id); - return tc_action_net_init(tn, &act_police_ops); + return tc_action_net_init(net, tn, &act_police_ops); } static void __net_exit police_exit_net(struct list_head *net_list) diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 595308d60133..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; @@ -102,13 +102,17 @@ 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_INIT_POINTER(s->psample_group, psample_group); + 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; s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]); } spin_unlock_bh(&s->tcf_lock); + + if (psample_group) + psample_group_put(psample_group); if (goto_ch) tcf_chain_put_by_act(goto_ch); @@ -142,6 +146,7 @@ static bool tcf_sample_dev_ok_push(struct net_device *dev) case ARPHRD_TUNNEL6: case ARPHRD_SIT: case ARPHRD_IPGRE: + case ARPHRD_IP6GRE: case ARPHRD_VOID: case ARPHRD_NONE: return false; @@ -248,6 +253,32 @@ static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index) return tcf_idr_search(tn, a, index); } +static void tcf_psample_group_put(void *priv) +{ + struct psample_group *group = priv; + + psample_group_put(group); +} + +static struct psample_group * +tcf_sample_get_group(const struct tc_action *a, + tc_action_priv_destructor *destructor) +{ + struct tcf_sample *s = to_sample(a); + struct psample_group *group; + + spin_lock_bh(&s->tcf_lock); + group = rcu_dereference_protected(s->psample_group, + lockdep_is_held(&s->tcf_lock)); + if (group) { + psample_group_take(group); + *destructor = tcf_psample_group_put; + } + spin_unlock_bh(&s->tcf_lock); + + return group; +} + static struct tc_action_ops act_sample_ops = { .kind = "sample", .id = TCA_ID_SAMPLE, @@ -258,6 +289,7 @@ static struct tc_action_ops act_sample_ops = { .cleanup = tcf_sample_cleanup, .walk = tcf_sample_walker, .lookup = tcf_sample_search, + .get_psample_group = tcf_sample_get_group, .size = sizeof(struct tcf_sample), }; @@ -265,7 +297,7 @@ static __net_init int sample_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, sample_net_id); - return tc_action_net_init(tn, &act_sample_ops); + return tc_action_net_init(net, tn, &act_sample_ops); } static void __net_exit sample_exit_net(struct list_head *net_list) diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 33aefa25b545..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; @@ -232,7 +233,7 @@ static __net_init int simp_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, simp_net_id); - return tc_action_net_init(tn, &act_simp_ops); + return tc_action_net_init(net, tn, &act_simp_ops); } static void __net_exit simp_exit_net(struct list_head *net_list) diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 37dced00b63d..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); @@ -336,7 +336,7 @@ static __net_init int skbedit_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); - return tc_action_net_init(tn, &act_skbedit_ops); + return tc_action_net_init(net, tn, &act_skbedit_ops); } static void __net_exit skbedit_exit_net(struct list_head *net_list) diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 7da3518e18ef..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; @@ -287,7 +287,7 @@ static __net_init int skbmod_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); - return tc_action_net_init(tn, &act_skbmod_ops); + return tc_action_net_init(net, tn, &act_skbmod_ops); } static void __net_exit skbmod_exit_net(struct list_head *net_list) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 6d0debdc9b97..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); @@ -600,7 +806,7 @@ static __net_init int tunnel_key_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); - return tc_action_net_init(tn, &act_tunnel_key_ops); + return tc_action_net_init(net, tn, &act_tunnel_key_ops); } static void __net_exit tunnel_key_exit_net(struct list_head *net_list) diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index a3c9eea1ee8a..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) @@ -301,6 +302,16 @@ static int tcf_vlan_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } +static void tcf_vlan_stats_update(struct tc_action *a, u64 bytes, u32 packets, + u64 lastuse, bool hw) +{ + struct tcf_vlan *v = to_vlan(a); + struct tcf_t *tm = &v->tcf_tm; + + tcf_action_update_stats(a, bytes, packets, false, hw); + tm->lastuse = max_t(u64, tm->lastuse, lastuse); +} + static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, vlan_net_id); @@ -325,6 +336,7 @@ static struct tc_action_ops act_vlan_ops = { .init = tcf_vlan_init, .cleanup = tcf_vlan_cleanup, .walk = tcf_vlan_walker, + .stats_update = tcf_vlan_stats_update, .get_fill_size = tcf_vlan_get_fill_size, .lookup = tcf_vlan_search, .size = sizeof(struct tcf_vlan), @@ -334,7 +346,7 @@ static __net_init int vlan_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, vlan_net_id); - return tc_action_net_init(tn, &act_vlan_ops); + return tc_action_net_init(net, tn, &act_vlan_ops); } static void __net_exit vlan_exit_net(struct list_head *net_list) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index efd3cfb80a2a..c2cdd0fc2e70 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> @@ -36,6 +37,8 @@ #include <net/tc_act/tc_sample.h> #include <net/tc_act/tc_skbedit.h> #include <net/tc_act/tc_ct.h> +#include <net/tc_act/tc_mpls.h> +#include <net/flow_offload.h> extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; @@ -45,6 +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) @@ -160,11 +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. @@ -221,9 +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); @@ -233,36 +305,15 @@ 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); -} - -static int walker_check_empty(struct tcf_proto *tp, void *fh, - struct tcf_walker *arg) -{ - if (fh) { - arg->nonempty = true; - return -1; - } - return 0; + tcf_proto_destroy(tp, rtnl_held, true, extack); } -static bool tcf_proto_is_empty(struct tcf_proto *tp, bool rtnl_held) +static bool tcf_proto_check_delete(struct tcf_proto *tp) { - struct tcf_walker walker = { .fn = walker_check_empty, }; + if (tp->ops->delete_empty) + return tp->ops->delete_empty(tp); - if (tp->ops->walk) { - tp->ops->walk(tp, &walker, rtnl_held); - return !walker.nonempty; - } - return true; -} - -static bool tcf_proto_check_delete(struct tcf_proto *tp, bool rtnl_held) -{ - spin_lock(&tp->lock); - if (tcf_proto_is_empty(tp, rtnl_held)) - tp->deleting = true; - spin_unlock(&tp->lock); + tp->deleting = true; return tp->deleting; } @@ -357,6 +408,7 @@ 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); } @@ -532,6 +584,12 @@ 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; @@ -544,235 +602,87 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held) } } -static struct tcf_block *tc_dev_ingress_block(struct net_device *dev) -{ - const struct Qdisc_class_ops *cops; - struct Qdisc *qdisc; - - if (!dev_ingress_queue(dev)) - return NULL; - - qdisc = dev_ingress_queue(dev)->qdisc_sleeping; - if (!qdisc) - return NULL; - - cops = qdisc->ops->cl_ops; - if (!cops) - return NULL; - - if (!cops->tcf_block) - return NULL; - - return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL); -} - -static struct rhashtable indr_setup_block_ht; - -struct tc_indr_block_dev { - struct rhash_head ht_node; - struct net_device *dev; - unsigned int refcnt; - struct list_head cb_list; - struct tcf_block *block; -}; - -struct tc_indr_block_cb { - struct list_head list; - void *cb_priv; - tc_indr_block_bind_cb_t *cb; - void *cb_ident; -}; - -static const struct rhashtable_params tc_indr_setup_block_ht_params = { - .key_offset = offsetof(struct tc_indr_block_dev, dev), - .head_offset = offsetof(struct tc_indr_block_dev, ht_node), - .key_len = sizeof(struct net_device *), -}; - -static struct tc_indr_block_dev * -tc_indr_block_dev_lookup(struct net_device *dev) -{ - return rhashtable_lookup_fast(&indr_setup_block_ht, &dev, - tc_indr_setup_block_ht_params); -} - -static struct tc_indr_block_dev *tc_indr_block_dev_get(struct net_device *dev) -{ - struct tc_indr_block_dev *indr_dev; - - indr_dev = tc_indr_block_dev_lookup(dev); - if (indr_dev) - goto inc_ref; - - indr_dev = kzalloc(sizeof(*indr_dev), GFP_KERNEL); - if (!indr_dev) - return NULL; - - INIT_LIST_HEAD(&indr_dev->cb_list); - indr_dev->dev = dev; - indr_dev->block = tc_dev_ingress_block(dev); - if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node, - tc_indr_setup_block_ht_params)) { - kfree(indr_dev); - return NULL; - } - -inc_ref: - indr_dev->refcnt++; - return indr_dev; -} - -static void tc_indr_block_dev_put(struct tc_indr_block_dev *indr_dev) -{ - if (--indr_dev->refcnt) - return; - - rhashtable_remove_fast(&indr_setup_block_ht, &indr_dev->ht_node, - tc_indr_setup_block_ht_params); - kfree(indr_dev); -} - -static struct tc_indr_block_cb * -tc_indr_block_cb_lookup(struct tc_indr_block_dev *indr_dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - - list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) - if (indr_block_cb->cb == cb && - indr_block_cb->cb_ident == cb_ident) - return indr_block_cb; - return NULL; -} - -static struct tc_indr_block_cb * -tc_indr_block_cb_add(struct tc_indr_block_dev *indr_dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - - indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident); - if (indr_block_cb) - return ERR_PTR(-EEXIST); - - indr_block_cb = kzalloc(sizeof(*indr_block_cb), GFP_KERNEL); - if (!indr_block_cb) - return ERR_PTR(-ENOMEM); - - indr_block_cb->cb_priv = cb_priv; - indr_block_cb->cb = cb; - indr_block_cb->cb_ident = cb_ident; - list_add(&indr_block_cb->list, &indr_dev->cb_list); - - return indr_block_cb; -} - -static void tc_indr_block_cb_del(struct tc_indr_block_cb *indr_block_cb) -{ - list_del(&indr_block_cb->list); - kfree(indr_block_cb); -} - static int tcf_block_setup(struct tcf_block *block, struct flow_block_offload *bo); -static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev, - struct tc_indr_block_cb *indr_block_cb, - enum flow_block_command command) +static void tc_indr_block_cmd(struct net_device *dev, struct tcf_block *block, + flow_indr_block_bind_cb_t *cb, void *cb_priv, + enum flow_block_command command, bool ingress) { struct flow_block_offload bo = { .command = command, - .binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS, - .net = dev_net(indr_dev->dev), - .block_shared = tcf_block_non_null_shared(indr_dev->block), + .binder_type = ingress ? + FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS : + FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS, + .net = dev_net(dev), + .block_shared = tcf_block_non_null_shared(block), }; INIT_LIST_HEAD(&bo.cb_list); - if (!indr_dev->block) + if (!block) return; - bo.block = &indr_dev->block->flow_block; + bo.block = &block->flow_block; + + down_write(&block->cb_lock); + cb(dev, cb_priv, TC_SETUP_BLOCK, &bo); - indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, - &bo); - tcf_block_setup(indr_dev->block, &bo); + tcf_block_setup(block, &bo); + up_write(&block->cb_lock); } -int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) +static struct tcf_block *tc_dev_block(struct net_device *dev, bool ingress) { - struct tc_indr_block_cb *indr_block_cb; - struct tc_indr_block_dev *indr_dev; - int err; + const struct Qdisc_class_ops *cops; + const struct Qdisc_ops *ops; + struct Qdisc *qdisc; - indr_dev = tc_indr_block_dev_get(dev); - if (!indr_dev) - return -ENOMEM; + if (!dev_ingress_queue(dev)) + return NULL; - indr_block_cb = tc_indr_block_cb_add(indr_dev, cb_priv, cb, cb_ident); - err = PTR_ERR_OR_ZERO(indr_block_cb); - if (err) - goto err_dev_put; + qdisc = dev_ingress_queue(dev)->qdisc_sleeping; + if (!qdisc) + return NULL; - tc_indr_block_ing_cmd(indr_dev, indr_block_cb, FLOW_BLOCK_BIND); - return 0; + ops = qdisc->ops; + if (!ops) + return NULL; -err_dev_put: - tc_indr_block_dev_put(indr_dev); - return err; -} -EXPORT_SYMBOL_GPL(__tc_indr_block_cb_register); + if (!ingress && !strcmp("ingress", ops->id)) + return NULL; -int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - int err; + cops = ops->cl_ops; + if (!cops) + return NULL; - rtnl_lock(); - err = __tc_indr_block_cb_register(dev, cb_priv, cb, cb_ident); - rtnl_unlock(); + if (!cops->tcf_block) + return NULL; - return err; + return cops->tcf_block(qdisc, + ingress ? TC_H_MIN_INGRESS : TC_H_MIN_EGRESS, + NULL); } -EXPORT_SYMBOL_GPL(tc_indr_block_cb_register); -void __tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) +static void tc_indr_block_get_and_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command) { - struct tc_indr_block_cb *indr_block_cb; - struct tc_indr_block_dev *indr_dev; - - indr_dev = tc_indr_block_dev_lookup(dev); - if (!indr_dev) - return; + struct tcf_block *block; - indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident); - if (!indr_block_cb) - return; + block = tc_dev_block(dev, true); + tc_indr_block_cmd(dev, block, cb, cb_priv, command, true); - /* Send unbind message if required to free any block cbs. */ - tc_indr_block_ing_cmd(indr_dev, indr_block_cb, FLOW_BLOCK_UNBIND); - tc_indr_block_cb_del(indr_block_cb); - tc_indr_block_dev_put(indr_dev); -} -EXPORT_SYMBOL_GPL(__tc_indr_block_cb_unregister); - -void tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - rtnl_lock(); - __tc_indr_block_cb_unregister(dev, cb, cb_ident); - rtnl_unlock(); + block = tc_dev_block(dev, false); + tc_indr_block_cmd(dev, block, cb, cb_priv, command, false); } -EXPORT_SYMBOL_GPL(tc_indr_block_cb_unregister); -static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev, +static void tc_indr_block_call(struct tcf_block *block, + struct net_device *dev, struct tcf_block_ext_info *ei, enum flow_block_command command, struct netlink_ext_ack *extack) { - struct tc_indr_block_cb *indr_block_cb; - struct tc_indr_block_dev *indr_dev; struct flow_block_offload bo = { .command = command, .binder_type = ei->binder_type, @@ -783,22 +693,13 @@ static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev, }; INIT_LIST_HEAD(&bo.cb_list); - indr_dev = tc_indr_block_dev_lookup(dev); - if (!indr_dev) - return; - - indr_dev->block = command == FLOW_BLOCK_BIND ? block : NULL; - - list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) - indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, - &bo); - + flow_indr_block_call(dev, &bo, command); tcf_block_setup(block, &bo); } static bool tcf_block_offload_in_use(struct tcf_block *block) { - return block->offloadcnt; + return atomic_read(&block->offloadcnt); } static int tcf_block_offload_cmd(struct tcf_block *block, @@ -832,6 +733,7 @@ static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, struct net_device *dev = q->dev_queue->dev; int err; + down_write(&block->cb_lock); if (!dev->netdev_ops->ndo_setup_tc) goto no_offload_dev_inc; @@ -840,24 +742,31 @@ static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, */ if (!tc_can_offload(dev) && tcf_block_offload_in_use(block)) { NL_SET_ERR_MSG(extack, "Bind to offloaded block failed as dev has offload disabled"); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto err_unlock; } err = tcf_block_offload_cmd(block, dev, ei, FLOW_BLOCK_BIND, extack); if (err == -EOPNOTSUPP) goto no_offload_dev_inc; if (err) - return err; + goto err_unlock; tc_indr_block_call(block, dev, ei, FLOW_BLOCK_BIND, extack); + up_write(&block->cb_lock); return 0; no_offload_dev_inc: - if (tcf_block_offload_in_use(block)) - return -EOPNOTSUPP; + if (tcf_block_offload_in_use(block)) { + err = -EOPNOTSUPP; + goto err_unlock; + } + err = 0; block->nooffloaddevcnt++; tc_indr_block_call(block, dev, ei, FLOW_BLOCK_BIND, extack); - return 0; +err_unlock: + up_write(&block->cb_lock); + return err; } static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q, @@ -866,6 +775,7 @@ static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q, struct net_device *dev = q->dev_queue->dev; int err; + down_write(&block->cb_lock); tc_indr_block_call(block, dev, ei, FLOW_BLOCK_UNBIND, NULL); if (!dev->netdev_ops->ndo_setup_tc) @@ -873,10 +783,12 @@ static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q, err = tcf_block_offload_cmd(block, dev, ei, FLOW_BLOCK_UNBIND, NULL); if (err == -EOPNOTSUPP) goto no_offload_dev_dec; + up_write(&block->cb_lock); return; no_offload_dev_dec: WARN_ON(block->nooffloaddevcnt-- == 0); + up_write(&block->cb_lock); } static int @@ -991,6 +903,8 @@ 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); INIT_LIST_HEAD(&block->owner_list); @@ -1526,6 +1440,8 @@ tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb, struct tcf_proto *tp, *tp_prev; int err; + lockdep_assert_held(&block->cb_lock); + for (chain = __tcf_get_next_chain(block, NULL); chain; chain_prev = chain, @@ -1564,6 +1480,8 @@ static int tcf_block_bind(struct tcf_block *block, struct flow_block_cb *block_cb, *next; int err, i = 0; + lockdep_assert_held(&block->cb_lock); + list_for_each_entry(block_cb, &bo->cb_list, list) { err = tcf_block_playback_offloads(block, block_cb->cb, block_cb->cb_priv, true, @@ -1571,6 +1489,8 @@ static int tcf_block_bind(struct tcf_block *block, bo->extack); if (err) goto err_unroll; + if (!bo->unlocked_driver_cb) + block->lockeddevcnt++; i++; } @@ -1586,6 +1506,8 @@ err_unroll: block_cb->cb_priv, false, tcf_block_offload_in_use(block), NULL); + if (!bo->unlocked_driver_cb) + block->lockeddevcnt--; } flow_block_cb_free(block_cb); } @@ -1598,6 +1520,8 @@ static void tcf_block_unbind(struct tcf_block *block, { struct flow_block_cb *block_cb, *next; + lockdep_assert_held(&block->cb_lock); + list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { tcf_block_playback_offloads(block, block_cb->cb, block_cb->cb_priv, false, @@ -1605,6 +1529,8 @@ static void tcf_block_unbind(struct tcf_block *block, NULL); list_del(&block_cb->list); flow_block_cb_free(block_cb); + if (!bo->unlocked_driver_cb) + block->lockeddevcnt--; } } @@ -1659,6 +1585,18 @@ reclassify: goto reset; } else if (unlikely(TC_ACT_EXT_CMP(err, TC_ACT_GOTO_CHAIN))) { first_tp = res->goto_tp; + +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + { + struct tc_skb_ext *ext; + + ext = skb_ext_add(skb, TC_SKB_EXT); + if (WARN_ON_ONCE(!ext)) + return TC_ACT_SHOT; + + ext->chain = err & TC_ACT_EXT_VAL_MASK; + } +#endif goto reset; } #endif @@ -1743,6 +1681,12 @@ 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) @@ -1750,10 +1694,10 @@ 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); } @@ -1786,11 +1730,12 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, * concurrently. * Mark tp for deletion if it is empty. */ - if (!tp_iter || !tcf_proto_check_delete(tp, rtnl_held)) { + if (!tp_iter || !tcf_proto_check_delete(tp)) { mutex_unlock(&chain->filter_chain_lock); 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); @@ -1976,6 +1921,7 @@ 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; @@ -2032,13 +1978,19 @@ 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(); } @@ -2103,9 +2055,8 @@ replay: &chain_info)); mutex_unlock(&chain->filter_chain_lock); - tp_new = tcf_proto_create(nla_data(tca[TCA_KIND]), - protocol, prio, chain, rtnl_held, - extack); + tp_new = tcf_proto_create(name, protocol, prio, chain, + rtnl_held, extack); if (IS_ERR(tp_new)) { err = PTR_ERR(tp_new); goto errout_tp; @@ -2196,6 +2147,7 @@ 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; @@ -2235,13 +2187,18 @@ 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(); } @@ -2297,6 +2254,7 @@ 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); @@ -2349,6 +2307,7 @@ 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; @@ -2385,12 +2344,17 @@ 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(); } @@ -2749,13 +2713,19 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, struct netlink_ext_ack *extack) { const struct tcf_proto_ops *ops; + char name[IFNAMSIZ]; void *tmplt_priv; /* If kind is not set, user did not specify template. */ if (!tca[TCA_KIND]) return 0; - ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), true, extack); + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC chain template name too long"); + return -EINVAL; + } + + ops = tcf_proto_lookup_ops(name, true, extack); if (IS_ERR(ops)) return PTR_ERR(ops); if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) { @@ -3027,8 +2997,10 @@ out: void tcf_exts_destroy(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT - tcf_action_destroy(exts->actions, TCA_ACT_UNBIND); - kfree(exts->actions); + if (exts->actions) { + tcf_action_destroy(exts->actions, TCA_ACT_UNBIND); + kfree(exts->actions); + } exts->nr_actions = 0; #endif } @@ -3151,17 +3123,61 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts) } EXPORT_SYMBOL(tcf_exts_dump_stats); -int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, - void *type_data, bool err_stop) +static void tcf_block_offload_inc(struct tcf_block *block, u32 *flags) +{ + if (*flags & TCA_CLS_FLAGS_IN_HW) + return; + *flags |= TCA_CLS_FLAGS_IN_HW; + atomic_inc(&block->offloadcnt); +} + +static void tcf_block_offload_dec(struct tcf_block *block, u32 *flags) +{ + if (!(*flags & TCA_CLS_FLAGS_IN_HW)) + return; + *flags &= ~TCA_CLS_FLAGS_IN_HW; + atomic_dec(&block->offloadcnt); +} + +static void tc_cls_offload_cnt_update(struct tcf_block *block, + struct tcf_proto *tp, u32 *cnt, + u32 *flags, u32 diff, bool add) +{ + lockdep_assert_held(&block->cb_lock); + + spin_lock(&tp->lock); + if (add) { + if (!*cnt) + tcf_block_offload_inc(block, flags); + *cnt += diff; + } else { + *cnt -= diff; + if (!*cnt) + tcf_block_offload_dec(block, flags); + } + spin_unlock(&tp->lock); +} + +static void +tc_cls_offload_cnt_reset(struct tcf_block *block, struct tcf_proto *tp, + u32 *cnt, u32 *flags) +{ + lockdep_assert_held(&block->cb_lock); + + spin_lock(&tp->lock); + tcf_block_offload_dec(block, flags); + *cnt = 0; + spin_unlock(&tp->lock); +} + +static int +__tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, + void *type_data, bool err_stop) { struct flow_block_cb *block_cb; int ok_count = 0; int err; - /* Make sure all netdevs sharing this block are offload-capable. */ - if (block->nooffloaddevcnt && err_stop) - return -EOPNOTSUPP; - list_for_each_entry(block_cb, &block->flow_block.cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err) { @@ -3173,17 +3189,261 @@ int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, } return ok_count; } + +int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, + void *type_data, bool err_stop, bool rtnl_held) +{ + bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held; + int ok_count; + +retry: + if (take_rtnl) + rtnl_lock(); + down_read(&block->cb_lock); + /* Need to obtain rtnl lock if block is bound to devs that require it. + * In block bind code cb_lock is obtained while holding rtnl, so we must + * obtain the locks in same order here. + */ + if (!rtnl_held && !take_rtnl && block->lockeddevcnt) { + up_read(&block->cb_lock); + take_rtnl = true; + goto retry; + } + + ok_count = __tc_setup_cb_call(block, type, type_data, err_stop); + + up_read(&block->cb_lock); + if (take_rtnl) + rtnl_unlock(); + return ok_count; +} EXPORT_SYMBOL(tc_setup_cb_call); +/* Non-destructive filter add. If filter that wasn't already in hardware is + * successfully offloaded, increment block offloads counter. On failure, + * previously offloaded filter is considered to be intact and offloads counter + * is not decremented. + */ + +int tc_setup_cb_add(struct tcf_block *block, struct tcf_proto *tp, + enum tc_setup_type type, void *type_data, bool err_stop, + u32 *flags, unsigned int *in_hw_count, bool rtnl_held) +{ + bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held; + int ok_count; + +retry: + if (take_rtnl) + rtnl_lock(); + down_read(&block->cb_lock); + /* Need to obtain rtnl lock if block is bound to devs that require it. + * In block bind code cb_lock is obtained while holding rtnl, so we must + * obtain the locks in same order here. + */ + if (!rtnl_held && !take_rtnl && block->lockeddevcnt) { + up_read(&block->cb_lock); + take_rtnl = true; + goto retry; + } + + /* Make sure all netdevs sharing this block are offload-capable. */ + if (block->nooffloaddevcnt && err_stop) { + ok_count = -EOPNOTSUPP; + goto err_unlock; + } + + ok_count = __tc_setup_cb_call(block, type, type_data, err_stop); + if (ok_count < 0) + goto err_unlock; + + if (tp->ops->hw_add) + tp->ops->hw_add(tp, type_data); + if (ok_count > 0) + tc_cls_offload_cnt_update(block, tp, in_hw_count, flags, + ok_count, true); +err_unlock: + up_read(&block->cb_lock); + if (take_rtnl) + rtnl_unlock(); + return ok_count < 0 ? ok_count : 0; +} +EXPORT_SYMBOL(tc_setup_cb_add); + +/* Destructive filter replace. If filter that wasn't already in hardware is + * successfully offloaded, increment block offload counter. On failure, + * previously offloaded filter is considered to be destroyed and offload counter + * is decremented. + */ + +int tc_setup_cb_replace(struct tcf_block *block, struct tcf_proto *tp, + enum tc_setup_type type, void *type_data, bool err_stop, + u32 *old_flags, unsigned int *old_in_hw_count, + u32 *new_flags, unsigned int *new_in_hw_count, + bool rtnl_held) +{ + bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held; + int ok_count; + +retry: + if (take_rtnl) + rtnl_lock(); + down_read(&block->cb_lock); + /* Need to obtain rtnl lock if block is bound to devs that require it. + * In block bind code cb_lock is obtained while holding rtnl, so we must + * obtain the locks in same order here. + */ + if (!rtnl_held && !take_rtnl && block->lockeddevcnt) { + up_read(&block->cb_lock); + take_rtnl = true; + goto retry; + } + + /* Make sure all netdevs sharing this block are offload-capable. */ + if (block->nooffloaddevcnt && err_stop) { + ok_count = -EOPNOTSUPP; + goto err_unlock; + } + + tc_cls_offload_cnt_reset(block, tp, old_in_hw_count, old_flags); + if (tp->ops->hw_del) + tp->ops->hw_del(tp, type_data); + + ok_count = __tc_setup_cb_call(block, type, type_data, err_stop); + if (ok_count < 0) + goto err_unlock; + + if (tp->ops->hw_add) + tp->ops->hw_add(tp, type_data); + if (ok_count > 0) + tc_cls_offload_cnt_update(block, tp, new_in_hw_count, + new_flags, ok_count, true); +err_unlock: + up_read(&block->cb_lock); + if (take_rtnl) + rtnl_unlock(); + return ok_count < 0 ? ok_count : 0; +} +EXPORT_SYMBOL(tc_setup_cb_replace); + +/* Destroy filter and decrement block offload counter, if filter was previously + * offloaded. + */ + +int tc_setup_cb_destroy(struct tcf_block *block, struct tcf_proto *tp, + enum tc_setup_type type, void *type_data, bool err_stop, + u32 *flags, unsigned int *in_hw_count, bool rtnl_held) +{ + bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held; + int ok_count; + +retry: + if (take_rtnl) + rtnl_lock(); + down_read(&block->cb_lock); + /* Need to obtain rtnl lock if block is bound to devs that require it. + * In block bind code cb_lock is obtained while holding rtnl, so we must + * obtain the locks in same order here. + */ + if (!rtnl_held && !take_rtnl && block->lockeddevcnt) { + up_read(&block->cb_lock); + take_rtnl = true; + goto retry; + } + + ok_count = __tc_setup_cb_call(block, type, type_data, err_stop); + + tc_cls_offload_cnt_reset(block, tp, in_hw_count, flags); + if (tp->ops->hw_del) + tp->ops->hw_del(tp, type_data); + + up_read(&block->cb_lock); + if (take_rtnl) + rtnl_unlock(); + return ok_count < 0 ? ok_count : 0; +} +EXPORT_SYMBOL(tc_setup_cb_destroy); + +int tc_setup_cb_reoffload(struct tcf_block *block, struct tcf_proto *tp, + bool add, flow_setup_cb_t *cb, + enum tc_setup_type type, void *type_data, + void *cb_priv, u32 *flags, unsigned int *in_hw_count) +{ + int err = cb(type, type_data, cb_priv); + + if (err) { + if (add && tc_skip_sw(*flags)) + return err; + } else { + tc_cls_offload_cnt_update(block, tp, in_hw_count, flags, 1, + add); + } + + return 0; +} +EXPORT_SYMBOL(tc_setup_cb_reoffload); + +void tc_cleanup_flow_action(struct flow_action *flow_action) +{ + struct flow_action_entry *entry; + int i; + + flow_action_for_each(i, entry, flow_action) + if (entry->destructor) + entry->destructor(entry->destructor_priv); +} +EXPORT_SYMBOL(tc_cleanup_flow_action); + +static void tcf_mirred_get_dev(struct flow_action_entry *entry, + const struct tc_action *act) +{ +#ifdef CONFIG_NET_CLS_ACT + entry->dev = act->ops->get_dev(act, &entry->destructor); + if (!entry->dev) + return; + entry->destructor_priv = entry->dev; +#endif +} + +static void tcf_tunnel_encap_put_tunnel(void *priv) +{ + struct ip_tunnel_info *tunnel = priv; + + kfree(tunnel); +} + +static int tcf_tunnel_encap_get_tunnel(struct flow_action_entry *entry, + const struct tc_action *act) +{ + entry->tunnel = tcf_tunnel_info_copy(act); + if (!entry->tunnel) + return -ENOMEM; + entry->destructor = tcf_tunnel_encap_put_tunnel; + entry->destructor_priv = entry->tunnel; + return 0; +} + +static void tcf_sample_get_group(struct flow_action_entry *entry, + const struct tc_action *act) +{ +#ifdef CONFIG_NET_CLS_ACT + entry->sample.psample_group = + act->ops->get_psample_group(act, &entry->destructor); + entry->destructor_priv = entry->sample.psample_group; +#endif +} + int tc_setup_flow_action(struct flow_action *flow_action, - const struct tcf_exts *exts) + const struct tcf_exts *exts, bool rtnl_held) { const struct tc_action *act; - int i, j, k; + int i, j, k, err = 0; if (!exts) return 0; + if (!rtnl_held) + rtnl_lock(); + j = 0; tcf_exts_for_each_action(i, act, exts) { struct flow_action_entry *entry; @@ -3200,10 +3460,16 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->chain_index = tcf_gact_goto_chain_index(act); } else if (is_tcf_mirred_egress_redirect(act)) { entry->id = FLOW_ACTION_REDIRECT; - entry->dev = tcf_mirred_dev(act); + tcf_mirred_get_dev(entry, act); } else if (is_tcf_mirred_egress_mirror(act)) { entry->id = FLOW_ACTION_MIRRED; - entry->dev = tcf_mirred_dev(act); + tcf_mirred_get_dev(entry, act); + } else if (is_tcf_mirred_ingress_redirect(act)) { + entry->id = FLOW_ACTION_REDIRECT_INGRESS; + tcf_mirred_get_dev(entry, act); + } else if (is_tcf_mirred_ingress_mirror(act)) { + entry->id = FLOW_ACTION_MIRRED_INGRESS; + tcf_mirred_get_dev(entry, act); } else if (is_tcf_vlan(act)) { switch (tcf_vlan_action(act)) { case TCA_VLAN_ACT_PUSH: @@ -3222,11 +3488,14 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->vlan.prio = tcf_vlan_push_prio(act); break; default: + err = -EOPNOTSUPP; goto err_out; } } else if (is_tcf_tunnel_set(act)) { entry->id = FLOW_ACTION_TUNNEL_ENCAP; - entry->tunnel = tcf_tunnel_info(act); + err = tcf_tunnel_encap_get_tunnel(entry, act); + if (err) + goto err_out; } else if (is_tcf_tunnel_release(act)) { entry->id = FLOW_ACTION_TUNNEL_DECAP; } else if (is_tcf_pedit(act)) { @@ -3239,6 +3508,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->id = FLOW_ACTION_ADD; break; default: + err = -EOPNOTSUPP; goto err_out; } entry->mangle.htype = tcf_pedit_htype(act, k); @@ -3255,11 +3525,10 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->mark = tcf_skbedit_mark(act); } else if (is_tcf_sample(act)) { entry->id = FLOW_ACTION_SAMPLE; - entry->sample.psample_group = - tcf_sample_psample_group(act); entry->sample.trunc_size = tcf_sample_trunc_size(act); entry->sample.truncate = tcf_sample_truncate(act); entry->sample.rate = tcf_sample_rate(act); + tcf_sample_get_group(entry, act); } else if (is_tcf_police(act)) { entry->id = FLOW_ACTION_POLICE; entry->police.burst = tcf_police_tcfp_burst(act); @@ -3269,16 +3538,50 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->id = FLOW_ACTION_CT; entry->ct.action = tcf_ct_action(act); entry->ct.zone = tcf_ct_zone(act); + } else if (is_tcf_mpls(act)) { + switch (tcf_mpls_action(act)) { + case TCA_MPLS_ACT_PUSH: + entry->id = FLOW_ACTION_MPLS_PUSH; + entry->mpls_push.proto = tcf_mpls_proto(act); + entry->mpls_push.label = tcf_mpls_label(act); + entry->mpls_push.tc = tcf_mpls_tc(act); + entry->mpls_push.bos = tcf_mpls_bos(act); + entry->mpls_push.ttl = tcf_mpls_ttl(act); + break; + case TCA_MPLS_ACT_POP: + entry->id = FLOW_ACTION_MPLS_POP; + entry->mpls_pop.proto = tcf_mpls_proto(act); + break; + case TCA_MPLS_ACT_MODIFY: + entry->id = FLOW_ACTION_MPLS_MANGLE; + entry->mpls_mangle.label = tcf_mpls_label(act); + entry->mpls_mangle.tc = tcf_mpls_tc(act); + entry->mpls_mangle.bos = tcf_mpls_bos(act); + entry->mpls_mangle.ttl = tcf_mpls_ttl(act); + break; + default: + goto err_out; + } + } else if (is_tcf_skbedit_ptype(act)) { + entry->id = FLOW_ACTION_PTYPE; + entry->ptype = tcf_skbedit_ptype(act); } else { + err = -EOPNOTSUPP; goto err_out; } if (!is_tcf_pedit(act)) j++; } - return 0; + err_out: - return -EOPNOTSUPP; + if (!rtnl_held) + rtnl_unlock(); + + if (err) + tc_cleanup_flow_action(flow_action); + + return err; } EXPORT_SYMBOL(tc_setup_flow_action); @@ -3321,6 +3624,11 @@ static struct pernet_operations tcf_net_ops = { .size = sizeof(struct tcf_net), }; +static struct flow_indr_block_entry block_entry = { + .cb = tc_indr_block_get_and_cmd, + .list = LIST_HEAD_INIT(block_entry.list), +}; + static int __init tc_filter_init(void) { int err; @@ -3333,10 +3641,7 @@ static int __init tc_filter_init(void) if (err) goto err_register_pernet_subsys; - err = rhashtable_init(&indr_setup_block_ht, - &tc_indr_setup_block_ht_params); - if (err) - goto err_rhash_setup_block_ht; + flow_indr_add_block_cb(&block_entry); rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, RTNL_FLAG_DOIT_UNLOCKED); @@ -3351,8 +3656,6 @@ static int __init tc_filter_init(void) return 0; -err_rhash_setup_block_ht: - unregister_pernet_subsys(&tcf_net_ops); err_register_pernet_subsys: destroy_workqueue(tc_filter_wq); return err; diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 4aafbe3d435c..f256a7c69093 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -263,12 +263,17 @@ skip: } } -static void basic_bind_class(void *fh, u32 classid, unsigned long cl) +static void basic_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct basic_filter *f = fh; - if (f && f->res.classid == classid) - f->res.class = cl; + if (f && f->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &f->res, base); + else + __tcf_unbind_filter(q, &f->res); + } } static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh, diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 3f7a9c02b70c..6e3e63db0e01 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -162,18 +162,24 @@ 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) - tcf_block_offload_dec(block, &oldprog->gen_flags); + 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 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); - err = tc_setup_cb_call(block, TC_SETUP_CLSBPF, &cls_bpf, skip_sw); - if (prog) { - if (err < 0) { - cls_bpf_offload_cmd(tp, oldprog, prog, extack); - return err; - } else if (err > 0) { - prog->in_hw_count = err; - tcf_block_offload_inc(block, &prog->gen_flags); - } + if (prog && err) { + cls_bpf_offload_cmd(tp, oldprog, prog, extack); + return err; } if (prog && skip_sw && !(prog->gen_flags & TCA_CLS_FLAGS_IN_HW)) @@ -230,7 +236,7 @@ static void cls_bpf_offload_update_stats(struct tcf_proto *tp, cls_bpf.name = prog->bpf_name; cls_bpf.exts_integrated = prog->exts_integrated; - tc_setup_cb_call(block, TC_SETUP_CLSBPF, &cls_bpf, false); + tc_setup_cb_call(block, TC_SETUP_CLSBPF, &cls_bpf, false, true); } static int cls_bpf_init(struct tcf_proto *tp) @@ -625,12 +631,17 @@ nla_put_failure: return -1; } -static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl) +static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl, + void *q, unsigned long base) { struct cls_bpf_prog *prog = fh; - if (prog && prog->res.classid == classid) - prog->res.class = cl; + if (prog && prog->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &prog->res, base); + else + __tcf_unbind_filter(q, &prog->res); + } } static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg, @@ -673,15 +684,11 @@ static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb cls_bpf.name = prog->bpf_name; cls_bpf.exts_integrated = prog->exts_integrated; - err = cb(TC_SETUP_CLSBPF, &cls_bpf, cb_priv); - if (err) { - if (add && tc_skip_sw(prog->gen_flags)) - return err; - continue; - } - - tc_cls_offload_cnt_update(block, &prog->in_hw_count, - &prog->gen_flags, add); + err = tc_setup_cb_reoffload(block, tp, add, cb, TC_SETUP_CLSBPF, + &cls_bpf, cb_priv, &prog->gen_flags, + &prog->in_hw_count); + if (err) + return err; } return 0; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 054123742e32..7e54d2ab5254 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> @@ -54,8 +56,13 @@ struct fl_flow_key { struct flow_dissector_key_ip ip; struct flow_dissector_key_ip enc_ip; struct flow_dissector_key_enc_opts enc_opts; - struct flow_dissector_key_ports tp_min; - struct flow_dissector_key_ports tp_max; + union { + struct flow_dissector_key_ports tp; + struct { + struct flow_dissector_key_ports tp_min; + struct flow_dissector_key_ports tp_max; + }; + } tp_range; struct flow_dissector_key_ct ct; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ @@ -198,19 +205,19 @@ static bool fl_range_port_dst_cmp(struct cls_fl_filter *filter, { __be16 min_mask, max_mask, min_val, max_val; - min_mask = htons(filter->mask->key.tp_min.dst); - max_mask = htons(filter->mask->key.tp_max.dst); - min_val = htons(filter->key.tp_min.dst); - max_val = htons(filter->key.tp_max.dst); + min_mask = htons(filter->mask->key.tp_range.tp_min.dst); + max_mask = htons(filter->mask->key.tp_range.tp_max.dst); + min_val = htons(filter->key.tp_range.tp_min.dst); + max_val = htons(filter->key.tp_range.tp_max.dst); if (min_mask && max_mask) { - if (htons(key->tp.dst) < min_val || - htons(key->tp.dst) > max_val) + if (htons(key->tp_range.tp.dst) < min_val || + htons(key->tp_range.tp.dst) > max_val) return false; /* skb does not have min and max values */ - mkey->tp_min.dst = filter->mkey.tp_min.dst; - mkey->tp_max.dst = filter->mkey.tp_max.dst; + mkey->tp_range.tp_min.dst = filter->mkey.tp_range.tp_min.dst; + mkey->tp_range.tp_max.dst = filter->mkey.tp_range.tp_max.dst; } return true; } @@ -221,19 +228,19 @@ static bool fl_range_port_src_cmp(struct cls_fl_filter *filter, { __be16 min_mask, max_mask, min_val, max_val; - min_mask = htons(filter->mask->key.tp_min.src); - max_mask = htons(filter->mask->key.tp_max.src); - min_val = htons(filter->key.tp_min.src); - max_val = htons(filter->key.tp_max.src); + min_mask = htons(filter->mask->key.tp_range.tp_min.src); + max_mask = htons(filter->mask->key.tp_range.tp_max.src); + min_val = htons(filter->key.tp_range.tp_min.src); + max_val = htons(filter->key.tp_range.tp_max.src); if (min_mask && max_mask) { - if (htons(key->tp.src) < min_val || - htons(key->tp.src) > max_val) + if (htons(key->tp_range.tp.src) < min_val || + htons(key->tp_range.tp.src) > max_val) return false; /* skb does not have min and max values */ - mkey->tp_min.src = filter->mkey.tp_min.src; - mkey->tp_max.src = filter->mkey.tp_max.src; + mkey->tp_range.tp_min.src = filter->mkey.tp_range.tp_min.src; + mkey->tp_range.tp_max.src = filter->mkey.tp_range.tp_max.src; } return true; } @@ -412,41 +419,27 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f, struct tcf_block *block = tp->chain->block; struct flow_cls_offload cls_flower = {}; - if (!rtnl_held) - rtnl_lock(); - tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); cls_flower.command = FLOW_CLS_DESTROY; cls_flower.cookie = (unsigned long) f; - tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); - spin_lock(&tp->lock); - list_del_init(&f->hw_list); - tcf_block_offload_dec(block, &f->flags); - spin_unlock(&tp->lock); + tc_setup_cb_destroy(block, tp, TC_SETUP_CLSFLOWER, &cls_flower, false, + &f->flags, &f->in_hw_count, rtnl_held); - if (!rtnl_held) - rtnl_unlock(); } static int fl_hw_replace_filter(struct tcf_proto *tp, struct cls_fl_filter *f, bool rtnl_held, struct netlink_ext_ack *extack) { - struct cls_fl_head *head = fl_head_dereference(tp); struct tcf_block *block = tp->chain->block; struct flow_cls_offload cls_flower = {}; bool skip_sw = tc_skip_sw(f->flags); int err = 0; - if (!rtnl_held) - rtnl_lock(); - cls_flower.rule = flow_rule_alloc(tcf_exts_num_actions(&f->exts)); - if (!cls_flower.rule) { - err = -ENOMEM; - goto errout; - } + if (!cls_flower.rule) + return -ENOMEM; tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); cls_flower.command = FLOW_CLS_REPLACE; @@ -456,43 +449,31 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, cls_flower.rule->match.key = &f->mkey; cls_flower.classid = f->res.classid; - err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts); + err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts, + rtnl_held); if (err) { kfree(cls_flower.rule); - if (skip_sw) + if (skip_sw) { NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action"); - else - err = 0; - goto errout; + return err; + } + return 0; } - err = tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, skip_sw); + err = tc_setup_cb_add(block, tp, TC_SETUP_CLSFLOWER, &cls_flower, + skip_sw, &f->flags, &f->in_hw_count, rtnl_held); + tc_cleanup_flow_action(&cls_flower.rule->action); kfree(cls_flower.rule); - if (err < 0) { - fl_hw_destroy_filter(tp, f, true, NULL); - goto errout; - } else if (err > 0) { - f->in_hw_count = err; - err = 0; - spin_lock(&tp->lock); - tcf_block_offload_inc(block, &f->flags); - spin_unlock(&tp->lock); - } - - if (skip_sw && !(f->flags & TCA_CLS_FLAGS_IN_HW)) { - err = -EINVAL; - goto errout; + if (err) { + fl_hw_destroy_filter(tp, f, rtnl_held, NULL); + return err; } - spin_lock(&tp->lock); - list_add(&f->hw_list, &head->hw_filters); - spin_unlock(&tp->lock); -errout: - if (!rtnl_held) - rtnl_unlock(); + if (skip_sw && !(f->flags & TCA_CLS_FLAGS_IN_HW)) + return -EINVAL; - return err; + return 0; } static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f, @@ -501,22 +482,17 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f, struct tcf_block *block = tp->chain->block; struct flow_cls_offload cls_flower = {}; - if (!rtnl_held) - rtnl_lock(); - tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, NULL); cls_flower.command = FLOW_CLS_STATS; cls_flower.cookie = (unsigned long) f; cls_flower.classid = f->res.classid; - tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); + tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false, + rtnl_held); tcf_exts_stats_update(&f->exts, cls_flower.stats.bytes, cls_flower.stats.pkts, cls_flower.stats.lastused); - - if (!rtnl_held) - rtnl_unlock(); } static void __fl_put(struct cls_fl_filter *f) @@ -715,11 +691,16 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { .len = 128 / BITS_PER_BYTE }, [TCA_FLOWER_KEY_CT_LABELS_MASK] = { .type = NLA_BINARY, .len = 128 / BITS_PER_BYTE }, + [TCA_FLOWER_FLAGS] = { .type = NLA_U32 }, }; 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 @@ -730,6 +711,19 @@ 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) @@ -746,23 +740,25 @@ static void fl_set_key_val(struct nlattr **tb, static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask) { - fl_set_key_val(tb, &key->tp_min.dst, - TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_min.dst, - TCA_FLOWER_UNSPEC, sizeof(key->tp_min.dst)); - fl_set_key_val(tb, &key->tp_max.dst, - TCA_FLOWER_KEY_PORT_DST_MAX, &mask->tp_max.dst, - TCA_FLOWER_UNSPEC, sizeof(key->tp_max.dst)); - fl_set_key_val(tb, &key->tp_min.src, - TCA_FLOWER_KEY_PORT_SRC_MIN, &mask->tp_min.src, - TCA_FLOWER_UNSPEC, sizeof(key->tp_min.src)); - fl_set_key_val(tb, &key->tp_max.src, - TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_max.src, - TCA_FLOWER_UNSPEC, sizeof(key->tp_max.src)); - - if ((mask->tp_min.dst && mask->tp_max.dst && - htons(key->tp_max.dst) <= htons(key->tp_min.dst)) || - (mask->tp_min.src && mask->tp_max.src && - htons(key->tp_max.src) <= htons(key->tp_min.src))) + fl_set_key_val(tb, &key->tp_range.tp_min.dst, + TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_range.tp_min.dst, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_min.dst)); + fl_set_key_val(tb, &key->tp_range.tp_max.dst, + TCA_FLOWER_KEY_PORT_DST_MAX, &mask->tp_range.tp_max.dst, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.dst)); + fl_set_key_val(tb, &key->tp_range.tp_min.src, + TCA_FLOWER_KEY_PORT_SRC_MIN, &mask->tp_range.tp_min.src, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_min.src)); + fl_set_key_val(tb, &key->tp_range.tp_max.src, + TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_range.tp_max.src, + TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.src)); + + if ((mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst && + htons(key->tp_range.tp_max.dst) <= + htons(key->tp_range.tp_min.dst)) || + (mask->tp_range.tp_min.src && mask->tp_range.tp_max.src && + htons(key->tp_range.tp_max.src) <= + htons(key->tp_range.tp_min.src))) return -EINVAL; return 0; @@ -959,6 +955,105 @@ 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) @@ -989,6 +1084,11 @@ 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, @@ -1017,6 +1117,72 @@ 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; @@ -1316,7 +1482,7 @@ static int fl_init_mask_hashtable(struct fl_flow_mask *mask) } #define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member) -#define FL_KEY_MEMBER_SIZE(member) FIELD_SIZEOF(struct fl_flow_key, member) +#define FL_KEY_MEMBER_SIZE(member) sizeof_field(struct fl_flow_key, member) #define FL_KEY_IS_MASKED(mask, member) \ memchr_inv(((char *)mask) + FL_KEY_MEMBER_OFFSET(member), \ @@ -1351,9 +1517,10 @@ static void fl_init_dissector(struct flow_dissector *dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6); - if (FL_KEY_IS_MASKED(mask, tp) || - FL_KEY_IS_MASKED(mask, tp_min) || FL_KEY_IS_MASKED(mask, tp_max)) - FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_PORTS, tp); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_PORTS, tp); + FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_PORTS_RANGE, tp_range); FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_IP, ip); FL_KEY_SET_IF_MASKED(mask, keys, cnt, @@ -1402,8 +1569,10 @@ static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head, fl_mask_copy(newmask, mask); - if ((newmask->key.tp_min.dst && newmask->key.tp_max.dst) || - (newmask->key.tp_min.src && newmask->key.tp_max.src)) + if ((newmask->key.tp_range.tp_min.dst && + newmask->key.tp_range.tp_max.dst) || + (newmask->key.tp_range.tp_min.src && + newmask->key.tp_range.tp_max.src)) newmask->flags |= TCA_FLOWER_MASK_FLAGS_RANGE; err = fl_init_mask_hashtable(newmask); @@ -1831,7 +2000,8 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, cls_flower.rule->match.mask = &f->mask->key; cls_flower.rule->match.key = &f->mkey; - err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts); + err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts, + true); if (err) { kfree(cls_flower.rule); if (tc_skip_sw(f->flags)) { @@ -1844,21 +2014,17 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, cls_flower.classid = f->res.classid; - err = cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv); + err = tc_setup_cb_reoffload(block, tp, add, cb, + TC_SETUP_CLSFLOWER, &cls_flower, + cb_priv, &f->flags, + &f->in_hw_count); + tc_cleanup_flow_action(&cls_flower.rule->action); kfree(cls_flower.rule); if (err) { - if (add && tc_skip_sw(f->flags)) { - __fl_put(f); - return err; - } - goto next_flow; + __fl_put(f); + return err; } - - spin_lock(&tp->lock); - tc_cls_offload_cnt_update(block, &f->in_hw_count, &f->flags, - add); - spin_unlock(&tp->lock); next_flow: __fl_put(f); } @@ -1866,6 +2032,30 @@ next_flow: return 0; } +static void fl_hw_add(struct tcf_proto *tp, void *type_data) +{ + struct flow_cls_offload *cls_flower = type_data; + struct cls_fl_filter *f = + (struct cls_fl_filter *) cls_flower->cookie; + struct cls_fl_head *head = fl_head_dereference(tp); + + spin_lock(&tp->lock); + list_add(&f->hw_list, &head->hw_filters); + spin_unlock(&tp->lock); +} + +static void fl_hw_del(struct tcf_proto *tp, void *type_data) +{ + struct flow_cls_offload *cls_flower = type_data; + struct cls_fl_filter *f = + (struct cls_fl_filter *) cls_flower->cookie; + + spin_lock(&tp->lock); + if (!list_empty(&f->hw_list)) + list_del_init(&f->hw_list); + spin_unlock(&tp->lock); +} + static int fl_hw_create_tmplt(struct tcf_chain *chain, struct fl_flow_tmplt *tmplt) { @@ -1886,7 +2076,7 @@ static int fl_hw_create_tmplt(struct tcf_chain *chain, /* We don't care if driver (any of them) fails to handle this * call. It serves just as a hint for it. */ - tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); + tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false, true); kfree(cls_flower.rule); return 0; @@ -1902,7 +2092,7 @@ static void fl_hw_destroy_tmplt(struct tcf_chain *chain, cls_flower.command = FLOW_CLS_TMPLT_DESTROY; cls_flower.cookie = (unsigned long) tmplt; - tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); + tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false, true); } static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain, @@ -1980,18 +2170,22 @@ static int fl_dump_key_val(struct sk_buff *skb, static int fl_dump_key_port_range(struct sk_buff *skb, struct fl_flow_key *key, struct fl_flow_key *mask) { - if (fl_dump_key_val(skb, &key->tp_min.dst, TCA_FLOWER_KEY_PORT_DST_MIN, - &mask->tp_min.dst, TCA_FLOWER_UNSPEC, - sizeof(key->tp_min.dst)) || - fl_dump_key_val(skb, &key->tp_max.dst, TCA_FLOWER_KEY_PORT_DST_MAX, - &mask->tp_max.dst, TCA_FLOWER_UNSPEC, - sizeof(key->tp_max.dst)) || - fl_dump_key_val(skb, &key->tp_min.src, TCA_FLOWER_KEY_PORT_SRC_MIN, - &mask->tp_min.src, TCA_FLOWER_UNSPEC, - sizeof(key->tp_min.src)) || - fl_dump_key_val(skb, &key->tp_max.src, TCA_FLOWER_KEY_PORT_SRC_MAX, - &mask->tp_max.src, TCA_FLOWER_UNSPEC, - sizeof(key->tp_max.src))) + if (fl_dump_key_val(skb, &key->tp_range.tp_min.dst, + TCA_FLOWER_KEY_PORT_DST_MIN, + &mask->tp_range.tp_min.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_min.dst)) || + fl_dump_key_val(skb, &key->tp_range.tp_max.dst, + TCA_FLOWER_KEY_PORT_DST_MAX, + &mask->tp_range.tp_max.dst, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_max.dst)) || + fl_dump_key_val(skb, &key->tp_range.tp_min.src, + TCA_FLOWER_KEY_PORT_SRC_MIN, + &mask->tp_range.tp_min.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_min.src)) || + fl_dump_key_val(skb, &key->tp_range.tp_max.src, + TCA_FLOWER_KEY_PORT_SRC_MAX, + &mask->tp_range.tp_max.src, TCA_FLOWER_UNSPEC, + sizeof(key->tp_range.tp_max.src))) return -1; return 0; @@ -2145,6 +2339,61 @@ 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) @@ -2198,6 +2447,16 @@ 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; } @@ -2507,12 +2766,28 @@ nla_put_failure: return -EMSGSIZE; } -static void fl_bind_class(void *fh, u32 classid, unsigned long cl) +static void fl_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct cls_fl_filter *f = fh; - if (f && f->res.classid == classid) - f->res.class = cl; + if (f && f->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &f->res, base); + else + __tcf_unbind_filter(q, &f->res); + } +} + +static bool fl_delete_empty(struct tcf_proto *tp) +{ + struct cls_fl_head *head = fl_head_dereference(tp); + + spin_lock(&tp->lock); + tp->deleting = idr_is_empty(&head->handle_idr); + spin_unlock(&tp->lock); + + return tp->deleting; } static struct tcf_proto_ops cls_fl_ops __read_mostly = { @@ -2524,8 +2799,11 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = { .put = fl_put, .change = fl_change, .delete = fl_delete, + .delete_empty = fl_delete_empty, .walk = fl_walk, .reoffload = fl_reoffload, + .hw_add = fl_hw_add, + .hw_del = fl_hw_del, .dump = fl_dump, .bind_class = fl_bind_class, .tmplt_create = fl_tmplt_create, diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index c9496c920d6f..ec945294626a 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -419,12 +419,17 @@ nla_put_failure: return -1; } -static void fw_bind_class(void *fh, u32 classid, unsigned long cl) +static void fw_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct fw_filter *f = fh; - if (f && f->res.classid == classid) - f->res.class = cl; + if (f && f->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &f->res, base); + else + __tcf_unbind_filter(q, &f->res); + } } static struct tcf_proto_ops cls_fw_ops __read_mostly = { diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 455ea2793f9b..610a0b728161 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -75,8 +75,8 @@ static void mall_destroy_hw_filter(struct tcf_proto *tp, cls_mall.command = TC_CLSMATCHALL_DESTROY; cls_mall.cookie = cookie; - tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, false); - tcf_block_offload_dec(block, &head->flags); + tc_setup_cb_destroy(block, tp, TC_SETUP_CLSMATCHALL, &cls_mall, false, + &head->flags, &head->in_hw_count, true); } static int mall_replace_hw_filter(struct tcf_proto *tp, @@ -97,7 +97,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, cls_mall.command = TC_CLSMATCHALL_REPLACE; cls_mall.cookie = cookie; - err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts); + err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts, true); if (err) { kfree(cls_mall.rule); mall_destroy_hw_filter(tp, head, cookie, NULL); @@ -109,15 +109,14 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, return err; } - err = tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, skip_sw); + err = tc_setup_cb_add(block, tp, TC_SETUP_CLSMATCHALL, &cls_mall, + skip_sw, &head->flags, &head->in_hw_count, true); + tc_cleanup_flow_action(&cls_mall.rule->action); kfree(cls_mall.rule); - if (err < 0) { + if (err) { mall_destroy_hw_filter(tp, head, cookie, NULL); return err; - } else if (err > 0) { - head->in_hw_count = err; - tcf_block_offload_inc(block, &head->flags); } if (skip_sw && !(head->flags & TCA_CLS_FLAGS_IN_HW)) @@ -158,6 +157,7 @@ static void *mall_get(struct tcf_proto *tp, u32 handle) static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = { [TCA_MATCHALL_UNSPEC] = { .type = NLA_UNSPEC }, [TCA_MATCHALL_CLASSID] = { .type = NLA_U32 }, + [TCA_MATCHALL_FLAGS] = { .type = NLA_U32 }, }; static int mall_set_parms(struct net *net, struct tcf_proto *tp, @@ -302,7 +302,7 @@ static int mall_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, TC_CLSMATCHALL_REPLACE : TC_CLSMATCHALL_DESTROY; cls_mall.cookie = (unsigned long)head; - err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts); + err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts, true); if (err) { kfree(cls_mall.rule); if (add && tc_skip_sw(head->flags)) { @@ -312,16 +312,14 @@ static int mall_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, return 0; } - err = cb(TC_SETUP_CLSMATCHALL, &cls_mall, cb_priv); + err = tc_setup_cb_reoffload(block, tp, add, cb, TC_SETUP_CLSMATCHALL, + &cls_mall, cb_priv, &head->flags, + &head->in_hw_count); + tc_cleanup_flow_action(&cls_mall.rule->action); kfree(cls_mall.rule); - if (err) { - if (add && tc_skip_sw(head->flags)) - return err; - return 0; - } - - tc_cls_offload_cnt_update(block, &head->in_hw_count, &head->flags, add); + if (err) + return err; return 0; } @@ -337,7 +335,7 @@ static void mall_stats_hw_filter(struct tcf_proto *tp, cls_mall.command = TC_CLSMATCHALL_STATS; cls_mall.cookie = cookie; - tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, false); + tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, false, true); tcf_exts_stats_update(&head->exts, cls_mall.stats.bytes, cls_mall.stats.pkts, cls_mall.stats.lastused); @@ -396,12 +394,17 @@ nla_put_failure: return -1; } -static void mall_bind_class(void *fh, u32 classid, unsigned long cl) +static void mall_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct cls_mall_head *head = fh; - if (head && head->res.classid == classid) - head->res.class = cl; + if (head && head->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &head->res, base); + else + __tcf_unbind_filter(q, &head->res); + } } static struct tcf_proto_ops cls_mall_ops __read_mostly = { diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 2d9e0b4484ea..6f8786b06bde 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -641,12 +641,17 @@ nla_put_failure: return -1; } -static void route4_bind_class(void *fh, u32 classid, unsigned long cl) +static void route4_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct route4_filter *f = fh; - if (f && f->res.classid == classid) - f->res.class = cl; + if (f && f->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &f->res, base); + else + __tcf_unbind_filter(q, &f->res); + } } static struct tcf_proto_ops cls_route4_ops __read_mostly = { diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 2f3c03b25d5d..d36949d9382c 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -463,10 +463,8 @@ static u32 gen_tunnel(struct rsvp_head *data) static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = { [TCA_RSVP_CLASSID] = { .type = NLA_U32 }, - [TCA_RSVP_DST] = { .type = NLA_BINARY, - .len = RSVP_DST_LEN * sizeof(u32) }, - [TCA_RSVP_SRC] = { .type = NLA_BINARY, - .len = RSVP_DST_LEN * sizeof(u32) }, + [TCA_RSVP_DST] = { .len = RSVP_DST_LEN * sizeof(u32) }, + [TCA_RSVP_SRC] = { .len = RSVP_DST_LEN * sizeof(u32) }, [TCA_RSVP_PINFO] = { .len = sizeof(struct tc_rsvp_pinfo) }, }; @@ -738,12 +736,17 @@ nla_put_failure: return -1; } -static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl) +static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct rsvp_filter *f = fh; - if (f && f->res.classid == classid) - f->res.class = cl; + if (f && f->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &f->res, base); + else + __tcf_unbind_filter(q, &f->res); + } } static struct tcf_proto_ops RSVP_OPS __read_mostly = { diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index e573e5a5c794..09b7dc5fe7e0 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -333,12 +333,31 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, cp->fall_through = p->fall_through; cp->tp = tp; + if (tb[TCA_TCINDEX_HASH]) + cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); + + if (tb[TCA_TCINDEX_MASK]) + cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]); + + if (tb[TCA_TCINDEX_SHIFT]) + cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]); + + if (!cp->hash) { + /* Hash not specified, use perfect hash if the upper limit + * of the hashing index is below the threshold. + */ + if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD) + cp->hash = (cp->mask >> cp->shift) + 1; + else + cp->hash = DEFAULT_HASH_SIZE; + } + if (p->perfect) { int i; if (tcindex_alloc_perfect_hash(net, cp) < 0) goto errout; - for (i = 0; i < cp->hash; i++) + for (i = 0; i < min(cp->hash, p->hash); i++) cp->perfect[i].res = p->perfect[i].res; balloc = 1; } @@ -346,19 +365,10 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = tcindex_filter_result_init(&new_filter_result, net); if (err < 0) - goto errout1; + goto errout_alloc; if (old_r) cr = r->res; - if (tb[TCA_TCINDEX_HASH]) - cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); - - if (tb[TCA_TCINDEX_MASK]) - cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]); - - if (tb[TCA_TCINDEX_SHIFT]) - cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]); - err = -EBUSY; /* Hash already allocated, make sure that we still meet the @@ -376,16 +386,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, if (tb[TCA_TCINDEX_FALL_THROUGH]) cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]); - if (!cp->hash) { - /* Hash not specified, use perfect hash if the upper limit - * of the hashing index is below the threshold. - */ - if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD) - cp->hash = (cp->mask >> cp->shift) + 1; - else - cp->hash = DEFAULT_HASH_SIZE; - } - if (!cp->perfect && !cp->h) cp->alloc_hash = cp->hash; @@ -484,7 +484,6 @@ errout_alloc: tcindex_free_perfect_hash(cp); else if (balloc == 2) kfree(cp->h); -errout1: tcf_exts_destroy(&new_filter_result.exts); errout: kfree(cp); @@ -654,12 +653,17 @@ nla_put_failure: return -1; } -static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl) +static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl, + void *q, unsigned long base) { struct tcindex_filter_result *r = fh; - if (r && r->res.classid == classid) - r->res.class = cl; + if (r && r->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &r->res, base); + else + __tcf_unbind_filter(q, &r->res); + } } static struct tcf_proto_ops cls_tcindex_ops __read_mostly = { diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 8614088edd1b..e15ff335953d 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -480,7 +480,7 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, cls_u32.hnode.handle = h->handle; cls_u32.hnode.prio = h->prio; - tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, false); + tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, false, true); } static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, @@ -498,7 +498,7 @@ static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, cls_u32.hnode.handle = h->handle; cls_u32.hnode.prio = h->prio; - err = tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, skip_sw); + err = tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, skip_sw, true); if (err < 0) { u32_clear_hw_hnode(tp, h, NULL); return err; @@ -522,8 +522,8 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, cls_u32.command = TC_CLSU32_DELETE_KNODE; cls_u32.knode.handle = n->handle; - tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, false); - tcf_block_offload_dec(block, &n->flags); + tc_setup_cb_destroy(block, tp, TC_SETUP_CLSU32, &cls_u32, false, + &n->flags, &n->in_hw_count, true); } static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, @@ -552,13 +552,11 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, if (n->ht_down) cls_u32.knode.link_handle = ht->handle; - err = tc_setup_cb_call(block, TC_SETUP_CLSU32, &cls_u32, skip_sw); - if (err < 0) { + err = tc_setup_cb_add(block, tp, TC_SETUP_CLSU32, &cls_u32, skip_sw, + &n->flags, &n->in_hw_count, true); + if (err) { u32_remove_hw_knode(tp, n, NULL); return err; - } else if (err > 0) { - n->in_hw_count = err; - tcf_block_offload_inc(block, &n->flags); } if (skip_sw && !(n->flags & TCA_CLS_FLAGS_IN_HW)) @@ -1201,14 +1199,11 @@ static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n, cls_u32.knode.link_handle = ht->handle; } - err = cb(TC_SETUP_CLSU32, &cls_u32, cb_priv); - if (err) { - if (add && tc_skip_sw(n->flags)) - return err; - return 0; - } - - tc_cls_offload_cnt_update(block, &n->in_hw_count, &n->flags, add); + err = tc_setup_cb_reoffload(block, tp, add, cb, TC_SETUP_CLSU32, + &cls_u32, cb_priv, &n->flags, + &n->in_hw_count); + if (err) + return err; return 0; } @@ -1260,12 +1255,17 @@ static int u32_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, return 0; } -static void u32_bind_class(void *fh, u32 classid, unsigned long cl) +static void u32_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct tc_u_knode *n = fh; - if (n && n->res.classid == classid) - n->res.class = cl; + if (n && n->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &n->res, base); + else + __tcf_unbind_filter(q, &n->res); + } } static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh, 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/ematch.c b/net/sched/ematch.c index 8f2ad706784d..dd3b8c11a2e0 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -238,6 +238,9 @@ static int tcf_em_validate(struct tcf_proto *tp, goto errout; if (em->ops->change) { + err = -EINVAL; + if (em_hdr->flags & TCF_EM_SIMPLE) + goto errout; err = em->ops->change(net, data, data_len, em); if (err < 0) goto errout; @@ -263,12 +266,12 @@ static int tcf_em_validate(struct tcf_proto *tp, } em->data = (unsigned long) v; } + em->datalen = data_len; } } em->matchid = em_hdr->matchid; em->flags = em_hdr->flags; - em->datalen = data_len; em->net = net; err = 0; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 04faee7ccbce..50794125bf02 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1891,8 +1891,9 @@ static int tclass_del_notify(struct net *net, struct tcf_bind_args { struct tcf_walker w; - u32 classid; + unsigned long base; unsigned long cl; + u32 classid; }; static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg) @@ -1903,26 +1904,30 @@ static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg) struct Qdisc *q = tcf_block_q(tp->chain->block); sch_tree_lock(q); - tp->ops->bind_class(n, a->classid, a->cl); + tp->ops->bind_class(n, a->classid, a->cl, q, a->base); sch_tree_unlock(q); } return 0; } -static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, - unsigned long new_cl) +struct tc_bind_class_args { + struct qdisc_walker w; + unsigned long new_cl; + u32 portid; + u32 clid; +}; + +static int tc_bind_class_walker(struct Qdisc *q, unsigned long cl, + struct qdisc_walker *w) { + struct tc_bind_class_args *a = (struct tc_bind_class_args *)w; const struct Qdisc_class_ops *cops = q->ops->cl_ops; struct tcf_block *block; struct tcf_chain *chain; - unsigned long cl; - cl = cops->find(q, portid); - if (!cl) - return; block = cops->tcf_block(q, cl, NULL); if (!block) - return; + return 0; for (chain = tcf_get_next_chain(block, NULL); chain; chain = tcf_get_next_chain(block, chain)) { @@ -1933,11 +1938,29 @@ static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, struct tcf_bind_args arg = {}; arg.w.fn = tcf_node_bind; - arg.classid = clid; - arg.cl = new_cl; + arg.classid = a->clid; + arg.base = cl; + arg.cl = a->new_cl; tp->ops->walk(tp, &arg.w, true); } } + + return 0; +} + +static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, + unsigned long new_cl) +{ + const struct Qdisc_class_ops *cops = q->ops->cl_ops; + struct tc_bind_class_args args = {}; + + if (!cops->tcf_block) + return; + args.portid = portid; + args.clid = clid; + args.new_cl = new_cl; + args.w.fn = tc_bind_class_walker; + q->ops->cl_ops->walk(q, &args.w); } #else diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 53a80bc6b13a..1496e87cd07b 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -173,8 +173,7 @@ struct cake_tin_data { u64 tin_rate_bps; u16 tin_rate_shft; - u16 tin_quantum_prio; - u16 tin_quantum_band; + u16 tin_quantum; s32 tin_deficit; u32 tin_backlog; u32 tin_dropped; @@ -1683,8 +1682,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (IS_ERR_OR_NULL(segs)) return qdisc_drop(skb, sch, to_free); - while (segs) { - nskb = segs->next; + skb_list_walk_safe(segs, segs, nskb) { skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; cobalt_set_enqueue_time(segs, now); @@ -1697,7 +1695,6 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, slen += segs->len; q->buffer_used += segs->truesize; b->packets++; - segs = nskb; } /* stats */ @@ -1769,7 +1766,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, q->avg_window_begin)); u64 b = q->avg_window_bytes * (u64)NSEC_PER_SEC; - do_div(b, window_interval); + b = div64_u64(b, window_interval); q->avg_peak_bandwidth = cake_ewma(q->avg_peak_bandwidth, b, b > q->avg_peak_bandwidth ? 2 : 8); @@ -1919,7 +1916,7 @@ begin: while (b->tin_deficit < 0 || !(b->sparse_flow_count + b->bulk_flow_count)) { if (b->tin_deficit <= 0) - b->tin_deficit += b->tin_quantum_band; + b->tin_deficit += b->tin_quantum; if (b->sparse_flow_count + b->bulk_flow_count) empty = false; @@ -2184,6 +2181,7 @@ static const struct nla_policy cake_policy[TCA_CAKE_MAX + 1] = { [TCA_CAKE_MPU] = { .type = NLA_U32 }, [TCA_CAKE_INGRESS] = { .type = NLA_U32 }, [TCA_CAKE_ACK_FILTER] = { .type = NLA_U32 }, + [TCA_CAKE_SPLIT_GSO] = { .type = NLA_U32 }, [TCA_CAKE_FWMARK] = { .type = NLA_U32 }, }; @@ -2240,8 +2238,7 @@ static int cake_config_besteffort(struct Qdisc *sch) cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); - b->tin_quantum_band = 65535; - b->tin_quantum_prio = 65535; + b->tin_quantum = 65535; return 0; } @@ -2252,8 +2249,7 @@ static int cake_config_precedence(struct Qdisc *sch) struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; - u32 quantum1 = 256; - u32 quantum2 = 256; + u32 quantum = 256; u32 i; q->tin_cnt = 8; @@ -2266,18 +2262,14 @@ static int cake_config_precedence(struct Qdisc *sch) cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); - b->tin_quantum_prio = max_t(u16, 1U, quantum1); - b->tin_quantum_band = max_t(u16, 1U, quantum2); + b->tin_quantum = max_t(u16, 1U, quantum); /* calculate next class's parameters */ rate *= 7; rate >>= 3; - quantum1 *= 3; - quantum1 >>= 1; - - quantum2 *= 7; - quantum2 >>= 3; + quantum *= 7; + quantum >>= 3; } return 0; @@ -2346,8 +2338,7 @@ static int cake_config_diffserv8(struct Qdisc *sch) struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; - u32 quantum1 = 256; - u32 quantum2 = 256; + u32 quantum = 256; u32 i; q->tin_cnt = 8; @@ -2363,18 +2354,14 @@ static int cake_config_diffserv8(struct Qdisc *sch) cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); - b->tin_quantum_prio = max_t(u16, 1U, quantum1); - b->tin_quantum_band = max_t(u16, 1U, quantum2); + b->tin_quantum = max_t(u16, 1U, quantum); /* calculate next class's parameters */ rate *= 7; rate >>= 3; - quantum1 *= 3; - quantum1 >>= 1; - - quantum2 *= 7; - quantum2 >>= 3; + quantum *= 7; + quantum >>= 3; } return 0; @@ -2413,17 +2400,11 @@ static int cake_config_diffserv4(struct Qdisc *sch) cake_set_rate(&q->tins[3], rate >> 2, mtu, us_to_ns(q->target), us_to_ns(q->interval)); - /* priority weights */ - q->tins[0].tin_quantum_prio = quantum; - q->tins[1].tin_quantum_prio = quantum >> 4; - q->tins[2].tin_quantum_prio = quantum << 2; - q->tins[3].tin_quantum_prio = quantum << 4; - /* bandwidth-sharing weights */ - q->tins[0].tin_quantum_band = quantum; - q->tins[1].tin_quantum_band = quantum >> 4; - q->tins[2].tin_quantum_band = quantum >> 1; - q->tins[3].tin_quantum_band = quantum >> 2; + q->tins[0].tin_quantum = quantum; + q->tins[1].tin_quantum = quantum >> 4; + q->tins[2].tin_quantum = quantum >> 1; + q->tins[3].tin_quantum = quantum >> 2; return 0; } @@ -2454,15 +2435,10 @@ static int cake_config_diffserv3(struct Qdisc *sch) cake_set_rate(&q->tins[2], rate >> 2, mtu, us_to_ns(q->target), us_to_ns(q->interval)); - /* priority weights */ - q->tins[0].tin_quantum_prio = quantum; - q->tins[1].tin_quantum_prio = quantum >> 4; - q->tins[2].tin_quantum_prio = quantum << 4; - /* bandwidth-sharing weights */ - q->tins[0].tin_quantum_band = quantum; - q->tins[1].tin_quantum_band = quantum >> 4; - q->tins[2].tin_quantum_band = quantum >> 2; + q->tins[0].tin_quantum = quantum; + q->tins[1].tin_quantum = quantum >> 4; + q->tins[2].tin_quantum = quantum >> 2; return 0; } 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 732e109c3055..b2905b03a432 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -181,11 +181,6 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) s64 credits; int len; - if (atomic64_read(&q->port_rate) == -1) { - WARN_ONCE(1, "cbs: dequeue() called with unknown port rate."); - return NULL; - } - if (q->credits < 0) { credits = timediff_to_credits(now - q->last, q->idleslope); @@ -303,11 +298,19 @@ static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q, static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q) { struct ethtool_link_ksettings ecmd; - int port_rate = -1; + int speed = SPEED_10; + int port_rate; + int err; + + err = __ethtool_get_link_ksettings(dev, &ecmd); + if (err < 0) + goto skip; + + if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN) + speed = ecmd.base.speed; - if (!__ethtool_get_link_ksettings(dev, &ecmd) && - ecmd.base.speed != SPEED_UNKNOWN) - port_rate = ecmd.base.speed * 1000 * BYTES_PER_KBIT; +skip: + port_rate = speed * 1000 * BYTES_PER_KBIT; atomic64_set(&q->port_rate, port_rate); netdev_dbg(dev, "cbs: set %s's port_rate to: %lld, linkspeed: %d\n", @@ -389,7 +392,6 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt, { struct cbs_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); - int err; if (!opt) { NL_SET_ERR_MSG(extack, "Missing CBS qdisc options which are mandatory"); @@ -401,6 +403,10 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt, if (!q->qdisc) return -ENOMEM; + spin_lock(&cbs_list_lock); + list_add(&q->cbs_list, &cbs_list); + spin_unlock(&cbs_list_lock); + qdisc_hash_add(q->qdisc, false); q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0); @@ -410,17 +416,7 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt, qdisc_watchdog_init(&q->watchdog, sch); - err = cbs_change(sch, opt, extack); - if (err) - return err; - - if (!q->offload) { - spin_lock(&cbs_list_lock); - list_add(&q->cbs_list, &cbs_list); - spin_unlock(&cbs_list_lock); - } - - return 0; + return cbs_change(sch, opt, extack); } static void cbs_destroy(struct Qdisc *sch) @@ -428,15 +424,18 @@ static void cbs_destroy(struct Qdisc *sch) struct cbs_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); - spin_lock(&cbs_list_lock); - list_del(&q->cbs_list); - spin_unlock(&cbs_list_lock); + /* Nothing to do if we couldn't create the underlying qdisc */ + if (!q->qdisc) + return; qdisc_watchdog_cancel(&q->watchdog); cbs_disable_offload(dev, q); - if (q->qdisc) - qdisc_put(q->qdisc); + spin_lock(&cbs_list_lock); + list_del(&q->cbs_list); + spin_unlock(&cbs_list_lock); + + qdisc_put(q->qdisc); } static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index dba70377bbd9..a36974e9c601 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -377,7 +377,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, if (mask != q->tab_mask) { struct sk_buff **ntab; - ntab = kvmalloc_array((mask + 1), sizeof(struct sk_buff *), GFP_KERNEL | __GFP_ZERO); + ntab = kvcalloc(mask + 1, sizeof(struct sk_buff *), GFP_KERNEL); if (!ntab) return -ENOMEM; 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_ets.c b/net/sched/sch_ets.c new file mode 100644 index 000000000000..a87e9159338c --- /dev/null +++ b/net/sched/sch_ets.c @@ -0,0 +1,828 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * net/sched/sch_ets.c Enhanced Transmission Selection scheduler + * + * Description + * ----------- + * + * The Enhanced Transmission Selection scheduler is a classful queuing + * discipline that merges functionality of PRIO and DRR qdiscs in one scheduler. + * ETS makes it easy to configure a set of strict and bandwidth-sharing bands to + * implement the transmission selection described in 802.1Qaz. + * + * Although ETS is technically classful, it's not possible to add and remove + * classes at will. Instead one specifies number of classes, how many are + * PRIO-like and how many DRR-like, and quanta for the latter. + * + * Algorithm + * --------- + * + * The strict classes, if any, are tried for traffic first: first band 0, if it + * has no traffic then band 1, etc. + * + * When there is no traffic in any of the strict queues, the bandwidth-sharing + * ones are tried next. Each band is assigned a deficit counter, initialized to + * "quantum" of that band. ETS maintains a list of active bandwidth-sharing + * bands whose qdiscs are non-empty. A packet is dequeued from the band at the + * head of the list if the packet size is smaller or equal to the deficit + * counter. If the counter is too small, it is increased by "quantum" and the + * scheduler moves on to the next band in the active list. + */ + +#include <linux/module.h> +#include <net/gen_stats.h> +#include <net/netlink.h> +#include <net/pkt_cls.h> +#include <net/pkt_sched.h> +#include <net/sch_generic.h> + +struct ets_class { + struct list_head alist; /* In struct ets_sched.active. */ + struct Qdisc *qdisc; + u32 quantum; + u32 deficit; + struct gnet_stats_basic_packed bstats; + struct gnet_stats_queue qstats; +}; + +struct ets_sched { + struct list_head active; + struct tcf_proto __rcu *filter_list; + struct tcf_block *block; + unsigned int nbands; + unsigned int nstrict; + u8 prio2band[TC_PRIO_MAX + 1]; + struct ets_class classes[TCQ_ETS_MAX_BANDS]; +}; + +static const struct nla_policy ets_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_NBANDS] = { .type = NLA_U8 }, + [TCA_ETS_NSTRICT] = { .type = NLA_U8 }, + [TCA_ETS_QUANTA] = { .type = NLA_NESTED }, + [TCA_ETS_PRIOMAP] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy ets_priomap_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_PRIOMAP_BAND] = { .type = NLA_U8 }, +}; + +static const struct nla_policy ets_quanta_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_QUANTA_BAND] = { .type = NLA_U32 }, +}; + +static const struct nla_policy ets_class_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_QUANTA_BAND] = { .type = NLA_U32 }, +}; + +static int ets_quantum_parse(struct Qdisc *sch, const struct nlattr *attr, + unsigned int *quantum, + struct netlink_ext_ack *extack) +{ + *quantum = nla_get_u32(attr); + if (!*quantum) { + NL_SET_ERR_MSG(extack, "ETS quantum cannot be zero"); + return -EINVAL; + } + return 0; +} + +static struct ets_class * +ets_class_from_arg(struct Qdisc *sch, unsigned long arg) +{ + struct ets_sched *q = qdisc_priv(sch); + + return &q->classes[arg - 1]; +} + +static u32 ets_class_id(struct Qdisc *sch, const struct ets_class *cl) +{ + struct ets_sched *q = qdisc_priv(sch); + int band = cl - q->classes; + + return TC_H_MAKE(sch->handle, band + 1); +} + +static void ets_offload_change(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct ets_sched *q = qdisc_priv(sch); + struct tc_ets_qopt_offload qopt; + unsigned int w_psum_prev = 0; + unsigned int q_psum = 0; + unsigned int q_sum = 0; + unsigned int quantum; + unsigned int w_psum; + unsigned int weight; + unsigned int i; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_ETS_REPLACE; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.replace_params.bands = q->nbands; + qopt.replace_params.qstats = &sch->qstats; + memcpy(&qopt.replace_params.priomap, + q->prio2band, sizeof(q->prio2band)); + + for (i = 0; i < q->nbands; i++) + q_sum += q->classes[i].quantum; + + for (i = 0; i < q->nbands; i++) { + quantum = q->classes[i].quantum; + q_psum += quantum; + w_psum = quantum ? q_psum * 100 / q_sum : 0; + weight = w_psum - w_psum_prev; + w_psum_prev = w_psum; + + qopt.replace_params.quanta[i] = quantum; + qopt.replace_params.weights[i] = weight; + } + + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETS, &qopt); +} + +static void ets_offload_destroy(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_ets_qopt_offload qopt; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_ETS_DESTROY; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETS, &qopt); +} + +static void ets_offload_graft(struct Qdisc *sch, struct Qdisc *new, + struct Qdisc *old, unsigned long arg, + struct netlink_ext_ack *extack) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_ets_qopt_offload qopt; + + qopt.command = TC_ETS_GRAFT; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.graft_params.band = arg - 1; + qopt.graft_params.child_handle = new->handle; + + qdisc_offload_graft_helper(dev, sch, new, old, TC_SETUP_QDISC_ETS, + &qopt, extack); +} + +static int ets_offload_dump(struct Qdisc *sch) +{ + struct tc_ets_qopt_offload qopt; + + qopt.command = TC_ETS_STATS; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.stats.bstats = &sch->bstats; + qopt.stats.qstats = &sch->qstats; + + return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_ETS, &qopt); +} + +static bool ets_class_is_strict(struct ets_sched *q, const struct ets_class *cl) +{ + unsigned int band = cl - q->classes; + + return band < q->nstrict; +} + +static int ets_class_change(struct Qdisc *sch, u32 classid, u32 parentid, + struct nlattr **tca, unsigned long *arg, + struct netlink_ext_ack *extack) +{ + struct ets_class *cl = ets_class_from_arg(sch, *arg); + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *opt = tca[TCA_OPTIONS]; + struct nlattr *tb[TCA_ETS_MAX + 1]; + unsigned int quantum; + int err; + + /* Classes can be added and removed only through Qdisc_ops.change + * interface. + */ + if (!cl) { + NL_SET_ERR_MSG(extack, "Fine-grained class addition and removal is not supported"); + return -EOPNOTSUPP; + } + + if (!opt) { + NL_SET_ERR_MSG(extack, "ETS options are required for this operation"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_ETS_MAX, opt, ets_class_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_ETS_QUANTA_BAND]) + /* Nothing to configure. */ + return 0; + + if (ets_class_is_strict(q, cl)) { + NL_SET_ERR_MSG(extack, "Strict bands do not have a configurable quantum"); + return -EINVAL; + } + + err = ets_quantum_parse(sch, tb[TCA_ETS_QUANTA_BAND], &quantum, + extack); + if (err) + return err; + + sch_tree_lock(sch); + cl->quantum = quantum; + sch_tree_unlock(sch); + + ets_offload_change(sch); + return 0; +} + +static int ets_class_graft(struct Qdisc *sch, unsigned long arg, + struct Qdisc *new, struct Qdisc **old, + struct netlink_ext_ack *extack) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + + if (!new) { + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + ets_class_id(sch, cl), NULL); + if (!new) + new = &noop_qdisc; + else + qdisc_hash_add(new, true); + } + + *old = qdisc_replace(sch, new, &cl->qdisc); + ets_offload_graft(sch, new, *old, arg, extack); + return 0; +} + +static struct Qdisc *ets_class_leaf(struct Qdisc *sch, unsigned long arg) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + + return cl->qdisc; +} + +static unsigned long ets_class_find(struct Qdisc *sch, u32 classid) +{ + unsigned long band = TC_H_MIN(classid); + struct ets_sched *q = qdisc_priv(sch); + + if (band - 1 >= q->nbands) + return 0; + return band; +} + +static void ets_class_qlen_notify(struct Qdisc *sch, unsigned long arg) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + struct ets_sched *q = qdisc_priv(sch); + + /* We get notified about zero-length child Qdiscs as well if they are + * offloaded. Those aren't on the active list though, so don't attempt + * to remove them. + */ + if (!ets_class_is_strict(q, cl) && sch->q.qlen) + list_del(&cl->alist); +} + +static int ets_class_dump(struct Qdisc *sch, unsigned long arg, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *nest; + + tcm->tcm_parent = TC_H_ROOT; + tcm->tcm_handle = ets_class_id(sch, cl); + tcm->tcm_info = cl->qdisc->handle; + + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + if (!ets_class_is_strict(q, cl)) { + if (nla_put_u32(skb, TCA_ETS_QUANTA_BAND, cl->quantum)) + goto nla_put_failure; + } + return nla_nest_end(skb, nest); + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int ets_class_dump_stats(struct Qdisc *sch, unsigned long arg, + struct gnet_dump *d) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + struct Qdisc *cl_q = cl->qdisc; + + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), + d, NULL, &cl_q->bstats) < 0 || + qdisc_qstats_copy(d, cl_q) < 0) + return -1; + + return 0; +} + +static void ets_qdisc_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct ets_sched *q = qdisc_priv(sch); + int i; + + if (arg->stop) + return; + + for (i = 0; i < q->nbands; i++) { + if (arg->count < arg->skip) { + arg->count++; + continue; + } + if (arg->fn(sch, i + 1, arg) < 0) { + arg->stop = 1; + break; + } + arg->count++; + } +} + +static struct tcf_block * +ets_qdisc_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) +{ + struct ets_sched *q = qdisc_priv(sch); + + if (cl) { + NL_SET_ERR_MSG(extack, "ETS classid must be zero"); + return NULL; + } + + return q->block; +} + +static unsigned long ets_qdisc_bind_tcf(struct Qdisc *sch, unsigned long parent, + u32 classid) +{ + return ets_class_find(sch, classid); +} + +static void ets_qdisc_unbind_tcf(struct Qdisc *sch, unsigned long arg) +{ +} + +static struct ets_class *ets_classify(struct sk_buff *skb, struct Qdisc *sch, + int *qerr) +{ + struct ets_sched *q = qdisc_priv(sch); + u32 band = skb->priority; + struct tcf_result res; + struct tcf_proto *fl; + int err; + + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + if (TC_H_MAJ(skb->priority) != sch->handle) { + fl = rcu_dereference_bh(q->filter_list); + err = tcf_classify(skb, fl, &res, false); +#ifdef CONFIG_NET_CLS_ACT + switch (err) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ + case TC_ACT_SHOT: + return NULL; + } +#endif + if (!fl || err < 0) { + if (TC_H_MAJ(band)) + band = 0; + return &q->classes[q->prio2band[band & TC_PRIO_MAX]]; + } + band = res.classid; + } + band = TC_H_MIN(band) - 1; + if (band >= q->nbands) + return &q->classes[q->prio2band[0]]; + return &q->classes[band]; +} + +static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + unsigned int len = qdisc_pkt_len(skb); + struct ets_sched *q = qdisc_priv(sch); + struct ets_class *cl; + int err = 0; + bool first; + + cl = ets_classify(skb, sch, &err); + if (!cl) { + if (err & __NET_XMIT_BYPASS) + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + return err; + } + + first = !cl->qdisc->q.qlen; + err = qdisc_enqueue(skb, cl->qdisc, to_free); + if (unlikely(err != NET_XMIT_SUCCESS)) { + if (net_xmit_drop_count(err)) { + cl->qstats.drops++; + qdisc_qstats_drop(sch); + } + return err; + } + + if (first && !ets_class_is_strict(q, cl)) { + list_add_tail(&cl->alist, &q->active); + cl->deficit = cl->quantum; + } + + sch->qstats.backlog += len; + sch->q.qlen++; + return err; +} + +static struct sk_buff * +ets_qdisc_dequeue_skb(struct Qdisc *sch, struct sk_buff *skb) +{ + qdisc_bstats_update(sch, skb); + qdisc_qstats_backlog_dec(sch, skb); + sch->q.qlen--; + return skb; +} + +static struct sk_buff *ets_qdisc_dequeue(struct Qdisc *sch) +{ + struct ets_sched *q = qdisc_priv(sch); + struct ets_class *cl; + struct sk_buff *skb; + unsigned int band; + unsigned int len; + + while (1) { + for (band = 0; band < q->nstrict; band++) { + cl = &q->classes[band]; + skb = qdisc_dequeue_peeked(cl->qdisc); + if (skb) + return ets_qdisc_dequeue_skb(sch, skb); + } + + if (list_empty(&q->active)) + goto out; + + cl = list_first_entry(&q->active, struct ets_class, alist); + skb = cl->qdisc->ops->peek(cl->qdisc); + if (!skb) { + qdisc_warn_nonwc(__func__, cl->qdisc); + goto out; + } + + len = qdisc_pkt_len(skb); + if (len <= cl->deficit) { + cl->deficit -= len; + skb = qdisc_dequeue_peeked(cl->qdisc); + if (unlikely(!skb)) + goto out; + if (cl->qdisc->q.qlen == 0) + list_del(&cl->alist); + return ets_qdisc_dequeue_skb(sch, skb); + } + + cl->deficit += cl->quantum; + list_move_tail(&cl->alist, &q->active); + } +out: + return NULL; +} + +static int ets_qdisc_priomap_parse(struct nlattr *priomap_attr, + unsigned int nbands, u8 *priomap, + struct netlink_ext_ack *extack) +{ + const struct nlattr *attr; + int prio = 0; + u8 band; + int rem; + int err; + + err = __nla_validate_nested(priomap_attr, TCA_ETS_MAX, + ets_priomap_policy, NL_VALIDATE_STRICT, + extack); + if (err) + return err; + + nla_for_each_nested(attr, priomap_attr, rem) { + switch (nla_type(attr)) { + case TCA_ETS_PRIOMAP_BAND: + if (prio > TC_PRIO_MAX) { + NL_SET_ERR_MSG_MOD(extack, "Too many priorities in ETS priomap"); + return -EINVAL; + } + band = nla_get_u8(attr); + if (band >= nbands) { + NL_SET_ERR_MSG_MOD(extack, "Invalid band number in ETS priomap"); + return -EINVAL; + } + priomap[prio++] = band; + break; + default: + WARN_ON_ONCE(1); /* Validate should have caught this. */ + return -EINVAL; + } + } + + return 0; +} + +static int ets_qdisc_quanta_parse(struct Qdisc *sch, struct nlattr *quanta_attr, + unsigned int nbands, unsigned int nstrict, + unsigned int *quanta, + struct netlink_ext_ack *extack) +{ + const struct nlattr *attr; + int band = nstrict; + int rem; + int err; + + err = __nla_validate_nested(quanta_attr, TCA_ETS_MAX, + ets_quanta_policy, NL_VALIDATE_STRICT, + extack); + if (err < 0) + return err; + + nla_for_each_nested(attr, quanta_attr, rem) { + switch (nla_type(attr)) { + case TCA_ETS_QUANTA_BAND: + if (band >= nbands) { + NL_SET_ERR_MSG_MOD(extack, "ETS quanta has more values than bands"); + return -EINVAL; + } + err = ets_quantum_parse(sch, attr, &quanta[band++], + extack); + if (err) + return err; + break; + default: + WARN_ON_ONCE(1); /* Validate should have caught this. */ + return -EINVAL; + } + } + + return 0; +} + +static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + unsigned int quanta[TCQ_ETS_MAX_BANDS] = {0}; + struct Qdisc *queues[TCQ_ETS_MAX_BANDS]; + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *tb[TCA_ETS_MAX + 1]; + unsigned int oldbands = q->nbands; + u8 priomap[TC_PRIO_MAX + 1]; + unsigned int nstrict = 0; + unsigned int nbands; + unsigned int i; + int err; + + if (!opt) { + NL_SET_ERR_MSG(extack, "ETS options are required for this operation"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_ETS_MAX, opt, ets_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_ETS_NBANDS]) { + NL_SET_ERR_MSG_MOD(extack, "Number of bands is a required argument"); + return -EINVAL; + } + nbands = nla_get_u8(tb[TCA_ETS_NBANDS]); + if (nbands < 1 || nbands > TCQ_ETS_MAX_BANDS) { + NL_SET_ERR_MSG_MOD(extack, "Invalid number of bands"); + return -EINVAL; + } + /* Unless overridden, traffic goes to the last band. */ + memset(priomap, nbands - 1, sizeof(priomap)); + + if (tb[TCA_ETS_NSTRICT]) { + nstrict = nla_get_u8(tb[TCA_ETS_NSTRICT]); + if (nstrict > nbands) { + NL_SET_ERR_MSG_MOD(extack, "Invalid number of strict bands"); + return -EINVAL; + } + } + + if (tb[TCA_ETS_PRIOMAP]) { + err = ets_qdisc_priomap_parse(tb[TCA_ETS_PRIOMAP], + nbands, priomap, extack); + if (err) + return err; + } + + if (tb[TCA_ETS_QUANTA]) { + err = ets_qdisc_quanta_parse(sch, tb[TCA_ETS_QUANTA], + nbands, nstrict, quanta, extack); + if (err) + return err; + } + /* If there are more bands than strict + quanta provided, the remaining + * ones are ETS with quantum of MTU. Initialize the missing values here. + */ + for (i = nstrict; i < nbands; i++) { + if (!quanta[i]) + quanta[i] = psched_mtu(qdisc_dev(sch)); + } + + /* Before commit, make sure we can allocate all new qdiscs */ + for (i = oldbands; i < nbands; i++) { + queues[i] = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + ets_class_id(sch, &q->classes[i]), + extack); + if (!queues[i]) { + while (i > oldbands) + qdisc_put(queues[--i]); + return -ENOMEM; + } + } + + sch_tree_lock(sch); + + q->nbands = nbands; + q->nstrict = nstrict; + memcpy(q->prio2band, priomap, sizeof(priomap)); + + for (i = q->nbands; i < oldbands; i++) + qdisc_tree_flush_backlog(q->classes[i].qdisc); + + for (i = 0; i < q->nbands; i++) + q->classes[i].quantum = quanta[i]; + + for (i = oldbands; i < q->nbands; i++) { + q->classes[i].qdisc = queues[i]; + if (q->classes[i].qdisc != &noop_qdisc) + qdisc_hash_add(q->classes[i].qdisc, true); + } + + sch_tree_unlock(sch); + + ets_offload_change(sch); + for (i = q->nbands; i < oldbands; i++) { + qdisc_put(q->classes[i].qdisc); + memset(&q->classes[i], 0, sizeof(q->classes[i])); + } + return 0; +} + +static int ets_qdisc_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct ets_sched *q = qdisc_priv(sch); + int err; + + if (!opt) + return -EINVAL; + + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); + if (err) + return err; + + INIT_LIST_HEAD(&q->active); + return ets_qdisc_change(sch, opt, extack); +} + +static void ets_qdisc_reset(struct Qdisc *sch) +{ + struct ets_sched *q = qdisc_priv(sch); + int band; + + for (band = q->nstrict; band < q->nbands; band++) { + if (q->classes[band].qdisc->q.qlen) + list_del(&q->classes[band].alist); + } + for (band = 0; band < q->nbands; band++) + qdisc_reset(q->classes[band].qdisc); + sch->qstats.backlog = 0; + sch->q.qlen = 0; +} + +static void ets_qdisc_destroy(struct Qdisc *sch) +{ + struct ets_sched *q = qdisc_priv(sch); + int band; + + ets_offload_destroy(sch); + tcf_block_put(q->block); + for (band = 0; band < q->nbands; band++) + qdisc_put(q->classes[band].qdisc); +} + +static int ets_qdisc_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *opts; + struct nlattr *nest; + int band; + int prio; + int err; + + err = ets_offload_dump(sch); + if (err) + return err; + + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!opts) + goto nla_err; + + if (nla_put_u8(skb, TCA_ETS_NBANDS, q->nbands)) + goto nla_err; + + if (q->nstrict && + nla_put_u8(skb, TCA_ETS_NSTRICT, q->nstrict)) + goto nla_err; + + if (q->nbands > q->nstrict) { + nest = nla_nest_start(skb, TCA_ETS_QUANTA); + if (!nest) + goto nla_err; + + for (band = q->nstrict; band < q->nbands; band++) { + if (nla_put_u32(skb, TCA_ETS_QUANTA_BAND, + q->classes[band].quantum)) + goto nla_err; + } + + nla_nest_end(skb, nest); + } + + nest = nla_nest_start(skb, TCA_ETS_PRIOMAP); + if (!nest) + goto nla_err; + + for (prio = 0; prio <= TC_PRIO_MAX; prio++) { + if (nla_put_u8(skb, TCA_ETS_PRIOMAP_BAND, q->prio2band[prio])) + goto nla_err; + } + + nla_nest_end(skb, nest); + + return nla_nest_end(skb, opts); + +nla_err: + nla_nest_cancel(skb, opts); + return -EMSGSIZE; +} + +static const struct Qdisc_class_ops ets_class_ops = { + .change = ets_class_change, + .graft = ets_class_graft, + .leaf = ets_class_leaf, + .find = ets_class_find, + .qlen_notify = ets_class_qlen_notify, + .dump = ets_class_dump, + .dump_stats = ets_class_dump_stats, + .walk = ets_qdisc_walk, + .tcf_block = ets_qdisc_tcf_block, + .bind_tcf = ets_qdisc_bind_tcf, + .unbind_tcf = ets_qdisc_unbind_tcf, +}; + +static struct Qdisc_ops ets_qdisc_ops __read_mostly = { + .cl_ops = &ets_class_ops, + .id = "ets", + .priv_size = sizeof(struct ets_sched), + .enqueue = ets_qdisc_enqueue, + .dequeue = ets_qdisc_dequeue, + .peek = qdisc_peek_dequeued, + .change = ets_qdisc_change, + .init = ets_qdisc_init, + .reset = ets_qdisc_reset, + .destroy = ets_qdisc_destroy, + .dump = ets_qdisc_dump, + .owner = THIS_MODULE, +}; + +static int __init ets_init(void) +{ + return register_qdisc(&ets_qdisc_ops); +} + +static void __exit ets_exit(void) +{ + unregister_qdisc(&ets_qdisc_ops); +} + +module_init(ets_init); +module_exit(ets_exit); +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 98dd87ce1510..a5a295477ecc 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -301,6 +301,9 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) f->socket_hash != sk->sk_hash)) { f->credit = q->initial_quantum; f->socket_hash = sk->sk_hash; + if (q->rate_enable) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); if (fq_flow_is_throttled(f)) fq_flow_unset_throttled(q, f); f->time_next_packet = 0ULL; @@ -322,8 +325,12 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) fq_flow_set_detached(f); f->sk = sk; - if (skb->sk == sk) + if (skb->sk == sk) { f->socket_hash = sk->sk_hash; + if (q->rate_enable) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); + } f->credit = q->initial_quantum; rb_link_node(&f->fq_node, parent, p); @@ -428,17 +435,9 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, f->qlen++; qdisc_qstats_backlog_inc(sch, skb); if (fq_flow_is_detached(f)) { - struct sock *sk = skb->sk; - fq_flow_add_tail(&q->new_flows, f); if (time_after(jiffies, f->age + q->flow_refill_delay)) f->credit = max_t(u32, f->credit, q->quantum); - if (sk && q->rate_enable) { - if (unlikely(smp_load_acquire(&sk->sk_pacing_status) != - SK_PACING_FQ)) - smp_store_release(&sk->sk_pacing_status, - SK_PACING_FQ); - } q->inactive_flows--; } @@ -530,8 +529,7 @@ 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++; } @@ -788,10 +786,12 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_FQ_QUANTUM]) { u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]); - if (quantum > 0) + if (quantum > 0 && quantum <= (1 << 20)) { q->quantum = quantum; - else + } else { + NL_SET_ERR_MSG_MOD(extack, "invalid quantum"); err = -EINVAL; + } } if (tb[TCA_FQ_INITIAL_QUANTUM]) diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index d59fbcc745d1..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> @@ -45,7 +44,6 @@ struct fq_codel_flow { struct sk_buff *tail; struct list_head flowchain; int deficit; - u32 dropped; /* number of drops (or ECN marks) on this flow */ struct codel_vars cvars; }; /* please try to keep this structure <= 64 bytes */ @@ -173,7 +171,8 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets, __qdisc_drop(skb, to_free); } while (++i < max_packets && len < threshold); - flow->dropped += i; + /* Tell codel to increase its signal strength also */ + flow->cvars.count += i; q->backlogs[idx] -= len; q->memory_usage -= mem; sch->qstats.drops += i; @@ -211,7 +210,6 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch, list_add_tail(&flow->flowchain, &q->new_flows); q->new_flow_count++; flow->deficit = q->quantum; - flow->dropped = 0; } get_codel_cb(skb)->mem_usage = skb->truesize; q->memory_usage += get_codel_cb(skb)->mem_usage; @@ -286,7 +284,6 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch) struct sk_buff *skb; struct fq_codel_flow *flow; struct list_head *head; - u32 prev_drop_count, prev_ecn_mark; begin: head = &q->new_flows; @@ -303,16 +300,10 @@ begin: goto begin; } - prev_drop_count = q->cstats.drop_count; - prev_ecn_mark = q->cstats.ecn_mark; - skb = codel_dequeue(sch, &sch->qstats.backlog, &q->cparams, &flow->cvars, &q->cstats, qdisc_pkt_len, codel_get_enqueue_time, drop_func, dequeue_func); - flow->dropped += q->cstats.drop_count - prev_drop_count; - flow->dropped += q->cstats.ecn_mark - prev_ecn_mark; - if (!skb) { /* force a pass through old_flows to prevent starvation */ if ((head == &q->new_flows) && !list_empty(&q->old_flows)) @@ -658,7 +649,7 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl, sch_tree_unlock(sch); } qs.backlog = q->backlogs[idx]; - qs.drops = flow->dropped; + qs.drops = 0; } if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0) return -1; diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c new file mode 100644 index 000000000000..214657eb3dfd --- /dev/null +++ b/net/sched/sch_fq_pie.c @@ -0,0 +1,562 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Flow Queue PIE discipline + * + * Copyright (C) 2019 Mohit P. Tahiliani <tahiliani@nitk.edu.in> + * Copyright (C) 2019 Sachin D. Patil <sdp.sachin@gmail.com> + * Copyright (C) 2019 V. Saicharan <vsaicharan1998@gmail.com> + * Copyright (C) 2019 Mohit Bhasi <mohitbhasi1998@gmail.com> + * Copyright (C) 2019 Leslie Monis <lesliemonis@gmail.com> + * Copyright (C) 2019 Gautam Ramakrishnan <gautamramk@gmail.com> + */ + +#include <linux/jhash.h> +#include <linux/sizes.h> +#include <linux/vmalloc.h> +#include <net/pkt_cls.h> +#include <net/pie.h> + +/* Flow Queue PIE + * + * Principles: + * - Packets are classified on flows. + * - This is a Stochastic model (as we use a hash, several flows might + * be hashed to the same slot) + * - Each flow has a PIE managed queue. + * - Flows are linked onto two (Round Robin) lists, + * so that new flows have priority on old ones. + * - For a given flow, packets are not reordered. + * - Drops during enqueue only. + * - ECN capability is off by default. + * - ECN threshold (if ECN is enabled) is at 10% by default. + * - Uses timestamps to calculate queue delay by default. + */ + +/** + * struct fq_pie_flow - contains data for each flow + * @vars: pie vars associated with the flow + * @deficit: number of remaining byte credits + * @backlog: size of data in the flow + * @qlen: number of packets in the flow + * @flowchain: flowchain for the flow + * @head: first packet in the flow + * @tail: last packet in the flow + */ +struct fq_pie_flow { + struct pie_vars vars; + s32 deficit; + u32 backlog; + u32 qlen; + struct list_head flowchain; + struct sk_buff *head; + struct sk_buff *tail; +}; + +struct fq_pie_sched_data { + struct tcf_proto __rcu *filter_list; /* optional external classifier */ + struct tcf_block *block; + struct fq_pie_flow *flows; + struct Qdisc *sch; + struct list_head old_flows; + struct list_head new_flows; + struct pie_params p_params; + u32 ecn_prob; + u32 flows_cnt; + u32 quantum; + u32 memory_limit; + u32 new_flow_count; + u32 memory_usage; + u32 overmemory; + struct pie_stats stats; + struct timer_list adapt_timer; +}; + +static unsigned int fq_pie_hash(const struct fq_pie_sched_data *q, + struct sk_buff *skb) +{ + return reciprocal_scale(skb_get_hash(skb), q->flows_cnt); +} + +static unsigned int fq_pie_classify(struct sk_buff *skb, struct Qdisc *sch, + int *qerr) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct tcf_proto *filter; + struct tcf_result res; + int result; + + if (TC_H_MAJ(skb->priority) == sch->handle && + TC_H_MIN(skb->priority) > 0 && + TC_H_MIN(skb->priority) <= q->flows_cnt) + return TC_H_MIN(skb->priority); + + filter = rcu_dereference_bh(q->filter_list); + if (!filter) + return fq_pie_hash(q, skb) + 1; + + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + result = tcf_classify(skb, filter, &res, false); + if (result >= 0) { +#ifdef CONFIG_NET_CLS_ACT + switch (result) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ + case TC_ACT_SHOT: + return 0; + } +#endif + if (TC_H_MIN(res.classid) <= q->flows_cnt) + return TC_H_MIN(res.classid); + } + return 0; +} + +/* add skb to flow queue (tail add) */ +static inline void flow_queue_add(struct fq_pie_flow *flow, + struct sk_buff *skb) +{ + if (!flow->head) + flow->head = skb; + else + flow->tail->next = skb; + flow->tail = skb; + skb->next = NULL; +} + +static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct fq_pie_flow *sel_flow; + int uninitialized_var(ret); + u8 memory_limited = false; + u8 enqueue = false; + u32 pkt_len; + u32 idx; + + /* Classifies packet into corresponding flow */ + idx = fq_pie_classify(skb, sch, &ret); + sel_flow = &q->flows[idx]; + + /* Checks whether adding a new packet would exceed memory limit */ + get_pie_cb(skb)->mem_usage = skb->truesize; + memory_limited = q->memory_usage > q->memory_limit + skb->truesize; + + /* Checks if the qdisc is full */ + if (unlikely(qdisc_qlen(sch) >= sch->limit)) { + q->stats.overlimit++; + goto out; + } else if (unlikely(memory_limited)) { + q->overmemory++; + } + + if (!pie_drop_early(sch, &q->p_params, &sel_flow->vars, + sel_flow->backlog, skb->len)) { + enqueue = true; + } else if (q->p_params.ecn && + sel_flow->vars.prob <= (MAX_PROB / 100) * q->ecn_prob && + INET_ECN_set_ce(skb)) { + /* If packet is ecn capable, mark it if drop probability + * is lower than the parameter ecn_prob, else drop it. + */ + q->stats.ecn_mark++; + enqueue = true; + } + if (enqueue) { + /* Set enqueue time only when dq_rate_estimator is disabled. */ + if (!q->p_params.dq_rate_estimator) + pie_set_enqueue_time(skb); + + pkt_len = qdisc_pkt_len(skb); + q->stats.packets_in++; + q->memory_usage += skb->truesize; + sch->qstats.backlog += pkt_len; + sch->q.qlen++; + flow_queue_add(sel_flow, skb); + if (list_empty(&sel_flow->flowchain)) { + list_add_tail(&sel_flow->flowchain, &q->new_flows); + q->new_flow_count++; + sel_flow->deficit = q->quantum; + sel_flow->qlen = 0; + sel_flow->backlog = 0; + } + sel_flow->qlen++; + sel_flow->backlog += pkt_len; + return NET_XMIT_SUCCESS; + } +out: + q->stats.dropped++; + sel_flow->vars.accu_prob = 0; + sel_flow->vars.accu_prob_overflows = 0; + __qdisc_drop(skb, to_free); + qdisc_qstats_drop(sch); + return NET_XMIT_CN; +} + +static const struct nla_policy fq_pie_policy[TCA_FQ_PIE_MAX + 1] = { + [TCA_FQ_PIE_LIMIT] = {.type = NLA_U32}, + [TCA_FQ_PIE_FLOWS] = {.type = NLA_U32}, + [TCA_FQ_PIE_TARGET] = {.type = NLA_U32}, + [TCA_FQ_PIE_TUPDATE] = {.type = NLA_U32}, + [TCA_FQ_PIE_ALPHA] = {.type = NLA_U32}, + [TCA_FQ_PIE_BETA] = {.type = NLA_U32}, + [TCA_FQ_PIE_QUANTUM] = {.type = NLA_U32}, + [TCA_FQ_PIE_MEMORY_LIMIT] = {.type = NLA_U32}, + [TCA_FQ_PIE_ECN_PROB] = {.type = NLA_U32}, + [TCA_FQ_PIE_ECN] = {.type = NLA_U32}, + [TCA_FQ_PIE_BYTEMODE] = {.type = NLA_U32}, + [TCA_FQ_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32}, +}; + +static inline struct sk_buff *dequeue_head(struct fq_pie_flow *flow) +{ + struct sk_buff *skb = flow->head; + + flow->head = skb->next; + skb->next = NULL; + return skb; +} + +static struct sk_buff *fq_pie_qdisc_dequeue(struct Qdisc *sch) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb = NULL; + struct fq_pie_flow *flow; + struct list_head *head; + u32 pkt_len; + +begin: + head = &q->new_flows; + if (list_empty(head)) { + head = &q->old_flows; + if (list_empty(head)) + return NULL; + } + + flow = list_first_entry(head, struct fq_pie_flow, flowchain); + /* Flow has exhausted all its credits */ + if (flow->deficit <= 0) { + flow->deficit += q->quantum; + list_move_tail(&flow->flowchain, &q->old_flows); + goto begin; + } + + if (flow->head) { + skb = dequeue_head(flow); + pkt_len = qdisc_pkt_len(skb); + sch->qstats.backlog -= pkt_len; + sch->q.qlen--; + qdisc_bstats_update(sch, skb); + } + + if (!skb) { + /* force a pass through old_flows to prevent starvation */ + if (head == &q->new_flows && !list_empty(&q->old_flows)) + list_move_tail(&flow->flowchain, &q->old_flows); + else + list_del_init(&flow->flowchain); + goto begin; + } + + flow->qlen--; + flow->deficit -= pkt_len; + flow->backlog -= pkt_len; + q->memory_usage -= get_pie_cb(skb)->mem_usage; + pie_process_dequeue(skb, &q->p_params, &flow->vars, flow->backlog); + return skb; +} + +static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_FQ_PIE_MAX + 1]; + unsigned int len_dropped = 0; + unsigned int num_dropped = 0; + int err; + + if (!opt) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_FQ_PIE_MAX, opt, fq_pie_policy, extack); + if (err < 0) + return err; + + sch_tree_lock(sch); + if (tb[TCA_FQ_PIE_LIMIT]) { + u32 limit = nla_get_u32(tb[TCA_FQ_PIE_LIMIT]); + + q->p_params.limit = limit; + sch->limit = limit; + } + if (tb[TCA_FQ_PIE_FLOWS]) { + if (q->flows) { + NL_SET_ERR_MSG_MOD(extack, + "Number of flows cannot be changed"); + goto flow_error; + } + q->flows_cnt = nla_get_u32(tb[TCA_FQ_PIE_FLOWS]); + if (!q->flows_cnt || q->flows_cnt > 65536) { + NL_SET_ERR_MSG_MOD(extack, + "Number of flows must be < 65536"); + goto flow_error; + } + } + + /* convert from microseconds to pschedtime */ + if (tb[TCA_FQ_PIE_TARGET]) { + /* target is in us */ + u32 target = nla_get_u32(tb[TCA_FQ_PIE_TARGET]); + + /* convert to pschedtime */ + q->p_params.target = + PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC); + } + + /* tupdate is in jiffies */ + if (tb[TCA_FQ_PIE_TUPDATE]) + q->p_params.tupdate = + usecs_to_jiffies(nla_get_u32(tb[TCA_FQ_PIE_TUPDATE])); + + if (tb[TCA_FQ_PIE_ALPHA]) + q->p_params.alpha = nla_get_u32(tb[TCA_FQ_PIE_ALPHA]); + + if (tb[TCA_FQ_PIE_BETA]) + q->p_params.beta = nla_get_u32(tb[TCA_FQ_PIE_BETA]); + + if (tb[TCA_FQ_PIE_QUANTUM]) + q->quantum = nla_get_u32(tb[TCA_FQ_PIE_QUANTUM]); + + if (tb[TCA_FQ_PIE_MEMORY_LIMIT]) + q->memory_limit = nla_get_u32(tb[TCA_FQ_PIE_MEMORY_LIMIT]); + + if (tb[TCA_FQ_PIE_ECN_PROB]) + q->ecn_prob = nla_get_u32(tb[TCA_FQ_PIE_ECN_PROB]); + + if (tb[TCA_FQ_PIE_ECN]) + q->p_params.ecn = nla_get_u32(tb[TCA_FQ_PIE_ECN]); + + if (tb[TCA_FQ_PIE_BYTEMODE]) + q->p_params.bytemode = nla_get_u32(tb[TCA_FQ_PIE_BYTEMODE]); + + if (tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR]) + q->p_params.dq_rate_estimator = + nla_get_u32(tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR]); + + /* Drop excess packets if new limit is lower */ + while (sch->q.qlen > sch->limit) { + struct sk_buff *skb = fq_pie_qdisc_dequeue(sch); + + len_dropped += qdisc_pkt_len(skb); + num_dropped += 1; + rtnl_kfree_skbs(skb, skb); + } + qdisc_tree_reduce_backlog(sch, num_dropped, len_dropped); + + sch_tree_unlock(sch); + return 0; + +flow_error: + sch_tree_unlock(sch); + return -EINVAL; +} + +static void fq_pie_timer(struct timer_list *t) +{ + struct fq_pie_sched_data *q = from_timer(q, t, adapt_timer); + struct Qdisc *sch = q->sch; + spinlock_t *root_lock; /* to lock qdisc for probability calculations */ + u16 idx; + + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + spin_lock(root_lock); + + for (idx = 0; idx < q->flows_cnt; idx++) + pie_calculate_probability(&q->p_params, &q->flows[idx].vars, + q->flows[idx].backlog); + + /* reset the timer to fire after 'tupdate' jiffies. */ + if (q->p_params.tupdate) + mod_timer(&q->adapt_timer, jiffies + q->p_params.tupdate); + + spin_unlock(root_lock); +} + +static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + int err; + u16 idx; + + pie_params_init(&q->p_params); + sch->limit = 10 * 1024; + q->p_params.limit = sch->limit; + q->quantum = psched_mtu(qdisc_dev(sch)); + q->sch = sch; + q->ecn_prob = 10; + q->flows_cnt = 1024; + q->memory_limit = SZ_32M; + + INIT_LIST_HEAD(&q->new_flows); + INIT_LIST_HEAD(&q->old_flows); + + if (opt) { + err = fq_pie_change(sch, opt, extack); + + if (err) + return err; + } + + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); + if (err) + goto init_failure; + + q->flows = kvcalloc(q->flows_cnt, sizeof(struct fq_pie_flow), + GFP_KERNEL); + if (!q->flows) { + err = -ENOMEM; + goto init_failure; + } + for (idx = 0; idx < q->flows_cnt; idx++) { + struct fq_pie_flow *flow = q->flows + idx; + + INIT_LIST_HEAD(&flow->flowchain); + pie_vars_init(&flow->vars); + } + + timer_setup(&q->adapt_timer, fq_pie_timer, 0); + mod_timer(&q->adapt_timer, jiffies + HZ / 2); + + return 0; + +init_failure: + q->flows_cnt = 0; + + return err; +} + +static int fq_pie_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct nlattr *opts; + + opts = nla_nest_start(skb, TCA_OPTIONS); + if (!opts) + return -EMSGSIZE; + + /* convert target from pschedtime to us */ + if (nla_put_u32(skb, TCA_FQ_PIE_LIMIT, sch->limit) || + nla_put_u32(skb, TCA_FQ_PIE_FLOWS, q->flows_cnt) || + nla_put_u32(skb, TCA_FQ_PIE_TARGET, + ((u32)PSCHED_TICKS2NS(q->p_params.target)) / + NSEC_PER_USEC) || + nla_put_u32(skb, TCA_FQ_PIE_TUPDATE, + jiffies_to_usecs(q->p_params.tupdate)) || + nla_put_u32(skb, TCA_FQ_PIE_ALPHA, q->p_params.alpha) || + nla_put_u32(skb, TCA_FQ_PIE_BETA, q->p_params.beta) || + nla_put_u32(skb, TCA_FQ_PIE_QUANTUM, q->quantum) || + nla_put_u32(skb, TCA_FQ_PIE_MEMORY_LIMIT, q->memory_limit) || + nla_put_u32(skb, TCA_FQ_PIE_ECN_PROB, q->ecn_prob) || + nla_put_u32(skb, TCA_FQ_PIE_ECN, q->p_params.ecn) || + nla_put_u32(skb, TCA_FQ_PIE_BYTEMODE, q->p_params.bytemode) || + nla_put_u32(skb, TCA_FQ_PIE_DQ_RATE_ESTIMATOR, + q->p_params.dq_rate_estimator)) + goto nla_put_failure; + + return nla_nest_end(skb, opts); + +nla_put_failure: + nla_nest_cancel(skb, opts); + return -EMSGSIZE; +} + +static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct tc_fq_pie_xstats st = { + .packets_in = q->stats.packets_in, + .overlimit = q->stats.overlimit, + .overmemory = q->overmemory, + .dropped = q->stats.dropped, + .ecn_mark = q->stats.ecn_mark, + .new_flow_count = q->new_flow_count, + .memory_usage = q->memory_usage, + }; + struct list_head *pos; + + sch_tree_lock(sch); + list_for_each(pos, &q->new_flows) + st.new_flows_len++; + + list_for_each(pos, &q->old_flows) + st.old_flows_len++; + sch_tree_unlock(sch); + + return gnet_stats_copy_app(d, &st, sizeof(st)); +} + +static void fq_pie_reset(struct Qdisc *sch) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + u16 idx; + + INIT_LIST_HEAD(&q->new_flows); + INIT_LIST_HEAD(&q->old_flows); + for (idx = 0; idx < q->flows_cnt; idx++) { + struct fq_pie_flow *flow = q->flows + idx; + + /* Removes all packets from flow */ + rtnl_kfree_skbs(flow->head, flow->tail); + flow->head = NULL; + + INIT_LIST_HEAD(&flow->flowchain); + pie_vars_init(&flow->vars); + } + + sch->q.qlen = 0; + sch->qstats.backlog = 0; +} + +static void fq_pie_destroy(struct Qdisc *sch) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + + tcf_block_put(q->block); + del_timer_sync(&q->adapt_timer); + kvfree(q->flows); +} + +static struct Qdisc_ops fq_pie_qdisc_ops __read_mostly = { + .id = "fq_pie", + .priv_size = sizeof(struct fq_pie_sched_data), + .enqueue = fq_pie_qdisc_enqueue, + .dequeue = fq_pie_qdisc_dequeue, + .peek = qdisc_peek_dequeued, + .init = fq_pie_init, + .destroy = fq_pie_destroy, + .reset = fq_pie_reset, + .change = fq_pie_change, + .dump = fq_pie_dump, + .dump_stats = fq_pie_dump_stats, + .owner = THIS_MODULE, +}; + +static int __init fq_pie_module_init(void) +{ + return register_qdisc(&fq_pie_qdisc_ops); +} + +static void __exit fq_pie_module_exit(void) +{ + unregister_qdisc(&fq_pie_qdisc_ops); +} + +module_init(fq_pie_module_init); +module_exit(fq_pie_module_exit); + +MODULE_DESCRIPTION("Flow Queue Proportional Integral controller Enhanced (FQ-PIE)"); +MODULE_AUTHOR("Mohit P. Tahiliani"); +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 11c03cf4aa74..6c9595f1048a 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -46,6 +46,8 @@ EXPORT_SYMBOL(default_qdisc_ops); * - updates to tree and tree walking are only done under the rtnl mutex. */ +#define SKB_XOFF_MAGIC ((struct sk_buff *)1UL) + static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q) { const struct netdev_queue *txq = q->dev_queue; @@ -71,7 +73,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q) q->q.qlen--; } } else { - skb = NULL; + skb = SKB_XOFF_MAGIC; } } @@ -253,8 +255,11 @@ validate: return skb; skb = qdisc_dequeue_skb_bad_txq(q); - if (unlikely(skb)) + if (unlikely(skb)) { + if (skb == SKB_XOFF_MAGIC) + return NULL; goto bulk; + } skb = q->dequeue(q); if (skb) { bulk: @@ -377,13 +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; } @@ -441,7 +441,7 @@ static void dev_watchdog(struct timer_list *t) trace_net_dev_xmit_timeout(dev, i); WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n", dev->name, netdev_drivername(dev), i); - dev->netdev_ops->ndo_tx_timeout(dev); + dev->netdev_ops->ndo_tx_timeout(dev, i); } if (!mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + @@ -624,8 +624,12 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, err = skb_array_produce(q, skb); - if (unlikely(err)) - return qdisc_drop_cpu(skb, qdisc, to_free); + if (unlikely(err)) { + if (qdisc_is_percpu_stats(qdisc)) + return qdisc_drop_cpu(skb, qdisc, to_free); + else + return qdisc_drop(skb, qdisc, to_free); + } qdisc_update_stats_at_enqueue(qdisc, pkt_len); return NET_XMIT_SUCCESS; @@ -648,7 +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; @@ -688,11 +692,14 @@ static void pfifo_fast_reset(struct Qdisc *qdisc) kfree_skb(skb); } - for_each_possible_cpu(i) { - struct gnet_stats_queue *q = per_cpu_ptr(qdisc->cpu_qstats, i); + if (qdisc_is_percpu_stats(qdisc)) { + for_each_possible_cpu(i) { + struct gnet_stats_queue *q; - q->backlog = 0; - q->qlen = 0; + q = per_cpu_ptr(qdisc->cpu_qstats, i); + q->backlog = 0; + q->qlen = 0; + } } } @@ -787,9 +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) @@ -842,17 +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; @@ -863,6 +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); @@ -973,6 +975,9 @@ static void qdisc_destroy(struct Qdisc *qdisc) void qdisc_put(struct Qdisc *qdisc) { + if (!qdisc) + return; + if (qdisc->flags & TCQ_F_BUILTIN || !refcount_dec_and_test(&qdisc->refcnt)) return; @@ -1028,6 +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) { @@ -1202,8 +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 cee6971c1c82..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; @@ -531,7 +531,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt, new_hhf_non_hh_weight = nla_get_u32(tb[TCA_HHF_NON_HH_WEIGHT]); non_hh_quantum = (u64)new_quantum * new_hhf_non_hh_weight; - if (non_hh_quantum > INT_MAX) + if (non_hh_quantum == 0 || non_hh_quantum > INT_MAX) return -EINVAL; sch_tree_lock(sch); @@ -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_htb.c b/net/sched/sch_htb.c index 7bcf20ef9145..8184c87da8be 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1302,6 +1302,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, struct htb_class *cl = (struct htb_class *)*arg, *parent; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_HTB_MAX + 1]; + struct Qdisc *parent_qdisc = NULL; struct tc_htb_opt *hopt; u64 rate64, ceil64; int warn = 0; @@ -1401,7 +1402,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (parent && !parent->level) { /* turn parent into inner node */ qdisc_purge_queue(parent->leaf.q); - qdisc_put(parent->leaf.q); + parent_qdisc = parent->leaf.q; if (parent->prio_activity) htb_deactivate(q, parent); @@ -1480,6 +1481,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer); sch_tree_unlock(sch); + qdisc_put(parent_qdisc); if (warn) pr_warn("HTB: quantum of class %X is %s. Consider r2q change.\n", diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index 0d578333e967..e79f1afe0cfd 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -153,6 +153,7 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) __gnet_stats_copy_queue(&sch->qstats, qdisc->cpu_qstats, &qdisc->qstats, qlen); + sch->q.qlen += qlen; } else { sch->q.qlen += qdisc->q.qlen; sch->bstats.bytes += qdisc->bstats.bytes; @@ -245,7 +246,8 @@ 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..8766ab5b8788 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -411,6 +411,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) __gnet_stats_copy_queue(&sch->qstats, qdisc->cpu_qstats, &qdisc->qstats, qlen); + sch->q.qlen += qlen; } else { sch->q.qlen += qdisc->q.qlen; sch->bstats.bytes += qdisc->bstats.bytes; @@ -433,7 +434,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) opt.offset[tc] = dev->tc_to_txq[tc].offset; } - if (nla_put(skb, TCA_OPTIONS, NLA_ALIGN(sizeof(opt)), &opt)) + if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; if ((priv->flags & TC_MQPRIO_F_MODE) && @@ -557,8 +558,8 @@ 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 e1087746f6a2..1330ad224931 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -174,7 +174,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, { struct multiq_sched_data *q = qdisc_priv(sch); struct tc_multiq_qopt *qopt; - int i; + struct Qdisc **removed; + int i, n_removed = 0; if (!netif_is_multiqueue(qdisc_dev(sch))) return -EOPNOTSUPP; @@ -185,6 +186,11 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, qopt->bands = qdisc_dev(sch)->real_num_tx_queues; + removed = kmalloc(sizeof(*removed) * (q->max_bands - q->bands), + GFP_KERNEL); + if (!removed) + return -ENOMEM; + sch_tree_lock(sch); q->bands = qopt->bands; for (i = q->bands; i < q->max_bands; i++) { @@ -192,13 +198,17 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, struct Qdisc *child = q->queues[i]; q->queues[i] = &noop_qdisc; - qdisc_tree_flush_backlog(child); - qdisc_put(child); + qdisc_purge_queue(child); + removed[n_removed++] = child; } } sch_tree_unlock(sch); + for (i = 0; i < n_removed; i++) + qdisc_put(removed[i]); + kfree(removed); + for (i = 0; i < q->bands; i++) { if (q->queues[i] == &noop_qdisc) { struct Qdisc *child, *old; @@ -213,11 +223,10 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, if (child != &noop_qdisc) qdisc_hash_add(child, true); - if (old != &noop_qdisc) { - qdisc_tree_flush_backlog(old); - qdisc_put(old); - } + if (old != &noop_qdisc) + qdisc_purge_queue(old); sch_tree_unlock(sch); + qdisc_put(old); } } } @@ -330,7 +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 b17f2ed970e2..42e557d48e4e 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -476,7 +476,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, * skb will be queued. */ if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) { - struct Qdisc *rootq = qdisc_root(sch); + struct Qdisc *rootq = qdisc_root_bh(sch); u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ q->duplicate = 0; @@ -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; } @@ -777,7 +782,7 @@ static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, struct disttable *d; int i; - if (n > NETEM_DIST_MAX) + if (!n || n > NETEM_DIST_MAX) return -EINVAL; d = kvmalloc(sizeof(struct disttable) + n * sizeof(s16), GFP_KERNEL); diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index df98a887eb89..915bcdb59a9f 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -19,134 +19,76 @@ #include <linux/skbuff.h> #include <net/pkt_sched.h> #include <net/inet_ecn.h> - -#define QUEUE_THRESHOLD 16384 -#define DQCOUNT_INVALID -1 -#define MAX_PROB 0xffffffffffffffff -#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 0 and 32 */ - 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 { - u64 prob; /* probability but scaled by u64 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 */ - u64 accu_prob; /* accumulated drop probability */ - u32 avg_dq_rate; /* bytes per pschedtime tick,scaled */ - u32 qlen_old; /* in bytes */ - u8 accu_prob_overflows; /* overflows of accu_prob */ -}; - -/* 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 */ -}; +#include <net/pie.h> /* private data for the Qdisc */ struct pie_sched_data { - struct pie_params params; struct pie_vars vars; + struct pie_params params; struct pie_stats stats; struct timer_list adapt_timer; struct Qdisc *sch; }; -static void pie_params_init(struct pie_params *params) -{ - params->alpha = 2; - params->beta = 20; - params->tupdate = usecs_to_jiffies(15 * USEC_PER_MSEC); /* 15 ms */ - params->limit = 1000; /* default of 1000 packets */ - params->target = PSCHED_NS2TICKS(15 * NSEC_PER_MSEC); /* 15 ms */ - params->ecn = false; - params->bytemode = false; -} - -static void pie_vars_init(struct pie_vars *vars) +bool pie_drop_early(struct Qdisc *sch, struct pie_params *params, + struct pie_vars *vars, u32 qlen, u32 packet_size) { - vars->dq_count = DQCOUNT_INVALID; - vars->accu_prob = 0; - vars->avg_dq_rate = 0; - /* default of 150 ms in pschedtime */ - vars->burst_time = PSCHED_NS2TICKS(150 * NSEC_PER_MSEC); - vars->accu_prob_overflows = 0; -} - -static bool drop_early(struct Qdisc *sch, u32 packet_size) -{ - struct pie_sched_data *q = qdisc_priv(sch); u64 rnd; - u64 local_prob = q->vars.prob; + u64 local_prob = 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) + if (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)) + if ((vars->qdelay < params->target / 2) && + (vars->prob < MAX_PROB / 5)) return false; - /* If we have fewer than 2 mtu-sized packets, disable drop_early, + /* If we have fewer than 2 mtu-sized packets, disable pie_drop_early, * similar to min_th in RED */ - if (sch->qstats.backlog < 2 * mtu) + if (qlen < 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) + if (params->bytemode && packet_size <= mtu) local_prob = (u64)packet_size * div_u64(local_prob, mtu); else - local_prob = q->vars.prob; + local_prob = vars->prob; if (local_prob == 0) { - q->vars.accu_prob = 0; - q->vars.accu_prob_overflows = 0; + vars->accu_prob = 0; + vars->accu_prob_overflows = 0; } - if (local_prob > MAX_PROB - q->vars.accu_prob) - q->vars.accu_prob_overflows++; + if (local_prob > MAX_PROB - vars->accu_prob) + vars->accu_prob_overflows++; - q->vars.accu_prob += local_prob; + vars->accu_prob += local_prob; - if (q->vars.accu_prob_overflows == 0 && - q->vars.accu_prob < (MAX_PROB / 100) * 85) + if (vars->accu_prob_overflows == 0 && + vars->accu_prob < (MAX_PROB / 100) * 85) return false; - if (q->vars.accu_prob_overflows == 8 && - q->vars.accu_prob >= MAX_PROB / 2) + if (vars->accu_prob_overflows == 8 && + vars->accu_prob >= MAX_PROB / 2) return true; prandom_bytes(&rnd, 8); if (rnd < local_prob) { - q->vars.accu_prob = 0; - q->vars.accu_prob_overflows = 0; + vars->accu_prob = 0; + vars->accu_prob_overflows = 0; return true; } return false; } +EXPORT_SYMBOL_GPL(pie_drop_early); static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) @@ -159,7 +101,8 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, goto out; } - if (!drop_early(sch, skb->len)) { + if (!pie_drop_early(sch, &q->params, &q->vars, sch->qstats.backlog, + skb->len)) { enqueue = true; } else if (q->params.ecn && (q->vars.prob <= MAX_PROB / 10) && INET_ECN_set_ce(skb)) { @@ -172,6 +115,10 @@ 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); @@ -187,13 +134,14 @@ out: } 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}, + [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}, + [TCA_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32}, }; static int pie_change(struct Qdisc *sch, struct nlattr *opt, @@ -247,6 +195,10 @@ 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) { @@ -262,48 +214,69 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt, return 0; } -static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb) +void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params, + struct pie_vars *vars, u32 qlen) { - 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 (!params->dq_rate_estimator) { + vars->qdelay = now - pie_get_enqueue_time(skb); + + if (vars->dq_tstamp != DTIME_INVALID) + dtime = now - vars->dq_tstamp; + + vars->dq_tstamp = now; + + if (qlen == 0) + 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 * 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; + if (qlen >= QUEUE_THRESHOLD && vars->dq_count == DQCOUNT_INVALID) { + vars->dq_tstamp = psched_get_time(); + 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 + /* 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 + * 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 (vars->dq_count != DQCOUNT_INVALID) { + vars->dq_count += skb->len; + + if (vars->dq_count >= QUEUE_THRESHOLD) { + u32 count = vars->dq_count << PIE_SCALE; - 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 - vars->dq_tstamp; if (dtime == 0) return; count = count / dtime; - if (q->vars.avg_dq_rate == 0) - q->vars.avg_dq_rate = count; + if (vars->avg_dq_rate == 0) + vars->avg_dq_rate = count; else - q->vars.avg_dq_rate = - (q->vars.avg_dq_rate - - (q->vars.avg_dq_rate >> 3)) + (count >> 3); + vars->avg_dq_rate = + (vars->avg_dq_rate - + (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 @@ -311,43 +284,54 @@ static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb) * packet is dequeued */ if (qlen < QUEUE_THRESHOLD) { - q->vars.dq_count = DQCOUNT_INVALID; + vars->dq_count = DQCOUNT_INVALID; } else { - q->vars.dq_count = 0; - q->vars.dq_tstamp = psched_get_time(); + vars->dq_count = 0; + 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 (vars->burst_time > 0) { + if (vars->burst_time > dtime) + vars->burst_time -= dtime; + else + vars->burst_time = 0; + } } +EXPORT_SYMBOL_GPL(pie_process_dequeue); -static void calculate_probability(struct Qdisc *sch) +void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, + u32 qlen) { - 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 (params->dq_rate_estimator) { + qdelay_old = vars->qdelay; + vars->qdelay_old = vars->qdelay; - if (q->vars.avg_dq_rate > 0) - qdelay = (qlen << PIE_SCALE) / q->vars.avg_dq_rate; - else - qdelay = 0; + if (vars->avg_dq_rate > 0) + qdelay = (qlen << PIE_SCALE) / vars->avg_dq_rate; + else + qdelay = 0; + } else { + qdelay = vars->qdelay; + qdelay_old = 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 + /* If qdelay is zero and qlen is not, it means qlen is very small, + * so we do not update probabilty in this round. */ if (qdelay == 0 && qlen != 0) update_prob = false; @@ -359,18 +343,18 @@ static void calculate_probability(struct Qdisc *sch) * probability. alpha/beta are updated locally below by scaling down * by 16 to come to 0-2 range. */ - alpha = ((u64)q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; - beta = ((u64)q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; + alpha = ((u64)params->alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; + beta = ((u64)params->beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; /* We scale alpha and beta differently depending on how heavy the * congestion is. Please see RFC 8033 for details. */ - if (q->vars.prob < MAX_PROB / 10) { + if (vars->prob < MAX_PROB / 10) { alpha >>= 1; beta >>= 1; power = 100; - while (q->vars.prob < div_u64(MAX_PROB, power) && + while (vars->prob < div_u64(MAX_PROB, power) && power <= 1000000) { alpha >>= 2; beta >>= 2; @@ -379,14 +363,14 @@ static void calculate_probability(struct Qdisc *sch) } /* alpha and beta should be between 0 and 32, in multiples of 1/16 */ - delta += alpha * (u64)(qdelay - q->params.target); + delta += alpha * (u64)(qdelay - params->target); delta += beta * (u64)(qdelay - qdelay_old); - oldprob = q->vars.prob; + oldprob = vars->prob; /* to ensure we increase probability in steps of no more than 2% */ if (delta > (s64)(MAX_PROB / (100 / 2)) && - q->vars.prob >= MAX_PROB / 10) + vars->prob >= MAX_PROB / 10) delta = (MAX_PROB / 100) * 2; /* Non-linear drop: @@ -397,12 +381,12 @@ static void calculate_probability(struct Qdisc *sch) if (qdelay > (PSCHED_NS2TICKS(250 * NSEC_PER_MSEC))) delta += MAX_PROB / (100 / 2); - q->vars.prob += delta; + vars->prob += delta; if (delta > 0) { /* prevent overflow */ - if (q->vars.prob < oldprob) { - q->vars.prob = MAX_PROB; + if (vars->prob < oldprob) { + 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 @@ -412,8 +396,8 @@ static void calculate_probability(struct Qdisc *sch) } } else { /* prevent underflow */ - if (q->vars.prob > oldprob) - q->vars.prob = 0; + if (vars->prob > oldprob) + vars->prob = 0; } /* Non-linear drop in probability: Reduce drop probability quickly if @@ -422,23 +406,28 @@ static void calculate_probability(struct Qdisc *sch) if (qdelay == 0 && qdelay_old == 0 && update_prob) /* Reduce drop probability to 98.4% */ - q->vars.prob -= q->vars.prob / 64u; + vars->prob -= vars->prob / 64; - q->vars.qdelay = qdelay; - q->vars.qlen_old = qlen; + vars->qdelay = qdelay; + 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 + * 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) - pie_vars_init(&q->vars); + if ((vars->qdelay < params->target / 2) && + (vars->qdelay_old < params->target / 2) && + vars->prob == 0 && + (!params->dq_rate_estimator || vars->avg_dq_rate > 0)) { + pie_vars_init(vars); + } + + if (!params->dq_rate_estimator) + vars->qdelay_old = qdelay; } +EXPORT_SYMBOL_GPL(pie_calculate_probability); static void pie_timer(struct timer_list *t) { @@ -447,7 +436,7 @@ static void pie_timer(struct timer_list *t) spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); - calculate_probability(sch); + pie_calculate_probability(&q->params, &q->vars, sch->qstats.backlog); /* reset the timer to fire after 'tupdate'. tupdate is in jiffies. */ if (q->params.tupdate) @@ -497,7 +486,9 @@ 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 +505,6 @@ 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, @@ -524,17 +512,26 @@ 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)); } static struct sk_buff *pie_qdisc_dequeue(struct Qdisc *sch) { + struct pie_sched_data *q = qdisc_priv(sch); struct sk_buff *skb = qdisc_dequeue_head(sch); if (!skb) return NULL; - pie_process_dequeue(sch, skb); + pie_process_dequeue(skb, &q->params, &q->vars, sch->qstats.backlog); return skb; } @@ -555,7 +552,7 @@ static void pie_destroy(struct Qdisc *sch) } static struct Qdisc_ops pie_qdisc_ops __read_mostly = { - .id = "pie", + .id = "pie", .priv_size = sizeof(struct pie_sched_data), .enqueue = pie_qdisc_enqueue, .dequeue = pie_qdisc_dequeue, diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 0f8fedb8809a..647941702f9f 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -292,8 +292,14 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct tc_prio_qopt_offload graft_offload; unsigned long band = arg - 1; - if (new == NULL) - new = &noop_qdisc; + if (!new) { + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + TC_H_MAKE(sch->handle, arg), extack); + if (!new) + new = &noop_qdisc; + else + qdisc_hash_add(new, true); + } *old = qdisc_replace(sch, new, &q->queues[band]); @@ -356,7 +362,7 @@ 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 1dff8506a715..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; @@ -488,7 +489,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); - struct Qdisc *child; + struct Qdisc *child, *old; struct nlattr *tb[TCA_SFB_MAX + 1]; const struct tc_sfb_qopt *ctl = &sfb_default_ops; u32 limit; @@ -518,8 +519,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, qdisc_hash_add(child, true); sch_tree_lock(sch); - qdisc_tree_flush_backlog(q->qdisc); - qdisc_put(q->qdisc); + qdisc_purge_queue(q->qdisc); + old = q->qdisc; q->qdisc = child; q->rehash_interval = msecs_to_jiffies(ctl->rehash_interval); @@ -542,6 +543,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, sfb_init_perturbation(1, q); sch_tree_unlock(sch); + qdisc_put(old); return 0; } 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 e25d414ae12f..660fc45ee40f 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -29,8 +29,9 @@ static DEFINE_SPINLOCK(taprio_list_lock); #define TAPRIO_ALL_GATES_OPEN -1 -#define FLAGS_VALID(flags) (!((flags) & ~TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST)) #define TXTIME_ASSIST_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) +#define FULL_OFFLOAD_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD) +#define TAPRIO_FLAGS_INVALID U32_MAX struct sched_entry { struct list_head list; @@ -75,9 +76,16 @@ struct taprio_sched { struct sched_gate_list __rcu *admin_sched; struct hrtimer advance_timer; struct list_head taprio_list; + struct sk_buff *(*dequeue)(struct Qdisc *sch); + struct sk_buff *(*peek)(struct Qdisc *sch); u32 txtime_delay; }; +struct __tc_taprio_qopt_offload { + refcount_t users; + struct tc_taprio_qopt_offload offload; +}; + static ktime_t sched_base_time(const struct sched_gate_list *sched) { if (!sched) @@ -268,6 +276,19 @@ static bool is_valid_interval(struct sk_buff *skb, struct Qdisc *sch) return entry; } +static bool taprio_flags_valid(u32 flags) +{ + /* Make sure no other flag bits are set. */ + if (flags & ~(TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST | + TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD)) + return false; + /* txtime-assist and full offload are mutually exclusive */ + if ((flags & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) && + (flags & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD)) + return false; + return true; +} + /* This returns the tstamp value set by TCP in terms of the set clock. */ static ktime_t get_tcp_tstamp(struct taprio_sched *q, struct sk_buff *skb) { @@ -417,7 +438,7 @@ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, return qdisc_enqueue(skb, child, to_free); } -static struct sk_buff *taprio_peek(struct Qdisc *sch) +static struct sk_buff *taprio_peek_soft(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); @@ -461,6 +482,36 @@ static struct sk_buff *taprio_peek(struct Qdisc *sch) return NULL; } +static struct sk_buff *taprio_peek_offload(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sk_buff *skb; + int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct Qdisc *child = q->qdiscs[i]; + + if (unlikely(!child)) + continue; + + skb = child->ops->peek(child); + if (!skb) + continue; + + return skb; + } + + return NULL; +} + +static struct sk_buff *taprio_peek(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + + return q->peek(sch); +} + static void taprio_set_budget(struct taprio_sched *q, struct sched_entry *entry) { atomic_set(&entry->budget, @@ -468,7 +519,7 @@ static void taprio_set_budget(struct taprio_sched *q, struct sched_entry *entry) atomic64_read(&q->picos_per_byte))); } -static struct sk_buff *taprio_dequeue(struct Qdisc *sch) +static struct sk_buff *taprio_dequeue_soft(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); @@ -477,11 +528,6 @@ static struct sk_buff *taprio_dequeue(struct Qdisc *sch) u32 gate_mask; int i; - if (atomic64_read(&q->picos_per_byte) == -1) { - WARN_ONCE(1, "taprio: dequeue() called with unknown picos per byte."); - return NULL; - } - rcu_read_lock(); entry = rcu_dereference(q->current_entry); /* if there's no entry, it means that the schedule didn't @@ -555,6 +601,40 @@ done: return skb; } +static struct sk_buff *taprio_dequeue_offload(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sk_buff *skb; + int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct Qdisc *child = q->qdiscs[i]; + + if (unlikely(!child)) + continue; + + skb = child->ops->dequeue(child); + if (unlikely(!skb)) + continue; + + qdisc_bstats_update(sch, skb); + qdisc_qstats_backlog_dec(sch, skb); + sch->q.qlen--; + + return skb; + } + + return NULL; +} + +static struct sk_buff *taprio_dequeue(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + + return q->dequeue(sch); +} + static bool should_restart_cycle(const struct sched_gate_list *oper, const struct sched_entry *entry) { @@ -677,10 +757,6 @@ static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { [TCA_TAPRIO_SCHED_ENTRY_INTERVAL] = { .type = NLA_U32 }, }; -static const struct nla_policy entry_list_policy[TCA_TAPRIO_SCHED_MAX + 1] = { - [TCA_TAPRIO_SCHED_ENTRY] = { .type = NLA_NESTED }, -}; - static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_PRIOMAP] = { .len = sizeof(struct tc_mqprio_qopt) @@ -691,6 +767,7 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 }, [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 }, + [TCA_TAPRIO_ATTR_FLAGS] = { .type = NLA_U32 }, }; static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, @@ -847,7 +924,7 @@ 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; @@ -941,6 +1018,9 @@ static void taprio_start_sched(struct Qdisc *sch, struct taprio_sched *q = qdisc_priv(sch); ktime_t expires; + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) + return; + expires = hrtimer_get_expires(&q->advance_timer); if (expires == 0) expires = KTIME_MAX; @@ -958,12 +1038,19 @@ static void taprio_set_picos_per_byte(struct net_device *dev, struct taprio_sched *q) { struct ethtool_link_ksettings ecmd; - int picos_per_byte = -1; + int speed = SPEED_10; + int picos_per_byte; + int err; + + err = __ethtool_get_link_ksettings(dev, &ecmd); + if (err < 0) + goto skip; + + if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN) + speed = ecmd.base.speed; - if (!__ethtool_get_link_ksettings(dev, &ecmd) && - ecmd.base.speed != SPEED_UNKNOWN) - picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8, - ecmd.base.speed * 1000 * 1000); +skip: + 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", @@ -1012,6 +1099,303 @@ static void setup_txtime(struct taprio_sched *q, } } +static struct tc_taprio_qopt_offload *taprio_offload_alloc(int num_entries) +{ + size_t size = sizeof(struct tc_taprio_sched_entry) * num_entries + + sizeof(struct __tc_taprio_qopt_offload); + struct __tc_taprio_qopt_offload *__offload; + + __offload = kzalloc(size, GFP_KERNEL); + if (!__offload) + return NULL; + + refcount_set(&__offload->users, 1); + + return &__offload->offload; +} + +struct tc_taprio_qopt_offload *taprio_offload_get(struct tc_taprio_qopt_offload + *offload) +{ + struct __tc_taprio_qopt_offload *__offload; + + __offload = container_of(offload, struct __tc_taprio_qopt_offload, + offload); + + refcount_inc(&__offload->users); + + return offload; +} +EXPORT_SYMBOL_GPL(taprio_offload_get); + +void taprio_offload_free(struct tc_taprio_qopt_offload *offload) +{ + struct __tc_taprio_qopt_offload *__offload; + + __offload = container_of(offload, struct __tc_taprio_qopt_offload, + offload); + + if (!refcount_dec_and_test(&__offload->users)) + return; + + kfree(__offload); +} +EXPORT_SYMBOL_GPL(taprio_offload_free); + +/* The function will only serve to keep the pointers to the "oper" and "admin" + * schedules valid in relation to their base times, so when calling dump() the + * users looks at the right schedules. + * When using full offload, the admin configuration is promoted to oper at the + * base_time in the PHC time domain. But because the system time is not + * necessarily in sync with that, we can't just trigger a hrtimer to call + * switch_schedules at the right hardware time. + * At the moment we call this by hand right away from taprio, but in the future + * it will be useful to create a mechanism for drivers to notify taprio of the + * offload state (PENDING, ACTIVE, INACTIVE) so it can be visible in dump(). + * This is left as TODO. + */ +static void taprio_offload_config_changed(struct taprio_sched *q) +{ + struct sched_gate_list *oper, *admin; + + spin_lock(&q->current_entry_lock); + + oper = rcu_dereference_protected(q->oper_sched, + lockdep_is_held(&q->current_entry_lock)); + admin = rcu_dereference_protected(q->admin_sched, + lockdep_is_held(&q->current_entry_lock)); + + switch_schedules(q, &admin, &oper); + + spin_unlock(&q->current_entry_lock); +} + +static void taprio_sched_to_offload(struct taprio_sched *q, + struct sched_gate_list *sched, + const struct tc_mqprio_qopt *mqprio, + struct tc_taprio_qopt_offload *offload) +{ + struct sched_entry *entry; + int i = 0; + + offload->base_time = sched->base_time; + offload->cycle_time = sched->cycle_time; + offload->cycle_time_extension = sched->cycle_time_extension; + + list_for_each_entry(entry, &sched->entries, list) { + struct tc_taprio_sched_entry *e = &offload->entries[i]; + + e->command = entry->command; + e->interval = entry->interval; + e->gate_mask = entry->gate_mask; + i++; + } + + offload->num_entries = i; +} + +static int taprio_enable_offload(struct net_device *dev, + struct tc_mqprio_qopt *mqprio, + struct taprio_sched *q, + struct sched_gate_list *sched, + struct netlink_ext_ack *extack) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct tc_taprio_qopt_offload *offload; + int err = 0; + + if (!ops->ndo_setup_tc) { + NL_SET_ERR_MSG(extack, + "Device does not support taprio offload"); + return -EOPNOTSUPP; + } + + offload = taprio_offload_alloc(sched->num_entries); + if (!offload) { + NL_SET_ERR_MSG(extack, + "Not enough memory for enabling offload mode"); + return -ENOMEM; + } + offload->enable = 1; + taprio_sched_to_offload(q, sched, mqprio, offload); + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); + if (err < 0) { + NL_SET_ERR_MSG(extack, + "Device failed to setup taprio offload"); + goto done; + } + +done: + taprio_offload_free(offload); + + return err; +} + +static int taprio_disable_offload(struct net_device *dev, + struct taprio_sched *q, + struct netlink_ext_ack *extack) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct tc_taprio_qopt_offload *offload; + int err; + + if (!FULL_OFFLOAD_IS_ENABLED(q->flags)) + return 0; + + if (!ops->ndo_setup_tc) + return -EOPNOTSUPP; + + offload = taprio_offload_alloc(0); + if (!offload) { + NL_SET_ERR_MSG(extack, + "Not enough memory to disable offload mode"); + return -ENOMEM; + } + offload->enable = 0; + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); + if (err < 0) { + NL_SET_ERR_MSG(extack, + "Device failed to disable offload"); + goto out; + } + +out: + taprio_offload_free(offload); + + return err; +} + +/* If full offload is enabled, the only possible clockid is the net device's + * PHC. For that reason, specifying a clockid through netlink is incorrect. + * For txtime-assist, it is implicitly assumed that the device's PHC is kept + * in sync with the specified clockid via a user space daemon such as phc2sys. + * For both software taprio and txtime-assist, the clockid is used for the + * hrtimer that advances the schedule and hence mandatory. + */ +static int taprio_parse_clockid(struct Qdisc *sch, struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int err = -EINVAL; + + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_ts_info info = { + .cmd = ETHTOOL_GET_TS_INFO, + .phc_index = -1, + }; + + if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { + NL_SET_ERR_MSG(extack, + "The 'clockid' cannot be specified for full offload"); + goto out; + } + + if (ops && ops->get_ts_info) + err = ops->get_ts_info(dev, &info); + + if (err || info.phc_index < 0) { + NL_SET_ERR_MSG(extack, + "Device does not have a PTP clock"); + err = -ENOTSUPP; + goto out; + } + } else if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { + int clockid = nla_get_s32(tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]); + + /* We only support static clockids and we don't allow + * for it to be modified after the first init. + */ + if (clockid < 0 || + (q->clockid != -1 && q->clockid != clockid)) { + NL_SET_ERR_MSG(extack, + "Changing the 'clockid' of a running schedule is not supported"); + err = -ENOTSUPP; + goto out; + } + + switch (clockid) { + case CLOCK_REALTIME: + q->tk_offset = TK_OFFS_REAL; + break; + case CLOCK_MONOTONIC: + q->tk_offset = TK_OFFS_MAX; + break; + case CLOCK_BOOTTIME: + q->tk_offset = TK_OFFS_BOOT; + break; + case CLOCK_TAI: + q->tk_offset = TK_OFFS_TAI; + break; + default: + NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); + err = -EINVAL; + goto out; + } + + q->clockid = clockid; + } else { + 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; +} + +/* The semantics of the 'flags' argument in relation to 'change()' + * requests, are interpreted following two rules (which are applied in + * this order): (1) an omitted 'flags' argument is interpreted as + * zero; (2) the 'flags' of a "running" taprio instance cannot be + * changed. + */ +static int taprio_new_flags(const struct nlattr *attr, u32 old, + struct netlink_ext_ack *extack) +{ + u32 new = 0; + + if (attr) + new = nla_get_u32(attr); + + if (old != TAPRIO_FLAGS_INVALID && old != new) { + NL_SET_ERR_MSG_MOD(extack, "Changing 'flags' of a running schedule is not supported"); + return -EOPNOTSUPP; + } + + if (!taprio_flags_valid(new)) { + NL_SET_ERR_MSG_MOD(extack, "Specified 'flags' are not valid"); + return -EINVAL; + } + + return new; +} + static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -1020,10 +1404,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct tc_mqprio_qopt *mqprio = NULL; - u32 taprio_flags = 0; - int i, err, clockid; unsigned long flags; ktime_t start; + int i, err; err = nla_parse_nested_deprecated(tb, TCA_TAPRIO_ATTR_MAX, opt, taprio_policy, extack); @@ -1033,21 +1416,14 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_TAPRIO_ATTR_PRIOMAP]) mqprio = nla_data(tb[TCA_TAPRIO_ATTR_PRIOMAP]); - if (tb[TCA_TAPRIO_ATTR_FLAGS]) { - taprio_flags = nla_get_u32(tb[TCA_TAPRIO_ATTR_FLAGS]); - - if (q->flags != 0 && q->flags != taprio_flags) { - NL_SET_ERR_MSG_MOD(extack, "Changing 'flags' of a running schedule is not supported"); - return -EOPNOTSUPP; - } else if (!FLAGS_VALID(taprio_flags)) { - NL_SET_ERR_MSG_MOD(extack, "Specified 'flags' are not valid"); - return -EINVAL; - } + err = taprio_new_flags(tb[TCA_TAPRIO_ATTR_FLAGS], + q->flags, extack); + if (err < 0) + return err; - q->flags = taprio_flags; - } + q->flags = err; - err = taprio_parse_mqprio_opt(dev, mqprio, extack, taprio_flags); + err = taprio_parse_mqprio_opt(dev, mqprio, extack, q->flags); if (err < 0) return err; @@ -1063,6 +1439,10 @@ 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; @@ -1079,29 +1459,31 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, goto free_sched; } - if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { - clockid = nla_get_s32(tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]); + err = taprio_parse_clockid(sch, tb, extack); + if (err < 0) + goto free_sched; - /* We only support static clockids and we don't allow - * for it to be modified after the first init. - */ - if (clockid < 0 || - (q->clockid != -1 && q->clockid != clockid)) { - NL_SET_ERR_MSG(extack, "Changing the 'clockid' of a running schedule is not supported"); - err = -ENOTSUPP; - goto free_sched; - } + taprio_set_picos_per_byte(dev, q); - q->clockid = clockid; - } + if (mqprio) { + netdev_set_num_tc(dev, mqprio->num_tc); + for (i = 0; i < mqprio->num_tc; i++) + netdev_set_tc_queue(dev, i, + mqprio->count[i], + mqprio->offset[i]); - if (q->clockid == -1 && !tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { - NL_SET_ERR_MSG(extack, "Specifying a 'clockid' is mandatory"); - err = -EINVAL; - goto free_sched; + /* Always use supplied priority mappings */ + for (i = 0; i <= TC_BITMASK; i++) + netdev_set_prio_tc_map(dev, i, + mqprio->prio_tc_map[i]); } - taprio_set_picos_per_byte(dev, q); + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) + err = taprio_enable_offload(dev, mqprio, q, new_admin, extack); + else + err = taprio_disable_offload(dev, q, extack); + if (err) + goto free_sched; /* Protects against enqueue()/dequeue() */ spin_lock_bh(qdisc_lock(sch)); @@ -1116,42 +1498,22 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, q->txtime_delay = nla_get_u32(tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]); } - if (!TXTIME_ASSIST_IS_ENABLED(taprio_flags) && + if (!TXTIME_ASSIST_IS_ENABLED(q->flags) && + !FULL_OFFLOAD_IS_ENABLED(q->flags) && !hrtimer_active(&q->advance_timer)) { hrtimer_init(&q->advance_timer, q->clockid, HRTIMER_MODE_ABS); q->advance_timer.function = advance_sched; } - if (mqprio) { - netdev_set_num_tc(dev, mqprio->num_tc); - for (i = 0; i < mqprio->num_tc; i++) - netdev_set_tc_queue(dev, i, - mqprio->count[i], - mqprio->offset[i]); - - /* Always use supplied priority mappings */ - for (i = 0; i < TC_BITMASK + 1; i++) - netdev_set_prio_tc_map(dev, i, - mqprio->prio_tc_map[i]); - } - - switch (q->clockid) { - case CLOCK_REALTIME: - q->tk_offset = TK_OFFS_REAL; - break; - case CLOCK_MONOTONIC: - q->tk_offset = TK_OFFS_MAX; - break; - case CLOCK_BOOTTIME: - q->tk_offset = TK_OFFS_BOOT; - break; - case CLOCK_TAI: - q->tk_offset = TK_OFFS_TAI; - break; - default: - NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); - err = -EINVAL; - goto unlock; + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { + q->dequeue = taprio_dequeue_offload; + q->peek = taprio_peek_offload; + } else { + /* Be sure to always keep the function pointers + * in a consistent state. + */ + q->dequeue = taprio_dequeue_soft; + q->peek = taprio_peek_soft; } err = taprio_get_start_time(sch, new_admin, &start); @@ -1160,9 +1522,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, goto unlock; } - if (TXTIME_ASSIST_IS_ENABLED(taprio_flags)) { - setup_txtime(q, new_admin, start); + setup_txtime(q, new_admin, start); + if (TXTIME_ASSIST_IS_ENABLED(q->flags)) { if (!oper) { rcu_assign_pointer(q->oper_sched, new_admin); err = 0; @@ -1186,6 +1548,9 @@ 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(q->flags)) + taprio_offload_config_changed(q); } new_admin = NULL; @@ -1213,6 +1578,8 @@ static void taprio_destroy(struct Qdisc *sch) hrtimer_cancel(&q->advance_timer); + taprio_disable_offload(dev, q, NULL); + if (q->qdiscs) { for (i = 0; i < dev->num_tx_queues && q->qdiscs[i]; i++) qdisc_put(q->qdiscs[i]); @@ -1221,7 +1588,7 @@ static void taprio_destroy(struct Qdisc *sch) } q->qdiscs = NULL; - netdev_set_num_tc(dev, 0); + netdev_reset_tc(dev); if (q->oper_sched) call_rcu(&q->oper_sched->rcu, taprio_free_sched_cb); @@ -1242,12 +1609,20 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt, hrtimer_init(&q->advance_timer, CLOCK_TAI, HRTIMER_MODE_ABS); q->advance_timer.function = advance_sched; + q->dequeue = taprio_dequeue_soft; + q->peek = taprio_peek_soft; + q->root = sch; /* We only support static clockids. Use an invalid value as default * and get the valid one on taprio_change(). */ q->clockid = -1; + q->flags = TAPRIO_FLAGS_INVALID; + + spin_lock(&taprio_list_lock); + list_add(&q->taprio_list, &taprio_list); + spin_unlock(&taprio_list_lock); if (sch->parent != TC_H_ROOT) return -EOPNOTSUPP; @@ -1266,10 +1641,6 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt, if (!opt) return -EINVAL; - spin_lock(&taprio_list_lock); - list_add(&q->taprio_list, &taprio_list); - spin_unlock(&taprio_list_lock); - for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *dev_queue; struct Qdisc *qdisc; @@ -1424,7 +1795,8 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_TAPRIO_ATTR_PRIOMAP, sizeof(opt), &opt)) goto options_error; - if (nla_put_s32(skb, TCA_TAPRIO_ATTR_SCHED_CLOCKID, q->clockid)) + if (!FULL_OFFLOAD_IS_ENABLED(q->flags) && + nla_put_s32(skb, TCA_TAPRIO_ATTR_SCHED_CLOCKID, q->clockid)) goto options_error; if (q->flags && nla_put_u32(skb, TCA_TAPRIO_ATTR_FLAGS, q->flags)) diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 5f72f3f916a5..78e79029dc63 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -15,6 +15,7 @@ #include <linux/skbuff.h> #include <net/netlink.h> #include <net/sch_generic.h> +#include <net/pkt_cls.h> #include <net/pkt_sched.h> @@ -137,6 +138,52 @@ static u64 psched_ns_t2l(const struct psched_ratecfg *r, return len; } +static void tbf_offload_change(struct Qdisc *sch) +{ + struct tbf_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_tbf_qopt_offload qopt; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_TBF_REPLACE; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.replace_params.rate = q->rate; + qopt.replace_params.max_size = q->max_size; + qopt.replace_params.qstats = &sch->qstats; + + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TBF, &qopt); +} + +static void tbf_offload_destroy(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_tbf_qopt_offload qopt; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_TBF_DESTROY; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TBF, &qopt); +} + +static int tbf_offload_dump(struct Qdisc *sch) +{ + struct tc_tbf_qopt_offload qopt; + + qopt.command = TC_TBF_STATS; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.stats.bstats = &sch->bstats; + qopt.stats.qstats = &sch->qstats; + + return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_TBF, &qopt); +} + /* GSO packet is too big, segment it so that tbf can transmit * each segment in time */ @@ -155,8 +202,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, return qdisc_drop(skb, sch, to_free); nb = 0; - while (segs) { - nskb = segs->next; + skb_list_walk_safe(segs, segs, nskb) { skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; len += segs->len; @@ -167,7 +213,6 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, } else { nb++; } - segs = nskb; } sch->q.qlen += nb; if (nb > 1) @@ -409,6 +454,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_unlock(sch); err = 0; + + tbf_offload_change(sch); done: return err; } @@ -434,6 +481,7 @@ static void tbf_destroy(struct Qdisc *sch) struct tbf_sched_data *q = qdisc_priv(sch); qdisc_watchdog_cancel(&q->watchdog); + tbf_offload_destroy(sch); qdisc_put(q->qdisc); } @@ -442,8 +490,12 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb) struct tbf_sched_data *q = qdisc_priv(sch); struct nlattr *nest; struct tc_tbf_qopt opt; + int err; + + err = tbf_offload_dump(sch); + if (err) + return err; - sch->qstats.backlog = q->qdisc->qstats.backlog; nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; |
