diff options
Diffstat (limited to 'net/sched')
33 files changed, 1183 insertions, 360 deletions
diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 3258da3d5bed..32563cef85bf 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -19,8 +19,10 @@ #include <net/sock.h> #include <net/sch_generic.h> #include <net/pkt_cls.h> +#include <net/tc_act/tc_pedit.h> #include <net/act_api.h> #include <net/netlink.h> +#include <net/flow_offload.h> #ifdef CONFIG_INET DEFINE_STATIC_KEY_FALSE(tcf_frag_xmit_count); @@ -129,8 +131,244 @@ static void free_tcf(struct tc_action *p) kfree(p); } +static void offload_action_hw_count_set(struct tc_action *act, + u32 hw_count) +{ + act->in_hw_count = hw_count; +} + +static void offload_action_hw_count_inc(struct tc_action *act, + u32 hw_count) +{ + act->in_hw_count += hw_count; +} + +static void offload_action_hw_count_dec(struct tc_action *act, + u32 hw_count) +{ + act->in_hw_count = act->in_hw_count > hw_count ? + act->in_hw_count - hw_count : 0; +} + +static unsigned int tcf_offload_act_num_actions_single(struct tc_action *act) +{ + if (is_tcf_pedit(act)) + return tcf_pedit_nkeys(act); + else + return 1; +} + +static bool tc_act_skip_hw(u32 flags) +{ + return (flags & TCA_ACT_FLAGS_SKIP_HW) ? true : false; +} + +static bool tc_act_skip_sw(u32 flags) +{ + return (flags & TCA_ACT_FLAGS_SKIP_SW) ? true : false; +} + +static bool tc_act_in_hw(struct tc_action *act) +{ + return !!act->in_hw_count; +} + +/* SKIP_HW and SKIP_SW are mutually exclusive flags. */ +static bool tc_act_flags_valid(u32 flags) +{ + flags &= TCA_ACT_FLAGS_SKIP_HW | TCA_ACT_FLAGS_SKIP_SW; + + return flags ^ (TCA_ACT_FLAGS_SKIP_HW | TCA_ACT_FLAGS_SKIP_SW); +} + +static int offload_action_init(struct flow_offload_action *fl_action, + struct tc_action *act, + enum offload_act_command cmd, + struct netlink_ext_ack *extack) +{ + int err; + + fl_action->extack = extack; + fl_action->command = cmd; + fl_action->index = act->tcfa_index; + + if (act->ops->offload_act_setup) { + spin_lock_bh(&act->tcfa_lock); + err = act->ops->offload_act_setup(act, fl_action, NULL, + false); + spin_unlock_bh(&act->tcfa_lock); + return err; + } + + return -EOPNOTSUPP; +} + +static int tcf_action_offload_cmd_ex(struct flow_offload_action *fl_act, + u32 *hw_count) +{ + int err; + + err = flow_indr_dev_setup_offload(NULL, NULL, TC_SETUP_ACT, + fl_act, NULL, NULL); + if (err < 0) + return err; + + if (hw_count) + *hw_count = err; + + return 0; +} + +static int tcf_action_offload_cmd_cb_ex(struct flow_offload_action *fl_act, + u32 *hw_count, + flow_indr_block_bind_cb_t *cb, + void *cb_priv) +{ + int err; + + err = cb(NULL, NULL, cb_priv, TC_SETUP_ACT, NULL, fl_act, NULL); + if (err < 0) + return err; + + if (hw_count) + *hw_count = 1; + + return 0; +} + +static int tcf_action_offload_cmd(struct flow_offload_action *fl_act, + u32 *hw_count, + flow_indr_block_bind_cb_t *cb, + void *cb_priv) +{ + return cb ? tcf_action_offload_cmd_cb_ex(fl_act, hw_count, + cb, cb_priv) : + tcf_action_offload_cmd_ex(fl_act, hw_count); +} + +static int tcf_action_offload_add_ex(struct tc_action *action, + struct netlink_ext_ack *extack, + flow_indr_block_bind_cb_t *cb, + void *cb_priv) +{ + bool skip_sw = tc_act_skip_sw(action->tcfa_flags); + struct tc_action *actions[TCA_ACT_MAX_PRIO] = { + [0] = action, + }; + struct flow_offload_action *fl_action; + u32 in_hw_count = 0; + int num, err = 0; + + if (tc_act_skip_hw(action->tcfa_flags)) + return 0; + + num = tcf_offload_act_num_actions_single(action); + fl_action = offload_action_alloc(num); + if (!fl_action) + return -ENOMEM; + + err = offload_action_init(fl_action, action, FLOW_ACT_REPLACE, extack); + if (err) + goto fl_err; + + err = tc_setup_action(&fl_action->action, actions); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to setup tc actions for offload\n"); + goto fl_err; + } + + err = tcf_action_offload_cmd(fl_action, &in_hw_count, cb, cb_priv); + if (!err) + cb ? offload_action_hw_count_inc(action, in_hw_count) : + offload_action_hw_count_set(action, in_hw_count); + + if (skip_sw && !tc_act_in_hw(action)) + err = -EINVAL; + + tc_cleanup_offload_action(&fl_action->action); + +fl_err: + kfree(fl_action); + + return err; +} + +/* offload the tc action after it is inserted */ +static int tcf_action_offload_add(struct tc_action *action, + struct netlink_ext_ack *extack) +{ + return tcf_action_offload_add_ex(action, extack, NULL, NULL); +} + +int tcf_action_update_hw_stats(struct tc_action *action) +{ + struct flow_offload_action fl_act = {}; + int err; + + if (!tc_act_in_hw(action)) + return -EOPNOTSUPP; + + err = offload_action_init(&fl_act, action, FLOW_ACT_STATS, NULL); + if (err) + return err; + + err = tcf_action_offload_cmd(&fl_act, NULL, NULL, NULL); + if (!err) { + preempt_disable(); + tcf_action_stats_update(action, fl_act.stats.bytes, + fl_act.stats.pkts, + fl_act.stats.drops, + fl_act.stats.lastused, + true); + preempt_enable(); + action->used_hw_stats = fl_act.stats.used_hw_stats; + action->used_hw_stats_valid = true; + } else { + return -EOPNOTSUPP; + } + + return 0; +} +EXPORT_SYMBOL(tcf_action_update_hw_stats); + +static int tcf_action_offload_del_ex(struct tc_action *action, + flow_indr_block_bind_cb_t *cb, + void *cb_priv) +{ + struct flow_offload_action fl_act = {}; + u32 in_hw_count = 0; + int err = 0; + + if (!tc_act_in_hw(action)) + return 0; + + err = offload_action_init(&fl_act, action, FLOW_ACT_DESTROY, NULL); + if (err) + return err; + + err = tcf_action_offload_cmd(&fl_act, &in_hw_count, cb, cb_priv); + if (err < 0) + return err; + + if (!cb && action->in_hw_count != in_hw_count) + return -EINVAL; + + /* do not need to update hw state when deleting action */ + if (cb && in_hw_count) + offload_action_hw_count_dec(action, in_hw_count); + + return 0; +} + +static int tcf_action_offload_del(struct tc_action *action) +{ + return tcf_action_offload_del_ex(action, NULL, NULL); +} + static void tcf_action_cleanup(struct tc_action *p) { + tcf_action_offload_del(p); if (p->ops->cleanup) p->ops->cleanup(p); @@ -497,7 +735,7 @@ 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 & TCA_ACT_FLAGS_USER_MASK; + p->tcfa_flags = flags; if (est) { err = gen_new_estimator(&p->tcfa_bstats, p->cpu_bstats, &p->tcfa_rate_est, @@ -622,6 +860,59 @@ EXPORT_SYMBOL(tcf_idrinfo_destroy); static LIST_HEAD(act_base); static DEFINE_RWLOCK(act_mod_lock); +/* since act ops id is stored in pernet subsystem list, + * then there is no way to walk through only all the action + * subsystem, so we keep tc action pernet ops id for + * reoffload to walk through. + */ +static LIST_HEAD(act_pernet_id_list); +static DEFINE_MUTEX(act_id_mutex); +struct tc_act_pernet_id { + struct list_head list; + unsigned int id; +}; + +static int tcf_pernet_add_id_list(unsigned int id) +{ + struct tc_act_pernet_id *id_ptr; + int ret = 0; + + mutex_lock(&act_id_mutex); + list_for_each_entry(id_ptr, &act_pernet_id_list, list) { + if (id_ptr->id == id) { + ret = -EEXIST; + goto err_out; + } + } + + id_ptr = kzalloc(sizeof(*id_ptr), GFP_KERNEL); + if (!id_ptr) { + ret = -ENOMEM; + goto err_out; + } + id_ptr->id = id; + + list_add_tail(&id_ptr->list, &act_pernet_id_list); + +err_out: + mutex_unlock(&act_id_mutex); + return ret; +} + +static void tcf_pernet_del_id_list(unsigned int id) +{ + struct tc_act_pernet_id *id_ptr; + + mutex_lock(&act_id_mutex); + list_for_each_entry(id_ptr, &act_pernet_id_list, list) { + if (id_ptr->id == id) { + list_del(&id_ptr->list); + kfree(id_ptr); + break; + } + } + mutex_unlock(&act_id_mutex); +} int tcf_register_action(struct tc_action_ops *act, struct pernet_operations *ops) @@ -640,18 +931,31 @@ int tcf_register_action(struct tc_action_ops *act, if (ret) return ret; + if (ops->id) { + ret = tcf_pernet_add_id_list(*ops->id); + if (ret) + goto err_id; + } + write_lock(&act_mod_lock); list_for_each_entry(a, &act_base, head) { if (act->id == a->id || (strcmp(act->kind, a->kind) == 0)) { - write_unlock(&act_mod_lock); - unregister_pernet_subsys(ops); - return -EEXIST; + ret = -EEXIST; + goto err_out; } } list_add_tail(&act->head, &act_base); write_unlock(&act_mod_lock); return 0; + +err_out: + write_unlock(&act_mod_lock); + if (ops->id) + tcf_pernet_del_id_list(*ops->id); +err_id: + unregister_pernet_subsys(ops); + return ret; } EXPORT_SYMBOL(tcf_register_action); @@ -670,8 +974,11 @@ int tcf_unregister_action(struct tc_action_ops *act, } } write_unlock(&act_mod_lock); - if (!err) + if (!err) { unregister_pernet_subsys(ops); + if (ops->id) + tcf_pernet_del_id_list(*ops->id); + } return err; } EXPORT_SYMBOL(tcf_unregister_action); @@ -735,6 +1042,9 @@ restart_act_graph: jmp_prgcnt -= 1; continue; } + + if (tc_act_skip_sw(a->tcfa_flags)) + continue; repeat: ret = a->ops->act(skb, a, res); if (ret == TC_ACT_REPEAT) @@ -821,6 +1131,7 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) int err = -EINVAL; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; + u32 flags; if (tcf_action_dump_terse(skb, a, false)) goto nla_put_failure; @@ -835,9 +1146,13 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) a->used_hw_stats, TCA_ACT_HW_STATS_ANY)) goto nla_put_failure; - if (a->tcfa_flags && + flags = a->tcfa_flags & TCA_ACT_FLAGS_USER_MASK; + if (flags && nla_put_bitfield32(skb, TCA_ACT_FLAGS, - a->tcfa_flags, a->tcfa_flags)) + flags, flags)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_ACT_IN_HW_COUNT, a->in_hw_count)) goto nla_put_failure; nest = nla_nest_start_noflag(skb, TCA_OPTIONS); @@ -919,7 +1234,9 @@ static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = { [TCA_ACT_COOKIE] = { .type = NLA_BINARY, .len = TC_COOKIE_MAX_SIZE }, [TCA_ACT_OPTIONS] = { .type = NLA_NESTED }, - [TCA_ACT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_ACT_FLAGS_NO_PERCPU_STATS), + [TCA_ACT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_ACT_FLAGS_NO_PERCPU_STATS | + TCA_ACT_FLAGS_SKIP_HW | + TCA_ACT_FLAGS_SKIP_SW), [TCA_ACT_HW_STATS] = NLA_POLICY_BITFIELD32(TCA_ACT_HW_STATS_ANY), }; @@ -1032,8 +1349,13 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, } } hw_stats = tcf_action_hw_stats_get(tb[TCA_ACT_HW_STATS]); - if (tb[TCA_ACT_FLAGS]) + if (tb[TCA_ACT_FLAGS]) { userflags = nla_get_bitfield32(tb[TCA_ACT_FLAGS]); + if (!tc_act_flags_valid(userflags.value)) { + err = -EINVAL; + goto err_out; + } + } err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, tp, userflags.value | flags, extack); @@ -1061,11 +1383,17 @@ err_out: return ERR_PTR(err); } +static bool tc_act_bind(u32 flags) +{ + return !!(flags & TCA_ACT_FLAGS_BIND); +} + /* Returns numbers of initialized actions or negative error. */ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, struct tc_action *actions[], - int init_res[], size_t *attr_size, u32 flags, + int init_res[], size_t *attr_size, + u32 flags, u32 fl_flags, struct netlink_ext_ack *extack) { struct tc_action_ops *ops[TCA_ACT_MAX_PRIO] = {}; @@ -1103,6 +1431,22 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, sz += tcf_action_fill_size(act); /* Start from index 0 */ actions[i - 1] = act; + if (tc_act_bind(flags)) { + bool skip_sw = tc_skip_sw(fl_flags); + bool skip_hw = tc_skip_hw(fl_flags); + + if (tc_act_bind(act->tcfa_flags)) + continue; + if (skip_sw != tc_act_skip_sw(act->tcfa_flags) || + skip_hw != tc_act_skip_hw(act->tcfa_flags)) { + err = -EINVAL; + goto err; + } + } else { + err = tcf_action_offload_add(act, extack); + if (tc_act_skip_sw(act->tcfa_flags) && err) + goto err; + } } /* We have to commit them all together, because if any error happened in @@ -1154,6 +1498,9 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p, if (p == NULL) goto errout; + /* update hw stats for this action */ + tcf_action_update_hw_stats(p); + /* compat_mode being true specifies a call that is supposed * to add additional backward compatibility statistic TLVs. */ @@ -1396,6 +1743,96 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[]) } static int +tcf_reoffload_del_notify(struct net *net, struct tc_action *action) +{ + size_t attr_size = tcf_action_fill_size(action); + struct tc_action *actions[TCA_ACT_MAX_PRIO] = { + [0] = action, + }; + const struct tc_action_ops *ops = action->ops; + struct sk_buff *skb; + int ret; + + skb = alloc_skb(attr_size <= NLMSG_GOODSIZE ? NLMSG_GOODSIZE : attr_size, + GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (tca_get_fill(skb, actions, 0, 0, 0, RTM_DELACTION, 0, 1) <= 0) { + kfree_skb(skb); + return -EINVAL; + } + + ret = tcf_idr_release_unsafe(action); + if (ret == ACT_P_DELETED) { + module_put(ops->owner); + ret = rtnetlink_send(skb, net, 0, RTNLGRP_TC, 0); + } else { + kfree_skb(skb); + } + + return ret; +} + +int tcf_action_reoffload_cb(flow_indr_block_bind_cb_t *cb, + void *cb_priv, bool add) +{ + struct tc_act_pernet_id *id_ptr; + struct tcf_idrinfo *idrinfo; + struct tc_action_net *tn; + struct tc_action *p; + unsigned int act_id; + unsigned long tmp; + unsigned long id; + struct idr *idr; + struct net *net; + int ret; + + if (!cb) + return -EINVAL; + + down_read(&net_rwsem); + mutex_lock(&act_id_mutex); + + for_each_net(net) { + list_for_each_entry(id_ptr, &act_pernet_id_list, list) { + act_id = id_ptr->id; + tn = net_generic(net, act_id); + if (!tn) + continue; + idrinfo = tn->idrinfo; + if (!idrinfo) + continue; + + mutex_lock(&idrinfo->lock); + idr = &idrinfo->action_idr; + idr_for_each_entry_ul(idr, p, tmp, id) { + if (IS_ERR(p) || tc_act_bind(p->tcfa_flags)) + continue; + if (add) { + tcf_action_offload_add_ex(p, NULL, cb, + cb_priv); + continue; + } + + /* cb unregister to update hw count */ + ret = tcf_action_offload_del_ex(p, cb, cb_priv); + if (ret < 0) + continue; + if (tc_act_skip_sw(p->tcfa_flags) && + !tc_act_in_hw(p)) + tcf_reoffload_del_notify(net, p); + } + mutex_unlock(&idrinfo->lock); + } + } + mutex_unlock(&act_id_mutex); + up_read(&net_rwsem); + + return 0; +} + +static int tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], u32 portid, size_t attr_size, struct netlink_ext_ack *extack) { @@ -1508,7 +1945,7 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, for (loop = 0; loop < 10; loop++) { ret = tcf_action_init(net, NULL, nla, NULL, actions, init_res, - &attr_size, flags, extack); + &attr_size, flags, 0, extack); if (ret != -EAGAIN) break; } diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index f2bf896331a5..a77d8908e737 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -305,7 +305,7 @@ 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, 0); + &act_bpf_ops, bind, true, flags); if (ret < 0) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 94e78ac7a748..09e2aafc8943 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -124,7 +124,7 @@ 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, 0); + &act_connmark_ops, bind, false, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index a15ec95e69c3..e0f515b774ca 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -695,6 +695,24 @@ static size_t tcf_csum_get_fill_size(const struct tc_action *act) return nla_total_size(sizeof(struct tc_csum)); } +static int tcf_csum_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind) +{ + if (bind) { + struct flow_action_entry *entry = entry_data; + + entry->id = FLOW_ACTION_CSUM; + entry->csum_flags = tcf_csum_update_flags(act); + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + fl_action->id = FLOW_ACTION_CSUM; + } + + return 0; +} + static struct tc_action_ops act_csum_ops = { .kind = "csum", .id = TCA_ID_CSUM, @@ -706,6 +724,7 @@ static struct tc_action_ops act_csum_ops = { .walk = tcf_csum_walker, .lookup = tcf_csum_search, .get_fill_size = tcf_csum_get_fill_size, + .offload_act_setup = tcf_csum_offload_act_setup, .size = sizeof(struct tcf_csum), }; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 90866ae45573..f99247fc6468 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -32,6 +32,7 @@ #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> +#include <net/netfilter/nf_conntrack_act_ct.h> #include <uapi/linux/netfilter/nf_nat.h> static struct workqueue_struct *act_ct_wq; @@ -56,6 +57,12 @@ static const struct rhashtable_params zones_params = { .automatic_shrinking = true, }; +static struct nf_ct_ext_type act_ct_extend __read_mostly = { + .len = sizeof(struct nf_conn_act_ct_ext), + .align = __alignof__(struct nf_conn_act_ct_ext), + .id = NF_CT_EXT_ACT_CT, +}; + static struct flow_action_entry * tcf_ct_flow_table_flow_action_get_next(struct flow_action *flow_action) { @@ -358,6 +365,7 @@ static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, struct nf_conn *ct, bool tcp) { + struct nf_conn_act_ct_ext *act_ct_ext; struct flow_offload *entry; int err; @@ -375,6 +383,14 @@ static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; } + act_ct_ext = nf_conn_act_ct_ext_find(ct); + if (act_ct_ext) { + entry->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.iifidx = + act_ct_ext->ifindex[IP_CT_DIR_ORIGINAL]; + entry->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.iifidx = + act_ct_ext->ifindex[IP_CT_DIR_REPLY]; + } + err = flow_offload_add(&ct_ft->nf_ft, entry); if (err) goto err_add; @@ -393,7 +409,8 @@ static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft, { bool tcp = false; - if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) + if ((ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) || + !test_bit(IPS_ASSURED_BIT, &ct->status)) return; switch (nf_ct_protonum(ct)) { @@ -597,7 +614,7 @@ static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb, if (nf_ct_is_confirmed(ct)) nf_ct_kill(ct); - nf_conntrack_put(&ct->ct_general); + nf_ct_put(ct); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); return false; @@ -690,10 +707,10 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, u8 family, u16 zone, bool *defrag) { enum ip_conntrack_info ctinfo; - struct qdisc_skb_cb cb; struct nf_conn *ct; int err = 0; bool frag; + u16 mru; /* Previously seen (loopback)? Ignore. */ ct = nf_ct_get(skb, &ctinfo); @@ -708,7 +725,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, return err; skb_get(skb); - cb = *qdisc_skb_cb(skb); + mru = tc_skb_cb(skb)->mru; if (family == NFPROTO_IPV4) { enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone; @@ -722,7 +739,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, if (!err) { *defrag = true; - cb.mru = IPCB(skb)->frag_max_size; + mru = IPCB(skb)->frag_max_size; } } else { /* NFPROTO_IPV6 */ #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) @@ -735,7 +752,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, if (!err) { *defrag = true; - cb.mru = IP6CB(skb)->frag_max_size; + mru = IP6CB(skb)->frag_max_size; } #else err = -EOPNOTSUPP; @@ -744,7 +761,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, } if (err != -EINPROGRESS) - *qdisc_skb_cb(skb) = cb; + tc_skb_cb(skb)->mru = mru; skb_clear_hash(skb); skb->ignore_df = 1; return err; @@ -762,7 +779,7 @@ static void tcf_ct_params_free(struct rcu_head *head) tcf_ct_flow_table_put(params); if (params->tmpl) - nf_conntrack_put(¶ms->tmpl->ct_general); + nf_ct_put(params->tmpl); kfree(params); } @@ -839,6 +856,12 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, } err = nf_nat_packet(ct, ctinfo, hooknum, skb); + if (err == NF_ACCEPT) { + if (maniptype == NF_NAT_MANIP_SRC) + tc_skb_cb(skb)->post_ct_snat = 1; + if (maniptype == NF_NAT_MANIP_DST) + tc_skb_cb(skb)->post_ct_dnat = 1; + } out: return err; } @@ -963,10 +986,10 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, tcf_action_update_bstats(&c->common, skb); if (clear) { - qdisc_skb_cb(skb)->post_ct = false; + tc_skb_cb(skb)->post_ct = false; ct = nf_ct_get(skb, &ctinfo); if (ct) { - nf_conntrack_put(&ct->ct_general); + nf_ct_put(ct); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); } @@ -1026,6 +1049,7 @@ do_nat: if (!ct) goto out_push; nf_ct_deliver_cached_events(ct); + nf_conn_act_ct_ext_fill(skb, ct, ctinfo); err = tcf_ct_act_nat(skb, ct, ctinfo, p->ct_action, &p->range, commit); if (err != NF_ACCEPT) @@ -1035,6 +1059,9 @@ do_nat: tcf_ct_act_set_mark(ct, p->mark, p->mark_mask); tcf_ct_act_set_labels(ct, p->labels, p->labels_mask); + if (!nf_ct_is_confirmed(ct)) + nf_conn_act_ct_ext_add(ct); + /* This will take care of sending queued events * even if the connection is already confirmed. */ @@ -1048,7 +1075,8 @@ do_nat: out_push: skb_push_rcsum(skb, nh_ofs); - qdisc_skb_cb(skb)->post_ct = true; + tc_skb_cb(skb)->post_ct = true; + tc_skb_cb(skb)->zone = p->zone; out_clear: if (defrag) qdisc_skb_cb(skb)->pkt_len = skb->len; @@ -1227,7 +1255,6 @@ static int tcf_ct_fill_params(struct net *net, return -ENOMEM; } __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); - nf_conntrack_get(&tmpl->ct_general); p->tmpl = tmpl; return 0; @@ -1492,6 +1519,26 @@ static void tcf_stats_update(struct tc_action *a, u64 bytes, u64 packets, c->tcf_tm.lastuse = max_t(u64, c->tcf_tm.lastuse, lastuse); } +static int tcf_ct_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind) +{ + if (bind) { + struct flow_action_entry *entry = entry_data; + + entry->id = FLOW_ACTION_CT; + entry->ct.action = tcf_ct_action(act); + entry->ct.zone = tcf_ct_zone(act); + entry->ct.flow_table = tcf_ct_ft(act); + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + fl_action->id = FLOW_ACTION_CT; + } + + return 0; +} + static struct tc_action_ops act_ct_ops = { .kind = "ct", .id = TCA_ID_CT, @@ -1503,6 +1550,7 @@ static struct tc_action_ops act_ct_ops = { .walk = tcf_ct_walker, .lookup = tcf_ct_search, .stats_update = tcf_stats_update, + .offload_act_setup = tcf_ct_offload_act_setup, .size = sizeof(struct tcf_ct), }; @@ -1560,10 +1608,16 @@ static int __init ct_init_module(void) if (err) goto err_register; + err = nf_ct_extend_register(&act_ct_extend); + if (err) + goto err_register_extend; + static_branch_inc(&tcf_frag_xmit_count); return 0; +err_register_extend: + tcf_unregister_action(&act_ct_ops, &ct_net_ops); err_register: tcf_ct_flow_tables_uninit(); err_tbl_init: @@ -1574,6 +1628,7 @@ err_tbl_init: static void __exit ct_cleanup_module(void) { static_branch_dec(&tcf_frag_xmit_count); + nf_ct_extend_unregister(&act_ct_extend); tcf_unregister_action(&act_ct_ops, &ct_net_ops); tcf_ct_flow_tables_uninit(); destroy_workqueue(act_ct_wq); diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 549374a2d008..0281e45987a4 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -212,7 +212,7 @@ 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, 0); + &act_ctinfo_ops, bind, false, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index d8dce173df37..bde6a6c01e64 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -252,6 +252,43 @@ static size_t tcf_gact_get_fill_size(const struct tc_action *act) return sz; } +static int tcf_gact_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind) +{ + if (bind) { + struct flow_action_entry *entry = entry_data; + + if (is_tcf_gact_ok(act)) { + entry->id = FLOW_ACTION_ACCEPT; + } else if (is_tcf_gact_shot(act)) { + entry->id = FLOW_ACTION_DROP; + } else if (is_tcf_gact_trap(act)) { + entry->id = FLOW_ACTION_TRAP; + } else if (is_tcf_gact_goto_chain(act)) { + entry->id = FLOW_ACTION_GOTO; + entry->chain_index = tcf_gact_goto_chain_index(act); + } else { + return -EOPNOTSUPP; + } + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + if (is_tcf_gact_ok(act)) + fl_action->id = FLOW_ACTION_ACCEPT; + else if (is_tcf_gact_shot(act)) + fl_action->id = FLOW_ACTION_DROP; + else if (is_tcf_gact_trap(act)) + fl_action->id = FLOW_ACTION_TRAP; + else if (is_tcf_gact_goto_chain(act)) + fl_action->id = FLOW_ACTION_GOTO; + else + return -EOPNOTSUPP; + } + + return 0; +} + static struct tc_action_ops act_gact_ops = { .kind = "gact", .id = TCA_ID_GACT, @@ -263,6 +300,7 @@ static struct tc_action_ops act_gact_ops = { .walk = tcf_gact_walker, .lookup = tcf_gact_search, .get_fill_size = tcf_gact_get_fill_size, + .offload_act_setup = tcf_gact_offload_act_setup, .size = sizeof(struct tcf_gact), }; diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index 7df72a4197a3..d56e73843a4b 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -357,7 +357,7 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (!err) { ret = tcf_idr_create(tn, index, est, a, - &act_gate_ops, bind, false, 0); + &act_gate_ops, bind, false, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -597,6 +597,54 @@ static size_t tcf_gate_get_fill_size(const struct tc_action *act) return nla_total_size(sizeof(struct tc_gate)); } +static void tcf_gate_entry_destructor(void *priv) +{ + struct action_gate_entry *oe = priv; + + kfree(oe); +} + +static int tcf_gate_get_entries(struct flow_action_entry *entry, + const struct tc_action *act) +{ + entry->gate.entries = tcf_gate_get_list(act); + + if (!entry->gate.entries) + return -EINVAL; + + entry->destructor = tcf_gate_entry_destructor; + entry->destructor_priv = entry->gate.entries; + + return 0; +} + +static int tcf_gate_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind) +{ + int err; + + if (bind) { + struct flow_action_entry *entry = entry_data; + + entry->id = FLOW_ACTION_GATE; + entry->gate.prio = tcf_gate_prio(act); + entry->gate.basetime = tcf_gate_basetime(act); + entry->gate.cycletime = tcf_gate_cycletime(act); + entry->gate.cycletimeext = tcf_gate_cycletimeext(act); + entry->gate.num_entries = tcf_gate_num_entries(act); + err = tcf_gate_get_entries(entry, act); + if (err) + return err; + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + fl_action->id = FLOW_ACTION_GATE; + } + + return 0; +} + static struct tc_action_ops act_gate_ops = { .kind = "gate", .id = TCA_ID_GATE, @@ -609,6 +657,7 @@ static struct tc_action_ops act_gate_ops = { .stats_update = tcf_gate_stats_update, .get_fill_size = tcf_gate_get_fill_size, .lookup = tcf_gate_search, + .offload_act_setup = tcf_gate_offload_act_setup, .size = sizeof(struct tcf_gate), }; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index b757f90a2d58..41ba55e60b1b 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -553,7 +553,7 @@ 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, 0); + bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); kfree(p); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 265b1443e252..2f3d507c24a1 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -145,7 +145,7 @@ 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, 0); + false, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index efc963ab995a..39acd1d18609 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -79,7 +79,7 @@ static void tcf_mirred_release(struct tc_action *a) /* last reference to action, no need to lock */ dev = rcu_dereference_protected(m->tcfm_dev, 1); - dev_put(dev); + dev_put_track(dev, &m->tcfm_dev_tracker); } static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { @@ -101,7 +101,6 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, bool mac_header_xmit = false; struct tc_mirred *parm; struct tcf_mirred *m; - struct net_device *dev; bool exists = false; int ret, err; u32 index; @@ -171,16 +170,19 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, spin_lock_bh(&m->tcf_lock); if (parm->ifindex) { - dev = dev_get_by_index(net, parm->ifindex); - if (!dev) { + struct net_device *odev, *ndev; + + ndev = dev_get_by_index(net, parm->ifindex); + if (!ndev) { spin_unlock_bh(&m->tcf_lock); err = -ENODEV; goto put_chain; } - mac_header_xmit = dev_is_mac_header_xmit(dev); - dev = rcu_replace_pointer(m->tcfm_dev, dev, + mac_header_xmit = dev_is_mac_header_xmit(ndev); + odev = rcu_replace_pointer(m->tcfm_dev, ndev, lockdep_is_held(&m->tcf_lock)); - dev_put(dev); + dev_put_track(odev, &m->tcfm_dev_tracker); + netdev_tracker_alloc(ndev, &m->tcfm_dev_tracker, GFP_ATOMIC); m->tcfm_mac_header_xmit = mac_header_xmit; } goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); @@ -400,7 +402,7 @@ static int mirred_device_event(struct notifier_block *unused, list_for_each_entry(m, &mirred_list, tcfm_list) { spin_lock_bh(&m->tcf_lock); if (tcf_mirred_dev_dereference(m) == dev) { - dev_put(dev); + dev_put_track(dev, &m->tcfm_dev_tracker); /* Note : no rcu grace period necessary, as * net_device are already rcu protected. */ @@ -448,6 +450,55 @@ static size_t tcf_mirred_get_fill_size(const struct tc_action *act) return nla_total_size(sizeof(struct tc_mirred)); } +static void tcf_offload_mirred_get_dev(struct flow_action_entry *entry, + const struct tc_action *act) +{ + entry->dev = act->ops->get_dev(act, &entry->destructor); + if (!entry->dev) + return; + entry->destructor_priv = entry->dev; +} + +static int tcf_mirred_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind) +{ + if (bind) { + struct flow_action_entry *entry = entry_data; + + if (is_tcf_mirred_egress_redirect(act)) { + entry->id = FLOW_ACTION_REDIRECT; + tcf_offload_mirred_get_dev(entry, act); + } else if (is_tcf_mirred_egress_mirror(act)) { + entry->id = FLOW_ACTION_MIRRED; + tcf_offload_mirred_get_dev(entry, act); + } else if (is_tcf_mirred_ingress_redirect(act)) { + entry->id = FLOW_ACTION_REDIRECT_INGRESS; + tcf_offload_mirred_get_dev(entry, act); + } else if (is_tcf_mirred_ingress_mirror(act)) { + entry->id = FLOW_ACTION_MIRRED_INGRESS; + tcf_offload_mirred_get_dev(entry, act); + } else { + return -EOPNOTSUPP; + } + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + if (is_tcf_mirred_egress_redirect(act)) + fl_action->id = FLOW_ACTION_REDIRECT; + else if (is_tcf_mirred_egress_mirror(act)) + fl_action->id = FLOW_ACTION_MIRRED; + else if (is_tcf_mirred_ingress_redirect(act)) + fl_action->id = FLOW_ACTION_REDIRECT_INGRESS; + else if (is_tcf_mirred_ingress_mirror(act)) + fl_action->id = FLOW_ACTION_MIRRED_INGRESS; + else + return -EOPNOTSUPP; + } + + return 0; +} + static struct tc_action_ops act_mirred_ops = { .kind = "mirred", .id = TCA_ID_MIRRED, @@ -460,6 +511,7 @@ static struct tc_action_ops act_mirred_ops = { .walk = tcf_mirred_walker, .lookup = tcf_mirred_search, .get_fill_size = tcf_mirred_get_fill_size, + .offload_act_setup = tcf_mirred_offload_act_setup, .size = sizeof(struct tcf_mirred), .get_dev = tcf_mirred_get_dev, }; diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index 8faa4c58305e..b9ff3459fdab 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -248,7 +248,7 @@ 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, 0); + &act_mpls_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -384,6 +384,57 @@ static int tcf_mpls_search(struct net *net, struct tc_action **a, u32 index) return tcf_idr_search(tn, a, index); } +static int tcf_mpls_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind) +{ + if (bind) { + struct flow_action_entry *entry = entry_data; + + 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: + return -EOPNOTSUPP; + } + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + switch (tcf_mpls_action(act)) { + case TCA_MPLS_ACT_PUSH: + fl_action->id = FLOW_ACTION_MPLS_PUSH; + break; + case TCA_MPLS_ACT_POP: + fl_action->id = FLOW_ACTION_MPLS_POP; + break; + case TCA_MPLS_ACT_MODIFY: + fl_action->id = FLOW_ACTION_MPLS_MANGLE; + break; + default: + return -EOPNOTSUPP; + } + } + + return 0; +} + static struct tc_action_ops act_mpls_ops = { .kind = "mpls", .id = TCA_ID_MPLS, @@ -394,6 +445,7 @@ static struct tc_action_ops act_mpls_ops = { .cleanup = tcf_mpls_cleanup, .walk = tcf_mpls_walker, .lookup = tcf_mpls_search, + .offload_act_setup = tcf_mpls_offload_act_setup, .size = sizeof(struct tcf_mpls), }; diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 7dd6b586ba7f..2a39b3729e84 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -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, 0); + &act_nat_ops, bind, false, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index c6c862c459cc..31fcd279c177 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -189,7 +189,7 @@ static int tcf_pedit_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_pedit_ops, bind, false, 0); + &act_pedit_ops, bind, false, flags); if (ret) { tcf_idr_cleanup(tn, index); goto out_free; @@ -487,6 +487,39 @@ static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index) return tcf_idr_search(tn, a, index); } +static int tcf_pedit_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind) +{ + if (bind) { + struct flow_action_entry *entry = entry_data; + int k; + + for (k = 0; k < tcf_pedit_nkeys(act); k++) { + switch (tcf_pedit_cmd(act, k)) { + case TCA_PEDIT_KEY_EX_CMD_SET: + entry->id = FLOW_ACTION_MANGLE; + break; + case TCA_PEDIT_KEY_EX_CMD_ADD: + entry->id = FLOW_ACTION_ADD; + break; + default: + return -EOPNOTSUPP; + } + entry->mangle.htype = tcf_pedit_htype(act, k); + entry->mangle.mask = tcf_pedit_mask(act, k); + entry->mangle.val = tcf_pedit_val(act, k); + entry->mangle.offset = tcf_pedit_offset(act, k); + entry->hw_stats = tc_act_hw_stats(act->hw_stats); + entry++; + } + *index_inc = k; + } else { + return -EOPNOTSUPP; + } + + return 0; +} + static struct tc_action_ops act_pedit_ops = { .kind = "pedit", .id = TCA_ID_PEDIT, @@ -498,6 +531,7 @@ static struct tc_action_ops act_pedit_ops = { .init = tcf_pedit_init, .walk = tcf_pedit_walker, .lookup = tcf_pedit_search, + .offload_act_setup = tcf_pedit_offload_act_setup, .size = sizeof(struct tcf_pedit), }; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 9e77ba8401e5..0923aa2b8f8a 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -90,7 +90,7 @@ 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, 0); + &act_police_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -405,6 +405,30 @@ static int tcf_police_search(struct net *net, struct tc_action **a, u32 index) return tcf_idr_search(tn, a, index); } +static int tcf_police_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind) +{ + if (bind) { + struct flow_action_entry *entry = entry_data; + + entry->id = FLOW_ACTION_POLICE; + entry->police.burst = tcf_police_burst(act); + entry->police.rate_bytes_ps = + tcf_police_rate_bytes_ps(act); + entry->police.burst_pkt = tcf_police_burst_pkt(act); + entry->police.rate_pkt_ps = + tcf_police_rate_pkt_ps(act); + entry->police.mtu = tcf_police_tcfp_mtu(act); + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + fl_action->id = FLOW_ACTION_POLICE; + } + + return 0; +} + MODULE_AUTHOR("Alexey Kuznetsov"); MODULE_DESCRIPTION("Policing actions"); MODULE_LICENSE("GPL"); @@ -420,6 +444,7 @@ static struct tc_action_ops act_police_ops = { .walk = tcf_police_walker, .lookup = tcf_police_search, .cleanup = tcf_police_cleanup, + .offload_act_setup = tcf_police_offload_act_setup, .size = sizeof(struct tcf_police), }; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index ce859b0e0deb..9a22cdda6bbd 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -70,7 +70,7 @@ 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, 0); + &act_sample_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -282,6 +282,35 @@ tcf_sample_get_group(const struct tc_action *a, return group; } +static void tcf_offload_sample_get_group(struct flow_action_entry *entry, + const struct tc_action *act) +{ + entry->sample.psample_group = + act->ops->get_psample_group(act, &entry->destructor); + entry->destructor_priv = entry->sample.psample_group; +} + +static int tcf_sample_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind) +{ + if (bind) { + struct flow_action_entry *entry = entry_data; + + entry->id = FLOW_ACTION_SAMPLE; + entry->sample.trunc_size = tcf_sample_trunc_size(act); + entry->sample.truncate = tcf_sample_truncate(act); + entry->sample.rate = tcf_sample_rate(act); + tcf_offload_sample_get_group(entry, act); + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + fl_action->id = FLOW_ACTION_SAMPLE; + } + + return 0; +} + static struct tc_action_ops act_sample_ops = { .kind = "sample", .id = TCA_ID_SAMPLE, @@ -294,6 +323,7 @@ static struct tc_action_ops act_sample_ops = { .walk = tcf_sample_walker, .lookup = tcf_sample_search, .get_psample_group = tcf_sample_get_group, + .offload_act_setup = tcf_sample_offload_act_setup, .size = sizeof(struct tcf_sample), }; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index e617ab4505ca..8c1d60bde93e 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -129,7 +129,7 @@ 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, 0); + &act_simp_ops, bind, false, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index d30ecbfc8f84..ceba11b198bb 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -176,7 +176,7 @@ 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, 0); + &act_skbedit_ops, bind, true, act_flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; @@ -327,6 +327,41 @@ static size_t tcf_skbedit_get_fill_size(const struct tc_action *act) + nla_total_size_64bit(sizeof(u64)); /* TCA_SKBEDIT_FLAGS */ } +static int tcf_skbedit_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind) +{ + if (bind) { + struct flow_action_entry *entry = entry_data; + + if (is_tcf_skbedit_mark(act)) { + entry->id = FLOW_ACTION_MARK; + entry->mark = tcf_skbedit_mark(act); + } else if (is_tcf_skbedit_ptype(act)) { + entry->id = FLOW_ACTION_PTYPE; + entry->ptype = tcf_skbedit_ptype(act); + } else if (is_tcf_skbedit_priority(act)) { + entry->id = FLOW_ACTION_PRIORITY; + entry->priority = tcf_skbedit_priority(act); + } else { + return -EOPNOTSUPP; + } + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + if (is_tcf_skbedit_mark(act)) + fl_action->id = FLOW_ACTION_MARK; + else if (is_tcf_skbedit_ptype(act)) + fl_action->id = FLOW_ACTION_PTYPE; + else if (is_tcf_skbedit_priority(act)) + fl_action->id = FLOW_ACTION_PRIORITY; + else + return -EOPNOTSUPP; + } + + return 0; +} + static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", .id = TCA_ID_SKBEDIT, @@ -339,6 +374,7 @@ static struct tc_action_ops act_skbedit_ops = { .walk = tcf_skbedit_walker, .get_fill_size = tcf_skbedit_get_fill_size, .lookup = tcf_skbedit_search, + .offload_act_setup = tcf_skbedit_offload_act_setup, .size = sizeof(struct tcf_skbedit), }; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 9b6b52c5e24e..2083612d8780 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -168,7 +168,7 @@ 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, 0); + &act_skbmod_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index d9cd174eecb7..23aba03d26a8 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -787,6 +787,59 @@ static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index) return tcf_idr_search(tn, a, index); } +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 int tcf_tunnel_key_offload_act_setup(struct tc_action *act, + void *entry_data, + u32 *index_inc, + bool bind) +{ + int err; + + if (bind) { + struct flow_action_entry *entry = entry_data; + + if (is_tcf_tunnel_set(act)) { + entry->id = FLOW_ACTION_TUNNEL_ENCAP; + err = tcf_tunnel_encap_get_tunnel(entry, act); + if (err) + return err; + } else if (is_tcf_tunnel_release(act)) { + entry->id = FLOW_ACTION_TUNNEL_DECAP; + } else { + return -EOPNOTSUPP; + } + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + if (is_tcf_tunnel_set(act)) + fl_action->id = FLOW_ACTION_TUNNEL_ENCAP; + else if (is_tcf_tunnel_release(act)) + fl_action->id = FLOW_ACTION_TUNNEL_DECAP; + else + return -EOPNOTSUPP; + } + + return 0; +} + static struct tc_action_ops act_tunnel_key_ops = { .kind = "tunnel_key", .id = TCA_ID_TUNNEL_KEY, @@ -797,6 +850,7 @@ static struct tc_action_ops act_tunnel_key_ops = { .cleanup = tunnel_key_release, .walk = tunnel_key_walker, .lookup = tunnel_key_search, + .offload_act_setup = tcf_tunnel_key_offload_act_setup, .size = sizeof(struct tcf_tunnel_key), }; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index e4dc5a555bd8..756e2dcde1cd 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -368,6 +368,53 @@ static size_t tcf_vlan_get_fill_size(const struct tc_action *act) + nla_total_size(sizeof(u8)); /* TCA_VLAN_PUSH_VLAN_PRIORITY */ } +static int tcf_vlan_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind) +{ + if (bind) { + struct flow_action_entry *entry = entry_data; + + switch (tcf_vlan_action(act)) { + case TCA_VLAN_ACT_PUSH: + entry->id = FLOW_ACTION_VLAN_PUSH; + entry->vlan.vid = tcf_vlan_push_vid(act); + entry->vlan.proto = tcf_vlan_push_proto(act); + entry->vlan.prio = tcf_vlan_push_prio(act); + break; + case TCA_VLAN_ACT_POP: + entry->id = FLOW_ACTION_VLAN_POP; + break; + case TCA_VLAN_ACT_MODIFY: + entry->id = FLOW_ACTION_VLAN_MANGLE; + entry->vlan.vid = tcf_vlan_push_vid(act); + entry->vlan.proto = tcf_vlan_push_proto(act); + entry->vlan.prio = tcf_vlan_push_prio(act); + break; + default: + return -EOPNOTSUPP; + } + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + switch (tcf_vlan_action(act)) { + case TCA_VLAN_ACT_PUSH: + fl_action->id = FLOW_ACTION_VLAN_PUSH; + break; + case TCA_VLAN_ACT_POP: + fl_action->id = FLOW_ACTION_VLAN_POP; + break; + case TCA_VLAN_ACT_MODIFY: + fl_action->id = FLOW_ACTION_VLAN_MANGLE; + break; + default: + return -EOPNOTSUPP; + } + } + + return 0; +} + static struct tc_action_ops act_vlan_ops = { .kind = "vlan", .id = TCA_ID_VLAN, @@ -380,6 +427,7 @@ static struct tc_action_ops act_vlan_ops = { .stats_update = tcf_vlan_stats_update, .get_fill_size = tcf_vlan_get_fill_size, .lookup = tcf_vlan_search, + .offload_act_setup = tcf_vlan_offload_act_setup, .size = sizeof(struct tcf_vlan), }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2ef8f5a6205a..d4e27c679123 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1617,12 +1617,17 @@ int tcf_classify(struct sk_buff *skb, /* If we missed on some chain */ if (ret == TC_ACT_UNSPEC && last_executed_chain) { + struct tc_skb_cb *cb = tc_skb_cb(skb); + ext = tc_skb_ext_alloc(skb); if (WARN_ON_ONCE(!ext)) return TC_ACT_SHOT; ext->chain = last_executed_chain; - ext->mru = qdisc_skb_cb(skb)->mru; - ext->post_ct = qdisc_skb_cb(skb)->post_ct; + ext->mru = cb->mru; + ext->post_ct = cb->post_ct; + ext->post_ct_snat = cb->post_ct_snat; + ext->post_ct_dnat = cb->post_ct_dnat; + ext->zone = cb->zone; } return ret; @@ -3025,9 +3030,9 @@ void tcf_exts_destroy(struct tcf_exts *exts) } EXPORT_SYMBOL(tcf_exts_destroy); -int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, - struct nlattr *rate_tlv, struct tcf_exts *exts, - u32 flags, struct netlink_ext_ack *extack) +int tcf_exts_validate_ex(struct net *net, struct tcf_proto *tp, struct nlattr **tb, + struct nlattr *rate_tlv, struct tcf_exts *exts, + u32 flags, u32 fl_flags, struct netlink_ext_ack *extack) { #ifdef CONFIG_NET_CLS_ACT { @@ -3061,7 +3066,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, flags |= TCA_ACT_FLAGS_BIND; err = tcf_action_init(net, tp, tb[exts->action], rate_tlv, exts->actions, init_res, - &attr_size, flags, extack); + &attr_size, flags, fl_flags, + extack); if (err < 0) return err; exts->nr_actions = err; @@ -3077,6 +3083,15 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, return 0; } +EXPORT_SYMBOL(tcf_exts_validate_ex); + +int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, + struct nlattr *rate_tlv, struct tcf_exts *exts, + u32 flags, struct netlink_ext_ack *extack) +{ + return tcf_exts_validate_ex(net, tp, tb, rate_tlv, exts, + flags, 0, extack); +} EXPORT_SYMBOL(tcf_exts_validate); void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src) @@ -3320,7 +3335,7 @@ err_unlock: up_read(&block->cb_lock); if (take_rtnl) rtnl_unlock(); - return ok_count < 0 ? ok_count : 0; + return min(ok_count, 0); } EXPORT_SYMBOL(tc_setup_cb_add); @@ -3376,7 +3391,7 @@ err_unlock: up_read(&block->cb_lock); if (take_rtnl) rtnl_unlock(); - return ok_count < 0 ? ok_count : 0; + return min(ok_count, 0); } EXPORT_SYMBOL(tc_setup_cb_replace); @@ -3414,7 +3429,7 @@ retry: up_read(&block->cb_lock); if (take_rtnl) rtnl_unlock(); - return ok_count < 0 ? ok_count : 0; + return min(ok_count, 0); } EXPORT_SYMBOL(tc_setup_cb_destroy); @@ -3461,7 +3476,7 @@ static void tcf_act_put_cookie(struct flow_action_entry *entry) flow_action_cookie_destroy(entry->cookie); } -void tc_cleanup_flow_action(struct flow_action *flow_action) +void tc_cleanup_offload_action(struct flow_action *flow_action) { struct flow_action_entry *entry; int i; @@ -3472,93 +3487,37 @@ void tc_cleanup_flow_action(struct flow_action *flow_action) entry->destructor(entry->destructor_priv); } } -EXPORT_SYMBOL(tc_cleanup_flow_action); +EXPORT_SYMBOL(tc_cleanup_offload_action); -static void tcf_mirred_get_dev(struct flow_action_entry *entry, - const struct tc_action *act) +static int tc_setup_offload_act(struct tc_action *act, + struct flow_action_entry *entry, + u32 *index_inc) { #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; + if (act->ops->offload_act_setup) + return act->ops->offload_act_setup(act, entry, index_inc, true); + else + return -EOPNOTSUPP; +#else 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 } -static void tcf_gate_entry_destructor(void *priv) -{ - struct action_gate_entry *oe = priv; - - kfree(oe); -} - -static int tcf_gate_get_entries(struct flow_action_entry *entry, - const struct tc_action *act) -{ - entry->gate.entries = tcf_gate_get_list(act); - - if (!entry->gate.entries) - return -EINVAL; - - entry->destructor = tcf_gate_entry_destructor; - entry->destructor_priv = entry->gate.entries; - - return 0; -} - -static enum flow_action_hw_stats tc_act_hw_stats(u8 hw_stats) -{ - if (WARN_ON_ONCE(hw_stats > TCA_ACT_HW_STATS_ANY)) - return FLOW_ACTION_HW_STATS_DONT_CARE; - else if (!hw_stats) - return FLOW_ACTION_HW_STATS_DISABLED; - - return hw_stats; -} - -int tc_setup_flow_action(struct flow_action *flow_action, - const struct tcf_exts *exts) +int tc_setup_action(struct flow_action *flow_action, + struct tc_action *actions[]) { + int i, j, index, err = 0; struct tc_action *act; - int i, j, k, err = 0; BUILD_BUG_ON(TCA_ACT_HW_STATS_ANY != FLOW_ACTION_HW_STATS_ANY); BUILD_BUG_ON(TCA_ACT_HW_STATS_IMMEDIATE != FLOW_ACTION_HW_STATS_IMMEDIATE); BUILD_BUG_ON(TCA_ACT_HW_STATS_DELAYED != FLOW_ACTION_HW_STATS_DELAYED); - if (!exts) + if (!actions) return 0; j = 0; - tcf_exts_for_each_action(i, act, exts) { + tcf_act_for_each_action(i, act, actions) { struct flow_action_entry *entry; entry = &flow_action->entries[j]; @@ -3568,164 +3527,39 @@ int tc_setup_flow_action(struct flow_action *flow_action, goto err_out_locked; entry->hw_stats = tc_act_hw_stats(act->hw_stats); - - if (is_tcf_gact_ok(act)) { - entry->id = FLOW_ACTION_ACCEPT; - } else if (is_tcf_gact_shot(act)) { - entry->id = FLOW_ACTION_DROP; - } else if (is_tcf_gact_trap(act)) { - entry->id = FLOW_ACTION_TRAP; - } else if (is_tcf_gact_goto_chain(act)) { - entry->id = FLOW_ACTION_GOTO; - entry->chain_index = tcf_gact_goto_chain_index(act); - } else if (is_tcf_mirred_egress_redirect(act)) { - entry->id = FLOW_ACTION_REDIRECT; - tcf_mirred_get_dev(entry, act); - } else if (is_tcf_mirred_egress_mirror(act)) { - entry->id = FLOW_ACTION_MIRRED; - 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: - entry->id = FLOW_ACTION_VLAN_PUSH; - entry->vlan.vid = tcf_vlan_push_vid(act); - entry->vlan.proto = tcf_vlan_push_proto(act); - entry->vlan.prio = tcf_vlan_push_prio(act); - break; - case TCA_VLAN_ACT_POP: - entry->id = FLOW_ACTION_VLAN_POP; - break; - case TCA_VLAN_ACT_MODIFY: - entry->id = FLOW_ACTION_VLAN_MANGLE; - entry->vlan.vid = tcf_vlan_push_vid(act); - entry->vlan.proto = tcf_vlan_push_proto(act); - entry->vlan.prio = tcf_vlan_push_prio(act); - break; - default: - err = -EOPNOTSUPP; - goto err_out_locked; - } - } else if (is_tcf_tunnel_set(act)) { - entry->id = FLOW_ACTION_TUNNEL_ENCAP; - err = tcf_tunnel_encap_get_tunnel(entry, act); - if (err) - goto err_out_locked; - } else if (is_tcf_tunnel_release(act)) { - entry->id = FLOW_ACTION_TUNNEL_DECAP; - } else if (is_tcf_pedit(act)) { - for (k = 0; k < tcf_pedit_nkeys(act); k++) { - switch (tcf_pedit_cmd(act, k)) { - case TCA_PEDIT_KEY_EX_CMD_SET: - entry->id = FLOW_ACTION_MANGLE; - break; - case TCA_PEDIT_KEY_EX_CMD_ADD: - entry->id = FLOW_ACTION_ADD; - break; - default: - err = -EOPNOTSUPP; - goto err_out_locked; - } - entry->mangle.htype = tcf_pedit_htype(act, k); - entry->mangle.mask = tcf_pedit_mask(act, k); - entry->mangle.val = tcf_pedit_val(act, k); - entry->mangle.offset = tcf_pedit_offset(act, k); - entry->hw_stats = tc_act_hw_stats(act->hw_stats); - entry = &flow_action->entries[++j]; - } - } else if (is_tcf_csum(act)) { - entry->id = FLOW_ACTION_CSUM; - entry->csum_flags = tcf_csum_update_flags(act); - } else if (is_tcf_skbedit_mark(act)) { - entry->id = FLOW_ACTION_MARK; - entry->mark = tcf_skbedit_mark(act); - } else if (is_tcf_sample(act)) { - entry->id = FLOW_ACTION_SAMPLE; - 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_burst(act); - entry->police.rate_bytes_ps = - tcf_police_rate_bytes_ps(act); - entry->police.burst_pkt = tcf_police_burst_pkt(act); - entry->police.rate_pkt_ps = - tcf_police_rate_pkt_ps(act); - entry->police.mtu = tcf_police_tcfp_mtu(act); - entry->police.index = act->tcfa_index; - } else if (is_tcf_ct(act)) { - entry->id = FLOW_ACTION_CT; - entry->ct.action = tcf_ct_action(act); - entry->ct.zone = tcf_ct_zone(act); - entry->ct.flow_table = tcf_ct_ft(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_locked; - } - } else if (is_tcf_skbedit_ptype(act)) { - entry->id = FLOW_ACTION_PTYPE; - entry->ptype = tcf_skbedit_ptype(act); - } else if (is_tcf_skbedit_priority(act)) { - entry->id = FLOW_ACTION_PRIORITY; - entry->priority = tcf_skbedit_priority(act); - } else if (is_tcf_gate(act)) { - entry->id = FLOW_ACTION_GATE; - entry->gate.index = tcf_gate_index(act); - entry->gate.prio = tcf_gate_prio(act); - entry->gate.basetime = tcf_gate_basetime(act); - entry->gate.cycletime = tcf_gate_cycletime(act); - entry->gate.cycletimeext = tcf_gate_cycletimeext(act); - entry->gate.num_entries = tcf_gate_num_entries(act); - err = tcf_gate_get_entries(entry, act); - if (err) - goto err_out_locked; - } else { - err = -EOPNOTSUPP; + entry->hw_index = act->tcfa_index; + index = 0; + err = tc_setup_offload_act(act, entry, &index); + if (!err) + j += index; + else goto err_out_locked; - } spin_unlock_bh(&act->tcfa_lock); - - if (!is_tcf_pedit(act)) - j++; } err_out: if (err) - tc_cleanup_flow_action(flow_action); + tc_cleanup_offload_action(flow_action); return err; err_out_locked: spin_unlock_bh(&act->tcfa_lock); goto err_out; } -EXPORT_SYMBOL(tc_setup_flow_action); + +int tc_setup_offload_action(struct flow_action *flow_action, + const struct tcf_exts *exts) +{ +#ifdef CONFIG_NET_CLS_ACT + if (!exts) + return 0; + + return tc_setup_action(flow_action, exts->actions); +#else + return 0; +#endif +} +EXPORT_SYMBOL(tc_setup_offload_action); unsigned int tcf_exts_num_actions(struct tcf_exts *exts) { diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index aab13ba11767..1a9b1f140f9e 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -19,6 +19,7 @@ #include <net/sch_generic.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include <net/ip.h> #include <net/flow_dissector.h> #include <net/geneve.h> @@ -309,7 +310,8 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct cls_fl_head *head = rcu_dereference_bh(tp->root); - bool post_ct = qdisc_skb_cb(skb)->post_ct; + bool post_ct = tc_skb_cb(skb)->post_ct; + u16 zone = tc_skb_cb(skb)->zone; struct fl_flow_key skb_key; struct fl_flow_mask *mask; struct cls_fl_filter *f; @@ -327,7 +329,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, skb_flow_dissect_ct(skb, &mask->dissector, &skb_key, fl_ct_info_to_flower_map, ARRAY_SIZE(fl_ct_info_to_flower_map), - post_ct); + post_ct, zone); skb_flow_dissect_hash(skb, &mask->dissector, &skb_key); skb_flow_dissect(skb, &mask->dissector, &skb_key, FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP); @@ -461,7 +463,7 @@ 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_offload_action(&cls_flower.rule->action, &f->exts); if (err) { kfree(cls_flower.rule); if (skip_sw) { @@ -473,7 +475,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, 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); + tc_cleanup_offload_action(&cls_flower.rule->action); kfree(cls_flower.rule); if (err) { @@ -501,12 +503,12 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f, 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.drops, - cls_flower.stats.lastused, - cls_flower.stats.used_hw_stats, - cls_flower.stats.used_hw_stats_valid); + tcf_exts_hw_stats_update(&f->exts, cls_flower.stats.bytes, + cls_flower.stats.pkts, + cls_flower.stats.drops, + cls_flower.stats.lastused, + cls_flower.stats.used_hw_stats, + cls_flower.stats.used_hw_stats_valid); } static void __fl_put(struct cls_fl_filter *f) @@ -1917,12 +1919,14 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp, struct cls_fl_filter *f, struct fl_flow_mask *mask, unsigned long base, struct nlattr **tb, struct nlattr *est, - struct fl_flow_tmplt *tmplt, u32 flags, + struct fl_flow_tmplt *tmplt, + u32 flags, u32 fl_flags, struct netlink_ext_ack *extack) { int err; - err = tcf_exts_validate(net, tp, tb, est, &f->exts, flags, extack); + err = tcf_exts_validate_ex(net, tp, tb, est, &f->exts, flags, + fl_flags, extack); if (err < 0) return err; @@ -2036,7 +2040,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, } err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], - tp->chain->tmplt_priv, flags, extack); + tp->chain->tmplt_priv, flags, fnew->flags, + extack); if (err) goto errout; @@ -2266,7 +2271,7 @@ 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_offload_action(&cls_flower.rule->action, &f->exts); if (err) { kfree(cls_flower.rule); if (tc_skip_sw(f->flags)) { @@ -2283,7 +2288,7 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, TC_SETUP_CLSFLOWER, &cls_flower, cb_priv, &f->flags, &f->in_hw_count); - tc_cleanup_flow_action(&cls_flower.rule->action); + tc_cleanup_offload_action(&cls_flower.rule->action); kfree(cls_flower.rule); if (err) { diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 24f0046ce0b3..ca5670fd5228 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -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_offload_action(&cls_mall.rule->action, &head->exts); if (err) { kfree(cls_mall.rule); mall_destroy_hw_filter(tp, head, cookie, NULL); @@ -111,7 +111,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, 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); + tc_cleanup_offload_action(&cls_mall.rule->action); kfree(cls_mall.rule); if (err) { @@ -163,12 +163,13 @@ static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = { static int mall_set_parms(struct net *net, struct tcf_proto *tp, struct cls_mall_head *head, unsigned long base, struct nlattr **tb, - struct nlattr *est, u32 flags, + struct nlattr *est, u32 flags, u32 fl_flags, struct netlink_ext_ack *extack) { int err; - err = tcf_exts_validate(net, tp, tb, est, &head->exts, flags, extack); + err = tcf_exts_validate_ex(net, tp, tb, est, &head->exts, flags, + fl_flags, extack); if (err < 0) return err; @@ -226,8 +227,8 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, goto err_alloc_percpu; } - err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], flags, - extack); + err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], + flags, new->flags, extack); if (err) goto err_set_parms; @@ -301,7 +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_offload_action(&cls_mall.rule->action, &head->exts); if (err) { kfree(cls_mall.rule); if (add && tc_skip_sw(head->flags)) { @@ -314,7 +315,7 @@ static int mall_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, 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); + tc_cleanup_offload_action(&cls_mall.rule->action); kfree(cls_mall.rule); if (err) @@ -336,11 +337,11 @@ static void mall_stats_hw_filter(struct tcf_proto *tp, 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.drops, - cls_mall.stats.lastused, - cls_mall.stats.used_hw_stats, - cls_mall.stats.used_hw_stats_valid); + tcf_exts_hw_stats_update(&head->exts, cls_mall.stats.bytes, + cls_mall.stats.pkts, cls_mall.stats.drops, + cls_mall.stats.lastused, + cls_mall.stats.used_hw_stats, + cls_mall.stats.used_hw_stats_valid); } static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh, diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 4272814487f0..cf5649292ee0 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -709,12 +709,13 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { static int u32_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct tc_u_knode *n, struct nlattr **tb, - struct nlattr *est, u32 flags, + struct nlattr *est, u32 flags, u32 fl_flags, struct netlink_ext_ack *extack) { int err; - err = tcf_exts_validate(net, tp, tb, est, &n->exts, flags, extack); + err = tcf_exts_validate_ex(net, tp, tb, est, &n->exts, flags, + fl_flags, extack); if (err < 0) return err; @@ -895,7 +896,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -ENOMEM; err = u32_set_parms(net, tp, base, new, tb, - tca[TCA_RATE], flags, extack); + tca[TCA_RATE], flags, new->flags, + extack); if (err) { u32_destroy_key(new, false); @@ -1060,8 +1062,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, } #endif - err = u32_set_parms(net, tp, base, n, tb, tca[TCA_RATE], flags, - extack); + err = u32_set_parms(net, tp, base, n, tb, tca[TCA_RATE], + flags, n->flags, extack); if (err == 0) { struct tc_u_knode __rcu **ins; struct tc_u_knode *pins; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index efcd0b5e9a32..c9c6f49f9c28 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1292,7 +1292,7 @@ err_out5: if (ops->destroy) ops->destroy(sch); err_out3: - dev_put(dev); + dev_put_track(dev, &sch->dev_tracker); qdisc_free(sch); err_out2: module_put(ops->owner); diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 3c2300d14468..a43a58a73d09 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -2342,9 +2342,7 @@ static int cake_config_precedence(struct Qdisc *sch) /* List of known Diffserv codepoints: * - * Least Effort (CS1, LE) - * Best Effort (CS0) - * Max Reliability & LLT "Lo" (TOS1) + * Default Forwarding (DF/CS0) - Best Effort * Max Throughput (TOS2) * Min Delay (TOS4) * LLT "La" (TOS5) @@ -2352,6 +2350,7 @@ static int cake_config_precedence(struct Qdisc *sch) * Assured Forwarding 2 (AF2x) - x3 * Assured Forwarding 3 (AF3x) - x3 * Assured Forwarding 4 (AF4x) - x3 + * Precedence Class 1 (CS1) * Precedence Class 2 (CS2) * Precedence Class 3 (CS3) * Precedence Class 4 (CS4) @@ -2360,8 +2359,9 @@ static int cake_config_precedence(struct Qdisc *sch) * Precedence Class 7 (CS7) * Voice Admit (VA) * Expedited Forwarding (EF) - - * Total 25 codepoints. + * Lower Effort (LE) + * + * Total 26 codepoints. */ /* List of traffic classes in RFC 4594, updated by RFC 8622: @@ -2375,12 +2375,12 @@ static int cake_config_precedence(struct Qdisc *sch) * Realtime Interactive (CS4) - eg. games * Multimedia Streaming (AF3x) - eg. YouTube, NetFlix, Twitch * Broadcast Video (CS3) - * Low Latency Data (AF2x,TOS4) - eg. database - * Ops, Admin, Management (CS2,TOS1) - eg. ssh - * Standard Service (CS0 & unrecognised codepoints) - * High Throughput Data (AF1x,TOS2) - eg. web traffic - * Low Priority Data (CS1,LE) - eg. BitTorrent - + * Low-Latency Data (AF2x,TOS4) - eg. database + * Ops, Admin, Management (CS2) - eg. ssh + * Standard Service (DF & unrecognised codepoints) + * High-Throughput Data (AF1x,TOS2) - eg. web traffic + * Low-Priority Data (LE,CS1) - eg. BitTorrent + * * Total 12 traffic classes. */ @@ -2390,12 +2390,12 @@ static int cake_config_diffserv8(struct Qdisc *sch) * * Network Control (CS6, CS7) * Minimum Latency (EF, VA, CS5, CS4) - * Interactive Shell (CS2, TOS1) + * Interactive Shell (CS2) * Low Latency Transactions (AF2x, TOS4) * Video Streaming (AF4x, AF3x, CS3) - * Bog Standard (CS0 etc.) - * High Throughput (AF1x, TOS2) - * Background Traffic (CS1, LE) + * Bog Standard (DF etc.) + * High Throughput (AF1x, TOS2, CS1) + * Background Traffic (LE) * * Total 8 traffic classes. */ @@ -2437,9 +2437,9 @@ static int cake_config_diffserv4(struct Qdisc *sch) /* Further pruned list of traffic classes for four-class system: * * Latency Sensitive (CS7, CS6, EF, VA, CS5, CS4) - * Streaming Media (AF4x, AF3x, CS3, AF2x, TOS4, CS2, TOS1) - * Best Effort (CS0, AF1x, TOS2, and those not specified) - * Background Traffic (CS1, LE) + * Streaming Media (AF4x, AF3x, CS3, AF2x, TOS4, CS2) + * Best Effort (DF, AF1x, TOS2, and those not specified) + * Background Traffic (LE, CS1) * * Total 4 traffic classes. */ @@ -2477,9 +2477,9 @@ static int cake_config_diffserv4(struct Qdisc *sch) static int cake_config_diffserv3(struct Qdisc *sch) { /* Simplified Diffserv structure with 3 tins. - * Low Priority (CS1, LE) + * Latency Sensitive (CS7, CS6, EF, VA, TOS4) * Best Effort - * Latency Sensitive (TOS4, VA, EF, CS6, CS7) + * Low Priority (LE, CS1) */ struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); @@ -2736,7 +2736,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, q->tins = kvcalloc(CAKE_MAX_TINS, sizeof(struct cake_tin_data), GFP_KERNEL); if (!q->tins) - goto nomem; + return -ENOMEM; for (i = 0; i < CAKE_MAX_TINS; i++) { struct cake_tin_data *b = q->tins + i; @@ -2766,10 +2766,6 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, q->min_netlen = ~0; q->min_adjlen = ~0; return 0; - -nomem: - cake_destroy(sch); - return -ENOMEM; } static int cake_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index e007fc75ef2f..d73393493553 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -666,9 +666,9 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, } } for (i = q->nbands; i < oldbands; i++) { - qdisc_tree_flush_backlog(q->classes[i].qdisc); - if (i >= q->nstrict) + if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) list_del(&q->classes[i].alist); + qdisc_tree_flush_backlog(q->classes[i].qdisc); } q->nstrict = nstrict; memcpy(q->prio2band, priomap, sizeof(priomap)); diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 830f3559f727..d6aba6edd16e 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -531,6 +531,7 @@ static void fq_pie_destroy(struct Qdisc *sch) struct fq_pie_sched_data *q = qdisc_priv(sch); tcf_block_put(q->block); + q->p_params.tupdate = 0; del_timer_sync(&q->adapt_timer); kvfree(q->flows); } diff --git a/net/sched/sch_frag.c b/net/sched/sch_frag.c index 8c06381391d6..a9bd0a235890 100644 --- a/net/sched/sch_frag.c +++ b/net/sched/sch_frag.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +#include <linux/if_vlan.h> #include <net/netlink.h> #include <net/sch_generic.h> +#include <net/pkt_sched.h> #include <net/dst.h> #include <net/ip.h> #include <net/ip6_fib.h> @@ -137,7 +139,7 @@ err: int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)) { - u16 mru = qdisc_skb_cb(skb)->mru; + u16 mru = tc_skb_cb(skb)->mru; int err; if (mru && skb->len > mru + skb->dev->hard_header_len) diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 3b0f62095803..b07bd1c7330f 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -434,9 +434,9 @@ unsigned long dev_trans_start(struct net_device *dev) dev = vlan_dev_real_dev(dev); else if (netif_is_macvlan(dev)) dev = macvlan_dev_real_dev(dev); - res = netdev_get_tx_queue(dev, 0)->trans_start; + res = READ_ONCE(netdev_get_tx_queue(dev, 0)->trans_start); for (i = 1; i < dev->num_tx_queues; i++) { - val = netdev_get_tx_queue(dev, i)->trans_start; + val = READ_ONCE(netdev_get_tx_queue(dev, i)->trans_start); if (val && time_after(val, res)) res = val; } @@ -445,11 +445,63 @@ unsigned long dev_trans_start(struct net_device *dev) } EXPORT_SYMBOL(dev_trans_start); +static void netif_freeze_queues(struct net_device *dev) +{ + unsigned int i; + int cpu; + + cpu = smp_processor_id(); + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + + /* We are the only thread of execution doing a + * freeze, but we have to grab the _xmit_lock in + * order to synchronize with threads which are in + * the ->hard_start_xmit() handler and already + * checked the frozen bit. + */ + __netif_tx_lock(txq, cpu); + set_bit(__QUEUE_STATE_FROZEN, &txq->state); + __netif_tx_unlock(txq); + } +} + +void netif_tx_lock(struct net_device *dev) +{ + spin_lock(&dev->tx_global_lock); + netif_freeze_queues(dev); +} +EXPORT_SYMBOL(netif_tx_lock); + +static void netif_unfreeze_queues(struct net_device *dev) +{ + unsigned int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + + /* No need to grab the _xmit_lock here. If the + * queue is not stopped for another reason, we + * force a schedule. + */ + clear_bit(__QUEUE_STATE_FROZEN, &txq->state); + netif_schedule_queue(txq); + } +} + +void netif_tx_unlock(struct net_device *dev) +{ + netif_unfreeze_queues(dev); + spin_unlock(&dev->tx_global_lock); +} +EXPORT_SYMBOL(netif_tx_unlock); + static void dev_watchdog(struct timer_list *t) { struct net_device *dev = from_timer(dev, t, watchdog_timer); + bool release = true; - netif_tx_lock(dev); + spin_lock(&dev->tx_global_lock); if (!qdisc_tx_is_noop(dev)) { if (netif_device_present(dev) && netif_running(dev) && @@ -462,31 +514,34 @@ static void dev_watchdog(struct timer_list *t) struct netdev_queue *txq; txq = netdev_get_tx_queue(dev, i); - trans_start = txq->trans_start; + trans_start = READ_ONCE(txq->trans_start); if (netif_xmit_stopped(txq) && time_after(jiffies, (trans_start + dev->watchdog_timeo))) { some_queue_timedout = 1; - txq->trans_timeout++; + atomic_long_inc(&txq->trans_timeout); break; } } - if (some_queue_timedout) { + if (unlikely(some_queue_timedout)) { 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); + netif_freeze_queues(dev); dev->netdev_ops->ndo_tx_timeout(dev, i); + netif_unfreeze_queues(dev); } if (!mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + dev->watchdog_timeo))) - dev_hold(dev); + release = false; } } - netif_tx_unlock(dev); + spin_unlock(&dev->tx_global_lock); - dev_put(dev); + if (release) + dev_put_track(dev, &dev->watchdog_dev_tracker); } void __netdev_watchdog_up(struct net_device *dev) @@ -496,7 +551,7 @@ void __netdev_watchdog_up(struct net_device *dev) dev->watchdog_timeo = 5*HZ; if (!mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + dev->watchdog_timeo))) - dev_hold(dev); + dev_hold_track(dev, &dev->watchdog_dev_tracker, GFP_ATOMIC); } } EXPORT_SYMBOL_GPL(__netdev_watchdog_up); @@ -510,7 +565,7 @@ static void dev_watchdog_down(struct net_device *dev) { netif_tx_lock_bh(dev); if (del_timer(&dev->watchdog_timer)) - dev_put(dev); + dev_put_track(dev, &dev->watchdog_dev_tracker); netif_tx_unlock_bh(dev); } @@ -920,7 +975,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; - dev_hold(dev); + dev_hold_track(dev, &sch->dev_tracker, GFP_KERNEL); refcount_set(&sch->refcnt, 1); return sch; @@ -1020,7 +1075,7 @@ static void qdisc_destroy(struct Qdisc *qdisc) ops->destroy(qdisc); module_put(ops->owner); - dev_put(qdisc_dev(qdisc)); + dev_put_track(qdisc_dev(qdisc), &qdisc->dev_tracker); trace_qdisc_destroy(qdisc); @@ -1148,7 +1203,7 @@ static void transition_one_qdisc(struct net_device *dev, rcu_assign_pointer(dev_queue->qdisc, new_qdisc); if (need_watchdog_p) { - dev_queue->trans_start = 0; + WRITE_ONCE(dev_queue->trans_start, 0); *need_watchdog_p = 1; } } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index ecbb10db1111..ed4ccef5d6a8 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -208,17 +208,17 @@ static bool loss_4state(struct netem_sched_data *q) * next state and if the next packet has to be transmitted or lost. * The four states correspond to: * TX_IN_GAP_PERIOD => successfully transmitted packets within a gap period - * LOST_IN_BURST_PERIOD => isolated losses within a gap period - * LOST_IN_GAP_PERIOD => lost packets within a burst period - * TX_IN_GAP_PERIOD => successfully transmitted packets within a burst period + * LOST_IN_GAP_PERIOD => isolated losses within a gap period + * LOST_IN_BURST_PERIOD => lost packets within a burst period + * TX_IN_BURST_PERIOD => successfully transmitted packets within a burst period */ switch (clg->state) { case TX_IN_GAP_PERIOD: if (rnd < clg->a4) { - clg->state = LOST_IN_BURST_PERIOD; + clg->state = LOST_IN_GAP_PERIOD; return true; } else if (clg->a4 < rnd && rnd < clg->a1 + clg->a4) { - clg->state = LOST_IN_GAP_PERIOD; + clg->state = LOST_IN_BURST_PERIOD; return true; } else if (clg->a1 + clg->a4 < rnd) { clg->state = TX_IN_GAP_PERIOD; @@ -227,24 +227,24 @@ static bool loss_4state(struct netem_sched_data *q) break; case TX_IN_BURST_PERIOD: if (rnd < clg->a5) { - clg->state = LOST_IN_GAP_PERIOD; + clg->state = LOST_IN_BURST_PERIOD; return true; } else { clg->state = TX_IN_BURST_PERIOD; } break; - case LOST_IN_GAP_PERIOD: + case LOST_IN_BURST_PERIOD: if (rnd < clg->a3) clg->state = TX_IN_BURST_PERIOD; else if (clg->a3 < rnd && rnd < clg->a2 + clg->a3) { clg->state = TX_IN_GAP_PERIOD; } else if (clg->a2 + clg->a3 < rnd) { - clg->state = LOST_IN_GAP_PERIOD; + clg->state = LOST_IN_BURST_PERIOD; return true; } break; - case LOST_IN_BURST_PERIOD: + case LOST_IN_GAP_PERIOD: clg->state = TX_IN_GAP_PERIOD; break; } diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 0b7f9ba28deb..d4ce58c90f9f 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -1421,10 +1421,8 @@ static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt, if (err < 0) return err; - if (qdisc_dev(sch)->tx_queue_len + 1 > QFQ_MAX_AGG_CLASSES) - max_classes = QFQ_MAX_AGG_CLASSES; - else - max_classes = qdisc_dev(sch)->tx_queue_len + 1; + max_classes = min_t(u64, (u64)qdisc_dev(sch)->tx_queue_len + 1, + QFQ_MAX_AGG_CLASSES); /* max_cl_shift = floor(log_2(max_classes)) */ max_cl_shift = __fls(max_classes); q->max_agg_classes = 1<<max_cl_shift; |