diff options
Diffstat (limited to 'net/sched/act_api.c')
-rw-r--r-- | net/sched/act_api.c | 914 |
1 files changed, 747 insertions, 167 deletions
diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 8c466a712cda..9b31a10cc639 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -19,8 +19,26 @@ #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); +EXPORT_SYMBOL_GPL(tcf_frag_xmit_count); +#endif + +int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)) +{ +#ifdef CONFIG_INET + if (static_branch_unlikely(&tcf_frag_xmit_count)) + return sch_frag_xmit_hook(skb, xmit); +#endif + + return xmit(skb); +} +EXPORT_SYMBOL_GPL(tcf_dev_queue_xmit); static void tcf_action_goto_chain_exec(const struct tc_action *a, struct tcf_result *res) @@ -113,8 +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, extack); + 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, extack); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to setup tc actions for offload"); + 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); @@ -142,7 +396,7 @@ static int __tcf_action_put(struct tc_action *p, bool bind) return 0; } -int __tcf_idr_release(struct tc_action *p, bool bind, bool strict) +static int __tcf_idr_release(struct tc_action *p, bool bind, bool strict) { int ret = 0; @@ -168,7 +422,18 @@ int __tcf_idr_release(struct tc_action *p, bool bind, bool strict) return ret; } -EXPORT_SYMBOL(__tcf_idr_release); + +int tcf_idr_release(struct tc_action *a, bool bind) +{ + const struct tc_action_ops *ops = a->ops; + int ret; + + ret = __tcf_idr_release(a, bind, false); + if (ret == ACT_P_DELETED) + module_put(ops->owner); + return ret; +} +EXPORT_SYMBOL(tcf_idr_release); static size_t tcf_action_shared_attrs_size(const struct tc_action *act) { @@ -185,6 +450,7 @@ static size_t tcf_action_shared_attrs_size(const struct tc_action *act) return nla_total_size(0) /* action number nested */ + nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */ + cookie_len /* TCA_ACT_COOKIE */ + + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_HW_STATS */ + nla_total_size(0) /* TCA_ACT_STATS nested */ + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */ /* TCA_STATS_BASIC */ @@ -214,6 +480,36 @@ static size_t tcf_action_fill_size(const struct tc_action *act) return sz; } +static int +tcf_action_dump_terse(struct sk_buff *skb, struct tc_action *a, bool from_act) +{ + unsigned char *b = skb_tail_pointer(skb); + struct tc_cookie *cookie; + + if (nla_put_string(skb, TCA_KIND, a->ops->kind)) + goto nla_put_failure; + if (tcf_action_copy_stats(skb, a, 0)) + goto nla_put_failure; + if (from_act && nla_put_u32(skb, TCA_ACT_INDEX, a->tcfa_index)) + goto nla_put_failure; + + rcu_read_lock(); + cookie = rcu_dereference(a->act_cookie); + if (cookie) { + if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) { + rcu_read_unlock(); + goto nla_put_failure; + } + } + rcu_read_unlock(); + + return 0; + +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, struct netlink_callback *cb) { @@ -234,6 +530,8 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, index++; if (index < s_i) continue; + if (IS_ERR(p)) + continue; if (jiffy_since && time_after(jiffy_since, @@ -245,7 +543,9 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, index--; goto nla_put_failure; } - err = tcf_action_dump_1(skb, p, 0, 0); + err = (act_flags & TCA_ACT_FLAG_TERSE_DUMP) ? + tcf_action_dump_terse(skb, p, true) : + tcf_action_dump_1(skb, p, 0, 0); if (err < 0) { index--; nlmsg_trim(skb, nest); @@ -253,7 +553,7 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, } nla_nest_end(skb, nest); n_i++; - if (!(act_flags & TCA_FLAG_LARGE_DUMP_ON) && + if (!(act_flags & TCA_ACT_FLAG_LARGE_DUMP_ON) && n_i >= TCA_ACT_MAX_PRIO) goto done; } @@ -263,7 +563,7 @@ done: mutex_unlock(&idrinfo->lock); if (n_i) { - if (act_flags & TCA_FLAG_LARGE_DUMP_ON) + if (act_flags & TCA_ACT_FLAG_LARGE_DUMP_ON) cb->args[1] = n_i; } return n_i; @@ -288,7 +588,8 @@ static int tcf_idr_release_unsafe(struct tc_action *p) } static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct nlattr *nest; int n_i = 0; @@ -304,20 +605,28 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, if (nla_put_string(skb, TCA_KIND, ops->kind)) goto nla_put_failure; + ret = 0; mutex_lock(&idrinfo->lock); idr_for_each_entry_ul(idr, p, tmp, id) { + if (IS_ERR(p)) + continue; ret = tcf_idr_release_unsafe(p); - if (ret == ACT_P_DELETED) { + if (ret == ACT_P_DELETED) module_put(ops->owner); - n_i++; - } else if (ret < 0) { - mutex_unlock(&idrinfo->lock); - goto nla_put_failure; - } + else if (ret < 0) + break; + n_i++; } mutex_unlock(&idrinfo->lock); + if (ret < 0) { + if (n_i) + NL_SET_ERR_MSG(extack, "Unable to flush all TC actions"); + else + goto nla_put_failure; + } - if (nla_put_u32(skb, TCA_FCNT, n_i)) + ret = nla_put_u32(skb, TCA_FCNT, n_i); + if (ret) goto nla_put_failure; nla_nest_end(skb, nest); @@ -335,7 +644,7 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, struct tcf_idrinfo *idrinfo = tn->idrinfo; if (type == RTM_DELACTION) { - return tcf_del_walker(idrinfo, skb, ops); + return tcf_del_walker(idrinfo, skb, ops, extack); } else if (type == RTM_GETACTION) { return tcf_dump_walker(idrinfo, skb, cb); } else { @@ -367,6 +676,31 @@ int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index) } EXPORT_SYMBOL(tcf_idr_search); +static int __tcf_generic_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) +{ + struct tc_action_net *tn = net_generic(net, ops->net_id); + + if (unlikely(ops->walk)) + return ops->walk(net, skb, cb, type, ops, extack); + + return tcf_generic_walker(tn, skb, cb, type, ops, extack); +} + +static int __tcf_idr_search(struct net *net, + const struct tc_action_ops *ops, + struct tc_action **a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, ops->net_id); + + if (unlikely(ops->lookup)) + return ops->lookup(net, a, index); + + return tcf_idr_search(tn, a, index); +} + static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index) { struct tc_action *p; @@ -415,16 +749,18 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, atomic_set(&p->tcfa_bindcnt, 1); if (cpustats) { - p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); + p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync); if (!p->cpu_bstats) goto err1; - p->cpu_bstats_hw = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); + p->cpu_bstats_hw = netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync); if (!p->cpu_bstats_hw) goto err2; p->cpu_qstats = alloc_percpu(struct gnet_stats_queue); if (!p->cpu_qstats) goto err3; } + gnet_stats_basic_sync_init(&p->tcfa_bstats); + gnet_stats_basic_sync_init(&p->tcfa_bstats_hw); spin_lock_init(&p->tcfa_lock); p->tcfa_index = index; p->tcfa_tm.install = jiffies; @@ -434,12 +770,13 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, if (est) { err = gen_new_estimator(&p->tcfa_bstats, p->cpu_bstats, &p->tcfa_rate_est, - &p->tcfa_lock, NULL, est); + &p->tcfa_lock, false, est); if (err) goto err4; } p->idrinfo = idrinfo; + __module_get(ops->owner); p->ops = ops; *a = p; return 0; @@ -466,17 +803,6 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index, } 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; - - mutex_lock(&idrinfo->lock); - /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */ - WARN_ON(!IS_ERR(idr_replace(&idrinfo->action_idr, a, a->tcfa_index))); - mutex_unlock(&idrinfo->lock); -} -EXPORT_SYMBOL(tcf_idr_insert); - /* Cleanup idr index that was allocated but not initialized. */ void tcf_idr_cleanup(struct tc_action_net *tn, u32 index) @@ -565,6 +891,59 @@ 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) @@ -572,7 +951,7 @@ int tcf_register_action(struct tc_action_ops *act, struct tc_action_ops *a; int ret; - if (!act->act || !act->dump || !act->init || !act->walk || !act->lookup) + if (!act->act || !act->dump || !act->init) return -EINVAL; /* We have to register pernet ops before making the action ops visible, @@ -583,18 +962,31 @@ 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); @@ -613,8 +1005,11 @@ 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); @@ -657,7 +1052,7 @@ static struct tc_action_ops *tc_lookup_action(struct nlattr *kind) return res; } -/*TCA_ACT_MAX_PRIO is 32, there count upto 32 */ +/*TCA_ACT_MAX_PRIO is 32, there count up to 32 */ #define TCA_ACT_MAX_PRIO_MASK 0x1FF int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, int nr_actions, struct tcf_result *res) @@ -673,16 +1068,26 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, restart_act_graph: for (i = 0; i < nr_actions; i++) { const struct tc_action *a = actions[i]; + int repeat_ttl; if (jmp_prgcnt > 0) { jmp_prgcnt -= 1; continue; } + + if (tc_act_skip_sw(a->tcfa_flags)) + continue; + + repeat_ttl = 32; repeat: ret = a->ops->act(skb, a, res); - if (ret == TC_ACT_REPEAT) - goto repeat; /* we need a ttl - JHS */ - + if (unlikely(ret == TC_ACT_REPEAT)) { + if (--repeat_ttl != 0) + goto repeat; + /* suspicious opcode, stop pipeline */ + net_warn_ratelimited("TC_ACT_REPEAT abuse ?\n"); + return TC_ACT_OK; + } if (TC_ACT_EXT_CMP(ret, TC_ACT_JUMP)) { jmp_prgcnt = ret & TCA_ACT_MAX_PRIO_MASK; if (!jmp_prgcnt || (jmp_prgcnt > nr_actions)) { @@ -730,13 +1135,6 @@ int tcf_action_destroy(struct tc_action *actions[], int bind) return ret; } -static int tcf_action_destroy_1(struct tc_action *a, int bind) -{ - struct tc_action *actions[] = { a, NULL }; - - return tcf_action_destroy(actions, bind); -} - static int tcf_action_put(struct tc_action *p) { return __tcf_action_put(p, false); @@ -771,30 +1169,29 @@ 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; - struct tc_cookie *cookie; + u32 flags; - if (nla_put_string(skb, TCA_KIND, a->ops->kind)) + if (tcf_action_dump_terse(skb, a, false)) goto nla_put_failure; - if (tcf_action_copy_stats(skb, a, 0)) + + if (a->hw_stats != TCA_ACT_HW_STATS_ANY && + nla_put_bitfield32(skb, TCA_ACT_HW_STATS, + a->hw_stats, TCA_ACT_HW_STATS_ANY)) goto nla_put_failure; - rcu_read_lock(); - cookie = rcu_dereference(a->act_cookie); - if (cookie) { - if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) { - rcu_read_unlock(); - goto nla_put_failure; - } - } - rcu_read_unlock(); + if (a->used_hw_stats_valid && + nla_put_bitfield32(skb, TCA_ACT_USED_HW_STATS, + a->used_hw_stats, TCA_ACT_HW_STATS_ANY)) + goto nla_put_failure; - if (a->tcfa_flags) { - struct nla_bitfield32 flags = { a->tcfa_flags, - a->tcfa_flags, }; + flags = a->tcfa_flags & TCA_ACT_FLAGS_USER_MASK; + if (flags && + nla_put_bitfield32(skb, TCA_ACT_FLAGS, + flags, flags)) + goto nla_put_failure; - if (nla_put(skb, TCA_ACT_FLAGS, sizeof(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); if (nest == NULL) @@ -812,7 +1209,7 @@ nla_put_failure: EXPORT_SYMBOL(tcf_action_dump_1); int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], - int bind, int ref) + int bind, int ref, bool terse) { struct tc_action *a; int err = -EINVAL, i; @@ -823,7 +1220,8 @@ int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], nest = nla_nest_start_noflag(skb, i + 1); if (nest == NULL) goto nla_put_failure; - err = tcf_action_dump_1(skb, a, bind, ref); + err = terse ? tcf_action_dump_terse(skb, a, false) : + tcf_action_dump_1(skb, a, bind, ref); if (err < 0) goto errout; nla_nest_end(skb, nest); @@ -854,62 +1252,81 @@ 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 u8 tcf_action_hw_stats_get(struct nlattr *hw_stats_attr) +{ + struct nla_bitfield32 hw_stats_bf; + + /* If the user did not pass the attr, that means he does + * not care about the type. Return "any" in that case + * which is setting on all supported types. + */ + if (!hw_stats_attr) + return TCA_ACT_HW_STATS_ANY; + hw_stats_bf = nla_get_bitfield32(hw_stats_attr); + return hw_stats_bf.value; +} + 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 }, + [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), }; -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) +void tcf_idr_insert_many(struct tc_action *actions[]) { - struct nla_bitfield32 flags = { 0, 0 }; - struct tc_action *a; + int i; + + for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { + struct tc_action *a = actions[i]; + struct tcf_idrinfo *idrinfo; + + if (!a) + continue; + idrinfo = a->idrinfo; + mutex_lock(&idrinfo->lock); + /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc if + * it is just created, otherwise this is just a nop. + */ + idr_replace(&idrinfo->action_idr, a, a->tcfa_index); + mutex_unlock(&idrinfo->lock); + } +} + +struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police, + bool rtnl_held, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_ACT_MAX + 1]; struct tc_action_ops *a_o; - struct tc_cookie *cookie = NULL; char act_name[IFNAMSIZ]; - struct nlattr *tb[TCA_ACT_MAX + 1]; struct nlattr *kind; int err; - if (name == NULL) { + if (!police) { err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, tcf_action_policy, extack); if (err < 0) - goto err_out; + return ERR_PTR(err); err = -EINVAL; kind = tb[TCA_ACT_KIND]; if (!kind) { NL_SET_ERR_MSG(extack, "TC action kind must be specified"); - goto err_out; + return ERR_PTR(err); } - if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) { + if (nla_strscpy(act_name, kind, IFNAMSIZ) < 0) { NL_SET_ERR_MSG(extack, "TC action name too long"); - goto err_out; + return ERR_PTR(err); } - if (tb[TCA_ACT_COOKIE]) { - cookie = nla_memdup_cookie(tb); - if (!cookie) { - NL_SET_ERR_MSG(extack, "No memory to generate TC cookie"); - err = -ENOMEM; - goto err_out; - } - } - if (tb[TCA_ACT_FLAGS]) - flags = nla_get_bitfield32(tb[TCA_ACT_FLAGS]); } else { - if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ) { + if (strlcpy(act_name, "police", IFNAMSIZ) >= IFNAMSIZ) { NL_SET_ERR_MSG(extack, "TC action name too long"); - err = -EINVAL; - goto err_out; + return ERR_PTR(-EINVAL); } } @@ -931,46 +1348,71 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, * indicate this using -EAGAIN. */ if (a_o != NULL) { - err = -EAGAIN; - goto err_mod; + module_put(a_o->owner); + return ERR_PTR(-EAGAIN); } #endif NL_SET_ERR_MSG(extack, "Failed to load TC action module"); - err = -ENOENT; - goto err_out; + return ERR_PTR(-ENOENT); } + return a_o; +} + +struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, + struct nlattr *nla, struct nlattr *est, + struct tc_action_ops *a_o, int *init_res, + u32 flags, struct netlink_ext_ack *extack) +{ + bool police = flags & TCA_ACT_FLAGS_POLICE; + struct nla_bitfield32 userflags = { 0, 0 }; + u8 hw_stats = TCA_ACT_HW_STATS_ANY; + struct nlattr *tb[TCA_ACT_MAX + 1]; + struct tc_cookie *cookie = NULL; + struct tc_action *a; + int err; + /* backward compatibility for policer */ - if (name == NULL) - err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind, - rtnl_held, tp, flags.value, extack); - else - err = a_o->init(net, nla, est, &a, ovr, bind, rtnl_held, - tp, flags.value, extack); + if (!police) { + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, + tcf_action_policy, extack); + if (err < 0) + return ERR_PTR(err); + if (tb[TCA_ACT_COOKIE]) { + cookie = nla_memdup_cookie(tb); + if (!cookie) { + NL_SET_ERR_MSG(extack, "No memory to generate TC cookie"); + err = -ENOMEM; + goto err_out; + } + } + hw_stats = tcf_action_hw_stats_get(tb[TCA_ACT_HW_STATS]); + 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); + } else { + err = a_o->init(net, nla, est, &a, tp, userflags.value | flags, + extack); + } if (err < 0) - goto err_mod; + goto err_out; + *init_res = err; - if (!name && tb[TCA_ACT_COOKIE]) + if (!police && tb[TCA_ACT_COOKIE]) tcf_set_action_cookie(&a->act_cookie, cookie); - /* module count goes up only when brand new policy is created - * if it exists and is only bound to in a_o->init() then - * ACT_P_CREATED is not returned (a zero is). - */ - if (err != ACT_P_CREATED) - module_put(a_o->owner); - - if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN) && - !rcu_access_pointer(a->goto_chain)) { - tcf_action_destroy_1(a, bind); - NL_SET_ERR_MSG(extack, "can't use goto chain with NULL chain"); - return ERR_PTR(-EINVAL); - } + if (!police) + a->hw_stats = hw_stats; return a; -err_mod: - module_put(a_o->owner); err_out: if (cookie) { kfree(cookie->data); @@ -979,13 +1421,20 @@ 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, char *name, int ovr, int bind, - struct tc_action *actions[], size_t *attr_size, - bool rtnl_held, struct netlink_ext_ack *extack) + struct nlattr *est, struct tc_action *actions[], + 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] = {}; struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; size_t sz = 0; @@ -998,8 +1447,21 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, return err; for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { - act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind, - rtnl_held, extack); + struct tc_action_ops *a_o; + + a_o = tc_action_load_ops(tb[i], flags & TCA_ACT_FLAGS_POLICE, + !(flags & TCA_ACT_FLAGS_NO_RTNL), + extack); + if (IS_ERR(a_o)) { + err = PTR_ERR(a_o); + goto err_mod; + } + ops[i - 1] = a_o; + } + + for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { + act = tcf_action_init_1(net, tp, tb[i], est, ops[i - 1], + &init_res[i - 1], flags, extack); if (IS_ERR(act)) { err = PTR_ERR(act); goto err; @@ -1007,34 +1469,61 @@ 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)) { + NL_SET_ERR_MSG(extack, + "Mismatch between action and filter offload 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 + * between, we could not handle the failure gracefully. + */ + tcf_idr_insert_many(actions); + *attr_size = tcf_action_full_attrs_size(sz); - return i - 1; + err = i - 1; + goto err_mod; err: - tcf_action_destroy(actions, bind); + tcf_action_destroy(actions, flags & TCA_ACT_FLAGS_BIND); +err_mod: + for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { + if (ops[i]) + module_put(ops[i]->owner); + } return err; } -void tcf_action_update_stats(struct tc_action *a, u64 bytes, u32 packets, - bool drop, bool hw) +void tcf_action_update_stats(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, bool hw) { if (a->cpu_bstats) { - _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); + _bstats_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); - if (drop) - this_cpu_ptr(a->cpu_qstats)->drops += packets; + this_cpu_ptr(a->cpu_qstats)->drops += drops; if (hw) - _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw), - bytes, packets); + _bstats_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; + a->tcfa_qstats.drops += drops; if (hw) _bstats_update(&a->tcfa_bstats_hw, bytes, packets); } @@ -1049,6 +1538,9 @@ 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. */ @@ -1068,9 +1560,10 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p, if (err < 0) goto errout; - if (gnet_stats_copy_basic(NULL, &d, p->cpu_bstats, &p->tcfa_bstats) < 0 || - gnet_stats_copy_basic_hw(NULL, &d, p->cpu_bstats_hw, - &p->tcfa_bstats_hw) < 0 || + if (gnet_stats_copy_basic(&d, p->cpu_bstats, + &p->tcfa_bstats, false) < 0 || + gnet_stats_copy_basic_hw(&d, p->cpu_bstats_hw, + &p->tcfa_bstats_hw, false) < 0 || gnet_stats_copy_rate_est(&d, &p->tcfa_rate_est) < 0 || gnet_stats_copy_queue(&d, p->cpu_qstats, &p->tcfa_qstats, @@ -1107,7 +1600,7 @@ static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], if (!nest) goto out_nlmsg_trim; - if (tcf_action_dump(skb, actions, bind, ref) < 0) + if (tcf_action_dump(skb, actions, bind, ref, false) < 0) goto out_nlmsg_trim; nla_nest_end(skb, nest); @@ -1170,7 +1663,7 @@ static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla, goto err_out; } err = -ENOENT; - if (ops->lookup(net, &a, index) == 0) { + if (__tcf_idr_search(net, ops, &a, index) == 0) { NL_SET_ERR_MSG(extack, "TC action with specified index not found"); goto err_mod; } @@ -1235,7 +1728,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, goto out_module_put; } - err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops, extack); + err = __tcf_generic_walker(net, skb, &dcb, RTM_DELACTION, ops, extack); if (err <= 0) { nla_nest_cancel(skb, nest); goto out_module_put; @@ -1248,8 +1741,6 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, module_put(ops->owner); err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); - if (err > 0) - return 0; if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send TC action flush notification"); @@ -1292,6 +1783,96 @@ 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) { @@ -1320,8 +1901,6 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); - if (ret > 0) - return 0; return ret; } @@ -1378,7 +1957,6 @@ tcf_add_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], u32 portid, size_t attr_size, struct netlink_ext_ack *extack) { struct sk_buff *skb; - int err = 0; skb = alloc_skb(attr_size <= NLMSG_GOODSIZE ? NLMSG_GOODSIZE : attr_size, GFP_KERNEL); @@ -1392,24 +1970,22 @@ tcf_add_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], return -EINVAL; } - err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); - if (err > 0) - err = 0; - return err; + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); } static int tcf_action_add(struct net *net, struct nlattr *nla, - struct nlmsghdr *n, u32 portid, int ovr, + struct nlmsghdr *n, u32 portid, u32 flags, struct netlink_ext_ack *extack) { size_t attr_size = 0; - int loop, ret; + int loop, ret, i; struct tc_action *actions[TCA_ACT_MAX_PRIO] = {}; + int init_res[TCA_ACT_MAX_PRIO] = {}; for (loop = 0; loop < 10; loop++) { - ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, - actions, &attr_size, true, extack); + ret = tcf_action_init(net, NULL, nla, NULL, actions, init_res, + &attr_size, flags, 0, extack); if (ret != -EAGAIN) break; } @@ -1417,16 +1993,19 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, if (ret < 0) return ret; ret = tcf_add_notify(net, n, actions, portid, attr_size, extack); - if (ovr) - tcf_action_put_many(actions); + + /* only put existing actions */ + for (i = 0; i < TCA_ACT_MAX_PRIO; i++) + if (init_res[i] == ACT_P_CREATED) + actions[i] = NULL; + tcf_action_put_many(actions); return ret; } -static u32 tcaa_root_flags_allowed = TCA_FLAG_LARGE_DUMP_ON; static const struct nla_policy tcaa_policy[TCA_ROOT_MAX + 1] = { - [TCA_ROOT_FLAGS] = { .type = NLA_BITFIELD32, - .validation_data = &tcaa_root_flags_allowed }, + [TCA_ROOT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_ACT_FLAG_LARGE_DUMP_ON | + TCA_ACT_FLAG_TERSE_DUMP), [TCA_ROOT_TIME_DELTA] = { .type = NLA_U32 }, }; @@ -1435,8 +2014,9 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_ROOT_MAX + 1]; - u32 portid = skb ? NETLINK_CB(skb).portid : 0; - int ret = 0, ovr = 0; + u32 portid = NETLINK_CB(skb).portid; + u32 flags = 0; + int ret = 0; if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN)) @@ -1462,8 +2042,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, * is zero) then just set this */ if (n->nlmsg_flags & NLM_F_REPLACE) - ovr = 1; - ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr, + flags = TCA_ACT_FLAGS_REPLACE; + ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, flags, extack); break; case RTM_DELACTION: @@ -1566,7 +2146,7 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) if (nest == NULL) goto out_module_put; - ret = a_o->walk(net, skb, cb, RTM_GETACTION, a_o, NULL); + ret = __tcf_generic_walker(net, skb, cb, RTM_GETACTION, a_o, NULL); if (ret < 0) goto out_module_put; |