diff options
Diffstat (limited to 'net/sched/act_api.c')
| -rw-r--r-- | net/sched/act_api.c | 1405 |
1 files changed, 1087 insertions, 318 deletions
diff --git a/net/sched/act_api.c b/net/sched/act_api.c index d4b8355737d8..ff6be5cfe2b0 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1,14 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_api.c Packet action API. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Author: Jamal Hadi Salim - * - * */ #include <linux/types.h> @@ -25,30 +19,32 @@ #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> +#include <net/tc_wrapper.h> -static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp) -{ - u32 chain_index = a->tcfa_action & TC_ACT_EXT_VAL_MASK; - - if (!tp) - return -EINVAL; - a->goto_chain = tcf_chain_get_by_act(tp->chain->block, chain_index); - if (!a->goto_chain) - return -ENOMEM; - return 0; -} +#ifdef CONFIG_INET +DEFINE_STATIC_KEY_FALSE(tcf_frag_xmit_count); +EXPORT_SYMBOL_GPL(tcf_frag_xmit_count); +#endif -static void tcf_action_goto_chain_fini(struct tc_action *a) +int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)) { - tcf_chain_put_by_act(a->goto_chain); +#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) { - const struct tcf_chain *chain = a->goto_chain; + const struct tcf_chain *chain = rcu_dereference_bh(a->goto_chain); res->goto_tp = rcu_dereference_bh(chain->filter_chain); } @@ -66,11 +62,56 @@ static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie, { struct tc_cookie *old; - old = xchg((__force struct tc_cookie **)old_cookie, new_cookie); + old = unrcu_pointer(xchg(old_cookie, RCU_INITIALIZER(new_cookie))); if (old) call_rcu(&old->rcu, tcf_free_cookie_rcu); } +int tcf_action_check_ctrlact(int action, struct tcf_proto *tp, + struct tcf_chain **newchain, + struct netlink_ext_ack *extack) +{ + int opcode = TC_ACT_EXT_OPCODE(action), ret = -EINVAL; + u32 chain_index; + + if (!opcode) + ret = action > TC_ACT_VALUE_MAX ? -EINVAL : 0; + else if (opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC) + ret = 0; + if (ret) { + NL_SET_ERR_MSG(extack, "invalid control action"); + goto end; + } + + if (TC_ACT_EXT_CMP(action, TC_ACT_GOTO_CHAIN)) { + chain_index = action & TC_ACT_EXT_VAL_MASK; + if (!tp || !newchain) { + ret = -EINVAL; + NL_SET_ERR_MSG(extack, + "can't goto NULL proto/chain"); + goto end; + } + *newchain = tcf_chain_get_by_act(tp->chain->block, chain_index); + if (!*newchain) { + ret = -ENOMEM; + NL_SET_ERR_MSG(extack, + "can't allocate goto_chain"); + } + } +end: + return ret; +} +EXPORT_SYMBOL(tcf_action_check_ctrlact); + +struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action, + struct tcf_chain *goto_chain) +{ + a->tcfa_action = action; + goto_chain = rcu_replace_pointer(a->goto_chain, goto_chain, 1); + return goto_chain; +} +EXPORT_SYMBOL(tcf_action_set_ctrlact); + /* XXX: For standalone actions, we don't need a RCU grace period either, because * actions are always connected to filters and filters are already destroyed in * RCU callbacks, so after a RCU grace period actions are already disconnected @@ -78,19 +119,250 @@ static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie, */ static void free_tcf(struct tc_action *p) { + struct tcf_chain *chain = rcu_dereference_protected(p->goto_chain, 1); + free_percpu(p->cpu_bstats); free_percpu(p->cpu_bstats_hw); free_percpu(p->cpu_qstats); - tcf_set_action_cookie(&p->act_cookie, NULL); - if (p->goto_chain) - tcf_action_goto_chain_fini(p); + tcf_set_action_cookie(&p->user_cookie, NULL); + if (chain) + tcf_chain_put_by_act(chain); 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; +} + +/* 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; + fl_action->cookie = (unsigned long)act; + + 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, 0, 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; + + 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); @@ -118,7 +390,7 @@ 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; @@ -144,29 +416,44 @@ 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) { - struct tc_cookie *act_cookie; + struct tc_cookie *user_cookie; u32 cookie_len = 0; rcu_read_lock(); - act_cookie = rcu_dereference(act->act_cookie); + user_cookie = rcu_dereference(act->user_cookie); - if (act_cookie) - cookie_len = nla_total_size(act_cookie->len); + if (user_cookie) + cookie_len = nla_total_size(user_cookie->len); rcu_read_unlock(); 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 */ + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) + /* TCA_STATS_PKT64 */ + + nla_total_size_64bit(sizeof(u64)) /* TCA_STATS_QUEUE */ + nla_total_size_64bit(sizeof(struct gnet_stats_queue)) - + nla_total_size(0) /* TCA_OPTIONS nested */ + + nla_total_size(0) /* TCA_ACT_OPTIONS nested */ + nla_total_size(sizeof(struct tcf_t)); /* TCA_GACT_TM */ } @@ -187,6 +474,80 @@ 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_ACT_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->user_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_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) +{ + unsigned char *b = skb_tail_pointer(skb); + struct nlattr *nest; + int err = -EINVAL; + u32 flags; + + if (tcf_action_dump_terse(skb, a, false)) + goto nla_put_failure; + + 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; + + 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; + + 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_u32(skb, TCA_ACT_IN_HW_COUNT, a->in_hw_count)) + goto nla_put_failure; + + nest = nla_nest_start_noflag(skb, TCA_ACT_OPTIONS); + if (nest == NULL) + goto nla_put_failure; + err = tcf_action_dump_old(skb, a, bind, ref); + if (err > 0) { + nla_nest_end(skb, nest); + return err; + } + +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) { @@ -197,27 +558,34 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, struct idr *idr = &idrinfo->action_idr; struct tc_action *p; unsigned long id = 1; + unsigned long tmp; mutex_lock(&idrinfo->lock); s_i = cb->args[0]; - idr_for_each_entry_ul(idr, p, id) { + idr_for_each_entry_ul(idr, p, tmp, id) { index++; if (index < s_i) continue; + if (IS_ERR(p)) + continue; if (jiffy_since && time_after(jiffy_since, (unsigned long)p->tcfa_tm.lastuse)) continue; - nest = nla_nest_start(skb, n_i); + tcf_action_update_hw_stats(p); + + nest = nla_nest_start_noflag(skb, n_i); if (!nest) { 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); @@ -225,7 +593,7 @@ 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; } @@ -235,7 +603,7 @@ 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; @@ -260,7 +628,8 @@ 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; @@ -268,27 +637,36 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, struct idr *idr = &idrinfo->action_idr; struct tc_action *p; unsigned long id = 1; + unsigned long tmp; - nest = nla_nest_start(skb, 0); + nest = nla_nest_start_noflag(skb, 0); if (nest == NULL) goto nla_put_failure; - if (nla_put_string(skb, TCA_KIND, ops->kind)) + if (nla_put_string(skb, TCA_ACT_KIND, ops->kind)) goto nla_put_failure; + ret = 0; mutex_lock(&idrinfo->lock); - idr_for_each_entry_ul(idr, p, id) { + 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); @@ -306,7 +684,7 @@ 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 { @@ -338,6 +716,31 @@ 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; @@ -373,7 +776,7 @@ static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index) int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, - int bind, bool cpustats) + int bind, bool cpustats, u32 flags) { struct tc_action *p = kzalloc(ops->size, GFP_KERNEL); struct tcf_idrinfo *idrinfo = tn->idrinfo; @@ -386,30 +789,34 @@ 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; p->tcfa_tm.lastuse = jiffies; p->tcfa_tm.firstuse = 0; + p->tcfa_flags = flags; if (est) { err = gen_new_estimator(&p->tcfa_bstats, p->cpu_bstats, &p->tcfa_rate_est, - &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; @@ -425,16 +832,16 @@ err1: } EXPORT_SYMBOL(tcf_idr_create); -void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a) +int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index, + struct nlattr *est, struct tc_action **a, + const struct tc_action_ops *ops, int bind, + u32 flags) { - 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); + /* Set cpustats according to actions flags. */ + return tcf_idr_create(tn, index, est, a, ops, bind, + !(flags & TCA_ACT_FLAGS_NO_PERCPU_STATS), flags); } -EXPORT_SYMBOL(tcf_idr_insert); +EXPORT_SYMBOL(tcf_idr_create_from_flags); /* Cleanup idr index that was allocated but not initialized. */ @@ -453,6 +860,9 @@ EXPORT_SYMBOL(tcf_idr_cleanup); * its reference and bind counters, and return 1. Otherwise insert temporary * error pointer (to prevent concurrent users from inserting actions with same * index) and return 0. + * + * May return -EAGAIN for binding actions in case of a parallel add/delete on + * the requested index. */ int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, @@ -461,43 +871,60 @@ int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, struct tcf_idrinfo *idrinfo = tn->idrinfo; struct tc_action *p; int ret; + u32 max; -again: - mutex_lock(&idrinfo->lock); if (*index) { + rcu_read_lock(); p = idr_find(&idrinfo->action_idr, *index); + if (IS_ERR(p)) { /* This means that another process allocated * index but did not assign the pointer yet. */ - mutex_unlock(&idrinfo->lock); - goto again; + rcu_read_unlock(); + return -EAGAIN; } - if (p) { - refcount_inc(&p->tcfa_refcnt); - if (bind) - atomic_inc(&p->tcfa_bindcnt); - *a = p; - ret = 1; - } else { - *a = NULL; - ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index, - *index, GFP_KERNEL); - if (!ret) - idr_replace(&idrinfo->action_idr, - ERR_PTR(-EBUSY), *index); + if (!p) { + /* Empty slot, try to allocate it */ + max = *index; + rcu_read_unlock(); + goto new; } + + if (!refcount_inc_not_zero(&p->tcfa_refcnt)) { + /* Action was deleted in parallel */ + rcu_read_unlock(); + return -EAGAIN; + } + + if (bind) + atomic_inc(&p->tcfa_bindcnt); + *a = p; + + rcu_read_unlock(); + + return 1; } else { + /* Find a slot */ *index = 1; - *a = NULL; - ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index, - UINT_MAX, GFP_KERNEL); - if (!ret) - idr_replace(&idrinfo->action_idr, ERR_PTR(-EBUSY), - *index); + max = UINT_MAX; } + +new: + *a = NULL; + + mutex_lock(&idrinfo->lock); + ret = idr_alloc_u32(&idrinfo->action_idr, ERR_PTR(-EBUSY), index, max, + GFP_KERNEL); mutex_unlock(&idrinfo->lock); + + /* N binds raced for action allocation, + * retry for all the ones that failed. + */ + if (ret == -ENOSPC && *index == max) + ret = -EAGAIN; + return ret; } EXPORT_SYMBOL(tcf_idr_check_alloc); @@ -506,23 +933,84 @@ void tcf_idrinfo_destroy(const struct tc_action_ops *ops, struct tcf_idrinfo *idrinfo) { struct idr *idr = &idrinfo->action_idr; + bool mutex_taken = false; struct tc_action *p; - int ret; unsigned long id = 1; + unsigned long tmp; + int ret; - idr_for_each_entry_ul(idr, p, id) { + idr_for_each_entry_ul(idr, p, tmp, id) { + if (tc_act_in_hw(p) && !mutex_taken) { + rtnl_lock(); + mutex_taken = true; + } ret = __tcf_idr_release(p, false, true); if (ret == ACT_P_DELETED) module_put(ops->owner); else if (ret < 0) return; } + if (mutex_taken) + rtnl_unlock(); idr_destroy(&idrinfo->action_idr); } 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) @@ -530,7 +1018,7 @@ 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, @@ -541,18 +1029,31 @@ 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->type == a->type || (strcmp(act->kind, a->kind) == 0)) { - write_unlock(&act_mod_lock); - unregister_pernet_subsys(ops); - return -EEXIST; + if (act->id == a->id || (strcmp(act->kind, a->kind) == 0)) { + 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); @@ -571,8 +1072,11 @@ 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); @@ -615,7 +1119,7 @@ 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) @@ -631,16 +1135,26 @@ 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; } -repeat: - ret = a->ops->act(skb, a, res); - if (ret == TC_ACT_REPEAT) - goto repeat; /* we need a ttl - JHS */ + if (tc_act_skip_sw(a->tcfa_flags)) + continue; + + repeat_ttl = 32; +repeat: + ret = tc_act(skb, a, res); + 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)) { @@ -654,6 +1168,11 @@ repeat: return TC_ACT_OK; } } else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) { + if (unlikely(!rcu_access_pointer(a->goto_chain))) { + tcf_set_drop_reason(skb, + SKB_DROP_REASON_TC_CHAIN_NOTFOUND); + return TC_ACT_SHOT; + } tcf_action_goto_chain_exec(a, res); } @@ -671,8 +1190,7 @@ int tcf_action_destroy(struct tc_action *actions[], int bind) struct tc_action *a; int ret = 0, i; - for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { - a = actions[i]; + tcf_act_for_each_action(i, a, actions) { actions[i] = NULL; ops = a->ops; ret = __tcf_idr_release(a, bind, true); @@ -684,92 +1202,58 @@ 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); } -/* Put all actions in this array, skip those NULL's. */ static void tcf_action_put_many(struct tc_action *actions[]) { + struct tc_action *a; int i; - for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { - struct tc_action *a = actions[i]; - const struct tc_action_ops *ops; - - if (!a) - continue; - ops = a->ops; + tcf_act_for_each_action(i, a, actions) { + const struct tc_action_ops *ops = a->ops; if (tcf_action_put(a)) module_put(ops->owner); } } -int -tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref) +static void tca_put_bound_many(struct tc_action *actions[], int init_res[]) { - return a->ops->dump(skb, a, bind, ref); -} - -int -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; + struct tc_action *a; + int i; - 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; + tcf_act_for_each_action(i, a, actions) { + const struct tc_action_ops *ops = a->ops; - 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 (init_res[i] == ACT_P_CREATED) + continue; - nest = nla_nest_start(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - err = tcf_action_dump_old(skb, a, bind, ref); - if (err > 0) { - nla_nest_end(skb, nest); - return err; + if (tcf_action_put(a)) + module_put(ops->owner); } +} -nla_put_failure: - nlmsg_trim(skb, b); - return -1; +int +tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref) +{ + return a->ops->dump(skb, a, bind, ref); } -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; struct nlattr *nest; - for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { - a = actions[i]; - nest = nla_nest_start(skb, a->order); + tcf_act_for_each_action(i, a, 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); @@ -800,72 +1284,91 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) return c; } -static bool tcf_action_valid(int action) +static u8 tcf_action_hw_stats_get(struct nlattr *hw_stats_attr) { - int opcode = TC_ACT_EXT_OPCODE(action); + struct nla_bitfield32 hw_stats_bf; - if (!opcode) - return action <= TC_ACT_VALUE_MAX; - return opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC; + /* 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; } -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) +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] = 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), +}; + +void tcf_idr_insert_many(struct tc_action *actions[], int init_res[]) { struct tc_action *a; + int i; + + tcf_act_for_each_action(i, a, actions) { + struct tcf_idrinfo *idrinfo; + + if (init_res[i] == ACT_P_BOUND) + continue; + + idrinfo = a->idrinfo; + mutex_lock(&idrinfo->lock); + /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */ + idr_replace(&idrinfo->action_idr, a, a->tcfa_index); + mutex_unlock(&idrinfo->lock); + } +} + +struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, u32 flags, + struct netlink_ext_ack *extack) +{ + bool police = flags & TCA_ACT_FLAGS_POLICE; + 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) { - err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, extack); + 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; - } - if (tb[TCA_ACT_COOKIE]) { - int cklen = nla_len(tb[TCA_ACT_COOKIE]); - - if (cklen > TC_COOKIE_MAX_SIZE) { - NL_SET_ERR_MSG(extack, "TC cookie size above the maximum"); - goto err_out; - } - - cookie = nla_memdup_cookie(tb); - if (!cookie) { - NL_SET_ERR_MSG(extack, "No memory to generate TC cookie"); - err = -ENOMEM; - goto err_out; - } + return ERR_PTR(err); } } else { - if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ) { + if (strscpy(act_name, "police", IFNAMSIZ) < 0) { NL_SET_ERR_MSG(extack, "TC action name too long"); - err = -EINVAL; - goto err_out; + return ERR_PTR(-EINVAL); } } a_o = tc_lookup_action_n(act_name); if (a_o == NULL) { #ifdef CONFIG_MODULES + bool rtnl_held = !(flags & TCA_ACT_FLAGS_NO_RTNL); + if (rtnl_held) rtnl_unlock(); - request_module("act_%s", act_name); + request_module(NET_ACT_ALIAS_PREFIX "%s", act_name); if (rtnl_held) rtnl_lock(); @@ -878,105 +1381,222 @@ 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); } - /* backward compatibility for policer */ - if (name == NULL) - err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind, - rtnl_held, extack); - else - err = a_o->init(net, nla, est, &a, ovr, bind, rtnl_held, - extack); - if (err < 0) - goto err_mod; + return a_o; +} - if (!name && tb[TCA_ACT_COOKIE]) - tcf_set_action_cookie(&a->act_cookie, cookie); +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 }; + struct tc_cookie *user_cookie = NULL; + u8 hw_stats = TCA_ACT_HW_STATS_ANY; + struct nlattr *tb[TCA_ACT_MAX + 1]; + struct tc_action *a; + int err; - /* 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)) { - err = tcf_action_goto_chain_init(a, tp); - if (err) { - tcf_action_destroy_1(a, bind); - NL_SET_ERR_MSG(extack, "Failed to init TC action chain"); + /* backward compatibility for policer */ + 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]) { + user_cookie = nla_memdup_cookie(tb); + if (!user_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; + } } - } - if (!tcf_action_valid(a->tcfa_action)) { - tcf_action_destroy_1(a, bind); - NL_SET_ERR_MSG(extack, "Invalid control action value"); - return ERR_PTR(-EINVAL); + 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_out; + *init_res = err; + + if (!police && tb[TCA_ACT_COOKIE]) + tcf_set_action_cookie(&a->user_cookie, user_cookie); + + if (!police) + a->hw_stats = hw_stats; return a; -err_mod: - module_put(a_o->owner); err_out: - if (cookie) { - kfree(cookie->data); - kfree(cookie); + if (user_cookie) { + kfree(user_cookie->data); + kfree(user_cookie); } 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 nlattr *tb[TCA_ACT_MAX_PRIO + 1]; + struct tc_action_ops *ops[TCA_ACT_MAX_PRIO] = {}; + struct nlattr *tb[TCA_ACT_MAX_PRIO + 2]; struct tc_action *act; size_t sz = 0; int err; int i; - err = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack); + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX_PRIO + 1, nla, NULL, + extack); if (err < 0) return err; + /* The nested attributes are parsed as types, but they are really an + * array of actions. So we parse one more than we can handle, and return + * an error if the last one is set (as that indicates that the request + * contained more than the maximum number of actions). + */ + if (tb[TCA_ACT_MAX_PRIO + 1]) { + NL_SET_ERR_MSG_FMT(extack, + "Only %d actions supported per filter", + TCA_ACT_MAX_PRIO); + return -EINVAL; + } + 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, 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; } - act->order = i; 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)) { + /* Action is created by classifier and is not + * standalone. Check that the user did not set + * any action flags different than the + * classifier flags, and inherit the flags from + * the classifier for the compatibility case + * where no flags were specified at all. + */ + if ((tc_act_skip_sw(act->tcfa_flags) && !skip_sw) || + (tc_act_skip_hw(act->tcfa_flags) && !skip_hw)) { + NL_SET_ERR_MSG(extack, + "Mismatch between action and filter offload flags"); + err = -EINVAL; + goto err; + } + if (skip_sw) + act->tcfa_flags |= TCA_ACT_FLAGS_SKIP_SW; + if (skip_hw) + act->tcfa_flags |= TCA_ACT_FLAGS_SKIP_HW; + continue; + } + + /* Action is standalone */ + 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, init_res); + *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 && ops[i]; i++) + module_put(ops[i]->owner); return err; } +void tcf_action_update_stats(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, bool hw) +{ + if (a->cpu_bstats) { + _bstats_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); + + this_cpu_ptr(a->cpu_qstats)->drops += drops; + + if (hw) + _bstats_update(this_cpu_ptr(a->cpu_bstats_hw), + bytes, packets); + return; + } + + _bstats_update(&a->tcfa_bstats, bytes, packets); + atomic_add(drops, &a->tcfa_drops); + if (hw) + _bstats_update(&a->tcfa_bstats_hw, bytes, packets); +} +EXPORT_SYMBOL(tcf_action_update_stats); + int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p, int compat_mode) { - int err = 0; + struct gnet_stats_queue qstats = {0}; struct gnet_dump d; + int err = 0; if (p == NULL) goto errout; @@ -1000,13 +1620,17 @@ 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 || + qstats.drops = atomic_read(&p->tcfa_drops); + qstats.overlimits = atomic_read(&p->tcfa_overlimits); + + 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, - p->tcfa_qstats.qlen) < 0) + &qstats, + qstats.qlen) < 0) goto errout; if (gnet_stats_finish_copy(&d) < 0) @@ -1020,7 +1644,7 @@ errout: static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], u32 portid, u32 seq, u16 flags, int event, int bind, - int ref) + int ref, struct netlink_ext_ack *extack) { struct tcamsg *t; struct nlmsghdr *nlh; @@ -1035,16 +1659,21 @@ static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], t->tca__pad1 = 0; t->tca__pad2 = 0; - nest = nla_nest_start(skb, TCA_ACT_TAB); + if (extack && extack->_msg && + nla_put_string(skb, TCA_ROOT_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + + nest = nla_nest_start_noflag(skb, TCA_ACT_TAB); 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); nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; out_nlmsg_trim: @@ -1063,7 +1692,7 @@ tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, if (!skb) return -ENOBUFS; if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, - 0, 1) <= 0) { + 0, 1, NULL) <= 0) { NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action"); kfree_skb(skb); return -EINVAL; @@ -1082,7 +1711,8 @@ static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla, int index; int err; - err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, extack); + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, + tcf_action_policy, extack); if (err < 0) goto err_out; @@ -1101,7 +1731,7 @@ 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; } @@ -1136,7 +1766,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, b = skb_tail_pointer(skb); - err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, extack); + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, + tcf_action_policy, extack); if (err < 0) goto err_out; @@ -1159,13 +1790,13 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, t->tca__pad1 = 0; t->tca__pad2 = 0; - nest = nla_nest_start(skb, TCA_ACT_TAB); + nest = nla_nest_start_noflag(skb, TCA_ACT_TAB); if (!nest) { NL_SET_ERR_MSG(extack, "Failed to add new netlink message"); 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; @@ -1178,8 +1809,6 @@ 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"); @@ -1194,10 +1823,10 @@ err_out: static int tcf_action_delete(struct net *net, struct tc_action *actions[]) { + struct tc_action *a; int i; - for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { - struct tc_action *a = actions[i]; + tcf_act_for_each_action(i, a, actions) { const struct tc_action_ops *ops = a->ops; /* Actions can be deleted concurrently so we must save their * type and id to search again after reference is released. @@ -1209,7 +1838,7 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[]) if (tcf_action_put(a)) { /* last reference, action was deleted concurrently */ module_put(ops->owner); - } else { + } else { int ret; /* now do the delete */ @@ -1221,23 +1850,145 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[]) 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) +static struct sk_buff *tcf_reoffload_del_notify_msg(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, + }; + struct sk_buff *skb; + + skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); + if (!skb) + return ERR_PTR(-ENOBUFS); + + if (tca_get_fill(skb, actions, 0, 0, 0, RTM_DELACTION, 0, 1, NULL) <= 0) { + kfree_skb(skb); + return ERR_PTR(-EINVAL); + } + + return skb; +} + +static int tcf_reoffload_del_notify(struct net *net, struct tc_action *action) +{ + const struct tc_action_ops *ops = action->ops; + struct sk_buff *skb; + int ret; + + if (!rtnl_notify_needed(net, 0, RTNLGRP_TC)) { + skb = NULL; + } else { + skb = tcf_reoffload_del_notify_msg(net, action); + if (IS_ERR(skb)) + return PTR_ERR(skb); + } + + ret = tcf_idr_release_unsafe(action); + if (ret == ACT_P_DELETED) { + module_put(ops->owner); + ret = rtnetlink_maybe_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 struct sk_buff *tcf_del_notify_msg(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; - skb = alloc_skb(attr_size <= NLMSG_GOODSIZE ? NLMSG_GOODSIZE : attr_size, - GFP_KERNEL); + skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) - return -ENOBUFS; + return ERR_PTR(-ENOBUFS); if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION, - 0, 2) <= 0) { + 0, 2, extack) <= 0) { NL_SET_ERR_MSG(extack, "Failed to fill netlink TC action attributes"); kfree_skb(skb); - return -EINVAL; + return ERR_PTR(-EINVAL); + } + + return skb; +} + +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) +{ + struct sk_buff *skb; + int ret; + + if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) { + skb = NULL; + } else { + skb = tcf_del_notify_msg(net, n, actions, portid, attr_size, + extack); + if (IS_ERR(skb)) + return PTR_ERR(skb); } /* now do the delete */ @@ -1248,11 +1999,8 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], return ret; } - ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); - if (ret > 0) - return 0; - return ret; + return rtnetlink_maybe_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); } static int @@ -1265,7 +2013,8 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, size_t attr_size = 0; struct tc_action *actions[TCA_ACT_MAX_PRIO] = {}; - ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack); + ret = nla_parse_nested_deprecated(tb, TCA_ACT_MAX_PRIO, nla, NULL, + extack); if (ret < 0) return ret; @@ -1283,7 +2032,6 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, ret = PTR_ERR(act); goto err; } - act->order = i; attr_size += tcf_action_fill_size(act); actions[i - 1] = act; } @@ -1303,55 +2051,76 @@ err: return ret; } -static int -tcf_add_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], - u32 portid, size_t attr_size, struct netlink_ext_ack *extack) +static struct sk_buff *tcf_add_notify_msg(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); + skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) - return -ENOBUFS; + return ERR_PTR(-ENOBUFS); if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, n->nlmsg_flags, - RTM_NEWACTION, 0, 0) <= 0) { + RTM_NEWACTION, 0, 0, extack) <= 0) { NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action"); kfree_skb(skb); - return -EINVAL; + return ERR_PTR(-EINVAL); } - err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); - if (err > 0) - err = 0; - return err; + return skb; +} + +static int 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; + + if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) { + skb = NULL; + } else { + skb = tcf_add_notify_msg(net, n, actions, portid, attr_size, + extack); + if (IS_ERR(skb)) + return PTR_ERR(skb); + } + + return rtnetlink_maybe_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 ret = 0; + int loop, ret; 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, actions, init_res, + &attr_size, flags, 0, extack); + if (ret != -EAGAIN) + break; + } - ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, actions, - &attr_size, true, extack); 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 bound actions */ + tca_put_bound_many(actions, init_res); 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 }, }; @@ -1360,15 +2129,16 @@ 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)) return -EPERM; - ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ROOT_MAX, NULL, - extack); + ret = nlmsg_parse_deprecated(n, sizeof(struct tcamsg), tca, + TCA_ROOT_MAX, NULL, extack); if (ret < 0) return ret; @@ -1387,12 +2157,9 @@ 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; -replay: - 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); - if (ret == -EAGAIN) - goto replay; break; case RTM_DELACTION: ret = tca_action_gd(net, tca[TCA_ACT_TAB], n, @@ -1419,13 +2186,12 @@ static struct nlattr *find_dump_kind(struct nlattr **nla) if (tb1 == NULL) return NULL; - if (nla_parse(tb, TCA_ACT_MAX_PRIO, nla_data(tb1), - NLMSG_ALIGN(nla_len(tb1)), NULL, NULL) < 0) + if (nla_parse_deprecated(tb, TCA_ACT_MAX_PRIO, nla_data(tb1), NLMSG_ALIGN(nla_len(tb1)), NULL, NULL) < 0) return NULL; if (tb[1] == NULL) return NULL; - if (nla_parse_nested(tb2, TCA_ACT_MAX, tb[1], NULL, NULL) < 0) + if (nla_parse_nested_deprecated(tb2, TCA_ACT_MAX, tb[1], tcf_action_policy, NULL) < 0) return NULL; kind = tb2[TCA_ACT_KIND]; @@ -1449,8 +2215,8 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) u32 msecs_since = 0; u32 act_count = 0; - ret = nlmsg_parse(cb->nlh, sizeof(struct tcamsg), tb, TCA_ROOT_MAX, - tcaa_policy, cb->extack); + ret = nlmsg_parse_deprecated(cb->nlh, sizeof(struct tcamsg), tb, + TCA_ROOT_MAX, tcaa_policy, cb->extack); if (ret < 0) return ret; @@ -1491,11 +2257,11 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) if (!count_attr) goto out_module_put; - nest = nla_nest_start(skb, TCA_ACT_TAB); + nest = nla_nest_start_noflag(skb, TCA_ACT_TAB); 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; @@ -1520,13 +2286,16 @@ out_module_put: return skb->len; } +static const struct rtnl_msg_handler tc_action_rtnl_msg_handlers[] __initconst = { + {.msgtype = RTM_NEWACTION, .doit = tc_ctl_action}, + {.msgtype = RTM_DELACTION, .doit = tc_ctl_action}, + {.msgtype = RTM_GETACTION, .doit = tc_ctl_action, + .dumpit = tc_dump_action}, +}; + static int __init tc_action_init(void) { - rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL, 0); - rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL, 0); - rtnl_register(PF_UNSPEC, RTM_GETACTION, tc_ctl_action, tc_dump_action, - 0); - + rtnl_register_many(tc_action_rtnl_msg_handlers); return 0; } |
