diff options
Diffstat (limited to 'net/sched/cls_api.c')
| -rw-r--r-- | net/sched/cls_api.c | 3092 |
1 files changed, 2317 insertions, 775 deletions
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index e2b5cb2eb34e..ebca4b926dcf 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1,17 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/cls_api.c Packet classifier 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. - * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Changes: * * Eduardo J. Blanco <ejbs@netlabs.com.uy> :990222: kmod support - * */ #include <linux/module.h> @@ -25,14 +20,28 @@ #include <linux/kmod.h> #include <linux/slab.h> #include <linux/idr.h> +#include <linux/jhash.h> +#include <linux/rculist.h> #include <linux/rhashtable.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> - -extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; +#include <net/tc_act/tc_pedit.h> +#include <net/tc_act/tc_mirred.h> +#include <net/tc_act/tc_vlan.h> +#include <net/tc_act/tc_tunnel_key.h> +#include <net/tc_act/tc_csum.h> +#include <net/tc_act/tc_gact.h> +#include <net/tc_act/tc_police.h> +#include <net/tc_act/tc_sample.h> +#include <net/tc_act/tc_skbedit.h> +#include <net/tc_act/tc_ct.h> +#include <net/tc_act/tc_mpls.h> +#include <net/tc_act/tc_gate.h> +#include <net/flow_offload.h> +#include <net/tc_wrapper.h> /* The list of all installed classifier types */ static LIST_HEAD(tcf_proto_base); @@ -40,6 +49,182 @@ static LIST_HEAD(tcf_proto_base); /* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK(cls_mod_lock); +static struct xarray tcf_exts_miss_cookies_xa; +struct tcf_exts_miss_cookie_node { + const struct tcf_chain *chain; + const struct tcf_proto *tp; + const struct tcf_exts *exts; + u32 chain_index; + u32 tp_prio; + u32 handle; + u32 miss_cookie_base; + struct rcu_head rcu; +}; + +/* Each tc action entry cookie will be comprised of 32bit miss_cookie_base + + * action index in the exts tc actions array. + */ +union tcf_exts_miss_cookie { + struct { + u32 miss_cookie_base; + u32 act_index; + }; + u64 miss_cookie; +}; + +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) +static int +tcf_exts_miss_cookie_base_alloc(struct tcf_exts *exts, struct tcf_proto *tp, + u32 handle) +{ + struct tcf_exts_miss_cookie_node *n; + static u32 next; + int err; + + if (WARN_ON(!handle || !tp->ops->get_exts)) + return -EINVAL; + + n = kzalloc(sizeof(*n), GFP_KERNEL); + if (!n) + return -ENOMEM; + + n->chain_index = tp->chain->index; + n->chain = tp->chain; + n->tp_prio = tp->prio; + n->tp = tp; + n->exts = exts; + n->handle = handle; + + err = xa_alloc_cyclic(&tcf_exts_miss_cookies_xa, &n->miss_cookie_base, + n, xa_limit_32b, &next, GFP_KERNEL); + if (err < 0) + goto err_xa_alloc; + + exts->miss_cookie_node = n; + return 0; + +err_xa_alloc: + kfree(n); + return err; +} + +static void tcf_exts_miss_cookie_base_destroy(struct tcf_exts *exts) +{ + struct tcf_exts_miss_cookie_node *n; + + if (!exts->miss_cookie_node) + return; + + n = exts->miss_cookie_node; + xa_erase(&tcf_exts_miss_cookies_xa, n->miss_cookie_base); + kfree_rcu(n, rcu); +} + +static struct tcf_exts_miss_cookie_node * +tcf_exts_miss_cookie_lookup(u64 miss_cookie, int *act_index) +{ + union tcf_exts_miss_cookie mc = { .miss_cookie = miss_cookie, }; + + *act_index = mc.act_index; + return xa_load(&tcf_exts_miss_cookies_xa, mc.miss_cookie_base); +} +#else /* IS_ENABLED(CONFIG_NET_TC_SKB_EXT) */ +static int +tcf_exts_miss_cookie_base_alloc(struct tcf_exts *exts, struct tcf_proto *tp, + u32 handle) +{ + return 0; +} + +static void tcf_exts_miss_cookie_base_destroy(struct tcf_exts *exts) +{ +} +#endif /* IS_ENABLED(CONFIG_NET_TC_SKB_EXT) */ + +static u64 tcf_exts_miss_cookie_get(u32 miss_cookie_base, int act_index) +{ + union tcf_exts_miss_cookie mc = { .act_index = act_index, }; + + if (!miss_cookie_base) + return 0; + + mc.miss_cookie_base = miss_cookie_base; + return mc.miss_cookie; +} + +#ifdef CONFIG_NET_CLS_ACT +DEFINE_STATIC_KEY_FALSE(tc_skb_ext_tc); +EXPORT_SYMBOL(tc_skb_ext_tc); + +void tc_skb_ext_tc_enable(void) +{ + static_branch_inc(&tc_skb_ext_tc); +} +EXPORT_SYMBOL(tc_skb_ext_tc_enable); + +void tc_skb_ext_tc_disable(void) +{ + static_branch_dec(&tc_skb_ext_tc); +} +EXPORT_SYMBOL(tc_skb_ext_tc_disable); +#endif + +static u32 destroy_obj_hashfn(const struct tcf_proto *tp) +{ + return jhash_3words(tp->chain->index, tp->prio, + (__force __u32)tp->protocol, 0); +} + +static void tcf_proto_signal_destroying(struct tcf_chain *chain, + struct tcf_proto *tp) +{ + struct tcf_block *block = chain->block; + + mutex_lock(&block->proto_destroy_lock); + hash_add_rcu(block->proto_destroy_ht, &tp->destroy_ht_node, + destroy_obj_hashfn(tp)); + mutex_unlock(&block->proto_destroy_lock); +} + +static bool tcf_proto_cmp(const struct tcf_proto *tp1, + const struct tcf_proto *tp2) +{ + return tp1->chain->index == tp2->chain->index && + tp1->prio == tp2->prio && + tp1->protocol == tp2->protocol; +} + +static bool tcf_proto_exists_destroying(struct tcf_chain *chain, + struct tcf_proto *tp) +{ + u32 hash = destroy_obj_hashfn(tp); + struct tcf_proto *iter; + bool found = false; + + rcu_read_lock(); + hash_for_each_possible_rcu(chain->block->proto_destroy_ht, iter, + destroy_ht_node, hash) { + if (tcf_proto_cmp(tp, iter)) { + found = true; + break; + } + } + rcu_read_unlock(); + + return found; +} + +static void +tcf_proto_signal_destroyed(struct tcf_chain *chain, struct tcf_proto *tp) +{ + struct tcf_block *block = chain->block; + + mutex_lock(&block->proto_destroy_lock); + if (hash_hashed(&tp->destroy_ht_node)) + hash_del_rcu(&tp->destroy_ht_node); + mutex_unlock(&block->proto_destroy_lock); +} + /* Find classifier type by string name */ static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind) @@ -61,7 +246,8 @@ static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind) } static const struct tcf_proto_ops * -tcf_proto_lookup_ops(const char *kind, struct netlink_ext_ack *extack) +tcf_proto_lookup_ops(const char *kind, bool rtnl_held, + struct netlink_ext_ack *extack) { const struct tcf_proto_ops *ops; @@ -69,9 +255,11 @@ tcf_proto_lookup_ops(const char *kind, struct netlink_ext_ack *extack) if (ops) return ops; #ifdef CONFIG_MODULES - rtnl_unlock(); - request_module("cls_%s", kind); - rtnl_lock(); + if (rtnl_held) + rtnl_unlock(); + request_module(NET_CLS_ALIAS_PREFIX "%s", kind); + if (rtnl_held) + rtnl_lock(); ops = __tcf_proto_lookup_ops(kind); /* We dropped the RTNL semaphore in order to perform * the module load. So, even if we succeeded in loading @@ -109,7 +297,7 @@ EXPORT_SYMBOL(register_tcf_proto_ops); static struct workqueue_struct *tc_filter_wq; -int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) +void unregister_tcf_proto_ops(struct tcf_proto_ops *ops) { struct tcf_proto_ops *t; int rc = -ENOENT; @@ -129,7 +317,8 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) } } write_unlock(&cls_mod_lock); - return rc; + + WARN(rc, "unregister tc filter kind(%s) failed %d\n", ops->kind, rc); } EXPORT_SYMBOL(unregister_tcf_proto_ops); @@ -152,8 +341,37 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) return TC_H_MAJ(first); } +static bool tcf_proto_check_kind(struct nlattr *kind, char *name) +{ + if (kind) + return nla_strscpy(name, kind, IFNAMSIZ) < 0; + memset(name, 0, IFNAMSIZ); + return false; +} + +static bool tcf_proto_is_unlocked(const char *kind) +{ + const struct tcf_proto_ops *ops; + bool ret; + + if (strlen(kind) == 0) + return false; + + ops = tcf_proto_lookup_ops(kind, false, NULL); + /* On error return false to take rtnl lock. Proto lookup/create + * functions will perform lookup again and properly handle errors. + */ + if (IS_ERR(ops)) + return false; + + ret = !!(ops->flags & TCF_PROTO_OPS_DOIT_UNLOCKED); + module_put(ops->owner); + return ret; +} + static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, u32 prio, struct tcf_chain *chain, + bool rtnl_held, struct netlink_ext_ack *extack) { struct tcf_proto *tp; @@ -163,7 +381,7 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, if (!tp) return ERR_PTR(-ENOBUFS); - tp->ops = tcf_proto_lookup_ops(kind, extack); + tp->ops = tcf_proto_lookup_ops(kind, rtnl_held, extack); if (IS_ERR(tp->ops)) { err = PTR_ERR(tp->ops); goto errout; @@ -172,6 +390,9 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, tp->protocol = protocol; tp->prio = prio; tp->chain = chain; + tp->usesw = !tp->ops->reoffload; + spin_lock_init(&tp->lock); + refcount_set(&tp->refcnt, 1); err = tp->ops->init(tp); if (err) { @@ -185,14 +406,89 @@ errout: return ERR_PTR(err); } -static void tcf_proto_destroy(struct tcf_proto *tp, - struct netlink_ext_ack *extack) +static void tcf_proto_get(struct tcf_proto *tp) { - tp->ops->destroy(tp, extack); + refcount_inc(&tp->refcnt); +} + +static void tcf_proto_count_usesw(struct tcf_proto *tp, bool add) +{ +#ifdef CONFIG_NET_CLS_ACT + struct tcf_block *block = tp->chain->block; + bool counted = false; + + if (!add) { + if (tp->usesw && tp->counted) { + if (!atomic_dec_return(&block->useswcnt)) + static_branch_dec(&tcf_sw_enabled_key); + tp->counted = false; + } + return; + } + + spin_lock(&tp->lock); + if (tp->usesw && !tp->counted) { + counted = true; + tp->counted = true; + } + spin_unlock(&tp->lock); + + if (counted && atomic_inc_return(&block->useswcnt) == 1) + static_branch_inc(&tcf_sw_enabled_key); +#endif +} + +static void tcf_chain_put(struct tcf_chain *chain); + +static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held, + bool sig_destroy, struct netlink_ext_ack *extack) +{ + tp->ops->destroy(tp, rtnl_held, extack); + tcf_proto_count_usesw(tp, false); + if (sig_destroy) + tcf_proto_signal_destroyed(tp->chain, tp); + tcf_chain_put(tp->chain); module_put(tp->ops->owner); kfree_rcu(tp, rcu); } +static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + if (refcount_dec_and_test(&tp->refcnt)) + tcf_proto_destroy(tp, rtnl_held, true, extack); +} + +static bool tcf_proto_check_delete(struct tcf_proto *tp) +{ + if (tp->ops->delete_empty) + return tp->ops->delete_empty(tp); + + tp->deleting = true; + return tp->deleting; +} + +static void tcf_proto_mark_delete(struct tcf_proto *tp) +{ + spin_lock(&tp->lock); + tp->deleting = true; + spin_unlock(&tp->lock); +} + +static bool tcf_proto_is_deleting(struct tcf_proto *tp) +{ + bool deleting; + + spin_lock(&tp->lock); + deleting = tp->deleting; + spin_unlock(&tp->lock); + + return deleting; +} + +#define ASSERT_BLOCK_LOCKED(block) \ + lockdep_assert_held(&(block)->lock) + struct tcf_filter_chain_list_item { struct list_head list; tcf_chain_head_change_t *chain_head_change; @@ -204,10 +500,13 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block, { struct tcf_chain *chain; + ASSERT_BLOCK_LOCKED(block); + chain = kzalloc(sizeof(*chain), GFP_KERNEL); if (!chain) return NULL; - list_add_tail(&chain->list, &block->chain_list); + list_add_tail_rcu(&chain->list, &block->chain_list); + mutex_init(&chain->filter_chain_lock); chain->block = block; chain->index = chain_index; chain->refcnt = 1; @@ -231,29 +530,61 @@ static void tcf_chain0_head_change(struct tcf_chain *chain, if (chain->index) return; + + mutex_lock(&block->lock); list_for_each_entry(item, &block->chain0.filter_chain_list, list) tcf_chain_head_change_item(item, tp_head); + mutex_unlock(&block->lock); } -static void tcf_chain_destroy(struct tcf_chain *chain) +/* Returns true if block can be safely freed. */ + +static bool tcf_chain_detach(struct tcf_chain *chain) { struct tcf_block *block = chain->block; - list_del(&chain->list); + ASSERT_BLOCK_LOCKED(block); + + list_del_rcu(&chain->list); if (!chain->index) block->chain0.chain = NULL; - kfree(chain); - if (list_empty(&block->chain_list) && !refcount_read(&block->refcnt)) - kfree_rcu(block, rcu); + + if (list_empty(&block->chain_list) && + refcount_read(&block->refcnt) == 0) + return true; + + return false; +} + +static void tcf_block_destroy(struct tcf_block *block) +{ + mutex_destroy(&block->lock); + mutex_destroy(&block->proto_destroy_lock); + xa_destroy(&block->ports); + kfree_rcu(block, rcu); +} + +static void tcf_chain_destroy(struct tcf_chain *chain, bool free_block) +{ + struct tcf_block *block = chain->block; + + mutex_destroy(&chain->filter_chain_lock); + kfree_rcu(chain, rcu); + if (free_block) + tcf_block_destroy(block); } static void tcf_chain_hold(struct tcf_chain *chain) { + ASSERT_BLOCK_LOCKED(chain->block); + ++chain->refcnt; } static bool tcf_chain_held_by_acts_only(struct tcf_chain *chain) { + ASSERT_BLOCK_LOCKED(chain->block); + /* In case all the references are action references, this * chain should not be shown to the user. */ @@ -265,6 +596,8 @@ static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block, { struct tcf_chain *chain; + ASSERT_BLOCK_LOCKED(block); + list_for_each_entry(chain, &block->chain_list, list) { if (chain->index == chain_index) return chain; @@ -272,38 +605,62 @@ static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block, return NULL; } +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) +static struct tcf_chain *tcf_chain_lookup_rcu(const struct tcf_block *block, + u32 chain_index) +{ + struct tcf_chain *chain; + + list_for_each_entry_rcu(chain, &block->chain_list, list) { + if (chain->index == chain_index) + return chain; + } + return NULL; +} +#endif + static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, - u32 seq, u16 flags, int event, bool unicast); + u32 seq, u16 flags, int event, bool unicast, + struct netlink_ext_ack *extack); static struct tcf_chain *__tcf_chain_get(struct tcf_block *block, u32 chain_index, bool create, bool by_act) { - struct tcf_chain *chain = tcf_chain_lookup(block, chain_index); + struct tcf_chain *chain = NULL; + bool is_first_reference; + mutex_lock(&block->lock); + chain = tcf_chain_lookup(block, chain_index); if (chain) { tcf_chain_hold(chain); } else { if (!create) - return NULL; + goto errout; chain = tcf_chain_create(block, chain_index); if (!chain) - return NULL; + goto errout; } if (by_act) ++chain->action_refcnt; + is_first_reference = chain->refcnt - chain->action_refcnt == 1; + mutex_unlock(&block->lock); /* Send notification only in case we got the first * non-action reference. Until then, the chain acts only as * a placeholder for actions pointing to it and user ought * not know about them. */ - if (chain->refcnt - chain->action_refcnt == 1 && !by_act) + if (is_first_reference && !by_act) tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, - RTM_NEWCHAIN, false); + RTM_NEWCHAIN, false, NULL); return chain; + +errout: + mutex_unlock(&block->lock); + return chain; } static struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, @@ -318,311 +675,181 @@ struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index) } EXPORT_SYMBOL(tcf_chain_get_by_act); -static void tc_chain_tmplt_del(struct tcf_chain *chain); +static void tc_chain_tmplt_del(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv); +static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv, u32 chain_index, + struct tcf_block *block, struct sk_buff *oskb, + u32 seq, u16 flags); -static void __tcf_chain_put(struct tcf_chain *chain, bool by_act) +static void __tcf_chain_put(struct tcf_chain *chain, bool by_act, + bool explicitly_created) { + struct tcf_block *block = chain->block; + const struct tcf_proto_ops *tmplt_ops; + unsigned int refcnt, non_act_refcnt; + bool free_block = false; + void *tmplt_priv; + + mutex_lock(&block->lock); + if (explicitly_created) { + if (!chain->explicitly_created) { + mutex_unlock(&block->lock); + return; + } + chain->explicitly_created = false; + } + if (by_act) chain->action_refcnt--; - chain->refcnt--; - /* The last dropped non-action reference will trigger notification. */ - if (chain->refcnt - chain->action_refcnt == 0 && !by_act) - tc_chain_notify(chain, NULL, 0, 0, RTM_DELCHAIN, false); + /* tc_chain_notify_delete can't be called while holding block lock. + * However, when block is unlocked chain can be changed concurrently, so + * save these to temporary variables. + */ + refcnt = --chain->refcnt; + non_act_refcnt = refcnt - chain->action_refcnt; + tmplt_ops = chain->tmplt_ops; + tmplt_priv = chain->tmplt_priv; + + if (non_act_refcnt == chain->explicitly_created && !by_act) { + if (non_act_refcnt == 0) + tc_chain_notify_delete(tmplt_ops, tmplt_priv, + chain->index, block, NULL, 0, 0); + /* Last reference to chain, no need to lock. */ + chain->flushing = false; + } - if (chain->refcnt == 0) { - tc_chain_tmplt_del(chain); - tcf_chain_destroy(chain); + if (refcnt == 0) + free_block = tcf_chain_detach(chain); + mutex_unlock(&block->lock); + + if (refcnt == 0) { + tc_chain_tmplt_del(tmplt_ops, tmplt_priv); + tcf_chain_destroy(chain, free_block); } } static void tcf_chain_put(struct tcf_chain *chain) { - __tcf_chain_put(chain, false); + __tcf_chain_put(chain, false, false); } void tcf_chain_put_by_act(struct tcf_chain *chain) { - __tcf_chain_put(chain, true); + __tcf_chain_put(chain, true, false); } EXPORT_SYMBOL(tcf_chain_put_by_act); static void tcf_chain_put_explicitly_created(struct tcf_chain *chain) { - if (chain->explicitly_created) - tcf_chain_put(chain); + __tcf_chain_put(chain, false, true); } -static void tcf_chain_flush(struct tcf_chain *chain) +static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held) { - struct tcf_proto *tp = rtnl_dereference(chain->filter_chain); + struct tcf_proto *tp, *tp_next; - tcf_chain0_head_change(chain, NULL); + mutex_lock(&chain->filter_chain_lock); + tp = tcf_chain_dereference(chain->filter_chain, chain); while (tp) { - RCU_INIT_POINTER(chain->filter_chain, tp->next); - tcf_proto_destroy(tp, NULL); - tp = rtnl_dereference(chain->filter_chain); - tcf_chain_put(chain); + tp_next = rcu_dereference_protected(tp->next, 1); + tcf_proto_signal_destroying(chain, tp); + tp = tp_next; } -} - -static struct tcf_block *tc_dev_ingress_block(struct net_device *dev) -{ - const struct Qdisc_class_ops *cops; - struct Qdisc *qdisc; - - if (!dev_ingress_queue(dev)) - return NULL; - - qdisc = dev_ingress_queue(dev)->qdisc_sleeping; - if (!qdisc) - return NULL; - - cops = qdisc->ops->cl_ops; - if (!cops) - return NULL; - - if (!cops->tcf_block) - return NULL; - - return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL); -} - -static struct rhashtable indr_setup_block_ht; - -struct tc_indr_block_dev { - struct rhash_head ht_node; - struct net_device *dev; - unsigned int refcnt; - struct list_head cb_list; - struct tcf_block *block; -}; - -struct tc_indr_block_cb { - struct list_head list; - void *cb_priv; - tc_indr_block_bind_cb_t *cb; - void *cb_ident; -}; - -static const struct rhashtable_params tc_indr_setup_block_ht_params = { - .key_offset = offsetof(struct tc_indr_block_dev, dev), - .head_offset = offsetof(struct tc_indr_block_dev, ht_node), - .key_len = sizeof(struct net_device *), -}; - -static struct tc_indr_block_dev * -tc_indr_block_dev_lookup(struct net_device *dev) -{ - return rhashtable_lookup_fast(&indr_setup_block_ht, &dev, - tc_indr_setup_block_ht_params); -} - -static struct tc_indr_block_dev *tc_indr_block_dev_get(struct net_device *dev) -{ - struct tc_indr_block_dev *indr_dev; - - indr_dev = tc_indr_block_dev_lookup(dev); - if (indr_dev) - goto inc_ref; - - indr_dev = kzalloc(sizeof(*indr_dev), GFP_KERNEL); - if (!indr_dev) - return NULL; + tp = tcf_chain_dereference(chain->filter_chain, chain); + RCU_INIT_POINTER(chain->filter_chain, NULL); + tcf_chain0_head_change(chain, NULL); + chain->flushing = true; + mutex_unlock(&chain->filter_chain_lock); - INIT_LIST_HEAD(&indr_dev->cb_list); - indr_dev->dev = dev; - indr_dev->block = tc_dev_ingress_block(dev); - if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node, - tc_indr_setup_block_ht_params)) { - kfree(indr_dev); - return NULL; + while (tp) { + tp_next = rcu_dereference_protected(tp->next, 1); + tcf_proto_put(tp, rtnl_held, NULL); + tp = tp_next; } - -inc_ref: - indr_dev->refcnt++; - return indr_dev; } -static void tc_indr_block_dev_put(struct tc_indr_block_dev *indr_dev) -{ - if (--indr_dev->refcnt) - return; - - rhashtable_remove_fast(&indr_setup_block_ht, &indr_dev->ht_node, - tc_indr_setup_block_ht_params); - kfree(indr_dev); -} +static int tcf_block_setup(struct tcf_block *block, + struct flow_block_offload *bo); -static struct tc_indr_block_cb * -tc_indr_block_cb_lookup(struct tc_indr_block_dev *indr_dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) +static void tcf_block_offload_init(struct flow_block_offload *bo, + struct net_device *dev, struct Qdisc *sch, + enum flow_block_command command, + enum flow_block_binder_type binder_type, + struct flow_block *flow_block, + bool shared, struct netlink_ext_ack *extack) { - struct tc_indr_block_cb *indr_block_cb; - - list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) - if (indr_block_cb->cb == cb && - indr_block_cb->cb_ident == cb_ident) - return indr_block_cb; - return NULL; + bo->net = dev_net(dev); + bo->command = command; + bo->binder_type = binder_type; + bo->block = flow_block; + bo->block_shared = shared; + bo->extack = extack; + bo->sch = sch; + bo->cb_list_head = &flow_block->cb_list; + INIT_LIST_HEAD(&bo->cb_list); } -static struct tc_indr_block_cb * -tc_indr_block_cb_add(struct tc_indr_block_dev *indr_dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - - indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident); - if (indr_block_cb) - return ERR_PTR(-EEXIST); +static void tcf_block_unbind(struct tcf_block *block, + struct flow_block_offload *bo); - indr_block_cb = kzalloc(sizeof(*indr_block_cb), GFP_KERNEL); - if (!indr_block_cb) - return ERR_PTR(-ENOMEM); - - indr_block_cb->cb_priv = cb_priv; - indr_block_cb->cb = cb; - indr_block_cb->cb_ident = cb_ident; - list_add(&indr_block_cb->list, &indr_dev->cb_list); - - return indr_block_cb; -} - -static void tc_indr_block_cb_del(struct tc_indr_block_cb *indr_block_cb) +static void tc_block_indr_cleanup(struct flow_block_cb *block_cb) { - list_del(&indr_block_cb->list); - kfree(indr_block_cb); -} - -static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev, - struct tc_indr_block_cb *indr_block_cb, - enum tc_block_command command) -{ - struct tc_block_offload bo = { - .command = command, - .binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS, - .block = indr_dev->block, - }; - - if (!indr_dev->block) - return; - - indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, - &bo); -} - -int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - struct tc_indr_block_dev *indr_dev; - int err; - - indr_dev = tc_indr_block_dev_get(dev); - if (!indr_dev) - return -ENOMEM; - - indr_block_cb = tc_indr_block_cb_add(indr_dev, cb_priv, cb, cb_ident); - err = PTR_ERR_OR_ZERO(indr_block_cb); - if (err) - goto err_dev_put; - - tc_indr_block_ing_cmd(indr_dev, indr_block_cb, TC_BLOCK_BIND); - return 0; - -err_dev_put: - tc_indr_block_dev_put(indr_dev); - return err; -} -EXPORT_SYMBOL_GPL(__tc_indr_block_cb_register); - -int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - int err; - + struct tcf_block *block = block_cb->indr.data; + struct net_device *dev = block_cb->indr.dev; + struct Qdisc *sch = block_cb->indr.sch; + struct netlink_ext_ack extack = {}; + struct flow_block_offload bo = {}; + + tcf_block_offload_init(&bo, dev, sch, FLOW_BLOCK_UNBIND, + block_cb->indr.binder_type, + &block->flow_block, tcf_block_shared(block), + &extack); rtnl_lock(); - err = __tc_indr_block_cb_register(dev, cb_priv, cb, cb_ident); + down_write(&block->cb_lock); + list_del(&block_cb->driver_list); + list_move(&block_cb->list, &bo.cb_list); + tcf_block_unbind(block, &bo); + up_write(&block->cb_lock); rtnl_unlock(); - - return err; -} -EXPORT_SYMBOL_GPL(tc_indr_block_cb_register); - -void __tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - struct tc_indr_block_dev *indr_dev; - - indr_dev = tc_indr_block_dev_lookup(dev); - if (!indr_dev) - return; - - indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident); - if (!indr_block_cb) - return; - - /* Send unbind message if required to free any block cbs. */ - tc_indr_block_ing_cmd(indr_dev, indr_block_cb, TC_BLOCK_UNBIND); - tc_indr_block_cb_del(indr_block_cb); - tc_indr_block_dev_put(indr_dev); } -EXPORT_SYMBOL_GPL(__tc_indr_block_cb_unregister); -void tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) +static bool tcf_block_offload_in_use(struct tcf_block *block) { - rtnl_lock(); - __tc_indr_block_cb_unregister(dev, cb, cb_ident); - rtnl_unlock(); + return atomic_read(&block->offloadcnt); } -EXPORT_SYMBOL_GPL(tc_indr_block_cb_unregister); -static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev, - struct tcf_block_ext_info *ei, - enum tc_block_command command, - struct netlink_ext_ack *extack) +static int tcf_block_offload_cmd(struct tcf_block *block, + struct net_device *dev, struct Qdisc *sch, + struct tcf_block_ext_info *ei, + enum flow_block_command command, + struct netlink_ext_ack *extack) { - struct tc_indr_block_cb *indr_block_cb; - struct tc_indr_block_dev *indr_dev; - struct tc_block_offload bo = { - .command = command, - .binder_type = ei->binder_type, - .block = block, - .extack = extack, - }; + struct flow_block_offload bo = {}; - indr_dev = tc_indr_block_dev_lookup(dev); - if (!indr_dev) - return; + tcf_block_offload_init(&bo, dev, sch, command, ei->binder_type, + &block->flow_block, tcf_block_shared(block), + extack); - indr_dev->block = command == TC_BLOCK_BIND ? block : NULL; + if (dev->netdev_ops->ndo_setup_tc) { + int err; - list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) - indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, - &bo); -} + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); + if (err < 0) { + if (err != -EOPNOTSUPP) + NL_SET_ERR_MSG(extack, "Driver ndo_setup_tc failed"); + return err; + } -static bool tcf_block_offload_in_use(struct tcf_block *block) -{ - return block->offloadcnt; -} + return tcf_block_setup(block, &bo); + } -static int tcf_block_offload_cmd(struct tcf_block *block, - struct net_device *dev, - struct tcf_block_ext_info *ei, - enum tc_block_command command, - struct netlink_ext_ack *extack) -{ - struct tc_block_offload bo = {}; + flow_indr_dev_setup_offload(dev, sch, TC_SETUP_BLOCK, block, &bo, + tc_block_indr_cleanup); + tcf_block_setup(block, &bo); - bo.command = command; - bo.binder_type = ei->binder_type; - bo.block = block; - bo.extack = extack; - return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); + return -EOPNOTSUPP; } static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, @@ -632,32 +859,37 @@ static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, struct net_device *dev = q->dev_queue->dev; int err; - if (!dev->netdev_ops->ndo_setup_tc) - goto no_offload_dev_inc; + down_write(&block->cb_lock); /* If tc offload feature is disabled and the block we try to bind * to already has some offloaded filters, forbid to bind. */ - if (!tc_can_offload(dev) && tcf_block_offload_in_use(block)) { + if (dev->netdev_ops->ndo_setup_tc && + !tc_can_offload(dev) && + tcf_block_offload_in_use(block)) { NL_SET_ERR_MSG(extack, "Bind to offloaded block failed as dev has offload disabled"); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto err_unlock; } - err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND, extack); + err = tcf_block_offload_cmd(block, dev, q, ei, FLOW_BLOCK_BIND, extack); if (err == -EOPNOTSUPP) goto no_offload_dev_inc; if (err) - return err; + goto err_unlock; - tc_indr_block_call(block, dev, ei, TC_BLOCK_BIND, extack); + up_write(&block->cb_lock); return 0; no_offload_dev_inc: if (tcf_block_offload_in_use(block)) - return -EOPNOTSUPP; + goto err_unlock; + + err = 0; block->nooffloaddevcnt++; - tc_indr_block_call(block, dev, ei, TC_BLOCK_BIND, extack); - return 0; +err_unlock: + up_write(&block->cb_lock); + return err; } static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q, @@ -666,17 +898,16 @@ static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q, struct net_device *dev = q->dev_queue->dev; int err; - tc_indr_block_call(block, dev, ei, TC_BLOCK_UNBIND, NULL); - - if (!dev->netdev_ops->ndo_setup_tc) - goto no_offload_dev_dec; - err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND, NULL); + down_write(&block->cb_lock); + err = tcf_block_offload_cmd(block, dev, q, ei, FLOW_BLOCK_UNBIND, NULL); if (err == -EOPNOTSUPP) goto no_offload_dev_dec; + up_write(&block->cb_lock); return; no_offload_dev_dec: WARN_ON(block->nooffloaddevcnt-- == 0); + up_write(&block->cb_lock); } static int @@ -684,8 +915,8 @@ tcf_chain0_head_change_cb_add(struct tcf_block *block, struct tcf_block_ext_info *ei, struct netlink_ext_ack *extack) { - struct tcf_chain *chain0 = block->chain0.chain; struct tcf_filter_chain_list_item *item; + struct tcf_chain *chain0; item = kmalloc(sizeof(*item), GFP_KERNEL); if (!item) { @@ -694,9 +925,32 @@ tcf_chain0_head_change_cb_add(struct tcf_block *block, } item->chain_head_change = ei->chain_head_change; item->chain_head_change_priv = ei->chain_head_change_priv; - if (chain0 && chain0->filter_chain) - tcf_chain_head_change_item(item, chain0->filter_chain); - list_add(&item->list, &block->chain0.filter_chain_list); + + mutex_lock(&block->lock); + chain0 = block->chain0.chain; + if (chain0) + tcf_chain_hold(chain0); + else + list_add(&item->list, &block->chain0.filter_chain_list); + mutex_unlock(&block->lock); + + if (chain0) { + struct tcf_proto *tp_head; + + mutex_lock(&chain0->filter_chain_lock); + + tp_head = tcf_chain_dereference(chain0->filter_chain, chain0); + if (tp_head) + tcf_chain_head_change_item(item, tp_head); + + mutex_lock(&block->lock); + list_add(&item->list, &block->chain0.filter_chain_list); + mutex_unlock(&block->lock); + + mutex_unlock(&chain0->filter_chain_lock); + tcf_chain_put(chain0); + } + return 0; } @@ -704,20 +958,23 @@ static void tcf_chain0_head_change_cb_del(struct tcf_block *block, struct tcf_block_ext_info *ei) { - struct tcf_chain *chain0 = block->chain0.chain; struct tcf_filter_chain_list_item *item; + mutex_lock(&block->lock); list_for_each_entry(item, &block->chain0.filter_chain_list, list) { if ((!ei->chain_head_change && !ei->chain_head_change_priv) || (item->chain_head_change == ei->chain_head_change && item->chain_head_change_priv == ei->chain_head_change_priv)) { - if (chain0) + if (block->chain0.chain) tcf_chain_head_change_item(item, NULL); list_del(&item->list); + mutex_unlock(&block->lock); + kfree(item); return; } } + mutex_unlock(&block->lock); WARN_ON(1); } @@ -764,14 +1021,18 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, NL_SET_ERR_MSG(extack, "Memory allocation for block failed"); return ERR_PTR(-ENOMEM); } + mutex_init(&block->lock); + mutex_init(&block->proto_destroy_lock); + init_rwsem(&block->cb_lock); + flow_block_init(&block->flow_block); INIT_LIST_HEAD(&block->chain_list); - INIT_LIST_HEAD(&block->cb_list); INIT_LIST_HEAD(&block->owner_list); INIT_LIST_HEAD(&block->chain0.filter_chain_list); refcount_set(&block->refcnt, 1); block->net = net; block->index = block_index; + xa_init(&block->ports); /* Don't store q pointer for blocks which are shared */ if (!tcf_block_shared(block)) @@ -779,12 +1040,13 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, return block; } -static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index) +struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index) { struct tcf_net *tn = net_generic(net, tcf_net_id); return idr_find(&tn->idr, block_index); } +EXPORT_SYMBOL(tcf_block_lookup); static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index) { @@ -799,157 +1061,240 @@ static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index) return block; } -static void tcf_block_flush_all_chains(struct tcf_block *block) +static struct tcf_chain * +__tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain) { - struct tcf_chain *chain; + mutex_lock(&block->lock); + if (chain) + chain = list_is_last(&chain->list, &block->chain_list) ? + NULL : list_next_entry(chain, list); + else + chain = list_first_entry_or_null(&block->chain_list, + struct tcf_chain, list); - /* Hold a refcnt for all chains, so that they don't disappear - * while we are iterating. - */ - list_for_each_entry(chain, &block->chain_list, list) + /* skip all action-only chains */ + while (chain && tcf_chain_held_by_acts_only(chain)) + chain = list_is_last(&chain->list, &block->chain_list) ? + NULL : list_next_entry(chain, list); + + if (chain) tcf_chain_hold(chain); + mutex_unlock(&block->lock); - list_for_each_entry(chain, &block->chain_list, list) - tcf_chain_flush(chain); + return chain; } -static void tcf_block_put_all_chains(struct tcf_block *block) +/* Function to be used by all clients that want to iterate over all chains on + * block. It properly obtains block->lock and takes reference to chain before + * returning it. Users of this function must be tolerant to concurrent chain + * insertion/deletion or ensure that no concurrent chain modification is + * possible. Note that all netlink dump callbacks cannot guarantee to provide + * consistent dump because rtnl lock is released each time skb is filled with + * data and sent to user-space. + */ + +struct tcf_chain * +tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain) { - struct tcf_chain *chain, *tmp; + struct tcf_chain *chain_next = __tcf_get_next_chain(block, chain); - /* At this point, all the chains should have refcnt >= 1. */ - list_for_each_entry_safe(chain, tmp, &block->chain_list, list) { - tcf_chain_put_explicitly_created(chain); + if (chain) tcf_chain_put(chain); - } + + return chain_next; } +EXPORT_SYMBOL(tcf_get_next_chain); -static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q, - struct tcf_block_ext_info *ei) +static struct tcf_proto * +__tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp) { - if (refcount_dec_and_test(&block->refcnt)) { - /* Flushing/putting all chains will cause the block to be - * deallocated when last chain is freed. However, if chain_list - * is empty, block has to be manually deallocated. After block - * reference counter reached 0, it is no longer possible to - * increment it or add new chains to block. - */ - bool free_block = list_empty(&block->chain_list); + u32 prio = 0; - if (tcf_block_shared(block)) - tcf_block_remove(block, block->net); - if (!free_block) - tcf_block_flush_all_chains(block); + ASSERT_RTNL(); + mutex_lock(&chain->filter_chain_lock); - if (q) - tcf_block_offload_unbind(block, q, ei); + if (!tp) { + tp = tcf_chain_dereference(chain->filter_chain, chain); + } else if (tcf_proto_is_deleting(tp)) { + /* 'deleting' flag is set and chain->filter_chain_lock was + * unlocked, which means next pointer could be invalid. Restart + * search. + */ + prio = tp->prio + 1; + tp = tcf_chain_dereference(chain->filter_chain, chain); - if (free_block) - kfree_rcu(block, rcu); - else - tcf_block_put_all_chains(block); - } else if (q) { - tcf_block_offload_unbind(block, q, ei); + for (; tp; tp = tcf_chain_dereference(tp->next, chain)) + if (!tp->deleting && tp->prio >= prio) + break; + } else { + tp = tcf_chain_dereference(tp->next, chain); } + + if (tp) + tcf_proto_get(tp); + + mutex_unlock(&chain->filter_chain_lock); + + return tp; } -static void tcf_block_refcnt_put(struct tcf_block *block) +/* Function to be used by all clients that want to iterate over all tp's on + * chain. Users of this function must be tolerant to concurrent tp + * insertion/deletion or ensure that no concurrent chain modification is + * possible. Note that all netlink dump callbacks cannot guarantee to provide + * consistent dump because rtnl lock is released each time skb is filled with + * data and sent to user-space. + */ + +struct tcf_proto * +tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp) { - __tcf_block_put(block, NULL, NULL); + struct tcf_proto *tp_next = __tcf_get_next_proto(chain, tp); + + if (tp) + tcf_proto_put(tp, true, NULL); + + return tp_next; } +EXPORT_SYMBOL(tcf_get_next_proto); -/* Find tcf block. - * Set q, parent, cl when appropriate. +static void tcf_block_flush_all_chains(struct tcf_block *block, bool rtnl_held) +{ + struct tcf_chain *chain; + + /* Last reference to block. At this point chains cannot be added or + * removed concurrently. + */ + for (chain = tcf_get_next_chain(block, NULL); + chain; + chain = tcf_get_next_chain(block, chain)) { + tcf_chain_put_explicitly_created(chain); + tcf_chain_flush(chain, rtnl_held); + } +} + +/* Lookup Qdisc and increments its reference counter. + * Set parent, if necessary. */ -static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, - u32 *parent, unsigned long *cl, - int ifindex, u32 block_index, - struct netlink_ext_ack *extack) +static int __tcf_qdisc_find(struct net *net, struct Qdisc **q, + u32 *parent, int ifindex, bool rtnl_held, + struct netlink_ext_ack *extack) { - struct tcf_block *block; + const struct Qdisc_class_ops *cops; + struct net_device *dev; int err = 0; - if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) { - block = tcf_block_refcnt_get(net, block_index); - if (!block) { - NL_SET_ERR_MSG(extack, "Block of given index was not found"); - return ERR_PTR(-EINVAL); - } - } else { - const struct Qdisc_class_ops *cops; - struct net_device *dev; - - rcu_read_lock(); + if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) + return 0; - /* Find link */ - dev = dev_get_by_index_rcu(net, ifindex); - if (!dev) { - rcu_read_unlock(); - return ERR_PTR(-ENODEV); - } + rcu_read_lock(); - /* Find qdisc */ - if (!*parent) { - *q = dev->qdisc; - *parent = (*q)->handle; - } else { - *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent)); - if (!*q) { - NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); - err = -EINVAL; - goto errout_rcu; - } - } + /* Find link */ + dev = dev_get_by_index_rcu(net, ifindex); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; + } - *q = qdisc_refcount_inc_nz(*q); + /* Find qdisc */ + if (!*parent) { + *q = rcu_dereference(dev->qdisc); + *parent = (*q)->handle; + } else { + *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent)); if (!*q) { NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); err = -EINVAL; goto errout_rcu; } + } - /* Is it classful? */ - cops = (*q)->ops->cl_ops; - if (!cops) { - NL_SET_ERR_MSG(extack, "Qdisc not classful"); - err = -EINVAL; - goto errout_rcu; - } + *q = qdisc_refcount_inc_nz(*q); + if (!*q) { + NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); + err = -EINVAL; + goto errout_rcu; + } - if (!cops->tcf_block) { - NL_SET_ERR_MSG(extack, "Class doesn't support blocks"); - err = -EOPNOTSUPP; - goto errout_rcu; - } + /* Is it classful? */ + cops = (*q)->ops->cl_ops; + if (!cops) { + NL_SET_ERR_MSG(extack, "Qdisc not classful"); + err = -EINVAL; + goto errout_qdisc; + } - /* At this point we know that qdisc is not noop_qdisc, - * which means that qdisc holds a reference to net_device - * and we hold a reference to qdisc, so it is safe to release - * rcu read lock. - */ - rcu_read_unlock(); + if (!cops->tcf_block) { + NL_SET_ERR_MSG(extack, "Class doesn't support blocks"); + err = -EOPNOTSUPP; + goto errout_qdisc; + } - /* Do we search for filter, attached to class? */ - if (TC_H_MIN(*parent)) { - *cl = cops->find(*q, *parent); - if (*cl == 0) { - NL_SET_ERR_MSG(extack, "Specified class doesn't exist"); - err = -ENOENT; - goto errout_qdisc; - } +errout_rcu: + /* At this point we know that qdisc is not noop_qdisc, + * which means that qdisc holds a reference to net_device + * and we hold a reference to qdisc, so it is safe to release + * rcu read lock. + */ + rcu_read_unlock(); + return err; + +errout_qdisc: + rcu_read_unlock(); + + if (rtnl_held) + qdisc_put(*q); + else + qdisc_put_unlocked(*q); + *q = NULL; + + return err; +} + +static int __tcf_qdisc_cl_find(struct Qdisc *q, u32 parent, unsigned long *cl, + int ifindex, struct netlink_ext_ack *extack) +{ + if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) + return 0; + + /* Do we search for filter, attached to class? */ + if (TC_H_MIN(parent)) { + const struct Qdisc_class_ops *cops = q->ops->cl_ops; + + *cl = cops->find(q, parent); + if (*cl == 0) { + NL_SET_ERR_MSG(extack, "Specified class doesn't exist"); + return -ENOENT; } + } + + return 0; +} + +static struct tcf_block *__tcf_block_find(struct net *net, struct Qdisc *q, + unsigned long cl, int ifindex, + u32 block_index, + struct netlink_ext_ack *extack) +{ + struct tcf_block *block; - /* And the last stroke */ - block = cops->tcf_block(*q, *cl, extack); + if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) { + block = tcf_block_refcnt_get(net, block_index); if (!block) { - err = -EINVAL; - goto errout_qdisc; + NL_SET_ERR_MSG(extack, "Block of given index was not found"); + return ERR_PTR(-EINVAL); } + } else { + const struct Qdisc_class_ops *cops = q->ops->cl_ops; + + block = cops->tcf_block(q, cl, extack); + if (!block) + return ERR_PTR(-EINVAL); + if (tcf_block_shared(block)) { NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters"); - err = -EOPNOTSUPP; - goto errout_qdisc; + return ERR_PTR(-EOPNOTSUPP); } /* Always take reference to block in order to support execution @@ -962,40 +1307,107 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, } return block; +} + +static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei, bool rtnl_held) +{ + if (refcount_dec_and_mutex_lock(&block->refcnt, &block->lock)) { + /* Flushing/putting all chains will cause the block to be + * deallocated when last chain is freed. However, if chain_list + * is empty, block has to be manually deallocated. After block + * reference counter reached 0, it is no longer possible to + * increment it or add new chains to block. + */ + bool free_block = list_empty(&block->chain_list); + + mutex_unlock(&block->lock); + if (tcf_block_shared(block)) + tcf_block_remove(block, block->net); + + if (q) + tcf_block_offload_unbind(block, q, ei); + + if (free_block) + tcf_block_destroy(block); + else + tcf_block_flush_all_chains(block, rtnl_held); + } else if (q) { + tcf_block_offload_unbind(block, q, ei); + } +} + +static void tcf_block_refcnt_put(struct tcf_block *block, bool rtnl_held) +{ + __tcf_block_put(block, NULL, NULL, rtnl_held); +} + +/* Find tcf block. + * Set q, parent, cl when appropriate. + */ + +static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, + u32 *parent, unsigned long *cl, + int ifindex, u32 block_index, + struct netlink_ext_ack *extack) +{ + struct tcf_block *block; + int err = 0; + + ASSERT_RTNL(); + + err = __tcf_qdisc_find(net, q, parent, ifindex, true, extack); + if (err) + goto errout; + + err = __tcf_qdisc_cl_find(*q, *parent, cl, ifindex, extack); + if (err) + goto errout_qdisc; + + block = __tcf_block_find(net, *q, *cl, ifindex, block_index, extack); + if (IS_ERR(block)) { + err = PTR_ERR(block); + goto errout_qdisc; + } + + return block; -errout_rcu: - rcu_read_unlock(); errout_qdisc: - if (*q) { + if (*q) qdisc_put(*q); - *q = NULL; - } +errout: + *q = NULL; return ERR_PTR(err); } -static void tcf_block_release(struct Qdisc *q, struct tcf_block *block) +static void tcf_block_release(struct Qdisc *q, struct tcf_block *block, + bool rtnl_held) { if (!IS_ERR_OR_NULL(block)) - tcf_block_refcnt_put(block); + tcf_block_refcnt_put(block, rtnl_held); - if (q) - qdisc_put(q); + if (q) { + if (rtnl_held) + qdisc_put(q); + else + qdisc_put_unlocked(q); + } } struct tcf_block_owner_item { struct list_head list; struct Qdisc *q; - enum tcf_block_binder_type binder_type; + enum flow_block_binder_type binder_type; }; static void tcf_block_owner_netif_keep_dst(struct tcf_block *block, struct Qdisc *q, - enum tcf_block_binder_type binder_type) + enum flow_block_binder_type binder_type) { if (block->keep_dst && - binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS && - binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS) + binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS && + binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) netif_keep_dst(qdisc_dev(q)); } @@ -1012,7 +1424,7 @@ EXPORT_SYMBOL(tcf_block_netif_keep_dst); static int tcf_block_owner_add(struct tcf_block *block, struct Qdisc *q, - enum tcf_block_binder_type binder_type) + enum flow_block_binder_type binder_type) { struct tcf_block_owner_item *item; @@ -1027,7 +1439,7 @@ static int tcf_block_owner_add(struct tcf_block *block, static void tcf_block_owner_del(struct tcf_block *block, struct Qdisc *q, - enum tcf_block_binder_type binder_type) + enum flow_block_binder_type binder_type) { struct tcf_block_owner_item *item; @@ -1041,10 +1453,19 @@ static void tcf_block_owner_del(struct tcf_block *block, WARN_ON(1); } +static bool tcf_block_tracks_dev(struct tcf_block *block, + struct tcf_block_ext_info *ei) +{ + return tcf_block_shared(block) && + (ei->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS || + ei->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS); +} + int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, struct tcf_block_ext_info *ei, struct netlink_ext_ack *extack) { + struct net_device *dev = qdisc_dev(q); struct net *net = qdisc_net(q); struct tcf_block *block = NULL; int err; @@ -1078,16 +1499,26 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, if (err) goto err_block_offload_bind; + if (tcf_block_tracks_dev(block, ei)) { + err = xa_insert(&block->ports, dev->ifindex, dev, GFP_KERNEL); + if (err) { + NL_SET_ERR_MSG(extack, "block dev insert failed"); + goto err_dev_insert; + } + } + *p_block = block; return 0; +err_dev_insert: + tcf_block_offload_unbind(block, q, ei); err_block_offload_bind: tcf_chain0_head_change_cb_del(block, ei); err_chain0_head_change_cb_add: tcf_block_owner_del(block, q, ei->binder_type); err_block_owner_add: err_block_insert: - tcf_block_refcnt_put(block); + tcf_block_refcnt_put(block, true); return err; } EXPORT_SYMBOL(tcf_block_get_ext); @@ -1119,12 +1550,16 @@ EXPORT_SYMBOL(tcf_block_get); void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, struct tcf_block_ext_info *ei) { + struct net_device *dev = qdisc_dev(q); + if (!block) return; + if (tcf_block_tracks_dev(block, ei)) + xa_erase(&block->ports, dev->ifindex); tcf_chain0_head_change_cb_del(block, ei); tcf_block_owner_del(block, q, ei->binder_type); - __tcf_block_put(block, q, ei); + __tcf_block_put(block, q, ei, true); } EXPORT_SYMBOL(tcf_block_put_ext); @@ -1139,55 +1574,29 @@ void tcf_block_put(struct tcf_block *block) EXPORT_SYMBOL(tcf_block_put); -struct tcf_block_cb { - struct list_head list; - tc_setup_cb_t *cb; - void *cb_ident; - void *cb_priv; - unsigned int refcnt; -}; - -void *tcf_block_cb_priv(struct tcf_block_cb *block_cb) -{ - return block_cb->cb_priv; -} -EXPORT_SYMBOL(tcf_block_cb_priv); - -struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident) -{ struct tcf_block_cb *block_cb; - - list_for_each_entry(block_cb, &block->cb_list, list) - if (block_cb->cb == cb && block_cb->cb_ident == cb_ident) - return block_cb; - return NULL; -} -EXPORT_SYMBOL(tcf_block_cb_lookup); - -void tcf_block_cb_incref(struct tcf_block_cb *block_cb) -{ - block_cb->refcnt++; -} -EXPORT_SYMBOL(tcf_block_cb_incref); - -unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb) -{ - return --block_cb->refcnt; -} -EXPORT_SYMBOL(tcf_block_cb_decref); - static int -tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb, +tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb, void *cb_priv, bool add, bool offload_in_use, struct netlink_ext_ack *extack) { - struct tcf_chain *chain; - struct tcf_proto *tp; + struct tcf_chain *chain, *chain_prev; + struct tcf_proto *tp, *tp_prev; int err; - list_for_each_entry(chain, &block->chain_list, list) { - for (tp = rtnl_dereference(chain->filter_chain); tp; - tp = rtnl_dereference(tp->next)) { + lockdep_assert_held(&block->cb_lock); + + for (chain = __tcf_get_next_chain(block, NULL); + chain; + chain_prev = chain, + chain = __tcf_get_next_chain(block, chain), + tcf_chain_put(chain_prev)) { + if (chain->tmplt_ops && add) + chain->tmplt_ops->tmplt_reoffload(chain, true, cb, + cb_priv); + for (tp = __tcf_get_next_proto(chain, NULL); tp; + tp_prev = tp, + tp = __tcf_get_next_proto(chain, tp), + tcf_proto_put(tp_prev, true, NULL)) { if (tp->ops->reoffload) { err = tp->ops->reoffload(tp, add, cb, cb_priv, extack); @@ -1199,107 +1608,169 @@ tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb, goto err_playback_remove; } } + if (chain->tmplt_ops && !add) + chain->tmplt_ops->tmplt_reoffload(chain, false, cb, + cb_priv); } return 0; err_playback_remove: + tcf_proto_put(tp, true, NULL); + tcf_chain_put(chain); tcf_block_playback_offloads(block, cb, cb_priv, false, offload_in_use, extack); return err; } -struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv, - struct netlink_ext_ack *extack) +static int tcf_block_bind(struct tcf_block *block, + struct flow_block_offload *bo) { - struct tcf_block_cb *block_cb; - int err; + struct flow_block_cb *block_cb, *next; + int err, i = 0; - /* Replay any already present rules */ - err = tcf_block_playback_offloads(block, cb, cb_priv, true, - tcf_block_offload_in_use(block), - extack); - if (err) - return ERR_PTR(err); + lockdep_assert_held(&block->cb_lock); - block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL); - if (!block_cb) - return ERR_PTR(-ENOMEM); - block_cb->cb = cb; - block_cb->cb_ident = cb_ident; - block_cb->cb_priv = cb_priv; - list_add(&block_cb->list, &block->cb_list); - return block_cb; -} -EXPORT_SYMBOL(__tcf_block_cb_register); + list_for_each_entry(block_cb, &bo->cb_list, list) { + err = tcf_block_playback_offloads(block, block_cb->cb, + block_cb->cb_priv, true, + tcf_block_offload_in_use(block), + bo->extack); + if (err) + goto err_unroll; + if (!bo->unlocked_driver_cb) + block->lockeddevcnt++; -int tcf_block_cb_register(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident, - void *cb_priv, struct netlink_ext_ack *extack) -{ - struct tcf_block_cb *block_cb; + i++; + } + list_splice(&bo->cb_list, &block->flow_block.cb_list); + + return 0; - block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv, - extack); - return PTR_ERR_OR_ZERO(block_cb); +err_unroll: + list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { + list_del(&block_cb->driver_list); + if (i-- > 0) { + list_del(&block_cb->list); + tcf_block_playback_offloads(block, block_cb->cb, + block_cb->cb_priv, false, + tcf_block_offload_in_use(block), + NULL); + if (!bo->unlocked_driver_cb) + block->lockeddevcnt--; + } + flow_block_cb_free(block_cb); + } + + return err; } -EXPORT_SYMBOL(tcf_block_cb_register); -void __tcf_block_cb_unregister(struct tcf_block *block, - struct tcf_block_cb *block_cb) +static void tcf_block_unbind(struct tcf_block *block, + struct flow_block_offload *bo) { - tcf_block_playback_offloads(block, block_cb->cb, block_cb->cb_priv, - false, tcf_block_offload_in_use(block), - NULL); - list_del(&block_cb->list); - kfree(block_cb); + struct flow_block_cb *block_cb, *next; + + lockdep_assert_held(&block->cb_lock); + + list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { + tcf_block_playback_offloads(block, block_cb->cb, + block_cb->cb_priv, false, + tcf_block_offload_in_use(block), + NULL); + list_del(&block_cb->list); + flow_block_cb_free(block_cb); + if (!bo->unlocked_driver_cb) + block->lockeddevcnt--; + } } -EXPORT_SYMBOL(__tcf_block_cb_unregister); -void tcf_block_cb_unregister(struct tcf_block *block, - tc_setup_cb_t *cb, void *cb_ident) +static int tcf_block_setup(struct tcf_block *block, + struct flow_block_offload *bo) { - struct tcf_block_cb *block_cb; + int err; - block_cb = tcf_block_cb_lookup(block, cb, cb_ident); - if (!block_cb) - return; - __tcf_block_cb_unregister(block, block_cb); + switch (bo->command) { + case FLOW_BLOCK_BIND: + err = tcf_block_bind(block, bo); + break; + case FLOW_BLOCK_UNBIND: + err = 0; + tcf_block_unbind(block, bo); + break; + default: + WARN_ON_ONCE(1); + err = -EOPNOTSUPP; + } + + return err; } -EXPORT_SYMBOL(tcf_block_cb_unregister); /* Main classifier routine: scans classifier chain attached * to this qdisc, (optionally) tests for protocol and asks * specific classifiers. */ -int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res, bool compat_mode) +static inline int __tcf_classify(struct sk_buff *skb, + const struct tcf_proto *tp, + const struct tcf_proto *orig_tp, + struct tcf_result *res, + bool compat_mode, + struct tcf_exts_miss_cookie_node *n, + int act_index, + u32 *last_executed_chain) { #ifdef CONFIG_NET_CLS_ACT - const int max_reclassify_loop = 4; - const struct tcf_proto *orig_tp = tp; + const int max_reclassify_loop = 16; const struct tcf_proto *first_tp; int limit = 0; reclassify: #endif for (; tp; tp = rcu_dereference_bh(tp->next)) { - __be16 protocol = tc_skb_protocol(skb); - int err; + __be16 protocol = skb_protocol(skb, false); + int err = 0; + + if (n) { + struct tcf_exts *exts; + + if (n->tp_prio != tp->prio) + continue; + + /* We re-lookup the tp and chain based on index instead + * of having hard refs and locks to them, so do a sanity + * check if any of tp,chain,exts was replaced by the + * time we got here with a cookie from hardware. + */ + if (unlikely(n->tp != tp || n->tp->chain != n->chain || + !tp->ops->get_exts)) { + tcf_set_drop_reason(skb, + SKB_DROP_REASON_TC_COOKIE_ERROR); + return TC_ACT_SHOT; + } - if (tp->protocol != protocol && - tp->protocol != htons(ETH_P_ALL)) - continue; + exts = tp->ops->get_exts(tp, n->handle); + if (unlikely(!exts || n->exts != exts)) { + tcf_set_drop_reason(skb, + SKB_DROP_REASON_TC_COOKIE_ERROR); + return TC_ACT_SHOT; + } - err = tp->classify(skb, tp, res); + n = NULL; + err = tcf_exts_exec_ex(skb, exts, act_index, res); + } else { + if (tp->protocol != protocol && + tp->protocol != htons(ETH_P_ALL)) + continue; + + err = tc_classify(skb, tp, res); + } #ifdef CONFIG_NET_CLS_ACT if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) { first_tp = orig_tp; + *last_executed_chain = first_tp->chain->index; goto reset; } else if (unlikely(TC_ACT_EXT_CMP(err, TC_ACT_GOTO_CHAIN))) { first_tp = res->goto_tp; + *last_executed_chain = err & TC_ACT_EXT_VAL_MASK; goto reset; } #endif @@ -1307,6 +1778,12 @@ reclassify: return err; } + if (unlikely(n)) { + tcf_set_drop_reason(skb, + SKB_DROP_REASON_TC_COOKIE_ERROR); + return TC_ACT_SHOT; + } + return TC_ACT_UNSPEC; /* signal: continue lookup */ #ifdef CONFIG_NET_CLS_ACT reset: @@ -1315,6 +1792,8 @@ reset: tp->chain->block->index, tp->prio & 0xffff, ntohs(tp->protocol)); + tcf_set_drop_reason(skb, + SKB_DROP_REASON_TC_RECLASSIFY_LOOP); return TC_ACT_SHOT; } @@ -1322,6 +1801,87 @@ reset: goto reclassify; #endif } + +int tcf_classify(struct sk_buff *skb, + const struct tcf_block *block, + const struct tcf_proto *tp, + struct tcf_result *res, bool compat_mode) +{ +#if !IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + u32 last_executed_chain = 0; + + return __tcf_classify(skb, tp, tp, res, compat_mode, NULL, 0, + &last_executed_chain); +#else + u32 last_executed_chain = tp ? tp->chain->index : 0; + struct tcf_exts_miss_cookie_node *n = NULL; + const struct tcf_proto *orig_tp = tp; + struct tc_skb_ext *ext; + int act_index = 0; + int ret; + + if (block) { + ext = skb_ext_find(skb, TC_SKB_EXT); + + if (ext && (ext->chain || ext->act_miss)) { + struct tcf_chain *fchain; + u32 chain; + + if (ext->act_miss) { + n = tcf_exts_miss_cookie_lookup(ext->act_miss_cookie, + &act_index); + if (!n) { + tcf_set_drop_reason(skb, + SKB_DROP_REASON_TC_COOKIE_ERROR); + return TC_ACT_SHOT; + } + + chain = n->chain_index; + } else { + chain = ext->chain; + } + + fchain = tcf_chain_lookup_rcu(block, chain); + if (!fchain) { + tcf_set_drop_reason(skb, + SKB_DROP_REASON_TC_CHAIN_NOTFOUND); + + return TC_ACT_SHOT; + } + + /* Consume, so cloned/redirect skbs won't inherit ext */ + skb_ext_del(skb, TC_SKB_EXT); + + tp = rcu_dereference_bh(fchain->filter_chain); + last_executed_chain = fchain->index; + } + } + + ret = __tcf_classify(skb, tp, orig_tp, res, compat_mode, n, act_index, + &last_executed_chain); + + if (tc_skb_ext_tc_enabled()) { + /* 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 (!ext) { + tcf_set_drop_reason(skb, SKB_DROP_REASON_NOMEM); + return TC_ACT_SHOT; + } + ext->chain = last_executed_chain; + ext->mru = cb->mru; + ext->post_ct = qdisc_skb_cb(skb)->post_ct; + ext->post_ct_snat = qdisc_skb_cb(skb)->post_ct_snat; + ext->post_ct_dnat = qdisc_skb_cb(skb)->post_ct_dnat; + ext->zone = cb->zone; + } + } + + return ret; +#endif +} EXPORT_SYMBOL(tcf_classify); struct tcf_chain_info { @@ -1329,50 +1889,148 @@ struct tcf_chain_info { struct tcf_proto __rcu *next; }; -static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain_info *chain_info) +static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain *chain, + struct tcf_chain_info *chain_info) { - return rtnl_dereference(*chain_info->pprev); + return tcf_chain_dereference(*chain_info->pprev, chain); } -static void tcf_chain_tp_insert(struct tcf_chain *chain, - struct tcf_chain_info *chain_info, - struct tcf_proto *tp) +static int tcf_chain_tp_insert(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + struct tcf_proto *tp) { + if (chain->flushing) + return -EAGAIN; + + RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info)); if (*chain_info->pprev == chain->filter_chain) tcf_chain0_head_change(chain, tp); - RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info)); + tcf_proto_get(tp); rcu_assign_pointer(*chain_info->pprev, tp); - tcf_chain_hold(chain); + + return 0; } static void tcf_chain_tp_remove(struct tcf_chain *chain, struct tcf_chain_info *chain_info, struct tcf_proto *tp) { - struct tcf_proto *next = rtnl_dereference(chain_info->next); + struct tcf_proto *next = tcf_chain_dereference(chain_info->next, chain); + tcf_proto_mark_delete(tp); if (tp == chain->filter_chain) tcf_chain0_head_change(chain, next); RCU_INIT_POINTER(*chain_info->pprev, next); - tcf_chain_put(chain); } static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, struct tcf_chain_info *chain_info, u32 protocol, u32 prio, - bool prio_allocate) + bool prio_allocate, + struct netlink_ext_ack *extack); + +/* Try to insert new proto. + * If proto with specified priority already exists, free new proto + * and return existing one. + */ + +static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain, + struct tcf_proto *tp_new, + u32 protocol, u32 prio, + bool rtnl_held) +{ + struct tcf_chain_info chain_info; + struct tcf_proto *tp; + int err = 0; + + mutex_lock(&chain->filter_chain_lock); + + if (tcf_proto_exists_destroying(chain, tp_new)) { + mutex_unlock(&chain->filter_chain_lock); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); + return ERR_PTR(-EAGAIN); + } + + tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, false, NULL); + if (!tp) + err = tcf_chain_tp_insert(chain, &chain_info, tp_new); + mutex_unlock(&chain->filter_chain_lock); + + if (tp) { + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); + tp_new = tp; + } else if (err) { + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); + tp_new = ERR_PTR(err); + } + + return tp_new; +} + +static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, + struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + struct tcf_chain_info chain_info; + struct tcf_proto *tp_iter; + struct tcf_proto **pprev; + struct tcf_proto *next; + + mutex_lock(&chain->filter_chain_lock); + + /* Atomically find and remove tp from chain. */ + for (pprev = &chain->filter_chain; + (tp_iter = tcf_chain_dereference(*pprev, chain)); + pprev = &tp_iter->next) { + if (tp_iter == tp) { + chain_info.pprev = pprev; + chain_info.next = tp_iter->next; + WARN_ON(tp_iter->deleting); + break; + } + } + /* Verify that tp still exists and no new filters were inserted + * concurrently. + * Mark tp for deletion if it is empty. + */ + if (!tp_iter || !tcf_proto_check_delete(tp)) { + mutex_unlock(&chain->filter_chain_lock); + return; + } + + tcf_proto_signal_destroying(chain, tp); + next = tcf_chain_dereference(chain_info.next, chain); + if (tp == chain->filter_chain) + tcf_chain0_head_change(chain, next); + RCU_INIT_POINTER(*chain_info.pprev, next); + mutex_unlock(&chain->filter_chain_lock); + + tcf_proto_put(tp, rtnl_held, extack); +} + +static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + u32 protocol, u32 prio, + bool prio_allocate, + struct netlink_ext_ack *extack) { struct tcf_proto **pprev; struct tcf_proto *tp; /* Check the chain for existence of proto-tcf with this priority */ for (pprev = &chain->filter_chain; - (tp = rtnl_dereference(*pprev)); pprev = &tp->next) { + (tp = tcf_chain_dereference(*pprev, chain)); + pprev = &tp->next) { if (tp->prio >= prio) { if (tp->prio == prio) { - if (prio_allocate || - (tp->protocol != protocol && protocol)) + if (prio_allocate) { + NL_SET_ERR_MSG(extack, "Lowest ID from auto-alloc range already in use"); + return ERR_PTR(-ENOSPC); + } + if (tp->protocol != protocol && protocol) { + NL_SET_ERR_MSG(extack, "Protocol mismatch for filter with specified priority"); return ERR_PTR(-EINVAL); + } } else { tp = NULL; } @@ -1380,18 +2038,26 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, } } chain_info->pprev = pprev; - chain_info->next = tp ? tp->next : NULL; + if (tp) { + chain_info->next = tp->next; + tcf_proto_get(tp); + } else { + chain_info->next = NULL; + } return tp; } static int tcf_fill_node(struct net *net, struct sk_buff *skb, struct tcf_proto *tp, struct tcf_block *block, struct Qdisc *q, u32 parent, void *fh, - u32 portid, u32 seq, u16 flags, int event) + u32 portid, u32 seq, u16 flags, int event, + bool terse_dump, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tcmsg *tcm; struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); + int ret = -EMSGSIZE; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) @@ -1414,92 +2080,152 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; if (!fh) { tcm->tcm_handle = 0; + } else if (terse_dump) { + if (tp->ops->terse_dump) { + if (tp->ops->terse_dump(net, tp, fh, skb, tcm, + rtnl_held) < 0) + goto nla_put_failure; + } else { + goto cls_op_not_supp; + } } else { - if (tp->ops->dump && tp->ops->dump(net, tp, fh, skb, tcm) < 0) + if (tp->ops->dump && + tp->ops->dump(net, tp, fh, skb, tcm, rtnl_held) < 0) goto nla_put_failure; } + + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto nla_put_failure; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; +cls_op_not_supp: + ret = -EOPNOTSUPP; out_nlmsg_trim: nla_put_failure: nlmsg_trim(skb, b); - return -1; + return ret; +} + +static struct sk_buff *tfilter_notify_prep(struct net *net, + struct sk_buff *oskb, + struct nlmsghdr *n, + struct tcf_proto *tp, + struct tcf_block *block, + struct Qdisc *q, u32 parent, + void *fh, int event, + u32 portid, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + unsigned int size = oskb ? max(NLMSG_GOODSIZE, oskb->len) : NLMSG_GOODSIZE; + struct sk_buff *skb; + int ret; + +retry: + skb = alloc_skb(size, GFP_KERNEL); + if (!skb) + return ERR_PTR(-ENOBUFS); + + ret = tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, + n->nlmsg_seq, n->nlmsg_flags, event, false, + rtnl_held, extack); + if (ret <= 0) { + kfree_skb(skb); + if (ret == -EMSGSIZE) { + size += NLMSG_GOODSIZE; + goto retry; + } + return ERR_PTR(-EINVAL); + } + return skb; } static int tfilter_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, struct tcf_block *block, struct Qdisc *q, - u32 parent, void *fh, int event, bool unicast) + u32 parent, void *fh, int event, bool unicast, + bool rtnl_held, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + int err = 0; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) - return -ENOBUFS; + if (!unicast && !rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) + return 0; - if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, - n->nlmsg_seq, n->nlmsg_flags, event) <= 0) { - kfree_skb(skb); - return -EINVAL; - } + skb = tfilter_notify_prep(net, oskb, n, tp, block, q, parent, fh, event, + portid, rtnl_held, extack); + if (IS_ERR(skb)) + return PTR_ERR(skb); if (unicast) - return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT); - - return rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); + err = rtnl_unicast(skb, net, portid); + else + err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); + return err; } static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, struct tcf_block *block, struct Qdisc *q, - u32 parent, void *fh, bool unicast, bool *last, + u32 parent, void *fh, bool *last, bool rtnl_held, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; int err; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) - return -ENOBUFS; + if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) + return tp->ops->delete(tp, fh, last, rtnl_held, extack); - if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, - n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER) <= 0) { + skb = tfilter_notify_prep(net, oskb, n, tp, block, q, parent, fh, + RTM_DELTFILTER, portid, rtnl_held, extack); + if (IS_ERR(skb)) { NL_SET_ERR_MSG(extack, "Failed to build del event notification"); - kfree_skb(skb); - return -EINVAL; + return PTR_ERR(skb); } - err = tp->ops->delete(tp, fh, last, extack); + err = tp->ops->delete(tp, fh, last, rtnl_held, extack); if (err) { kfree_skb(skb); return err; } - if (unicast) - return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT); - err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send filter delete notification"); + return err; } static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, struct tcf_block *block, struct Qdisc *q, u32 parent, struct nlmsghdr *n, - struct tcf_chain *chain, int event) + struct tcf_chain *chain, int event, + struct netlink_ext_ack *extack) { struct tcf_proto *tp; - for (tp = rtnl_dereference(chain->filter_chain); - tp; tp = rtnl_dereference(tp->next)) - tfilter_notify(net, oskb, n, tp, block, - q, parent, NULL, event, false); + for (tp = tcf_get_next_proto(chain, NULL); + tp; tp = tcf_get_next_proto(chain, tp)) + tfilter_notify(net, oskb, n, tp, block, q, parent, NULL, + event, false, true, extack); +} + +static void tfilter_put(struct tcf_proto *tp, void *fh) +{ + if (tp->ops->put && fh) + tp->ops->put(tp, fh); +} + +static bool is_qdisc_ingress(__u32 classid) +{ + return (TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS)); } static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, @@ -1507,29 +2233,30 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; bool prio_allocate; u32 parent; u32 chain_index; - struct Qdisc *q = NULL; + struct Qdisc *q; struct tcf_chain_info chain_info; - struct tcf_chain *chain = NULL; + struct tcf_chain *chain; struct tcf_block *block; struct tcf_proto *tp; unsigned long cl; void *fh; int err; int tp_created; - - if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) - return -EPERM; + bool rtnl_held = false; + u32 flags; replay: tp_created = 0; - err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack); + err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX, + rtm_tca_policy, extack); if (err < 0) return err; @@ -1538,7 +2265,12 @@ replay: prio = TC_H_MAJ(t->tcm_info); prio_allocate = false; parent = t->tcm_parent; + tp = NULL; cl = 0; + block = NULL; + q = NULL; + chain = NULL; + flags = 0; if (prio == 0) { /* If no priority is provided by the user, @@ -1555,14 +2287,40 @@ replay: /* Find head of filter chain. */ - block = tcf_block_find(net, &q, &parent, &cl, - t->tcm_ifindex, t->tcm_block_index, extack); + err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack); + if (err) + return err; + + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } + + /* Take rtnl mutex if rtnl_held was set to true on previous iteration, + * block is shared (no qdisc found), qdisc is not unlocked, classifier + * type is not specified, classifier is not unlocked. + */ + if (rtnl_held || + (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || + !tcf_proto_is_unlocked(name)) { + rtnl_held = true; + rtnl_lock(); + } + + err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack); + if (err) + goto errout; + + block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index, + extack); if (IS_ERR(block)) { err = PTR_ERR(block); goto errout; } + block->classid = parent; - chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; + chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0); if (chain_index > TC_ACT_EXT_VAL_MASK) { NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); err = -EINVAL; @@ -1575,40 +2333,60 @@ replay: goto errout; } + mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_tp_find(chain, &chain_info, protocol, - prio, prio_allocate); + prio, prio_allocate, extack); if (IS_ERR(tp)) { - NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); err = PTR_ERR(tp); - goto errout; + goto errout_locked; } if (tp == NULL) { + struct tcf_proto *tp_new = NULL; + + if (chain->flushing) { + err = -EAGAIN; + goto errout_locked; + } + /* Proto-tcf does not exist, create new one */ if (tca[TCA_KIND] == NULL || !protocol) { NL_SET_ERR_MSG(extack, "Filter kind and protocol must be specified"); err = -EINVAL; - goto errout; + goto errout_locked; } if (!(n->nlmsg_flags & NLM_F_CREATE)) { NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter"); err = -ENOENT; - goto errout; + goto errout_locked; } if (prio_allocate) - prio = tcf_auto_prio(tcf_chain_tp_prev(&chain_info)); + prio = tcf_auto_prio(tcf_chain_tp_prev(chain, + &chain_info)); + + mutex_unlock(&chain->filter_chain_lock); + tp_new = tcf_proto_create(name, protocol, prio, chain, + rtnl_held, extack); + if (IS_ERR(tp_new)) { + err = PTR_ERR(tp_new); + goto errout_tp; + } - tp = tcf_proto_create(nla_data(tca[TCA_KIND]), - protocol, prio, chain, extack); + tp_created = 1; + tp = tcf_chain_tp_insert_unique(chain, tp_new, protocol, prio, + rtnl_held); if (IS_ERR(tp)) { err = PTR_ERR(tp); - goto errout; + goto errout_tp; } - tp_created = 1; - } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { + } else { + mutex_unlock(&chain->filter_chain_lock); + } + + if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one"); err = -EINVAL; goto errout; @@ -1623,38 +2401,65 @@ replay: goto errout; } } else if (n->nlmsg_flags & NLM_F_EXCL) { + tfilter_put(tp, fh); NL_SET_ERR_MSG(extack, "Filter already exists"); err = -EEXIST; goto errout; } if (chain->tmplt_ops && chain->tmplt_ops != tp->ops) { + tfilter_put(tp, fh); NL_SET_ERR_MSG(extack, "Chain template is set to a different filter kind"); err = -EINVAL; goto errout; } + if (!(n->nlmsg_flags & NLM_F_CREATE)) + flags |= TCA_ACT_FLAGS_REPLACE; + if (!rtnl_held) + flags |= TCA_ACT_FLAGS_NO_RTNL; + if (is_qdisc_ingress(parent)) + flags |= TCA_ACT_FLAGS_AT_INGRESS; err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, - n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE, - extack); + flags, extack); if (err == 0) { - if (tp_created) - tcf_chain_tp_insert(chain, &chain_info, tp); tfilter_notify(net, skb, n, tp, block, q, parent, fh, - RTM_NEWTFILTER, false); - } else { - if (tp_created) - tcf_proto_destroy(tp, NULL); + RTM_NEWTFILTER, false, rtnl_held, extack); + tfilter_put(tp, fh); + tcf_proto_count_usesw(tp, true); + /* q pointer is NULL for shared blocks */ + if (q) + q->flags &= ~TCQ_F_CAN_BYPASS; } errout: - if (chain) - tcf_chain_put(chain); - tcf_block_release(q, block); - if (err == -EAGAIN) + if (err && tp_created) + tcf_chain_tp_delete_empty(chain, tp, rtnl_held, NULL); +errout_tp: + if (chain) { + if (tp && !IS_ERR(tp)) + tcf_proto_put(tp, rtnl_held, NULL); + if (!tp_created) + tcf_chain_put(chain); + } + tcf_block_release(q, block, rtnl_held); + + if (rtnl_held) + rtnl_unlock(); + + if (err == -EAGAIN) { + /* Take rtnl lock in case EAGAIN is caused by concurrent flush + * of target chain. + */ + rtnl_held = true; /* Replay the request. */ goto replay; + } return err; + +errout_locked: + mutex_unlock(&chain->filter_chain_lock); + goto errout; } static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, @@ -1662,6 +2467,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; @@ -1670,16 +2476,15 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct Qdisc *q = NULL; struct tcf_chain_info chain_info; struct tcf_chain *chain = NULL; - struct tcf_block *block; + struct tcf_block *block = NULL; struct tcf_proto *tp = NULL; unsigned long cl = 0; void *fh = NULL; int err; + bool rtnl_held = false; - if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) - return -EPERM; - - err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack); + err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX, + rtm_tca_policy, extack); if (err < 0) return err; @@ -1695,14 +2500,38 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, /* Find head of filter chain. */ - block = tcf_block_find(net, &q, &parent, &cl, - t->tcm_ifindex, t->tcm_block_index, extack); + err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack); + if (err) + return err; + + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } + /* Take rtnl mutex if flushing whole chain, block is shared (no qdisc + * found), qdisc is not unlocked, classifier type is not specified, + * classifier is not unlocked. + */ + if (!prio || + (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || + !tcf_proto_is_unlocked(name)) { + rtnl_held = true; + rtnl_lock(); + } + + err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack); + if (err) + goto errout; + + block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index, + extack); if (IS_ERR(block)) { err = PTR_ERR(block); goto errout; } - chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; + chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0); if (chain_index > TC_ACT_EXT_VAL_MASK) { NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); err = -EINVAL; @@ -1724,56 +2553,72 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, if (prio == 0) { tfilter_notify_chain(net, skb, block, q, parent, n, - chain, RTM_DELTFILTER); - tcf_chain_flush(chain); + chain, RTM_DELTFILTER, extack); + tcf_chain_flush(chain, rtnl_held); err = 0; goto errout; } + mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_tp_find(chain, &chain_info, protocol, - prio, false); - if (!tp || IS_ERR(tp)) { + prio, false, extack); + if (!tp) { + err = -ENOENT; NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); - err = tp ? PTR_ERR(tp) : -ENOENT; - goto errout; + goto errout_locked; + } else if (IS_ERR(tp)) { + err = PTR_ERR(tp); + goto errout_locked; } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one"); err = -EINVAL; + goto errout_locked; + } else if (t->tcm_handle == 0) { + tcf_proto_signal_destroying(chain, tp); + tcf_chain_tp_remove(chain, &chain_info, tp); + mutex_unlock(&chain->filter_chain_lock); + + tcf_proto_put(tp, rtnl_held, NULL); + tfilter_notify(net, skb, n, tp, block, q, parent, fh, + RTM_DELTFILTER, false, rtnl_held, extack); + err = 0; goto errout; } + mutex_unlock(&chain->filter_chain_lock); fh = tp->ops->get(tp, t->tcm_handle); if (!fh) { - if (t->tcm_handle == 0) { - tcf_chain_tp_remove(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, block, q, parent, fh, - RTM_DELTFILTER, false); - tcf_proto_destroy(tp, extack); - err = 0; - } else { - NL_SET_ERR_MSG(extack, "Specified filter handle not found"); - err = -ENOENT; - } + NL_SET_ERR_MSG(extack, "Specified filter handle not found"); + err = -ENOENT; } else { bool last; - err = tfilter_del_notify(net, skb, n, tp, block, - q, parent, fh, false, &last, - extack); + err = tfilter_del_notify(net, skb, n, tp, block, q, parent, fh, + &last, rtnl_held, extack); + if (err) goto errout; - if (last) { - tcf_chain_tp_remove(chain, &chain_info, tp); - tcf_proto_destroy(tp, extack); - } + if (last) + tcf_chain_tp_delete_empty(chain, tp, rtnl_held, extack); } errout: - if (chain) + if (chain) { + if (tp && !IS_ERR(tp)) + tcf_proto_put(tp, rtnl_held, NULL); tcf_chain_put(chain); - tcf_block_release(q, block); + } + tcf_block_release(q, block, rtnl_held); + + if (rtnl_held) + rtnl_unlock(); + return err; + +errout_locked: + mutex_unlock(&chain->filter_chain_lock); + goto errout; } static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, @@ -1781,6 +2626,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; @@ -1789,13 +2635,15 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct Qdisc *q = NULL; struct tcf_chain_info chain_info; struct tcf_chain *chain = NULL; - struct tcf_block *block; + struct tcf_block *block = NULL; struct tcf_proto *tp = NULL; unsigned long cl = 0; void *fh = NULL; int err; + bool rtnl_held = false; - err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack); + err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX, + rtm_tca_policy, extack); if (err < 0) return err; @@ -1811,14 +2659,37 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, /* Find head of filter chain. */ - block = tcf_block_find(net, &q, &parent, &cl, - t->tcm_ifindex, t->tcm_block_index, extack); + err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack); + if (err) + return err; + + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } + /* Take rtnl mutex if block is shared (no qdisc found), qdisc is not + * unlocked, classifier type is not specified, classifier is not + * unlocked. + */ + if ((q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || + !tcf_proto_is_unlocked(name)) { + rtnl_held = true; + rtnl_lock(); + } + + err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack); + if (err) + goto errout; + + block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index, + extack); if (IS_ERR(block)) { err = PTR_ERR(block); goto errout; } - chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; + chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0); if (chain_index > TC_ACT_EXT_VAL_MASK) { NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); err = -EINVAL; @@ -1831,11 +2702,16 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, goto errout; } + mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_tp_find(chain, &chain_info, protocol, - prio, false); - if (!tp || IS_ERR(tp)) { + prio, false, extack); + mutex_unlock(&chain->filter_chain_lock); + if (!tp) { + err = -ENOENT; NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); - err = tp ? PTR_ERR(tp) : -ENOENT; + goto errout; + } else if (IS_ERR(tp)) { + err = PTR_ERR(tp); goto errout; } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one"); @@ -1850,15 +2726,23 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, err = -ENOENT; } else { err = tfilter_notify(net, skb, n, tp, block, q, parent, - fh, RTM_NEWTFILTER, true); + fh, RTM_NEWTFILTER, true, rtnl_held, NULL); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send filter notify message"); } + tfilter_put(tp, fh); errout: - if (chain) + if (chain) { + if (tp && !IS_ERR(tp)) + tcf_proto_put(tp, rtnl_held, NULL); tcf_chain_put(chain); - tcf_block_release(q, block); + } + tcf_block_release(q, block, rtnl_held); + + if (rtnl_held) + rtnl_unlock(); + return err; } @@ -1869,6 +2753,7 @@ struct tcf_dump_args { struct tcf_block *block; struct Qdisc *q; u32 parent; + bool terse_dump; }; static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) @@ -1879,21 +2764,25 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) return tcf_fill_node(net, a->skb, tp, a->block, a->q, a->parent, n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTFILTER); + RTM_NEWTFILTER, a->terse_dump, true, NULL); } static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, struct sk_buff *skb, struct netlink_callback *cb, - long index_start, long *p_index) + long index_start, long *p_index, bool terse) { struct net *net = sock_net(skb->sk); struct tcf_block *block = chain->block; struct tcmsg *tcm = nlmsg_data(cb->nlh); + struct tcf_proto *tp, *tp_prev; struct tcf_dump_args arg; - struct tcf_proto *tp; - for (tp = rtnl_dereference(chain->filter_chain); - tp; tp = rtnl_dereference(tp->next), (*p_index)++) { + for (tp = __tcf_get_next_proto(chain, NULL); + tp; + tp_prev = tp, + tp = __tcf_get_next_proto(chain, tp), + tcf_proto_put(tp_prev, true, NULL), + (*p_index)++) { if (*p_index < index_start) continue; if (TC_H_MAJ(tcm->tcm_info) && @@ -1909,9 +2798,8 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, if (tcf_fill_node(net, skb, tp, block, q, parent, NULL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTFILTER) <= 0) - return false; - + RTM_NEWTFILTER, false, true, NULL) <= 0) + goto errout; cb->args[1] = 1; } if (!tp->ops->walk) @@ -1926,24 +2814,35 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, arg.w.skip = cb->args[1] - 1; arg.w.count = 0; arg.w.cookie = cb->args[2]; - tp->ops->walk(tp, &arg.w); + arg.terse_dump = terse; + tp->ops->walk(tp, &arg.w, true); cb->args[2] = arg.w.cookie; cb->args[1] = arg.w.count + 1; if (arg.w.stop) - return false; + goto errout; } return true; + +errout: + tcf_proto_put(tp, true, NULL); + return false; } +static const struct nla_policy tcf_tfilter_dump_policy[TCA_MAX + 1] = { + [TCA_CHAIN] = { .type = NLA_U32 }, + [TCA_DUMP_FLAGS] = NLA_POLICY_BITFIELD32(TCA_DUMP_FLAGS_TERSE), +}; + /* called with RTNL */ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) { + struct tcf_chain *chain, *chain_prev; struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; struct Qdisc *q = NULL; struct tcf_block *block; - struct tcf_chain *chain; struct tcmsg *tcm = nlmsg_data(cb->nlh); + bool terse_dump = false; long index_start; long index; u32 parent; @@ -1952,11 +2851,18 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (nlmsg_len(cb->nlh) < sizeof(*tcm)) return skb->len; - err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, - cb->extack); + err = nlmsg_parse_deprecated(cb->nlh, sizeof(*tcm), tca, TCA_MAX, + tcf_tfilter_dump_policy, cb->extack); if (err) return err; + if (tca[TCA_DUMP_FLAGS]) { + struct nla_bitfield32 flags = + nla_get_bitfield32(tca[TCA_DUMP_FLAGS]); + + terse_dump = flags.value & TCA_DUMP_FLAGS_TERSE; + } + if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) { block = tcf_block_refcnt_get(net, tcm->tcm_block_index); if (!block) @@ -1978,12 +2884,10 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; parent = tcm->tcm_parent; - if (!parent) { - q = dev->qdisc; - parent = q->handle; - } else { + if (!parent) + q = rtnl_dereference(dev->qdisc); + else q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); - } if (!q) goto out; cops = q->ops->cl_ops; @@ -1999,6 +2903,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) block = cops->tcf_block(q, cl, NULL); if (!block) goto out; + parent = block->classid; if (tcf_block_shared(block)) q = NULL; } @@ -2006,19 +2911,24 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) index_start = cb->args[0]; index = 0; - list_for_each_entry(chain, &block->chain_list, list) { + for (chain = __tcf_get_next_chain(block, NULL); + chain; + chain_prev = chain, + chain = __tcf_get_next_chain(block, chain), + tcf_chain_put(chain_prev)) { if (tca[TCA_CHAIN] && nla_get_u32(tca[TCA_CHAIN]) != chain->index) continue; if (!tcf_chain_dump(chain, q, parent, skb, cb, - index_start, &index)) { + index_start, &index, terse_dump)) { + tcf_chain_put(chain); err = -EMSGSIZE; break; } } if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) - tcf_block_refcnt_put(block); + tcf_block_refcnt_put(block, true); cb->args[0] = index; out: @@ -2028,9 +2938,12 @@ out: return skb->len; } -static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net, - struct sk_buff *skb, struct tcf_block *block, - u32 portid, u32 seq, u16 flags, int event) +static int tc_chain_fill_node(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv, u32 chain_index, + struct net *net, struct sk_buff *skb, + struct tcf_block *block, + u32 portid, u32 seq, u16 flags, int event, + struct netlink_ext_ack *extack) { unsigned char *b = skb_tail_pointer(skb); const struct tcf_proto_ops *ops; @@ -2038,8 +2951,8 @@ static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net, struct tcmsg *tcm; void *priv; - ops = chain->tmplt_ops; - priv = chain->tmplt_priv; + ops = tmplt_ops; + priv = tmplt_priv; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) @@ -2057,7 +2970,7 @@ static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net, tcm->tcm_block_index = block->index; } - if (nla_put_u32(skb, TCA_CHAIN, chain->index)) + if (nla_put_u32(skb, TCA_CHAIN, chain_index)) goto nla_put_failure; if (ops) { @@ -2067,7 +2980,12 @@ static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net, goto nla_put_failure; } + if (extack && extack->_msg && + nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; out_nlmsg_trim: @@ -2077,25 +2995,59 @@ nla_put_failure: } static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, - u32 seq, u16 flags, int event, bool unicast) + u32 seq, u16 flags, int event, bool unicast, + struct netlink_ext_ack *extack) { u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; struct tcf_block *block = chain->block; struct net *net = block->net; struct sk_buff *skb; + int err = 0; + + if (!unicast && !rtnl_notify_needed(net, flags, RTNLGRP_TC)) + return 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; - if (tc_chain_fill_node(chain, net, skb, block, portid, - seq, flags, event) <= 0) { + if (tc_chain_fill_node(chain->tmplt_ops, chain->tmplt_priv, + chain->index, net, skb, block, portid, + seq, flags, event, extack) <= 0) { kfree_skb(skb); return -EINVAL; } if (unicast) - return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT); + err = rtnl_unicast(skb, net, portid); + else + err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, + flags & NLM_F_ECHO); + + return err; +} + +static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv, u32 chain_index, + struct tcf_block *block, struct sk_buff *oskb, + u32 seq, u16 flags) +{ + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + struct net *net = block->net; + struct sk_buff *skb; + + if (!rtnl_notify_needed(net, flags, RTNLGRP_TC)) + return 0; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (tc_chain_fill_node(tmplt_ops, tmplt_priv, chain_index, net, skb, + block, portid, seq, flags, RTM_DELCHAIN, NULL) <= 0) { + kfree_skb(skb); + return -EINVAL; + } return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO); } @@ -2105,17 +3057,25 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, struct netlink_ext_ack *extack) { const struct tcf_proto_ops *ops; + char name[IFNAMSIZ]; void *tmplt_priv; /* If kind is not set, user did not specify template. */ if (!tca[TCA_KIND]) return 0; - ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), extack); + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC chain template name too long"); + return -EINVAL; + } + + ops = tcf_proto_lookup_ops(name, true, extack); if (IS_ERR(ops)) return PTR_ERR(ops); - if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) { + if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump || + !ops->tmplt_reoffload) { NL_SET_ERR_MSG(extack, "Chain templates are not supported with specified classifier"); + module_put(ops->owner); return -EOPNOTSUPP; } @@ -2129,16 +3089,15 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, return 0; } -static void tc_chain_tmplt_del(struct tcf_chain *chain) +static void tc_chain_tmplt_del(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv) { - const struct tcf_proto_ops *ops = chain->tmplt_ops; - /* If template ops are set, no work to do for us. */ - if (!ops) + if (!tmplt_ops) return; - ops->tmplt_destroy(chain->tmplt_priv); - module_put(ops->owner); + tmplt_ops->tmplt_destroy(tmplt_priv); + module_put(tmplt_ops->owner); } /* Add/delete/get a chain */ @@ -2151,18 +3110,16 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n, struct tcmsg *t; u32 parent; u32 chain_index; - struct Qdisc *q = NULL; - struct tcf_chain *chain = NULL; + struct Qdisc *q; + struct tcf_chain *chain; struct tcf_block *block; unsigned long cl; int err; - if (n->nlmsg_type != RTM_GETCHAIN && - !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) - return -EPERM; - replay: - err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack); + q = NULL; + err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX, + rtm_tca_policy, extack); if (err < 0) return err; @@ -2175,12 +3132,14 @@ replay: if (IS_ERR(block)) return PTR_ERR(block); - chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; + chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0); if (chain_index > TC_ACT_EXT_VAL_MASK) { NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); err = -EINVAL; goto errout_block; } + + mutex_lock(&block->lock); chain = tcf_chain_lookup(block, chain_index); if (n->nlmsg_type == RTM_NEWCHAIN) { if (chain) { @@ -2192,58 +3151,65 @@ replay: } else { NL_SET_ERR_MSG(extack, "Filter chain already exists"); err = -EEXIST; - goto errout_block; + goto errout_block_locked; } } else { if (!(n->nlmsg_flags & NLM_F_CREATE)) { NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain"); err = -ENOENT; - goto errout_block; + goto errout_block_locked; } chain = tcf_chain_create(block, chain_index); if (!chain) { NL_SET_ERR_MSG(extack, "Failed to create filter chain"); err = -ENOMEM; - goto errout_block; + goto errout_block_locked; } } } else { if (!chain || tcf_chain_held_by_acts_only(chain)) { NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); err = -EINVAL; - goto errout_block; + goto errout_block_locked; } tcf_chain_hold(chain); } + if (n->nlmsg_type == RTM_NEWCHAIN) { + /* Modifying chain requires holding parent block lock. In case + * the chain was successfully added, take a reference to the + * chain. This ensures that an empty chain does not disappear at + * the end of this function. + */ + tcf_chain_hold(chain); + chain->explicitly_created = true; + } + mutex_unlock(&block->lock); + switch (n->nlmsg_type) { case RTM_NEWCHAIN: err = tc_chain_tmplt_add(chain, net, tca, extack); - if (err) + if (err) { + tcf_chain_put_explicitly_created(chain); goto errout; - /* In case the chain was successfully added, take a reference - * to the chain. This ensures that an empty chain - * does not disappear at the end of this function. - */ - tcf_chain_hold(chain); - chain->explicitly_created = true; + } + tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, - RTM_NEWCHAIN, false); + RTM_NEWCHAIN, false, extack); break; case RTM_DELCHAIN: tfilter_notify_chain(net, skb, block, q, parent, n, - chain, RTM_DELTFILTER); + chain, RTM_DELTFILTER, extack); /* Flush the chain first as the user requested chain removal. */ - tcf_chain_flush(chain); + tcf_chain_flush(chain, true); /* In case the chain was successfully deleted, put a reference * to the chain previously taken during addition. */ tcf_chain_put_explicitly_created(chain); - chain->explicitly_created = false; break; case RTM_GETCHAIN: err = tc_chain_notify(chain, skb, n->nlmsg_seq, - n->nlmsg_seq, n->nlmsg_type, true); + n->nlmsg_flags, n->nlmsg_type, true, extack); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send chain notify message"); break; @@ -2256,11 +3222,15 @@ replay: errout: tcf_chain_put(chain); errout_block: - tcf_block_release(q, block); + tcf_block_release(q, block, true); if (err == -EAGAIN) /* Replay the request. */ goto replay; return err; + +errout_block_locked: + mutex_unlock(&block->lock); + goto errout_block; } /* called with RTNL */ @@ -2270,18 +3240,17 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) struct nlattr *tca[TCA_MAX + 1]; struct Qdisc *q = NULL; struct tcf_block *block; - struct tcf_chain *chain; struct tcmsg *tcm = nlmsg_data(cb->nlh); + struct tcf_chain *chain; long index_start; long index; - u32 parent; int err; if (nlmsg_len(cb->nlh) < sizeof(*tcm)) return skb->len; - err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, - cb->extack); + err = nlmsg_parse_deprecated(cb->nlh, sizeof(*tcm), tca, TCA_MAX, + rtm_tca_policy, cb->extack); if (err) return err; @@ -2289,13 +3258,6 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) block = tcf_block_refcnt_get(net, tcm->tcm_block_index); if (!block) goto out; - /* If we work with block index, q is NULL and parent value - * will never be used in the following code. The check - * in tcf_fill_node prevents it. However, compiler does not - * see that far, so set parent to zero to silence the warning - * about parent being uninitialized. - */ - parent = 0; } else { const struct Qdisc_class_ops *cops; struct net_device *dev; @@ -2305,13 +3267,11 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) if (!dev) return skb->len; - parent = tcm->tcm_parent; - if (!parent) { - q = dev->qdisc; - parent = q->handle; - } else { + if (!tcm->tcm_parent) + q = rtnl_dereference(dev->qdisc); + else q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); - } + if (!q) goto out; cops = q->ops->cl_ops; @@ -2334,6 +3294,7 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) index_start = cb->args[0]; index = 0; + mutex_lock(&block->lock); list_for_each_entry(chain, &block->chain_list, list) { if ((tca[TCA_CHAIN] && nla_get_u32(tca[TCA_CHAIN]) != chain->index)) @@ -2344,17 +3305,19 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) } if (tcf_chain_held_by_acts_only(chain)) continue; - err = tc_chain_fill_node(chain, net, skb, block, + err = tc_chain_fill_node(chain->tmplt_ops, chain->tmplt_priv, + chain->index, net, skb, block, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWCHAIN); + RTM_NEWCHAIN, NULL); if (err <= 0) break; index++; } + mutex_unlock(&block->lock); if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) - tcf_block_refcnt_put(block); + tcf_block_refcnt_put(block, true); cb->args[0] = index; out: @@ -2364,47 +3327,102 @@ out: return skb->len; } +int tcf_exts_init_ex(struct tcf_exts *exts, struct net *net, int action, + int police, struct tcf_proto *tp, u32 handle, + bool use_action_miss) +{ + int err = 0; + +#ifdef CONFIG_NET_CLS_ACT + exts->type = 0; + exts->nr_actions = 0; + exts->miss_cookie_node = NULL; + /* Note: we do not own yet a reference on net. + * This reference might be taken later from tcf_exts_get_net(). + */ + exts->net = net; + exts->actions = kcalloc(TCA_ACT_MAX_PRIO, sizeof(struct tc_action *), + GFP_KERNEL); + if (!exts->actions) + return -ENOMEM; +#endif + + exts->action = action; + exts->police = police; + + if (!use_action_miss) + return 0; + + err = tcf_exts_miss_cookie_base_alloc(exts, tp, handle); + if (err) + goto err_miss_alloc; + + return 0; + +err_miss_alloc: + tcf_exts_destroy(exts); +#ifdef CONFIG_NET_CLS_ACT + exts->actions = NULL; +#endif + return err; +} +EXPORT_SYMBOL(tcf_exts_init_ex); + void tcf_exts_destroy(struct tcf_exts *exts) { + tcf_exts_miss_cookie_base_destroy(exts); + #ifdef CONFIG_NET_CLS_ACT - tcf_action_destroy(exts->actions, TCA_ACT_UNBIND); - kfree(exts->actions); + if (exts->actions) { + tcf_action_destroy(exts->actions, TCA_ACT_UNBIND); + kfree(exts->actions); + } exts->nr_actions = 0; #endif } 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, bool ovr, - 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 { + int init_res[TCA_ACT_MAX_PRIO] = {}; struct tc_action *act; size_t attr_size = 0; if (exts->police && tb[exts->police]) { + struct tc_action_ops *a_o; + + flags |= TCA_ACT_FLAGS_POLICE | TCA_ACT_FLAGS_BIND; + a_o = tc_action_load_ops(tb[exts->police], flags, + extack); + if (IS_ERR(a_o)) + return PTR_ERR(a_o); act = tcf_action_init_1(net, tp, tb[exts->police], - rate_tlv, "police", ovr, - TCA_ACT_BIND, true, extack); + rate_tlv, a_o, init_res, flags, + extack); + module_put(a_o->owner); if (IS_ERR(act)) return PTR_ERR(act); act->type = exts->type = TCA_OLD_COMPAT; exts->actions[0] = act; exts->nr_actions = 1; + tcf_idr_insert_many(exts->actions, init_res); } else if (exts->action && tb[exts->action]) { int err; + flags |= TCA_ACT_FLAGS_BIND; err = tcf_action_init(net, tp, tb[exts->action], - rate_tlv, NULL, ovr, TCA_ACT_BIND, - exts->actions, &attr_size, true, + rate_tlv, exts->actions, init_res, + &attr_size, flags, fl_flags, extack); if (err < 0) return err; exts->nr_actions = err; } - exts->net = net; } #else if ((exts->action && tb[exts->action]) || @@ -2416,6 +3434,15 @@ 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) @@ -2451,16 +3478,17 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts) * tc data even if iproute2 was newer - jhs */ if (exts->type != TCA_OLD_COMPAT) { - nest = nla_nest_start(skb, exts->action); + nest = nla_nest_start_noflag(skb, exts->action); if (nest == NULL) goto nla_put_failure; - if (tcf_action_dump(skb, exts->actions, 0, 0) < 0) + if (tcf_action_dump(skb, exts->actions, 0, 0, false) + < 0) goto nla_put_failure; nla_nest_end(skb, nest); } else if (exts->police) { struct tc_action *act = tcf_exts_first_act(exts); - nest = nla_nest_start(skb, exts->police); + nest = nla_nest_start_noflag(skb, exts->police); if (nest == NULL || !act) goto nla_put_failure; if (tcf_action_dump_old(skb, act, 0, 0) < 0) @@ -2479,6 +3507,31 @@ nla_put_failure: } EXPORT_SYMBOL(tcf_exts_dump); +int tcf_exts_terse_dump(struct sk_buff *skb, struct tcf_exts *exts) +{ +#ifdef CONFIG_NET_CLS_ACT + struct nlattr *nest; + + if (!exts->action || !tcf_exts_has_actions(exts)) + return 0; + + nest = nla_nest_start_noflag(skb, exts->action); + if (!nest) + goto nla_put_failure; + + if (tcf_action_dump(skb, exts->actions, 0, 0, true) < 0) + goto nla_put_failure; + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +#else + return 0; +#endif +} +EXPORT_SYMBOL(tcf_exts_terse_dump); int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts) { @@ -2491,18 +3544,62 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts) } EXPORT_SYMBOL(tcf_exts_dump_stats); -int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, - void *type_data, bool err_stop) +static void tcf_block_offload_inc(struct tcf_block *block, u32 *flags) { - struct tcf_block_cb *block_cb; + if (*flags & TCA_CLS_FLAGS_IN_HW) + return; + *flags |= TCA_CLS_FLAGS_IN_HW; + atomic_inc(&block->offloadcnt); +} + +static void tcf_block_offload_dec(struct tcf_block *block, u32 *flags) +{ + if (!(*flags & TCA_CLS_FLAGS_IN_HW)) + return; + *flags &= ~TCA_CLS_FLAGS_IN_HW; + atomic_dec(&block->offloadcnt); +} + +static void tc_cls_offload_cnt_update(struct tcf_block *block, + struct tcf_proto *tp, u32 *cnt, + u32 *flags, u32 diff, bool add) +{ + lockdep_assert_held(&block->cb_lock); + + spin_lock(&tp->lock); + if (add) { + if (!*cnt) + tcf_block_offload_inc(block, flags); + *cnt += diff; + } else { + *cnt -= diff; + if (!*cnt) + tcf_block_offload_dec(block, flags); + } + spin_unlock(&tp->lock); +} + +static void +tc_cls_offload_cnt_reset(struct tcf_block *block, struct tcf_proto *tp, + u32 *cnt, u32 *flags) +{ + lockdep_assert_held(&block->cb_lock); + + spin_lock(&tp->lock); + tcf_block_offload_dec(block, flags); + *cnt = 0; + spin_unlock(&tp->lock); +} + +static int +__tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, + void *type_data, bool err_stop) +{ + struct flow_block_cb *block_cb; int ok_count = 0; int err; - /* Make sure all netdevs sharing this block are offload-capable. */ - if (block->nooffloaddevcnt && err_stop) - return -EOPNOTSUPP; - - list_for_each_entry(block_cb, &block->cb_list, list) { + list_for_each_entry(block_cb, &block->flow_block.cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err) { if (err_stop) @@ -2513,8 +3610,453 @@ int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, } return ok_count; } + +int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, + void *type_data, bool err_stop, bool rtnl_held) +{ + bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held; + int ok_count; + +retry: + if (take_rtnl) + rtnl_lock(); + down_read(&block->cb_lock); + /* Need to obtain rtnl lock if block is bound to devs that require it. + * In block bind code cb_lock is obtained while holding rtnl, so we must + * obtain the locks in same order here. + */ + if (!rtnl_held && !take_rtnl && block->lockeddevcnt) { + up_read(&block->cb_lock); + take_rtnl = true; + goto retry; + } + + ok_count = __tc_setup_cb_call(block, type, type_data, err_stop); + + up_read(&block->cb_lock); + if (take_rtnl) + rtnl_unlock(); + return ok_count; +} EXPORT_SYMBOL(tc_setup_cb_call); +/* Non-destructive filter add. If filter that wasn't already in hardware is + * successfully offloaded, increment block offloads counter. On failure, + * previously offloaded filter is considered to be intact and offloads counter + * is not decremented. + */ + +int tc_setup_cb_add(struct tcf_block *block, struct tcf_proto *tp, + enum tc_setup_type type, void *type_data, bool err_stop, + u32 *flags, unsigned int *in_hw_count, bool rtnl_held) +{ + bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held; + int ok_count; + +retry: + if (take_rtnl) + rtnl_lock(); + down_read(&block->cb_lock); + /* Need to obtain rtnl lock if block is bound to devs that require it. + * In block bind code cb_lock is obtained while holding rtnl, so we must + * obtain the locks in same order here. + */ + if (!rtnl_held && !take_rtnl && block->lockeddevcnt) { + up_read(&block->cb_lock); + take_rtnl = true; + goto retry; + } + + /* Make sure all netdevs sharing this block are offload-capable. */ + if (block->nooffloaddevcnt && err_stop) { + ok_count = -EOPNOTSUPP; + goto err_unlock; + } + + ok_count = __tc_setup_cb_call(block, type, type_data, err_stop); + if (ok_count < 0) + goto err_unlock; + + if (tp->ops->hw_add) + tp->ops->hw_add(tp, type_data); + if (ok_count > 0) + tc_cls_offload_cnt_update(block, tp, in_hw_count, flags, + ok_count, true); +err_unlock: + up_read(&block->cb_lock); + if (take_rtnl) + rtnl_unlock(); + return min(ok_count, 0); +} +EXPORT_SYMBOL(tc_setup_cb_add); + +/* Destructive filter replace. If filter that wasn't already in hardware is + * successfully offloaded, increment block offload counter. On failure, + * previously offloaded filter is considered to be destroyed and offload counter + * is decremented. + */ + +int tc_setup_cb_replace(struct tcf_block *block, struct tcf_proto *tp, + enum tc_setup_type type, void *type_data, bool err_stop, + u32 *old_flags, unsigned int *old_in_hw_count, + u32 *new_flags, unsigned int *new_in_hw_count, + bool rtnl_held) +{ + bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held; + int ok_count; + +retry: + if (take_rtnl) + rtnl_lock(); + down_read(&block->cb_lock); + /* Need to obtain rtnl lock if block is bound to devs that require it. + * In block bind code cb_lock is obtained while holding rtnl, so we must + * obtain the locks in same order here. + */ + if (!rtnl_held && !take_rtnl && block->lockeddevcnt) { + up_read(&block->cb_lock); + take_rtnl = true; + goto retry; + } + + /* Make sure all netdevs sharing this block are offload-capable. */ + if (block->nooffloaddevcnt && err_stop) { + ok_count = -EOPNOTSUPP; + goto err_unlock; + } + + tc_cls_offload_cnt_reset(block, tp, old_in_hw_count, old_flags); + if (tp->ops->hw_del) + tp->ops->hw_del(tp, type_data); + + ok_count = __tc_setup_cb_call(block, type, type_data, err_stop); + if (ok_count < 0) + goto err_unlock; + + if (tp->ops->hw_add) + tp->ops->hw_add(tp, type_data); + if (ok_count > 0) + tc_cls_offload_cnt_update(block, tp, new_in_hw_count, + new_flags, ok_count, true); +err_unlock: + up_read(&block->cb_lock); + if (take_rtnl) + rtnl_unlock(); + return min(ok_count, 0); +} +EXPORT_SYMBOL(tc_setup_cb_replace); + +/* Destroy filter and decrement block offload counter, if filter was previously + * offloaded. + */ + +int tc_setup_cb_destroy(struct tcf_block *block, struct tcf_proto *tp, + enum tc_setup_type type, void *type_data, bool err_stop, + u32 *flags, unsigned int *in_hw_count, bool rtnl_held) +{ + bool take_rtnl = READ_ONCE(block->lockeddevcnt) && !rtnl_held; + int ok_count; + +retry: + if (take_rtnl) + rtnl_lock(); + down_read(&block->cb_lock); + /* Need to obtain rtnl lock if block is bound to devs that require it. + * In block bind code cb_lock is obtained while holding rtnl, so we must + * obtain the locks in same order here. + */ + if (!rtnl_held && !take_rtnl && block->lockeddevcnt) { + up_read(&block->cb_lock); + take_rtnl = true; + goto retry; + } + + ok_count = __tc_setup_cb_call(block, type, type_data, err_stop); + + tc_cls_offload_cnt_reset(block, tp, in_hw_count, flags); + if (tp->ops->hw_del) + tp->ops->hw_del(tp, type_data); + + up_read(&block->cb_lock); + if (take_rtnl) + rtnl_unlock(); + return min(ok_count, 0); +} +EXPORT_SYMBOL(tc_setup_cb_destroy); + +int tc_setup_cb_reoffload(struct tcf_block *block, struct tcf_proto *tp, + bool add, flow_setup_cb_t *cb, + enum tc_setup_type type, void *type_data, + void *cb_priv, u32 *flags, unsigned int *in_hw_count) +{ + int err = cb(type, type_data, cb_priv); + + if (err) { + if (add && tc_skip_sw(*flags)) + return err; + } else { + tc_cls_offload_cnt_update(block, tp, in_hw_count, flags, 1, + add); + } + + return 0; +} +EXPORT_SYMBOL(tc_setup_cb_reoffload); + +static int tcf_act_get_user_cookie(struct flow_action_entry *entry, + const struct tc_action *act) +{ + struct tc_cookie *user_cookie; + int err = 0; + + rcu_read_lock(); + user_cookie = rcu_dereference(act->user_cookie); + if (user_cookie) { + entry->user_cookie = flow_action_cookie_create(user_cookie->data, + user_cookie->len, + GFP_ATOMIC); + if (!entry->user_cookie) + err = -ENOMEM; + } + rcu_read_unlock(); + return err; +} + +static void tcf_act_put_user_cookie(struct flow_action_entry *entry) +{ + flow_action_cookie_destroy(entry->user_cookie); +} + +void tc_cleanup_offload_action(struct flow_action *flow_action) +{ + struct flow_action_entry *entry; + int i; + + flow_action_for_each(i, entry, flow_action) { + tcf_act_put_user_cookie(entry); + if (entry->destructor) + entry->destructor(entry->destructor_priv); + } +} +EXPORT_SYMBOL(tc_cleanup_offload_action); + +static int tc_setup_offload_act(struct tc_action *act, + struct flow_action_entry *entry, + u32 *index_inc, + struct netlink_ext_ack *extack) +{ +#ifdef CONFIG_NET_CLS_ACT + if (act->ops->offload_act_setup) { + return act->ops->offload_act_setup(act, entry, index_inc, true, + extack); + } else { + NL_SET_ERR_MSG(extack, "Action does not support offload"); + return -EOPNOTSUPP; + } +#else + return 0; +#endif +} + +int tc_setup_action(struct flow_action *flow_action, + struct tc_action *actions[], + u32 miss_cookie_base, + struct netlink_ext_ack *extack) +{ + int i, j, k, index, err = 0; + struct tc_action *act; + + 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 (!actions) + return 0; + + j = 0; + tcf_act_for_each_action(i, act, actions) { + struct flow_action_entry *entry; + + entry = &flow_action->entries[j]; + spin_lock_bh(&act->tcfa_lock); + err = tcf_act_get_user_cookie(entry, act); + if (err) + goto err_out_locked; + + index = 0; + err = tc_setup_offload_act(act, entry, &index, extack); + if (err) + goto err_out_locked; + + for (k = 0; k < index ; k++) { + entry[k].hw_stats = tc_act_hw_stats(act->hw_stats); + entry[k].hw_index = act->tcfa_index; + entry[k].cookie = (unsigned long)act; + entry[k].miss_cookie = + tcf_exts_miss_cookie_get(miss_cookie_base, i); + } + + j += index; + + spin_unlock_bh(&act->tcfa_lock); + } + +err_out: + if (err) + tc_cleanup_offload_action(flow_action); + + return err; +err_out_locked: + spin_unlock_bh(&act->tcfa_lock); + goto err_out; +} + +int tc_setup_offload_action(struct flow_action *flow_action, + const struct tcf_exts *exts, + struct netlink_ext_ack *extack) +{ +#ifdef CONFIG_NET_CLS_ACT + u32 miss_cookie_base; + + if (!exts) + return 0; + + miss_cookie_base = exts->miss_cookie_node ? + exts->miss_cookie_node->miss_cookie_base : 0; + return tc_setup_action(flow_action, exts->actions, miss_cookie_base, + extack); +#else + return 0; +#endif +} +EXPORT_SYMBOL(tc_setup_offload_action); + +unsigned int tcf_exts_num_actions(struct tcf_exts *exts) +{ + unsigned int num_acts = 0; + struct tc_action *act; + int i; + + tcf_exts_for_each_action(i, act, exts) { + if (is_tcf_pedit(act)) + num_acts += tcf_pedit_nkeys(act); + else + num_acts++; + } + return num_acts; +} +EXPORT_SYMBOL(tcf_exts_num_actions); + +#ifdef CONFIG_NET_CLS_ACT +static int tcf_qevent_parse_block_index(struct nlattr *block_index_attr, + u32 *p_block_index, + struct netlink_ext_ack *extack) +{ + *p_block_index = nla_get_u32(block_index_attr); + if (!*p_block_index) { + NL_SET_ERR_MSG(extack, "Block number may not be zero"); + return -EINVAL; + } + + return 0; +} + +int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch, + enum flow_block_binder_type binder_type, + struct nlattr *block_index_attr, + struct netlink_ext_ack *extack) +{ + u32 block_index; + int err; + + if (!block_index_attr) + return 0; + + err = tcf_qevent_parse_block_index(block_index_attr, &block_index, extack); + if (err) + return err; + + qe->info.binder_type = binder_type; + qe->info.chain_head_change = tcf_chain_head_change_dflt; + qe->info.chain_head_change_priv = &qe->filter_chain; + qe->info.block_index = block_index; + + return tcf_block_get_ext(&qe->block, sch, &qe->info, extack); +} +EXPORT_SYMBOL(tcf_qevent_init); + +void tcf_qevent_destroy(struct tcf_qevent *qe, struct Qdisc *sch) +{ + if (qe->info.block_index) + tcf_block_put_ext(qe->block, sch, &qe->info); +} +EXPORT_SYMBOL(tcf_qevent_destroy); + +int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index_attr, + struct netlink_ext_ack *extack) +{ + u32 block_index; + int err; + + if (!block_index_attr) + return 0; + + err = tcf_qevent_parse_block_index(block_index_attr, &block_index, extack); + if (err) + return err; + + /* Bounce newly-configured block or change in block. */ + if (block_index != qe->info.block_index) { + NL_SET_ERR_MSG(extack, "Change of blocks is not supported"); + return -EINVAL; + } + + return 0; +} +EXPORT_SYMBOL(tcf_qevent_validate_change); + +struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb, + struct sk_buff **to_free, int *ret) +{ + struct tcf_result cl_res; + struct tcf_proto *fl; + + if (!qe->info.block_index) + return skb; + + fl = rcu_dereference_bh(qe->filter_chain); + + switch (tcf_classify(skb, NULL, fl, &cl_res, false)) { + case TC_ACT_SHOT: + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + *ret = __NET_XMIT_BYPASS; + return NULL; + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + __qdisc_drop(skb, to_free); + *ret = __NET_XMIT_STOLEN; + return NULL; + case TC_ACT_REDIRECT: + skb_do_redirect(skb); + *ret = __NET_XMIT_STOLEN; + return NULL; + } + + return skb; +} +EXPORT_SYMBOL(tcf_qevent_handle); + +int tcf_qevent_dump(struct sk_buff *skb, int attr_name, struct tcf_qevent *qe) +{ + if (!qe->info.block_index) + return 0; + return nla_put_u32(skb, attr_name, qe->info.block_index); +} +EXPORT_SYMBOL(tcf_qevent_dump); +#endif + static __net_init int tcf_net_init(struct net *net) { struct tcf_net *tn = net_generic(net, tcf_net_id); @@ -2538,6 +4080,19 @@ static struct pernet_operations tcf_net_ops = { .size = sizeof(struct tcf_net), }; +static const struct rtnl_msg_handler tc_filter_rtnl_msg_handlers[] __initconst = { + {.msgtype = RTM_NEWTFILTER, .doit = tc_new_tfilter, + .flags = RTNL_FLAG_DOIT_UNLOCKED}, + {.msgtype = RTM_DELTFILTER, .doit = tc_del_tfilter, + .flags = RTNL_FLAG_DOIT_UNLOCKED}, + {.msgtype = RTM_GETTFILTER, .doit = tc_get_tfilter, + .dumpit = tc_dump_tfilter, .flags = RTNL_FLAG_DOIT_UNLOCKED}, + {.msgtype = RTM_NEWCHAIN, .doit = tc_ctl_chain}, + {.msgtype = RTM_DELCHAIN, .doit = tc_ctl_chain}, + {.msgtype = RTM_GETCHAIN, .doit = tc_ctl_chain, + .dumpit = tc_dump_chain}, +}; + static int __init tc_filter_init(void) { int err; @@ -2550,24 +4105,11 @@ static int __init tc_filter_init(void) if (err) goto err_register_pernet_subsys; - err = rhashtable_init(&indr_setup_block_ht, - &tc_indr_setup_block_ht_params); - if (err) - goto err_rhash_setup_block_ht; - - rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, 0); - rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, 0); - rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter, - tc_dump_tfilter, 0); - rtnl_register(PF_UNSPEC, RTM_NEWCHAIN, tc_ctl_chain, NULL, 0); - rtnl_register(PF_UNSPEC, RTM_DELCHAIN, tc_ctl_chain, NULL, 0); - rtnl_register(PF_UNSPEC, RTM_GETCHAIN, tc_ctl_chain, - tc_dump_chain, 0); + xa_init_flags(&tcf_exts_miss_cookies_xa, XA_FLAGS_ALLOC1); + rtnl_register_many(tc_filter_rtnl_msg_handlers); return 0; -err_rhash_setup_block_ht: - unregister_pernet_subsys(&tcf_net_ops); err_register_pernet_subsys: destroy_workqueue(tc_filter_wq); return err; |