diff options
Diffstat (limited to 'net/netfilter/nf_tables_api.c')
-rw-r--r-- | net/netfilter/nf_tables_api.c | 4495 |
1 files changed, 3215 insertions, 1280 deletions
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 38c680f28f15..e7152d599d73 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -12,6 +12,7 @@ #include <linux/netlink.h> #include <linux/vmalloc.h> #include <linux/rhashtable.h> +#include <linux/audit.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nf_tables.h> @@ -24,12 +25,13 @@ #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-")) +unsigned int nf_tables_net_id __read_mostly; + static LIST_HEAD(nf_tables_expressions); static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); static LIST_HEAD(nf_tables_destroy_list); static DEFINE_SPINLOCK(nf_tables_destroy_list_lock); -static u64 table_handle; enum { NFT_VALIDATE_SKIP = 0, @@ -65,9 +67,46 @@ static const struct rhashtable_params nft_objname_ht_params = { .automatic_shrinking = true, }; +struct nft_audit_data { + struct nft_table *table; + int entries; + int op; + struct list_head list; +}; + +static const u8 nft2audit_op[NFT_MSG_MAX] = { // enum nf_tables_msg_types + [NFT_MSG_NEWTABLE] = AUDIT_NFT_OP_TABLE_REGISTER, + [NFT_MSG_GETTABLE] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_DELTABLE] = AUDIT_NFT_OP_TABLE_UNREGISTER, + [NFT_MSG_NEWCHAIN] = AUDIT_NFT_OP_CHAIN_REGISTER, + [NFT_MSG_GETCHAIN] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_DELCHAIN] = AUDIT_NFT_OP_CHAIN_UNREGISTER, + [NFT_MSG_NEWRULE] = AUDIT_NFT_OP_RULE_REGISTER, + [NFT_MSG_GETRULE] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_DELRULE] = AUDIT_NFT_OP_RULE_UNREGISTER, + [NFT_MSG_NEWSET] = AUDIT_NFT_OP_SET_REGISTER, + [NFT_MSG_GETSET] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_DELSET] = AUDIT_NFT_OP_SET_UNREGISTER, + [NFT_MSG_NEWSETELEM] = AUDIT_NFT_OP_SETELEM_REGISTER, + [NFT_MSG_GETSETELEM] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_DELSETELEM] = AUDIT_NFT_OP_SETELEM_UNREGISTER, + [NFT_MSG_NEWGEN] = AUDIT_NFT_OP_GEN_REGISTER, + [NFT_MSG_GETGEN] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_TRACE] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_NEWOBJ] = AUDIT_NFT_OP_OBJ_REGISTER, + [NFT_MSG_GETOBJ] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_DELOBJ] = AUDIT_NFT_OP_OBJ_UNREGISTER, + [NFT_MSG_GETOBJ_RESET] = AUDIT_NFT_OP_OBJ_RESET, + [NFT_MSG_NEWFLOWTABLE] = AUDIT_NFT_OP_FLOWTABLE_REGISTER, + [NFT_MSG_GETFLOWTABLE] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_DELFLOWTABLE] = AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, +}; + static void nft_validate_state_update(struct net *net, u8 new_validate_state) { - switch (net->nft.validate_state) { + struct nftables_pernet *nft_net = nft_pernet(net); + + switch (nft_net->validate_state) { case NFT_VALIDATE_SKIP: WARN_ON_ONCE(new_validate_state == NFT_VALIDATE_DO); break; @@ -78,7 +117,7 @@ static void nft_validate_state_update(struct net *net, u8 new_validate_state) return; } - net->nft.validate_state = new_validate_state; + nft_net->validate_state = new_validate_state; } static void nf_tables_trans_destroy_work(struct work_struct *w); static DECLARE_WORK(trans_destroy_work, nf_tables_trans_destroy_work); @@ -113,6 +152,7 @@ static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx, if (trans == NULL) return NULL; + INIT_LIST_HEAD(&trans->list); trans->msg_type = msg_type; trans->ctx = *ctx; @@ -133,13 +173,15 @@ static void nft_trans_destroy(struct nft_trans *trans) static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) { + struct nftables_pernet *nft_net; struct net *net = ctx->net; struct nft_trans *trans; if (!nft_set_is_anonymous(set)) return; - list_for_each_entry_reverse(trans, &net->nft.commit_list, list) { + nft_net = nft_pernet(net); + list_for_each_entry_reverse(trans, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWSET: if (nft_trans_set(trans) == set) @@ -180,30 +222,18 @@ err_register: } static void nft_netdev_unregister_hooks(struct net *net, - struct list_head *hook_list) + struct list_head *hook_list, + bool release_netdev) { - struct nft_hook *hook; + struct nft_hook *hook, *next; - list_for_each_entry(hook, hook_list, list) + list_for_each_entry_safe(hook, next, hook_list, list) { nf_unregister_net_hook(net, &hook->ops); -} - -static int nft_register_basechain_hooks(struct net *net, int family, - struct nft_base_chain *basechain) -{ - if (family == NFPROTO_NETDEV) - return nft_netdev_register_hooks(net, &basechain->hook_list); - - return nf_register_net_hook(net, &basechain->ops); -} - -static void nft_unregister_basechain_hooks(struct net *net, int family, - struct nft_base_chain *basechain) -{ - if (family == NFPROTO_NETDEV) - nft_netdev_unregister_hooks(net, &basechain->hook_list); - else - nf_unregister_net_hook(net, &basechain->ops); + if (release_netdev) { + list_del(&hook->list); + kfree_rcu(hook, rcu); + } + } } static int nf_tables_register_hook(struct net *net, @@ -223,12 +253,16 @@ static int nf_tables_register_hook(struct net *net, if (basechain->type->ops_register) return basechain->type->ops_register(net, ops); - return nft_register_basechain_hooks(net, table->family, basechain); + if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) + return nft_netdev_register_hooks(net, &basechain->hook_list); + + return nf_register_net_hook(net, &basechain->ops); } -static void nf_tables_unregister_hook(struct net *net, - const struct nft_table *table, - struct nft_chain *chain) +static void __nf_tables_unregister_hook(struct net *net, + const struct nft_table *table, + struct nft_chain *chain, + bool release_netdev) { struct nft_base_chain *basechain; const struct nf_hook_ops *ops; @@ -242,7 +276,25 @@ static void nf_tables_unregister_hook(struct net *net, if (basechain->type->ops_unregister) return basechain->type->ops_unregister(net, ops); - nft_unregister_basechain_hooks(net, table->family, basechain); + if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) + nft_netdev_unregister_hooks(net, &basechain->hook_list, + release_netdev); + else + nf_unregister_net_hook(net, &basechain->ops); +} + +static void nf_tables_unregister_hook(struct net *net, + const struct nft_table *table, + struct nft_chain *chain) +{ + return __nf_tables_unregister_hook(net, table, chain, false); +} + +static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *trans) +{ + struct nftables_pernet *nft_net = nft_pernet(net); + + list_add_tail(&trans->list, &nft_net->commit_list); } static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) @@ -256,7 +308,7 @@ static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) if (msg_type == NFT_MSG_NEWTABLE) nft_activate_next(ctx->net, ctx->table); - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -280,10 +332,16 @@ static struct nft_trans *nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) if (trans == NULL) return ERR_PTR(-ENOMEM); - if (msg_type == NFT_MSG_NEWCHAIN) + if (msg_type == NFT_MSG_NEWCHAIN) { nft_activate_next(ctx->net, ctx->chain); - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + if (ctx->nla[NFTA_CHAIN_ID]) { + nft_trans_chain_id(trans) = + ntohl(nla_get_be32(ctx->nla[NFTA_CHAIN_ID])); + } + } + + nft_trans_commit_list_add_tail(ctx->net, trans); return trans; } @@ -307,7 +365,7 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_expr *expr; expr = nft_expr_first(rule); - while (expr != nft_expr_last(rule) && expr->ops) { + while (nft_expr_more(rule, expr)) { if (expr->ops->activate) expr->ops->activate(ctx, expr); @@ -322,7 +380,7 @@ static void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_expr *expr; expr = nft_expr_first(rule); - while (expr != nft_expr_last(rule) && expr->ops) { + while (nft_expr_more(rule, expr)) { if (expr->ops->deactivate) expr->ops->deactivate(ctx, expr, phase); @@ -356,7 +414,7 @@ static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type, ntohl(nla_get_be32(ctx->nla[NFTA_RULE_ID])); } nft_trans_rule(trans) = rule; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return trans; } @@ -422,7 +480,7 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, nft_activate_next(ctx->net, set); } nft_trans_set(trans) = set; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -454,7 +512,7 @@ static int nft_trans_obj_add(struct nft_ctx *ctx, int msg_type, nft_activate_next(ctx->net, obj); nft_trans_obj(trans) = obj; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -486,8 +544,9 @@ static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, if (msg_type == NFT_MSG_NEWFLOWTABLE) nft_activate_next(ctx->net, flowtable); + INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); nft_trans_flowtable(trans) = flowtable; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -507,24 +566,84 @@ static int nft_delflowtable(struct nft_ctx *ctx, return err; } +static void __nft_reg_track_clobber(struct nft_regs_track *track, u8 dreg) +{ + int i; + + for (i = track->regs[dreg].num_reg; i > 0; i--) + __nft_reg_track_cancel(track, dreg - i); +} + +static void __nft_reg_track_update(struct nft_regs_track *track, + const struct nft_expr *expr, + u8 dreg, u8 num_reg) +{ + track->regs[dreg].selector = expr; + track->regs[dreg].bitwise = NULL; + track->regs[dreg].num_reg = num_reg; +} + +void nft_reg_track_update(struct nft_regs_track *track, + const struct nft_expr *expr, u8 dreg, u8 len) +{ + unsigned int regcount; + int i; + + __nft_reg_track_clobber(track, dreg); + + regcount = DIV_ROUND_UP(len, NFT_REG32_SIZE); + for (i = 0; i < regcount; i++, dreg++) + __nft_reg_track_update(track, expr, dreg, i); +} +EXPORT_SYMBOL_GPL(nft_reg_track_update); + +void nft_reg_track_cancel(struct nft_regs_track *track, u8 dreg, u8 len) +{ + unsigned int regcount; + int i; + + __nft_reg_track_clobber(track, dreg); + + regcount = DIV_ROUND_UP(len, NFT_REG32_SIZE); + for (i = 0; i < regcount; i++, dreg++) + __nft_reg_track_cancel(track, dreg); +} +EXPORT_SYMBOL_GPL(nft_reg_track_cancel); + +void __nft_reg_track_cancel(struct nft_regs_track *track, u8 dreg) +{ + track->regs[dreg].selector = NULL; + track->regs[dreg].bitwise = NULL; + track->regs[dreg].num_reg = 0; +} +EXPORT_SYMBOL_GPL(__nft_reg_track_cancel); + /* * Tables */ static struct nft_table *nft_table_lookup(const struct net *net, const struct nlattr *nla, - u8 family, u8 genmask) + u8 family, u8 genmask, u32 nlpid) { + struct nftables_pernet *nft_net; struct nft_table *table; if (nla == NULL) return ERR_PTR(-EINVAL); - list_for_each_entry_rcu(table, &net->nft.tables, list) { + nft_net = nft_pernet(net); + list_for_each_entry_rcu(table, &nft_net->tables, list, + lockdep_is_held(&nft_net->commit_mutex)) { if (!nla_strcmp(nla, table->name) && table->family == family && - nft_active_genmask(table, genmask)) + nft_active_genmask(table, genmask)) { + if (nft_table_has_owner(table) && + nlpid && table->nlpid != nlpid) + return ERR_PTR(-EPERM); + return table; + } } return ERR_PTR(-ENOENT); @@ -532,14 +651,21 @@ static struct nft_table *nft_table_lookup(const struct net *net, static struct nft_table *nft_table_lookup_byhandle(const struct net *net, const struct nlattr *nla, - u8 genmask) + u8 genmask, u32 nlpid) { + struct nftables_pernet *nft_net; struct nft_table *table; - list_for_each_entry(table, &net->nft.tables, list) { + nft_net = nft_pernet(net); + list_for_each_entry(table, &nft_net->tables, list) { if (be64_to_cpu(nla_get_be64(nla)) == table->handle && - nft_active_genmask(table, genmask)) + nft_active_genmask(table, genmask)) { + if (nft_table_has_owner(table) && + nlpid && table->nlpid != nlpid) + return ERR_PTR(-EPERM); + return table; + } } return ERR_PTR(-ENOENT); @@ -585,9 +711,11 @@ struct nft_module_request { }; #ifdef CONFIG_MODULES -static int nft_request_module(struct net *net, const char *fmt, ...) +__printf(2, 3) int nft_request_module(struct net *net, const char *fmt, + ...) { char module_name[MODULE_NAME_LEN]; + struct nftables_pernet *nft_net; struct nft_module_request *req; va_list args; int ret; @@ -598,7 +726,8 @@ static int nft_request_module(struct net *net, const char *fmt, ...) if (ret >= MODULE_NAME_LEN) return 0; - list_for_each_entry(req, &net->nft.module_list, list) { + nft_net = nft_pernet(net); + list_for_each_entry(req, &nft_net->module_list, list) { if (!strcmp(req->module, module_name)) { if (req->done) return 0; @@ -613,17 +742,19 @@ static int nft_request_module(struct net *net, const char *fmt, ...) return -ENOMEM; req->done = false; - strlcpy(req->module, module_name, MODULE_NAME_LEN); - list_add_tail(&req->list, &net->nft.module_list); + strscpy(req->module, module_name, MODULE_NAME_LEN); + list_add_tail(&req->list, &nft_net->module_list); return -EAGAIN; } +EXPORT_SYMBOL_GPL(nft_request_module); #endif static void lockdep_nfnl_nft_mutex_not_held(void) { #ifdef CONFIG_PROVE_LOCKING - WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); + if (debug_locks) + WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); #endif } @@ -649,11 +780,20 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, return ERR_PTR(-ENOENT); } +static __be16 nft_base_seq(const struct net *net) +{ + struct nftables_pernet *nft_net = nft_pernet(net); + + return htons(nft_net->base_seq & 0xffff); +} + static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { [NFTA_TABLE_NAME] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_TABLE_FLAGS] = { .type = NLA_U32 }, [NFTA_TABLE_HANDLE] = { .type = NLA_U64 }, + [NFTA_TABLE_USERDATA] = { .type = NLA_BINARY, + .len = NFT_USERDATA_MAXLEN } }; static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, @@ -661,24 +801,28 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, int family, const struct nft_table *table) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) || - nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)) || + nla_put_be32(skb, NFTA_TABLE_FLAGS, + htonl(table->flags & NFT_TABLE_F_MASK)) || nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)) || nla_put_be64(skb, NFTA_TABLE_HANDLE, cpu_to_be64(table->handle), NFTA_TABLE_PAD)) goto nla_put_failure; + if (nft_table_has_owner(table) && + nla_put_be32(skb, NFTA_TABLE_OWNER, htonl(table->nlpid))) + goto nla_put_failure; + + if (table->udata) { + if (nla_put(skb, NFTA_TABLE_USERDATA, table->udlen, table->udata)) + goto nla_put_failure; + } nlmsg_end(skb, nlh); return 0; @@ -688,9 +832,23 @@ nla_put_failure: return -1; } +struct nftnl_skb_parms { + bool report; +}; +#define NFT_CB(skb) (*(struct nftnl_skb_parms*)&((skb)->cb)) + +static void nft_notify_enqueue(struct sk_buff *skb, bool report, + struct list_head *notify_list) +{ + NFT_CB(skb).report = report; + list_add_tail(&skb->list, notify_list); +} + static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) { + struct nftables_pernet *nft_net; struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && @@ -701,15 +859,18 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_table_info(skb, ctx->net, ctx->portid, ctx->seq, - event, 0, ctx->family, ctx->table); + event, flags, ctx->family, ctx->table); if (err < 0) { kfree_skb(skb); goto err; } - nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, - ctx->report, GFP_KERNEL); + nft_net = nft_pernet(ctx->net); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -719,15 +880,17 @@ static int nf_tables_dump_tables(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); + struct nftables_pernet *nft_net; const struct nft_table *table; unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = nft_pernet(net); + cb->seq = READ_ONCE(nft_net->base_seq); - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -773,28 +936,27 @@ static int nft_netlink_dump_start_rcu(struct sock *nlsk, struct sk_buff *skb, } /* called with rcu_read_lock held */ -static int nf_tables_gettable(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_gettable(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_cur(net); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_cur(info->net); + u8 family = info->nfmsg->nfgen_family; const struct nft_table *table; + struct net *net = info->net; struct sk_buff *skb2; - int family = nfmsg->nfgen_family; int err; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nf_tables_dump_tables, .module = THIS_MODULE, }; - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } - table = nft_table_lookup(net, nla[NFTA_TABLE_NAME], family, genmask); + table = nft_table_lookup(net, nla[NFTA_TABLE_NAME], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_TABLE_NAME]); return PTR_ERR(table); @@ -805,14 +967,14 @@ static int nf_tables_gettable(struct net *net, struct sock *nlsk, return -ENOMEM; err = nf_tables_fill_table_info(skb2, net, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, NFT_MSG_NEWTABLE, 0, - family, table); + info->nlh->nlmsg_seq, NFT_MSG_NEWTABLE, + 0, family, table); if (err < 0) - goto err; + goto err_fill_table_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_table_info: kfree_skb(skb2); return err; } @@ -831,8 +993,7 @@ static void nft_table_disable(struct net *net, struct nft_table *table, u32 cnt) if (cnt && i++ == cnt) break; - nft_unregister_basechain_hooks(net, table->family, - nft_base_chain(chain)); + nf_tables_unregister_hook(net, table, chain); } } @@ -847,8 +1008,7 @@ static int nf_tables_table_enable(struct net *net, struct nft_table *table) if (!nft_is_base_chain(chain)) continue; - err = nft_register_basechain_hooks(net, table->family, - nft_base_chain(chain)); + err = nf_tables_register_hook(net, table, chain); if (err < 0) goto err_register_hooks; @@ -864,25 +1024,39 @@ err_register_hooks: static void nf_tables_table_disable(struct net *net, struct nft_table *table) { + table->flags &= ~NFT_TABLE_F_DORMANT; nft_table_disable(net, table, 0); + table->flags |= NFT_TABLE_F_DORMANT; } +#define __NFT_TABLE_F_INTERNAL (NFT_TABLE_F_MASK + 1) +#define __NFT_TABLE_F_WAS_DORMANT (__NFT_TABLE_F_INTERNAL << 0) +#define __NFT_TABLE_F_WAS_AWAKEN (__NFT_TABLE_F_INTERNAL << 1) +#define __NFT_TABLE_F_UPDATE (__NFT_TABLE_F_WAS_DORMANT | \ + __NFT_TABLE_F_WAS_AWAKEN) + static int nf_tables_updtable(struct nft_ctx *ctx) { struct nft_trans *trans; u32 flags; - int ret = 0; + int ret; if (!ctx->nla[NFTA_TABLE_FLAGS]) return 0; flags = ntohl(nla_get_be32(ctx->nla[NFTA_TABLE_FLAGS])); - if (flags & ~NFT_TABLE_F_DORMANT) - return -EINVAL; + if (flags & ~NFT_TABLE_F_MASK) + return -EOPNOTSUPP; if (flags == ctx->table->flags) return 0; + if ((nft_table_has_owner(ctx->table) && + !(flags & NFT_TABLE_F_OWNER)) || + (!nft_table_has_owner(ctx->table) && + flags & NFT_TABLE_F_OWNER)) + return -EOPNOTSUPP; + trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, sizeof(struct nft_trans_table)); if (trans == NULL) @@ -890,22 +1064,27 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if ((flags & NFT_TABLE_F_DORMANT) && !(ctx->table->flags & NFT_TABLE_F_DORMANT)) { - nft_trans_table_enable(trans) = false; + ctx->table->flags |= NFT_TABLE_F_DORMANT; + if (!(ctx->table->flags & __NFT_TABLE_F_UPDATE)) + ctx->table->flags |= __NFT_TABLE_F_WAS_AWAKEN; } else if (!(flags & NFT_TABLE_F_DORMANT) && ctx->table->flags & NFT_TABLE_F_DORMANT) { - ret = nf_tables_table_enable(ctx->net, ctx->table); - if (ret >= 0) { - ctx->table->flags &= ~NFT_TABLE_F_DORMANT; - nft_trans_table_enable(trans) = true; + ctx->table->flags &= ~NFT_TABLE_F_DORMANT; + if (!(ctx->table->flags & __NFT_TABLE_F_UPDATE)) { + ret = nf_tables_table_enable(ctx->net, ctx->table); + if (ret < 0) + goto err_register_hooks; + + ctx->table->flags |= __NFT_TABLE_F_WAS_DORMANT; } } - if (ret < 0) - goto err; nft_trans_table_update(trans) = true; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); + return 0; -err: + +err_register_hooks: nft_trans_destroy(trans); return ret; } @@ -961,53 +1140,90 @@ static int nft_objname_hash_cmp(struct rhashtable_compare_arg *arg, return strcmp(obj->key.name, k->name); } -static int nf_tables_newtable(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static bool nft_supported_family(u8 family) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); - int family = nfmsg->nfgen_family; + return false +#ifdef CONFIG_NF_TABLES_INET + || family == NFPROTO_INET +#endif +#ifdef CONFIG_NF_TABLES_IPV4 + || family == NFPROTO_IPV4 +#endif +#ifdef CONFIG_NF_TABLES_ARP + || family == NFPROTO_ARP +#endif +#ifdef CONFIG_NF_TABLES_NETDEV + || family == NFPROTO_NETDEV +#endif +#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) + || family == NFPROTO_BRIDGE +#endif +#ifdef CONFIG_NF_TABLES_IPV6 + || family == NFPROTO_IPV6 +#endif + ; +} + +static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct nftables_pernet *nft_net = nft_pernet(info->net); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; + struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; - u32 flags = 0; struct nft_ctx ctx; + u32 flags = 0; int err; - lockdep_assert_held(&net->nft.commit_mutex); + if (!nft_supported_family(family)) + return -EOPNOTSUPP; + + lockdep_assert_held(&nft_net->commit_mutex); attr = nla[NFTA_TABLE_NAME]; - table = nft_table_lookup(net, attr, family, genmask); + table = nft_table_lookup(net, attr, family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { if (PTR_ERR(table) != -ENOENT) return PTR_ERR(table); } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) { + if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } - if (nlh->nlmsg_flags & NLM_F_REPLACE) + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + return nf_tables_updtable(&ctx); } if (nla[NFTA_TABLE_FLAGS]) { flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS])); - if (flags & ~NFT_TABLE_F_DORMANT) - return -EINVAL; + if (flags & ~NFT_TABLE_F_MASK) + return -EOPNOTSUPP; } err = -ENOMEM; - table = kzalloc(sizeof(*table), GFP_KERNEL); + table = kzalloc(sizeof(*table), GFP_KERNEL_ACCOUNT); if (table == NULL) goto err_kzalloc; - table->name = nla_strdup(attr, GFP_KERNEL); + table->name = nla_strdup(attr, GFP_KERNEL_ACCOUNT); if (table->name == NULL) goto err_strdup; + if (nla[NFTA_TABLE_USERDATA]) { + table->udata = nla_memdup(nla[NFTA_TABLE_USERDATA], GFP_KERNEL_ACCOUNT); + if (table->udata == NULL) + goto err_table_udata; + + table->udlen = nla_len(nla[NFTA_TABLE_USERDATA]); + } + err = rhltable_init(&table->chains_ht, &nft_chain_ht_params); if (err) goto err_chain_ht; @@ -1018,18 +1234,22 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, INIT_LIST_HEAD(&table->flowtables); table->family = family; table->flags = flags; - table->handle = ++table_handle; + table->handle = ++nft_net->table_handle; + if (table->flags & NFT_TABLE_F_OWNER) + table->nlpid = NETLINK_CB(skb).portid; - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE); if (err < 0) goto err_trans; - list_add_tail_rcu(&table->list, &net->nft.tables); + list_add_tail_rcu(&table->list, &nft_net->tables); return 0; err_trans: rhltable_destroy(&table->chains_ht); err_chain_ht: + kfree(table->udata); +err_table_udata: kfree(table->name); err_strdup: kfree(table); @@ -1049,6 +1269,9 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; + if (nft_chain_is_bound(chain)) + continue; + ctx->chain = chain; err = nft_delrule_by_chain(ctx); @@ -1091,6 +1314,9 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; + if (nft_chain_is_bound(chain)) + continue; + ctx->chain = chain; err = nft_delchain(ctx); @@ -1105,11 +1331,12 @@ out: static int nft_flush(struct nft_ctx *ctx, int family) { - struct nft_table *table, *nt; + struct nftables_pernet *nft_net = nft_pernet(ctx->net); const struct nlattr * const *nla = ctx->nla; + struct nft_table *table, *nt; int err = 0; - list_for_each_entry_safe(table, nt, &ctx->net->nft.tables, list) { + list_for_each_entry_safe(table, nt, &nft_net->tables, list) { if (family != AF_UNSPEC && table->family != family) continue; @@ -1118,6 +1345,9 @@ static int nft_flush(struct nft_ctx *ctx, int family) if (!nft_is_active_next(ctx->net, table)) continue; + if (nft_table_has_owner(table) && table->nlpid != ctx->portid) + continue; + if (nla[NFTA_TABLE_NAME] && nla_strcmp(nla[NFTA_TABLE_NAME], table->name) != 0) continue; @@ -1132,29 +1362,30 @@ out: return err; } -static int nf_tables_deltable(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); - int family = nfmsg->nfgen_family; + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; + struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_ctx ctx; - nft_ctx_init(&ctx, net, skb, nlh, 0, NULL, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, 0, NULL, NULL, nla); if (family == AF_UNSPEC || (!nla[NFTA_TABLE_NAME] && !nla[NFTA_TABLE_HANDLE])) return nft_flush(&ctx, family); if (nla[NFTA_TABLE_HANDLE]) { attr = nla[NFTA_TABLE_HANDLE]; - table = nft_table_lookup_byhandle(net, attr, genmask); + table = nft_table_lookup_byhandle(net, attr, genmask, + NETLINK_CB(skb).portid); } else { attr = nla[NFTA_TABLE_NAME]; - table = nft_table_lookup(net, attr, family, genmask); + table = nft_table_lookup(net, attr, family, genmask, + NETLINK_CB(skb).portid); } if (IS_ERR(table)) { @@ -1162,7 +1393,7 @@ static int nf_tables_deltable(struct net *net, struct sock *nlsk, return PTR_ERR(table); } - if (nlh->nlmsg_flags & NLM_F_NONREC && + if (info->nlh->nlmsg_flags & NLM_F_NONREC && table->use > 0) return -EBUSY; @@ -1179,6 +1410,7 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx) rhltable_destroy(&ctx->table->chains_ht); kfree(ctx->table->name); + kfree(ctx->table->udata); kfree(ctx->table); } @@ -1223,7 +1455,9 @@ nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask) static bool lockdep_commit_lock_is_held(const struct net *net) { #ifdef CONFIG_PROVE_LOCKING - return lockdep_is_held(&net->nft.commit_mutex); + struct nftables_pernet *nft_net = nft_pernet(net); + + return lockdep_is_held(&nft_net->commit_mutex); #else return true; #endif @@ -1240,7 +1474,7 @@ static struct nft_chain *nft_chain_lookup(struct net *net, if (nla == NULL) return ERR_PTR(-EINVAL); - nla_strlcpy(search, nla, sizeof(search)); + nla_strscpy(search, nla, sizeof(search)); WARN_ON(!rcu_read_lock_held() && !lockdep_commit_lock_is_held(net)); @@ -1273,6 +1507,9 @@ static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = { .len = NFT_MODULE_AUTOLOAD_LIMIT }, [NFTA_CHAIN_COUNTERS] = { .type = NLA_NESTED }, [NFTA_CHAIN_FLAGS] = { .type = NLA_U32 }, + [NFTA_CHAIN_ID] = { .type = NLA_U32 }, + [NFTA_CHAIN_USERDATA] = { .type = NLA_BINARY, + .len = NFT_USERDATA_MAXLEN }, }; static const struct nla_policy nft_hook_policy[NFTA_HOOK_MAX + 1] = { @@ -1337,7 +1574,7 @@ static int nft_dump_basechain_hook(struct sk_buff *skb, int family, if (nla_put_be32(skb, NFTA_HOOK_PRIORITY, htonl(ops->priority))) goto nla_put_failure; - if (family == NFPROTO_NETDEV) { + if (nft_base_chain_netdev(family, ops->hooknum)) { nest_devs = nla_nest_start_noflag(skb, NFTA_HOOK_DEVS); list_for_each_entry(hook, &basechain->hook_list, list) { if (!first) @@ -1367,18 +1604,13 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, const struct nft_chain *chain) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_CHAIN_TABLE, table->name)) goto nla_put_failure; if (nla_put_be64(skb, NFTA_CHAIN_HANDLE, cpu_to_be64(chain->handle), @@ -1405,16 +1637,19 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, lockdep_commit_lock_is_held(net)); if (nft_dump_stats(skb, stats)) goto nla_put_failure; - - if ((chain->flags & NFT_CHAIN_HW_OFFLOAD) && - nla_put_be32(skb, NFTA_CHAIN_FLAGS, - htonl(NFT_CHAIN_HW_OFFLOAD))) - goto nla_put_failure; } + if (chain->flags && + nla_put_be32(skb, NFTA_CHAIN_FLAGS, htonl(chain->flags))) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use))) goto nla_put_failure; + if (chain->udata && + nla_put(skb, NFTA_CHAIN_USERDATA, chain->udlen, chain->udata)) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; @@ -1425,7 +1660,9 @@ nla_put_failure: static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) { + struct nftables_pernet *nft_net; struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && @@ -1436,16 +1673,19 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_chain_info(skb, ctx->net, ctx->portid, ctx->seq, - event, 0, ctx->family, ctx->table, + event, flags, ctx->family, ctx->table, ctx->chain); if (err < 0) { kfree_skb(skb); goto err; } - nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, - ctx->report, GFP_KERNEL); + nft_net = nft_pernet(ctx->net); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -1455,16 +1695,18 @@ static int nf_tables_dump_chains(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); - const struct nft_table *table; - const struct nft_chain *chain; unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net; + const struct nft_table *table; + const struct nft_chain *chain; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = nft_pernet(net); + cb->seq = READ_ONCE(nft_net->base_seq); - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -1497,29 +1739,28 @@ done: } /* called with rcu_read_lock held */ -static int nf_tables_getchain(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_getchain(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_cur(net); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_cur(info->net); + u8 family = info->nfmsg->nfgen_family; const struct nft_chain *chain; + struct net *net = info->net; struct nft_table *table; struct sk_buff *skb2; - int family = nfmsg->nfgen_family; int err; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nf_tables_dump_chains, .module = THIS_MODULE, }; - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } - table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); @@ -1536,14 +1777,14 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk, return -ENOMEM; err = nf_tables_fill_chain_info(skb2, net, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, 0, - family, table, chain); + info->nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, + 0, family, table, chain); if (err < 0) - goto err; + goto err_fill_chain_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_chain_info: kfree_skb(skb2); return err; } @@ -1601,19 +1842,19 @@ static void nft_chain_stats_replace(struct nft_trans *trans) static void nf_tables_chain_free_chain_rules(struct nft_chain *chain) { - struct nft_rule **g0 = rcu_dereference_raw(chain->rules_gen_0); - struct nft_rule **g1 = rcu_dereference_raw(chain->rules_gen_1); + struct nft_rule_blob *g0 = rcu_dereference_raw(chain->blob_gen_0); + struct nft_rule_blob *g1 = rcu_dereference_raw(chain->blob_gen_1); if (g0 != g1) kvfree(g1); kvfree(g0); /* should be NULL either via abort or via successful commit */ - WARN_ON_ONCE(chain->rules_next); - kvfree(chain->rules_next); + WARN_ON_ONCE(chain->blob_next); + kvfree(chain->blob_next); } -static void nf_tables_chain_destroy(struct nft_ctx *ctx) +void nf_tables_chain_destroy(struct nft_ctx *ctx) { struct nft_chain *chain = ctx->chain; struct nft_hook *hook, *next; @@ -1627,7 +1868,7 @@ static void nf_tables_chain_destroy(struct nft_ctx *ctx) if (nft_is_base_chain(chain)) { struct nft_base_chain *basechain = nft_base_chain(chain); - if (ctx->family == NFPROTO_NETDEV) { + if (nft_base_chain_netdev(ctx->family, basechain->ops.hooknum)) { list_for_each_entry_safe(hook, next, &basechain->hook_list, list) { list_del_rcu(&hook->list); @@ -1640,9 +1881,11 @@ static void nf_tables_chain_destroy(struct nft_ctx *ctx) free_percpu(rcu_dereference_raw(basechain->stats)); } kfree(chain->name); + kfree(chain->udata); kfree(basechain); } else { kfree(chain->name); + kfree(chain->udata); kfree(chain); } } @@ -1655,13 +1898,17 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net, struct nft_hook *hook; int err; - hook = kmalloc(sizeof(struct nft_hook), GFP_KERNEL); + hook = kmalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT); if (!hook) { err = -ENOMEM; goto err_hook_alloc; } - nla_strlcpy(ifname, attr, IFNAMSIZ); + nla_strscpy(ifname, attr, IFNAMSIZ); + /* nf_tables_netdev_event() is called under rtnl_mutex, this is + * indirectly serializing all the other holders of the commit_mutex with + * the rtnl_mutex. + */ dev = __dev_get_by_name(net, ifname); if (!dev) { err = -ENOENT; @@ -1677,17 +1924,17 @@ err_hook_alloc: return ERR_PTR(err); } -static bool nft_hook_list_find(struct list_head *hook_list, - const struct nft_hook *this) +static struct nft_hook *nft_hook_list_find(struct list_head *hook_list, + const struct nft_hook *this) { struct nft_hook *hook; list_for_each_entry(hook, hook_list, list) { if (this->ops.dev == hook->ops.dev) - return true; + return hook; } - return false; + return NULL; } static int nf_tables_parse_netdev_hooks(struct net *net, @@ -1722,8 +1969,6 @@ static int nf_tables_parse_netdev_hooks(struct net *net, goto err_hook; } } - if (!n) - return -EINVAL; return 0; @@ -1760,6 +2005,9 @@ static int nft_chain_parse_netdev(struct net *net, hook_list); if (err < 0) return err; + + if (list_empty(hook_list)) + return -EINVAL; } else { return -EINVAL; } @@ -1770,13 +2018,14 @@ static int nft_chain_parse_netdev(struct net *net, static int nft_chain_parse_hook(struct net *net, const struct nlattr * const nla[], struct nft_chain_hook *hook, u8 family, - bool autoload) + struct netlink_ext_ack *extack, bool autoload) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nlattr *ha[NFTA_HOOK_MAX + 1]; const struct nft_chain_type *type; int err; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); lockdep_nfnl_nft_mutex_not_held(); err = nla_parse_nested_deprecated(ha, NFTA_HOOK_MAX, @@ -1799,23 +2048,28 @@ static int nft_chain_parse_hook(struct net *net, if (nla[NFTA_CHAIN_TYPE]) { type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE], family, autoload); - if (IS_ERR(type)) + if (IS_ERR(type)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TYPE]); return PTR_ERR(type); + } } - if (hook->num > NF_MAX_HOOKS || !(type->hook_mask & (1 << hook->num))) + if (hook->num >= NFT_MAX_HOOKS || !(type->hook_mask & (1 << hook->num))) return -EOPNOTSUPP; if (type->type == NFT_CHAIN_T_NAT && hook->priority <= NF_IP_PRI_CONNTRACK) return -EOPNOTSUPP; - if (!try_module_get(type->owner)) + if (!try_module_get(type->owner)) { + if (nla[NFTA_CHAIN_TYPE]) + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TYPE]); return -ENOENT; + } hook->type = type; INIT_LIST_HEAD(&hook->list); - if (family == NFPROTO_NETDEV) { + if (nft_base_chain_netdev(family, hook->num)) { err = nft_chain_parse_netdev(net, ha, &hook->list); if (err < 0) { module_put(type->owner); @@ -1842,34 +2096,50 @@ static void nft_chain_release_hook(struct nft_chain_hook *hook) struct nft_rules_old { struct rcu_head h; - struct nft_rule **start; + struct nft_rule_blob *blob; }; -static struct nft_rule **nf_tables_chain_alloc_rules(const struct nft_chain *chain, - unsigned int alloc) +static void nft_last_rule(struct nft_rule_blob *blob, const void *ptr) { - if (alloc > INT_MAX) + struct nft_rule_dp *prule; + + prule = (struct nft_rule_dp *)ptr; + prule->is_last = 1; + /* blob size does not include the trailer rule */ +} + +static struct nft_rule_blob *nf_tables_chain_alloc_rules(unsigned int size) +{ + struct nft_rule_blob *blob; + + /* size must include room for the last rule */ + if (size < offsetof(struct nft_rule_dp, data)) + return NULL; + + size += sizeof(struct nft_rule_blob) + sizeof(struct nft_rules_old); + if (size > INT_MAX) return NULL; - alloc += 1; /* NULL, ends rules */ - if (sizeof(struct nft_rule *) > INT_MAX / alloc) + blob = kvmalloc(size, GFP_KERNEL_ACCOUNT); + if (!blob) return NULL; - alloc *= sizeof(struct nft_rule *); - alloc += sizeof(struct nft_rules_old); + blob->size = 0; + nft_last_rule(blob, blob->data); - return kvmalloc(alloc, GFP_KERNEL); + return blob; } static void nft_basechain_hook_init(struct nf_hook_ops *ops, u8 family, const struct nft_chain_hook *hook, struct nft_chain *chain) { - ops->pf = family; - ops->hooknum = hook->num; - ops->priority = hook->priority; - ops->priv = chain; - ops->hook = hook->type->hooks[ops->hooknum]; + ops->pf = family; + ops->hooknum = hook->num; + ops->priority = hook->priority; + ops->priv = chain; + ops->hook = hook->type->hooks[ops->hooknum]; + ops->hook_ops_type = NF_HOOK_OP_NF_TABLES; } static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, @@ -1882,7 +2152,7 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, INIT_LIST_HEAD(&basechain->hook_list); chain = &basechain->chain; - if (family == NFPROTO_NETDEV) { + if (nft_base_chain_netdev(family, hook->num)) { list_splice_init(&hook->list, &basechain->hook_list); list_for_each_entry(h, &basechain->hook_list, list) nft_basechain_hook_init(&h->ops, family, hook, chain); @@ -1893,41 +2163,66 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, nft_basechain_hook_init(&basechain->ops, family, hook, chain); } - chain->flags |= NFT_BASE_CHAIN | flags; + chain->flags |= NFT_CHAIN_BASE | flags; basechain->policy = NF_ACCEPT; if (chain->flags & NFT_CHAIN_HW_OFFLOAD && - nft_chain_offload_priority(basechain) < 0) + !nft_chain_offload_support(basechain)) { + list_splice_init(&basechain->hook_list, &hook->list); return -EOPNOTSUPP; + } flow_block_init(&basechain->flow_block); return 0; } +static int nft_chain_add(struct nft_table *table, struct nft_chain *chain) +{ + int err; + + err = rhltable_insert_key(&table->chains_ht, chain->name, + &chain->rhlhead, nft_chain_ht_params); + if (err) + return err; + + list_add_tail_rcu(&chain->list, &table->chains); + + return 0; +} + +static u64 chain_id; + static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, - u8 policy, u32 flags) + u8 policy, u32 flags, + struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_table *table = ctx->table; struct nft_base_chain *basechain; - struct nft_stats __percpu *stats; struct net *net = ctx->net; + char name[NFT_NAME_MAXLEN]; + struct nft_rule_blob *blob; struct nft_trans *trans; struct nft_chain *chain; - struct nft_rule **rules; + unsigned int data_size; int err; if (table->use == UINT_MAX) return -EOVERFLOW; if (nla[NFTA_CHAIN_HOOK]) { + struct nft_stats __percpu *stats = NULL; struct nft_chain_hook hook; - err = nft_chain_parse_hook(net, nla, &hook, family, true); + if (flags & NFT_CHAIN_BINDING) + return -EOPNOTSUPP; + + err = nft_chain_parse_hook(net, nla, &hook, family, extack, + true); if (err < 0) return err; - basechain = kzalloc(sizeof(*basechain), GFP_KERNEL); + basechain = kzalloc(sizeof(*basechain), GFP_KERNEL_ACCOUNT); if (basechain == NULL) { nft_chain_release_hook(&hook); return -ENOMEM; @@ -1942,69 +2237,97 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, return PTR_ERR(stats); } rcu_assign_pointer(basechain->stats, stats); - static_branch_inc(&nft_counters_enabled); } err = nft_basechain_init(basechain, family, &hook, flags); if (err < 0) { nft_chain_release_hook(&hook); kfree(basechain); + free_percpu(stats); return err; } + if (stats) + static_branch_inc(&nft_counters_enabled); } else { - chain = kzalloc(sizeof(*chain), GFP_KERNEL); + if (flags & NFT_CHAIN_BASE) + return -EINVAL; + if (flags & NFT_CHAIN_HW_OFFLOAD) + return -EOPNOTSUPP; + + chain = kzalloc(sizeof(*chain), GFP_KERNEL_ACCOUNT); if (chain == NULL) return -ENOMEM; + + chain->flags = flags; } ctx->chain = chain; INIT_LIST_HEAD(&chain->rules); chain->handle = nf_tables_alloc_handle(table); chain->table = table; - chain->name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL); + + if (nla[NFTA_CHAIN_NAME]) { + chain->name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL_ACCOUNT); + } else { + if (!(flags & NFT_CHAIN_BINDING)) { + err = -EINVAL; + goto err_destroy_chain; + } + + snprintf(name, sizeof(name), "__chain%llu", ++chain_id); + chain->name = kstrdup(name, GFP_KERNEL_ACCOUNT); + } + if (!chain->name) { err = -ENOMEM; - goto err1; + goto err_destroy_chain; + } + + if (nla[NFTA_CHAIN_USERDATA]) { + chain->udata = nla_memdup(nla[NFTA_CHAIN_USERDATA], GFP_KERNEL_ACCOUNT); + if (chain->udata == NULL) { + err = -ENOMEM; + goto err_destroy_chain; + } + chain->udlen = nla_len(nla[NFTA_CHAIN_USERDATA]); } - rules = nf_tables_chain_alloc_rules(chain, 0); - if (!rules) { + data_size = offsetof(struct nft_rule_dp, data); /* last rule */ + blob = nf_tables_chain_alloc_rules(data_size); + if (!blob) { err = -ENOMEM; - goto err1; + goto err_destroy_chain; } - *rules = NULL; - rcu_assign_pointer(chain->rules_gen_0, rules); - rcu_assign_pointer(chain->rules_gen_1, rules); + RCU_INIT_POINTER(chain->blob_gen_0, blob); + RCU_INIT_POINTER(chain->blob_gen_1, blob); err = nf_tables_register_hook(net, table, chain); if (err < 0) - goto err1; - - err = rhltable_insert_key(&table->chains_ht, chain->name, - &chain->rhlhead, nft_chain_ht_params); - if (err) - goto err2; + goto err_destroy_chain; trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (IS_ERR(trans)) { err = PTR_ERR(trans); - rhltable_remove(&table->chains_ht, &chain->rhlhead, - nft_chain_ht_params); - goto err2; + goto err_unregister_hook; } nft_trans_chain_policy(trans) = NFT_CHAIN_POLICY_UNSET; if (nft_is_base_chain(chain)) nft_trans_chain_policy(trans) = policy; + err = nft_chain_add(table, chain); + if (err < 0) { + nft_trans_destroy(trans); + goto err_unregister_hook; + } + table->use++; - list_add_tail_rcu(&chain->list, &table->chains); return 0; -err2: +err_unregister_hook: nf_tables_unregister_hook(net, table, chain); -err1: +err_destroy_chain: nf_tables_chain_destroy(ctx); return err; @@ -2030,7 +2353,8 @@ static bool nft_hook_list_equal(struct list_head *hook_list1, } static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, - u32 flags) + u32 flags, const struct nlattr *attr, + struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_table *table = ctx->table; @@ -2046,32 +2370,36 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, return -EOPNOTSUPP; if (nla[NFTA_CHAIN_HOOK]) { - if (!nft_is_base_chain(chain)) - return -EBUSY; - + if (!nft_is_base_chain(chain)) { + NL_SET_BAD_ATTR(extack, attr); + return -EEXIST; + } err = nft_chain_parse_hook(ctx->net, nla, &hook, ctx->family, - false); + extack, false); if (err < 0) return err; basechain = nft_base_chain(chain); if (basechain->type != hook.type) { nft_chain_release_hook(&hook); - return -EBUSY; + NL_SET_BAD_ATTR(extack, attr); + return -EEXIST; } - if (ctx->family == NFPROTO_NETDEV) { + if (nft_base_chain_netdev(ctx->family, hook.num)) { if (!nft_hook_list_equal(&basechain->hook_list, &hook.list)) { nft_chain_release_hook(&hook); - return -EBUSY; + NL_SET_BAD_ATTR(extack, attr); + return -EEXIST; } } else { ops = &basechain->ops; if (ops->hooknum != hook.num || ops->priority != hook.priority) { nft_chain_release_hook(&hook); - return -EBUSY; + NL_SET_BAD_ATTR(extack, attr); + return -EEXIST; } } nft_chain_release_hook(&hook); @@ -2083,8 +2411,10 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, chain2 = nft_chain_lookup(ctx->net, table, nla[NFTA_CHAIN_NAME], genmask); - if (!IS_ERR(chain2)) + if (!IS_ERR(chain2)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); return -EEXIST; + } } if (nla[NFTA_CHAIN_COUNTERS]) { @@ -2112,21 +2442,23 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, if (nla[NFTA_CHAIN_HANDLE] && nla[NFTA_CHAIN_NAME]) { + struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct nft_trans *tmp; char *name; err = -ENOMEM; - name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL); + name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL_ACCOUNT); if (!name) goto err; err = -EEXIST; - list_for_each_entry(tmp, &ctx->net->nft.commit_list, list) { + list_for_each_entry(tmp, &nft_net->commit_list, list) { if (tmp->msg_type == NFT_MSG_NEWCHAIN && tmp->ctx.table == table && nft_trans_chain_update(tmp) && nft_trans_chain_name(tmp) && strcmp(name, nft_trans_chain_name(tmp)) == 0) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); kfree(name); goto err; } @@ -2134,7 +2466,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, nft_trans_chain_name(trans) = name; } - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err: @@ -2143,25 +2475,45 @@ err: return err; } -static int nf_tables_newchain(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static struct nft_chain *nft_chain_lookup_byid(const struct net *net, + const struct nft_table *table, + const struct nlattr *nla) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); - int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net = nft_pernet(net); + u32 id = ntohl(nla_get_be32(nla)); + struct nft_trans *trans; + + list_for_each_entry(trans, &nft_net->commit_list, list) { + struct nft_chain *chain = trans->ctx.chain; + + if (trans->msg_type == NFT_MSG_NEWCHAIN && + chain->table == table && + id == nft_trans_chain_id(trans)) + return chain; + } + return ERR_PTR(-ENOENT); +} + +static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct nftables_pernet *nft_net = nft_pernet(info->net); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; + struct nft_chain *chain = NULL; + struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; - struct nft_chain *chain; u8 policy = NF_ACCEPT; struct nft_ctx ctx; u64 handle = 0; u32 flags = 0; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); - table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); @@ -2178,7 +2530,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, return PTR_ERR(chain); } attr = nla[NFTA_CHAIN_HANDLE]; - } else { + } else if (nla[NFTA_CHAIN_NAME]) { chain = nft_chain_lookup(net, table, attr, genmask); if (IS_ERR(chain)) { if (PTR_ERR(chain) != -ENOENT) { @@ -2187,6 +2539,8 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, } chain = NULL; } + } else if (!nla[NFTA_CHAIN_ID]) { + return -EINVAL; } if (nla[NFTA_CHAIN_POLICY]) { @@ -2217,31 +2571,37 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, else if (chain) flags = chain->flags; - nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); + if (flags & ~NFT_CHAIN_FLAGS) + return -EOPNOTSUPP; + + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (chain != NULL) { - if (nlh->nlmsg_flags & NLM_F_EXCL) { + if (chain->flags & NFT_CHAIN_BINDING) + return -EINVAL; + + if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } - if (nlh->nlmsg_flags & NLM_F_REPLACE) + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - flags |= chain->flags & NFT_BASE_CHAIN; - return nf_tables_updchain(&ctx, genmask, policy, flags); + flags |= chain->flags & NFT_CHAIN_BASE; + return nf_tables_updchain(&ctx, genmask, policy, flags, attr, + extack); } - return nf_tables_addchain(&ctx, family, genmask, policy, flags); + return nf_tables_addchain(&ctx, family, genmask, policy, flags, extack); } -static int nf_tables_delchain(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); - int family = nfmsg->nfgen_family; + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; + struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_chain *chain; @@ -2251,7 +2611,8 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, u32 use; int err; - table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); @@ -2270,11 +2631,11 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, return PTR_ERR(chain); } - if (nlh->nlmsg_flags & NLM_F_NONREC && + if (info->nlh->nlmsg_flags & NLM_F_NONREC && chain->use > 0) return -EBUSY; - nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); use = chain->use; list_for_each_entry(rule, &chain->rules, list) { @@ -2304,7 +2665,7 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, /** * nft_register_expr - register nf_tables expr type - * @ops: expr type + * @type: expr type * * Registers the expr type for use with nf_tables. Returns zero on * success or a negative errno code otherwise. @@ -2323,7 +2684,7 @@ EXPORT_SYMBOL_GPL(nft_register_expr); /** * nft_unregister_expr - unregister nf_tables expr type - * @ops: expr type + * @type: expr type * * Unregisters the expr typefor use with nf_tables. */ @@ -2438,6 +2799,7 @@ nla_put_failure: struct nft_expr_info { const struct nft_expr_ops *ops; + const struct nlattr *attr; struct nlattr *tb[NFT_EXPR_MAXATTR + 1]; }; @@ -2485,7 +2847,9 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx, } else ops = type->ops; + info->attr = nla; info->ops = ops; + return 0; err1: @@ -2494,15 +2858,15 @@ err1: } static int nf_tables_newexpr(const struct nft_ctx *ctx, - const struct nft_expr_info *info, + const struct nft_expr_info *expr_info, struct nft_expr *expr) { - const struct nft_expr_ops *ops = info->ops; + const struct nft_expr_ops *ops = expr_info->ops; int err; expr->ops = ops; if (ops->init) { - err = ops->init(ctx, expr, (const struct nlattr **)info->tb); + err = ops->init(ctx, expr, (const struct nlattr **)expr_info->tb); if (err < 0) goto err1; } @@ -2523,40 +2887,62 @@ static void nf_tables_expr_destroy(const struct nft_ctx *ctx, module_put(type->owner); } -struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, - const struct nlattr *nla) +static struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, + const struct nlattr *nla) { - struct nft_expr_info info; + struct nft_expr_info expr_info; struct nft_expr *expr; struct module *owner; int err; - err = nf_tables_expr_parse(ctx, nla, &info); + err = nf_tables_expr_parse(ctx, nla, &expr_info); if (err < 0) - goto err1; + goto err_expr_parse; + + err = -EOPNOTSUPP; + if (!(expr_info.ops->type->flags & NFT_EXPR_STATEFUL)) + goto err_expr_stateful; err = -ENOMEM; - expr = kzalloc(info.ops->size, GFP_KERNEL); + expr = kzalloc(expr_info.ops->size, GFP_KERNEL_ACCOUNT); if (expr == NULL) - goto err2; + goto err_expr_stateful; - err = nf_tables_newexpr(ctx, &info, expr); + err = nf_tables_newexpr(ctx, &expr_info, expr); if (err < 0) - goto err3; + goto err_expr_new; return expr; -err3: +err_expr_new: kfree(expr); -err2: - owner = info.ops->type->owner; - if (info.ops->type->release_ops) - info.ops->type->release_ops(info.ops); +err_expr_stateful: + owner = expr_info.ops->type->owner; + if (expr_info.ops->type->release_ops) + expr_info.ops->type->release_ops(expr_info.ops); module_put(owner); -err1: +err_expr_parse: return ERR_PTR(err); } +int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) +{ + int err; + + if (src->ops->clone) { + dst->ops = src->ops; + err = src->ops->clone(dst, src); + if (err < 0) + return err; + } else { + memcpy(dst, src, src->ops->size); + } + + __module_get(src->ops->type->owner); + + return 0; +} + void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr) { nf_tables_expr_destroy(ctx, expr); @@ -2603,6 +2989,7 @@ static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = { .len = NFT_USERDATA_MAXLEN }, [NFTA_RULE_ID] = { .type = NLA_U32 }, [NFTA_RULE_POSITION_ID] = { .type = NLA_U32 }, + [NFTA_RULE_CHAIN_ID] = { .type = NLA_U32 }, }; static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, @@ -2610,24 +2997,18 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, u32 flags, int family, const struct nft_table *table, const struct nft_chain *chain, - const struct nft_rule *rule, - const struct nft_rule *prule) + const struct nft_rule *rule, u64 handle) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; const struct nft_expr *expr, *next; struct nlattr *list; u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, type, sizeof(struct nfgenmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, type, flags, family, NFNETLINK_V0, + nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_RULE_TABLE, table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_RULE_CHAIN, chain->name)) @@ -2636,13 +3017,15 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, NFTA_RULE_PAD)) goto nla_put_failure; - if (event != NFT_MSG_DELRULE && prule) { - if (nla_put_be64(skb, NFTA_RULE_POSITION, - cpu_to_be64(prule->handle), + if (event != NFT_MSG_DELRULE && handle) { + if (nla_put_be64(skb, NFTA_RULE_POSITION, cpu_to_be64(handle), NFTA_RULE_PAD)) goto nla_put_failure; } + if (chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_stats(chain, rule); + list = nla_nest_start_noflag(skb, NFTA_RULE_EXPRESSIONS); if (list == NULL) goto nla_put_failure; @@ -2670,7 +3053,11 @@ nla_put_failure: static void nf_tables_rule_notify(const struct nft_ctx *ctx, const struct nft_rule *rule, int event) { + struct nftables_pernet *nft_net = nft_pernet(ctx->net); + const struct nft_rule *prule; struct sk_buff *skb; + u64 handle = 0; + u16 flags = 0; int err; if (!ctx->report && @@ -2681,16 +3068,26 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx, if (skb == NULL) goto err; + if (event == NFT_MSG_NEWRULE && + !list_is_first(&rule->list, &ctx->chain->rules) && + !list_is_last(&rule->list, &ctx->chain->rules)) { + prule = list_prev_entry(rule, list); + handle = prule->handle; + } + if (ctx->flags & (NLM_F_APPEND | NLM_F_REPLACE)) + flags |= NLM_F_APPEND; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_rule_info(skb, ctx->net, ctx->portid, ctx->seq, - event, 0, ctx->family, ctx->table, - ctx->chain, rule, NULL); + event, flags, ctx->family, ctx->table, + ctx->chain, rule, handle); if (err < 0) { kfree_skb(skb); goto err; } - nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, - ctx->report, GFP_KERNEL); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -2710,6 +3107,7 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, struct net *net = sock_net(skb->sk); const struct nft_rule *rule, *prule; unsigned int s_idx = cb->args[0]; + u64 handle; prule = NULL; list_for_each_entry_rcu(rule, &chain->rules, list) { @@ -2721,12 +3119,17 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); } + if (prule) + handle = prule->handle; + else + handle = 0; + if (nf_tables_fill_rule_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFT_MSG_NEWRULE, NLM_F_MULTI | NLM_F_APPEND, table->family, - table, chain, rule, prule) < 0) + table, chain, rule, handle) < 0) return 1; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -2748,11 +3151,13 @@ static int nf_tables_dump_rules(struct sk_buff *skb, unsigned int idx = 0; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = nft_pernet(net); + cb->seq = READ_ONCE(nft_net->base_seq); - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -2838,21 +3243,20 @@ static int nf_tables_dump_rules_done(struct netlink_callback *cb) } /* called with rcu_read_lock held */ -static int nf_tables_getrule(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_cur(net); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_cur(info->net); + u8 family = info->nfmsg->nfgen_family; const struct nft_chain *chain; const struct nft_rule *rule; + struct net *net = info->net; struct nft_table *table; struct sk_buff *skb2; - int family = nfmsg->nfgen_family; int err; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start= nf_tables_dump_rules_start, .dump = nf_tables_dump_rules, @@ -2861,10 +3265,10 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, .data = (void *)nla, }; - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } - table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); @@ -2887,14 +3291,14 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, return -ENOMEM; err = nf_tables_fill_rule_info(skb2, net, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, - family, table, chain, rule, NULL); + info->nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, + family, table, chain, rule, 0); if (err < 0) - goto err; + goto err_fill_rule_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_rule_info: kfree_skb(skb2); return err; } @@ -2909,7 +3313,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, * is called on error from nf_tables_newrule(). */ expr = nft_expr_first(rule); - while (expr != nft_expr_last(rule) && expr->ops) { + while (nft_expr_more(rule, expr)) { next = nft_expr_next(expr); nf_tables_expr_destroy(ctx, expr); expr = next; @@ -2917,8 +3321,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, kfree(rule); } -static void nf_tables_rule_release(const struct nft_ctx *ctx, - struct nft_rule *rule) +void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); @@ -2946,6 +3349,8 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) if (err < 0) return err; } + + cond_resched(); } return 0; @@ -2975,44 +3380,60 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) } static struct nft_rule *nft_rule_lookup_byid(const struct net *net, + const struct nft_chain *chain, const struct nlattr *nla); #define NFT_RULE_MAXEXPRS 128 -static int nf_tables_newrule(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); - struct nft_expr_info *info = NULL; - int family = nfmsg->nfgen_family; - struct nft_flow_rule *flow; - struct nft_table *table; - struct nft_chain *chain; + struct nftables_pernet *nft_net = nft_pernet(info->net); + struct netlink_ext_ack *extack = info->extack; + unsigned int size, i, n, ulen = 0, usize = 0; + u8 genmask = nft_genmask_next(info->net); struct nft_rule *rule, *old_rule = NULL; + struct nft_expr_info *expr_info = NULL; + u8 family = info->nfmsg->nfgen_family; + struct nft_flow_rule *flow = NULL; + struct net *net = info->net; struct nft_userdata *udata; - struct nft_trans *trans = NULL; + struct nft_table *table; + struct nft_chain *chain; + struct nft_trans *trans; + u64 handle, pos_handle; struct nft_expr *expr; struct nft_ctx ctx; struct nlattr *tmp; - unsigned int size, i, n, ulen = 0, usize = 0; int err, rem; - u64 handle, pos_handle; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); - table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); } - chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask); - if (IS_ERR(chain)) { - NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); - return PTR_ERR(chain); + if (nla[NFTA_RULE_CHAIN]) { + chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], + genmask); + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); + return PTR_ERR(chain); + } + if (nft_chain_is_bound(chain)) + return -EOPNOTSUPP; + + } else if (nla[NFTA_RULE_CHAIN_ID]) { + chain = nft_chain_lookup_byid(net, table, nla[NFTA_RULE_CHAIN_ID]); + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN_ID]); + return PTR_ERR(chain); + } + } else { + return -EINVAL; } if (nla[NFTA_RULE_HANDLE]) { @@ -3023,17 +3444,17 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, return PTR_ERR(rule); } - if (nlh->nlmsg_flags & NLM_F_EXCL) { + if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return -EEXIST; } - if (nlh->nlmsg_flags & NLM_F_REPLACE) + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) old_rule = rule; else return -EOPNOTSUPP; } else { - if (!(nlh->nlmsg_flags & NLM_F_CREATE) || - nlh->nlmsg_flags & NLM_F_REPLACE) + if (!(info->nlh->nlmsg_flags & NLM_F_CREATE) || + info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EINVAL; handle = nf_tables_alloc_handle(table); @@ -3048,7 +3469,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, return PTR_ERR(old_rule); } } else if (nla[NFTA_RULE_POSITION_ID]) { - old_rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_POSITION_ID]); + old_rule = nft_rule_lookup_byid(net, chain, nla[NFTA_RULE_POSITION_ID]); if (IS_ERR(old_rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION_ID]); return PTR_ERR(old_rule); @@ -3056,34 +3477,36 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, } } - nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); n = 0; size = 0; if (nla[NFTA_RULE_EXPRESSIONS]) { - info = kvmalloc_array(NFT_RULE_MAXEXPRS, - sizeof(struct nft_expr_info), - GFP_KERNEL); - if (!info) + expr_info = kvmalloc_array(NFT_RULE_MAXEXPRS, + sizeof(struct nft_expr_info), + GFP_KERNEL); + if (!expr_info) return -ENOMEM; nla_for_each_nested(tmp, nla[NFTA_RULE_EXPRESSIONS], rem) { err = -EINVAL; if (nla_type(tmp) != NFTA_LIST_ELEM) - goto err1; + goto err_release_expr; if (n == NFT_RULE_MAXEXPRS) - goto err1; - err = nf_tables_expr_parse(&ctx, tmp, &info[n]); - if (err < 0) - goto err1; - size += info[n].ops->size; + goto err_release_expr; + err = nf_tables_expr_parse(&ctx, tmp, &expr_info[n]); + if (err < 0) { + NL_SET_BAD_ATTR(extack, tmp); + goto err_release_expr; + } + size += expr_info[n].ops->size; n++; } } /* Check for overflow of dlen field */ err = -EFBIG; if (size >= 1 << 12) - goto err1; + goto err_release_expr; if (nla[NFTA_RULE_USERDATA]) { ulen = nla_len(nla[NFTA_RULE_USERDATA]); @@ -3092,9 +3515,9 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, } err = -ENOMEM; - rule = kzalloc(sizeof(*rule) + size + usize, GFP_KERNEL); + rule = kzalloc(sizeof(*rule) + size + usize, GFP_KERNEL_ACCOUNT); if (rule == NULL) - goto err1; + goto err_release_expr; nft_activate_next(net, rule); @@ -3110,38 +3533,46 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, expr = nft_expr_first(rule); for (i = 0; i < n; i++) { - err = nf_tables_newexpr(&ctx, &info[i], expr); - if (err < 0) - goto err2; + err = nf_tables_newexpr(&ctx, &expr_info[i], expr); + if (err < 0) { + NL_SET_BAD_ATTR(extack, expr_info[i].attr); + goto err_release_rule; + } - if (info[i].ops->validate) + if (expr_info[i].ops->validate) nft_validate_state_update(net, NFT_VALIDATE_NEED); - info[i].ops = NULL; + expr_info[i].ops = NULL; expr = nft_expr_next(expr); } - if (nlh->nlmsg_flags & NLM_F_REPLACE) { + if (chain->flags & NFT_CHAIN_HW_OFFLOAD) { + flow = nft_flow_rule_create(net, rule); + if (IS_ERR(flow)) { + err = PTR_ERR(flow); + goto err_release_rule; + } + } + + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { + err = nft_delrule(&ctx, old_rule); + if (err < 0) + goto err_destroy_flow_rule; + trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; - goto err2; + goto err_destroy_flow_rule; } - err = nft_delrule(&ctx, old_rule); - if (err < 0) { - nft_trans_destroy(trans); - goto err2; - } - list_add_tail_rcu(&rule->list, &old_rule->list); } else { trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (!trans) { err = -ENOMEM; - goto err2; + goto err_destroy_flow_rule; } - if (nlh->nlmsg_flags & NLM_F_APPEND) { + if (info->nlh->nlmsg_flags & NLM_F_APPEND) { if (old_rule) list_add_rcu(&rule->list, &old_rule->list); else @@ -3153,65 +3584,69 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, list_add_rcu(&rule->list, &chain->rules); } } - kvfree(info); + kvfree(expr_info); chain->use++; - if (net->nft.validate_state == NFT_VALIDATE_DO) - return nft_table_validate(net, table); - - if (chain->flags & NFT_CHAIN_HW_OFFLOAD) { - flow = nft_flow_rule_create(net, rule); - if (IS_ERR(flow)) - return PTR_ERR(flow); - + if (flow) nft_trans_flow_rule(trans) = flow; - } + + if (nft_net->validate_state == NFT_VALIDATE_DO) + return nft_table_validate(net, table); return 0; -err2: + +err_destroy_flow_rule: + if (flow) + nft_flow_rule_destroy(flow); +err_release_rule: nf_tables_rule_release(&ctx, rule); -err1: +err_release_expr: for (i = 0; i < n; i++) { - if (info[i].ops) { - module_put(info[i].ops->type->owner); - if (info[i].ops->type->release_ops) - info[i].ops->type->release_ops(info[i].ops); + if (expr_info[i].ops) { + module_put(expr_info[i].ops->type->owner); + if (expr_info[i].ops->type->release_ops) + expr_info[i].ops->type->release_ops(expr_info[i].ops); } } - kvfree(info); + kvfree(expr_info); + return err; } static struct nft_rule *nft_rule_lookup_byid(const struct net *net, + const struct nft_chain *chain, const struct nlattr *nla) { + struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); struct nft_trans *trans; - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { struct nft_rule *rule = nft_trans_rule(trans); if (trans->msg_type == NFT_MSG_NEWRULE && + trans->ctx.chain == chain && id == nft_trans_rule_id(trans)) return rule; } return ERR_PTR(-ENOENT); } -static int nf_tables_delrule(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); - struct nft_table *table; + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; struct nft_chain *chain = NULL; + struct net *net = info->net; + struct nft_table *table; struct nft_rule *rule; - int family = nfmsg->nfgen_family, err = 0; struct nft_ctx ctx; + int err = 0; - table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); @@ -3224,9 +3659,11 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } + if (nft_chain_is_bound(chain)) + return -EOPNOTSUPP; } - nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (chain) { if (nla[NFTA_RULE_HANDLE]) { @@ -3238,7 +3675,7 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, err = nft_delrule(&ctx, rule); } else if (nla[NFTA_RULE_ID]) { - rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_ID]); + rule = nft_rule_lookup_byid(net, chain, nla[NFTA_RULE_ID]); if (IS_ERR(rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_ID]); return PTR_ERR(rule); @@ -3266,25 +3703,17 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, /* * Sets */ - -static LIST_HEAD(nf_tables_set_types); - -int nft_register_set(struct nft_set_type *type) -{ - nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_add_tail_rcu(&type->list, &nf_tables_set_types); - nfnl_unlock(NFNL_SUBSYS_NFTABLES); - return 0; -} -EXPORT_SYMBOL_GPL(nft_register_set); - -void nft_unregister_set(struct nft_set_type *type) -{ - nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_del_rcu(&type->list); - nfnl_unlock(NFNL_SUBSYS_NFTABLES); -} -EXPORT_SYMBOL_GPL(nft_unregister_set); +static const struct nft_set_type *nft_set_types[] = { + &nft_set_hash_fast_type, + &nft_set_hash_type, + &nft_set_rhash_type, + &nft_set_bitmap_type, + &nft_set_rbtree_type, +#if defined(CONFIG_X86_64) && !defined(CONFIG_UML) + &nft_set_pipapo_avx2_type, +#endif + &nft_set_pipapo_type, +}; #define NFT_SET_FEATURES (NFT_SET_INTERVAL | NFT_SET_MAP | \ NFT_SET_TIMEOUT | NFT_SET_OBJECT | \ @@ -3306,19 +3735,16 @@ nft_select_set_ops(const struct nft_ctx *ctx, const struct nft_set_desc *desc, enum nft_set_policies policy) { + struct nftables_pernet *nft_net = nft_pernet(ctx->net); const struct nft_set_ops *ops, *bops; struct nft_set_estimate est, best; const struct nft_set_type *type; u32 flags = 0; + int i; - lockdep_assert_held(&ctx->net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); lockdep_nfnl_nft_mutex_not_held(); -#ifdef CONFIG_MODULES - if (list_empty(&nf_tables_set_types)) { - if (nft_request_module(ctx->net, "nft-set") == -EAGAIN) - return ERR_PTR(-EAGAIN); - } -#endif + if (nla[NFTA_SET_FLAGS] != NULL) flags = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS])); @@ -3327,7 +3753,8 @@ nft_select_set_ops(const struct nft_ctx *ctx, best.lookup = ~0; best.space = ~0; - list_for_each_entry(type, &nf_tables_set_types, list) { + for (i = 0; i < ARRAY_SIZE(nft_set_types); i++) { + type = nft_set_types[i]; ops = &type->ops; if (!nft_set_ops_candidate(type, flags)) @@ -3358,11 +3785,6 @@ nft_select_set_ops(const struct nft_ctx *ctx, break; } - if (!try_module_get(type->owner)) - continue; - if (bops != NULL) - module_put(to_set_type(bops)->owner); - bops = ops; best = est; } @@ -3392,6 +3814,8 @@ static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = { .len = NFT_USERDATA_MAXLEN }, [NFTA_SET_OBJ_TYPE] = { .type = NLA_U32 }, [NFTA_SET_HANDLE] = { .type = NLA_U64 }, + [NFTA_SET_EXPR] = { .type = NLA_NESTED }, + [NFTA_SET_EXPRESSIONS] = { .type = NLA_NESTED }, }; static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { @@ -3399,30 +3823,6 @@ static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { [NFTA_SET_DESC_CONCAT] = { .type = NLA_NESTED }, }; -static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, - const struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack, - u8 genmask) -{ - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - int family = nfmsg->nfgen_family; - struct nft_table *table = NULL; - - if (nla[NFTA_SET_TABLE] != NULL) { - table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, - genmask); - if (IS_ERR(table)) { - NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); - return PTR_ERR(table); - } - } - - nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla); - return 0; -} - static struct nft_set *nft_set_lookup(const struct nft_table *table, const struct nlattr *nla, u8 genmask) { @@ -3454,16 +3854,19 @@ static struct nft_set *nft_set_lookup_byhandle(const struct nft_table *table, } static struct nft_set *nft_set_lookup_byid(const struct net *net, + const struct nft_table *table, const struct nlattr *nla, u8 genmask) { - struct nft_trans *trans; + struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); + struct nft_trans *trans; - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->msg_type == NFT_MSG_NEWSET) { struct nft_set *set = nft_trans_set(trans); if (id == nft_trans_set_id(trans) && + set->table == table && nft_active_genmask(set, genmask)) return set; } @@ -3484,7 +3887,7 @@ struct nft_set *nft_set_lookup_global(const struct net *net, if (!nla_set_id) return set; - set = nft_set_lookup_byid(net, nla_set_id, genmask); + set = nft_set_lookup_byid(net, table, nla_set_id, genmask); } return set; } @@ -3510,7 +3913,7 @@ cont: list_for_each_entry(i, &ctx->table->sets, list) { int tmp; - if (!nft_is_active_next(ctx->net, set)) + if (!nft_is_active_next(ctx->net, i)) continue; if (!sscanf(i->name, name, &tmp)) continue; @@ -3529,7 +3932,7 @@ cont: free_page((unsigned long)inuse); } - set->name = kasprintf(GFP_KERNEL, name, min + n); + set->name = kasprintf(GFP_KERNEL_ACCOUNT, name, min + n); if (!set->name) return -ENOMEM; @@ -3538,13 +3941,14 @@ cont: continue; if (!strcmp(set->name, i->name)) { kfree(set->name); + set->name = NULL; return -ENFILE; } } return 0; } -static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) +int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) { u64 ms = be64_to_cpu(nla_get_be64(nla)); u64 max = (u64)(~((u64)0)); @@ -3558,7 +3962,7 @@ static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) return 0; } -static __be64 nf_jiffies64_to_msecs(u64 input) +__be64 nf_jiffies64_to_msecs(u64 input) { return cpu_to_be64(jiffies64_to_msecs(input)); } @@ -3593,23 +3997,18 @@ static int nf_tables_fill_set_concat(struct sk_buff *skb, static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, const struct nft_set *set, u16 event, u16 flags) { - struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; - struct nlattr *desc; u32 portid = ctx->portid; + struct nlattr *nest; u32 seq = ctx->seq; + int i; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), - flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family, + NFNETLINK_V0, nft_base_seq(ctx->net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = ctx->family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(ctx->net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_NAME, set->name)) @@ -3649,12 +4048,12 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, goto nla_put_failure; } - if (nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata)) + if (set->udata && + nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata)) goto nla_put_failure; - desc = nla_nest_start_noflag(skb, NFTA_SET_DESC); - - if (desc == NULL) + nest = nla_nest_start_noflag(skb, NFTA_SET_DESC); + if (!nest) goto nla_put_failure; if (set->size && nla_put_be32(skb, NFTA_SET_DESC_SIZE, htonl(set->size))) @@ -3664,7 +4063,26 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, nf_tables_fill_set_concat(skb, set)) goto nla_put_failure; - nla_nest_end(skb, desc); + nla_nest_end(skb, nest); + + if (set->num_exprs == 1) { + nest = nla_nest_start_noflag(skb, NFTA_SET_EXPR); + if (nf_tables_fill_expr_info(skb, set->exprs[0]) < 0) + goto nla_put_failure; + + nla_nest_end(skb, nest); + } else if (set->num_exprs > 1) { + nest = nla_nest_start_noflag(skb, NFTA_SET_EXPRESSIONS); + if (nest == NULL) + goto nla_put_failure; + + for (i = 0; i < set->num_exprs; i++) { + if (nft_expr_dump(skb, NFTA_LIST_ELEM, + set->exprs[i]) < 0) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } nlmsg_end(skb, nlh); return 0; @@ -3678,8 +4096,10 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, const struct nft_set *set, int event, gfp_t gfp_flags) { - struct sk_buff *skb; + struct nftables_pernet *nft_net = nft_pernet(ctx->net); u32 portid = ctx->portid; + struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && @@ -3690,14 +4110,16 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, if (skb == NULL) goto err; - err = nf_tables_fill_set(skb, ctx, set, event, 0); + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + + err = nf_tables_fill_set(skb, ctx, set, event, flags); if (err < 0) { kfree_skb(skb); goto err; } - nfnetlink_send(skb, ctx->net, portid, NFNLGRP_NFTABLES, ctx->report, - gfp_flags); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -3710,14 +4132,16 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2]; struct net *net = sock_net(skb->sk); struct nft_ctx *ctx = cb->data, ctx_set; + struct nftables_pernet *nft_net; if (cb->args[1]) return skb->len; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = nft_pernet(net); + cb->seq = READ_ONCE(nft_net->base_seq); - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (ctx->family != NFPROTO_UNSPEC && ctx->family != table->family) continue; @@ -3781,25 +4205,31 @@ static int nf_tables_dump_sets_done(struct netlink_callback *cb) } /* called with rcu_read_lock held */ -static int nf_tables_getset(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_getset(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - u8 genmask = nft_genmask_cur(net); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_cur(info->net); + u8 family = info->nfmsg->nfgen_family; + struct nft_table *table = NULL; + struct net *net = info->net; const struct nft_set *set; - struct nft_ctx ctx; struct sk_buff *skb2; - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + struct nft_ctx ctx; int err; - /* Verify existence before starting dump */ - err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack, - genmask); - if (err < 0) - return err; + if (nla[NFTA_SET_TABLE]) { + table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, + genmask, 0); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); + return PTR_ERR(table); + } + } + + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_sets_start, .dump = nf_tables_dump_sets, @@ -3808,16 +4238,16 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, .module = THIS_MODULE, }; - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } /* Only accept unspec with dump */ - if (nfmsg->nfgen_family == NFPROTO_UNSPEC) + if (info->nfmsg->nfgen_family == NFPROTO_UNSPEC) return -EAFNOSUPPORT; if (!nla[NFTA_SET_TABLE]) return -EINVAL; - set = nft_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask); + set = nft_set_lookup(table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) return PTR_ERR(set); @@ -3827,11 +4257,11 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, err = nf_tables_fill_set(skb2, &ctx, set, NFT_MSG_NEWSET, 0); if (err < 0) - goto err; + goto err_fill_set_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_set_info: kfree_skb(skb2); return err; } @@ -3847,6 +4277,9 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, u32 len; int err; + if (desc->field_count >= ARRAY_SIZE(desc->field_len)) + return -E2BIG; + err = nla_parse_nested_deprecated(tb, NFTA_SET_FIELD_MAX, attr, nft_concat_policy, NULL); if (err < 0) @@ -3856,9 +4289,8 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, return -EINVAL; len = ntohl(nla_get_be32(tb[NFTA_SET_FIELD_LEN])); - - if (len * BITS_PER_BYTE / 32 > NFT_REG32_COUNT) - return -E2BIG; + if (!len || len > U8_MAX) + return -EINVAL; desc->field_len[desc->field_count++] = len; @@ -3869,7 +4301,8 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, const struct nlattr *nla) { struct nlattr *attr; - int rem, err; + u32 num_regs = 0; + int rem, err, i; nla_for_each_nested(attr, nla, rem) { if (nla_type(attr) != NFTA_LIST_ELEM) @@ -3880,6 +4313,12 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, return err; } + for (i = 0; i < desc->field_count; i++) + num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32)); + + if (num_regs > NFT_REG32_COUNT) + return -E2BIG; + return 0; } @@ -3902,27 +4341,27 @@ static int nf_tables_set_desc_parse(struct nft_set_desc *desc, return err; } -static int nf_tables_newset(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); - int family = nfmsg->nfgen_family; + u32 ktype, dtype, flags, policy, gc_int, objtype; + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; const struct nft_set_ops *ops; + struct nft_expr *expr = NULL; + struct net *net = info->net; + struct nft_set_desc desc; struct nft_table *table; + unsigned char *udata; struct nft_set *set; struct nft_ctx ctx; - char *name; - u64 size; + size_t alloc_size; u64 timeout; - u32 ktype, dtype, flags, policy, gc_int, objtype; - struct nft_set_desc desc; - unsigned char *udata; + char *name; + int err, i; u16 udlen; - int err; - int i; + u64 size; if (nla[NFTA_SET_TABLE] == NULL || nla[NFTA_SET_NAME] == NULL || @@ -3949,8 +4388,8 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (flags & ~(NFT_SET_ANONYMOUS | NFT_SET_CONSTANT | NFT_SET_INTERVAL | NFT_SET_TIMEOUT | NFT_SET_MAP | NFT_SET_EVAL | - NFT_SET_OBJECT)) - return -EINVAL; + NFT_SET_OBJECT | NFT_SET_CONCAT | NFT_SET_EXPR)) + return -EOPNOTSUPP; /* Only one of these operations is supported */ if ((flags & (NFT_SET_MAP | NFT_SET_OBJECT)) == (NFT_SET_MAP | NFT_SET_OBJECT)) @@ -3988,7 +4427,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE])); if (objtype == NFT_OBJECT_UNSPEC || objtype > NFT_OBJECT_MAX) - return -EINVAL; + return -EOPNOTSUPP; } else if (flags & NFT_SET_OBJECT) return -EINVAL; else @@ -4018,15 +4457,24 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]); if (err < 0) return err; + + if (desc.field_count > 1 && !(flags & NFT_SET_CONCAT)) + return -EINVAL; + } else if (flags & NFT_SET_CONCAT) { + return -EINVAL; } - table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask); + if (nla[NFTA_SET_EXPR] || nla[NFTA_SET_EXPRESSIONS]) + desc.expr = true; + + table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); return PTR_ERR(table); } - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); set = nft_set_lookup(table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) { @@ -4035,17 +4483,17 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, return PTR_ERR(set); } } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) { + if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); return -EEXIST; } - if (nlh->nlmsg_flags & NLM_F_REPLACE) + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; return 0; } - if (!(nlh->nlmsg_flags & NLM_F_CREATE)) + if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; ops = nft_select_set_ops(&ctx, nla, &desc, policy); @@ -4059,23 +4507,23 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, size = 0; if (ops->privsize != NULL) size = ops->privsize(nla, &desc); + alloc_size = sizeof(*set) + size + udlen; + if (alloc_size < size || alloc_size > INT_MAX) + return -ENOMEM; + set = kvzalloc(alloc_size, GFP_KERNEL_ACCOUNT); + if (!set) + return -ENOMEM; - set = kvzalloc(sizeof(*set) + size + udlen, GFP_KERNEL); - if (!set) { - err = -ENOMEM; - goto err1; - } - - name = nla_strdup(nla[NFTA_SET_NAME], GFP_KERNEL); + name = nla_strdup(nla[NFTA_SET_NAME], GFP_KERNEL_ACCOUNT); if (!name) { err = -ENOMEM; - goto err2; + goto err_set_name; } err = nf_tables_set_alloc_name(&ctx, set, name); kfree(name); if (err < 0) - goto err2; + goto err_set_name; udata = NULL; if (udlen) { @@ -4084,22 +4532,22 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, } INIT_LIST_HEAD(&set->bindings); + INIT_LIST_HEAD(&set->catchall_list); set->table = table; write_pnet(&set->net, net); - set->ops = ops; + set->ops = ops; set->ktype = ktype; - set->klen = desc.klen; + set->klen = desc.klen; set->dtype = dtype; set->objtype = objtype; - set->dlen = desc.dlen; + set->dlen = desc.dlen; set->flags = flags; - set->size = desc.size; + set->size = desc.size; set->policy = policy; - set->udlen = udlen; - set->udata = udata; + set->udlen = udlen; + set->udata = udata; set->timeout = timeout; set->gc_int = gc_int; - set->handle = nf_tables_alloc_handle(table); set->field_count = desc.field_count; for (i = 0; i < desc.field_count; i++) @@ -4107,66 +4555,129 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, err = ops->init(set, &desc, nla); if (err < 0) - goto err3; + goto err_set_init; + + if (nla[NFTA_SET_EXPR]) { + expr = nft_set_elem_expr_alloc(&ctx, set, nla[NFTA_SET_EXPR]); + if (IS_ERR(expr)) { + err = PTR_ERR(expr); + goto err_set_expr_alloc; + } + set->exprs[0] = expr; + set->num_exprs++; + } else if (nla[NFTA_SET_EXPRESSIONS]) { + struct nft_expr *expr; + struct nlattr *tmp; + int left; + + if (!(flags & NFT_SET_EXPR)) { + err = -EINVAL; + goto err_set_expr_alloc; + } + i = 0; + nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) { + if (i == NFT_SET_EXPR_MAX) { + err = -E2BIG; + goto err_set_expr_alloc; + } + if (nla_type(tmp) != NFTA_LIST_ELEM) { + err = -EINVAL; + goto err_set_expr_alloc; + } + expr = nft_set_elem_expr_alloc(&ctx, set, tmp); + if (IS_ERR(expr)) { + err = PTR_ERR(expr); + goto err_set_expr_alloc; + } + set->exprs[i++] = expr; + set->num_exprs++; + } + } + + set->handle = nf_tables_alloc_handle(table); err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) - goto err4; + goto err_set_expr_alloc; list_add_tail_rcu(&set->list, &table->sets); table->use++; return 0; -err4: +err_set_expr_alloc: + for (i = 0; i < set->num_exprs; i++) + nft_expr_destroy(&ctx, set->exprs[i]); + ops->destroy(set); -err3: +err_set_init: kfree(set->name); -err2: +err_set_name: kvfree(set); -err1: - module_put(to_set_type(ops)->owner); return err; } -static void nft_set_destroy(struct nft_set *set) +struct nft_set_elem_catchall { + struct list_head list; + struct rcu_head rcu; + void *elem; +}; + +static void nft_set_catchall_destroy(const struct nft_ctx *ctx, + struct nft_set *set) +{ + struct nft_set_elem_catchall *next, *catchall; + + list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { + list_del_rcu(&catchall->list); + nft_set_elem_destroy(set, catchall->elem, true); + kfree_rcu(catchall, rcu); + } +} + +static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) { + int i; + if (WARN_ON(set->use > 0)) return; + for (i = 0; i < set->num_exprs; i++) + nft_expr_destroy(ctx, set->exprs[i]); + set->ops->destroy(set); - module_put(to_set_type(set->ops)->owner); + nft_set_catchall_destroy(ctx, set); kfree(set->name); kvfree(set); } -static int nf_tables_delset(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; + struct net *net = info->net; const struct nlattr *attr; + struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; - int err; - if (nfmsg->nfgen_family == NFPROTO_UNSPEC) + if (info->nfmsg->nfgen_family == NFPROTO_UNSPEC) return -EAFNOSUPPORT; - if (nla[NFTA_SET_TABLE] == NULL) - return -EINVAL; - err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack, - genmask); - if (err < 0) - return err; + table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, + genmask, NETLINK_CB(skb).portid); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); + return PTR_ERR(table); + } if (nla[NFTA_SET_HANDLE]) { attr = nla[NFTA_SET_HANDLE]; - set = nft_set_lookup_byhandle(ctx.table, attr, genmask); + set = nft_set_lookup_byhandle(table, attr, genmask); } else { attr = nla[NFTA_SET_NAME]; - set = nft_set_lookup(ctx.table, attr, genmask); + set = nft_set_lookup(table, attr, genmask); } if (IS_ERR(set)) { @@ -4174,18 +4685,26 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, return PTR_ERR(set); } if (set->use || - (nlh->nlmsg_flags & NLM_F_NONREC && atomic_read(&set->nelems) > 0)) { + (info->nlh->nlmsg_flags & NLM_F_NONREC && + atomic_read(&set->nelems) > 0)) { NL_SET_BAD_ATTR(extack, attr); return -EBUSY; } + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + return nft_delset(&ctx, set); } -static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, - struct nft_set *set, - const struct nft_set_iter *iter, - struct nft_set_elem *elem) +static int nft_validate_register_store(const struct nft_ctx *ctx, + enum nft_registers reg, + const struct nft_data *data, + enum nft_data_types type, + unsigned int len); + +static int nft_setelem_data_validate(const struct nft_ctx *ctx, + struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); enum nft_registers dreg; @@ -4197,6 +4716,37 @@ static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, set->dlen); } +static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, + struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + return nft_setelem_data_validate(ctx, set, elem); +} + +static int nft_set_catchall_bind_check(const struct nft_ctx *ctx, + struct nft_set *set) +{ + u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_elem_catchall *catchall; + struct nft_set_elem elem; + struct nft_set_ext *ext; + int ret = 0; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask)) + continue; + + elem.priv = catchall->elem; + ret = nft_setelem_data_validate(ctx, set, &elem); + if (ret < 0) + break; + } + + return ret; +} + int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding) { @@ -4226,6 +4776,9 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, iter.fn = nf_tables_bind_check_setelem; set->ops->walk(ctx, set, &iter); + if (!iter.err) + iter.err = nft_set_catchall_bind_check(ctx, set); + if (iter.err < 0) return iter.err; } @@ -4263,7 +4816,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: set->use--; - /* fall through */ + fallthrough; default: nf_tables_unbind_set(ctx, set, binding, phase == NFT_TRANS_COMMIT); @@ -4274,7 +4827,7 @@ EXPORT_SYMBOL_GPL(nf_tables_deactivate_set); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set) { if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) - nft_set_destroy(set); + nft_set_destroy(ctx, set); } EXPORT_SYMBOL_GPL(nf_tables_destroy_set); @@ -4285,8 +4838,8 @@ const struct nft_set_ext_type nft_set_ext_types[] = { [NFT_SET_EXT_DATA] = { .align = __alignof__(u32), }, - [NFT_SET_EXT_EXPR] = { - .align = __alignof__(struct nft_expr), + [NFT_SET_EXT_EXPRESSIONS] = { + .align = __alignof__(struct nft_set_elem_expr), }, [NFT_SET_EXT_OBJREF] = { .len = sizeof(struct nft_object *), @@ -4312,7 +4865,6 @@ const struct nft_set_ext_type nft_set_ext_types[] = { .align = __alignof__(u32), }, }; -EXPORT_SYMBOL_GPL(nft_set_ext_types); /* * Set elements @@ -4330,6 +4882,7 @@ static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = { [NFTA_SET_ELEM_OBJREF] = { .type = NLA_STRING, .len = NFT_OBJ_MAXNAMELEN - 1 }, [NFTA_SET_ELEM_KEY_END] = { .type = NLA_NESTED }, + [NFTA_SET_ELEM_EXPRESSIONS] = { .type = NLA_NESTED }, }; static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = { @@ -4341,26 +4894,41 @@ static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + [NFTA_SET_ELEM_LIST_SET_ID] = { .type = NLA_U32 }, }; -static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net, - const struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack, - u8 genmask) +static int nft_set_elem_expr_dump(struct sk_buff *skb, + const struct nft_set *set, + const struct nft_set_ext *ext) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - int family = nfmsg->nfgen_family; - struct nft_table *table; + struct nft_set_elem_expr *elem_expr; + u32 size, num_exprs = 0; + struct nft_expr *expr; + struct nlattr *nest; - table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, - genmask); - if (IS_ERR(table)) { - NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); - return PTR_ERR(table); - } + elem_expr = nft_set_ext_expr(ext); + nft_setelem_expr_foreach(expr, elem_expr, size) + num_exprs++; - nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla); + if (num_exprs == 1) { + expr = nft_setelem_expr_at(elem_expr, 0); + if (nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, expr) < 0) + return -1; + + return 0; + } else if (num_exprs > 1) { + nest = nla_nest_start_noflag(skb, NFTA_SET_ELEM_EXPRESSIONS); + if (nest == NULL) + goto nla_put_failure; + + nft_setelem_expr_foreach(expr, elem_expr, size) { + expr = nft_setelem_expr_at(elem_expr, size); + if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr) < 0) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } return 0; + +nla_put_failure: + return -1; } static int nf_tables_fill_setelem(struct sk_buff *skb, @@ -4375,7 +4943,8 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nest == NULL) goto nla_put_failure; - if (nft_data_dump(skb, NFTA_SET_ELEM_KEY, nft_set_ext_key(ext), + if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY) && + nft_data_dump(skb, NFTA_SET_ELEM_KEY, nft_set_ext_key(ext), NFT_DATA_VALUE, set->klen) < 0) goto nla_put_failure; @@ -4390,8 +4959,8 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, set->dlen) < 0) goto nla_put_failure; - if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR) && - nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, nft_set_ext_expr(ext)) < 0) + if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS) && + nft_set_elem_expr_dump(skb, set, ext)) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) && @@ -4464,22 +5033,48 @@ struct nft_set_dump_ctx { struct nft_ctx ctx; }; +static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb, + const struct nft_set *set) +{ + struct nft_set_elem_catchall *catchall; + u8 genmask = nft_genmask_cur(net); + struct nft_set_elem elem; + struct nft_set_ext *ext; + int ret = 0; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask) || + nft_set_elem_expired(ext)) + continue; + + elem.priv = catchall->elem; + ret = nf_tables_fill_setelem(skb, set, &elem); + break; + } + + return ret; +} + static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) { struct nft_set_dump_ctx *dump_ctx = cb->data; struct net *net = sock_net(skb->sk); + struct nftables_pernet *nft_net; struct nft_table *table; struct nft_set *set; struct nft_set_dump_args args; bool set_found = false; - struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; struct nlattr *nest; u32 portid, seq; int event; rcu_read_lock(); - list_for_each_entry_rcu(table, &net->nft.tables, list) { + nft_net = nft_pernet(net); + cb->seq = READ_ONCE(nft_net->base_seq); + + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (dump_ctx->ctx.family != NFPROTO_UNSPEC && dump_ctx->ctx.family != table->family) continue; @@ -4505,16 +5100,11 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) portid = NETLINK_CB(cb->skb).portid; seq = cb->nlh->nlmsg_seq; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), - NLM_F_MULTI); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, NLM_F_MULTI, + table->family, NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = table->family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_SET_ELEM_LIST_TABLE, table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_ELEM_LIST_SET, set->name)) @@ -4532,6 +5122,9 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) args.iter.err = 0; args.iter.fn = nf_tables_dump_setelem; set->ops->walk(&dump_ctx->ctx, set, &args.iter); + + if (!args.iter.err && args.iter.count == cb->args[0]) + args.iter.err = nft_set_catchall_dump(net, skb, set); rcu_read_unlock(); nla_nest_end(skb, nest); @@ -4571,22 +5164,16 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb, const struct nft_set *set, const struct nft_set_elem *elem) { - struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; struct nlattr *nest; int err; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), - flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family, + NFNETLINK_V0, nft_base_seq(ctx->net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = ctx->family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(ctx->net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_NAME, set->name)) @@ -4617,11 +5204,14 @@ static int nft_setelem_parse_flags(const struct nft_set *set, return 0; *flags = ntohl(nla_get_be32(attr)); - if (*flags & ~NFT_SET_ELEM_INTERVAL_END) - return -EINVAL; + if (*flags & ~(NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL)) + return -EOPNOTSUPP; if (!(set->flags & NFT_SET_INTERVAL) && *flags & NFT_SET_ELEM_INTERVAL_END) return -EINVAL; + if ((*flags & (NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL)) == + (NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL)) + return -EINVAL; return 0; } @@ -4629,18 +5219,72 @@ static int nft_setelem_parse_flags(const struct nft_set *set, static int nft_setelem_parse_key(struct nft_ctx *ctx, struct nft_set *set, struct nft_data *key, struct nlattr *attr) { - struct nft_data_desc desc; - int err; + struct nft_data_desc desc = { + .type = NFT_DATA_VALUE, + .size = NFT_DATA_VALUE_MAXLEN, + .len = set->klen, + }; - err = nft_data_init(ctx, key, NFT_DATA_VALUE_MAXLEN, &desc, attr); - if (err < 0) - return err; + return nft_data_init(ctx, key, &desc, attr); +} - if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) { - nft_data_release(key, desc.type); - return -EINVAL; +static int nft_setelem_parse_data(struct nft_ctx *ctx, struct nft_set *set, + struct nft_data_desc *desc, + struct nft_data *data, + struct nlattr *attr) +{ + u32 dtype; + + if (set->dtype == NFT_DATA_VERDICT) + dtype = NFT_DATA_VERDICT; + else + dtype = NFT_DATA_VALUE; + + desc->type = dtype; + desc->size = NFT_DATA_VALUE_MAXLEN; + desc->len = set->dlen; + desc->flags = NFT_DATA_DESC_SETELEM; + + return nft_data_init(ctx, data, desc, attr); +} + +static void *nft_setelem_catchall_get(const struct net *net, + const struct nft_set *set) +{ + struct nft_set_elem_catchall *catchall; + u8 genmask = nft_genmask_cur(net); + struct nft_set_ext *ext; + void *priv = NULL; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask) || + nft_set_elem_expired(ext)) + continue; + + priv = catchall->elem; + break; } + return priv; +} + +static int nft_setelem_get(struct nft_ctx *ctx, struct nft_set *set, + struct nft_set_elem *elem, u32 flags) +{ + void *priv; + + if (!(flags & NFT_SET_ELEM_CATCHALL)) { + priv = set->ops->get(ctx->net, set, elem, flags); + if (IS_ERR(priv)) + return PTR_ERR(priv); + } else { + priv = nft_setelem_catchall_get(ctx->net, set); + if (!priv) + return -ENOENT; + } + elem->priv = priv; + return 0; } @@ -4651,7 +5295,6 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, struct nft_set_elem elem; struct sk_buff *skb; uint32_t flags = 0; - void *priv; int err; err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr, @@ -4659,17 +5302,19 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) return err; - if (!nla[NFTA_SET_ELEM_KEY]) - return -EINVAL; - err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags); if (err < 0) return err; - err = nft_setelem_parse_key(ctx, set, &elem.key.val, - nla[NFTA_SET_ELEM_KEY]); - if (err < 0) - return err; + if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) + return -EINVAL; + + if (nla[NFTA_SET_ELEM_KEY]) { + err = nft_setelem_parse_key(ctx, set, &elem.key.val, + nla[NFTA_SET_ELEM_KEY]); + if (err < 0) + return err; + } if (nla[NFTA_SET_ELEM_KEY_END]) { err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, @@ -4678,57 +5323,56 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, return err; } - priv = set->ops->get(ctx->net, set, &elem, flags); - if (IS_ERR(priv)) - return PTR_ERR(priv); - - elem.priv = priv; + err = nft_setelem_get(ctx, set, &elem, flags); + if (err < 0) + return err; err = -ENOMEM; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb == NULL) - goto err1; + return err; err = nf_tables_fill_setelem_info(skb, ctx, ctx->seq, ctx->portid, NFT_MSG_NEWSETELEM, 0, set, &elem); if (err < 0) - goto err2; + goto err_fill_setelem; - err = nfnetlink_unicast(skb, ctx->net, ctx->portid, MSG_DONTWAIT); - /* This avoids a loop in nfnetlink. */ - if (err < 0) - goto err1; + return nfnetlink_unicast(skb, ctx->net, ctx->portid); - return 0; -err2: +err_fill_setelem: kfree_skb(skb); -err1: - /* this avoids a loop in nfnetlink. */ - return err == -EAGAIN ? -ENOBUFS : err; + return err; } /* called with rcu_read_lock held */ -static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) -{ - u8 genmask = nft_genmask_cur(net); +static int nf_tables_getsetelem(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_cur(info->net); + u8 family = info->nfmsg->nfgen_family; + struct net *net = info->net; + struct nft_table *table; struct nft_set *set; struct nlattr *attr; struct nft_ctx ctx; int rem, err = 0; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, - genmask); - if (err < 0) - return err; + table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, + genmask, NETLINK_CB(skb).portid); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); + return PTR_ERR(table); + } - set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask); + set = nft_set_lookup(table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) return PTR_ERR(set); - if (nlh->nlmsg_flags & NLM_F_DUMP) { + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_set_start, .dump = nf_tables_dump_set, @@ -4741,7 +5385,7 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, }; c.data = &dump_ctx; - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) @@ -4749,8 +5393,10 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_get_set_elem(&ctx, set, attr); - if (err < 0) + if (err < 0) { + NL_SET_BAD_ATTR(extack, attr); break; + } } return err; @@ -4759,11 +5405,13 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, static void nf_tables_setelem_notify(const struct nft_ctx *ctx, const struct nft_set *set, const struct nft_set_elem *elem, - int event, u16 flags) + int event) { + struct nftables_pernet *nft_net; struct net *net = ctx->net; u32 portid = ctx->portid; struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) @@ -4773,6 +5421,9 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_setelem_info(skb, ctx, 0, portid, event, flags, set, elem); if (err < 0) { @@ -4780,8 +5431,8 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, goto err; } - nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, ctx->report, - GFP_KERNEL); + nft_net = nft_pernet(net); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -4801,6 +5452,54 @@ static struct nft_trans *nft_trans_elem_alloc(struct nft_ctx *ctx, return trans; } +struct nft_expr *nft_set_elem_expr_alloc(const struct nft_ctx *ctx, + const struct nft_set *set, + const struct nlattr *attr) +{ + struct nft_expr *expr; + int err; + + expr = nft_expr_init(ctx, attr); + if (IS_ERR(expr)) + return expr; + + err = -EOPNOTSUPP; + if (expr->ops->type->flags & NFT_EXPR_GC) { + if (set->flags & NFT_SET_TIMEOUT) + goto err_set_elem_expr; + if (!set->ops->gc_init) + goto err_set_elem_expr; + set->ops->gc_init(set); + } + + return expr; + +err_set_elem_expr: + nft_expr_destroy(ctx, expr); + return ERR_PTR(err); +} + +static int nft_set_ext_check(const struct nft_set_ext_tmpl *tmpl, u8 id, u32 len) +{ + len += nft_set_ext_types[id].len; + if (len > tmpl->ext_len[id] || + len > U8_MAX) + return -1; + + return 0; +} + +static int nft_set_ext_memcpy(const struct nft_set_ext_tmpl *tmpl, u8 id, + void *to, const void *from, u32 len) +{ + if (nft_set_ext_check(tmpl, id, len) < 0) + return -1; + + memcpy(to, from, len); + + return 0; +} + void *nft_set_elem_init(const struct nft_set *set, const struct nft_set_ext_tmpl *tmpl, const u32 *key, const u32 *key_end, @@ -4811,16 +5510,26 @@ void *nft_set_elem_init(const struct nft_set *set, elem = kzalloc(set->ops->elemsize + tmpl->len, gfp); if (elem == NULL) - return NULL; + return ERR_PTR(-ENOMEM); ext = nft_set_elem_ext(set, elem); nft_set_ext_init(ext, tmpl); - memcpy(nft_set_ext_key(ext), key, set->klen); - if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END)) - memcpy(nft_set_ext_key_end(ext), key_end, set->klen); - if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) - memcpy(nft_set_ext_data(ext), data, set->dlen); + if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY) && + nft_set_ext_memcpy(tmpl, NFT_SET_EXT_KEY, + nft_set_ext_key(ext), key, set->klen) < 0) + goto err_ext_check; + + if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END) && + nft_set_ext_memcpy(tmpl, NFT_SET_EXT_KEY_END, + nft_set_ext_key_end(ext), key_end, set->klen) < 0) + goto err_ext_check; + + if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && + nft_set_ext_memcpy(tmpl, NFT_SET_EXT_DATA, + nft_set_ext_data(ext), data, set->dlen) < 0) + goto err_ext_check; + if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { *nft_set_ext_expiration(ext) = get_jiffies_64() + expiration; if (expiration == 0) @@ -4830,6 +5539,32 @@ void *nft_set_elem_init(const struct nft_set *set, *nft_set_ext_timeout(ext) = timeout; return elem; + +err_ext_check: + kfree(elem); + + return ERR_PTR(-EINVAL); +} + +static void __nft_set_elem_expr_destroy(const struct nft_ctx *ctx, + struct nft_expr *expr) +{ + if (expr->ops->destroy_clone) { + expr->ops->destroy_clone(ctx, expr); + module_put(expr->ops->type->owner); + } else { + nf_tables_expr_destroy(ctx, expr); + } +} + +static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx, + struct nft_set_elem_expr *elem_expr) +{ + struct nft_expr *expr; + u32 size; + + nft_setelem_expr_foreach(expr, elem_expr, size) + __nft_set_elem_expr_destroy(ctx, expr); } void nft_set_elem_destroy(const struct nft_set *set, void *elem, @@ -4844,40 +5579,311 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, nft_data_release(nft_set_ext_key(ext), NFT_DATA_VALUE); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_release(nft_set_ext_data(ext), set->dtype); - if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) { - struct nft_expr *expr = nft_set_ext_expr(ext); + if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS)) + nft_set_elem_expr_destroy(&ctx, nft_set_ext_expr(ext)); - if (expr->ops->destroy_clone) { - expr->ops->destroy_clone(&ctx, expr); - module_put(expr->ops->type->owner); - } else { - nf_tables_expr_destroy(&ctx, expr); - } - } if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) (*nft_set_ext_obj(ext))->use--; kfree(elem); } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); -/* Only called from commit path, nft_set_elem_deactivate() already deals with - * the refcounting from the preparation phase. +/* Only called from commit path, nft_setelem_data_deactivate() already deals + * with the refcounting from the preparation phase. */ static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, const struct nft_set *set, void *elem) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem); - if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) - nf_tables_expr_destroy(ctx, nft_set_ext_expr(ext)); + if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS)) + nft_set_elem_expr_destroy(ctx, nft_set_ext_expr(ext)); + kfree(elem); } +int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, + struct nft_expr *expr_array[]) +{ + struct nft_expr *expr; + int err, i, k; + + for (i = 0; i < set->num_exprs; i++) { + expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL_ACCOUNT); + if (!expr) + goto err_expr; + + err = nft_expr_clone(expr, set->exprs[i]); + if (err < 0) { + kfree(expr); + goto err_expr; + } + expr_array[i] = expr; + } + + return 0; + +err_expr: + for (k = i - 1; k >= 0; k--) + nft_expr_destroy(ctx, expr_array[k]); + + return -ENOMEM; +} + +static int nft_set_elem_expr_setup(struct nft_ctx *ctx, + const struct nft_set_ext_tmpl *tmpl, + const struct nft_set_ext *ext, + struct nft_expr *expr_array[], + u32 num_exprs) +{ + struct nft_set_elem_expr *elem_expr = nft_set_ext_expr(ext); + u32 len = sizeof(struct nft_set_elem_expr); + struct nft_expr *expr; + int i, err; + + if (num_exprs == 0) + return 0; + + for (i = 0; i < num_exprs; i++) + len += expr_array[i]->ops->size; + + if (nft_set_ext_check(tmpl, NFT_SET_EXT_EXPRESSIONS, len) < 0) + return -EINVAL; + + for (i = 0; i < num_exprs; i++) { + expr = nft_setelem_expr_at(elem_expr, elem_expr->size); + err = nft_expr_clone(expr, expr_array[i]); + if (err < 0) + goto err_elem_expr_setup; + + elem_expr->size += expr_array[i]->ops->size; + nft_expr_destroy(ctx, expr_array[i]); + expr_array[i] = NULL; + } + + return 0; + +err_elem_expr_setup: + for (; i < num_exprs; i++) { + nft_expr_destroy(ctx, expr_array[i]); + expr_array[i] = NULL; + } + + return -ENOMEM; +} + +struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, + const struct nft_set *set) +{ + struct nft_set_elem_catchall *catchall; + u8 genmask = nft_genmask_cur(net); + struct nft_set_ext *ext; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (nft_set_elem_active(ext, genmask) && + !nft_set_elem_expired(ext)) + return ext; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(nft_set_catchall_lookup); + +void *nft_set_catchall_gc(const struct nft_set *set) +{ + struct nft_set_elem_catchall *catchall, *next; + struct nft_set_ext *ext; + void *elem = NULL; + + list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + + if (!nft_set_elem_expired(ext) || + nft_set_elem_mark_busy(ext)) + continue; + + elem = catchall->elem; + list_del_rcu(&catchall->list); + kfree_rcu(catchall, rcu); + break; + } + + return elem; +} +EXPORT_SYMBOL_GPL(nft_set_catchall_gc); + +static int nft_setelem_catchall_insert(const struct net *net, + struct nft_set *set, + const struct nft_set_elem *elem, + struct nft_set_ext **pext) +{ + struct nft_set_elem_catchall *catchall; + u8 genmask = nft_genmask_next(net); + struct nft_set_ext *ext; + + list_for_each_entry(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (nft_set_elem_active(ext, genmask)) { + *pext = ext; + return -EEXIST; + } + } + + catchall = kmalloc(sizeof(*catchall), GFP_KERNEL); + if (!catchall) + return -ENOMEM; + + catchall->elem = elem->priv; + list_add_tail_rcu(&catchall->list, &set->catchall_list); + + return 0; +} + +static int nft_setelem_insert(const struct net *net, + struct nft_set *set, + const struct nft_set_elem *elem, + struct nft_set_ext **ext, unsigned int flags) +{ + int ret; + + if (flags & NFT_SET_ELEM_CATCHALL) + ret = nft_setelem_catchall_insert(net, set, elem, ext); + else + ret = set->ops->insert(net, set, elem, ext); + + return ret; +} + +static bool nft_setelem_is_catchall(const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && + *nft_set_ext_flags(ext) & NFT_SET_ELEM_CATCHALL) + return true; + + return false; +} + +static void nft_setelem_activate(struct net *net, struct nft_set *set, + struct nft_set_elem *elem) +{ + struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + + if (nft_setelem_is_catchall(set, elem)) { + nft_set_elem_change_active(net, set, ext); + nft_set_elem_clear_busy(ext); + } else { + set->ops->activate(net, set, elem); + } +} + +static int nft_setelem_catchall_deactivate(const struct net *net, + struct nft_set *set, + struct nft_set_elem *elem) +{ + struct nft_set_elem_catchall *catchall; + struct nft_set_ext *ext; + + list_for_each_entry(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_is_active(net, ext) || + nft_set_elem_mark_busy(ext)) + continue; + + kfree(elem->priv); + elem->priv = catchall->elem; + nft_set_elem_change_active(net, set, ext); + return 0; + } + + return -ENOENT; +} + +static int __nft_setelem_deactivate(const struct net *net, + struct nft_set *set, + struct nft_set_elem *elem) +{ + void *priv; + + priv = set->ops->deactivate(net, set, elem); + if (!priv) + return -ENOENT; + + kfree(elem->priv); + elem->priv = priv; + set->ndeact++; + + return 0; +} + +static int nft_setelem_deactivate(const struct net *net, + struct nft_set *set, + struct nft_set_elem *elem, u32 flags) +{ + int ret; + + if (flags & NFT_SET_ELEM_CATCHALL) + ret = nft_setelem_catchall_deactivate(net, set, elem); + else + ret = __nft_setelem_deactivate(net, set, elem); + + return ret; +} + +static void nft_setelem_catchall_remove(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_set_elem_catchall *catchall, *next; + + list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { + if (catchall->elem == elem->priv) { + list_del_rcu(&catchall->list); + kfree_rcu(catchall, rcu); + break; + } + } +} + +static void nft_setelem_remove(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) +{ + if (nft_setelem_is_catchall(set, elem)) + nft_setelem_catchall_remove(net, set, elem); + else + set->ops->remove(net, set, elem); +} + +static bool nft_setelem_valid_key_end(const struct nft_set *set, + struct nlattr **nla, u32 flags) +{ + if ((set->flags & (NFT_SET_CONCAT | NFT_SET_INTERVAL)) == + (NFT_SET_CONCAT | NFT_SET_INTERVAL)) { + if (flags & NFT_SET_ELEM_INTERVAL_END) + return false; + + if (nla[NFTA_SET_ELEM_KEY_END] && + flags & NFT_SET_ELEM_CATCHALL) + return false; + } else { + if (nla[NFTA_SET_ELEM_KEY_END]) + return false; + } + + return true; +} + static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr, u32 nlmsg_flags) { + struct nft_expr *expr_array[NFT_SET_EXPR_MAX] = {}; struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; u8 genmask = nft_genmask_next(ctx->net); + u32 flags = 0, size = 0, num_exprs = 0; struct nft_set_ext_tmpl tmpl; struct nft_set_ext *ext, *ext2; struct nft_set_elem elem; @@ -4885,30 +5891,32 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, struct nft_object *obj = NULL; struct nft_userdata *udata; struct nft_data_desc desc; - struct nft_data data; enum nft_registers dreg; struct nft_trans *trans; - u32 flags = 0; u64 timeout; u64 expiration; + int err, i; u8 ulen; - int err; err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr, nft_set_elem_policy, NULL); if (err < 0) return err; - if (nla[NFTA_SET_ELEM_KEY] == NULL) - return -EINVAL; - nft_set_ext_prepare(&tmpl); err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags); if (err < 0) return err; - if (flags != 0) - nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + + if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) + return -EINVAL; + + if (flags != 0) { + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + if (err < 0) + return err; + } if (set->flags & NFT_SET_MAP) { if (nla[NFTA_SET_ELEM_DATA] == NULL && @@ -4919,13 +5927,27 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, return -EINVAL; } + if (set->flags & NFT_SET_OBJECT) { + if (!nla[NFTA_SET_ELEM_OBJREF] && + !(flags & NFT_SET_ELEM_INTERVAL_END)) + return -EINVAL; + } else { + if (nla[NFTA_SET_ELEM_OBJREF]) + return -EINVAL; + } + + if (!nft_setelem_valid_key_end(set, nla, flags)) + return -EINVAL; + if ((flags & NFT_SET_ELEM_INTERVAL_END) && (nla[NFTA_SET_ELEM_DATA] || nla[NFTA_SET_ELEM_OBJREF] || nla[NFTA_SET_ELEM_TIMEOUT] || nla[NFTA_SET_ELEM_EXPIRATION] || nla[NFTA_SET_ELEM_USERDATA] || - nla[NFTA_SET_ELEM_EXPR])) + nla[NFTA_SET_ELEM_EXPR] || + nla[NFTA_SET_ELEM_KEY_END] || + nla[NFTA_SET_ELEM_EXPRESSIONS])) return -EINVAL; timeout = 0; @@ -4950,12 +5972,76 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, return err; } - err = nft_setelem_parse_key(ctx, set, &elem.key.val, - nla[NFTA_SET_ELEM_KEY]); - if (err < 0) - return err; + if (nla[NFTA_SET_ELEM_EXPR]) { + struct nft_expr *expr; + + if (set->num_exprs && set->num_exprs != 1) + return -EOPNOTSUPP; + + expr = nft_set_elem_expr_alloc(ctx, set, + nla[NFTA_SET_ELEM_EXPR]); + if (IS_ERR(expr)) + return PTR_ERR(expr); + + expr_array[0] = expr; + num_exprs = 1; + + if (set->num_exprs && set->exprs[0]->ops != expr->ops) { + err = -EOPNOTSUPP; + goto err_set_elem_expr; + } + } else if (nla[NFTA_SET_ELEM_EXPRESSIONS]) { + struct nft_expr *expr; + struct nlattr *tmp; + int left; + + i = 0; + nla_for_each_nested(tmp, nla[NFTA_SET_ELEM_EXPRESSIONS], left) { + if (i == NFT_SET_EXPR_MAX || + (set->num_exprs && set->num_exprs == i)) { + err = -E2BIG; + goto err_set_elem_expr; + } + if (nla_type(tmp) != NFTA_LIST_ELEM) { + err = -EINVAL; + goto err_set_elem_expr; + } + expr = nft_set_elem_expr_alloc(ctx, set, tmp); + if (IS_ERR(expr)) { + err = PTR_ERR(expr); + goto err_set_elem_expr; + } + expr_array[i] = expr; + num_exprs++; + + if (set->num_exprs && expr->ops != set->exprs[i]->ops) { + err = -EOPNOTSUPP; + goto err_set_elem_expr; + } + i++; + } + if (set->num_exprs && set->num_exprs != i) { + err = -EOPNOTSUPP; + goto err_set_elem_expr; + } + } else if (set->num_exprs > 0) { + err = nft_set_elem_expr_clone(ctx, set, expr_array); + if (err < 0) + goto err_set_elem_expr_clone; + + num_exprs = set->num_exprs; + } + + if (nla[NFTA_SET_ELEM_KEY]) { + err = nft_setelem_parse_key(ctx, set, &elem.key.val, + nla[NFTA_SET_ELEM_KEY]); + if (err < 0) + goto err_set_elem_expr; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + if (err < 0) + goto err_parse_key; + } if (nla[NFTA_SET_ELEM_KEY_END]) { err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, @@ -4963,20 +6049,34 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) goto err_parse_key; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + if (err < 0) + goto err_parse_key_end; } if (timeout > 0) { - nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION); - if (timeout != set->timeout) - nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT); + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION); + if (err < 0) + goto err_parse_key_end; + + if (timeout != set->timeout) { + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT); + if (err < 0) + goto err_parse_key_end; + } } - if (nla[NFTA_SET_ELEM_OBJREF] != NULL) { - if (!(set->flags & NFT_SET_OBJECT)) { - err = -EINVAL; + if (num_exprs) { + for (i = 0; i < num_exprs; i++) + size += expr_array[i]->ops->size; + + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS, + sizeof(struct nft_set_elem_expr) + size); + if (err < 0) goto err_parse_key_end; - } + } + + if (nla[NFTA_SET_ELEM_OBJREF] != NULL) { obj = nft_obj_lookup(ctx->net, ctx->table, nla[NFTA_SET_ELEM_OBJREF], set->objtype, genmask); @@ -4984,19 +6084,17 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = PTR_ERR(obj); goto err_parse_key_end; } - nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); + if (err < 0) + goto err_parse_key_end; } if (nla[NFTA_SET_ELEM_DATA] != NULL) { - err = nft_data_init(ctx, &data, sizeof(data), &desc, - nla[NFTA_SET_ELEM_DATA]); + err = nft_setelem_parse_data(ctx, set, &desc, &elem.data.val, + nla[NFTA_SET_ELEM_DATA]); if (err < 0) goto err_parse_key_end; - err = -EINVAL; - if (set->dtype != NFT_DATA_VERDICT && desc.len != set->dlen) - goto err_parse_data; - dreg = nft_type_to_reg(set->dtype); list_for_each_entry(binding, &set->bindings, list) { struct nft_ctx bind_ctx = { @@ -5010,19 +6108,21 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, continue; err = nft_validate_register_store(&bind_ctx, dreg, - &data, + &elem.data.val, desc.type, desc.len); if (err < 0) goto err_parse_data; if (desc.type == NFT_DATA_VERDICT && - (data.verdict.code == NFT_GOTO || - data.verdict.code == NFT_JUMP)) + (elem.data.val.verdict.code == NFT_GOTO || + elem.data.val.verdict.code == NFT_JUMP)) nft_validate_state_update(ctx->net, NFT_VALIDATE_NEED); } - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len); + if (err < 0) + goto err_parse_data; } /* The full maximum length of userdata can exceed the maximum @@ -5032,22 +6132,31 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, ulen = 0; if (nla[NFTA_SET_ELEM_USERDATA] != NULL) { ulen = nla_len(nla[NFTA_SET_ELEM_USERDATA]); - if (ulen > 0) - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA, - ulen); + if (ulen > 0) { + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA, + ulen); + if (err < 0) + goto err_parse_data; + } } - err = -ENOMEM; elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, - elem.key_end.val.data, data.data, - timeout, expiration, GFP_KERNEL); - if (elem.priv == NULL) + elem.key_end.val.data, elem.data.val.data, + timeout, expiration, GFP_KERNEL_ACCOUNT); + if (IS_ERR(elem.priv)) { + err = PTR_ERR(elem.priv); goto err_parse_data; + } ext = nft_set_elem_ext(set, elem.priv); if (flags) *nft_set_ext_flags(ext) = flags; + if (ulen > 0) { + if (nft_set_ext_check(&tmpl, NFT_SET_EXT_USERDATA, ulen) < 0) { + err = -EINVAL; + goto err_elem_userdata; + } udata = nft_set_ext_userdata(ext); udata->len = ulen - 1; nla_memcpy(&udata->data, nla[NFTA_SET_ELEM_USERDATA], ulen); @@ -5056,22 +6165,26 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, *nft_set_ext_obj(ext) = obj; obj->use++; } + err = nft_set_elem_expr_setup(ctx, &tmpl, ext, expr_array, num_exprs); + if (err < 0) + goto err_elem_free; trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set); - if (trans == NULL) - goto err_trans; + if (trans == NULL) { + err = -ENOMEM; + goto err_elem_free; + } ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK; - err = set->ops->insert(ctx->net, set, &elem, &ext2); + + err = nft_setelem_insert(ctx->net, set, &elem, &ext2, flags); if (err) { if (err == -EEXIST) { if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) ^ nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) || nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) ^ - nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF)) { - err = -EBUSY; + nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF)) goto err_element_clash; - } if ((nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) && memcmp(nft_set_ext_data(ext), @@ -5079,49 +6192,62 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) && nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF) && *nft_set_ext_obj(ext) != *nft_set_ext_obj(ext2))) - err = -EBUSY; + goto err_element_clash; else if (!(nlmsg_flags & NLM_F_EXCL)) err = 0; + } else if (err == -ENOTEMPTY) { + /* ENOTEMPTY reports overlapping between this element + * and an existing one. + */ + err = -EEXIST; } goto err_element_clash; } - if (set->size && + if (!(flags & NFT_SET_ELEM_CATCHALL) && set->size && !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact)) { err = -ENFILE; goto err_set_full; } nft_trans_elem(trans) = elem; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_set_full: - set->ops->remove(ctx->net, set, &elem); + nft_setelem_remove(ctx->net, set, &elem); err_element_clash: kfree(trans); -err_trans: +err_elem_free: if (obj) obj->use--; - kfree(elem.priv); +err_elem_userdata: + nf_tables_set_elem_destroy(ctx, set, elem.priv); err_parse_data: if (nla[NFTA_SET_ELEM_DATA] != NULL) - nft_data_release(&data, desc.type); + nft_data_release(&elem.data.val, desc.type); err_parse_key_end: nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); err_parse_key: nft_data_release(&elem.key.val, NFT_DATA_VALUE); - +err_set_elem_expr: + for (i = 0; i < num_exprs && expr_array[i]; i++) + nft_expr_destroy(ctx, expr_array[i]); +err_set_elem_expr_clone: return err; } -static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_newsetelem(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) { - u8 genmask = nft_genmask_next(net); + struct nftables_pernet *nft_net = nft_pernet(info->net); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; + struct net *net = info->net; const struct nlattr *attr; + struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; int rem, err; @@ -5129,12 +6255,14 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) return -EINVAL; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, - genmask); - if (err < 0) - return err; + table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, + genmask, NETLINK_CB(skb).portid); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); + return PTR_ERR(table); + } - set = nft_set_lookup_global(net, ctx.table, nla[NFTA_SET_ELEM_LIST_SET], + set = nft_set_lookup_global(net, table, nla[NFTA_SET_ELEM_LIST_SET], nla[NFTA_SET_ELEM_LIST_SET_ID], genmask); if (IS_ERR(set)) return PTR_ERR(set); @@ -5142,14 +6270,18 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) return -EBUSY; + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { - err = nft_add_set_elem(&ctx, set, attr, nlh->nlmsg_flags); - if (err < 0) + err = nft_add_set_elem(&ctx, set, attr, info->nlh->nlmsg_flags); + if (err < 0) { + NL_SET_BAD_ATTR(extack, attr); return err; + } } - if (net->nft.validate_state == NFT_VALIDATE_DO) - return nft_table_validate(net, ctx.table); + if (nft_net->validate_state == NFT_VALIDATE_DO) + return nft_table_validate(net, table); return 0; } @@ -5167,19 +6299,32 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, */ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) { + struct nft_chain *chain; + struct nft_rule *rule; + if (type == NFT_DATA_VERDICT) { switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: - data->verdict.chain->use++; + chain = data->verdict.chain; + chain->use++; + + if (!nft_chain_is_bound(chain)) + break; + + chain->table->use++; + list_for_each_entry(rule, &chain->rules, list) + chain->use++; + + nft_chain_add(chain->table, chain); break; } } } -static void nft_set_elem_activate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +static void nft_setelem_data_activate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -5189,9 +6334,9 @@ static void nft_set_elem_activate(const struct net *net, (*nft_set_ext_obj(ext))->use++; } -static void nft_set_elem_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +static void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -5210,7 +6355,6 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, struct nft_set_ext *ext; struct nft_trans *trans; u32 flags = 0; - void *priv; int err; err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr, @@ -5218,39 +6362,54 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) return err; - if (nla[NFTA_SET_ELEM_KEY] == NULL) + err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags); + if (err < 0) + return err; + + if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) + return -EINVAL; + + if (!nft_setelem_valid_key_end(set, nla, flags)) return -EINVAL; nft_set_ext_prepare(&tmpl); - err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags); - if (err < 0) - return err; - if (flags != 0) - nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + if (flags != 0) { + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + if (err < 0) + return err; + } - err = nft_setelem_parse_key(ctx, set, &elem.key.val, - nla[NFTA_SET_ELEM_KEY]); - if (err < 0) - return err; + if (nla[NFTA_SET_ELEM_KEY]) { + err = nft_setelem_parse_key(ctx, set, &elem.key.val, + nla[NFTA_SET_ELEM_KEY]); + if (err < 0) + return err; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + if (err < 0) + goto fail_elem; + } if (nla[NFTA_SET_ELEM_KEY_END]) { err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, nla[NFTA_SET_ELEM_KEY_END]); if (err < 0) - return err; + goto fail_elem; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + if (err < 0) + goto fail_elem_key_end; } err = -ENOMEM; elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, elem.key_end.val.data, NULL, 0, 0, - GFP_KERNEL); - if (elem.priv == NULL) - goto fail_elem; + GFP_KERNEL_ACCOUNT); + if (IS_ERR(elem.priv)) { + err = PTR_ERR(elem.priv); + goto fail_elem_key_end; + } ext = nft_set_elem_ext(set, elem.priv); if (flags) @@ -5260,33 +6419,31 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (trans == NULL) goto fail_trans; - priv = set->ops->deactivate(ctx->net, set, &elem); - if (priv == NULL) { - err = -ENOENT; + err = nft_setelem_deactivate(ctx->net, set, &elem, flags); + if (err < 0) goto fail_ops; - } - kfree(elem.priv); - elem.priv = priv; - nft_set_elem_deactivate(ctx->net, set, &elem); + nft_setelem_data_deactivate(ctx->net, set, &elem); nft_trans_elem(trans) = elem; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; fail_ops: kfree(trans); fail_trans: kfree(elem.priv); +fail_elem_key_end: + nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); fail_elem: nft_data_release(&elem.key.val, NFT_DATA_VALUE); return err; } -static int nft_flush_set(const struct nft_ctx *ctx, - struct nft_set *set, - const struct nft_set_iter *iter, - struct nft_set_elem *elem) +static int nft_setelem_flush(const struct nft_ctx *ctx, + struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) { struct nft_trans *trans; int err; @@ -5302,10 +6459,10 @@ static int nft_flush_set(const struct nft_ctx *ctx, } set->ndeact++; - nft_set_elem_deactivate(ctx->net, set, elem); + nft_setelem_data_deactivate(ctx->net, set, elem); nft_trans_elem_set(trans) = set; nft_trans_elem(trans) = *elem; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err1: @@ -5313,44 +6470,101 @@ err1: return err; } -static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int __nft_set_catchall_flush(const struct nft_ctx *ctx, + struct nft_set *set, + struct nft_set_elem *elem) { - u8 genmask = nft_genmask_next(net); + struct nft_trans *trans; + + trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM, + sizeof(struct nft_trans_elem), GFP_KERNEL); + if (!trans) + return -ENOMEM; + + nft_setelem_data_deactivate(ctx->net, set, elem); + nft_trans_elem_set(trans) = set; + nft_trans_elem(trans) = *elem; + nft_trans_commit_list_add_tail(ctx->net, trans); + + return 0; +} + +static int nft_set_catchall_flush(const struct nft_ctx *ctx, + struct nft_set *set) +{ + u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_elem_catchall *catchall; + struct nft_set_elem elem; + struct nft_set_ext *ext; + int ret = 0; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask) || + nft_set_elem_mark_busy(ext)) + continue; + + elem.priv = catchall->elem; + ret = __nft_set_catchall_flush(ctx, set, &elem); + if (ret < 0) + break; + } + + return ret; +} + +static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask) +{ + struct nft_set_iter iter = { + .genmask = genmask, + .fn = nft_setelem_flush, + }; + + set->ops->walk(ctx, set, &iter); + if (!iter.err) + iter.err = nft_set_catchall_flush(ctx, set); + + return iter.err; +} + +static int nf_tables_delsetelem(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; + struct net *net = info->net; const struct nlattr *attr; + struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; int rem, err = 0; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, - genmask); - if (err < 0) - return err; + table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, + genmask, NETLINK_CB(skb).portid); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); + return PTR_ERR(table); + } - set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask); + set = nft_set_lookup(table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) return PTR_ERR(set); if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) return -EBUSY; - if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) { - struct nft_set_iter iter = { - .genmask = genmask, - .fn = nft_flush_set, - }; - set->ops->walk(&ctx, set, &iter); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); - return iter.err; - } + if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) + return nft_set_flush(&ctx, set, genmask); nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_del_setelem(&ctx, set, attr); - if (err < 0) + if (err < 0) { + NL_SET_BAD_ATTR(extack, attr); break; - - set->ndeact++; + } } return err; } @@ -5365,7 +6579,6 @@ void nft_set_gc_batch_release(struct rcu_head *rcu) nft_set_elem_destroy(gcb->head.set, gcb->elems[i], true); kfree(gcb); } -EXPORT_SYMBOL_GPL(nft_set_gc_batch_release); struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, gfp_t gfp) @@ -5378,7 +6591,6 @@ struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, gcb->head.set = set; return gcb; } -EXPORT_SYMBOL_GPL(nft_set_gc_batch_alloc); /* * Stateful objects @@ -5386,7 +6598,7 @@ EXPORT_SYMBOL_GPL(nft_set_gc_batch_alloc); /** * nft_register_obj- register nf_tables stateful object type - * @obj: object type + * @obj_type: object type * * Registers the object type for use with nf_tables. Returns zero on * success or a negative errno code otherwise. @@ -5405,7 +6617,7 @@ EXPORT_SYMBOL_GPL(nft_register_obj); /** * nft_unregister_obj - unregister nf_tables object type - * @obj: object type + * @obj_type: object type * * Unregisters the object type for use with nf_tables. */ @@ -5427,7 +6639,7 @@ struct nft_object *nft_obj_lookup(const struct net *net, struct rhlist_head *tmp, *list; struct nft_object *obj; - nla_strlcpy(search, nla, sizeof(search)); + nla_strscpy(search, nla, sizeof(search)); k.name = search; WARN_ON_ONCE(!rcu_read_lock_held() && @@ -5474,6 +6686,8 @@ static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = { [NFTA_OBJ_TYPE] = { .type = NLA_U32 }, [NFTA_OBJ_DATA] = { .type = NLA_NESTED }, [NFTA_OBJ_HANDLE] = { .type = NLA_U64}, + [NFTA_OBJ_USERDATA] = { .type = NLA_BINARY, + .len = NFT_USERDATA_MAXLEN }, }; static struct nft_object *nft_obj_init(const struct nft_ctx *ctx, @@ -5509,7 +6723,7 @@ static struct nft_object *nft_obj_init(const struct nft_ctx *ctx, } err = -ENOMEM; - obj = kzalloc(sizeof(*obj) + ops->size, GFP_KERNEL); + obj = kzalloc(sizeof(*obj) + ops->size, GFP_KERNEL_ACCOUNT); if (!obj) goto err2; @@ -5583,12 +6797,15 @@ static int nf_tables_updobj(const struct nft_ctx *ctx, { struct nft_object *newobj; struct nft_trans *trans; - int err; + int err = -ENOMEM; + + if (!try_module_get(type->owner)) + return -ENOENT; trans = nft_trans_alloc(ctx, NFT_MSG_NEWOBJ, sizeof(struct nft_trans_obj)); if (!trans) - return -ENOMEM; + goto err_trans; newobj = nft_obj_init(ctx, type, attr); if (IS_ERR(newobj)) { @@ -5599,24 +6816,25 @@ static int nf_tables_updobj(const struct nft_ctx *ctx, nft_trans_obj(trans) = obj; nft_trans_obj_update(trans) = true; nft_trans_obj_newobj(trans) = newobj; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_free_trans: kfree(trans); +err_trans: + module_put(type->owner); return err; } -static int nf_tables_newobj(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; const struct nft_object_type *type; - u8 genmask = nft_genmask_next(net); - int family = nfmsg->nfgen_family; + struct net *net = info->net; struct nft_table *table; struct nft_object *obj; struct nft_ctx ctx; @@ -5628,7 +6846,8 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, !nla[NFTA_OBJ_DATA]) return -EINVAL; - table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); @@ -5643,20 +6862,20 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, return err; } } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) { + if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return -EEXIST; } - if (nlh->nlmsg_flags & NLM_F_REPLACE) + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; type = __nft_obj_type_get(objtype); - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); return nf_tables_updobj(&ctx, type, nla[NFTA_OBJ_DATA], obj); } - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); type = nft_obj_type_get(net, objtype); if (IS_ERR(type)) @@ -5665,40 +6884,50 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]); if (IS_ERR(obj)) { err = PTR_ERR(obj); - goto err1; + goto err_init; } obj->key.table = table; obj->handle = nf_tables_alloc_handle(table); - obj->key.name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL); + obj->key.name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL_ACCOUNT); if (!obj->key.name) { err = -ENOMEM; - goto err2; + goto err_strdup; + } + + if (nla[NFTA_OBJ_USERDATA]) { + obj->udata = nla_memdup(nla[NFTA_OBJ_USERDATA], GFP_KERNEL); + if (obj->udata == NULL) + goto err_userdata; + + obj->udlen = nla_len(nla[NFTA_OBJ_USERDATA]); } err = nft_trans_obj_add(&ctx, NFT_MSG_NEWOBJ, obj); if (err < 0) - goto err3; + goto err_trans; err = rhltable_insert(&nft_objname_ht, &obj->rhlhead, nft_objname_ht_params); if (err < 0) - goto err4; + goto err_obj_ht; list_add_tail_rcu(&obj->list, &table->objects); table->use++; return 0; -err4: +err_obj_ht: /* queued in transaction log */ INIT_LIST_HEAD(&obj->list); return err; -err3: +err_trans: + kfree(obj->udata); +err_userdata: kfree(obj->key.name); -err2: +err_strdup: if (obj->ops->destroy) obj->ops->destroy(&ctx, obj); kfree(obj); -err1: +err_init: module_put(type->owner); return err; } @@ -5708,19 +6937,14 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, int family, const struct nft_table *table, struct nft_object *obj, bool reset) { - struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_OBJ_TABLE, table->name) || nla_put_string(skb, NFTA_OBJ_NAME, obj->key.name) || nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->ops->type->type)) || @@ -5730,6 +6954,10 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, NFTA_OBJ_PAD)) goto nla_put_failure; + if (obj->udata && + nla_put(skb, NFTA_OBJ_USERDATA, obj->udlen, obj->udata)) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; @@ -5751,6 +6979,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) struct nft_obj_filter *filter = cb->data; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net; struct nft_object *obj; bool reset = false; @@ -5758,9 +6987,10 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) reset = true; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = nft_pernet(net); + cb->seq = READ_ONCE(nft_net->base_seq); - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -5779,6 +7009,19 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) filter->type != NFT_OBJECT_UNSPEC && obj->ops->type->type != filter->type) goto cont; + if (reset) { + char *buf = kasprintf(GFP_ATOMIC, + "%s:%u", + table->name, + nft_net->base_seq); + + audit_log_nfcfg(buf, + family, + obj->handle, + AUDIT_NFT_OP_OBJ_RESET, + GFP_ATOMIC); + kfree(buf); + } if (nf_tables_fill_obj_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, @@ -5839,22 +7082,21 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb) } /* called with rcu_read_lock held */ -static int nf_tables_getobj(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_cur(net); - int family = nfmsg->nfgen_family; + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_cur(info->net); + u8 family = info->nfmsg->nfgen_family; const struct nft_table *table; + struct net *net = info->net; struct nft_object *obj; struct sk_buff *skb2; bool reset = false; u32 objtype; int err; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_obj_start, .dump = nf_tables_dump_obj, @@ -5863,14 +7105,14 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, .data = (void *)nla, }; - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!nla[NFTA_OBJ_NAME] || !nla[NFTA_OBJ_TYPE]) return -EINVAL; - table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); @@ -5887,17 +7129,33 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, if (!skb2) return -ENOMEM; - if (NFNL_MSG_TYPE(nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) + if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) reset = true; + if (reset) { + const struct nftables_pernet *nft_net; + char *buf; + + nft_net = nft_pernet(net); + buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, nft_net->base_seq); + + audit_log_nfcfg(buf, + family, + obj->handle, + AUDIT_NFT_OP_OBJ_RESET, + GFP_ATOMIC); + kfree(buf); + } + err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, + info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, family, table, obj, reset); if (err < 0) - goto err; + goto err_fill_obj_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); -err: + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + +err_fill_obj_info: kfree_skb(skb2); return err; } @@ -5909,17 +7167,17 @@ static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) module_put(obj->ops->type->owner); kfree(obj->key.name); + kfree(obj->udata); kfree(obj); } -static int nf_tables_delobj(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); - int family = nfmsg->nfgen_family; + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; + struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_object *obj; @@ -5930,7 +7188,8 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk, (!nla[NFTA_OBJ_NAME] && !nla[NFTA_OBJ_HANDLE])) return -EINVAL; - table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); @@ -5954,17 +7213,29 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk, return -EBUSY; } - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); return nft_delobj(&ctx, obj); } void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, - int family, int report, gfp_t gfp) + u16 flags, int family, int report, gfp_t gfp) { + struct nftables_pernet *nft_net = nft_pernet(net); struct sk_buff *skb; int err; + char *buf = kasprintf(gfp, "%s:%u", + table->name, nft_net->base_seq); + + audit_log_nfcfg(buf, + family, + obj->handle, + event == NFT_MSG_NEWOBJ ? + AUDIT_NFT_OP_OBJ_REGISTER : + AUDIT_NFT_OP_OBJ_UNREGISTER, + gfp); + kfree(buf); if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) @@ -5974,14 +7245,15 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, if (skb == NULL) goto err; - err = nf_tables_fill_obj_info(skb, net, portid, seq, event, 0, family, - table, obj, false); + err = nf_tables_fill_obj_info(skb, net, portid, seq, event, + flags & (NLM_F_CREATE | NLM_F_EXCL), + family, table, obj, false); if (err < 0) { kfree_skb(skb); goto err; } - nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report, gfp); + nft_notify_enqueue(skb, report, &nft_net->notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -5992,7 +7264,7 @@ static void nf_tables_obj_notify(const struct nft_ctx *ctx, struct nft_object *obj, int event) { nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, ctx->seq, event, - ctx->family, ctx->report, GFP_KERNEL); + ctx->flags, ctx->family, ctx->report, GFP_KERNEL); } /* @@ -6047,7 +7319,7 @@ void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: flowtable->use--; - /* fall through */ + fallthrough; default: return; } @@ -6068,50 +7340,77 @@ nft_flowtable_lookup_byhandle(const struct nft_table *table, return ERR_PTR(-ENOENT); } +struct nft_flowtable_hook { + u32 num; + int priority; + struct list_head list; +}; + static const struct nla_policy nft_flowtable_hook_policy[NFTA_FLOWTABLE_HOOK_MAX + 1] = { [NFTA_FLOWTABLE_HOOK_NUM] = { .type = NLA_U32 }, [NFTA_FLOWTABLE_HOOK_PRIORITY] = { .type = NLA_U32 }, [NFTA_FLOWTABLE_HOOK_DEVS] = { .type = NLA_NESTED }, }; -static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx, - const struct nlattr *attr, - struct nft_flowtable *flowtable) +static int nft_flowtable_parse_hook(const struct nft_ctx *ctx, + const struct nlattr *attr, + struct nft_flowtable_hook *flowtable_hook, + struct nft_flowtable *flowtable, bool add) { struct nlattr *tb[NFTA_FLOWTABLE_HOOK_MAX + 1]; struct nft_hook *hook; int hooknum, priority; int err; + INIT_LIST_HEAD(&flowtable_hook->list); + err = nla_parse_nested_deprecated(tb, NFTA_FLOWTABLE_HOOK_MAX, attr, nft_flowtable_hook_policy, NULL); if (err < 0) return err; - if (!tb[NFTA_FLOWTABLE_HOOK_NUM] || - !tb[NFTA_FLOWTABLE_HOOK_PRIORITY] || - !tb[NFTA_FLOWTABLE_HOOK_DEVS]) - return -EINVAL; + if (add) { + if (!tb[NFTA_FLOWTABLE_HOOK_NUM] || + !tb[NFTA_FLOWTABLE_HOOK_PRIORITY]) + return -EINVAL; - hooknum = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_NUM])); - if (hooknum != NF_NETDEV_INGRESS) - return -EINVAL; + hooknum = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_NUM])); + if (hooknum != NF_NETDEV_INGRESS) + return -EOPNOTSUPP; - priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY])); + priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY])); - err = nf_tables_parse_netdev_hooks(ctx->net, - tb[NFTA_FLOWTABLE_HOOK_DEVS], - &flowtable->hook_list); - if (err < 0) - return err; + flowtable_hook->priority = priority; + flowtable_hook->num = hooknum; + } else { + if (tb[NFTA_FLOWTABLE_HOOK_NUM]) { + hooknum = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_NUM])); + if (hooknum != flowtable->hooknum) + return -EOPNOTSUPP; + } - flowtable->hooknum = hooknum; - flowtable->data.priority = priority; + if (tb[NFTA_FLOWTABLE_HOOK_PRIORITY]) { + priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY])); + if (priority != flowtable->data.priority) + return -EOPNOTSUPP; + } - list_for_each_entry(hook, &flowtable->hook_list, list) { + flowtable_hook->priority = flowtable->data.priority; + flowtable_hook->num = flowtable->hooknum; + } + + if (tb[NFTA_FLOWTABLE_HOOK_DEVS]) { + err = nf_tables_parse_netdev_hooks(ctx->net, + tb[NFTA_FLOWTABLE_HOOK_DEVS], + &flowtable_hook->list); + if (err < 0) + return err; + } + + list_for_each_entry(hook, &flowtable_hook->list, list) { hook->ops.pf = NFPROTO_NETDEV; - hook->ops.hooknum = hooknum; - hook->ops.priority = priority; + hook->ops.hooknum = flowtable_hook->num; + hook->ops.priority = flowtable_hook->priority; hook->ops.priv = &flowtable->data; hook->ops.hook = flowtable->data.type->hook; } @@ -6159,29 +7458,45 @@ static void nft_unregister_flowtable_hook(struct net *net, FLOW_BLOCK_UNBIND); } -static void nft_unregister_flowtable_net_hooks(struct net *net, - struct nft_flowtable *flowtable) +static void __nft_unregister_flowtable_net_hooks(struct net *net, + struct list_head *hook_list, + bool release_netdev) { - struct nft_hook *hook; + struct nft_hook *hook, *next; - list_for_each_entry(hook, &flowtable->hook_list, list) + list_for_each_entry_safe(hook, next, hook_list, list) { nf_unregister_net_hook(net, &hook->ops); + if (release_netdev) { + list_del(&hook->list); + kfree_rcu(hook, rcu); + } + } +} + +static void nft_unregister_flowtable_net_hooks(struct net *net, + struct list_head *hook_list) +{ + __nft_unregister_flowtable_net_hooks(net, hook_list, false); } static int nft_register_flowtable_net_hooks(struct net *net, struct nft_table *table, + struct list_head *hook_list, struct nft_flowtable *flowtable) { struct nft_hook *hook, *hook2, *next; struct nft_flowtable *ft; int err, i = 0; - list_for_each_entry(hook, &flowtable->hook_list, list) { + list_for_each_entry(hook, hook_list, list) { list_for_each_entry(ft, &table->flowtables, list) { + if (!nft_is_active_next(net, ft)) + continue; + list_for_each_entry(hook2, &ft->hook_list, list) { if (hook->ops.dev == hook2->ops.dev && hook->ops.pf == hook2->ops.pf) { - err = -EBUSY; + err = -EEXIST; goto err_unregister_net_hooks; } } @@ -6207,7 +7522,7 @@ static int nft_register_flowtable_net_hooks(struct net *net, return 0; err_unregister_net_hooks: - list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { + list_for_each_entry_safe(hook, next, hook_list, list) { if (i-- <= 0) break; @@ -6219,18 +7534,101 @@ err_unregister_net_hooks: return err; } -static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static void nft_flowtable_hooks_destroy(struct list_head *hook_list) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + struct nft_hook *hook, *next; + + list_for_each_entry_safe(hook, next, hook_list, list) { + list_del_rcu(&hook->list); + kfree_rcu(hook, rcu); + } +} + +static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, + struct nft_flowtable *flowtable) +{ + const struct nlattr * const *nla = ctx->nla; + struct nft_flowtable_hook flowtable_hook; + struct nft_hook *hook, *next; + struct nft_trans *trans; + bool unregister = false; + u32 flags; + int err; + + err = nft_flowtable_parse_hook(ctx, nla[NFTA_FLOWTABLE_HOOK], + &flowtable_hook, flowtable, false); + if (err < 0) + return err; + + list_for_each_entry_safe(hook, next, &flowtable_hook.list, list) { + if (nft_hook_list_find(&flowtable->hook_list, hook)) { + list_del(&hook->list); + kfree(hook); + } + } + + if (nla[NFTA_FLOWTABLE_FLAGS]) { + flags = ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS])); + if (flags & ~NFT_FLOWTABLE_MASK) { + err = -EOPNOTSUPP; + goto err_flowtable_update_hook; + } + if ((flowtable->data.flags & NFT_FLOWTABLE_HW_OFFLOAD) ^ + (flags & NFT_FLOWTABLE_HW_OFFLOAD)) { + err = -EOPNOTSUPP; + goto err_flowtable_update_hook; + } + } else { + flags = flowtable->data.flags; + } + + err = nft_register_flowtable_net_hooks(ctx->net, ctx->table, + &flowtable_hook.list, flowtable); + if (err < 0) + goto err_flowtable_update_hook; + + trans = nft_trans_alloc(ctx, NFT_MSG_NEWFLOWTABLE, + sizeof(struct nft_trans_flowtable)); + if (!trans) { + unregister = true; + err = -ENOMEM; + goto err_flowtable_update_hook; + } + + nft_trans_flowtable_flags(trans) = flags; + nft_trans_flowtable(trans) = flowtable; + nft_trans_flowtable_update(trans) = true; + INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); + list_splice(&flowtable_hook.list, &nft_trans_flowtable_hooks(trans)); + + nft_trans_commit_list_add_tail(ctx->net, trans); + + return 0; + +err_flowtable_update_hook: + list_for_each_entry_safe(hook, next, &flowtable_hook.list, list) { + if (unregister) + nft_unregister_flowtable_hook(ctx->net, flowtable, hook); + list_del_rcu(&hook->list); + kfree_rcu(hook, rcu); + } + + return err; + +} + +static int nf_tables_newflowtable(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct netlink_ext_ack *extack = info->extack; + struct nft_flowtable_hook flowtable_hook; + u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; const struct nf_flowtable_type *type; - u8 genmask = nft_genmask_next(net); - int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; struct nft_hook *hook, *next; + struct net *net = info->net; struct nft_table *table; struct nft_ctx ctx; int err; @@ -6241,7 +7639,7 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, return -EINVAL; table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, - genmask); + genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); @@ -6256,17 +7654,19 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, return err; } } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) { + if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); return -EEXIST; } - return 0; + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + + return nft_flowtable_update(&ctx, info->nlh, flowtable); } - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); - flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL); + flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL_ACCOUNT); if (!flowtable) return -ENOMEM; @@ -6274,7 +7674,7 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, flowtable->handle = nf_tables_alloc_handle(table); INIT_LIST_HEAD(&flowtable->hook_list); - flowtable->name = nla_strdup(nla[NFTA_FLOWTABLE_NAME], GFP_KERNEL); + flowtable->name = nla_strdup(nla[NFTA_FLOWTABLE_NAME], GFP_KERNEL_ACCOUNT); if (!flowtable->name) { err = -ENOMEM; goto err1; @@ -6289,8 +7689,10 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, if (nla[NFTA_FLOWTABLE_FLAGS]) { flowtable->data.flags = ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS])); - if (flowtable->data.flags & ~NF_FLOWTABLE_HW_OFFLOAD) + if (flowtable->data.flags & ~NFT_FLOWTABLE_MASK) { + err = -EOPNOTSUPP; goto err3; + } } write_pnet(&flowtable->data.net, net); @@ -6299,17 +7701,20 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, if (err < 0) goto err3; - err = nf_tables_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK], - flowtable); + err = nft_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK], + &flowtable_hook, flowtable, true); if (err < 0) goto err4; - err = nft_register_flowtable_net_hooks(ctx.net, table, flowtable); + list_splice(&flowtable_hook.list, &flowtable->hook_list); + flowtable->data.priority = flowtable_hook.priority; + flowtable->hooknum = flowtable_hook.num; + + err = nft_register_flowtable_net_hooks(ctx.net, table, + &flowtable->hook_list, + flowtable); if (err < 0) { - list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { - list_del_rcu(&hook->list); - kfree_rcu(hook, rcu); - } + nft_flowtable_hooks_destroy(&flowtable->hook_list); goto err4; } @@ -6338,16 +7743,73 @@ err1: return err; } -static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static void nft_flowtable_hook_release(struct nft_flowtable_hook *flowtable_hook) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); - int family = nfmsg->nfgen_family; + struct nft_hook *this, *next; + + list_for_each_entry_safe(this, next, &flowtable_hook->list, list) { + list_del(&this->list); + kfree(this); + } +} + +static int nft_delflowtable_hook(struct nft_ctx *ctx, + struct nft_flowtable *flowtable) +{ + const struct nlattr * const *nla = ctx->nla; + struct nft_flowtable_hook flowtable_hook; + LIST_HEAD(flowtable_del_list); + struct nft_hook *this, *hook; + struct nft_trans *trans; + int err; + + err = nft_flowtable_parse_hook(ctx, nla[NFTA_FLOWTABLE_HOOK], + &flowtable_hook, flowtable, false); + if (err < 0) + return err; + + list_for_each_entry(this, &flowtable_hook.list, list) { + hook = nft_hook_list_find(&flowtable->hook_list, this); + if (!hook) { + err = -ENOENT; + goto err_flowtable_del_hook; + } + list_move(&hook->list, &flowtable_del_list); + } + + trans = nft_trans_alloc(ctx, NFT_MSG_DELFLOWTABLE, + sizeof(struct nft_trans_flowtable)); + if (!trans) { + err = -ENOMEM; + goto err_flowtable_del_hook; + } + + nft_trans_flowtable(trans) = flowtable; + nft_trans_flowtable_update(trans) = true; + INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); + list_splice(&flowtable_del_list, &nft_trans_flowtable_hooks(trans)); + nft_flowtable_hook_release(&flowtable_hook); + + nft_trans_commit_list_add_tail(ctx->net, trans); + + return 0; + +err_flowtable_del_hook: + list_splice(&flowtable_del_list, &flowtable->hook_list); + nft_flowtable_hook_release(&flowtable_hook); + + return err; +} + +static int nf_tables_delflowtable(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; struct nft_flowtable *flowtable; + struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_ctx ctx; @@ -6358,7 +7820,7 @@ static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, return -EINVAL; table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, - genmask); + genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); @@ -6376,36 +7838,36 @@ static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(flowtable); } + + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + + if (nla[NFTA_FLOWTABLE_HOOK]) + return nft_delflowtable_hook(&ctx, flowtable); + if (flowtable->use > 0) { NL_SET_BAD_ATTR(extack, attr); return -EBUSY; } - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); - return nft_delflowtable(&ctx, flowtable); } static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, - struct nft_flowtable *flowtable) + struct nft_flowtable *flowtable, + struct list_head *hook_list) { struct nlattr *nest, *nest_devs; - struct nfgenmsg *nfmsg; struct nft_hook *hook; struct nlmsghdr *nlh; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_FLOWTABLE_TABLE, flowtable->table->name) || nla_put_string(skb, NFTA_FLOWTABLE_NAME, flowtable->name) || nla_put_be32(skb, NFTA_FLOWTABLE_USE, htonl(flowtable->use)) || @@ -6425,7 +7887,7 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, if (!nest_devs) goto nla_put_failure; - list_for_each_entry_rcu(hook, &flowtable->hook_list, list) { + list_for_each_entry_rcu(hook, hook_list, list) { if (nla_put_string(skb, NFTA_DEVICE_NAME, hook->ops.dev->name)) goto nla_put_failure; } @@ -6453,12 +7915,14 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb, struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; + struct nftables_pernet *nft_net; const struct nft_table *table; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = nft_pernet(net); + cb->seq = READ_ONCE(nft_net->base_seq); - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -6478,7 +7942,9 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb, cb->nlh->nlmsg_seq, NFT_MSG_NEWFLOWTABLE, NLM_F_MULTI | NLM_F_APPEND, - table->family, flowtable) < 0) + table->family, + flowtable, + &flowtable->hook_list) < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -6529,21 +7995,19 @@ static int nf_tables_dump_flowtable_done(struct netlink_callback *cb) } /* called with rcu_read_lock held */ -static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_getflowtable(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_cur(net); - int family = nfmsg->nfgen_family; + u8 genmask = nft_genmask_cur(info->net); + u8 family = info->nfmsg->nfgen_family; struct nft_flowtable *flowtable; const struct nft_table *table; + struct net *net = info->net; struct sk_buff *skb2; int err; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_flowtable_start, .dump = nf_tables_dump_flowtable, @@ -6552,14 +8016,14 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, .data = (void *)nla, }; - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!nla[NFTA_FLOWTABLE_NAME]) return -EINVAL; table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, - genmask); + genmask, 0); if (IS_ERR(table)) return PTR_ERR(table); @@ -6573,26 +8037,30 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, return -ENOMEM; err = nf_tables_fill_flowtable_info(skb2, net, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, + info->nlh->nlmsg_seq, NFT_MSG_NEWFLOWTABLE, 0, family, - flowtable); + flowtable, &flowtable->hook_list); if (err < 0) - goto err; + goto err_fill_flowtable_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); -err: + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + +err_fill_flowtable_info: kfree_skb(skb2); return err; } static void nf_tables_flowtable_notify(struct nft_ctx *ctx, struct nft_flowtable *flowtable, + struct list_head *hook_list, int event) { + struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct sk_buff *skb; + u16 flags = 0; int err; - if (ctx->report && + if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return; @@ -6600,16 +8068,18 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_flowtable_info(skb, ctx->net, ctx->portid, - ctx->seq, event, 0, - ctx->family, flowtable); + ctx->seq, event, flags, + ctx->family, flowtable, hook_list); if (err < 0) { kfree_skb(skb); goto err; } - nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, - ctx->report, GFP_KERNEL); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -6634,21 +8104,17 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; char buf[TASK_COMM_LEN]; int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), 0); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, 0, AF_UNSPEC, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - - if (nla_put_be32(skb, NFTA_GEN_ID, htonl(net->nft.base_seq)) || + if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_net->base_seq)) || nla_put_be32(skb, NFTA_GEN_PROC_PID, htonl(task_pid_nr(current))) || nla_put_string(skb, NFTA_GEN_PROC_NAME, get_task_comm(buf, current))) goto nla_put_failure; @@ -6683,6 +8149,7 @@ static int nf_tables_flowtable_event(struct notifier_block *this, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nft_flowtable *flowtable; + struct nftables_pernet *nft_net; struct nft_table *table; struct net *net; @@ -6690,13 +8157,14 @@ static int nf_tables_flowtable_event(struct notifier_block *this, return 0; net = dev_net(dev); - mutex_lock(&net->nft.commit_mutex); - list_for_each_entry(table, &net->nft.tables, list) { + nft_net = nft_pernet(net); + mutex_lock(&nft_net->commit_mutex); + list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(flowtable, &table->flowtables, list) { nft_flowtable_event(event, dev, flowtable); } } - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } @@ -6712,7 +8180,7 @@ static void nf_tables_gen_notify(struct net *net, struct sk_buff *skb, struct sk_buff *skb2; int err; - if (nlmsg_report(nlh) && + if (!nlmsg_report(nlh) && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) return; @@ -6735,10 +8203,8 @@ err: -ENOBUFS); } -static int nf_tables_getgen(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_getgen(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { struct sk_buff *skb2; int err; @@ -6747,128 +8213,152 @@ static int nf_tables_getgen(struct net *net, struct sock *nlsk, if (skb2 == NULL) return -ENOMEM; - err = nf_tables_fill_gen_info(skb2, net, NETLINK_CB(skb).portid, - nlh->nlmsg_seq); + err = nf_tables_fill_gen_info(skb2, info->net, NETLINK_CB(skb).portid, + info->nlh->nlmsg_seq); if (err < 0) - goto err; + goto err_fill_gen_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); -err: + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); + +err_fill_gen_info: kfree_skb(skb2); return err; } static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { [NFT_MSG_NEWTABLE] = { - .call_batch = nf_tables_newtable, + .call = nf_tables_newtable, + .type = NFNL_CB_BATCH, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, [NFT_MSG_GETTABLE] = { - .call_rcu = nf_tables_gettable, + .call = nf_tables_gettable, + .type = NFNL_CB_RCU, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, [NFT_MSG_DELTABLE] = { - .call_batch = nf_tables_deltable, + .call = nf_tables_deltable, + .type = NFNL_CB_BATCH, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, [NFT_MSG_NEWCHAIN] = { - .call_batch = nf_tables_newchain, + .call = nf_tables_newchain, + .type = NFNL_CB_BATCH, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, [NFT_MSG_GETCHAIN] = { - .call_rcu = nf_tables_getchain, + .call = nf_tables_getchain, + .type = NFNL_CB_RCU, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, [NFT_MSG_DELCHAIN] = { - .call_batch = nf_tables_delchain, + .call = nf_tables_delchain, + .type = NFNL_CB_BATCH, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, [NFT_MSG_NEWRULE] = { - .call_batch = nf_tables_newrule, + .call = nf_tables_newrule, + .type = NFNL_CB_BATCH, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_GETRULE] = { - .call_rcu = nf_tables_getrule, + .call = nf_tables_getrule, + .type = NFNL_CB_RCU, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_DELRULE] = { - .call_batch = nf_tables_delrule, + .call = nf_tables_delrule, + .type = NFNL_CB_BATCH, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_NEWSET] = { - .call_batch = nf_tables_newset, + .call = nf_tables_newset, + .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_GETSET] = { - .call_rcu = nf_tables_getset, + .call = nf_tables_getset, + .type = NFNL_CB_RCU, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_DELSET] = { - .call_batch = nf_tables_delset, + .call = nf_tables_delset, + .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_NEWSETELEM] = { - .call_batch = nf_tables_newsetelem, + .call = nf_tables_newsetelem, + .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_GETSETELEM] = { - .call_rcu = nf_tables_getsetelem, + .call = nf_tables_getsetelem, + .type = NFNL_CB_RCU, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_DELSETELEM] = { - .call_batch = nf_tables_delsetelem, + .call = nf_tables_delsetelem, + .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_GETGEN] = { - .call_rcu = nf_tables_getgen, + .call = nf_tables_getgen, + .type = NFNL_CB_RCU, }, [NFT_MSG_NEWOBJ] = { - .call_batch = nf_tables_newobj, + .call = nf_tables_newobj, + .type = NFNL_CB_BATCH, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ] = { - .call_rcu = nf_tables_getobj, + .call = nf_tables_getobj, + .type = NFNL_CB_RCU, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_DELOBJ] = { - .call_batch = nf_tables_delobj, + .call = nf_tables_delobj, + .type = NFNL_CB_BATCH, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ_RESET] = { - .call_rcu = nf_tables_getobj, + .call = nf_tables_getobj, + .type = NFNL_CB_RCU, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_NEWFLOWTABLE] = { - .call_batch = nf_tables_newflowtable, + .call = nf_tables_newflowtable, + .type = NFNL_CB_BATCH, .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, [NFT_MSG_GETFLOWTABLE] = { - .call_rcu = nf_tables_getflowtable, + .call = nf_tables_getflowtable, + .type = NFNL_CB_RCU, .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, [NFT_MSG_DELFLOWTABLE] = { - .call_batch = nf_tables_delflowtable, + .call = nf_tables_delflowtable, + .type = NFNL_CB_BATCH, .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, @@ -6876,16 +8366,17 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { static int nf_tables_validate(struct net *net) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_table *table; - switch (net->nft.validate_state) { + switch (nft_net->validate_state) { case NFT_VALIDATE_SKIP: break; case NFT_VALIDATE_NEED: nft_validate_state_update(net, NFT_VALIDATE_DO); - /* fall through */ + fallthrough; case NFT_VALIDATE_DO: - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_validate(net, table) < 0) return -EAGAIN; } @@ -6957,7 +8448,7 @@ static void nft_obj_commit_update(struct nft_trans *trans) if (obj->ops->update) obj->ops->update(obj, newobj); - kfree(newobj); + nft_obj_destroy(&trans->ctx, newobj); } static void nft_commit_release(struct nft_trans *trans) @@ -6977,7 +8468,7 @@ static void nft_commit_release(struct nft_trans *trans) nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_DELSET: - nft_set_destroy(nft_trans_set(trans)); + nft_set_destroy(&trans->ctx, nft_trans_set(trans)); break; case NFT_MSG_DELSETELEM: nf_tables_set_elem_destroy(&trans->ctx, @@ -6988,7 +8479,10 @@ static void nft_commit_release(struct nft_trans *trans) nft_obj_destroy(&trans->ctx, nft_trans_obj(trans)); break; case NFT_MSG_DELFLOWTABLE: - nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); + if (nft_trans_flowtable_update(trans)) + nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans)); + else + nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; } @@ -7018,48 +8512,108 @@ static void nf_tables_trans_destroy_work(struct work_struct *w) } } +void nf_tables_trans_destroy_flush_work(void) +{ + flush_work(&trans_destroy_work); +} +EXPORT_SYMBOL_GPL(nf_tables_trans_destroy_flush_work); + +static bool nft_expr_reduce(struct nft_regs_track *track, + const struct nft_expr *expr) +{ + return false; +} + static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *chain) { + const struct nft_expr *expr, *last; + struct nft_regs_track track = {}; + unsigned int size, data_size; + void *data, *data_boundary; + struct nft_rule_dp *prule; struct nft_rule *rule; - unsigned int alloc = 0; - int i; /* already handled or inactive chain? */ - if (chain->rules_next || !nft_is_active_next(net, chain)) + if (chain->blob_next || !nft_is_active_next(net, chain)) return 0; - rule = list_entry(&chain->rules, struct nft_rule, list); - i = 0; - - list_for_each_entry_continue(rule, &chain->rules, list) { - if (nft_is_active_next(net, rule)) - alloc++; + data_size = 0; + list_for_each_entry(rule, &chain->rules, list) { + if (nft_is_active_next(net, rule)) { + data_size += sizeof(*prule) + rule->dlen; + if (data_size > INT_MAX) + return -ENOMEM; + } } + data_size += offsetof(struct nft_rule_dp, data); /* last rule */ - chain->rules_next = nf_tables_chain_alloc_rules(chain, alloc); - if (!chain->rules_next) + chain->blob_next = nf_tables_chain_alloc_rules(data_size); + if (!chain->blob_next) return -ENOMEM; - list_for_each_entry_continue(rule, &chain->rules, list) { - if (nft_is_active_next(net, rule)) - chain->rules_next[i++] = rule; + data = (void *)chain->blob_next->data; + data_boundary = data + data_size; + size = 0; + + list_for_each_entry(rule, &chain->rules, list) { + if (!nft_is_active_next(net, rule)) + continue; + + prule = (struct nft_rule_dp *)data; + data += offsetof(struct nft_rule_dp, data); + if (WARN_ON_ONCE(data > data_boundary)) + return -ENOMEM; + + size = 0; + track.last = nft_expr_last(rule); + nft_rule_for_each_expr(expr, last, rule) { + track.cur = expr; + + if (nft_expr_reduce(&track, expr)) { + expr = track.cur; + continue; + } + + if (WARN_ON_ONCE(data + expr->ops->size > data_boundary)) + return -ENOMEM; + + memcpy(data + size, expr, expr->ops->size); + size += expr->ops->size; + } + if (WARN_ON_ONCE(size >= 1 << 12)) + return -ENOMEM; + + prule->handle = rule->handle; + prule->dlen = size; + prule->is_last = 0; + + data += size; + size = 0; + chain->blob_next->size += (unsigned long)(data - (void *)prule); } - chain->rules_next[i] = NULL; + prule = (struct nft_rule_dp *)data; + data += offsetof(struct nft_rule_dp, data); + if (WARN_ON_ONCE(data > data_boundary)) + return -ENOMEM; + + nft_last_rule(chain->blob_next, prule); + return 0; } static void nf_tables_commit_chain_prepare_cancel(struct net *net) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { struct nft_chain *chain = trans->ctx.chain; if (trans->msg_type == NFT_MSG_NEWRULE || trans->msg_type == NFT_MSG_DELRULE) { - kvfree(chain->rules_next); - chain->rules_next = NULL; + kvfree(chain->blob_next); + chain->blob_next = NULL; } } } @@ -7068,38 +8622,34 @@ static void __nf_tables_commit_chain_free_rules_old(struct rcu_head *h) { struct nft_rules_old *o = container_of(h, struct nft_rules_old, h); - kvfree(o->start); + kvfree(o->blob); } -static void nf_tables_commit_chain_free_rules_old(struct nft_rule **rules) +static void nf_tables_commit_chain_free_rules_old(struct nft_rule_blob *blob) { - struct nft_rule **r = rules; struct nft_rules_old *old; - while (*r) - r++; - - r++; /* rcu_head is after end marker */ - old = (void *) r; - old->start = rules; + /* rcu_head is after end marker */ + old = (void *)blob + sizeof(*blob) + blob->size; + old->blob = blob; call_rcu(&old->h, __nf_tables_commit_chain_free_rules_old); } static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain) { - struct nft_rule **g0, **g1; + struct nft_rule_blob *g0, *g1; bool next_genbit; next_genbit = nft_gencursor_next(net); - g0 = rcu_dereference_protected(chain->rules_gen_0, + g0 = rcu_dereference_protected(chain->blob_gen_0, lockdep_commit_lock_is_held(net)); - g1 = rcu_dereference_protected(chain->rules_gen_1, + g1 = rcu_dereference_protected(chain->blob_gen_1, lockdep_commit_lock_is_held(net)); /* No changes to this chain? */ - if (chain->rules_next == NULL) { + if (chain->blob_next == NULL) { /* chain had no change in last or next generation */ if (g0 == g1) return; @@ -7108,10 +8658,10 @@ static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain) * one uses same rules as current generation. */ if (next_genbit) { - rcu_assign_pointer(chain->rules_gen_1, g0); + rcu_assign_pointer(chain->blob_gen_1, g0); nf_tables_commit_chain_free_rules_old(g1); } else { - rcu_assign_pointer(chain->rules_gen_0, g1); + rcu_assign_pointer(chain->blob_gen_0, g1); nf_tables_commit_chain_free_rules_old(g0); } @@ -7119,11 +8669,11 @@ static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain) } if (next_genbit) - rcu_assign_pointer(chain->rules_gen_1, chain->rules_next); + rcu_assign_pointer(chain->blob_gen_1, chain->blob_next); else - rcu_assign_pointer(chain->rules_gen_0, chain->rules_next); + rcu_assign_pointer(chain->blob_gen_0, chain->blob_next); - chain->rules_next = NULL; + chain->blob_next = NULL; if (g0 == g1) return; @@ -7140,7 +8690,7 @@ static void nft_obj_del(struct nft_object *obj) list_del_rcu(&obj->list); } -static void nft_chain_del(struct nft_chain *chain) +void nft_chain_del(struct nft_chain *chain) { struct nft_table *table = chain->table; @@ -7151,10 +8701,11 @@ static void nft_chain_del(struct nft_chain *chain) static void nf_tables_module_autoload_cleanup(struct net *net) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_module_request *req, *next; - WARN_ON_ONCE(!list_empty(&net->nft.commit_list)); - list_for_each_entry_safe(req, next, &net->nft.module_list, list) { + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + list_for_each_entry_safe(req, next, &nft_net->module_list, list) { WARN_ON_ONCE(!req->done); list_del(&req->list); kfree(req); @@ -7163,6 +8714,7 @@ static void nf_tables_module_autoload_cleanup(struct net *net) static void nf_tables_commit_release(struct net *net) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans; /* all side effects have to be made visible. @@ -7172,38 +8724,138 @@ static void nf_tables_commit_release(struct net *net) * Memory reclaim happens asynchronously from work queue * to prevent expensive synchronize_rcu() in commit phase. */ - if (list_empty(&net->nft.commit_list)) { + if (list_empty(&nft_net->commit_list)) { nf_tables_module_autoload_cleanup(net); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return; } - trans = list_last_entry(&net->nft.commit_list, + trans = list_last_entry(&nft_net->commit_list, struct nft_trans, list); get_net(trans->ctx.net); WARN_ON_ONCE(trans->put_net); trans->put_net = true; spin_lock(&nf_tables_destroy_list_lock); - list_splice_tail_init(&net->nft.commit_list, &nf_tables_destroy_list); + list_splice_tail_init(&nft_net->commit_list, &nf_tables_destroy_list); spin_unlock(&nf_tables_destroy_list_lock); nf_tables_module_autoload_cleanup(net); - mutex_unlock(&net->nft.commit_mutex); - schedule_work(&trans_destroy_work); + + mutex_unlock(&nft_net->commit_mutex); +} + +static void nft_commit_notify(struct net *net, u32 portid) +{ + struct nftables_pernet *nft_net = nft_pernet(net); + struct sk_buff *batch_skb = NULL, *nskb, *skb; + unsigned char *data; + int len; + + list_for_each_entry_safe(skb, nskb, &nft_net->notify_list, list) { + if (!batch_skb) { +new_batch: + batch_skb = skb; + len = NLMSG_GOODSIZE - skb->len; + list_del(&skb->list); + continue; + } + len -= skb->len; + if (len > 0 && NFT_CB(skb).report == NFT_CB(batch_skb).report) { + data = skb_put(batch_skb, skb->len); + memcpy(data, skb->data, skb->len); + list_del(&skb->list); + kfree_skb(skb); + continue; + } + nfnetlink_send(batch_skb, net, portid, NFNLGRP_NFTABLES, + NFT_CB(batch_skb).report, GFP_KERNEL); + goto new_batch; + } + + if (batch_skb) { + nfnetlink_send(batch_skb, net, portid, NFNLGRP_NFTABLES, + NFT_CB(batch_skb).report, GFP_KERNEL); + } + + WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); +} + +static int nf_tables_commit_audit_alloc(struct list_head *adl, + struct nft_table *table) +{ + struct nft_audit_data *adp; + + list_for_each_entry(adp, adl, list) { + if (adp->table == table) + return 0; + } + adp = kzalloc(sizeof(*adp), GFP_KERNEL); + if (!adp) + return -ENOMEM; + adp->table = table; + list_add(&adp->list, adl); + return 0; +} + +static void nf_tables_commit_audit_free(struct list_head *adl) +{ + struct nft_audit_data *adp, *adn; + + list_for_each_entry_safe(adp, adn, adl, list) { + list_del(&adp->list); + kfree(adp); + } +} + +static void nf_tables_commit_audit_collect(struct list_head *adl, + struct nft_table *table, u32 op) +{ + struct nft_audit_data *adp; + + list_for_each_entry(adp, adl, list) { + if (adp->table == table) + goto found; + } + WARN_ONCE(1, "table=%s not expected in commit list", table->name); + return; +found: + adp->entries++; + if (!adp->op || adp->op > op) + adp->op = op; +} + +#define AUNFTABLENAMELEN (NFT_TABLE_MAXNAMELEN + 22) + +static void nf_tables_commit_audit_log(struct list_head *adl, u32 generation) +{ + struct nft_audit_data *adp, *adn; + char aubuf[AUNFTABLENAMELEN]; + + list_for_each_entry_safe(adp, adn, adl, list) { + snprintf(aubuf, AUNFTABLENAMELEN, "%s:%u", adp->table->name, + generation); + audit_log_nfcfg(aubuf, adp->table->family, adp->entries, + nft2audit_op[adp->op], GFP_KERNEL); + list_del(&adp->list); + kfree(adp); + } } static int nf_tables_commit(struct net *net, struct sk_buff *skb) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; struct nft_trans_elem *te; struct nft_chain *chain; struct nft_table *table; + unsigned int base_seq; + LIST_HEAD(adl); int err; - if (list_empty(&net->nft.commit_list)) { - mutex_unlock(&net->nft.commit_mutex); + if (list_empty(&nft_net->commit_list)) { + mutex_unlock(&nft_net->commit_mutex); return 0; } @@ -7216,9 +8868,15 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) return err; /* 1. Allocate space for next generation rules_gen_X[] */ - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { int ret; + ret = nf_tables_commit_audit_alloc(&adl, trans->ctx.table); + if (ret) { + nf_tables_commit_chain_prepare_cancel(net); + nf_tables_commit_audit_free(&adl); + return ret; + } if (trans->msg_type == NFT_MSG_NEWRULE || trans->msg_type == NFT_MSG_DELRULE) { chain = trans->ctx.chain; @@ -7226,13 +8884,14 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) ret = nf_tables_commit_chain_prepare(net, chain); if (ret < 0) { nf_tables_commit_chain_prepare_cancel(net); + nf_tables_commit_audit_free(&adl); return ret; } } } /* step 2. Make rules_gen_X visible to packet path */ - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(chain, &table->chains, list) nf_tables_commit_chain(net, chain); } @@ -7241,20 +8900,29 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) * Bump generation counter, invalidate any dump in progress. * Cannot fail after this point. */ - while (++net->nft.base_seq == 0); + base_seq = READ_ONCE(nft_net->base_seq); + while (++base_seq == 0) + ; + + WRITE_ONCE(nft_net->base_seq, base_seq); /* step 3. Start new generation, rules_gen_X now in use. */ net->nft.gencursor = nft_gencursor_next(net); - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { + nf_tables_commit_audit_collect(&adl, trans->ctx.table, + trans->msg_type); switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { - if (!nft_trans_table_enable(trans)) { - nf_tables_table_disable(net, - trans->ctx.table); - trans->ctx.table->flags |= NFT_TABLE_F_DORMANT; + if (!(trans->ctx.table->flags & __NFT_TABLE_F_UPDATE)) { + nft_trans_destroy(trans); + break; } + if (trans->ctx.table->flags & NFT_TABLE_F_DORMANT) + nf_tables_table_disable(net, trans->ctx.table); + + trans->ctx.table->flags &= ~__NFT_TABLE_F_UPDATE; } else { nft_clear(net, trans->ctx.table); } @@ -7289,6 +8957,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_rule_notify(&trans->ctx, nft_trans_rule(trans), NFT_MSG_NEWRULE); + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); + nft_trans_destroy(trans); break; case NFT_MSG_DELRULE: @@ -7299,6 +8970,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), NFT_TRANS_COMMIT); + + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_NEWSET: nft_clear(net, nft_trans_set(trans)); @@ -7321,10 +8995,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) case NFT_MSG_NEWSETELEM: te = (struct nft_trans_elem *)trans->data; - te->set->ops->activate(net, te->set, &te->elem); + nft_setelem_activate(net, te->set, &te->elem); nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, - NFT_MSG_NEWSETELEM, 0); + NFT_MSG_NEWSETELEM); nft_trans_destroy(trans); break; case NFT_MSG_DELSETELEM: @@ -7332,10 +9006,12 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, - NFT_MSG_DELSETELEM, 0); - te->set->ops->remove(net, te->set, &te->elem); - atomic_dec(&te->set->nelems); - te->set->ndeact--; + NFT_MSG_DELSETELEM); + nft_setelem_remove(net, te->set, &te->elem); + if (!nft_setelem_is_catchall(te->set, &te->elem)) { + atomic_dec(&te->set->nelems); + te->set->ndeact--; + } break; case NFT_MSG_NEWOBJ: if (nft_trans_obj_update(trans)) { @@ -7357,24 +9033,48 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) NFT_MSG_DELOBJ); break; case NFT_MSG_NEWFLOWTABLE: - nft_clear(net, nft_trans_flowtable(trans)); - nf_tables_flowtable_notify(&trans->ctx, - nft_trans_flowtable(trans), - NFT_MSG_NEWFLOWTABLE); + if (nft_trans_flowtable_update(trans)) { + nft_trans_flowtable(trans)->data.flags = + nft_trans_flowtable_flags(trans); + nf_tables_flowtable_notify(&trans->ctx, + nft_trans_flowtable(trans), + &nft_trans_flowtable_hooks(trans), + NFT_MSG_NEWFLOWTABLE); + list_splice(&nft_trans_flowtable_hooks(trans), + &nft_trans_flowtable(trans)->hook_list); + } else { + nft_clear(net, nft_trans_flowtable(trans)); + nf_tables_flowtable_notify(&trans->ctx, + nft_trans_flowtable(trans), + &nft_trans_flowtable(trans)->hook_list, + NFT_MSG_NEWFLOWTABLE); + } nft_trans_destroy(trans); break; case NFT_MSG_DELFLOWTABLE: - list_del_rcu(&nft_trans_flowtable(trans)->list); - nf_tables_flowtable_notify(&trans->ctx, - nft_trans_flowtable(trans), - NFT_MSG_DELFLOWTABLE); - nft_unregister_flowtable_net_hooks(net, - nft_trans_flowtable(trans)); + if (nft_trans_flowtable_update(trans)) { + nf_tables_flowtable_notify(&trans->ctx, + nft_trans_flowtable(trans), + &nft_trans_flowtable_hooks(trans), + NFT_MSG_DELFLOWTABLE); + nft_unregister_flowtable_net_hooks(net, + &nft_trans_flowtable_hooks(trans)); + } else { + list_del_rcu(&nft_trans_flowtable(trans)->list); + nf_tables_flowtable_notify(&trans->ctx, + nft_trans_flowtable(trans), + &nft_trans_flowtable(trans)->hook_list, + NFT_MSG_DELFLOWTABLE); + nft_unregister_flowtable_net_hooks(net, + &nft_trans_flowtable(trans)->hook_list); + } break; } } + nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); + nf_tables_commit_audit_log(&adl, nft_net->base_seq); nf_tables_commit_release(net); return 0; @@ -7382,17 +9082,18 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) static void nf_tables_module_autoload(struct net *net) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_module_request *req, *next; LIST_HEAD(module_list); - list_splice_init(&net->nft.module_list, &module_list); - mutex_unlock(&net->nft.commit_mutex); + list_splice_init(&nft_net->module_list, &module_list); + mutex_unlock(&nft_net->commit_mutex); list_for_each_entry_safe(req, next, &module_list, list) { request_module("%s", req->module); req->done = true; } - mutex_lock(&net->nft.commit_mutex); - list_splice(&module_list, &net->nft.module_list); + mutex_lock(&nft_net->commit_mutex); + list_splice(&module_list, &nft_net->module_list); } static void nf_tables_abort_release(struct nft_trans *trans) @@ -7408,7 +9109,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_NEWSET: - nft_set_destroy(nft_trans_set(trans)); + nft_set_destroy(&trans->ctx, nft_trans_set(trans)); break; case NFT_MSG_NEWSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), @@ -7418,27 +9119,41 @@ static void nf_tables_abort_release(struct nft_trans *trans) nft_obj_destroy(&trans->ctx, nft_trans_obj(trans)); break; case NFT_MSG_NEWFLOWTABLE: - nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); + if (nft_trans_flowtable_update(trans)) + nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans)); + else + nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; } kfree(trans); } -static int __nf_tables_abort(struct net *net, bool autoload) +static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; struct nft_trans_elem *te; - list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list, + if (action == NFNL_ABORT_VALIDATE && + nf_tables_validate(net) < 0) + return -EAGAIN; + + list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { - if (nft_trans_table_enable(trans)) { - nf_tables_table_disable(net, - trans->ctx.table); + if (!(trans->ctx.table->flags & __NFT_TABLE_F_UPDATE)) { + nft_trans_destroy(trans); + break; + } + if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_DORMANT) { + nf_tables_table_disable(net, trans->ctx.table); trans->ctx.table->flags |= NFT_TABLE_F_DORMANT; + } else if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_AWAKEN) { + trans->ctx.table->flags &= ~NFT_TABLE_F_DORMANT; } + trans->ctx.table->flags &= ~__NFT_TABLE_F_UPDATE; nft_trans_destroy(trans); } else { list_del_rcu(&trans->ctx.table->list); @@ -7454,6 +9169,10 @@ static int __nf_tables_abort(struct net *net, bool autoload) kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); } else { + if (nft_chain_is_bound(trans->ctx.chain)) { + nft_trans_destroy(trans); + break; + } trans->ctx.table->use--; nft_chain_del(trans->ctx.chain); nf_tables_unregister_hook(trans->ctx.net, @@ -7472,11 +9191,16 @@ static int __nf_tables_abort(struct net *net, bool autoload) nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), NFT_TRANS_ABORT); + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_DELRULE: trans->ctx.chain->use++; nft_clear(trans->ctx.net, nft_trans_rule(trans)); nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans)); + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); + nft_trans_destroy(trans); break; case NFT_MSG_NEWSET: @@ -7498,21 +9222,23 @@ static int __nf_tables_abort(struct net *net, bool autoload) break; } te = (struct nft_trans_elem *)trans->data; - te->set->ops->remove(net, te->set, &te->elem); - atomic_dec(&te->set->nelems); + nft_setelem_remove(net, te->set, &te->elem); + if (!nft_setelem_is_catchall(te->set, &te->elem)) + atomic_dec(&te->set->nelems); break; case NFT_MSG_DELSETELEM: te = (struct nft_trans_elem *)trans->data; - nft_set_elem_activate(net, te->set, &te->elem); - te->set->ops->activate(net, te->set, &te->elem); - te->set->ndeact--; + nft_setelem_data_activate(net, te->set, &te->elem); + nft_setelem_activate(net, te->set, &te->elem); + if (!nft_setelem_is_catchall(te->set, &te->elem)) + te->set->ndeact--; nft_trans_destroy(trans); break; case NFT_MSG_NEWOBJ: if (nft_trans_obj_update(trans)) { - kfree(nft_trans_obj_newobj(trans)); + nft_obj_destroy(&trans->ctx, nft_trans_obj_newobj(trans)); nft_trans_destroy(trans); } else { trans->ctx.table->use--; @@ -7525,14 +9251,24 @@ static int __nf_tables_abort(struct net *net, bool autoload) nft_trans_destroy(trans); break; case NFT_MSG_NEWFLOWTABLE: - trans->ctx.table->use--; - list_del_rcu(&nft_trans_flowtable(trans)->list); - nft_unregister_flowtable_net_hooks(net, - nft_trans_flowtable(trans)); + if (nft_trans_flowtable_update(trans)) { + nft_unregister_flowtable_net_hooks(net, + &nft_trans_flowtable_hooks(trans)); + } else { + trans->ctx.table->use--; + list_del_rcu(&nft_trans_flowtable(trans)->list); + nft_unregister_flowtable_net_hooks(net, + &nft_trans_flowtable(trans)->hook_list); + } break; case NFT_MSG_DELFLOWTABLE: - trans->ctx.table->use++; - nft_clear(trans->ctx.net, nft_trans_flowtable(trans)); + if (nft_trans_flowtable_update(trans)) { + list_splice(&nft_trans_flowtable_hooks(trans), + &nft_trans_flowtable(trans)->hook_list); + } else { + trans->ctx.table->use++; + nft_clear(trans->ctx.net, nft_trans_flowtable(trans)); + } nft_trans_destroy(trans); break; } @@ -7541,12 +9277,12 @@ static int __nf_tables_abort(struct net *net, bool autoload) synchronize_rcu(); list_for_each_entry_safe_reverse(trans, next, - &net->nft.commit_list, list) { + &nft_net->commit_list, list) { list_del(&trans->list); nf_tables_abort_release(trans); } - if (autoload) + if (action == NFNL_ABORT_AUTOLOAD) nf_tables_module_autoload(net); else nf_tables_module_autoload_cleanup(net); @@ -7559,24 +9295,27 @@ static void nf_tables_cleanup(struct net *net) nft_validate_state_update(net, NFT_VALIDATE_SKIP); } -static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload) +static int nf_tables_abort(struct net *net, struct sk_buff *skb, + enum nfnl_abort_action action) { - int ret = __nf_tables_abort(net, autoload); + struct nftables_pernet *nft_net = nft_pernet(net); + int ret = __nf_tables_abort(net, action); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return ret; } static bool nf_tables_valid_genid(struct net *net, u32 genid) { + struct nftables_pernet *nft_net = nft_pernet(net); bool genid_ok; - mutex_lock(&net->nft.commit_mutex); + mutex_lock(&nft_net->commit_mutex); - genid_ok = genid == 0 || net->nft.base_seq == genid; + genid_ok = genid == 0 || nft_net->base_seq == genid; if (!genid_ok) - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); /* else, commit mutex has to be released by commit or abort function */ return genid_ok; @@ -7638,26 +9377,59 @@ EXPORT_SYMBOL_GPL(nft_chain_validate_hooks); static int nf_tables_check_loops(const struct nft_ctx *ctx, const struct nft_chain *chain); +static int nft_check_loops(const struct nft_ctx *ctx, + const struct nft_set_ext *ext) +{ + const struct nft_data *data; + int ret; + + data = nft_set_ext_data(ext); + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + ret = nf_tables_check_loops(ctx, data->verdict.chain); + break; + default: + ret = 0; + break; + } + + return ret; +} + static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); - const struct nft_data *data; if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) return 0; - data = nft_set_ext_data(ext); - switch (data->verdict.code) { - case NFT_JUMP: - case NFT_GOTO: - return nf_tables_check_loops(ctx, data->verdict.chain); - default: - return 0; + return nft_check_loops(ctx, ext); +} + +static int nft_set_catchall_loops(const struct nft_ctx *ctx, + struct nft_set *set) +{ + u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_elem_catchall *catchall; + struct nft_set_ext *ext; + int ret = 0; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask)) + continue; + + ret = nft_check_loops(ctx, ext); + if (ret < 0) + return ret; } + + return ret; } static int nf_tables_check_loops(const struct nft_ctx *ctx, @@ -7693,6 +9465,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, data->verdict.chain); if (err < 0) return err; + break; default: break; } @@ -7718,6 +9491,9 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, iter.fn = nf_tables_loop_check_setelem; set->ops->walk(ctx, set, &iter); + if (!iter.err) + iter.err = nft_set_catchall_loops(ctx, set); + if (iter.err < 0) return iter.err; } @@ -7751,28 +9527,24 @@ int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest) } EXPORT_SYMBOL_GPL(nft_parse_u32_check); -/** - * nft_parse_register - parse a register value from a netlink attribute - * - * @attr: netlink attribute - * - * Parse and translate a register value from a netlink attribute. - * Registers used to be 128 bit wide, these register numbers will be - * mapped to the corresponding 32 bit register numbers. - */ -unsigned int nft_parse_register(const struct nlattr *attr) +static int nft_parse_register(const struct nlattr *attr, u32 *preg) { unsigned int reg; reg = ntohl(nla_get_be32(attr)); switch (reg) { case NFT_REG_VERDICT...NFT_REG_4: - return reg * NFT_REG_SIZE / NFT_REG32_SIZE; + *preg = reg * NFT_REG_SIZE / NFT_REG32_SIZE; + break; + case NFT_REG32_00...NFT_REG32_15: + *preg = reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00; + break; default: - return reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00; + return -ERANGE; } + + return 0; } -EXPORT_SYMBOL_GPL(nft_parse_register); /** * nft_dump_register - dump a register value to a netlink attribute @@ -7796,16 +9568,7 @@ int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg) } EXPORT_SYMBOL_GPL(nft_dump_register); -/** - * nft_validate_register_load - validate a load from a register - * - * @reg: the register number - * @len: the length of the data - * - * Validate that the input register is one of the general purpose - * registers and that the length of the load is within the bounds. - */ -int nft_validate_register_load(enum nft_registers reg, unsigned int len) +static int nft_validate_register_load(enum nft_registers reg, unsigned int len) { if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE) return -EINVAL; @@ -7816,26 +9579,30 @@ int nft_validate_register_load(enum nft_registers reg, unsigned int len) return 0; } -EXPORT_SYMBOL_GPL(nft_validate_register_load); -/** - * nft_validate_register_store - validate an expressions' register store - * - * @ctx: context of the expression performing the load - * @reg: the destination register number - * @data: the data to load - * @type: the data type - * @len: the length of the data - * - * Validate that a data load uses the appropriate data type for - * the destination register and the length is within the bounds. - * A value of NULL for the data means that its runtime gathered - * data. - */ -int nft_validate_register_store(const struct nft_ctx *ctx, - enum nft_registers reg, - const struct nft_data *data, - enum nft_data_types type, unsigned int len) +int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len) +{ + u32 reg; + int err; + + err = nft_parse_register(attr, ®); + if (err < 0) + return err; + + err = nft_validate_register_load(reg, len); + if (err < 0) + return err; + + *sreg = reg; + return 0; +} +EXPORT_SYMBOL_GPL(nft_parse_register_load); + +static int nft_validate_register_store(const struct nft_ctx *ctx, + enum nft_registers reg, + const struct nft_data *data, + enum nft_data_types type, + unsigned int len) { int err; @@ -7867,12 +9634,33 @@ int nft_validate_register_store(const struct nft_ctx *ctx, return 0; } } -EXPORT_SYMBOL_GPL(nft_validate_register_store); + +int nft_parse_register_store(const struct nft_ctx *ctx, + const struct nlattr *attr, u8 *dreg, + const struct nft_data *data, + enum nft_data_types type, unsigned int len) +{ + int err; + u32 reg; + + err = nft_parse_register(attr, ®); + if (err < 0) + return err; + + err = nft_validate_register_store(ctx, reg, data, type, len); + if (err < 0) + return err; + + *dreg = reg; + return 0; +} +EXPORT_SYMBOL_GPL(nft_parse_register_store); static const struct nla_policy nft_verdict_policy[NFTA_VERDICT_MAX + 1] = { [NFTA_VERDICT_CODE] = { .type = NLA_U32 }, [NFTA_VERDICT_CHAIN] = { .type = NLA_STRING, .len = NFT_CHAIN_MAXNAMELEN - 1 }, + [NFTA_VERDICT_CHAIN_ID] = { .type = NLA_U32 }, }; static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, @@ -7902,21 +9690,35 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, default: return -EINVAL; } - /* fall through */ + fallthrough; case NFT_CONTINUE: case NFT_BREAK: case NFT_RETURN: break; case NFT_JUMP: case NFT_GOTO: - if (!tb[NFTA_VERDICT_CHAIN]) + if (tb[NFTA_VERDICT_CHAIN]) { + chain = nft_chain_lookup(ctx->net, ctx->table, + tb[NFTA_VERDICT_CHAIN], + genmask); + } else if (tb[NFTA_VERDICT_CHAIN_ID]) { + chain = nft_chain_lookup_byid(ctx->net, ctx->table, + tb[NFTA_VERDICT_CHAIN_ID]); + if (IS_ERR(chain)) + return PTR_ERR(chain); + } else { return -EINVAL; - chain = nft_chain_lookup(ctx->net, ctx->table, - tb[NFTA_VERDICT_CHAIN], genmask); + } + if (IS_ERR(chain)) return PTR_ERR(chain); if (nft_is_base_chain(chain)) return -EOPNOTSUPP; + if (nft_chain_is_bound(chain)) + return -EINVAL; + if (desc->flags & NFT_DATA_DESC_SETELEM && + chain->flags & NFT_CHAIN_BINDING) + return -EINVAL; chain->use++; data->verdict.chain = chain; @@ -7924,16 +9726,29 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, } desc->len = sizeof(data->verdict); - desc->type = NFT_DATA_VERDICT; + return 0; } static void nft_verdict_uninit(const struct nft_data *data) { + struct nft_chain *chain; + struct nft_rule *rule; + switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: - data->verdict.chain->use--; + chain = data->verdict.chain; + chain->use--; + + if (!nft_chain_is_bound(chain)) + break; + + chain->table->use--; + list_for_each_entry(rule, &chain->rules, list) + chain->use--; + + nft_chain_del(chain); break; } } @@ -7964,20 +9779,25 @@ nla_put_failure: } static int nft_value_init(const struct nft_ctx *ctx, - struct nft_data *data, unsigned int size, - struct nft_data_desc *desc, const struct nlattr *nla) + struct nft_data *data, struct nft_data_desc *desc, + const struct nlattr *nla) { unsigned int len; len = nla_len(nla); if (len == 0) return -EINVAL; - if (len > size) + if (len > desc->size) return -EOVERFLOW; + if (desc->len) { + if (len != desc->len) + return -EINVAL; + } else { + desc->len = len; + } nla_memcpy(data->data, nla, len); - desc->type = NFT_DATA_VALUE; - desc->len = len; + return 0; } @@ -7997,7 +9817,6 @@ static const struct nla_policy nft_data_policy[NFTA_DATA_MAX + 1] = { * * @ctx: context of the expression using the data * @data: destination struct nft_data - * @size: maximum data length * @desc: data description * @nla: netlink attribute containing data * @@ -8007,24 +9826,35 @@ static const struct nla_policy nft_data_policy[NFTA_DATA_MAX + 1] = { * The caller can indicate that it only wants to accept data of type * NFT_DATA_VALUE by passing NULL for the ctx argument. */ -int nft_data_init(const struct nft_ctx *ctx, - struct nft_data *data, unsigned int size, +int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data, struct nft_data_desc *desc, const struct nlattr *nla) { struct nlattr *tb[NFTA_DATA_MAX + 1]; int err; + if (WARN_ON_ONCE(!desc->size)) + return -EINVAL; + err = nla_parse_nested_deprecated(tb, NFTA_DATA_MAX, nla, nft_data_policy, NULL); if (err < 0) return err; - if (tb[NFTA_DATA_VALUE]) - return nft_value_init(ctx, data, size, desc, - tb[NFTA_DATA_VALUE]); - if (tb[NFTA_DATA_VERDICT] && ctx != NULL) - return nft_verdict_init(ctx, data, desc, tb[NFTA_DATA_VERDICT]); - return -EINVAL; + if (tb[NFTA_DATA_VALUE]) { + if (desc->type != NFT_DATA_VALUE) + return -EINVAL; + + err = nft_value_init(ctx, data, desc, tb[NFTA_DATA_VALUE]); + } else if (tb[NFTA_DATA_VERDICT] && ctx != NULL) { + if (desc->type != NFT_DATA_VERDICT) + return -EINVAL; + + err = nft_verdict_init(ctx, data, desc, tb[NFTA_DATA_VERDICT]); + } else { + err = -EINVAL; + } + + return err; } EXPORT_SYMBOL_GPL(nft_data_init); @@ -8098,10 +9928,34 @@ int __nft_release_basechain(struct nft_ctx *ctx) } EXPORT_SYMBOL_GPL(__nft_release_basechain); -static void __nft_release_tables(struct net *net) +static void __nft_release_hook(struct net *net, struct nft_table *table) +{ + struct nft_flowtable *flowtable; + struct nft_chain *chain; + + list_for_each_entry(chain, &table->chains, list) + __nf_tables_unregister_hook(net, table, chain, true); + list_for_each_entry(flowtable, &table->flowtables, list) + __nft_unregister_flowtable_net_hooks(net, &flowtable->hook_list, + true); +} + +static void __nft_release_hooks(struct net *net) +{ + struct nftables_pernet *nft_net = nft_pernet(net); + struct nft_table *table; + + list_for_each_entry(table, &nft_net->tables, list) { + if (nft_table_has_owner(table)) + continue; + + __nft_release_hook(net, table); + } +} + +static void __nft_release_table(struct net *net, struct nft_table *table) { struct nft_flowtable *flowtable, *nf; - struct nft_table *table, *nt; struct nft_chain *chain, *nc; struct nft_object *obj, *ne; struct nft_rule *rule, *nr; @@ -8111,123 +9965,203 @@ static void __nft_release_tables(struct net *net) .family = NFPROTO_NETDEV, }; - list_for_each_entry_safe(table, nt, &net->nft.tables, list) { - ctx.family = table->family; - - list_for_each_entry(chain, &table->chains, list) - nf_tables_unregister_hook(net, table, chain); - /* No packets are walking on these chains anymore. */ - ctx.table = table; - list_for_each_entry(chain, &table->chains, list) { - ctx.chain = chain; - list_for_each_entry_safe(rule, nr, &chain->rules, list) { - list_del(&rule->list); - chain->use--; - nf_tables_rule_release(&ctx, rule); - } - } - list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { - list_del(&flowtable->list); - table->use--; - nf_tables_flowtable_destroy(flowtable); - } - list_for_each_entry_safe(set, ns, &table->sets, list) { - list_del(&set->list); - table->use--; - nft_set_destroy(set); - } - list_for_each_entry_safe(obj, ne, &table->objects, list) { - nft_obj_del(obj); - table->use--; - nft_obj_destroy(&ctx, obj); - } - list_for_each_entry_safe(chain, nc, &table->chains, list) { - ctx.chain = chain; - nft_chain_del(chain); - table->use--; - nf_tables_chain_destroy(&ctx); + ctx.family = table->family; + ctx.table = table; + list_for_each_entry(chain, &table->chains, list) { + ctx.chain = chain; + list_for_each_entry_safe(rule, nr, &chain->rules, list) { + list_del(&rule->list); + chain->use--; + nf_tables_rule_release(&ctx, rule); } + } + list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { + list_del(&flowtable->list); + table->use--; + nf_tables_flowtable_destroy(flowtable); + } + list_for_each_entry_safe(set, ns, &table->sets, list) { + list_del(&set->list); + table->use--; + nft_set_destroy(&ctx, set); + } + list_for_each_entry_safe(obj, ne, &table->objects, list) { + nft_obj_del(obj); + table->use--; + nft_obj_destroy(&ctx, obj); + } + list_for_each_entry_safe(chain, nc, &table->chains, list) { + ctx.chain = chain; + nft_chain_del(chain); + table->use--; + nf_tables_chain_destroy(&ctx); + } + nf_tables_table_destroy(&ctx); +} + +static void __nft_release_tables(struct net *net) +{ + struct nftables_pernet *nft_net = nft_pernet(net); + struct nft_table *table, *nt; + + list_for_each_entry_safe(table, nt, &nft_net->tables, list) { + if (nft_table_has_owner(table)) + continue; + list_del(&table->list); - nf_tables_table_destroy(&ctx); + + __nft_release_table(net, table); } } +static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct nft_table *table, *to_delete[8]; + struct nftables_pernet *nft_net; + struct netlink_notify *n = ptr; + struct net *net = n->net; + unsigned int deleted; + bool restart = false; + + if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER) + return NOTIFY_DONE; + + nft_net = nft_pernet(net); + deleted = 0; + mutex_lock(&nft_net->commit_mutex); + if (!list_empty(&nf_tables_destroy_list)) + rcu_barrier(); +again: + list_for_each_entry(table, &nft_net->tables, list) { + if (nft_table_has_owner(table) && + n->portid == table->nlpid) { + __nft_release_hook(net, table); + list_del_rcu(&table->list); + to_delete[deleted++] = table; + if (deleted >= ARRAY_SIZE(to_delete)) + break; + } + } + if (deleted) { + restart = deleted >= ARRAY_SIZE(to_delete); + synchronize_rcu(); + while (deleted) + __nft_release_table(net, to_delete[--deleted]); + + if (restart) + goto again; + } + mutex_unlock(&nft_net->commit_mutex); + + return NOTIFY_DONE; +} + +static struct notifier_block nft_nl_notifier = { + .notifier_call = nft_rcv_nl_event, +}; + static int __net_init nf_tables_init_net(struct net *net) { - INIT_LIST_HEAD(&net->nft.tables); - INIT_LIST_HEAD(&net->nft.commit_list); - INIT_LIST_HEAD(&net->nft.module_list); - mutex_init(&net->nft.commit_mutex); - net->nft.base_seq = 1; - net->nft.validate_state = NFT_VALIDATE_SKIP; + struct nftables_pernet *nft_net = nft_pernet(net); + + INIT_LIST_HEAD(&nft_net->tables); + INIT_LIST_HEAD(&nft_net->commit_list); + INIT_LIST_HEAD(&nft_net->module_list); + INIT_LIST_HEAD(&nft_net->notify_list); + mutex_init(&nft_net->commit_mutex); + nft_net->base_seq = 1; + nft_net->validate_state = NFT_VALIDATE_SKIP; return 0; } +static void __net_exit nf_tables_pre_exit_net(struct net *net) +{ + struct nftables_pernet *nft_net = nft_pernet(net); + + mutex_lock(&nft_net->commit_mutex); + __nft_release_hooks(net); + mutex_unlock(&nft_net->commit_mutex); +} + static void __net_exit nf_tables_exit_net(struct net *net) { - mutex_lock(&net->nft.commit_mutex); - if (!list_empty(&net->nft.commit_list)) - __nf_tables_abort(net, false); + struct nftables_pernet *nft_net = nft_pernet(net); + + mutex_lock(&nft_net->commit_mutex); + if (!list_empty(&nft_net->commit_list) || + !list_empty(&nft_net->module_list)) + __nf_tables_abort(net, NFNL_ABORT_NONE); __nft_release_tables(net); - mutex_unlock(&net->nft.commit_mutex); - WARN_ON_ONCE(!list_empty(&net->nft.tables)); - WARN_ON_ONCE(!list_empty(&net->nft.module_list)); + mutex_unlock(&nft_net->commit_mutex); + WARN_ON_ONCE(!list_empty(&nft_net->tables)); + WARN_ON_ONCE(!list_empty(&nft_net->module_list)); + WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); } static struct pernet_operations nf_tables_net_ops = { - .init = nf_tables_init_net, - .exit = nf_tables_exit_net, + .init = nf_tables_init_net, + .pre_exit = nf_tables_pre_exit_net, + .exit = nf_tables_exit_net, + .id = &nf_tables_net_id, + .size = sizeof(struct nftables_pernet), }; static int __init nf_tables_module_init(void) { int err; - spin_lock_init(&nf_tables_destroy_list_lock); err = register_pernet_subsys(&nf_tables_net_ops); if (err < 0) return err; err = nft_chain_filter_init(); if (err < 0) - goto err1; + goto err_chain_filter; err = nf_tables_core_module_init(); if (err < 0) - goto err2; + goto err_core_module; err = register_netdevice_notifier(&nf_tables_flowtable_notifier); if (err < 0) - goto err3; + goto err_netdev_notifier; err = rhltable_init(&nft_objname_ht, &nft_objname_ht_params); if (err < 0) - goto err4; + goto err_rht_objname; err = nft_offload_init(); if (err < 0) - goto err5; + goto err_offload; + + err = netlink_register_notifier(&nft_nl_notifier); + if (err < 0) + goto err_netlink_notifier; /* must be last */ err = nfnetlink_subsys_register(&nf_tables_subsys); if (err < 0) - goto err6; + goto err_nfnl_subsys; nft_chain_route_init(); return err; -err6: + +err_nfnl_subsys: + netlink_unregister_notifier(&nft_nl_notifier); +err_netlink_notifier: nft_offload_exit(); -err5: +err_offload: rhltable_destroy(&nft_objname_ht); -err4: +err_rht_objname: unregister_netdevice_notifier(&nf_tables_flowtable_notifier); -err3: +err_netdev_notifier: nf_tables_core_module_exit(); -err2: +err_core_module: nft_chain_filter_fini(); -err1: +err_chain_filter: unregister_pernet_subsys(&nf_tables_net_ops); return err; } @@ -8235,6 +10169,7 @@ err1: static void __exit nf_tables_module_exit(void) { nfnetlink_subsys_unregister(&nf_tables_subsys); + netlink_unregister_notifier(&nft_nl_notifier); nft_offload_exit(); unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); |