From c50b960ccc5981627628302701e93e6aceccdb1c Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 28 Mar 2014 10:19:47 +0000 Subject: netfilter: nf_tables: implement proper set selection The current set selection simply choses the first set type that provides the requested features, which always results in the rbtree being chosen by virtue of being the first set in the list. What we actually want to do is choose the implementation that can provide the requested features and is optimal from either a performance or memory perspective depending on the characteristics of the elements and the preferences specified by the user. The elements are not known when creating a set. Even if we would provide them for anonymous (literal) sets, we'd still have standalone sets where the elements are not known in advance. We therefore need an abstract description of the data charcteristics. The kernel already knows the size of the key, this patch starts by introducing a nested set description which so far contains only the maximum amount of elements. Based on this the set implementations are changed to provide an estimate of the required amount of memory and the lookup complexity class. The set ops have a new callback ->estimate() that is invoked during set selection. It receives a structure containing the attributes known to the kernel and is supposed to populate a struct nft_set_estimate with the complexity class and, in case the size is known, the complete amount of memory required, or the amount of memory required per element otherwise. Based on the policy specified by the user (performance/memory, defaulting to performance) the kernel will then select the best suited implementation. Even if the set implementation would allow to add more than the specified maximum amount of elements, they are enforced since new implementations might not be able to add more than maximum based on which they were selected. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/uapi/linux/netfilter') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index c88ccbfda5f1..160159274cab 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -211,6 +211,29 @@ enum nft_set_flags { NFT_SET_MAP = 0x8, }; +/** + * enum nft_set_policies - set selection policy + * + * @NFT_SET_POL_PERFORMANCE: prefer high performance over low memory use + * @NFT_SET_POL_MEMORY: prefer low memory use over high performance + */ +enum nft_set_policies { + NFT_SET_POL_PERFORMANCE, + NFT_SET_POL_MEMORY, +}; + +/** + * enum nft_set_desc_attributes - set element description + * + * @NFTA_SET_DESC_SIZE: number of elements in set (NLA_U32) + */ +enum nft_set_desc_attributes { + NFTA_SET_DESC_UNSPEC, + NFTA_SET_DESC_SIZE, + __NFTA_SET_DESC_MAX +}; +#define NFTA_SET_DESC_MAX (__NFTA_SET_DESC_MAX - 1) + /** * enum nft_set_attributes - nf_tables set netlink attributes * @@ -221,6 +244,8 @@ enum nft_set_flags { * @NFTA_SET_KEY_LEN: key data length (NLA_U32) * @NFTA_SET_DATA_TYPE: mapping data type (NLA_U32) * @NFTA_SET_DATA_LEN: mapping data length (NLA_U32) + * @NFTA_SET_POLICY: selection policy (NLA_U32) + * @NFTA_SET_DESC: set description (NLA_NESTED) */ enum nft_set_attributes { NFTA_SET_UNSPEC, @@ -231,6 +256,8 @@ enum nft_set_attributes { NFTA_SET_KEY_LEN, NFTA_SET_DATA_TYPE, NFTA_SET_DATA_LEN, + NFTA_SET_POLICY, + NFTA_SET_DESC, __NFTA_SET_MAX }; #define NFTA_SET_MAX (__NFTA_SET_MAX - 1) -- cgit v1.3-7-g2ca7 From f5efc696cc711021cc73e7543cc3038e58459707 Mon Sep 17 00:00:00 2001 From: Tomasz Bursztyka Date: Mon, 14 Apr 2014 15:41:28 +0300 Subject: netfilter: nf_tables: Add meta expression key for bridge interface name NFT_META_BRI_IIFNAME to get packet input bridge interface name NFT_META_BRI_OIFNAME to get packet output bridge interface name Such meta key are accessible only through NFPROTO_BRIDGE family, on a dedicated nft meta module: nft_meta_bridge. Suggested-by: Pablo Neira Ayuso Signed-off-by: Tomasz Bursztyka Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 4 + net/bridge/Makefile | 2 +- net/bridge/netfilter/Kconfig | 14 +++- net/bridge/netfilter/Makefile | 1 + net/bridge/netfilter/nft_meta_bridge.c | 139 +++++++++++++++++++++++++++++++ 5 files changed, 158 insertions(+), 2 deletions(-) create mode 100644 net/bridge/netfilter/nft_meta_bridge.c (limited to 'include/uapi/linux/netfilter') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 160159274cab..7d6433f66bf8 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -563,6 +563,8 @@ enum nft_exthdr_attributes { * @NFT_META_SECMARK: packet secmark (skb->secmark) * @NFT_META_NFPROTO: netfilter protocol * @NFT_META_L4PROTO: layer 4 protocol number + * @NFT_META_BRI_IIFNAME: packet input bridge interface name + * @NFT_META_BRI_OIFNAME: packet output bridge interface name */ enum nft_meta_keys { NFT_META_LEN, @@ -582,6 +584,8 @@ enum nft_meta_keys { NFT_META_SECMARK, NFT_META_NFPROTO, NFT_META_L4PROTO, + NFT_META_BRI_IIFNAME, + NFT_META_BRI_OIFNAME, }; /** diff --git a/net/bridge/Makefile b/net/bridge/Makefile index e85498b2f166..906a18b4e74a 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -16,4 +16,4 @@ bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o -obj-$(CONFIG_BRIDGE_NF_EBTABLES) += netfilter/ +obj-$(CONFIG_BRIDGE_NETFILTER) += netfilter/ diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index 5ca74a0e595f..3baf29d34e62 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -2,13 +2,25 @@ # Bridge netfilter configuration # # -config NF_TABLES_BRIDGE +menuconfig NF_TABLES_BRIDGE depends on NF_TABLES + select BRIDGE_NETFILTER tristate "Ethernet Bridge nf_tables support" +if NF_TABLES_BRIDGE + +config NFT_BRIDGE_META + tristate "Netfilter nf_table bridge meta support" + depends on NFT_META + help + Add support for bridge dedicated meta key. + +endif # NF_TABLES_BRIDGE + menuconfig BRIDGE_NF_EBTABLES tristate "Ethernet Bridge tables (ebtables) support" depends on BRIDGE && NETFILTER + select BRIDGE_NETFILTER select NETFILTER_XTABLES help ebtables is a general, extensible frame/packet identification diff --git a/net/bridge/netfilter/Makefile b/net/bridge/netfilter/Makefile index ea7629f58b3d..6f2f3943d66f 100644 --- a/net/bridge/netfilter/Makefile +++ b/net/bridge/netfilter/Makefile @@ -3,6 +3,7 @@ # obj-$(CONFIG_NF_TABLES_BRIDGE) += nf_tables_bridge.o +obj-$(CONFIG_NFT_BRIDGE_META) += nft_meta_bridge.o obj-$(CONFIG_BRIDGE_NF_EBTABLES) += ebtables.o diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c new file mode 100644 index 000000000000..4f02109d708f --- /dev/null +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -0,0 +1,139 @@ +/* + * Copyright (c) 2014 Intel Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../br_private.h" + +static void nft_meta_bridge_get_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + const struct nft_meta *priv = nft_expr_priv(expr); + const struct net_device *in = pkt->in, *out = pkt->out; + struct nft_data *dest = &data[priv->dreg]; + const struct net_bridge_port *p; + + switch (priv->key) { + case NFT_META_BRI_IIFNAME: + if (in == NULL || (p = br_port_get_rcu(in)) == NULL) + goto err; + break; + case NFT_META_BRI_OIFNAME: + if (out == NULL || (p = br_port_get_rcu(out)) == NULL) + goto err; + break; + default: + goto out; + } + + strncpy((char *)dest->data, p->br->dev->name, sizeof(dest->data)); + return; +out: + return nft_meta_get_eval(expr, data, pkt); +err: + data[NFT_REG_VERDICT].verdict = NFT_BREAK; +} + +static int nft_meta_bridge_get_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_meta *priv = nft_expr_priv(expr); + int err; + + priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); + switch (priv->key) { + case NFT_META_BRI_IIFNAME: + case NFT_META_BRI_OIFNAME: + break; + default: + return nft_meta_get_init(ctx, expr, tb); + } + + priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG])); + err = nft_validate_output_register(priv->dreg); + if (err < 0) + return err; + + err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE); + if (err < 0) + return err; + + return 0; +} + +static struct nft_expr_type nft_meta_bridge_type; +static const struct nft_expr_ops nft_meta_bridge_get_ops = { + .type = &nft_meta_bridge_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), + .eval = nft_meta_bridge_get_eval, + .init = nft_meta_bridge_get_init, + .dump = nft_meta_get_dump, +}; + +static const struct nft_expr_ops nft_meta_bridge_set_ops = { + .type = &nft_meta_bridge_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), + .eval = nft_meta_set_eval, + .init = nft_meta_set_init, + .dump = nft_meta_set_dump, +}; + +static const struct nft_expr_ops * +nft_meta_bridge_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + if (tb[NFTA_META_KEY] == NULL) + return ERR_PTR(-EINVAL); + + if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG]) + return ERR_PTR(-EINVAL); + + if (tb[NFTA_META_DREG]) + return &nft_meta_bridge_get_ops; + + if (tb[NFTA_META_SREG]) + return &nft_meta_bridge_set_ops; + + return ERR_PTR(-EINVAL); +} + +static struct nft_expr_type nft_meta_bridge_type __read_mostly = { + .family = NFPROTO_BRIDGE, + .name = "meta", + .select_ops = &nft_meta_bridge_select_ops, + .policy = nft_meta_policy, + .maxattr = NFTA_META_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_meta_bridge_module_init(void) +{ + return nft_register_expr(&nft_meta_bridge_type); +} + +static void __exit nft_meta_bridge_module_exit(void) +{ + nft_unregister_expr(&nft_meta_bridge_type); +} + +module_init(nft_meta_bridge_module_init); +module_exit(nft_meta_bridge_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Tomasz Bursztyka "); +MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "meta"); -- cgit v1.3-7-g2ca7 From 683399eddb9fff742b1a14c5a5d03e12bfc0afff Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Sun, 20 Apr 2014 18:57:36 -0600 Subject: netfilter: nfnetlink_acct: Adding quota support to accounting framework nfacct objects already support accounting at the byte and packet level. As such it is a natural extension to add the possiblity to define a ceiling limit for both metrics. All the support for quotas itself is added to nfnetlink acctounting framework to stay coherent with current accounting object management. Quota limit checks are implemented in xt_nfacct filter where statistic collection is already done. Pablo Neira Ayuso has also contributed to this feature. Signed-off-by: Mathieu Poirier Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink_acct.h | 8 ++- include/uapi/linux/netfilter/nfnetlink.h | 2 + include/uapi/linux/netfilter/nfnetlink_acct.h | 9 +++ net/netfilter/nfnetlink_acct.c | 85 +++++++++++++++++++++++++++ net/netfilter/xt_nfacct.c | 5 +- 5 files changed, 107 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux/netfilter') diff --git a/include/linux/netfilter/nfnetlink_acct.h b/include/linux/netfilter/nfnetlink_acct.h index b2e85e59f760..6ec975748742 100644 --- a/include/linux/netfilter/nfnetlink_acct.h +++ b/include/linux/netfilter/nfnetlink_acct.h @@ -3,11 +3,17 @@ #include +enum { + NFACCT_NO_QUOTA = -1, + NFACCT_UNDERQUOTA, + NFACCT_OVERQUOTA, +}; struct nf_acct; struct nf_acct *nfnl_acct_find_get(const char *filter_name); void nfnl_acct_put(struct nf_acct *acct); void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct); - +extern int nfnl_acct_overquota(const struct sk_buff *skb, + struct nf_acct *nfacct); #endif /* _NFNL_ACCT_H */ diff --git a/include/uapi/linux/netfilter/nfnetlink.h b/include/uapi/linux/netfilter/nfnetlink.h index 596ddd45253c..354a7e5e50f2 100644 --- a/include/uapi/linux/netfilter/nfnetlink.h +++ b/include/uapi/linux/netfilter/nfnetlink.h @@ -20,6 +20,8 @@ enum nfnetlink_groups { #define NFNLGRP_CONNTRACK_EXP_DESTROY NFNLGRP_CONNTRACK_EXP_DESTROY NFNLGRP_NFTABLES, #define NFNLGRP_NFTABLES NFNLGRP_NFTABLES + NFNLGRP_ACCT_QUOTA, +#define NFNLGRP_ACCT_QUOTA NFNLGRP_ACCT_QUOTA __NFNLGRP_MAX, }; #define NFNLGRP_MAX (__NFNLGRP_MAX - 1) diff --git a/include/uapi/linux/netfilter/nfnetlink_acct.h b/include/uapi/linux/netfilter/nfnetlink_acct.h index c7b6269e760b..51404ec19022 100644 --- a/include/uapi/linux/netfilter/nfnetlink_acct.h +++ b/include/uapi/linux/netfilter/nfnetlink_acct.h @@ -10,15 +10,24 @@ enum nfnl_acct_msg_types { NFNL_MSG_ACCT_GET, NFNL_MSG_ACCT_GET_CTRZERO, NFNL_MSG_ACCT_DEL, + NFNL_MSG_ACCT_OVERQUOTA, NFNL_MSG_ACCT_MAX }; +enum nfnl_acct_flags { + NFACCT_F_QUOTA_PKTS = (1 << 0), + NFACCT_F_QUOTA_BYTES = (1 << 1), + NFACCT_F_OVERQUOTA = (1 << 2), /* can't be set from userspace */ +}; + enum nfnl_acct_type { NFACCT_UNSPEC, NFACCT_NAME, NFACCT_PKTS, NFACCT_BYTES, NFACCT_USE, + NFACCT_FLAGS, + NFACCT_QUOTA, __NFACCT_MAX }; #define NFACCT_MAX (__NFACCT_MAX - 1) diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index c7b6d466a662..70e86bbb3637 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -32,18 +32,24 @@ static LIST_HEAD(nfnl_acct_list); struct nf_acct { atomic64_t pkts; atomic64_t bytes; + unsigned long flags; struct list_head head; atomic_t refcnt; char name[NFACCT_NAME_MAX]; struct rcu_head rcu_head; + char data[0]; }; +#define NFACCT_F_QUOTA (NFACCT_F_QUOTA_PKTS | NFACCT_F_QUOTA_BYTES) + static int nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const tb[]) { struct nf_acct *nfacct, *matching = NULL; char *acct_name; + unsigned int size = 0; + u32 flags = 0; if (!tb[NFACCT_NAME]) return -EINVAL; @@ -68,15 +74,39 @@ nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb, /* reset counters if you request a replacement. */ atomic64_set(&matching->pkts, 0); atomic64_set(&matching->bytes, 0); + smp_mb__before_clear_bit(); + /* reset overquota flag if quota is enabled. */ + if ((matching->flags & NFACCT_F_QUOTA)) + clear_bit(NFACCT_F_OVERQUOTA, &matching->flags); return 0; } return -EBUSY; } nfacct = kzalloc(sizeof(struct nf_acct), GFP_KERNEL); + if (tb[NFACCT_FLAGS]) { + flags = ntohl(nla_get_be32(tb[NFACCT_FLAGS])); + if (flags & ~NFACCT_F_QUOTA) + return -EOPNOTSUPP; + if ((flags & NFACCT_F_QUOTA) == NFACCT_F_QUOTA) + return -EINVAL; + if (flags & NFACCT_F_OVERQUOTA) + return -EINVAL; + + size += sizeof(u64); + } + + nfacct = kzalloc(sizeof(struct nf_acct) + size, GFP_KERNEL); if (nfacct == NULL) return -ENOMEM; + if (flags & NFACCT_F_QUOTA) { + u64 *quota = (u64 *)nfacct->data; + + *quota = be64_to_cpu(nla_get_be64(tb[NFACCT_QUOTA])); + nfacct->flags = flags; + } + strncpy(nfacct->name, nla_data(tb[NFACCT_NAME]), NFACCT_NAME_MAX); if (tb[NFACCT_BYTES]) { @@ -117,6 +147,9 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, if (type == NFNL_MSG_ACCT_GET_CTRZERO) { pkts = atomic64_xchg(&acct->pkts, 0); bytes = atomic64_xchg(&acct->bytes, 0); + smp_mb__before_clear_bit(); + if (acct->flags & NFACCT_F_QUOTA) + clear_bit(NFACCT_F_OVERQUOTA, &acct->flags); } else { pkts = atomic64_read(&acct->pkts); bytes = atomic64_read(&acct->bytes); @@ -125,7 +158,13 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, nla_put_be64(skb, NFACCT_BYTES, cpu_to_be64(bytes)) || nla_put_be32(skb, NFACCT_USE, htonl(atomic_read(&acct->refcnt)))) goto nla_put_failure; + if (acct->flags & NFACCT_F_QUOTA) { + u64 *quota = (u64 *)acct->data; + if (nla_put_be32(skb, NFACCT_FLAGS, htonl(acct->flags)) || + nla_put_be64(skb, NFACCT_QUOTA, cpu_to_be64(*quota))) + goto nla_put_failure; + } nlmsg_end(skb, nlh); return skb->len; @@ -270,6 +309,8 @@ static const struct nla_policy nfnl_acct_policy[NFACCT_MAX+1] = { [NFACCT_NAME] = { .type = NLA_NUL_STRING, .len = NFACCT_NAME_MAX-1 }, [NFACCT_BYTES] = { .type = NLA_U64 }, [NFACCT_PKTS] = { .type = NLA_U64 }, + [NFACCT_FLAGS] = { .type = NLA_U32 }, + [NFACCT_QUOTA] = { .type = NLA_U64 }, }; static const struct nfnl_callback nfnl_acct_cb[NFNL_MSG_ACCT_MAX] = { @@ -336,6 +377,50 @@ void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct) } EXPORT_SYMBOL_GPL(nfnl_acct_update); +static void nfnl_overquota_report(struct nf_acct *nfacct) +{ + int ret; + struct sk_buff *skb; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (skb == NULL) + return; + + ret = nfnl_acct_fill_info(skb, 0, 0, NFNL_MSG_ACCT_OVERQUOTA, 0, + nfacct); + if (ret <= 0) { + kfree_skb(skb); + return; + } + netlink_broadcast(init_net.nfnl, skb, 0, NFNLGRP_ACCT_QUOTA, + GFP_ATOMIC); +} + +int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) +{ + u64 now; + u64 *quota; + int ret = NFACCT_UNDERQUOTA; + + /* no place here if we don't have a quota */ + if (!(nfacct->flags & NFACCT_F_QUOTA)) + return NFACCT_NO_QUOTA; + + quota = (u64 *)nfacct->data; + now = (nfacct->flags & NFACCT_F_QUOTA_PKTS) ? + atomic64_read(&nfacct->pkts) : atomic64_read(&nfacct->bytes); + + ret = now > *quota; + + if (now >= *quota && + !test_and_set_bit(NFACCT_F_OVERQUOTA, &nfacct->flags)) { + nfnl_overquota_report(nfacct); + } + + return ret; +} +EXPORT_SYMBOL_GPL(nfnl_acct_overquota); + static int __init nfnl_acct_init(void) { int ret; diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c index b3be0ef21f19..8c646ed9c921 100644 --- a/net/netfilter/xt_nfacct.c +++ b/net/netfilter/xt_nfacct.c @@ -21,11 +21,14 @@ MODULE_ALIAS("ip6t_nfacct"); static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par) { + int overquota; const struct xt_nfacct_match_info *info = par->targinfo; nfnl_acct_update(skb, info->nfacct); - return true; + overquota = nfnl_acct_overquota(skb, info->nfacct); + + return overquota == NFACCT_UNDERQUOTA ? false : true; } static int -- cgit v1.3-7-g2ca7 From 958bee14d0718ca7a5002c0f48a099d1d345812a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 3 Apr 2014 11:48:44 +0200 Subject: netfilter: nf_tables: use new transaction infrastructure to handle sets This patch reworks the nf_tables API so set updates are included in the same batch that contains rule updates. This speeds up rule-set updates since we skip a dialog of four messages between kernel and user-space (two on each direction), from: 1) create the set and send netlink message to the kernel 2) process the response from the kernel that contains the allocated name. 3) add the set elements and send netlink message to the kernel. 4) process the response from the kernel (to check for errors). To: 1) add the set to the batch. 2) add the set elements to the batch. 3) add the rule that points to the set. 4) send batch to the kernel. This also introduces an internal set ID (NFTA_SET_ID) that is unique in the batch so set elements and rules can refer to new sets. Backward compatibility has been only retained in userspace, this means that new nft versions can talk to the kernel both in the new and the old fashion. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 12 +++ include/uapi/linux/netfilter/nf_tables.h | 6 ++ net/netfilter/nf_tables_api.c | 123 +++++++++++++++++++++++++++---- net/netfilter/nft_lookup.c | 10 ++- 4 files changed, 133 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux/netfilter') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index d8dfb2695e0f..0f472d668cbe 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -268,6 +268,8 @@ static inline void *nft_set_priv(const struct nft_set *set) struct nft_set *nf_tables_set_lookup(const struct nft_table *table, const struct nlattr *nla); +struct nft_set *nf_tables_set_lookup_byid(const struct net *net, + const struct nlattr *nla); /** * struct nft_set_binding - nf_tables set binding @@ -408,6 +410,16 @@ struct nft_trans_rule { #define nft_trans_rule(trans) \ (((struct nft_trans_rule *)trans->data)->rule) +struct nft_trans_set { + struct nft_set *set; + u32 set_id; +}; + +#define nft_trans_set(trans) \ + (((struct nft_trans_set *)trans->data)->set) +#define nft_trans_set_id(trans) \ + (((struct nft_trans_set *)trans->data)->set_id) + static inline struct nft_expr *nft_expr_first(const struct nft_rule *rule) { return (struct nft_expr *)&rule->data[0]; diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 7d6433f66bf8..2a88f645a5d8 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -246,6 +246,7 @@ enum nft_set_desc_attributes { * @NFTA_SET_DATA_LEN: mapping data length (NLA_U32) * @NFTA_SET_POLICY: selection policy (NLA_U32) * @NFTA_SET_DESC: set description (NLA_NESTED) + * @NFTA_SET_ID: uniquely identifies a set in a transaction (NLA_U32) */ enum nft_set_attributes { NFTA_SET_UNSPEC, @@ -258,6 +259,7 @@ enum nft_set_attributes { NFTA_SET_DATA_LEN, NFTA_SET_POLICY, NFTA_SET_DESC, + NFTA_SET_ID, __NFTA_SET_MAX }; #define NFTA_SET_MAX (__NFTA_SET_MAX - 1) @@ -293,12 +295,14 @@ enum nft_set_elem_attributes { * @NFTA_SET_ELEM_LIST_TABLE: table of the set to be changed (NLA_STRING) * @NFTA_SET_ELEM_LIST_SET: name of the set to be changed (NLA_STRING) * @NFTA_SET_ELEM_LIST_ELEMENTS: list of set elements (NLA_NESTED: nft_set_elem_attributes) + * @NFTA_SET_ELEM_LIST_SET_ID: uniquely identifies a set in a transaction (NLA_U32) */ enum nft_set_elem_list_attributes { NFTA_SET_ELEM_LIST_UNSPEC, NFTA_SET_ELEM_LIST_TABLE, NFTA_SET_ELEM_LIST_SET, NFTA_SET_ELEM_LIST_ELEMENTS, + NFTA_SET_ELEM_LIST_SET_ID, __NFTA_SET_ELEM_LIST_MAX }; #define NFTA_SET_ELEM_LIST_MAX (__NFTA_SET_ELEM_LIST_MAX - 1) @@ -484,12 +488,14 @@ enum nft_cmp_attributes { * @NFTA_LOOKUP_SET: name of the set where to look for (NLA_STRING) * @NFTA_LOOKUP_SREG: source register of the data to look for (NLA_U32: nft_registers) * @NFTA_LOOKUP_DREG: destination register (NLA_U32: nft_registers) + * @NFTA_LOOKUP_SET_ID: uniquely identifies a set in a transaction (NLA_U32) */ enum nft_lookup_attributes { NFTA_LOOKUP_UNSPEC, NFTA_LOOKUP_SET, NFTA_LOOKUP_SREG, NFTA_LOOKUP_DREG, + NFTA_LOOKUP_SET_ID, __NFTA_LOOKUP_MAX }; #define NFTA_LOOKUP_MAX (__NFTA_LOOKUP_MAX - 1) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 34aa3d507542..02d3cc65690c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1934,6 +1934,7 @@ static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = { [NFTA_SET_DATA_LEN] = { .type = NLA_U32 }, [NFTA_SET_POLICY] = { .type = NLA_U32 }, [NFTA_SET_DESC] = { .type = NLA_NESTED }, + [NFTA_SET_ID] = { .type = NLA_U32 }, }; static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { @@ -1984,6 +1985,20 @@ struct nft_set *nf_tables_set_lookup(const struct nft_table *table, return ERR_PTR(-ENOENT); } +struct nft_set *nf_tables_set_lookup_byid(const struct net *net, + const struct nlattr *nla) +{ + struct nft_trans *trans; + u32 id = ntohl(nla_get_be32(nla)); + + list_for_each_entry(trans, &net->nft.commit_list, list) { + if (trans->msg_type == NFT_MSG_NEWSET && + id == nft_trans_set_id(trans)) + return nft_trans_set(trans); + } + return ERR_PTR(-ENOENT); +} + static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, const char *name) { @@ -2259,6 +2274,8 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) return ret; } +#define NFT_SET_INACTIVE (1 << 15) /* Internal set flag */ + static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) @@ -2288,6 +2305,8 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb, set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]); if (IS_ERR(set)) return PTR_ERR(set); + if (set->flags & NFT_SET_INACTIVE) + return -ENOENT; skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (skb2 == NULL) @@ -2321,6 +2340,26 @@ static int nf_tables_set_desc_parse(const struct nft_ctx *ctx, return 0; } +static int nft_trans_set_add(struct nft_ctx *ctx, int msg_type, + struct nft_set *set) +{ + struct nft_trans *trans; + + trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_set)); + if (trans == NULL) + return -ENOMEM; + + if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] != NULL) { + nft_trans_set_id(trans) = + ntohl(nla_get_be32(ctx->nla[NFTA_SET_ID])); + set->flags |= NFT_SET_INACTIVE; + } + nft_trans_set(trans) = set; + list_add_tail(&trans->list, &ctx->net->nft.commit_list); + + return 0; +} + static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) @@ -2341,7 +2380,8 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, if (nla[NFTA_SET_TABLE] == NULL || nla[NFTA_SET_NAME] == NULL || - nla[NFTA_SET_KEY_LEN] == NULL) + nla[NFTA_SET_KEY_LEN] == NULL || + nla[NFTA_SET_ID] == NULL) return -EINVAL; memset(&desc, 0, sizeof(desc)); @@ -2458,8 +2498,11 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb, if (err < 0) goto err2; + err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); + if (err < 0) + goto err2; + list_add_tail(&set->list, &table->sets); - nf_tables_set_notify(&ctx, set, NFT_MSG_NEWSET); return 0; err2: @@ -2469,16 +2512,20 @@ err1: return err; } -static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) +static void nft_set_destroy(struct nft_set *set) { - list_del(&set->list); - nf_tables_set_notify(ctx, set, NFT_MSG_DELSET); - set->ops->destroy(set); module_put(set->ops->owner); kfree(set); } +static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) +{ + list_del(&set->list); + nf_tables_set_notify(ctx, set, NFT_MSG_DELSET); + nft_set_destroy(set); +} + static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) @@ -2500,10 +2547,16 @@ static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb, set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]); if (IS_ERR(set)) return PTR_ERR(set); + if (set->flags & NFT_SET_INACTIVE) + return -ENOENT; if (!list_empty(&set->bindings)) return -EBUSY; - nf_tables_set_destroy(&ctx, set); + err = nft_trans_set_add(&ctx, NFT_MSG_DELSET, set); + if (err < 0) + return err; + + list_del(&set->list); return 0; } @@ -2563,7 +2616,8 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, { list_del(&binding->list); - if (list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS) + if (list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS && + !(set->flags & NFT_SET_INACTIVE)) nf_tables_set_destroy(ctx, set); } @@ -2581,6 +2635,7 @@ static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + [NFTA_SET_ELEM_LIST_TABLE] = { .type = NLA_STRING }, [NFTA_SET_ELEM_LIST_SET] = { .type = NLA_STRING }, [NFTA_SET_ELEM_LIST_ELEMENTS] = { .type = NLA_NESTED }, + [NFTA_SET_ELEM_LIST_SET_ID] = { .type = NLA_U32 }, }; static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, @@ -2680,6 +2735,8 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]); if (IS_ERR(set)) return PTR_ERR(set); + if (set->flags & NFT_SET_INACTIVE) + return -ENOENT; event = NFT_MSG_NEWSETELEM; event |= NFNL_SUBSYS_NFTABLES << 8; @@ -2743,6 +2800,8 @@ static int nf_tables_getsetelem(struct sock *nlsk, struct sk_buff *skb, set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]); if (IS_ERR(set)) return PTR_ERR(set); + if (set->flags & NFT_SET_INACTIVE) + return -ENOENT; if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { @@ -2928,6 +2987,7 @@ static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { + struct net *net = sock_net(skb->sk); const struct nlattr *attr; struct nft_set *set; struct nft_ctx ctx; @@ -2938,8 +2998,15 @@ static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb, return err; set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]); - if (IS_ERR(set)) - return PTR_ERR(set); + if (IS_ERR(set)) { + if (nla[NFTA_SET_ELEM_LIST_SET_ID]) { + set = nf_tables_set_lookup_byid(net, + nla[NFTA_SET_ELEM_LIST_SET_ID]); + } + if (IS_ERR(set)) + return PTR_ERR(set); + } + if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) return -EBUSY; @@ -3069,7 +3136,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_rule_policy, }, [NFT_MSG_NEWSET] = { - .call = nf_tables_newset, + .call_batch = nf_tables_newset, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, @@ -3079,12 +3146,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_set_policy, }, [NFT_MSG_DELSET] = { - .call = nf_tables_delset, + .call_batch = nf_tables_delset, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_NEWSETELEM] = { - .call = nf_tables_newsetelem, + .call_batch = nf_tables_newsetelem, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, @@ -3094,7 +3161,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_set_elem_list_policy, }, [NFT_MSG_DELSETELEM] = { - .call = nf_tables_delsetelem, + .call_batch = nf_tables_delsetelem, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, @@ -3136,6 +3203,16 @@ static int nf_tables_commit(struct sk_buff *skb) nft_trans_rule(trans), NFT_MSG_DELRULE, 0, trans->ctx.afi->family); break; + case NFT_MSG_NEWSET: + nft_trans_set(trans)->flags &= ~NFT_SET_INACTIVE; + nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), + NFT_MSG_NEWSET); + nft_trans_destroy(trans); + break; + case NFT_MSG_DELSET: + nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), + NFT_MSG_DELSET); + break; } } @@ -3148,9 +3225,12 @@ static int nf_tables_commit(struct sk_buff *skb) case NFT_MSG_DELRULE: nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); - nft_trans_destroy(trans); + break; + case NFT_MSG_DELSET: + nft_set_destroy(nft_trans_set(trans)); break; } + nft_trans_destroy(trans); } return 0; @@ -3170,6 +3250,14 @@ static int nf_tables_abort(struct sk_buff *skb) nft_rule_clear(trans->ctx.net, nft_trans_rule(trans)); nft_trans_destroy(trans); break; + case NFT_MSG_NEWSET: + list_del(&nft_trans_set(trans)->list); + break; + case NFT_MSG_DELSET: + list_add_tail(&nft_trans_set(trans)->list, + &trans->ctx.table->sets); + nft_trans_destroy(trans); + break; } } @@ -3181,9 +3269,12 @@ static int nf_tables_abort(struct sk_buff *skb) case NFT_MSG_NEWRULE: nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); - nft_trans_destroy(trans); + break; + case NFT_MSG_NEWSET: + nft_set_destroy(nft_trans_set(trans)); break; } + nft_trans_destroy(trans); } return 0; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 7fd2bea8aa23..6404a726d17b 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -56,8 +56,14 @@ static int nft_lookup_init(const struct nft_ctx *ctx, return -EINVAL; set = nf_tables_set_lookup(ctx->table, tb[NFTA_LOOKUP_SET]); - if (IS_ERR(set)) - return PTR_ERR(set); + if (IS_ERR(set)) { + if (tb[NFTA_LOOKUP_SET_ID]) { + set = nf_tables_set_lookup_byid(ctx->net, + tb[NFTA_LOOKUP_SET_ID]); + } + if (IS_ERR(set)) + return PTR_ERR(set); + } priv->sreg = ntohl(nla_get_be32(tb[NFTA_LOOKUP_SREG])); err = nft_validate_input_register(priv->sreg); -- cgit v1.3-7-g2ca7