From bea74641e3786d51dcf1175527cc1781420961c9 Mon Sep 17 00:00:00 2001 From: Vishwanath Pai Date: Fri, 18 Aug 2017 20:58:59 +0200 Subject: netfilter: xt_hashlimit: add rate match mode This patch adds a new feature to hashlimit that allows matching on the current packet/byte rate without rate limiting. This can be enabled with a new flag --hashlimit-rate-match. The match returns true if the current rate of packets is above/below the user specified value. The main difference between the existing algorithm and the new one is that the existing algorithm rate-limits the flow whereas the new algorithm does not. Instead it *classifies* the flow based on whether it is above or below a certain rate. I will demonstrate this with an example below. Let us assume this rule: iptables -A INPUT -m hashlimit --hashlimit-above 10/s -j new_chain If the packet rate is 15/s, the existing algorithm would ACCEPT 10 packets every second and send 5 packets to "new_chain". But with the new algorithm, as long as the rate of 15/s is sustained, all packets will continue to match and every packet is sent to new_chain. This new functionality will let us classify different flows based on their current rate, so that further decisions can be made on them based on what the current rate is. This is how the new algorithm works: We divide time into intervals of 1 (sec/min/hour) as specified by the user. We keep track of the number of packets/bytes processed in the current interval. After each interval we reset the counter to 0. When we receive a packet for match, we look at the packet rate during the current interval and the previous interval to make a decision: if [ prev_rate < user and cur_rate < user ] return Below else return Above Where cur_rate is the number of packets/bytes seen in the current interval, prev is the number of packets/bytes seen in the previous interval and 'user' is the rate specified by the user. We also provide flexibility to the user for choosing the time interval using the option --hashilmit-interval. For example the user can keep a low rate like x/hour but still keep the interval as small as 1 second. To preserve backwards compatibility we have to add this feature in a new revision, so I've created revision 3 for hashlimit. The two new options we add are: --hashlimit-rate-match --hashlimit-rate-interval I have updated the help text to add these new options. Also added a few tests for the new options. Suggested-by: Igor Lubashev Reviewed-by: Josh Hunt Signed-off-by: Vishwanath Pai Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/xt_hashlimit.h | 36 ++++++++++++++++++++++++----- 1 file changed, 30 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/xt_hashlimit.h b/include/uapi/linux/netfilter/xt_hashlimit.h index 79da349f1060..aa98573248b1 100644 --- a/include/uapi/linux/netfilter/xt_hashlimit.h +++ b/include/uapi/linux/netfilter/xt_hashlimit.h @@ -19,12 +19,13 @@ struct xt_hashlimit_htable; enum { - XT_HASHLIMIT_HASH_DIP = 1 << 0, - XT_HASHLIMIT_HASH_DPT = 1 << 1, - XT_HASHLIMIT_HASH_SIP = 1 << 2, - XT_HASHLIMIT_HASH_SPT = 1 << 3, - XT_HASHLIMIT_INVERT = 1 << 4, - XT_HASHLIMIT_BYTES = 1 << 5, + XT_HASHLIMIT_HASH_DIP = 1 << 0, + XT_HASHLIMIT_HASH_DPT = 1 << 1, + XT_HASHLIMIT_HASH_SIP = 1 << 2, + XT_HASHLIMIT_HASH_SPT = 1 << 3, + XT_HASHLIMIT_INVERT = 1 << 4, + XT_HASHLIMIT_BYTES = 1 << 5, + XT_HASHLIMIT_RATE_MATCH = 1 << 6, }; struct hashlimit_cfg { @@ -79,6 +80,21 @@ struct hashlimit_cfg2 { __u8 srcmask, dstmask; }; +struct hashlimit_cfg3 { + __u64 avg; /* Average secs between packets * scale */ + __u64 burst; /* Period multiplier for upper limit. */ + __u32 mode; /* bitmask of XT_HASHLIMIT_HASH_* */ + + /* user specified */ + __u32 size; /* how many buckets */ + __u32 max; /* max number of entries */ + __u32 gc_interval; /* gc interval */ + __u32 expire; /* when do entries expire? */ + + __u32 interval; + __u8 srcmask, dstmask; +}; + struct xt_hashlimit_mtinfo1 { char name[IFNAMSIZ]; struct hashlimit_cfg1 cfg; @@ -95,4 +111,12 @@ struct xt_hashlimit_mtinfo2 { struct xt_hashlimit_htable *hinfo __attribute__((aligned(8))); }; +struct xt_hashlimit_mtinfo3 { + char name[NAME_MAX]; + struct hashlimit_cfg3 cfg; + + /* Used internally by the kernel */ + struct xt_hashlimit_htable *hinfo __attribute__((aligned(8))); +}; + #endif /* _UAPI_XT_HASHLIMIT_H */ -- cgit v1.2.3 From a691205571723cb0544110ca91653ac4b0eb5b17 Mon Sep 17 00:00:00 2001 From: "Pablo M. Bermudo Garay" Date: Wed, 23 Aug 2017 22:41:25 +0200 Subject: netfilter: nft_limit: add stateful object type Register a new limit stateful object type into the stateful object infrastructure. Signed-off-by: Pablo M. Bermudo Garay Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 3 +- net/netfilter/nft_limit.c | 122 ++++++++++++++++++++++++++++++- 2 files changed, 123 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index b49da72efa68..871afa4871bf 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1282,7 +1282,8 @@ enum nft_ct_helper_attributes { #define NFT_OBJECT_COUNTER 1 #define NFT_OBJECT_QUOTA 2 #define NFT_OBJECT_CT_HELPER 3 -#define __NFT_OBJECT_MAX 4 +#define NFT_OBJECT_LIMIT 4 +#define __NFT_OBJECT_MAX 5 #define NFT_OBJECT_MAX (__NFT_OBJECT_MAX - 1) /** diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index aae2d1ec27f3..a9fc298ef4c3 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -229,14 +229,133 @@ static struct nft_expr_type nft_limit_type __read_mostly = { .owner = THIS_MODULE, }; +static void nft_limit_obj_pkts_eval(struct nft_object *obj, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_limit_pkts *priv = nft_obj_data(obj); + + if (nft_limit_eval(&priv->limit, priv->cost)) + regs->verdict.code = NFT_BREAK; +} + +static int nft_limit_obj_pkts_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], + struct nft_object *obj) +{ + struct nft_limit_pkts *priv = nft_obj_data(obj); + int err; + + err = nft_limit_init(&priv->limit, tb); + if (err < 0) + return err; + + priv->cost = div64_u64(priv->limit.nsecs, priv->limit.rate); + return 0; +} + +static int nft_limit_obj_pkts_dump(struct sk_buff *skb, + struct nft_object *obj, + bool reset) +{ + const struct nft_limit_pkts *priv = nft_obj_data(obj); + + return nft_limit_dump(skb, &priv->limit, NFT_LIMIT_PKTS); +} + +static struct nft_object_type nft_limit_obj_type; +static const struct nft_object_ops nft_limit_obj_pkts_ops = { + .type = &nft_limit_obj_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_limit_pkts)), + .init = nft_limit_obj_pkts_init, + .eval = nft_limit_obj_pkts_eval, + .dump = nft_limit_obj_pkts_dump, +}; + +static void nft_limit_obj_bytes_eval(struct nft_object *obj, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_limit *priv = nft_obj_data(obj); + u64 cost = div64_u64(priv->nsecs * pkt->skb->len, priv->rate); + + if (nft_limit_eval(priv, cost)) + regs->verdict.code = NFT_BREAK; +} + +static int nft_limit_obj_bytes_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], + struct nft_object *obj) +{ + struct nft_limit *priv = nft_obj_data(obj); + + return nft_limit_init(priv, tb); +} + +static int nft_limit_obj_bytes_dump(struct sk_buff *skb, + struct nft_object *obj, + bool reset) +{ + const struct nft_limit *priv = nft_obj_data(obj); + + return nft_limit_dump(skb, priv, NFT_LIMIT_PKT_BYTES); +} + +static struct nft_object_type nft_limit_obj_type; +static const struct nft_object_ops nft_limit_obj_bytes_ops = { + .type = &nft_limit_obj_type, + .size = sizeof(struct nft_limit), + .init = nft_limit_obj_bytes_init, + .eval = nft_limit_obj_bytes_eval, + .dump = nft_limit_obj_bytes_dump, +}; + +static const struct nft_object_ops * +nft_limit_obj_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + if (!tb[NFTA_LIMIT_TYPE]) + return &nft_limit_obj_pkts_ops; + + switch (ntohl(nla_get_be32(tb[NFTA_LIMIT_TYPE]))) { + case NFT_LIMIT_PKTS: + return &nft_limit_obj_pkts_ops; + case NFT_LIMIT_PKT_BYTES: + return &nft_limit_obj_bytes_ops; + } + return ERR_PTR(-EOPNOTSUPP); +} + +static struct nft_object_type nft_limit_obj_type __read_mostly = { + .select_ops = nft_limit_obj_select_ops, + .type = NFT_OBJECT_LIMIT, + .maxattr = NFTA_LIMIT_MAX, + .policy = nft_limit_policy, + .owner = THIS_MODULE, +}; + static int __init nft_limit_module_init(void) { - return nft_register_expr(&nft_limit_type); + int err; + + err = nft_register_obj(&nft_limit_obj_type); + if (err < 0) + return err; + + err = nft_register_expr(&nft_limit_type); + if (err < 0) + goto err1; + + return 0; +err1: + nft_unregister_obj(&nft_limit_obj_type); + return err; } static void __exit nft_limit_module_exit(void) { nft_unregister_expr(&nft_limit_type); + nft_unregister_obj(&nft_limit_obj_type); } module_init(nft_limit_module_init); @@ -245,3 +364,4 @@ module_exit(nft_limit_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy "); MODULE_ALIAS_NFT_EXPR("limit"); +MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_LIMIT); -- cgit v1.2.3 From 2335ba704f32b855651d0cd15dd9b271ec565fb6 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 3 Sep 2017 23:55:59 +0200 Subject: netlink: add NLM_F_NONREC flag for deletion requests In the last NFWS in Faro, Portugal, we discussed that netlink is lacking the semantics to request non recursive deletions, ie. do not delete an object iff it has child objects that hang from this parent object that the user requests to be deleted. We need this new flag to solve a problem for the iptables-compat backward compatibility utility, that runs iptables commands using the existing nf_tables netlink interface. Specifically, custom chains in iptables cannot be deleted if there are rules in it, however, nf_tables allows to remove any chain that is populated with content. To sort out this asymmetry, iptables-compat userspace sets this new NLM_F_NONREC flag to obtain the same semantics that iptables provides. This new flag should only be used for deletion requests. Note this new flag value overlaps with the existing: * NLM_F_ROOT for get requests. * NLM_F_REPLACE for new requests. However, those flags should not ever be used in deletion requests. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netlink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index f4fc9c9e123d..e8af60a7c56d 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -69,6 +69,9 @@ struct nlmsghdr { #define NLM_F_CREATE 0x400 /* Create, if it does not exist */ #define NLM_F_APPEND 0x800 /* Add to end of list */ +/* Modifiers to DELETE request */ +#define NLM_F_NONREC 0x100 /* Do not delete recursively */ + /* Flags for ACK message */ #define NLM_F_CAPPED 0x100 /* request was capped */ #define NLM_F_ACK_TLVS 0x200 /* extended ACK TVLs were included */ -- cgit v1.2.3