diff options
author | David S. Miller <davem@davemloft.net> | 2017-09-04 15:27:49 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2017-09-04 15:27:49 -0700 |
commit | 2ff81cd35f9e9c8e6896ea129eb04976d109f15d (patch) | |
tree | a141c7c7cfe7b9f9a210cac26018d8452f3c662e | |
parent | 45865dabb14cee3be334c1376d69e959a62af561 (diff) | |
parent | 9dee1474121550b20542321f9e0579801c6b587c (diff) | |
download | linux-2ff81cd35f9e9c8e6896ea129eb04976d109f15d.tar.bz2 |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next
Pablo Neira Ayuso says:
====================
Netfilter updates for next-net (part 2)
The following patchset contains Netfilter updates for net-next. This
patchset includes updates for nf_tables, removal of
CONFIG_NETFILTER_DEBUG and a new mode for xt_hashlimit. More
specifically, they:
1) Add new rate match mode for hashlimit, this introduces a new revision
for this match. The idea is to stop matching packets until ratelimit
criteria stands true. Patch from Vishwanath Pai.
2) Add ->select_ops indirection to nf_tables named objects, so we can
choose between different flavours of the same object type, patch from
Pablo M. Bermudo.
3) Shorter function names in nft_limit, basically:
s/nft_limit_pkt_bytes/nft_limit_bytes, also from Pablo M. Bermudo.
4) Add new stateful limit named object type, this allows us to create
limit policies that you can identify via name, also from Pablo.
5) Remove unused hooknum parameter in conntrack ->packet indirection.
From Florian Westphal.
6) Patches to remove CONFIG_NETFILTER_DEBUG and macros such as
IP_NF_ASSERT and IP_NF_ASSERT. From Varsha Rao.
7) Add nf_tables_updchain() helper function and use it from
nf_tables_newchain() to make it more maintainable. Similarly,
add nf_tables_addchain() and use it too.
8) Add new netlink NLM_F_NONREC flag, this flag should only be used for
deletion requests, specifically, to support non-recursive deletion.
Based on what we discussed during NFWS'17 in Faro.
9) Use NLM_F_NONREC from table and sets in nf_tables.
10) Support for recursive chain deletion. Table and set deletion
commands come with an implicit content flush on deletion, while
chains do not. This patch addresses this inconsistency by adding
the code to perform recursive chain deletions. This also comes with
the bits to deal with the new NLM_F_NONREC netlink flag.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
40 files changed, 788 insertions, 352 deletions
diff --git a/arch/parisc/configs/c3000_defconfig b/arch/parisc/configs/c3000_defconfig index 0764d3971cf6..8d41a73bd71b 100644 --- a/arch/parisc/configs/c3000_defconfig +++ b/arch/parisc/configs/c3000_defconfig @@ -31,7 +31,6 @@ CONFIG_IP_PNP_BOOTP=y CONFIG_INET6_IPCOMP=m CONFIG_IPV6_TUNNEL=m CONFIG_NETFILTER=y -CONFIG_NETFILTER_DEBUG=y CONFIG_NET_PKTGEN=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y diff --git a/arch/sh/configs/se7751_defconfig b/arch/sh/configs/se7751_defconfig index 75c92fc1876b..56b5e4ce8d4a 100644 --- a/arch/sh/configs/se7751_defconfig +++ b/arch/sh/configs/se7751_defconfig @@ -28,7 +28,6 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set CONFIG_NETFILTER=y -CONFIG_NETFILTER_DEBUG=y CONFIG_IP_NF_QUEUE=y CONFIG_MTD=y CONFIG_MTD_PARTITIONS=y diff --git a/include/linux/netfilter/xt_hashlimit.h b/include/linux/netfilter/xt_hashlimit.h index 074790c0cf74..0fc458bde80b 100644 --- a/include/linux/netfilter/xt_hashlimit.h +++ b/include/linux/netfilter/xt_hashlimit.h @@ -5,5 +5,6 @@ #define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \ XT_HASHLIMIT_HASH_SIP | XT_HASHLIMIT_HASH_SPT | \ - XT_HASHLIMIT_INVERT | XT_HASHLIMIT_BYTES) + XT_HASHLIMIT_INVERT | XT_HASHLIMIT_BYTES |\ + XT_HASHLIMIT_RATE_MATCH) #endif /*_XT_HASHLIMIT_H*/ diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 6e6f678aaac7..fdc9c64a1c94 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -44,12 +44,6 @@ union nf_conntrack_expect_proto { #include <linux/types.h> #include <linux/skbuff.h> -#ifdef CONFIG_NETFILTER_DEBUG -#define NF_CT_ASSERT(x) WARN_ON(!(x)) -#else -#define NF_CT_ASSERT(x) -#endif - #include <net/netfilter/ipv4/nf_conntrack_ipv4.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> @@ -159,7 +153,7 @@ nf_ct_get(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo) /* decrement reference count on a conntrack */ static inline void nf_ct_put(struct nf_conn *ct) { - NF_CT_ASSERT(ct); + WARN_ON(!ct); nf_conntrack_put(&ct->ct_general); } diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index d4933d56809d..738a0307a96b 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -43,7 +43,6 @@ struct nf_conntrack_l4proto { unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum, unsigned int *timeouts); /* Called when a new connection for this protocol found; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index f9795fe394f3..0f5b12a4ad09 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1007,12 +1007,12 @@ int nft_verdict_dump(struct sk_buff *skb, int type, * * @list: table stateful object list node * @table: table this object belongs to - * @type: pointer to object type - * @data: pointer to object data * @name: name of this stateful object * @genmask: generation mask * @use: number of references to this stateful object * @data: object data, layout depends on type + * @ops: object operations + * @data: pointer to object data */ struct nft_object { struct list_head list; @@ -1021,7 +1021,7 @@ struct nft_object { u32 genmask:2, use:30; /* runtime data below here */ - const struct nft_object_type *type ____cacheline_aligned; + const struct nft_object_ops *ops ____cacheline_aligned; unsigned char data[] __attribute__((aligned(__alignof__(u64)))); }; @@ -1044,27 +1044,39 @@ void nft_obj_notify(struct net *net, struct nft_table *table, /** * struct nft_object_type - stateful object type * - * @eval: stateful object evaluation function + * @select_ops: function to select nft_object_ops + * @ops: default ops, used when no select_ops functions is present * @list: list node in list of object types * @type: stateful object numeric type - * @size: stateful object size * @owner: module owner * @maxattr: maximum netlink attribute * @policy: netlink attribute policy + */ +struct nft_object_type { + const struct nft_object_ops *(*select_ops)(const struct nft_ctx *, + const struct nlattr * const tb[]); + const struct nft_object_ops *ops; + struct list_head list; + u32 type; + unsigned int maxattr; + struct module *owner; + const struct nla_policy *policy; +}; + +/** + * struct nft_object_ops - stateful object operations + * + * @eval: stateful object evaluation function + * @size: stateful object size * @init: initialize object from netlink attributes * @destroy: release existing stateful object * @dump: netlink dump stateful object */ -struct nft_object_type { +struct nft_object_ops { void (*eval)(struct nft_object *obj, struct nft_regs *regs, const struct nft_pktinfo *pkt); - struct list_head list; - u32 type; unsigned int size; - unsigned int maxattr; - struct module *owner; - const struct nla_policy *policy; int (*init)(const struct nft_ctx *ctx, const struct nlattr *const tb[], struct nft_object *obj); @@ -1072,6 +1084,7 @@ struct nft_object_type { int (*dump)(struct sk_buff *skb, struct nft_object *obj, bool reset); + const struct nft_object_type *type; }; int nft_register_obj(struct nft_object_type *obj_type); 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/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 */ 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 */ diff --git a/net/Kconfig b/net/Kconfig index e0e7c62c88f0..9dba2715919d 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -166,13 +166,6 @@ menuconfig NETFILTER if NETFILTER -config NETFILTER_DEBUG - bool "Network packet filtering debugging" - depends on NETFILTER - help - You can say Y here if you want to get additional messages useful in - debugging the netfilter code. - config NETFILTER_ADVANCED bool "Advanced netfilter configuration" depends on NETFILTER diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 54c7ef4e970e..83951f978445 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -252,13 +252,11 @@ unsigned int ebt_do_table(struct sk_buff *skb, } if (verdict == EBT_RETURN) { letsreturn: -#ifdef CONFIG_NETFILTER_DEBUG - if (sp == 0) { - BUGPRINT("RETURN on base chain"); + if (WARN(sp == 0, "RETURN on base chain")) { /* act like this is EBT_CONTINUE */ goto letscontinue; } -#endif + sp--; /* put all the local variables right */ i = cs[sp].n; @@ -271,26 +269,24 @@ letsreturn: } if (verdict == EBT_CONTINUE) goto letscontinue; -#ifdef CONFIG_NETFILTER_DEBUG - if (verdict < 0) { - BUGPRINT("bogus standard verdict\n"); + + if (WARN(verdict < 0, "bogus standard verdict\n")) { read_unlock_bh(&table->lock); return NF_DROP; } -#endif + /* jump to a udc */ cs[sp].n = i + 1; cs[sp].chaininfo = chaininfo; cs[sp].e = ebt_next_entry(point); i = 0; chaininfo = (struct ebt_entries *) (base + verdict); -#ifdef CONFIG_NETFILTER_DEBUG - if (chaininfo->distinguisher) { - BUGPRINT("jump to non-chain\n"); + + if (WARN(chaininfo->distinguisher, "jump to non-chain\n")) { read_unlock_bh(&table->lock); return NF_DROP; } -#endif + nentries = chaininfo->nentries; point = (struct ebt_entry *)chaininfo->data; counter_base = cb_base + chaininfo->counter_offset; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index ce1d97579ce8..576cba2b57e9 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -35,12 +35,6 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("IPv4 packet filter"); -#ifdef CONFIG_NETFILTER_DEBUG -#define IP_NF_ASSERT(x) WARN_ON(!(x)) -#else -#define IP_NF_ASSERT(x) -#endif - void *ipt_alloc_initial_table(const struct xt_table *info) { return xt_alloc_initial_table(ipt, IPT); @@ -263,7 +257,7 @@ ipt_do_table(struct sk_buff *skb, acpar.hotdrop = false; acpar.state = state; - IP_NF_ASSERT(table->valid_hooks & (1 << hook)); + WARN_ON(!(table->valid_hooks & (1 << hook))); local_bh_disable(); addend = xt_write_recseq_begin(); private = table->private; @@ -293,7 +287,7 @@ ipt_do_table(struct sk_buff *skb, const struct xt_entry_match *ematch; struct xt_counters *counter; - IP_NF_ASSERT(e); + WARN_ON(!e); if (!ip_packet_match(ip, indev, outdev, &e->ip, acpar.fragoff)) { no_match: @@ -312,7 +306,7 @@ ipt_do_table(struct sk_buff *skb, ADD_COUNTER(*counter, skb->len, 1); t = ipt_get_target(e); - IP_NF_ASSERT(t->u.kernel.target); + WARN_ON(!t->u.kernel.target); #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 434b4e20f6db..a046c298413a 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -82,7 +82,6 @@ static int icmp_packet(struct nf_conn *ct, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum, unsigned int *timeout) { /* Do not immediately delete the connection after the first @@ -127,7 +126,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; - NF_CT_ASSERT(!skb_nfct(skb)); + WARN_ON(skb_nfct(skb)); zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); /* Are they talking about one of our connections? */ diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index feedd759ca80..a0f37b208268 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -190,7 +190,7 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conntrack_tuple target; unsigned long statusbit; - NF_CT_ASSERT(ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY); + WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) return 0; @@ -306,8 +306,8 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, default: /* ESTABLISHED */ - NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || - ctinfo == IP_CT_ESTABLISHED_REPLY); + WARN_ON(ctinfo != IP_CT_ESTABLISHED && + ctinfo != IP_CT_ESTABLISHED_REPLY); if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out)) goto oif_changed; } diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c index f39037fca923..0c366aad89cb 100644 --- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c @@ -34,12 +34,12 @@ nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, const struct rtable *rt; __be32 newsrc, nh; - NF_CT_ASSERT(hooknum == NF_INET_POST_ROUTING); + WARN_ON(hooknum != NF_INET_POST_ROUTING); ct = nf_ct_get(skb, &ctinfo); - NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || - ctinfo == IP_CT_RELATED_REPLY)); + WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY))); /* Source address is 0.0.0.0 - locally generated packet that is * probably not supposed to be masqueraded. @@ -96,7 +96,7 @@ static int masq_device_event(struct notifier_block *this, * conntracks which were associated with that device, * and forget them. */ - NF_CT_ASSERT(dev->ifindex != 0); + WARN_ON(dev->ifindex == 0); nf_ct_iterate_cleanup_net(net, device_cmp, (void *)(long)dev->ifindex, 0, 0); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 9f6644958e5e..54b1e75eded1 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -39,12 +39,6 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("IPv6 packet filter"); -#ifdef CONFIG_NETFILTER_DEBUG -#define IP_NF_ASSERT(x) WARN_ON(!(x)) -#else -#define IP_NF_ASSERT(x) -#endif - void *ip6t_alloc_initial_table(const struct xt_table *info) { return xt_alloc_initial_table(ip6t, IP6T); @@ -284,7 +278,7 @@ ip6t_do_table(struct sk_buff *skb, acpar.hotdrop = false; acpar.state = state; - IP_NF_ASSERT(table->valid_hooks & (1 << hook)); + WARN_ON(!(table->valid_hooks & (1 << hook))); local_bh_disable(); addend = xt_write_recseq_begin(); @@ -315,7 +309,7 @@ ip6t_do_table(struct sk_buff *skb, const struct xt_entry_match *ematch; struct xt_counters *counter; - IP_NF_ASSERT(e); + WARN_ON(!e); acpar.thoff = 0; if (!ip6_packet_match(skb, indev, outdev, &e->ipv6, &acpar.thoff, &acpar.fragoff, &acpar.hotdrop)) { @@ -335,7 +329,7 @@ ip6t_do_table(struct sk_buff *skb, ADD_COUNTER(*counter, skb->len, 1); t = ip6t_get_target_c(e); - IP_NF_ASSERT(t->u.kernel.target); + WARN_ON(!t->u.kernel.target); #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 43544b975eae..a9e1fd1a8536 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -95,7 +95,6 @@ static int icmpv6_packet(struct nf_conn *ct, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum, unsigned int *timeout) { /* Do not immediately delete the connection after the first @@ -129,8 +128,7 @@ static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb, static int icmpv6_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, - unsigned int icmp6off, - unsigned int hooknum) + unsigned int icmp6off) { struct nf_conntrack_tuple intuple, origtuple; const struct nf_conntrack_tuple_hash *h; @@ -138,7 +136,7 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; - NF_CT_ASSERT(!skb_nfct(skb)); + WARN_ON(skb_nfct(skb)); /* Are they talking about one of our connections? */ if (!nf_ct_get_tuplepr(skb, @@ -214,7 +212,7 @@ icmpv6_error(struct net *net, struct nf_conn *tmpl, if (icmp6h->icmp6_type >= 128) return NF_ACCEPT; - return icmpv6_error_message(net, tmpl, skb, dataoff, hooknum); + return icmpv6_error_message(net, tmpl, skb, dataoff); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index b2b4f031b3a1..46d6dba50698 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -196,7 +196,7 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conntrack_tuple target; unsigned long statusbit; - NF_CT_ASSERT(ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY); + WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) return 0; @@ -319,8 +319,8 @@ nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, default: /* ESTABLISHED */ - NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || - ctinfo == IP_CT_ESTABLISHED_REPLY); + WARN_ON(ctinfo != IP_CT_ESTABLISHED && + ctinfo != IP_CT_ESTABLISHED_REPLY); if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out)) goto oif_changed; } diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index d7b679037bae..98f61fcb9108 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -36,8 +36,8 @@ nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, struct nf_nat_range newrange; ct = nf_ct_get(skb, &ctinfo); - NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || - ctinfo == IP_CT_RELATED_REPLY)); + WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY))); if (ipv6_dev_get_saddr(nf_ct_net(ct), out, &ipv6_hdr(skb)->daddr, 0, &src) < 0) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c23df7c9cd59..99c753c485ee 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -403,7 +403,7 @@ destroy_conntrack(struct nf_conntrack *nfct) const struct nf_conntrack_l4proto *l4proto; pr_debug("destroy_conntrack(%p)\n", ct); - NF_CT_ASSERT(atomic_read(&nfct->use) == 0); + WARN_ON(atomic_read(&nfct->use) != 0); if (unlikely(nf_ct_is_template(ct))) { nf_ct_tmpl_free(ct); @@ -756,12 +756,11 @@ __nf_conntrack_confirm(struct sk_buff *skb) * connections for unconfirmed conns. But packet copies and * REJECT will give spurious warnings here. */ - /* NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 1); */ /* No external references means no one else could have * confirmed us. */ - NF_CT_ASSERT(!nf_ct_is_confirmed(ct)); + WARN_ON(nf_ct_is_confirmed(ct)); pr_debug("Confirming conntrack %p\n", ct); /* We have to check the DYING flag after unlink to prevent * a race against nf_ct_get_next_corpse() possibly called from @@ -1160,7 +1159,7 @@ void nf_conntrack_free(struct nf_conn *ct) /* A freed object has refcnt == 0, that's * the golden rule for SLAB_TYPESAFE_BY_RCU */ - NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0); + WARN_ON(atomic_read(&ct->ct_general.use) != 0); nf_ct_ext_destroy(ct); nf_ct_ext_free(ct); @@ -1414,7 +1413,7 @@ repeat: /* Decide what timeout policy we want to apply to this flow. */ timeouts = nf_ct_timeout_lookup(net, ct, l4proto); - ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, hooknum, timeouts); + ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, timeouts); if (ret <= 0) { /* Invalid: inverse of the return code tells * the netfilter core what to do */ @@ -1468,7 +1467,7 @@ void nf_conntrack_alter_reply(struct nf_conn *ct, struct nf_conn_help *help = nfct_help(ct); /* Should be unconfirmed, so not in hash table yet */ - NF_CT_ASSERT(!nf_ct_is_confirmed(ct)); + WARN_ON(nf_ct_is_confirmed(ct)); pr_debug("Altering reply tuple of %p to ", ct); nf_ct_dump_tuple(newreply); @@ -1490,7 +1489,7 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, unsigned long extra_jiffies, int do_acct) { - NF_CT_ASSERT(skb); + WARN_ON(!skb); /* Only update if this is not a fixed timeout */ if (test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index dad2c0c22ad5..64778f9a8548 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -51,8 +51,8 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, struct nf_conn_help *master_help = nfct_help(exp->master); struct net *net = nf_ct_exp_net(exp); - NF_CT_ASSERT(master_help); - NF_CT_ASSERT(!timer_pending(&exp->timeout)); + WARN_ON(!master_help); + WARN_ON(timer_pending(&exp->timeout)); hlist_del_rcu(&exp->hnode); net->ct.expect_count--; diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 6c605e88ebae..9fe0ddc333fb 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -47,7 +47,7 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) struct nf_ct_ext_type *t; /* Conntrack must not be confirmed to avoid races on reallocation. */ - NF_CT_ASSERT(!nf_ct_is_confirmed(ct)); + WARN_ON(nf_ct_is_confirmed(ct)); old = ct->ext; diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 188347571fc7..0f5a4d79f6b8 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -469,7 +469,7 @@ static unsigned int *dccp_get_timeouts(struct net *net) static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, - u_int8_t pf, unsigned int hooknum, + u_int8_t pf, unsigned int *timeouts) { struct net *net = nf_ct_net(ct); diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 2993995b690d..9cd40700842e 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -61,7 +61,6 @@ static int generic_packet(struct nf_conn *ct, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum, unsigned int *timeout) { nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index c0e3a23ac23a..09a90484c27d 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -245,7 +245,6 @@ static int gre_packet(struct nf_conn *ct, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum, unsigned int *timeouts) { /* If we've seen traffic both ways, this is a GRE connection. diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 890b5c73368d..6303a88af12b 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -307,7 +307,6 @@ static int sctp_packet(struct nf_conn *ct, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum, unsigned int *timeouts) { enum sctp_conntrack new_state, old_state; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 33c52d9ab2f5..cba1c6ffe51a 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -803,7 +803,6 @@ static int tcp_packet(struct nf_conn *ct, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum, unsigned int *timeouts) { struct net *net = nf_ct_net(ct); diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index dcf3030d2226..8af734cd1a94 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -74,7 +74,6 @@ static int udp_packet(struct nf_conn *ct, unsigned int dataoff, enum ip_conntrack_info ctinfo, u_int8_t pf, - unsigned int hooknum, unsigned int *timeouts) { /* If we've seen traffic both ways, this is some kind of UDP diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 9eb85858d764..5a101caa3e12 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -287,7 +287,7 @@ static int ct_seq_show(struct seq_file *s, void *v) struct net *net = seq_file_net(s); int ret = 0; - NF_CT_ASSERT(ct); + WARN_ON(!ct); if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use))) return 0; @@ -304,9 +304,9 @@ static int ct_seq_show(struct seq_file *s, void *v) goto release; l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct)); - NF_CT_ASSERT(l3proto); + WARN_ON(!l3proto); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); - NF_CT_ASSERT(l4proto); + WARN_ON(!l4proto); ret = -ENOSPC; seq_printf(s, "%-8s %u %-8s %u %ld ", diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index b1d3740ae36a..40573aa6c133 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -414,8 +414,8 @@ nf_nat_setup_info(struct nf_conn *ct, if (nf_ct_is_confirmed(ct)) return NF_ACCEPT; - NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC || - maniptype == NF_NAT_MANIP_DST); + WARN_ON(maniptype != NF_NAT_MANIP_SRC && + maniptype != NF_NAT_MANIP_DST); BUG_ON(nf_nat_initialized(ct, maniptype)); /* What we've got will look like inverse of reply. Normally diff --git a/net/netfilter/nf_nat_redirect.c b/net/netfilter/nf_nat_redirect.c index 86067560a318..25b06b959118 100644 --- a/net/netfilter/nf_nat_redirect.c +++ b/net/netfilter/nf_nat_redirect.c @@ -38,11 +38,11 @@ nf_nat_redirect_ipv4(struct sk_buff *skb, __be32 newdst; struct nf_nat_range newrange; - NF_CT_ASSERT(hooknum == NF_INET_PRE_ROUTING || - hooknum == NF_INET_LOCAL_OUT); + WARN_ON(hooknum != NF_INET_PRE_ROUTING && + hooknum != NF_INET_LOCAL_OUT); ct = nf_ct_get(skb, &ctinfo); - NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); + WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED))); /* Local packets: make them go to loopback */ if (hooknum == NF_INET_LOCAL_OUT) { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 149785ff1c7b..929927171426 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -860,6 +860,10 @@ static int nf_tables_deltable(struct net *net, struct sock *nlsk, if (IS_ERR(table)) return PTR_ERR(table); + if (nlh->nlmsg_flags & NLM_F_NONREC && + table->use > 0) + return -EBUSY; + ctx.afi = afi; ctx.table = table; @@ -1335,160 +1339,18 @@ static void nft_chain_release_hook(struct nft_chain_hook *hook) dev_put(hook->dev); } -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 int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, + u8 policy, bool create) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - const struct nlattr * uninitialized_var(name); - struct nft_af_info *afi; - struct nft_table *table; + const struct nlattr * const *nla = ctx->nla; + struct nft_table *table = ctx->table; + struct nft_af_info *afi = ctx->afi; + struct nft_base_chain *basechain; + struct nft_stats __percpu *stats; + struct net *net = ctx->net; struct nft_chain *chain; - struct nft_base_chain *basechain = NULL; - u8 genmask = nft_genmask_next(net); - int family = nfmsg->nfgen_family; - u8 policy = NF_ACCEPT; - u64 handle = 0; unsigned int i; - struct nft_stats __percpu *stats; int err; - bool create; - struct nft_ctx ctx; - - create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false; - - afi = nf_tables_afinfo_lookup(net, family, true); - if (IS_ERR(afi)) - return PTR_ERR(afi); - - table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], genmask); - if (IS_ERR(table)) - return PTR_ERR(table); - - chain = NULL; - name = nla[NFTA_CHAIN_NAME]; - - if (nla[NFTA_CHAIN_HANDLE]) { - handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE])); - chain = nf_tables_chain_lookup_byhandle(table, handle, genmask); - if (IS_ERR(chain)) - return PTR_ERR(chain); - } else { - chain = nf_tables_chain_lookup(table, name, genmask); - if (IS_ERR(chain)) { - if (PTR_ERR(chain) != -ENOENT) - return PTR_ERR(chain); - chain = NULL; - } - } - - if (nla[NFTA_CHAIN_POLICY]) { - if (chain != NULL && - !nft_is_base_chain(chain)) - return -EOPNOTSUPP; - - if (chain == NULL && - nla[NFTA_CHAIN_HOOK] == NULL) - return -EOPNOTSUPP; - - policy = ntohl(nla_get_be32(nla[NFTA_CHAIN_POLICY])); - switch (policy) { - case NF_DROP: - case NF_ACCEPT: - break; - default: - return -EINVAL; - } - } - - if (chain != NULL) { - struct nft_stats *stats = NULL; - struct nft_trans *trans; - - if (nlh->nlmsg_flags & NLM_F_EXCL) - return -EEXIST; - if (nlh->nlmsg_flags & NLM_F_REPLACE) - return -EOPNOTSUPP; - - if (nla[NFTA_CHAIN_HOOK]) { - struct nft_base_chain *basechain; - struct nft_chain_hook hook; - struct nf_hook_ops *ops; - - if (!nft_is_base_chain(chain)) - return -EBUSY; - - err = nft_chain_parse_hook(net, nla, afi, &hook, - create); - if (err < 0) - return err; - - basechain = nft_base_chain(chain); - if (basechain->type != hook.type) { - nft_chain_release_hook(&hook); - return -EBUSY; - } - - for (i = 0; i < afi->nops; i++) { - ops = &basechain->ops[i]; - if (ops->hooknum != hook.num || - ops->priority != hook.priority || - ops->dev != hook.dev) { - nft_chain_release_hook(&hook); - return -EBUSY; - } - } - nft_chain_release_hook(&hook); - } - - if (nla[NFTA_CHAIN_HANDLE] && name) { - struct nft_chain *chain2; - - chain2 = nf_tables_chain_lookup(table, - nla[NFTA_CHAIN_NAME], - genmask); - if (IS_ERR(chain2)) - return PTR_ERR(chain2); - } - - if (nla[NFTA_CHAIN_COUNTERS]) { - if (!nft_is_base_chain(chain)) - return -EOPNOTSUPP; - - stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); - if (IS_ERR(stats)) - return PTR_ERR(stats); - } - - nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla); - trans = nft_trans_alloc(&ctx, NFT_MSG_NEWCHAIN, - sizeof(struct nft_trans_chain)); - if (trans == NULL) { - free_percpu(stats); - return -ENOMEM; - } - - nft_trans_chain_stats(trans) = stats; - nft_trans_chain_update(trans) = true; - - if (nla[NFTA_CHAIN_POLICY]) - nft_trans_chain_policy(trans) = policy; - else - nft_trans_chain_policy(trans) = -1; - - if (nla[NFTA_CHAIN_HANDLE] && name) { - nft_trans_chain_name(trans) = - nla_strdup(name, GFP_KERNEL); - if (!nft_trans_chain_name(trans)) { - kfree(trans); - free_percpu(stats); - return -ENOMEM; - } - } - list_add_tail(&trans->list, &net->nft.commit_list); - return 0; - } if (table->use == UINT_MAX) return -EOVERFLOW; @@ -1547,11 +1409,10 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, if (chain == NULL) return -ENOMEM; } - INIT_LIST_HEAD(&chain->rules); chain->handle = nf_tables_alloc_handle(table); chain->table = table; - chain->name = nla_strdup(name, GFP_KERNEL); + chain->name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL); if (!chain->name) { err = -ENOMEM; goto err1; @@ -1561,21 +1422,191 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, if (err < 0) goto err1; - nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla); - err = nft_trans_chain_add(&ctx, NFT_MSG_NEWCHAIN); + ctx->chain = chain; + err = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (err < 0) goto err2; table->use++; list_add_tail_rcu(&chain->list, &table->chains); + return 0; err2: nf_tables_unregister_hooks(net, table, chain, afi->nops); err1: nf_tables_chain_destroy(chain); + return err; } +static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, + bool create) +{ + const struct nlattr * const *nla = ctx->nla; + struct nft_table *table = ctx->table; + struct nft_chain *chain = ctx->chain; + struct nft_af_info *afi = ctx->afi; + struct nft_base_chain *basechain; + struct nft_stats *stats = NULL; + struct nft_chain_hook hook; + const struct nlattr *name; + struct nf_hook_ops *ops; + struct nft_trans *trans; + int err, i; + + if (nla[NFTA_CHAIN_HOOK]) { + if (!nft_is_base_chain(chain)) + return -EBUSY; + + err = nft_chain_parse_hook(ctx->net, nla, ctx->afi, &hook, + create); + if (err < 0) + return err; + + basechain = nft_base_chain(chain); + if (basechain->type != hook.type) { + nft_chain_release_hook(&hook); + return -EBUSY; + } + + for (i = 0; i < afi->nops; i++) { + ops = &basechain->ops[i]; + if (ops->hooknum != hook.num || + ops->priority != hook.priority || + ops->dev != hook.dev) { + nft_chain_release_hook(&hook); + return -EBUSY; + } + } + nft_chain_release_hook(&hook); + } + + if (nla[NFTA_CHAIN_HANDLE] && + nla[NFTA_CHAIN_NAME]) { + struct nft_chain *chain2; + + chain2 = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], + genmask); + if (IS_ERR(chain2)) + return PTR_ERR(chain2); + } + + if (nla[NFTA_CHAIN_COUNTERS]) { + if (!nft_is_base_chain(chain)) + return -EOPNOTSUPP; + + stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); + if (IS_ERR(stats)) + return PTR_ERR(stats); + } + + trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN, + sizeof(struct nft_trans_chain)); + if (trans == NULL) { + free_percpu(stats); + return -ENOMEM; + } + + nft_trans_chain_stats(trans) = stats; + nft_trans_chain_update(trans) = true; + + if (nla[NFTA_CHAIN_POLICY]) + nft_trans_chain_policy(trans) = policy; + else + nft_trans_chain_policy(trans) = -1; + + name = nla[NFTA_CHAIN_NAME]; + if (nla[NFTA_CHAIN_HANDLE] && name) { + nft_trans_chain_name(trans) = + nla_strdup(name, GFP_KERNEL); + if (!nft_trans_chain_name(trans)) { + kfree(trans); + free_percpu(stats); + return -ENOMEM; + } + } + list_add_tail(&trans->list, &ctx->net->nft.commit_list); + + return 0; +} + +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) +{ + const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + const struct nlattr * uninitialized_var(name); + u8 genmask = nft_genmask_next(net); + int family = nfmsg->nfgen_family; + struct nft_af_info *afi; + struct nft_table *table; + struct nft_chain *chain; + u8 policy = NF_ACCEPT; + struct nft_ctx ctx; + u64 handle = 0; + bool create; + + create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false; + + afi = nf_tables_afinfo_lookup(net, family, true); + if (IS_ERR(afi)) + return PTR_ERR(afi); + + table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], genmask); + if (IS_ERR(table)) + return PTR_ERR(table); + + chain = NULL; + name = nla[NFTA_CHAIN_NAME]; + + if (nla[NFTA_CHAIN_HANDLE]) { + handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE])); + chain = nf_tables_chain_lookup_byhandle(table, handle, genmask); + if (IS_ERR(chain)) + return PTR_ERR(chain); + } else { + chain = nf_tables_chain_lookup(table, name, genmask); + if (IS_ERR(chain)) { + if (PTR_ERR(chain) != -ENOENT) + return PTR_ERR(chain); + chain = NULL; + } + } + + if (nla[NFTA_CHAIN_POLICY]) { + if (chain != NULL && + !nft_is_base_chain(chain)) + return -EOPNOTSUPP; + + if (chain == NULL && + nla[NFTA_CHAIN_HOOK] == NULL) + return -EOPNOTSUPP; + + policy = ntohl(nla_get_be32(nla[NFTA_CHAIN_POLICY])); + switch (policy) { + case NF_DROP: + case NF_ACCEPT: + break; + default: + return -EINVAL; + } + } + + nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla); + + if (chain != NULL) { + if (nlh->nlmsg_flags & NLM_F_EXCL) + return -EEXIST; + if (nlh->nlmsg_flags & NLM_F_REPLACE) + return -EOPNOTSUPP; + + return nf_tables_updchain(&ctx, genmask, policy, create); + } + + return nf_tables_addchain(&ctx, family, genmask, policy, create); +} + static int nf_tables_delchain(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -1586,8 +1617,11 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, struct nft_af_info *afi; struct nft_table *table; struct nft_chain *chain; + struct nft_rule *rule; int family = nfmsg->nfgen_family; struct nft_ctx ctx; + u32 use; + int err; afi = nf_tables_afinfo_lookup(net, family, false); if (IS_ERR(afi)) @@ -1600,11 +1634,30 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); if (IS_ERR(chain)) return PTR_ERR(chain); - if (chain->use > 0) + + if (nlh->nlmsg_flags & NLM_F_NONREC && + chain->use > 0) return -EBUSY; nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla); + use = chain->use; + list_for_each_entry(rule, &chain->rules, list) { + if (!nft_is_active_next(net, rule)) + continue; + use--; + + err = nft_delrule(&ctx, rule); + if (err < 0) + return err; + } + + /* There are rules and elements that are still holding references to us, + * we cannot do a recursive removal in this case. + */ + if (use > 0) + return -EBUSY; + return nft_delchain(&ctx); } @@ -3198,7 +3251,9 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) return PTR_ERR(set); - if (!list_empty(&set->bindings)) + + if (!list_empty(&set->bindings) || + (nlh->nlmsg_flags & NLM_F_NONREC && atomic_read(&set->nelems) > 0)) return -EBUSY; return nft_delset(&ctx, set); @@ -4248,7 +4303,7 @@ struct nft_object *nf_tables_obj_lookup(const struct nft_table *table, list_for_each_entry(obj, &table->objects, list) { if (!nla_strcmp(nla, obj->name) && - objtype == obj->type->type && + objtype == obj->ops->type->type && nft_active_genmask(obj, genmask)) return obj; } @@ -4270,6 +4325,7 @@ static struct nft_object *nft_obj_init(const struct nft_ctx *ctx, const struct nlattr *attr) { struct nlattr *tb[type->maxattr + 1]; + const struct nft_object_ops *ops; struct nft_object *obj; int err; @@ -4282,16 +4338,27 @@ static struct nft_object *nft_obj_init(const struct nft_ctx *ctx, memset(tb, 0, sizeof(tb[0]) * (type->maxattr + 1)); } + if (type->select_ops) { + ops = type->select_ops(ctx, (const struct nlattr * const *)tb); + if (IS_ERR(ops)) { + err = PTR_ERR(ops); + goto err1; + } + } else { + ops = type->ops; + } + err = -ENOMEM; - obj = kzalloc(sizeof(struct nft_object) + type->size, GFP_KERNEL); + obj = kzalloc(sizeof(*obj) + ops->size, GFP_KERNEL); if (obj == NULL) goto err1; - err = type->init(ctx, (const struct nlattr * const *)tb, obj); + err = ops->init(ctx, (const struct nlattr * const *)tb, obj); if (err < 0) goto err2; - obj->type = type; + obj->ops = ops; + return obj; err2: kfree(obj); @@ -4307,7 +4374,7 @@ static int nft_object_dump(struct sk_buff *skb, unsigned int attr, nest = nla_nest_start(skb, attr); if (!nest) goto nla_put_failure; - if (obj->type->dump(skb, obj, reset) < 0) + if (obj->ops->dump(skb, obj, reset) < 0) goto nla_put_failure; nla_nest_end(skb, nest); return 0; @@ -4418,8 +4485,8 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, err3: kfree(obj->name); err2: - if (obj->type->destroy) - obj->type->destroy(obj); + if (obj->ops->destroy) + obj->ops->destroy(obj); kfree(obj); err1: module_put(type->owner); @@ -4446,7 +4513,7 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, if (nla_put_string(skb, NFTA_OBJ_TABLE, table->name) || nla_put_string(skb, NFTA_OBJ_NAME, obj->name) || - nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->type->type)) || + nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->ops->type->type)) || nla_put_be32(skb, NFTA_OBJ_USE, htonl(obj->use)) || nft_object_dump(skb, NFTA_OBJ_DATA, obj, reset)) goto nla_put_failure; @@ -4500,7 +4567,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) goto cont; if (filter && filter->type != NFT_OBJECT_UNSPEC && - obj->type->type != filter->type) + obj->ops->type->type != filter->type) goto cont; if (nf_tables_fill_obj_info(skb, net, NETLINK_CB(cb->skb).portid, @@ -4628,10 +4695,10 @@ err: static void nft_obj_destroy(struct nft_object *obj) { - if (obj->type->destroy) - obj->type->destroy(obj); + if (obj->ops->destroy) + obj->ops->destroy(obj); - module_put(obj->type->owner); + module_put(obj->ops->type->owner); kfree(obj->name); kfree(obj); } diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 67a710ebde09..eefe3b409925 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -175,15 +175,21 @@ static const struct nla_policy nft_counter_policy[NFTA_COUNTER_MAX + 1] = { [NFTA_COUNTER_BYTES] = { .type = NLA_U64 }, }; -static struct nft_object_type nft_counter_obj __read_mostly = { - .type = NFT_OBJECT_COUNTER, +static struct nft_object_type nft_counter_obj_type; +static const struct nft_object_ops nft_counter_obj_ops = { + .type = &nft_counter_obj_type, .size = sizeof(struct nft_counter_percpu_priv), - .maxattr = NFTA_COUNTER_MAX, - .policy = nft_counter_policy, .eval = nft_counter_obj_eval, .init = nft_counter_obj_init, .destroy = nft_counter_obj_destroy, .dump = nft_counter_obj_dump, +}; + +static struct nft_object_type nft_counter_obj_type __read_mostly = { + .type = NFT_OBJECT_COUNTER, + .ops = &nft_counter_obj_ops, + .maxattr = NFTA_COUNTER_MAX, + .policy = nft_counter_policy, .owner = THIS_MODULE, }; @@ -271,7 +277,7 @@ static int __init nft_counter_module_init(void) for_each_possible_cpu(cpu) seqcount_init(per_cpu_ptr(&nft_counter_seq, cpu)); - err = nft_register_obj(&nft_counter_obj); + err = nft_register_obj(&nft_counter_obj_type); if (err < 0) return err; @@ -281,14 +287,14 @@ static int __init nft_counter_module_init(void) return 0; err1: - nft_unregister_obj(&nft_counter_obj); + nft_unregister_obj(&nft_counter_obj_type); return err; } static void __exit nft_counter_module_exit(void) { nft_unregister_expr(&nft_counter_type); - nft_unregister_obj(&nft_counter_obj); + nft_unregister_obj(&nft_counter_obj_type); } module_init(nft_counter_module_init); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 1678e9e75e8e..bd0975d7dd6f 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -904,15 +904,21 @@ static const struct nla_policy nft_ct_helper_policy[NFTA_CT_HELPER_MAX + 1] = { [NFTA_CT_HELPER_L4PROTO] = { .type = NLA_U8 }, }; -static struct nft_object_type nft_ct_helper_obj __read_mostly = { - .type = NFT_OBJECT_CT_HELPER, +static struct nft_object_type nft_ct_helper_obj_type; +static const struct nft_object_ops nft_ct_helper_obj_ops = { + .type = &nft_ct_helper_obj_type, .size = sizeof(struct nft_ct_helper_obj), - .maxattr = NFTA_CT_HELPER_MAX, - .policy = nft_ct_helper_policy, .eval = nft_ct_helper_obj_eval, .init = nft_ct_helper_obj_init, .destroy = nft_ct_helper_obj_destroy, .dump = nft_ct_helper_obj_dump, +}; + +static struct nft_object_type nft_ct_helper_obj_type __read_mostly = { + .type = NFT_OBJECT_CT_HELPER, + .ops = &nft_ct_helper_obj_ops, + .maxattr = NFTA_CT_HELPER_MAX, + .policy = nft_ct_helper_policy, .owner = THIS_MODULE, }; @@ -930,7 +936,7 @@ static int __init nft_ct_module_init(void) if (err < 0) goto err1; - err = nft_register_obj(&nft_ct_helper_obj); + err = nft_register_obj(&nft_ct_helper_obj_type); if (err < 0) goto err2; @@ -945,7 +951,7 @@ err1: static void __exit nft_ct_module_exit(void) { - nft_unregister_obj(&nft_ct_helper_obj); + nft_unregister_obj(&nft_ct_helper_obj_type); nft_unregister_expr(&nft_notrack_type); nft_unregister_expr(&nft_ct_type); } diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 14538b1d4d11..a9fc298ef4c3 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -168,9 +168,9 @@ static const struct nft_expr_ops nft_limit_pkts_ops = { .dump = nft_limit_pkts_dump, }; -static void nft_limit_pkt_bytes_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +static void nft_limit_bytes_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { struct nft_limit *priv = nft_expr_priv(expr); u64 cost = div64_u64(priv->nsecs * pkt->skb->len, priv->rate); @@ -179,29 +179,29 @@ static void nft_limit_pkt_bytes_eval(const struct nft_expr *expr, regs->verdict.code = NFT_BREAK; } -static int nft_limit_pkt_bytes_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_limit_bytes_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { struct nft_limit *priv = nft_expr_priv(expr); return nft_limit_init(priv, tb); } -static int nft_limit_pkt_bytes_dump(struct sk_buff *skb, - const struct nft_expr *expr) +static int nft_limit_bytes_dump(struct sk_buff *skb, + const struct nft_expr *expr) { const struct nft_limit *priv = nft_expr_priv(expr); return nft_limit_dump(skb, priv, NFT_LIMIT_PKT_BYTES); } -static const struct nft_expr_ops nft_limit_pkt_bytes_ops = { +static const struct nft_expr_ops nft_limit_bytes_ops = { .type = &nft_limit_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_limit)), - .eval = nft_limit_pkt_bytes_eval, - .init = nft_limit_pkt_bytes_init, - .dump = nft_limit_pkt_bytes_dump, + .eval = nft_limit_bytes_eval, + .init = nft_limit_bytes_init, + .dump = nft_limit_bytes_dump, }; static const struct nft_expr_ops * @@ -215,7 +215,7 @@ nft_limit_select_ops(const struct nft_ctx *ctx, case NFT_LIMIT_PKTS: return &nft_limit_pkts_ops; case NFT_LIMIT_PKT_BYTES: - return &nft_limit_pkt_bytes_ops; + return &nft_limit_bytes_ops; } return ERR_PTR(-EOPNOTSUPP); } @@ -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 <kaber@trash.net>"); MODULE_ALIAS_NFT_EXPR("limit"); +MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_LIMIT); diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 1dd428fbaaa3..7bcdc48f3d73 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -22,7 +22,7 @@ static void nft_objref_eval(const struct nft_expr *expr, { struct nft_object *obj = nft_objref_priv(expr); - obj->type->eval(obj, regs, pkt); + obj->ops->eval(obj, regs, pkt); } static int nft_objref_init(const struct nft_ctx *ctx, @@ -54,7 +54,8 @@ static int nft_objref_dump(struct sk_buff *skb, const struct nft_expr *expr) const struct nft_object *obj = nft_objref_priv(expr); if (nla_put_string(skb, NFTA_OBJREF_IMM_NAME, obj->name) || - nla_put_be32(skb, NFTA_OBJREF_IMM_TYPE, htonl(obj->type->type))) + nla_put_be32(skb, NFTA_OBJREF_IMM_TYPE, + htonl(obj->ops->type->type))) goto nla_put_failure; return 0; @@ -104,7 +105,7 @@ static void nft_objref_map_eval(const struct nft_expr *expr, return; } obj = *nft_set_ext_obj(ext); - obj->type->eval(obj, regs, pkt); + obj->ops->eval(obj, regs, pkt); } static int nft_objref_map_init(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 25e33159be57..0ed124a93fcf 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -151,14 +151,20 @@ static int nft_quota_obj_dump(struct sk_buff *skb, struct nft_object *obj, return nft_quota_do_dump(skb, priv, reset); } -static struct nft_object_type nft_quota_obj __read_mostly = { - .type = NFT_OBJECT_QUOTA, +static struct nft_object_type nft_quota_obj_type; +static const struct nft_object_ops nft_quota_obj_ops = { + .type = &nft_quota_obj_type, .size = sizeof(struct nft_quota), - .maxattr = NFTA_QUOTA_MAX, - .policy = nft_quota_policy, .init = nft_quota_obj_init, .eval = nft_quota_obj_eval, .dump = nft_quota_obj_dump, +}; + +static struct nft_object_type nft_quota_obj_type __read_mostly = { + .type = NFT_OBJECT_QUOTA, + .ops = &nft_quota_obj_ops, + .maxattr = NFTA_QUOTA_MAX, + .policy = nft_quota_policy, .owner = THIS_MODULE, }; @@ -209,7 +215,7 @@ static int __init nft_quota_module_init(void) { int err; - err = nft_register_obj(&nft_quota_obj); + err = nft_register_obj(&nft_quota_obj_type); if (err < 0) return err; @@ -219,14 +225,14 @@ static int __init nft_quota_module_init(void) return 0; err1: - nft_unregister_obj(&nft_quota_obj); + nft_unregister_obj(&nft_quota_obj_type); return err; } static void __exit nft_quota_module_exit(void) { nft_unregister_expr(&nft_quota_type); - nft_unregister_obj(&nft_quota_obj); + nft_unregister_obj(&nft_quota_obj_type); } module_init(nft_quota_module_init); diff --git a/net/netfilter/xt_NETMAP.c b/net/netfilter/xt_NETMAP.c index e45a01255e70..58aa9dd3c5b7 100644 --- a/net/netfilter/xt_NETMAP.c +++ b/net/netfilter/xt_NETMAP.c @@ -77,10 +77,10 @@ netmap_tg4(struct sk_buff *skb, const struct xt_action_param *par) const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; struct nf_nat_range newrange; - NF_CT_ASSERT(xt_hooknum(par) == NF_INET_PRE_ROUTING || - xt_hooknum(par) == NF_INET_POST_ROUTING || - xt_hooknum(par) == NF_INET_LOCAL_OUT || - xt_hooknum(par) == NF_INET_LOCAL_IN); + WARN_ON(xt_hooknum(par) != NF_INET_PRE_ROUTING && + xt_hooknum(par) != NF_INET_POST_ROUTING && + xt_hooknum(par) != NF_INET_LOCAL_OUT && + xt_hooknum(par) != NF_INET_LOCAL_IN); ct = nf_ct_get(skb, &ctinfo); netmask = ~(mr->range[0].min_ip ^ mr->range[0].max_ip); diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index ffdb611e54a2..10d48234f5f4 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -56,6 +56,7 @@ static inline struct hashlimit_net *hashlimit_pernet(struct net *net) } /* need to declare this at the top */ +static const struct file_operations dl_file_ops_v2; static const struct file_operations dl_file_ops_v1; static const struct file_operations dl_file_ops; @@ -87,8 +88,19 @@ struct dsthash_ent { unsigned long expires; /* precalculated expiry time */ struct { unsigned long prev; /* last modification */ - u_int64_t credit; - u_int64_t credit_cap, cost; + union { + struct { + u_int64_t credit; + u_int64_t credit_cap; + u_int64_t cost; + }; + struct { + u_int32_t interval, prev_window; + u_int64_t current_rate; + u_int64_t rate; + int64_t burst; + }; + }; } rateinfo; struct rcu_head rcu; }; @@ -99,7 +111,7 @@ struct xt_hashlimit_htable { u_int8_t family; bool rnd_initialized; - struct hashlimit_cfg2 cfg; /* config */ + struct hashlimit_cfg3 cfg; /* config */ /* used internally */ spinlock_t lock; /* lock for list_head */ @@ -116,10 +128,10 @@ struct xt_hashlimit_htable { }; static int -cfg_copy(struct hashlimit_cfg2 *to, void *from, int revision) +cfg_copy(struct hashlimit_cfg3 *to, const void *from, int revision) { if (revision == 1) { - struct hashlimit_cfg1 *cfg = from; + struct hashlimit_cfg1 *cfg = (struct hashlimit_cfg1 *)from; to->mode = cfg->mode; to->avg = cfg->avg; @@ -131,7 +143,19 @@ cfg_copy(struct hashlimit_cfg2 *to, void *from, int revision) to->srcmask = cfg->srcmask; to->dstmask = cfg->dstmask; } else if (revision == 2) { - memcpy(to, from, sizeof(struct hashlimit_cfg2)); + struct hashlimit_cfg2 *cfg = (struct hashlimit_cfg2 *)from; + + to->mode = cfg->mode; + to->avg = cfg->avg; + to->burst = cfg->burst; + to->size = cfg->size; + to->max = cfg->max; + to->gc_interval = cfg->gc_interval; + to->expire = cfg->expire; + to->srcmask = cfg->srcmask; + to->dstmask = cfg->dstmask; + } else if (revision == 3) { + memcpy(to, from, sizeof(struct hashlimit_cfg3)); } else { return -EINVAL; } @@ -240,13 +264,14 @@ dsthash_free(struct xt_hashlimit_htable *ht, struct dsthash_ent *ent) } static void htable_gc(struct work_struct *work); -static int htable_create(struct net *net, struct hashlimit_cfg2 *cfg, +static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, const char *name, u_int8_t family, struct xt_hashlimit_htable **out_hinfo, int revision) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); struct xt_hashlimit_htable *hinfo; + const struct file_operations *fops; unsigned int size, i; int ret; @@ -268,7 +293,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg2 *cfg, *out_hinfo = hinfo; /* copy match config into hashtable config */ - ret = cfg_copy(&hinfo->cfg, (void *)cfg, 2); + ret = cfg_copy(&hinfo->cfg, (void *)cfg, 3); if (ret) return ret; @@ -293,11 +318,21 @@ static int htable_create(struct net *net, struct hashlimit_cfg2 *cfg, } spin_lock_init(&hinfo->lock); + switch (revision) { + case 1: + fops = &dl_file_ops_v1; + break; + case 2: + fops = &dl_file_ops_v2; + break; + default: + fops = &dl_file_ops; + } + hinfo->pde = proc_create_data(name, 0, (family == NFPROTO_IPV4) ? hashlimit_net->ipt_hashlimit : hashlimit_net->ip6t_hashlimit, - (revision == 1) ? &dl_file_ops_v1 : &dl_file_ops, - hinfo); + fops, hinfo); if (hinfo->pde == NULL) { kfree(hinfo->name); vfree(hinfo); @@ -482,6 +517,25 @@ static u32 user2credits_byte(u32 user) return (u32) (us >> 32); } +static u64 user2rate(u64 user) +{ + if (user != 0) { + return div64_u64(XT_HASHLIMIT_SCALE_v2, user); + } else { + pr_warn("invalid rate from userspace: %llu\n", user); + return 0; + } +} + +static u64 user2rate_bytes(u64 user) +{ + u64 r; + + r = user ? 0xFFFFFFFFULL / user : 0xFFFFFFFFULL; + r = (r - 1) << 4; + return r; +} + static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode, int revision) { @@ -491,6 +545,21 @@ static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, if (delta == 0) return; + if (revision >= 3 && mode & XT_HASHLIMIT_RATE_MATCH) { + u64 interval = dh->rateinfo.interval * HZ; + + if (delta < interval) + return; + + dh->rateinfo.prev = now; + dh->rateinfo.prev_window = + ((dh->rateinfo.current_rate * interval) > + (delta * dh->rateinfo.rate)); + dh->rateinfo.current_rate = 0; + + return; + } + dh->rateinfo.prev = now; if (mode & XT_HASHLIMIT_BYTES) { @@ -515,7 +584,23 @@ static void rateinfo_init(struct dsthash_ent *dh, struct xt_hashlimit_htable *hinfo, int revision) { dh->rateinfo.prev = jiffies; - if (hinfo->cfg.mode & XT_HASHLIMIT_BYTES) { + if (revision >= 3 && hinfo->cfg.mode & XT_HASHLIMIT_RATE_MATCH) { + dh->rateinfo.prev_window = 0; + dh->rateinfo.current_rate = 0; + if (hinfo->cfg.mode & XT_HASHLIMIT_BYTES) { + dh->rateinfo.rate = user2rate_bytes(hinfo->cfg.avg); + if (hinfo->cfg.burst) + dh->rateinfo.burst = + hinfo->cfg.burst * dh->rateinfo.rate; + else + dh->rateinfo.burst = dh->rateinfo.rate; + } else { + dh->rateinfo.rate = user2rate(hinfo->cfg.avg); + dh->rateinfo.burst = + hinfo->cfg.burst + dh->rateinfo.rate; + } + dh->rateinfo.interval = hinfo->cfg.interval; + } else if (hinfo->cfg.mode & XT_HASHLIMIT_BYTES) { dh->rateinfo.credit = CREDITS_PER_JIFFY_BYTES * HZ; dh->rateinfo.cost = user2credits_byte(hinfo->cfg.avg); dh->rateinfo.credit_cap = hinfo->cfg.burst; @@ -648,7 +733,7 @@ static u32 hashlimit_byte_cost(unsigned int len, struct dsthash_ent *dh) static bool hashlimit_mt_common(const struct sk_buff *skb, struct xt_action_param *par, struct xt_hashlimit_htable *hinfo, - const struct hashlimit_cfg2 *cfg, int revision) + const struct hashlimit_cfg3 *cfg, int revision) { unsigned long now = jiffies; struct dsthash_ent *dh; @@ -680,6 +765,20 @@ hashlimit_mt_common(const struct sk_buff *skb, struct xt_action_param *par, rateinfo_recalc(dh, now, hinfo->cfg.mode, revision); } + if (cfg->mode & XT_HASHLIMIT_RATE_MATCH) { + cost = (cfg->mode & XT_HASHLIMIT_BYTES) ? skb->len : 1; + dh->rateinfo.current_rate += cost; + + if (!dh->rateinfo.prev_window && + (dh->rateinfo.current_rate <= dh->rateinfo.burst)) { + spin_unlock(&dh->lock); + rcu_read_unlock_bh(); + return !(cfg->mode & XT_HASHLIMIT_INVERT); + } else { + goto overlimit; + } + } + if (cfg->mode & XT_HASHLIMIT_BYTES) cost = hashlimit_byte_cost(skb->len, dh); else @@ -693,6 +792,7 @@ hashlimit_mt_common(const struct sk_buff *skb, struct xt_action_param *par, return !(cfg->mode & XT_HASHLIMIT_INVERT); } +overlimit: spin_unlock(&dh->lock); local_bh_enable(); /* default match is underlimit - so over the limit, we need to invert */ @@ -708,7 +808,7 @@ hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_hashlimit_mtinfo1 *info = par->matchinfo; struct xt_hashlimit_htable *hinfo = info->hinfo; - struct hashlimit_cfg2 cfg = {}; + struct hashlimit_cfg3 cfg = {}; int ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 1); @@ -720,17 +820,33 @@ hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) } static bool -hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) +hashlimit_mt_v2(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; struct xt_hashlimit_htable *hinfo = info->hinfo; + struct hashlimit_cfg3 cfg = {}; + int ret; + + ret = cfg_copy(&cfg, (void *)&info->cfg, 2); + + if (ret) + return ret; + + return hashlimit_mt_common(skb, par, hinfo, &cfg, 2); +} + +static bool +hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_hashlimit_mtinfo3 *info = par->matchinfo; + struct xt_hashlimit_htable *hinfo = info->hinfo; - return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 2); + return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 3); } static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, struct xt_hashlimit_htable **hinfo, - struct hashlimit_cfg2 *cfg, + struct hashlimit_cfg3 *cfg, const char *name, int revision) { struct net *net = par->net; @@ -753,7 +869,17 @@ static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, } /* Check for overflow. */ - if (cfg->mode & XT_HASHLIMIT_BYTES) { + if (revision >= 3 && cfg->mode & XT_HASHLIMIT_RATE_MATCH) { + if (cfg->avg == 0) { + pr_info("hashlimit invalid rate\n"); + return -ERANGE; + } + + if (cfg->interval == 0) { + pr_info("hashlimit invalid interval\n"); + return -EINVAL; + } + } else if (cfg->mode & XT_HASHLIMIT_BYTES) { if (user2credits_byte(cfg->avg) == 0) { pr_info("overflow, rate too high: %llu\n", cfg->avg); return -EINVAL; @@ -784,7 +910,7 @@ static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) { struct xt_hashlimit_mtinfo1 *info = par->matchinfo; - struct hashlimit_cfg2 cfg = {}; + struct hashlimit_cfg3 cfg = {}; int ret; if (info->name[sizeof(info->name) - 1] != '\0') @@ -799,15 +925,40 @@ static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) &cfg, info->name, 1); } -static int hashlimit_mt_check(const struct xt_mtchk_param *par) +static int hashlimit_mt_check_v2(const struct xt_mtchk_param *par) { struct xt_hashlimit_mtinfo2 *info = par->matchinfo; + struct hashlimit_cfg3 cfg = {}; + int ret; + + if (info->name[sizeof(info->name) - 1] != '\0') + return -EINVAL; + + ret = cfg_copy(&cfg, (void *)&info->cfg, 2); + + if (ret) + return ret; + + return hashlimit_mt_check_common(par, &info->hinfo, + &cfg, info->name, 2); +} + +static int hashlimit_mt_check(const struct xt_mtchk_param *par) +{ + struct xt_hashlimit_mtinfo3 *info = par->matchinfo; if (info->name[sizeof(info->name) - 1] != '\0') return -EINVAL; return hashlimit_mt_check_common(par, &info->hinfo, &info->cfg, - info->name, 2); + info->name, 3); +} + +static void hashlimit_mt_destroy_v2(const struct xt_mtdtor_param *par) +{ + const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; + + htable_put(info->hinfo); } static void hashlimit_mt_destroy_v1(const struct xt_mtdtor_param *par) @@ -819,7 +970,7 @@ static void hashlimit_mt_destroy_v1(const struct xt_mtdtor_param *par) static void hashlimit_mt_destroy(const struct xt_mtdtor_param *par) { - const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; + const struct xt_hashlimit_mtinfo3 *info = par->matchinfo; htable_put(info->hinfo); } @@ -840,9 +991,20 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { .name = "hashlimit", .revision = 2, .family = NFPROTO_IPV4, - .match = hashlimit_mt, + .match = hashlimit_mt_v2, .matchsize = sizeof(struct xt_hashlimit_mtinfo2), .usersize = offsetof(struct xt_hashlimit_mtinfo2, hinfo), + .checkentry = hashlimit_mt_check_v2, + .destroy = hashlimit_mt_destroy_v2, + .me = THIS_MODULE, + }, + { + .name = "hashlimit", + .revision = 3, + .family = NFPROTO_IPV4, + .match = hashlimit_mt, + .matchsize = sizeof(struct xt_hashlimit_mtinfo3), + .usersize = offsetof(struct xt_hashlimit_mtinfo3, hinfo), .checkentry = hashlimit_mt_check, .destroy = hashlimit_mt_destroy, .me = THIS_MODULE, @@ -863,9 +1025,20 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { .name = "hashlimit", .revision = 2, .family = NFPROTO_IPV6, - .match = hashlimit_mt, + .match = hashlimit_mt_v2, .matchsize = sizeof(struct xt_hashlimit_mtinfo2), .usersize = offsetof(struct xt_hashlimit_mtinfo2, hinfo), + .checkentry = hashlimit_mt_check_v2, + .destroy = hashlimit_mt_destroy_v2, + .me = THIS_MODULE, + }, + { + .name = "hashlimit", + .revision = 3, + .family = NFPROTO_IPV6, + .match = hashlimit_mt, + .matchsize = sizeof(struct xt_hashlimit_mtinfo3), + .usersize = offsetof(struct xt_hashlimit_mtinfo3, hinfo), .checkentry = hashlimit_mt_check, .destroy = hashlimit_mt_destroy, .me = THIS_MODULE, @@ -947,6 +1120,21 @@ static void dl_seq_print(struct dsthash_ent *ent, u_int8_t family, } } +static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, + struct seq_file *s) +{ + const struct xt_hashlimit_htable *ht = s->private; + + spin_lock(&ent->lock); + /* recalculate to show accurate numbers */ + rateinfo_recalc(ent, jiffies, ht->cfg.mode, 2); + + dl_seq_print(ent, family, s); + + spin_unlock(&ent->lock); + return seq_has_overflowed(s); +} + static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { @@ -969,7 +1157,7 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, spin_lock(&ent->lock); /* recalculate to show accurate numbers */ - rateinfo_recalc(ent, jiffies, ht->cfg.mode, 2); + rateinfo_recalc(ent, jiffies, ht->cfg.mode, 3); dl_seq_print(ent, family, s); @@ -977,6 +1165,20 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, return seq_has_overflowed(s); } +static int dl_seq_show_v2(struct seq_file *s, void *v) +{ + struct xt_hashlimit_htable *htable = s->private; + unsigned int *bucket = (unsigned int *)v; + struct dsthash_ent *ent; + + if (!hlist_empty(&htable->hash[*bucket])) { + hlist_for_each_entry(ent, &htable->hash[*bucket], node) + if (dl_seq_real_show_v2(ent, htable->family, s)) + return -1; + } + return 0; +} + static int dl_seq_show_v1(struct seq_file *s, void *v) { struct xt_hashlimit_htable *htable = s->private; @@ -1012,6 +1214,13 @@ static const struct seq_operations dl_seq_ops_v1 = { .show = dl_seq_show_v1 }; +static const struct seq_operations dl_seq_ops_v2 = { + .start = dl_seq_start, + .next = dl_seq_next, + .stop = dl_seq_stop, + .show = dl_seq_show_v2 +}; + static const struct seq_operations dl_seq_ops = { .start = dl_seq_start, .next = dl_seq_next, @@ -1019,6 +1228,18 @@ static const struct seq_operations dl_seq_ops = { .show = dl_seq_show }; +static int dl_proc_open_v2(struct inode *inode, struct file *file) +{ + int ret = seq_open(file, &dl_seq_ops_v2); + + if (!ret) { + struct seq_file *sf = file->private_data; + + sf->private = PDE_DATA(inode); + } + return ret; +} + static int dl_proc_open_v1(struct inode *inode, struct file *file) { int ret = seq_open(file, &dl_seq_ops_v1); @@ -1042,6 +1263,14 @@ static int dl_proc_open(struct inode *inode, struct file *file) return ret; } +static const struct file_operations dl_file_ops_v2 = { + .owner = THIS_MODULE, + .open = dl_proc_open_v2, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release +}; + static const struct file_operations dl_file_ops_v1 = { .owner = THIS_MODULE, .open = dl_proc_open_v1, diff --git a/net/netfilter/xt_nat.c b/net/netfilter/xt_nat.c index 8107b3eb865f..0fd14d1eb09d 100644 --- a/net/netfilter/xt_nat.c +++ b/net/netfilter/xt_nat.c @@ -58,9 +58,9 @@ xt_snat_target_v0(struct sk_buff *skb, const struct xt_action_param *par) struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); - NF_CT_ASSERT(ct != NULL && - (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || - ctinfo == IP_CT_RELATED_REPLY)); + WARN_ON(!(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY))); xt_nat_convert_range(&range, &mr->range[0]); return nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); @@ -75,8 +75,8 @@ xt_dnat_target_v0(struct sk_buff *skb, const struct xt_action_param *par) struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); - NF_CT_ASSERT(ct != NULL && - (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); + WARN_ON(!(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED))); xt_nat_convert_range(&range, &mr->range[0]); return nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); @@ -90,9 +90,9 @@ xt_snat_target_v1(struct sk_buff *skb, const struct xt_action_param *par) struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); - NF_CT_ASSERT(ct != NULL && - (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || - ctinfo == IP_CT_RELATED_REPLY)); + WARN_ON(!(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY))); return nf_nat_setup_info(ct, range, NF_NAT_MANIP_SRC); } @@ -105,8 +105,8 @@ xt_dnat_target_v1(struct sk_buff *skb, const struct xt_action_param *par) struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); - NF_CT_ASSERT(ct != NULL && - (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); + WARN_ON(!(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED))); return nf_nat_setup_info(ct, range, NF_NAT_MANIP_DST); } |