From 0e60ebe04c51807db972d03665651ae6b5c26d7e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Nov 2010 18:17:21 +0100 Subject: netfilter: add __rcu annotations Add some __rcu annotations and use helpers to reduce number of sparse warnings (CONFIG_SPARSE_RCU_POINTER=y) Signed-off-by: Eric Dumazet Signed-off-by: Patrick McHardy --- include/linux/netfilter.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/netfilter.h') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 89341c32631a..928a35ec21c7 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -265,7 +265,7 @@ struct nf_afinfo { int route_key_size; }; -extern const struct nf_afinfo *nf_afinfo[NFPROTO_NUMPROTO]; +extern const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO]; static inline const struct nf_afinfo *nf_get_afinfo(unsigned short family) { return rcu_dereference(nf_afinfo[family]); @@ -355,9 +355,9 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #endif /*CONFIG_NETFILTER*/ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) -extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *); +extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu; extern void nf_ct_attach(struct sk_buff *, struct sk_buff *); -extern void (*nf_ct_destroy)(struct nf_conntrack *); +extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} #endif -- cgit v1.2.3 From f615df76ed862b7d3927ec5f55b805ca19be29d9 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 18 Jan 2011 15:52:14 +0100 Subject: netfilter: reduce NF_VERDICT_MASK to 0xff NF_VERDICT_MASK is currently 0xffff. This is because the upper 16 bits are used to store errno (for NF_DROP) or the queue number (NF_QUEUE verdict). As there are up to 0xffff different queues available, there is no more room to store additional flags. At the moment there are only 6 different verdicts, i.e. we can reduce NF_VERDICT_MASK to 0xff to allow storing additional flags in the 0xff00 space. NF_VERDICT_BITS would then be reduced to 8, but because the value is exported to userspace, this might cause breakage; e.g.: e.g. 'queuenr = (1 << NF_VERDICT_BITS) | NF_QUEUE' would now break. Thus, remove NF_VERDICT_BITS usage in the kernel and move the old value to the 'userspace compat' section. Signed-off-by: Florian Westphal Signed-off-by: Patrick McHardy --- include/linux/netfilter.h | 20 +++++++++++++++----- net/netfilter/core.c | 4 ++-- net/netfilter/nf_queue.c | 2 +- 3 files changed, 18 insertions(+), 8 deletions(-) (limited to 'include/linux/netfilter.h') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 0ab7ca787b22..78b73cc10216 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -24,16 +24,19 @@ #define NF_MAX_VERDICT NF_STOP /* we overload the higher bits for encoding auxiliary data such as the queue - * number. Not nice, but better than additional function arguments. */ -#define NF_VERDICT_MASK 0x0000ffff -#define NF_VERDICT_BITS 16 + * number or errno values. Not nice, but better than additional function + * arguments. */ +#define NF_VERDICT_MASK 0x000000ff + +/* extra verdict flags have mask 0x0000ff00 */ +/* queue number (NF_QUEUE) or errno (NF_DROP) */ #define NF_VERDICT_QMASK 0xffff0000 #define NF_VERDICT_QBITS 16 -#define NF_QUEUE_NR(x) ((((x) << NF_VERDICT_BITS) & NF_VERDICT_QMASK) | NF_QUEUE) +#define NF_QUEUE_NR(x) ((((x) << 16) & NF_VERDICT_QMASK) | NF_QUEUE) -#define NF_DROP_ERR(x) (((-x) << NF_VERDICT_BITS) | NF_DROP) +#define NF_DROP_ERR(x) (((-x) << 16) | NF_DROP) /* only for userspace compatibility */ #ifndef __KERNEL__ @@ -41,6 +44,9 @@ <= 0x2000 is used for protocol-flags. */ #define NFC_UNKNOWN 0x4000 #define NFC_ALTERED 0x8000 + +/* NF_VERDICT_BITS should be 8 now, but userspace might break if this changes */ +#define NF_VERDICT_BITS 16 #endif enum nf_inet_hooks { @@ -72,6 +78,10 @@ union nf_inet_addr { #ifdef __KERNEL__ #ifdef CONFIG_NETFILTER +static inline int NF_DROP_GETERR(int verdict) +{ + return -(verdict >> NF_VERDICT_QBITS); +} static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1, const union nf_inet_addr *a2) diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 0c5b796ef527..4d88e45b978e 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -175,12 +175,12 @@ next_hook: ret = 1; } else if ((verdict & NF_VERDICT_MASK) == NF_DROP) { kfree_skb(skb); - ret = -(verdict >> NF_VERDICT_BITS); + ret = NF_DROP_GETERR(verdict); if (ret == 0) ret = -EPERM; } else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) { ret = nf_queue(skb, elem, pf, hook, indev, outdev, okfn, - verdict >> NF_VERDICT_BITS); + verdict >> NF_VERDICT_QBITS); if (ret < 0) { if (ret == -ECANCELED) goto next_hook; diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 5c4b730a2e68..ce1150d4a3f2 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -299,7 +299,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) case NF_QUEUE: err = __nf_queue(skb, elem, entry->pf, entry->hook, entry->indev, entry->outdev, entry->okfn, - verdict >> NF_VERDICT_BITS); + verdict >> NF_VERDICT_QBITS); if (err < 0) { if (err == -ECANCELED) goto next_hook; -- cgit v1.2.3 From 94b27cc36123069966616670c3653cd6873babe9 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 18 Jan 2011 16:08:30 +0100 Subject: netfilter: allow NFQUEUE bypass if no listener is available If an skb is to be NF_QUEUE'd, but no program has opened the queue, the packet is dropped. This adds a v2 target revision of xt_NFQUEUE that allows packets to continue through the ruleset instead. Because the actual queueing happens outside of the target context, the 'bypass' flag has to be communicated back to the netfilter core. Unfortunately the only choice to do this without adding a new function argument is to use the target function return value (i.e. the verdict). In the NF_QUEUE case, the upper 16bit already contain the queue number to use. The previous patch reduced NF_VERDICT_MASK to 0xff, i.e. we now have extra room for a new flag. If a hook issued a NF_QUEUE verdict, then the netfilter core will continue packet processing if the queueing hook returns -ESRCH (== "this queue does not exist") and the new NF_VERDICT_FLAG_QUEUE_BYPASS flag is set in the verdict value. Note: If the queue exists, but userspace does not consume packets fast enough, the skb will still be dropped. Signed-off-by: Florian Westphal Signed-off-by: Patrick McHardy --- include/linux/netfilter.h | 1 + include/linux/netfilter/xt_NFQUEUE.h | 6 ++++++ net/netfilter/core.c | 3 +++ net/netfilter/nf_queue.c | 7 ++++++- net/netfilter/xt_NFQUEUE.c | 28 +++++++++++++++++++++++++--- 5 files changed, 41 insertions(+), 4 deletions(-) (limited to 'include/linux/netfilter.h') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 78b73cc10216..eeec00abb664 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -29,6 +29,7 @@ #define NF_VERDICT_MASK 0x000000ff /* extra verdict flags have mask 0x0000ff00 */ +#define NF_VERDICT_FLAG_QUEUE_BYPASS 0x00008000 /* queue number (NF_QUEUE) or errno (NF_DROP) */ #define NF_VERDICT_QMASK 0xffff0000 diff --git a/include/linux/netfilter/xt_NFQUEUE.h b/include/linux/netfilter/xt_NFQUEUE.h index 2584f4a777de..9eafdbbb401c 100644 --- a/include/linux/netfilter/xt_NFQUEUE.h +++ b/include/linux/netfilter/xt_NFQUEUE.h @@ -20,4 +20,10 @@ struct xt_NFQ_info_v1 { __u16 queues_total; }; +struct xt_NFQ_info_v2 { + __u16 queuenum; + __u16 queues_total; + __u16 bypass; +}; + #endif /* _XT_NFQ_TARGET_H */ diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 4d88e45b978e..1e00bf7d27c5 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -184,6 +184,9 @@ next_hook: if (ret < 0) { if (ret == -ECANCELED) goto next_hook; + if (ret == -ESRCH && + (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) + goto next_hook; kfree_skb(skb); } ret = 0; diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index ce1150d4a3f2..5ab22e2bbd7d 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -138,8 +138,10 @@ static int __nf_queue(struct sk_buff *skb, rcu_read_lock(); qh = rcu_dereference(queue_handler[pf]); - if (!qh) + if (!qh) { + status = -ESRCH; goto err_unlock; + } afinfo = nf_get_afinfo(pf); if (!afinfo) @@ -303,6 +305,9 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) if (err < 0) { if (err == -ECANCELED) goto next_hook; + if (err == -ESRCH && + (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) + goto next_hook; kfree_skb(skb); } break; diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index 39627706aac6..d4f4b5d66b20 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -83,9 +83,20 @@ nfqueue_tg_v1(struct sk_buff *skb, const struct xt_action_param *par) return NF_QUEUE_NR(queue); } -static int nfqueue_tg_v1_check(const struct xt_tgchk_param *par) +static unsigned int +nfqueue_tg_v2(struct sk_buff *skb, const struct xt_action_param *par) { - const struct xt_NFQ_info_v1 *info = par->targinfo; + const struct xt_NFQ_info_v2 *info = par->targinfo; + unsigned int ret = nfqueue_tg_v1(skb, par); + + if (info->bypass) + ret |= NF_VERDICT_FLAG_QUEUE_BYPASS; + return ret; +} + +static int nfqueue_tg_check(const struct xt_tgchk_param *par) +{ + const struct xt_NFQ_info_v2 *info = par->targinfo; u32 maxid; if (unlikely(!rnd_inited)) { @@ -102,6 +113,8 @@ static int nfqueue_tg_v1_check(const struct xt_tgchk_param *par) info->queues_total, maxid); return -ERANGE; } + if (par->target->revision == 2 && info->bypass > 1) + return -EINVAL; return 0; } @@ -117,11 +130,20 @@ static struct xt_target nfqueue_tg_reg[] __read_mostly = { .name = "NFQUEUE", .revision = 1, .family = NFPROTO_UNSPEC, - .checkentry = nfqueue_tg_v1_check, + .checkentry = nfqueue_tg_check, .target = nfqueue_tg_v1, .targetsize = sizeof(struct xt_NFQ_info_v1), .me = THIS_MODULE, }, + { + .name = "NFQUEUE", + .revision = 2, + .family = NFPROTO_UNSPEC, + .checkentry = nfqueue_tg_check, + .target = nfqueue_tg_v2, + .targetsize = sizeof(struct xt_NFQ_info_v2), + .me = THIS_MODULE, + }, }; static int __init nfqueue_tg_init(void) -- cgit v1.2.3 From 31ad3dd64e689bc79dd819f8f134b9b025240eb8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 4 Apr 2011 16:56:29 +0200 Subject: netfilter: af_info: add network namespace parameter to route hook This is required to eventually replace the rt6_lookup call in xt_addrtype.c with nf_afinfo->route(). Signed-off-by: Florian Westphal Acked-by: David S. Miller Signed-off-by: Patrick McHardy --- include/linux/netfilter.h | 3 ++- net/ipv4/netfilter.c | 5 +++-- net/ipv6/netfilter.c | 5 +++-- net/netfilter/nf_conntrack_h323_main.c | 8 ++++---- net/netfilter/xt_TCPMSS.c | 2 +- 5 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include/linux/netfilter.h') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index eeec00abb664..20ed4528e850 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -270,7 +270,8 @@ struct nf_afinfo { unsigned int dataoff, unsigned int len, u_int8_t protocol); - int (*route)(struct dst_entry **dst, struct flowi *fl); + int (*route)(struct net *net, struct dst_entry **dst, + struct flowi *fl); void (*saveroute)(const struct sk_buff *skb, struct nf_queue_entry *entry); int (*reroute)(struct sk_buff *skb, diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index f3c0b549b8e1..f1035f056503 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -221,9 +221,10 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook, return csum; } -static int nf_ip_route(struct dst_entry **dst, struct flowi *fl) +static int nf_ip_route(struct net *net, struct dst_entry **dst, + struct flowi *fl) { - struct rtable *rt = ip_route_output_key(&init_net, &fl->u.ip4); + struct rtable *rt = ip_route_output_key(net, &fl->u.ip4); if (IS_ERR(rt)) return PTR_ERR(rt); *dst = &rt->dst; diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 39aaca2b4fd2..e008b9b4a779 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -90,9 +90,10 @@ static int nf_ip6_reroute(struct sk_buff *skb, return 0; } -static int nf_ip6_route(struct dst_entry **dst, struct flowi *fl) +static int nf_ip6_route(struct net *net, struct dst_entry **dst, + struct flowi *fl) { - *dst = ip6_route_output(&init_net, NULL, &fl->u.ip6); + *dst = ip6_route_output(net, NULL, &fl->u.ip6); return (*dst)->error; } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 533a183e6661..39a453895b4d 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -731,9 +731,9 @@ static int callforward_do_filter(const union nf_inet_addr *src, memset(&fl2, 0, sizeof(fl2)); fl2.daddr = dst->ip; - if (!afinfo->route((struct dst_entry **)&rt1, + if (!afinfo->route(&init_net, (struct dst_entry **)&rt1, flowi4_to_flowi(&fl1))) { - if (!afinfo->route((struct dst_entry **)&rt2, + if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, flowi4_to_flowi(&fl2))) { if (rt1->rt_gateway == rt2->rt_gateway && rt1->dst.dev == rt2->dst.dev) @@ -755,9 +755,9 @@ static int callforward_do_filter(const union nf_inet_addr *src, memset(&fl2, 0, sizeof(fl2)); ipv6_addr_copy(&fl2.daddr, &dst->in6); - if (!afinfo->route((struct dst_entry **)&rt1, + if (!afinfo->route(&init_net, (struct dst_entry **)&rt1, flowi6_to_flowi(&fl1))) { - if (!afinfo->route((struct dst_entry **)&rt2, + if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, flowi6_to_flowi(&fl2))) { if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway, sizeof(rt1->rt6i_gateway)) && diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 6e6b46cb1db9..8690125e3b18 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -166,7 +166,7 @@ static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb, rcu_read_lock(); ai = nf_get_afinfo(family); if (ai != NULL) - ai->route((struct dst_entry **)&rt, &fl); + ai->route(&init_net, (struct dst_entry **)&rt, &fl); rcu_read_unlock(); if (rt != NULL) { -- cgit v1.2.3 From 0fae2e7740aca7e384c5f337f458897e7e337d58 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 4 Apr 2011 17:00:54 +0200 Subject: netfilter: af_info: add 'strict' parameter to limit lookup to .oif ipv6 fib lookup can set RT6_LOOKUP_F_IFACE flag to restrict search to an interface, but this flag cannot be set via struct flowi. Also, it cannot be set via ip6_route_output: this function uses the passed sock struct to determine if this flag is required (by testing for nonzero sk_bound_dev_if). Work around this by passing in an artificial struct sk in case 'strict' argument is true. This is required to replace the rt6_lookup call in xt_addrtype.c with nf_afinfo->route(). Signed-off-by: Florian Westphal Acked-by: David S. Miller Signed-off-by: Patrick McHardy --- include/linux/netfilter.h | 2 +- net/ipv4/netfilter.c | 2 +- net/ipv6/netfilter.c | 12 ++++++++++-- net/netfilter/nf_conntrack_h323_main.c | 8 ++++---- net/netfilter/xt_TCPMSS.c | 2 +- 5 files changed, 17 insertions(+), 9 deletions(-) (limited to 'include/linux/netfilter.h') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 20ed4528e850..7fa95df60146 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -271,7 +271,7 @@ struct nf_afinfo { unsigned int len, u_int8_t protocol); int (*route)(struct net *net, struct dst_entry **dst, - struct flowi *fl); + struct flowi *fl, bool strict); void (*saveroute)(const struct sk_buff *skb, struct nf_queue_entry *entry); int (*reroute)(struct sk_buff *skb, diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index f1035f056503..4614babdc45f 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -222,7 +222,7 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook, } static int nf_ip_route(struct net *net, struct dst_entry **dst, - struct flowi *fl) + struct flowi *fl, bool strict __always_unused) { struct rtable *rt = ip_route_output_key(net, &fl->u.ip4); if (IS_ERR(rt)) diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index e008b9b4a779..28bc1f644b7b 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -91,9 +91,17 @@ static int nf_ip6_reroute(struct sk_buff *skb, } static int nf_ip6_route(struct net *net, struct dst_entry **dst, - struct flowi *fl) + struct flowi *fl, bool strict) { - *dst = ip6_route_output(net, NULL, &fl->u.ip6); + static const struct ipv6_pinfo fake_pinfo; + static const struct inet_sock fake_sk = { + /* makes ip6_route_output set RT6_LOOKUP_F_IFACE: */ + .sk.sk_bound_dev_if = 1, + .pinet6 = (struct ipv6_pinfo *) &fake_pinfo, + }; + const void *sk = strict ? &fake_sk : NULL; + + *dst = ip6_route_output(net, sk, &fl->u.ip6); return (*dst)->error; } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 39a453895b4d..18b2ce5c8ced 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -732,9 +732,9 @@ static int callforward_do_filter(const union nf_inet_addr *src, memset(&fl2, 0, sizeof(fl2)); fl2.daddr = dst->ip; if (!afinfo->route(&init_net, (struct dst_entry **)&rt1, - flowi4_to_flowi(&fl1))) { + flowi4_to_flowi(&fl1), false)) { if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, - flowi4_to_flowi(&fl2))) { + flowi4_to_flowi(&fl2), false)) { if (rt1->rt_gateway == rt2->rt_gateway && rt1->dst.dev == rt2->dst.dev) ret = 1; @@ -756,9 +756,9 @@ static int callforward_do_filter(const union nf_inet_addr *src, memset(&fl2, 0, sizeof(fl2)); ipv6_addr_copy(&fl2.daddr, &dst->in6); if (!afinfo->route(&init_net, (struct dst_entry **)&rt1, - flowi6_to_flowi(&fl1))) { + flowi6_to_flowi(&fl1), false)) { if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, - flowi6_to_flowi(&fl2))) { + flowi6_to_flowi(&fl2), false)) { if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway, sizeof(rt1->rt6i_gateway)) && rt1->dst.dev == rt2->dst.dev) diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 8690125e3b18..9e63b43faeed 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -166,7 +166,7 @@ static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb, rcu_read_lock(); ai = nf_get_afinfo(family); if (ai != NULL) - ai->route(&init_net, (struct dst_entry **)&rt, &fl); + ai->route(&init_net, (struct dst_entry **)&rt, &fl, false); rcu_read_unlock(); if (rt != NULL) { -- cgit v1.2.3