From e53376bef2cd97d3e3f61fdc677fb8da7d03d0da Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 3 Feb 2014 20:01:53 +0100 Subject: netfilter: nf_conntrack: don't release a conntrack with non-zero refcnt With this patch, the conntrack refcount is initially set to zero and it is bumped once it is added to any of the list, so we fulfill Eric's golden rule which is that all released objects always have a refcount that equals zero. Andrey Vagin reports that nf_conntrack_free can't be called for a conntrack with non-zero ref-counter, because it can race with nf_conntrack_find_get(). A conntrack slab is created with SLAB_DESTROY_BY_RCU. Non-zero ref-counter says that this conntrack is used. So when we release a conntrack with non-zero counter, we break this assumption. CPU1 CPU2 ____nf_conntrack_find() nf_ct_put() destroy_conntrack() ... init_conntrack __nf_conntrack_alloc (set use = 1) atomic_inc_not_zero(&ct->use) (use = 2) if (!l4proto->new(ct, skb, dataoff, timeouts)) nf_conntrack_free(ct); (use = 2 !!!) ... __nf_conntrack_alloc (set use = 1) if (!nf_ct_key_equal(h, tuple, zone)) nf_ct_put(ct); (use = 0) destroy_conntrack() /* continue to work with CT */ After applying the path "[PATCH] netfilter: nf_conntrack: fix RCU race in nf_conntrack_find_get" another bug was triggered in destroy_conntrack(): <4>[67096.759334] ------------[ cut here ]------------ <2>[67096.759353] kernel BUG at net/netfilter/nf_conntrack_core.c:211! ... <4>[67096.759837] Pid: 498649, comm: atdd veid: 666 Tainted: G C --------------- 2.6.32-042stab084.18 #1 042stab084_18 /DQ45CB <4>[67096.759932] RIP: 0010:[] [] destroy_conntrack+0x15c/0x190 [nf_conntrack] <4>[67096.760255] Call Trace: <4>[67096.760255] [] nf_conntrack_destroy+0x17/0x30 <4>[67096.760255] [] nf_conntrack_find_get+0x85/0x130 [nf_conntrack] <4>[67096.760255] [] nf_conntrack_in+0x352/0xb60 [nf_conntrack] <4>[67096.760255] [] ipv4_conntrack_local+0x51/0x60 [nf_conntrack_ipv4] <4>[67096.760255] [] nf_iterate+0x69/0xb0 <4>[67096.760255] [] ? dst_output+0x0/0x20 <4>[67096.760255] [] nf_hook_slow+0x74/0x110 <4>[67096.760255] [] ? dst_output+0x0/0x20 <4>[67096.760255] [] raw_sendmsg+0x775/0x910 <4>[67096.760255] [] ? flush_tlb_others_ipi+0x128/0x130 <4>[67096.760255] [] ? apic_timer_interrupt+0xe/0x20 <4>[67096.760255] [] ? apic_timer_interrupt+0xe/0x20 <4>[67096.760255] [] inet_sendmsg+0x4a/0xb0 <4>[67096.760255] [] ? sock_sendmsg+0x13/0x140 <4>[67096.760255] [] sock_sendmsg+0x117/0x140 <4>[67096.760255] [] ? native_smp_send_reschedule+0x49/0x60 <4>[67096.760255] [] ? _spin_unlock_bh+0x1b/0x20 <4>[67096.760255] [] ? autoremove_wake_function+0x0/0x40 <4>[67096.760255] [] ? do_ip_setsockopt+0x90/0xd80 <4>[67096.760255] [] ? apic_timer_interrupt+0xe/0x20 <4>[67096.760255] [] ? apic_timer_interrupt+0xe/0x20 <4>[67096.760255] [] sys_sendto+0x139/0x190 <4>[67096.760255] [] ? audit_syscall_entry+0x1d7/0x200 <4>[67096.760255] [] ? __audit_syscall_exit+0x265/0x290 <4>[67096.760255] [] compat_sys_socketcall+0x13f/0x210 <4>[67096.760255] [] ia32_sysret+0x0/0x5 I have reused the original title for the RFC patch that Andrey posted and most of the original patch description. Cc: Eric Dumazet Cc: Andrew Vagin Cc: Florian Westphal Reported-by: Andrew Vagin Signed-off-by: Pablo Neira Ayuso Reviewed-by: Eric Dumazet Acked-by: Andrew Vagin --- include/net/netfilter/nf_conntrack.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 01ea6eed1bb1..b2ac6246b7e0 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -284,6 +284,8 @@ extern unsigned int nf_conntrack_max; extern unsigned int nf_conntrack_hash_rnd; void init_nf_conntrack_hash_rnd(void); +void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl); + #define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count) -- cgit v1.2.3 From 64d46806b6218c97f68742c5663a8ae3a5fbe838 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 5 Feb 2014 15:03:37 +0000 Subject: netfilter: nf_tables: add AF specific expression support For the reject module, we need to add AF-specific implementations to get rid of incorrect module dependencies. Try to load an AF-specific module first and fall back to generic modules. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 57c8ff7955df..0f68e47d3e5e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -252,6 +252,7 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, * @owner: module reference * @policy: netlink attribute policy * @maxattr: highest netlink attribute number + * @family: address family for AF-specific types */ struct nft_expr_type { const struct nft_expr_ops *(*select_ops)(const struct nft_ctx *, @@ -262,6 +263,7 @@ struct nft_expr_type { struct module *owner; const struct nla_policy *policy; unsigned int maxattr; + u8 family; }; /** @@ -529,6 +531,9 @@ void nft_unregister_expr(struct nft_expr_type *); #define MODULE_ALIAS_NFT_CHAIN(family, name) \ MODULE_ALIAS("nft-chain-" __stringify(family) "-" name) +#define MODULE_ALIAS_NFT_AF_EXPR(family, name) \ + MODULE_ALIAS("nft-expr-" __stringify(family) "-" name) + #define MODULE_ALIAS_NFT_EXPR(name) \ MODULE_ALIAS("nft-expr-" name) -- cgit v1.2.3 From cc4723ca316742891954efa346298e7c747c0d17 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 5 Feb 2014 15:03:38 +0000 Subject: netfilter: nft_reject: split up reject module into IPv4 and IPv6 specifc parts Currently the nft_reject module depends on symbols from ipv6. This is wrong since no generic module should force IPv6 support to be loaded. Split up the module into AF-specific and a generic part. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nft_reject.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/net/netfilter/nft_reject.h (limited to 'include/net') diff --git a/include/net/netfilter/nft_reject.h b/include/net/netfilter/nft_reject.h new file mode 100644 index 000000000000..ecda75945e77 --- /dev/null +++ b/include/net/netfilter/nft_reject.h @@ -0,0 +1,17 @@ +#ifndef _NFT_REJECT_H_ +#define _NFT_REJECT_H_ + +struct nft_reject { + enum nft_reject_types type:8; + u8 icmp_code; +}; + +extern const struct nla_policy nft_reject_policy[]; + +int nft_reject_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]); + +int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr); + +#endif -- cgit v1.2.3 From 05513e9e33dbded8124567466a444d32173eecc6 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 5 Feb 2014 15:03:39 +0000 Subject: netfilter: nf_tables: add reject module for NFPROTO_INET Add a reject module for NFPROTO_INET. It does nothing but dispatch to the AF-specific modules based on the hook family. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nft_reject.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/net') diff --git a/include/net/netfilter/nft_reject.h b/include/net/netfilter/nft_reject.h index ecda75945e77..36b0da2d55bb 100644 --- a/include/net/netfilter/nft_reject.h +++ b/include/net/netfilter/nft_reject.h @@ -14,4 +14,12 @@ int nft_reject_init(const struct nft_ctx *ctx, int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr); +void nft_reject_ipv4_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt); + +void nft_reject_ipv6_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt); + #endif -- cgit v1.2.3 From 0165d9325d6a3cf856e2cbbe64a0f4635ac75893 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 25 Jan 2014 14:03:51 +0100 Subject: netfilter: nf_tables: fix racy rule deletion We may lost race if we flush the rule-set (which happens asynchronously via call_rcu) and we try to remove the table (that userspace assumes to be empty). Fix this by recovering synchronous rule and chain deletion. This was introduced time ago before we had no batch support, and synchronous rule deletion performance was not good. Now that we have the batch support, we can just postpone the purge of old rule in a second step in the commit phase. All object deletions are synchronous after this patch. As a side effect, we save memory as we don't need rcu_head per rule anymore. Cc: Patrick McHardy Reported-by: Arturo Borrero Gonzalez Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 0f68e47d3e5e..e7e14ffe0f6a 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -322,7 +322,6 @@ static inline void *nft_expr_priv(const struct nft_expr *expr) * struct nft_rule - nf_tables rule * * @list: used internally - * @rcu_head: used internally for rcu * @handle: rule handle * @genmask: generation mask * @dlen: length of expression data @@ -330,7 +329,6 @@ static inline void *nft_expr_priv(const struct nft_expr *expr) */ struct nft_rule { struct list_head list; - struct rcu_head rcu_head; u64 handle:46, genmask:2, dlen:16; @@ -391,7 +389,6 @@ enum nft_chain_flags { * * @rules: list of rules in the chain * @list: used internally - * @rcu_head: used internally * @net: net namespace that this chain belongs to * @table: table that this chain belongs to * @handle: chain handle @@ -403,7 +400,6 @@ enum nft_chain_flags { struct nft_chain { struct list_head rules; struct list_head list; - struct rcu_head rcu_head; struct net *net; struct nft_table *table; u64 handle; -- cgit v1.2.3