From b8dfe498775de912116f275680ddb57c8799d9ef Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 25 Mar 2009 17:31:52 +0100 Subject: netfilter: factorize ifname_compare() We use same not trivial helper function in four places. We can factorize it. Signed-off-by: Eric Dumazet Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/arp_tables.c | 14 +------------- net/ipv4/netfilter/ip_tables.c | 23 ++--------------------- 2 files changed, 3 insertions(+), 34 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 64a7c6ce0b9..4b35dba7cf7 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -80,19 +80,7 @@ static inline int arp_devaddr_compare(const struct arpt_devaddr_info *ap, static unsigned long ifname_compare(const char *_a, const char *_b, const char *_mask) { #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS - const unsigned long *a = (const unsigned long *)_a; - const unsigned long *b = (const unsigned long *)_b; - const unsigned long *mask = (const unsigned long *)_mask; - unsigned long ret; - - ret = (a[0] ^ b[0]) & mask[0]; - if (IFNAMSIZ > sizeof(unsigned long)) - ret |= (a[1] ^ b[1]) & mask[1]; - if (IFNAMSIZ > 2 * sizeof(unsigned long)) - ret |= (a[2] ^ b[2]) & mask[2]; - if (IFNAMSIZ > 3 * sizeof(unsigned long)) - ret |= (a[3] ^ b[3]) & mask[3]; - BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); + unsigned long ret = ifname_compare_aligned(_a, _b, _mask); #else unsigned long ret = 0; int i; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index e5294aec967..41c59e391a6 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -74,25 +74,6 @@ do { \ Hence the start of any table is given by get_table() below. */ -static unsigned long ifname_compare(const char *_a, const char *_b, - const unsigned char *_mask) -{ - const unsigned long *a = (const unsigned long *)_a; - const unsigned long *b = (const unsigned long *)_b; - const unsigned long *mask = (const unsigned long *)_mask; - unsigned long ret; - - ret = (a[0] ^ b[0]) & mask[0]; - if (IFNAMSIZ > sizeof(unsigned long)) - ret |= (a[1] ^ b[1]) & mask[1]; - if (IFNAMSIZ > 2 * sizeof(unsigned long)) - ret |= (a[2] ^ b[2]) & mask[2]; - if (IFNAMSIZ > 3 * sizeof(unsigned long)) - ret |= (a[3] ^ b[3]) & mask[3]; - BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); - return ret; -} - /* Returns whether matches rule or not. */ /* Performance critical - called for every packet */ static inline bool @@ -121,7 +102,7 @@ ip_packet_match(const struct iphdr *ip, return false; } - ret = ifname_compare(indev, ipinfo->iniface, ipinfo->iniface_mask); + ret = ifname_compare_aligned(indev, ipinfo->iniface, ipinfo->iniface_mask); if (FWINV(ret != 0, IPT_INV_VIA_IN)) { dprintf("VIA in mismatch (%s vs %s).%s\n", @@ -130,7 +111,7 @@ ip_packet_match(const struct iphdr *ip, return false; } - ret = ifname_compare(outdev, ipinfo->outiface, ipinfo->outiface_mask); + ret = ifname_compare_aligned(outdev, ipinfo->outiface, ipinfo->outiface_mask); if (FWINV(ret != 0, IPT_INV_VIA_OUT)) { dprintf("VIA out mismatch (%s vs %s).%s\n", -- cgit v1.2.3 From 1f9352ae2253a97b07b34dcf16ffa3b4ca12c558 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 25 Mar 2009 19:26:35 +0100 Subject: netfilter: {ip,ip6,arp}_tables: fix incorrect loop detection Commit e1b4b9f ([NETFILTER]: {ip,ip6,arp}_tables: fix exponential worst-case search for loops) introduced a regression in the loop detection algorithm, causing sporadic incorrectly detected loops. When a chain has already been visited during the check, it is treated as having a standard target containing a RETURN verdict directly at the beginning in order to not check it again. The real target of the first rule is then incorrectly treated as STANDARD target and checked not to contain invalid verdicts. Fix by making sure the rule does actually contain a standard target. Based on patch by Francis Dupont Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/arp_tables.c | 4 +++- net/ipv4/netfilter/ip_tables.c | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 4b35dba7cf7..4f454ce9a60 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -388,7 +388,9 @@ static int mark_source_chains(struct xt_table_info *newinfo, && unconditional(&e->arp)) || visited) { unsigned int oldpos, size; - if (t->verdict < -NF_MAX_VERDICT - 1) { + if ((strcmp(t->target.u.user.name, + ARPT_STANDARD_TARGET) == 0) && + t->verdict < -NF_MAX_VERDICT - 1) { duprintf("mark_source_chains: bad " "negative verdict (%i)\n", t->verdict); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 41c59e391a6..82ee7c9049f 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -488,7 +488,9 @@ mark_source_chains(struct xt_table_info *newinfo, && unconditional(&e->ip)) || visited) { unsigned int oldpos, size; - if (t->verdict < -NF_MAX_VERDICT - 1) { + if ((strcmp(t->target.u.user.name, + IPT_STANDARD_TARGET) == 0) && + t->verdict < -NF_MAX_VERDICT - 1) { duprintf("mark_source_chains: bad " "negative verdict (%i)\n", t->verdict); -- cgit v1.2.3 From ea781f197d6a835cbb93a0bf88ee1696296ed8aa Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 25 Mar 2009 21:05:46 +0100 Subject: netfilter: nf_conntrack: use SLAB_DESTROY_BY_RCU and get rid of call_rcu() Use "hlist_nulls" infrastructure we added in 2.6.29 for RCUification of UDP & TCP. This permits an easy conversion from call_rcu() based hash lists to a SLAB_DESTROY_BY_RCU one. Avoiding call_rcu() delay at nf_conn freeing time has numerous gains. First, it doesnt fill RCU queues (up to 10000 elements per cpu). This reduces OOM possibility, if queued elements are not taken into account This reduces latency problems when RCU queue size hits hilimit and triggers emergency mode. - It allows fast reuse of just freed elements, permitting better use of CPU cache. - We delete rcu_head from "struct nf_conn", shrinking size of this structure by 8 or 16 bytes. This patch only takes care of "struct nf_conn". call_rcu() is still used for less critical conntrack parts, that may be converted later if necessary. Signed-off-by: Eric Dumazet Signed-off-by: Patrick McHardy --- .../netfilter/nf_conntrack_l3proto_ipv4_compat.c | 63 ++++++++++++---------- net/ipv4/netfilter/nf_nat_core.c | 2 +- 2 files changed, 37 insertions(+), 28 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index 6ba5c557690..8668a3defda 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -25,40 +25,42 @@ struct ct_iter_state { unsigned int bucket; }; -static struct hlist_node *ct_get_first(struct seq_file *seq) +static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ct_iter_state *st = seq->private; - struct hlist_node *n; + struct hlist_nulls_node *n; for (st->bucket = 0; st->bucket < nf_conntrack_htable_size; st->bucket++) { n = rcu_dereference(net->ct.hash[st->bucket].first); - if (n) + if (!is_a_nulls(n)) return n; } return NULL; } -static struct hlist_node *ct_get_next(struct seq_file *seq, - struct hlist_node *head) +static struct hlist_nulls_node *ct_get_next(struct seq_file *seq, + struct hlist_nulls_node *head) { struct net *net = seq_file_net(seq); struct ct_iter_state *st = seq->private; head = rcu_dereference(head->next); - while (head == NULL) { - if (++st->bucket >= nf_conntrack_htable_size) - return NULL; + while (is_a_nulls(head)) { + if (likely(get_nulls_value(head) == st->bucket)) { + if (++st->bucket >= nf_conntrack_htable_size) + return NULL; + } head = rcu_dereference(net->ct.hash[st->bucket].first); } return head; } -static struct hlist_node *ct_get_idx(struct seq_file *seq, loff_t pos) +static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos) { - struct hlist_node *head = ct_get_first(seq); + struct hlist_nulls_node *head = ct_get_first(seq); if (head) while (pos && (head = ct_get_next(seq, head))) @@ -87,69 +89,76 @@ static void ct_seq_stop(struct seq_file *s, void *v) static int ct_seq_show(struct seq_file *s, void *v) { - const struct nf_conntrack_tuple_hash *hash = v; - const struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash); + struct nf_conntrack_tuple_hash *hash = v; + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash); const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; + int ret = 0; NF_CT_ASSERT(ct); + if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use))) + return 0; + /* we only want to print DIR_ORIGINAL */ if (NF_CT_DIRECTION(hash)) - return 0; + goto release; if (nf_ct_l3num(ct) != AF_INET) - return 0; + goto release; l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct)); NF_CT_ASSERT(l3proto); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); NF_CT_ASSERT(l4proto); + ret = -ENOSPC; if (seq_printf(s, "%-8s %u %ld ", l4proto->name, nf_ct_protonum(ct), timer_pending(&ct->timeout) ? (long)(ct->timeout.expires - jiffies)/HZ : 0) != 0) - return -ENOSPC; + goto release; if (l4proto->print_conntrack && l4proto->print_conntrack(s, ct)) - return -ENOSPC; + goto release; if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, l3proto, l4proto)) - return -ENOSPC; + goto release; if (seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL)) - return -ENOSPC; + goto release; if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status))) if (seq_printf(s, "[UNREPLIED] ")) - return -ENOSPC; + goto release; if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, l3proto, l4proto)) - return -ENOSPC; + goto release; if (seq_print_acct(s, ct, IP_CT_DIR_REPLY)) - return -ENOSPC; + goto release; if (test_bit(IPS_ASSURED_BIT, &ct->status)) if (seq_printf(s, "[ASSURED] ")) - return -ENOSPC; + goto release; #ifdef CONFIG_NF_CONNTRACK_MARK if (seq_printf(s, "mark=%u ", ct->mark)) - return -ENOSPC; + goto release; #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK if (seq_printf(s, "secmark=%u ", ct->secmark)) - return -ENOSPC; + goto release; #endif if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use))) - return -ENOSPC; - - return 0; + goto release; + ret = 0; +release: + nf_ct_put(ct); + return ret; } static const struct seq_operations ct_seq_ops = { diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index a65cf692359..fe65187810f 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -679,7 +679,7 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct, static int __net_init nf_nat_net_init(struct net *net) { net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, - &net->ipv4.nat_vmalloced); + &net->ipv4.nat_vmalloced, 0); if (!net->ipv4.nat_bysource) return -ENOMEM; return 0; -- cgit v1.2.3 From a400c30edb1958ceb53c4b8ce78989189b36df47 Mon Sep 17 00:00:00 2001 From: Holger Eitzenberger Date: Wed, 25 Mar 2009 21:53:39 +0100 Subject: netfilter: nf_conntrack: calculate per-protocol nlattr size Signed-off-by: Holger Eitzenberger Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 6 ++++++ net/ipv4/netfilter/nf_conntrack_proto_icmp.c | 6 ++++++ 2 files changed, 12 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 8b681f24e27..7d2ead7228a 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -328,6 +328,11 @@ static int ipv4_nlattr_to_tuple(struct nlattr *tb[], return 0; } + +static int ipv4_nlattr_tuple_size(void) +{ + return nla_policy_len(ipv4_nla_policy, CTA_IP_MAX + 1); +} #endif static struct nf_sockopt_ops so_getorigdst = { @@ -347,6 +352,7 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = { .get_l4proto = ipv4_get_l4proto, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nlattr = ipv4_tuple_to_nlattr, + .nlattr_tuple_size = ipv4_nlattr_tuple_size, .nlattr_to_tuple = ipv4_nlattr_to_tuple, .nla_policy = ipv4_nla_policy, #endif diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 2a8bee26f43..23b2c2ee869 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -262,6 +262,11 @@ static int icmp_nlattr_to_tuple(struct nlattr *tb[], return 0; } + +static int icmp_nlattr_tuple_size(void) +{ + return nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1); +} #endif #ifdef CONFIG_SYSCTL @@ -309,6 +314,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly = .me = NULL, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nlattr = icmp_tuple_to_nlattr, + .nlattr_tuple_size = icmp_nlattr_tuple_size, .nlattr_to_tuple = icmp_nlattr_to_tuple, .nla_policy = icmp_nla_policy, #endif -- cgit v1.2.3