From 71951b64a5a87c09eb6fde59ce51aaab2fdaeab2 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 24 Apr 2009 16:58:41 +0200 Subject: netfilter: nf_ct_dccp: add missing role attributes for DCCP This patch adds missing role attribute to the DCCP type, otherwise the creation of entries is not of any use. The attribute added is CTA_PROTOINFO_DCCP_ROLE which contains the role of the conntrack original tuple. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy --- include/linux/netfilter/nfnetlink_conntrack.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/netfilter') diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index 29fe9ea1d346..1a865e48b8eb 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -100,6 +100,7 @@ enum ctattr_protoinfo_tcp { enum ctattr_protoinfo_dccp { CTA_PROTOINFO_DCCP_UNSPEC, CTA_PROTOINFO_DCCP_STATE, + CTA_PROTOINFO_DCCP_ROLE, __CTA_PROTOINFO_DCCP_MAX, }; #define CTA_PROTOINFO_DCCP_MAX (__CTA_PROTOINFO_DCCP_MAX - 1) -- cgit v1.2.3 From 942e4a2bd680c606af0211e64eb216be2e19bf61 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 28 Apr 2009 22:36:33 -0700 Subject: netfilter: revised locking for x_tables The x_tables are organized with a table structure and a per-cpu copies of the counters and rules. On older kernels there was a reader/writer lock per table which was a performance bottleneck. In 2.6.30-rc, this was converted to use RCU and the counters/rules which solved the performance problems for do_table but made replacing rules much slower because of the necessary RCU grace period. This version uses a per-cpu set of spinlocks and counters to allow to table processing to proceed without the cache thrashing of a global reader lock and keeps the same performance for table updates. Signed-off-by: Stephen Hemminger Acked-by: Linus Torvalds Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 73 +++++++++++++++++++-- net/ipv4/netfilter/arp_tables.c | 125 +++++++++++------------------------- net/ipv4/netfilter/ip_tables.c | 126 +++++++++++-------------------------- net/ipv6/netfilter/ip6_tables.c | 123 +++++++++++------------------------- net/netfilter/x_tables.c | 53 ++++++++-------- 5 files changed, 204 insertions(+), 296 deletions(-) (limited to 'include/linux/netfilter') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 7b1a652066c0..1b2e43502ef7 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -354,9 +354,6 @@ struct xt_table /* What hooks you will enter on */ unsigned int valid_hooks; - /* Lock for the curtain */ - struct mutex lock; - /* Man behind the curtain... */ struct xt_table_info *private; @@ -434,8 +431,74 @@ extern void xt_proto_fini(struct net *net, u_int8_t af); extern struct xt_table_info *xt_alloc_table_info(unsigned int size); extern void xt_free_table_info(struct xt_table_info *info); -extern void xt_table_entry_swap_rcu(struct xt_table_info *old, - struct xt_table_info *new); + +/* + * Per-CPU spinlock associated with per-cpu table entries, and + * with a counter for the "reading" side that allows a recursive + * reader to avoid taking the lock and deadlocking. + * + * "reading" is used by ip/arp/ip6 tables rule processing which runs per-cpu. + * It needs to ensure that the rules are not being changed while the packet + * is being processed. In some cases, the read lock will be acquired + * twice on the same CPU; this is okay because of the count. + * + * "writing" is used when reading counters. + * During replace any readers that are using the old tables have to complete + * before freeing the old table. This is handled by the write locking + * necessary for reading the counters. + */ +struct xt_info_lock { + spinlock_t lock; + unsigned char readers; +}; +DECLARE_PER_CPU(struct xt_info_lock, xt_info_locks); + +/* + * Note: we need to ensure that preemption is disabled before acquiring + * the per-cpu-variable, so we do it as a two step process rather than + * using "spin_lock_bh()". + * + * We _also_ need to disable bottom half processing before updating our + * nesting count, to make sure that the only kind of re-entrancy is this + * code being called by itself: since the count+lock is not an atomic + * operation, we can allow no races. + * + * _Only_ that special combination of being per-cpu and never getting + * re-entered asynchronously means that the count is safe. + */ +static inline void xt_info_rdlock_bh(void) +{ + struct xt_info_lock *lock; + + local_bh_disable(); + lock = &__get_cpu_var(xt_info_locks); + if (!lock->readers++) + spin_lock(&lock->lock); +} + +static inline void xt_info_rdunlock_bh(void) +{ + struct xt_info_lock *lock = &__get_cpu_var(xt_info_locks); + + if (!--lock->readers) + spin_unlock(&lock->lock); + local_bh_enable(); +} + +/* + * The "writer" side needs to get exclusive access to the lock, + * regardless of readers. This must be called with bottom half + * processing (and thus also preemption) disabled. + */ +static inline void xt_info_wrlock(unsigned int cpu) +{ + spin_lock(&per_cpu(xt_info_locks, cpu).lock); +} + +static inline void xt_info_wrunlock(unsigned int cpu) +{ + spin_unlock(&per_cpu(xt_info_locks, cpu).lock); +} /* * This helper is performance critical and must be inlined diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 5ba533d234db..831fe1879dc0 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -253,9 +253,9 @@ unsigned int arpt_do_table(struct sk_buff *skb, indev = in ? in->name : nulldevname; outdev = out ? out->name : nulldevname; - rcu_read_lock_bh(); - private = rcu_dereference(table->private); - table_base = rcu_dereference(private->entries[smp_processor_id()]); + xt_info_rdlock_bh(); + private = table->private; + table_base = private->entries[smp_processor_id()]; e = get_entry(table_base, private->hook_entry[hook]); back = get_entry(table_base, private->underflow[hook]); @@ -273,6 +273,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, hdr_len = sizeof(*arp) + (2 * sizeof(struct in_addr)) + (2 * skb->dev->addr_len); + ADD_COUNTER(e->counters, hdr_len, 1); t = arpt_get_target(e); @@ -328,8 +329,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, e = (void *)e + e->next_offset; } } while (!hotdrop); - - rcu_read_unlock_bh(); + xt_info_rdunlock_bh(); if (hotdrop) return NF_DROP; @@ -711,9 +711,12 @@ static void get_counters(const struct xt_table_info *t, /* Instead of clearing (by a previous call to memset()) * the counters and using adds, we set the counters * with data used by 'current' CPU - * We dont care about preemption here. + * + * Bottom half has to be disabled to prevent deadlock + * if new softirq were to run and call ipt_do_table */ - curcpu = raw_smp_processor_id(); + local_bh_disable(); + curcpu = smp_processor_id(); i = 0; ARPT_ENTRY_ITERATE(t->entries[curcpu], @@ -726,73 +729,22 @@ static void get_counters(const struct xt_table_info *t, if (cpu == curcpu) continue; i = 0; + xt_info_wrlock(cpu); ARPT_ENTRY_ITERATE(t->entries[cpu], t->size, add_entry_to_counter, counters, &i); + xt_info_wrunlock(cpu); } -} - - -/* We're lazy, and add to the first CPU; overflow works its fey magic - * and everything is OK. */ -static int -add_counter_to_entry(struct arpt_entry *e, - const struct xt_counters addme[], - unsigned int *i) -{ - ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); - - (*i)++; - return 0; -} - -/* Take values from counters and add them back onto the current cpu */ -static void put_counters(struct xt_table_info *t, - const struct xt_counters counters[]) -{ - unsigned int i, cpu; - - local_bh_disable(); - cpu = smp_processor_id(); - i = 0; - ARPT_ENTRY_ITERATE(t->entries[cpu], - t->size, - add_counter_to_entry, - counters, - &i); local_bh_enable(); } -static inline int -zero_entry_counter(struct arpt_entry *e, void *arg) -{ - e->counters.bcnt = 0; - e->counters.pcnt = 0; - return 0; -} - -static void -clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info) -{ - unsigned int cpu; - const void *loc_cpu_entry = info->entries[raw_smp_processor_id()]; - - memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); - for_each_possible_cpu(cpu) { - memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size); - ARPT_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size, - zero_entry_counter, NULL); - } -} - static struct xt_counters *alloc_counters(struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; struct xt_table_info *private = table->private; - struct xt_table_info *info; /* We need atomic snapshot of counters: rest doesn't change * (other than comefrom, which userspace doesn't care @@ -802,30 +754,11 @@ static struct xt_counters *alloc_counters(struct xt_table *table) counters = vmalloc_node(countersize, numa_node_id()); if (counters == NULL) - goto nomem; - - info = xt_alloc_table_info(private->size); - if (!info) - goto free_counters; - - clone_counters(info, private); - - mutex_lock(&table->lock); - xt_table_entry_swap_rcu(private, info); - synchronize_net(); /* Wait until smoke has cleared */ + return ERR_PTR(-ENOMEM); - get_counters(info, counters); - put_counters(private, counters); - mutex_unlock(&table->lock); - - xt_free_table_info(info); + get_counters(private, counters); return counters; - - free_counters: - vfree(counters); - nomem: - return ERR_PTR(-ENOMEM); } static int copy_entries_to_user(unsigned int total_size, @@ -1094,8 +1027,9 @@ static int __do_replace(struct net *net, const char *name, (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); - /* Get the old counters. */ + /* Get the old counters, and synchronize with replace */ get_counters(oldinfo, counters); + /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; ARPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry, @@ -1165,10 +1099,23 @@ static int do_replace(struct net *net, void __user *user, unsigned int len) return ret; } +/* We're lazy, and add to the first CPU; overflow works its fey magic + * and everything is OK. */ +static int +add_counter_to_entry(struct arpt_entry *e, + const struct xt_counters addme[], + unsigned int *i) +{ + ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); + + (*i)++; + return 0; +} + static int do_add_counters(struct net *net, void __user *user, unsigned int len, int compat) { - unsigned int i; + unsigned int i, curcpu; struct xt_counters_info tmp; struct xt_counters *paddc; unsigned int num_counters; @@ -1224,26 +1171,26 @@ static int do_add_counters(struct net *net, void __user *user, unsigned int len, goto free; } - mutex_lock(&t->lock); + local_bh_disable(); private = t->private; if (private->number != num_counters) { ret = -EINVAL; goto unlock_up_free; } - preempt_disable(); i = 0; /* Choose the copy that is on our node */ - loc_cpu_entry = private->entries[smp_processor_id()]; + curcpu = smp_processor_id(); + loc_cpu_entry = private->entries[curcpu]; + xt_info_wrlock(curcpu); ARPT_ENTRY_ITERATE(loc_cpu_entry, private->size, add_counter_to_entry, paddc, &i); - preempt_enable(); + xt_info_wrunlock(curcpu); unlock_up_free: - mutex_unlock(&t->lock); - + local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 810c0b62c7d4..2ec8d7290c40 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -338,10 +338,9 @@ ipt_do_table(struct sk_buff *skb, tgpar.hooknum = hook; IP_NF_ASSERT(table->valid_hooks & (1 << hook)); - - rcu_read_lock_bh(); - private = rcu_dereference(table->private); - table_base = rcu_dereference(private->entries[smp_processor_id()]); + xt_info_rdlock_bh(); + private = table->private; + table_base = private->entries[smp_processor_id()]; e = get_entry(table_base, private->hook_entry[hook]); @@ -436,8 +435,7 @@ ipt_do_table(struct sk_buff *skb, e = (void *)e + e->next_offset; } } while (!hotdrop); - - rcu_read_unlock_bh(); + xt_info_rdunlock_bh(); #ifdef DEBUG_ALLOW_ALL return NF_ACCEPT; @@ -896,10 +894,13 @@ get_counters(const struct xt_table_info *t, /* Instead of clearing (by a previous call to memset()) * the counters and using adds, we set the counters - * with data used by 'current' CPU - * We dont care about preemption here. + * with data used by 'current' CPU. + * + * Bottom half has to be disabled to prevent deadlock + * if new softirq were to run and call ipt_do_table */ - curcpu = raw_smp_processor_id(); + local_bh_disable(); + curcpu = smp_processor_id(); i = 0; IPT_ENTRY_ITERATE(t->entries[curcpu], @@ -912,74 +913,22 @@ get_counters(const struct xt_table_info *t, if (cpu == curcpu) continue; i = 0; + xt_info_wrlock(cpu); IPT_ENTRY_ITERATE(t->entries[cpu], t->size, add_entry_to_counter, counters, &i); + xt_info_wrunlock(cpu); } - -} - -/* We're lazy, and add to the first CPU; overflow works its fey magic - * and everything is OK. */ -static int -add_counter_to_entry(struct ipt_entry *e, - const struct xt_counters addme[], - unsigned int *i) -{ - ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); - - (*i)++; - return 0; -} - -/* Take values from counters and add them back onto the current cpu */ -static void put_counters(struct xt_table_info *t, - const struct xt_counters counters[]) -{ - unsigned int i, cpu; - - local_bh_disable(); - cpu = smp_processor_id(); - i = 0; - IPT_ENTRY_ITERATE(t->entries[cpu], - t->size, - add_counter_to_entry, - counters, - &i); local_bh_enable(); } - -static inline int -zero_entry_counter(struct ipt_entry *e, void *arg) -{ - e->counters.bcnt = 0; - e->counters.pcnt = 0; - return 0; -} - -static void -clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info) -{ - unsigned int cpu; - const void *loc_cpu_entry = info->entries[raw_smp_processor_id()]; - - memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); - for_each_possible_cpu(cpu) { - memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size); - IPT_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size, - zero_entry_counter, NULL); - } -} - static struct xt_counters * alloc_counters(struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; struct xt_table_info *private = table->private; - struct xt_table_info *info; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -988,30 +937,11 @@ static struct xt_counters * alloc_counters(struct xt_table *table) counters = vmalloc_node(countersize, numa_node_id()); if (counters == NULL) - goto nomem; + return ERR_PTR(-ENOMEM); - info = xt_alloc_table_info(private->size); - if (!info) - goto free_counters; - - clone_counters(info, private); - - mutex_lock(&table->lock); - xt_table_entry_swap_rcu(private, info); - synchronize_net(); /* Wait until smoke has cleared */ - - get_counters(info, counters); - put_counters(private, counters); - mutex_unlock(&table->lock); - - xt_free_table_info(info); + get_counters(private, counters); return counters; - - free_counters: - vfree(counters); - nomem: - return ERR_PTR(-ENOMEM); } static int @@ -1306,8 +1236,9 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); - /* Get the old counters. */ + /* Get the old counters, and synchronize with replace */ get_counters(oldinfo, counters); + /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; IPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry, @@ -1377,11 +1308,23 @@ do_replace(struct net *net, void __user *user, unsigned int len) return ret; } +/* We're lazy, and add to the first CPU; overflow works its fey magic + * and everything is OK. */ +static int +add_counter_to_entry(struct ipt_entry *e, + const struct xt_counters addme[], + unsigned int *i) +{ + ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); + + (*i)++; + return 0; +} static int do_add_counters(struct net *net, void __user *user, unsigned int len, int compat) { - unsigned int i; + unsigned int i, curcpu; struct xt_counters_info tmp; struct xt_counters *paddc; unsigned int num_counters; @@ -1437,25 +1380,26 @@ do_add_counters(struct net *net, void __user *user, unsigned int len, int compat goto free; } - mutex_lock(&t->lock); + local_bh_disable(); private = t->private; if (private->number != num_counters) { ret = -EINVAL; goto unlock_up_free; } - preempt_disable(); i = 0; /* Choose the copy that is on our node */ - loc_cpu_entry = private->entries[raw_smp_processor_id()]; + curcpu = smp_processor_id(); + loc_cpu_entry = private->entries[curcpu]; + xt_info_wrlock(curcpu); IPT_ENTRY_ITERATE(loc_cpu_entry, private->size, add_counter_to_entry, paddc, &i); - preempt_enable(); + xt_info_wrunlock(curcpu); unlock_up_free: - mutex_unlock(&t->lock); + local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 800ae8542471..219e165aea10 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -365,9 +365,9 @@ ip6t_do_table(struct sk_buff *skb, IP_NF_ASSERT(table->valid_hooks & (1 << hook)); - rcu_read_lock_bh(); - private = rcu_dereference(table->private); - table_base = rcu_dereference(private->entries[smp_processor_id()]); + xt_info_rdlock_bh(); + private = table->private; + table_base = private->entries[smp_processor_id()]; e = get_entry(table_base, private->hook_entry[hook]); @@ -466,7 +466,7 @@ ip6t_do_table(struct sk_buff *skb, #ifdef CONFIG_NETFILTER_DEBUG ((struct ip6t_entry *)table_base)->comefrom = NETFILTER_LINK_POISON; #endif - rcu_read_unlock_bh(); + xt_info_rdunlock_bh(); #ifdef DEBUG_ALLOW_ALL return NF_ACCEPT; @@ -926,9 +926,12 @@ get_counters(const struct xt_table_info *t, /* Instead of clearing (by a previous call to memset()) * the counters and using adds, we set the counters * with data used by 'current' CPU - * We dont care about preemption here. + * + * Bottom half has to be disabled to prevent deadlock + * if new softirq were to run and call ipt_do_table */ - curcpu = raw_smp_processor_id(); + local_bh_disable(); + curcpu = smp_processor_id(); i = 0; IP6T_ENTRY_ITERATE(t->entries[curcpu], @@ -941,72 +944,22 @@ get_counters(const struct xt_table_info *t, if (cpu == curcpu) continue; i = 0; + xt_info_wrlock(cpu); IP6T_ENTRY_ITERATE(t->entries[cpu], t->size, add_entry_to_counter, counters, &i); + xt_info_wrunlock(cpu); } -} - -/* We're lazy, and add to the first CPU; overflow works its fey magic - * and everything is OK. */ -static int -add_counter_to_entry(struct ip6t_entry *e, - const struct xt_counters addme[], - unsigned int *i) -{ - ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); - - (*i)++; - return 0; -} - -/* Take values from counters and add them back onto the current cpu */ -static void put_counters(struct xt_table_info *t, - const struct xt_counters counters[]) -{ - unsigned int i, cpu; - - local_bh_disable(); - cpu = smp_processor_id(); - i = 0; - IP6T_ENTRY_ITERATE(t->entries[cpu], - t->size, - add_counter_to_entry, - counters, - &i); local_bh_enable(); } -static inline int -zero_entry_counter(struct ip6t_entry *e, void *arg) -{ - e->counters.bcnt = 0; - e->counters.pcnt = 0; - return 0; -} - -static void -clone_counters(struct xt_table_info *newinfo, const struct xt_table_info *info) -{ - unsigned int cpu; - const void *loc_cpu_entry = info->entries[raw_smp_processor_id()]; - - memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); - for_each_possible_cpu(cpu) { - memcpy(newinfo->entries[cpu], loc_cpu_entry, info->size); - IP6T_ENTRY_ITERATE(newinfo->entries[cpu], newinfo->size, - zero_entry_counter, NULL); - } -} - static struct xt_counters *alloc_counters(struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; struct xt_table_info *private = table->private; - struct xt_table_info *info; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -1015,30 +968,11 @@ static struct xt_counters *alloc_counters(struct xt_table *table) counters = vmalloc_node(countersize, numa_node_id()); if (counters == NULL) - goto nomem; + return ERR_PTR(-ENOMEM); - info = xt_alloc_table_info(private->size); - if (!info) - goto free_counters; - - clone_counters(info, private); - - mutex_lock(&table->lock); - xt_table_entry_swap_rcu(private, info); - synchronize_net(); /* Wait until smoke has cleared */ - - get_counters(info, counters); - put_counters(private, counters); - mutex_unlock(&table->lock); - - xt_free_table_info(info); + get_counters(private, counters); return counters; - - free_counters: - vfree(counters); - nomem: - return ERR_PTR(-ENOMEM); } static int @@ -1334,8 +1268,9 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); - /* Get the old counters. */ + /* Get the old counters, and synchronize with replace */ get_counters(oldinfo, counters); + /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; IP6T_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry, @@ -1405,11 +1340,24 @@ do_replace(struct net *net, void __user *user, unsigned int len) return ret; } +/* We're lazy, and add to the first CPU; overflow works its fey magic + * and everything is OK. */ +static int +add_counter_to_entry(struct ip6t_entry *e, + const struct xt_counters addme[], + unsigned int *i) +{ + ADD_COUNTER(e->counters, addme[*i].bcnt, addme[*i].pcnt); + + (*i)++; + return 0; +} + static int do_add_counters(struct net *net, void __user *user, unsigned int len, int compat) { - unsigned int i; + unsigned int i, curcpu; struct xt_counters_info tmp; struct xt_counters *paddc; unsigned int num_counters; @@ -1465,25 +1413,28 @@ do_add_counters(struct net *net, void __user *user, unsigned int len, goto free; } - mutex_lock(&t->lock); + + local_bh_disable(); private = t->private; if (private->number != num_counters) { ret = -EINVAL; goto unlock_up_free; } - preempt_disable(); i = 0; /* Choose the copy that is on our node */ - loc_cpu_entry = private->entries[raw_smp_processor_id()]; + curcpu = smp_processor_id(); + xt_info_wrlock(curcpu); + loc_cpu_entry = private->entries[curcpu]; IP6T_ENTRY_ITERATE(loc_cpu_entry, private->size, add_counter_to_entry, paddc, &i); - preempt_enable(); + xt_info_wrunlock(curcpu); + unlock_up_free: - mutex_unlock(&t->lock); + local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 509a95621f9f..150e5cf62f85 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -625,20 +625,6 @@ void xt_free_table_info(struct xt_table_info *info) } EXPORT_SYMBOL(xt_free_table_info); -void xt_table_entry_swap_rcu(struct xt_table_info *oldinfo, - struct xt_table_info *newinfo) -{ - unsigned int cpu; - - for_each_possible_cpu(cpu) { - void *p = oldinfo->entries[cpu]; - rcu_assign_pointer(oldinfo->entries[cpu], newinfo->entries[cpu]); - newinfo->entries[cpu] = p; - } - -} -EXPORT_SYMBOL_GPL(xt_table_entry_swap_rcu); - /* Find table by name, grabs mutex & ref. Returns ERR_PTR() on error. */ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name) @@ -676,32 +662,43 @@ void xt_compat_unlock(u_int8_t af) EXPORT_SYMBOL_GPL(xt_compat_unlock); #endif +DEFINE_PER_CPU(struct xt_info_lock, xt_info_locks); +EXPORT_PER_CPU_SYMBOL_GPL(xt_info_locks); + + struct xt_table_info * xt_replace_table(struct xt_table *table, unsigned int num_counters, struct xt_table_info *newinfo, int *error) { - struct xt_table_info *oldinfo, *private; + struct xt_table_info *private; /* Do the substitution. */ - mutex_lock(&table->lock); + local_bh_disable(); private = table->private; + /* Check inside lock: is the old number correct? */ if (num_counters != private->number) { duprintf("num_counters != table->private->number (%u/%u)\n", num_counters, private->number); - mutex_unlock(&table->lock); + local_bh_enable(); *error = -EAGAIN; return NULL; } - oldinfo = private; - rcu_assign_pointer(table->private, newinfo); - newinfo->initial_entries = oldinfo->initial_entries; - mutex_unlock(&table->lock); - synchronize_net(); - return oldinfo; + table->private = newinfo; + newinfo->initial_entries = private->initial_entries; + + /* + * Even though table entries have now been swapped, other CPU's + * may still be using the old entries. This is okay, because + * resynchronization happens because of the locking done + * during the get_counters() routine. + */ + local_bh_enable(); + + return private; } EXPORT_SYMBOL_GPL(xt_replace_table); @@ -734,7 +731,6 @@ struct xt_table *xt_register_table(struct net *net, struct xt_table *table, /* Simplifies replace_table code. */ table->private = bootstrap; - mutex_init(&table->lock); if (!xt_replace_table(table, 0, newinfo, &ret)) goto unlock; @@ -1147,7 +1143,14 @@ static struct pernet_operations xt_net_ops = { static int __init xt_init(void) { - int i, rv; + unsigned int i; + int rv; + + for_each_possible_cpu(i) { + struct xt_info_lock *lock = &per_cpu(xt_info_locks, i); + spin_lock_init(&lock->lock); + lock->readers = 0; + } xt = kmalloc(sizeof(struct xt_af) * NFPROTO_NUMPROTO, GFP_KERNEL); if (!xt) -- cgit v1.2.3 From 0f3d042ed2f934f149ccb78300454beaf0c1134b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 1 May 2009 09:10:46 -0700 Subject: netfilter: use likely() in xt_info_rdlock_bh() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/netfilter') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 1b2e43502ef7..c9efe039dc57 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -472,7 +472,7 @@ static inline void xt_info_rdlock_bh(void) local_bh_disable(); lock = &__get_cpu_var(xt_info_locks); - if (!lock->readers++) + if (likely(!lock->readers++)) spin_lock(&lock->lock); } @@ -480,7 +480,7 @@ static inline void xt_info_rdunlock_bh(void) { struct xt_info_lock *lock = &__get_cpu_var(xt_info_locks); - if (!--lock->readers) + if (likely(!--lock->readers)) spin_unlock(&lock->lock); local_bh_enable(); } -- cgit v1.2.3 From a7ca7fccacc029958fd09985e7f3529b90ec791d Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 5 May 2009 14:31:12 +0200 Subject: netfilter: add missing linux/types.h include to xt_LED.h Pointed out by Dave Miller: CHECK include/linux/netfilter (57 files) /home/davem/src/GIT/net-2.6/usr/include/linux/netfilter/xt_LED.h:6: found __[us]{8,16,32,64} type without #include Signed-off-by: Patrick McHardy --- include/linux/netfilter/xt_LED.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/netfilter') diff --git a/include/linux/netfilter/xt_LED.h b/include/linux/netfilter/xt_LED.h index 4c91a0d770d0..f5509e7524d3 100644 --- a/include/linux/netfilter/xt_LED.h +++ b/include/linux/netfilter/xt_LED.h @@ -1,6 +1,8 @@ #ifndef _XT_LED_H #define _XT_LED_H +#include + struct xt_led_info { char id[27]; /* Unique ID for this trigger in the LED class */ __u8 always_blink; /* Blink even if the LED is already on */ -- cgit v1.2.3 From 280f37afa2c270ff029cb420b34396aa002909c3 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 5 May 2009 17:46:07 +0200 Subject: netfilter: xt_cluster: fix use of cluster match with 32 nodes This patch fixes a problem when you use 32 nodes in the cluster match: % iptables -I PREROUTING -t mangle -i eth0 -m cluster \ --cluster-total-nodes 32 --cluster-local-node 32 \ --cluster-hash-seed 0xdeadbeef -j MARK --set-mark 0xffff iptables: Invalid argument. Run `dmesg' for more information. % dmesg | tail -1 xt_cluster: this node mask cannot be higher than the total number of nodes The problem is related to this checking: if (info->node_mask >= (1 << info->total_nodes)) { printk(KERN_ERR "xt_cluster: this node mask cannot be " "higher than the total number of nodes\n"); return false; } (1 << 32) is 1. Thus, the checking fails. BTW, I said this before but I insist: I have only tested the cluster match with 2 nodes getting ~45% extra performance in an active-active setup. The maximum limit of 32 nodes is still completely arbitrary. I'd really appreciate if people that have more nodes in their setups let me know. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy --- include/linux/netfilter/xt_cluster.h | 2 ++ net/netfilter/xt_cluster.c | 8 +++++++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux/netfilter') diff --git a/include/linux/netfilter/xt_cluster.h b/include/linux/netfilter/xt_cluster.h index 5e0a0d07b526..886682656f09 100644 --- a/include/linux/netfilter/xt_cluster.h +++ b/include/linux/netfilter/xt_cluster.h @@ -12,4 +12,6 @@ struct xt_cluster_match_info { u_int32_t flags; }; +#define XT_CLUSTER_NODES_MAX 32 + #endif /* _XT_CLUSTER_MATCH_H */ diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c index 6c4847662b85..69a639f35403 100644 --- a/net/netfilter/xt_cluster.c +++ b/net/netfilter/xt_cluster.c @@ -135,7 +135,13 @@ static bool xt_cluster_mt_checkentry(const struct xt_mtchk_param *par) { struct xt_cluster_match_info *info = par->matchinfo; - if (info->node_mask >= (1 << info->total_nodes)) { + if (info->total_nodes > XT_CLUSTER_NODES_MAX) { + printk(KERN_ERR "xt_cluster: you have exceeded the maximum " + "number of cluster nodes (%u > %u)\n", + info->total_nodes, XT_CLUSTER_NODES_MAX); + return false; + } + if (info->node_mask >= (1ULL << info->total_nodes)) { printk(KERN_ERR "xt_cluster: this node mask cannot be " "higher than the total number of nodes\n"); return false; -- cgit v1.2.3 From bfcaa50270e18f35220a11d46e98fc6232c24606 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 25 May 2009 17:23:15 +0200 Subject: netfilter: nf_ct_tcp: fix accepting invalid RST segments Robert L Mathews discovered that some clients send evil TCP RST segments, which are accepted by netfilter conntrack but discarded by the destination. Thus the conntrack entry is destroyed but the destination retransmits data until timeout. The same technique, i.e. sending properly crafted RST segments, can easily be used to bypass connlimit/connbytes based restrictions (the sample script written by Robert can be found in the netfilter mailing list archives). The patch below adds a new flag and new field to struct ip_ct_tcp_state so that checking RST segments can be made more strict and thus TCP conntrack can catch the invalid ones: the RST segment is accepted only if its sequence number higher than or equal to the highest ack we seen from the other direction. (The last_ack field cannot be reused because it is used to catch resent packets.) Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/nf_conntrack_tcp.h | 4 ++++ net/netfilter/nf_conntrack_proto_tcp.c | 18 ++++++++++++++++++ 2 files changed, 22 insertions(+) (limited to 'include/linux/netfilter') diff --git a/include/linux/netfilter/nf_conntrack_tcp.h b/include/linux/netfilter/nf_conntrack_tcp.h index 3066789b972a..b2f384d42611 100644 --- a/include/linux/netfilter/nf_conntrack_tcp.h +++ b/include/linux/netfilter/nf_conntrack_tcp.h @@ -35,6 +35,9 @@ enum tcp_conntrack { /* Has unacknowledged data */ #define IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED 0x10 +/* The field td_maxack has been set */ +#define IP_CT_TCP_FLAG_MAXACK_SET 0x20 + struct nf_ct_tcp_flags { __u8 flags; __u8 mask; @@ -46,6 +49,7 @@ struct ip_ct_tcp_state { u_int32_t td_end; /* max of seq + len */ u_int32_t td_maxend; /* max of ack + max(win, 1) */ u_int32_t td_maxwin; /* max(win) */ + u_int32_t td_maxack; /* max of ack */ u_int8_t td_scale; /* window scale factor */ u_int8_t flags; /* per direction options */ }; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index b5ccf2b4b2e7..97a6e93d742e 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -634,6 +634,14 @@ static bool tcp_in_window(const struct nf_conn *ct, sender->td_end = end; sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED; } + if (tcph->ack) { + if (!(sender->flags & IP_CT_TCP_FLAG_MAXACK_SET)) { + sender->td_maxack = ack; + sender->flags |= IP_CT_TCP_FLAG_MAXACK_SET; + } else if (after(ack, sender->td_maxack)) + sender->td_maxack = ack; + } + /* * Update receiver data. */ @@ -918,6 +926,16 @@ static int tcp_packet(struct nf_conn *ct, "nf_ct_tcp: invalid state "); return -NF_ACCEPT; case TCP_CONNTRACK_CLOSE: + if (index == TCP_RST_SET + && (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) + && before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) { + /* Invalid RST */ + write_unlock_bh(&tcp_lock); + if (LOG_INVALID(net, IPPROTO_TCP)) + nf_log_packet(pf, 0, skb, NULL, NULL, NULL, + "nf_ct_tcp: invalid RST "); + return -NF_ACCEPT; + } if (index == TCP_RST_SET && ((test_bit(IPS_SEEN_REPLY_BIT, &ct->status) && ct->proto.tcp.last_index == TCP_SYN_SET) -- cgit v1.2.3