* [PATCH 35/36] netfilter: conntrack: use a single nat bysource table for all namespaces
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
From: Florian Westphal <fw@strlen.de>
We already include netns address in the hash, so we only need to use
net_eq in find_appropriate_src and can then put all entries into
same table.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netns/conntrack.h | 4 ----
net/netfilter/nf_nat_core.c | 33 +++++++++++++++++----------------
2 files changed, 17 insertions(+), 20 deletions(-)
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 2811ddc..1e751bf 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -103,9 +103,5 @@ struct netns_ct {
unsigned int labels_used;
u8 label_words;
#endif
-#ifdef CONFIG_NF_NAT_NEEDED
- struct hlist_head *nat_bysource;
- unsigned int nat_htable_size;
-#endif
};
#endif
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 069912c..6877a39 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -37,6 +37,9 @@ static const struct nf_nat_l3proto __rcu *nf_nat_l3protos[NFPROTO_NUMPROTO]
__read_mostly;
static const struct nf_nat_l4proto __rcu **nf_nat_l4protos[NFPROTO_NUMPROTO]
__read_mostly;
+
+static struct hlist_head *nf_nat_bysource __read_mostly;
+static unsigned int nf_nat_htable_size __read_mostly;
static unsigned int nf_nat_hash_rnd __read_mostly;
inline const struct nf_nat_l3proto *
@@ -128,7 +131,7 @@ hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple)
hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32),
tuple->dst.protonum ^ nf_nat_hash_rnd ^ net_hash_mix(n));
- return reciprocal_scale(hash, n->ct.nat_htable_size);
+ return reciprocal_scale(hash, nf_nat_htable_size);
}
/* Is this tuple already taken? (not by us) */
@@ -198,9 +201,10 @@ find_appropriate_src(struct net *net,
const struct nf_conn_nat *nat;
const struct nf_conn *ct;
- hlist_for_each_entry_rcu(nat, &net->ct.nat_bysource[h], bysource) {
+ hlist_for_each_entry_rcu(nat, &nf_nat_bysource[h], bysource) {
ct = nat->ct;
if (same_src(ct, tuple) &&
+ net_eq(net, nf_ct_net(ct)) &&
nf_ct_zone_equal(ct, zone, IP_CT_DIR_ORIGINAL)) {
/* Copy source part from reply tuple. */
nf_ct_invert_tuplepr(result,
@@ -433,7 +437,7 @@ nf_nat_setup_info(struct nf_conn *ct,
nat = nfct_nat(ct);
nat->ct = ct;
hlist_add_head_rcu(&nat->bysource,
- &net->ct.nat_bysource[srchash]);
+ &nf_nat_bysource[srchash]);
spin_unlock_bh(&nf_nat_lock);
}
@@ -821,27 +825,14 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct,
}
#endif
-static int __net_init nf_nat_net_init(struct net *net)
-{
- /* Leave them the same for the moment. */
- net->ct.nat_htable_size = nf_conntrack_htable_size;
- net->ct.nat_bysource = nf_ct_alloc_hashtable(&net->ct.nat_htable_size, 0);
- if (!net->ct.nat_bysource)
- return -ENOMEM;
- return 0;
-}
-
static void __net_exit nf_nat_net_exit(struct net *net)
{
struct nf_nat_proto_clean clean = {};
nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean, 0, 0);
- synchronize_rcu();
- nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size);
}
static struct pernet_operations nf_nat_net_ops = {
- .init = nf_nat_net_init,
.exit = nf_nat_net_exit,
};
@@ -854,8 +845,16 @@ static int __init nf_nat_init(void)
{
int ret;
+ /* Leave them the same for the moment. */
+ nf_nat_htable_size = nf_conntrack_htable_size;
+
+ nf_nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, 0);
+ if (!nf_nat_bysource)
+ return -ENOMEM;
+
ret = nf_ct_extend_register(&nat_extend);
if (ret < 0) {
+ nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size);
printk(KERN_ERR "nf_nat_core: Unable to register extension\n");
return ret;
}
@@ -879,6 +878,7 @@ static int __init nf_nat_init(void)
return 0;
cleanup_extend:
+ nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size);
nf_ct_extend_unregister(&nat_extend);
return ret;
}
@@ -897,6 +897,7 @@ static void __exit nf_nat_cleanup(void)
for (i = 0; i < NFPROTO_NUMPROTO; i++)
kfree(nf_nat_l4protos[i]);
synchronize_net();
+ nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size);
}
MODULE_LICENSE("GPL");
--
2.1.4
^ permalink raw reply related
* [PATCH 36/36] netfilter: conntrack: use single slab cache
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
From: Florian Westphal <fw@strlen.de>
An earlier patch changed lookup side to also net_eq() namespaces after
obtaining a reference on the conntrack, so a single kmemcache can be used.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netns/conntrack.h | 2 --
net/netfilter/nf_conntrack_core.c | 36 ++++++++++++++----------------------
2 files changed, 14 insertions(+), 24 deletions(-)
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 1e751bf..38b1a80 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -84,7 +84,6 @@ struct netns_ct {
struct ctl_table_header *event_sysctl_header;
struct ctl_table_header *helper_sysctl_header;
#endif
- char *slabname;
unsigned int sysctl_log_invalid; /* Log invalid packets */
int sysctl_events;
int sysctl_acct;
@@ -93,7 +92,6 @@ struct netns_ct {
int sysctl_tstamp;
int sysctl_checksum;
- struct kmem_cache *nf_conntrack_cachep;
struct ct_pcpu __percpu *pcpu_lists;
struct ip_conntrack_stat __percpu *stat;
struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index f58a704..0cd2936 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -72,6 +72,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock);
struct hlist_nulls_head *nf_conntrack_hash __read_mostly;
EXPORT_SYMBOL_GPL(nf_conntrack_hash);
+static __read_mostly struct kmem_cache *nf_conntrack_cachep;
static __read_mostly spinlock_t nf_conntrack_locks_all_lock;
static __read_mostly seqcount_t nf_conntrack_generation;
static __read_mostly bool nf_conntrack_locks_all;
@@ -910,7 +911,7 @@ __nf_conntrack_alloc(struct net *net,
* Do not use kmem_cache_zalloc(), as this cache uses
* SLAB_DESTROY_BY_RCU.
*/
- ct = kmem_cache_alloc(net->ct.nf_conntrack_cachep, gfp);
+ ct = kmem_cache_alloc(nf_conntrack_cachep, gfp);
if (ct == NULL)
goto out;
@@ -937,7 +938,7 @@ __nf_conntrack_alloc(struct net *net,
atomic_set(&ct->ct_general.use, 0);
return ct;
out_free:
- kmem_cache_free(net->ct.nf_conntrack_cachep, ct);
+ kmem_cache_free(nf_conntrack_cachep, ct);
out:
atomic_dec(&net->ct.count);
return ERR_PTR(-ENOMEM);
@@ -964,7 +965,7 @@ void nf_conntrack_free(struct nf_conn *ct)
nf_ct_ext_destroy(ct);
nf_ct_ext_free(ct);
- kmem_cache_free(net->ct.nf_conntrack_cachep, ct);
+ kmem_cache_free(nf_conntrack_cachep, ct);
smp_mb__before_atomic();
atomic_dec(&net->ct.count);
}
@@ -1587,8 +1588,6 @@ i_see_dead_people:
nf_conntrack_tstamp_pernet_fini(net);
nf_conntrack_acct_pernet_fini(net);
nf_conntrack_expect_pernet_fini(net);
- kmem_cache_destroy(net->ct.nf_conntrack_cachep);
- kfree(net->ct.slabname);
free_percpu(net->ct.stat);
free_percpu(net->ct.pcpu_lists);
}
@@ -1693,7 +1692,8 @@ EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or);
int nf_conntrack_init_start(void)
{
int max_factor = 8;
- int i, ret, cpu;
+ int ret = -ENOMEM;
+ int i, cpu;
seqcount_init(&nf_conntrack_generation);
@@ -1729,6 +1729,12 @@ int nf_conntrack_init_start(void)
nf_conntrack_max = max_factor * nf_conntrack_htable_size;
+ nf_conntrack_cachep = kmem_cache_create("nf_conntrack",
+ sizeof(struct nf_conn), 0,
+ SLAB_DESTROY_BY_RCU, NULL);
+ if (!nf_conntrack_cachep)
+ goto err_cachep;
+
printk(KERN_INFO "nf_conntrack version %s (%u buckets, %d max)\n",
NF_CONNTRACK_VERSION, nf_conntrack_htable_size,
nf_conntrack_max);
@@ -1805,6 +1811,8 @@ err_tstamp:
err_acct:
nf_conntrack_expect_fini();
err_expect:
+ kmem_cache_destroy(nf_conntrack_cachep);
+err_cachep:
nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size);
return ret;
}
@@ -1846,18 +1854,6 @@ int nf_conntrack_init_net(struct net *net)
if (!net->ct.stat)
goto err_pcpu_lists;
- net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%p", net);
- if (!net->ct.slabname)
- goto err_slabname;
-
- net->ct.nf_conntrack_cachep = kmem_cache_create(net->ct.slabname,
- sizeof(struct nf_conn), 0,
- SLAB_DESTROY_BY_RCU, NULL);
- if (!net->ct.nf_conntrack_cachep) {
- printk(KERN_ERR "Unable to create nf_conn slab cache\n");
- goto err_cache;
- }
-
ret = nf_conntrack_expect_pernet_init(net);
if (ret < 0)
goto err_expect;
@@ -1889,10 +1885,6 @@ err_tstamp:
err_acct:
nf_conntrack_expect_pernet_fini(net);
err_expect:
- kmem_cache_destroy(net->ct.nf_conntrack_cachep);
-err_cache:
- kfree(net->ct.slabname);
-err_slabname:
free_percpu(net->ct.stat);
err_pcpu_lists:
free_percpu(net->ct.pcpu_lists);
--
2.1.4
^ permalink raw reply related
* [PATCH 01/36] ipvs: handle connections started by real-servers
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
From: Marco Angaroni <marcoangaroni@gmail.com>
When using LVS-NAT and SIP persistence-egine over UDP, the following
limitations are present with current implementation:
1) To actually have load-balancing based on Call-ID header, you need to
use one-packet-scheduling mode. But with one-packet-scheduling the
connection is deleted just after packet is forwarded, so SIP responses
coming from real-servers do not match any connection and SNAT is
not applied.
2) If you do not use "-o" option, IPVS behaves as normal UDP load
balancer, so different SIP calls (each one identified by a different
Call-ID) coming from the same ip-address/port go to the same
real-server. So basically you don’t have load-balancing based on
Call-ID as intended.
3) Call-ID is not learned when a new SIP call is started by a real-server
(inside-to-outside direction), but only in the outside-to-inside
direction. This would be a general problem for all SIP servers acting
as Back2BackUserAgent.
This patch aims to solve problems 1) and 3) while keeping OPS mode
mandatory for SIP-UDP, so that 2) is not a problem anymore.
The basic mechanism implemented is to make packets, that do not match any
existent connection but come from real-servers, create new connections
instead of let them pass without any effect.
When such packets pass through ip_vs_out(), if their source ip address and
source port match a configured real-server, a new connection is
automatically created in the same way as it would have happened if the
packet had come from outside-to-inside direction. A new connection template
is created too if the virtual-service is persistent and there is no
matching connection template found. The new connection automatically
created, if the service had "-o" option, is an OPS connection that lasts
only the time to forward the packet, just like it happens on the
ingress side.
The main part of this mechanism is implemented inside a persistent-engine
specific callback (at the moment only SIP persistent engine exists) and
is triggered only for UDP packets, since connection oriented protocols, by
using different set of ports (typically ephemeral ports) to open new
outgoing connections, should not need this feature.
The following requisites are needed for automatic connection creation; if
any is missing the packet simply goes the same way as before.
a) virtual-service is not fwmark based (this is because fwmark services
do not store address and port of the virtual-service, required to
build the connection data).
b) virtual-service and real-servers must not have been configured with
omitted port (this is again to have all data to create the connection).
Signed-off-by: Marco Angaroni <marcoangaroni@gmail.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 17 +++++
net/netfilter/ipvs/ip_vs_core.c | 154 ++++++++++++++++++++++++++++++++++++++
net/netfilter/ipvs/ip_vs_ctl.c | 46 +++++++++++-
net/netfilter/ipvs/ip_vs_pe_sip.c | 15 ++++
4 files changed, 231 insertions(+), 1 deletion(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index a6cc576..af4c10e 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -731,6 +731,12 @@ struct ip_vs_pe {
u32 (*hashkey_raw)(const struct ip_vs_conn_param *p, u32 initval,
bool inverse);
int (*show_pe_data)(const struct ip_vs_conn *cp, char *buf);
+ /* create connections for real-server outgoing packets */
+ struct ip_vs_conn* (*conn_out)(struct ip_vs_service *svc,
+ struct ip_vs_dest *dest,
+ struct sk_buff *skb,
+ const struct ip_vs_iphdr *iph,
+ __be16 dport, __be16 cport);
};
/* The application module object (a.k.a. app incarnation) */
@@ -874,6 +880,7 @@ struct netns_ipvs {
/* Service counters */
atomic_t ftpsvc_counter;
atomic_t nullsvc_counter;
+ atomic_t conn_out_counter;
#ifdef CONFIG_SYSCTL
/* 1/rate drop and drop-entry variables */
@@ -1147,6 +1154,12 @@ static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs)
*/
const char *ip_vs_proto_name(unsigned int proto);
void ip_vs_init_hash_table(struct list_head *table, int rows);
+struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc,
+ struct ip_vs_dest *dest,
+ struct sk_buff *skb,
+ const struct ip_vs_iphdr *iph,
+ __be16 dport,
+ __be16 cport);
#define IP_VS_INIT_HASH_TABLE(t) ip_vs_init_hash_table((t), ARRAY_SIZE((t)))
#define IP_VS_APP_TYPE_FTP 1
@@ -1378,6 +1391,10 @@ ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol
bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol,
const union nf_inet_addr *daddr, __be16 dport);
+struct ip_vs_dest *
+ip_vs_find_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol,
+ const union nf_inet_addr *daddr, __be16 dport);
+
int ip_vs_use_count_inc(void);
void ip_vs_use_count_dec(void);
int ip_vs_register_nl_ioctl(void);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index b9a4082..f3bac2e 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -68,6 +68,7 @@ EXPORT_SYMBOL(ip_vs_conn_put);
#ifdef CONFIG_IP_VS_DEBUG
EXPORT_SYMBOL(ip_vs_get_debug_level);
#endif
+EXPORT_SYMBOL(ip_vs_new_conn_out);
static int ip_vs_net_id __read_mostly;
/* netns cnt used for uniqueness */
@@ -1100,6 +1101,143 @@ static inline bool is_new_conn_expected(const struct ip_vs_conn *cp,
}
}
+/* Generic function to create new connections for outgoing RS packets
+ *
+ * Pre-requisites for successful connection creation:
+ * 1) Virtual Service is NOT fwmark based:
+ * In fwmark-VS actual vaddr and vport are unknown to IPVS
+ * 2) Real Server and Virtual Service were NOT configured without port:
+ * This is to allow match of different VS to the same RS ip-addr
+ */
+struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc,
+ struct ip_vs_dest *dest,
+ struct sk_buff *skb,
+ const struct ip_vs_iphdr *iph,
+ __be16 dport,
+ __be16 cport)
+{
+ struct ip_vs_conn_param param;
+ struct ip_vs_conn *ct = NULL, *cp = NULL;
+ const union nf_inet_addr *vaddr, *daddr, *caddr;
+ union nf_inet_addr snet;
+ __be16 vport;
+ unsigned int flags;
+
+ EnterFunction(12);
+ vaddr = &svc->addr;
+ vport = svc->port;
+ daddr = &iph->saddr;
+ caddr = &iph->daddr;
+
+ /* check pre-requisites are satisfied */
+ if (svc->fwmark)
+ return NULL;
+ if (!vport || !dport)
+ return NULL;
+
+ /* for persistent service first create connection template */
+ if (svc->flags & IP_VS_SVC_F_PERSISTENT) {
+ /* apply netmask the same way ingress-side does */
+#ifdef CONFIG_IP_VS_IPV6
+ if (svc->af == AF_INET6)
+ ipv6_addr_prefix(&snet.in6, &caddr->in6,
+ (__force __u32)svc->netmask);
+ else
+#endif
+ snet.ip = caddr->ip & svc->netmask;
+ /* fill params and create template if not existent */
+ if (ip_vs_conn_fill_param_persist(svc, skb, iph->protocol,
+ &snet, 0, vaddr,
+ vport, ¶m) < 0)
+ return NULL;
+ ct = ip_vs_ct_in_get(¶m);
+ if (!ct) {
+ ct = ip_vs_conn_new(¶m, dest->af, daddr, dport,
+ IP_VS_CONN_F_TEMPLATE, dest, 0);
+ if (!ct) {
+ kfree(param.pe_data);
+ return NULL;
+ }
+ ct->timeout = svc->timeout;
+ } else {
+ kfree(param.pe_data);
+ }
+ }
+
+ /* connection flags */
+ flags = ((svc->flags & IP_VS_SVC_F_ONEPACKET) &&
+ iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0;
+ /* create connection */
+ ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol,
+ caddr, cport, vaddr, vport, ¶m);
+ cp = ip_vs_conn_new(¶m, dest->af, daddr, dport, flags, dest, 0);
+ if (!cp) {
+ if (ct)
+ ip_vs_conn_put(ct);
+ return NULL;
+ }
+ if (ct) {
+ ip_vs_control_add(cp, ct);
+ ip_vs_conn_put(ct);
+ }
+ ip_vs_conn_stats(cp, svc);
+
+ /* return connection (will be used to handle outgoing packet) */
+ IP_VS_DBG_BUF(6, "New connection RS-initiated:%c c:%s:%u v:%s:%u "
+ "d:%s:%u conn->flags:%X conn->refcnt:%d\n",
+ ip_vs_fwd_tag(cp),
+ IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
+ IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
+ IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport),
+ cp->flags, atomic_read(&cp->refcnt));
+ LeaveFunction(12);
+ return cp;
+}
+
+/* Handle outgoing packets which are considered requests initiated by
+ * real servers, so that subsequent responses from external client can be
+ * routed to the right real server.
+ * Used also for outgoing responses in OPS mode.
+ *
+ * Connection management is handled by persistent-engine specific callback.
+ */
+static struct ip_vs_conn *__ip_vs_rs_conn_out(unsigned int hooknum,
+ struct netns_ipvs *ipvs,
+ int af, struct sk_buff *skb,
+ const struct ip_vs_iphdr *iph)
+{
+ struct ip_vs_dest *dest;
+ struct ip_vs_conn *cp = NULL;
+ __be16 _ports[2], *pptr;
+
+ if (hooknum == NF_INET_LOCAL_IN)
+ return NULL;
+
+ pptr = frag_safe_skb_hp(skb, iph->len,
+ sizeof(_ports), _ports, iph);
+ if (!pptr)
+ return NULL;
+
+ rcu_read_lock();
+ dest = ip_vs_find_real_service(ipvs, af, iph->protocol,
+ &iph->saddr, pptr[0]);
+ if (dest) {
+ struct ip_vs_service *svc;
+ struct ip_vs_pe *pe;
+
+ svc = rcu_dereference(dest->svc);
+ if (svc) {
+ pe = rcu_dereference(svc->pe);
+ if (pe && pe->conn_out)
+ cp = pe->conn_out(svc, dest, skb, iph,
+ pptr[0], pptr[1]);
+ }
+ }
+ rcu_read_unlock();
+
+ return cp;
+}
+
/* Handle response packets: rewrite addresses and send away...
*/
static unsigned int
@@ -1245,6 +1383,22 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in
if (likely(cp))
return handle_response(af, skb, pd, cp, &iph, hooknum);
+
+ /* Check for real-server-started requests */
+ if (atomic_read(&ipvs->conn_out_counter)) {
+ /* Currently only for UDP:
+ * connection oriented protocols typically use
+ * ephemeral ports for outgoing connections, so
+ * related incoming responses would not match any VS
+ */
+ if (pp->protocol == IPPROTO_UDP) {
+ cp = __ip_vs_rs_conn_out(hooknum, ipvs, af, skb, &iph);
+ if (likely(cp))
+ return handle_response(af, skb, pd, cp, &iph,
+ hooknum);
+ }
+ }
+
if (sysctl_nat_icmp_send(ipvs) &&
(pp->protocol == IPPROTO_TCP ||
pp->protocol == IPPROTO_UDP ||
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 404b2a4..6794391 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -567,6 +567,36 @@ bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol,
return false;
}
+/* Find real service record by <proto,addr,port>.
+ * In case of multiple records with the same <proto,addr,port>, only
+ * the first found record is returned.
+ *
+ * To be called under RCU lock.
+ */
+struct ip_vs_dest *ip_vs_find_real_service(struct netns_ipvs *ipvs, int af,
+ __u16 protocol,
+ const union nf_inet_addr *daddr,
+ __be16 dport)
+{
+ unsigned int hash;
+ struct ip_vs_dest *dest;
+
+ /* Check for "full" addressed entries */
+ hash = ip_vs_rs_hashkey(af, daddr, dport);
+
+ hlist_for_each_entry_rcu(dest, &ipvs->rs_table[hash], d_list) {
+ if (dest->port == dport &&
+ dest->af == af &&
+ ip_vs_addr_equal(af, &dest->addr, daddr) &&
+ (dest->protocol == protocol || dest->vfwmark)) {
+ /* HIT */
+ return dest;
+ }
+ }
+
+ return NULL;
+}
+
/* Lookup destination by {addr,port} in the given service
* Called under RCU lock.
*/
@@ -1253,6 +1283,8 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
atomic_inc(&ipvs->ftpsvc_counter);
else if (svc->port == 0)
atomic_inc(&ipvs->nullsvc_counter);
+ if (svc->pe && svc->pe->conn_out)
+ atomic_inc(&ipvs->conn_out_counter);
ip_vs_start_estimator(ipvs, &svc->stats);
@@ -1293,6 +1325,7 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
struct ip_vs_scheduler *sched = NULL, *old_sched;
struct ip_vs_pe *pe = NULL, *old_pe = NULL;
int ret = 0;
+ bool new_pe_conn_out, old_pe_conn_out;
/*
* Lookup the scheduler, by 'u->sched_name'
@@ -1355,8 +1388,16 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
svc->netmask = u->netmask;
old_pe = rcu_dereference_protected(svc->pe, 1);
- if (pe != old_pe)
+ if (pe != old_pe) {
rcu_assign_pointer(svc->pe, pe);
+ /* check for optional methods in new pe */
+ new_pe_conn_out = (pe && pe->conn_out) ? true : false;
+ old_pe_conn_out = (old_pe && old_pe->conn_out) ? true : false;
+ if (new_pe_conn_out && !old_pe_conn_out)
+ atomic_inc(&svc->ipvs->conn_out_counter);
+ if (old_pe_conn_out && !new_pe_conn_out)
+ atomic_dec(&svc->ipvs->conn_out_counter);
+ }
out:
ip_vs_scheduler_put(old_sched);
@@ -1389,6 +1430,8 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup)
/* Unbind persistence engine, keep svc->pe */
old_pe = rcu_dereference_protected(svc->pe, 1);
+ if (old_pe && old_pe->conn_out)
+ atomic_dec(&ipvs->conn_out_counter);
ip_vs_pe_put(old_pe);
/*
@@ -3957,6 +4000,7 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs)
(unsigned long) ipvs);
atomic_set(&ipvs->ftpsvc_counter, 0);
atomic_set(&ipvs->nullsvc_counter, 0);
+ atomic_set(&ipvs->conn_out_counter, 0);
/* procfs stats */
ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index 0a6eb5c..d07ef9e 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -143,6 +143,20 @@ static int ip_vs_sip_show_pe_data(const struct ip_vs_conn *cp, char *buf)
return cp->pe_data_len;
}
+static struct ip_vs_conn *
+ip_vs_sip_conn_out(struct ip_vs_service *svc,
+ struct ip_vs_dest *dest,
+ struct sk_buff *skb,
+ const struct ip_vs_iphdr *iph,
+ __be16 dport,
+ __be16 cport)
+{
+ if (likely(iph->protocol == IPPROTO_UDP))
+ return ip_vs_new_conn_out(svc, dest, skb, iph, dport, cport);
+ /* currently no need to handle other than UDP */
+ return NULL;
+}
+
static struct ip_vs_pe ip_vs_sip_pe =
{
.name = "sip",
@@ -153,6 +167,7 @@ static struct ip_vs_pe ip_vs_sip_pe =
.ct_match = ip_vs_sip_ct_match,
.hashkey_raw = ip_vs_sip_hashkey_raw,
.show_pe_data = ip_vs_sip_show_pe_data,
+ .conn_out = ip_vs_sip_conn_out,
};
static int __init ip_vs_sip_init(void)
--
2.1.4
^ permalink raw reply related
* [PATCH 00/36] Netfilter updates for net-next
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
Hi David,
The following large patchset contains Netfilter updates for your
net-next tree. My initial intention was to send you this in two goes but
when I looked back twice I already had this burden on top of me.
Several updates for IPVS from Marco Angaroni:
1) Allow SIP connections originating from real-servers to be load
balanced by the SIP persistence engine as is already implemented
in the other direction.
2) Release connections immediately for One-packet-scheduling (OPS)
in IPVS, instead of making it via timer and rcu callback.
3) Skip deleting conntracks for each one packet in OPS, and don't call
nf_conntrack_alter_reply() since no reply is expected.
4) Enable drop on exhaustion for OPS + SIP persistence.
Miscelaneous conntrack updates from Florian Westphal, including fix for
hash resize:
5) Move conntrack generation counter out of conntrack pernet structure
since this is only used by the init_ns to allow hash resizing.
6) Use get_random_once() from packet path to collect hash random seed
instead of our compound.
7) Don't disable BH from ____nf_conntrack_find() for statistics,
use NF_CT_STAT_INC_ATOMIC() instead.
8) Fix lookup race during conntrack hash resizing.
9) Introduce clash resolution on conntrack insertion for connectionless
protocol.
Then, Florian's netns rework to get rid of per-netns conntrack table,
thus we use one single table for them all. There was consensus on this
change during the NFWS 2015 and, on top of that, it has recently been
pointed as a source of multiple problems from unpriviledged netns:
11) Use a single conntrack hashtable for all namespaces. Include netns
in object comparisons and make it part of the hash calculation.
Adapt early_drop() to consider netns.
12) Use single expectation and NAT hashtable for all namespaces.
13) Use a single slab cache for all namespaces for conntrack objects.
14) Skip full table scanning from nf_ct_iterate_cleanup() if the pernet
conntrack counter tells us the table is empty (ie. equals zero).
Fixes for nf_tables interval set element handling, support to set
conntrack connlabels and allow set names up to 32 bytes.
15) Parse element flags from element deletion path and pass it up to the
backend set implementation.
16) Allow adjacent intervals in the rbtree set type for dynamic interval
updates.
17) Add support to set connlabel from nf_tables, from Florian Westphal.
18) Allow set names up to 32 bytes in nf_tables.
Several x_tables fixes and updates:
19) Fix incorrect use of IS_ERR_VALUE() in x_tables, original patch
from Andrzej Hajda.
And finally, miscelaneous netfilter updates such as:
20) Disable automatic helper assignment by default. Note this proc knob
was introduced by a9006892643a ("netfilter: nf_ct_helper: allow to
disable automatic helper assignment") 4 years ago to start moving
towards explicit conntrack helper configuration via iptables CT
target.
21) Get rid of obsolete and inconsistent debugging instrumentation
in x_tables.
22) Remove unnecessary check for null after ip6_route_output().
You can pull these changes from:
git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next.git
Thanks!
----------------------------------------------------------------
The following changes since commit 15cfd40771e18a4e9b788c64c9db2606f958b93d:
hv_netvsc: Fix the list processing for network change event (2016-04-24 23:27:58 -0400)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next.git HEAD
for you to fetch changes up to 0c5366b3a8c77fd6d67b763c5a76dfdc314e7726:
netfilter: conntrack: use single slab cache (2016-05-09 16:45:50 +0200)
----------------------------------------------------------------
Florian Westphal (19):
netfilter: conntrack: move generation seqcnt out of netns_ct
netfilter: conntrack: use get_random_once for nat and expectations
netfilter: conntrack: use get_random_once for conntrack hash seed
netfilter: nftables: add connlabel set support
netfilter: conntrack: keep BH enabled during lookup
netfilter: conntrack: fix lookup race during hash resize
netfilter: conntrack: don't attempt to iterate over empty table
netfilter: conntrack: use nf_ct_key_equal() in more places
netfilter: conntrack: small refactoring of conntrack seq_printf
netfilter: conntrack: check netns when comparing conntrack objects
netfilter: conntrack: make netns address part of hash
netfilter: conntrack: use a single hashtable for all namespaces
netfilter: conntrack: consider ct netns in early_drop logic
netfilter: conntrack: check netns when walking expect hash
netfilter: conntrack: make netns address part of expect hash
netfilter: conntrack: use a single expectation table for all namespaces
netfilter: conntrack: make netns address part of nat bysrc hash
netfilter: conntrack: use a single nat bysource table for all namespaces
netfilter: conntrack: use single slab cache
Liping Zhang (1):
netfilter: ip6t_SYNPROXY: unnecessary to check whether ip6_route_output returns NULL
Marco Angaroni (4):
ipvs: handle connections started by real-servers
ipvs: optimize release of connections in OPS mode
ipvs: don't alter conntrack in OPS mode
ipvs: make drop_entry protection effective for SIP-pe
Pablo Neira Ayuso (14):
netfilter: nf_tables: introduce nft_setelem_parse_flags() helper
netfilter: nf_tables: parse element flags from nft_del_setelem()
netfilter: nft_rbtree: introduce nft_rbtree_interval_end() helper
netfilter: nft_rbtree: allow adjacent intervals with dynamic updates
netfilter: nf_ct_helper: disable automatic helper assignment
Merge tag 'ipvs-for-v4.7' of https://git.kernel.org/.../horms/ipvs-next
netfilter: fix IS_ERR_VALUE usage
netfilter: conntrack: __nf_ct_l4proto_find() always returns valid pointer
netfilter: conntrack: introduce nf_ct_acct_update()
netfilter: conntrack: introduce clash resolution on insertion race
openvswitch: __nf_ct_l{3,4}proto_find() always return a valid pointer
netfilter: x_tables: get rid of old and inconsistent debugging
netfilter: nf_tables: allow set names up to 32 bytes
Merge tag 'ipvs2-for-v4.7' of https://git.kernel.org/.../horms/ipvs-next
include/linux/netfilter/x_tables.h | 6 +-
include/net/ip_vs.h | 17 +
include/net/netfilter/nf_conntrack.h | 2 -
include/net/netfilter/nf_conntrack_core.h | 1 +
include/net/netfilter/nf_conntrack_expect.h | 1 +
include/net/netfilter/nf_conntrack_l4proto.h | 3 +
include/net/netfilter/nf_tables.h | 2 +-
include/net/netns/conntrack.h | 10 -
include/uapi/linux/netfilter/nf_tables.h | 1 +
net/ipv4/netfilter/arp_tables.c | 223 ++---------
net/ipv4/netfilter/ip_tables.c | 250 +++----------
net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 2 +-
.../netfilter/nf_conntrack_l3proto_ipv4_compat.c | 47 ++-
net/ipv6/netfilter/ip6_tables.c | 235 +++---------
net/ipv6/netfilter/ip6t_SYNPROXY.c | 2 +-
net/netfilter/ipvs/ip_vs_conn.c | 51 ++-
net/netfilter/ipvs/ip_vs_core.c | 162 +++++++-
net/netfilter/ipvs/ip_vs_ctl.c | 46 ++-
net/netfilter/ipvs/ip_vs_nfct.c | 4 +
net/netfilter/ipvs/ip_vs_pe_sip.c | 15 +
net/netfilter/nf_conntrack_core.c | 415 +++++++++++----------
net/netfilter/nf_conntrack_expect.c | 83 +++--
net/netfilter/nf_conntrack_helper.c | 12 +-
net/netfilter/nf_conntrack_netlink.c | 29 +-
net/netfilter/nf_conntrack_proto_udp.c | 2 +
net/netfilter/nf_conntrack_proto_udplite.c | 2 +
net/netfilter/nf_conntrack_standalone.c | 13 +-
net/netfilter/nf_nat_core.c | 39 +-
net/netfilter/nf_tables_api.c | 78 +++-
net/netfilter/nfnetlink_cttimeout.c | 6 +-
net/netfilter/nft_ct.c | 30 ++
net/netfilter/nft_rbtree.c | 49 ++-
net/openvswitch/conntrack.c | 8 -
33 files changed, 916 insertions(+), 930 deletions(-)
^ permalink raw reply
* [PATCH 02/36] ipvs: optimize release of connections in OPS mode
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
From: Marco Angaroni <marcoangaroni@gmail.com>
One-packet-scheduling is the most expensive mode in IPVS from
performance point of view: for each packet to be processed a new
connection data structure is created and, after packet is sent,
deleted by starting a new timer set to expire immediately.
SIP persistent-engine needs OPS mode to have Call-ID based load
balancing, so OPS mode performance has negative impact in SIP
protocol load balancing.
This patch aims to improve performance of OPS mode by means of the
following changes in the release mechanism of OPS connections:
a) call expire callback ip_vs_conn_expire() directly instead of
starting a timer programmed to fire immediately.
b) avoid call_rcu() overhead inside expire callback, since OPS
connection are not inserted in the hash-table and last just the
time to process the packet, hence there is no concurrent access
to such data structures.
Signed-off-by: Marco Angaroni <marcoangaroni@gmail.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_conn.c | 26 +++++++++++++++++++++++---
1 file changed, 23 insertions(+), 3 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 85ca189..dd75d41 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -104,6 +104,7 @@ static inline void ct_write_unlock_bh(unsigned int key)
spin_unlock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
}
+static void ip_vs_conn_expire(unsigned long data);
/*
* Returns hash value for IPVS connection entry
@@ -453,10 +454,16 @@ ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af,
}
EXPORT_SYMBOL_GPL(ip_vs_conn_out_get_proto);
+static void __ip_vs_conn_put_notimer(struct ip_vs_conn *cp)
+{
+ __ip_vs_conn_put(cp);
+ ip_vs_conn_expire((unsigned long)cp);
+}
+
/*
* Put back the conn and restart its timer with its timeout
*/
-void ip_vs_conn_put(struct ip_vs_conn *cp)
+static void __ip_vs_conn_put_timer(struct ip_vs_conn *cp)
{
unsigned long t = (cp->flags & IP_VS_CONN_F_ONE_PACKET) ?
0 : cp->timeout;
@@ -465,6 +472,16 @@ void ip_vs_conn_put(struct ip_vs_conn *cp)
__ip_vs_conn_put(cp);
}
+void ip_vs_conn_put(struct ip_vs_conn *cp)
+{
+ if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) &&
+ (atomic_read(&cp->refcnt) == 1) &&
+ !timer_pending(&cp->timer))
+ /* expire connection immediately */
+ __ip_vs_conn_put_notimer(cp);
+ else
+ __ip_vs_conn_put_timer(cp);
+}
/*
* Fill a no_client_port connection with a client port number
@@ -834,7 +851,10 @@ static void ip_vs_conn_expire(unsigned long data)
ip_vs_unbind_dest(cp);
if (cp->flags & IP_VS_CONN_F_NO_CPORT)
atomic_dec(&ip_vs_conn_no_cport_cnt);
- call_rcu(&cp->rcu_head, ip_vs_conn_rcu_free);
+ if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
+ ip_vs_conn_rcu_free(&cp->rcu_head);
+ else
+ call_rcu(&cp->rcu_head, ip_vs_conn_rcu_free);
atomic_dec(&ipvs->conn_count);
return;
}
@@ -850,7 +870,7 @@ static void ip_vs_conn_expire(unsigned long data)
if (ipvs->sync_state & IP_VS_STATE_MASTER)
ip_vs_sync_conn(ipvs, cp, sysctl_sync_threshold(ipvs));
- ip_vs_conn_put(cp);
+ __ip_vs_conn_put_timer(cp);
}
/* Modify timer, so that it expires as soon as possible.
--
2.1.4
^ permalink raw reply related
* [PATCH 05/36] netfilter: conntrack: use get_random_once for nat and expectations
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
From: Florian Westphal <fw@strlen.de>
Use a private seed and init it using get_random_once.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_expect.c | 7 +++----
net/netfilter/nf_nat_core.c | 6 ++++--
2 files changed, 7 insertions(+), 6 deletions(-)
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 278927a..c2f7c4f 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -38,6 +38,7 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_hsize);
unsigned int nf_ct_expect_max __read_mostly;
static struct kmem_cache *nf_ct_expect_cachep __read_mostly;
+static unsigned int nf_ct_expect_hashrnd __read_mostly;
/* nf_conntrack_expect helper functions */
void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
@@ -76,13 +77,11 @@ static unsigned int nf_ct_expect_dst_hash(const struct nf_conntrack_tuple *tuple
{
unsigned int hash;
- if (unlikely(!nf_conntrack_hash_rnd)) {
- init_nf_conntrack_hash_rnd();
- }
+ get_random_once(&nf_ct_expect_hashrnd, sizeof(nf_ct_expect_hashrnd));
hash = jhash2(tuple->dst.u3.all, ARRAY_SIZE(tuple->dst.u3.all),
(((tuple->dst.protonum ^ tuple->src.l3num) << 16) |
- (__force __u16)tuple->dst.u.all) ^ nf_conntrack_hash_rnd);
+ (__force __u16)tuple->dst.u.all) ^ nf_ct_expect_hashrnd);
return reciprocal_scale(hash, nf_ct_expect_hsize);
}
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 06a9f45..3d52271 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -37,7 +37,7 @@ static const struct nf_nat_l3proto __rcu *nf_nat_l3protos[NFPROTO_NUMPROTO]
__read_mostly;
static const struct nf_nat_l4proto __rcu **nf_nat_l4protos[NFPROTO_NUMPROTO]
__read_mostly;
-
+static unsigned int nf_nat_hash_rnd __read_mostly;
inline const struct nf_nat_l3proto *
__nf_nat_l3proto_find(u8 family)
@@ -122,9 +122,11 @@ hash_by_src(const struct net *net, const struct nf_conntrack_tuple *tuple)
{
unsigned int hash;
+ get_random_once(&nf_nat_hash_rnd, sizeof(nf_nat_hash_rnd));
+
/* Original src, to ensure we map it consistently if poss. */
hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32),
- tuple->dst.protonum ^ nf_conntrack_hash_rnd);
+ tuple->dst.protonum ^ nf_nat_hash_rnd);
return reciprocal_scale(hash, net->ct.nat_htable_size);
}
--
2.1.4
^ permalink raw reply related
* [PATCH 07/36] netfilter: nf_tables: introduce nft_setelem_parse_flags() helper
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
This function parses the set element flags, thus, we can reuse the same
handling when deleting elements.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_tables_api.c | 34 ++++++++++++++++++++++------------
1 file changed, 22 insertions(+), 12 deletions(-)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 7a85a9d..1b3210b 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3375,6 +3375,22 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem)
}
EXPORT_SYMBOL_GPL(nft_set_elem_destroy);
+static int nft_setelem_parse_flags(const struct nft_set *set,
+ const struct nlattr *attr, u32 *flags)
+{
+ if (attr == NULL)
+ return 0;
+
+ *flags = ntohl(nla_get_be32(attr));
+ if (*flags & ~NFT_SET_ELEM_INTERVAL_END)
+ return -EINVAL;
+ if (!(set->flags & NFT_SET_INTERVAL) &&
+ *flags & NFT_SET_ELEM_INTERVAL_END)
+ return -EINVAL;
+
+ return 0;
+}
+
static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
const struct nlattr *attr)
{
@@ -3388,8 +3404,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
struct nft_data data;
enum nft_registers dreg;
struct nft_trans *trans;
+ u32 flags = 0;
u64 timeout;
- u32 flags;
u8 ulen;
int err;
@@ -3403,17 +3419,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
nft_set_ext_prepare(&tmpl);
- flags = 0;
- if (nla[NFTA_SET_ELEM_FLAGS] != NULL) {
- flags = ntohl(nla_get_be32(nla[NFTA_SET_ELEM_FLAGS]));
- if (flags & ~NFT_SET_ELEM_INTERVAL_END)
- return -EINVAL;
- if (!(set->flags & NFT_SET_INTERVAL) &&
- flags & NFT_SET_ELEM_INTERVAL_END)
- return -EINVAL;
- if (flags != 0)
- nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
- }
+ err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags);
+ if (err < 0)
+ return err;
+ if (flags != 0)
+ nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS);
if (set->flags & NFT_SET_MAP) {
if (nla[NFTA_SET_ELEM_DATA] == NULL &&
--
2.1.4
^ permalink raw reply related
* [PATCH 09/36] netfilter: nft_rbtree: introduce nft_rbtree_interval_end() helper
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
Add this new nft_rbtree_interval_end() helper function to check in the
end interval is set.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_rbtree.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
index 1c30f41..29f2ab8 100644
--- a/net/netfilter/nft_rbtree.c
+++ b/net/netfilter/nft_rbtree.c
@@ -29,6 +29,11 @@ struct nft_rbtree_elem {
struct nft_set_ext ext;
};
+static bool nft_rbtree_interval_end(const struct nft_rbtree_elem *rbe)
+{
+ return nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) &&
+ (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END);
+}
static bool nft_rbtree_lookup(const struct nft_set *set, const u32 *key,
const struct nft_set_ext **ext)
@@ -56,9 +61,7 @@ found:
parent = parent->rb_left;
continue;
}
- if (nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) &&
- *nft_set_ext_flags(&rbe->ext) &
- NFT_SET_ELEM_INTERVAL_END)
+ if (nft_rbtree_interval_end(rbe))
goto out;
spin_unlock_bh(&nft_rbtree_lock);
--
2.1.4
^ permalink raw reply related
* [PATCH 10/36] netfilter: nft_rbtree: allow adjacent intervals with dynamic updates
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
This patch fixes dynamic element updates for adjacent intervals in the
rb-tree representation.
Since elements are sorted in the rb-tree, in case of adjacent nodes with
the same key, the assumption is that an interval end node must be placed
before an interval opening.
In tree lookup operations, the idea is to search for the closer element
that is smaller than the one we're searching for. Given that we'll have
two possible matchings, we have to take the opening interval in case of
adjacent nodes.
Range merges are not trivial with the current representation,
specifically we have to check if node extensions are equal and make sure
we keep the existing internal states around.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_rbtree.c | 40 +++++++++++++++++++++++++++++++++++-----
1 file changed, 35 insertions(+), 5 deletions(-)
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
index 29f2ab8..f762094 100644
--- a/net/netfilter/nft_rbtree.c
+++ b/net/netfilter/nft_rbtree.c
@@ -35,6 +35,12 @@ static bool nft_rbtree_interval_end(const struct nft_rbtree_elem *rbe)
(*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END);
}
+static bool nft_rbtree_equal(const struct nft_set *set, const void *this,
+ const struct nft_rbtree_elem *interval)
+{
+ return memcmp(this, nft_set_ext_key(&interval->ext), set->klen) == 0;
+}
+
static bool nft_rbtree_lookup(const struct nft_set *set, const u32 *key,
const struct nft_set_ext **ext)
{
@@ -42,6 +48,7 @@ static bool nft_rbtree_lookup(const struct nft_set *set, const u32 *key,
const struct nft_rbtree_elem *rbe, *interval = NULL;
const struct rb_node *parent;
u8 genmask = nft_genmask_cur(read_pnet(&set->pnet));
+ const void *this;
int d;
spin_lock_bh(&nft_rbtree_lock);
@@ -49,9 +56,16 @@ static bool nft_rbtree_lookup(const struct nft_set *set, const u32 *key,
while (parent != NULL) {
rbe = rb_entry(parent, struct nft_rbtree_elem, node);
- d = memcmp(nft_set_ext_key(&rbe->ext), key, set->klen);
+ this = nft_set_ext_key(&rbe->ext);
+ d = memcmp(this, key, set->klen);
if (d < 0) {
parent = parent->rb_left;
+ /* In case of adjacent ranges, we always see the high
+ * part of the range in first place, before the low one.
+ * So don't update interval if the keys are equal.
+ */
+ if (interval && nft_rbtree_equal(set, this, interval))
+ continue;
interval = rbe;
} else if (d > 0)
parent = parent->rb_right;
@@ -101,9 +115,16 @@ static int __nft_rbtree_insert(const struct nft_set *set,
else if (d > 0)
p = &parent->rb_right;
else {
- if (nft_set_elem_active(&rbe->ext, genmask))
- return -EEXIST;
- p = &parent->rb_left;
+ if (nft_set_elem_active(&rbe->ext, genmask)) {
+ if (nft_rbtree_interval_end(rbe) &&
+ !nft_rbtree_interval_end(new))
+ p = &parent->rb_left;
+ else if (!nft_rbtree_interval_end(rbe) &&
+ nft_rbtree_interval_end(new))
+ p = &parent->rb_right;
+ else
+ return -EEXIST;
+ }
}
}
rb_link_node(&new->node, parent, p);
@@ -148,7 +169,7 @@ static void *nft_rbtree_deactivate(const struct nft_set *set,
{
const struct nft_rbtree *priv = nft_set_priv(set);
const struct rb_node *parent = priv->root.rb_node;
- struct nft_rbtree_elem *rbe;
+ struct nft_rbtree_elem *rbe, *this = elem->priv;
u8 genmask = nft_genmask_cur(read_pnet(&set->pnet));
int d;
@@ -166,6 +187,15 @@ static void *nft_rbtree_deactivate(const struct nft_set *set,
parent = parent->rb_left;
continue;
}
+ if (nft_rbtree_interval_end(rbe) &&
+ !nft_rbtree_interval_end(this)) {
+ parent = parent->rb_left;
+ continue;
+ } else if (!nft_rbtree_interval_end(rbe) &&
+ nft_rbtree_interval_end(this)) {
+ parent = parent->rb_right;
+ continue;
+ }
nft_set_elem_change_active(set, &rbe->ext);
return rbe;
}
--
2.1.4
^ permalink raw reply related
* [PATCH 11/36] netfilter: nf_ct_helper: disable automatic helper assignment
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
Four years ago we introduced a new sysctl knob to disable automatic
helper assignment in 72110dfaa907 ("netfilter: nf_ct_helper: disable
automatic helper assignment"). This knob kept this behaviour enabled by
default to remain conservative.
This measure was introduced to provide a secure way to configure
iptables and connection tracking helpers through explicit rules.
Give the time we have waited for this, let's turn off this by default
now, worse case users still have a chance to recover the former
behaviour by explicitly enabling this back through sysctl.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_helper.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 3b40ec5..498bf74 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -38,10 +38,10 @@ unsigned int nf_ct_helper_hsize __read_mostly;
EXPORT_SYMBOL_GPL(nf_ct_helper_hsize);
static unsigned int nf_ct_helper_count __read_mostly;
-static bool nf_ct_auto_assign_helper __read_mostly = true;
+static bool nf_ct_auto_assign_helper __read_mostly = false;
module_param_named(nf_conntrack_helper, nf_ct_auto_assign_helper, bool, 0644);
MODULE_PARM_DESC(nf_conntrack_helper,
- "Enable automatic conntrack helper assignment (default 1)");
+ "Enable automatic conntrack helper assignment (default 0)");
#ifdef CONFIG_SYSCTL
static struct ctl_table helper_sysctl_table[] = {
--
2.1.4
^ permalink raw reply related
* [PATCH 12/36] netfilter: ip6t_SYNPROXY: unnecessary to check whether ip6_route_output returns NULL
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
From: Liping Zhang <liping.zhang@spreadtrum.com>
ip6_route_output() will never return a NULL pointer, so there's no need
to check it.
Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/ipv6/netfilter/ip6t_SYNPROXY.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index 5d778dd..06bed74 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -60,7 +60,7 @@ synproxy_send_tcp(struct net *net,
fl6.fl6_dport = nth->dest;
security_skb_classify_flow((struct sk_buff *)skb, flowi6_to_flowi(&fl6));
dst = ip6_route_output(net, NULL, &fl6);
- if (dst == NULL || dst->error) {
+ if (dst->error) {
dst_release(dst);
goto free_nskb;
}
--
2.1.4
^ permalink raw reply related
* [PATCH 18/36] netfilter: conntrack: use nf_ct_key_equal() in more places
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
From: Florian Westphal <fw@strlen.de>
This prepares for upcoming change that places all conntracks into a
single, global table. For this to work we will need to also compare
net pointer during lookup. To avoid open-coding such check use the
nf_ct_key_equal helper and then later extend it to also consider net_eq.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_core.c | 29 +++++++++++------------------
1 file changed, 11 insertions(+), 18 deletions(-)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index f2e75a5..3b9c302 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -572,16 +572,13 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
/* See if there's one in the list already, including reverse */
hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
- if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
- &h->tuple) &&
- nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone,
- NF_CT_DIRECTION(h)))
+ if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+ zone))
goto out;
+
hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
- if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
- &h->tuple) &&
- nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone,
- NF_CT_DIRECTION(h)))
+ if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+ zone))
goto out;
add_timer(&ct->timeout);
@@ -665,16 +662,13 @@ __nf_conntrack_confirm(struct sk_buff *skb)
NAT could have grabbed it without realizing, since we're
not in the hash. If there is, we lost race. */
hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
- if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
- &h->tuple) &&
- nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone,
- NF_CT_DIRECTION(h)))
+ if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+ zone))
goto out;
+
hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
- if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
- &h->tuple) &&
- nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone,
- NF_CT_DIRECTION(h)))
+ if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
+ zone))
goto out;
/* Timer relative to confirmation time, not original
@@ -746,8 +740,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) {
ct = nf_ct_tuplehash_to_ctrack(h);
if (ct != ignored_conntrack &&
- nf_ct_tuple_equal(tuple, &h->tuple) &&
- nf_ct_zone_equal(ct, zone, NF_CT_DIRECTION(h))) {
+ nf_ct_key_equal(h, tuple, zone)) {
NF_CT_STAT_INC_ATOMIC(net, found);
rcu_read_unlock();
return 1;
--
2.1.4
^ permalink raw reply related
* [PATCH 13/36] netfilter: fix IS_ERR_VALUE usage
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
This is a forward-port of the original patch from Andrzej Hajda,
he said:
"IS_ERR_VALUE should be used only with unsigned long type.
Otherwise it can work incorrectly. To achieve this function
xt_percpu_counter_alloc is modified to return unsigned long,
and its result is assigned to temporary variable to perform
error checking, before assigning to .pcnt field.
The patch follows conclusion from discussion on LKML [1][2].
[1]: http://permalink.gmane.org/gmane.linux.kernel/2120927
[2]: http://permalink.gmane.org/gmane.linux.kernel/2150581"
Original patch from Andrzej is here:
http://patchwork.ozlabs.org/patch/582970/
This patch has clashed with input validation fixes for x_tables.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/linux/netfilter/x_tables.h | 6 +++---
net/ipv4/netfilter/arp_tables.c | 6 ++++--
net/ipv4/netfilter/ip_tables.c | 6 ++++--
net/ipv6/netfilter/ip6_tables.c | 6 ++++--
4 files changed, 15 insertions(+), 9 deletions(-)
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 4dd9306..dc4f58a 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -380,16 +380,16 @@ static inline unsigned long ifname_compare_aligned(const char *_a,
* allows us to return 0 for single core systems without forcing
* callers to deal with SMP vs. NONSMP issues.
*/
-static inline u64 xt_percpu_counter_alloc(void)
+static inline unsigned long xt_percpu_counter_alloc(void)
{
if (nr_cpu_ids > 1) {
void __percpu *res = __alloc_percpu(sizeof(struct xt_counters),
sizeof(struct xt_counters));
if (res == NULL)
- return (u64) -ENOMEM;
+ return -ENOMEM;
- return (u64) (__force unsigned long) res;
+ return (__force unsigned long) res;
}
return 0;
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 60f5161..3355ed7 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -513,11 +513,13 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size)
{
struct xt_entry_target *t;
struct xt_target *target;
+ unsigned long pcnt;
int ret;
- e->counters.pcnt = xt_percpu_counter_alloc();
- if (IS_ERR_VALUE(e->counters.pcnt))
+ pcnt = xt_percpu_counter_alloc();
+ if (IS_ERR_VALUE(pcnt))
return -ENOMEM;
+ e->counters.pcnt = pcnt;
t = arpt_get_target(e);
target = xt_request_find_target(NFPROTO_ARP, t->u.user.name,
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 735d1ee..21ccc19 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -656,10 +656,12 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
unsigned int j;
struct xt_mtchk_param mtpar;
struct xt_entry_match *ematch;
+ unsigned long pcnt;
- e->counters.pcnt = xt_percpu_counter_alloc();
- if (IS_ERR_VALUE(e->counters.pcnt))
+ pcnt = xt_percpu_counter_alloc();
+ if (IS_ERR_VALUE(pcnt))
return -ENOMEM;
+ e->counters.pcnt = pcnt;
j = 0;
mtpar.net = net;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 73e606c..17874e8 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -669,10 +669,12 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name,
unsigned int j;
struct xt_mtchk_param mtpar;
struct xt_entry_match *ematch;
+ unsigned long pcnt;
- e->counters.pcnt = xt_percpu_counter_alloc();
- if (IS_ERR_VALUE(e->counters.pcnt))
+ pcnt = xt_percpu_counter_alloc();
+ if (IS_ERR_VALUE(pcnt))
return -ENOMEM;
+ e->counters.pcnt = pcnt;
j = 0;
mtpar.net = net;
--
2.1.4
^ permalink raw reply related
* [PATCH 19/36] netfilter: conntrack: small refactoring of conntrack seq_printf
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
From: Florian Westphal <fw@strlen.de>
The iteration process is lockless, so we test if the conntrack object is
eligible for printing (e.g. is AF_INET) after obtaining the reference
count.
Once we put all conntracks into same hash table we might see more
entries that need to be skipped.
So add a helper and first perform the test in a lockless fashion
for fast skip.
Once we obtain the reference count, just repeat the check.
Note that this refactoring also includes a missing check for unconfirmed
conntrack entries due to slab rcu object re-usage, so they need to be
skipped since they are not part of the listing.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
.../netfilter/nf_conntrack_l3proto_ipv4_compat.c | 24 +++++++++++++++++-----
1 file changed, 19 insertions(+), 5 deletions(-)
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index f0dfe92..483cf79 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -114,6 +114,19 @@ static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
}
#endif
+static bool ct_seq_should_skip(const struct nf_conn *ct,
+ const struct nf_conntrack_tuple_hash *hash)
+{
+ /* we only want to print DIR_ORIGINAL */
+ if (NF_CT_DIRECTION(hash))
+ return true;
+
+ if (nf_ct_l3num(ct) != AF_INET)
+ return true;
+
+ return false;
+}
+
static int ct_seq_show(struct seq_file *s, void *v)
{
struct nf_conntrack_tuple_hash *hash = v;
@@ -123,14 +136,15 @@ static int ct_seq_show(struct seq_file *s, void *v)
int ret = 0;
NF_CT_ASSERT(ct);
- if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
+ if (ct_seq_should_skip(ct, hash))
return 0;
+ if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
+ return 0;
- /* we only want to print DIR_ORIGINAL */
- if (NF_CT_DIRECTION(hash))
- goto release;
- if (nf_ct_l3num(ct) != AF_INET)
+ /* check if we raced w. object reuse */
+ if (!nf_ct_is_confirmed(ct) ||
+ ct_seq_should_skip(ct, hash))
goto release;
l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct));
--
2.1.4
^ permalink raw reply related
* [PATCH 20/36] netfilter: conntrack: check netns when comparing conntrack objects
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
From: Florian Westphal <fw@strlen.de>
Once we place all conntracks in the same hash table we must also compare
the netns pointer to skip conntracks that belong to a different namespace.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
.../netfilter/nf_conntrack_l3proto_ipv4_compat.c | 8 ++++++--
net/netfilter/nf_conntrack_core.c | 23 ++++++++++++----------
net/netfilter/nf_conntrack_netlink.c | 3 +++
3 files changed, 22 insertions(+), 12 deletions(-)
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 483cf79..171aba1 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -115,6 +115,7 @@ static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
#endif
static bool ct_seq_should_skip(const struct nf_conn *ct,
+ const struct net *net,
const struct nf_conntrack_tuple_hash *hash)
{
/* we only want to print DIR_ORIGINAL */
@@ -124,6 +125,9 @@ static bool ct_seq_should_skip(const struct nf_conn *ct,
if (nf_ct_l3num(ct) != AF_INET)
return true;
+ if (!net_eq(nf_ct_net(ct), net))
+ return true;
+
return false;
}
@@ -136,7 +140,7 @@ static int ct_seq_show(struct seq_file *s, void *v)
int ret = 0;
NF_CT_ASSERT(ct);
- if (ct_seq_should_skip(ct, hash))
+ if (ct_seq_should_skip(ct, seq_file_net(s), hash))
return 0;
if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
@@ -144,7 +148,7 @@ static int ct_seq_show(struct seq_file *s, void *v)
/* check if we raced w. object reuse */
if (!nf_ct_is_confirmed(ct) ||
- ct_seq_should_skip(ct, hash))
+ ct_seq_should_skip(ct, seq_file_net(s), hash))
goto release;
l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct));
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 3b9c302..10ae2ee 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -447,7 +447,8 @@ static void death_by_timeout(unsigned long ul_conntrack)
static inline bool
nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
const struct nf_conntrack_tuple *tuple,
- const struct nf_conntrack_zone *zone)
+ const struct nf_conntrack_zone *zone,
+ const struct net *net)
{
struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
@@ -456,7 +457,8 @@ nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
*/
return nf_ct_tuple_equal(tuple, &h->tuple) &&
nf_ct_zone_equal(ct, zone, NF_CT_DIRECTION(h)) &&
- nf_ct_is_confirmed(ct);
+ nf_ct_is_confirmed(ct) &&
+ net_eq(net, nf_ct_net(ct));
}
/*
@@ -481,7 +483,7 @@ begin:
} while (read_seqcount_retry(&nf_conntrack_generation, sequence));
hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[bucket], hnnode) {
- if (nf_ct_key_equal(h, tuple, zone)) {
+ if (nf_ct_key_equal(h, tuple, zone, net)) {
NF_CT_STAT_INC_ATOMIC(net, found);
return h;
}
@@ -517,7 +519,7 @@ begin:
!atomic_inc_not_zero(&ct->ct_general.use)))
h = NULL;
else {
- if (unlikely(!nf_ct_key_equal(h, tuple, zone))) {
+ if (unlikely(!nf_ct_key_equal(h, tuple, zone, net))) {
nf_ct_put(ct);
goto begin;
}
@@ -573,12 +575,12 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
/* See if there's one in the list already, including reverse */
hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
- zone))
+ zone, net))
goto out;
hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
- zone))
+ zone, net))
goto out;
add_timer(&ct->timeout);
@@ -663,12 +665,12 @@ __nf_conntrack_confirm(struct sk_buff *skb)
not in the hash. If there is, we lost race. */
hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
- zone))
+ zone, net))
goto out;
hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
- zone))
+ zone, net))
goto out;
/* Timer relative to confirmation time, not original
@@ -740,7 +742,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) {
ct = nf_ct_tuplehash_to_ctrack(h);
if (ct != ignored_conntrack &&
- nf_ct_key_equal(h, tuple, zone)) {
+ nf_ct_key_equal(h, tuple, zone, net)) {
NF_CT_STAT_INC_ATOMIC(net, found);
rcu_read_unlock();
return 1;
@@ -1383,7 +1385,8 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
continue;
ct = nf_ct_tuplehash_to_ctrack(h);
- if (iter(ct, data))
+ if (net_eq(nf_ct_net(ct), net) &&
+ iter(ct, data))
goto found;
}
}
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 294a8e2..f6bbcb2 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -837,6 +837,9 @@ restart:
if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
continue;
ct = nf_ct_tuplehash_to_ctrack(h);
+ if (!net_eq(net, nf_ct_net(ct)))
+ continue;
+
/* Dump entries of a given L3 protocol number.
* If it is not specified, ie. l3proto == 0,
* then dump everything. */
--
2.1.4
^ permalink raw reply related
* [PATCH 23/36] netfilter: conntrack: consider ct netns in early_drop logic
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
From: Florian Westphal <fw@strlen.de>
When iterating, skip conntrack entries living in a different netns.
We could ignore netns and kill some other non-assured one, but it
has two problems:
- a netns can kill non-assured conntracks in other namespace
- we would start to 'over-subscribe' the affected/overlimit netns.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_core.c | 43 +++++++++++++++++++++++----------------
1 file changed, 25 insertions(+), 18 deletions(-)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 4c906e7..e3787cf 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -764,18 +764,20 @@ static noinline int early_drop(struct net *net, unsigned int _hash)
{
/* Use oldest entry, which is roughly LRU */
struct nf_conntrack_tuple_hash *h;
- struct nf_conn *ct = NULL, *tmp;
+ struct nf_conn *tmp;
struct hlist_nulls_node *n;
- unsigned int i = 0, cnt = 0;
- int dropped = 0;
- unsigned int hash, sequence;
+ unsigned int i, hash, sequence;
+ struct nf_conn *ct = NULL;
spinlock_t *lockp;
+ bool ret = false;
+
+ i = 0;
local_bh_disable();
restart:
sequence = read_seqcount_begin(&nf_conntrack_generation);
- hash = scale_hash(_hash);
- for (; i < nf_conntrack_htable_size; i++) {
+ for (; i < NF_CT_EVICTION_RANGE; i++) {
+ hash = scale_hash(_hash++);
lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS];
nf_conntrack_lock(lockp);
if (read_seqcount_retry(&nf_conntrack_generation, sequence)) {
@@ -785,35 +787,40 @@ restart:
hlist_nulls_for_each_entry_rcu(h, n, &nf_conntrack_hash[hash],
hnnode) {
tmp = nf_ct_tuplehash_to_ctrack(h);
- if (!test_bit(IPS_ASSURED_BIT, &tmp->status) &&
- !nf_ct_is_dying(tmp) &&
- atomic_inc_not_zero(&tmp->ct_general.use)) {
+
+ if (test_bit(IPS_ASSURED_BIT, &tmp->status) ||
+ !net_eq(nf_ct_net(tmp), net) ||
+ nf_ct_is_dying(tmp))
+ continue;
+
+ if (atomic_inc_not_zero(&tmp->ct_general.use)) {
ct = tmp;
break;
}
- cnt++;
}
- hash = (hash + 1) % nf_conntrack_htable_size;
spin_unlock(lockp);
-
- if (ct || cnt >= NF_CT_EVICTION_RANGE)
+ if (ct)
break;
-
}
+
local_bh_enable();
if (!ct)
- return dropped;
+ return false;
- if (del_timer(&ct->timeout)) {
+ /* kill only if in same netns -- might have moved due to
+ * SLAB_DESTROY_BY_RCU rules
+ */
+ if (net_eq(nf_ct_net(ct), net) && del_timer(&ct->timeout)) {
if (nf_ct_delete(ct, 0, 0)) {
- dropped = 1;
NF_CT_STAT_INC_ATOMIC(net, early_drop);
+ ret = true;
}
}
+
nf_ct_put(ct);
- return dropped;
+ return ret;
}
static struct nf_conn *
--
2.1.4
^ permalink raw reply related
* [PATCH 22/36] netfilter: conntrack: use a single hashtable for all namespaces
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
From: Florian Westphal <fw@strlen.de>
We already include netns address in the hash and compare the netns pointers
during lookup, so even if namespaces have overlapping addresses entries
will be spread across the table.
Assuming 64k bucket size, this change saves 0.5 mbyte per namespace on a
64bit system.
NAT bysrc and expectation hash is still per namespace, those will
changed too soon.
Future patch will also make conntrack object slab cache global again.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_conntrack_core.h | 1 +
include/net/netns/conntrack.h | 2 -
net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 2 +-
.../netfilter/nf_conntrack_l3proto_ipv4_compat.c | 10 ++-
net/netfilter/nf_conntrack_core.c | 80 +++++++++++-----------
net/netfilter/nf_conntrack_helper.c | 6 +-
net/netfilter/nf_conntrack_netlink.c | 8 +--
net/netfilter/nf_conntrack_standalone.c | 13 ++--
net/netfilter/nf_nat_core.c | 2 +-
net/netfilter/nfnetlink_cttimeout.c | 6 +-
10 files changed, 62 insertions(+), 68 deletions(-)
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 62e17d1..3e2f332 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -81,6 +81,7 @@ print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
#define CONNTRACK_LOCKS 1024
+extern struct hlist_nulls_head *nf_conntrack_hash;
extern spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS];
void nf_conntrack_lock(spinlock_t *lock);
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index b052785..251c435 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -93,9 +93,7 @@ struct netns_ct {
int sysctl_tstamp;
int sysctl_checksum;
- unsigned int htable_size;
struct kmem_cache *nf_conntrack_cachep;
- struct hlist_nulls_head *hash;
struct hlist_head *expect_hash;
struct ct_pcpu __percpu *pcpu_lists;
struct ip_conntrack_stat __percpu *stat;
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index e3c46e8..ae1a71a 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -360,7 +360,7 @@ static int ipv4_init_net(struct net *net)
in->ctl_table[0].data = &nf_conntrack_max;
in->ctl_table[1].data = &net->ct.count;
- in->ctl_table[2].data = &net->ct.htable_size;
+ in->ctl_table[2].data = &nf_conntrack_htable_size;
in->ctl_table[3].data = &net->ct.sysctl_checksum;
in->ctl_table[4].data = &net->ct.sysctl_log_invalid;
#endif
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 171aba1..f8fc7ab 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -31,15 +31,14 @@ struct ct_iter_state {
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_nulls_node *n;
for (st->bucket = 0;
- st->bucket < net->ct.htable_size;
+ st->bucket < nf_conntrack_htable_size;
st->bucket++) {
n = rcu_dereference(
- hlist_nulls_first_rcu(&net->ct.hash[st->bucket]));
+ hlist_nulls_first_rcu(&nf_conntrack_hash[st->bucket]));
if (!is_a_nulls(n))
return n;
}
@@ -49,17 +48,16 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
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(hlist_nulls_next_rcu(head));
while (is_a_nulls(head)) {
if (likely(get_nulls_value(head) == st->bucket)) {
- if (++st->bucket >= net->ct.htable_size)
+ if (++st->bucket >= nf_conntrack_htable_size)
return NULL;
}
head = rcu_dereference(
- hlist_nulls_first_rcu(&net->ct.hash[st->bucket]));
+ hlist_nulls_first_rcu(&nf_conntrack_hash[st->bucket]));
}
return head;
}
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index ebafa77..4c906e7 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -69,6 +69,9 @@ EXPORT_SYMBOL_GPL(nf_conntrack_locks);
__cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock);
EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock);
+struct hlist_nulls_head *nf_conntrack_hash __read_mostly;
+EXPORT_SYMBOL_GPL(nf_conntrack_hash);
+
static __read_mostly spinlock_t nf_conntrack_locks_all_lock;
static __read_mostly seqcount_t nf_conntrack_generation;
static __read_mostly bool nf_conntrack_locks_all;
@@ -164,9 +167,9 @@ static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
tuple->dst.protonum));
}
-static u32 hash_bucket(u32 hash, const struct net *net)
+static u32 scale_hash(u32 hash)
{
- return reciprocal_scale(hash, net->ct.htable_size);
+ return reciprocal_scale(hash, nf_conntrack_htable_size);
}
static u32 __hash_conntrack(const struct net *net,
@@ -179,7 +182,7 @@ static u32 __hash_conntrack(const struct net *net,
static u32 hash_conntrack(const struct net *net,
const struct nf_conntrack_tuple *tuple)
{
- return __hash_conntrack(net, tuple, net->ct.htable_size);
+ return scale_hash(hash_conntrack_raw(tuple, net));
}
bool
@@ -478,8 +481,8 @@ ____nf_conntrack_find(struct net *net, const struct nf_conntrack_zone *zone,
begin:
do {
sequence = read_seqcount_begin(&nf_conntrack_generation);
- bucket = hash_bucket(hash, net);
- ct_hash = net->ct.hash;
+ bucket = scale_hash(hash);
+ ct_hash = nf_conntrack_hash;
} while (read_seqcount_retry(&nf_conntrack_generation, sequence));
hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[bucket], hnnode) {
@@ -543,12 +546,10 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct,
unsigned int hash,
unsigned int reply_hash)
{
- struct net *net = nf_ct_net(ct);
-
hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
- &net->ct.hash[hash]);
+ &nf_conntrack_hash[hash]);
hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
- &net->ct.hash[reply_hash]);
+ &nf_conntrack_hash[reply_hash]);
}
int
@@ -573,12 +574,12 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
/* See if there's one in the list already, including reverse */
- hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
+ hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode)
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
zone, net))
goto out;
- hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
+ hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode)
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
zone, net))
goto out;
@@ -633,7 +634,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
sequence = read_seqcount_begin(&nf_conntrack_generation);
/* reuse the hash saved before */
hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev;
- hash = hash_bucket(hash, net);
+ hash = scale_hash(hash);
reply_hash = hash_conntrack(net,
&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
@@ -663,12 +664,12 @@ __nf_conntrack_confirm(struct sk_buff *skb)
/* See if there's one in the list already, including reverse:
NAT could have grabbed it without realizing, since we're
not in the hash. If there is, we lost race. */
- hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
+ hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode)
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
zone, net))
goto out;
- hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
+ hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode)
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
zone, net))
goto out;
@@ -736,7 +737,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
do {
sequence = read_seqcount_begin(&nf_conntrack_generation);
hash = hash_conntrack(net, tuple);
- ct_hash = net->ct.hash;
+ ct_hash = nf_conntrack_hash;
} while (read_seqcount_retry(&nf_conntrack_generation, sequence));
hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) {
@@ -773,16 +774,16 @@ static noinline int early_drop(struct net *net, unsigned int _hash)
local_bh_disable();
restart:
sequence = read_seqcount_begin(&nf_conntrack_generation);
- hash = hash_bucket(_hash, net);
- for (; i < net->ct.htable_size; i++) {
+ hash = scale_hash(_hash);
+ for (; i < nf_conntrack_htable_size; i++) {
lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS];
nf_conntrack_lock(lockp);
if (read_seqcount_retry(&nf_conntrack_generation, sequence)) {
spin_unlock(lockp);
goto restart;
}
- hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash],
- hnnode) {
+ hlist_nulls_for_each_entry_rcu(h, n, &nf_conntrack_hash[hash],
+ hnnode) {
tmp = nf_ct_tuplehash_to_ctrack(h);
if (!test_bit(IPS_ASSURED_BIT, &tmp->status) &&
!nf_ct_is_dying(tmp) &&
@@ -793,7 +794,7 @@ restart:
cnt++;
}
- hash = (hash + 1) % net->ct.htable_size;
+ hash = (hash + 1) % nf_conntrack_htable_size;
spin_unlock(lockp);
if (ct || cnt >= NF_CT_EVICTION_RANGE)
@@ -1376,12 +1377,12 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
int cpu;
spinlock_t *lockp;
- for (; *bucket < net->ct.htable_size; (*bucket)++) {
+ for (; *bucket < nf_conntrack_htable_size; (*bucket)++) {
lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS];
local_bh_disable();
nf_conntrack_lock(lockp);
- if (*bucket < net->ct.htable_size) {
- hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) {
+ if (*bucket < nf_conntrack_htable_size) {
+ hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) {
if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
continue;
ct = nf_ct_tuplehash_to_ctrack(h);
@@ -1478,6 +1479,8 @@ void nf_conntrack_cleanup_end(void)
while (untrack_refs() > 0)
schedule();
+ nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size);
+
#ifdef CONFIG_NF_CONNTRACK_ZONES
nf_ct_extend_unregister(&nf_ct_zone_extend);
#endif
@@ -1528,7 +1531,6 @@ i_see_dead_people:
}
list_for_each_entry(net, net_exit_list, exit_list) {
- nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size);
nf_conntrack_proto_pernet_fini(net);
nf_conntrack_helper_pernet_fini(net);
nf_conntrack_ecache_pernet_fini(net);
@@ -1599,10 +1601,10 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
* though since that required taking the locks.
*/
- for (i = 0; i < init_net.ct.htable_size; i++) {
- while (!hlist_nulls_empty(&init_net.ct.hash[i])) {
- h = hlist_nulls_entry(init_net.ct.hash[i].first,
- struct nf_conntrack_tuple_hash, hnnode);
+ for (i = 0; i < nf_conntrack_htable_size; i++) {
+ while (!hlist_nulls_empty(&nf_conntrack_hash[i])) {
+ h = hlist_nulls_entry(nf_conntrack_hash[i].first,
+ struct nf_conntrack_tuple_hash, hnnode);
ct = nf_ct_tuplehash_to_ctrack(h);
hlist_nulls_del_rcu(&h->hnnode);
bucket = __hash_conntrack(nf_ct_net(ct),
@@ -1610,11 +1612,11 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]);
}
}
- old_size = init_net.ct.htable_size;
- old_hash = init_net.ct.hash;
+ old_size = nf_conntrack_htable_size;
+ old_hash = nf_conntrack_hash;
- init_net.ct.htable_size = nf_conntrack_htable_size = hashsize;
- init_net.ct.hash = hash;
+ nf_conntrack_hash = hash;
+ nf_conntrack_htable_size = hashsize;
write_seqcount_end(&nf_conntrack_generation);
nf_conntrack_all_unlock();
@@ -1670,6 +1672,11 @@ int nf_conntrack_init_start(void)
* entries. */
max_factor = 4;
}
+
+ nf_conntrack_hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size, 1);
+ if (!nf_conntrack_hash)
+ return -ENOMEM;
+
nf_conntrack_max = max_factor * nf_conntrack_htable_size;
printk(KERN_INFO "nf_conntrack version %s (%u buckets, %d max)\n",
@@ -1748,6 +1755,7 @@ err_tstamp:
err_acct:
nf_conntrack_expect_fini();
err_expect:
+ nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size);
return ret;
}
@@ -1800,12 +1808,6 @@ int nf_conntrack_init_net(struct net *net)
goto err_cache;
}
- net->ct.htable_size = nf_conntrack_htable_size;
- net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, 1);
- if (!net->ct.hash) {
- printk(KERN_ERR "Unable to create nf_conntrack_hash\n");
- goto err_hash;
- }
ret = nf_conntrack_expect_pernet_init(net);
if (ret < 0)
goto err_expect;
@@ -1837,8 +1839,6 @@ err_tstamp:
err_acct:
nf_conntrack_expect_pernet_fini(net);
err_expect:
- nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size);
-err_hash:
kmem_cache_destroy(net->ct.nf_conntrack_cachep);
err_cache:
kfree(net->ct.slabname);
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 498bf74..cb48e6a 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -424,10 +424,10 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me,
spin_unlock_bh(&pcpu->lock);
}
local_bh_disable();
- for (i = 0; i < net->ct.htable_size; i++) {
+ for (i = 0; i < nf_conntrack_htable_size; i++) {
nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
- if (i < net->ct.htable_size) {
- hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode)
+ if (i < nf_conntrack_htable_size) {
+ hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode)
unhelp(h, me);
}
spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index f6bbcb2..e00f178 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -824,16 +824,16 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
last = (struct nf_conn *)cb->args[1];
local_bh_disable();
- for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) {
+ for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) {
restart:
lockp = &nf_conntrack_locks[cb->args[0] % CONNTRACK_LOCKS];
nf_conntrack_lock(lockp);
- if (cb->args[0] >= net->ct.htable_size) {
+ if (cb->args[0] >= nf_conntrack_htable_size) {
spin_unlock(lockp);
goto out;
}
- hlist_nulls_for_each_entry(h, n, &net->ct.hash[cb->args[0]],
- hnnode) {
+ hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[cb->args[0]],
+ hnnode) {
if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
continue;
ct = nf_ct_tuplehash_to_ctrack(h);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 0f1a45b..f87e84e 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -54,14 +54,13 @@ struct ct_iter_state {
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_nulls_node *n;
for (st->bucket = 0;
- st->bucket < net->ct.htable_size;
+ st->bucket < nf_conntrack_htable_size;
st->bucket++) {
- n = rcu_dereference(hlist_nulls_first_rcu(&net->ct.hash[st->bucket]));
+ n = rcu_dereference(hlist_nulls_first_rcu(&nf_conntrack_hash[st->bucket]));
if (!is_a_nulls(n))
return n;
}
@@ -71,18 +70,17 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
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(hlist_nulls_next_rcu(head));
while (is_a_nulls(head)) {
if (likely(get_nulls_value(head) == st->bucket)) {
- if (++st->bucket >= net->ct.htable_size)
+ if (++st->bucket >= nf_conntrack_htable_size)
return NULL;
}
head = rcu_dereference(
hlist_nulls_first_rcu(
- &net->ct.hash[st->bucket]));
+ &nf_conntrack_hash[st->bucket]));
}
return head;
}
@@ -458,7 +456,7 @@ static struct ctl_table nf_ct_sysctl_table[] = {
},
{
.procname = "nf_conntrack_buckets",
- .data = &init_net.ct.htable_size,
+ .data = &nf_conntrack_htable_size,
.maxlen = sizeof(unsigned int),
.mode = 0444,
.proc_handler = proc_dointvec,
@@ -512,7 +510,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
goto out_kmemdup;
table[1].data = &net->ct.count;
- table[2].data = &net->ct.htable_size;
table[3].data = &net->ct.sysctl_checksum;
table[4].data = &net->ct.sysctl_log_invalid;
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 3d52271..d74e716 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -824,7 +824,7 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct,
static int __net_init nf_nat_net_init(struct net *net)
{
/* Leave them the same for the moment. */
- net->ct.nat_htable_size = net->ct.htable_size;
+ net->ct.nat_htable_size = nf_conntrack_htable_size;
net->ct.nat_bysource = nf_ct_alloc_hashtable(&net->ct.nat_htable_size, 0);
if (!net->ct.nat_bysource)
return -ENOMEM;
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 2671b9d..3c84f14 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -306,10 +306,10 @@ static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout)
int i;
local_bh_disable();
- for (i = 0; i < net->ct.htable_size; i++) {
+ for (i = 0; i < nf_conntrack_htable_size; i++) {
nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
- if (i < net->ct.htable_size) {
- hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode)
+ if (i < nf_conntrack_htable_size) {
+ hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode)
untimeout(h, timeout);
}
spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
--
2.1.4
^ permalink raw reply related
* [PATCH 24/36] netfilter: conntrack: __nf_ct_l4proto_find() always returns valid pointer
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
Remove unnecessary check for non-nul pointer in destroy_conntrack()
given that __nf_ct_l4proto_find() returns the generic protocol tracker
if the protocol is not supported.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index e3787cf..f72ede1 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -363,7 +363,7 @@ destroy_conntrack(struct nf_conntrack *nfct)
}
rcu_read_lock();
l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
- if (l4proto && l4proto->destroy)
+ if (l4proto->destroy)
l4proto->destroy(ct);
rcu_read_unlock();
--
2.1.4
^ permalink raw reply related
* [PATCH 26/36] netfilter: conntrack: introduce clash resolution on insertion race
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
This patch introduces nf_ct_resolve_clash() to resolve race condition on
conntrack insertions.
This is particularly a problem for connection-less protocols such as
UDP, with no initial handshake. Two or more packets may race to insert
the entry resulting in packet drops.
Another problematic scenario are packets enqueued to userspace via
NFQUEUE after the raw table, that make it easier to trigger this
race.
To resolve this, the idea is to reset the conntrack entry to the one
that won race. Packet and bytes counters are also merged.
The 'insert_failed' stats still accounts for this situation, after
this patch, the drop counter is bumped whenever we drop packets, so we
can watch for unresolved clashes.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_conntrack_l4proto.h | 3 ++
net/netfilter/nf_conntrack_core.c | 53 ++++++++++++++++++++++++++--
net/netfilter/nf_conntrack_proto_udp.c | 2 ++
net/netfilter/nf_conntrack_proto_udplite.c | 2 ++
4 files changed, 57 insertions(+), 3 deletions(-)
diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h
index 956d8a6..1a5fb36 100644
--- a/include/net/netfilter/nf_conntrack_l4proto.h
+++ b/include/net/netfilter/nf_conntrack_l4proto.h
@@ -23,6 +23,9 @@ struct nf_conntrack_l4proto {
/* L4 Protocol number. */
u_int8_t l4proto;
+ /* Resolve clashes on insertion races. */
+ bool allow_clash;
+
/* Try to fill in the third arg: dataoff is offset past network protocol
hdr. Return true if possible. */
bool (*pkt_to_tuple)(const struct sk_buff *skb, unsigned int dataoff,
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 25e0c26..f58a704 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -617,6 +617,48 @@ static inline void nf_ct_acct_update(struct nf_conn *ct,
}
}
+static void nf_ct_acct_merge(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
+ const struct nf_conn *loser_ct)
+{
+ struct nf_conn_acct *acct;
+
+ acct = nf_conn_acct_find(loser_ct);
+ if (acct) {
+ struct nf_conn_counter *counter = acct->counter;
+ enum ip_conntrack_info ctinfo;
+ unsigned int bytes;
+
+ /* u32 should be fine since we must have seen one packet. */
+ bytes = atomic64_read(&counter[CTINFO2DIR(ctinfo)].bytes);
+ nf_ct_acct_update(ct, ctinfo, bytes);
+ }
+}
+
+/* Resolve race on insertion if this protocol allows this. */
+static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb,
+ enum ip_conntrack_info ctinfo,
+ struct nf_conntrack_tuple_hash *h)
+{
+ /* This is the conntrack entry already in hashes that won race. */
+ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
+ struct nf_conntrack_l4proto *l4proto;
+
+ l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
+ if (l4proto->allow_clash &&
+ !nf_ct_is_dying(ct) &&
+ atomic_inc_not_zero(&ct->ct_general.use)) {
+ nf_ct_acct_merge(ct, ctinfo, (struct nf_conn *)skb->nfct);
+ nf_conntrack_put(skb->nfct);
+ /* Assign conntrack already in hashes to this skbuff. Don't
+ * modify skb->nfctinfo to ensure consistent stateful filtering.
+ */
+ skb->nfct = &ct->ct_general;
+ return NF_ACCEPT;
+ }
+ NF_CT_STAT_INC(net, drop);
+ return NF_DROP;
+}
+
/* Confirm a connection given skb; places it in hash table */
int
__nf_conntrack_confirm(struct sk_buff *skb)
@@ -631,6 +673,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
enum ip_conntrack_info ctinfo;
struct net *net;
unsigned int sequence;
+ int ret = NF_DROP;
ct = nf_ct_get(skb, &ctinfo);
net = nf_ct_net(ct);
@@ -673,8 +716,10 @@ __nf_conntrack_confirm(struct sk_buff *skb)
*/
nf_ct_del_from_dying_or_unconfirmed_list(ct);
- if (unlikely(nf_ct_is_dying(ct)))
- goto out;
+ if (unlikely(nf_ct_is_dying(ct))) {
+ nf_ct_add_to_dying_list(ct);
+ goto dying;
+ }
/* See if there's one in the list already, including reverse:
NAT could have grabbed it without realizing, since we're
@@ -725,10 +770,12 @@ __nf_conntrack_confirm(struct sk_buff *skb)
out:
nf_ct_add_to_dying_list(ct);
+ ret = nf_ct_resolve_clash(net, skb, ctinfo, h);
+dying:
nf_conntrack_double_unlock(hash, reply_hash);
NF_CT_STAT_INC(net, insert_failed);
local_bh_enable();
- return NF_DROP;
+ return ret;
}
EXPORT_SYMBOL_GPL(__nf_conntrack_confirm);
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index 478f92f..4fd0405 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -309,6 +309,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 __read_mostly =
.l3proto = PF_INET,
.l4proto = IPPROTO_UDP,
.name = "udp",
+ .allow_clash = true,
.pkt_to_tuple = udp_pkt_to_tuple,
.invert_tuple = udp_invert_tuple,
.print_tuple = udp_print_tuple,
@@ -341,6 +342,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 __read_mostly =
.l3proto = PF_INET6,
.l4proto = IPPROTO_UDP,
.name = "udp",
+ .allow_clash = true,
.pkt_to_tuple = udp_pkt_to_tuple,
.invert_tuple = udp_invert_tuple,
.print_tuple = udp_print_tuple,
diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c
index 1ac8ee1..9d692f5 100644
--- a/net/netfilter/nf_conntrack_proto_udplite.c
+++ b/net/netfilter/nf_conntrack_proto_udplite.c
@@ -274,6 +274,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 __read_mostly =
.l3proto = PF_INET,
.l4proto = IPPROTO_UDPLITE,
.name = "udplite",
+ .allow_clash = true,
.pkt_to_tuple = udplite_pkt_to_tuple,
.invert_tuple = udplite_invert_tuple,
.print_tuple = udplite_print_tuple,
@@ -306,6 +307,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly =
.l3proto = PF_INET6,
.l4proto = IPPROTO_UDPLITE,
.name = "udplite",
+ .allow_clash = true,
.pkt_to_tuple = udplite_pkt_to_tuple,
.invert_tuple = udplite_invert_tuple,
.print_tuple = udplite_print_tuple,
--
2.1.4
^ permalink raw reply related
* [PATCH 27/36] openvswitch: __nf_ct_l{3,4}proto_find() always return a valid pointer
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
If the protocol is not natively supported, this assigns generic protocol
tracker so we can always assume a valid pointer after these calls.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Jarno Rajahalme <jrajahalme@nicira.com>
Acked-by: Joe Stringer <joe@ovn.org>
---
net/openvswitch/conntrack.c | 8 --------
1 file changed, 8 deletions(-)
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 9741a76..9f0bc49 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -439,20 +439,12 @@ ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone,
u8 protonum;
l3proto = __nf_ct_l3proto_find(l3num);
- if (!l3proto) {
- pr_debug("ovs_ct_find_existing: Can't get l3proto\n");
- return NULL;
- }
if (l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff,
&protonum) <= 0) {
pr_debug("ovs_ct_find_existing: Can't get protonum\n");
return NULL;
}
l4proto = __nf_ct_l4proto_find(l3num, protonum);
- if (!l4proto) {
- pr_debug("ovs_ct_find_existing: Can't get l4proto\n");
- return NULL;
- }
if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num,
protonum, net, &tuple, l3proto, l4proto)) {
pr_debug("ovs_ct_find_existing: Can't get tuple\n");
--
2.1.4
^ permalink raw reply related
* [PATCH 29/36] netfilter: nf_tables: allow set names up to 32 bytes
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
Currently, we support set names of up to 16 bytes, get this aligned
with the maximum length we can use in ipset to make it easier when
considering migration to nf_tables.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_tables.h | 2 +-
include/uapi/linux/netfilter/nf_tables.h | 1 +
net/netfilter/nf_tables_api.c | 6 +++---
3 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index f6b1daf..0922354 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -303,7 +303,7 @@ void nft_unregister_set(struct nft_set_ops *ops);
struct nft_set {
struct list_head list;
struct list_head bindings;
- char name[IFNAMSIZ];
+ char name[NFT_SET_MAXNAMELEN];
u32 ktype;
u32 dtype;
u32 size;
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 6602313..6a4dbe0 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -3,6 +3,7 @@
#define NFT_TABLE_MAXNAMELEN 32
#define NFT_CHAIN_MAXNAMELEN 32
+#define NFT_SET_MAXNAMELEN 32
#define NFT_USERDATA_MAXLEN 256
/**
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 73c8fad..4d292b9 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2317,7 +2317,7 @@ nft_select_set_ops(const struct nlattr * const nla[],
static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
[NFTA_SET_TABLE] = { .type = NLA_STRING },
[NFTA_SET_NAME] = { .type = NLA_STRING,
- .len = IFNAMSIZ - 1 },
+ .len = NFT_SET_MAXNAMELEN - 1 },
[NFTA_SET_FLAGS] = { .type = NLA_U32 },
[NFTA_SET_KEY_TYPE] = { .type = NLA_U32 },
[NFTA_SET_KEY_LEN] = { .type = NLA_U32 },
@@ -2401,7 +2401,7 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set,
unsigned long *inuse;
unsigned int n = 0, min = 0;
- p = strnchr(name, IFNAMSIZ, '%');
+ p = strnchr(name, NFT_SET_MAXNAMELEN, '%');
if (p != NULL) {
if (p[1] != 'd' || strchr(p + 2, '%'))
return -EINVAL;
@@ -2696,7 +2696,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
struct nft_table *table;
struct nft_set *set;
struct nft_ctx ctx;
- char name[IFNAMSIZ];
+ char name[NFT_SET_MAXNAMELEN];
unsigned int size;
bool create;
u64 timeout;
--
2.1.4
^ permalink raw reply related
* [PATCH 32/36] netfilter: conntrack: make netns address part of expect hash
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
From: Florian Westphal <fw@strlen.de>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_expect.c | 17 ++++++++++-------
1 file changed, 10 insertions(+), 7 deletions(-)
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index da95d74..130f1be 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -24,6 +24,7 @@
#include <linux/moduleparam.h>
#include <linux/export.h>
#include <net/net_namespace.h>
+#include <net/netns/hash.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
@@ -73,15 +74,17 @@ static void nf_ct_expectation_timed_out(unsigned long ul_expect)
nf_ct_expect_put(exp);
}
-static unsigned int nf_ct_expect_dst_hash(const struct nf_conntrack_tuple *tuple)
+static unsigned int nf_ct_expect_dst_hash(const struct net *n, const struct nf_conntrack_tuple *tuple)
{
- unsigned int hash;
+ unsigned int hash, seed;
get_random_once(&nf_ct_expect_hashrnd, sizeof(nf_ct_expect_hashrnd));
+ seed = nf_ct_expect_hashrnd ^ net_hash_mix(n);
+
hash = jhash2(tuple->dst.u3.all, ARRAY_SIZE(tuple->dst.u3.all),
(((tuple->dst.protonum ^ tuple->src.l3num) << 16) |
- (__force __u16)tuple->dst.u.all) ^ nf_ct_expect_hashrnd);
+ (__force __u16)tuple->dst.u.all) ^ seed);
return reciprocal_scale(hash, nf_ct_expect_hsize);
}
@@ -108,7 +111,7 @@ __nf_ct_expect_find(struct net *net,
if (!net->ct.expect_count)
return NULL;
- h = nf_ct_expect_dst_hash(tuple);
+ h = nf_ct_expect_dst_hash(net, tuple);
hlist_for_each_entry_rcu(i, &net->ct.expect_hash[h], hnode) {
if (nf_ct_exp_equal(tuple, i, zone, net))
return i;
@@ -148,7 +151,7 @@ nf_ct_find_expectation(struct net *net,
if (!net->ct.expect_count)
return NULL;
- h = nf_ct_expect_dst_hash(tuple);
+ h = nf_ct_expect_dst_hash(net, tuple);
hlist_for_each_entry(i, &net->ct.expect_hash[h], hnode) {
if (!(i->flags & NF_CT_EXPECT_INACTIVE) &&
nf_ct_exp_equal(tuple, i, zone, net)) {
@@ -352,7 +355,7 @@ static int nf_ct_expect_insert(struct nf_conntrack_expect *exp)
struct nf_conn_help *master_help = nfct_help(exp->master);
struct nf_conntrack_helper *helper;
struct net *net = nf_ct_exp_net(exp);
- unsigned int h = nf_ct_expect_dst_hash(&exp->tuple);
+ unsigned int h = nf_ct_expect_dst_hash(net, &exp->tuple);
/* two references : one for hash insert, one for the timer */
atomic_add(2, &exp->use);
@@ -411,7 +414,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
ret = -ESHUTDOWN;
goto out;
}
- h = nf_ct_expect_dst_hash(&expect->tuple);
+ h = nf_ct_expect_dst_hash(net, &expect->tuple);
hlist_for_each_entry_safe(i, next, &net->ct.expect_hash[h], hnode) {
if (expect_matches(i, expect)) {
if (del_timer(&i->timeout)) {
--
2.1.4
^ permalink raw reply related
* [PATCH 33/36] netfilter: conntrack: use a single expectation table for all namespaces
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
From: Florian Westphal <fw@strlen.de>
We already include netns address in the hash and compare the netns pointers
during lookup, so even if namespaces have overlapping addresses entries
will be spread across the expectation table.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_conntrack_expect.h | 1 +
include/net/netns/conntrack.h | 1 -
.../netfilter/nf_conntrack_l3proto_ipv4_compat.c | 6 ++--
net/netfilter/nf_conntrack_expect.c | 42 ++++++++++------------
net/netfilter/nf_conntrack_helper.c | 2 +-
net/netfilter/nf_conntrack_netlink.c | 6 ++--
6 files changed, 25 insertions(+), 33 deletions(-)
diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index dce56f0..5ed33ea 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -10,6 +10,7 @@
extern unsigned int nf_ct_expect_hsize;
extern unsigned int nf_ct_expect_max;
+extern struct hlist_head *nf_ct_expect_hash;
struct nf_conntrack_expect {
/* Conntrack expectation list member */
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 251c435..2811ddc 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -94,7 +94,6 @@ struct netns_ct {
int sysctl_checksum;
struct kmem_cache *nf_conntrack_cachep;
- struct hlist_head *expect_hash;
struct ct_pcpu __percpu *pcpu_lists;
struct ip_conntrack_stat __percpu *stat;
struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 2b4c729..c6f3c40 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -236,13 +236,12 @@ struct ct_expect_iter_state {
static struct hlist_node *ct_expect_get_first(struct seq_file *seq)
{
- struct net *net = seq_file_net(seq);
struct ct_expect_iter_state *st = seq->private;
struct hlist_node *n;
for (st->bucket = 0; st->bucket < nf_ct_expect_hsize; st->bucket++) {
n = rcu_dereference(
- hlist_first_rcu(&net->ct.expect_hash[st->bucket]));
+ hlist_first_rcu(&nf_ct_expect_hash[st->bucket]));
if (n)
return n;
}
@@ -252,7 +251,6 @@ static struct hlist_node *ct_expect_get_first(struct seq_file *seq)
static struct hlist_node *ct_expect_get_next(struct seq_file *seq,
struct hlist_node *head)
{
- struct net *net = seq_file_net(seq);
struct ct_expect_iter_state *st = seq->private;
head = rcu_dereference(hlist_next_rcu(head));
@@ -260,7 +258,7 @@ static struct hlist_node *ct_expect_get_next(struct seq_file *seq,
if (++st->bucket >= nf_ct_expect_hsize)
return NULL;
head = rcu_dereference(
- hlist_first_rcu(&net->ct.expect_hash[st->bucket]));
+ hlist_first_rcu(&nf_ct_expect_hash[st->bucket]));
}
return head;
}
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 130f1be..9e36931 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -36,6 +36,9 @@
unsigned int nf_ct_expect_hsize __read_mostly;
EXPORT_SYMBOL_GPL(nf_ct_expect_hsize);
+struct hlist_head *nf_ct_expect_hash __read_mostly;
+EXPORT_SYMBOL_GPL(nf_ct_expect_hash);
+
unsigned int nf_ct_expect_max __read_mostly;
static struct kmem_cache *nf_ct_expect_cachep __read_mostly;
@@ -112,7 +115,7 @@ __nf_ct_expect_find(struct net *net,
return NULL;
h = nf_ct_expect_dst_hash(net, tuple);
- hlist_for_each_entry_rcu(i, &net->ct.expect_hash[h], hnode) {
+ hlist_for_each_entry_rcu(i, &nf_ct_expect_hash[h], hnode) {
if (nf_ct_exp_equal(tuple, i, zone, net))
return i;
}
@@ -152,7 +155,7 @@ nf_ct_find_expectation(struct net *net,
return NULL;
h = nf_ct_expect_dst_hash(net, tuple);
- hlist_for_each_entry(i, &net->ct.expect_hash[h], hnode) {
+ hlist_for_each_entry(i, &nf_ct_expect_hash[h], hnode) {
if (!(i->flags & NF_CT_EXPECT_INACTIVE) &&
nf_ct_exp_equal(tuple, i, zone, net)) {
exp = i;
@@ -363,7 +366,7 @@ static int nf_ct_expect_insert(struct nf_conntrack_expect *exp)
hlist_add_head(&exp->lnode, &master_help->expectations);
master_help->expecting[exp->class]++;
- hlist_add_head_rcu(&exp->hnode, &net->ct.expect_hash[h]);
+ hlist_add_head_rcu(&exp->hnode, &nf_ct_expect_hash[h]);
net->ct.expect_count++;
setup_timer(&exp->timeout, nf_ct_expectation_timed_out,
@@ -415,7 +418,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
goto out;
}
h = nf_ct_expect_dst_hash(net, &expect->tuple);
- hlist_for_each_entry_safe(i, next, &net->ct.expect_hash[h], hnode) {
+ hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) {
if (expect_matches(i, expect)) {
if (del_timer(&i->timeout)) {
nf_ct_unlink_expect(i);
@@ -481,12 +484,11 @@ struct ct_expect_iter_state {
static struct hlist_node *ct_expect_get_first(struct seq_file *seq)
{
- struct net *net = seq_file_net(seq);
struct ct_expect_iter_state *st = seq->private;
struct hlist_node *n;
for (st->bucket = 0; st->bucket < nf_ct_expect_hsize; st->bucket++) {
- n = rcu_dereference(hlist_first_rcu(&net->ct.expect_hash[st->bucket]));
+ n = rcu_dereference(hlist_first_rcu(&nf_ct_expect_hash[st->bucket]));
if (n)
return n;
}
@@ -496,14 +498,13 @@ static struct hlist_node *ct_expect_get_first(struct seq_file *seq)
static struct hlist_node *ct_expect_get_next(struct seq_file *seq,
struct hlist_node *head)
{
- struct net *net = seq_file_net(seq);
struct ct_expect_iter_state *st = seq->private;
head = rcu_dereference(hlist_next_rcu(head));
while (head == NULL) {
if (++st->bucket >= nf_ct_expect_hsize)
return NULL;
- head = rcu_dereference(hlist_first_rcu(&net->ct.expect_hash[st->bucket]));
+ head = rcu_dereference(hlist_first_rcu(&nf_ct_expect_hash[st->bucket]));
}
return head;
}
@@ -636,28 +637,13 @@ module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0400);
int nf_conntrack_expect_pernet_init(struct net *net)
{
- int err = -ENOMEM;
-
net->ct.expect_count = 0;
- net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, 0);
- if (net->ct.expect_hash == NULL)
- goto err1;
-
- err = exp_proc_init(net);
- if (err < 0)
- goto err2;
-
- return 0;
-err2:
- nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize);
-err1:
- return err;
+ return exp_proc_init(net);
}
void nf_conntrack_expect_pernet_fini(struct net *net)
{
exp_proc_remove(net);
- nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize);
}
int nf_conntrack_expect_init(void)
@@ -673,6 +659,13 @@ int nf_conntrack_expect_init(void)
0, 0, NULL);
if (!nf_ct_expect_cachep)
return -ENOMEM;
+
+ nf_ct_expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, 0);
+ if (!nf_ct_expect_hash) {
+ kmem_cache_destroy(nf_ct_expect_cachep);
+ return -ENOMEM;
+ }
+
return 0;
}
@@ -680,4 +673,5 @@ void nf_conntrack_expect_fini(void)
{
rcu_barrier(); /* Wait for call_rcu() before destroy */
kmem_cache_destroy(nf_ct_expect_cachep);
+ nf_ct_free_hashtable(nf_ct_expect_hash, nf_ct_expect_hsize);
}
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index cb48e6a..f703adb 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -400,7 +400,7 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me,
spin_lock_bh(&nf_conntrack_expect_lock);
for (i = 0; i < nf_ct_expect_hsize; i++) {
hlist_for_each_entry_safe(exp, next,
- &net->ct.expect_hash[i], hnode) {
+ &nf_ct_expect_hash[i], hnode) {
struct nf_conn_help *help = nfct_help(exp->master);
if ((rcu_dereference_protected(
help->helper,
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 5dfb84d..a18d1ce 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2632,7 +2632,7 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
last = (struct nf_conntrack_expect *)cb->args[1];
for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) {
restart:
- hlist_for_each_entry(exp, &net->ct.expect_hash[cb->args[0]],
+ hlist_for_each_entry(exp, &nf_ct_expect_hash[cb->args[0]],
hnode) {
if (l3proto && exp->tuple.src.l3num != l3proto)
continue;
@@ -2890,7 +2890,7 @@ static int ctnetlink_del_expect(struct net *net, struct sock *ctnl,
spin_lock_bh(&nf_conntrack_expect_lock);
for (i = 0; i < nf_ct_expect_hsize; i++) {
hlist_for_each_entry_safe(exp, next,
- &net->ct.expect_hash[i],
+ &nf_ct_expect_hash[i],
hnode) {
if (!net_eq(nf_ct_exp_net(exp), net))
@@ -2912,7 +2912,7 @@ static int ctnetlink_del_expect(struct net *net, struct sock *ctnl,
spin_lock_bh(&nf_conntrack_expect_lock);
for (i = 0; i < nf_ct_expect_hsize; i++) {
hlist_for_each_entry_safe(exp, next,
- &net->ct.expect_hash[i],
+ &nf_ct_expect_hash[i],
hnode) {
if (!net_eq(nf_ct_exp_net(exp), net))
--
2.1.4
^ permalink raw reply related
* [PATCH 31/36] netfilter: conntrack: check netns when walking expect hash
From: Pablo Neira Ayuso @ 2016-05-09 18:46 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1462819614-5402-1-git-send-email-pablo@netfilter.org>
From: Florian Westphal <fw@strlen.de>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c | 3 +++
net/netfilter/nf_conntrack_expect.c | 19 +++++++++++++++----
net/netfilter/nf_conntrack_netlink.c | 12 ++++++++++++
3 files changed, 30 insertions(+), 4 deletions(-)
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index f8fc7ab..2b4c729 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -301,6 +301,9 @@ static int exp_seq_show(struct seq_file *s, void *v)
exp = hlist_entry(n, struct nf_conntrack_expect, hnode);
+ if (!net_eq(nf_ct_net(exp->master), seq_file_net(s)))
+ return 0;
+
if (exp->tuple.src.l3num != AF_INET)
return 0;
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index c2f7c4f..da95d74 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -86,6 +86,17 @@ static unsigned int nf_ct_expect_dst_hash(const struct nf_conntrack_tuple *tuple
return reciprocal_scale(hash, nf_ct_expect_hsize);
}
+static bool
+nf_ct_exp_equal(const struct nf_conntrack_tuple *tuple,
+ const struct nf_conntrack_expect *i,
+ const struct nf_conntrack_zone *zone,
+ const struct net *net)
+{
+ return nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) &&
+ net_eq(net, nf_ct_net(i->master)) &&
+ nf_ct_zone_equal_any(i->master, zone);
+}
+
struct nf_conntrack_expect *
__nf_ct_expect_find(struct net *net,
const struct nf_conntrack_zone *zone,
@@ -99,8 +110,7 @@ __nf_ct_expect_find(struct net *net,
h = nf_ct_expect_dst_hash(tuple);
hlist_for_each_entry_rcu(i, &net->ct.expect_hash[h], hnode) {
- if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) &&
- nf_ct_zone_equal_any(i->master, zone))
+ if (nf_ct_exp_equal(tuple, i, zone, net))
return i;
}
return NULL;
@@ -141,8 +151,7 @@ nf_ct_find_expectation(struct net *net,
h = nf_ct_expect_dst_hash(tuple);
hlist_for_each_entry(i, &net->ct.expect_hash[h], hnode) {
if (!(i->flags & NF_CT_EXPECT_INACTIVE) &&
- nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) &&
- nf_ct_zone_equal_any(i->master, zone)) {
+ nf_ct_exp_equal(tuple, i, zone, net)) {
exp = i;
break;
}
@@ -222,6 +231,7 @@ static inline int expect_clash(const struct nf_conntrack_expect *a,
}
return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) &&
+ net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) &&
nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master));
}
@@ -231,6 +241,7 @@ static inline int expect_matches(const struct nf_conntrack_expect *a,
return a->master == b->master && a->class == b->class &&
nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
nf_ct_tuple_mask_equal(&a->mask, &b->mask) &&
+ net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) &&
nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master));
}
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index e00f178..5dfb84d 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2636,6 +2636,10 @@ restart:
hnode) {
if (l3proto && exp->tuple.src.l3num != l3proto)
continue;
+
+ if (!net_eq(nf_ct_net(exp->master), net))
+ continue;
+
if (cb->args[1]) {
if (exp != last)
continue;
@@ -2888,6 +2892,10 @@ static int ctnetlink_del_expect(struct net *net, struct sock *ctnl,
hlist_for_each_entry_safe(exp, next,
&net->ct.expect_hash[i],
hnode) {
+
+ if (!net_eq(nf_ct_exp_net(exp), net))
+ continue;
+
m_help = nfct_help(exp->master);
if (!strcmp(m_help->helper->name, name) &&
del_timer(&exp->timeout)) {
@@ -2906,6 +2914,10 @@ static int ctnetlink_del_expect(struct net *net, struct sock *ctnl,
hlist_for_each_entry_safe(exp, next,
&net->ct.expect_hash[i],
hnode) {
+
+ if (!net_eq(nf_ct_exp_net(exp), net))
+ continue;
+
if (del_timer(&exp->timeout)) {
nf_ct_unlink_expect_report(exp,
NETLINK_CB(skb).portid,
--
2.1.4
^ permalink raw reply related
* Re: [PATCH 1/1] net: thunderx: avoid exposing kernel stack
From: Sunil Kovvuri @ 2016-05-09 18:57 UTC (permalink / raw)
To: Heinrich Schuchardt
Cc: Sunil Goutham, Robert Richter, LAKML, Linux Netdev List, LKML
In-Reply-To: <1462747578-6147-1-git-send-email-xypron.glpk@gmx.de>
Thanks for fixing, changes look okay.
Sunil.
On Sun, May 8, 2016 at 3:46 PM, Heinrich Schuchardt <xypron.glpk@gmx.de> wrote:
> Reserved fields should be set to zero to avoid exposing
> bits from the kernel stack.
>
> Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
> ---
> drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 4 ++++
> 1 file changed, 4 insertions(+)
>
> diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
> index 8acd7c0..0ff8e60 100644
> --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
> +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
> @@ -533,6 +533,7 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs,
> nicvf_config_vlan_stripping(nic, nic->netdev->features);
>
> /* Enable Receive queue */
> + memset(&rq_cfg, 0, sizeof(struct rq_cfg));
> rq_cfg.ena = 1;
> rq_cfg.tcp_ena = 0;
> nicvf_queue_reg_write(nic, NIC_QSET_RQ_0_7_CFG, qidx, *(u64 *)&rq_cfg);
> @@ -565,6 +566,7 @@ void nicvf_cmp_queue_config(struct nicvf *nic, struct queue_set *qs,
> qidx, (u64)(cq->dmem.phys_base));
>
> /* Enable Completion queue */
> + memset(&cq_cfg, 0, sizeof(struct cq_cfg));
> cq_cfg.ena = 1;
> cq_cfg.reset = 0;
> cq_cfg.caching = 0;
> @@ -613,6 +615,7 @@ static void nicvf_snd_queue_config(struct nicvf *nic, struct queue_set *qs,
> qidx, (u64)(sq->dmem.phys_base));
>
> /* Enable send queue & set queue size */
> + memset(&sq_cfg, 0, sizeof(struct sq_cfg));
> sq_cfg.ena = 1;
> sq_cfg.reset = 0;
> sq_cfg.ldwb = 0;
> @@ -649,6 +652,7 @@ static void nicvf_rbdr_config(struct nicvf *nic, struct queue_set *qs,
>
> /* Enable RBDR & set queue size */
> /* Buffer size should be in multiples of 128 bytes */
> + memset(&rbdr_cfg, 0, sizeof(struct rbdr_cfg));
> rbdr_cfg.ena = 1;
> rbdr_cfg.reset = 0;
> rbdr_cfg.ldwb = 0;
> --
> 2.1.4
>
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox