Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

11 files changed, 109 insertions, 155 deletions

diff --git a/include/linux/netfilter_bridge/ebt_log.h b/include/linux/netfilter_bridge/ebt_log.h
index 358fbc84fb59..96e231ae7554 100644
--- a/include/linux/netfilter_bridge/ebt_log.h
+++ b/include/linux/netfilter_bridge/ebt_log.h
@@ -3,6 +3,7 @@
 
 #define EBT_LOG_IP 0x01 /* if the frame is made by ip, log the ip information */
 #define EBT_LOG_ARP 0x02
+#define EBT_LOG_NFLOG 0x04
 #define EBT_LOG_MASK (EBT_LOG_IP | EBT_LOG_ARP)
 #define EBT_LOG_PREFIX_SIZE 30
 #define EBT_LOG_WATCHER "log"
diff --git a/include/linux/netfilter_ipv4/ipt_LOG.h b/include/linux/netfilter_ipv4/ipt_LOG.h
index 22d16177319b..892f9a33fea8 100644
--- a/include/linux/netfilter_ipv4/ipt_LOG.h
+++ b/include/linux/netfilter_ipv4/ipt_LOG.h
@@ -6,7 +6,8 @@
 #define IPT_LOG_TCPOPT          0x02    /* Log TCP options */
 #define IPT_LOG_IPOPT           0x04    /* Log IP options */
 #define IPT_LOG_UID             0x08    /* Log UID owning local socket */
-#define IPT_LOG_MASK            0x0f
+#define IPT_LOG_NFLOG           0x10    /* Log using nf_log backend */
+#define IPT_LOG_MASK            0x1f
 
 struct ipt_log_info {
         unsigned char level;
diff --git a/include/linux/netfilter_ipv6/ip6t_LOG.h b/include/linux/netfilter_ipv6/ip6t_LOG.h
index 9008ff5c40ae..060c1a1c6c60 100644
--- a/include/linux/netfilter_ipv6/ip6t_LOG.h
+++ b/include/linux/netfilter_ipv6/ip6t_LOG.h
@@ -6,7 +6,8 @@
 #define IP6T_LOG_TCPOPT         0x02    /* Log TCP options */
 #define IP6T_LOG_IPOPT          0x04    /* Log IP options */
 #define IP6T_LOG_UID            0x08    /* Log UID owning local socket */
-#define IP6T_LOG_MASK           0x0f
+#define IP6T_LOG_NFLOG          0x10    /* Log using nf_log backend */
+#define IP6T_LOG_MASK           0x1f
 
 struct ip6t_log_info {
         unsigned char level;
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 004e645f3e18..8d362c49b8a9 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -233,7 +233,6 @@ struct xfrm_type
         int                     (*init_state)(struct xfrm_state *x);
         void                    (*destructor)(struct xfrm_state *);
         int                     (*input)(struct xfrm_state *, struct xfrm_decap_state *, struct sk_buff *skb);
-        int                     (*post_input)(struct xfrm_state *, struct xfrm_decap_state *, struct sk_buff *skb);
         int                     (*output)(struct xfrm_state *, struct sk_buff *pskb);
         /* Estimate maximal size of result of transformation of a dgram */
         u32                     (*get_max_size)(struct xfrm_state *, int size);
diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c
index 0128fbbe2328..288ff1d4ccc4 100644
--- a/net/bridge/netfilter/ebt_log.c
+++ b/net/bridge/netfilter/ebt_log.c
@@ -166,7 +166,12 @@ static void ebt_log(const struct sk_buff *skb, unsigned int hooknr,
         li.u.log.level = info->loglevel;
         li.u.log.logflags = info->bitmask;
 
-        nf_log_packet(PF_BRIDGE, hooknr, skb, in, out, &li, info->prefix);
+        if (info->bitmask & EBT_LOG_NFLOG)
+                nf_log_packet(PF_BRIDGE, hooknr, skb, in, out, &li,
+                              info->prefix);
+        else
+                ebt_log_packet(PF_BRIDGE, hooknr, skb, in, out, &li,
+                               info->prefix);
 }
 
 static struct ebt_watcher log =
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index b8203de5ff07..98f0fc923f91 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -52,7 +52,6 @@ int reqsk_queue_alloc(struct request_sock_queue *queue,
         get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd));
         rwlock_init(&queue->syn_wait_lock);
         queue->rskq_accept_head = queue->rskq_accept_head = NULL;
-        queue->rskq_defer_accept = 0;
         lopt->nr_table_entries = nr_table_entries;
 
         write_lock_bh(&queue->syn_wait_lock);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 73bfcae8af9c..09590f356086 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -12,13 +12,6 @@
 #include <net/protocol.h>
 #include <net/udp.h>
 
-/* decapsulation data for use when post-processing */
-struct esp_decap_data {
-        xfrm_address_t  saddr;
-        __u16           sport;
-        __u8            proto;
-};
-
 static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 {
         int err;
@@ -150,6 +143,10 @@ static int esp_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struc
         int elen = skb->len - sizeof(struct ip_esp_hdr) - esp->conf.ivlen - alen;
         int nfrags;
         int encap_len = 0;
+        u8 nexthdr[2];
+        struct scatterlist *sg;
+        u8 workbuf[60];
+        int padlen;
 
         if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr)))
                 goto out;
@@ -185,122 +182,82 @@ static int esp_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struc
         if (esp->conf.ivlen)
                 crypto_cipher_set_iv(esp->conf.tfm, esph->enc_data, crypto_tfm_alg_ivsize(esp->conf.tfm));
 
-        {
-                u8 nexthdr[2];
-                struct scatterlist *sg = &esp->sgbuf[0];
-                u8 workbuf[60];
-                int padlen;
-
-                if (unlikely(nfrags > ESP_NUM_FAST_SG)) {
-                        sg = kmalloc(sizeof(struct scatterlist)*nfrags, GFP_ATOMIC);
-                        if (!sg)
-                                goto out;
-                }
-                skb_to_sgvec(skb, sg, sizeof(struct ip_esp_hdr) + esp->conf.ivlen, elen);
-                crypto_cipher_decrypt(esp->conf.tfm, sg, sg, elen);
-                if (unlikely(sg != &esp->sgbuf[0]))
-                        kfree(sg);
-
-                if (skb_copy_bits(skb, skb->len-alen-2, nexthdr, 2))
-                        BUG();
+        sg = &esp->sgbuf[0];
 
-                padlen = nexthdr[0];
-                if (padlen+2 >= elen)
+        if (unlikely(nfrags > ESP_NUM_FAST_SG)) {
+                sg = kmalloc(sizeof(struct scatterlist)*nfrags, GFP_ATOMIC);
+                if (!sg)
                         goto out;
-
-                /* ... check padding bits here. Silly. :-) */ 
-
-                if (x->encap && decap && decap->decap_type) {
-                        struct esp_decap_data *encap_data;
-                        struct udphdr *uh = (struct udphdr *) (iph+1);
-
-                        encap_data = (struct esp_decap_data *) (decap->decap_data);
-                        encap_data->proto = 0;
-
-                        switch (decap->decap_type) {
-                        case UDP_ENCAP_ESPINUDP:
-                        case UDP_ENCAP_ESPINUDP_NON_IKE:
-                                encap_data->proto = AF_INET;
-                                encap_data->saddr.a4 = iph->saddr;
-                                encap_data->sport = uh->source;
-                                encap_len = (void*)esph - (void*)uh;
-                                break;
-
-                        default:
-                                goto out;
-                        }
-                }
-
-                iph->protocol = nexthdr[1];
-                pskb_trim(skb, skb->len - alen - padlen - 2);
-                memcpy(workbuf, skb->nh.raw, iph->ihl*4);
-                skb->h.raw = skb_pull(skb, sizeof(struct ip_esp_hdr) + esp->conf.ivlen);
-                skb->nh.raw += encap_len + sizeof(struct ip_esp_hdr) + esp->conf.ivlen;
-                memcpy(skb->nh.raw, workbuf, iph->ihl*4);
-                skb->nh.iph->tot_len = htons(skb->len);
         }
+        skb_to_sgvec(skb, sg, sizeof(struct ip_esp_hdr) + esp->conf.ivlen, elen);
+        crypto_cipher_decrypt(esp->conf.tfm, sg, sg, elen);
+        if (unlikely(sg != &esp->sgbuf[0]))
+                kfree(sg);
 
-        return 0;
+        if (skb_copy_bits(skb, skb->len-alen-2, nexthdr, 2))
+                BUG();
 
-out:
-        return -EINVAL;
-}
+        padlen = nexthdr[0];
+        if (padlen+2 >= elen)
+                goto out;
 
-static int esp_post_input(struct xfrm_state *x, struct xfrm_decap_state *decap, struct sk_buff *skb)
-{
-  
-        if (x->encap) {
-                struct xfrm_encap_tmpl *encap;
-                struct esp_decap_data *decap_data;
+        /* ... check padding bits here. Silly. :-) */ 
 
-                encap = x->encap;
-                decap_data = (struct esp_decap_data *)(decap->decap_data);
+        if (x->encap) {
+                struct xfrm_encap_tmpl *encap = x->encap;
+                struct udphdr *uh;
 
-                /* first, make sure that the decap type == the encap type */
                 if (encap->encap_type != decap->decap_type)
-                        return -EINVAL;
+                        goto out;
 
-                switch (encap->encap_type) {
-                default:
-                case UDP_ENCAP_ESPINUDP:
-                case UDP_ENCAP_ESPINUDP_NON_IKE:
-                        /*
-                         * 1) if the NAT-T peer's IP or port changed then
-                         *    advertize the change to the keying daemon.
-                         *    This is an inbound SA, so just compare
-                         *    SRC ports.
-                         */
-                        if (decap_data->proto == AF_INET &&
-                            (decap_data->saddr.a4 != x->props.saddr.a4 ||
-                             decap_data->sport != encap->encap_sport)) {
-                                xfrm_address_t ipaddr;
-
-                                ipaddr.a4 = decap_data->saddr.a4;
-                                km_new_mapping(x, &ipaddr, decap_data->sport);
-                                        
-                                /* XXX: perhaps add an extra
-                                 * policy check here, to see
-                                 * if we should allow or
-                                 * reject a packet from a
-                                 * different source
-                                 * address/port.
-                                 */
-                        }
-                
-                        /*
-                         * 2) ignore UDP/TCP checksums in case
-                         *    of NAT-T in Transport Mode, or
-                         *    perform other post-processing fixes
-                         *    as per * draft-ietf-ipsec-udp-encaps-06,
-                         *    section 3.1.2
+                uh = (struct udphdr *)(iph + 1);
+                encap_len = (void*)esph - (void*)uh;
+
+                /*
+                 * 1) if the NAT-T peer's IP or port changed then
+                 *    advertize the change to the keying daemon.
+                 *    This is an inbound SA, so just compare
+                 *    SRC ports.
+                 */
+                if (iph->saddr != x->props.saddr.a4 ||
+                    uh->source != encap->encap_sport) {
+                        xfrm_address_t ipaddr;
+
+                        ipaddr.a4 = iph->saddr;
+                        km_new_mapping(x, &ipaddr, uh->source);
+                                
+                        /* XXX: perhaps add an extra
+                         * policy check here, to see
+                         * if we should allow or
+                         * reject a packet from a
+                         * different source
+                         * address/port.
                          */
-                        if (!x->props.mode)
-                                skb->ip_summed = CHECKSUM_UNNECESSARY;
-
-                        break;
                 }
+        
+                /*
+                 * 2) ignore UDP/TCP checksums in case
+                 *    of NAT-T in Transport Mode, or
+                 *    perform other post-processing fixes
+                 *    as per draft-ietf-ipsec-udp-encaps-06,
+                 *    section 3.1.2
+                 */
+                if (!x->props.mode)
+                        skb->ip_summed = CHECKSUM_UNNECESSARY;
         }
+
+        iph->protocol = nexthdr[1];
+        pskb_trim(skb, skb->len - alen - padlen - 2);
+        memcpy(workbuf, skb->nh.raw, iph->ihl*4);
+        skb->h.raw = skb_pull(skb, sizeof(struct ip_esp_hdr) + esp->conf.ivlen);
+        skb->nh.raw += encap_len + sizeof(struct ip_esp_hdr) + esp->conf.ivlen;
+        memcpy(skb->nh.raw, workbuf, iph->ihl*4);
+        skb->nh.iph->tot_len = htons(skb->len);
+
         return 0;
+
+out:
+        return -EINVAL;
 }
 
 static u32 esp4_get_max_size(struct xfrm_state *x, int mtu)
@@ -458,7 +415,6 @@ static struct xfrm_type esp_type =
         .destructor     = esp_destroy,
         .get_max_size   = esp4_get_max_size,
         .input          = esp_input,
-        .post_input     = esp_post_input,
         .output         = esp_output
 };
 
@@ -470,15 +426,6 @@ static struct net_protocol esp4_protocol = {
 
 static int __init esp4_init(void)
 {
-        struct xfrm_decap_state decap;
-
-        if (sizeof(struct esp_decap_data)  >
-            sizeof(decap.decap_data)) {
-                extern void decap_data_too_small(void);
-
-                decap_data_too_small();
-        }
-
         if (xfrm_register_type(&esp_type, AF_INET) < 0) {
                 printk(KERN_INFO "ip esp init: can't add xfrm type\n");
                 return -EAGAIN;
diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c
index 6606ddb66a29..cc27545ff97f 100644
--- a/net/ipv4/netfilter/ipt_LOG.c
+++ b/net/ipv4/netfilter/ipt_LOG.c
@@ -425,7 +425,12 @@ ipt_log_target(struct sk_buff **pskb,
         li.u.log.level = loginfo->level;
         li.u.log.logflags = loginfo->logflags;
 
-        nf_log_packet(PF_INET, hooknum, *pskb, in, out, &li, loginfo->prefix);
+        if (loginfo->logflags & IPT_LOG_NFLOG)
+                nf_log_packet(PF_INET, hooknum, *pskb, in, out, &li,
+                              loginfo->prefix);
+        else
+                ipt_log_packet(PF_INET, hooknum, *pskb, in, out, &li,
+                               loginfo->prefix);
 
         return IPT_CONTINUE;
 }
diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c
index 77c725832dec..6b930efa9fb9 100644
--- a/net/ipv6/netfilter/ip6t_LOG.c
+++ b/net/ipv6/netfilter/ip6t_LOG.c
@@ -436,7 +436,12 @@ ip6t_log_target(struct sk_buff **pskb,
         li.u.log.level = loginfo->level;
         li.u.log.logflags = loginfo->logflags;
 
-        nf_log_packet(PF_INET6, hooknum, *pskb, in, out, &li, loginfo->prefix);
+        if (loginfo->logflags & IP6T_LOG_NFLOG)
+                nf_log_packet(PF_INET6, hooknum, *pskb, in, out, &li,
+                              loginfo->prefix);
+        else
+                ip6t_log_packet(PF_INET6, hooknum, *pskb, in, out, &li,
+                                loginfo->prefix);
 
         return IP6T_CONTINUE;
 }
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index d3a4f30a7f22..d9f0d7ef103b 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -6,6 +6,7 @@
 #include <linux/skbuff.h>
 #include <linux/netfilter.h>
 #include <linux/seq_file.h>
+#include <linux/rcupdate.h>
 #include <net/protocol.h>
 
 #include "nf_internals.h"
@@ -16,7 +17,7 @@
  * for queueing and must reinject all packets it receives, no matter what.
  */
 static struct nf_queue_handler *queue_handler[NPROTO];
-static struct nf_queue_rerouter *queue_rerouter;
+static struct nf_queue_rerouter *queue_rerouter[NPROTO];
 
 static DEFINE_RWLOCK(queue_handler_lock);
 
@@ -64,7 +65,7 @@ int nf_register_queue_rerouter(int pf, struct nf_queue_rerouter *rer)
                 return -EINVAL;
 
         write_lock_bh(&queue_handler_lock);
-        memcpy(&queue_rerouter[pf], rer, sizeof(queue_rerouter[pf]));
+        rcu_assign_pointer(queue_rerouter[pf], rer);
         write_unlock_bh(&queue_handler_lock);
 
         return 0;
@@ -77,8 +78,9 @@ int nf_unregister_queue_rerouter(int pf)
                 return -EINVAL;
 
         write_lock_bh(&queue_handler_lock);
-        memset(&queue_rerouter[pf], 0, sizeof(queue_rerouter[pf]));
+        rcu_assign_pointer(queue_rerouter[pf], NULL);
         write_unlock_bh(&queue_handler_lock);
+        synchronize_rcu();
         return 0;
 }
 EXPORT_SYMBOL_GPL(nf_unregister_queue_rerouter);
@@ -114,16 +116,17 @@ int nf_queue(struct sk_buff **skb,
         struct net_device *physindev = NULL;
         struct net_device *physoutdev = NULL;
 #endif
+        struct nf_queue_rerouter *rerouter;
 
         /* QUEUE == DROP if noone is waiting, to be safe. */
         read_lock(&queue_handler_lock);
-        if (!queue_handler[pf] || !queue_handler[pf]->outfn) {
+        if (!queue_handler[pf]) {
                 read_unlock(&queue_handler_lock);
                 kfree_skb(*skb);
                 return 1;
         }
 
-        info = kmalloc(sizeof(*info)+queue_rerouter[pf].rer_size, GFP_ATOMIC);
+        info = kmalloc(sizeof(*info)+queue_rerouter[pf]->rer_size, GFP_ATOMIC);
         if (!info) {
                 if (net_ratelimit())
                         printk(KERN_ERR "OOM queueing packet %p\n",
@@ -155,15 +158,13 @@ int nf_queue(struct sk_buff **skb,
                 if (physoutdev) dev_hold(physoutdev);
         }
 #endif
-        if (queue_rerouter[pf].save)
-                queue_rerouter[pf].save(*skb, info);
+        rerouter = rcu_dereference(queue_rerouter[pf]);
+        if (rerouter)
+                rerouter->save(*skb, info);
 
         status = queue_handler[pf]->outfn(*skb, info, queuenum,
                                           queue_handler[pf]->data);
 
-        if (status >= 0 && queue_rerouter[pf].reroute)
-                status = queue_rerouter[pf].reroute(skb, info);
-
         read_unlock(&queue_handler_lock);
 
         if (status < 0) {
@@ -189,6 +190,7 @@ void nf_reinject(struct sk_buff *skb, struct nf_info *info,
 {
         struct list_head *elem = &info->elem->list;
         struct list_head *i;
+        struct nf_queue_rerouter *rerouter;
 
         rcu_read_lock();
 
@@ -212,7 +214,7 @@ void nf_reinject(struct sk_buff *skb, struct nf_info *info,
                         break;
         }
   
-        if (elem == &nf_hooks[info->pf][info->hook]) {
+        if (i == &nf_hooks[info->pf][info->hook]) {
                 /* The module which sent it to userspace is gone. */
                 NFDEBUG("%s: module disappeared, dropping packet.\n",
                         __FUNCTION__);
@@ -226,6 +228,12 @@ void nf_reinject(struct sk_buff *skb, struct nf_info *info,
         }
 
         if (verdict == NF_ACCEPT) {
+                rerouter = rcu_dereference(queue_rerouter[info->pf]);
+                if (rerouter && rerouter->reroute(&skb, info) < 0)
+                        verdict = NF_DROP;
+        }
+
+        if (verdict == NF_ACCEPT) {
         next_hook:
                 verdict = nf_iterate(&nf_hooks[info->pf][info->hook],
                                      &skb, info->hook, 
@@ -322,22 +330,12 @@ int __init netfilter_queue_init(void)
 {
 #ifdef CONFIG_PROC_FS
         struct proc_dir_entry *pde;
-#endif
-        queue_rerouter = kmalloc(NPROTO * sizeof(struct nf_queue_rerouter),
-                                 GFP_KERNEL);
-        if (!queue_rerouter)
-                return -ENOMEM;
 
-#ifdef CONFIG_PROC_FS
         pde = create_proc_entry("nf_queue", S_IRUGO, proc_net_netfilter);
-        if (!pde) {
-                kfree(queue_rerouter);
+        if (!pde)
                 return -1;
-        }
         pde->proc_fops = &nfqueue_file_ops;
 #endif
-        memset(queue_rerouter, 0, NPROTO * sizeof(struct nf_queue_rerouter));
-
         return 0;
 }
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 8206025d8e46..ae62054a9fc4 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -996,13 +996,6 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
                         struct sec_decap_state *xvec = &(skb->sp->x[i]);
                         if (!xfrm_selector_match(&xvec->xvec->sel, &fl, family))
                                 return 0;
-
-                        /* If there is a post_input processor, try running it */
-                        if (xvec->xvec->type->post_input &&
-                            (xvec->xvec->type->post_input)(xvec->xvec,
-                                                           &(xvec->decap),
-                                                           skb) != 0)
-                                return 0;
                 }
         }