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

* 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: (24 commits)
  [IPSEC]: Add xfrm_sysctl.txt.
  [BRIDGE]: Round off STP perodic timers.
  [BRIDGE]: Reduce frequency of forwarding cleanup timer in bridge.
  [TCP] tcp_probe: use GCC printf attribute
  [TCP] tcp_probe: a trivial fix for mismatched number of printl arguments.
  [IPV6] ADDRCONF: Fix conflicts in DEVCONF_xxx constant.
  [NET] napi: Call __netif_rx_complete in netif_rx_complete
  [TCP]: Consolidate checking for tcp orphan count being too big.
  [SOCK]: Shrink struct sock by 8 bytes on 64-bit.
  [AF_PACKET]: Kill CONFIG_PACKET_SOCKET.
  [IPV6]: Fix build warning.
  [AF_PACKET]: Kill bogus CONFIG_PACKET_MULTICAST
  [IPV4]: Kill references to bogus non-existent CONFIG_IP_NOSIOCRT
  [IPSEC]: Fix panic when using inter address familiy IPsec on loopback.
  [NET]: parse ip:port strings correctly in in4_pton
  [IPV6] ROUTE: No longer handle ::/0 specially.
  [IPSEC]: Fix IPv6 AH calculation in outbound
  [XFRM]: xfrm_larval_drop sysctl should be __read_mostly.
  [XFRM]: Allow XFRM_ACQ_EXPIRES to be tunable via sysctl.
  [CASSINI]: Fix printk message typo.
  ...

diff --git a/Documentation/networking/xfrm_sysctl.txt b/Documentation/networking/xfrm_sysctl.txt
new file mode 100644 (file)
index 0000000..5bbd167
--- /dev/null
+++ b/Documentation/networking/xfrm_sysctl.txt
@@ -0,0 +1,4 @@
+/proc/sys/net/core/xfrm_* Variables:
+
+xfrm_acq_expires - INTEGER
+       default 30 - hard timeout in seconds for acquire requests

diff --git a/drivers/net/cassini.c b/drivers/net/cassini.c
index 9fe3a38..59b9943 100644 (file)
--- a/drivers/net/cassini.c
+++ b/drivers/net/cassini.c
@@ -4920,7 +4920,7 @@ static int __devinit cas_init_one(struct pci_dev *pdev,
        pci_cmd |= PCI_COMMAND_PARITY;
        pci_write_config_word(pdev, PCI_COMMAND, pci_cmd);
        if (pci_set_mwi(pdev))
-               printk(KERN_WARNING PFX "Could enable MWI for %s\n",
+               printk(KERN_WARNING PFX "Could not enable MWI for %s\n",
                       pci_name(pdev));
 
        /*

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 09ea01a..648bd1f 100644 (file)
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -209,9 +209,8 @@ enum {
        DEVCONF_RTR_PROBE_INTERVAL,
        DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN,
        DEVCONF_PROXY_NDP,
-       __DEVCONF_OPTIMISTIC_DAD,
-       DEVCONF_ACCEPT_SOURCE_ROUTE,
        DEVCONF_OPTIMISTIC_DAD,
+       DEVCONF_ACCEPT_SOURCE_ROUTE,
        DEVCONF_MAX
 };
 

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f671cd2..3a70f55 100644 (file)
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -910,6 +910,17 @@ static inline int netif_rx_reschedule(struct net_device *dev, int undo)
        return 0;
 }
 
+/* same as netif_rx_complete, except that local_irq_save(flags)
+ * has already been issued
+ */
+static inline void __netif_rx_complete(struct net_device *dev)
+{
+       BUG_ON(!test_bit(__LINK_STATE_RX_SCHED, &dev->state));
+       list_del(&dev->poll_list);
+       smp_mb__before_clear_bit();
+       clear_bit(__LINK_STATE_RX_SCHED, &dev->state);
+}
+
 /* Remove interface from poll list: it must be in the poll list
  * on current cpu. This primitive is called by dev->poll(), when
  * it completes the work. The device cannot be out of poll list at this
@@ -920,10 +931,7 @@ static inline void netif_rx_complete(struct net_device *dev)
        unsigned long flags;
 
        local_irq_save(flags);
-       BUG_ON(!test_bit(__LINK_STATE_RX_SCHED, &dev->state));
-       list_del(&dev->poll_list);
-       smp_mb__before_clear_bit();
-       clear_bit(__LINK_STATE_RX_SCHED, &dev->state);
+       __netif_rx_complete(dev);
        local_irq_restore(flags);
 }
 
@@ -940,17 +948,6 @@ static inline void netif_poll_enable(struct net_device *dev)
        clear_bit(__LINK_STATE_RX_SCHED, &dev->state);
 }
 
-/* same as netif_rx_complete, except that local_irq_save(flags)
- * has already been issued
- */
-static inline void __netif_rx_complete(struct net_device *dev)
-{
-       BUG_ON(!test_bit(__LINK_STATE_RX_SCHED, &dev->state));
-       list_del(&dev->poll_list);
-       smp_mb__before_clear_bit();
-       clear_bit(__LINK_STATE_RX_SCHED, &dev->state);
-}
-
 static inline void netif_tx_lock(struct net_device *dev)
 {
        spin_lock(&dev->_xmit_lock);

diff --git a/include/net/sock.h b/include/net/sock.h
index 689b886..dfeb8b1 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -218,13 +218,13 @@ struct sock {
        atomic_t                sk_rmem_alloc;
        atomic_t                sk_wmem_alloc;
        atomic_t                sk_omem_alloc;
+       int                     sk_sndbuf;
        struct sk_buff_head     sk_receive_queue;
        struct sk_buff_head     sk_write_queue;
        struct sk_buff_head     sk_async_wait_queue;
        int                     sk_wmem_queued;
        int                     sk_forward_alloc;
        gfp_t                   sk_allocation;
-       int                     sk_sndbuf;
        int                     sk_route_caps;
        int                     sk_gso_type;
        int                     sk_rcvlowat;

diff --git a/include/net/tcp.h b/include/net/tcp.h
index e22b4f0..a8af9ae 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -254,6 +254,12 @@ static inline int between(__u32 seq1, __u32 seq2, __u32 seq3)
        return seq3 - seq2 >= seq1 - seq2;
 }
 
+static inline int tcp_too_many_orphans(struct sock *sk, int num)
+{
+       return (num > sysctl_tcp_max_orphans) ||
+               (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
+                atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2]);
+}
 
 extern struct proto tcp_prot;
 

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 39ef925..90185e8 100644 (file)
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -237,7 +237,6 @@ extern int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo);
 extern int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo);
 extern void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c);
 extern void km_state_notify(struct xfrm_state *x, struct km_event *c);
-#define XFRM_ACQ_EXPIRES       30
 
 struct xfrm_tmpl;
 extern int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol);

diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 91b0170..3fc6972 100644 (file)
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -121,6 +121,7 @@ void br_fdb_cleanup(unsigned long _data)
 {
        struct net_bridge *br = (struct net_bridge *)_data;
        unsigned long delay = hold_time(br);
+       unsigned long next_timer = jiffies + br->forward_delay;
        int i;
 
        spin_lock_bh(&br->hash_lock);
@@ -129,14 +130,21 @@ void br_fdb_cleanup(unsigned long _data)
                struct hlist_node *h, *n;
 
                hlist_for_each_entry_safe(f, h, n, &br->hash[i], hlist) {
-                       if (!f->is_static &&
-                           time_before_eq(f->ageing_timer + delay, jiffies))
+                       unsigned long this_timer;
+                       if (f->is_static)
+                               continue;
+                       this_timer = f->ageing_timer + delay;
+                       if (time_before_eq(this_timer, jiffies))
                                fdb_delete(f);
+                       else if (this_timer < next_timer)
+                               next_timer = this_timer;
                }
        }
        spin_unlock_bh(&br->hash_lock);
 
-       mod_timer(&br->gc_timer, jiffies + HZ/10);
+       /* Add HZ/4 to ensure we round the jiffies upwards to be after the next
+        * timer, otherwise we might round down and will have no-op run. */
+       mod_timer(&br->gc_timer, round_jiffies(next_timer + HZ/4));
 }
 
 /* Completely flush all dynamic entries in forwarding database.*/

diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 0e035d6..e38034a 100644 (file)
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -178,7 +178,8 @@ void br_transmit_config(struct net_bridge_port *p)
                br_send_config_bpdu(p, &bpdu);
                p->topology_change_ack = 0;
                p->config_pending = 0;
-               mod_timer(&p->hold_timer, jiffies + BR_HOLD_TIME);
+               mod_timer(&p->hold_timer,
+                         round_jiffies(jiffies + BR_HOLD_TIME));
        }
 }
 

diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c
index 24e0ca4..77f5255 100644 (file)
--- a/net/bridge/br_stp_timer.c
+++ b/net/bridge/br_stp_timer.c
@@ -42,7 +42,7 @@ static void br_hello_timer_expired(unsigned long arg)
        if (br->dev->flags & IFF_UP) {
                br_config_bpdu_generation(br);
 
-               mod_timer(&br->hello_timer, jiffies + br->hello_time);
+               mod_timer(&br->hello_timer, round_jiffies(jiffies + br->hello_time));
        }
        spin_unlock(&br->lock);
 }

diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index f34aca0..6d5ea97 100644 (file)
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -25,6 +25,7 @@ extern int sysctl_core_destroy_delay;
 extern u32 sysctl_xfrm_aevent_etime;
 extern u32 sysctl_xfrm_aevent_rseqth;
 extern int sysctl_xfrm_larval_drop;
+extern u32 sysctl_xfrm_acq_expires;
 #endif
 
 ctl_table core_table[] = {
@@ -127,6 +128,14 @@ ctl_table core_table[] = {
                .mode           = 0644,
                .proc_handler   = &proc_dointvec
        },
+       {
+               .ctl_name       = CTL_UNNUMBERED,
+               .procname       = "xfrm_acq_expires",
+               .data           = &sysctl_xfrm_acq_expires,
+               .maxlen         = sizeof(int),
+               .mode           = 0644,
+               .proc_handler   = &proc_dointvec
+       },
 #endif /* CONFIG_XFRM */
 #endif /* CONFIG_NET */
        {

diff --git a/net/core/utils.c b/net/core/utils.c
index adecfd2..2030bb8 100644 (file)
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -139,16 +139,16 @@ int in4_pton(const char *src, int srclen,
        while(1) {
                int c;
                c = xdigit2bin(srclen > 0 ? *s : '\0', delim);
-               if (!(c & (IN6PTON_DIGIT | IN6PTON_DOT | IN6PTON_DELIM))) {
+               if (!(c & (IN6PTON_DIGIT | IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK))) {
                        goto out;
                }
-               if (c & (IN6PTON_DOT | IN6PTON_DELIM)) {
+               if (c & (IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK)) {
                        if (w == 0)
                                goto out;
                        *d++ = w & 0xff;
                        w = 0;
                        i++;
-                       if (c & IN6PTON_DELIM) {
+                       if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) {
                                if (i != 4)
                                        goto out;
                                break;

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 837f295..9ad1f62 100644 (file)
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -250,8 +250,6 @@ e_inval:
        return -EINVAL;
 }
 
-#ifndef CONFIG_IP_NOSIOCRT
-
 static inline __be32 sk_extract_addr(struct sockaddr *addr)
 {
        return ((struct sockaddr_in *) addr)->sin_addr.s_addr;
@@ -443,15 +441,6 @@ int ip_rt_ioctl(unsigned int cmd, void __user *arg)
        return -EINVAL;
 }
 
-#else
-
-int ip_rt_ioctl(unsigned int cmd, void *arg)
-{
-       return -EINVAL;
-}
-
-#endif
-
 struct nla_policy rtm_ipv4_policy[RTA_MAX+1] __read_mostly = {
        [RTA_DST]               = { .type = NLA_U32 },
        [RTA_SRC]               = { .type = NLA_U32 },

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bd4c295..7663145 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1674,9 +1674,8 @@ adjudge_to_death:
        }
        if (sk->sk_state != TCP_CLOSE) {
                sk_stream_mem_reclaim(sk);
-               if (atomic_read(sk->sk_prot->orphan_count) > sysctl_tcp_max_orphans ||
-                   (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
-                    atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2])) {
+               if (tcp_too_many_orphans(sk,
+                               atomic_read(sk->sk_prot->orphan_count))) {
                        if (net_ratelimit())
                                printk(KERN_INFO "TCP: too many of orphaned "
                                       "sockets\n");

diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index 3938d5d..760165a 100644 (file)
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -80,7 +80,8 @@ static void printl(const char *fmt, ...)
 
        kfifo_put(tcpw.fifo, tbuf, len);
        wake_up(&tcpw.wait);
-}
+} __attribute__ ((format (printf, 1, 2)));
+
 
 /*
  * Hook inserted to be called before each receive packet.
@@ -95,7 +96,7 @@ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
        /* Only update if port matches */
        if ((port == 0 || ntohs(inet->dport) == port || ntohs(inet->sport) == port)
            && (full || tp->snd_cwnd != tcpw.lastcwnd)) {
-               printl("%d.%d.%d.%d:%u %d.%d.%d.%d:%u %d %#x %#x %u %u %u\n",
+               printl("%d.%d.%d.%d:%u %d.%d.%d.%d:%u %d %#x %#x %u %u %u %u\n",
                       NIPQUAD(inet->saddr), ntohs(inet->sport),
                       NIPQUAD(inet->daddr), ntohs(inet->dport),
                       skb->len, tp->snd_nxt, tp->snd_una,

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 2ca97b2..e613401 100644 (file)
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -78,9 +78,7 @@ static int tcp_out_of_resources(struct sock *sk, int do_reset)
        if (sk->sk_err_soft)
                orphans <<= 1;
 
-       if (orphans >= sysctl_tcp_max_orphans ||
-           (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
-            atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2])) {
+       if (tcp_too_many_orphans(sk, orphans)) {
                if (net_ratelimit())
                        printk(KERN_INFO "Out of socket memory\n");
 

diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index 5ceca95..fa1902d 100644 (file)
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -139,10 +139,8 @@ int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type)
        nf_reset(skb);
 
        if (decaps) {
-               if (!(skb->dev->flags&IFF_LOOPBACK)) {
-                       dst_release(skb->dst);
-                       skb->dst = NULL;
-               }
+               dst_release(skb->dst);
+               skb->dst = NULL;
                netif_rx(skb);
                return 0;
        } else {

diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index a2f2e6a..9963700 100644 (file)
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -85,6 +85,8 @@ static int xfrm4_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
        top_iph->saddr = x->props.saddr.a4;
        top_iph->daddr = x->id.daddr.a4;
 
+       skb->protocol = htons(ETH_P_IP);
+
        memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options));
        return 0;
 }

diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index b696c84..128f94c 100644 (file)
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -247,7 +247,7 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
        memcpy(tmp_base, top_iph, sizeof(tmp_base));
 
        tmp_ext = NULL;
-       extlen = skb_transport_offset(skb) + sizeof(struct ipv6hdr);
+       extlen = skb_transport_offset(skb) - sizeof(struct ipv6hdr);
        if (extlen) {
                extlen += sizeof(*tmp_ext);
                tmp_ext = kmalloc(extlen, GFP_ATOMIC);

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index ca08ee8..662a7d9 100644 (file)
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -619,14 +619,6 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 
        ins = &fn->leaf;
 
-       if (fn->fn_flags&RTN_TL_ROOT &&
-           fn->leaf == &ip6_null_entry &&
-           !(rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) ){
-               fn->leaf = rt;
-               rt->u.dst.rt6_next = NULL;
-               goto out;
-       }
-
        for (iter = fn->leaf; iter; iter=iter->u.dst.rt6_next) {
                /*
                 *      Search for duplicates
@@ -666,7 +658,6 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
         *      insert node
         */
 
-out:
        rt->u.dst.rt6_next = iter;
        *ins = rt;
        rt->rt6i_node = fn;

diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index d7ed8aa..c858537 100644 (file)
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -104,10 +104,8 @@ int xfrm6_rcv_spi(struct sk_buff *skb, __be32 spi)
        nf_reset(skb);
 
        if (decaps) {
-               if (!(skb->dev->flags&IFF_LOOPBACK)) {
-                       dst_release(skb->dst);
-                       skb->dst = NULL;
-               }
+               dst_release(skb->dst);
+               skb->dst = NULL;
                netif_rx(skb);
                return -1;
        } else {

diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index a6c0cdf..9fc95bc 100644 (file)
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -80,6 +80,7 @@ static int xfrm6_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
        top_iph->hop_limit = dst_metric(dst->child, RTAX_HOPLIMIT);
        ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr);
        ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr);
+       skb->protocol = htons(ETH_P_IPV6);
        return 0;
 }
 

diff --git a/net/mac80211/ieee80211.c b/net/mac80211/ieee80211.c
index 6e36df6..4e84f24 100644 (file)
--- a/net/mac80211/ieee80211.c
+++ b/net/mac80211/ieee80211.c
@@ -2474,6 +2474,8 @@ static int ieee80211_open(struct net_device *dev)
        if (sdata->type == IEEE80211_IF_TYPE_STA &&
            !local->user_space_mlme)
                netif_carrier_off(dev);
+       else
+               netif_carrier_on(dev);
 
        netif_start_queue(dev);
        return 0;
@@ -3278,8 +3280,10 @@ ieee80211_rx_h_defragment(struct ieee80211_txrx_data *rx)
                        return TXRX_DROP;
                }
        }
-       while ((skb = __skb_dequeue(&entry->skb_list)))
+       while ((skb = __skb_dequeue(&entry->skb_list))) {
                memcpy(skb_put(rx->skb, skb->len), skb->data, skb->len);
+               dev_kfree_skb(skb);
+       }
 
        /* Complete frame has been reassembled - process it now */
        rx->fragmented = 1;

diff --git a/net/mac80211/ieee80211_sta.c b/net/mac80211/ieee80211_sta.c
index 3e07e9d..9f30ae4 100644 (file)
--- a/net/mac80211/ieee80211_sta.c
+++ b/net/mac80211/ieee80211_sta.c
@@ -1155,6 +1155,8 @@ static void ieee80211_rx_mgmt_assoc_resp(struct net_device *dev,
        if (status_code != WLAN_STATUS_SUCCESS) {
                printk(KERN_DEBUG "%s: AP denied association (code=%d)\n",
                       dev->name, status_code);
+               if (status_code == WLAN_STATUS_REASSOC_NO_ASSOC)
+                       ifsta->prev_bssid_set = 0;
                return;
        }
 
@@ -2995,7 +2997,7 @@ struct sta_info * ieee80211_ibss_add_sta(struct net_device *dev,
 {
        struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr);
        struct sta_info *sta;
-       struct ieee80211_sub_if_data *sdata = NULL;
+       struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 
        /* TODO: Could consider removing the least recently used entry and
         * allow new one to be added. */

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 02e401c..f8b8301 100644 (file)
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -83,22 +83,6 @@
 #include <net/inet_common.h>
 #endif
 
-#define CONFIG_SOCK_PACKET     1
-
-/*
-   Proposed replacement for SIOC{ADD,DEL}MULTI and
-   IFF_PROMISC, IFF_ALLMULTI flags.
-
-   It is more expensive, but I believe,
-   it is really correct solution: reentereble, safe and fault tolerant.
-
-   IFF_PROMISC/IFF_ALLMULTI/SIOC{ADD/DEL}MULTI are faked by keeping
-   reference count and global flag, so that real status is
-   (gflag|(count != 0)), so that we can use obsolete faulty interface
-   not harming clever users.
- */
-#define CONFIG_PACKET_MULTICAST        1
-
 /*
    Assumptions:
    - if device has no dev->hard_header routine, it adds and removes ll header
@@ -159,7 +143,6 @@ static atomic_t packet_socks_nr;
 
 /* Private packet socket structures. */
 
-#ifdef CONFIG_PACKET_MULTICAST
 struct packet_mclist
 {
        struct packet_mclist    *next;
@@ -179,7 +162,7 @@ struct packet_mreq_max
        unsigned short  mr_alen;
        unsigned char   mr_address[MAX_ADDR_LEN];
 };
-#endif
+
 #ifdef CONFIG_PACKET_MMAP
 static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing);
 #endif
@@ -205,9 +188,7 @@ struct packet_sock {
                                origdev:1;
        int                     ifindex;        /* bound device         */
        __be16                  num;
-#ifdef CONFIG_PACKET_MULTICAST
        struct packet_mclist    *mclist;
-#endif
 #ifdef CONFIG_PACKET_MMAP
        atomic_t                mapped;
        unsigned int            pg_vec_order;
@@ -263,7 +244,6 @@ static void packet_sock_destruct(struct sock *sk)
 
 static const struct proto_ops packet_ops;
 
-#ifdef CONFIG_SOCK_PACKET
 static const struct proto_ops packet_ops_spkt;
 
 static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev,  struct packet_type *pt, struct net_device *orig_dev)
@@ -435,7 +415,6 @@ out_unlock:
                dev_put(dev);
        return err;
 }
-#endif
 
 static inline unsigned int run_filter(struct sk_buff *skb, struct sock *sk,
                                      unsigned int res)
@@ -851,9 +830,7 @@ static int packet_release(struct socket *sock)
                __sock_put(sk);
        }
 
-#ifdef CONFIG_PACKET_MULTICAST
        packet_flush_mclist(sk);
-#endif
 
 #ifdef CONFIG_PACKET_MMAP
        if (po->pg_vec) {
@@ -936,8 +913,6 @@ out_unlock:
  *     Bind a packet socket to a device
  */
 
-#ifdef CONFIG_SOCK_PACKET
-
 static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
        struct sock *sk=sock->sk;
@@ -960,7 +935,6 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int add
        }
        return err;
 }
-#endif
 
 static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
@@ -1012,11 +986,8 @@ static int packet_create(struct socket *sock, int protocol)
 
        if (!capable(CAP_NET_RAW))
                return -EPERM;
-       if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW
-#ifdef CONFIG_SOCK_PACKET
-           && sock->type != SOCK_PACKET
-#endif
-           )
+       if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW &&
+           sock->type != SOCK_PACKET)
                return -ESOCKTNOSUPPORT;
 
        sock->state = SS_UNCONNECTED;
@@ -1027,10 +998,9 @@ static int packet_create(struct socket *sock, int protocol)
                goto out;
 
        sock->ops = &packet_ops;
-#ifdef CONFIG_SOCK_PACKET
        if (sock->type == SOCK_PACKET)
                sock->ops = &packet_ops_spkt;
-#endif
+
        sock_init_data(sock, sk);
 
        po = pkt_sk(sk);
@@ -1046,10 +1016,10 @@ static int packet_create(struct socket *sock, int protocol)
 
        spin_lock_init(&po->bind_lock);
        po->prot_hook.func = packet_rcv;
-#ifdef CONFIG_SOCK_PACKET
+
        if (sock->type == SOCK_PACKET)
                po->prot_hook.func = packet_rcv_spkt;
-#endif
+
        po->prot_hook.af_packet_priv = sk;
 
        if (proto) {
@@ -1169,7 +1139,6 @@ out:
        return err;
 }
 
-#ifdef CONFIG_SOCK_PACKET
 static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr,
                               int *uaddr_len, int peer)
 {
@@ -1190,7 +1159,6 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr,
 
        return 0;
 }
-#endif
 
 static int packet_getname(struct socket *sock, struct sockaddr *uaddr,
                          int *uaddr_len, int peer)
@@ -1221,7 +1189,6 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr,
        return 0;
 }
 
-#ifdef CONFIG_PACKET_MULTICAST
 static void packet_dev_mc(struct net_device *dev, struct packet_mclist *i, int what)
 {
        switch (i->type) {
@@ -1349,7 +1316,6 @@ static void packet_flush_mclist(struct sock *sk)
        }
        rtnl_unlock();
 }
-#endif
 
 static int
 packet_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen)
@@ -1362,7 +1328,6 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
                return -ENOPROTOOPT;
 
        switch(optname) {
-#ifdef CONFIG_PACKET_MULTICAST
        case PACKET_ADD_MEMBERSHIP:
        case PACKET_DROP_MEMBERSHIP:
        {
@@ -1383,7 +1348,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
                        ret = packet_mc_drop(sk, &mreq);
                return ret;
        }
-#endif
+
 #ifdef CONFIG_PACKET_MMAP
        case PACKET_RX_RING:
        {
@@ -1506,11 +1471,10 @@ static int packet_notifier(struct notifier_block *this, unsigned long msg, void
 
                switch (msg) {
                case NETDEV_UNREGISTER:
-#ifdef CONFIG_PACKET_MULTICAST
                        if (po->mclist)
                                packet_dev_mclist(dev, po->mclist, -1);
-                       // fallthrough
-#endif
+                       /* fallthrough */
+
                case NETDEV_DOWN:
                        if (dev->ifindex == po->ifindex) {
                                spin_lock(&po->bind_lock);
@@ -1856,7 +1820,6 @@ out:
 #endif
 
 
-#ifdef CONFIG_SOCK_PACKET
 static const struct proto_ops packet_ops_spkt = {
        .family =       PF_PACKET,
        .owner =        THIS_MODULE,
@@ -1877,7 +1840,6 @@ static const struct proto_ops packet_ops_spkt = {
        .mmap =         sock_no_mmap,
        .sendpage =     sock_no_sendpage,
 };
-#endif
 
 static const struct proto_ops packet_ops = {
        .family =       PF_PACKET,

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index b8bab89..64a3751 100644 (file)
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -26,10 +26,11 @@
 #include <net/xfrm.h>
 #include <net/ip.h>
 #include <linux/audit.h>
+#include <linux/cache.h>
 
 #include "xfrm_hash.h"
 
-int sysctl_xfrm_larval_drop;
+int sysctl_xfrm_larval_drop __read_mostly;
 
 DEFINE_MUTEX(xfrm_cfg_mutex);
 EXPORT_SYMBOL(xfrm_cfg_mutex);

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 9955ff4..372f06e 100644 (file)
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -21,18 +21,21 @@
 #include <linux/cache.h>
 #include <asm/uaccess.h>
 #include <linux/audit.h>
+#include <linux/cache.h>
 
 #include "xfrm_hash.h"
 
 struct sock *xfrm_nl;
 EXPORT_SYMBOL(xfrm_nl);
 
-u32 sysctl_xfrm_aevent_etime = XFRM_AE_ETIME;
+u32 sysctl_xfrm_aevent_etime __read_mostly = XFRM_AE_ETIME;
 EXPORT_SYMBOL(sysctl_xfrm_aevent_etime);
 
-u32 sysctl_xfrm_aevent_rseqth = XFRM_AE_SEQT_SIZE;
+u32 sysctl_xfrm_aevent_rseqth __read_mostly = XFRM_AE_SEQT_SIZE;
 EXPORT_SYMBOL(sysctl_xfrm_aevent_rseqth);
 
+u32 sysctl_xfrm_acq_expires __read_mostly = 30;
+
 /* Each xfrm_state may be linked to two tables:
 
    1. Hash table by (spi,daddr,ah/esp) to find SA by SPI. (input,ctl)
@@ -622,8 +625,8 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
                                h = xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, family);
                                hlist_add_head(&x->byspi, xfrm_state_byspi+h);
                        }
-                       x->lft.hard_add_expires_seconds = XFRM_ACQ_EXPIRES;
-                       x->timer.expires = jiffies + XFRM_ACQ_EXPIRES*HZ;
+                       x->lft.hard_add_expires_seconds = sysctl_xfrm_acq_expires;
+                       x->timer.expires = jiffies + sysctl_xfrm_acq_expires*HZ;
                        add_timer(&x->timer);
                        xfrm_state_num++;
                        xfrm_hash_grow_check(x->bydst.next != NULL);
@@ -772,9 +775,9 @@ static struct xfrm_state *__find_acq_core(unsigned short family, u8 mode, u32 re
                x->props.family = family;
                x->props.mode = mode;
                x->props.reqid = reqid;
-               x->lft.hard_add_expires_seconds = XFRM_ACQ_EXPIRES;
+               x->lft.hard_add_expires_seconds = sysctl_xfrm_acq_expires;
                xfrm_state_hold(x);
-               x->timer.expires = jiffies + XFRM_ACQ_EXPIRES*HZ;
+               x->timer.expires = jiffies + sysctl_xfrm_acq_expires*HZ;
                add_timer(&x->timer);
                hlist_add_head(&x->bydst, xfrm_state_bydst+h);
                h = xfrm_src_hash(daddr, saddr, family);